Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

author: Ingo Molnar <mingo@elte.hu> 2008-10-28 11:26:12 -0400
committer: Ingo Molnar <mingo@elte.hu> 2008-10-28 11:26:12 -0400
commit: 7a9787e1eba95a166265e6a260cf30af04ef0a99 (patch)
tree: e730a4565e0318140d2fbd2f0415d18a339d7336 /Documentation
parent: 41b9eb264c8407655db57b60b4457fe1b2ec9977 (diff)
parent: 0173a3265b228da319ceb9c1ec6a5682fd1b2d92 (diff)
303 files changed, 15554 insertions, 5624 deletions
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 1977fab38656..7286ad090db7 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -21,6 +21,9 @@ Changes
        - list of changes that break older software packages.
 CodingStyle
        - how the boss likes the C code in the kernel to look.
+development-process/
+        - An extended tutorial on how to work with the kernel development
+          process.
 DMA-API.txt
        - DMA API, pci_ API & extensions for non-consistent memory machines.
 DMA-ISA-LPC.txt
@@ -89,8 +92,6 @@ cciss.txt
        - info, major/minor #'s for Compaq's SMART Array Controllers.
 cdrom/
        - directory with information on the CD-ROM drivers that Linux has.
-cli-sti-removal.txt
-        - cli()/sti() removal guide.
 computone.txt
        - info on Computone Intelliport II/Plus Multiport Serial Driver.
 connector/
@@ -161,8 +162,6 @@ hayes-esp.txt
        - info on using the Hayes ESP serial driver.
 highuid.txt
        - notes on the change from 16 bit to 32 bit user/group IDs.
-hpet.txt
-        - High Precision Event Timer Driver for Linux.
 timers/
        - info on the timer related topics
 hw_random.txt
@@ -253,8 +252,6 @@ mono.txt
        - how to execute Mono-based .NET binaries with the help of BINFMT_MISC.
 moxa-smartio
        - file with info on installing/using Moxa multiport serial driver.
-mtrr.txt
-        - how to use PPro Memory Type Range Registers to increase performance.
 mutex-design.txt
        - info on the generic mutex subsystem.
 namespaces/
@@ -361,8 +358,6 @@ telephony/
        - directory with info on telephony (e.g. voice over IP) support.
 time_interpolators.txt
        - info on time interpolators.
-tipar.txt
-        - information about Parallel link cable for Texas Instruments handhelds.
 tty.txt
        - guide to the locking policies of the tty layer.
 uml/
diff --git a/Documentation/ABI/stable/sysfs-driver-usb-usbtmc b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
new file mode 100644
index 000000000000..9a75fb22187d
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
@@ -0,0 +1,62 @@
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/interface_capabilities
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/device_capabilities
+Date:           August 2008
+Contact:        Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+                These files show the various USB TMC capabilities as described
+                by the device itself.  The full description of the bitfields
+                can be found in the USB TMC documents from the USB-IF entitled
+                "Universal Serial Bus Test and Measurement Class Specification
+                (USBTMC) Revision 1.0" section 4.2.1.8.
+                The files are read only.
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/usb488_interface_capabilities
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/usb488_device_capabilities
+Date:           August 2008
+Contact:        Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+                These files show the various USB TMC capabilities as described
+                by the device itself.  The full description of the bitfields
+                can be found in the USB TMC documents from the USB-IF entitled
+                "Universal Serial Bus Test and Measurement Class, Subclass
+                USB488 Specification (USBTMC-USB488) Revision 1.0" section
+                4.2.2.
+                The files are read only.
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/TermChar
+Date:           August 2008
+Contact:        Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+                This file is the TermChar value to be sent to the USB TMC
+                device as described by the document, "Universal Serial Bus Test
+                and Measurement Class Specification
+                (USBTMC) Revision 1.0" as published by the USB-IF.
+                Note that the TermCharEnabled file determines if this value is
+                sent to the device or not.
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/TermCharEnabled
+Date:           August 2008
+Contact:        Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+                This file determines if the TermChar is to be sent to the
+                device on every transaction or not.  For more details about
+                this, please see the document, "Universal Serial Bus Test and
+                Measurement Class Specification (USBTMC) Revision 1.0" as
+                published by the USB-IF.
+What:           /sys/bus/usb/drivers/usbtmc/devices/*/auto_abort
+Date:           August 2008
+Contact:        Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+                This file determines if the the transaction of the USB TMC
+                device is to be automatically aborted if there is any error.
+                For more details about this, please see the document,
+                "Universal Serial Bus Test and Measurement Class Specification
+                (USBTMC) Revision 1.0" as published by the USB-IF.
diff --git a/Documentation/ABI/testing/sysfs-bus-umc b/Documentation/ABI/testing/sysfs-bus-umc
new file mode 100644
index 000000000000..948fec412446
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-umc
@@ -0,0 +1,28 @@
+What:           /sys/bus/umc/
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The Wireless Host Controller Interface (WHCI)
+                specification describes a PCI-based device with
+                multiple capabilities; the UWB Multi-interface
+                Controller (UMC).
+                The umc bus presents each of the individual
+                capabilties as a device.
+What:           /sys/bus/umc/devices/.../capability_id
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The ID of this capability, with 0 being the radio
+                controller capability.
+What:           /sys/bus/umc/devices/.../version
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The specification version this capability's hardware
+                interface complies with.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 11a3c1682cec..7772928ee48f 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -85,3 +85,62 @@ Description:
 Users:
                PowerTOP <power@bughost.org>
                http://www.lesswatts.org/projects/powertop/
+What:           /sys/bus/usb/device/<busnum>-<devnum>...:<config num>-<interface num>/supports_autosuspend
+Date:           January 2008
+KernelVersion:  2.6.27
+Contact:        Sarah Sharp <sarah.a.sharp@intel.com>
+Description:
+                When read, this file returns 1 if the interface driver
+                for this interface supports autosuspend.  It also
+                returns 1 if no driver has claimed this interface, as an
+                unclaimed interface will not stop the device from being
+                autosuspended if all other interface drivers are idle.
+                The file returns 0 if autosuspend support has not been
+                added to the driver.
+Users:
+                USB PM tool
+                git://git.moblin.org/users/sarah/usb-pm-tool/
+What:           /sys/bus/usb/device/.../authorized
+Date:           July 2008
+KernelVersion:  2.6.26
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                Authorized devices are available for use by device
+                drivers, non-authorized one are not.  By default, wired
+                USB devices are authorized.
+                Certified Wireless USB devices are not authorized
+                initially and should be (by writing 1) after the
+                device has been authenticated.
+What:           /sys/bus/usb/device/.../wusb_cdid
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                For Certified Wireless USB devices only.
+                A devices's CDID, as 16 space-separated hex octets.
+What:           /sys/bus/usb/device/.../wusb_ck
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                For Certified Wireless USB devices only.
+                Write the device's connection key (CK) to start the
+                authentication of the device.  The CK is 16
+                space-separated hex octets.
+What:           /sys/bus/usb/device/.../wusb_disconnect
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                For Certified Wireless USB devices only.
+                Write a 1 to force the device to disconnect
+                (equivalent to unplugging a wired USB device).
diff --git a/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
new file mode 100644
index 000000000000..cb830df8777c
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-usb-devices-usbsevseg
@@ -0,0 +1,43 @@
+Where:          /sys/bus/usb/.../powered
+Date:           August 2008
+Kernel Version: 2.6.26
+Contact:        Harrison Metzger <harrisonmetz@gmail.com>
+Description:    Controls whether the device's display will powered.
+                A value of 0 is off and a non-zero value is on.
+Where:          /sys/bus/usb/.../mode_msb
+Where:          /sys/bus/usb/.../mode_lsb
+Date:           August 2008
+Kernel Version: 2.6.26
+Contact:        Harrison Metzger <harrisonmetz@gmail.com>
+Description:    Controls the devices display mode.
+                For a 6 character display the values are
+                        MSB 0x06; LSB 0x3F, and
+                for an 8 character display the values are
+                        MSB 0x08; LSB 0xFF.
+Where:          /sys/bus/usb/.../textmode
+Date:           August 2008
+Kernel Version: 2.6.26
+Contact:        Harrison Metzger <harrisonmetz@gmail.com>
+Description:    Controls the way the device interprets its text buffer.
+                raw:    each character controls its segment manually
+                hex:    each character is between 0-15
+                ascii:  each character is between '0'-'9' and 'A'-'F'.
+Where:          /sys/bus/usb/.../text
+Date:           August 2008
+Kernel Version: 2.6.26
+Contact:        Harrison Metzger <harrisonmetz@gmail.com>
+Description:    The text (or data) for the device to display
+Where:          /sys/bus/usb/.../decimals
+Date:           August 2008
+Kernel Version: 2.6.26
+Contact:        Harrison Metzger <harrisonmetz@gmail.com>
+Description:    Controls the decimal places on the device.
+                To set the nth decimal place, give this field
+                the value of 10 ** n. Assume this field has
+                the value k and has 1 or more decimal places set,
+                to set the mth place (where m is not already set),
+                change this fields value to k + 10 ** m.
+\ No newline at end of file
diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator
new file mode 100644
index 000000000000..3731f6f29bcb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-regulator
@@ -0,0 +1,328 @@
+What:           /sys/class/regulator/.../state
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                state. This holds the regulator output state.
+                This will be one of the following strings:
+                'enabled'
+                'disabled'
+                'unknown'
+                'enabled' means the regulator output is ON and is supplying
+                power to the system.
+                'disabled' means the regulator output is OFF and is not
+                supplying power to the system..
+                'unknown' means software cannot determine the state.
+                NOTE: this field can be used in conjunction with microvolts
+                and microamps to determine regulator output levels.
+What:           /sys/class/regulator/.../type
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                type. This holds the regulator type.
+                This will be one of the following strings:
+                'voltage'
+                'current'
+                'unknown'
+                'voltage' means the regulator output voltage can be controlled
+                by software.
+                'current' means the regulator output current limit can be
+                controlled by software.
+                'unknown' means software cannot control either voltage or
+                current limit.
+What:           /sys/class/regulator/.../microvolts
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                microvolts. This holds the regulator output voltage setting
+                measured in microvolts (i.e. E-6 Volts).
+                NOTE: This value should not be used to determine the regulator
+                output voltage level as this value is the same regardless of
+                whether the regulator is enabled or disabled.
+What:           /sys/class/regulator/.../microamps
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                microamps. This holds the regulator output current limit
+                setting measured in microamps (i.e. E-6 Amps).
+                NOTE: This value should not be used to determine the regulator
+                output current level as this value is the same regardless of
+                whether the regulator is enabled or disabled.
+What:           /sys/class/regulator/.../opmode
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                opmode. This holds the regulator operating mode setting.
+                The opmode value can be one of the following strings:
+                'fast'
+                'normal'
+                'idle'
+                'standby'
+                'unknown'
+                The modes are described in include/linux/regulator/regulator.h
+                NOTE: This value should not be used to determine the regulator
+                output operating mode as this value is the same regardless of
+                whether the regulator is enabled or disabled.
+What:           /sys/class/regulator/.../min_microvolts
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                min_microvolts. This holds the minimum safe working regulator
+                output voltage setting for this domain measured in microvolts.
+                NOTE: this will return the string 'constraint not defined' if
+                the power domain has no min microvolts constraint defined by
+                platform code.
+What:           /sys/class/regulator/.../max_microvolts
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                max_microvolts. This holds the maximum safe working regulator
+                output voltage setting for this domain measured in microvolts.
+                NOTE: this will return the string 'constraint not defined' if
+                the power domain has no max microvolts constraint defined by
+                platform code.
+What:           /sys/class/regulator/.../min_microamps
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                min_microamps. This holds the minimum safe working regulator
+                output current limit setting for this domain measured in
+                microamps.
+                NOTE: this will return the string 'constraint not defined' if
+                the power domain has no min microamps constraint defined by
+                platform code.
+What:           /sys/class/regulator/.../max_microamps
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                max_microamps. This holds the maximum safe working regulator
+                output current limit setting for this domain measured in
+                microamps.
+                NOTE: this will return the string 'constraint not defined' if
+                the power domain has no max microamps constraint defined by
+                platform code.
+What:           /sys/class/regulator/.../name
+Date:           October 2008
+KernelVersion:  2.6.28
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                name. This holds a string identifying the regulator for
+                display purposes.
+                NOTE: this will be empty if no suitable name is provided
+                by platform or regulator drivers.
+What:           /sys/class/regulator/.../num_users
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                num_users. This holds the number of consumer devices that
+                have called regulator_enable() on this regulator.
+What:           /sys/class/regulator/.../requested_microamps
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                requested_microamps. This holds the total requested load
+                current in microamps for this regulator from all its consumer
+                devices.
+What:           /sys/class/regulator/.../parent
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Some regulator directories will contain a link called parent.
+                This points to the parent or supply regulator if one exists.
+What:           /sys/class/regulator/.../suspend_mem_microvolts
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_mem_microvolts. This holds the regulator output
+                voltage setting for this domain measured in microvolts when
+                the system is suspended to memory.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to memory voltage defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_disk_microvolts
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_disk_microvolts. This holds the regulator output
+                voltage setting for this domain measured in microvolts when
+                the system is suspended to disk.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to disk voltage defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_standby_microvolts
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_standby_microvolts. This holds the regulator output
+                voltage setting for this domain measured in microvolts when
+                the system is suspended to standby.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to standby voltage defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_mem_mode
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_mem_mode. This holds the regulator operating mode
+                setting for this domain when the system is suspended to
+                memory.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to memory mode defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_disk_mode
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_disk_mode. This holds the regulator operating mode
+                setting for this domain when the system is suspended to disk.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to disk mode defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_standby_mode
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_standby_mode. This holds the regulator operating mode
+                setting for this domain when the system is suspended to
+                standby.
+                NOTE: this will return the string 'not defined' if
+                the power domain has no suspend to standby mode defined by
+                platform code.
+What:           /sys/class/regulator/.../suspend_mem_state
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_mem_state. This holds the regulator operating state
+                when suspended to memory.
+                This will be one of the following strings:
+                'enabled'
+                'disabled'
+                'not defined'
+What:           /sys/class/regulator/.../suspend_disk_state
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_disk_state. This holds the regulator operating state
+                when suspended to disk.
+                This will be one of the following strings:
+                'enabled'
+                'disabled'
+                'not defined'
+What:           /sys/class/regulator/.../suspend_standby_state
+Date:           May 2008
+KernelVersion:  2.6.26
+Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
+Description:
+                Each regulator directory will contain a field called
+                suspend_standby_state. This holds the regulator operating
+                state when suspended to standby.
+                This will be one of the following strings:
+                'enabled'
+                'disabled'
+                'not defined'
diff --git a/Documentation/ABI/testing/sysfs-class-usb_host b/Documentation/ABI/testing/sysfs-class-usb_host
new file mode 100644
index 000000000000..46b66ad1f1b4
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-usb_host
@@ -0,0 +1,25 @@
+What:           /sys/class/usb_host/usb_hostN/wusb_chid
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                Write the CHID (16 space-separated hex octets) for this host controller.
+                This starts the host controller, allowing it to accept connection from
+                WUSB devices.
+                Set an all zero CHID to stop the host controller.
+What:           /sys/class/usb_host/usb_hostN/wusb_trust_timeout
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                Devices that haven't sent a WUSB packet to the host
+                within 'wusb_trust_timeout' ms are considered to have
+                disconnected and are removed.  The default value of
+                4000 ms is the value required by the WUSB
+                specification.
+                Since this relates to security (specifically, the
+                lifetime of PTKs and GTKs) it should not be changed
+                from the default.
diff --git a/Documentation/ABI/testing/sysfs-class-uwb_rc b/Documentation/ABI/testing/sysfs-class-uwb_rc
new file mode 100644
index 000000000000..a0d18dbeb7a9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-uwb_rc
@@ -0,0 +1,144 @@
+What:           /sys/class/uwb_rc
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                Interfaces for WiMedia Ultra Wideband Common Radio
+                Platform (UWB) radio controllers.
+                Familiarity with the ECMA-368 'High Rate Ultra
+                Wideband MAC and PHY Specification' is assumed.
+What:           /sys/class/uwb_rc/beacon_timeout_ms
+Date:           July 2008
+KernelVersion:  2.6.27
+Description:
+                If no beacons are received from a device for at least
+                this time, the device will be considered to have gone
+                and it will be removed.  The default is 3 superframes
+                (~197 ms) as required by the specification.
+What:           /sys/class/uwb_rc/uwbN/
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                An individual UWB radio controller.
+What:           /sys/class/uwb_rc/uwbN/beacon
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                Write:
+                <channel> [<bpst offset>]
+                to start beaconing on a specific channel, or stop
+                beaconing if <channel> is -1.  Valid channels depends
+                on the radio controller's supported band groups.
+                <bpst offset> may be used to try and join a specific
+                beacon group if more than one was found during a scan.
+What:           /sys/class/uwb_rc/uwbN/scan
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                Write:
+                <channel> <type> [<bpst offset>]
+                to start (or stop) scanning on a channel.  <type> is one of:
+                    0 - scan
+                    1 - scan outside BP
+                    2 - scan while inactive
+                    3 - scanning disabled
+                    4 - scan (with start time of <bpst offset>)
+What:           /sys/class/uwb_rc/uwbN/mac_address
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                The EUI-48, in colon-separated hex octets, for this
+                radio controller.  A write will change the radio
+                controller's EUI-48 but only do so while the device is
+                not beaconing or scanning.
+What:           /sys/class/uwb_rc/uwbN/wusbhc
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                A symlink to the device (if any) of the WUSB Host
+                Controller PAL using this radio controller.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                A neighbour UWB device that has either been detected
+                as part of a scan or is a member of the radio
+                controllers beacon group.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/BPST
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                The time (using the radio controllers internal 1 ms
+                interval superframe timer) of the last beacon from
+                this device was received.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/DevAddr
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                The current DevAddr of this device in colon separated
+                hex octets.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/EUI_48
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                The EUI-48 of this device in colon separated hex
+                octets.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/BPST
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/IEs
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                The latest IEs included in this device's beacon, in
+                space separated hex octets with one IE per line.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/LQE
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                Link Quality Estimate - the Signal to Noise Ratio
+                (SNR) of all packets received from this device in dB.
+                This gives an estimate on a suitable PHY rate. Refer
+                to [ECMA-368] section 13.3 for more details.
+What:           /sys/class/uwb_rc/uwbN/<EUI-48>/RSSI
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        linux-usb@vger.kernel.org
+Description:
+                Received Signal Strength Indication - the strength of
+                the received signal in dB.  LQE is a more useful
+                measure of the radio link quality.
diff --git a/Documentation/ABI/testing/sysfs-dev b/Documentation/ABI/testing/sysfs-dev
new file mode 100644
index 000000000000..a9f2b8b0530f
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-dev
@@ -0,0 +1,20 @@
+What:           /sys/dev
+Date:           April 2008
+KernelVersion:  2.6.26
+Contact:        Dan Williams <dan.j.williams@intel.com>
+Description:    The /sys/dev tree provides a method to look up the sysfs
+                path for a device using the information returned from
+                stat(2).  There are two directories, 'block' and 'char',
+                beneath /sys/dev containing symbolic links with names of
+                the form "<major>:<minor>".  These links point to the
+                corresponding sysfs path for the given device.
+                Example:
+                $ readlink /sys/dev/block/8:32
+                ../../block/sdc
+                Entries in /sys/dev/char and /sys/dev/block will be
+                dynamically created and destroyed as devices enter and
+                leave the system.
+Users:          mdadm <linux-raid@vger.kernel.org>
diff --git a/Documentation/ABI/testing/sysfs-devices-memory b/Documentation/ABI/testing/sysfs-devices-memory
new file mode 100644
index 000000000000..7a16fe1e2270
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-memory
@@ -0,0 +1,24 @@
+What:           /sys/devices/system/memory
+Date:           June 2008
+Contact:        Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+                The /sys/devices/system/memory contains a snapshot of the
+                internal state of the kernel memory blocks. Files could be
+                added or removed dynamically to represent hot-add/remove
+                operations.
+Users:          hotplug memory add/remove tools
+                https://w3.opensource.ibm.com/projects/powerpc-utils/
+What:           /sys/devices/system/memory/memoryX/removable
+Date:           June 2008
+Contact:        Badari Pulavarty <pbadari@us.ibm.com>
+Description:
+                The file /sys/devices/system/memory/memoryX/removable
+                indicates whether this memory block is removable or not.
+                This is useful for a user-level agent to determine
+                identify removable sections of the memory before attempting
+                potentially expensive hot-remove memory operation
+Users:          hotplug memory remove tools
+                https://w3.opensource.ibm.com/projects/powerpc-utils/
diff --git a/Documentation/ABI/testing/sysfs-firmware-sgi_uv b/Documentation/ABI/testing/sysfs-firmware-sgi_uv
new file mode 100644
index 000000000000..4573fd4b7876
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-sgi_uv
@@ -0,0 +1,27 @@
+What:           /sys/firmware/sgi_uv/
+Date:           August 2008
+Contact:        Russ Anderson <rja@sgi.com>
+Description:
+                The /sys/firmware/sgi_uv directory contains information
+                about the SGI UV platform.
+                Under that directory are a number of files:
+                        partition_id
+                        coherence_id
+                The partition_id entry contains the partition id.
+                SGI UV systems can be partitioned into multiple physical
+                machines, which each partition running a unique copy
+                of the operating system.  Each partition will have a unique
+                partition id.  To display the partition id, use the command:
+                        cat /sys/firmware/sgi_uv/partition_id
+                The coherence_id entry contains the coherence id.
+                A partitioned SGI UV system can have one or more coherence
+                domain.  The coherence id indicates which coherence domain
+                this partition is in.  To display the coherence id, use the
+                command:
+                        cat /sys/firmware/sgi_uv/coherence_id
diff --git a/Documentation/ABI/testing/sysfs-gpio b/Documentation/ABI/testing/sysfs-gpio
new file mode 100644
index 000000000000..8aab8092ad35
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-gpio
@@ -0,0 +1,26 @@
+What:           /sys/class/gpio/
+Date:           July 2008
+KernelVersion:  2.6.27
+Contact:        David Brownell <dbrownell@users.sourceforge.net>
+Description:
+  As a Kconfig option, individual GPIO signals may be accessed from
+  userspace.  GPIOs are only made available to userspace by an explicit
+  "export" operation.  If a given GPIO is not claimed for use by
+  kernel code, it may be exported by userspace (and unexported later).
+  Kernel code may export it for complete or partial access.
+  GPIOs are identified as they are inside the kernel, using integers in
+  the range 0..INT_MAX.  See Documentation/gpio.txt for more information.
+    /sys/class/gpio
+        /export ... asks the kernel to export a GPIO to userspace
+        /unexport ... to return a GPIO to the kernel
+        /gpioN ... for each exported GPIO #N
+            /value ... always readable, writes fail for input GPIOs
+            /direction ... r/w as: in, out (default low); write: high, low
+        /gpiochipN ... for each gpiochip; #N is its first GPIO
+            /base ... (r/o) same as N
+            /label ... (r/o) descriptive, not necessarily unique
+            /ngpio ... (r/o) number of GPIOs; numbered N to N + (ngpio - 1)
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm b/Documentation/ABI/testing/sysfs-kernel-mm
new file mode 100644
index 000000000000..190d523ac159
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm
@@ -0,0 +1,6 @@
+What:           /sys/kernel/mm
+Date:           July 2008
+Contact:        Nishanth Aravamudan <nacc@us.ibm.com>, VM maintainers
+Description:
+                /sys/kernel/mm/ should contain any and all VM
+                related information in /sys/kernel/.
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-hugepages b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
new file mode 100644
index 000000000000..e21c00571cf4
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -0,0 +1,15 @@
+What:           /sys/kernel/mm/hugepages/
+Date:           June 2008
+Contact:        Nishanth Aravamudan <nacc@us.ibm.com>, hugetlb maintainers
+Description:
+                /sys/kernel/mm/hugepages/ contains a number of subdirectories
+                of the form hugepages-<size>kB, where <size> is the page size
+                of the hugepages supported by the kernel/CPU combination.
+                Under these directories are a number of files:
+                        nr_hugepages
+                        nr_overcommit_hugepages
+                        free_hugepages
+                        surplus_hugepages
+                        resv_hugepages
+                See Documentation/vm/hugetlbpage.txt for details.
diff --git a/Documentation/ABI/testing/sysfs-profiling b/Documentation/ABI/testing/sysfs-profiling
new file mode 100644
index 000000000000..b02d8b8c173a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-profiling
@@ -0,0 +1,13 @@
+What:           /sys/kernel/profile
+Date:           September 2008
+Contact:        Dave Hansen <dave@linux.vnet.ibm.com>
+Description:
+                /sys/kernel/profile is the runtime equivalent
+                of the boot-time profile= option.
+                You can get the same effect running:
+                        echo 2 > /sys/kernel/profile
+                as you would by issuing profile=2 on the boot
+                command line.
diff --git a/Documentation/ABI/testing/sysfs-wusb_cbaf b/Documentation/ABI/testing/sysfs-wusb_cbaf
new file mode 100644
index 000000000000..a99c5f86a37a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-wusb_cbaf
@@ -0,0 +1,100 @@
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_*
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                Various files for managing Cable Based Association of
+                (wireless) USB devices.
+                The sequence of operations should be:
+                1. Device is plugged in.
+                2. The connection manager (CM) sees a device with CBA capability.
+                   (the wusb_chid etc. files in /sys/devices/blah/OURDEVICE).
+                3. The CM writes the host name, supported band groups,
+                   and the CHID (host ID) into the wusb_host_name,
+                   wusb_host_band_groups and wusb_chid files. These
+                   get sent to the device and the CDID (if any) for
+                   this host is requested.
+                4. The CM can verify that the device's supported band
+                   groups (wusb_device_band_groups) are compatible
+                   with the host.
+                5. The CM reads the wusb_cdid file.
+                6. The CM looks it up its database.
+                   - If it has a matching CHID,CDID entry, the device
+                     has been authorized before and nothing further
+                     needs to be done.
+                   - If the CDID is zero (or the CM doesn't find a
+                     matching CDID in its database), the device is
+                     assumed to be not known.  The CM may associate
+                     the host with device by: writing a randomly
+                     generated CDID to wusb_cdid and then a random CK
+                     to wusb_ck (this uploads the new CC to the
+                     device).
+                     CMD may choose to prompt the user before
+                     associating with a new device.
+                7. Device is unplugged.
+                References:
+                  [WUSB-AM] Association Models Supplement to the
+                            Certified Wireless Universal Serial Bus
+                            Specification, version 1.0.
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_chid
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The CHID of the host formatted as 16 space-separated
+                hex octets.
+                Writes fetches device's supported band groups and the
+                the CDID for any existing association with this host.
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_host_name
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                A friendly name for the host as a UTF-8 encoded string.
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_host_band_groups
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The band groups supported by the host, in the format
+                defined in [WUSB-AM].
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_device_band_groups
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The band groups supported by the device, in the format
+                defined in [WUSB-AM].
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_cdid
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                The device's CDID formatted as 16 space-separated hex
+                octets.
+What:           /sys/bus/usb/drivers/wusb_cbaf/.../wusb_ck
+Date:           August 2008
+KernelVersion:  2.6.27
+Contact:        David Vrabel <david.vrabel@csr.com>
+Description:
+                Write 16 space-separated random, hex octets to
+                associate with the device.
diff --git a/Documentation/CodingStyle b/Documentation/CodingStyle
index 6caa14615578..1875e502f872 100644
--- a/Documentation/CodingStyle
+++ b/Documentation/CodingStyle
@@ -474,25 +474,29 @@ make a good program).
 So, you can either get rid of GNU emacs, or change it to use saner
 values.  To do the latter, you can stick the following in your .emacs file:
-(defun linux-c-mode ()
+(defun c-lineup-arglist-tabs-only (ignored)
-  "C mode with adjusted defaults for use with the Linux kernel."
+  "Line up argument lists by tabs, not spaces"
-  (interactive)
+  (let* ((anchor (c-langelem-pos c-syntactic-element))
-  (c-mode)
+         (column (c-langelem-2nd-pos c-syntactic-element))
-  (c-set-style "K&R")
+         (offset (- (1+ column) anchor))
-  (setq tab-width 8)
+         (steps (floor offset c-basic-offset)))
-  (setq indent-tabs-mode t)
+    (* (max steps 1)
-  (setq c-basic-offset 8))
+       c-basic-offset)))
-This will define the M-x linux-c-mode command.  When hacking on a
+(add-hook 'c-mode-hook
-module, if you put the string -*- linux-c -*- somewhere on the first
+          (lambda ()
-two lines, this mode will be automatically invoked. Also, you may want
+            (let ((filename (buffer-file-name)))
-to add
+              ;; Enable kernel mode for the appropriate files
+              (when (and filename
-(setq auto-mode-alist (cons '("/usr/src/linux.*/.*\\.[ch]$" . linux-c-mode)
+                         (string-match "~/src/linux-trees" filename))
-                        auto-mode-alist))
+                (setq indent-tabs-mode t)
+                (c-set-style "linux")
-to your .emacs file if you want to have linux-c-mode switched on
+                (c-set-offset 'arglist-cont-nonempty
-automagically when you edit source files under /usr/src/linux.
+                              '(c-lineup-gcc-asm-reg
+                                c-lineup-arglist-tabs-only))))))
+This will make emacs go better with the kernel coding style for C
+files below ~/src/linux-trees.
 But even if you fail in getting emacs to do sane formatting, not
 everything is lost: use "indent".
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 80d150458c80..b8e86460046e 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -298,10 +298,10 @@ recommended that you never use these unless you really know what the
 cache width is.
 int
-dma_mapping_error(dma_addr_t dma_addr)
+dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 int
-pci_dma_mapping_error(dma_addr_t dma_addr)
+pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned
@@ -337,7 +337,7 @@ With scatterlists, you use the resulting mapping like this:
        int i, count = dma_map_sg(dev, sglist, nents, direction);
        struct scatterlist *sg;
-        for (i = 0, sg = sglist; i < count; i++, sg++) {
+        for_each_sg(sglist, sg, count, i) {
                hw_address[i] = sg_dma_address(sg);
                hw_len[i] = sg_dma_len(sg);
        }
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 6d772f84b477..b768cc0e402b 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -22,3 +22,12 @@ ready and available in memory.  The DMA of the "completion indication"
 could race with data DMA.  Mapping the memory used for completion
 indications with DMA_ATTR_WRITE_BARRIER would prevent the race.
+DMA_ATTR_WEAK_ORDERING
+----------------------
+DMA_ATTR_WEAK_ORDERING specifies that reads and writes to the mapping
+may be weakly ordered, that is that reads and writes may pass each other.
+Since it is optional for platforms to implement DMA_ATTR_WEAK_ORDERING,
+those that do not will simply ignore the attribute and exhibit default
+behavior.
diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt
index b463ecd0c7ce..c74fec8c2351 100644
--- a/Documentation/DMA-mapping.txt
+++ b/Documentation/DMA-mapping.txt
@@ -740,7 +740,7 @@ failure can be determined by:
        dma_addr_t dma_handle;
        dma_handle = pci_map_single(pdev, addr, size, direction);
-        if (pci_dma_mapping_error(dma_handle)) {
+        if (pci_dma_mapping_error(pdev, dma_handle)) {
                /*
                 * reduce current DMA mapping usage,
                 * delay and try again later or
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 0eb0d027eb32..fabc06466b93 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -6,13 +6,13 @@
 # To add a new book the only step required is to add the book to the
 # list of DOCBOOKS.
-DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml videobook.xml \
+DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml \
            kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
            procfs-guide.xml writing_usb_driver.xml networking.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
+            mac80211.xml debugobjects.xml sh.xml
 ###
 # The build process is as follows (targets):
@@ -102,6 +102,13 @@ C-procfs-example = procfs_example.xml
 C-procfs-example2 = $(addprefix $(obj)/,$(C-procfs-example))
 $(obj)/procfs-guide.xml: $(C-procfs-example2)
+# List of programs to build
+##oops, this is a kernel module::hostprogs-y := procfs_example
+obj-m += procfs_example.o
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
 notfoundtemplate = echo "*** You have to install docbook-utils or xmlto ***"; \
                   exit 1
 db2xtemplate = db2TYPE -o $(dir $@) $<
diff --git a/Documentation/DocBook/gadget.tmpl b/Documentation/DocBook/gadget.tmpl
index 5a8ffa761e09..6ef2f0073e5a 100644
--- a/Documentation/DocBook/gadget.tmpl
+++ b/Documentation/DocBook/gadget.tmpl
@@ -524,6 +524,47 @@ These utilities include endpoint autoconfiguration.
 <!-- !Edrivers/usb/gadget/epautoconf.c -->
 </sect1>
+<sect1 id="composite"><title>Composite Device Framework</title>
+<para>The core API is sufficient for writing drivers for composite
+USB devices (with more than one function in a given configuration),
+and also multi-configuration devices (also more than one function,
+but not necessarily sharing a given configuration).
+There is however an optional framework which makes it easier to
+reuse and combine functions.
+</para>
+<para>Devices using this framework provide a <emphasis>struct
+usb_composite_driver</emphasis>, which in turn provides one or
+more <emphasis>struct usb_configuration</emphasis> instances.
+Each such configuration includes at least one
+<emphasis>struct usb_function</emphasis>, which packages a user
+visible role such as "network link" or "mass storage device".
+Management functions may also exist, such as "Device Firmware
+Upgrade".
+</para>
+!Iinclude/linux/usb/composite.h
+!Edrivers/usb/gadget/composite.c
+</sect1>
+<sect1 id="functions"><title>Composite Device Functions</title>
+<para>At this writing, a few of the current gadget drivers have
+been converted to this framework.
+Near-term plans include converting all of them, except for "gadgetfs".
+</para>
+!Edrivers/usb/gadget/f_acm.c
+!Edrivers/usb/gadget/f_ecm.c
+!Edrivers/usb/gadget/f_subset.c
+!Edrivers/usb/gadget/f_obex.c
+!Edrivers/usb/gadget/f_serial.c
+</sect1>
 </chapter>
 <chapter id="controllers"><title>Peripheral Controller Drivers</title>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index b7b1482f6e04..9d0058e788e5 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -283,6 +283,7 @@ X!Earch/x86/kernel/mca_32.c
  <chapter id="security">
     <title>Security Framework</title>
 !Isecurity/security.c
+!Esecurity/inode.c
  </chapter>
  <chapter id="audit">
@@ -364,6 +365,10 @@ X!Edrivers/pnp/system.c
 !Eblock/blk-barrier.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
+!Eblock/blk-integrity.c
+!Iblock/blktrace.c
+!Iblock/genhd.c
+!Eblock/genhd.c
  </chapter>
  <chapter id="chrdev">
diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl
index 4c63e5864160..ae15d55350ec 100644
--- a/Documentation/DocBook/kernel-hacking.tmpl
+++ b/Documentation/DocBook/kernel-hacking.tmpl
@@ -1105,7 +1105,7 @@ static struct block_device_operations opt_fops = {
    </listitem>
    <listitem>
     <para>
-      Function names as strings (__FUNCTION__).
+      Function names as strings (__func__).
     </para>
    </listitem>
    <listitem>
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index 2510763295d0..084f6ad7b7a0 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -219,10 +219,10 @@
   </para>
   <sect1 id="lock-intro">
-   <title>Three Main Types of Kernel Locks: Spinlocks, Mutexes and Semaphores</title>
+   <title>Two Main Types of Kernel Locks: Spinlocks and Mutexes</title>
   <para>
-     There are three main types of kernel locks.  The fundamental type
+     There are two main types of kernel locks.  The fundamental type
     is the spinlock 
     (<filename class="headerfile">include/asm/spinlock.h</filename>),
     which is a very simple single-holder lock: if you can't get the 
@@ -240,14 +240,6 @@
     use a spinlock instead.
   </para>
   <para>
-     The third type is a semaphore
-     (<filename class="headerfile">include/linux/semaphore.h</filename>): it
-     can have more than one holder at any time (the number decided at
-     initialization time), although it is most commonly used as a
-     single-holder lock (a mutex).  If you can't get a semaphore, your
-     task will be suspended and later on woken up - just like for mutexes.
-   </para>
-   <para>
     Neither type of lock is recursive: see
     <xref linkend="deadlock"/>.
   </para>
@@ -278,7 +270,7 @@
    </para>
    <para>
-      Semaphores still exist, because they are required for
+      Mutexes still exist, because they are required for
      synchronization between <firstterm linkend="gloss-usercontext">user 
      contexts</firstterm>, as we will see below.
    </para>
@@ -289,18 +281,17 @@
     <para>
       If you have a data structure which is only ever accessed from
-       user context, then you can use a simple semaphore
+       user context, then you can use a simple mutex
-       (<filename>linux/linux/semaphore.h</filename>) to protect it.  This
+       (<filename>include/linux/mutex.h</filename>) to protect it.  This
-       is the most trivial case: you initialize the semaphore to the number 
+       is the most trivial case: you initialize the mutex.  Then you can
-       of resources available (usually 1), and call
+       call <function>mutex_lock_interruptible()</function> to grab the mutex,
-       <function>down_interruptible()</function> to grab the semaphore, and 
+       and <function>mutex_unlock()</function> to release it.  There is also a 
-       <function>up()</function> to release it.  There is also a 
+       <function>mutex_lock()</function>, which should be avoided, because it 
-       <function>down()</function>, which should be avoided, because it 
       will not return if a signal is received.
     </para>
     <para>
-       Example: <filename>linux/net/core/netfilter.c</filename> allows 
+       Example: <filename>net/netfilter/nf_sockopt.c</filename> allows 
       registration of new <function>setsockopt()</function> and 
       <function>getsockopt()</function> calls, with
       <function>nf_register_sockopt()</function>.  Registration and 
@@ -515,7 +506,7 @@
      <listitem>
        <para>
          If you are in a process context (any syscall) and want to
-        lock other process out, use a semaphore.  You can take a semaphore
+        lock other process out, use a mutex.  You can take a mutex
        and sleep (<function>copy_from_user*(</function> or
        <function>kmalloc(x,GFP_KERNEL)</function>).
      </para>
@@ -662,7 +653,7 @@
 <entry>SLBH</entry>
 <entry>SLBH</entry>
 <entry>SLBH</entry>
-<entry>DI</entry>
+<entry>MLI</entry>
 <entry>None</entry>
 </row>
@@ -692,8 +683,8 @@
 <entry>spin_lock_bh</entry>
 </row>
 <row>
-<entry>DI</entry>
+<entry>MLI</entry>
-<entry>down_interruptible</entry>
+<entry>mutex_lock_interruptible</entry>
 </row>
 </tbody>
@@ -1310,7 +1301,7 @@ as Alan Cox says, <quote>Lock data, not code</quote>.
    <para>
      There is a coding bug where a piece of code tries to grab a
      spinlock twice: it will spin forever, waiting for the lock to
-      be released (spinlocks, rwlocks and semaphores are not
+      be released (spinlocks, rwlocks and mutexes are not
      recursive in Linux).  This is trivial to diagnose: not a
      stay-up-five-nights-talk-to-fluffy-code-bunnies kind of
      problem.
@@ -1335,7 +1326,7 @@ as Alan Cox says, <quote>Lock data, not code</quote>.
    <para>
      This complete lockup is easy to diagnose: on SMP boxes the
-      watchdog timer or compiling with <symbol>DEBUG_SPINLOCKS</symbol> set
+      watchdog timer or compiling with <symbol>DEBUG_SPINLOCK</symbol> set
      (<filename>include/linux/spinlock.h</filename>) will show this up 
      immediately when it happens.
    </para>
@@ -1558,7 +1549,7 @@ the amount of locking which needs to be done.
   <title>Read/Write Lock Variants</title>
   <para>
-      Both spinlocks and semaphores have read/write variants:
+      Both spinlocks and mutexes have read/write variants:
      <type>rwlock_t</type> and <structname>struct rw_semaphore</structname>.
      These divide users into two classes: the readers and the writers.  If
      you are only reading the data, you can get a read lock, but to write to
@@ -1681,7 +1672,7 @@ the amount of locking which needs to be done.
 #include &lt;linux/slab.h&gt;
 #include &lt;linux/string.h&gt;
 +#include &lt;linux/rcupdate.h&gt;
- #include &lt;linux/semaphore.h&gt;
+ #include &lt;linux/mutex.h&gt;
 #include &lt;asm/errno.h&gt;
 struct object
@@ -1913,7 +1904,7 @@ machines due to caching.
       </listitem>
       <listitem>
        <para>
-          <function> put_user()</function>
+          <function>put_user()</function>
        </para>
       </listitem>
      </itemizedlist>
@@ -1927,13 +1918,13 @@ machines due to caching.
     <listitem>
      <para>
-      <function>down_interruptible()</function> and
+      <function>mutex_lock_interruptible()</function> and
-      <function>down()</function>
+      <function>mutex_lock()</function>
      </para>
      <para>
-       There is a <function>down_trylock()</function> which can be
+       There is a <function>mutex_trylock()</function> which can be
       used inside interrupt context, as it will not sleep.
-       <function>up()</function> will also never sleep.
+       <function>mutex_unlock()</function> will also never sleep.
      </para>
     </listitem>
    </itemizedlist>
@@ -2023,7 +2014,7 @@ machines due to caching.
      <para>
        Prior to 2.5, or when <symbol>CONFIG_PREEMPT</symbol> is
        unset, processes in user context inside the kernel would not
-        preempt each other (ie. you had that CPU until you have it up,
+        preempt each other (ie. you had that CPU until you gave it up,
        except for interrupts).  With the addition of
        <symbol>CONFIG_PREEMPT</symbol> in 2.5.4, this changed: when
        in user context, higher priority tasks can "cut in": spinlocks
diff --git a/Documentation/DocBook/kgdb.tmpl b/Documentation/DocBook/kgdb.tmpl
index e8acd1f03456..372dec20c8da 100644
--- a/Documentation/DocBook/kgdb.tmpl
+++ b/Documentation/DocBook/kgdb.tmpl
@@ -98,6 +98,24 @@
    "Kernel debugging" select "KGDB: kernel debugging with remote gdb".
    </para>
    <para>
+    It is advised, but not required that you turn on the
+    CONFIG_FRAME_POINTER kernel option.  This option inserts code to
+    into the compiled executable which saves the frame information in
+    registers or on the stack at different points which will allow a
+    debugger such as gdb to more accurately construct stack back traces
+    while debugging the kernel.
+    </para>
+    <para>
+    If the architecture that you are using supports the kernel option
+    CONFIG_DEBUG_RODATA, you should consider turning it off.  This
+    option will prevent the use of software breakpoints because it
+    marks certain regions of the kernel's memory space as read-only.
+    If kgdb supports it for the architecture you are using, you can
+    use hardware breakpoints if you desire to run with the
+    CONFIG_DEBUG_RODATA option turned on, else you need to turn off
+    this option.
+    </para>
+    <para>
    Next you should choose one of more I/O drivers to interconnect debugging
    host and debugged target.  Early boot debugging requires a KGDB
    I/O driver that supports early debugging and the driver must be
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index b651e0a4b1c0..77c3c202991b 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -145,7 +145,6 @@ usage should require reading the full document.
        this though and the recommendation to allow only a single
        interface in STA mode at first!
      </para>
-!Finclude/net/mac80211.h ieee80211_if_types
 !Finclude/net/mac80211.h ieee80211_if_init_conf
 !Finclude/net/mac80211.h ieee80211_if_conf
    </chapter>
@@ -177,8 +176,7 @@ usage should require reading the full document.
        <title>functions/definitions</title>
 !Finclude/net/mac80211.h ieee80211_rx_status
 !Finclude/net/mac80211.h mac80211_rx_flags
-!Finclude/net/mac80211.h ieee80211_tx_control
+!Finclude/net/mac80211.h ieee80211_tx_info
-!Finclude/net/mac80211.h ieee80211_tx_status_flags
 !Finclude/net/mac80211.h ieee80211_rx
 !Finclude/net/mac80211.h ieee80211_rx_irqsafe
 !Finclude/net/mac80211.h ieee80211_tx_status
@@ -189,12 +187,11 @@ usage should require reading the full document.
 !Finclude/net/mac80211.h ieee80211_ctstoself_duration
 !Finclude/net/mac80211.h ieee80211_generic_frame_duration
 !Finclude/net/mac80211.h ieee80211_get_hdrlen_from_skb
-!Finclude/net/mac80211.h ieee80211_get_hdrlen
+!Finclude/net/mac80211.h ieee80211_hdrlen
 !Finclude/net/mac80211.h ieee80211_wake_queue
 !Finclude/net/mac80211.h ieee80211_stop_queue
-!Finclude/net/mac80211.h ieee80211_start_queues
-!Finclude/net/mac80211.h ieee80211_stop_queues
 !Finclude/net/mac80211.h ieee80211_wake_queues
+!Finclude/net/mac80211.h ieee80211_stop_queues
      </sect1>
    </chapter>
@@ -230,8 +227,7 @@ usage should require reading the full document.
      <title>Multiple queues and QoS support</title>
      <para>TBD</para>
 !Finclude/net/mac80211.h ieee80211_tx_queue_params
-!Finclude/net/mac80211.h ieee80211_tx_queue_stats_data
+!Finclude/net/mac80211.h ieee80211_tx_queue_stats
-!Finclude/net/mac80211.h ieee80211_tx_queue
    </chapter>
    <chapter id="AP">
diff --git a/Documentation/DocBook/procfs-guide.tmpl b/Documentation/DocBook/procfs-guide.tmpl
index 1fd6a1ec7591..9eba4b7af73d 100644
--- a/Documentation/DocBook/procfs-guide.tmpl
+++ b/Documentation/DocBook/procfs-guide.tmpl
@@ -14,27 +14,30 @@
        <othername>(J.A.K.)</othername>
        <surname>Mouw</surname>
        <affiliation>
-          <orgname>Delft University of Technology</orgname>
-          <orgdiv>Faculty of Information Technology and Systems</orgdiv>
          <address>
-            <email>J.A.K.Mouw@its.tudelft.nl</email>
+            <email>mouw@nl.linux.org</email>
-            <pob>PO BOX 5031</pob>
-            <postcode>2600 GA</postcode>
-            <city>Delft</city>
-            <country>The Netherlands</country>
          </address>
        </affiliation>
      </author>
+      <othercredit>
+        <contrib>
+        This software and documentation were written while working on the
+        LART computing board
+        (<ulink url="http://www.lartmaker.nl/">http://www.lartmaker.nl/</ulink>),
+        which was sponsored by the Delt University of Technology projects
+        Mobile Multi-media Communications and Ubiquitous Communications.
+        </contrib>
+      </othercredit>
    </authorgroup>
    <revhistory>
      <revision>
-        <revnumber>1.0&nbsp;</revnumber>
+        <revnumber>1.0</revnumber>
        <date>May 30, 2001</date>
        <revremark>Initial revision posted to linux-kernel</revremark>
      </revision>
      <revision>
-        <revnumber>1.1&nbsp;</revnumber>
+        <revnumber>1.1</revnumber>
        <date>June 3, 2001</date>
        <revremark>Revised after comments from linux-kernel</revremark>
      </revision>
@@ -109,18 +112,6 @@
    </para>
    <para>
-      This documentation was written while working on the LART
-      computing board (<ulink
-      url="http://www.lart.tudelft.nl/">http://www.lart.tudelft.nl/</ulink>),
-      which is sponsored by the Mobile Multi-media Communications
-      (<ulink
-      url="http://www.mmc.tudelft.nl/">http://www.mmc.tudelft.nl/</ulink>)
-      and Ubiquitous Communications (<ulink
-      url="http://www.ubicom.tudelft.nl/">http://www.ubicom.tudelft.nl/</ulink>)
-      projects.
-    </para>
-    <para>
      Erik
    </para>
  </preface>
diff --git a/Documentation/DocBook/procfs_example.c b/Documentation/DocBook/procfs_example.c
index 7064084c1c5e..8c6396e4bf31 100644
--- a/Documentation/DocBook/procfs_example.c
+++ b/Documentation/DocBook/procfs_example.c
@@ -1,28 +1,16 @@
 /*
 * procfs_example.c: an example proc interface
 *
- * Copyright (C) 2001, Erik Mouw (J.A.K.Mouw@its.tudelft.nl)
+ * Copyright (C) 2001, Erik Mouw (mouw@nl.linux.org)
 *
 * This file accompanies the procfs-guide in the Linux kernel
 * source. Its main use is to demonstrate the concepts and
 * functions described in the guide.
 *
 * This software has been developed while working on the LART
- * computing board (http://www.lart.tudelft.nl/), which is
+ * computing board (http://www.lartmaker.nl), which was sponsored
- * sponsored by the Mobile Multi-media Communications
+ * by the Delt University of Technology projects Mobile Multi-media
- * (http://www.mmc.tudelft.nl/) and Ubiquitous Communications 
+ * Communications and Ubiquitous Communications.
- * (http://www.ubicom.tudelft.nl/) projects.
- *
- * The author can be reached at:
- *
- *  Erik Mouw
- *  Information and Communication Theory Group
- *  Faculty of Information Technology and Systems
- *  Delft University of Technology
- *  P.O. Box 5031
- *  2600 GA Delft
- *  The Netherlands
- *
 *
 * This program is free software; you can redistribute
 * it and/or modify it under the terms of the GNU General
@@ -189,8 +177,6 @@ static int __init init_procfs_example(void)
        return 0;
 no_symlink:
-        remove_proc_entry("tty", example_dir);
-no_tty:
        remove_proc_entry("bar", example_dir);
 no_bar:
        remove_proc_entry("foo", example_dir);
@@ -206,7 +192,6 @@ out:
 static void __exit cleanup_procfs_example(void)
 {
        remove_proc_entry("jiffies_too", example_dir);
-        remove_proc_entry("tty", example_dir);
        remove_proc_entry("bar", example_dir);
        remove_proc_entry("foo", example_dir);
        remove_proc_entry("jiffies", example_dir);
@@ -222,3 +207,4 @@ module_exit(cleanup_procfs_example);
 MODULE_AUTHOR("Erik Mouw");
 MODULE_DESCRIPTION("procfs examples");
+MODULE_LICENSE("GPL");
diff --git a/Documentation/DocBook/s390-drivers.tmpl b/Documentation/DocBook/s390-drivers.tmpl
index 4acc73240a6d..95bfc12e5439 100644
--- a/Documentation/DocBook/s390-drivers.tmpl
+++ b/Documentation/DocBook/s390-drivers.tmpl
@@ -100,7 +100,7 @@
      the hardware structures represented here, please consult the Principles
      of Operation.
    </para>
-!Iinclude/asm-s390/cio.h
+!Iarch/s390/include/asm/cio.h
    </sect1>
    <sect1 id="ccwdev">
     <title>ccw devices</title>
@@ -114,7 +114,7 @@
      ccw device structure. Device drivers must not bypass those functions
      or strange side effects may happen.
    </para>
-!Iinclude/asm-s390/ccwdev.h
+!Iarch/s390/include/asm/ccwdev.h
 !Edrivers/s390/cio/device.c
 !Edrivers/s390/cio/device_ops.c
    </sect1>
@@ -125,7 +125,7 @@
        measurement data which is made available by the channel subsystem
        for each channel attached device.
  </para>
-!Iinclude/asm-s390/cmb.h
+!Iarch/s390/include/asm/cmb.h
 !Edrivers/s390/cio/cmf.c
    </sect1>
  </chapter>
@@ -142,7 +142,7 @@
  </para>
   <sect1 id="ccwgroupdevices">
    <title>ccw group devices</title>
-!Iinclude/asm-s390/ccwgroup.h
+!Iarch/s390/include/asm/ccwgroup.h
 !Edrivers/s390/cio/ccwgroup.c
   </sect1>
  </chapter>
diff --git a/Documentation/DocBook/sh.tmpl b/Documentation/DocBook/sh.tmpl
new file mode 100644
index 000000000000..0c3dc4c69dd1
--- /dev/null
+++ b/Documentation/DocBook/sh.tmpl
@@ -0,0 +1,105 @@
+<?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="sh-drivers">
+ <bookinfo>
+  <title>SuperH Interfaces Guide</title>
+  
+  <authorgroup>
+   <author>
+    <firstname>Paul</firstname>
+    <surname>Mundt</surname>
+    <affiliation>
+     <address>
+      <email>lethal@linux-sh.org</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+  <copyright>
+   <year>2008</year>
+   <holder>Paul Mundt</holder>
+  </copyright>
+  <copyright>
+   <year>2008</year>
+   <holder>Renesas Technology Corp.</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 program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+      
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+     MA 02111-1307 USA
+   </para>
+      
+   <para>
+     For more details see the file COPYING in the source
+     distribution of Linux.
+   </para>
+  </legalnotice>
+ </bookinfo>
+<toc></toc>
+  <chapter id="mm">
+    <title>Memory Management</title>
+    <sect1 id="sh4">
+    <title>SH-4</title>
+      <sect2 id="sq">
+        <title>Store Queue API</title>
+!Earch/sh/kernel/cpu/sh4/sq.c
+      </sect2>
+    </sect1>
+    <sect1 id="sh5">
+      <title>SH-5</title>
+      <sect2 id="tlb">
+        <title>TLB Interfaces</title>
+!Iarch/sh/mm/tlb-sh5.c
+!Iarch/sh/include/asm/tlb_64.h
+      </sect2>
+    </sect1>
+  </chapter>
+  <chapter id="clk">
+    <title>Clock Framework Extensions</title>
+!Iarch/sh/include/asm/clock.h
+  </chapter>
+  <chapter id="mach">
+    <title>Machine Specific Interfaces</title>
+    <sect1 id="dreamcast">
+      <title>mach-dreamcast</title>
+!Iarch/sh/boards/mach-dreamcast/rtc.c
+    </sect1>
+    <sect1 id="x3proto">
+      <title>mach-x3proto</title>
+!Earch/sh/boards/mach-x3proto/ilsel.c
+    </sect1>
+  </chapter>
+  <chapter id="busses">
+    <title>Busses</title>
+    <sect1 id="superhyway">
+      <title>SuperHyway</title>
+!Edrivers/sh/superhyway/superhyway.c
+    </sect1>
+    <sect1 id="maple">
+      <title>Maple</title>
+!Edrivers/sh/maple/maple.c
+    </sect1>
+  </chapter>
+</book>
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index fdd7f4f887b7..df87d1b93605 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -21,6 +21,18 @@
    </affiliation>
 </author>
+<copyright>
+        <year>2006-2008</year>
+        <holder>Hans-Jürgen Koch.</holder>
+</copyright>
+<legalnotice>
+<para>
+This documentation is Free Software licensed under the terms of the
+GPL version 2.
+</para>
+</legalnotice>
 <pubdate>2006-12-11</pubdate>
 <abstract>
@@ -30,6 +42,12 @@
 <revhistory>
        <revision>
+        <revnumber>0.5</revnumber>
+        <date>2008-05-22</date>
+        <authorinitials>hjk</authorinitials>
+        <revremark>Added description of write() function.</revremark>
+        </revision>
+        <revision>
        <revnumber>0.4</revnumber>
        <date>2007-11-26</date>
        <authorinitials>hjk</authorinitials>
@@ -57,20 +75,9 @@
 </bookinfo>
 <chapter id="aboutthisdoc">
-<?dbhtml filename="about.html"?>
+<?dbhtml filename="aboutthis.html"?>
 <title>About this document</title>
-<sect1 id="copyright">
-<?dbhtml filename="copyright.html"?>
-<title>Copyright and License</title>
-<para>
-      Copyright (c) 2006 by Hans-Jürgen Koch.</para>
-<para>
-This documentation is Free Software licensed under the terms of the
-GPL version 2.
-</para>
-</sect1>
 <sect1 id="translations">
 <?dbhtml filename="translations.html"?>
 <title>Translations</title>
@@ -189,6 +196,30 @@ interested in translating it, please email me
        represents the total interrupt count. You can use this number
        to figure out if you missed some interrupts.
        </para>
+        <para>
+        For some hardware that has more than one interrupt source internally,
+        but not separate IRQ mask and status registers, there might be
+        situations where userspace cannot determine what the interrupt source
+        was if the kernel handler disables them by writing to the chip's IRQ
+        register. In such a case, the kernel has to disable the IRQ completely
+        to leave the chip's register untouched. Now the userspace part can
+        determine the cause of the interrupt, but it cannot re-enable
+        interrupts. Another cornercase is chips where re-enabling interrupts
+        is a read-modify-write operation to a combined IRQ status/acknowledge
+        register. This would be racy if a new interrupt occurred
+        simultaneously.
+        </para>
+        <para>
+        To address these problems, UIO also implements a write() function. It
+        is normally not used and can be ignored for hardware that has only a
+        single interrupt source or has separate IRQ mask and status registers.
+        If you need it, however, a write to <filename>/dev/uioX</filename>
+        will call the <function>irqcontrol()</function> function implemented
+        by the driver. You have to write a 32-bit value that is usually either
+        0 or 1 to disable or enable interrupts. If a driver does not implement
+        <function>irqcontrol()</function>, <function>write()</function> will
+        return with <varname>-ENOSYS</varname>.
+        </para>
        <para>
        To handle interrupts properly, your custom kernel module can
@@ -362,6 +393,14 @@ device is actually used.
 <function>open()</function>, you will probably also want a custom
 <function>release()</function> function.
 </para></listitem>
+<listitem><para>
+<varname>int (*irqcontrol)(struct uio_info *info, s32 irq_on)
+</varname>: Optional. If you need to be able to enable or disable
+interrupts from userspace by writing to <filename>/dev/uioX</filename>,
+you can implement this function. The parameter <varname>irq_on</varname>
+will be 0 to disable interrupts and 1 to enable them.
+</para></listitem>
 </itemizedlist>
 <para>
diff --git a/Documentation/DocBook/videobook.tmpl b/Documentation/DocBook/videobook.tmpl
deleted file mode 100644
index 89817795e668..000000000000
--- a/Documentation/DocBook/videobook.tmpl
+++ /dev/null
@@ -1,1654 +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="V4LGuide">
- <bookinfo>
-  <title>Video4Linux Programming</title>
-  
-  <authorgroup>
-   <author>
-    <firstname>Alan</firstname>
-    <surname>Cox</surname>
-    <affiliation>
-     <address>
-      <email>alan@redhat.com</email>
-     </address>
-    </affiliation>
-   </author>
-  </authorgroup>
-  <copyright>
-   <year>2000</year>
-   <holder>Alan Cox</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 as published by the Free Software Foundation; either
-     version 2 of the License, or (at your option) any later
-     version.
-   </para>
-      
-   <para>
-     This program is distributed in the hope that it will be
-     useful, but WITHOUT ANY WARRANTY; without even the implied
-     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-     See the GNU General Public License for more details.
-   </para>
-      
-   <para>
-     You should have received a copy of the GNU General Public
-     License along with this program; if not, write to the Free
-     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
-     MA 02111-1307 USA
-   </para>
-      
-   <para>
-     For more details see the file COPYING in the source
-     distribution of Linux.
-   </para>
-  </legalnotice>
- </bookinfo>
-<toc></toc>
-  <chapter id="intro">
-      <title>Introduction</title>
-  <para>
-        Parts of this document first appeared in Linux Magazine under a
-        ninety day exclusivity.
-  </para>
-  <para>
-        Video4Linux is intended to provide a common programming interface
-        for the many TV and capture cards now on the market, as well as
-        parallel port and USB video cameras. Radio, teletext decoders and
-        vertical blanking data interfaces are also provided.
-  </para>
-  </chapter>
-  <chapter id="radio">
-        <title>Radio Devices</title>
-  <para>
-        There are a wide variety of radio interfaces available for PC's, and these
-        are generally very simple to program. The biggest problem with supporting
-        such devices is normally extracting documentation from the vendor.
-  </para>
-  <para>
-        The radio interface supports a simple set of control ioctls standardised
-        across all radio and tv interfaces. It does not support read or write, which
-        are used for video streams. The reason radio cards do not allow you to read
-        the audio stream into an application is that without exception they provide
-        a connection on to a soundcard. Soundcards can be used to read the radio
-        data just fine. 
-  </para>
-  <sect1 id="registerradio">
-  <title>Registering Radio Devices</title>
-  <para>
-        The Video4linux core provides an interface for registering devices. The
-        first step in writing our radio card driver is to register it.
-  </para>
-  <programlisting>
-static struct video_device my_radio
-{
-        "My radio",
-        VID_TYPE_TUNER,
-        radio_open.
-        radio_close,
-        NULL,                /* no read */
-        NULL,                 /* no write */
-        NULL,                /* no poll */
-        radio_ioctl,
-        NULL,                /* no special init function */
-        NULL                /* no private data */
-};
-  </programlisting>
-  <para>
-        This declares our video4linux device driver interface. The VID_TYPE_ value
-        defines what kind of an interface we are, and defines basic capabilities.
-  </para>
-  <para>
-        The only defined value relevant for a radio card is VID_TYPE_TUNER which
-        indicates that the device can be tuned. Clearly our radio is going to have some
-        way to change channel so it is tuneable.
-  </para>
-  <para>
-        We declare an open and close routine, but we do not need read or write,
-        which are used to read and write video data to or from the card itself. As
-        we have no read or write there is no poll function.
-  </para>
-  <para>
-        The private initialise function is run when the device is registered. In
-        this driver we've already done all the work needed. The final pointer is a
-        private data pointer that can be used by the device driver to attach and
-        retrieve private data structures. We set this field "priv" to NULL for
-        the moment.
-  </para>
-  <para>
-        Having the structure defined is all very well but we now need to register it
-        with the kernel. 
-  </para>
-  <programlisting>
-static int io = 0x320;
-int __init myradio_init(struct video_init *v)
-{
-        if(!request_region(io, MY_IO_SIZE, "myradio"))
-        {
-                printk(KERN_ERR 
-                    "myradio: port 0x%03X is in use.\n", io);
-                return -EBUSY;
-        }
-        if(video_device_register(&amp;my_radio, VFL_TYPE_RADIO)==-1) {
-                release_region(io, MY_IO_SIZE);
-                return -EINVAL;
-        }               
-        return 0;
-}
-  </programlisting>
-  <para>
-        The first stage of the initialisation, as is normally the case, is to check 
-        that the I/O space we are about to fiddle with doesn't belong to some other 
-        driver. If it is we leave well alone. If the user gives the address of the 
-        wrong device then we will spot this. These policies will generally avoid 
-        crashing the machine.
-  </para>
-  <para>
-        Now we ask the Video4Linux layer to register the device for us. We hand it
-        our carefully designed video_device structure and also tell it which group
-        of devices we want it registered with. In this case VFL_TYPE_RADIO.
-  </para>
-  <para>
-        The types available are
-  </para>
-   <table frame="all" id="Device_Types"><title>Device Types</title>
-   <tgroup cols="3" align="left">
-   <tbody>
-   <row>
-        <entry>VFL_TYPE_RADIO</entry><entry>/dev/radio{n}</entry><entry>
-        Radio devices are assigned in this block. As with all of these
-        selections the actual number assignment is done by the video layer
-        accordijng to what is free.</entry>
-        </row><row>
-        <entry>VFL_TYPE_GRABBER</entry><entry>/dev/video{n}</entry><entry>
-        Video capture devices and also -- counter-intuitively for the name --
-        hardware video playback devices such as MPEG2 cards.</entry>
-        </row><row>
-        <entry>VFL_TYPE_VBI</entry><entry>/dev/vbi{n}</entry><entry>
-        The VBI devices capture the hidden lines on a television picture
-        that carry further information like closed caption data, teletext
-        (primarily in Europe) and now Intercast and the ATVEC internet
-        television encodings.</entry>
-        </row><row>
-        <entry>VFL_TYPE_VTX</entry><entry>/dev/vtx[n}</entry><entry>
-        VTX is 'Videotext' also known as 'Teletext'. This is a system for
-        sending numbered, 40x25, mostly textual page images over the hidden
-        lines. Unlike the /dev/vbi interfaces, this is for 'smart' decoder 
-        chips. (The use of the word smart here has to be taken in context,
-        the smartest teletext chips are fairly dumb pieces of technology).
-        </entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-  <para>
-        We are most definitely a radio.
-  </para>
-  <para>
-        Finally we allocate our I/O space so that nobody treads on us and return 0
-        to signify general happiness with the state of the universe.
-  </para>
-  </sect1>
-  <sect1 id="openradio">
-  <title>Opening And Closing The Radio</title>
-  <para>
-        The functions we declared in our video_device are mostly very simple.
-        Firstly we can drop in what is basically standard code for open and close. 
-  </para>
-  <programlisting>
-static int users = 0;
-static int radio_open(struct video_device *dev, int flags)
-{
-        if(users)
-                return -EBUSY;
-        users++;
-        return 0;
-}
-  </programlisting>
-  <para>
-        At open time we need to do nothing but check if someone else is also using
-        the radio card. If nobody is using it we make a note that we are using it,
-        then we ensure that nobody unloads our driver on us.
-  </para>
-  <programlisting>
-static int radio_close(struct video_device *dev)
-{
-        users--;
-}
-  </programlisting>
-  <para>
-        At close time we simply need to reduce the user count and allow the module
-        to become unloadable.
-  </para>
-  <para>
-        If you are sharp you will have noticed neither the open nor the close
-        routines attempt to reset or change the radio settings. This is intentional.
-        It allows an application to set up the radio and exit. It avoids a user
-        having to leave an application running all the time just to listen to the
-        radio. 
-  </para>
-  </sect1>
-  <sect1 id="ioctlradio">
-  <title>The Ioctl Interface</title>
-  <para>
-        This leaves the ioctl routine, without which the driver will not be
-        terribly useful to anyone.
-  </para>
-  <programlisting>
-static int radio_ioctl(struct video_device *dev, unsigned int cmd, void *arg)
-{
-        switch(cmd)
-        {
-                case VIDIOCGCAP:
-                {
-                        struct video_capability v;
-                        v.type = VID_TYPE_TUNER;
-                        v.channels = 1;
-                        v.audios = 1;
-                        v.maxwidth = 0;
-                        v.minwidth = 0;
-                        v.maxheight = 0;
-                        v.minheight = 0;
-                        strcpy(v.name, "My Radio");
-                        if(copy_to_user(arg, &amp;v, sizeof(v)))
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        VIDIOCGCAP is the first ioctl all video4linux devices must support. It
-        allows the applications to find out what sort of a card they have found and
-        to figure out what they want to do about it. The fields in the structure are
-  </para>
-   <table frame="all" id="video_capability_fields"><title>struct video_capability fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-        <entry>name</entry><entry>The device text name. This is intended for the user.</entry>
-        </row><row>
-        <entry>channels</entry><entry>The number of different channels you can tune on
-                        this card. It could even by zero for a card that has
-                        no tuning capability. For our simple FM radio it is 1. 
-                        An AM/FM radio would report 2.</entry>
-        </row><row>
-        <entry>audios</entry><entry>The number of audio inputs on this device. For our
-                        radio there is only one audio input.</entry>
-        </row><row>
-        <entry>minwidth,minheight</entry><entry>The smallest size the card is capable of capturing
-                        images in. We set these to zero. Radios do not
-                        capture pictures</entry>
-        </row><row>
-        <entry>maxwidth,maxheight</entry><entry>The largest image size the card is capable of
-                                      capturing. For our radio we report 0.
-                                </entry>
-        </row><row>
-        <entry>type</entry><entry>This reports the capabilities of the device, and
-                        matches the field we filled in in the struct
-                        video_device when registering.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-  <para>
-        Having filled in the fields, we use copy_to_user to copy the structure into
-        the users buffer. If the copy fails we return an EFAULT to the application
-        so that it knows it tried to feed us garbage.
-  </para>
-  <para>
-        The next pair of ioctl operations select which tuner is to be used and let
-        the application find the tuner properties. We have only a single FM band
-        tuner in our example device.
-  </para>
-  <programlisting>
-                case VIDIOCGTUNER:
-                {
-                        struct video_tuner v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v))!=0)
-                                return -EFAULT;
-                        if(v.tuner)
-                                return -EINVAL;
-                        v.rangelow=(87*16000);
-                        v.rangehigh=(108*16000);
-                        v.flags = VIDEO_TUNER_LOW;
-                        v.mode = VIDEO_MODE_AUTO;
-                        v.signal = 0xFFFF;
-                        strcpy(v.name, "FM");
-                        if(copy_to_user(&amp;v, arg, sizeof(v))!=0)
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        The VIDIOCGTUNER ioctl allows applications to query a tuner. The application
-        sets the tuner field to the tuner number it wishes to query. The query does
-        not change the tuner that is being used, it merely enquires about the tuner
-        in question.
-  </para>
-  <para>
-        We have exactly one tuner so after copying the user buffer to our temporary
-        structure we complain if they asked for a tuner other than tuner 0. 
-  </para>
-  <para>
-        The video_tuner structure has the following fields
-  </para>
-   <table frame="all" id="video_tuner_fields"><title>struct video_tuner fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-        <entry>int tuner</entry><entry>The number of the tuner in question</entry>
-   </row><row>
-        <entry>char name[32]</entry><entry>A text description of this tuner. "FM" will do fine.
-                        This is intended for the application.</entry>
-   </row><row>
-        <entry>u32 flags</entry>
-        <entry>Tuner capability flags</entry>
-   </row>
-   <row>
-        <entry>u16 mode</entry><entry>The current reception mode</entry>
-   </row><row>
-        <entry>u16 signal</entry><entry>The signal strength scaled between 0 and 65535. If
-                        a device cannot tell the signal strength it should
-                        report 65535. Many simple cards contain only a 
-                        signal/no signal bit. Such cards will report either
-                        0 or 65535.</entry>
-   </row><row>
-        <entry>u32 rangelow, rangehigh</entry><entry>
-                        The range of frequencies supported by the radio
-                        or TV. It is scaled according to the VIDEO_TUNER_LOW
-                        flag.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-   <table frame="all" id="video_tuner_flags"><title>struct video_tuner flags</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-        <entry>VIDEO_TUNER_PAL</entry><entry>A PAL TV tuner</entry>
-        </row><row>
-        <entry>VIDEO_TUNER_NTSC</entry><entry>An NTSC (US) TV tuner</entry>
-        </row><row>
-        <entry>VIDEO_TUNER_SECAM</entry><entry>A SECAM (French) TV tuner</entry>
-        </row><row>
-        <entry>VIDEO_TUNER_LOW</entry><entry>
-             The tuner frequency is scaled in 1/16th of a KHz
-             steps. If not it is in 1/16th of a MHz steps
-        </entry>
-        </row><row>
-        <entry>VIDEO_TUNER_NORM</entry><entry>The tuner can set its format</entry>
-        </row><row>
-        <entry>VIDEO_TUNER_STEREO_ON</entry><entry>The tuner is currently receiving a stereo signal</entry>
-        </row>
-    </tbody>
-    </tgroup>
-    </table>
-   <table frame="all" id="video_tuner_modes"><title>struct video_tuner modes</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-                <entry>VIDEO_MODE_PAL</entry><entry>PAL Format</entry>
-   </row><row>
-                <entry>VIDEO_MODE_NTSC</entry><entry>NTSC Format (USA)</entry>
-   </row><row>
-                <entry>VIDEO_MODE_SECAM</entry><entry>French Format</entry>
-   </row><row>
-                <entry>VIDEO_MODE_AUTO</entry><entry>A device that does not need to do
-                                        TV format switching</entry>
-   </row>
-    </tbody>
-    </tgroup>
-    </table>
-  <para>
-        The settings for the radio card are thus fairly simple. We report that we
-        are a tuner called "FM" for FM radio. In order to get the best tuning
-        resolution we report VIDEO_TUNER_LOW and select tuning to 1/16th of KHz. Its
-        unlikely our card can do that resolution but it is a fair bet the card can
-        do better than 1/16th of a MHz. VIDEO_TUNER_LOW is appropriate to almost all
-        radio usage.
-  </para>
-  <para>
-        We report that the tuner automatically handles deciding what format it is
-        receiving - true enough as it only handles FM radio. Our example card is
-        also incapable of detecting stereo or signal strengths so it reports a
-        strength of 0xFFFF (maximum) and no stereo detected.
-  </para>
-  <para>
-        To finish off we set the range that can be tuned to be 87-108Mhz, the normal
-        FM broadcast radio range. It is important to find out what the card is
-        actually capable of tuning. It is easy enough to simply use the FM broadcast
-        range. Unfortunately if you do this you will discover the FM broadcast
-        ranges in the USA, Europe and Japan are all subtly different and some users
-        cannot receive all the stations they wish.
-  </para>
-  <para>
-        The application also needs to be able to set the tuner it wishes to use. In
-        our case, with a single tuner this is rather simple to arrange.
-  </para>
-  <programlisting>
-                case VIDIOCSTUNER:
-                {
-                        struct video_tuner v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.tuner != 0)
-                                return -EINVAL;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        We copy the user supplied structure into kernel memory so we can examine it. 
-        If the user has selected a tuner other than zero we reject the request. If 
-        they wanted tuner 0 then, surprisingly enough, that is the current tuner already.
-  </para>
-  <para>
-        The next two ioctls we need to provide are to get and set the frequency of
-        the radio. These both use an unsigned long argument which is the frequency.
-        The scale of the frequency depends on the VIDEO_TUNER_LOW flag as I
-        mentioned earlier on. Since we have VIDEO_TUNER_LOW set this will be in
-        1/16ths of a KHz.
-  </para>
-  <programlisting>
-static unsigned long current_freq;
-                case VIDIOCGFREQ:
-                        if(copy_to_user(arg, &amp;current_freq, 
-                                sizeof(unsigned long))
-                                return -EFAULT;
-                        return 0;
-  </programlisting>
-  <para>
-        Querying the frequency in our case is relatively simple. Our radio card is
-        too dumb to let us query the signal strength so we remember our setting if 
-        we know it. All we have to do is copy it to the user.
-  </para>
-  <programlisting>
-                case VIDIOCSFREQ:
-                {
-                        u32 freq;
-                        if(copy_from_user(arg, &amp;freq, 
-                                sizeof(unsigned long))!=0)
-                                return -EFAULT;
-                        if(hardware_set_freq(freq)&lt;0)
-                                return -EINVAL;
-                        current_freq = freq;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        Setting the frequency is a little more complex. We begin by copying the
-        desired frequency into kernel space. Next we call a hardware specific routine
-        to set the radio up. This might be as simple as some scaling and a few
-        writes to an I/O port. For most radio cards it turns out a good deal more
-        complicated and may involve programming things like a phase locked loop on
-        the card. This is what documentation is for. 
-  </para>
-  <para>
-        The final set of operations we need to provide for our radio are the 
-        volume controls. Not all radio cards can even do volume control. After all
-        there is a perfectly good volume control on the sound card. We will assume
-        our radio card has a simple 4 step volume control.
-  </para>
-  <para>
-        There are two ioctls with audio we need to support
-  </para>
-  <programlisting>
-static int current_volume=0;
-                case VIDIOCGAUDIO:
-                {
-                        struct video_audio v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.audio != 0)
-                                return -EINVAL;
-                        v.volume = 16384*current_volume;
-                        v.step = 16384;
-                        strcpy(v.name, "Radio");
-                        v.mode = VIDEO_SOUND_MONO;
-                        v.balance = 0;
-                        v.base = 0;
-                        v.treble = 0;
-                        
-                        if(copy_to_user(arg. &amp;v, sizeof(v)))
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        Much like the tuner we start by copying the user structure into kernel
-        space. Again we check if the user has asked for a valid audio input. We have
-        only input 0 and we punt if they ask for another input.
-  </para>
-  <para>
-        Then we fill in the video_audio structure. This has the following format
-  </para>
-   <table frame="all" id="video_audio_fields"><title>struct video_audio fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-   <entry>audio</entry><entry>The input the user wishes to query</entry>
-   </row><row>
-   <entry>volume</entry><entry>The volume setting on a scale of 0-65535</entry>
-   </row><row>
-   <entry>base</entry><entry>The base level on a scale of 0-65535</entry>
-   </row><row>
-   <entry>treble</entry><entry>The treble level on a scale of 0-65535</entry>
-   </row><row>
-   <entry>flags</entry><entry>The features this audio device supports
-   </entry>
-   </row><row>
-   <entry>name</entry><entry>A text name to display to the user. We picked
-                        "Radio" as it explains things quite nicely.</entry>
-   </row><row>
-   <entry>mode</entry><entry>The current reception mode for the audio
-                We report MONO because our card is too stupid to know if it is in
-                mono or stereo. 
-   </entry>
-   </row><row>
-   <entry>balance</entry><entry>The stereo balance on a scale of 0-65535, 32768 is
-                        middle.</entry>
-   </row><row>
-   <entry>step</entry><entry>The step by which the volume control jumps. This is
-                        used to help make it easy for applications to set 
-                        slider behaviour.</entry>
-   </row>
-   </tbody>
-   </tgroup>
-   </table>
-   <table frame="all" id="video_audio_flags"><title>struct video_audio flags</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-                <entry>VIDEO_AUDIO_MUTE</entry><entry>The audio is currently muted. We
-                                        could fake this in our driver but we
-                                        choose not to bother.</entry>
-   </row><row>
-                <entry>VIDEO_AUDIO_MUTABLE</entry><entry>The input has a mute option</entry>
-   </row><row>
-                <entry>VIDEO_AUDIO_TREBLE</entry><entry>The  input has a treble control</entry>
-   </row><row>
-                <entry>VIDEO_AUDIO_BASS</entry><entry>The input has a base control</entry>
-   </row>
-   </tbody>
-   </tgroup>
-   </table>
-   <table frame="all" id="video_audio_modes"><title>struct video_audio modes</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-                <entry>VIDEO_SOUND_MONO</entry><entry>Mono sound</entry>
-   </row><row>
-                <entry>VIDEO_SOUND_STEREO</entry><entry>Stereo sound</entry>
-   </row><row>
-                <entry>VIDEO_SOUND_LANG1</entry><entry>Alternative language 1 (TV specific)</entry>
-   </row><row>
-                <entry>VIDEO_SOUND_LANG2</entry><entry>Alternative language 2 (TV specific)</entry>
-   </row>
-   </tbody>
-   </tgroup>
-   </table>
-  <para>
-        Having filled in the structure we copy it back to user space.
-  </para>
-  <para>
-        The VIDIOCSAUDIO ioctl allows the user to set the audio parameters in the
-        video_audio structure. The driver does its best to honour the request.
-  </para>
-  <programlisting>
-                case VIDIOCSAUDIO:
-                {
-                        struct video_audio v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.audio)
-                                return -EINVAL;
-                        current_volume = v/16384;
-                        hardware_set_volume(current_volume);
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        In our case there is very little that the user can set. The volume is
-        basically the limit. Note that we could pretend to have a mute feature
-        by rewriting this to 
-  </para>
-  <programlisting>
-                case VIDIOCSAUDIO:
-                {
-                        struct video_audio v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.audio)
-                                return -EINVAL;
-                        current_volume = v/16384;
-                        if(v.flags&amp;VIDEO_AUDIO_MUTE)
-                                hardware_set_volume(0);
-                        else
-                                hardware_set_volume(current_volume);
-                        current_muted = v.flags &amp; 
-                                              VIDEO_AUDIO_MUTE;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        This with the corresponding changes to the VIDIOCGAUDIO code to report the
-        state of the mute flag we save and to report the card has a mute function,
-        will allow applications to use a mute facility with this card. It is
-        questionable whether this is a good idea however. User applications can already
-        fake this themselves and kernel space is precious.
-  </para>
-  <para>
-        We now have a working radio ioctl handler. So we just wrap up the function
-  </para>
-  <programlisting>
-        }
-        return -ENOIOCTLCMD;
-}
-  </programlisting>
-  <para>
-        and pass the Video4Linux layer back an error so that it knows we did not
-        understand the request we got passed.
-  </para>
-  </sect1>
-  <sect1 id="modradio">
-  <title>Module Wrapper</title>
-  <para>
-        Finally we add in the usual module wrapping and the driver is done.
-  </para>
-  <programlisting>
-#ifndef MODULE
-static int io = 0x300;
-#else
-static int io = -1;
-#endif
-MODULE_AUTHOR("Alan Cox");
-MODULE_DESCRIPTION("A driver for an imaginary radio card.");
-module_param(io, int, 0444);
-MODULE_PARM_DESC(io, "I/O address of the card.");
-static int __init init(void)
-{
-        if(io==-1)
-        {
-                printk(KERN_ERR 
-         "You must set an I/O address with io=0x???\n");
-                return -EINVAL;
-        }
-        return myradio_init(NULL);
-}
-static void __exit cleanup(void)
-{
-        video_unregister_device(&amp;my_radio);
-        release_region(io, MY_IO_SIZE);
-}
-module_init(init);
-module_exit(cleanup);
-  </programlisting>
-  <para>
-        In this example we set the IO base by default if the driver is compiled into
-        the kernel: you can still set it using "my_radio.irq" if this file is called <filename>my_radio.c</filename>. For the module we require the
-        user sets the parameter. We set io to a nonsense port (-1) so that we can
-        tell if the user supplied an io parameter or not.
-  </para>
-  <para>
-        We use MODULE_ defines to give an author for the card driver and a
-        description. We also use them to declare that io is an integer and it is the
-        address of the card, and can be read by anyone from sysfs.
-  </para>
-  <para>
-        The clean-up routine unregisters the video_device we registered, and frees
-        up the I/O space. Note that the unregister takes the actual video_device
-        structure as its argument. Unlike the file operations structure which can be
-        shared by all instances of a device a video_device structure as an actual
-        instance of the device. If you are registering multiple radio devices you
-        need to fill in one structure per device (most likely by setting up a
-        template and copying it to each of the actual device structures).
-  </para>
-  </sect1>
-  </chapter>
-  <chapter id="Video_Capture_Devices">
-        <title>Video Capture Devices</title>
-  <sect1 id="introvid">
-  <title>Video Capture Device Types</title>
-  <para>
-        The video capture devices share the same interfaces as radio devices. In
-        order to explain the video capture interface I will use the example of a
-        camera that has no tuners or audio input. This keeps the example relatively
-        clean. To get both combine the two driver examples.
-  </para>
-  <para>
-        Video capture devices divide into four categories. A little technology
-        backgrounder. Full motion video even at television resolution (which is
-        actually fairly low) is pretty resource-intensive. You are continually
-        passing megabytes of data every second from the capture card to the display. 
-        several alternative approaches have emerged because copying this through the 
-        processor and the user program is a particularly bad idea .
-  </para>
-  <para>
-        The first is to add the television image onto the video output directly.
-        This is also how some 3D cards work. These basic cards can generally drop the
-        video into any chosen rectangle of the display. Cards like this, which
-        include most mpeg1 cards that used the feature connector,  aren't very
-        friendly in a windowing environment. They don't understand windows or
-        clipping. The video window is always on the top of the display.
-  </para>
-  <para>
-        Chroma keying is a technique used by cards to get around this. It is an old
-        television mixing trick where you mark all the areas you wish to replace
-        with a single clear colour that isn't used in the image - TV people use an
-        incredibly bright blue while computing people often use a particularly
-        virulent purple. Bright blue occurs on the desktop. Anyone with virulent
-        purple windows has another problem besides their TV overlay.
-  </para>
-  <para>
-        The third approach is to copy the data from the capture card to the video
-        card, but to do it directly across the PCI bus. This relieves the processor
-        from doing the work but does require some smartness on the part of the video
-        capture chip, as well as a suitable video card. Programming this kind of
-        card and more so debugging it can be extremely tricky. There are some quite
-        complicated interactions with the display and you may also have to cope with
-        various chipset bugs that show up when PCI cards start talking to each
-        other. 
-  </para>
-  <para>
-        To keep our example fairly simple we will assume a card that supports
-        overlaying a flat rectangular image onto the frame buffer output, and which
-        can also capture stuff into processor memory.
-  </para>
-  </sect1>
-  <sect1 id="regvid">
-  <title>Registering Video Capture Devices</title>
-  <para>
-        This time we need to add more functions for our camera device.
-  </para>
-  <programlisting>
-static struct video_device my_camera
-{
-        "My Camera",
-        VID_TYPE_OVERLAY|VID_TYPE_SCALES|\
-        VID_TYPE_CAPTURE|VID_TYPE_CHROMAKEY,
-        camera_open.
-        camera_close,
-        camera_read,      /* no read */
-        NULL,             /* no write */
-        camera_poll,      /* no poll */
-        camera_ioctl,
-        NULL,             /* no special init function */
-        NULL              /* no private data */
-};
-  </programlisting>
-  <para>
-        We need a read() function which is used for capturing data from
-        the card, and we need a poll function so that a driver can wait for the next
-        frame to be captured.
-  </para>
-  <para>
-        We use the extra video capability flags that did not apply to the
-        radio interface. The video related flags are
-  </para>
-   <table frame="all" id="Capture_Capabilities"><title>Capture Capabilities</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-<entry>VID_TYPE_CAPTURE</entry><entry>We support image capture</entry>
-</row><row>
-<entry>VID_TYPE_TELETEXT</entry><entry>A teletext capture device (vbi{n])</entry>
-</row><row>
-<entry>VID_TYPE_OVERLAY</entry><entry>The image can be directly overlaid onto the
-                                frame buffer</entry>
-</row><row>
-<entry>VID_TYPE_CHROMAKEY</entry><entry>Chromakey can be used to select which parts
-                                of the image to display</entry>
-</row><row>
-<entry>VID_TYPE_CLIPPING</entry><entry>It is possible to give the board a list of
-                                rectangles to draw around. </entry>
-</row><row>
-<entry>VID_TYPE_FRAMERAM</entry><entry>The video capture goes into the video memory
-                                and actually changes it. Applications need
-                                to know this so they can clean up after the
-                                card</entry>
-</row><row>
-<entry>VID_TYPE_SCALES</entry><entry>The image can be scaled to various sizes,
-                                rather than being a single fixed size.</entry>
-</row><row>
-<entry>VID_TYPE_MONOCHROME</entry><entry>The capture will be monochrome. This isn't a
-                                complete answer to the question since a mono
-                                camera on a colour capture card will still
-                                produce mono output.</entry>
-</row><row>
-<entry>VID_TYPE_SUBCAPTURE</entry><entry>The card allows only part of its field of
-                                view to be captured. This enables
-                                applications to avoid copying all of a large
-                                image into memory when only some section is
-                                relevant.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-  <para>
-        We set VID_TYPE_CAPTURE so that we are seen as a capture card,
-        VID_TYPE_CHROMAKEY so the application knows it is time to draw in virulent
-        purple, and VID_TYPE_SCALES because we can be resized.
-  </para>
-  <para>
-        Our setup is fairly similar. This time we also want an interrupt line
-        for the 'frame captured' signal. Not all cards have this so some of them
-        cannot handle poll().
-  </para>
-  <programlisting>
-static int io = 0x320;
-static int irq = 11;
-int __init mycamera_init(struct video_init *v)
-{
-        if(!request_region(io, MY_IO_SIZE, "mycamera"))
-        {
-                printk(KERN_ERR 
-                      "mycamera: port 0x%03X is in use.\n", io);
-                return -EBUSY;
-        }
-        if(video_device_register(&amp;my_camera, 
-            VFL_TYPE_GRABBER)==-1) {
-                release_region(io, MY_IO_SIZE);
-                return -EINVAL;
-        }
-        return 0;
-}
-  </programlisting>
-  <para>
-        This is little changed from the needs of the radio card. We specify
-        VFL_TYPE_GRABBER this time as we want to be allocated a /dev/video name.
-  </para>
-  </sect1>
-  <sect1 id="opvid">
-  <title>Opening And Closing The Capture Device</title>
-  <programlisting>
-static int users = 0;
-static int camera_open(struct video_device *dev, int flags)
-{
-        if(users)
-                return -EBUSY;
-        if(request_irq(irq, camera_irq, 0, "camera", dev)&lt;0)
-                return -EBUSY;
-        users++;
-        return 0;
-}
-static int camera_close(struct video_device *dev)
-{
-        users--;
-        free_irq(irq, dev);
-}
-  </programlisting>
-  <para>
-        The open and close routines are also quite similar. The only real change is
-        that we now request an interrupt for the camera device interrupt line. If we
-        cannot get the interrupt we report EBUSY to the application and give up.
-  </para>
-  </sect1>
-  <sect1 id="irqvid">
-  <title>Interrupt Handling</title>
-  <para>
-        Our example handler is for an ISA bus device. If it was PCI you would be
-        able to share the interrupt and would have set IRQF_SHARED to indicate a
-        shared IRQ. We pass the device pointer as the interrupt routine argument. We
-        don't need to since we only support one card but doing this will make it
-        easier to upgrade the driver for multiple devices in the future.
-  </para>
-  <para>
-        Our interrupt routine needs to do little if we assume the card can simply
-        queue one frame to be read after it captures it. 
-  </para>
-  <programlisting>
-static struct wait_queue *capture_wait;
-static int capture_ready = 0;
-static void camera_irq(int irq, void *dev_id, 
-                          struct pt_regs *regs)
-{
-        capture_ready=1;
-        wake_up_interruptible(&amp;capture_wait);
-}
-  </programlisting>
-  <para>
-        The interrupt handler is nice and simple for this card as we are assuming
-        the card is buffering the frame for us. This means we have little to do but
-        wake up        anybody interested. We also set a capture_ready flag, as we may
-        capture a frame before an application needs it. In this case we need to know
-        that a frame is ready. If we had to collect the frame on the interrupt life
-        would be more complex.
-  </para>
-  <para>
-        The two new routines we need to supply are camera_read which returns a
-        frame, and camera_poll which waits for a frame to become ready.
-  </para>
-  <programlisting>
-static int camera_poll(struct video_device *dev, 
-        struct file *file, struct poll_table *wait)
-{
-        poll_wait(file, &amp;capture_wait, wait);
-        if(capture_read)
-                return POLLIN|POLLRDNORM;
-        return 0;
-}
-  </programlisting>
-  <para>
-        Our wait queue for polling is the capture_wait queue. This will cause the
-        task to be woken up by our camera_irq routine. We check capture_read to see
-        if there is an image present and if so report that it is readable.
-  </para>
-  </sect1>
-  <sect1 id="rdvid">
-  <title>Reading The Video Image</title>
-  <programlisting>
-static long camera_read(struct video_device *dev, char *buf,
-                                unsigned long count)
-{
-        struct wait_queue wait = { current, NULL };
-        u8 *ptr;
-        int len;
-        int i;
-        add_wait_queue(&amp;capture_wait, &amp;wait);
-        while(!capture_ready)
-        {
-                if(file->flags&amp;O_NDELAY)
-                {
-                        remove_wait_queue(&amp;capture_wait, &amp;wait);
-                        current->state = TASK_RUNNING;
-                        return -EWOULDBLOCK;
-                }
-                if(signal_pending(current))
-                {
-                        remove_wait_queue(&amp;capture_wait, &amp;wait);
-                        current->state = TASK_RUNNING;
-                        return -ERESTARTSYS;
-                }
-                schedule();
-                current->state = TASK_INTERRUPTIBLE;
-        }
-        remove_wait_queue(&amp;capture_wait, &amp;wait);
-        current->state = TASK_RUNNING;
-  </programlisting>
-  <para>
-        The first thing we have to do is to ensure that the application waits until
-        the next frame is ready. The code here is almost identical to the mouse code
-        we used earlier in this chapter. It is one of the common building blocks of
-        Linux device driver code and probably one which you will find occurs in any
-        drivers you write.
-  </para>
-  <para>
-        We wait for a frame to be ready, or for a signal to interrupt our waiting. If a
-        signal occurs we need to return from the system call so that the signal can
-        be sent to the application itself. We also check to see if the user actually
-        wanted to avoid waiting - ie  if they are using non-blocking I/O and have other things 
-        to get on with.
-  </para>
-  <para>
-        Next we copy the data from the card to the user application. This is rarely
-        as easy as our example makes out. We will add capture_w, and capture_h here
-        to hold the width and height of the captured image. We assume the card only
-        supports 24bit RGB for now.
-  </para>
-  <programlisting>
-        capture_ready = 0;
-        ptr=(u8 *)buf;
-        len = capture_w * 3 * capture_h; /* 24bit RGB */
-        if(len>count)
-                len=count;  /* Doesn't all fit */
-        for(i=0; i&lt;len; i++)
-        {
-                put_user(inb(io+IMAGE_DATA), ptr);
-                ptr++;
-        }
-        hardware_restart_capture();
-                
-        return i;
-}
-  </programlisting>
-  <para>
-        For a real hardware device you would try to avoid the loop with put_user().
-        Each call to put_user() has a time overhead checking whether the accesses to user
-        space are allowed. It would be better to read a line into a temporary buffer
-        then copy this to user space in one go.
-  </para>
-  <para>
-        Having captured the image and put it into user space we can kick the card to
-        get the next frame acquired.
-  </para>
-  </sect1>
-  <sect1 id="iocvid">
-  <title>Video Ioctl Handling</title>
-  <para>
-        As with the radio driver the major control interface is via the ioctl()
-        function. Video capture devices support the same tuner calls as a radio
-        device and also support additional calls to control how the video functions
-        are handled. In this simple example the card has no tuners to avoid making
-        the code complex. 
-  </para>
-  <programlisting>
-static int camera_ioctl(struct video_device *dev, unsigned int cmd, void *arg)
-{
-        switch(cmd)
-        {
-                case VIDIOCGCAP:
-                {
-                        struct video_capability v;
-                        v.type = VID_TYPE_CAPTURE|\
-                                 VID_TYPE_CHROMAKEY|\
-                                 VID_TYPE_SCALES|\
-                                 VID_TYPE_OVERLAY;
-                        v.channels = 1;
-                        v.audios = 0;
-                        v.maxwidth = 640;
-                        v.minwidth = 16;
-                        v.maxheight = 480;
-                        v.minheight = 16;
-                        strcpy(v.name, "My Camera");
-                        if(copy_to_user(arg, &amp;v, sizeof(v)))
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        The first ioctl we must support and which all video capture and radio
-        devices are required to support is VIDIOCGCAP. This behaves exactly the same
-        as with a radio device. This time, however, we report the extra capabilities
-        we outlined earlier on when defining our video_dev structure.
-  </para>
-  <para>
-        We now set the video flags saying that we support overlay, capture,
-        scaling and chromakey. We also report size limits - our smallest image is
-        16x16 pixels, our largest is 640x480. 
-  </para>
-  <para>
-        To keep things simple we report no audio and no tuning capabilities at all.
-  </para>
-  <programlisting>        
-                case VIDIOCGCHAN:
-                {
-                        struct video_channel v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.channel != 0)
-                                return -EINVAL;
-                        v.flags = 0;
-                        v.tuners = 0;
-                        v.type = VIDEO_TYPE_CAMERA;
-                        v.norm = VIDEO_MODE_AUTO;
-                        strcpy(v.name, "Camera Input");break;
-                        if(copy_to_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        This follows what is very much the standard way an ioctl handler looks
-        in Linux. We copy the data into a kernel space variable and we check that the
-        request is valid (in this case that the input is 0). Finally we copy the
-        camera info back to the user.
-  </para>
-  <para>
-        The VIDIOCGCHAN ioctl allows a user to ask about video channels (that is
-        inputs to the video card). Our example card has a single camera input. The
-        fields in the structure are
-  </para>
-   <table frame="all" id="video_channel_fields"><title>struct video_channel fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-   <entry>channel</entry><entry>The channel number we are selecting</entry>
-   </row><row>
-   <entry>name</entry><entry>The name for this channel. This is intended
-                   to describe the port to the user.
-                   Appropriate names are therefore things like
-                   "Camera" "SCART input"</entry>
-   </row><row>
-   <entry>flags</entry><entry>Channel properties</entry>
-   </row><row>
-   <entry>type</entry><entry>Input type</entry>
-   </row><row>
-   <entry>norm</entry><entry>The current television encoding being used
-                   if relevant for this channel.
-    </entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <table frame="all" id="video_channel_flags"><title>struct video_channel flags</title>
-    <tgroup cols="2" align="left">
-    <tbody>
-    <row>
-        <entry>VIDEO_VC_TUNER</entry><entry>Channel has a tuner.</entry>
-   </row><row>
-        <entry>VIDEO_VC_AUDIO</entry><entry>Channel has audio.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <table frame="all" id="video_channel_types"><title>struct video_channel types</title>
-    <tgroup cols="2" align="left">
-    <tbody>
-    <row>
-        <entry>VIDEO_TYPE_TV</entry><entry>Television input.</entry>
-   </row><row>
-        <entry>VIDEO_TYPE_CAMERA</entry><entry>Fixed camera input.</entry>
-   </row><row>
-        <entry>0</entry><entry>Type is unknown.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <table frame="all" id="video_channel_norms"><title>struct video_channel norms</title>
-    <tgroup cols="2" align="left">
-    <tbody>
-    <row>
-        <entry>VIDEO_MODE_PAL</entry><entry>PAL encoded Television</entry>
-   </row><row>
-        <entry>VIDEO_MODE_NTSC</entry><entry>NTSC (US) encoded Television</entry>
-   </row><row>
-        <entry>VIDEO_MODE_SECAM</entry><entry>SECAM (French) Television </entry>
-   </row><row>
-        <entry>VIDEO_MODE_AUTO</entry><entry>Automatic switching, or format does not
-                                matter</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <para>
-        The corresponding VIDIOCSCHAN ioctl allows a user to change channel and to
-        request the norm is changed - for example to switch between a PAL or an NTSC
-        format camera.
-  </para>
-  <programlisting>
-                case VIDIOCSCHAN:
-                {
-                        struct video_channel v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.channel != 0)
-                                return -EINVAL;
-                        if(v.norm != VIDEO_MODE_AUTO)
-                                return -EINVAL;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        The implementation of this call in our driver is remarkably easy. Because we
-        are assuming fixed format hardware we need only check that the user has not
-        tried to change anything. 
-  </para>
-  <para>
-        The user also needs to be able to configure and adjust the picture they are
-        seeing. This is much like adjusting a television set. A user application
-        also needs to know the palette being used so that it knows how to display
-        the image that has been captured. The VIDIOCGPICT and VIDIOCSPICT ioctl
-        calls provide this information.
-  </para>
-  <programlisting>
-                case VIDIOCGPICT
-                {
-                        struct video_picture v;
-                        v.brightness = hardware_brightness();
-                        v.hue = hardware_hue();
-                        v.colour = hardware_saturation();
-                        v.contrast = hardware_brightness();
-                        /* Not settable */
-                        v.whiteness = 32768;
-                        v.depth = 24;           /* 24bit */
-                        v.palette = VIDEO_PALETTE_RGB24;
-                        if(copy_to_user(&amp;v, arg, 
-                             sizeof(v)))
-                                return -EFAULT;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        The brightness, hue, color, and contrast provide the picture controls that
-        are akin to a conventional television. Whiteness provides additional
-        control for greyscale images. All of these values are scaled between 0-65535
-        and have 32768 as the mid point setting. The scaling means that applications
-        do not have to worry about the capability range of the hardware but can let
-        it make a best effort attempt.
-  </para>
-  <para>
-        Our depth is 24, as this is in bits. We will be returning RGB24 format. This
-        has one byte of red, then one of green, then one of blue. This then repeats
-        for every other pixel in the image. The other common formats the interface 
-        defines are
-  </para>
-   <table frame="all" id="Framebuffer_Encodings"><title>Framebuffer Encodings</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-   <entry>GREY</entry><entry>Linear greyscale. This is for simple cameras and the
-                        like</entry>
-   </row><row>
-   <entry>RGB565</entry><entry>The top 5 bits hold 32 red levels, the next six bits
-                        hold green and the low 5 bits hold blue. </entry>
-   </row><row>
-   <entry>RGB555</entry><entry>The top bit is clear. The red green and blue levels
-                        each occupy five bits.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-  <para>
-        Additional modes are support for YUV capture formats. These are common for
-        TV and video conferencing applications.
-  </para>
-  <para>
-        The VIDIOCSPICT ioctl allows a user to set some of the picture parameters.
-        Exactly which ones are supported depends heavily on the card itself. It is
-        possible to support many modes and effects in software. In general doing
-        this in the kernel is a bad idea. Video capture is a performance-sensitive
-        application and the programs can often do better if they aren't being
-        'helped' by an overkeen driver writer. Thus for our device we will report
-        RGB24 only and refuse to allow a change.
-  </para>
-  <programlisting>
-                case VIDIOCSPICT:
-                {
-                        struct video_picture v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.depth!=24 || 
-                           v.palette != VIDEO_PALETTE_RGB24)
-                                return -EINVAL;
-                        set_hardware_brightness(v.brightness);
-                        set_hardware_hue(v.hue);
-                        set_hardware_saturation(v.colour);
-                        set_hardware_brightness(v.contrast);
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        We check the user has not tried to change the palette or the depth. We do
-        not want to carry out some of the changes and then return an error. This may
-        confuse the application which will be assuming no change occurred.
-  </para>
-  <para>
-        In much the same way as you need to be able to set the picture controls to
-        get the right capture images, many cards need to know what they are
-        displaying onto when generating overlay output. In some cases getting this
-        wrong even makes a nasty mess or may crash the computer. For that reason
-        the VIDIOCSBUF ioctl used to set up the frame buffer information may well
-        only be usable by root.
-  </para>
-  <para>
-        We will assume our card is one of the old ISA devices with feature connector
-        and only supports a couple of standard video modes. Very common for older
-        cards although the PCI devices are way smarter than this.
-  </para>
-  <programlisting>
-static struct video_buffer capture_fb;
-                case VIDIOCGFBUF:
-                {
-                        if(copy_to_user(arg, &amp;capture_fb, 
-                             sizeof(capture_fb)))
-                                return -EFAULT;
-                        return 0;
-                        
-                }
-  </programlisting>
-  <para>
-        We keep the frame buffer information in the format the ioctl uses. This
-        makes it nice and easy to work with in the ioctl calls.
-  </para>
-  <programlisting>
-                case VIDIOCSFBUF:
-                {
-                        struct video_buffer v;
-                        if(!capable(CAP_SYS_ADMIN))
-                                return -EPERM;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.width!=320 &amp;&amp; v.width!=640)
-                                return -EINVAL;
-                        if(v.height!=200 &amp;&amp; v.height!=240 
-                                &amp;&amp; v.height!=400
-                                &amp;&amp; v.height !=480)
-                                return -EINVAL;
-                        memcpy(&amp;capture_fb, &amp;v, sizeof(v));
-                        hardware_set_fb(&amp;v);
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        The capable() function checks a user has the required capability. The Linux
-        operating system has a set of about 30 capabilities indicating privileged
-        access to services. The default set up gives the superuser (uid 0) all of
-        them and nobody else has any.
-  </para>
-  <para>
-        We check that the user has the SYS_ADMIN capability, that is they are
-        allowed to operate as the machine administrator. We don't want anyone but
-        the administrator making a mess of the display.
-  </para>
-  <para>
-        Next we check for standard PC video modes (320 or 640 wide with either
-        EGA or VGA depths). If the mode is not a standard video mode we reject it as
-        not supported by our card. If the mode is acceptable we save it so that
-        VIDIOCFBUF will give the right answer next time it is called.  The
-        hardware_set_fb() function is some undescribed card specific function to
-        program the card for the desired mode.
-  </para>
-  <para>
-        Before the driver can display an overlay window it needs to know where the
-        window should be placed, and also how large it should be. If the card
-        supports clipping it needs to know which rectangles to omit from the
-        display. The video_window structure is used to describe the way the image 
-        should be displayed. 
-   </para>
-   <table frame="all" id="video_window_fields"><title>struct video_window fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-        <entry>width</entry><entry>The width in pixels of the desired image. The card
-                        may use a smaller size if this size is not available</entry>
-        </row><row>
-        <entry>height</entry><entry>The height of the image. The card may use a smaller
-                        size if this size is not available.</entry>
-        </row><row>
-        <entry>x</entry><entry>   The X position of the top left of the window. This
-                        is in pixels relative to the left hand edge of the
-                        picture. Not all cards can display images aligned on
-                        any pixel boundary. If the position is unsuitable
-                        the card adjusts the image right and reduces the
-                        width.</entry>
-        </row><row>
-        <entry>y</entry><entry>   The Y position of the top left of the window. This
-                        is counted in pixels relative to the top edge of the
-                        picture. As with the width if the card cannot
-                        display  starting on this line it will adjust the
-                        values.</entry>
-        </row><row>
-        <entry>chromakey</entry><entry>The colour (expressed in RGB32 format) for the
-                        chromakey colour if chroma keying is being used. </entry>
-        </row><row>
-        <entry>clips</entry><entry>An array of rectangles that must not be drawn
-                        over.</entry>
-        </row><row>
-        <entry>clipcount</entry><entry>The number of clips in this array.</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <para>
-        Each clip is a struct video_clip which has the following fields
-   </para>
-   <table frame="all" id="video_clip_fields"><title>video_clip fields</title>
-   <tgroup cols="2" align="left">
-   <tbody>
-   <row>
-        <entry>x, y</entry><entry>Co-ordinates relative to the display</entry>
-        </row><row>
-        <entry>width, height</entry><entry>Width and height in pixels</entry>
-        </row><row>
-        <entry>next</entry><entry>A spare field for the application to use</entry>
-    </row>
-    </tbody>
-    </tgroup>
-    </table>
-    <para>
-        The driver is required to ensure it always draws in the area requested or a        smaller area, and that it never draws in any of the areas that are clipped.
-        This may well mean it has to leave alone. small areas the application wished to be
-        drawn.
-  </para>
-  <para>
-        Our example card uses chromakey so does not have to address most of the
-        clipping.  We will add a video_window structure to our global variables to
-        remember our parameters, as we did with the frame buffer.
-  </para>
-  <programlisting>
-                case VIDIOCGWIN:
-                {
-                        if(copy_to_user(arg, &amp;capture_win, 
-                            sizeof(capture_win)))
-                                return -EFAULT;
-                        return 0;
-                }
-                case VIDIOCSWIN:
-                {
-                        struct video_window v;
-                        if(copy_from_user(&amp;v, arg, sizeof(v)))
-                                return -EFAULT;
-                        if(v.width &gt; 640 || v.height &gt; 480)
-                                return -EINVAL;
-                        if(v.width &lt; 16 || v.height &lt; 16)
-                                return -EINVAL;
-                        hardware_set_key(v.chromakey);
-                        hardware_set_window(v);
-                        memcpy(&amp;capture_win, &amp;v, sizeof(v));
-                        capture_w = v.width;
-                        capture_h = v.height;
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        Because we are using Chromakey our setup is fairly simple. Mostly we have to
-        check the values are sane and load them into the capture card.
-  </para>
-  <para>
-        With all the setup done we can now turn on the actual capture/overlay. This
-        is done with the VIDIOCCAPTURE ioctl. This takes a single integer argument
-        where 0 is on and 1 is off.
-  </para>
-  <programlisting>
-                case VIDIOCCAPTURE:
-                {
-                        int v;
-                        if(get_user(v, (int *)arg))
-                                return -EFAULT;
-                        if(v==0)
-                                hardware_capture_off();
-                        else
-                        {
-                                if(capture_fb.width == 0 
-                                    || capture_w == 0)
-                                        return -EINVAL;
-                                hardware_capture_on();
-                        }
-                        return 0;
-                }
-  </programlisting>
-  <para>
-        We grab the flag from user space and either enable or disable according to
-        its value. There is one small corner case we have to consider here. Suppose
-        that the capture was requested before the video window or the frame buffer
-        had been set up. In those cases there will be unconfigured fields in our
-        card data, as well as unconfigured hardware settings. We check for this case and
-        return an error if the frame buffer or the capture window width is zero.
-  </para>
-  <programlisting>
-                default:
-                        return -ENOIOCTLCMD;
-        }
-}
-  </programlisting>
-  <para>
-        We don't need to support any other ioctls, so if we get this far, it is time
-        to tell the video layer that we don't now what the user is talking about.
-  </para>
-  </sect1>
-  <sect1 id="endvid">
-  <title>Other Functionality</title>
-  <para>
-        The Video4Linux layer supports additional features, including a high
-        performance mmap() based capture mode and capturing part of the image. 
-        These features are out of the scope of the book.  You should however have enough 
-        example code to implement most simple video4linux devices for radio and TV
-        cards.
-  </para>
-  </sect1>
-  </chapter>
-  <chapter id="bugs">
-     <title>Known Bugs And Assumptions</title>
-  <para>
-  <variablelist>
-    <varlistentry><term>Multiple Opens</term>
-    <listitem>
-    <para>
-        The driver assumes multiple opens should not be allowed. A driver
-        can work around this but not cleanly.
-    </para>
-    </listitem></varlistentry>
-    <varlistentry><term>API Deficiencies</term>
-    <listitem>
-    <para>
-        The existing API poorly reflects compression capable devices. There
-        are plans afoot to merge V4L, V4L2 and some other ideas into a
-        better interface.
-    </para>
-    </listitem></varlistentry>
-  </variablelist>
-  </para>
-  </chapter>
-  <chapter id="pubfunctions">
-     <title>Public Functions Provided</title>
-!Edrivers/media/video/videodev.c
-  </chapter>
-</book>
diff --git a/Documentation/DocBook/z8530book.tmpl b/Documentation/DocBook/z8530book.tmpl
index 42c75ba71ba2..a42a8a4c7689 100644
--- a/Documentation/DocBook/z8530book.tmpl
+++ b/Documentation/DocBook/z8530book.tmpl
@@ -69,12 +69,6 @@
        device to be used as both a tty interface and as a synchronous 
        controller is a project for Linux post the 2.4 release
  </para>
-  <para>
-        The support code handles most common card configurations and
-        supports running both Cisco HDLC and Synchronous PPP. With extra
-        glue the frame relay and X.25 protocols can also be used with this
-        driver.
-  </para>
  </chapter>
  
  <chapter id="Driver_Modes">
@@ -179,35 +173,27 @@
  <para>
        If you wish to use the network interface facilities of the driver,
        then you need to attach a network device to each channel that is
-        present and in use. In addition to use the SyncPPP and Cisco HDLC
+        present and in use. In addition to use the generic HDLC
        you need to follow some additional plumbing rules. They may seem 
        complex but a look at the example hostess_sv11 driver should
        reassure you.
  </para>
  <para>
        The network device used for each channel should be pointed to by
-        the netdevice field of each channel. The dev-&gt; priv field of the
+        the netdevice field of each channel. The hdlc-&gt; priv field of the
        network device points to your private data - you will need to be
-        able to find your ppp device from this. In addition to use the
+        able to find your private data from this.
-        sync ppp layer the private data must start with a void * pointer
-        to the syncppp structures.
  </para>
  <para>
        The way most drivers approach this particular problem is to
        create a structure holding the Z8530 device definition and
-        put that and the syncppp pointer into the private field of
+        put that into the private field of the network device. The
-        the network device. The network device fields of the channels
+        network device fields of the channels then point back to the
-        then point back to the network devices. The ppp_device can also
+        network devices.
-        be put in the private structure conveniently.
  </para>
  <para>
-        If you wish to use the synchronous ppp then you need to attach
+        If you wish to use the generic HDLC then you need to register
-        the syncppp layer to the network device. You should do this before
+        the HDLC device.
-        you register the network device. The
-        <function>sppp_attach</function> requires that the first void *
-        pointer in your private data is pointing to an empty struct
-        ppp_device. The function fills in the initial data for the
-        ppp/hdlc layer.
  </para>
  <para>
        Before you register your network device you will also need to
@@ -314,10 +300,10 @@
        buffer in sk_buff format and queues it for transmission. The
        caller must provide the entire packet with the exception of the
        bitstuffing and CRC. This is normally done by the caller via
-        the syncppp interface layer. It returns 0 if the buffer has been 
+        the generic HDLC interface layer. It returns 0 if the buffer has been
-        queued and non zero values  for queue full. If the function accepts 
+        queued and non zero values for queue full. If the function accepts
-        the buffer it becomes property of the Z8530 layer and the caller 
+        the buffer it becomes property of the Z8530 layer and the caller
-        should not free it. 
+        should not free it.
  </para>
  <para>
        The function <function>z8530_get_stats</function> returns a pointer
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 619e8caf30db..8495fc970391 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -77,7 +77,8 @@ documentation files are also added which explain how to use the feature.
 When a kernel change causes the interface that the kernel exposes to
 userspace to change, it is recommended that you send the information or
 a patch to the manual pages explaining the change to the manual pages
-maintainer at mtk.manpages@gmail.com.
+maintainer at mtk.manpages@gmail.com, and CC the list
+linux-api@vger.kernel.org.
 Here is a list of files that are in the kernel source tree that are
 required reading:
@@ -111,7 +112,7 @@ required reading:
    Other excellent descriptions of how to create patches properly are:
        "The Perfect Patch"
-                http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt
+                http://userweb.kernel.org/~akpm/stuff/tpp.txt
        "Linux kernel patch submission format"
                http://linux.yyz.us/patch-format.html
@@ -358,7 +359,7 @@ Here is a list of some of the different kernel trees available:
    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
        git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-    - SCSI, James Bottomley <James.Bottomley@SteelEye.com>
+    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
        git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
    - x86, Ingo Molnar <mingo@elte.hu>
@@ -619,7 +620,7 @@ all time.  It should describe the patch completely, containing:
 For more details on what this should all look like, please see the
 ChangeLog section of the document:
  "The Perfect Patch"
-      http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt
+      http://userweb.kernel.org/~akpm/stuff/tpp.txt
diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt
index c2321903aa09..21bc416d887e 100644
--- a/Documentation/Intel-IOMMU.txt
+++ b/Documentation/Intel-IOMMU.txt
@@ -48,7 +48,7 @@ IOVA generation is pretty generic. We used the same technique as vmalloc()
 but these are not global address spaces, but separate for each domain.
 Different DMA engines may support different number of domains.
-We also allocate gaurd pages with each mapping, so we can attempt to catch
+We also allocate guard pages with each mapping, so we can attempt to catch
 any overflow that might happen.
@@ -112,4 +112,4 @@ TBD
 - For compatibility testing, could use unity map domain for all devices, just
  provide a 1-1 for all useful memory under a single domain for all devices.
- API for paravirt ops for abstracting functionlity for VMM folks.
+- API for paravirt ops for abstracting functionality for VMM folks.
diff --git a/Documentation/MSI-HOWTO.txt b/Documentation/MSI-HOWTO.txt
index a51f693c1541..256defd7e174 100644
--- a/Documentation/MSI-HOWTO.txt
+++ b/Documentation/MSI-HOWTO.txt
@@ -236,10 +236,8 @@ software system can set different pages for controlling accesses to the
 MSI-X structure. The implementation of MSI support requires the PCI
 subsystem, not a device driver, to maintain full control of the MSI-X
 table/MSI-X PBA (Pending Bit Array) and MMIO address space of the MSI-X
-table/MSI-X PBA.  A device driver is prohibited from requesting the MMIO
+table/MSI-X PBA.  A device driver should not access the MMIO address
-address space of the MSI-X table/MSI-X PBA. Otherwise, the PCI subsystem
+space of the MSI-X table/MSI-X PBA.
-will fail enabling MSI-X on its hardware device when it calls the function
-pci_enable_msix().
 5.3.2 API pci_enable_msix
diff --git a/Documentation/Makefile b/Documentation/Makefile
new file mode 100644
index 000000000000..94b945733534
--- /dev/null
+++ b/Documentation/Makefile
@@ -0,0 +1,3 @@
+obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
+        filesystems/configfs/ ia64/ networking/ \
+        pcmcia/ spi/ video4linux/ vm/ watchdog/src/
diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt
index 8d4dc6250c58..fd4907a2968c 100644
--- a/Documentation/PCI/pci.txt
+++ b/Documentation/PCI/pci.txt
@@ -163,6 +163,10 @@ need pass only as many optional fields as necessary:
        o class and classmask fields default to 0
        o driver_data defaults to 0UL.
+Note that driver_data must match the value used by any of the pci_device_id
+entries defined in the driver. This makes the driver_data field mandatory
+if all the pci_device_id entries have a non-zero driver_data value.
 Once added, the driver probe routine will be invoked for any unclaimed
 PCI devices listed in its (newly updated) pci_ids list.
diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt
index 16c251230c82..ddeb14beacc8 100644
--- a/Documentation/PCI/pcieaer-howto.txt
+++ b/Documentation/PCI/pcieaer-howto.txt
@@ -203,22 +203,17 @@ to mmio_enabled.
 3.3 helper functions
-3.3.1 int pci_find_aer_capability(struct pci_dev *dev);
+3.3.1 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
-pci_find_aer_capability locates the PCI Express AER capability
-in the device configuration space. If the device doesn't support
-PCI-Express AER, the function returns 0.
-3.3.2 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
 pci_enable_pcie_error_reporting enables the device to send error
 messages to root port when an error is detected. Note that devices
 don't enable the error reporting by default, so device drivers need
 call this function to enable it.
-3.3.3 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
+3.3.2 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 pci_disable_pcie_error_reporting disables the device to send error
 messages to root port when an error is detected.
-3.3.4 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
+3.3.3 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
 pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
 error status register.
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index cf5562cbe356..6e253407b3dc 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -210,7 +210,7 @@ over a rather long period of time, but improvements are always welcome!
                number of updates per grace period.
 9.      All RCU list-traversal primitives, which include
-        rcu_dereference(), list_for_each_rcu(), list_for_each_entry_rcu(),
+        rcu_dereference(), list_for_each_entry_rcu(),
        list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
        must be either within an RCU read-side critical section or
        must be protected by appropriate update-side locks.  RCU
diff --git a/Documentation/RCU/rcuref.txt b/Documentation/RCU/rcuref.txt
index 451de2ad8329..4202ad093130 100644
--- a/Documentation/RCU/rcuref.txt
+++ b/Documentation/RCU/rcuref.txt
@@ -29,9 +29,9 @@ release_referenced()			delete()
                                        }
 If this list/array is made lock free using RCU as in changing the
-write_lock() in add() and delete() to spin_lock and changing read_lock
+write_lock() in add() and delete() to spin_lock() and changing read_lock()
-in search_and_reference to rcu_read_lock(), the atomic_get in
+in search_and_reference() to rcu_read_lock(), the atomic_inc() in
-search_and_reference could potentially hold reference to an element which
+search_and_reference() could potentially hold reference to an element which
 has already been deleted from the list/array.  Use atomic_inc_not_zero()
 in this scenario as follows:
@@ -40,20 +40,20 @@ add()					search_and_reference()
 {                                       {
    alloc_object                            rcu_read_lock();
    ...                                     search_for_element
-    atomic_set(&el->rc, 1);                 if (atomic_inc_not_zero(&el->rc)) {
+    atomic_set(&el->rc, 1);                 if (!atomic_inc_not_zero(&el->rc)) {
-    write_lock(&list_lock);                     rcu_read_unlock();
+    spin_lock(&list_lock);                      rcu_read_unlock();
                                                return FAIL;
    add_element                             }
    ...                                     ...
-    write_unlock(&list_lock);               rcu_read_unlock();
+    spin_unlock(&list_lock);                rcu_read_unlock();
 }                                       }
 3.                                      4.
 release_referenced()                    delete()
 {                                       {
-    ...                                     write_lock(&list_lock);
+    ...                                     spin_lock(&list_lock);
    if (atomic_dec_and_test(&el->rc))       ...
        call_rcu(&el->head, el_free);       delete_element
-    ...                                     write_unlock(&list_lock);
+    ...                                     spin_unlock(&list_lock);
 }                                           ...
                                            if (atomic_dec_and_test(&el->rc))
                                                call_rcu(&el->head, el_free);
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index e04d643a9f57..96170824a717 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -786,8 +786,6 @@ RCU pointer/list traversal:
        list_for_each_entry_rcu
        hlist_for_each_entry_rcu
-        list_for_each_rcu               (to be deprecated in favor of
-                                         list_for_each_entry_rcu)
        list_for_each_continue_rcu      (to be deprecated in favor of new
                                         list_for_each_entry_continue_rcu)
diff --git a/Documentation/SAK.txt b/Documentation/SAK.txt
index b9019ca872ea..74be14679ed8 100644
--- a/Documentation/SAK.txt
+++ b/Documentation/SAK.txt
@@ -1,5 +1,5 @@
 Linux 2.4.2 Secure Attention Key (SAK) handling
-18 March 2001, Andrew Morton <akpm@osdl.org>
+18 March 2001, Andrew Morton
 An operating system's Secure Attention Key is a security tool which is
 provided as protection against trojan password capturing programs.  It
diff --git a/Documentation/SELinux.txt b/Documentation/SELinux.txt
new file mode 100644
index 000000000000..07eae00f3314
--- /dev/null
+++ b/Documentation/SELinux.txt
@@ -0,0 +1,27 @@
+If you want to use SELinux, chances are you will want
+to use the distro-provided policies, or install the
+latest reference policy release from
+        http://oss.tresys.com/projects/refpolicy
+However, if you want to install a dummy policy for
+testing, you can do using 'mdp' provided under
+scripts/selinux.  Note that this requires the selinux
+userspace to be installed - in particular you will
+need checkpolicy to compile a kernel, and setfiles and
+fixfiles to label the filesystem.
+        1. Compile the kernel with selinux enabled.
+        2. Type 'make' to compile mdp.
+        3. Make sure that you are not running with
+           SELinux enabled and a real policy.  If
+           you are, reboot with selinux disabled
+           before continuing.
+        4. Run install_policy.sh:
+                cd scripts/selinux
+                sh install_policy.sh
+Step 4 will create a new dummy policy valid for your
+kernel, with a single selinux user, role, and type.
+It will compile the policy, will set your SELINUXTYPE to
+dummy in /etc/selinux/config, install the compiled policy
+as 'dummy', and relabel your filesystem.
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index da10e0714241..ac5e0b2f1097 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -67,6 +67,8 @@ kernel patches.
 19: All new userspace interfaces are documented in Documentation/ABI/.
    See Documentation/ABI/README for more information.
+    Patches that change userspace interfaces should be CCed to
+    linux-api@vger.kernel.org.
 20: Check that it all passes `make headers_check'.
@@ -83,3 +85,6 @@ kernel patches.
 23: Tested after it has been merged into the -mm patchset to make sure
    that it still works with all of the other queued patches and various
    changes in the VM, VFS, and other subsystems.
+24: All memory barriers {e.g., barrier(), rmb(), wmb()} need a comment in the
+    source code that explains the logic of what they are doing and why.
diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers
index 24f2eb40cae5..99e72a81fa2f 100644
--- a/Documentation/SubmittingDrivers
+++ b/Documentation/SubmittingDrivers
@@ -41,7 +41,7 @@ Linux 2.4:
 Linux 2.6:
        The same rules apply as 2.4 except that you should follow linux-kernel
        to track changes in API's. The final contact point for Linux 2.6
-        submissions is Andrew Morton <akpm@osdl.org>.
+        submissions is Andrew Morton.
 What Criteria Determine Acceptance
 ----------------------------------
diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 118ca6e9404f..f309d3c6221c 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -77,7 +77,7 @@ Quilt:
 http://savannah.nongnu.org/projects/quilt
 Andrew Morton's patch scripts:
-http://www.zip.com.au/~akpm/linux/patches/
+http://userweb.kernel.org/~akpm/stuff/patch-scripts.tar.gz
 Instead of these scripts, quilt is the recommended patch management
 tool (see above).
@@ -405,7 +405,7 @@ person it names.  This tag documents that potentially interested parties
 have been included in the discussion
-14) Using Test-by: and Reviewed-by:
+14) Using Tested-by: and Reviewed-by:
 A Tested-by: tag indicates that the patch has been successfully tested (in
 some environment) by the person named.  This tag informs maintainers that
@@ -528,7 +528,33 @@ See more details on the proper patch format in the following
 references.
+16) Sending "git pull" requests  (from Linus emails)
+Please write the git repo address and branch name alone on the same line
+so that I can't even by mistake pull from the wrong branch, and so
+that a triple-click just selects the whole thing.
+So the proper format is something along the lines of:
+        "Please pull from
+                git://jdelvare.pck.nerim.net/jdelvare-2.6 i2c-for-linus
+         to get these changes:"
+so that I don't have to hunt-and-peck for the address and inevitably
+get it wrong (actually, I've only gotten it wrong a few times, and
+checking against the diffstat tells me when I get it wrong, but I'm
+just a lot more comfortable when I don't have to "look for" the right
+thing to pull, and double-check that I have the right branch-name).
+Please use "git diff -M --stat --summary" to generate the diffstat:
+the -M enables rename detection, and the summary enables a summary of
+new/deleted or renamed files.
+With rename detection, the statistics are rather different [...]
+because git will notice that a fair number of the changes are renames.
 -----------------------------------
 SECTION 2 - HINTS, TIPS, AND TRICKS
@@ -627,7 +653,7 @@ SECTION 3 - REFERENCES
 ----------------------
 Andrew Morton, "The perfect patch" (tpp).
-  <http://www.zip.com.au/~akpm/linux/patches/stuff/tpp.txt>
+  <http://userweb.kernel.org/~akpm/stuff/tpp.txt>
 Jeff Garzik, "Linux kernel patch submission format".
  <http://linux.yyz.us/patch-format.html>
@@ -646,4 +672,9 @@ Kernel Documentation/CodingStyle:
 Linus Torvalds's mail on the canonical patch format:
  <http://lkml.org/lkml/2005/4/7/183>
+Andi Kleen, "On submitting kernel patches"
+  Some strategies to get difficult or controversal changes in.
+  http://halobates.de/on-submitting-patches.pdf
 --
diff --git a/Documentation/accounting/Makefile b/Documentation/accounting/Makefile
new file mode 100644
index 000000000000..31929eb875b1
--- /dev/null
+++ b/Documentation/accounting/Makefile
@@ -0,0 +1,10 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := getdelays
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_getdelays.o += -I$(objtree)/usr/include
diff --git a/Documentation/accounting/delay-accounting.txt b/Documentation/accounting/delay-accounting.txt
index 1443cd71d263..8a12f0730c94 100644
--- a/Documentation/accounting/delay-accounting.txt
+++ b/Documentation/accounting/delay-accounting.txt
@@ -11,6 +11,7 @@ the delays experienced by a task while
 a) waiting for a CPU (while being runnable)
 b) completion of synchronous block I/O initiated by the task
 c) swapping in pages
+d) memory reclaim
 and makes these statistics available to userspace through
 the taskstats interface.
@@ -41,7 +42,7 @@ this structure. See
     include/linux/taskstats.h
 for a description of the fields pertaining to delay accounting.
 It will generally be in the form of counters returning the cumulative
-delay seen for cpu, sync block I/O, swapin etc.
+delay seen for cpu, sync block I/O, swapin, memory reclaim etc.
 Taking the difference of two successive readings of a given
 counter (say cpu_delay_total) for a task will give the delay
@@ -94,7 +95,9 @@ CPU	count	real total	virtual total	delay total
        7876    92005750        100000000       24001500
 IO      count   delay total
        0       0
-MEM     count   delay total
+SWAP    count   delay total
+        0       0
+RECLAIM count   delay total
        0       0
 Get delays seen in executing a given simple command
@@ -108,5 +111,7 @@ CPU	count	real total	virtual total	delay total
        6       4000250         4000000         0
 IO      count   delay total
        0       0
-MEM     count   delay total
+SWAP    count   delay total
+        0       0
+RECLAIM count   delay total
        0       0
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index 40121b5cca14..cc49400b4af8 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -196,14 +196,24 @@ void print_delayacct(struct taskstats *t)
               "      %15llu%15llu%15llu%15llu\n"
               "IO    %15s%15s\n"
               "      %15llu%15llu\n"
-               "MEM   %15s%15s\n"
+               "SWAP  %15s%15s\n"
+               "      %15llu%15llu\n"
+               "RECLAIM  %12s%15s\n"
               "      %15llu%15llu\n",
               "count", "real total", "virtual total", "delay total",
-               t->cpu_count, t->cpu_run_real_total, t->cpu_run_virtual_total,
+               (unsigned long long)t->cpu_count,
-               t->cpu_delay_total,
+               (unsigned long long)t->cpu_run_real_total,
+               (unsigned long long)t->cpu_run_virtual_total,
+               (unsigned long long)t->cpu_delay_total,
+               "count", "delay total",
+               (unsigned long long)t->blkio_count,
+               (unsigned long long)t->blkio_delay_total,
+               "count", "delay total",
+               (unsigned long long)t->swapin_count,
+               (unsigned long long)t->swapin_delay_total,
               "count", "delay total",
-               t->blkio_count, t->blkio_delay_total,
+               (unsigned long long)t->freepages_count,
-               "count", "delay total", t->swapin_count, t->swapin_delay_total);
+               (unsigned long long)t->freepages_delay_total);
 }
 void task_context_switch_counts(struct taskstats *t)
@@ -211,14 +221,17 @@ void task_context_switch_counts(struct taskstats *t)
        printf("\n\nTask   %15s%15s\n"
               "       %15llu%15llu\n",
               "voluntary", "nonvoluntary",
-               t->nvcsw, t->nivcsw);
+               (unsigned long long)t->nvcsw, (unsigned long long)t->nivcsw);
 }
 void print_cgroupstats(struct cgroupstats *c)
 {
        printf("sleeping %llu, blocked %llu, running %llu, stopped %llu, "
-                "uninterruptible %llu\n", c->nr_sleeping, c->nr_io_wait,
+                "uninterruptible %llu\n", (unsigned long long)c->nr_sleeping,
-                c->nr_running, c->nr_stopped, c->nr_uninterruptible);
+                (unsigned long long)c->nr_io_wait,
+                (unsigned long long)c->nr_running,
+                (unsigned long long)c->nr_stopped,
+                (unsigned long long)c->nr_uninterruptible);
 }
diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index cd784f46bf8a..e7512c061c15 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/Documentation/accounting/taskstats-struct.txt
@@ -6,7 +6,7 @@ This document contains an explanation of the struct taskstats fields.
 There are three different groups of fields in the struct taskstats:
 1) Common and basic accounting fields
-    If CONFIG_TASKSTATS is set, the taskstats inteface is enabled and
+    If CONFIG_TASKSTATS is set, the taskstats interface is enabled and
    the common fields and basic accounting fields are collected for
    delivery at do_exit() of a task.
 2) Delay accounting fields
@@ -26,6 +26,8 @@ There are three different groups of fields in the struct taskstats:
 5) Time accounting for SMT machines
+6) Extended delay accounting fields for memory reclaim
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
@@ -170,4 +172,9 @@ struct taskstats {
        __u64   ac_utimescaled;         /* utime scaled on frequency etc */
        __u64   ac_stimescaled;         /* stime scaled on frequency etc */
        __u64   cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
+6) Extended delay accounting fields for memory reclaim
+        /* Delay waiting for memory reclaim */
+        __u64   freepages_count;
+        __u64   freepages_delay_total;
 }
diff --git a/Documentation/arm/IXP4xx b/Documentation/arm/IXP4xx
index 43edb4ecf27d..72fbcc4fcab0 100644
--- a/Documentation/arm/IXP4xx
+++ b/Documentation/arm/IXP4xx
@@ -32,7 +32,7 @@ Linux currently supports the following features on the IXP4xx chips:
 - Flash access (MTD/JFFS)
 - I2C through GPIO on IXP42x
 - GPIO for input/output/interrupts 
-  See include/asm-arm/arch-ixp4xx/platform.h for access functions.
+  See arch/arm/mach-ixp4xx/include/mach/platform.h for access functions.
 - Timers (watchdog, OS)
 The following components of the chips are not supported by Linux and
diff --git a/Documentation/arm/Interrupts b/Documentation/arm/Interrupts
index 0d3dbf1099bc..f09ab1b90ef1 100644
--- a/Documentation/arm/Interrupts
+++ b/Documentation/arm/Interrupts
@@ -138,14 +138,8 @@ So, what's changed?
                Set active the IRQ edge(s)/level.  This replaces the
                SA1111 INTPOL manipulation, and the set_GPIO_IRQ_edge()
-                function.  Type should be one of the following:
+                function.  Type should be one of IRQ_TYPE_xxx defined in
+                <linux/irq.h>
-                #define IRQT_NOEDGE     (0)
-                #define IRQT_RISING     (__IRQT_RISEDGE)
-                #define IRQT_FALLING    (__IRQT_FALEDGE)
-                #define IRQT_BOTHEDGE   (__IRQT_RISEDGE|__IRQT_FALEDGE)
-                #define IRQT_LOW        (__IRQT_LOWLVL)
-                #define IRQT_HIGH       (__IRQT_HIGHLVL)
 3. set_GPIO_IRQ_edge() is obsolete, and should be replaced by set_irq_type.
@@ -164,7 +158,7 @@ So, what's changed?
   be re-checked for pending events.  (see the Neponset IRQ handler for
   details).
-7. fixup_irq() is gone, as is include/asm-arm/arch-*/irq.h
+7. fixup_irq() is gone, as is arch/arm/mach-*/include/mach/irq.h
 Please note that this will not solve all problems - some of them are
 hardware based.  Mixing level-based and edge-based IRQs on the same
diff --git a/Documentation/arm/README b/Documentation/arm/README
index 9b9c8226fdc4..d98783fbe0c7 100644
--- a/Documentation/arm/README
+++ b/Documentation/arm/README
@@ -79,7 +79,7 @@ Machine/Platform support
  To this end, we now have arch/arm/mach-$(MACHINE) directories which are
  designed to house the non-driver files for a particular machine (eg, PCI,
  memory management, architecture definitions etc).  For all future
-  machines, there should be a corresponding include/asm-arm/arch-$(MACHINE)
+  machines, there should be a corresponding arch/arm/mach-$(MACHINE)/include/mach
  directory.
@@ -176,7 +176,7 @@ Kernel entry (head.S)
  class typically based around one or more system on a chip devices, and
  acts as a natural container around the actual implementations.  These
  classes are given directories - arch/arm/mach-<class> and
-  include/asm-arm/arch-<class> - which contain the source files to
+  arch/arm/mach-<class> - which contain the source files to/include/mach
  support the machine class.  This directories also contain any machine
  specific supporting code.
diff --git a/Documentation/arm/Samsung-S3C24XX/GPIO.txt b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
index 8caea8c237ee..ea7ccfc4b274 100644
--- a/Documentation/arm/Samsung-S3C24XX/GPIO.txt
+++ b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
@@ -13,16 +13,31 @@ Introduction
  data-sheet/users manual to find out the complete list.
+GPIOLIB
+-------
+  With the event of the GPIOLIB in drivers/gpio, support for some
+  of the GPIO functions such as reading and writing a pin will
+  be removed in favour of this common access method.
+  Once all the extant drivers have been converted, the functions
+  listed below will be removed (they may be marked as __deprecated
+  in the near future).
+  - s3c2410_gpio_getpin
+  - s3c2410_gpio_setpin
 Headers
 -------
-  See include/asm-arm/arch-s3c2410/regs-gpio.h for the list
+  See arch/arm/mach-s3c2410/include/mach/regs-gpio.h for the list
  of GPIO pins, and the configuration values for them. This
-  is included by using #include <asm/arch/regs-gpio.h>
+  is included by using #include <mach/regs-gpio.h>
  The GPIO management functions are defined in the hardware
-  header include/asm-arm/arch-s3c2410/hardware.h which can be
+  header arch/arm/mach-s3c2410/include/mach/hardware.h which can be
-  included by #include <asm/arch/hardware.h>
+  included by #include <mach/hardware.h>
  A useful amount of documentation can be found in the hardware
  header on how the GPIO functions (and others) work.
diff --git a/Documentation/arm/Samsung-S3C24XX/Overview.txt b/Documentation/arm/Samsung-S3C24XX/Overview.txt
index d04e1e30c47f..cff6227b4484 100644
--- a/Documentation/arm/Samsung-S3C24XX/Overview.txt
+++ b/Documentation/arm/Samsung-S3C24XX/Overview.txt
@@ -8,9 +8,10 @@ Introduction
  The Samsung S3C24XX range of ARM9 System-on-Chip CPUs are supported
  by the 's3c2410' architecture of ARM Linux. Currently the S3C2410,
-  S3C2412, S3C2413, S3C2440 and S3C2442 devices are supported.
+  S3C2412, S3C2413, S3C2440, S3C2442 and S3C2443 devices are supported.
+  Support for the S3C2400 and S3C24A0 series are in progress.
-  Support for the S3C2400 series is in progress.
 Configuration
 -------------
@@ -36,7 +37,23 @@ Layout
  in arch/arm/mach-s3c2410 and S3C2440 in arch/arm/mach-s3c2440
  Register, kernel and platform data definitions are held in the
-  include/asm-arm/arch-s3c2410 directory.
+  arch/arm/mach-s3c2410 directory./include/mach
+arch/arm/plat-s3c24xx:
+  Files in here are either common to all the s3c24xx family,
+  or are common to only some of them with names to indicate this
+  status. The files that are not common to all are generally named
+  with the initial cpu they support in the series to ensure a short
+  name without any possibility of confusion with newer devices.
+  As an example, initially s3c244x would cover s3c2440 and s3c2442, but
+  with the s3c2443 which does not share many of the same drivers in
+  this directory, the name becomes invalid. We stick to s3c2440-<x>
+  to indicate a driver that is s3c2440 and s3c2442 compatible.
+  This does mean that to find the status of any given SoC, a number
+  of directories may need to be searched.
 Machines
@@ -159,6 +176,17 @@ NAND
  For more information see Documentation/arm/Samsung-S3C24XX/NAND.txt
+SD/MMC
+------
+  The SD/MMC hardware pre S3C2443 is supported in the current
+  kernel, the driver is drivers/mmc/host/s3cmci.c and supports
+  1 and 4 bit SD or MMC cards.
+  The SDIO behaviour of this driver has not been fully tested. There is no
+  current support for hardware SDIO interrupts.
 Serial
 ------
@@ -178,6 +206,9 @@ GPIO
  The core contains support for manipulating the GPIO, see the
  documentation in GPIO.txt in the same directory as this file.
+  Newer kernels carry GPIOLIB, and support is being moved towards
+  this with some of the older support in line to be removed.
 Clock Management
 ----------------
diff --git a/Documentation/arm/Samsung-S3C24XX/USB-Host.txt b/Documentation/arm/Samsung-S3C24XX/USB-Host.txt
index b93b68e2b143..67671eba4231 100644
--- a/Documentation/arm/Samsung-S3C24XX/USB-Host.txt
+++ b/Documentation/arm/Samsung-S3C24XX/USB-Host.txt
@@ -49,7 +49,7 @@ Board Support
 Platform Data
 -------------
-  See linux/include/asm-arm/arch-s3c2410/usb-control.h for the
+  See arch/arm/mach-s3c2410/include/mach/usb-control.h for the
  descriptions of the platform device data. An implementation
  can be found in linux/arch/arm/mach-s3c2410/usb-simtec.c .
diff --git a/Documentation/auxdisplay/Makefile b/Documentation/auxdisplay/Makefile
new file mode 100644
index 000000000000..51fe23332c81
--- /dev/null
+++ b/Documentation/auxdisplay/Makefile
@@ -0,0 +1,10 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := cfag12864b-example
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_cfag12864b-example.o += -I$(objtree)/usr/include
diff --git a/Documentation/blackfin/kgdb.txt b/Documentation/blackfin/kgdb.txt
deleted file mode 100644
index 84f6a484ae9a..000000000000
--- a/Documentation/blackfin/kgdb.txt
+++ /dev/null
@@ -1,155 +0,0 @@
-                        A Simple Guide to Configure KGDB
-                        Sonic Zhang <sonic.zhang@analog.com>
-                                Aug. 24th 2006
-This KGDB patch enables the kernel developer to do source level debugging on
-the kernel for the Blackfin architecture.  The debugging works over either the
-ethernet interface or one of the uarts.  Both software breakpoints and
-hardware breakpoints are supported in this version.
-http://docs.blackfin.uclinux.org/doku.php?id=kgdb
-2 known issues:
-1. This bug:
-       http://blackfin.uclinux.org/tracker/index.php?func=detail&aid=544&group_id=18&atid=145
-   The GDB client for Blackfin uClinux causes incorrect values of local
-   variables to be displayed when the user breaks the running of kernel in GDB.
-2. Because of a hardware bug in Blackfin 533 v1.0.3:
-       05000067 - Watchpoints (Hardware Breakpoints) are not supported
-   Hardware breakpoints cannot be set properly.
-Debug over Ethernet:
- 
-1. Compile and install the cross platform version of gdb for blackfin, which
-   can be found at $(BINROOT)/bfin-elf-gdb.
-2. Apply this patch to the 2.6.x kernel.  Select the menuconfig option under
-   "Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
-   With this selected, option "Full Symbolic/Source Debugging support" and 
-   "Compile the kernel with frame pointers" are also selected.
-3. Select option "KGDB: connect over (Ethernet)".  Add "kgdboe=@target-IP/,@host-IP/" to
-   the option "Compiled-in Kernel Boot Parameter" under "Kernel hacking".
-4. Connect minicom to the serial port and boot the kernel image.
-5. Configure the IP "/> ifconfig eth0 target-IP"
-6. Start GDB client "bfin-elf-gdb vmlinux".
-7. Connect to the target "(gdb) target remote udp:target-IP:6443".
-8. Set software breakpoint "(gdb) break sys_open".
-9. Continue "(gdb) c".
-10. Run ls in the target console "/> ls".
-11. Breakpoint hits. "Breakpoint 1: sys_open(..."
-12. Display local variables and function paramters.
-    (*) This operation gives wrong results, see known issue 1.
-13. Single stepping "(gdb) si".
-14. Remove breakpoint 1. "(gdb) del 1"
-15. Set hardware breakpoint "(gdb) hbreak sys_open".
-16. Continue "(gdb) c".
-17. Run ls in the target console "/> ls".
-18. Hardware breakpoint hits. "Breakpoint 1: sys_open(...".
-    (*) This hardware breakpoint will not be hit, see known issue 2.
-19. Continue "(gdb) c".
-20. Interrupt the target in GDB "Ctrl+C".
-21. Detach from the target "(gdb) detach".
-22. Exit GDB "(gdb) quit".
-Debug over the UART:
-1. Compile and install the cross platform version of gdb for blackfin, which
-   can be found at $(BINROOT)/bfin-elf-gdb.
-2. Apply this patch to the 2.6.x kernel.  Select the menuconfig option under
-   "Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
-   With this selected, option "Full Symbolic/Source Debugging support" and 
-   "Compile the kernel with frame pointers" are also selected.
-3. Select option "KGDB: connect over (UART)".  Set "KGDB: UART port number" to be
-   a different one from the console.  Don't forget to change the mode of
-   blackfin serial driver to PIO.  Otherwise kgdb works incorrectly on UART.
- 
-4. If you want connect to kgdb when the kernel boots, enable
-   "KGDB: Wait for gdb connection early" 
-5. Compile kernel.
-6. Connect minicom to the serial port of the console and boot the kernel image.
-7. Start GDB client "bfin-elf-gdb vmlinux".
-8. Set the baud rate in GDB "(gdb) set remotebaud 57600".
-9. Connect to the target on the second serial port "(gdb) target remote /dev/ttyS1".
-10. Set software breakpoint "(gdb) break sys_open".
-11. Continue "(gdb) c". 
-12. Run ls in the target console "/> ls". 
-13. A breakpoint is hit. "Breakpoint 1: sys_open(..."
-14. All other operations are the same as that in KGDB over Ethernet. 
-Debug over the same UART as console:
-1. Compile and install the cross platform version of gdb for blackfin, which
-   can be found at $(BINROOT)/bfin-elf-gdb.
-2. Apply this patch to the 2.6.x kernel.  Select the menuconfig option under
-   "Kernel hacking" -> "Kernel debugging" -> "KGDB: kernel debug with remote gdb".
-   With this selected, option "Full Symbolic/Source Debugging support" and 
-   "Compile the kernel with frame pointers" are also selected.
-3. Select option "KGDB: connect over UART".  Set "KGDB: UART port number" to console.
-   Don't forget to change the mode of blackfin serial driver to PIO.
-   Otherwise kgdb works incorrectly on UART.
- 
-4. If you want connect to kgdb when the kernel boots, enable
-   "KGDB: Wait for gdb connection early" 
-5. Connect minicom to the serial port and boot the kernel image. 
-6. (Optional) Ask target to wait for gdb connection by entering Ctrl+A. In minicom, you should enter Ctrl+A+A.
-7. Start GDB client "bfin-elf-gdb vmlinux".
-8. Set the baud rate in GDB "(gdb) set remotebaud 57600".
-9. Connect to the target "(gdb) target remote /dev/ttyS0".
-10. Set software breakpoint "(gdb) break sys_open".
-11. Continue "(gdb) c". Then enter Ctrl+C twice to stop GDB connection.
-12. Run ls in the target console "/> ls". Dummy string can be seen on the console.
-13. Then connect the gdb to target again. "(gdb) target remote /dev/ttyS0".
-    Now you will find a breakpoint is hit. "Breakpoint 1: sys_open(..."
-14. All other operations are the same as that in KGDB over Ethernet.  The only
-    difference is that after continue command in GDB, please stop GDB
-    connection by 2 "Ctrl+C"s and connect again after breakpoints are hit or
-    Ctrl+A is entered.
diff --git a/Documentation/block/data-integrity.txt b/Documentation/block/data-integrity.txt
index e9dc8d86adc7..e8ca040ba2cf 100644
--- a/Documentation/block/data-integrity.txt
+++ b/Documentation/block/data-integrity.txt
@@ -246,7 +246,7 @@ will require extra work due to the application tag.
      retrieve the tag buffer using bio_integrity_get_tag().
-6.3 PASSING EXISTING INTEGRITY METADATA
+5.3 PASSING EXISTING INTEGRITY METADATA
    Filesystems that either generate their own integrity metadata or
    are capable of transferring IMD from user space can use the
@@ -283,7 +283,7 @@ will require extra work due to the application tag.
      integrity upon completion.
-6.4 REGISTERING A BLOCK DEVICE AS CAPABLE OF EXCHANGING INTEGRITY
+5.4 REGISTERING A BLOCK DEVICE AS CAPABLE OF EXCHANGING INTEGRITY
    METADATA
    To enable integrity exchange on a block device the gendisk must be
diff --git a/Documentation/block/deadline-iosched.txt b/Documentation/block/deadline-iosched.txt
index c23cab13c3d1..72576769e0f4 100644
--- a/Documentation/block/deadline-iosched.txt
+++ b/Documentation/block/deadline-iosched.txt
@@ -30,12 +30,18 @@ write_expire	(in ms)
 Similar to read_expire mentioned above, but for writes.
-fifo_batch
+fifo_batch      (number of requests)
 ----------
-When a read request expires its deadline, we must move some requests from
+Requests are grouped into ``batches'' of a particular data direction (read or
-the sorted io scheduler list to the block device dispatch queue. fifo_batch
+write) which are serviced in increasing sector order.  To limit extra seeking,
-controls how many requests we move.
+deadline expiries are only checked between batches.  fifo_batch controls the
+maximum number of requests per batch.
+This parameter tunes the balance between per-request latency and aggregate
+throughput.  When low latency is the primary concern, smaller is better (where
+a value of 1 yields first-come first-served behaviour).  Increasing fifo_batch
+generally improves throughput, at the cost of latency variation.
 writes_starved  (number of dispatches)
diff --git a/Documentation/bt8xxgpio.txt b/Documentation/bt8xxgpio.txt
new file mode 100644
index 000000000000..d8297e4ebd26
--- /dev/null
+++ b/Documentation/bt8xxgpio.txt
@@ -0,0 +1,67 @@
+===============================================================
+==  BT8XXGPIO driver                                         ==
+==                                                           ==
+==  A driver for a selfmade cheap BT8xx based PCI GPIO-card  ==
+==                                                           ==
+==  For advanced documentation, see                          ==
+==  http://www.bu3sch.de/btgpio.php                          ==
+===============================================================
+A generic digital 24-port PCI GPIO card can be built out of an ordinary
+Brooktree bt848, bt849, bt878 or bt879 based analog TV tuner card. The
+Brooktree chip is used in old analog Hauppauge WinTV PCI cards. You can easily
+find them used for low prices on the net.
+The bt8xx chip does have 24 digital GPIO ports.
+These ports are accessible via 24 pins on the SMD chip package.
+==============================================
+==  How to physically access the GPIO pins  ==
+==============================================
+The are several ways to access these pins. One might unsolder the whole chip
+and put it on a custom PCI board, or one might only unsolder each individual
+GPIO pin and solder that to some tiny wire. As the chip package really is tiny
+there are some advanced soldering skills needed in any case.
+The physical pinouts are drawn in the following ASCII art.
+The GPIO pins are marked with G00-G23
+                                           G G G G G G G G G G G G     G G G G G G
+                                           0 0 0 0 0 0 0 0 0 0 1 1     1 1 1 1 1 1
+                                           0 1 2 3 4 5 6 7 8 9 0 1     2 3 4 5 6 7
+           | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
+           ---------------------------------------------------------------------------
+         --|                               ^                                     ^   |--
+         --|                               pin 86                           pin 67   |--
+         --|                                                                         |--
+         --|                                                               pin 61 >  |-- G18
+         --|                                                                         |-- G19
+         --|                                                                         |-- G20
+         --|                                                                         |-- G21
+         --|                                                                         |-- G22
+         --|                                                               pin 56 >  |-- G23
+         --|                                                                         |--
+         --|                           Brooktree 878/879                             |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|                                                                         |--
+         --|   O                                                                     |--
+         --|                                                                         |--
+           ---------------------------------------------------------------------------
+           | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
+           ^
+           This is pin 1
diff --git a/Documentation/cciss.txt b/Documentation/cciss.txt
index 63e59b8847c5..8244c6442faa 100644
--- a/Documentation/cciss.txt
+++ b/Documentation/cciss.txt
@@ -112,27 +112,18 @@ Hot plug support for SCSI tape drives
 Hot plugging of SCSI tape drives is supported, with some caveats.
 The cciss driver must be informed that changes to the SCSI bus
-have been made, in addition to and prior to informing the SCSI 
+have been made.  This may be done via the /proc filesystem.
-mid layer.  This may be done via the /proc filesystem.  For example:
+For example:
        echo "rescan" > /proc/scsi/cciss0/1
-This causes the adapter to query the adapter about changes to the 
+This causes the driver to query the adapter about changes to the
-physical SCSI buses and/or fibre channel arbitrated loop and the 
+physical SCSI buses and/or fibre channel arbitrated loop and the
 driver to make note of any new or removed sequential access devices
 or medium changers.  The driver will output messages indicating what 
 devices have been added or removed and the controller, bus, target and 
-lun used to address the device.  Once this is done, the SCSI mid layer 
+lun used to address the device.  It then notifies the SCSI mid layer
-can be informed of changes to the virtual SCSI bus which the driver 
+of these changes.
-presents to it in the usual way. For example: 
-        echo scsi add-single-device 3 2 1 0 > /proc/scsi/scsi
- 
-to add a device on controller 3, bus 2, target 1, lun 0.   Note that
-the driver makes an effort to preserve the devices positions
-in the virtual SCSI bus, so if you are only moving tape drives 
-around on the same adapter and not adding or removing tape drives 
-from the adapter, informing the SCSI mid layer may not be necessary.
 Note that the naming convention of the /proc filesystem entries 
 contains a number in addition to the driver name.  (E.g. "cciss0" 
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 91c0dcc6fa5c..2c558cd6c1ef 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -145,8 +145,7 @@ useful for reading photocds.
 To play an audio CD, you should first unmount and remove any data
 CDROM.  Any of the CDROM player programs should then work (workman,
-workbone, cdplayer, etc.).  Lacking anything else, you could use the
+workbone, cdplayer, etc.).
-cdtester program in Documentation/cdrom/sbpcd.
 On a few drives, you can read digital audio directly using a program
 such as cdda2wav.  The only types of drive which I've heard support
diff --git a/Documentation/cgroups.txt b/Documentation/cgroups/cgroups.txt
index d9014aa0eb68..d9014aa0eb68 100644
--- a/Documentation/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
diff --git a/Documentation/cgroups/freezer-subsystem.txt b/Documentation/cgroups/freezer-subsystem.txt
new file mode 100644
index 000000000000..c50ab58b72eb
--- /dev/null
+++ b/Documentation/cgroups/freezer-subsystem.txt
@@ -0,0 +1,99 @@
+        The cgroup freezer is useful to batch job management system which start
+and stop sets of tasks in order to schedule the resources of a machine
+according to the desires of a system administrator. This sort of program
+is often used on HPC clusters to schedule access to the cluster as a
+whole. The cgroup freezer uses cgroups to describe the set of tasks to
+be started/stopped by the batch job management system. It also provides
+a means to start and stop the tasks composing the job.
+        The cgroup freezer will also be useful for checkpointing running groups
+of tasks. The freezer allows the checkpoint code to obtain a consistent
+image of the tasks by attempting to force the tasks in a cgroup into a
+quiescent state. Once the tasks are quiescent another task can
+walk /proc or invoke a kernel interface to gather information about the
+quiesced tasks. Checkpointed tasks can be restarted later should a
+recoverable error occur. This also allows the checkpointed tasks to be
+migrated between nodes in a cluster by copying the gathered information
+to another node and restarting the tasks there.
+        Sequences of SIGSTOP and SIGCONT are not always sufficient for stopping
+and resuming tasks in userspace. Both of these signals are observable
+from within the tasks we wish to freeze. While SIGSTOP cannot be caught,
+blocked, or ignored it can be seen by waiting or ptracing parent tasks.
+SIGCONT is especially unsuitable since it can be caught by the task. Any
+programs designed to watch for SIGSTOP and SIGCONT could be broken by
+attempting to use SIGSTOP and SIGCONT to stop and resume tasks. We can
+demonstrate this problem using nested bash shells:
+        $ echo $$
+        16644
+        $ bash
+        $ echo $$
+        16690
+        From a second, unrelated bash shell:
+        $ kill -SIGSTOP 16690
+        $ kill -SIGCONT 16990
+        <at this point 16990 exits and causes 16644 to exit too>
+        This happens because bash can observe both signals and choose how it
+responds to them.
+        Another example of a program which catches and responds to these
+signals is gdb. In fact any program designed to use ptrace is likely to
+have a problem with this method of stopping and resuming tasks.
+         In contrast, the cgroup freezer uses the kernel freezer code to
+prevent the freeze/unfreeze cycle from becoming visible to the tasks
+being frozen. This allows the bash example above and gdb to run as
+expected.
+        The freezer subsystem in the container filesystem defines a file named
+freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the
+cgroup. Subsequently writing "THAWED" will unfreeze the tasks in the cgroup.
+Reading will return the current state.
+* Examples of usage :
+   # mkdir /containers/freezer
+   # mount -t cgroup -ofreezer freezer  /containers
+   # mkdir /containers/0
+   # echo $some_pid > /containers/0/tasks
+to get status of the freezer subsystem :
+   # cat /containers/0/freezer.state
+   THAWED
+to freeze all tasks in the container :
+   # echo FROZEN > /containers/0/freezer.state
+   # cat /containers/0/freezer.state
+   FREEZING
+   # cat /containers/0/freezer.state
+   FROZEN
+to unfreeze all tasks in the container :
+   # echo THAWED > /containers/0/freezer.state
+   # cat /containers/0/freezer.state
+   THAWED
+This is the basic mechanism which should do the right thing for user space task
+in a simple scenario.
+It's important to note that freezing can be incomplete. In that case we return
+EBUSY. This means that some tasks in the cgroup are busy doing something that
+prevents us from completely freezing the cgroup at this time. After EBUSY,
+the cgroup will remain partially frozen -- reflected by freezer.state reporting
+"FREEZING" when read. The state will remain "FREEZING" until one of these
+things happens:
+        1) Userspace cancels the freezing operation by writing "THAWED" to
+                the freezer.state file
+        2) Userspace retries the freezing operation by writing "FROZEN" to
+                the freezer.state file (writing "FREEZING" is not legal
+                and returns EIO)
+        3) The tasks that blocked the cgroup from entering the "FROZEN"
+                state disappear from the cgroup's set of tasks.
diff --git a/Documentation/cli-sti-removal.txt b/Documentation/cli-sti-removal.txt
deleted file mode 100644
index 60932b02fcb3..000000000000
--- a/Documentation/cli-sti-removal.txt
+++ /dev/null
@@ -1,133 +0,0 @@
-#### cli()/sti() removal guide, started by Ingo Molnar <mingo@redhat.com>
-as of 2.5.28, five popular macros have been removed on SMP, and
-are being phased out on UP:
- cli(), sti(), save_flags(flags), save_flags_cli(flags), restore_flags(flags)
-until now it was possible to protect driver code against interrupt
-handlers via a cli(), but from now on other, more lightweight methods
-have to be used for synchronization, such as spinlocks or semaphores.
-for example, driver code that used to do something like:
-        struct driver_data;
-        irq_handler (...)
-        {
-                ....
-                driver_data.finish = 1;
-                driver_data.new_work = 0;
-                ....
-        }
-        ...
-        ioctl_func (...)
-        {
-                ...
-                cli();
-                ...
-                driver_data.finish = 0;
-                driver_data.new_work = 2;
-                ...
-                sti();
-                ...
-        }
-was SMP-correct because the cli() function ensured that no
-interrupt handler (amongst them the above irq_handler()) function
-would execute while the cli()-ed section is executing.
-but from now on a more direct method of locking has to be used:
-        DEFINE_SPINLOCK(driver_lock);
-        struct driver_data;
-        irq_handler (...)
-        {
-                unsigned long flags;
-                ....
-                spin_lock_irqsave(&driver_lock, flags);
-                ....
-                driver_data.finish = 1;
-                driver_data.new_work = 0;
-                ....
-                spin_unlock_irqrestore(&driver_lock, flags);
-                ....
-        }
-        ...
-        ioctl_func (...)
-        {
-                ...
-                spin_lock_irq(&driver_lock);
-                ...
-                driver_data.finish = 0;
-                driver_data.new_work = 2;
-                ...
-                spin_unlock_irq(&driver_lock);
-                ...
-        }
-the above code has a number of advantages:
- the locking relation is easier to understand - actual lock usage
-  pinpoints the critical sections. cli() usage is too opaque.
-  Easier to understand means it's easier to debug.
- it's faster, because spinlocks are faster to acquire than the
-  potentially heavily-used IRQ lock. Furthermore, your driver does
-  not have to wait eg. for a big heavy SCSI interrupt to finish,
-  because the driver_lock spinlock is only used by your driver.
-  cli() on the other hand was used by many drivers, and extended
-  the critical section to the whole IRQ handler function - creating
-  serious lock contention.
- 
-to make the transition easier, we've still kept the cli(), sti(),
-save_flags(), save_flags_cli() and restore_flags() macros defined
-on UP systems - but their usage will be phased out until 2.6 is
-released.
-drivers that want to disable local interrupts (interrupts on the
-current CPU), can use the following five macros:
-  local_irq_disable(), local_irq_enable(), local_save_flags(flags),
-  local_irq_save(flags), local_irq_restore(flags)
-but beware, their meaning and semantics are much simpler, far from
-that of the old cli(), sti(), save_flags(flags) and restore_flags(flags)
-SMP meaning:
-    local_irq_disable()       => turn local IRQs off
-    local_irq_enable()        => turn local IRQs on
-    local_save_flags(flags)   => save the current IRQ state into flags. The
-                                 state can be on or off. (on some
-                                 architectures there's even more bits in it.)
-    local_irq_save(flags)     => save the current IRQ state into flags and
-                                 disable interrupts.
-    local_irq_restore(flags)  => restore the IRQ state from flags.
-(local_irq_save can save both irqs on and irqs off state, and
-local_irq_restore can restore into both irqs on and irqs off state.)
-another related change is that synchronize_irq() now takes a parameter:
-synchronize_irq(irq). This change too has the purpose of making SMP
-synchronization more lightweight - this way you can wait for your own
-interrupt handler to finish, no need to wait for other IRQ sources.
-why were these changes done? The main reason was the architectural burden
-of maintaining the cli()/sti() interface - it became a real problem. The
-new interrupt system is much more streamlined, easier to understand, debug,
-and it's also a bit faster - the same happened to it that will happen to
-cli()/sti() using drivers once they convert to spinlocks :-)
diff --git a/Documentation/connector/Makefile b/Documentation/connector/Makefile
new file mode 100644
index 000000000000..8df1a7285a06
--- /dev/null
+++ b/Documentation/connector/Makefile
@@ -0,0 +1,11 @@
+ifneq ($(CONFIG_CONNECTOR),)
+obj-m += cn_test.o
+endif
+# List of programs to build
+hostprogs-y := ucon
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_ucon.o += -I$(objtree)/usr/include
diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
index 866b9cd9a959..1c07547d3f81 100644
--- a/Documentation/controllers/memory.txt
+++ b/Documentation/controllers/memory.txt
@@ -112,14 +112,22 @@ the per cgroup LRU.
 2.2.1 Accounting details
-All mapped pages (RSS) and unmapped user pages (Page Cache) are accounted.
+All mapped anon pages (RSS) and cache pages (Page Cache) are accounted.
-RSS pages are accounted at the time of page_add_*_rmap() unless they've already
+(some pages which never be reclaimable and will not be on global LRU
-been accounted for earlier. A file page will be accounted for as Page Cache;
+ are not accounted. we just accounts pages under usual vm management.)
-it's mapped into the page tables of a process, duplicate accounting is carefully
-avoided. Page Cache pages are accounted at the time of add_to_page_cache().
+RSS pages are accounted at page_fault unless they've already been accounted
-The corresponding routines that remove a page from the page tables or removes
+for earlier. A file page will be accounted for as Page Cache when it's
-a page from Page Cache is used to decrement the accounting counters of the
+inserted into inode (radix-tree). While it's mapped into the page tables of
-cgroup.
+processes, duplicate accounting is carefully avoided.
+A RSS page is unaccounted when it's fully unmapped. A PageCache page is
+unaccounted when it's removed from radix-tree.
+At page migration, accounting information is kept.
+Note: we just account pages-on-lru because our purpose is to control amount
+of used pages. not-on-lru pages are tend to be out-of-control from vm view.
 2.3 Shared Page Accounting
@@ -242,8 +250,7 @@ rmdir() if there are no tasks.
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
 3. Teach controller to account for shared-pages
-4. Start reclamation when the limit is lowered
+4. Start reclamation in the background when the limit is
-5. Start reclamation in the background when the limit is
   not yet hit but the usage is getting closer
 Summary
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index dcec0564d040..5b0cfa67aff9 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -122,7 +122,7 @@ around '10000' or more.
 show_sampling_rate_(min|max): the minimum and maximum sampling rates
 available that you may set 'sampling_rate' to.
-up_threshold: defines what the average CPU usaged between the samplings
+up_threshold: defines what the average CPU usage between the samplings
 of 'sampling_rate' needs to be for the kernel to make a decision on
 whether it should increase the frequency.  For example when it is set
 to its default value of '80' it means that between the checking
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index ffdb5323df37..3d0b915035b9 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -35,11 +35,9 @@ Mailing List
 ------------
 There is a CPU frequency changing CVS commit and general list where
 you can report bugs, problems or submit patches. To post a message,
-send an email to cpufreq@lists.linux.org.uk, to subscribe go to
+send an email to cpufreq@vger.kernel.org, to subscribe go to
-http://lists.linux.org.uk/mailman/listinfo/cpufreq. Previous post to the
+http://vger.kernel.org/vger-lists.html#cpufreq and follow the
-mailing list are available to subscribers at
+instructions there.
-http://lists.linux.org.uk/mailman/private/cpufreq/.
 Links
 -----
@@ -50,7 +48,7 @@ how to access the CVS repository:
 * http://cvs.arm.linux.org.uk/
 the CPUFreq Mailing list:
-* http://lists.linux.org.uk/mailman/listinfo/cpufreq
+* http://vger.kernel.org/vger-lists.html#cpufreq
 Clock and voltage scaling for the SA-1100:
 * http://www.lartmaker.nl/projects/scaling
diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index ba0aacde94fb..94bbc27ddd4f 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -59,15 +59,10 @@ apicid values in those tables for disabled apics. In the event BIOS doesn't
 mark such hot-pluggable cpus as disabled entries, one could use this
 parameter "additional_cpus=x" to represent those cpus in the cpu_possible_map.
-s390 uses the number of cpus it detects at IPL time to also the number of bits
-in cpu_possible_map. If it is desired to add additional cpus at a later time
-the number should be specified using this option or the possible_cpus option.
 possible_cpus=n         [s390 only] use this to set hotpluggable cpus.
                        This option sets possible_cpus bits in
                        cpu_possible_map. Thus keeping the numbers of bits set
                        constant even if the machine gets rebooted.
-                        This option overrides additional_cpus.
 CPU maps and such
 -----------------
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index 1f5a924d1e56..5c86c258c791 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -48,7 +48,7 @@ hooks, beyond what is already present, required to manage dynamic
 job placement on large systems.
 Cpusets use the generic cgroup subsystem described in
-Documentation/cgroup.txt.
+Documentation/cgroups/cgroups.txt.
 Requests by a task, using the sched_setaffinity(2) system call to
 include CPUs in its CPU affinity mask, and using the mbind(2) and
@@ -635,14 +635,16 @@ prior 'mems' setting, will not be moved.
 There is an exception to the above.  If hotplug functionality is used
 to remove all the CPUs that are currently assigned to a cpuset,
-then the kernel will automatically update the cpus_allowed of all
+then all the tasks in that cpuset will be moved to the nearest ancestor
-tasks attached to CPUs in that cpuset to allow all CPUs.  When memory
+with non-empty cpus.  But the moving of some (or all) tasks might fail if
-hotplug functionality for removing Memory Nodes is available, a
+cpuset is bound with another cgroup subsystem which has some restrictions
-similar exception is expected to apply there as well.  In general,
+on task attaching.  In this failing case, those tasks will stay
-the kernel prefers to violate cpuset placement, over starving a task
+in the original cpuset, and the kernel will automatically update
-that has had all its allowed CPUs or Memory Nodes taken offline.  User
+their cpus_allowed to allow all online CPUs.  When memory hotplug
-code should reconfigure cpusets to only refer to online CPUs and Memory
+functionality for removing Memory Nodes is available, a similar exception
-Nodes when using hotplug to add or remove such resources.
+is expected to apply there as well.  In general, the kernel prefers to
+violate cpuset placement, over starving a task that has had all
+its allowed CPUs or Memory Nodes taken offline.
 There is a second exception to the above.  GFP_ATOMIC requests are
 kernel internal allocations that must be satisfied, immediately.
diff --git a/Documentation/cris/README b/Documentation/cris/README
index 795a1dabe6c7..d9b086869a60 100644
--- a/Documentation/cris/README
+++ b/Documentation/cris/README
@@ -27,7 +27,7 @@ operating system.
 The ETRAX 100LX chip
 --------------------
-For reference, plase see the press-release:
+For reference, please see the press-release:
 http://www.axis.com/news/us/001101_etrax.htm
diff --git a/Documentation/development-process/1.Intro b/Documentation/development-process/1.Intro
new file mode 100644
index 000000000000..8cc2cba2b10d
--- /dev/null
+++ b/Documentation/development-process/1.Intro
@@ -0,0 +1,274 @@
+1: A GUIDE TO THE KERNEL DEVELOPMENT PROCESS
+The purpose of this document is to help developers (and their managers)
+work with the development community with a minimum of frustration.  It is
+an attempt to document how this community works in a way which is
+accessible to those who are not intimately familiar with Linux kernel
+development (or, indeed, free software development in general).  While
+there is some technical material here, this is very much a process-oriented
+discussion which does not require a deep knowledge of kernel programming to
+understand.
+1.1: EXECUTIVE SUMMARY
+The rest of this section covers the scope of the kernel development process
+and the kinds of frustrations that developers and their employers can
+encounter there.  There are a great many reasons why kernel code should be
+merged into the official ("mainline") kernel, including automatic
+availability to users, community support in many forms, and the ability to
+influence the direction of kernel development.  Code contributed to the
+Linux kernel must be made available under a GPL-compatible license.
+Section 2 introduces the development process, the kernel release cycle, and
+the mechanics of the merge window.  The various phases in the patch
+development, review, and merging cycle are covered.  There is some
+discussion of tools and mailing lists.  Developers wanting to get started
+with kernel development are encouraged to track down and fix bugs as an
+initial exercise.
+Section 3 covers early-stage project planning, with an emphasis on
+involving the development community as soon as possible.
+Section 4 is about the coding process; several pitfalls which have been
+encountered by other developers are discussed.  Some requirements for
+patches are covered, and there is an introduction to some of the tools
+which can help to ensure that kernel patches are correct.
+Section 5 talks about the process of posting patches for review.  To be
+taken seriously by the development community, patches must be properly
+formatted and described, and they must be sent to the right place.
+Following the advice in this section should help to ensure the best
+possible reception for your work.
+Section 6 covers what happens after posting patches; the job is far from
+done at that point.  Working with reviewers is a crucial part of the
+development process; this section offers a number of tips on how to avoid
+problems at this important stage.  Developers are cautioned against
+assuming that the job is done when a patch is merged into the mainline.
+Section 7 introduces a couple of "advanced" topics: managing patches with
+git and reviewing patches posted by others.
+Section 8 concludes the document with pointers to sources for more
+information on kernel development.
+1.2: WHAT THIS DOCUMENT IS ABOUT
+The Linux kernel, at over 6 million lines of code and well over 1000 active
+contributors, is one of the largest and most active free software projects
+in existence.  Since its humble beginning in 1991, this kernel has evolved
+into a best-of-breed operating system component which runs on pocket-sized
+digital music players, desktop PCs, the largest supercomputers in
+existence, and all types of systems in between.  It is a robust, efficient,
+and scalable solution for almost any situation.
+With the growth of Linux has come an increase in the number of developers
+(and companies) wishing to participate in its development.  Hardware
+vendors want to ensure that Linux supports their products well, making
+those products attractive to Linux users.  Embedded systems vendors, who
+use Linux as a component in an integrated product, want Linux to be as
+capable and well-suited to the task at hand as possible.  Distributors and
+other software vendors who base their products on Linux have a clear
+interest in the capabilities, performance, and reliability of the Linux
+kernel.  And end users, too, will often wish to change Linux to make it
+better suit their needs.
+One of the most compelling features of Linux is that it is accessible to
+these developers; anybody with the requisite skills can improve Linux and
+influence the direction of its development.  Proprietary products cannot
+offer this kind of openness, which is a characteristic of the free software
+process.  But, if anything, the kernel is even more open than most other
+free software projects.  A typical three-month kernel development cycle can
+involve over 1000 developers working for more than 100 different companies
+(or for no company at all).
+Working with the kernel development community is not especially hard.  But,
+that notwithstanding, many potential contributors have experienced
+difficulties when trying to do kernel work.  The kernel community has
+evolved its own distinct ways of operating which allow it to function
+smoothly (and produce a high-quality product) in an environment where
+thousands of lines of code are being changed every day.  So it is not
+surprising that Linux kernel development process differs greatly from
+proprietary development methods.
+The kernel's development process may come across as strange and
+intimidating to new developers, but there are good reasons and solid
+experience behind it.  A developer who does not understand the kernel
+community's ways (or, worse, who tries to flout or circumvent them) will
+have a frustrating experience in store.  The development community, while
+being helpful to those who are trying to learn, has little time for those
+who will not listen or who do not care about the development process.
+It is hoped that those who read this document will be able to avoid that
+frustrating experience.  There is a lot of material here, but the effort
+involved in reading it will be repaid in short order.  The development
+community is always in need of developers who will help to make the kernel
+better; the following text should help you - or those who work for you -
+join our community.
+1.3: CREDITS
+This document was written by Jonathan Corbet, corbet@lwn.net.  It has been
+improved by comments from Johannes Berg, James Berry, Alex Chiang, Roland
+Dreier, Randy Dunlap, Jake Edge, Jiri Kosina, Matt Mackall, Arthur Marsh,
+Amanda McPherson, Andrew Morton, Andrew Price, Tsugikazu Shibata, and
+Jochen Voß. 
+This work was supported by the Linux Foundation; thanks especially to
+Amanda McPherson, who saw the value of this effort and made it all happen.
+1.4: THE IMPORTANCE OF GETTING CODE INTO THE MAINLINE
+Some companies and developers occasionally wonder why they should bother
+learning how to work with the kernel community and get their code into the
+mainline kernel (the "mainline" being the kernel maintained by Linus
+Torvalds and used as a base by Linux distributors).  In the short term,
+contributing code can look like an avoidable expense; it seems easier to
+just keep the code separate and support users directly.  The truth of the
+matter is that keeping code separate ("out of tree") is a false economy.
+As a way of illustrating the costs of out-of-tree code, here are a few
+relevant aspects of the kernel development process; most of these will be
+discussed in greater detail later in this document.  Consider:
+- Code which has been merged into the mainline kernel is available to all
+  Linux users.  It will automatically be present on all distributions which
+  enable it.  There is no need for driver disks, downloads, or the hassles
+  of supporting multiple versions of multiple distributions; it all just
+  works, for the developer and for the user.  Incorporation into the
+  mainline solves a large number of distribution and support problems.
+- While kernel developers strive to maintain a stable interface to user
+  space, the internal kernel API is in constant flux.  The lack of a stable
+  internal interface is a deliberate design decision; it allows fundamental
+  improvements to be made at any time and results in higher-quality code.
+  But one result of that policy is that any out-of-tree code requires
+  constant upkeep if it is to work with new kernels.  Maintaining
+  out-of-tree code requires significant amounts of work just to keep that
+  code working.
+  Code which is in the mainline, instead, does not require this work as the
+  result of a simple rule requiring any developer who makes an API change
+  to also fix any code that breaks as the result of that change.  So code
+  which has been merged into the mainline has significantly lower
+  maintenance costs.
+- Beyond that, code which is in the kernel will often be improved by other
+  developers.  Surprising results can come from empowering your user
+  community and customers to improve your product.
+- Kernel code is subjected to review, both before and after merging into
+  the mainline.  No matter how strong the original developer's skills are,
+  this review process invariably finds ways in which the code can be
+  improved.  Often review finds severe bugs and security problems.  This is
+  especially true for code which has been developed in a closed
+  environment; such code benefits strongly from review by outside
+  developers.  Out-of-tree code is lower-quality code.
+- Participation in the development process is your way to influence the
+  direction of kernel development.  Users who complain from the sidelines
+  are heard, but active developers have a stronger voice - and the ability
+  to implement changes which make the kernel work better for their needs.
+- When code is maintained separately, the possibility that a third party
+  will contribute a different implementation of a similar feature always
+  exists.  Should that happen, getting your code merged will become much
+  harder - to the point of impossibility.  Then you will be faced with the
+  unpleasant alternatives of either (1) maintaining a nonstandard feature
+  out of tree indefinitely, or (2) abandoning your code and migrating your
+  users over to the in-tree version.
+- Contribution of code is the fundamental action which makes the whole
+  process work.  By contributing your code you can add new functionality to
+  the kernel and provide capabilities and examples which are of use to
+  other kernel developers.  If you have developed code for Linux (or are
+  thinking about doing so), you clearly have an interest in the continued
+  success of this platform; contributing code is one of the best ways to
+  help ensure that success.
+All of the reasoning above applies to any out-of-tree kernel code,
+including code which is distributed in proprietary, binary-only form.
+There are, however, additional factors which should be taken into account
+before considering any sort of binary-only kernel code distribution.  These
+include:
+- The legal issues around the distribution of proprietary kernel modules
+  are cloudy at best; quite a few kernel copyright holders believe that
+  most binary-only modules are derived products of the kernel and that, as
+  a result, their distribution is a violation of the GNU General Public
+  license (about which more will be said below).  Your author is not a
+  lawyer, and nothing in this document can possibly be considered to be
+  legal advice.  The true legal status of closed-source modules can only be
+  determined by the courts.  But the uncertainty which haunts those modules
+  is there regardless.
+- Binary modules greatly increase the difficulty of debugging kernel
+  problems, to the point that most kernel developers will not even try.  So
+  the distribution of binary-only modules will make it harder for your
+  users to get support from the community.
+- Support is also harder for distributors of binary-only modules, who must
+  provide a version of the module for every distribution and every kernel
+  version they wish to support.  Dozens of builds of a single module can
+  be required to provide reasonably comprehensive coverage, and your users
+  will have to upgrade your module separately every time they upgrade their
+  kernel.
+- Everything that was said above about code review applies doubly to
+  closed-source code.  Since this code is not available at all, it cannot
+  have been reviewed by the community and will, beyond doubt, have serious
+  problems. 
+Makers of embedded systems, in particular, may be tempted to disregard much
+of what has been said in this section in the belief that they are shipping
+a self-contained product which uses a frozen kernel version and requires no
+more development after its release.  This argument misses the value of
+widespread code review and the value of allowing your users to add
+capabilities to your product.  But these products, too, have a limited
+commercial life, after which a new version must be released.  At that
+point, vendors whose code is in the mainline and well maintained will be
+much better positioned to get the new product ready for market quickly.
+1.5: LICENSING
+Code is contributed to the Linux kernel under a number of licenses, but all
+code must be compatible with version 2 of the GNU General Public License
+(GPLv2), which is the license covering the kernel distribution as a whole.
+In practice, that means that all code contributions are covered either by
+GPLv2 (with, optionally, language allowing distribution under later
+versions of the GPL) or the three-clause BSD license.  Any contributions
+which are not covered by a compatible license will not be accepted into the
+kernel.
+Copyright assignments are not required (or requested) for code contributed
+to the kernel.  All code merged into the mainline kernel retains its
+original ownership; as a result, the kernel now has thousands of owners.
+One implication of this ownership structure is that any attempt to change
+the licensing of the kernel is doomed to almost certain failure.  There are
+few practical scenarios where the agreement of all copyright holders could
+be obtained (or their code removed from the kernel).  So, in particular,
+there is no prospect of a migration to version 3 of the GPL in the
+foreseeable future.
+It is imperative that all code contributed to the kernel be legitimately
+free software.  For that reason, code from anonymous (or pseudonymous)
+contributors will not be accepted.  All contributors are required to "sign
+off" on their code, stating that the code can be distributed with the
+kernel under the GPL.  Code which has not been licensed as free software by
+its owner, or which risks creating copyright-related problems for the
+kernel (such as code which derives from reverse-engineering efforts lacking
+proper safeguards) cannot be contributed.
+Questions about copyright-related issues are common on Linux development
+mailing lists.  Such questions will normally receive no shortage of
+answers, but one should bear in mind that the people answering those
+questions are not lawyers and cannot provide legal advice.  If you have
+legal questions relating to Linux source code, there is no substitute for
+talking with a lawyer who understands this field.  Relying on answers
+obtained on technical mailing lists is a risky affair.
diff --git a/Documentation/development-process/2.Process b/Documentation/development-process/2.Process
new file mode 100644
index 000000000000..d750321acd5a
--- /dev/null
+++ b/Documentation/development-process/2.Process
@@ -0,0 +1,459 @@
+2: HOW THE DEVELOPMENT PROCESS WORKS
+Linux kernel development in the early 1990's was a pretty loose affair,
+with relatively small numbers of users and developers involved.  With a
+user base in the millions and with some 2,000 developers involved over the
+course of one year, the kernel has since had to evolve a number of
+processes to keep development happening smoothly.  A solid understanding of
+how the process works is required in order to be an effective part of it.
+2.1: THE BIG PICTURE
+The kernel developers use a loosely time-based release process, with a new
+major kernel release happening every two or three months.  The recent
+release history looks like this:
+        2.6.26  July 13, 2008
+        2.6.25  April 16, 2008
+        2.6.24  January 24, 2008
+        2.6.23  October 9, 2007
+        2.6.22  July 8, 2007
+        2.6.21  April 25, 2007
+        2.6.20  February 4, 2007
+Every 2.6.x release is a major kernel release with new features, internal
+API changes, and more.  A typical 2.6 release can contain over 10,000
+changesets with changes to several hundred thousand lines of code.  2.6 is
+thus the leading edge of Linux kernel development; the kernel uses a
+rolling development model which is continually integrating major changes.
+A relatively straightforward discipline is followed with regard to the
+merging of patches for each release.  At the beginning of each development
+cycle, the "merge window" is said to be open.  At that time, code which is
+deemed to be sufficiently stable (and which is accepted by the development
+community) is merged into the mainline kernel.  The bulk of changes for a
+new development cycle (and all of the major changes) will be merged during
+this time, at a rate approaching 1,000 changes ("patches," or "changesets")
+per day.
+(As an aside, it is worth noting that the changes integrated during the
+merge window do not come out of thin air; they have been collected, tested,
+and staged ahead of time.  How that process works will be described in
+detail later on).
+The merge window lasts for two weeks.  At the end of this time, Linus
+Torvalds will declare that the window is closed and release the first of
+the "rc" kernels.  For the kernel which is destined to be 2.6.26, for
+example, the release which happens at the end of the merge window will be
+called 2.6.26-rc1.  The -rc1 release is the signal that the time to merge
+new features has passed, and that the time to stabilize the next kernel has
+begun.
+Over the next six to ten weeks, only patches which fix problems should be
+submitted to the mainline.  On occasion a more significant change will be
+allowed, but such occasions are rare; developers who try to merge new
+features outside of the merge window tend to get an unfriendly reception.
+As a general rule, if you miss the merge window for a given feature, the
+best thing to do is to wait for the next development cycle.  (An occasional
+exception is made for drivers for previously-unsupported hardware; if they
+touch no in-tree code, they cannot cause regressions and should be safe to
+add at any time).
+As fixes make their way into the mainline, the patch rate will slow over
+time.  Linus releases new -rc kernels about once a week; a normal series
+will get up to somewhere between -rc6 and -rc9 before the kernel is
+considered to be sufficiently stable and the final 2.6.x release is made.
+At that point the whole process starts over again.
+As an example, here is how the 2.6.25 development cycle went (all dates in
+2008): 
+        January 24      2.6.24 stable release
+        February 10     2.6.25-rc1, merge window closes
+        February 15     2.6.25-rc2
+        February 24     2.6.25-rc3
+        March 4         2.6.25-rc4
+        March 9         2.6.25-rc5
+        March 16        2.6.25-rc6
+        March 25        2.6.25-rc7
+        April 1         2.6.25-rc8
+        April 11        2.6.25-rc9
+        April 16        2.6.25 stable release
+How do the developers decide when to close the development cycle and create
+the stable release?  The most significant metric used is the list of
+regressions from previous releases.  No bugs are welcome, but those which
+break systems which worked in the past are considered to be especially
+serious.  For this reason, patches which cause regressions are looked upon
+unfavorably and are quite likely to be reverted during the stabilization
+period. 
+The developers' goal is to fix all known regressions before the stable
+release is made.  In the real world, this kind of perfection is hard to
+achieve; there are just too many variables in a project of this size.
+There comes a point where delaying the final release just makes the problem
+worse; the pile of changes waiting for the next merge window will grow
+larger, creating even more regressions the next time around.  So most 2.6.x
+kernels go out with a handful of known regressions though, hopefully, none
+of them are serious.
+Once a stable release is made, its ongoing maintenance is passed off to the
+"stable team," currently comprised of Greg Kroah-Hartman and Chris Wright.
+The stable team will release occasional updates to the stable release using
+the 2.6.x.y numbering scheme.  To be considered for an update release, a
+patch must (1) fix a significant bug, and (2) already be merged into the
+mainline for the next development kernel.  Continuing our 2.6.25 example,
+the history (as of this writing) is:
+        May 1           2.6.25.1
+        May 6           2.6.25.2 
+        May 9           2.6.25.3 
+        May 15          2.6.25.4
+        June 7          2.6.25.5
+        June 9          2.6.25.6
+        June 16         2.6.25.7
+        June 21         2.6.25.8
+        June 24         2.6.25.9
+Stable updates for a given kernel are made for approximately six months;
+after that, the maintenance of stable releases is solely the responsibility
+of the distributors which have shipped that particular kernel.
+2.2: THE LIFECYCLE OF A PATCH
+Patches do not go directly from the developer's keyboard into the mainline
+kernel.  There is, instead, a somewhat involved (if somewhat informal)
+process designed to ensure that each patch is reviewed for quality and that
+each patch implements a change which is desirable to have in the mainline.
+This process can happen quickly for minor fixes, or, in the case of large
+and controversial changes, go on for years.  Much developer frustration
+comes from a lack of understanding of this process or from attempts to
+circumvent it.  
+In the hopes of reducing that frustration, this document will describe how
+a patch gets into the kernel.  What follows below is an introduction which
+describes the process in a somewhat idealized way.  A much more detailed
+treatment will come in later sections.
+The stages that a patch goes through are, generally:
+ - Design.  This is where the real requirements for the patch - and the way
+   those requirements will be met - are laid out.  Design work is often
+   done without involving the community, but it is better to do this work
+   in the open if at all possible; it can save a lot of time redesigning
+   things later.
+ - Early review.  Patches are posted to the relevant mailing list, and
+   developers on that list reply with any comments they may have.  This
+   process should turn up any major problems with a patch if all goes
+   well.
+ - Wider review.  When the patch is getting close to ready for mainline
+   inclusion, it will be accepted by a relevant subsystem maintainer -
+   though this acceptance is not a guarantee that the patch will make it
+   all the way to the mainline.  The patch will show up in the maintainer's
+   subsystem tree and into the staging trees (described below).  When the
+   process works, this step leads to more extensive review of the patch and
+   the discovery of any problems resulting from the integration of this
+   patch with work being done by others.
+ - Merging into the mainline.  Eventually, a successful patch will be
+   merged into the mainline repository managed by Linus Torvalds.  More
+   comments and/or problems may surface at this time; it is important that
+   the developer be responsive to these and fix any issues which arise.
+ - Stable release.  The number of users potentially affected by the patch
+   is now large, so, once again, new problems may arise.
+ - Long-term maintenance.  While it is certainly possible for a developer
+   to forget about code after merging it, that sort of behavior tends to
+   leave a poor impression in the development community.  Merging code
+   eliminates some of the maintenance burden, in that others will fix
+   problems caused by API changes.  But the original developer should
+   continue to take responsibility for the code if it is to remain useful
+   in the longer term.
+One of the largest mistakes made by kernel developers (or their employers)
+is to try to cut the process down to a single "merging into the mainline"
+step.  This approach invariably leads to frustration for everybody
+involved.
+2.3: HOW PATCHES GET INTO THE KERNEL
+There is exactly one person who can merge patches into the mainline kernel
+repository: Linus Torvalds.  But, of the over 12,000 patches which went
+into the 2.6.25 kernel, only 250 (around 2%) were directly chosen by Linus
+himself.  The kernel project has long since grown to a size where no single
+developer could possibly inspect and select every patch unassisted.  The
+way the kernel developers have addressed this growth is through the use of
+a lieutenant system built around a chain of trust.
+The kernel code base is logically broken down into a set of subsystems:
+networking, specific architecture support, memory management, video
+devices, etc.  Most subsystems have a designated maintainer, a developer
+who has overall responsibility for the code within that subsystem.  These
+subsystem maintainers are the gatekeepers (in a loose way) for the portion
+of the kernel they manage; they are the ones who will (usually) accept a
+patch for inclusion into the mainline kernel.
+Subsystem maintainers each manage their own version of the kernel source
+tree, usually (but certainly not always) using the git source management
+tool.  Tools like git (and related tools like quilt or mercurial) allow
+maintainers to track a list of patches, including authorship information
+and other metadata.  At any given time, the maintainer can identify which
+patches in his or her repository are not found in the mainline.
+When the merge window opens, top-level maintainers will ask Linus to "pull"
+the patches they have selected for merging from their repositories.  If
+Linus agrees, the stream of patches will flow up into his repository,
+becoming part of the mainline kernel.  The amount of attention that Linus
+pays to specific patches received in a pull operation varies.  It is clear
+that, sometimes, he looks quite closely.  But, as a general rule, Linus
+trusts the subsystem maintainers to not send bad patches upstream.
+Subsystem maintainers, in turn, can pull patches from other maintainers.
+For example, the networking tree is built from patches which accumulated
+first in trees dedicated to network device drivers, wireless networking,
+etc.  This chain of repositories can be arbitrarily long, though it rarely
+exceeds two or three links.  Since each maintainer in the chain trusts
+those managing lower-level trees, this process is known as the "chain of
+trust." 
+Clearly, in a system like this, getting patches into the kernel depends on
+finding the right maintainer.  Sending patches directly to Linus is not
+normally the right way to go.
+2.4: STAGING TREES
+The chain of subsystem trees guides the flow of patches into the kernel,
+but it also raises an interesting question: what if somebody wants to look
+at all of the patches which are being prepared for the next merge window?
+Developers will be interested in what other changes are pending to see
+whether there are any conflicts to worry about; a patch which changes a
+core kernel function prototype, for example, will conflict with any other
+patches which use the older form of that function.  Reviewers and testers
+want access to the changes in their integrated form before all of those
+changes land in the mainline kernel.  One could pull changes from all of
+the interesting subsystem trees, but that would be a big and error-prone
+job.
+The answer comes in the form of staging trees, where subsystem trees are
+collected for testing and review.  The older of these trees, maintained by
+Andrew Morton, is called "-mm" (for memory management, which is how it got
+started).  The -mm tree integrates patches from a long list of subsystem
+trees; it also has some patches aimed at helping with debugging.  
+Beyond that, -mm contains a significant collection of patches which have
+been selected by Andrew directly.  These patches may have been posted on a
+mailing list, or they may apply to a part of the kernel for which there is
+no designated subsystem tree.  As a result, -mm operates as a sort of
+subsystem tree of last resort; if there is no other obvious path for a
+patch into the mainline, it is likely to end up in -mm.  Miscellaneous
+patches which accumulate in -mm will eventually either be forwarded on to
+an appropriate subsystem tree or be sent directly to Linus.  In a typical
+development cycle, approximately 10% of the patches going into the mainline
+get there via -mm.
+The current -mm patch can always be found from the front page of
+        http://kernel.org/
+Those who want to see the current state of -mm can get the "-mm of the
+moment" tree, found at:
+        http://userweb.kernel.org/~akpm/mmotm/
+Use of the MMOTM tree is likely to be a frustrating experience, though;
+there is a definite chance that it will not even compile.
+The other staging tree, started more recently, is linux-next, maintained by
+Stephen Rothwell.  The linux-next tree is, by design, a snapshot of what
+the mainline is expected to look like after the next merge window closes.
+Linux-next trees are announced on the linux-kernel and linux-next mailing
+lists when they are assembled; they can be downloaded from:
+        http://www.kernel.org/pub/linux/kernel/people/sfr/linux-next/
+Some information about linux-next has been gathered at:
+        http://linux.f-seidel.de/linux-next/pmwiki/
+How the linux-next tree will fit into the development process is still
+changing.  As of this writing, the first full development cycle involving
+linux-next (2.6.26) is coming to an end; thus far, it has proved to be a
+valuable resource for finding and fixing integration problems before the
+beginning of the merge window.  See http://lwn.net/Articles/287155/ for
+more information on how linux-next has worked to set up the 2.6.27 merge
+window.
+Some developers have begun to suggest that linux-next should be used as the
+target for future development as well.  The linux-next tree does tend to be
+far ahead of the mainline and is more representative of the tree into which
+any new work will be merged.  The downside to this idea is that the
+volatility of linux-next tends to make it a difficult development target.
+See http://lwn.net/Articles/289013/ for more information on this topic, and
+stay tuned; much is still in flux where linux-next is involved.
+2.5: TOOLS
+As can be seen from the above text, the kernel development process depends
+heavily on the ability to herd collections of patches in various
+directions.  The whole thing would not work anywhere near as well as it
+does without suitably powerful tools.  Tutorials on how to use these tools
+are well beyond the scope of this document, but there is space for a few
+pointers.
+By far the dominant source code management system used by the kernel
+community is git.  Git is one of a number of distributed version control
+systems being developed in the free software community.  It is well tuned
+for kernel development, in that it performs quite well when dealing with
+large repositories and large numbers of patches.  It also has a reputation
+for being difficult to learn and use, though it has gotten better over
+time.  Some sort of familiarity with git is almost a requirement for kernel
+developers; even if they do not use it for their own work, they'll need git
+to keep up with what other developers (and the mainline) are doing.
+Git is now packaged by almost all Linux distributions.  There is a home
+page at 
+        http://git.or.cz/
+That page has pointers to documentation and tutorials.  One should be
+aware, in particular, of the Kernel Hacker's Guide to git, which has
+information specific to kernel development:
+        http://linux.yyz.us/git-howto.html
+Among the kernel developers who do not use git, the most popular choice is
+almost certainly Mercurial:
+        http://www.selenic.com/mercurial/
+Mercurial shares many features with git, but it provides an interface which
+many find easier to use.
+The other tool worth knowing about is Quilt:
+        http://savannah.nongnu.org/projects/quilt/
+Quilt is a patch management system, rather than a source code management
+system.  It does not track history over time; it is, instead, oriented
+toward tracking a specific set of changes against an evolving code base.
+Some major subsystem maintainers use quilt to manage patches intended to go
+upstream.  For the management of certain kinds of trees (-mm, for example),
+quilt is the best tool for the job.
+2.6: MAILING LISTS
+A great deal of Linux kernel development work is done by way of mailing
+lists.  It is hard to be a fully-functioning member of the community
+without joining at least one list somewhere.  But Linux mailing lists also
+represent a potential hazard to developers, who risk getting buried under a
+load of electronic mail, running afoul of the conventions used on the Linux
+lists, or both.
+Most kernel mailing lists are run on vger.kernel.org; the master list can
+be found at:
+        http://vger.kernel.org/vger-lists.html
+There are lists hosted elsewhere, though; a number of them are at
+lists.redhat.com.
+The core mailing list for kernel development is, of course, linux-kernel.
+This list is an intimidating place to be; volume can reach 500 messages per
+day, the amount of noise is high, the conversation can be severely
+technical, and participants are not always concerned with showing a high
+degree of politeness.  But there is no other place where the kernel
+development community comes together as a whole; developers who avoid this
+list will miss important information.
+There are a few hints which can help with linux-kernel survival:
+- Have the list delivered to a separate folder, rather than your main
+  mailbox.  One must be able to ignore the stream for sustained periods of
+  time.
+- Do not try to follow every conversation - nobody else does.  It is
+  important to filter on both the topic of interest (though note that
+  long-running conversations can drift away from the original subject
+  without changing the email subject line) and the people who are
+  participating.  
+- Do not feed the trolls.  If somebody is trying to stir up an angry
+  response, ignore them.
+- When responding to linux-kernel email (or that on other lists) preserve
+  the Cc: header for all involved.  In the absence of a strong reason (such
+  as an explicit request), you should never remove recipients.  Always make
+  sure that the person you are responding to is in the Cc: list.  This
+  convention also makes it unnecessary to explicitly ask to be copied on
+  replies to your postings.
+- Search the list archives (and the net as a whole) before asking
+  questions.  Some developers can get impatient with people who clearly
+  have not done their homework.
+- Avoid top-posting (the practice of putting your answer above the quoted
+  text you are responding to).  It makes your response harder to read and
+  makes a poor impression.
+- Ask on the correct mailing list.  Linux-kernel may be the general meeting
+  point, but it is not the best place to find developers from all
+  subsystems.
+The last point - finding the correct mailing list - is a common place for
+beginning developers to go wrong.  Somebody who asks a networking-related
+question on linux-kernel will almost certainly receive a polite suggestion
+to ask on the netdev list instead, as that is the list frequented by most
+networking developers.  Other lists exist for the SCSI, video4linux, IDE,
+filesystem, etc. subsystems.  The best place to look for mailing lists is
+in the MAINTAINERS file packaged with the kernel source.
+2.7: GETTING STARTED WITH KERNEL DEVELOPMENT
+Questions about how to get started with the kernel development process are
+common - from both individuals and companies.  Equally common are missteps
+which make the beginning of the relationship harder than it has to be.
+Companies often look to hire well-known developers to get a development
+group started.  This can, in fact, be an effective technique.  But it also
+tends to be expensive and does not do much to grow the pool of experienced
+kernel developers.  It is possible to bring in-house developers up to speed
+on Linux kernel development, given the investment of a bit of time.  Taking
+this time can endow an employer with a group of developers who understand
+the kernel and the company both, and who can help to train others as well.
+Over the medium term, this is often the more profitable approach.
+Individual developers are often, understandably, at a loss for a place to
+start.  Beginning with a large project can be intimidating; one often wants
+to test the waters with something smaller first.  This is the point where
+some developers jump into the creation of patches fixing spelling errors or
+minor coding style issues.  Unfortunately, such patches create a level of
+noise which is distracting for the development community as a whole, so,
+increasingly, they are looked down upon.  New developers wishing to
+introduce themselves to the community will not get the sort of reception
+they wish for by these means.
+Andrew Morton gives this advice for aspiring kernel developers
+        The #1 project for all kernel beginners should surely be "make sure
+        that the kernel runs perfectly at all times on all machines which
+        you can lay your hands on".  Usually the way to do this is to work
+        with others on getting things fixed up (this can require
+        persistence!) but that's fine - it's a part of kernel development.
+(http://lwn.net/Articles/283982/).
+In the absence of obvious problems to fix, developers are advised to look
+at the current lists of regressions and open bugs in general.  There is
+never any shortage of issues in need of fixing; by addressing these issues,
+developers will gain experience with the process while, at the same time,
+building respect with the rest of the development community.
diff --git a/Documentation/development-process/3.Early-stage b/Documentation/development-process/3.Early-stage
new file mode 100644
index 000000000000..307a159a70ca
--- /dev/null
+++ b/Documentation/development-process/3.Early-stage
@@ -0,0 +1,195 @@
+3: EARLY-STAGE PLANNING
+When contemplating a Linux kernel development project, it can be tempting
+to jump right in and start coding.  As with any significant project,
+though, much of the groundwork for success is best laid before the first
+line of code is written.  Some time spent in early planning and
+communication can save far more time later on.
+3.1: SPECIFYING THE PROBLEM
+Like any engineering project, a successful kernel enhancement starts with a
+clear description of the problem to be solved.  In some cases, this step is
+easy: when a driver is needed for a specific piece of hardware, for
+example.  In others, though, it is tempting to confuse the real problem
+with the proposed solution, and that can lead to difficulties.
+Consider an example: some years ago, developers working with Linux audio
+sought a way to run applications without dropouts or other artifacts caused
+by excessive latency in the system.  The solution they arrived at was a
+kernel module intended to hook into the Linux Security Module (LSM)
+framework; this module could be configured to give specific applications
+access to the realtime scheduler.  This module was implemented and sent to
+the linux-kernel mailing list, where it immediately ran into problems.
+To the audio developers, this security module was sufficient to solve their
+immediate problem.  To the wider kernel community, though, it was seen as a
+misuse of the LSM framework (which is not intended to confer privileges
+onto processes which they would not otherwise have) and a risk to system
+stability.  Their preferred solutions involved realtime scheduling access
+via the rlimit mechanism for the short term, and ongoing latency reduction
+work in the long term.
+The audio community, however, could not see past the particular solution
+they had implemented; they were unwilling to accept alternatives.  The
+resulting disagreement left those developers feeling disillusioned with the
+entire kernel development process; one of them went back to an audio list
+and posted this:
+        There are a number of very good Linux kernel developers, but they
+        tend to get outshouted by a large crowd of arrogant fools. Trying
+        to communicate user requirements to these people is a waste of
+        time. They are much too "intelligent" to listen to lesser mortals.
+(http://lwn.net/Articles/131776/).
+The reality of the situation was different; the kernel developers were far
+more concerned about system stability, long-term maintenance, and finding
+the right solution to the problem than they were with a specific module.
+The moral of the story is to focus on the problem - not a specific solution
+- and to discuss it with the development community before investing in the
+creation of a body of code.
+So, when contemplating a kernel development project, one should obtain
+answers to a short set of questions:
+ - What, exactly, is the problem which needs to be solved?
+ - Who are the users affected by this problem?  Which use cases should the
+   solution address?
+ - How does the kernel fall short in addressing that problem now?
+Only then does it make sense to start considering possible solutions.
+3.2: EARLY DISCUSSION
+When planning a kernel development project, it makes great sense to hold
+discussions with the community before launching into implementation.  Early
+communication can save time and trouble in a number of ways:
+ - It may well be that the problem is addressed by the kernel in ways which
+   you have not understood.  The Linux kernel is large and has a number of
+   features and capabilities which are not immediately obvious.  Not all
+   kernel capabilities are documented as well as one might like, and it is
+   easy to miss things.  Your author has seen the posting of a complete
+   driver which duplicated an existing driver that the new author had been
+   unaware of.  Code which reinvents existing wheels is not only wasteful;
+   it will also not be accepted into the mainline kernel.
+ - There may be elements of the proposed solution which will not be
+   acceptable for mainline merging.  It is better to find out about
+   problems like this before writing the code.
+ - It's entirely possible that other developers have thought about the
+   problem; they may have ideas for a better solution, and may be willing
+   to help in the creation of that solution.
+Years of experience with the kernel development community have taught a
+clear lesson: kernel code which is designed and developed behind closed
+doors invariably has problems which are only revealed when the code is
+released into the community.  Sometimes these problems are severe,
+requiring months or years of effort before the code can be brought up to
+the kernel community's standards.  Some examples include:
+ - The Devicescape network stack was designed and implemented for
+   single-processor systems.  It could not be merged into the mainline
+   until it was made suitable for multiprocessor systems.  Retrofitting
+   locking and such into code is a difficult task; as a result, the merging
+   of this code (now called mac80211) was delayed for over a year.
+ - The Reiser4 filesystem included a number of capabilities which, in the
+   core kernel developers' opinion, should have been implemented in the
+   virtual filesystem layer instead.  It also included features which could
+   not easily be implemented without exposing the system to user-caused
+   deadlocks.  The late revelation of these problems - and refusal to
+   address some of them - has caused Reiser4 to stay out of the mainline
+   kernel.
+ - The AppArmor security module made use of internal virtual filesystem
+   data structures in ways which were considered to be unsafe and
+   unreliable.  This code has since been significantly reworked, but
+   remains outside of the mainline.
+In each of these cases, a great deal of pain and extra work could have been
+avoided with some early discussion with the kernel developers.
+3.3: WHO DO YOU TALK TO?
+When developers decide to take their plans public, the next question will
+be: where do we start?  The answer is to find the right mailing list(s) and
+the right maintainer.  For mailing lists, the best approach is to look in
+the MAINTAINERS file for a relevant place to post.  If there is a suitable
+subsystem list, posting there is often preferable to posting on
+linux-kernel; you are more likely to reach developers with expertise in the
+relevant subsystem and the environment may be more supportive.
+Finding maintainers can be a bit harder.  Again, the MAINTAINERS file is
+the place to start.  That file tends to not always be up to date, though,
+and not all subsystems are represented there.  The person listed in the
+MAINTAINERS file may, in fact, not be the person who is actually acting in
+that role currently.  So, when there is doubt about who to contact, a
+useful trick is to use git (and "git log" in particular) to see who is
+currently active within the subsystem of interest.  Look at who is writing
+patches, and who, if anybody, is attaching Signed-off-by lines to those
+patches.  Those are the people who will be best placed to help with a new
+development project.
+If all else fails, talking to Andrew Morton can be an effective way to
+track down a maintainer for a specific piece of code.
+3.4: WHEN TO POST?
+If possible, posting your plans during the early stages can only be
+helpful.  Describe the problem being solved and any plans that have been
+made on how the implementation will be done.  Any information you can
+provide can help the development community provide useful input on the
+project.
+One discouraging thing which can happen at this stage is not a hostile
+reaction, but, instead, little or no reaction at all.  The sad truth of the
+matter is (1) kernel developers tend to be busy, (2) there is no shortage
+of people with grand plans and little code (or even prospect of code) to
+back them up, and (3) nobody is obligated to review or comment on ideas
+posted by others.  If a request-for-comments posting yields little in the
+way of comments, do not assume that it means there is no interest in the
+project.  Unfortunately, you also cannot assume that there are no problems
+with your idea.  The best thing to do in this situation is to proceed,
+keeping the community informed as you go.
+3.5: GETTING OFFICIAL BUY-IN
+If your work is being done in a corporate environment - as most Linux
+kernel work is - you must, obviously, have permission from suitably
+empowered managers before you can post your company's plans or code to a
+public mailing list.  The posting of code which has not been cleared for
+release under a GPL-compatible license can be especially problematic; the
+sooner that a company's management and legal staff can agree on the posting
+of a kernel development project, the better off everybody involved will be.
+Some readers may be thinking at this point that their kernel work is
+intended to support a product which does not yet have an officially
+acknowledged existence.  Revealing their employer's plans on a public
+mailing list may not be a viable option.  In cases like this, it is worth
+considering whether the secrecy is really necessary; there is often no real
+need to keep development plans behind closed doors.
+That said, there are also cases where a company legitimately cannot
+disclose its plans early in the development process.  Companies with
+experienced kernel developers may choose to proceed in an open-loop manner
+on the assumption that they will be able to avoid serious integration
+problems later.  For companies without that sort of in-house expertise, the
+best option is often to hire an outside developer to review the plans under
+a non-disclosure agreement.  The Linux Foundation operates an NDA program
+designed to help with this sort of situation; more information can be found
+at:
+    http://www.linuxfoundation.org/en/NDA_program
+This kind of review is often enough to avoid serious problems later on
+without requiring public disclosure of the project.
diff --git a/Documentation/development-process/4.Coding b/Documentation/development-process/4.Coding
new file mode 100644
index 000000000000..014aca8f14e2
--- /dev/null
+++ b/Documentation/development-process/4.Coding
@@ -0,0 +1,384 @@
+4: GETTING THE CODE RIGHT
+While there is much to be said for a solid and community-oriented design
+process, the proof of any kernel development project is in the resulting
+code.  It is the code which will be examined by other developers and merged
+(or not) into the mainline tree.  So it is the quality of this code which
+will determine the ultimate success of the project.
+This section will examine the coding process.  We'll start with a look at a
+number of ways in which kernel developers can go wrong.  Then the focus
+will shift toward doing things right and the tools which can help in that
+quest.
+4.1: PITFALLS
+* Coding style
+The kernel has long had a standard coding style, described in
+Documentation/CodingStyle.  For much of that time, the policies described
+in that file were taken as being, at most, advisory.  As a result, there is
+a substantial amount of code in the kernel which does not meet the coding
+style guidelines.  The presence of that code leads to two independent
+hazards for kernel developers.
+The first of these is to believe that the kernel coding standards do not
+matter and are not enforced.  The truth of the matter is that adding new
+code to the kernel is very difficult if that code is not coded according to
+the standard; many developers will request that the code be reformatted
+before they will even review it.  A code base as large as the kernel
+requires some uniformity of code to make it possible for developers to
+quickly understand any part of it.  So there is no longer room for
+strangely-formatted code.
+Occasionally, the kernel's coding style will run into conflict with an
+employer's mandated style.  In such cases, the kernel's style will have to
+win before the code can be merged.  Putting code into the kernel means
+giving up a degree of control in a number of ways - including control over
+how the code is formatted.
+The other trap is to assume that code which is already in the kernel is
+urgently in need of coding style fixes.  Developers may start to generate
+reformatting patches as a way of gaining familiarity with the process, or
+as a way of getting their name into the kernel changelogs - or both.  But
+pure coding style fixes are seen as noise by the development community;
+they tend to get a chilly reception.  So this type of patch is best
+avoided.  It is natural to fix the style of a piece of code while working
+on it for other reasons, but coding style changes should not be made for
+their own sake.
+The coding style document also should not be read as an absolute law which
+can never be transgressed.  If there is a good reason to go against the
+style (a line which becomes far less readable if split to fit within the
+80-column limit, for example), just do it.
+* Abstraction layers
+Computer Science professors teach students to make extensive use of
+abstraction layers in the name of flexibility and information hiding.
+Certainly the kernel makes extensive use of abstraction; no project
+involving several million lines of code could do otherwise and survive.
+But experience has shown that excessive or premature abstraction can be
+just as harmful as premature optimization.  Abstraction should be used to
+the level required and no further.
+At a simple level, consider a function which has an argument which is
+always passed as zero by all callers.  One could retain that argument just
+in case somebody eventually needs to use the extra flexibility that it
+provides.  By that time, though, chances are good that the code which
+implements this extra argument has been broken in some subtle way which was
+never noticed - because it has never been used.  Or, when the need for
+extra flexibility arises, it does not do so in a way which matches the
+programmer's early expectation.  Kernel developers will routinely submit
+patches to remove unused arguments; they should, in general, not be added
+in the first place.
+Abstraction layers which hide access to hardware - often to allow the bulk
+of a driver to be used with multiple operating systems - are especially
+frowned upon.  Such layers obscure the code and may impose a performance
+penalty; they do not belong in the Linux kernel.
+On the other hand, if you find yourself copying significant amounts of code
+from another kernel subsystem, it is time to ask whether it would, in fact,
+make sense to pull out some of that code into a separate library or to
+implement that functionality at a higher level.  There is no value in
+replicating the same code throughout the kernel.
+* #ifdef and preprocessor use in general
+The C preprocessor seems to present a powerful temptation to some C
+programmers, who see it as a way to efficiently encode a great deal of
+flexibility into a source file.  But the preprocessor is not C, and heavy
+use of it results in code which is much harder for others to read and
+harder for the compiler to check for correctness.  Heavy preprocessor use
+is almost always a sign of code which needs some cleanup work.
+Conditional compilation with #ifdef is, indeed, a powerful feature, and it
+is used within the kernel.  But there is little desire to see code which is
+sprinkled liberally with #ifdef blocks.  As a general rule, #ifdef use
+should be confined to header files whenever possible.
+Conditionally-compiled code can be confined to functions which, if the code
+is not to be present, simply become empty.  The compiler will then quietly
+optimize out the call to the empty function.  The result is far cleaner
+code which is easier to follow.
+C preprocessor macros present a number of hazards, including possible
+multiple evaluation of expressions with side effects and no type safety.
+If you are tempted to define a macro, consider creating an inline function
+instead.  The code which results will be the same, but inline functions are
+easier to read, do not evaluate their arguments multiple times, and allow
+the compiler to perform type checking on the arguments and return value.
+* Inline functions
+Inline functions present a hazard of their own, though.  Programmers can
+become enamored of the perceived efficiency inherent in avoiding a function
+call and fill a source file with inline functions.  Those functions,
+however, can actually reduce performance.  Since their code is replicated
+at each call site, they end up bloating the size of the compiled kernel.
+That, in turn, creates pressure on the processor's memory caches, which can
+slow execution dramatically.  Inline functions, as a rule, should be quite
+small and relatively rare.  The cost of a function call, after all, is not
+that high; the creation of large numbers of inline functions is a classic
+example of premature optimization.
+In general, kernel programmers ignore cache effects at their peril.  The
+classic time/space tradeoff taught in beginning data structures classes
+often does not apply to contemporary hardware.  Space *is* time, in that a
+larger program will run slower than one which is more compact.
+* Locking
+In May, 2006, the "Devicescape" networking stack was, with great
+fanfare, released under the GPL and made available for inclusion in the
+mainline kernel.  This donation was welcome news; support for wireless
+networking in Linux was considered substandard at best, and the Devicescape
+stack offered the promise of fixing that situation.  Yet, this code did not
+actually make it into the mainline until June, 2007 (2.6.22).  What
+happened?
+This code showed a number of signs of having been developed behind
+corporate doors.  But one large problem in particular was that it was not
+designed to work on multiprocessor systems.  Before this networking stack
+(now called mac80211) could be merged, a locking scheme needed to be
+retrofitted onto it.  
+Once upon a time, Linux kernel code could be developed without thinking
+about the concurrency issues presented by multiprocessor systems.  Now,
+however, this document is being written on a dual-core laptop.  Even on
+single-processor systems, work being done to improve responsiveness will
+raise the level of concurrency within the kernel.  The days when kernel
+code could be written without thinking about locking are long past.
+Any resource (data structures, hardware registers, etc.) which could be
+accessed concurrently by more than one thread must be protected by a lock.
+New code should be written with this requirement in mind; retrofitting
+locking after the fact is a rather more difficult task.  Kernel developers
+should take the time to understand the available locking primitives well
+enough to pick the right tool for the job.  Code which shows a lack of
+attention to concurrency will have a difficult path into the mainline.
+* Regressions
+One final hazard worth mentioning is this: it can be tempting to make a
+change (which may bring big improvements) which causes something to break
+for existing users.  This kind of change is called a "regression," and
+regressions have become most unwelcome in the mainline kernel.  With few
+exceptions, changes which cause regressions will be backed out if the
+regression cannot be fixed in a timely manner.  Far better to avoid the
+regression in the first place.
+It is often argued that a regression can be justified if it causes things
+to work for more people than it creates problems for.  Why not make a
+change if it brings new functionality to ten systems for each one it
+breaks?  The best answer to this question was expressed by Linus in July,
+2007:
+        So we don't fix bugs by introducing new problems.  That way lies
+        madness, and nobody ever knows if you actually make any real
+        progress at all. Is it two steps forwards, one step back, or one
+        step forward and two steps back?
+(http://lwn.net/Articles/243460/).
+An especially unwelcome type of regression is any sort of change to the
+user-space ABI.  Once an interface has been exported to user space, it must
+be supported indefinitely.  This fact makes the creation of user-space
+interfaces particularly challenging: since they cannot be changed in
+incompatible ways, they must be done right the first time.  For this
+reason, a great deal of thought, clear documentation, and wide review for
+user-space interfaces is always required.
+4.2: CODE CHECKING TOOLS
+For now, at least, the writing of error-free code remains an ideal that few
+of us can reach.  What we can hope to do, though, is to catch and fix as
+many of those errors as possible before our code goes into the mainline
+kernel.  To that end, the kernel developers have put together an impressive
+array of tools which can catch a wide variety of obscure problems in an
+automated way.  Any problem caught by the computer is a problem which will
+not afflict a user later on, so it stands to reason that the automated
+tools should be used whenever possible.
+The first step is simply to heed the warnings produced by the compiler.
+Contemporary versions of gcc can detect (and warn about) a large number of
+potential errors.  Quite often, these warnings point to real problems.
+Code submitted for review should, as a rule, not produce any compiler
+warnings.  When silencing warnings, take care to understand the real cause
+and try to avoid "fixes" which make the warning go away without addressing
+its cause.
+Note that not all compiler warnings are enabled by default.  Build the
+kernel with "make EXTRA_CFLAGS=-W" to get the full set.
+The kernel provides several configuration options which turn on debugging
+features; most of these are found in the "kernel hacking" submenu.  Several
+of these options should be turned on for any kernel used for development or
+testing purposes.  In particular, you should turn on:
+ - ENABLE_WARN_DEPRECATED, ENABLE_MUST_CHECK, and FRAME_WARN to get an
+   extra set of warnings for problems like the use of deprecated interfaces
+   or ignoring an important return value from a function.  The output
+   generated by these warnings can be verbose, but one need not worry about
+   warnings from other parts of the kernel.
+ - DEBUG_OBJECTS will add code to track the lifetime of various objects
+   created by the kernel and warn when things are done out of order.  If
+   you are adding a subsystem which creates (and exports) complex objects
+   of its own, consider adding support for the object debugging
+   infrastructure.
+ - DEBUG_SLAB can find a variety of memory allocation and use errors; it
+   should be used on most development kernels.
+ - DEBUG_SPINLOCK, DEBUG_SPINLOCK_SLEEP, and DEBUG_MUTEXES will find a
+   number of common locking errors.
+There are quite a few other debugging options, some of which will be
+discussed below.  Some of them have a significant performance impact and
+should not be used all of the time.  But some time spent learning the
+available options will likely be paid back many times over in short order. 
+One of the heavier debugging tools is the locking checker, or "lockdep."
+This tool will track the acquisition and release of every lock (spinlock or
+mutex) in the system, the order in which locks are acquired relative to
+each other, the current interrupt environment, and more.  It can then
+ensure that locks are always acquired in the same order, that the same
+interrupt assumptions apply in all situations, and so on.  In other words,
+lockdep can find a number of scenarios in which the system could, on rare
+occasion, deadlock.  This kind of problem can be painful (for both
+developers and users) in a deployed system; lockdep allows them to be found
+in an automated manner ahead of time.  Code with any sort of non-trivial
+locking should be run with lockdep enabled before being submitted for
+inclusion. 
+As a diligent kernel programmer, you will, beyond doubt, check the return
+status of any operation (such as a memory allocation) which can fail.  The
+fact of the matter, though, is that the resulting failure recovery paths
+are, probably, completely untested.  Untested code tends to be broken code;
+you could be much more confident of your code if all those error-handling
+paths had been exercised a few times.
+The kernel provides a fault injection framework which can do exactly that,
+especially where memory allocations are involved.  With fault injection
+enabled, a configurable percentage of memory allocations will be made to
+fail; these failures can be restricted to a specific range of code.
+Running with fault injection enabled allows the programmer to see how the
+code responds when things go badly.  See
+Documentation/fault-injection/fault-injection.text for more information on
+how to use this facility.
+Other kinds of errors can be found with the "sparse" static analysis tool.
+With sparse, the programmer can be warned about confusion between
+user-space and kernel-space addresses, mixture of big-endian and
+small-endian quantities, the passing of integer values where a set of bit
+flags is expected, and so on.  Sparse must be installed separately (it can
+be found at http://www.kernel.org/pub/software/devel/sparse/ if your
+distributor does not package it); it can then be run on the code by adding
+"C=1" to your make command.
+Other kinds of portability errors are best found by compiling your code for
+other architectures.  If you do not happen to have an S/390 system or a
+Blackfin development board handy, you can still perform the compilation
+step.  A large set of cross compilers for x86 systems can be found at 
+        http://www.kernel.org/pub/tools/crosstool/
+Some time spent installing and using these compilers will help avoid
+embarrassment later.
+4.3: DOCUMENTATION
+Documentation has often been more the exception than the rule with kernel
+development.  Even so, adequate documentation will help to ease the merging
+of new code into the kernel, make life easier for other developers, and
+will be helpful for your users.  In many cases, the addition of
+documentation has become essentially mandatory.
+The first piece of documentation for any patch is its associated
+changelog.  Log entries should describe the problem being solved, the form
+of the solution, the people who worked on the patch, any relevant
+effects on performance, and anything else that might be needed to
+understand the patch.
+Any code which adds a new user-space interface - including new sysfs or
+/proc files - should include documentation of that interface which enables
+user-space developers to know what they are working with.  See
+Documentation/ABI/README for a description of how this documentation should
+be formatted and what information needs to be provided.
+The file Documentation/kernel-parameters.txt describes all of the kernel's
+boot-time parameters.  Any patch which adds new parameters should add the
+appropriate entries to this file.
+Any new configuration options must be accompanied by help text which
+clearly explains the options and when the user might want to select them. 
+Internal API information for many subsystems is documented by way of
+specially-formatted comments; these comments can be extracted and formatted
+in a number of ways by the "kernel-doc" script.  If you are working within
+a subsystem which has kerneldoc comments, you should maintain them and add
+them, as appropriate, for externally-available functions.  Even in areas
+which have not been so documented, there is no harm in adding kerneldoc
+comments for the future; indeed, this can be a useful activity for
+beginning kernel developers.  The format of these comments, along with some
+information on how to create kerneldoc templates can be found in the file
+Documentation/kernel-doc-nano-HOWTO.txt.
+Anybody who reads through a significant amount of existing kernel code will
+note that, often, comments are most notable by their absence.  Once again,
+the expectations for new code are higher than they were in the past;
+merging uncommented code will be harder.  That said, there is little desire
+for verbosely-commented code.  The code should, itself, be readable, with
+comments explaining the more subtle aspects.
+Certain things should always be commented.  Uses of memory barriers should
+be accompanied by a line explaining why the barrier is necessary.  The
+locking rules for data structures generally need to be explained somewhere.
+Major data structures need comprehensive documentation in general.
+Non-obvious dependencies between separate bits of code should be pointed
+out.  Anything which might tempt a code janitor to make an incorrect
+"cleanup" needs a comment saying why it is done the way it is.  And so on.
+4.4: INTERNAL API CHANGES
+The binary interface provided by the kernel to user space cannot be broken
+except under the most severe circumstances.  The kernel's internal
+programming interfaces, instead, are highly fluid and can be changed when
+the need arises.  If you find yourself having to work around a kernel API,
+or simply not using a specific functionality because it does not meet your
+needs, that may be a sign that the API needs to change.  As a kernel
+developer, you are empowered to make such changes.
+There are, of course, some catches.  API changes can be made, but they need
+to be well justified.  So any patch making an internal API change should be
+accompanied by a description of what the change is and why it is
+necessary.  This kind of change should also be broken out into a separate
+patch, rather than buried within a larger patch.
+The other catch is that a developer who changes an internal API is
+generally charged with the task of fixing any code within the kernel tree
+which is broken by the change.  For a widely-used function, this duty can
+lead to literally hundreds or thousands of changes - many of which are
+likely to conflict with work being done by other developers.  Needless to
+say, this can be a large job, so it is best to be sure that the
+justification is solid.
+When making an incompatible API change, one should, whenever possible,
+ensure that code which has not been updated is caught by the compiler.  
+This will help you to be sure that you have found all in-tree uses of that
+interface.  It will also alert developers of out-of-tree code that there is
+a change that they need to respond to.  Supporting out-of-tree code is not
+something that kernel developers need to be worried about, but we also do
+not have to make life harder for out-of-tree developers than it it needs to
+be. 
diff --git a/Documentation/development-process/5.Posting b/Documentation/development-process/5.Posting
new file mode 100644
index 000000000000..dd48132a74dd
--- /dev/null
+++ b/Documentation/development-process/5.Posting
@@ -0,0 +1,278 @@
+5: POSTING PATCHES
+Sooner or later, the time comes when your work is ready to be presented to
+the community for review and, eventually, inclusion into the mainline
+kernel.  Unsurprisingly, the kernel development community has evolved a set
+of conventions and procedures which are used in the posting of patches;
+following them will make life much easier for everybody involved.  This
+document will attempt to cover these expectations in reasonable detail;
+more information can also be found in the files SubmittingPatches,
+SubmittingDrivers, and SubmitChecklist in the kernel documentation
+directory.
+5.1: WHEN TO POST
+There is a constant temptation to avoid posting patches before they are
+completely "ready."  For simple patches, that is not a problem.  If the
+work being done is complex, though, there is a lot to be gained by getting
+feedback from the community before the work is complete.  So you should
+consider posting in-progress work, or even making a git tree available so
+that interested developers can catch up with your work at any time.
+When posting code which is not yet considered ready for inclusion, it is a
+good idea to say so in the posting itself.  Also mention any major work
+which remains to be done and any known problems.  Fewer people will look at
+patches which are known to be half-baked, but those who do will come in
+with the idea that they can help you drive the work in the right direction.
+5.2: BEFORE CREATING PATCHES
+There are a number of things which should be done before you consider
+sending patches to the development community.  These include:
+ - Test the code to the extent that you can.  Make use of the kernel's
+   debugging tools, ensure that the kernel will build with all reasonable
+   combinations of configuration options, use cross-compilers to build for
+   different architectures, etc.
+ - Make sure your code is compliant with the kernel coding style
+   guidelines.
+ - Does your change have performance implications?  If so, you should run
+   benchmarks showing what the impact (or benefit) of your change is; a
+   summary of the results should be included with the patch.
+ - Be sure that you have the right to post the code.  If this work was done
+   for an employer, the employer likely has a right to the work and must be
+   agreeable with its release under the GPL.
+As a general rule, putting in some extra thought before posting code almost
+always pays back the effort in short order.
+5.3: PATCH PREPARATION
+The preparation of patches for posting can be a surprising amount of work,
+but, once again, attempting to save time here is not generally advisable
+even in the short term.
+Patches must be prepared against a specific version of the kernel.  As a
+general rule, a patch should be based on the current mainline as found in
+Linus's git tree.  It may become necessary to make versions against -mm,
+linux-next, or a subsystem tree, though, to facilitate wider testing and
+review.  Depending on the area of your patch and what is going on
+elsewhere, basing a patch against these other trees can require a
+significant amount of work resolving conflicts and dealing with API
+changes.
+Only the most simple changes should be formatted as a single patch;
+everything else should be made as a logical series of changes.  Splitting
+up patches is a bit of an art; some developers spend a long time figuring
+out how to do it in the way that the community expects.  There are a few
+rules of thumb, however, which can help considerably:
+ - The patch series you post will almost certainly not be the series of
+   changes found in your working revision control system.  Instead, the
+   changes you have made need to be considered in their final form, then
+   split apart in ways which make sense.  The developers are interested in
+   discrete, self-contained changes, not the path you took to get to those
+   changes.
+ - Each logically independent change should be formatted as a separate
+   patch.  These changes can be small ("add a field to this structure") or
+   large (adding a significant new driver, for example), but they should be
+   conceptually small and amenable to a one-line description.  Each patch
+   should make a specific change which can be reviewed on its own and
+   verified to do what it says it does.
+ - As a way of restating the guideline above: do not mix different types of
+   changes in the same patch.  If a single patch fixes a critical security
+   bug, rearranges a few structures, and reformats the code, there is a
+   good chance that it will be passed over and the important fix will be
+   lost.
+ - Each patch should yield a kernel which builds and runs properly; if your
+   patch series is interrupted in the middle, the result should still be a
+   working kernel.  Partial application of a patch series is a common
+   scenario when the "git bisect" tool is used to find regressions; if the
+   result is a broken kernel, you will make life harder for developers and
+   users who are engaging in the noble work of tracking down problems.
+ - Do not overdo it, though.  One developer recently posted a set of edits
+   to a single file as 500 separate patches - an act which did not make him
+   the most popular person on the kernel mailing list.  A single patch can
+   be reasonably large as long as it still contains a single *logical*
+   change. 
+ - It can be tempting to add a whole new infrastructure with a series of
+   patches, but to leave that infrastructure unused until the final patch
+   in the series enables the whole thing.  This temptation should be
+   avoided if possible; if that series adds regressions, bisection will
+   finger the last patch as the one which caused the problem, even though
+   the real bug is elsewhere.  Whenever possible, a patch which adds new
+   code should make that code active immediately.
+Working to create the perfect patch series can be a frustrating process
+which takes quite a bit of time and thought after the "real work" has been
+done.  When done properly, though, it is time well spent.
+5.4: PATCH FORMATTING
+So now you have a perfect series of patches for posting, but the work is
+not done quite yet.  Each patch needs to be formatted into a message which
+quickly and clearly communicates its purpose to the rest of the world.  To
+that end, each patch will be composed of the following:
+ - An optional "From" line naming the author of the patch.  This line is
+   only necessary if you are passing on somebody else's patch via email,
+   but it never hurts to add it when in doubt.
+ - A one-line description of what the patch does.  This message should be
+   enough for a reader who sees it with no other context to figure out the
+   scope of the patch; it is the line that will show up in the "short form"
+   changelogs.  This message is usually formatted with the relevant
+   subsystem name first, followed by the purpose of the patch.  For
+   example:
+        gpio: fix build on CONFIG_GPIO_SYSFS=n
+ - A blank line followed by a detailed description of the contents of the
+   patch.  This description can be as long as is required; it should say
+   what the patch does and why it should be applied to the kernel.
+ - One or more tag lines, with, at a minimum, one Signed-off-by: line from
+   the author of the patch.  Tags will be described in more detail below.
+The above three items should, normally, be the text used when committing
+the change to a revision control system.  They are followed by:
+ - The patch itself, in the unified ("-u") patch format.  Using the "-p"
+   option to diff will associate function names with changes, making the
+   resulting patch easier for others to read.
+You should avoid including changes to irrelevant files (those generated by
+the build process, for example, or editor backup files) in the patch.  The
+file "dontdiff" in the Documentation directory can help in this regard;
+pass it to diff with the "-X" option.
+The tags mentioned above are used to describe how various developers have
+been associated with the development of this patch.  They are described in
+detail in the SubmittingPatches document; what follows here is a brief
+summary.  Each of these lines has the format:
+        tag: Full Name <email address>  optional-other-stuff
+The tags in common use are:
+ - Signed-off-by: this is a developer's certification that he or she has
+   the right to submit the patch for inclusion into the kernel.  It is an
+   agreement to the Developer's Certificate of Origin, the full text of
+   which can be found in Documentation/SubmittingPatches.  Code without a
+   proper signoff cannot be merged into the mainline.
+ - Acked-by: indicates an agreement by another developer (often a
+   maintainer of the relevant code) that the patch is appropriate for
+   inclusion into the kernel.
+ - Tested-by: states that the named person has tested the patch and found
+   it to work.
+ - Reviewed-by: the named developer has reviewed the patch for correctness;
+   see the reviewer's statement in Documentation/SubmittingPatches for more
+   detail.
+ - Reported-by: names a user who reported a problem which is fixed by this
+   patch; this tag is used to give credit to the (often underappreciated)
+   people who test our code and let us know when things do not work
+   correctly.
+ - Cc: the named person received a copy of the patch and had the
+   opportunity to comment on it.
+Be careful in the addition of tags to your patches: only Cc: is appropriate
+for addition without the explicit permission of the person named.
+5.5: SENDING THE PATCH
+Before you mail your patches, there are a couple of other things you should
+take care of:
+ - Are you sure that your mailer will not corrupt the patches?  Patches
+   which have had gratuitous white-space changes or line wrapping performed
+   by the mail client will not apply at the other end, and often will not
+   be examined in any detail.  If there is any doubt at all, mail the patch
+   to yourself and convince yourself that it shows up intact.  
+   Documentation/email-clients.txt has some helpful hints on making
+   specific mail clients work for sending patches.
+ - Are you sure your patch is free of silly mistakes?  You should always
+   run patches through scripts/checkpatch.pl and address the complaints it
+   comes up with.  Please bear in mind that checkpatch.pl, while being the
+   embodiment of a fair amount of thought about what kernel patches should
+   look like, is not smarter than you.  If fixing a checkpatch.pl complaint
+   would make the code worse, don't do it.
+Patches should always be sent as plain text.  Please do not send them as
+attachments; that makes it much harder for reviewers to quote sections of
+the patch in their replies.  Instead, just put the patch directly into your
+message.
+When mailing patches, it is important to send copies to anybody who might
+be interested in it.  Unlike some other projects, the kernel encourages
+people to err on the side of sending too many copies; don't assume that the
+relevant people will see your posting on the mailing lists.  In particular,
+copies should go to:
+ - The maintainer(s) of the affected subsystem(s).  As described earlier,
+   the MAINTAINERS file is the first place to look for these people.
+ - Other developers who have been working in the same area - especially
+   those who might be working there now.  Using git to see who else has
+   modified the files you are working on can be helpful.
+ - If you are responding to a bug report or a feature request, copy the
+   original poster as well.
+ - Send a copy to the relevant mailing list, or, if nothing else applies,
+   the linux-kernel list.
+ - If you are fixing a bug, think about whether the fix should go into the
+   next stable update.  If so, stable@kernel.org should get a copy of the
+   patch.  Also add a "Cc: stable@kernel.org" to the tags within the patch
+   itself; that will cause the stable team to get a notification when your
+   fix goes into the mainline.
+When selecting recipients for a patch, it is good to have an idea of who
+you think will eventually accept the patch and get it merged.  While it
+is possible to send patches directly to Linus Torvalds and have him merge
+them, things are not normally done that way.  Linus is busy, and there are
+subsystem maintainers who watch over specific parts of the kernel.  Usually
+you will be wanting that maintainer to merge your patches.  If there is no
+obvious maintainer, Andrew Morton is often the patch target of last resort.
+Patches need good subject lines.  The canonical format for a patch line is
+something like:
+        [PATCH nn/mm] subsys: one-line description of the patch
+where "nn" is the ordinal number of the patch, "mm" is the total number of
+patches in the series, and "subsys" is the name of the affected subsystem.
+Clearly, nn/mm can be omitted for a single, standalone patch.  
+If you have a significant series of patches, it is customary to send an
+introductory description as part zero.  This convention is not universally
+followed though; if you use it, remember that information in the
+introduction does not make it into the kernel changelogs.  So please ensure
+that the patches, themselves, have complete changelog information.
+In general, the second and following parts of a multi-part patch should be
+sent as a reply to the first part so that they all thread together at the
+receiving end.  Tools like git and quilt have commands to mail out a set of
+patches with the proper threading.  If you have a long series, though, and
+are using git, please provide the --no-chain-reply-to option to avoid
+creating exceptionally deep nesting.
diff --git a/Documentation/development-process/6.Followthrough b/Documentation/development-process/6.Followthrough
new file mode 100644
index 000000000000..a8fba3d83a85
--- /dev/null
+++ b/Documentation/development-process/6.Followthrough
@@ -0,0 +1,202 @@
+6: FOLLOWTHROUGH
+At this point, you have followed the guidelines given so far and, with the
+addition of your own engineering skills, have posted a perfect series of
+patches.  One of the biggest mistakes that even experienced kernel
+developers can make is to conclude that their work is now done.  In truth,
+posting patches indicates a transition into the next stage of the process,
+with, possibly, quite a bit of work yet to be done.
+It is a rare patch which is so good at its first posting that there is no
+room for improvement.  The kernel development process recognizes this fact,
+and, as a result, is heavily oriented toward the improvement of posted
+code.  You, as the author of that code, will be expected to work with the
+kernel community to ensure that your code is up to the kernel's quality
+standards.  A failure to participate in this process is quite likely to
+prevent the inclusion of your patches into the mainline.
+6.1: WORKING WITH REVIEWERS
+A patch of any significance will result in a number of comments from other
+developers as they review the code.  Working with reviewers can be, for
+many developers, the most intimidating part of the kernel development
+process.  Life can be made much easier, though, if you keep a few things in
+mind:
+ - If you have explained your patch well, reviewers will understand its
+   value and why you went to the trouble of writing it.  But that value
+   will not keep them from asking a fundamental question: what will it be
+   like to maintain a kernel with this code in it five or ten years later?
+   Many of the changes you may be asked to make - from coding style tweaks
+   to substantial rewrites - come from the understanding that Linux will
+   still be around and under development a decade from now.
+ - Code review is hard work, and it is a relatively thankless occupation;
+   people remember who wrote kernel code, but there is little lasting fame
+   for those who reviewed it.  So reviewers can get grumpy, especially when
+   they see the same mistakes being made over and over again.  If you get a
+   review which seems angry, insulting, or outright offensive, resist the
+   impulse to respond in kind.  Code review is about the code, not about
+   the people, and code reviewers are not attacking you personally.
+ - Similarly, code reviewers are not trying to promote their employers'
+   agendas at the expense of your own.  Kernel developers often expect to
+   be working on the kernel years from now, but they understand that their
+   employer could change.  They truly are, almost without exception,
+   working toward the creation of the best kernel they can; they are not
+   trying to create discomfort for their employers' competitors.
+What all of this comes down to is that, when reviewers send you comments,
+you need to pay attention to the technical observations that they are
+making.  Do not let their form of expression or your own pride keep that
+from happening.  When you get review comments on a patch, take the time to
+understand what the reviewer is trying to say.  If possible, fix the things
+that the reviewer is asking you to fix.  And respond back to the reviewer:
+thank them, and describe how you will answer their questions.
+Note that you do not have to agree with every change suggested by
+reviewers.  If you believe that the reviewer has misunderstood your code,
+explain what is really going on.  If you have a technical objection to a
+suggested change, describe it and justify your solution to the problem.  If
+your explanations make sense, the reviewer will accept them.  Should your
+explanation not prove persuasive, though, especially if others start to
+agree with the reviewer, take some time to think things over again.  It can
+be easy to become blinded by your own solution to a problem to the point
+that you don't realize that something is fundamentally wrong or, perhaps,
+you're not even solving the right problem.
+One fatal mistake is to ignore review comments in the hope that they will
+go away.  They will not go away.  If you repost code without having
+responded to the comments you got the time before, you're likely to find
+that your patches go nowhere.
+Speaking of reposting code: please bear in mind that reviewers are not
+going to remember all the details of the code you posted the last time
+around.  So it is always a good idea to remind reviewers of previously
+raised issues and how you dealt with them; the patch changelog is a good
+place for this kind of information.  Reviewers should not have to search
+through list archives to familiarize themselves with what was said last
+time; if you help them get a running start, they will be in a better mood
+when they revisit your code.
+What if you've tried to do everything right and things still aren't going
+anywhere?  Most technical disagreements can be resolved through discussion,
+but there are times when somebody simply has to make a decision.  If you
+honestly believe that this decision is going against you wrongly, you can
+always try appealing to a higher power.  As of this writing, that higher
+power tends to be Andrew Morton.  Andrew has a great deal of respect in the
+kernel development community; he can often unjam a situation which seems to
+be hopelessly blocked.  Appealing to Andrew should not be done lightly,
+though, and not before all other alternatives have been explored.  And bear
+in mind, of course, that he may not agree with you either.
+6.2: WHAT HAPPENS NEXT
+If a patch is considered to be a good thing to add to the kernel, and once
+most of the review issues have been resolved, the next step is usually
+entry into a subsystem maintainer's tree.  How that works varies from one
+subsystem to the next; each maintainer has his or her own way of doing
+things.  In particular, there may be more than one tree - one, perhaps,
+dedicated to patches planned for the next merge window, and another for
+longer-term work.  
+For patches applying to areas for which there is no obvious subsystem tree
+(memory management patches, for example), the default tree often ends up
+being -mm.  Patches which affect multiple subsystems can also end up going
+through the -mm tree.
+Inclusion into a subsystem tree can bring a higher level of visibility to a
+patch.  Now other developers working with that tree will get the patch by
+default.  Subsystem trees typically feed into -mm and linux-next as well,
+making their contents visible to the development community as a whole.  At
+this point, there's a good chance that you will get more comments from a
+new set of reviewers; these comments need to be answered as in the previous
+round.
+What may also happen at this point, depending on the nature of your patch,
+is that conflicts with work being done by others turn up.  In the worst
+case, heavy patch conflicts can result in some work being put on the back
+burner so that the remaining patches can be worked into shape and merged.
+Other times, conflict resolution will involve working with the other
+developers and, possibly, moving some patches between trees to ensure that
+everything applies cleanly.  This work can be a pain, but count your
+blessings: before the advent of the linux-next tree, these conflicts often
+only turned up during the merge window and had to be addressed in a hurry.
+Now they can be resolved at leisure, before the merge window opens.
+Some day, if all goes well, you'll log on and see that your patch has been
+merged into the mainline kernel.  Congratulations!  Once the celebration is
+complete (and you have added yourself to the MAINTAINERS file), though, it
+is worth remembering an important little fact: the job still is not done.
+Merging into the mainline brings its own challenges.
+To begin with, the visibility of your patch has increased yet again.  There
+may be a new round of comments from developers who had not been aware of
+the patch before.  It may be tempting to ignore them, since there is no
+longer any question of your code being merged.  Resist that temptation,
+though; you still need to be responsive to developers who have questions or
+suggestions.
+More importantly, though: inclusion into the mainline puts your code into
+the hands of a much larger group of testers.  Even if you have contributed
+a driver for hardware which is not yet available, you will be surprised by
+how many people will build your code into their kernels.  And, of course,
+where there are testers, there will be bug reports.
+The worst sort of bug reports are regressions.  If your patch causes a
+regression, you'll find an uncomfortable number of eyes upon you;
+regressions need to be fixed as soon as possible.  If you are unwilling or
+unable to fix the regression (and nobody else does it for you), your patch
+will almost certainly be removed during the stabilization period.  Beyond
+negating all of the work you have done to get your patch into the mainline,
+having a patch pulled as the result of a failure to fix a regression could
+well make it harder for you to get work merged in the future.
+After any regressions have been dealt with, there may be other, ordinary
+bugs to deal with.  The stabilization period is your best opportunity to
+fix these bugs and ensure that your code's debut in a mainline kernel
+release is as solid as possible.  So, please, answer bug reports, and fix
+the problems if at all possible.  That's what the stabilization period is
+for; you can start creating cool new patches once any problems with the old
+ones have been taken care of.
+And don't forget that there are other milestones which may also create bug
+reports: the next mainline stable release, when prominent distributors pick
+up a version of the kernel containing your patch, etc.  Continuing to
+respond to these reports is a matter of basic pride in your work.  If that
+is insufficient motivation, though, it's also worth considering that the
+development community remembers developers who lose interest in their code
+after it's merged.  The next time you post a patch, they will be evaluating
+it with the assumption that you will not be around to maintain it
+afterward.
+6.3: OTHER THINGS THAT CAN HAPPEN
+One day, you may open your mail client and see that somebody has mailed you
+a patch to your code.  That is one of the advantages of having your code
+out there in the open, after all.  If you agree with the patch, you can
+either forward it on to the subsystem maintainer (be sure to include a
+proper From: line so that the attribution is correct, and add a signoff of
+your own), or send an Acked-by: response back and let the original poster
+send it upward.
+If you disagree with the patch, send a polite response explaining why.  If
+possible, tell the author what changes need to be made to make the patch
+acceptable to you.  There is a certain resistance to merging patches which
+are opposed by the author and maintainer of the code, but it only goes so
+far.  If you are seen as needlessly blocking good work, those patches will
+eventually flow around you and get into the mainline anyway.  In the Linux
+kernel, nobody has absolute veto power over any code.  Except maybe Linus.
+On very rare occasion, you may see something completely different: another
+developer posts a different solution to your problem.  At that point,
+chances are that one of the two patches will not be merged, and "mine was
+here first" is not considered to be a compelling technical argument.  If
+somebody else's patch displaces yours and gets into the mainline, there is
+really only one way to respond: be pleased that your problem got solved and
+get on with your work.  Having one's work shoved aside in this manner can
+be hurtful and discouraging, but the community will remember your reaction
+long after they have forgotten whose patch actually got merged.
diff --git a/Documentation/development-process/7.AdvancedTopics b/Documentation/development-process/7.AdvancedTopics
new file mode 100644
index 000000000000..a2cf74093aa1
--- /dev/null
+++ b/Documentation/development-process/7.AdvancedTopics
@@ -0,0 +1,173 @@
+7: ADVANCED TOPICS
+At this point, hopefully, you have a handle on how the development process
+works.  There is still more to learn, however!  This section will cover a
+number of topics which can be helpful for developers wanting to become a
+regular part of the Linux kernel development process.
+7.1: MANAGING PATCHES WITH GIT
+The use of distributed version control for the kernel began in early 2002,
+when Linus first started playing with the proprietary BitKeeper
+application.  While BitKeeper was controversial, the approach to software
+version management it embodied most certainly was not.  Distributed version
+control enabled an immediate acceleration of the kernel development
+project.  In current times, there are several free alternatives to
+BitKeeper.  For better or for worse, the kernel project has settled on git
+as its tool of choice.
+Managing patches with git can make life much easier for the developer,
+especially as the volume of those patches grows.  Git also has its rough
+edges and poses certain hazards; it is a young and powerful tool which is
+still being civilized by its developers.  This document will not attempt to
+teach the reader how to use git; that would be sufficient material for a
+long document in its own right.  Instead, the focus here will be on how git
+fits into the kernel development process in particular.  Developers who
+wish to come up to speed with git will find more information at:
+        http://git.or.cz/
+        http://www.kernel.org/pub/software/scm/git/docs/user-manual.html
+and on various tutorials found on the web.
+The first order of business is to read the above sites and get a solid
+understanding of how git works before trying to use it to make patches
+available to others.  A git-using developer should be able to obtain a copy
+of the mainline repository, explore the revision history, commit changes to
+the tree, use branches, etc.  An understanding of git's tools for the
+rewriting of history (such as rebase) is also useful.  Git comes with its
+own terminology and concepts; a new user of git should know about refs,
+remote branches, the index, fast-forward merges, pushes and pulls, detached
+heads, etc.  It can all be a little intimidating at the outset, but the
+concepts are not that hard to grasp with a bit of study.
+Using git to generate patches for submission by email can be a good
+exercise while coming up to speed.
+When you are ready to start putting up git trees for others to look at, you
+will, of course, need a server that can be pulled from.  Setting up such a
+server with git-daemon is relatively straightforward if you have a system
+which is accessible to the Internet.  Otherwise, free, public hosting sites
+(Github, for example) are starting to appear on the net.  Established
+developers can get an account on kernel.org, but those are not easy to come
+by; see http://kernel.org/faq/ for more information.
+The normal git workflow involves the use of a lot of branches.  Each line
+of development can be separated into a separate "topic branch" and
+maintained independently.  Branches in git are cheap, there is no reason to
+not make free use of them.  And, in any case, you should not do your
+development in any branch which you intend to ask others to pull from.
+Publicly-available branches should be created with care; merge in patches
+from development branches when they are in complete form and ready to go -
+not before.
+Git provides some powerful tools which can allow you to rewrite your
+development history.  An inconvenient patch (one which breaks bisection,
+say, or which has some other sort of obvious bug) can be fixed in place or
+made to disappear from the history entirely.  A patch series can be
+rewritten as if it had been written on top of today's mainline, even though
+you have been working on it for months.  Changes can be transparently
+shifted from one branch to another.  And so on.  Judicious use of git's
+ability to revise history can help in the creation of clean patch sets with
+fewer problems.
+Excessive use of this capability can lead to other problems, though, beyond
+a simple obsession for the creation of the perfect project history.
+Rewriting history will rewrite the changes contained in that history,
+turning a tested (hopefully) kernel tree into an untested one.  But, beyond
+that, developers cannot easily collaborate if they do not have a shared
+view of the project history; if you rewrite history which other developers
+have pulled into their repositories, you will make life much more difficult
+for those developers.  So a simple rule of thumb applies here: history
+which has been exported to others should generally be seen as immutable
+thereafter.
+So, once you push a set of changes to your publicly-available server, those
+changes should not be rewritten.  Git will attempt to enforce this rule if
+you try to push changes which do not result in a fast-forward merge
+(i.e. changes which do not share the same history).  It is possible to
+override this check, and there may be times when it is necessary to rewrite
+an exported tree.  Moving changesets between trees to avoid conflicts in
+linux-next is one example.  But such actions should be rare.  This is one
+of the reasons why development should be done in private branches (which
+can be rewritten if necessary) and only moved into public branches when
+it's in a reasonably advanced state.
+As the mainline (or other tree upon which a set of changes is based)
+advances, it is tempting to merge with that tree to stay on the leading
+edge.  For a private branch, rebasing can be an easy way to keep up with
+another tree, but rebasing is not an option once a tree is exported to the
+world.  Once that happens, a full merge must be done.  Merging occasionally
+makes good sense, but overly frequent merges can clutter the history
+needlessly.  Suggested technique in this case is to merge infrequently, and
+generally only at specific release points (such as a mainline -rc
+release).  If you are nervous about specific changes, you can always
+perform test merges in a private branch.  The git "rerere" tool can be
+useful in such situations; it remembers how merge conflicts were resolved
+so that you don't have to do the same work twice.
+One of the biggest recurring complaints about tools like git is this: the
+mass movement of patches from one repository to another makes it easy to
+slip in ill-advised changes which go into the mainline below the review
+radar.  Kernel developers tend to get unhappy when they see that kind of
+thing happening; putting up a git tree with unreviewed or off-topic patches
+can affect your ability to get trees pulled in the future.  Quoting Linus:
+        You can send me patches, but for me to pull a git patch from you, I
+        need to know that you know what you're doing, and I need to be able
+        to trust things *without* then having to go and check every
+        individual change by hand.
+(http://lwn.net/Articles/224135/).  
+To avoid this kind of situation, ensure that all patches within a given
+branch stick closely to the associated topic; a "driver fixes" branch
+should not be making changes to the core memory management code.  And, most
+importantly, do not use a git tree to bypass the review process.  Post an
+occasional summary of the tree to the relevant list, and, when the time is
+right, request that the tree be included in linux-next.
+If and when others start to send patches for inclusion into your tree,
+don't forget to review them.  Also ensure that you maintain the correct
+authorship information; the git "am" tool does its best in this regard, but
+you may have to add a "From:" line to the patch if it has been relayed to
+you via a third party.
+When requesting a pull, be sure to give all the relevant information: where
+your tree is, what branch to pull, and what changes will result from the
+pull.  The git request-pull command can be helpful in this regard; it will
+format the request as other developers expect, and will also check to be
+sure that you have remembered to push those changes to the public server. 
+7.2: REVIEWING PATCHES
+Some readers will certainly object to putting this section with "advanced
+topics" on the grounds that even beginning kernel developers should be
+reviewing patches.  It is certainly true that there is no better way to
+learn how to program in the kernel environment than by looking at code
+posted by others.  In addition, reviewers are forever in short supply; by
+looking at code you can make a significant contribution to the process as a
+whole.
+Reviewing code can be an intimidating prospect, especially for a new kernel
+developer who may well feel nervous about questioning code - in public -
+which has been posted by those with more experience.  Even code written by
+the most experienced developers can be improved, though.  Perhaps the best
+piece of advice for reviewers (all reviewers) is this: phrase review
+comments as questions rather than criticisms.  Asking "how does the lock
+get released in this path?" will always work better than stating "the
+locking here is wrong."
+Different developers will review code from different points of view.  Some
+are mostly concerned with coding style and whether code lines have trailing
+white space.  Others will focus primarily on whether the change implemented
+by the patch as a whole is a good thing for the kernel or not.  Yet others
+will check for problematic locking, excessive stack usage, possible
+security issues, duplication of code found elsewhere, adequate
+documentation, adverse effects on performance, user-space ABI changes, etc.
+All types of review, if they lead to better code going into the kernel, are
+welcome and worthwhile.
diff --git a/Documentation/development-process/8.Conclusion b/Documentation/development-process/8.Conclusion
new file mode 100644
index 000000000000..1990ab4b4949
--- /dev/null
+++ b/Documentation/development-process/8.Conclusion
@@ -0,0 +1,74 @@
+8: FOR MORE INFORMATION
+There are numerous sources of information on Linux kernel development and
+related topics.  First among those will always be the Documentation
+directory found in the kernel source distribution.  The top-level HOWTO
+file is an important starting point; SubmittingPatches and
+SubmittingDrivers are also something which all kernel developers should
+read.  Many internal kernel APIs are documented using the kerneldoc
+mechanism; "make htmldocs" or "make pdfdocs" can be used to generate those
+documents in HTML or PDF format (though the version of TeX shipped by some
+distributions runs into internal limits and fails to process the documents
+properly).
+Various web sites discuss kernel development at all levels of detail.  Your
+author would like to humbly suggest http://lwn.net/ as a source;
+information on many specific kernel topics can be found via the LWN kernel
+index at:
+        http://lwn.net/Kernel/Index/
+Beyond that, a valuable resource for kernel developers is:
+        http://kernelnewbies.org/
+Information about the linux-next tree gathers at:
+        http://linux.f-seidel.de/linux-next/pmwiki/
+And, of course, one should not forget http://kernel.org/, the definitive
+location for kernel release information.
+There are a number of books on kernel development:
+        Linux Device Drivers, 3rd Edition (Jonathan Corbet, Alessandro
+        Rubini, and Greg Kroah-Hartman).  Online at
+        http://lwn.net/Kernel/LDD3/.
+        Linux Kernel Development (Robert Love).
+        Understanding the Linux Kernel (Daniel Bovet and Marco Cesati).
+All of these books suffer from a common fault, though: they tend to be
+somewhat obsolete by the time they hit the shelves, and they have been on
+the shelves for a while now.  Still, there is quite a bit of good
+information to be found there.
+Documentation for git can be found at:
+        http://www.kernel.org/pub/software/scm/git/docs/
+        http://www.kernel.org/pub/software/scm/git/docs/user-manual.html
+9: CONCLUSION
+Congratulations to anybody who has made it through this long-winded
+document.  Hopefully it has provided a helpful understanding of how the
+Linux kernel is developed and how you can participate in that process.
+In the end, it's the participation that matters.  Any open source software
+project is no more than the sum of what its contributors put into it.  The
+Linux kernel has progressed as quickly and as well as it has because it has
+been helped by an impressively large group of developers, all of whom are
+working to make it better.  The kernel is a premier example of what can be
+done when thousands of people work together toward a common goal.
+The kernel can always benefit from a larger developer base, though.  There
+is always more work to do.  But, just as importantly, most other
+participants in the Linux ecosystem can benefit through contributing to the
+kernel.  Getting code into the mainline is the key to higher code quality,
+lower maintenance and distribution costs, a higher level of influence over
+the direction of kernel development, and more.  It is a situation where
+everybody involved wins.  Fire up your editor and come join us; you will be
+more than welcome.
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index e6244cde26e9..2be08240ee80 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -2560,9 +2560,6 @@ Your cooperation is appreciated.
                 96 = /dev/usb/hiddev0  1st USB HID device
                    ...
                111 = /dev/usb/hiddev15 16th USB HID device
-                112 = /dev/usb/auer0    1st auerswald ISDN device
-                    ...
-                127 = /dev/usb/auer15   16th auerswald ISDN device
                128 = /dev/usb/brlvgr0  First Braille Voyager device
                    ...
                131 = /dev/usb/brlvgr3  Fourth Braille Voyager device
@@ -2574,6 +2571,9 @@ Your cooperation is appreciated.
                160 = /dev/usb/legousbtower0    1st USB Legotower device
                    ...
                175 = /dev/usb/legousbtower15   16th USB Legotower device
+                176 = /dev/usb/usbtmc1  First USB TMC device
+                   ...
+                192 = /dev/usb/usbtmc16 16th USB TMC device
                240 = /dev/usb/dabusb0  First daubusb device
                    ...
                243 = /dev/usb/dabusb3  Fourth dabusb device
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 881e6dd03aea..1e89a51ea49b 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -2,9 +2,13 @@
 *.aux
 *.bin
 *.cpio
-*.css
+*.csp
+*.dsp
 *.dvi
+*.elf
 *.eps
+*.fw
+*.gen.S
 *.gif
 *.grep
 *.grp
@@ -28,6 +32,7 @@
 *.s
 *.sgml
 *.so
+*.so.dbg
 *.symtypes
 *.tab.c
 *.tab.h
@@ -36,24 +41,17 @@
 *.xml
 *_MODULES
 *_vga16.c
-*cscope*
 *~
 *.9
 *.9.gz
 .*
-.cscope
-.gitignore
-.mailmap
 .mm
 53c700_d.h
-53c8xx_d.h*
-COPYING
-CREDITS
 CVS
 ChangeSet
 Image
 Kerntypes
-MODS.txt
+Module.markers
 Module.symvers
 PENDING
 SCCS
@@ -71,7 +69,9 @@ autoconf.h*
 bbootsect
 bin2c
 binkernel.spec
+binoffset
 bootsect
+bounds.h
 bsetup
 btfixupprep
 build
@@ -87,39 +87,36 @@ config_data.h*
 config_data.gz*
 conmakehash
 consolemap_deftbl.c*
+cpustr.h
 crc32table.h*
 cscope.*
-defkeymap.c*
+defkeymap.c
 devlist.h*
 docproc
-dummy_sym.c*
 elf2ecoff
 elfconfig.h*
-filelist
 fixdep
 fore200e_mkfirm
 fore200e_pca_fw.c*
 gconf
 gen-devlist
-gen-kdb_cmds.c*
 gen_crc32table
 gen_init_cpio
 genksyms
-gentbl
 *_gray256.c
+ihex2fw
 ikconfig.h*
 initramfs_data.cpio
 initramfs_data.cpio.gz
 initramfs_list
 kallsyms
 kconfig
-kconfig.tk
+keywords.c
-keywords.c*
 ksym.c*
 ksym.h*
 kxgettext
 lkc_defs.h
-lex.c*
+lex.c
 lex.*.c
 logo_*.c
 logo_*_clut224.c
@@ -128,7 +125,6 @@ lxdialog
 mach-types
 mach-types.h
 machtypes.h
-make_times_h
 map
 maui_boot.h
 mconf
@@ -136,6 +132,7 @@ miboot*
 mk_elfconfig
 mkboot
 mkbugboot
+mkcpustr
 mkdep
 mkprep
 mktables
@@ -143,11 +140,12 @@ mktree
 modpost
 modules.order
 modversions.h*
+ncscope.*
 offset.h
 offsets.h
 oui.c*
-parse.c*
+parse.c
-parse.h*
+parse.h
 patches*
 pca200e.bin
 pca200e_ecd.bin2
@@ -155,7 +153,7 @@ piggy.gz
 piggyback
 pnmtologo
 ppc_defs.h*
-promcon_tbl.c*
+promcon_tbl.c
 pss_boot.h
 qconf
 raid6altivec*.c
@@ -166,27 +164,38 @@ series
 setup
 setup.bin
 setup.elf
-sim710_d.h*
 sImage
 sm_tbl*
 split-include
+syscalltab.h
 tags
 tftpboot.img
 timeconst.h
 times.h*
-tkparse
 trix_boot.h
 utsrelease.h*
+vdso-syms.lds
 vdso.lds
+vdso32-int80-syms.lds
+vdso32-syms.lds
+vdso32-syscall-syms.lds
+vdso32-sysenter-syms.lds
+vdso32.lds
+vdso32.so.dbg
+vdso64.lds
+vdso64.so.dbg
 version.h*
 vmlinux
 vmlinux-*
 vmlinux.aout
-vmlinux*.lds*
+vmlinux.lds
-vmlinux*.scr
 vsyscall.lds
+vsyscall_32.lds
 wanxlfw.inc
 uImage
 unifdef
+wakeup.bin
+wakeup.elf
+wakeup.lds
 zImage*
 zconf.hash.c
diff --git a/Documentation/edac.txt b/Documentation/edac.txt
index a5c36842ecef..8eda3fb66416 100644
--- a/Documentation/edac.txt
+++ b/Documentation/edac.txt
@@ -222,74 +222,9 @@ both csrow2 and csrow3 are populated, this indicates a dual ranked
 set of DIMMs for channels 0 and 1.
-Within each of the 'mc','mcX' and 'csrowX' directories are several
+Within each of the 'mcX' and 'csrowX' directories are several
 EDAC control and attribute files.
-============================================================================
-DIRECTORY 'mc'
-In directory 'mc' are EDAC system overall control and attribute files:
-Panic on UE control file:
-        'edac_mc_panic_on_ue'
-        An uncorrectable error will cause a machine panic.  This is usually
-        desirable.  It is a bad idea to continue when an uncorrectable error
-        occurs - it is indeterminate what was uncorrected and the operating
-        system context might be so mangled that continuing will lead to further
-        corruption. If the kernel has MCE configured, then EDAC will never
-        notice the UE.
-        LOAD TIME: module/kernel parameter: panic_on_ue=[0|1]
-        RUN TIME:  echo "1" >/sys/devices/system/edac/mc/edac_mc_panic_on_ue
-Log UE control file:
-        'edac_mc_log_ue'
-        Generate kernel messages describing uncorrectable errors.  These errors
-        are reported through the system message log system.  UE statistics
-        will be accumulated even when UE logging is disabled.
-        LOAD TIME: module/kernel parameter: log_ue=[0|1]
-        RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ue
-Log CE control file:
-        'edac_mc_log_ce'
-        Generate kernel messages describing correctable errors.  These
-        errors are reported through the system message log system.
-        CE statistics will be accumulated even when CE logging is disabled.
-        LOAD TIME: module/kernel parameter: log_ce=[0|1]
-        RUN TIME: echo "1" >/sys/devices/system/edac/mc/edac_mc_log_ce
-Polling period control file:
-        'edac_mc_poll_msec'
-        The time period, in milliseconds, for polling for error information.
-        Too small a value wastes resources.  Too large a value might delay
-        necessary handling of errors and might loose valuable information for
-        locating the error.  1000 milliseconds (once each second) is the current
-        default. Systems which require all the bandwidth they can get, may
-        increase this.
-        LOAD TIME: module/kernel parameter: poll_msec=[0|1]
-        RUN TIME: echo "1000" >/sys/devices/system/edac/mc/edac_mc_poll_msec
 ============================================================================
 'mcX' DIRECTORIES
@@ -392,7 +327,7 @@ Sdram memory scrubbing rate:
        'sdram_scrub_rate'
        Read/Write attribute file that controls memory scrubbing. The scrubbing
-        rate is set by writing a minimum bandwith in bytes/sec to the attribute
+        rate is set by writing a minimum bandwidth in bytes/sec to the attribute
        file. The rate will be translated to an internal value that gives at
        least the specified rate.
@@ -537,7 +472,6 @@ Channel 1 DIMM Label control file:
        motherboard specific and determination of this information
        must occur in userland at this time.
 ============================================================================
 SYSTEM LOGGING
@@ -570,7 +504,6 @@ error type, a notice of "no info" and then an optional,
 driver-specific error message.
 ============================================================================
 PCI Bus Parity Detection
@@ -604,6 +537,74 @@ Enable/Disable PCI Parity checking control file:
        echo "0" >/sys/devices/system/edac/pci/check_pci_parity
+Parity Count:
+        'pci_parity_count'
+        This attribute file will display the number of parity errors that
+        have been detected.
+============================================================================
+MODULE PARAMETERS
+Panic on UE control file:
+        'edac_mc_panic_on_ue'
+        An uncorrectable error will cause a machine panic.  This is usually
+        desirable.  It is a bad idea to continue when an uncorrectable error
+        occurs - it is indeterminate what was uncorrected and the operating
+        system context might be so mangled that continuing will lead to further
+        corruption. If the kernel has MCE configured, then EDAC will never
+        notice the UE.
+        LOAD TIME: module/kernel parameter: edac_mc_panic_on_ue=[0|1]
+        RUN TIME:  echo "1" > /sys/module/edac_core/parameters/edac_mc_panic_on_ue
+Log UE control file:
+        'edac_mc_log_ue'
+        Generate kernel messages describing uncorrectable errors.  These errors
+        are reported through the system message log system.  UE statistics
+        will be accumulated even when UE logging is disabled.
+        LOAD TIME: module/kernel parameter: edac_mc_log_ue=[0|1]
+        RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ue
+Log CE control file:
+        'edac_mc_log_ce'
+        Generate kernel messages describing correctable errors.  These
+        errors are reported through the system message log system.
+        CE statistics will be accumulated even when CE logging is disabled.
+        LOAD TIME: module/kernel parameter: edac_mc_log_ce=[0|1]
+        RUN TIME: echo "1" > /sys/module/edac_core/parameters/edac_mc_log_ce
+Polling period control file:
+        'edac_mc_poll_msec'
+        The time period, in milliseconds, for polling for error information.
+        Too small a value wastes resources.  Too large a value might delay
+        necessary handling of errors and might loose valuable information for
+        locating the error.  1000 milliseconds (once each second) is the current
+        default. Systems which require all the bandwidth they can get, may
+        increase this.
+        LOAD TIME: module/kernel parameter: edac_mc_poll_msec=[0|1]
+        RUN TIME: echo "1000" > /sys/module/edac_core/parameters/edac_mc_poll_msec
 Panic on PCI PARITY Error:
@@ -614,21 +615,13 @@ Panic on PCI PARITY Error:
        error has been detected.
-        module/kernel parameter: panic_on_pci_parity=[0|1]
+        module/kernel parameter: edac_panic_on_pci_pe=[0|1]
        Enable:
-        echo "1" >/sys/devices/system/edac/pci/panic_on_pci_parity
+        echo "1" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe
        Disable:
-        echo "0" >/sys/devices/system/edac/pci/panic_on_pci_parity
+        echo "0" > /sys/module/edac_core/parameters/edac_panic_on_pci_pe
-Parity Count:
-        'pci_parity_count'
-        This attribute file will display the number of parity errors that
-        have been detected.
diff --git a/Documentation/fb/intelfb.txt b/Documentation/fb/intelfb.txt
index 27a3160650a4..dd9e944ea628 100644
--- a/Documentation/fb/intelfb.txt
+++ b/Documentation/fb/intelfb.txt
@@ -14,6 +14,7 @@ graphics devices.  These would include:
        Intel 915GM
        Intel 945G
        Intel 945GM
+        Intel 945GME
        Intel 965G
        Intel 965GM
diff --git a/Documentation/fb/sh7760fb.txt b/Documentation/fb/sh7760fb.txt
new file mode 100644
index 000000000000..c87bfe5c630a
--- /dev/null
+++ b/Documentation/fb/sh7760fb.txt
@@ -0,0 +1,131 @@
+SH7760/SH7763 integrated LCDC Framebuffer driver
+================================================
+0. Overwiew
+-----------
+The SH7760/SH7763 have an integrated LCD Display controller (LCDC) which
+supports (in theory) resolutions ranging from 1x1 to 1024x1024,
+with color depths ranging from 1 to 16 bits, on STN, DSTN and TFT Panels.
+Caveats:
+* Framebuffer memory must be a large chunk allocated at the top
+  of Area3 (HW requirement). Because of this requirement you should NOT
+  make the driver a module since at runtime it may become impossible to
+  get a large enough contiguous chunk of memory.
+* The driver does not support changing resolution while loaded
+  (displays aren't hotpluggable anyway)
+* Heavy flickering may be observed
+  a) if you're using 15/16bit color modes at >= 640x480 px resolutions,
+  b) during PCMCIA (or any other slow bus) activity.
+* Rotation works only 90degress clockwise, and only if horizontal
+  resolution is <= 320 pixels.
+files:   drivers/video/sh7760fb.c
+        include/asm-sh/sh7760fb.h
+        Documentation/fb/sh7760fb.txt
+1. Platform setup
+-----------------
+SH7760:
+ Video data is fetched via the DMABRG DMA engine, so you have to
+ configure the SH DMAC for DMABRG mode (write 0x94808080 to the
+ DMARSRA register somewhere at boot).
+ PFC registers PCCR and PCDR must be set to peripheral mode.
+ (write zeros to both).
+The driver does NOT do the above for you since board setup is, well, job
+of the board setup code.
+2. Panel definitions
+--------------------
+The LCDC must explicitly be told about the type of LCD panel
+attached.  Data must be wrapped in a "struct sh7760fb_platdata" and
+passed to the driver as platform_data.
+Suggest you take a closer look at the SH7760 Manual, Section 30.
+(http://documentation.renesas.com/eng/products/mpumcu/e602291_sh7760.pdf)
+The following code illustrates what needs to be done to
+get the framebuffer working on a 640x480 TFT:
+====================== cut here ======================================
+#include <linux/fb.h>
+#include <asm/sh7760fb.h>
+/*
+ * NEC NL6440bc26-01 640x480 TFT
+ * dotclock 25175 kHz
+ * Xres                640     Yres            480
+ * Htotal      800     Vtotal          525
+ * HsynStart   656     VsynStart       490
+ * HsynLenn    30      VsynLenn        2
+ *
+ * The linux framebuffer layer does not use the syncstart/synclen
+ * values but right/left/upper/lower margin values. The comments
+ * for the x_margin explain how to calculate those from given
+ * panel sync timings.
+ */
+static struct fb_videomode nl6448bc26 = {
+       .name           = "NL6448BC26",
+       .refresh        = 60,
+       .xres           = 640,
+       .yres           = 480,
+       .pixclock       = 39683,        /* in picoseconds! */
+       .hsync_len      = 30,
+       .vsync_len      = 2,
+       .left_margin    = 114,  /* HTOT - (HSYNSLEN + HSYNSTART) */
+       .right_margin   = 16,   /* HSYNSTART - XRES */
+       .upper_margin   = 33,   /* VTOT - (VSYNLEN + VSYNSTART) */
+       .lower_margin   = 10,   /* VSYNSTART - YRES */
+       .sync           = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+       .vmode          = FB_VMODE_NONINTERLACED,
+       .flag           = 0,
+};
+static struct sh7760fb_platdata sh7760fb_nl6448 = {
+       .def_mode       = &nl6448bc26,
+       .ldmtr          = LDMTR_TFT_COLOR_16,   /* 16bit TFT panel */
+       .lddfr          = LDDFR_8BPP,           /* we want 8bit output */
+       .ldpmmr         = 0x0070,
+       .ldpspr         = 0x0500,
+       .ldaclnr        = 0,
+       .ldickr         = LDICKR_CLKSRC(LCDC_CLKSRC_EXTERNAL) |
+                         LDICKR_CLKDIV(1),
+       .rotate         = 0,
+       .novsync        = 1,
+       .blank          = NULL,
+};
+/* SH7760:
+ * 0xFE300800: 256 * 4byte xRGB palette ram
+ * 0xFE300C00: 42 bytes ctrl registers
+ */
+static struct resource sh7760_lcdc_res[] = {
+       [0] = {
+               .start  = 0xFE300800,
+               .end    = 0xFE300CFF,
+               .flags  = IORESOURCE_MEM,
+       },
+       [1] = {
+               .start  = 65,
+               .end    = 65,
+               .flags  = IORESOURCE_IRQ,
+       },
+};
+static struct platform_device sh7760_lcdc_dev = {
+       .dev    = {
+               .platform_data = &sh7760fb_nl6448,
+       },
+       .name           = "sh7760-lcdc",
+       .id             = -1,
+       .resource       = sh7760_lcdc_res,
+       .num_resources  = ARRAY_SIZE(sh7760_lcdc_res),
+};
+====================== cut here ======================================
diff --git a/Documentation/fb/tridentfb.txt b/Documentation/fb/tridentfb.txt
index 8a6c8a43e6a3..45d9de5b13a3 100644
--- a/Documentation/fb/tridentfb.txt
+++ b/Documentation/fb/tridentfb.txt
@@ -3,11 +3,25 @@ Tridentfb is a framebuffer driver for some Trident chip based cards.
 The following list of chips is thought to be supported although not all are
 tested:
-those from the Image series with Cyber in their names - accelerated
+those from the TGUI series 9440/96XX and with Cyber in their names
-those with Blade in their names (Blade3D,CyberBlade...) - accelerated
+those from the Image series and with Cyber in their names
-the newer CyberBladeXP family  - nonaccelerated
+those with Blade in their names (Blade3D,CyberBlade...)
+the newer CyberBladeXP family
-Only PCI/AGP based cards are supported, none of the older Tridents.
+All families are accelerated. Only PCI/AGP based cards are supported,
+none of the older Tridents.
+The driver supports 8, 16 and 32 bits per pixel depths.
+The TGUI family requires a line length to be power of 2 if acceleration
+is enabled. This means that range of possible resolutions and bpp is
+limited comparing to the range if acceleration is disabled (see list
+of parameters below).
+Known bugs:
+1. The driver randomly locks up on 3DImage975 chip with acceleration
+   enabled. The same happens in X11 (Xorg).
+2. The ramdac speeds require some more fine tuning. It is possible to
+   switch resolution which the chip does not support at some depths for
+   older chips.
 How to use it?
 ==============
@@ -17,12 +31,11 @@ video=tridentfb
 The parameters for tridentfb are concatenated with a ':' as in this example.
-video=tridentfb:800x600,bpp=16,noaccel
+video=tridentfb:800x600-16@75,noaccel
 The second level parameters that tridentfb understands are:
 noaccel - turns off acceleration (when it doesn't work for your card)
-accel - force text acceleration (for boards which by default are noacceled)
 fp      - use flat panel related stuff
 crt     - assume monitor is present instead of fp
@@ -31,21 +44,24 @@ center 	- for flat panels and resolutions smaller than native size center the
          image, otherwise use
 stretch
-memsize - integer value in Kb, use if your card's memory size is misdetected.
+memsize - integer value in KB, use if your card's memory size is misdetected.
          look at the driver output to see what it says when initializing.
-memdiff - integer value in Kb,should be nonzero if your card reports
-          more memory than it actually has.For instance mine is 192K less than
+memdiff - integer value in KB, should be nonzero if your card reports
+          more memory than it actually has. For instance mine is 192K less than
          detection says in all three BIOS selectable situations 2M, 4M, 8M.
          Only use if your video memory is taken from main memory hence of
-          configurable size.Otherwise use memsize.
+          configurable size. Otherwise use memsize.
-          If in some modes which barely fit the memory you see garbage at the bottom
+          If in some modes which barely fit the memory you see garbage
-          this might help by not letting change to that mode anymore.
+          at the bottom this might help by not letting change to that mode
+          anymore.
 nativex - the width in pixels of the flat panel.If you know it (usually 1024
          800 or 1280) and it is not what the driver seems to detect use it.
-bpp  - bits per pixel (8,16 or 32)
+bpp     - bits per pixel (8,16 or 32)
-mode - a mode name like 800x600 (as described in Documentation/fb/modedb.txt)
+mode    - a mode name like 800x600-8@75 as described in
+          Documentation/fb/modedb.txt
 Using insane values for the above parameters will probably result in driver
 misbehaviour so take care(for instance memsize=12345678 or memdiff=23784 or
diff --git a/Documentation/fb/uvesafb.txt b/Documentation/fb/uvesafb.txt
index bcfc233a0080..7ac3c4078ff9 100644
--- a/Documentation/fb/uvesafb.txt
+++ b/Documentation/fb/uvesafb.txt
@@ -52,7 +52,7 @@ are either given on the kernel command line or as module parameters, e.g.:
 video=uvesafb:1024x768-32,mtrr:3,ywrap (compiled into the kernel)
- # modprobe uvesafb mode=1024x768-32 mtrr=3 scroll=ywrap  (module)
+ # modprobe uvesafb mode_option=1024x768-32 mtrr=3 scroll=ywrap  (module)
 Accepted options:
@@ -105,7 +105,7 @@ vtotal:n
 <mode>  The mode you want to set, in the standard modedb format.  Refer to
        modedb.txt for a detailed description.  When uvesafb is compiled as
        a module, the mode string should be provided as a value of the
-        'mode' option.
+        'mode_option' option.
 vbemode:x
        Force the use of VBE mode x.  The mode will only be set if it's
diff --git a/Documentation/fb/viafb.modes b/Documentation/fb/viafb.modes
new file mode 100644
index 000000000000..02e5b487f00e
--- /dev/null
+++ b/Documentation/fb/viafb.modes
@@ -0,0 +1,870 @@
+#
+#
+#   These data are based on the CRTC parameters in
+#
+#       VIA Integration Graphics Chip
+#       (C) 2004 VIA Technologies Inc.
+#
+#
+#   640x480, 60 Hz, Non-Interlaced (25.175 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      640     480
+#   Scan Frequency      31.469 kHz  59.94 Hz
+#   Sync Width      3.813 us    0.064 ms
+#               12 chars    2 lines
+#   Front Porch     0.636 us    0.318  ms
+#               2 chars     10 lines
+#   Back Porch      1.907 us    1.048  ms
+#               6 chars     33 lines
+#   Active Time     25.422 us   15.253 ms
+#               80 chars    480 lines
+#   Blank Time      6.356 us    1.430 ms
+#               20 chars    45 lines
+#   Polarity        negative    negative
+#
+mode "640x480-60"
+# D: 25.175 MHz, H: 31.469 kHz, V: 59.94 Hz
+    geometry 640 480 640 480 32
+    timings 39722 48 16 33 10 96 2 endmode mode "480x640-60"
+# D: 24.823 MHz, H: 39.780 kHz, V: 60.00 Hz
+    geometry 480 640 480 640 32 timings 39722 72 24 19 1 48 3 endmode
+#
+#   640x480, 75 Hz, Non-Interlaced (31.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      640     480
+#   Scan Frequency      37.500 kHz  75.00 Hz
+#   Sync Width      2.032 us    0.080 ms
+#               8 chars     3 lines
+#   Front Porch     0.508 us    0.027 ms
+#               2 chars     1 lines
+#   Back Porch      3.810 us    0.427 ms
+#               15 chars    16 lines
+#   Active Time     20.317 us   12.800 ms
+#               80 chars    480 lines
+#   Blank Time      6.349 us    0.533 ms
+#               25 chars    20 lines
+#   Polarity        negative    negative
+#
+    mode "640x480-75"
+# D: 31.50 MHz, H: 37.500 kHz, V: 75.00 Hz
+    geometry 640 480 640 480 32 timings 31747 120 16 16 1 64 3 endmode
+#
+#   640x480, 85 Hz, Non-Interlaced (36.000 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      640     480
+#   Scan Frequency  43.269 kHz  85.00 Hz
+#   Sync Width      1.556 us    0.069 ms
+#               7 chars     3 lines
+#   Front Porch     1.556 us    0.023 ms
+#               7 chars     1 lines
+#   Back Porch      2.222 us    0.578 ms
+#               10 chars    25 lines
+#   Active Time     17.778 us   11.093 ms
+#               80 chars    480 lines
+#   Blank Time      5.333 us    0.670 ms
+#               24 chars    29 lines
+#   Polarity        negative    negative
+#
+    mode "640x480-85"
+# D: 36.000 MHz, H: 43.269 kHz, V: 85.00 Hz
+    geometry 640 480 640 480 32 timings 27777 80 56 25 1 56 3 endmode
+#
+#   640x480, 100 Hz, Non-Interlaced (43.163 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      640     480
+#   Scan Frequency      50.900 kHz  100.00 Hz
+#   Sync Width      1.483 us    0.058 ms
+#               8 chars     3 lines
+#   Front Porch     0.927 us    0.019 ms
+#               5 chars     1 lines
+#   Back Porch      2.409 us    0.475 ms
+#               13 chars    25 lines
+#   Active Time     14.827 us   9.430 ms
+#               80 chars    480 lines
+#   Blank Time      4.819 us    0.570 ms
+#               26 chars    29 lines
+#   Polarity        positive    positive
+#
+    mode "640x480-100"
+# D: 43.163 MHz, H: 50.900 kHz, V: 100.00 Hz
+    geometry 640 480 640 480 32 timings 23168 104 40 25 1 64 3 endmode
+#
+#   640x480, 120 Hz, Non-Interlaced (52.406 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      640     480
+#   Scan Frequency      61.800 kHz  120.00 Hz
+#   Sync Width      1.221 us    0.048 ms
+#               8 chars         3 lines
+#   Front Porch     0.763 us    0.016 ms
+#               5 chars     1 lines
+#   Back Porch      1.984 us    0.496 ms
+#               13 chars    31 lines
+#   Active Time     12.212 us   7.767 ms
+#               80 chars    480 lines
+#   Blank Time      3.969 us    0.566 ms
+#               26 chars    35 lines
+#   Polarity        positive    positive
+#
+    mode "640x480-120"
+# D: 52.406 MHz, H: 61.800 kHz, V: 120.00 Hz
+    geometry 640 480 640 480 32 timings 19081 104 40 31 1 64 3 endmode
+#
+#   720x480, 60 Hz, Non-Interlaced (26.880 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      720     480
+#   Scan Frequency      30.000 kHz  60.241 Hz
+#   Sync Width      2.679 us    0.099 ms
+#               9 chars     3 lines
+#   Front Porch     0.595 us    0.033 ms
+#               2 chars     1 lines
+#   Back Porch      3.274 us    0.462 ms
+#               11 chars    14 lines
+#   Active Time     26.786 us   16.000 ms
+#               90 chars    480 lines
+#   Blank Time      6.548 us    0.600 ms
+#               22 chars    18 lines
+#   Polarity        positive    positive
+#
+    mode "720x480-60"
+# D: 26.880 MHz, H: 30.000 kHz, V: 60.24 Hz
+    geometry 720 480 720 480 32 timings 37202 88 16 14 1 72 3 endmode
+#
+#   800x480, 60 Hz, Non-Interlaced (29.581 MHz dotclock)
+#
+#               Horizontal    Vertical
+#   Resolution      800         480
+#   Scan Frequency  29.892 kHz  60.00 Hz
+#   Sync Width      2.704 us    100.604 us
+#                   10 chars    3 lines
+#   Front Porch     0.541 us    33.535 us
+#                   2 chars     1 lines
+#   Back Porch      3.245 us    435.949 us
+#                   12 chars    13 lines
+#   Active Time     27.044 us   16.097 ms
+#                   100 chars   480 lines
+#   Blank Time      6.491 us    0.570 ms
+#                   24 chars    17 lines
+#   Polarity        positive    positive
+#
+    mode "800x480-60"
+# D: 29.500 MHz, H: 29.738 kHz, V: 60.00 Hz
+    geometry 800 480 800 480 32 timings 33805 96 24 10 3 72 7 endmode
+#
+#   720x576, 60 Hz, Non-Interlaced (32.668 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      720     576
+#   Scan Frequency      35.820 kHz  60.00 Hz
+#   Sync Width      2.204 us    0.083 ms
+#               9 chars     3 lines
+#   Front Porch     0.735 us    0.027 ms
+#               3 chars     1 lines
+#   Back Porch      2.939 us    0.459 ms
+#               12 chars    17 lines
+#   Active Time     22.040 us   16.080 ms
+#               90 chars    476 lines
+#   Blank Time      5.877 us    0.586 ms
+#               24 chars    21 lines
+#   Polarity        positive    positive
+#
+    mode "720x576-60"
+# D: 32.668 MHz, H: 35.820 kHz, V: 60.00 Hz
+    geometry 720 576 720 576 32 timings 30611 96 24 17 1 72 3 endmode
+#
+#   800x600, 60 Hz, Non-Interlaced (40.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      800     600
+#   Scan Frequency      37.879 kHz  60.32 Hz
+#   Sync Width      3.200 us    0.106 ms
+#               16 chars    4 lines
+#   Front Porch     1.000 us    0.026 ms
+#               5 chars     1 lines
+#   Back Porch      2.200 us    0.607 ms
+#               11 chars    23 lines
+#   Active Time     20.000 us   15.840 ms
+#               100 chars   600 lines
+#   Blank Time      6.400 us    0.739 ms
+#               32 chars    28 lines
+#   Polarity        positive    positive
+#
+    mode "800x600-60"
+# D: 40.00 MHz, H: 37.879 kHz, V: 60.32 Hz
+    geometry 800 600 800 600 32
+    timings 25000 88 40 23 1 128 4 hsync high vsync high endmode
+#
+#   800x600, 75 Hz, Non-Interlaced (49.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      800     600
+#   Scan Frequency      46.875 kHz  75.00 Hz
+#   Sync Width      1.616 us    0.064 ms
+#               10 chars    3 lines
+#   Front Porch     0.323 us    0.021 ms
+#               2 chars     1 lines
+#   Back Porch      3.232 us    0.448 ms
+#               20 chars    21 lines
+#   Active Time     16.162 us   12.800 ms
+#               100 chars   600 lines
+#   Blank Time      5.172 us    0.533 ms
+#               32 chars    25 lines
+#   Polarity        positive    positive
+#
+    mode "800x600-75"
+# D: 49.50 MHz, H: 46.875 kHz, V: 75.00 Hz
+    geometry 800 600 800 600 32
+    timings 20203 160 16 21 1 80 3 hsync high vsync high endmode
+#
+#   800x600, 85 Hz, Non-Interlaced (56.25 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      800     600
+#   Scan Frequency      53.674 kHz  85.061 Hz
+#   Sync Width      1.138 us    0.056 ms
+#               8 chars     3 lines
+#   Front Porch     0.569 us    0.019 ms
+#               4 chars     1 lines
+#   Back Porch      2.702 us    0.503 ms
+#               19 chars    27 lines
+#   Active Time     14.222 us   11.179 ms
+#               100 chars   600 lines
+#   Blank Time      4.409 us    0.578 ms
+#               31 chars    31 lines
+#   Polarity        positive    positive
+#
+    mode "800x600-85"
+# D: 56.25 MHz, H: 53.674 kHz, V: 85.061 Hz
+    geometry 800 600 800 600 32
+    timings 17777 152 32 27 1 64 3 hsync high vsync high endmode
+#
+#   800x600, 100 Hz, Non-Interlaced (67.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      800     600
+#   Scan Frequency      62.500 kHz  100.00 Hz
+#   Sync Width      0.948 us    0.064 ms
+#               8 chars     4 lines
+#   Front Porch     0.000 us    0.112 ms
+#               0 chars     7 lines
+#   Back Porch      3.200 us    0.224 ms
+#               27 chars    14 lines
+#   Active Time     11.852 us   9.600 ms
+#               100 chars   600 lines
+#   Blank Time      4.148 us    0.400 ms
+#               35 chars    25 lines
+#   Polarity        positive    positive
+#
+    mode "800x600-100"
+# D: 67.50 MHz, H: 62.500 kHz, V: 100.00 Hz
+    geometry 800 600 800 600 32
+    timings 14667 216 0 14 7 64 4 hsync high vsync high endmode
+#
+#   800x600, 120 Hz, Non-Interlaced (83.950 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      800     600
+#   Scan Frequency  77.160 kHz  120.00 Hz
+#   Sync Width      1.048 us    0.039 ms
+#               11 chars    3 lines
+#   Front Porch     0.667 us    0.013 ms
+#               7 chars     1 lines
+#   Back Porch      1.715 us    0.507 ms
+#               18 chars    39 lines
+#   Active Time     9.529 us    7.776 ms
+#               100 chars   600 lines
+#   Blank Time      3.431 us    0.557 ms
+#               36 chars    43 lines
+#   Polarity        positive    positive
+#
+    mode "800x600-120"
+# D: 83.950 MHz, H: 77.160 kHz, V: 120.00 Hz
+    geometry 800 600 800 600 32
+    timings 11912 144 56 39 1 88 3 hsync high vsync high endmode
+#
+#   848x480, 60 Hz, Non-Interlaced (31.490 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      848     480
+#   Scan Frequency  29.820 kHz  60.00 Hz
+#   Sync Width      2.795 us    0.099 ms
+#               11 chars    3 lines
+#   Front Porch     0.508 us    0.033 ms
+#               2 chars     1 lines
+#   Back Porch      3.303 us    0.429 ms
+#               13 chars    13 lines
+#   Active Time     26.929 us   16.097 ms
+#               106 chars   480 lines
+#   Blank Time      6.605 us    0.570 ms
+#               26 chars    17 lines
+#   Polarity        positive    positive
+#
+    mode "848x480-60"
+# D: 31.500 MHz, H: 29.830 kHz, V: 60.00 Hz
+    geometry 848 480 848 480 32
+    timings 31746 104 24 12 3 80 5 hsync high vsync high endmode
+#
+#   856x480, 60 Hz, Non-Interlaced (31.728 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      856     480
+#   Scan Frequency  29.820 kHz  60.00 Hz
+#   Sync Width      2.774 us    0.099 ms
+#               11 chars    3 lines
+#   Front Porch     0.504 us    0.033 ms
+#               2 chars     1 lines
+#   Back Porch      3.728 us    0.429 ms
+#               13 chars    13 lines
+#   Active Time     26.979 us   16.097 ms
+#               107 chars   480 lines
+#   Blank Time      6.556 us    0.570 ms
+#               26 chars    17 lines
+#   Polarity        positive    positive
+#
+    mode "856x480-60"
+# D: 31.728 MHz, H: 29.820 kHz, V: 60.00 Hz
+    geometry 856 480 856 480 32
+    timings 31518 104 16 13 1 88 3
+    hsync high vsync high endmode mode "960x600-60"
+# D: 45.250 MHz, H: 37.212 kHz, V: 60.00 Hz
+    geometry 960 600 960 600 32 timings 22099 128 32 15 3 96 6 endmode
+#
+#   1000x600, 60 Hz, Non-Interlaced (48.068 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1000     600
+#   Scan Frequency  37.320 kHz  60.00 Hz
+#   Sync Width      2.164 us    0.080 ms
+#               13 chars    3 lines
+#   Front Porch     0.832 us    0.027 ms
+#               5 chars     1 lines
+#   Back Porch      2.996 us    0.483 ms
+#               18 chars    18 lines
+#   Active Time     20.804 us   16.077 ms
+#               125 chars   600 lines
+#   Blank Time      5.991 us    0.589 ms
+#               36 chars    22 lines
+#   Polarity        negative    positive
+#
+    mode "1000x600-60"
+# D: 48.068 MHz, H: 37.320 kHz, V: 60.00 Hz
+    geometry 1000 600 1000 600 32
+    timings 20834 144 40 18 1 104 3 endmode mode "1024x576-60"
+# D: 46.996 MHz, H: 35.820 kHz, V: 60.00 Hz
+    geometry 1024 576 1024 576 32
+    timings 21278 144 40 17 1 104 3 endmode mode "1024x600-60"
+# D: 48.964 MHz, H: 37.320 kHz, V: 60.00 Hz
+    geometry 1024 600 1024 600 32
+    timings 20461 144 40 18 1 104 3 endmode mode "1088x612-60"
+# D: 52.952 MHz, H: 38.040 kHz, V: 60.00 Hz
+    geometry 1088 612 1088 612 32 timings 18877 152 48 16 3 104 5 endmode
+#
+#   1024x512, 60 Hz, Non-Interlaced (41.291 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1024    512
+#   Scan Frequency  31.860 kHz  60.00 Hz
+#   Sync Width      2.519 us    0.094 ms
+#               13 chars    3 lines
+#   Front Porch     0.775 us    0.031 ms
+#               4 chars     1 lines
+#   Back Porch      3.294 us    0.465 ms
+#               17 chars    15 lines
+#   Active Time     24.800 us   16.070 ms
+#               128 chars   512 lines
+#   Blank Time      6.587 us    0.596 ms
+#               34 chars    19 lines
+#   Polarity        positive    positive
+#
+    mode "1024x512-60"
+# D: 41.291 MHz, H: 31.860 kHz, V: 60.00 Hz
+    geometry 1024 512 1024 512 32
+    timings 24218 126 32 15 1 104 3 hsync high vsync high endmode
+#
+#   1024x600, 60 Hz, Non-Interlaced (48.875 MHz dotclock)
+#
+#                     Horizontal  Vertical
+#   Resolution          1024        768
+#   Scan Frequency      37.252 kHz  60.00 Hz
+#   Sync Width          2.128 us    80.532us
+#                       13 chars    3 lines
+#   Front Porch        0.818 us     26.844 us
+#                       5 chars     1 lines
+#   Back Porch          2.946 us    483.192 us
+#                       18 chars    18 lines
+#   Active Time         20.951 us   16.697 ms
+#                       128 chars   622 lines
+#   Blank Time          5.893 us    0.591 ms
+#                       36 chars    22 lines
+#   Polarity            negative    positive
+#
+#mode "1024x600-60"
+#     # D: 48.875 MHz, H: 37.252 kHz, V: 60.00 Hz
+#     geometry 1024 600 1024 600 32
+#    timings 20460  144 40 18 1 104  3
+# endmode
+#
+#   1024x768, 60 Hz, Non-Interlaced (65.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1024        768
+#   Scan Frequency      48.363 kHz  60.00 Hz
+#   Sync Width      2.092 us    0.124 ms
+#               17 chars    6 lines
+#   Front Porch     0.369 us    0.062 ms
+#               3 chars     3 lines
+#   Back Porch      2.462 us    0.601 ms
+#               20 chars    29 lines
+#   Active Time     15.754 us   15.880 ms
+#               128 chars   768 lines
+#   Blank Time      4.923 us    0.786 ms
+#               40 chars    38 lines
+#   Polarity        negative    negative
+#
+    mode "1024x768-60"
+# D: 65.00 MHz, H: 48.363 kHz, V: 60.00 Hz
+    geometry 1024 768 1024 768 32 timings 15385 160 24 29 3 136 6 endmode
+#
+#   1024x768, 75 Hz, Non-Interlaced (78.75 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1024        768
+#   Scan Frequency      60.023 kHz  75.03 Hz
+#   Sync Width      1.219 us    0.050 ms
+#               12 chars    3 lines
+#   Front Porch     0.203 us    0.017 ms
+#               2 chars     1 lines
+#   Back Porch      2.235 us    0.466 ms
+#               22 chars    28 lines
+#   Active Time     13.003 us   12.795 ms
+#               128 chars   768 lines
+#   Blank Time      3.657 us    0.533 ms
+#               36 chars    32 lines
+#   Polarity        positive    positive
+#
+    mode "1024x768-75"
+# D: 78.75 MHz, H: 60.023 kHz, V: 75.03 Hz
+    geometry 1024 768 1024 768 32
+    timings 12699 176 16 28 1 96 3 hsync high vsync high endmode
+#
+#   1024x768, 85 Hz, Non-Interlaced (94.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1024        768
+#   Scan Frequency  68.677 kHz  85.00 Hz
+#   Sync Width      1.016 us    0.044 ms
+#               12 chars    3 lines
+#   Front Porch     0.508 us    0.015 ms
+#               6 chars     1 lines
+#   Back Porch      2.201 us    0.524 ms
+#               26 chars    36 lines
+#   Active Time     10.836 us   11.183 ms
+#               128 chars   768 lines
+#   Blank Time      3.725 us    0.582 ms
+#               44 chars    40 lines
+#   Polarity        positive    positive
+#
+    mode "1024x768-85"
+# D: 94.50 MHz, H: 68.677 kHz, V: 85.00 Hz
+    geometry 1024 768 1024 768 32
+    timings 10582 208 48 36 1 96 3 hsync high vsync high endmode
+#
+#   1024x768, 100 Hz, Non-Interlaced (110.0 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1024        768
+#   Scan Frequency      79.023 kHz  99.78 Hz
+#   Sync Width      0.800 us    0.101 ms
+#               11 chars    8 lines
+#   Front Porch     0.000 us    0.000 ms
+#               0 chars     0 lines
+#   Back Porch      2.545 us    0.202 ms
+#               35 chars    16 lines
+#   Active Time     9.309 us    9.719 ms
+#               128 chars   768 lines
+#   Blank Time      3.345 us    0.304 ms
+#               46 chars    24 lines
+#   Polarity        negative    negative
+#
+    mode "1024x768-100"
+# D: 113.3 MHz, H: 79.023 kHz, V: 99.78 Hz
+    geometry 1024 768 1024 768 32
+    timings 8825 280 0 16 0 88 8 endmode mode "1152x720-60"
+# D: 66.750 MHz, H: 44.859 kHz, V: 60.00 Hz
+    geometry 1152 720 1152 720 32 timings 14981 168 56 19 3 112 6 endmode
+#
+#   1152x864, 75 Hz, Non-Interlaced (110.0 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1152        864
+#   Scan Frequency      75.137 kHz  74.99 Hz
+#   Sync Width      1.309 us    0.106 ms
+#               18 chars    8 lines
+#   Front Porch     0.245 us    0.599 ms
+#               3 chars     45 lines
+#   Back Porch      1.282 us    1.132 ms
+#               18 chars    85 lines
+#   Active Time     10.473 us   11.499 ms
+#               144 chars   864 lines
+#   Blank Time      2.836 us    1.837 ms
+#               39 chars    138 lines
+#   Polarity        positive    positive
+#
+    mode "1152x864-75"
+# D: 110.0 MHz, H: 75.137 kHz, V: 74.99 Hz
+    geometry 1152 864 1152 864 32
+    timings 9259 144 24 85 45 144 8
+    hsync high vsync high endmode mode "1200x720-60"
+# D: 70.184 MHz, H: 44.760 kHz, V: 60.00 Hz
+    geometry 1200 720 1200 720 32
+    timings 14253 184 28 22 1 128 3 endmode mode "1280x600-60"
+# D: 61.503 MHz, H: 37.320 kHz, V: 60.00 Hz
+    geometry 1280 600 1280 600 32
+    timings 16260 184 28 18 1 128 3 endmode mode "1280x720-50"
+# D: 60.466 MHz, H: 37.050 kHz, V: 50.00 Hz
+    geometry 1280 720 1280 720 32
+    timings 16538 176 48 17 1 128 3 endmode mode "1280x768-50"
+# D: 65.178 MHz, H: 39.550 kHz, V: 50.00 Hz
+    geometry 1280 768 1280 768 32 timings 15342 184 28 19 1 128 3 endmode
+#
+#   1280x768, 60 Hz, Non-Interlaced (80.136 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280    768
+#   Scan Frequency  47.700 kHz  60.00 Hz
+#   Sync Width      1.697 us    0.063 ms
+#               17 chars    3 lines
+#   Front Porch     0.799 us    0.021 ms
+#               8 chars     1 lines
+#   Back Porch      2.496 us    0.483 ms
+#               25 chars    23 lines
+#   Active Time     15.973 us   16.101 ms
+#               160 chars   768 lines
+#   Blank Time      4.992 us    0.566 ms
+#               50 chars    27 lines
+#   Polarity        positive    positive
+#
+    mode "1280x768-60"
+# D: 80.13 MHz, H: 47.700 kHz, V: 60.00 Hz
+    geometry 1280 768 1280 768 32
+    timings 12480 200 48 23 1 126 3 hsync high vsync high endmode
+#
+#   1280x800, 60 Hz, Non-Interlaced (83.375 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280    800
+#   Scan Frequency  49.628 kHz  60.00 Hz
+#   Sync Width      1.631 us    60.450 us
+#                   17 chars    3 lines
+#   Front Porch     0.768 us    20.15 us
+#                   8 chars     1 lines
+#   Back Porch      2.399 us    0.483 ms
+#                   25 chars    24 lines
+#   Active Time     15.352 us   16.120 ms
+#                   160 chars   800 lines
+#   Blank Time      4.798 us    0.564 ms
+#                   50 chars    28 lines
+#   Polarity        negtive    positive
+#
+    mode "1280x800-60"
+# D: 83.500 MHz, H: 49.702 kHz, V: 60.00 Hz
+    geometry 1280 800 1280 800 32 timings 11994 200 72 22 3 128 6 endmode
+#
+#   1280x960, 60 Hz, Non-Interlaced (108.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280    960
+#   Scan Frequency  60.000 kHz  60.00 Hz
+#   Sync Width      1.037 us    0.050 ms
+#               14 chars    3 lines
+#   Front Porch     0.889 us    0.017 ms
+#               12 chars    1 lines
+#   Back Porch      2.889 us    0.600 ms
+#               39 chars    36 lines
+#   Active Time     11.852 us   16.000 ms
+#               160 chars   960 lines
+#   Blank Time      4.815 us    0.667 ms
+#               65 chars    40 lines
+#   Polarity        positive    positive
+#
+    mode "1280x960-60"
+# D: 108.00 MHz, H: 60.000 kHz, V: 60.00 Hz
+    geometry 1280 960 1280 960 32
+    timings 9259 312 96 36 1 112 3 hsync high vsync high endmode
+#
+#   1280x1024, 60 Hz, Non-Interlaced (108.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280        1024
+#   Scan Frequency      63.981 kHz  60.02 Hz
+#   Sync Width      1.037 us    0.047 ms
+#               14 chars    3 lines
+#   Front Porch     0.444 us    0.015 ms
+#               6 chars     1 lines
+#   Back Porch      2.297 us    0.594 ms
+#               31 chars    38 lines
+#   Active Time     11.852 us   16.005 ms
+#               160 chars   1024 lines
+#   Blank Time      3.778 us    0.656 ms
+#               51 chars    42 lines
+#   Polarity        positive    positive
+#
+    mode "1280x1024-60"
+# D: 108.00 MHz, H: 63.981 kHz, V: 60.02 Hz
+    geometry 1280 1024 1280 1024 32
+    timings 9260 248 48 38 1 112 3 hsync high vsync high endmode
+#
+#   1280x1024, 75 Hz, Non-Interlaced (135.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280        1024
+#   Scan Frequency      79.976 kHz  75.02 Hz
+#   Sync Width      1.067 us    0.038 ms
+#               18 chars    3 lines
+#   Front Porch     0.119 us    0.012 ms
+#               2 chars     1 lines
+#   Back Porch      1.837 us    0.475 ms
+#               31 chars    38 lines
+#   Active Time     9.481 us    12.804 ms
+#               160 chars   1024 lines
+#   Blank Time      3.022 us    0.525 ms
+#               51 chars    42 lines
+#   Polarity        positive    positive
+#
+    mode "1280x1024-75"
+# D: 135.00 MHz, H: 79.976 kHz, V: 75.02 Hz
+    geometry 1280 1024 1280 1024 32
+    timings 7408 248 16 38 1 144 3 hsync high vsync high endmode
+#
+#   1280x1024, 85 Hz, Non-Interlaced (157.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280        1024
+#   Scan Frequency  91.146 kHz  85.02 Hz
+#   Sync Width      1.016 us    0.033 ms
+#               20 chars    3 lines
+#   Front Porch     0.406 us    0.011 ms
+#               8 chars     1 lines
+#   Back Porch      1.422 us    0.483 ms
+#               28 chars    44 lines
+#   Active Time     8.127 us    11.235 ms
+#               160 chars   1024 lines
+#   Blank Time      2.844 us    0.527 ms
+#               56 chars    48 lines
+#   Polarity        positive    positive
+#
+    mode "1280x1024-85"
+# D: 157.50 MHz, H: 91.146 kHz, V: 85.02 Hz
+    geometry 1280 1024 1280 1024 32
+    timings 6349 224 64 44 1 160 3
+    hsync high vsync high endmode mode "1440x900-60"
+# D: 106.500 MHz, H: 55.935 kHz, V: 60.00 Hz
+    geometry 1440 900 1440 900 32
+    timings 9390 232 80 25 3 152 6
+    hsync high vsync high endmode mode "1440x900-75"
+# D: 136.750 MHz, H: 70.635 kHz, V: 75.00 Hz
+    geometry 1440 900 1440 900 32
+    timings 7315 248 96 33 3 152 6 hsync high vsync high endmode
+#
+#   1440x1050, 60 Hz, Non-Interlaced (125.10 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1440        1050
+#   Scan Frequency      65.220 kHz  60.00 Hz
+#   Sync Width      1.204 us    0.046 ms
+#               19 chars    3 lines
+#   Front Porch     0.760 us    0.015 ms
+#               12 chars    1 lines
+#   Back Porch      1.964 us    0.495 ms
+#               31 chars    33 lines
+#   Active Time     11.405 us   16.099 ms
+#               180 chars   1050 lines
+#   Blank Time      3.928 us    0.567 ms
+#               62 chars    37 lines
+#   Polarity        positive    positive
+#
+    mode "1440x1050-60"
+# D: 125.10 MHz, H: 65.220 kHz, V: 60.00 Hz
+    geometry 1440 1050 1440 1050 32
+    timings 7993 248 96 33 1 152 3
+    hsync high vsync high endmode mode "1600x900-60"
+# D: 118.250 MHz, H: 55.990 kHz, V: 60.00 Hz
+    geometry 1600 900 1600 900 32
+    timings 8415 256 88 26 3 168 5 endmode mode "1600x1024-60"
+# D: 136.358 MHz, H: 63.600 kHz, V: 60.00 Hz
+    geometry 1600 1024 1600 1024 32 timings 7315 272 104 32 1 168 3 endmode
+#
+#   1600x1200, 60 Hz, Non-Interlaced (156.00 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1600        1200
+#   Scan Frequency      76.200 kHz  60.00 Hz
+#   Sync Width      1.026 us    0.105 ms
+#               20 chars    8 lines
+#   Front Porch     0.205 us    0.131 ms
+#               4 chars     10 lines
+#   Back Porch      1.636 us    0.682 ms
+#               32 chars    52 lines
+#   Active Time     10.256 us   15.748 ms
+#               200 chars   1200 lines
+#   Blank Time      2.872 us    0.866 ms
+#               56 chars    66 lines
+#   Polarity        negative    negative
+#
+    mode "1600x1200-60"
+# D: 156.00 MHz, H: 76.200 kHz, V: 60.00 Hz
+    geometry 1600 1200 1600 1200 32 timings 6172 256 32 52 10 160 8 endmode
+#
+#   1600x1200, 75 Hz, Non-Interlaced (202.50 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1600        1200
+#   Scan Frequency  93.750 kHz  75.00 Hz
+#   Sync Width      0.948 us    0.032 ms
+#               24 chars    3 lines
+#   Front Porch     0.316 us    0.011 ms
+#               8 chars     1 lines
+#   Back Porch      1.501 us    0.491 ms
+#               38 chars    46 lines
+#   Active Time     7.901 us    12.800 ms
+#               200 chars   1200 lines
+#   Blank Time      2.765 us    0.533 ms
+#               70 chars    50 lines
+#   Polarity    positive    positive
+#
+    mode "1600x1200-75"
+# D: 202.50 MHz, H: 93.750 kHz, V: 75.00 Hz
+    geometry 1600 1200 1600 1200 32
+    timings 4938 304 64 46 1 192 3
+    hsync high vsync high endmode mode "1680x1050-60"
+# D: 146.250 MHz, H: 65.290 kHz, V: 59.954 Hz
+    geometry 1680 1050 1680 1050 32
+    timings 6814 280 104 30 3 176 6
+    hsync high vsync high endmode mode "1680x1050-75"
+# D: 187.000 MHz, H: 82.306 kHz, V: 74.892 Hz
+    geometry 1680 1050 1680 1050 32
+    timings 5348 296 120 40 3 176 6
+    hsync high vsync high endmode mode "1792x1344-60"
+# D: 202.975 MHz, H: 83.460 kHz, V: 60.00 Hz
+    geometry 1792 1344 1792 1344 32
+    timings 4902 320 128 43 1 192 3
+    hsync high vsync high endmode mode "1856x1392-60"
+# D: 218.571 MHz, H: 86.460 kHz, V: 60.00 Hz
+    geometry 1856 1392 1856 1392 32
+    timings 4577 336 136 45 1 200 3
+    hsync high vsync high endmode mode "1920x1200-60"
+# D: 193.250 MHz, H: 74.556 kHz, V: 60.00 Hz
+    geometry 1920 1200 1920 1200 32
+    timings 5173 336 136 36 3 200 6
+    hsync high vsync high endmode mode "1920x1440-60"
+# D: 234.000 MHz, H:90.000 kHz, V: 60.00 Hz
+    geometry 1920 1440 1920 1440 32
+    timings 4274 344 128 56 1 208 3
+    hsync high vsync high endmode mode "1920x1440-75"
+# D: 297.000 MHz, H:112.500 kHz, V: 75.00 Hz
+    geometry 1920 1440 1920 1440 32
+    timings 3367 352 144 56 1 224 3
+    hsync high vsync high endmode mode "2048x1536-60"
+# D: 267.250 MHz, H: 95.446 kHz, V: 60.00 Hz
+    geometry 2048 1536 2048 1536 32
+    timings 3742 376 152 49 3 224 4 hsync high vsync high endmode
+#
+#   1280x720, 60 Hz, Non-Interlaced (74.481 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1280        720
+#   Scan Frequency      44.760 kHz  60.00 Hz
+#   Sync Width      1.826 us    67.024 ms
+#               17 chars    3 lines
+#   Front Porch     0.752 us    22.341 ms
+#               7 chars     1 lines
+#   Back Porch      2.578 us    491.510 ms
+#               24 chars    22 lines
+#   Active Time     17.186 us   16.086 ms
+#               160 chars   720 lines
+#   Blank Time      5.156 us    0.581 ms
+#               48 chars    26 lines
+#   Polarity        negative    negative
+#
+    mode "1280x720-60"
+# D: 74.481 MHz, H: 44.760 kHz, V: 60.00 Hz
+    geometry 1280 720 1280 720 32 timings 13426 192 64 22 1 136 3 endmode
+#
+#   1920x1080, 60 Hz, Non-Interlaced (172.798 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1920        1080
+#   Scan Frequency      67.080 kHz  60.00 Hz
+#   Sync Width      1.204 us    44.723 ms
+#               26 chars    3 lines
+#   Front Porch     0.694 us    14.908 ms
+#               15 chars     1 lines
+#   Back Porch      1.898 us    506.857 ms
+#               41 chars    34 lines
+#   Active Time     11.111 us   16.100 ms
+#               240 chars   1080 lines
+#   Blank Time      3.796 us    0.566 ms
+#               82 chars    38 lines
+#   Polarity        negative    negative
+#
+    mode "1920x1080-60"
+# D: 74.481 MHz, H: 67.080 kHz, V: 60.00 Hz
+    geometry 1920 1080 1920 1080 32 timings 5787 328 120 34 1 208 3 endmode
+#
+#   1400x1050, 60 Hz, Non-Interlaced (122.61 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1400        1050
+#   Scan Frequency      65.218 kHz  59.99 Hz
+#   Sync Width      1.037 us    0.047 ms
+#               19 chars    3 lines
+#   Front Porch     0.444 us    0.015 ms
+#               11 chars     1 lines
+#   Back Porch      1.185 us    0.188 ms
+#               30 chars    33 lines
+#   Active Time     12.963 us   16.411 ms
+#               175 chars   1050 lines
+#   Blank Time      2.667 us    0.250 ms
+#               60 chars    37 lines
+#   Polarity        negative    positive
+#
+    mode "1400x1050-60"
+# D: 122.750 MHz, H: 65.317 kHz, V: 59.99 Hz
+    geometry 1400 1050 1408 1050 32
+    timings 8214 232 88 32 3 144 4 endmode mode "1400x1050-75"
+# D: 156.000 MHz, H: 82.278 kHz, V: 74.867 Hz
+    geometry 1400 1050 1408 1050 32 timings 6410 248 104 42 3 144 4 endmode
+#
+#   1366x768, 60 Hz, Non-Interlaced (85.86 MHz dotclock)
+#
+#               Horizontal  Vertical
+#   Resolution      1366        768
+#   Scan Frequency      47.700 kHz  60.00 Hz
+#   Sync Width      1.677 us    0.063 ms
+#               18 chars    3 lines
+#   Front Porch     0.839 us    0.021 ms
+#               9 chars     1 lines
+#   Back Porch      2.516 us    0.482 ms
+#               27 chars    23 lines
+#   Active Time     15.933 us   16.101 ms
+#               171 chars   768 lines
+#   Blank Time      5.031 us    0.566 ms
+#               54 chars    27 lines
+#   Polarity        negative    positive
+#
+    mode "1360x768-60"
+# D: 84.750 MHz, H: 47.720 kHz, V: 60.00 Hz
+    geometry 1360 768 1360 768 32
+    timings 11799 208 72 22 3 136 5 endmode mode "1366x768-60"
+# D: 85.86 MHz, H: 47.700 kHz, V: 60.00 Hz
+    geometry 1366 768 1366 768 32
+    timings 11647 216 72 23 1 144 3 endmode mode "1366x768-50"
+# D: 69,924 MHz, H: 39.550 kHz, V: 50.00 Hz
+    geometry 1366 768 1366 768 32 timings 14301 200 56 19 1 144 3 endmode
diff --git a/Documentation/fb/viafb.txt b/Documentation/fb/viafb.txt
new file mode 100644
index 000000000000..67dbf442b0b6
--- /dev/null
+++ b/Documentation/fb/viafb.txt
@@ -0,0 +1,214 @@
+        VIA Integration Graphic Chip Console Framebuffer Driver
+[Platform]
+-----------------------
+    The console framebuffer driver is for graphics chips of
+    VIA UniChrome Family(CLE266, PM800 / CN400 / CN300,
+                        P4M800CE / P4M800Pro / CN700 / VN800,
+                        CX700 / VX700, K8M890, P4M890,
+                        CN896 / P4M900, VX800)
+[Driver features]
+------------------------
+    Device: CRT, LCD, DVI
+    Support viafb_mode:
+        CRT:
+            640x480(60, 75, 85, 100, 120 Hz), 720x480(60 Hz),
+            720x576(60 Hz), 800x600(60, 75, 85, 100, 120 Hz),
+            848x480(60 Hz), 856x480(60 Hz), 1024x512(60 Hz),
+            1024x768(60, 75, 85, 100 Hz), 1152x864(75 Hz),
+            1280x768(60 Hz), 1280x960(60 Hz), 1280x1024(60, 75, 85 Hz),
+            1440x1050(60 Hz), 1600x1200(60, 75 Hz), 1280x720(60 Hz),
+            1920x1080(60 Hz), 1400x1050(60 Hz), 800x480(60 Hz)
+    color depth: 8 bpp, 16 bpp, 32 bpp supports.
+    Support 2D hardware accelerator.
+[Using the viafb module]
+-- -- --------------------
+    Start viafb with default settings:
+        #modprobe viafb
+    Start viafb with with user options:
+        #modprobe viafb viafb_mode=800x600 viafb_bpp=16 viafb_refresh=60
+                  viafb_active_dev=CRT+DVI viafb_dvi_port=DVP1
+                  viafb_mode1=1024x768 viafb_bpp=16 viafb_refresh1=60
+                  viafb_SAMM_ON=1
+    viafb_mode:
+        640x480 (default)
+        720x480
+        800x600
+        1024x768
+        ......
+    viafb_bpp:
+        8, 16, 32 (default:32)
+    viafb_refresh:
+        60, 75, 85, 100, 120 (default:60)
+    viafb_lcd_dsp_method:
+        0 : expansion (default)
+        1 : centering
+    viafb_lcd_mode:
+        0 : LCD panel with LSB data format input (default)
+        1 : LCD panel with MSB data format input
+    viafb_lcd_panel_id:
+        0 : Resolution: 640x480, Channel: single, Dithering: Enable
+        1 : Resolution: 800x600, Channel: single, Dithering: Enable
+        2 : Resolution: 1024x768, Channel: single, Dithering: Enable (default)
+        3 : Resolution: 1280x768, Channel: single, Dithering: Enable
+        4 : Resolution: 1280x1024, Channel: dual, Dithering: Enable
+        5 : Resolution: 1400x1050, Channel: dual, Dithering: Enable
+        6 : Resolution: 1600x1200, Channel: dual, Dithering: Enable
+        8 : Resolution: 800x480, Channel: single, Dithering: Enable
+        9 : Resolution: 1024x768, Channel: dual, Dithering: Enable
+        10: Resolution: 1024x768, Channel: single, Dithering: Disable
+        11: Resolution: 1024x768, Channel: dual, Dithering: Disable
+        12: Resolution: 1280x768, Channel: single, Dithering: Disable
+        13: Resolution: 1280x1024, Channel: dual, Dithering: Disable
+        14: Resolution: 1400x1050, Channel: dual, Dithering: Disable
+        15: Resolution: 1600x1200, Channel: dual, Dithering: Disable
+        16: Resolution: 1366x768, Channel: single, Dithering: Disable
+        17: Resolution: 1024x600, Channel: single, Dithering: Enable
+        18: Resolution: 1280x768, Channel: dual, Dithering: Enable
+        19: Resolution: 1280x800, Channel: single, Dithering: Enable
+    viafb_accel:
+        0 : No 2D Hardware Acceleration
+        1 : 2D Hardware Acceleration (default)
+    viafb_SAMM_ON:
+        0 : viafb_SAMM_ON disable (default)
+        1 : viafb_SAMM_ON enable
+    viafb_mode1: (secondary display device)
+        640x480 (default)
+        720x480
+        800x600
+        1024x768
+        ... ...
+    viafb_bpp1: (secondary display device)
+        8, 16, 32 (default:32)
+    viafb_refresh1: (secondary display device)
+        60, 75, 85, 100, 120 (default:60)
+    viafb_active_dev:
+        This option is used to specify active devices.(CRT, DVI, CRT+LCD...)
+        DVI stands for DVI or HDMI, E.g., If you want to enable HDMI,
+        set viafb_active_dev=DVI. In SAMM case, the previous of
+        viafb_active_dev is primary device, and the following is
+        secondary device.
+        For example:
+        To enable one device, such as DVI only, we can use:
+            modprobe viafb viafb_active_dev=DVI
+        To enable two devices, such as CRT+DVI:
+            modprobe viafb viafb_active_dev=CRT+DVI;
+        For DuoView case, we can use:
+            modprobe viafb viafb_active_dev=CRT+DVI
+            OR
+            modprobe viafb viafb_active_dev=DVI+CRT...
+        For SAMM case:
+        If CRT is primary and DVI is secondary, we should use:
+            modprobe viafb viafb_active_dev=CRT+DVI viafb_SAMM_ON=1...
+        If DVI is primary and CRT is secondary, we should use:
+            modprobe viafb viafb_active_dev=DVI+CRT viafb_SAMM_ON=1...
+    viafb_display_hardware_layout:
+        This option is used to specify display hardware layout for CX700 chip.
+        1 : LCD only
+        2 : DVI only
+        3 : LCD+DVI (default)
+        4 : LCD1+LCD2 (internal + internal)
+        16: LCD1+ExternalLCD2 (internal + external)
+    viafb_second_size:
+        This option is used to set second device memory size(MB) in SAMM case.
+        The minimal size is 16.
+    viafb_platform_epia_dvi:
+        This option is used to enable DVI on EPIA - M
+        0 : No DVI on EPIA - M (default)
+        1 : DVI on EPIA - M
+    viafb_bus_width:
+        When using 24 - Bit Bus Width Digital Interface,
+        this option should be set.
+        12: 12-Bit LVDS or 12-Bit TMDS (default)
+        24: 24-Bit LVDS or 24-Bit TMDS
+    viafb_device_lcd_dualedge:
+        When using Dual Edge Panel, this option should be set.
+        0 : No Dual Edge Panel (default)
+        1 : Dual Edge Panel
+    viafb_video_dev:
+        This option is used to specify video output devices(CRT, DVI, LCD) for
+        duoview case.
+        For example:
+        To output video on DVI, we should use:
+            modprobe viafb viafb_video_dev=DVI...
+    viafb_lcd_port:
+        This option is used to specify LCD output port,
+        available values are "DVP0" "DVP1" "DFP_HIGHLOW" "DFP_HIGH" "DFP_LOW".
+        for external LCD + external DVI on CX700(External LCD is on DVP0),
+        we should use:
+            modprobe viafb viafb_lcd_port=DVP0...
+Notes:
+    1. CRT may not display properly for DuoView CRT & DVI display at
+       the "640x480" PAL mode with DVI overscan enabled.
+    2. SAMM stands for single adapter multi monitors. It is different from
+       multi-head since SAMM support multi monitor at driver layers, thus fbcon
+       layer doesn't even know about it; SAMM's second screen doesn't have a
+       device node file, thus a user mode application can't access it directly.
+       When SAMM is enabled, viafb_mode and viafb_mode1, viafb_bpp and
+       viafb_bpp1, viafb_refresh and viafb_refresh1 can be different.
+    3. When console is depending on viafbinfo1, dynamically change resolution
+       and bpp, need to call VIAFB specified ioctl interface VIAFB_SET_DEVICE
+       instead of calling common ioctl function FBIOPUT_VSCREENINFO since
+       viafb doesn't support multi-head well, or it will cause screen crush.
+    4. VX800 2D accelerator hasn't been supported in this driver yet. When
+       using driver on VX800, the driver will disable the acceleration
+       function as default.
+[Configure viafb with "fbset" tool]
+-----------------------------------
+    "fbset" is an inbox utility of Linux.
+    1. Inquire current viafb information, type,
+           # fbset -i
+    2. Set various resolutions and viafb_refresh rates,
+           # fbset <resolution-vertical_sync>
+       example,
+           # fbset "1024x768-75"
+       or
+           # fbset -g 1024 768 1024 768 32
+       Check the file "/etc/fb.modes" to find display modes available.
+    3. Set the color depth,
+           # fbset -depth <value>
+       example,
+           # fbset -depth 16
+[Bootup with viafb]:
+--------------------
+    Add the following line to your grub.conf:
+    append = "video=viafb:viafb_mode=1024x768,viafb_bpp=32,viafb_refresh=85"
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 65a1482457a8..05d71b4b9430 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,6 +6,24 @@ be removed from this file.
 ---------------------------
+What:   old static regulatory information and ieee80211_regdom module parameter
+When:   2.6.29
+Why:    The old regulatory infrastructure has been replaced with a new one
+        which does not require statically defined regulatory domains. We do
+        not want to keep static regulatory domains in the kernel due to the
+        the dynamic nature of regulatory law and localization. We kept around
+        the old static definitions for the regulatory domains of:
+                * US
+                * JP
+                * EU
+        and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
+        set. We also kept around the ieee80211_regdom module parameter in case
+        some applications were relying on it. Changing regulatory domains
+        can now be done instead by using nl80211, as is done with iw.
+Who:    Luis R. Rodriguez <lrodriguez@atheros.com>
+---------------------------
 What:   dev->power.power_state
 When:   July 2007
 Why:    Broken design for runtime control over driver power states, confusing
@@ -19,15 +37,6 @@ Who:	Pavel Machek <pavel@suse.cz>
 ---------------------------
-What:   old NCR53C9x driver
-When:   October 2007
-Why:    Replaced by the much better esp_scsi driver.  Actual low-level
-        driver can be ported over almost trivially.
-Who:    David Miller <davem@davemloft.net>
-        Christoph Hellwig <hch@lst.de>
---------------------------
 What:   Video4Linux API 1 ioctls and video_decoder.h from Video devices.
 When:   December 2008
 Files:  include/linux/video_decoder.h include/linux/videodev.h
@@ -47,6 +56,30 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
+What:   old tuner-3036 i2c driver
+When:   2.6.28
+Why:    This driver is for VERY old i2c-over-parallel port teletext receiver
+        boxes. Rather then spending effort on converting this driver to V4L2,
+        and since it is extremely unlikely that anyone still uses one of these
+        devices, it was decided to drop it.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
+        Mauro Carvalho Chehab <mchehab@infradead.org>
+ ---------------------------
+What:   V4L2 dpc7146 driver
+When:   2.6.28
+Why:    Old driver for the dpc7146 demonstration board that is no longer
+        relevant. The last time this was tested on actual hardware was
+        probably around 2002. Since this is a driver for a demonstration
+        board the decision was made to remove it rather than spending a
+        lot of effort continually updating this driver to stay in sync
+        with the latest internal V4L2 or I2C API.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
+        Mauro Carvalho Chehab <mchehab@infradead.org>
+---------------------------
 What:   PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
 When:   November 2005
 Files:  drivers/pcmcia/: pcmcia_ioctl.c
@@ -138,24 +171,6 @@ Who:	Kay Sievers <kay.sievers@suse.de>
 ---------------------------
-What:   find_task_by_pid
-When:   2.6.26
-Why:    With pid namespaces, calling this funciton will return the
-        wrong task when called from inside a namespace.
-        The best way to save a task pid and find a task by this
-        pid later, is to find this task's struct pid pointer (or get
-        it directly from the task) and call pid_task() later.
-        If someone really needs to get a task by its pid_t, then
-        he most likely needs the find_task_by_vpid() to get the
-        task from the same namespace as the current task is in, but
-        this may be not so in general.
-Who:    Pavel Emelyanov <xemul@openvz.org>
---------------------------
 What:   ACPI procfs interface
 When:   July 2008
 Why:    ACPI sysfs conversion should be finished by January 2008.
@@ -199,19 +214,6 @@ Who:  Tejun Heo <htejun@gmail.com>
 ---------------------------
-What: The arch/ppc and include/asm-ppc directories
-When: Jun 2008
-Why:  The arch/powerpc tree is the merged architecture for ppc32 and ppc64
-      platforms.  Currently there are efforts underway to port the remaining
-      arch/ppc platforms to the merged tree.  New submissions to the arch/ppc
-      tree have been frozen with the 2.6.22 kernel release and that tree will
-      remain in bug-fix only mode until its scheduled removal.  Platforms
-      that are not ported by June 2008 will be removed due to the lack of an
-      interested maintainer.
-Who:  linuxppc-dev@ozlabs.org
---------------------------
 What:   i386/x86_64 bzImage symlinks
 When:   April 2010
@@ -248,6 +250,9 @@ What (Why):
        - xt_mark match revision 0
          (superseded by xt_mark match revision 1)
+        - xt_recent: the old ipt_recent proc dir
+          (superseded by /proc/net/xt_recent)
 When:   January 2009 or Linux 2.7.0, whichever comes first
 Why:    Superseded by newer revisions or modules
 Who:    Jan Engelhardt <jengelh@computergmbh.de>
@@ -282,11 +287,19 @@ Who:	Glauber Costa <gcosta@redhat.com>
 ---------------------------
-What:   old style serial driver for ColdFire (CONFIG_SERIAL_COLDFIRE)
+What:   remove HID compat support
-When:   2.6.28
+When:   2.6.29
-Why:    This driver still uses the old interface and has been replaced
+Why:    needed only as a temporary solution until distros fix themselves up
-        by CONFIG_SERIAL_MCF.
+Who:    Jiri Slaby <jirislaby@gmail.com>
-Who:    Sebastian Siewior <sebastian@breakpoint.cc>
+---------------------------
+What: print_fn_descriptor_symbol()
+When: October 2009
+Why:  The %pF vsprintf format provides the same functionality in a
+      simpler way.  print_fn_descriptor_symbol() is deprecated but
+      still present to give out-of-tree modules time to change.
+Who:  Bjorn Helgaas <bjorn.helgaas@hp.com>
 ---------------------------
@@ -300,11 +313,15 @@ Who:	ocfs2-devel@oss.oracle.com
 ---------------------------
-What:   asm/semaphore.h
+What:   SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD,
-When:   2.6.26
+        SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD
-Why:    Implementation became generic; users should now include
+When:   June 2009
-        linux/semaphore.h instead.
+Why:    A newer version of the options have been introduced in 2005 that
-Who:    Matthew Wilcox <willy@linux.intel.com>
+        removes the limitions of the old API.  The sctp library has been
+        converted to use these new options at the same time.  Any user
+        space app that directly uses the old options should convert to using
+        the new options.
+Who:    Vlad Yasevich <vladislav.yasevich@hp.com>
 ---------------------------
@@ -314,3 +331,39 @@ Why:	This option was introduced just to allow older lm-sensors userspace
        to keep working over the upgrade to 2.6.26. At the scheduled time of
        removal fixed lm-sensors (2.x or 3.x) should be readily available.
 Who:    Rene Herman <rene.herman@gmail.com>
+---------------------------
+What:   Code that is now under CONFIG_WIRELESS_EXT_SYSFS
+        (in net/core/net-sysfs.c)
+When:   After the only user (hal) has seen a release with the patches
+        for enough time, probably some time in 2010.
+Why:    Over 1K .text/.data size reduction, data is available in other
+        ways (ioctls)
+Who:    Johannes Berg <johannes@sipsolutions.net>
+---------------------------
+What: CONFIG_NF_CT_ACCT
+When: 2.6.29
+Why:  Accounting can now be enabled/disabled without kernel recompilation.
+      Currently used only to set a default value for a feature that is also
+      controlled by a kernel/module/sysfs/sysctl parameter.
+Who:  Krzysztof Piotr Oledzki <ole@ans.pl>
+---------------------------
+What: ide-scsi (BLK_DEV_IDESCSI)
+When: 2.6.29
+Why:  The 2.6 kernel supports direct writing to ide CD drives, which
+      eliminates the need for ide-scsi. The new method is more
+      efficient in every way.
+Who:  FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
+---------------------------
+What:   i2c_attach_client(), i2c_detach_client(), i2c_driver->detach_client()
+When:   2.6.29 (ideally) or 2.6.30 (more likely)
+Why:    Deprecated by the new (standard) device driver binding model. Use
+        i2c_driver->probe() and ->remove() instead.
+Who:    Jean Delvare <khali@linux-fr.org>
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 8b22d7d8b991..8362860e21a7 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -144,8 +144,8 @@ prototypes:
        void (*kill_sb) (struct super_block *);
 locking rules:
                may block       BKL
-get_sb          yes             yes
+get_sb          yes             no
-kill_sb         yes             yes
+kill_sb         yes             no
 ->get_sb() returns error or 0 with locked superblock attached to the vfsmount
 (exclusive on ->s_umount).
@@ -409,12 +409,12 @@ ioctl:			yes	(see below)
 unlocked_ioctl:         no      (see below)
 compat_ioctl:           no
 mmap:                   no
-open:                   maybe   (see below)
+open:                   no
 flush:                  no
 release:                no
 fsync:                  no      (see below)
 aio_fsync:              no
-fasync:                 yes     (see below)
+fasync:                 no
 lock:                   yes
 readv:                  no
 writev:                 no
@@ -431,13 +431,6 @@ For many filesystems, it is probably safe to acquire the inode
 semaphore.  Note some filesystems (i.e. remote ones) provide no
 protection for i_size so you will need to use the BKL.
->open() locking is in-transit: big lock partially moved into the methods.
-The only exception is ->open() in the instances of file_operations that never
-end up in ->i_fop/->proc_fops, i.e. ones that belong to character devices
-(chrdev_open() takes lock before replacing ->f_op and calling the secondary
-method. As soon as we fix the handling of module reference counters all
-instances of ->open() will be called without the BKL.
 Note: ext2_release() was *the* source of contention on fs-intensive
 loads and dropping BKL on ->release() helps to get rid of that (we still
 grab BKL for cases when we close a file that had been opened r/w, but that
@@ -510,6 +503,7 @@ prototypes:
        void (*close)(struct vm_area_struct*);
        int (*fault)(struct vm_area_struct*, struct vm_fault *);
        int (*page_mkwrite)(struct vm_area_struct *, struct page *);
+        int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 locking rules:
                BKL     mmap_sem        PageLocked(page)
@@ -517,6 +511,7 @@ open:		no	yes
 close:          no      yes
 fault:          no      yes
 page_mkwrite:   no      yes             no
+access:         no      yes
        ->page_mkwrite() is called when a previously read-only page is
 about to become writeable. The file system is responsible for
@@ -525,6 +520,11 @@ taking to lock out truncate, the page range should be verified to be
 within i_size. The page mapping should also be checked that it is not
 NULL.
+        ->access() is called when get_user_pages() fails in
+acces_process_vm(), typically used to debug a process through
+/proc/pid/mem or ptrace.  This function is needed only for
+VM_IO | VM_PFNMAP VMAs.
 ================================================================================
                        Dubious stuff
diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt
new file mode 100644
index 000000000000..c6341745df37
--- /dev/null
+++ b/Documentation/filesystems/autofs4-mount-control.txt
@@ -0,0 +1,393 @@
+Miscellaneous Device control operations for the autofs4 kernel module
+====================================================================
+The problem
+===========
+There is a problem with active restarts in autofs (that is to say
+restarting autofs when there are busy mounts).
+During normal operation autofs uses a file descriptor opened on the
+directory that is being managed in order to be able to issue control
+operations. Using a file descriptor gives ioctl operations access to
+autofs specific information stored in the super block. The operations
+are things such as setting an autofs mount catatonic, setting the
+expire timeout and requesting expire checks. As is explained below,
+certain types of autofs triggered mounts can end up covering an autofs
+mount itself which prevents us being able to use open(2) to obtain a
+file descriptor for these operations if we don't already have one open.
+Currently autofs uses "umount -l" (lazy umount) to clear active mounts
+at restart. While using lazy umount works for most cases, anything that
+needs to walk back up the mount tree to construct a path, such as
+getcwd(2) and the proc file system /proc/<pid>/cwd, no longer works
+because the point from which the path is constructed has been detached
+from the mount tree.
+The actual problem with autofs is that it can't reconnect to existing
+mounts. Immediately one thinks of just adding the ability to remount
+autofs file systems would solve it, but alas, that can't work. This is
+because autofs direct mounts and the implementation of "on demand mount
+and expire" of nested mount trees have the file system mounted directly
+on top of the mount trigger directory dentry.
+For example, there are two types of automount maps, direct (in the kernel
+module source you will see a third type called an offset, which is just
+a direct mount in disguise) and indirect.
+Here is a master map with direct and indirect map entries:
+/-      /etc/auto.direct
+/test   /etc/auto.indirect
+and the corresponding map files:
+/etc/auto.direct:
+/automount/dparse/g6  budgie:/autofs/export1
+/automount/dparse/g1  shark:/autofs/export1
+and so on.
+/etc/auto.indirect:
+g1    shark:/autofs/export1
+g6    budgie:/autofs/export1
+and so on.
+For the above indirect map an autofs file system is mounted on /test and
+mounts are triggered for each sub-directory key by the inode lookup
+operation. So we see a mount of shark:/autofs/export1 on /test/g1, for
+example.
+The way that direct mounts are handled is by making an autofs mount on
+each full path, such as /automount/dparse/g1, and using it as a mount
+trigger. So when we walk on the path we mount shark:/autofs/export1 "on
+top of this mount point". Since these are always directories we can
+use the follow_link inode operation to trigger the mount.
+But, each entry in direct and indirect maps can have offsets (making
+them multi-mount map entries).
+For example, an indirect mount map entry could also be:
+g1  \
+   /        shark:/autofs/export5/testing/test \
+   /s1      shark:/autofs/export/testing/test/s1 \
+   /s2      shark:/autofs/export5/testing/test/s2 \
+   /s1/ss1  shark:/autofs/export1 \
+   /s2/ss2  shark:/autofs/export2
+and a similarly a direct mount map entry could also be:
+/automount/dparse/g1 \
+    /       shark:/autofs/export5/testing/test \
+    /s1     shark:/autofs/export/testing/test/s1 \
+    /s2     shark:/autofs/export5/testing/test/s2 \
+    /s1/ss1 shark:/autofs/export2 \
+    /s2/ss2 shark:/autofs/export2
+One of the issues with version 4 of autofs was that, when mounting an
+entry with a large number of offsets, possibly with nesting, we needed
+to mount and umount all of the offsets as a single unit. Not really a
+problem, except for people with a large number of offsets in map entries.
+This mechanism is used for the well known "hosts" map and we have seen
+cases (in 2.4) where the available number of mounts are exhausted or
+where the number of privileged ports available is exhausted.
+In version 5 we mount only as we go down the tree of offsets and
+similarly for expiring them which resolves the above problem. There is
+somewhat more detail to the implementation but it isn't needed for the
+sake of the problem explanation. The one important detail is that these
+offsets are implemented using the same mechanism as the direct mounts
+above and so the mount points can be covered by a mount.
+The current autofs implementation uses an ioctl file descriptor opened
+on the mount point for control operations. The references held by the
+descriptor are accounted for in checks made to determine if a mount is
+in use and is also used to access autofs file system information held
+in the mount super block. So the use of a file handle needs to be
+retained.
+The Solution
+============
+To be able to restart autofs leaving existing direct, indirect and
+offset mounts in place we need to be able to obtain a file handle
+for these potentially covered autofs mount points. Rather than just
+implement an isolated operation it was decided to re-implement the
+existing ioctl interface and add new operations to provide this
+functionality.
+In addition, to be able to reconstruct a mount tree that has busy mounts,
+the uid and gid of the last user that triggered the mount needs to be
+available because these can be used as macro substitution variables in
+autofs maps. They are recorded at mount request time and an operation
+has been added to retrieve them.
+Since we're re-implementing the control interface, a couple of other
+problems with the existing interface have been addressed. First, when
+a mount or expire operation completes a status is returned to the
+kernel by either a "send ready" or a "send fail" operation. The
+"send fail" operation of the ioctl interface could only ever send
+ENOENT so the re-implementation allows user space to send an actual
+status. Another expensive operation in user space, for those using
+very large maps, is discovering if a mount is present. Usually this
+involves scanning /proc/mounts and since it needs to be done quite
+often it can introduce significant overhead when there are many entries
+in the mount table. An operation to lookup the mount status of a mount
+point dentry (covered or not) has also been added.
+Current kernel development policy recommends avoiding the use of the
+ioctl mechanism in favor of systems such as Netlink. An implementation
+using this system was attempted to evaluate its suitability and it was
+found to be inadequate, in this case. The Generic Netlink system was
+used for this as raw Netlink would lead to a significant increase in
+complexity. There's no question that the Generic Netlink system is an
+elegant solution for common case ioctl functions but it's not a complete
+replacement probably because it's primary purpose in life is to be a
+message bus implementation rather than specifically an ioctl replacement.
+While it would be possible to work around this there is one concern
+that lead to the decision to not use it. This is that the autofs
+expire in the daemon has become far to complex because umount
+candidates are enumerated, almost for no other reason than to "count"
+the number of times to call the expire ioctl. This involves scanning
+the mount table which has proved to be a big overhead for users with
+large maps. The best way to improve this is try and get back to the
+way the expire was done long ago. That is, when an expire request is
+issued for a mount (file handle) we should continually call back to
+the daemon until we can't umount any more mounts, then return the
+appropriate status to the daemon. At the moment we just expire one
+mount at a time. A Generic Netlink implementation would exclude this
+possibility for future development due to the requirements of the
+message bus architecture.
+autofs4 Miscellaneous Device mount control interface
+====================================================
+The control interface is opening a device node, typically /dev/autofs.
+All the ioctls use a common structure to pass the needed parameter
+information and return operation results:
+struct autofs_dev_ioctl {
+        __u32 ver_major;
+        __u32 ver_minor;
+        __u32 size;             /* total size of data passed in
+                                 * including this struct */
+        __s32 ioctlfd;          /* automount command fd */
+        __u32 arg1;             /* Command parameters */
+        __u32 arg2;
+        char path[0];
+};
+The ioctlfd field is a mount point file descriptor of an autofs mount
+point. It is returned by the open call and is used by all calls except
+the check for whether a given path is a mount point, where it may
+optionally be used to check a specific mount corresponding to a given
+mount point file descriptor, and when requesting the uid and gid of the
+last successful mount on a directory within the autofs file system.
+The fields arg1 and arg2 are used to communicate parameters and results of
+calls made as described below.
+The path field is used to pass a path where it is needed and the size field
+is used account for the increased structure length when translating the
+structure sent from user space.
+This structure can be initialized before setting specific fields by using
+the void function call init_autofs_dev_ioctl(struct autofs_dev_ioctl *).
+All of the ioctls perform a copy of this structure from user space to
+kernel space and return -EINVAL if the size parameter is smaller than
+the structure size itself, -ENOMEM if the kernel memory allocation fails
+or -EFAULT if the copy itself fails. Other checks include a version check
+of the compiled in user space version against the module version and a
+mismatch results in a -EINVAL return. If the size field is greater than
+the structure size then a path is assumed to be present and is checked to
+ensure it begins with a "/" and is NULL terminated, otherwise -EINVAL is
+returned. Following these checks, for all ioctl commands except
+AUTOFS_DEV_IOCTL_VERSION_CMD, AUTOFS_DEV_IOCTL_OPENMOUNT_CMD and
+AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD the ioctlfd is validated and if it is
+not a valid descriptor or doesn't correspond to an autofs mount point
+an error of -EBADF, -ENOTTY or -EINVAL (not an autofs descriptor) is
+returned.
+The ioctls
+==========
+An example of an implementation which uses this interface can be seen
+in autofs version 5.0.4 and later in file lib/dev-ioctl-lib.c of the
+distribution tar available for download from kernel.org in directory
+/pub/linux/daemons/autofs/v5.
+The device node ioctl operations implemented by this interface are:
+AUTOFS_DEV_IOCTL_VERSION
+------------------------
+Get the major and minor version of the autofs4 device ioctl kernel module
+implementation. It requires an initialized struct autofs_dev_ioctl as an
+input parameter and sets the version information in the passed in structure.
+It returns 0 on success or the error -EINVAL if a version mismatch is
+detected.
+AUTOFS_DEV_IOCTL_PROTOVER_CMD and AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD
+------------------------------------------------------------------
+Get the major and minor version of the autofs4 protocol version understood
+by loaded module. This call requires an initialized struct autofs_dev_ioctl
+with the ioctlfd field set to a valid autofs mount point descriptor
+and sets the requested version number in structure field arg1. These
+commands return 0 on success or one of the negative error codes if
+validation fails.
+AUTOFS_DEV_IOCTL_OPENMOUNT and AUTOFS_DEV_IOCTL_CLOSEMOUNT
+----------------------------------------------------------
+Obtain and release a file descriptor for an autofs managed mount point
+path. The open call requires an initialized struct autofs_dev_ioctl with
+the the path field set and the size field adjusted appropriately as well
+as the arg1 field set to the device number of the autofs mount. The
+device number can be obtained from the mount options shown in
+/proc/mounts. The close call requires an initialized struct
+autofs_dev_ioct with the ioctlfd field set to the descriptor obtained
+from the open call. The release of the file descriptor can also be done
+with close(2) so any open descriptors will also be closed at process exit.
+The close call is included in the implemented operations largely for
+completeness and to provide for a consistent user space implementation.
+AUTOFS_DEV_IOCTL_READY_CMD and AUTOFS_DEV_IOCTL_FAIL_CMD
+--------------------------------------------------------
+Return mount and expire result status from user space to the kernel.
+Both of these calls require an initialized struct autofs_dev_ioctl
+with the ioctlfd field set to the descriptor obtained from the open
+call and the arg1 field set to the wait queue token number, received
+by user space in the foregoing mount or expire request. The arg2 field
+is set to the status to be returned. For the ready call this is always
+0 and for the fail call it is set to the errno of the operation.
+AUTOFS_DEV_IOCTL_SETPIPEFD_CMD
+------------------------------
+Set the pipe file descriptor used for kernel communication to the daemon.
+Normally this is set at mount time using an option but when reconnecting
+to a existing mount we need to use this to tell the autofs mount about
+the new kernel pipe descriptor. In order to protect mounts against
+incorrectly setting the pipe descriptor we also require that the autofs
+mount be catatonic (see next call).
+The call requires an initialized struct autofs_dev_ioctl with the
+ioctlfd field set to the descriptor obtained from the open call and
+the arg1 field set to descriptor of the pipe. On success the call
+also sets the process group id used to identify the controlling process
+(eg. the owning automount(8) daemon) to the process group of the caller.
+AUTOFS_DEV_IOCTL_CATATONIC_CMD
+------------------------------
+Make the autofs mount point catatonic. The autofs mount will no longer
+issue mount requests, the kernel communication pipe descriptor is released
+and any remaining waits in the queue released.
+The call requires an initialized struct autofs_dev_ioctl with the
+ioctlfd field set to the descriptor obtained from the open call.
+AUTOFS_DEV_IOCTL_TIMEOUT_CMD
+----------------------------
+Set the expire timeout for mounts withing an autofs mount point.
+The call requires an initialized struct autofs_dev_ioctl with the
+ioctlfd field set to the descriptor obtained from the open call.
+AUTOFS_DEV_IOCTL_REQUESTER_CMD
+------------------------------
+Return the uid and gid of the last process to successfully trigger a the
+mount on the given path dentry.
+The call requires an initialized struct autofs_dev_ioctl with the path
+field set to the mount point in question and the size field adjusted
+appropriately as well as the arg1 field set to the device number of the
+containing autofs mount. Upon return the struct field arg1 contains the
+uid and arg2 the gid.
+When reconstructing an autofs mount tree with active mounts we need to
+re-connect to mounts that may have used the original process uid and
+gid (or string variations of them) for mount lookups within the map entry.
+This call provides the ability to obtain this uid and gid so they may be
+used by user space for the mount map lookups.
+AUTOFS_DEV_IOCTL_EXPIRE_CMD
+---------------------------
+Issue an expire request to the kernel for an autofs mount. Typically
+this ioctl is called until no further expire candidates are found.
+The call requires an initialized struct autofs_dev_ioctl with the
+ioctlfd field set to the descriptor obtained from the open call. In
+addition an immediate expire, independent of the mount timeout, can be
+requested by setting the arg1 field to 1. If no expire candidates can
+be found the ioctl returns -1 with errno set to EAGAIN.
+This call causes the kernel module to check the mount corresponding
+to the given ioctlfd for mounts that can be expired, issues an expire
+request back to the daemon and waits for completion.
+AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD
+------------------------------
+Checks if an autofs mount point is in use.
+The call requires an initialized struct autofs_dev_ioctl with the
+ioctlfd field set to the descriptor obtained from the open call and
+it returns the result in the arg1 field, 1 for busy and 0 otherwise.
+AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD
+---------------------------------
+Check if the given path is a mountpoint.
+The call requires an initialized struct autofs_dev_ioctl. There are two
+possible variations. Both use the path field set to the path of the mount
+point to check and the size field adjusted appropriately. One uses the
+ioctlfd field to identify a specific mount point to check while the other
+variation uses the path and optionaly arg1 set to an autofs mount type.
+The call returns 1 if this is a mount point and sets arg1 to the device
+number of the mount and field arg2 to the relevant super block magic
+number (described below) or 0 if it isn't a mountpoint. In both cases
+the the device number (as returned by new_encode_dev()) is returned
+in field arg1.
+If supplied with a file descriptor we're looking for a specific mount,
+not necessarily at the top of the mounted stack. In this case the path
+the descriptor corresponds to is considered a mountpoint if it is itself
+a mountpoint or contains a mount, such as a multi-mount without a root
+mount. In this case we return 1 if the descriptor corresponds to a mount
+point and and also returns the super magic of the covering mount if there
+is one or 0 if it isn't a mountpoint.
+If a path is supplied (and the ioctlfd field is set to -1) then the path
+is looked up and is checked to see if it is the root of a mount. If a
+type is also given we are looking for a particular autofs mount and if
+a match isn't found a fail is returned. If the the located path is the
+root of a mount 1 is returned along with the super magic of the mount
+or 0 otherwise.
diff --git a/Documentation/filesystems/bfs.txt b/Documentation/filesystems/bfs.txt
index ea825e178e79..78043d5a8fc3 100644
--- a/Documentation/filesystems/bfs.txt
+++ b/Documentation/filesystems/bfs.txt
@@ -26,11 +26,11 @@ You can simplify mounting by just typing:
 this will allocate the first available loopback device (and load loop.o 
 kernel module if necessary) automatically. If the loopback driver is not
-loaded automatically, make sure that your kernel is compiled with kmod 
+loaded automatically, make sure that you have compiled the module and
-support (CONFIG_KMOD) enabled. Beware that umount will not
+that modprobe is functioning. Beware that umount will not deallocate
-deallocate /dev/loopN device if /etc/mtab file on your system is a
+/dev/loopN device if /etc/mtab file on your system is a symbolic link to
-symbolic link to /proc/mounts. You will need to do it manually using
+/proc/mounts. You will need to do it manually using "-d" switch of
-"-d" switch of losetup(8). Read losetup(8) manpage for more info.
+losetup(8). Read losetup(8) manpage for more info.
 To create the BFS image under UnixWare you need to find out first which
 slice contains it. The command prtvtoc(1M) is your friend:
diff --git a/Documentation/filesystems/configfs/Makefile b/Documentation/filesystems/configfs/Makefile
new file mode 100644
index 000000000000..be7ec5e67dbc
--- /dev/null
+++ b/Documentation/filesystems/configfs/Makefile
@@ -0,0 +1,3 @@
+ifneq ($(CONFIG_CONFIGFS_FS),)
+obj-m += configfs_example_explicit.o configfs_example_macros.o
+endif
diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt
index 15838d706ea2..fabcb0e00f25 100644
--- a/Documentation/filesystems/configfs/configfs.txt
+++ b/Documentation/filesystems/configfs/configfs.txt
@@ -233,12 +233,10 @@ accomplished via the group operations specified on the group's
 config_item_type.
        struct configfs_group_operations {
-                int (*make_item)(struct config_group *group,
+                struct config_item *(*make_item)(struct config_group *group,
-                                 const char *name,
+                                                 const char *name);
-                                 struct config_item **new_item);
+                struct config_group *(*make_group)(struct config_group *group,
-                int (*make_group)(struct config_group *group,
+                                                   const char *name);
-                                  const char *name,
-                                  struct config_group **new_group);
                int (*commit_item)(struct config_item *item);
                void (*disconnect_notify)(struct config_group *group,
                                          struct config_item *item);
@@ -313,9 +311,20 @@ the subsystem must be ready for it.
 [An Example]
 The best example of these basic concepts is the simple_children
-subsystem/group and the simple_child item in configfs_example.c  It
+subsystem/group and the simple_child item in configfs_example_explicit.c
-shows a trivial object displaying and storing an attribute, and a simple
+and configfs_example_macros.c.  It shows a trivial object displaying and
-group creating and destroying these children.
+storing an attribute, and a simple group creating and destroying these
+children.
+The only difference between configfs_example_explicit.c and
+configfs_example_macros.c is how the attributes of the childless item
+are defined.  The childless item has extended attributes, each with
+their own show()/store() operation.  This follows a convention commonly
+used in sysfs.  configfs_example_explicit.c creates these attributes
+by explicitly defining the structures involved.  Conversely
+configfs_example_macros.c uses some convenience macros from configfs.h
+to define the attributes.  These macros are similar to their sysfs
+counterparts.
 [Hierarchy Navigation and the Subsystem Mutex]
diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example_explicit.c
index 0b422acd470c..d428cc9f07f3 100644
--- a/Documentation/filesystems/configfs/configfs_example.c
+++ b/Documentation/filesystems/configfs/configfs_example_explicit.c
@@ -1,8 +1,10 @@
 /*
 * vim: noexpandtab ts=8 sts=0 sw=8:
 *
- * configfs_example.c - This file is a demonstration module containing
+ * configfs_example_explicit.c - This file is a demonstration module
- *      a number of configfs subsystems.
+ *      containing a number of configfs subsystems.  It explicitly defines
+ *      each structure without using the helper macros defined in
+ *      configfs.h.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
@@ -273,22 +275,20 @@ static inline struct simple_children *to_simple_children(struct config_item *ite
        return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
 }
-static int simple_children_make_item(struct config_group *group, const char *name, struct config_item **new_item)
+static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
 {
        struct simple_child *simple_child;
        simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
        if (!simple_child)
-                return -ENOMEM;
+                return ERR_PTR(-ENOMEM);
        config_item_init_type_name(&simple_child->item, name,
                                   &simple_child_type);
        simple_child->storeme = 0;
-        *new_item = &simple_child->item;
+        return &simple_child->item;
-        return 0;
 }
 static struct configfs_attribute simple_children_attr_description = {
@@ -303,8 +303,8 @@ static struct configfs_attribute *simple_children_attrs[] = {
 };
 static ssize_t simple_children_attr_show(struct config_item *item,
-                                         struct configfs_attribute *attr,
+                                         struct configfs_attribute *attr,
-                                         char *page)
+                                         char *page)
 {
        return sprintf(page,
 "[02-simple-children]\n"
@@ -319,7 +319,7 @@ static void simple_children_release(struct config_item *item)
 }
 static struct configfs_item_operations simple_children_item_ops = {
-        .release        = simple_children_release,
+        .release        = simple_children_release,
        .show_attribute = simple_children_attr_show,
 };
@@ -360,21 +360,19 @@ static struct configfs_subsystem simple_children_subsys = {
 * children of its own.
 */
-static int group_children_make_group(struct config_group *group, const char *name, struct config_group **new_group)
+static struct config_group *group_children_make_group(struct config_group *group, const char *name)
 {
        struct simple_children *simple_children;
        simple_children = kzalloc(sizeof(struct simple_children),
                                  GFP_KERNEL);
        if (!simple_children)
-                return -ENOMEM;
+                return ERR_PTR(-ENOMEM);
        config_group_init_type_name(&simple_children->group, name,
                                    &simple_children_type);
-        *new_group = &simple_children->group;
+        return &simple_children->group;
-        return 0;
 }
 static struct configfs_attribute group_children_attr_description = {
@@ -389,8 +387,8 @@ static struct configfs_attribute *group_children_attrs[] = {
 };
 static ssize_t group_children_attr_show(struct config_item *item,
-                                        struct configfs_attribute *attr,
+                                        struct configfs_attribute *attr,
-                                        char *page)
+                                        char *page)
 {
        return sprintf(page,
 "[03-group-children]\n"
diff --git a/Documentation/filesystems/configfs/configfs_example_macros.c b/Documentation/filesystems/configfs/configfs_example_macros.c
new file mode 100644
index 000000000000..d8e30a0378aa
--- /dev/null
+++ b/Documentation/filesystems/configfs/configfs_example_macros.c
@@ -0,0 +1,448 @@
+/*
+ * vim: noexpandtab ts=8 sts=0 sw=8:
+ *
+ * configfs_example_macros.c - This file is a demonstration module
+ *      containing a number of configfs subsystems.  It uses the helper
+ *      macros defined by configfs.h
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/configfs.h>
+/*
+ * 01-childless
+ *
+ * This first example is a childless subsystem.  It cannot create
+ * any config_items.  It just has attributes.
+ *
+ * Note that we are enclosing the configfs_subsystem inside a container.
+ * This is not necessary if a subsystem has no attributes directly
+ * on the subsystem.  See the next example, 02-simple-children, for
+ * such a subsystem.
+ */
+struct childless {
+        struct configfs_subsystem subsys;
+        int showme;
+        int storeme;
+};
+static inline struct childless *to_childless(struct config_item *item)
+{
+        return item ? container_of(to_configfs_subsystem(to_config_group(item)), struct childless, subsys) : NULL;
+}
+CONFIGFS_ATTR_STRUCT(childless);
+#define CHILDLESS_ATTR(_name, _mode, _show, _store)     \
+struct childless_attribute childless_attr_##_name = __CONFIGFS_ATTR(_name, _mode, _show, _store)
+#define CHILDLESS_ATTR_RO(_name, _show) \
+struct childless_attribute childless_attr_##_name = __CONFIGFS_ATTR_RO(_name, _show);
+static ssize_t childless_showme_read(struct childless *childless,
+                                     char *page)
+{
+        ssize_t pos;
+        pos = sprintf(page, "%d\n", childless->showme);
+        childless->showme++;
+        return pos;
+}
+static ssize_t childless_storeme_read(struct childless *childless,
+                                      char *page)
+{
+        return sprintf(page, "%d\n", childless->storeme);
+}
+static ssize_t childless_storeme_write(struct childless *childless,
+                                       const char *page,
+                                       size_t count)
+{
+        unsigned long tmp;
+        char *p = (char *) page;
+        tmp = simple_strtoul(p, &p, 10);
+        if (!p || (*p && (*p != '\n')))
+                return -EINVAL;
+        if (tmp > INT_MAX)
+                return -ERANGE;
+        childless->storeme = tmp;
+        return count;
+}
+static ssize_t childless_description_read(struct childless *childless,
+                                          char *page)
+{
+        return sprintf(page,
+"[01-childless]\n"
+"\n"
+"The childless subsystem is the simplest possible subsystem in\n"
+"configfs.  It does not support the creation of child config_items.\n"
+"It only has a few attributes.  In fact, it isn't much different\n"
+"than a directory in /proc.\n");
+}
+CHILDLESS_ATTR_RO(showme, childless_showme_read);
+CHILDLESS_ATTR(storeme, S_IRUGO | S_IWUSR, childless_storeme_read,
+               childless_storeme_write);
+CHILDLESS_ATTR_RO(description, childless_description_read);
+static struct configfs_attribute *childless_attrs[] = {
+        &childless_attr_showme.attr,
+        &childless_attr_storeme.attr,
+        &childless_attr_description.attr,
+        NULL,
+};
+CONFIGFS_ATTR_OPS(childless);
+static struct configfs_item_operations childless_item_ops = {
+        .show_attribute         = childless_attr_show,
+        .store_attribute        = childless_attr_store,
+};
+static struct config_item_type childless_type = {
+        .ct_item_ops    = &childless_item_ops,
+        .ct_attrs       = childless_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+static struct childless childless_subsys = {
+        .subsys = {
+                .su_group = {
+                        .cg_item = {
+                                .ci_namebuf = "01-childless",
+                                .ci_type = &childless_type,
+                        },
+                },
+        },
+};
+/* ----------------------------------------------------------------- */
+/*
+ * 02-simple-children
+ *
+ * This example merely has a simple one-attribute child.  Note that
+ * there is no extra attribute structure, as the child's attribute is
+ * known from the get-go.  Also, there is no container for the
+ * subsystem, as it has no attributes of its own.
+ */
+struct simple_child {
+        struct config_item item;
+        int storeme;
+};
+static inline struct simple_child *to_simple_child(struct config_item *item)
+{
+        return item ? container_of(item, struct simple_child, item) : NULL;
+}
+static struct configfs_attribute simple_child_attr_storeme = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "storeme",
+        .ca_mode = S_IRUGO | S_IWUSR,
+};
+static struct configfs_attribute *simple_child_attrs[] = {
+        &simple_child_attr_storeme,
+        NULL,
+};
+static ssize_t simple_child_attr_show(struct config_item *item,
+                                      struct configfs_attribute *attr,
+                                      char *page)
+{
+        ssize_t count;
+        struct simple_child *simple_child = to_simple_child(item);
+        count = sprintf(page, "%d\n", simple_child->storeme);
+        return count;
+}
+static ssize_t simple_child_attr_store(struct config_item *item,
+                                       struct configfs_attribute *attr,
+                                       const char *page, size_t count)
+{
+        struct simple_child *simple_child = to_simple_child(item);
+        unsigned long tmp;
+        char *p = (char *) page;
+        tmp = simple_strtoul(p, &p, 10);
+        if (!p || (*p && (*p != '\n')))
+                return -EINVAL;
+        if (tmp > INT_MAX)
+                return -ERANGE;
+        simple_child->storeme = tmp;
+        return count;
+}
+static void simple_child_release(struct config_item *item)
+{
+        kfree(to_simple_child(item));
+}
+static struct configfs_item_operations simple_child_item_ops = {
+        .release                = simple_child_release,
+        .show_attribute         = simple_child_attr_show,
+        .store_attribute        = simple_child_attr_store,
+};
+static struct config_item_type simple_child_type = {
+        .ct_item_ops    = &simple_child_item_ops,
+        .ct_attrs       = simple_child_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+struct simple_children {
+        struct config_group group;
+};
+static inline struct simple_children *to_simple_children(struct config_item *item)
+{
+        return item ? container_of(to_config_group(item), struct simple_children, group) : NULL;
+}
+static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
+{
+        struct simple_child *simple_child;
+        simple_child = kzalloc(sizeof(struct simple_child), GFP_KERNEL);
+        if (!simple_child)
+                return ERR_PTR(-ENOMEM);
+        config_item_init_type_name(&simple_child->item, name,
+                                   &simple_child_type);
+        simple_child->storeme = 0;
+        return &simple_child->item;
+}
+static struct configfs_attribute simple_children_attr_description = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "description",
+        .ca_mode = S_IRUGO,
+};
+static struct configfs_attribute *simple_children_attrs[] = {
+        &simple_children_attr_description,
+        NULL,
+};
+static ssize_t simple_children_attr_show(struct config_item *item,
+                                         struct configfs_attribute *attr,
+                                         char *page)
+{
+        return sprintf(page,
+"[02-simple-children]\n"
+"\n"
+"This subsystem allows the creation of child config_items.  These\n"
+"items have only one attribute that is readable and writeable.\n");
+}
+static void simple_children_release(struct config_item *item)
+{
+        kfree(to_simple_children(item));
+}
+static struct configfs_item_operations simple_children_item_ops = {
+        .release        = simple_children_release,
+        .show_attribute = simple_children_attr_show,
+};
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations simple_children_group_ops = {
+        .make_item      = simple_children_make_item,
+};
+static struct config_item_type simple_children_type = {
+        .ct_item_ops    = &simple_children_item_ops,
+        .ct_group_ops   = &simple_children_group_ops,
+        .ct_attrs       = simple_children_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+static struct configfs_subsystem simple_children_subsys = {
+        .su_group = {
+                .cg_item = {
+                        .ci_namebuf = "02-simple-children",
+                        .ci_type = &simple_children_type,
+                },
+        },
+};
+/* ----------------------------------------------------------------- */
+/*
+ * 03-group-children
+ *
+ * This example reuses the simple_children group from above.  However,
+ * the simple_children group is not the subsystem itself, it is a
+ * child of the subsystem.  Creation of a group in the subsystem creates
+ * a new simple_children group.  That group can then have simple_child
+ * children of its own.
+ */
+static struct config_group *group_children_make_group(struct config_group *group, const char *name)
+{
+        struct simple_children *simple_children;
+        simple_children = kzalloc(sizeof(struct simple_children),
+                                  GFP_KERNEL);
+        if (!simple_children)
+                return ERR_PTR(-ENOMEM);
+        config_group_init_type_name(&simple_children->group, name,
+                                    &simple_children_type);
+        return &simple_children->group;
+}
+static struct configfs_attribute group_children_attr_description = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "description",
+        .ca_mode = S_IRUGO,
+};
+static struct configfs_attribute *group_children_attrs[] = {
+        &group_children_attr_description,
+        NULL,
+};
+static ssize_t group_children_attr_show(struct config_item *item,
+                                        struct configfs_attribute *attr,
+                                        char *page)
+{
+        return sprintf(page,
+"[03-group-children]\n"
+"\n"
+"This subsystem allows the creation of child config_groups.  These\n"
+"groups are like the subsystem simple-children.\n");
+}
+static struct configfs_item_operations group_children_item_ops = {
+        .show_attribute = group_children_attr_show,
+};
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations group_children_group_ops = {
+        .make_group     = group_children_make_group,
+};
+static struct config_item_type group_children_type = {
+        .ct_item_ops    = &group_children_item_ops,
+        .ct_group_ops   = &group_children_group_ops,
+        .ct_attrs       = group_children_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+static struct configfs_subsystem group_children_subsys = {
+        .su_group = {
+                .cg_item = {
+                        .ci_namebuf = "03-group-children",
+                        .ci_type = &group_children_type,
+                },
+        },
+};
+/* ----------------------------------------------------------------- */
+/*
+ * We're now done with our subsystem definitions.
+ * For convenience in this module, here's a list of them all.  It
+ * allows the init function to easily register them.  Most modules
+ * will only have one subsystem, and will only call register_subsystem
+ * on it directly.
+ */
+static struct configfs_subsystem *example_subsys[] = {
+        &childless_subsys.subsys,
+        &simple_children_subsys,
+        &group_children_subsys,
+        NULL,
+};
+static int __init configfs_example_init(void)
+{
+        int ret;
+        int i;
+        struct configfs_subsystem *subsys;
+        for (i = 0; example_subsys[i]; i++) {
+                subsys = example_subsys[i];
+                config_group_init(&subsys->su_group);
+                mutex_init(&subsys->su_mutex);
+                ret = configfs_register_subsystem(subsys);
+                if (ret) {
+                        printk(KERN_ERR "Error %d while registering subsystem %s\n",
+                               ret,
+                               subsys->su_group.cg_item.ci_namebuf);
+                        goto out_unregister;
+                }
+        }
+        return 0;
+out_unregister:
+        for (; i >= 0; i--) {
+                configfs_unregister_subsystem(example_subsys[i]);
+        }
+        return ret;
+}
+static void __exit configfs_example_exit(void)
+{
+        int i;
+        for (i = 0; example_subsys[i]; i++) {
+                configfs_unregister_subsystem(example_subsys[i]);
+        }
+}
+module_init(configfs_example_init);
+module_exit(configfs_example_exit);
+MODULE_LICENSE("GPL");
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index b45f3c1b8b43..9dd2a3bb2acc 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -96,6 +96,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue         Keep going on a filesystem error.
 errors=panic            Panic and halt the machine if an error occurs.
+data_err=ignore(*)      Just print an error message if an error occurs
+                        in a file data buffer in ordered mode.
+data_err=abort          Abort the journal if an error occurs in a file
+                        data buffer in ordered mode.
 grpid                   Give objects the same group ID as their creator.
 bsdgroups
@@ -193,6 +198,5 @@ kernel source:	<file:fs/ext3/>
 programs:       http://e2fsprogs.sourceforge.net/
                http://ext2resize.sourceforge.net
-useful links:   http://www.zip.com.au/~akpm/linux/ext3/ext3-usage.html
+useful links:   http://www-106.ibm.com/developerworks/linux/library/l-fs7/
-                http://www-106.ibm.com/developerworks/linux/library/l-fs7/
                http://www-106.ibm.com/developerworks/linux/library/l-fs8/
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 80e193d82e2e..174eaff7ded9 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -2,19 +2,24 @@
 Ext4 Filesystem
 ===============
-This is a development version of the ext4 filesystem, an advanced level
+Ext4 is an an advanced level of the ext3 filesystem which incorporates
-of the ext3 filesystem which incorporates scalability and reliability
+scalability and reliability enhancements for supporting large filesystems
-enhancements for supporting large filesystems (64 bit) in keeping with
+(64 bit) in keeping with increasing disk capacities and state-of-the-art
-increasing disk capacities and state-of-the-art feature requirements.
+feature requirements.
-Mailing list: linux-ext4@vger.kernel.org
+Mailing list:   linux-ext4@vger.kernel.org
+Web site:       http://ext4.wiki.kernel.org
 1. Quick usage instructions:
 ===========================
+Note: More extensive information for getting started with ext4 can be
+      found at the ext4 wiki site at the URL:
+      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
  - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41) from:
+    writing version 1.41.3) from:
    http://sourceforge.net/project/showfiles.php?group_id=2406
        
@@ -26,28 +31,32 @@ Mailing list: linux-ext4@vger.kernel.org
    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
-  - Create a new filesystem using the ext4dev filesystem type:
+  - Note that it is highly important to install the mke2fs.conf file
+    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
+    you have edited the /etc/mke2fs.conf file installed on your system,
+    you will need to merge your changes with the version from e2fsprogs
+    1.41.x.
+  - Create a new filesystem using the ext4 filesystem type:
-        # mke2fs -t ext4dev /dev/hda1
+        # mke2fs -t ext4 /dev/hda1
-    Or configure an existing ext3 filesystem to support extents and set
+    Or to configure an existing ext3 filesystem to support extents: 
-    the test_fs flag to indicate that it's ok for an in-development
-    filesystem to touch this filesystem:
-        # tune2fs -O extents -E test_fs /dev/hda1
+        # tune2fs -O extents /dev/hda1
    If the filesystem was created with 128 byte inodes, it can be
    converted to use 256 byte for greater efficiency via:
        # tune2fs -I 256 /dev/hda1
-    (Note: we currently do not have tools to convert an ext4dev
+    (Note: we currently do not have tools to convert an ext4
    filesystem back to ext3; so please do not do try this on production
    filesystems.)
  - Mounting:
-        # mount -t ext4dev /dev/hda1 /wherever
+        # mount -t ext4 /dev/hda1 /wherever
  - When comparing performance with other filesystems, remember that
    ext3/4 by default offers higher data integrity guarantees than most.
@@ -98,8 +107,8 @@ exist yet so I'm not sure they're in the near-term roadmap.
 The big performance win will come with mballoc, delalloc and flex_bg
 grouping of bitmaps and inode tables.  Some test results available here:
- - http://www.bullopensource.org/ext4/20080530/ffsb-write-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
- - http://www.bullopensource.org/ext4/20080530/ffsb-readwrite-2.6.26-rc2.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
 3. Options
 ==========
@@ -171,6 +180,11 @@ barrier=<0|1(*)>	This enables/disables the use of write barriers in
                        your disks are battery-backed in one way or another,
                        disabling barriers may safely improve performance.
+inode_readahead=n       This tuning parameter controls the maximum
+                        number of inode table blocks that ext4's inode
+                        table readahead algorithm will pre-read into
+                        the buffer cache.  The default value is 32 blocks.
 orlov           (*)     This enables the new Orlov block allocator. It is
                        enabled by default.
@@ -203,15 +217,17 @@ noreservation
 bsddf           (*)     Make 'df' act like BSD.
 minixdf                 Make 'df' act like Minix.
-check=none              Don't do extra checking of bitmaps on mount.
-nocheck
 debug                   Extra debugging information is sent to syslog.
 errors=remount-ro(*)    Remount the filesystem read-only on an error.
 errors=continue         Keep going on a filesystem error.
 errors=panic            Panic and halt the machine if an error occurs.
+data_err=ignore(*)      Just print an error message if an error occurs
+                        in a file data buffer in ordered mode.
+data_err=abort          Abort the journal if an error occurs in a file
+                        data buffer in ordered mode.
 grpid                   Give objects the same group ID as their creator.
 bsdgroups
@@ -237,8 +253,6 @@ nobh			(a) cache disk block mapping information
                        "nobh" option tries to avoid associating buffer
                        heads (supported only for "writeback" mode).
-mballoc         (*)     Use the multiple block allocator for block allocation
-nomballoc               disabled multiple block allocator for block allocation.
 stripe=n                Number of filesystem blocks that mballoc will try
                        to use for allocation size and alignment. For RAID5/6
                        systems this should be the number of data
@@ -246,6 +260,7 @@ stripe=n		Number of filesystem blocks that mballoc will try
 delalloc        (*)     Deferring block allocation until write-out time.
 nodelalloc              Disable delayed allocation. Blocks are allocation
                        when data is copied from user to page cache.
 Data Mode
 =========
 There are 3 different data modes:
diff --git a/Documentation/filesystems/fiemap.txt b/Documentation/filesystems/fiemap.txt
new file mode 100644
index 000000000000..1e3defcfe50b
--- /dev/null
+++ b/Documentation/filesystems/fiemap.txt
@@ -0,0 +1,228 @@
+============
+Fiemap Ioctl
+============
+The fiemap ioctl is an efficient method for userspace to get file
+extent mappings. Instead of block-by-block mapping (such as bmap), fiemap
+returns a list of extents.
+Request Basics
+--------------
+A fiemap request is encoded within struct fiemap:
+struct fiemap {
+        __u64   fm_start;        /* logical offset (inclusive) at
+                                  * which to start mapping (in) */
+        __u64   fm_length;       /* logical length of mapping which
+                                  * userspace cares about (in) */
+        __u32   fm_flags;        /* FIEMAP_FLAG_* flags for request (in/out) */
+        __u32   fm_mapped_extents; /* number of extents that were
+                                    * mapped (out) */
+        __u32   fm_extent_count; /* size of fm_extents array (in) */
+        __u32   fm_reserved;
+        struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */
+};
+fm_start, and fm_length specify the logical range within the file
+which the process would like mappings for. Extents returned mirror
+those on disk - that is, the logical offset of the 1st returned extent
+may start before fm_start, and the range covered by the last returned
+extent may end after fm_length. All offsets and lengths are in bytes.
+Certain flags to modify the way in which mappings are looked up can be
+set in fm_flags. If the kernel doesn't understand some particular
+flags, it will return EBADR and the contents of fm_flags will contain
+the set of flags which caused the error. If the kernel is compatible
+with all flags passed, the contents of fm_flags will be unmodified.
+It is up to userspace to determine whether rejection of a particular
+flag is fatal to it's operation. This scheme is intended to allow the
+fiemap interface to grow in the future but without losing
+compatibility with old software.
+fm_extent_count specifies the number of elements in the fm_extents[] array
+that can be used to return extents.  If fm_extent_count is zero, then the
+fm_extents[] array is ignored (no extents will be returned), and the
+fm_mapped_extents count will hold the number of extents needed in
+fm_extents[] to hold the file's current mapping.  Note that there is
+nothing to prevent the file from changing between calls to FIEMAP.
+The following flags can be set in fm_flags:
+* FIEMAP_FLAG_SYNC
+If this flag is set, the kernel will sync the file before mapping extents.
+* FIEMAP_FLAG_XATTR
+If this flag is set, the extents returned will describe the inodes
+extended attribute lookup tree, instead of it's data tree.
+Extent Mapping
+--------------
+Extent information is returned within the embedded fm_extents array
+which userspace must allocate along with the fiemap structure. The
+number of elements in the fiemap_extents[] array should be passed via
+fm_extent_count. The number of extents mapped by kernel will be
+returned via fm_mapped_extents. If the number of fiemap_extents
+allocated is less than would be required to map the requested range,
+the maximum number of extents that can be mapped in the fm_extent[]
+array will be returned and fm_mapped_extents will be equal to
+fm_extent_count. In that case, the last extent in the array will not
+complete the requested range and will not have the FIEMAP_EXTENT_LAST
+flag set (see the next section on extent flags).
+Each extent is described by a single fiemap_extent structure as
+returned in fm_extents.
+struct fiemap_extent {
+        __u64   fe_logical;  /* logical offset in bytes for the start of
+                              * the extent */
+        __u64   fe_physical; /* physical offset in bytes for the start
+                              * of the extent */
+        __u64   fe_length;   /* length in bytes for the extent */
+        __u64   fe_reserved64[2];
+        __u32   fe_flags;    /* FIEMAP_EXTENT_* flags for this extent */
+        __u32   fe_reserved[3];
+};
+All offsets and lengths are in bytes and mirror those on disk.  It is valid
+for an extents logical offset to start before the request or it's logical
+length to extend past the request.  Unless FIEMAP_EXTENT_NOT_ALIGNED is
+returned, fe_logical, fe_physical, and fe_length will be aligned to the
+block size of the file system.  With the exception of extents flagged as
+FIEMAP_EXTENT_MERGED, adjacent extents will not be merged.
+The fe_flags field contains flags which describe the extent returned.
+A special flag, FIEMAP_EXTENT_LAST is always set on the last extent in
+the file so that the process making fiemap calls can determine when no
+more extents are available, without having to call the ioctl again.
+Some flags are intentionally vague and will always be set in the
+presence of other more specific flags. This way a program looking for
+a general property does not have to know all existing and future flags
+which imply that property.
+For example, if FIEMAP_EXTENT_DATA_INLINE or FIEMAP_EXTENT_DATA_TAIL
+are set, FIEMAP_EXTENT_NOT_ALIGNED will also be set. A program looking
+for inline or tail-packed data can key on the specific flag. Software
+which simply cares not to try operating on non-aligned extents
+however, can just key on FIEMAP_EXTENT_NOT_ALIGNED, and not have to
+worry about all present and future flags which might imply unaligned
+data. Note that the opposite is not true - it would be valid for
+FIEMAP_EXTENT_NOT_ALIGNED to appear alone.
+* FIEMAP_EXTENT_LAST
+This is the last extent in the file. A mapping attempt past this
+extent will return nothing.
+* FIEMAP_EXTENT_UNKNOWN
+The location of this extent is currently unknown. This may indicate
+the data is stored on an inaccessible volume or that no storage has
+been allocated for the file yet.
+* FIEMAP_EXTENT_DELALLOC
+  - This will also set FIEMAP_EXTENT_UNKNOWN.
+Delayed allocation - while there is data for this extent, it's
+physical location has not been allocated yet.
+* FIEMAP_EXTENT_ENCODED
+This extent does not consist of plain filesystem blocks but is
+encoded (e.g. encrypted or compressed).  Reading the data in this
+extent via I/O to the block device will have undefined results.
+Note that it is *always* undefined to try to update the data
+in-place by writing to the indicated location without the
+assistance of the filesystem, or to access the data using the
+information returned by the FIEMAP interface while the filesystem
+is mounted.  In other words, user applications may only read the
+extent data via I/O to the block device while the filesystem is
+unmounted, and then only if the FIEMAP_EXTENT_ENCODED flag is
+clear; user applications must not try reading or writing to the
+filesystem via the block device under any other circumstances.
+* FIEMAP_EXTENT_DATA_ENCRYPTED
+  - This will also set FIEMAP_EXTENT_ENCODED
+The data in this extent has been encrypted by the file system.
+* FIEMAP_EXTENT_NOT_ALIGNED
+Extent offsets and length are not guaranteed to be block aligned.
+* FIEMAP_EXTENT_DATA_INLINE
+  This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is located within a meta data block.
+* FIEMAP_EXTENT_DATA_TAIL
+  This will also set FIEMAP_EXTENT_NOT_ALIGNED
+Data is packed into a block with data from other files.
+* FIEMAP_EXTENT_UNWRITTEN
+Unwritten extent - the extent is allocated but it's data has not been
+initialized.  This indicates the extent's data will be all zero if read
+through the filesystem but the contents are undefined if read directly from
+the device.
+* FIEMAP_EXTENT_MERGED
+This will be set when a file does not support extents, i.e., it uses a block
+based addressing scheme.  Since returning an extent for each block back to
+userspace would be highly inefficient, the kernel will try to merge most
+adjacent blocks into 'extents'.
+VFS -> File System Implementation
+---------------------------------
+File systems wishing to support fiemap must implement a ->fiemap callback on
+their inode_operations structure. The fs ->fiemap call is responsible for
+defining it's set of supported fiemap flags, and calling a helper function on
+each discovered extent:
+struct inode_operations {
+       ...
+       int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
+                     u64 len);
+->fiemap is passed struct fiemap_extent_info which describes the
+fiemap request:
+struct fiemap_extent_info {
+        unsigned int fi_flags;          /* Flags as passed from user */
+        unsigned int fi_extents_mapped; /* Number of mapped extents */
+        unsigned int fi_extents_max;    /* Size of fiemap_extent array */
+        struct fiemap_extent *fi_extents_start; /* Start of fiemap_extent array */
+};
+It is intended that the file system should not need to access any of this
+structure directly.
+Flag checking should be done at the beginning of the ->fiemap callback via the
+fiemap_check_flags() helper:
+int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
+The struct fieinfo should be passed in as recieved from ioctl_fiemap(). The
+set of fiemap flags which the fs understands should be passed via fs_flags. If
+fiemap_check_flags finds invalid user flags, it will place the bad values in
+fieinfo->fi_flags and return -EBADR. If the file system gets -EBADR, from
+fiemap_check_flags(), it should immediately exit, returning that error back to
+ioctl_fiemap().
+For each extent in the request range, the file system should call
+the helper function, fiemap_fill_next_extent():
+int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
+                            u64 phys, u64 len, u32 flags, u32 dev);
+fiemap_fill_next_extent() will use the passed values to populate the
+next free extent in the fm_extents array. 'General' extent flags will
+automatically be set from specific flags on behalf of the calling file
+system so that the userspace API is not broken.
+fiemap_fill_next_extent() returns 0 on success, and 1 when the
+user-supplied fm_extents array is full. If an error is encountered
+while copying the extent to user memory, -EFAULT will be returned.
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index d0ec45ae4e7d..44bd766f2e5d 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -5,7 +5,7 @@
 ################################################################################
 Author: NetApp and Open Grid Computing
- Date: April 15, 2008
+ Date: May 29, 2008
 Table of Contents
 ~~~~~~~~~~~~~~~~~
@@ -60,16 +60,18 @@ Installation
    The procedures described in this document have been tested with
    distributions from Red Hat's Fedora Project (http://fedora.redhat.com/).
-  - Install nfs-utils-1.1.1 or greater on the client
+  - Install nfs-utils-1.1.2 or greater on the client
-    An NFS/RDMA mount point can only be obtained by using the mount.nfs
+    An NFS/RDMA mount point can be obtained by using the mount.nfs command in
-    command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs
+    nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils
-    you are using, type:
+    version with support for NFS/RDMA mounts, but for various reasons we
+    recommend using nfs-utils-1.1.2 or greater). To see which version of
+    mount.nfs you are using, type:
-    > /sbin/mount.nfs -V
+    $ /sbin/mount.nfs -V
-    If the version is less than 1.1.1 or the command does not exist,
+    If the version is less than 1.1.2 or the command does not exist,
-    then you will need to install the latest version of nfs-utils.
+    you should install the latest version of nfs-utils.
    Download the latest package from:
@@ -77,22 +79,33 @@ Installation
    Uncompress the package and follow the installation instructions.
-    If you will not be using GSS and NFSv4, the installation process
+    If you will not need the idmapper and gssd executables (you do not need
-    can be simplified by disabling these features when running configure:
+    these to create an NFS/RDMA enabled mount command), the installation
+    process can be simplified by disabling these features when running
+    configure:
-    > ./configure --disable-gss --disable-nfsv4
+    $ ./configure --disable-gss --disable-nfsv4
-    For more information on this see the package's README and INSTALL files.
+    To build nfs-utils you will need the tcp_wrappers package installed. For
+    more information on this see the package's README and INSTALL files.
    After building the nfs-utils package, there will be a mount.nfs binary in
    the utils/mount directory. This binary can be used to initiate NFS v2, v3,
-    or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4.
+    or v4 mounts. To initiate a v4 mount, the binary must be called
-    The standard technique is to create a symlink called mount.nfs4 to mount.nfs.
+    mount.nfs4.  The standard technique is to create a symlink called
+    mount.nfs4 to mount.nfs.
-    NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed
+    This mount.nfs binary should be installed at /sbin/mount.nfs as follows:
+    $ sudo cp utils/mount/mount.nfs /sbin/mount.nfs
+    In this location, mount.nfs will be invoked automatically for NFS mounts
+    by the system mount commmand.
+    NOTE: mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed
    on the NFS client machine. You do not need this specific version of
    nfs-utils on the server. Furthermore, only the mount.nfs command from
-    nfs-utils-1.1.1 is needed on the client.
+    nfs-utils-1.1.2 is needed on the client.
  - Install a Linux kernel with NFS/RDMA
@@ -156,8 +169,8 @@ Check RDMA and NFS Setup
    this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel
    card:
-    > modprobe ib_mthca
+    $ modprobe ib_mthca
-    > modprobe ib_ipoib
+    $ modprobe ib_ipoib
    If you are using InfiniBand, make sure there is a Subnet Manager (SM)
    running on the network. If your IB switch has an embedded SM, you can
@@ -166,7 +179,7 @@ Check RDMA and NFS Setup
    If an SM is running on your network, you should see the following:
-    > cat /sys/class/infiniband/driverX/ports/1/state
+    $ cat /sys/class/infiniband/driverX/ports/1/state
    4: ACTIVE
    where driverX is mthca0, ipath5, ehca3, etc.
@@ -174,10 +187,10 @@ Check RDMA and NFS Setup
    To further test the InfiniBand software stack, use IPoIB (this
    assumes you have two IB hosts named host1 and host2):
-    host1> ifconfig ib0 a.b.c.x
+    host1$ ifconfig ib0 a.b.c.x
-    host2> ifconfig ib0 a.b.c.y
+    host2$ ifconfig ib0 a.b.c.y
-    host1> ping a.b.c.y
+    host1$ ping a.b.c.y
-    host2> ping a.b.c.x
+    host2$ ping a.b.c.x
    For other device types, follow the appropriate procedures.
@@ -202,11 +215,11 @@ NFS/RDMA Setup
    /vol0   192.168.0.47(fsid=0,rw,async,insecure,no_root_squash)
    /vol0   192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash)
-    The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the
+    The IP address(es) is(are) the client's IPoIB address for an InfiniBand
-    cleint's iWARP address(es) for an RNIC.
+    HCA or the cleint's iWARP address(es) for an RNIC.
-    NOTE: The "insecure" option must be used because the NFS/RDMA client does not
+    NOTE: The "insecure" option must be used because the NFS/RDMA client does
-    use a reserved port.
+    not use a reserved port.
 Each time a machine boots:
@@ -214,43 +227,45 @@ NFS/RDMA Setup
    For InfiniBand using a Mellanox adapter:
-    > modprobe ib_mthca
+    $ modprobe ib_mthca
-    > modprobe ib_ipoib
+    $ modprobe ib_ipoib
-    > ifconfig ib0 a.b.c.d
+    $ ifconfig ib0 a.b.c.d
    NOTE: use unique addresses for the client and server
  - Start the NFS server
-    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    load the RDMA transport module:
+    kernel config), load the RDMA transport module:
-    > modprobe svcrdma
+    $ modprobe svcrdma
-    Regardless of how the server was built (module or built-in), start the server:
+    Regardless of how the server was built (module or built-in), start the
+    server:
-    > /etc/init.d/nfs start
+    $ /etc/init.d/nfs start
    or
-    > service nfs start
+    $ service nfs start
    Instruct the server to listen on the RDMA transport:
-    > echo rdma 2050 > /proc/fs/nfsd/portlist
+    $ echo rdma 2050 > /proc/fs/nfsd/portlist
  - On the client system
-    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    load the RDMA client module:
+    kernel config), load the RDMA client module:
-    > modprobe xprtrdma.ko
+    $ modprobe xprtrdma.ko
-    Regardless of how the client was built (module or built-in), issue the mount.nfs command:
+    Regardless of how the client was built (module or built-in), use this
+    command to mount the NFS/RDMA server:
-    > /path/to/your/mount.nfs <IPoIB-server-name-or-address>:/<export> /mnt -i -o rdma,port=2050
+    $ mount -o rdma,port=2050 <IPoIB-server-name-or-address>:/<export> /mnt
-    To verify that the mount is using RDMA, run "cat /proc/mounts" and check the
+    To verify that the mount is using RDMA, run "cat /proc/mounts" and check
-    "proto" field for the given mount.
+    the "proto" field for the given mount.
  Congratulations! You're using NFS/RDMA!
diff --git a/Documentation/filesystems/nfsroot.txt b/Documentation/filesystems/nfsroot.txt
index 31b329172343..68baddf3c3e0 100644
--- a/Documentation/filesystems/nfsroot.txt
+++ b/Documentation/filesystems/nfsroot.txt
@@ -169,7 +169,7 @@ They depend on various facilities being available:
 3.1)  Booting from a floppy using syslinux
        When building kernels, an easy way to create a boot floppy that uses
-        syslinux is to use the zdisk or bzdisk make targets which use
+        syslinux is to use the zdisk or bzdisk make targets which use zimage
        and bzimage images respectively. Both targets accept the
        FDARGS parameter which can be used to set the kernel command line.
diff --git a/Documentation/filesystems/ntfs.txt b/Documentation/filesystems/ntfs.txt
index e79ee2db183a..ac2a261c5f7d 100644
--- a/Documentation/filesystems/ntfs.txt
+++ b/Documentation/filesystems/ntfs.txt
@@ -40,7 +40,7 @@ Web site
 ========
 There is plenty of additional information on the linux-ntfs web site
-at http://linux-ntfs.sourceforge.net/
+at http://www.linux-ntfs.org/
 The web site has a lot of additional information, such as a comprehensive
 FAQ, documentation on the NTFS on-disk format, information on the Linux-NTFS
@@ -272,7 +272,7 @@ And you would know that /dev/hda2 has a size of 37768814 - 4209030 + 1 =
 For Win2k and later dynamic disks, you can for example use the ldminfo utility
 which is part of the Linux LDM tools (the latest version at the time of
 writing is linux-ldm-0.0.8.tar.bz2).  You can download it from:
-        http://linux-ntfs.sourceforge.net/downloads.html
+        http://www.linux-ntfs.org/
 Simply extract the downloaded archive (tar xvjf linux-ldm-0.0.8.tar.bz2), go
 into it (cd linux-ldm-0.0.8) and change to the test directory (cd test).  You
 will find the precompiled (i386) ldminfo utility there.  NOTE: You will not be
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index c318a8bbb1ef..4340cc825796 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -76,3 +76,9 @@ localalloc=8(*)		Allows custom localalloc size in MB. If the value is too
                        large, the fs will silently revert it to the default.
                        Localalloc is not enabled for local mounts.
 localflocks             This disables cluster aware flock.
+inode64                 Indicates that Ocfs2 is allowed to create inodes at
+                        any location in the filesystem, including those which
+                        will result in inode numbers occupying more than 32
+                        bits of significance.
+user_xattr      (*)     Enables Extended User Attributes.
+nouser_xattr            Disables Extended User Attributes.
diff --git a/Documentation/filesystems/omfs.txt b/Documentation/filesystems/omfs.txt
new file mode 100644
index 000000000000..1d0d41ff5c65
--- /dev/null
+++ b/Documentation/filesystems/omfs.txt
@@ -0,0 +1,106 @@
+Optimized MPEG Filesystem (OMFS)
+Overview
+========
+OMFS is a filesystem created by SonicBlue for use in the ReplayTV DVR
+and Rio Karma MP3 player.  The filesystem is extent-based, utilizing
+block sizes from 2k to 8k, with hash-based directories.  This
+filesystem driver may be used to read and write disks from these
+devices.
+Note, it is not recommended that this FS be used in place of a general
+filesystem for your own streaming media device.  Native Linux filesystems
+will likely perform better.
+More information is available at:
+    http://linux-karma.sf.net/
+Various utilities, including mkomfs and omfsck, are included with
+omfsprogs, available at:
+    http://bobcopeland.com/karma/
+Instructions are included in its README.
+Options
+=======
+OMFS supports the following mount-time options:
+    uid=n        - make all files owned by specified user
+    gid=n        - make all files owned by specified group
+    umask=xxx    - set permission umask to xxx
+    fmask=xxx    - set umask to xxx for files
+    dmask=xxx    - set umask to xxx for directories
+Disk format
+===========
+OMFS discriminates between "sysblocks" and normal data blocks.  The sysblock
+group consists of super block information, file metadata, directory structures,
+and extents.  Each sysblock has a header containing CRCs of the entire
+sysblock, and may be mirrored in successive blocks on the disk.  A sysblock may
+have a smaller size than a data block, but since they are both addressed by the
+same 64-bit block number, any remaining space in the smaller sysblock is
+unused.
+Sysblock header information:
+struct omfs_header {
+        __be64 h_self;                  /* FS block where this is located */
+        __be32 h_body_size;             /* size of useful data after header */
+        __be16 h_crc;                   /* crc-ccitt of body_size bytes */
+        char h_fill1[2];
+        u8 h_version;                   /* version, always 1 */
+        char h_type;                    /* OMFS_INODE_X */
+        u8 h_magic;                     /* OMFS_IMAGIC */
+        u8 h_check_xor;                 /* XOR of header bytes before this */
+        __be32 h_fill2;
+};
+Files and directories are both represented by omfs_inode:
+struct omfs_inode {
+        struct omfs_header i_head;      /* header */
+        __be64 i_parent;                /* parent containing this inode */
+        __be64 i_sibling;               /* next inode in hash bucket */
+        __be64 i_ctime;                 /* ctime, in milliseconds */
+        char i_fill1[35];
+        char i_type;                    /* OMFS_[DIR,FILE] */
+        __be32 i_fill2;
+        char i_fill3[64];
+        char i_name[OMFS_NAMELEN];      /* filename */
+        __be64 i_size;                  /* size of file, in bytes */
+};
+Directories in OMFS are implemented as a large hash table.  Filenames are
+hashed then prepended into the bucket list beginning at OMFS_DIR_START.
+Lookup requires hashing the filename, then seeking across i_sibling pointers
+until a match is found on i_name.  Empty buckets are represented by block
+pointers with all-1s (~0).
+A file is an omfs_inode structure followed by an extent table beginning at
+OMFS_EXTENT_START:
+struct omfs_extent_entry {
+        __be64 e_cluster;               /* start location of a set of blocks */
+        __be64 e_blocks;                /* number of blocks after e_cluster */
+};
+struct omfs_extent {
+        __be64 e_next;                  /* next extent table location */
+        __be32 e_extent_count;          /* total # extents in this table */
+        __be32 e_fill;
+        struct omfs_extent_entry e_entry;       /* start of extent entries */
+};
+Each extent holds the block offset followed by number of blocks allocated to
+the extent.  The final extent in each table is a terminator with e_cluster
+being ~0 and e_blocks being ones'-complement of the total number of blocks
+in the table.
+If this table overflows, a continuation inode is written and pointed to by
+e_next.  These have a header but lack the rest of the inode structure.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 7f268f327d75..bcceb99b81dd 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -296,6 +296,7 @@ Table 1-4: Kernel info in /proc
 uptime      System uptime                                     
 version     Kernel version                                    
 video       bttv info of video resources                       (2.4)
+ vmallocinfo Show vmalloced areas
 ..............................................................................
 You can,  for  example,  check  which interrupts are currently in use and what
@@ -557,6 +558,49 @@ VmallocTotal: total size of vmalloc memory area
 VmallocUsed: amount of vmalloc area which is used
 VmallocChunk: largest contigious block of vmalloc area which is free
+..............................................................................
+vmallocinfo:
+Provides information about vmalloced/vmaped areas. One line per area,
+containing the virtual address range of the area, size in bytes,
+caller information of the creator, and optional information depending
+on the kind of area :
+ pages=nr    number of pages
+ phys=addr   if a physical address was specified
+ ioremap     I/O mapping (ioremap() and friends)
+ vmalloc     vmalloc() area
+ vmap        vmap()ed pages
+ user        VM_USERMAP area
+ vpages      buffer for pages pointers was vmalloced (huge area)
+ N<node>=nr  (Only on NUMA kernels)
+             Number of pages allocated on memory node <node>
+> cat /proc/vmallocinfo
+0xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
+  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
+0xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
+  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
+0xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
+  phys=7fee8000 ioremap
+0xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
+  phys=7fee7000 ioremap
+0xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
+0xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
+  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
+0xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
+  pages=2 vmalloc N1=2
+0xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
+  /0x130 [x_tables] pages=4 vmalloc N0=4
+0xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
+   pages=14 vmalloc N2=14
+0xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
+   pages=4 vmalloc N1=4
+0xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
+   pages=2 vmalloc N1=2
+0xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
+   pages=10 vmalloc N0=10
 1.3 IDE devices in /proc/ide
 ----------------------------
@@ -879,45 +923,44 @@ CPUs.
 The   "procs_blocked" line gives  the  number of  processes currently blocked,
 waiting for I/O to complete.
 1.9 Ext4 file system parameters
 ------------------------------
-Ext4 file system have one directory per partition under /proc/fs/ext4/
-# ls /proc/fs/ext4/hdc/
-group_prealloc  max_to_scan  mb_groups  mb_history  min_to_scan  order2_req
-stats  stream_req
-mb_groups:
-This file gives the details of mutiblock allocator buddy cache of free blocks
-mb_history:
-Multiblock allocation history.
-stats:
+Information about mounted ext4 file systems can be found in
-This file indicate whether the multiblock allocator should start collecting
+/proc/fs/ext4.  Each mounted filesystem will have a directory in
-statistics. The statistics are shown during unmount
+/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
+/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
+in Table 1-10, below.
-group_prealloc:
+Table 1-10: Files in /proc/fs/ext4/<devname>
-The multiblock allocator normalize the block allocation request to
+..............................................................................
-group_prealloc filesystem blocks if we don't have strip value set.
+ File            Content                                        
-The stripe value can be specified at mount time or during mke2fs.
+ mb_groups       details of multiblock allocator buddy cache of free blocks
+ mb_history      multiblock allocation history
-max_to_scan:
+ stats           controls whether the multiblock allocator should start
-How long multiblock allocator can look for a best extent (in found extents)
+                 collecting statistics, which are shown during the unmount
+ group_prealloc  the multiblock allocator will round up allocation
-min_to_scan:
+                 requests to a multiple of this tuning parameter if the
-How long multiblock allocator  must look for a best extent
+                 stripe size is not set in the ext4 superblock
+ max_to_scan     The maximum number of extents the multiblock allocator
-order2_req:
+                 will search to find the best extent
-Multiblock allocator use  2^N search using buddies only for requests greater
+ min_to_scan     The minimum number of extents the multiblock allocator
-than or equal to order2_req. The request size is specfied in file system
+                 will search to find the best extent
-blocks. A value of 2 indicate only if the requests are greater than or equal
+ order2_req      Tuning parameter which controls the minimum size for 
-to 4 blocks.
+                 requests (as a power of 2) where the buddy cache is
+                 used
+ stream_req      Files which have fewer blocks than this tunable
+                 parameter will have their blocks allocated out of a
+                 block group specific preallocation pool, so that small
+                 files are packed closely together.  Each large file
+                 will have its blocks allocated out of its own unique
+                 preallocation pool.
+inode_readahead  Tuning parameter which controls the maximum number of
+                 inode table blocks that ext4's inode table readahead
+                 algorithm will pre-read into the buffer cache
+..............................................................................
-stream_req:
-Files smaller than stream_req are served by the stream allocator, whose
-purpose is to pack requests as close each to other as possible to
-produce smooth I/O traffic. Avalue of 16 indicate that file smaller than 16
-filesystem block size will use group based preallocation.
 ------------------------------------------------------------------------------
 Summary
@@ -1278,6 +1321,18 @@ debugging information is displayed on console.
 NMI switch that most IA32 servers have fires unknown NMI up, for example.
 If a system hangs up, try pressing the NMI switch.
+panic_on_unrecovered_nmi
+------------------------
+The default Linux behaviour on an NMI of either memory or unknown is to continue
+operation. For many environments such as scientific computing it is preferable
+that the box is taken out and the error dealt with than an uncorrected
+parity/ECC error get propogated.
+A small number of systems do generate NMI's for bizarre random reasons such as
+power management so the default is off. That sysctl works like the existing
+panic controls already in that directory.
 nmi_watchdog
 ------------
@@ -1288,12 +1343,24 @@ determine whether or not they are still functioning properly.
 Because the NMI watchdog shares registers with oprofile, by disabling the NMI
 watchdog, oprofile may have more registers to utilize.
-maps_protect
+msgmni
------------
+------
+Maximum number of message queue ids on the system.
+This value scales to the amount of lowmem. It is automatically recomputed
+upon memory add/remove or ipc namespace creation/removal.
+When a value is written into this file, msgmni's value becomes fixed, i.e. it
+is not recomputed anymore when one of the above events occurs.
+Use auto_msgmni to change this behavior.
-Enables/Disables the protection of the per-process proc entries "maps" and
+auto_msgmni
-"smaps".  When enabled, the contents of these files are visible only to
+-----------
-readers that are allowed to ptrace() the given process.
+Enables/Disables automatic recomputing of msgmni upon memory add/remove or
+upon ipc namespace creation/removal (see the msgmni description above).
+Echoing "1" into this file enables msgmni automatic recomputing.
+Echoing "0" turns it off.
+auto_msgmni default value is 1.
 2.4 /proc/sys/vm - The virtual memory subsystem
@@ -1317,15 +1384,18 @@ causes the kernel to prefer to reclaim dentries and inodes.
 dirty_background_ratio
 ----------------------
-Contains, as a percentage of total system memory, the number of pages at which
+Contains, as a percentage of the dirtyable system memory (free pages + mapped
-the pdflush background writeback daemon will start writing out dirty data.
+pages + file cache, not including locked pages and HugePages), the number of
+pages at which the pdflush background writeback daemon will start writing out
+dirty data.
 dirty_ratio
 -----------------
-Contains, as a percentage of total system memory, the number of pages at which
+Contains, as a percentage of the dirtyable system memory (free pages + mapped
-a process which is generating disk writes will itself start writing out dirty
+pages + file cache, not including locked pages and HugePages), the number of
-data.
+pages at which a process which is generating disk writes will itself start
+writing out dirty data.
 dirty_writeback_centisecs
 -------------------------
@@ -1430,7 +1500,7 @@ used because pages_free(1355) is smaller than watermark + protection[2]
 normal page requirement. If requirement is DMA zone(index=0), protection[0]
 (=0) is used.
-zone[i]'s protection[j] is calculated by following exprssion.
+zone[i]'s protection[j] is calculated by following expression.
 (i < j):
  zone[i]->protection[j]
@@ -2345,22 +2415,29 @@ will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
 of memory types. If a bit of the bitmask is set, memory segments of the
 corresponding memory type are dumped, otherwise they are not dumped.
-The following 4 memory types are supported:
+The following 7 memory types are supported:
  - (bit 0) anonymous private memory
  - (bit 1) anonymous shared memory
  - (bit 2) file-backed private memory
  - (bit 3) file-backed shared memory
+  - (bit 4) ELF header pages in file-backed private memory areas (it is
+            effective only if the bit 2 is cleared)
+  - (bit 5) hugetlb private memory
+  - (bit 6) hugetlb shared memory
  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
  are always dumped regardless of the bitmask status.
-Default value of coredump_filter is 0x3; this means all anonymous memory
+  Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
-segments are dumped.
+  effected by bit 5-6.
+Default value of coredump_filter is 0x23; this means all anonymous memory
+segments and hugetlb private memory are dumped.
 If you don't want to dump all shared memory segments attached to pid 1234,
-write 1 to the process's proc file.
+write 0x21 to the process's proc file.
-  $ echo 0x1 > /proc/1234/coredump_filter
+  $ echo 0x21 > /proc/1234/coredump_filter
 When a new process is created, the process inherits the bitmask status from its
 parent. It is useful to set up coredump_filter before the program runs.
diff --git a/Documentation/filesystems/quota.txt b/Documentation/filesystems/quota.txt
index a590c4093eff..5e8de25bf0f1 100644
--- a/Documentation/filesystems/quota.txt
+++ b/Documentation/filesystems/quota.txt
@@ -3,14 +3,14 @@ Quota subsystem
 ===============
 Quota subsystem allows system administrator to set limits on used space and
-number of used inodes (inode is a filesystem structure which is associated
+number of used inodes (inode is a filesystem structure which is associated with
-with each file or directory) for users and/or groups. For both used space and
+each file or directory) for users and/or groups. For both used space and number
-number of used inodes there are actually two limits. The first one is called
+of used inodes there are actually two limits. The first one is called softlimit
-softlimit and the second one hardlimit.  An user can never exceed a hardlimit
+and the second one hardlimit.  An user can never exceed a hardlimit for any
-for any resource. User is allowed to exceed softlimit but only for limited
+resource (unless he has CAP_SYS_RESOURCE capability). User is allowed to exceed
-period of time. This period is called "grace period" or "grace time". When
+softlimit but only for limited period of time. This period is called "grace
-grace time is over, user is not able to allocate more space/inodes until he
+period" or "grace time". When grace time is over, user is not able to allocate
-frees enough of them to get below softlimit.
+more space/inodes until he frees enough of them to get below softlimit.
 Quota limits (and amount of grace time) are set independently for each
 filesystem.
@@ -53,6 +53,12 @@ in parentheses):
                QUOTA_NL_BSOFTLONGWARN - space (block) softlimit is exceeded
                  longer than given grace period.
                QUOTA_NL_BSOFTWARN - space (block) softlimit
+          - four warnings are also defined for the event when user stops
+            exceeding some limit:
+                QUOTA_NL_IHARDBELOW - inode hardlimit
+                QUOTA_NL_ISOFTBELOW - inode softlimit
+                QUOTA_NL_BHARDBELOW - space (block) hardlimit
+                QUOTA_NL_BSOFTBELOW - space (block) softlimit
        QUOTA_NL_A_DEV_MAJOR (u32)
          - major number of a device with the affected filesystem
        QUOTA_NL_A_DEV_MINOR (u32)
diff --git a/Documentation/filesystems/ramfs-rootfs-initramfs.txt b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
index 7be232b44ee4..62fe9b1e0890 100644
--- a/Documentation/filesystems/ramfs-rootfs-initramfs.txt
+++ b/Documentation/filesystems/ramfs-rootfs-initramfs.txt
@@ -263,7 +263,7 @@ User Mode Linux, like so:
    sleep(999999999);
  }
  EOF
-  gcc -static hello2.c -o init
+  gcc -static hello.c -o init
  echo init | cpio -o -H newc | gzip > test.cpio.gz
  # Testing external initramfs using the initrd loading mechanism.
  qemu -kernel /boot/vmlinuz -initrd test.cpio.gz /dev/zero
diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
index 094f2d2f38b1..510b722667ac 100644
--- a/Documentation/filesystems/relay.txt
+++ b/Documentation/filesystems/relay.txt
@@ -294,6 +294,16 @@ user-defined data with a channel, and is immediately available
 (including in create_buf_file()) via chan->private_data or
 buf->chan->private_data.
+Buffer-only channels
+--------------------
+These channels have no files associated and can be created with
+relay_open(NULL, NULL, ...). Such channels are useful in scenarios such
+as when doing early tracing in the kernel, before the VFS is up. In these
+cases, one may open a buffer-only channel and then call
+relay_late_setup_files() when the kernel is ready to handle files,
+to expose the buffered data to the userspace.
 Channel 'modes'
 ---------------
diff --git a/Documentation/filesystems/sysfs.txt b/Documentation/filesystems/sysfs.txt
index 7f27b8f840d0..9e9c348275a9 100644
--- a/Documentation/filesystems/sysfs.txt
+++ b/Documentation/filesystems/sysfs.txt
@@ -248,6 +248,7 @@ The top level sysfs directory looks like:
 block/
 bus/
 class/
+dev/
 devices/
 firmware/
 net/
@@ -274,6 +275,11 @@ fs/ contains a directory for some filesystems.  Currently each
 filesystem wanting to export attributes must create its own hierarchy
 below fs/ (see ./fuse.txt for an example).
+dev/ contains two directories char/ and block/. Inside these two
+directories there are symlinks named <major>:<minor>.  These symlinks
+point to the sysfs directory for the given device.  /sys/dev provides a
+quick way to lookup the sysfs interface for a device from the result of
+a stat(2) operation.
 More information can driver-model specific features can be found in
 Documentation/driver-model/. 
diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt
index 540e9e7f59c5..dd84ea3c10da 100644
--- a/Documentation/filesystems/ubifs.txt
+++ b/Documentation/filesystems/ubifs.txt
@@ -57,7 +57,7 @@ Similarly to JFFS2, UBIFS supports on-the-flight compression which makes
 it possible to fit quite a lot of data to the flash.
 Similarly to JFFS2, UBIFS is tolerant of unclean reboots and power-cuts.
-It does not need stuff like ckfs.ext2. UBIFS automatically replays its
+It does not need stuff like fsck.ext2. UBIFS automatically replays its
 journal and recovers from crashes, ensuring that the on-flash data
 structures are consistent.
@@ -86,6 +86,15 @@ norm_unmount (*)	commit on unmount; the journal is committed
 fast_unmount            do not commit on unmount; this option makes
                        unmount faster, but the next mount slower
                        because of the need to replay the journal.
+bulk_read               read more in one go to take advantage of flash
+                        media that read faster sequentially
+no_bulk_read (*)        do not bulk-read
+no_chk_data_crc         skip checking of CRCs on data nodes in order to
+                        improve read performance. Use this option only
+                        if the flash media is highly reliable. The effect
+                        of this option is that corruption of the contents
+                        of a file can go unnoticed.
+chk_data_crc (*)        do not skip checking CRCs on data nodes
 Quick usage instructions
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index 2d5e1e582e13..bbac4f1d9056 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -96,6 +96,14 @@ shortname=lower|win95|winnt|mixed
                        emulate the Windows 95 rule for create.
                 Default setting is `lower'.
+tz=UTC        -- Interpret timestamps as UTC rather than local time.
+                 This option disables the conversion of timestamps
+                 between local time (as used by Windows on FAT) and UTC
+                 (which Linux uses internally).  This is particuluarly
+                 useful when mounting devices (like digital cameras)
+                 that are set to UTC in order to avoid the pitfalls of
+                 local time.
 <bool>: 0,1,yes,no,true,false
 TODO
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index b7522c6cbae3..c4d348dabe94 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -143,7 +143,7 @@ struct file_system_type {
 The get_sb() method has the following arguments:
-  struct file_system_type *fs_type: decribes the filesystem, partly initialized
+  struct file_system_type *fs_type: describes the filesystem, partly initialized
        by the specific filesystem code
  int flags: mount flags
@@ -895,9 +895,9 @@ struct dentry_operations {
        iput() yourself
  d_dname: called when the pathname of a dentry should be generated.
-        Usefull for some pseudo filesystems (sockfs, pipefs, ...) to delay
+        Useful for some pseudo filesystems (sockfs, pipefs, ...) to delay
        pathname generation. (Instead of doing it when dentry is created,
-        its done only when the path is needed.). Real filesystems probably
+        it's done only when the path is needed.). Real filesystems probably
        dont want to use it, because their dentries are present in global
        dcache hash, so their hash should be an invariant. As no lock is
        held, d_dname() should not try to modify the dentry itself, unless
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
index f218f616ff6b..d330fe3103da 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/ftrace.txt
@@ -4,6 +4,7 @@
 Copyright 2008 Red Hat Inc.
   Author:   Steven Rostedt <srostedt@redhat.com>
  License:   The GNU Free Documentation License, Version 1.2
+               (dual licensed under the GPL v2)
 Reviewers:   Elias Oltmanns, Randy Dunlap, Andrew Morton,
             John Kacur, and David Teigland.
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index c35ca9e40d4c..b1b988701247 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -240,6 +240,10 @@ signal, or (b) something wrongly believes it's safe to remove drivers
 needed to manage a signal that's in active use.  That is, requesting a
 GPIO can serve as a kind of lock.
+Some platforms may also use knowledge about what GPIOs are active for
+power management, such as by powering down unused chip sectors and, more
+easily, gating off unused clocks.
 These two calls are optional because not not all current Linux platforms
 offer such functionality in their GPIO support; a valid implementation
 could return success for all gpio_request() calls.  Unlike the other calls,
@@ -264,7 +268,7 @@ map between them using calls like:
        /* map GPIO numbers to IRQ numbers */
        int gpio_to_irq(unsigned gpio);
-        /* map IRQ numbers to GPIO numbers */
+        /* map IRQ numbers to GPIO numbers (avoid using this) */
        int irq_to_gpio(unsigned irq);
 Those return either the corresponding number in the other namespace, or
@@ -284,7 +288,8 @@ system wakeup capabilities.
 Non-error values returned from irq_to_gpio() would most commonly be used
 with gpio_get_value(), for example to initialize or update driver state
-when the IRQ is edge-triggered.
+when the IRQ is edge-triggered.  Note that some platforms don't support
+this reverse mapping, so you should avoid using it.
 Emulating Open Drain Signals
@@ -347,15 +352,12 @@ necessarily be nonportable.
 Dynamic definition of GPIOs is not currently standard; for example, as
 a side effect of configuring an add-on board with some GPIO expanders.
-These calls are purely for kernel space, but a userspace API could be built
-on top of them.
 GPIO implementor's framework (OPTIONAL)
 =======================================
 As noted earlier, there is an optional implementation framework making it
 easier for platforms to support different kinds of GPIO controller using
-the same programming interface.
+the same programming interface.  This framework is called "gpiolib".
 As a debugging aid, if debugfs is available a /sys/kernel/debug/gpio file
 will be found there.  That will list all the controllers registered through
@@ -392,11 +394,21 @@ either NULL or the label associated with that GPIO when it was requested.
 Platform Support
 ----------------
-To support this framework, a platform's Kconfig will "select HAVE_GPIO_LIB"
+To support this framework, a platform's Kconfig will "select" either
+ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
 They may also want to provide a custom value for ARCH_NR_GPIOS.
+ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+into the kernel on that architecture.
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+can enable it and build it into the kernel optionally.
+If neither of these options are selected, the platform does not support
+GPIOs through GPIO-lib and the code cannot be enabled by the user.
 Trivial implementations of those functions can directly use framework
 code, which always dispatches through the gpio_chip:
@@ -439,4 +451,120 @@ becomes available.  That may mean the device should not be registered until
 calls for that GPIO can work.  One way to address such dependencies is for
 such gpio_chip controllers to provide setup() and teardown() callbacks to
 board specific code; those board specific callbacks would register devices
-once all the necessary resources are available.
+once all the necessary resources are available, and remove them later when
+the GPIO controller device becomes unavailable.
+Sysfs Interface for Userspace (OPTIONAL)
+========================================
+Platforms which use the "gpiolib" implementors framework may choose to
+configure a sysfs user interface to GPIOs.  This is different from the
+debugfs interface, since it provides control over GPIO direction and
+value instead of just showing a gpio state summary.  Plus, it could be
+present on production systems without debugging support.
+Given approprate hardware documentation for the system, userspace could
+know for example that GPIO #23 controls the write protect line used to
+protect boot loader segments in flash memory.  System upgrade procedures
+may need to temporarily remove that protection, first importing a GPIO,
+then changing its output state, then updating the code before re-enabling
+the write protection.  In normal use, GPIO #23 would never be touched,
+and the kernel would have no need to know about it.
+Again depending on appropriate hardware documentation, on some systems
+userspace GPIO can be used to determine system configuration data that
+standard kernels won't know about.  And for some tasks, simple userspace
+GPIO drivers could be all that the system really needs.
+Note that standard kernel drivers exist for common "LEDs and Buttons"
+GPIO tasks:  "leds-gpio" and "gpio_keys", respectively.  Use those
+instead of talking directly to the GPIOs; they integrate with kernel
+frameworks better than your userspace code could.
+Paths in Sysfs
+--------------
+There are three kinds of entry in /sys/class/gpio:
+   -    Control interfaces used to get userspace control over GPIOs;
+   -    GPIOs themselves; and
+   -    GPIO controllers ("gpio_chip" instances).
+That's in addition to standard files including the "device" symlink.
+The control interfaces are write-only:
+    /sys/class/gpio/
+        "export" ... Userspace may ask the kernel to export control of
+                a GPIO to userspace by writing its number to this file.
+                Example:  "echo 19 > export" will create a "gpio19" node
+                for GPIO #19, if that's not requested by kernel code.
+        "unexport" ... Reverses the effect of exporting to userspace.
+                Example:  "echo 19 > unexport" will remove a "gpio19"
+                node exported using the "export" file.
+GPIO signals have paths like /sys/class/gpio/gpio42/ (for GPIO #42)
+and have the following read/write attributes:
+    /sys/class/gpio/gpioN/
+        "direction" ... reads as either "in" or "out".  This value may
+                normally be written.  Writing as "out" defaults to
+                initializing the value as low.  To ensure glitch free
+                operation, values "low" and "high" may be written to
+                configure the GPIO as an output with that initial value.
+                Note that this attribute *will not exist* if the kernel
+                doesn't support changing the direction of a GPIO, or
+                it was exported by kernel code that didn't explicitly
+                allow userspace to reconfigure this GPIO's direction.
+        "value" ... reads as either 0 (low) or 1 (high).  If the GPIO
+                is configured as an output, this value may be written;
+                any nonzero value is treated as high.
+GPIO controllers have paths like /sys/class/gpio/chipchip42/ (for the
+controller implementing GPIOs starting at #42) and have the following
+read-only attributes:
+    /sys/class/gpio/gpiochipN/
+        "base" ... same as N, the first GPIO managed by this chip
+        "label" ... provided for diagnostics (not always unique)
+        "ngpio" ... how many GPIOs this manges (N to N + ngpio - 1)
+Board documentation should in most cases cover what GPIOs are used for
+what purposes.  However, those numbers are not always stable; GPIOs on
+a daughtercard might be different depending on the base board being used,
+or other cards in the stack.  In such cases, you may need to use the
+gpiochip nodes (possibly in conjunction with schematics) to determine
+the correct GPIO number to use for a given signal.
+Exporting from Kernel code
+--------------------------
+Kernel code can explicitly manage exports of GPIOs which have already been
+requested using gpio_request():
+        /* export the GPIO to userspace */
+        int gpio_export(unsigned gpio, bool direction_may_change);
+        /* reverse gpio_export() */
+        void gpio_unexport();
+After a kernel driver requests a GPIO, it may only be made available in
+the sysfs interface by gpio_export().  The driver can control whether the
+signal direction may change.  This helps drivers prevent userspace code
+from accidentally clobbering important system state.
+This explicit exporting can help with debugging (by making some kinds
+of experiments easier), or can provide an always-there interface that's
+suitable for documenting as part of a board support package.
diff --git a/Documentation/hwmon/adt7470 b/Documentation/hwmon/adt7470
new file mode 100644
index 000000000000..75d13ca147cc
--- /dev/null
+++ b/Documentation/hwmon/adt7470
@@ -0,0 +1,76 @@
+Kernel driver adt7470
+=====================
+Supported chips:
+  * Analog Devices ADT7470
+    Prefix: 'adt7470'
+    Addresses scanned: I2C 0x2C, 0x2E, 0x2F
+    Datasheet: Publicly available at the Analog Devices website
+Author: Darrick J. Wong
+Description
+-----------
+This driver implements support for the Analog Devices ADT7470 chip.  There may
+be other chips that implement this interface.
+The ADT7470 uses the 2-wire interface compatible with the SMBus 2.0
+specification. Using an analog to digital converter it measures up to ten (10)
+external temperatures. It has four (4) 16-bit counters for measuring fan speed.
+There are four (4) PWM outputs that can be used to control fan speed.
+A sophisticated control system for the PWM outputs is designed into the ADT7470
+that allows fan speed to be adjusted automatically based on any of the ten
+temperature sensors. Each PWM output is individually adjustable and
+programmable. Once configured, the ADT7470 will adjust the PWM outputs in
+response to the measured temperatures with further host intervention.  This
+feature can also be disabled for manual control of the PWM's.
+Each of the measured inputs (temperature, fan speed) has corresponding high/low
+limit values. The ADT7470 will signal an ALARM if any measured value exceeds
+either limit.
+The ADT7470 DOES NOT sample all inputs continuously.  A single pin on the
+ADT7470 is connected to a multitude of thermal diodes, but the chip must be
+instructed explicitly to read the multitude of diodes.  If you want to use
+automatic fan control mode, you must manually read any of the temperature
+sensors or the fan control algorithm will not run.  The chip WILL NOT DO THIS
+AUTOMATICALLY; this must be done from userspace.  This may be a bug in the chip
+design, given that many other AD chips take care of this.  The driver will not
+read the registers more often than once every 5 seconds.  Further,
+configuration data is only read once per minute.
+Special Features
+----------------
+The ADT7470 has a 8-bit ADC and is capable of measuring temperatures with 1
+degC resolution.
+The Analog Devices datasheet is very detailed and describes a procedure for
+determining an optimal configuration for the automatic PWM control.
+Configuration Notes
+-------------------
+Besides standard interfaces driver adds the following:
+* PWM Control
+* pwm#_auto_point1_pwm and pwm#_auto_point1_temp and
+* pwm#_auto_point2_pwm and pwm#_auto_point2_temp -
+point1: Set the pwm speed at a lower temperature bound.
+point2: Set the pwm speed at a higher temperature bound.
+The ADT7470 will scale the pwm between the lower and higher pwm speed when
+the temperature is between the two temperature boundaries.  PWM values range
+from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
+temperature sensor associated with the PWM control exceeds
+pwm#_auto_point2_temp.
+Notes
+-----
+As stated above, the temperature inputs must be read periodically from
+userspace in order for the automatic pwm algorithm to run.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
index 2126de34c711..1cbf671822e2 100644
--- a/Documentation/hwmon/adt7473
+++ b/Documentation/hwmon/adt7473
@@ -14,14 +14,14 @@ Description
 This driver implements support for the Analog Devices ADT7473 chip family.
-The LM85 uses the 2-wire interface compatible with the SMBUS 2.0
+The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
 specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has three (3) 16-bit counters for
+temperatures and two (2) voltages. It has four (4) 16-bit counters for
 measuring fan speed. There are three (3) PWM outputs that can be used
 to control fan speed.
 A sophisticated control system for the PWM outputs is designed into the
-LM85 that allows fan speed to be adjusted automatically based on any of the
+ADT7473 that allows fan speed to be adjusted automatically based on any of the
 three temperature sensors. Each PWM output is individually adjustable and
 programmable. Once configured, the ADT7473 will adjust the PWM outputs in
 response to the measured temperatures without further host intervention.
@@ -46,14 +46,6 @@ from the raw value to get the temperature value.
 The Analog Devices datasheet is very detailed and describes a procedure for
 determining an optimal configuration for the automatic PWM control.
-Hardware Configurations
-----------------------
-The ADT7473 chips have an optional SMBALERT output that can be used to
-signal the chipset in case a limit is exceeded or the temperature sensors
-fail. Individual sensor interrupts can be masked so they won't trigger
-SMBALERT. The SMBALERT output if configured replaces the PWM2 function.
 Configuration Notes
 -------------------
@@ -61,8 +53,8 @@ Besides standard interfaces driver adds the following:
 * PWM Control
-* pwm#_auto_point1_pwm and pwm#_auto_point1_temp and
+* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and pwm#_auto_point2_temp -
+* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
 point1: Set the pwm speed at a lower temperature bound.
 point2: Set the pwm speed at a higher temperature bound.
diff --git a/Documentation/hwmon/dme1737 b/Documentation/hwmon/dme1737
index 8f446070e64a..001d2e70bc11 100644
--- a/Documentation/hwmon/dme1737
+++ b/Documentation/hwmon/dme1737
@@ -10,6 +10,10 @@ Supported chips:
    Prefix: 'sch311x'
    Addresses scanned: none, address read from Super-I/O config space
    Datasheet: http://www.nuhorizons.com/FeaturedProducts/Volume1/SMSC/311x.pdf
+  * SMSC SCH5027
+    Prefix: 'sch5027'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: Provided by SMSC upon request and under NDA
 Authors:
    Juerg Haefliger <juergh@gmail.com>
@@ -22,34 +26,36 @@ Module Parameters
                        and PWM output control functions. Using this parameter
                        shouldn't be required since the BIOS usually takes care
                        of this.
+* probe_all_addr: bool  Include non-standard LPC addresses 0x162e and 0x164e
-Note that there is no need to use this parameter if the driver loads without
+                        when probing for ISA devices. This is required for the
-complaining. The driver will say so if it is necessary.
+                        following boards:
+                        - VIA EPIA SN18000
 Description
 -----------
 This driver implements support for the hardware monitoring capabilities of the
-SMSC DME1737 and Asus A8000 (which are the same) and SMSC SCH311x Super-I/O
+SMSC DME1737 and Asus A8000 (which are the same), SMSC SCH5027, and SMSC
-chips. These chips feature monitoring of 3 temp sensors temp[1-3] (2 remote
+SCH311x Super-I/O chips. These chips feature monitoring of 3 temp sensors
-diodes and 1 internal), 7 voltages in[0-6] (6 external and 1 internal) and up
+temp[1-3] (2 remote diodes and 1 internal), 7 voltages in[0-6] (6 external and
-to 6 fan speeds fan[1-6]. Additionally, the chips implement up to 5 PWM
+1 internal) and up to 6 fan speeds fan[1-6]. Additionally, the chips implement
-outputs pwm[1-3,5-6] for controlling fan speeds both manually and
+up to 5 PWM outputs pwm[1-3,5-6] for controlling fan speeds both manually and
 automatically.
-For the DME1737 and A8000, fan[1-2] and pwm[1-2] are always present. Fan[3-6]
+For the DME1737, A8000 and SCH5027, fan[1-2] and pwm[1-2] are always present.
-and pwm[3,5-6] are optional features and their availability depends on the
+Fan[3-6] and pwm[3,5-6] are optional features and their availability depends on
-configuration of the chip. The driver will detect which features are present
+the configuration of the chip. The driver will detect which features are
-during initialization and create the sysfs attributes accordingly.
+present during initialization and create the sysfs attributes accordingly.
 For the SCH311x, fan[1-3] and pwm[1-3] are always present and fan[4-6] and
 pwm[5-6] don't exist.
-The hardware monitoring features of the DME1737 and A8000 are only accessible
+The hardware monitoring features of the DME1737, A8000, and SCH5027 are only
-via SMBus, while the SCH311x only provides access via the ISA bus. The driver
+accessible via SMBus, while the SCH311x only provides access via the ISA bus.
-will therefore register itself as an I2C client driver if it detects a DME1737
+The driver will therefore register itself as an I2C client driver if it detects
-or A8000 and as a platform driver if it detects a SCH311x chip.
+a DME1737, A8000, or SCH5027 and as a platform driver if it detects a SCH311x
+chip.
 Voltage Monitoring
@@ -60,6 +66,7 @@ scaling resistors. The values returned by the driver therefore reflect true
 millivolts and don't need scaling. The voltage inputs are mapped as follows
 (the last column indicates the input ranges):
+DME1737, A8000:
        in0: +5VTR      (+5V standby)           0V - 6.64V
        in1: Vccp       (processor core)        0V - 3V
        in2: VCC        (internal +3.3V)        0V - 4.38V
@@ -68,6 +75,24 @@ millivolts and don't need scaling. The voltage inputs are mapped as follows
        in5: VTR        (+3.3V standby)         0V - 4.38V
        in6: Vbat       (+3.0V)                 0V - 4.38V
+SCH311x:
+        in0: +2.5V                              0V - 6.64V
+        in1: Vccp       (processor core)        0V - 2V
+        in2: VCC        (internal +3.3V)        0V - 4.38V
+        in3: +5V                                0V - 6.64V
+        in4: +12V                               0V - 16V
+        in5: VTR        (+3.3V standby)         0V - 4.38V
+        in6: Vbat       (+3.0V)                 0V - 4.38V
+SCH5027:
+        in0: +5VTR      (+5V standby)           0V - 6.64V
+        in1: Vccp       (processor core)        0V - 3V
+        in2: VCC        (internal +3.3V)        0V - 4.38V
+        in3: V2_IN                              0V - 1.5V
+        in4: V1_IN                              0V - 1.5V
+        in5: VTR        (+3.3V standby)         0V - 4.38V
+        in6: Vbat       (+3.0V)                 0V - 4.38V
 Each voltage input has associated min and max limits which trigger an alarm
 when crossed.
diff --git a/Documentation/hwmon/ibmaem b/Documentation/hwmon/ibmaem
index 2fefaf582a43..e98bdfea3467 100644
--- a/Documentation/hwmon/ibmaem
+++ b/Documentation/hwmon/ibmaem
@@ -1,8 +1,11 @@
 Kernel driver ibmaem
 ======================
+This driver talks to the IBM Systems Director Active Energy Manager, known
+henceforth as AEM.
 Supported systems:
-  * Any recent IBM System X server with Active Energy Manager support.
+  * Any recent IBM System X server with AEM support.
    This includes the x3350, x3550, x3650, x3655, x3755, x3850 M2,
    x3950 M2, and certain HS2x/LS2x/QS2x blades.  The IPMI host interface
    driver ("ipmi-si") needs to be loaded for this driver to do anything.
@@ -14,24 +17,22 @@ Author: Darrick J. Wong
 Description
 -----------
-This driver implements sensor reading support for the energy and power
+This driver implements sensor reading support for the energy and power meters
-meters available on various IBM System X hardware through the BMC.  All
+available on various IBM System X hardware through the BMC.  All sensor banks
-sensor banks will be exported as platform devices; this driver can talk
+will be exported as platform devices; this driver can talk to both v1 and v2
-to both v1 and v2 interfaces.  This driver is completely separate from the
+interfaces.  This driver is completely separate from the older ibmpex driver.
-older ibmpex driver.
-The v1 AEM interface has a simple set of features to monitor energy use.
+The v1 AEM interface has a simple set of features to monitor energy use.  There
-There is a register that displays an estimate of raw energy consumption
+is a register that displays an estimate of raw energy consumption since the
-since the last BMC reset, and a power sensor that returns average power
+last BMC reset, and a power sensor that returns average power use over a
-use over a configurable interval.
+configurable interval.
-The v2 AEM interface is a bit more sophisticated, being able to present
+The v2 AEM interface is a bit more sophisticated, being able to present a wider
-a wider range of energy and power use registers, the power cap as
+range of energy and power use registers, the power cap as set by the AEM
-set by the AEM software, and temperature sensors.
+software, and temperature sensors.
 Special Features
 ----------------
-The "power_cap" value displays the current system power cap, as set by
+The "power_cap" value displays the current system power cap, as set by the AEM
-the Active Energy Manager software.  Setting the power cap from the host
+software.  Setting the power cap from the host is not currently supported.
-is not currently supported.
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index f4ce1fdbeff6..042c0415140b 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -6,12 +6,14 @@ Supported chips:
    Prefix: 'it87'
    Addresses scanned: from Super I/O config space (8 I/O ports)
    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/
+               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
  * IT8712F
    Prefix: 'it8712'
    Addresses scanned: from Super I/O config space (8 I/O ports)
    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/
+               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
+               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
+               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
  * IT8716F/IT8726F
    Prefix: 'it8716'
    Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -90,14 +92,13 @@ 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 and later IT8712F revisions have support for
-2 additional fans. They are supported by the driver for the IT8716F and
+2 additional fans. The additional fans are supported by the driver.
-IT8718F but not for the IT8712F
 The IT8716F and IT8718F, and late IT8712F and IT8705F also have optional
 16-bit tachometer counters for fans 1 to 3. This is better (no more fan
 clock divider mess) but not compatible with the older chips and
-revisions. For now, the driver only uses the 16-bit mode on the
+revisions. The 16-bit tachometer mode is enabled by the driver when one
-IT8716F and IT8718F.
+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
@@ -135,10 +136,10 @@ once-only alarms.
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
-To change sensor N to a thermistor, 'echo 2 > tempN_type' where N is 1, 2,
+To change sensor N to a thermistor, 'echo 4 > tempN_type' where N is 1, 2,
 or 3. To change sensor N to a thermal diode, 'echo 3 > tempN_type'.
 Give 0 for unused sensor. Any other value is invalid. To configure this at
-startup, consult lm_sensors's /etc/sensors.conf. (2 = thermistor;
+startup, consult lm_sensors's /etc/sensors.conf. (4 = thermistor;
 3 = thermal diode)
diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85
index 9549237530cf..400620741290 100644
--- a/Documentation/hwmon/lm85
+++ b/Documentation/hwmon/lm85
@@ -96,11 +96,6 @@ initial testing of the ADM1027 it was 1.00 degC steps. Analog Devices has
 confirmed this "bug". The ADT7463 is reported to work as described in the
 documentation. The current lm85 driver does not show the offset register.
-The ADT7463 has a THERM asserted counter. This counter has a 22.76ms
-resolution and a range of 5.8 seconds. The driver implements a 32-bit
-accumulator of the counter value to extend the range to over a year. The
-counter will stay at it's max value until read.
 See the vendor datasheets for more information. There is application note
 from National (AN-1260) with some additional information about the LM85.
 The Analog Devices datasheet is very detailed and describes a procedure for
@@ -168,16 +163,6 @@ configured individually according to the following options.
 * pwm#_auto_pwm_min - this specifies the PWM value for temp#_auto_temp_off
                      temperature. (PWM value from 0 to 255)
-* pwm#_auto_pwm_freq - select base frequency of PWM output. You can select
-                       in range of 10.0 to 94.0 Hz in .1 Hz units.
-                       (Values 100 to 940).
-The pwm#_auto_pwm_freq can be set to one of the following 8 values. Setting the
-frequency to a value not on this list, will result in the next higher frequency
-being selected. The actual device frequency may vary slightly from this
-specification as designed by the manufacturer. Consult the datasheet for more
-details. (PWM Frequency values:  100, 150, 230, 300, 380, 470, 620, 940)
 * pwm#_auto_pwm_minctl - this flags selects for temp#_auto_temp_off temperature
                         the bahaviour of fans. Write 1 to let fans spinning at
                         pwm#_auto_pwm_min or write 0 to let them off.
@@ -206,13 +191,15 @@ Configuration choices:
 The National LM85's have two vendor specific configuration
 features. Tach. mode and Spinup Control. For more details on these,
-see the LM85 datasheet or Application Note AN-1260.
+see the LM85 datasheet or Application Note AN-1260. These features
+are not currently supported by the lm85 driver.
 The Analog Devices ADM1027 has several vendor specific enhancements.
 The number of pulses-per-rev of the fans can be set, Tach monitoring
 can be optimized for PWM operation, and an offset can be applied to
 the temperatures to compensate for systemic errors in the
-measurements.
+measurements. These features are not currently supported by the lm85
+driver.
 In addition to the ADM1027 features, the ADT7463 also has Tmin control
 and THERM asserted counts. Automatic Tmin control acts to adjust the
diff --git a/Documentation/hwmon/lm87 b/Documentation/hwmon/lm87
index ec27aa1b94cb..6b47b67fd968 100644
--- a/Documentation/hwmon/lm87
+++ b/Documentation/hwmon/lm87
@@ -65,11 +65,10 @@ The LM87 has four pins which can serve one of two possible functions,
 depending on the hardware configuration.
 Some functions share pins, so not all functions are available at the same
-time. Which are depends on the hardware setup. This driver assumes that
+time. Which are depends on the hardware setup. This driver normally
-the BIOS configured the chip correctly. In that respect, it differs from
+assumes that firmware configured the chip correctly. Where this is not
-the original driver (from lm_sensors for Linux 2.4), which would force the
+the case, platform code must set the I2C client's platform_data to point
-LM87 to an arbitrary, compile-time chosen mode, regardless of the actual
+to a u8 value to be written to the channel register.
-chipset wiring.
 For reference, here is the list of exclusive functions:
 - in0+in5 (default) or temp3
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index aa4a0ec20081..0e8411710238 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -8,10 +8,10 @@ Supported chips:
    Datasheet: Publicly available at the National Semiconductor website
               http://www.national.com/pf/LM/LM90.html
  * National Semiconductor LM89
-    Prefix: 'lm99'
+    Prefix: 'lm89' (no auto-detection)
    Addresses scanned: I2C 0x4c and 0x4d
    Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM89.html
+               http://www.national.com/mpf/LM/LM89.html
  * National Semiconductor LM99
    Prefix: 'lm99'
    Addresses scanned: I2C 0x4c and 0x4d
@@ -21,18 +21,32 @@ Supported chips:
    Prefix: 'lm86'
    Addresses scanned: I2C 0x4c
    Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM86.html
+               http://www.national.com/mpf/LM/LM86.html
  * Analog Devices ADM1032
    Prefix: 'adm1032'
    Addresses scanned: I2C 0x4c and 0x4d
-    Datasheet: Publicly available at the Analog Devices website
+    Datasheet: Publicly available at the ON Semiconductor website
-               http://www.analog.com/en/prod/0,2877,ADM1032,00.html
+               http://www.onsemi.com/PowerSolutions/product.do?id=ADM1032
  * Analog Devices ADT7461
    Prefix: 'adt7461'
    Addresses scanned: I2C 0x4c and 0x4d
-    Datasheet: Publicly available at the Analog Devices website
+    Datasheet: Publicly available at the ON Semiconductor website
-               http://www.analog.com/en/prod/0,2877,ADT7461,00.html
+               http://www.onsemi.com/PowerSolutions/product.do?id=ADT7461
-    Note: Only if in ADM1032 compatibility mode
+  * Maxim MAX6646
+    Prefix: 'max6646'
+    Addresses scanned: I2C 0x4d
+    Datasheet: Publicly available at the Maxim website
+               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+  * Maxim MAX6647
+    Prefix: 'max6646'
+    Addresses scanned: I2C 0x4e
+    Datasheet: Publicly available at the Maxim website
+               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+  * Maxim MAX6649
+    Prefix: 'max6646'
+    Addresses scanned: I2C 0x4c
+    Datasheet: Publicly available at the Maxim website
+               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
  * Maxim MAX6657
    Prefix: 'max6657'
    Addresses scanned: I2C 0x4c
@@ -70,25 +84,21 @@ Description
 The LM90 is a digital temperature sensor. It senses its own temperature as
 well as the temperature of up to one external diode. It is compatible
-with many other devices such as the LM86, the LM89, the LM99, the ADM1032,
+with many other devices, many of which are supported by this driver.
-the MAX6657, MAX6658, MAX6659, MAX6680 and the MAX6681 all 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
 MAX6659 are not supported by this driver. The MAX6680 and MAX6681 only
 differ in their pinout, therefore they obviously can't (and don't need to)
-be distinguished. Additionally, the ADT7461 is supported if found in
+be distinguished.
-ADM1032 compatibility mode.
 The specificity of this family of chipsets over the ADM1021/LM84
 family is that it features critical limits with hysteresis, and an
 increased resolution of the remote temperature measurement.
 The different chipsets of the family are not strictly identical, although
-very similar. This driver doesn't handle any specific feature for now,
+very similar. For reference, here comes a non-exhaustive list of specific
-with the exception of SMBus PEC. For reference, here comes a non-exhaustive
+features:
-list of specific features:
 LM90:
  * Filter and alert configuration register at 0xBF.
@@ -114,9 +124,11 @@ ADT7461:
  * Lower resolution for remote temperature
 MAX6657 and MAX6658:
+  * Better local resolution
  * Remote sensor type selection
 MAX6659:
+  * Better local resolution
  * Selectable address
  * Second critical temperature limit
  * Remote sensor type selection
@@ -127,7 +139,8 @@ MAX6680 and MAX6681:
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
-temperature.
+temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
+resolution of 0.125 degree for both temperatures.
 Each sensor has its own high and low limits, plus a critical limit.
 Additionally, there is a relative hysteresis value common to both critical
diff --git a/Documentation/hwmon/pc87360 b/Documentation/hwmon/pc87360
index 89a8fcfa78df..cbac32b59c8c 100644
--- a/Documentation/hwmon/pc87360
+++ b/Documentation/hwmon/pc87360
@@ -5,12 +5,7 @@ Supported chips:
  * National Semiconductor PC87360, PC87363, PC87364, PC87365 and PC87366
    Prefixes: 'pc87360', 'pc87363', 'pc87364', 'pc87365', 'pc87366'
    Addresses scanned: none, address read from Super I/O config space
-    Datasheets:
+    Datasheets: No longer available
-        http://www.national.com/pf/PC/PC87360.html
-        http://www.national.com/pf/PC/PC87363.html
-        http://www.national.com/pf/PC/PC87364.html
-        http://www.national.com/pf/PC/PC87365.html
-        http://www.national.com/pf/PC/PC87366.html
 Authors: Jean Delvare <khali@linux-fr.org>
diff --git a/Documentation/hwmon/pc87427 b/Documentation/hwmon/pc87427
index 9a0708f9f49e..d1ebbe510f35 100644
--- a/Documentation/hwmon/pc87427
+++ b/Documentation/hwmon/pc87427
@@ -5,7 +5,7 @@ Supported chips:
  * National Semiconductor PC87427
    Prefix: 'pc87427'
    Addresses scanned: none, address read from Super I/O config space
-    Datasheet: http://www.winbond.com.tw/E-WINBONDHTM/partner/apc_007.html
+    Datasheet: No longer available
 Author: Jean Delvare <khali@linux-fr.org>
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 2d845730d4e0..6dbfd5efd991 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -329,6 +329,10 @@ power[1-*]_average		Average power use
                                Unit: microWatt
                                RO
+power[1-*]_average_interval     Power use averaging interval
+                                Unit: milliseconds
+                                RW
 power[1-*]_average_highest      Historical average maximum power use
                                Unit: microWatt
                                RO
@@ -354,6 +358,14 @@ power[1-*]_reset_history	Reset input_highest, input_lowest,
                                WO
 **********
+* Energy *
+**********
+energy[1-*]_input               Cumulative energy use
+                                Unit: microJoule
+                                RO
+**********
 * Alarms *
 **********
diff --git a/Documentation/hwmon/w83627hf b/Documentation/hwmon/w83627hf
index 880a59f53da9..6ee36dbafd64 100644
--- a/Documentation/hwmon/w83627hf
+++ b/Documentation/hwmon/w83627hf
@@ -40,10 +40,6 @@ Module Parameters
  (default is 1)
  Use 'init=0' to bypass initializing the chip.
  Try this if your computer crashes when you load the module.
-* reset: int
-  (default is 0)
-  The driver used to reset the chip on load, but does no more. Use
-  'reset=1' to restore the old behavior. Report if you need to do this.
 Description
 -----------
diff --git a/Documentation/hwmon/w83781d b/Documentation/hwmon/w83781d
index 6f800a0283e9..c91e0b63ea1d 100644
--- a/Documentation/hwmon/w83781d
+++ b/Documentation/hwmon/w83781d
@@ -353,7 +353,7 @@ in6=255
 # PWM
-Additional info about PWM on the AS99127F (may apply to other Asus
+* Additional info about PWM on the AS99127F (may apply to other Asus
 chips as well) by Jean Delvare as of 2004-04-09:
 AS99127F revision 2 seems to have two PWM registers at 0x59 and 0x5A,
@@ -396,7 +396,7 @@ Please contact us if you can figure out how it is supposed to work. As
 long as we don't know more, the w83781d driver doesn't handle PWM on
 AS99127F chips at all.
-Additional info about PWM on the AS99127F rev.1 by Hector Martin:
+* Additional info about PWM on the AS99127F rev.1 by Hector Martin:
 I've been fiddling around with the (in)famous 0x59 register and
 found out the following values do work as a form of coarse pwm:
@@ -418,3 +418,36 @@ change.
 My mobo is an ASUS A7V266-E. This behavior is similar to what I got
 with speedfan under Windows, where 0-15% would be off, 15-2x% (can't
 remember the exact value) would be 70% and higher would be full on.
+* Additional info about PWM on the AS99127F rev.1 from lm-sensors
+  ticket #2350:
+I conducted some experiment on Asus P3B-F motherboard with AS99127F
+(Ver. 1).
+I confirm that 0x59 register control the CPU_Fan Header on this
+motherboard, and 0x5a register control PWR_Fan.
+In order to reduce the dependency of specific fan, the measurement is
+conducted with a digital scope without fan connected. I found out that
+P3B-F actually output variable DC voltage on fan header center pin,
+looks like PWM is filtered on this motherboard.
+Here are some of measurements:
+0x80     20 mV
+0x81     20 mV
+0x82    232 mV
+0x83   1.2  V
+0x84   2.31 V
+0x85   3.44 V
+0x86   4.62 V
+0x87   5.81 V
+0x88   7.01 V
+9x89   8.22 V
+0x8a   9.42 V
+0x8b  10.6  V
+0x8c  11.9  V
+0x8d  12.4  V
+0x8e  12.4  V
+0x8f  12.4  V
diff --git a/Documentation/hwmon/w83791d b/Documentation/hwmon/w83791d
index f153b2f6d62c..5663e491655c 100644
--- a/Documentation/hwmon/w83791d
+++ b/Documentation/hwmon/w83791d
@@ -22,6 +22,7 @@ Credits:
 Additional contributors:
    Sven Anders <anders@anduras.de>
+    Marc Hulsman <m.hulsman@tudelft.nl>
 Module Parameters
 -----------------
@@ -57,30 +58,35 @@ internal state that allows no clean access (Bank with ID register is not
 currently selected). If you know the address of the chip, use a 'force'
 parameter; this will put it into a more well-behaved state first.
-The driver implements three temperature sensors, five fan rotation speed
+The driver implements three temperature sensors, ten voltage sensors,
-sensors, and ten voltage sensors.
+five fan rotation speed sensors and manual PWM control of each fan.
 Temperatures are measured in degrees Celsius and measurement resolution is 1
 degC for temp1 and 0.5 degC for temp2 and temp3. An alarm is triggered when
 the temperature gets higher than the Overtemperature Shutdown value; it stays
 on until the temperature falls below the Hysteresis value.
-Fan rotation speeds are reported in RPM (rotations per minute). An alarm is
-triggered if the rotation speed has dropped below a programmable limit. Fan
-readings can be divided by a programmable divider (1, 2, 4, 8 for fan 1/2/3
-and 1, 2, 4, 8, 16, 32, 64 or 128 for fan 4/5) to give the readings more
-range or accuracy.
 Voltage sensors (also known as IN sensors) report their values in millivolts.
 An alarm is triggered if the voltage has crossed a programmable minimum
 or maximum limit.
+Fan rotation speeds are reported in RPM (rotations per minute). An alarm is
+triggered if the rotation speed has dropped below a programmable limit. Fan
+readings can be divided by a programmable divider (1, 2, 4, 8, 16,
+32, 64 or 128 for all fans) to give the readings more range or accuracy.
+Each fan controlled is controlled by PWM. The PWM duty cycle can be read and
+set for each fan separately. Valid values range from 0 (stop) to 255 (full).
+PWM 1-3 support Thermal Cruise mode, in which the PWMs are automatically
+regulated to keep respectively temp 1-3 at a certain target temperature.
+See below for the description of the sysfs-interface.
 The w83791d has a global bit used to enable beeping from the speaker when an
 alarm is triggered as well as a bitmask to enable or disable the beep for
 specific alarms. You need both the global beep enable bit and the
 corresponding beep bit to be on for a triggered alarm to sound a beep.
-The sysfs interface to the gloabal enable is via the sysfs beep_enable file.
+The sysfs interface to the global enable is via the sysfs beep_enable file.
 This file is used for both legacy and new code.
 The sysfs interface to the beep bitmask has migrated from the original legacy
@@ -105,6 +111,27 @@ going forward.
 The driver reads the hardware chip values at most once every three seconds.
 User mode code requesting values more often will receive cached values.
+/sys files
+----------
+The sysfs-interface is documented in the 'sysfs-interface' file. Only
+chip-specific options are documented here.
+pwm[1-3]_enable -       this file controls mode of fan/temperature control for
+                        fan 1-3. Fan/PWM 4-5 only support manual mode.
+                            * 1 Manual mode
+                            * 2 Thermal Cruise mode
+                            * 3 Fan Speed Cruise mode (no further support)
+temp[1-3]_target -      defines the target temperature for Thermal Cruise mode.
+                        Unit: millidegree Celsius
+                        RW
+temp[1-3]_tolerance -   temperature tolerance for Thermal Cruise mode.
+                        Specifies an interval around the target temperature
+                        in which the fan speed is not changed.
+                        Unit: millidegree Celsius
+                        RW
 Alarms bitmap vs. beep_mask bitmask
 ------------------------------------
 For legacy code using the alarms and beep_mask files:
@@ -132,7 +159,3 @@ tart2        :  alarms: 0x020000 beep_mask: 0x080000 <== mismatch
 tart3        :  alarms: 0x040000 beep_mask: 0x100000 <== mismatch
 case_open    :  alarms: 0x001000 beep_mask: 0x001000
 global_enable:  alarms: -------- beep_mask: 0x800000 (modified via beep_enable)
-W83791D TODO:
---------------
-Provide a patch for smart-fan control (still need appropriate motherboard/fans)
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index c31e0291e167..81c0c59a60ea 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -13,8 +13,9 @@ Supported adapters:
  * Intel 631xESB/632xESB (ESB2)
  * Intel 82801H (ICH8)
  * Intel 82801I (ICH9)
-  * Intel Tolapai
+  * Intel EP80579 (Tolapai)
-  * Intel ICH10
+  * Intel 82801JI (ICH10)
+  * Intel PCH
   Datasheets: Publicly available at the Intel website
 Authors: 
@@ -32,7 +33,7 @@ Description
 -----------
 The ICH (properly known as the 82801AA), ICH0 (82801AB), ICH2 (82801BA),
-ICH3 (82801CA/CAM) and later devices are Intel chips that are a part of
+ICH3 (82801CA/CAM) and later devices (PCH) are Intel chips that are a part of
 Intel's '810' chipset for Celeron-based PCs, '810E' chipset for
 Pentium-based PCs, '815E' chipset, and others.
diff --git a/Documentation/i2c/busses/i2c-viapro b/Documentation/i2c/busses/i2c-viapro
index 1405fb69984c..22efedf60c87 100644
--- a/Documentation/i2c/busses/i2c-viapro
+++ b/Documentation/i2c/busses/i2c-viapro
@@ -16,6 +16,9 @@ Supported adapters:
  * VIA Technologies, Inc. CX700
    Datasheet: available on request and under NDA from VIA
+  * VIA Technologies, Inc. VX800/VX820
+    Datasheet: available on http://linux.via.com.tw
 Authors:
        Kyösti Mälkki <kmalkki@cc.hut.fi>,
        Mark D. Studebaker <mdsxyz123@yahoo.com>,
@@ -49,6 +52,7 @@ Your lspci -n listing must show one of these :
 device 1106:3372   (VT8237S)
 device 1106:3287   (VT8251)
 device 1106:8324   (CX700)
+ device 1106:8353   (VX800/VX820)
 If none of these show up, you should look in the BIOS for settings like
 enable ACPI / SMBus or even USB.
@@ -57,5 +61,5 @@ Except for the oldest chips (VT82C596A/B, VT82C686A and most probably
 VT8231), this driver supports I2C block transactions. Such transactions
 are mainly useful to read from and write to EEPROMs.
-The CX700 additionally appears to support SMBus PEC, although this driver
+The CX700/VX800/VX820 additionally appears to support SMBus PEC, although
-doesn't implement it yet.
+this driver doesn't implement it yet.
diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface
index 9dd79123ddd9..3e742ba25536 100644
--- a/Documentation/i2c/dev-interface
+++ b/Documentation/i2c/dev-interface
@@ -4,6 +4,10 @@ the /dev interface. You need to load module i2c-dev for this.
 Each registered i2c adapter gets a number, counting from 0. You can
 examine /sys/class/i2c-dev/ to see what number corresponds to which adapter.
+Alternatively, you can run "i2cdetect -l" to obtain a formated list of all
+i2c adapters present on your system at a given time. i2cdetect is part of
+the i2c-tools package.
 I2C device files are character device files with major device number 89
 and a minor device number corresponding to the number assigned as 
 explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ..., 
@@ -17,30 +21,34 @@ So let's say you want to access an i2c adapter from a C program. The
 first thing to do is "#include <linux/i2c-dev.h>". Please note that
 there are two files named "i2c-dev.h" out there, one is distributed
 with the Linux kernel and is meant to be included from kernel
-driver code, the other one is distributed with lm_sensors and is
+driver code, the other one is distributed with i2c-tools and is
 meant to be included from user-space programs. You obviously want
 the second one here.
 Now, you have to decide which adapter you want to access. You should
-inspect /sys/class/i2c-dev/ to decide this. Adapter numbers are assigned
+inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this.
-somewhat dynamically, so you can not even assume /dev/i2c-0 is the
+Adapter numbers are assigned somewhat dynamically, so you can not
-first adapter.
+assume much about them. They can even change from one boot to the next.
 Next thing, open the device file, as follows:
  int file;
  int adapter_nr = 2; /* probably dynamically determined */
  char filename[20];
  
-  sprintf(filename,"/dev/i2c-%d",adapter_nr);
+  snprintf(filename, 19, "/dev/i2c-%d", adapter_nr);
-  if ((file = open(filename,O_RDWR)) < 0) {
+  file = open(filename, O_RDWR);
+  if (file < 0) {
    /* ERROR HANDLING; you can check errno to see what went wrong */
    exit(1);
  }
 When you have opened the device, you must specify with what device
 address you want to communicate:
  int addr = 0x40; /* The I2C address */
-  if (ioctl(file,I2C_SLAVE,addr) < 0) {
+  if (ioctl(file, I2C_SLAVE, addr) < 0) {
    /* ERROR HANDLING; you can check errno to see what went wrong */
    exit(1);
  }
@@ -48,31 +56,41 @@ address you want to communicate:
 Well, you are all set up now. You can now use SMBus commands or plain
 I2C to communicate with your device. SMBus commands are preferred if
 the device supports them. Both are illustrated below.
  __u8 register = 0x10; /* Device register to access */
  __s32 res;
  char buf[10];
  /* Using SMBus commands */
-  res = i2c_smbus_read_word_data(file,register);
+  res = i2c_smbus_read_word_data(file, register);
  if (res < 0) {
    /* ERROR HANDLING: i2c transaction failed */
  } else {
    /* res contains the read word */
  }
  /* Using I2C Write, equivalent of 
-           i2c_smbus_write_word_data(file,register,0x6543) */
+     i2c_smbus_write_word_data(file, register, 0x6543) */
  buf[0] = register;
  buf[1] = 0x43;
  buf[2] = 0x65;
-  if ( write(file,buf,3) != 3) {
+  if (write(file, buf, 3) ! =3) {
    /* ERROR HANDLING: i2c transaction failed */
  }
  /* Using I2C Read, equivalent of i2c_smbus_read_byte(file) */
-  if (read(file,buf,1) != 1) {
+  if (read(file, buf, 1) != 1) {
    /* ERROR HANDLING: i2c transaction failed */
  } else {
    /* buf[0] contains the read byte */
  }
+Note that only a subset of the I2C and SMBus protocols can be achieved by
+the means of read() and write() calls. In particular, so-called combined
+transactions (mixing read and write messages in the same transaction)
+aren't supported. For this reason, this interface is almost never used by
+user-space programs.
 IMPORTANT: because of the use of inline functions, you *have* to use
 '-O' or some variation when you compile your program!
@@ -80,31 +98,29 @@ IMPORTANT: because of the use of inline functions, you *have* to use
 Full interface description
 ==========================
-The following IOCTLs are defined and fully supported 
+The following IOCTLs are defined:
-(see also i2c-dev.h):
-ioctl(file,I2C_SLAVE,long addr)
+ioctl(file, I2C_SLAVE, long addr)
  Change slave address. The address is passed in the 7 lower bits of the
  argument (except for 10 bit addresses, passed in the 10 lower bits in this
  case).
-ioctl(file,I2C_TENBIT,long select)
+ioctl(file, I2C_TENBIT, long select)
  Selects ten bit addresses if select not equals 0, selects normal 7 bit
  addresses if select equals 0. Default 0.  This request is only valid
  if the adapter has I2C_FUNC_10BIT_ADDR.
-ioctl(file,I2C_PEC,long select)
+ioctl(file, I2C_PEC, long select)
  Selects SMBus PEC (packet error checking) generation and verification
  if select not equals 0, disables if select equals 0. Default 0.
  Used only for SMBus transactions.  This request only has an effect if the
  the adapter has I2C_FUNC_SMBUS_PEC; it is still safe if not, it just
  doesn't have any effect.
-ioctl(file,I2C_FUNCS,unsigned long *funcs)
+ioctl(file, I2C_FUNCS, unsigned long *funcs)
  Gets the adapter functionality and puts it in *funcs.
-ioctl(file,I2C_RDWR,struct i2c_rdwr_ioctl_data *msgset)
+ioctl(file, I2C_RDWR, struct i2c_rdwr_ioctl_data *msgset)
  Do combined read/write transaction without stop in between.
  Only valid if the adapter has I2C_FUNC_I2C.  The argument is
  a pointer to a
@@ -120,10 +136,9 @@ ioctl(file,I2C_RDWR,struct i2c_rdwr_ioctl_data *msgset)
  The slave address and whether to use ten bit address mode has to be
  set in each message, overriding the values set with the above ioctl's.
+ioctl(file, I2C_SMBUS, struct i2c_smbus_ioctl_data *args)
-Other values are NOT supported at this moment, except for I2C_SMBUS,
+  Not meant to be called  directly; instead, use the access functions
-which you should never directly call; instead, use the access functions
+  below.
-below.
 You can do plain i2c transactions by using read(2) and write(2) calls.
 You do not need to pass the address byte; instead, set it through
@@ -148,7 +163,52 @@ what happened. The 'write' transactions return 0 on success; the
 returns the number of values read. The block buffers need not be longer
 than 32 bytes.
-The above functions are all macros, that resolve to calls to the
+The above functions are all inline functions, that resolve to calls to
-i2c_smbus_access function, that on its turn calls a specific ioctl
+the i2c_smbus_access function, that on its turn calls a specific ioctl
 with the data in a specific format. Read the source code if you
 want to know what happens behind the screens.
+Implementation details
+======================
+For the interested, here's the code flow which happens inside the kernel
+when you use the /dev interface to I2C:
+1* Your program opens /dev/i2c-N and calls ioctl() on it, as described in
+section "C example" above.
+2* These open() and ioctl() calls are handled by the i2c-dev kernel
+driver: see i2c-dev.c:i2cdev_open() and i2c-dev.c:i2cdev_ioctl(),
+respectively. You can think of i2c-dev as a generic I2C chip driver
+that can be programmed from user-space.
+3* Some ioctl() calls are for administrative tasks and are handled by
+i2c-dev directly. Examples include I2C_SLAVE (set the address of the
+device you want to access) and I2C_PEC (enable or disable SMBus error
+checking on future transactions.)
+4* Other ioctl() calls are converted to in-kernel function calls by
+i2c-dev. Examples include I2C_FUNCS, which queries the I2C adapter
+functionality using i2c.h:i2c_get_functionality(), and I2C_SMBUS, which
+performs an SMBus transaction using i2c-core.c:i2c_smbus_xfer().
+The i2c-dev driver is responsible for checking all the parameters that
+come from user-space for validity. After this point, there is no
+difference between these calls that came from user-space through i2c-dev
+and calls that would have been performed by kernel I2C chip drivers
+directly. This means that I2C bus drivers don't need to implement
+anything special to support access from user-space.
+5* These i2c-core.c/i2c.h functions are wrappers to the actual
+implementation of your I2C bus driver. Each adapter must declare
+callback functions implementing these standard calls.
+i2c.h:i2c_get_functionality() calls i2c_adapter.algo->functionality(),
+while i2c-core.c:i2c_smbus_xfer() calls either
+adapter.algo->smbus_xfer() if it is implemented, or if not,
+i2c-core.c:i2c_smbus_xfer_emulated() which in turn calls
+i2c_adapter.algo->master_xfer().
+After your I2C bus driver has processed these requests, execution runs
+up the call chain, with almost no processing done, except by i2c-dev to
+package the returned data, if any, in suitable format for the ioctl.
diff --git a/Documentation/i2c/porting-clients b/Documentation/i2c/porting-clients
deleted file mode 100644
index 7bf82c08f6ca..000000000000
--- a/Documentation/i2c/porting-clients
+++ /dev/null
@@ -1,160 +0,0 @@
-Revision 7, 2007-04-19
-Jean Delvare <khali@linux-fr.org>
-Greg KH <greg@kroah.com>
-This is a guide on how to convert I2C chip drivers from Linux 2.4 to
-Linux 2.6. I have been using existing drivers (lm75, lm78) as examples.
-Then I converted a driver myself (lm83) and updated this document.
-Note that this guide is strongly oriented towards hardware monitoring
-drivers. Many points are still valid for other type of drivers, but
-others may be irrelevant.
-There are two sets of points below. The first set concerns technical
-changes. The second set concerns coding policy. Both are mandatory.
-Although reading this guide will help you porting drivers, I suggest
-you keep an eye on an already ported driver while porting your own
-driver. This will help you a lot understanding what this guide
-exactly means. Choose the chip driver that is the more similar to
-yours for best results.
-Technical changes:
-* [Driver type] Any driver that was relying on i2c-isa has to be
-  converted to a proper isa, platform or pci driver. This is not
-  covered by this guide.
-* [Includes] Get rid of "version.h" and <linux/i2c-proc.h>.
-  Includes typically look like that:
-  #include <linux/module.h>
-  #include <linux/init.h>
-  #include <linux/slab.h>
-  #include <linux/jiffies.h>
-  #include <linux/i2c.h>
-  #include <linux/hwmon.h>      /* for hardware monitoring drivers */
-  #include <linux/hwmon-sysfs.h>
-  #include <linux/hwmon-vid.h>  /* if you need VRM support */
-  #include <linux/err.h>        /* for class registration */
-  Please respect this inclusion order. Some extra headers may be
-  required for a given driver (e.g. "lm75.h").
-* [Addresses] SENSORS_I2C_END becomes I2C_CLIENT_END, ISA addresses
-  are no more handled by the i2c core. Address ranges are no more
-  supported either, define each individual address separately.
-  SENSORS_INSMOD_<n> becomes I2C_CLIENT_INSMOD_<n>.
-* [Client data] Get rid of sysctl_id. Try using standard names for
-  register values (for example, temp_os becomes temp_max). You're
-  still relatively free here, but you *have* to follow the standard
-  names for sysfs files (see the Sysctl section below).
-* [Function prototypes] The detect functions loses its flags
-  parameter. Sysctl (e.g. lm75_temp) and miscellaneous functions
-  are off the list of prototypes. This usually leaves five
-  prototypes:
-  static int lm75_attach_adapter(struct i2c_adapter *adapter);
-  static int lm75_detect(struct i2c_adapter *adapter, int address,
-      int kind);
-  static void lm75_init_client(struct i2c_client *client);
-  static int lm75_detach_client(struct i2c_client *client);
-  static struct lm75_data lm75_update_device(struct device *dev);
-* [Sysctl] All sysctl stuff is of course gone (defines, ctl_table
-  and functions). Instead, you have to define show and set functions for
-  each sysfs file. Only define set for writable values. Take a look at an
-  existing 2.6 driver for details (it87 for example). Don't forget
-  to define the attributes for each file (this is that step that
-  links callback functions). Use the file names specified in
-  Documentation/hwmon/sysfs-interface for the individual files. Also
-  convert the units these files read and write to the specified ones.
-  If you need to add a new type of file, please discuss it on the
-  sensors mailing list <lm-sensors@lm-sensors.org> by providing a
-  patch to the Documentation/hwmon/sysfs-interface file.
-* [Attach] The attach function should make sure that the adapter's
-  class has I2C_CLASS_HWMON (or whatever class is suitable for your
-  driver), using the following construct:
-  if (!(adapter->class & I2C_CLASS_HWMON))
-          return 0;
-  Call i2c_probe() instead of i2c_detect().
-* [Detect] As mentioned earlier, the flags parameter is gone.
-  The type_name and client_name strings are replaced by a single
-  name string, which will be filled with a lowercase, short string.
-  The labels used for error paths are reduced to the number needed.
-  It is advised that the labels are given descriptive names such as
-  exit and exit_free. Don't forget to properly set err before
-  jumping to error labels. By the way, labels should be left-aligned.
-  Use kzalloc instead of kmalloc.
-  Use i2c_set_clientdata to set the client data (as opposed to
-  a direct access to client->data).
-  Use strlcpy instead of strcpy or snprintf to copy the client name.
-  Replace the sysctl directory registration by calls to
-  device_create_file. Move the driver initialization before any
-  sysfs file creation.
-  Register the client with the hwmon class (using hwmon_device_register)
-  if applicable.
-  Drop client->id.
-  Drop any 24RF08 corruption prevention you find, as this is now done
-  at the i2c-core level, and doing it twice voids it.
-  Don't add I2C_CLIENT_ALLOW_USE to client->flags, it's the default now.
-* [Init] Limits must not be set by the driver (can be done later in
-  user-space). Chip should not be reset default (although a module
-  parameter may be used to force it), and initialization should be
-  limited to the strictly necessary steps.
-* [Detach] Remove the call to i2c_deregister_entry. Do not log an
-  error message if i2c_detach_client fails, as i2c-core will now do
-  it for you.
-  Unregister from the hwmon class if applicable.
-* [Update] The function prototype changed, it is now
-  passed a device structure, which you have to convert to a client
-  using to_i2c_client(dev). The update function should return a
-  pointer to the client data.
-  Don't access client->data directly, use i2c_get_clientdata(client)
-  instead.
-  Use time_after() instead of direct jiffies comparison.
-* [Interface] Make sure there is a MODULE_LICENSE() line, at the bottom
-  of the file (after MODULE_AUTHOR() and MODULE_DESCRIPTION(), in this
-  order).
-* [Driver] The flags field of the i2c_driver structure is gone.
-  I2C_DF_NOTIFY is now the default behavior.
-  The i2c_driver structure has a driver member, which is itself a
-  structure, those name member should be initialized to a driver name
-  string. i2c_driver itself has no name member anymore.
-* [Driver model] Instead of shutdown or reboot notifiers, provide a
-  shutdown() method in your driver.
-* [Power management] Use the driver model suspend() and resume()
-  callbacks instead of the obsolete pm_register() calls.
-Coding policy:
-* [Copyright] Use (C), not (c), for copyright.
-* [Debug/log] Get rid of #ifdef DEBUG/#endif constructs whenever you
-  can. Calls to printk for debugging purposes are replaced by calls to
-  dev_dbg where possible, else to pr_debug. Here is an example of how
-  to call it (taken from lm75_detect):
-  dev_dbg(&client->dev, "Starting lm75 update\n");
-  Replace other printk calls with the dev_info, dev_err or dev_warn
-  function, as appropriate.
-* [Constants] Constants defines (registers, conversions) should be
-  aligned. This greatly improves readability.
-  Alignments are achieved by the means of tabs, not spaces. Remember
-  that tabs are set to 8 in the Linux kernel code.
-* [Layout] Avoid extra empty lines between comments and what they
-  comment. Respect the coding style (see Documentation/CodingStyle),
-  in particular when it comes to placing curly braces.
-* [Comments] Make sure that no comment refers to a file that isn't
-  part of the Linux source tree (typically doc/chips/<chip name>),
-  and that remaining comments still match the code. Merging comment
-  lines when possible is encouraged.
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 24bfb65da17d..9df47441f0e7 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -109,8 +109,8 @@ specified through the Comm byte.
 S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A] P
-SMBus Process Call
+SMBus Process Call:  i2c_smbus_process_call()
-==================
+=============================================
 This command selects a device register (through the Comm byte), sends
 16 bits of data to it, and reads 16 bits of data in return.
diff --git a/Documentation/i2c/upgrading-clients b/Documentation/i2c/upgrading-clients
new file mode 100644
index 000000000000..9a45f9bb6a25
--- /dev/null
+++ b/Documentation/i2c/upgrading-clients
@@ -0,0 +1,281 @@
+Upgrading I2C Drivers to the new 2.6 Driver Model
+=================================================
+Ben Dooks <ben-linux@fluff.org>
+Introduction
+------------
+This guide outlines how to alter existing Linux 2.6 client drivers from
+the old to the new new binding methods.
+Example old-style driver
+------------------------
+struct example_state {
+        struct i2c_client       client;
+        ....
+};
+static struct i2c_driver example_driver;
+static unsigned short ignore[] = { I2C_CLIENT_END };
+static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END };
+I2C_CLIENT_INSMOD;
+static int example_attach(struct i2c_adapter *adap, int addr, int kind)
+{
+        struct example_state *state;
+        struct device *dev = &adap->dev;  /* to use for dev_ reports */
+        int ret;
+        state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+        if (state == NULL) {
+                dev_err(dev, "failed to create our state\n");
+                return -ENOMEM;
+        }
+        example->client.addr    = addr;
+        example->client.flags   = 0;
+        example->client.adapter = adap;
+        i2c_set_clientdata(&state->i2c_client, state);
+        strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE);
+        ret = i2c_attach_client(&state->i2c_client);
+        if (ret < 0) {
+                dev_err(dev, "failed to attach client\n");
+                kfree(state);
+                return ret;
+        }
+        dev = &state->i2c_client.dev;
+        /* rest of the initialisation goes here. */
+        dev_info(dev, "example client created\n");
+        return 0;
+}
+static int __devexit example_detach(struct i2c_client *client)
+{
+        struct example_state *state = i2c_get_clientdata(client);
+        i2c_detach_client(client);
+        kfree(state);
+        return 0;
+}
+static int example_attach_adapter(struct i2c_adapter *adap)
+{
+        return i2c_probe(adap, &addr_data, example_attach);
+}
+static struct i2c_driver example_driver = {
+        .driver         = {
+                .owner          = THIS_MODULE,
+                .name           = "example",
+        },
+        .attach_adapter = example_attach_adapter,
+        .detach_client  = __devexit_p(example_detach),
+        .suspend        = example_suspend,
+        .resume         = example_resume,
+};
+Updating the client
+-------------------
+The new style binding model will check against a list of supported
+devices and their associated address supplied by the code registering
+the busses. This means that the driver .attach_adapter and
+.detach_adapter methods can be removed, along with the addr_data,
+as follows:
+- static struct i2c_driver example_driver;
+- static unsigned short ignore[] = { I2C_CLIENT_END };
+- static unsigned short normal_addr[] = { OUR_ADDR, I2C_CLIENT_END };
+- I2C_CLIENT_INSMOD;
+- static int example_attach_adapter(struct i2c_adapter *adap)
+- {
+-       return i2c_probe(adap, &addr_data, example_attach);
+- }
+ static struct i2c_driver example_driver = {
+-       .attach_adapter = example_attach_adapter,
+-       .detach_client  = __devexit_p(example_detach),
+ }
+Add the probe and remove methods to the i2c_driver, as so:
+ static struct i2c_driver example_driver = {
+       .probe          = example_probe,
+       .remove         = __devexit_p(example_remove),
+ }
+Change the example_attach method to accept the new parameters
+which include the i2c_client that it will be working with:
+- static int example_attach(struct i2c_adapter *adap, int addr, int kind)
+ static int example_probe(struct i2c_client *client,
+                          const struct i2c_device_id *id)
+Change the name of example_attach to example_probe to align it with the
+i2c_driver entry names. The rest of the probe routine will now need to be
+changed as the i2c_client has already been setup for use.
+The necessary client fields have already been setup before
+the probe function is called, so the following client setup
+can be removed:
+-       example->client.addr    = addr;
+-       example->client.flags   = 0;
+-       example->client.adapter = adap;
+-
+-       strlcpy(client->i2c_client.name, "example", I2C_NAME_SIZE);
+The i2c_set_clientdata is now:
+-       i2c_set_clientdata(&state->client, state);
+       i2c_set_clientdata(client, state);
+The call to i2c_attach_client is no longer needed, if the probe
+routine exits successfully, then the driver will be automatically
+attached by the core. Change the probe routine as so:
+-       ret = i2c_attach_client(&state->i2c_client);
+-       if (ret < 0) {
+-               dev_err(dev, "failed to attach client\n");
+-               kfree(state);
+-               return ret;
+-       }
+Remove the storage of 'struct i2c_client' from the 'struct example_state'
+as we are provided with the i2c_client in our example_probe. Instead we
+store a pointer to it for when it is needed.
+struct example_state {
+-       struct i2c_client       client;
+       struct i2c_client       *client;
+the new i2c client as so:
+-       struct device *dev = &adap->dev;  /* to use for dev_ reports */
+       struct device *dev = &i2c_client->dev;  /* to use for dev_ reports */
+And remove the change after our client is attached, as the driver no
+longer needs to register a new client structure with the core:
+-       dev = &state->i2c_client.dev;
+In the probe routine, ensure that the new state has the client stored
+in it:
+static int example_probe(struct i2c_client *i2c_client,
+                         const struct i2c_device_id *id)
+{
+        struct example_state *state;
+        struct device *dev = &i2c_client->dev;
+        int ret;
+        state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+        if (state == NULL) {
+                dev_err(dev, "failed to create our state\n");
+                return -ENOMEM;
+        }
+       state->client = i2c_client;
+Update the detach method, by changing the name to _remove and
+to delete the i2c_detach_client call. It is possible that you
+can also remove the ret variable as it is not not needed for
+any of the core functions.
+- static int __devexit example_detach(struct i2c_client *client)
+ static int __devexit example_remove(struct i2c_client *client)
+{
+        struct example_state *state = i2c_get_clientdata(client);
+-       i2c_detach_client(client);
+And finally ensure that we have the correct ID table for the i2c-core
+and other utilities:
+ struct i2c_device_id example_idtable[] = {
+       { "example", 0 },
+       { }
+};
+
+MODULE_DEVICE_TABLE(i2c, example_idtable);
+static struct i2c_driver example_driver = {
+        .driver         = {
+                .owner          = THIS_MODULE,
+                .name           = "example",
+        },
+       .id_table       = example_ids,
+Our driver should now look like this:
+struct example_state {
+        struct i2c_client       *client;
+        ....
+};
+static int example_probe(struct i2c_client *client,
+                         const struct i2c_device_id *id)
+{
+        struct example_state *state;
+        struct device *dev = &client->dev;
+        state = kzalloc(sizeof(struct example_state), GFP_KERNEL);
+        if (state == NULL) {
+                dev_err(dev, "failed to create our state\n");
+                return -ENOMEM;
+        }
+        state->client = client;
+        i2c_set_clientdata(client, state);
+        /* rest of the initialisation goes here. */
+        dev_info(dev, "example client created\n");
+        return 0;
+}
+static int __devexit example_remove(struct i2c_client *client)
+{
+        struct example_state *state = i2c_get_clientdata(client);
+        kfree(state);
+        return 0;
+}
+static struct i2c_device_id example_idtable[] = {
+        { "example", 0 },
+        { }
+};
+MODULE_DEVICE_TABLE(i2c, example_idtable);
+static struct i2c_driver example_driver = {
+        .driver         = {
+                .owner          = THIS_MODULE,
+                .name           = "example",
+        },
+        .id_table       = example_idtable,
+        .probe          = example_probe,
+        .remove         = __devexit_p(example_remove),
+        .suspend        = example_suspend,
+        .resume         = example_resume,
+};
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 6b61b3a2e90b..6b9af7d479c2 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -10,23 +10,21 @@ General remarks
 ===============
 Try to keep the kernel namespace as clean as possible. The best way to
-do this is to use a unique prefix for all global symbols. This is 
+do this is to use a unique prefix for all global symbols. This is
 especially important for exported symbols, but it is a good idea to do
 it for non-exported symbols too. We will use the prefix `foo_' in this
-tutorial, and `FOO_' for preprocessor variables.
+tutorial.
 The driver structure
 ====================
 Usually, you will implement a single driver structure, and instantiate
-all clients from it. Remember, a driver structure contains general access 
+all clients from it. Remember, a driver structure contains general access
 routines, and should be zero-initialized except for fields with data you
 provide.  A client structure holds device-specific information like the
 driver model device node, and its I2C address.
-/* iff driver uses driver model ("new style") binding model: */
 static struct i2c_device_id foo_idtable[] = {
        { "foo", my_id_for_foo },
        { "bar", my_id_for_bar },
@@ -40,7 +38,6 @@ static struct i2c_driver foo_driver = {
                .name   = "foo",
        },
-        /* iff driver uses driver model ("new style") binding model: */
        .id_table       = foo_ids,
        .probe          = foo_probe,
        .remove         = foo_remove,
@@ -49,24 +46,19 @@ static struct i2c_driver foo_driver = {
        .detect         = foo_detect,
        .address_data   = &addr_data,
-        /* else, driver uses "legacy" binding model: */
-        .attach_adapter = foo_attach_adapter,
-        .detach_client  = foo_detach_client,
-        /* these may be used regardless of the driver binding model */
        .shutdown       = foo_shutdown, /* optional */
        .suspend        = foo_suspend,  /* optional */
        .resume         = foo_resume,   /* optional */
-        .command        = foo_command,  /* optional */
+        .command        = foo_command,  /* optional, deprecated */
 }
- 
 The name field is the driver name, and must not contain spaces.  It
 should match the module name (if the driver can be compiled as a module),
 although you can use MODULE_ALIAS (passing "foo" in this example) to add
 another name for the module.  If the driver name doesn't match the module
 name, the module won't be automatically loaded (hotplug/coldplug).
-All other fields are for call-back functions which will be explained 
+All other fields are for call-back functions which will be explained
 below.
@@ -74,34 +66,13 @@ Extra client data
 =================
 Each client structure has a special `data' field that can point to any
-structure at all.  You should use this to keep device-specific data,
+structure at all.  You should use this to keep device-specific data.
-especially in drivers that handle multiple I2C or SMBUS devices.  You
-do not always need this, but especially for `sensors' drivers, it can
-be very useful.
        /* store the value */
        void i2c_set_clientdata(struct i2c_client *client, void *data);
        /* retrieve the value */
-        void *i2c_get_clientdata(struct i2c_client *client);
+        void *i2c_get_clientdata(const struct i2c_client *client);
-An example structure is below.
-  struct foo_data {
-    struct i2c_client client;
-    enum chips type;       /* To keep the chips type for `sensors' drivers. */
-   
-    /* Because the i2c bus is slow, it is often useful to cache the read
-       information of a chip for some time (for example, 1 or 2 seconds).
-       It depends of course on the device whether this is really worthwhile
-       or even sensible. */
-    struct mutex update_lock;     /* When we are reading lots of information,
-                                     another process should not update the
-                                     below information */
-    char valid;                   /* != 0 if the following fields are valid. */
-    unsigned long last_updated;   /* In jiffies */
-    /* Add the read information here too */
-  };
 Accessing the client
@@ -109,11 +80,9 @@ Accessing the client
 Let's say we have a valid client structure. At some time, we will need
 to gather information from the client, or write new information to the
-client. How we will export this information to user-space is less 
+client.
-important at this moment (perhaps we do not need to do this at all for
-some obscure clients). But we need generic reading and writing routines.
-I have found it useful to define foo_read and foo_write function for this.
+I have found it useful to define foo_read and foo_write functions for this.
 For some cases, it will be easier to call the i2c functions directly,
 but many chips have some kind of register-value idea that can easily
 be encapsulated.
@@ -121,33 +90,33 @@ be encapsulated.
 The below functions are simple examples, and should not be copied
 literally.
-  int foo_read_value(struct i2c_client *client, u8 reg)
+int foo_read_value(struct i2c_client *client, u8 reg)
-  {
+{
-    if (reg < 0x10) /* byte-sized register */
+        if (reg < 0x10) /* byte-sized register */
-      return i2c_smbus_read_byte_data(client,reg);
+                return i2c_smbus_read_byte_data(client, reg);
-    else /* word-sized register */
+        else            /* word-sized register */
-      return i2c_smbus_read_word_data(client,reg);
+                return i2c_smbus_read_word_data(client, reg);
-  }
+}
-  int foo_write_value(struct i2c_client *client, u8 reg, u16 value)
+int foo_write_value(struct i2c_client *client, u8 reg, u16 value)
-  {
+{
-    if (reg == 0x10) /* Impossible to write - driver error! */ {
+        if (reg == 0x10)        /* Impossible to write - driver error! */
-      return -1;
+                return -EINVAL;
-    else if (reg < 0x10) /* byte-sized register */
+        else if (reg < 0x10)    /* byte-sized register */
-      return i2c_smbus_write_byte_data(client,reg,value);
+                return i2c_smbus_write_byte_data(client, reg, value);
-    else /* word-sized register */
+        else                    /* word-sized register */
-      return i2c_smbus_write_word_data(client,reg,value);
+                return i2c_smbus_write_word_data(client, reg, value);
-  }
+}
 Probing and attaching
 =====================
 The Linux I2C stack was originally written to support access to hardware
-monitoring chips on PC motherboards, and thus it embeds some assumptions
+monitoring chips on PC motherboards, and thus used to embed some assumptions
-that are more appropriate to SMBus (and PCs) than to I2C.  One of these
+that were more appropriate to SMBus (and PCs) than to I2C.  One of these
-assumptions is that most adapters and devices drivers support the SMBUS_QUICK
+assumptions was that most adapters and devices drivers support the SMBUS_QUICK
-protocol to probe device presence.  Another is that devices and their drivers
+protocol to probe device presence.  Another was that devices and their drivers
 can be sufficiently configured using only such probe primitives.
 As Linux and its I2C stack became more widely used in embedded systems
@@ -164,6 +133,9 @@ since the "legacy" model requires drivers to create "i2c_client" device
 objects after SMBus style probing, while the Linux driver model expects
 drivers to be given such device objects in their probe() routines.
+The legacy model is deprecated now and will soon be removed, so we no
+longer document it here.
 Standard Driver Model Binding ("New Style")
 -------------------------------------------
@@ -193,8 +165,8 @@ matches the device's name. It is passed the entry that was matched so
 the driver knows which one in the table matched.
-Device Creation (Standard driver model)
+Device Creation
---------------------------------------
+---------------
 If you know for a fact that an I2C device is connected to a given I2C bus,
 you can instantiate that device by simply filling an i2c_board_info
@@ -221,8 +193,8 @@ in the I2C bus driver. You may want to save the returned i2c_client
 reference for later use.
-Device Detection (Standard driver model)
+Device Detection
----------------------------------------
+----------------
 Sometimes you do not know in advance which I2C devices are connected to
 a given I2C bus.  This is for example the case of hardware monitoring
@@ -246,8 +218,8 @@ otherwise misdetections are likely to occur and things can get wrong
 quickly.
-Device Deletion (Standard driver model)
+Device Deletion
---------------------------------------
+---------------
 Each I2C device which has been created using i2c_new_device() or
 i2c_new_probed_device() can be unregistered by calling
@@ -256,264 +228,37 @@ called automatically before the underlying I2C bus itself is removed, as a
 device can't survive its parent in the device driver model.
-Legacy Driver Binding Model
+Initializing the driver
---------------------------
+=======================
+When the kernel is booted, or when your foo driver module is inserted,
+you have to do some initializing. Fortunately, just registering the
+driver module is usually enough.
-Most i2c devices can be present on several i2c addresses; for some this
+static int __init foo_init(void)
-is determined in hardware (by soldering some chip pins to Vcc or Ground),
+{
-for others this can be changed in software (by writing to specific client
+        return i2c_add_driver(&foo_driver);
-registers). Some devices are usually on a specific address, but not always;
+}
-and some are even more tricky. So you will probably need to scan several
-i2c addresses for your clients, and do some sort of detection to see
+static void __exit foo_cleanup(void)
-whether it is actually a device supported by your driver.
+{
+        i2c_del_driver(&foo_driver);
+}
+/* Substitute your own name and email address */
+MODULE_AUTHOR("Frodo Looijaard <frodol@dds.nl>"
+MODULE_DESCRIPTION("Driver for Barf Inc. Foo I2C devices");
-To give the user a maximum of possibilities, some default module parameters
+/* a few non-GPL license types are also allowed */
-are defined to help determine what addresses are scanned. Several macros
+MODULE_LICENSE("GPL");
-are defined in i2c.h to help you support them, as well as a generic
-detection algorithm.
+module_init(foo_init);
+module_exit(foo_cleanup);
-You do not have to use this parameter interface; but don't try to use
-function i2c_probe() if you don't.
+Note that some functions are marked by `__init'.  These functions can
+be removed after kernel booting (or module loading) is completed.
+Likewise, functions marked by `__exit' are dropped by the compiler when
-Probing classes (Legacy model)
+the code is built into the kernel, as they would never be called.
------------------------------
-All parameters are given as lists of unsigned 16-bit integers. Lists are
-terminated by I2C_CLIENT_END.
-The following lists are used internally:
-  normal_i2c: filled in by the module writer. 
-     A list of I2C addresses which should normally be examined.
-   probe: insmod parameter. 
-     A list of pairs. The first value is a bus number (-1 for any I2C bus), 
-     the second is the address. These addresses are also probed, as if they 
-     were in the 'normal' list.
-   ignore: insmod parameter.
-     A list of pairs. The first value is a bus number (-1 for any I2C bus), 
-     the second is the I2C address. These addresses are never probed. 
-     This parameter overrules the 'normal_i2c' list only.
-   force: insmod parameter. 
-     A list of pairs. The first value is a bus number (-1 for any I2C bus),
-     the second is the I2C address. A device is blindly assumed to be on
-     the given address, no probing is done. 
-Additionally, kind-specific force lists may optionally be defined if
-the driver supports several chip kinds. They are grouped in a
-NULL-terminated list of pointers named forces, those first element if the
-generic force list mentioned above. Each additional list correspond to an
-insmod parameter of the form force_<kind>.
-Fortunately, as a module writer, you just have to define the `normal_i2c' 
-parameter. The complete declaration could look like this:
-  /* Scan 0x4c to 0x4f */
-  static const unsigned short normal_i2c[] = { 0x4c, 0x4d, 0x4e, 0x4f,
-                                               I2C_CLIENT_END };
-  /* Magic definition of all other variables and things */
-  I2C_CLIENT_INSMOD;
-  /* Or, if your driver supports, say, 2 kind of devices: */
-  I2C_CLIENT_INSMOD_2(foo, bar);
-If you use the multi-kind form, an enum will be defined for you:
-  enum chips { any_chip, foo, bar, ... }
-You can then (and certainly should) use it in the driver code.
-Note that you *have* to call the defined variable `normal_i2c',
-without any prefix!
-Attaching to an adapter (Legacy model)
--------------------------------------
-Whenever a new adapter is inserted, or for all adapters if the driver is
-being registered, the callback attach_adapter() is called. Now is the
-time to determine what devices are present on the adapter, and to register
-a client for each of them.
-The attach_adapter callback is really easy: we just call the generic
-detection function. This function will scan the bus for us, using the
-information as defined in the lists explained above. If a device is
-detected at a specific address, another callback is called.
-  int foo_attach_adapter(struct i2c_adapter *adapter)
-  {
-    return i2c_probe(adapter,&addr_data,&foo_detect_client);
-  }
-Remember, structure `addr_data' is defined by the macros explained above,
-so you do not have to define it yourself.
-The i2c_probe function will call the foo_detect_client
-function only for those i2c addresses that actually have a device on
-them (unless a `force' parameter was used). In addition, addresses that
-are already in use (by some other registered client) are skipped.
-The detect client function (Legacy model)
-----------------------------------------
-The detect client function is called by i2c_probe. The `kind' parameter
-contains -1 for a probed detection, 0 for a forced detection, or a positive
-number for a forced detection with a chip type forced.
-Returning an error different from -ENODEV in a detect function will cause
-the detection to stop: other addresses and adapters won't be scanned.
-This should only be done on fatal or internal errors, such as a memory
-shortage or i2c_attach_client failing.
-For now, you can ignore the `flags' parameter. It is there for future use.
-  int foo_detect_client(struct i2c_adapter *adapter, int address, 
-                        int kind)
-  {
-    int err = 0;
-    int i;
-    struct i2c_client *client;
-    struct foo_data *data;
-    const char *name = "";
-   
-    /* Let's see whether this adapter can support what we need.
-       Please substitute the things you need here! */
-    if (!i2c_check_functionality(adapter,I2C_FUNC_SMBUS_WORD_DATA |
-                                        I2C_FUNC_SMBUS_WRITE_BYTE))
-       goto ERROR0;
-    /* OK. For now, we presume we have a valid client. We now create the
-       client structure, even though we cannot fill it completely yet.
-       But it allows us to access several i2c functions safely */
-    
-    if (!(data = kzalloc(sizeof(struct foo_data), GFP_KERNEL))) {
-      err = -ENOMEM;
-      goto ERROR0;
-    }
-    client = &data->client;
-    i2c_set_clientdata(client, data);
-    client->addr = address;
-    client->adapter = adapter;
-    client->driver = &foo_driver;
-    /* Now, we do the remaining detection. If no `force' parameter is used. */
-    /* First, the generic detection (if any), that is skipped if any force
-       parameter was used. */
-    if (kind < 0) {
-      /* The below is of course bogus */
-      if (foo_read(client, FOO_REG_GENERIC) != FOO_GENERIC_VALUE)
-         goto ERROR1;
-    }
-    /* Next, specific detection. This is especially important for `sensors'
-       devices. */
-    /* Determine the chip type. Not needed if a `force_CHIPTYPE' parameter
-       was used. */
-    if (kind <= 0) {
-      i = foo_read(client, FOO_REG_CHIPTYPE);
-      if (i == FOO_TYPE_1) 
-        kind = chip1; /* As defined in the enum */
-      else if (i == FOO_TYPE_2)
-        kind = chip2;
-      else {
-        printk("foo: Ignoring 'force' parameter for unknown chip at "
-               "adapter %d, address 0x%02x\n",i2c_adapter_id(adapter),address);
-        goto ERROR1;
-      }
-    }
-    /* Now set the type and chip names */
-    if (kind == chip1) {
-      name = "chip1";
-    } else if (kind == chip2) {
-      name = "chip2";
-    }
-   
-    /* Fill in the remaining client fields. */
-    strlcpy(client->name, name, I2C_NAME_SIZE);
-    data->type = kind;
-    mutex_init(&data->update_lock); /* Only if you use this field */
-    /* Any other initializations in data must be done here too. */
-    /* This function can write default values to the client registers, if
-       needed. */
-    foo_init_client(client);
-    /* Tell the i2c layer a new client has arrived */
-    if ((err = i2c_attach_client(client)))
-      goto ERROR1;
-    return 0;
-    /* OK, this is not exactly good programming practice, usually. But it is
-       very code-efficient in this case. */
-    ERROR1:
-      kfree(data);
-    ERROR0:
-      return err;
-  }
-Removing the client (Legacy model)
-==================================
-The detach_client call back function is called when a client should be
-removed. It may actually fail, but only when panicking. This code is
-much simpler than the attachment code, fortunately!
-  int foo_detach_client(struct i2c_client *client)
-  {
-    int err;
-    /* Try to detach the client from i2c space */
-    if ((err = i2c_detach_client(client)))
-      return err;
-    kfree(i2c_get_clientdata(client));
-    return 0;
-  }
-Initializing the module or kernel
-=================================
-When the kernel is booted, or when your foo driver module is inserted, 
-you have to do some initializing. Fortunately, just attaching (registering)
-the driver module is usually enough.
-  static int __init foo_init(void)
-  {
-    int res;
-    
-    if ((res = i2c_add_driver(&foo_driver))) {
-      printk("foo: Driver registration failed, module not inserted.\n");
-      return res;
-    }
-    return 0;
-  }
-  static void __exit foo_cleanup(void)
-  {
-    i2c_del_driver(&foo_driver);
-  }
-  /* Substitute your own name and email address */
-  MODULE_AUTHOR("Frodo Looijaard <frodol@dds.nl>"
-  MODULE_DESCRIPTION("Driver for Barf Inc. Foo I2C devices");
-  /* a few non-GPL license types are also allowed */
-  MODULE_LICENSE("GPL");
-  module_init(foo_init);
-  module_exit(foo_cleanup);
-Note that some functions are marked by `__init', and some data structures
-by `__initdata'.  These functions and structures can be removed after
-kernel booting (or module loading) is completed.
 Power Management
@@ -548,33 +293,35 @@ Command function
 A generic ioctl-like function call back is supported. You will seldom
 need this, and its use is deprecated anyway, so newer design should not
-use it. Set it to NULL.
+use it.
 Sending and receiving
 =====================
 If you want to communicate with your device, there are several functions
-to do this. You can find all of them in i2c.h.
+to do this. You can find all of them in <linux/i2c.h>.
-If you can choose between plain i2c communication and SMBus level
+If you can choose between plain I2C communication and SMBus level
-communication, please use the last. All adapters understand SMBus level
+communication, please use the latter. All adapters understand SMBus level
-commands, but only some of them understand plain i2c!
+commands, but only some of them understand plain I2C!
-Plain i2c communication
+Plain I2C communication
 -----------------------
-  extern int i2c_master_send(struct i2c_client *,const char* ,int);
+        int i2c_master_send(struct i2c_client *client, const char *buf,
-  extern int i2c_master_recv(struct i2c_client *,char* ,int);
+                            int count);
+        int i2c_master_recv(struct i2c_client *client, char *buf, int count);
 These routines read and write some bytes from/to a client. The client
 contains the i2c address, so you do not have to include it. The second
-parameter contains the bytes the read/write, the third the length of the
+parameter contains the bytes to read/write, the third the number of bytes
-buffer. Returned is the actual number of bytes read/written.
+to read/write (must be less than the length of the buffer.) Returned is
-  
+the actual number of bytes read/written.
-  extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msg,
-                          int num);
+        int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msg,
+                         int num);
 This sends a series of messages. Each message can be a read or write,
 and they can be mixed in any way. The transactions are combined: no
@@ -583,49 +330,45 @@ for each message the client address, the number of bytes of the message
 and the message data itself.
 You can read the file `i2c-protocol' for more information about the
-actual i2c protocol.
+actual I2C protocol.
 SMBus communication
 -------------------
-  extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr, 
+        s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
-                             unsigned short flags,
+                           unsigned short flags, char read_write, u8 command,
-                             char read_write, u8 command, int size,
+                           int size, union i2c_smbus_data *data);
-                             union i2c_smbus_data * data);
+This is the generic SMBus function. All functions below are implemented
-  This is the generic SMBus function. All functions below are implemented
+in terms of it. Never use this function directly!
-  in terms of it. Never use this function directly!
+        s32 i2c_smbus_read_byte(struct i2c_client *client);
+        s32 i2c_smbus_write_byte(struct i2c_client *client, u8 value);
-  extern s32 i2c_smbus_read_byte(struct i2c_client * client);
+        s32 i2c_smbus_read_byte_data(struct i2c_client *client, u8 command);
-  extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value);
+        s32 i2c_smbus_write_byte_data(struct i2c_client *client,
-  extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command);
+                                      u8 command, u8 value);
-  extern s32 i2c_smbus_write_byte_data(struct i2c_client * client,
+        s32 i2c_smbus_read_word_data(struct i2c_client *client, u8 command);
-                                       u8 command, u8 value);
+        s32 i2c_smbus_write_word_data(struct i2c_client *client,
-  extern s32 i2c_smbus_read_word_data(struct i2c_client * client, u8 command);
+                                      u8 command, u16 value);
-  extern s32 i2c_smbus_write_word_data(struct i2c_client * client,
+        s32 i2c_smbus_process_call(struct i2c_client *client,
-                                       u8 command, u16 value);
+                                   u8 command, u16 value);
-  extern s32 i2c_smbus_read_block_data(struct i2c_client * client,
+        s32 i2c_smbus_read_block_data(struct i2c_client *client,
-                                       u8 command, u8 *values);
+                                      u8 command, u8 *values);
-  extern s32 i2c_smbus_write_block_data(struct i2c_client * client,
+        s32 i2c_smbus_write_block_data(struct i2c_client *client,
-                                        u8 command, u8 length,
+                                       u8 command, u8 length, const u8 *values);
-                                        u8 *values);
+        s32 i2c_smbus_read_i2c_block_data(struct i2c_client *client,
-  extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client * client,
+                                          u8 command, u8 length, u8 *values);
-                                           u8 command, u8 length, u8 *values);
+        s32 i2c_smbus_write_i2c_block_data(struct i2c_client *client,
-  extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client,
+                                           u8 command, u8 length,
-                                            u8 command, u8 length,
+                                           const u8 *values);
-                                            u8 *values);
 These ones were removed from i2c-core because they had no users, but could
 be added back later if needed:
-  extern s32 i2c_smbus_write_quick(struct i2c_client * client, u8 value);
+        s32 i2c_smbus_write_quick(struct i2c_client *client, u8 value);
-  extern s32 i2c_smbus_process_call(struct i2c_client * client,
+        s32 i2c_smbus_block_process_call(struct i2c_client *client,
-                                    u8 command, u16 value);
+                                         u8 command, u8 length, u8 *values);
-  extern s32 i2c_smbus_block_process_call(struct i2c_client *client,
-                                          u8 command, u8 length,
-                                          u8 *values)
 All these transactions return a negative errno value on failure. The 'write'
 transactions return 0 on success; the 'read' transactions return the read
@@ -642,7 +385,5 @@ General purpose routines
 Below all general purpose routines are listed, that were not mentioned
 before.
-  /* This call returns a unique low identifier for each registered adapter.
+        /* Return the adapter number for a specific adapter */
-   */
+        int i2c_adapter_id(struct i2c_adapter *adap);
-  extern int i2c_adapter_id(struct i2c_adapter *adap);
diff --git a/Documentation/ia64/Makefile b/Documentation/ia64/Makefile
new file mode 100644
index 000000000000..b75db69ec483
--- /dev/null
+++ b/Documentation/ia64/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := aliasing-test
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt
index bec9d815da33..84f7cb3d5bec 100644
--- a/Documentation/ia64/kvm.txt
+++ b/Documentation/ia64/kvm.txt
@@ -1,7 +1,8 @@
-Currently, kvm module in EXPERIMENTAL stage on IA64. This means that
+Currently, kvm module is in EXPERIMENTAL stage on IA64. This means that
-interfaces are not stable enough to use. So, plase had better don't run
+interfaces are not stable enough to use. So, please don't run critical
-critical applications in virtual machine. We will try our best to make it
+applications in virtual machine.
-strong in future versions!
+We will try our best to improve it in future versions!
                                Guide: How to boot up guests on kvm/ia64
 This guide is to describe how to enable kvm support for IA-64 systems.
@@ -50,9 +51,9 @@ Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qe
                /usr/local/bin/qemu-system-ia64 -smp xx -m 512 -hda $your_image
                (xx is the number of virtual processors for the guest, now the maximum value is 4)
-5. Known possibile issue on some platforms with old Firmware.
+5. Known possible issue on some platforms with old Firmware.
-If meet strange host crashe issues, try to solve it through either of the following ways:
+In the event of strange host crash issues, try to solve it through either of the following ways:
 (1): Upgrade your Firmware to the latest one.
@@ -65,8 +66,8 @@ index 0b53344..f02b0f7 100644
        mov ar.pfs = loc1
        mov rp = loc0
        ;;
-       srlz.d                          // seralize restoration of psr.l
+-       srlz.d                          // serialize restoration of psr.l
-+       srlz.i                  // seralize restoration of psr.l
+       srlz.i                  // serialize restoration of psr.l
 +       ;;
        br.ret.sptk.many b0
 END(ia64_pal_call_static)
diff --git a/Documentation/ia64/paravirt_ops.txt b/Documentation/ia64/paravirt_ops.txt
new file mode 100644
index 000000000000..39ded02ec33f
--- /dev/null
+++ b/Documentation/ia64/paravirt_ops.txt
@@ -0,0 +1,137 @@
+Paravirt_ops on IA64
+====================
+                          21 May 2008, Isaku Yamahata <yamahata@valinux.co.jp>
+Introduction
+------------
+The aim of this documentation is to help with maintainability and/or to
+encourage people to use paravirt_ops/IA64.
+paravirt_ops (pv_ops in short) is a way for virtualization support of
+Linux kernel on x86. Several ways for virtualization support were
+proposed, paravirt_ops is the winner.
+On the other hand, now there are also several IA64 virtualization
+technologies like kvm/IA64, xen/IA64 and many other academic IA64
+hypervisors so that it is good to add generic virtualization
+infrastructure on Linux/IA64.
+What is paravirt_ops?
+---------------------
+It has been developed on x86 as virtualization support via API, not ABI.
+It allows each hypervisor to override operations which are important for
+hypervisors at API level. And it allows a single kernel binary to run on
+all supported execution environments including native machine.
+Essentially paravirt_ops is a set of function pointers which represent
+operations corresponding to low level sensitive instructions and high
+level functionalities in various area. But one significant difference
+from usual function pointer table is that it allows optimization with
+binary patch. It is because some of these operations are very
+performance sensitive and indirect call overhead is not negligible.
+With binary patch, indirect C function call can be transformed into
+direct C function call or in-place execution to eliminate the overhead.
+Thus, operations of paravirt_ops are classified into three categories.
+- simple indirect call
+  These operations correspond to high level functionality so that the
+  overhead of indirect call isn't very important.
+- indirect call which allows optimization with binary patch
+  Usually these operations correspond to low level instructions. They
+  are called frequently and performance critical. So the overhead is
+  very important.
+- a set of macros for hand written assembly code
+  Hand written assembly codes (.S files) also need paravirtualization
+  because they include sensitive instructions or some of code paths in
+  them are very performance critical.
+The relation to the IA64 machine vector
+---------------------------------------
+Linux/IA64 has the IA64 machine vector functionality which allows the
+kernel to switch implementations (e.g. initialization, ipi, dma api...)
+depending on executing platform.
+We can replace some implementations very easily defining a new machine
+vector. Thus another approach for virtualization support would be
+enhancing the machine vector functionality.
+But paravirt_ops approach was taken because
+- virtualization support needs wider support than machine vector does.
+  e.g. low level instruction paravirtualization. It must be
+       initialized very early before platform detection.
+- virtualization support needs more functionality like binary patch.
+  Probably the calling overhead might not be very large compared to the
+  emulation overhead of virtualization. However in the native case, the
+  overhead should be eliminated completely.
+  A single kernel binary should run on each environment including native,
+  and the overhead of paravirt_ops on native environment should be as
+  small as possible.
+- for full virtualization technology, e.g. KVM/IA64 or
+  Xen/IA64 HVM domain, the result would be
+  (the emulated platform machine vector. probably dig) + (pv_ops).
+  This means that the virtualization support layer should be under
+  the machine vector layer.
+Possibly it might be better to move some function pointers from
+paravirt_ops to machine vector. In fact, Xen domU case utilizes both
+pv_ops and machine vector.
+IA64 paravirt_ops
+-----------------
+In this section, the concrete paravirt_ops will be discussed.
+Because of the architecture difference between ia64 and x86, the
+resulting set of functions is very different from x86 pv_ops.
+- C function pointer tables
+They are not very performance critical so that simple C indirect
+function call is acceptable. The following structures are defined at
+this moment. For details see linux/include/asm-ia64/paravirt.h
+  - struct pv_info
+    This structure describes the execution environment.
+  - struct pv_init_ops
+    This structure describes the various initialization hooks.
+  - struct pv_iosapic_ops
+    This structure describes hooks to iosapic operations.
+  - struct pv_irq_ops
+    This structure describes hooks to irq related operations
+  - struct pv_time_op
+    This structure describes hooks to steal time accounting.
+- a set of indirect calls which need optimization
+Currently this class of functions correspond to a subset of IA64
+intrinsics. At this moment the optimization with binary patch isn't
+implemented yet.
+struct pv_cpu_op is defined. For details see
+linux/include/asm-ia64/paravirt_privop.h
+Mostly they correspond to ia64 intrinsics 1-to-1.
+Caveat: Now they are defined as C indirect function pointers, but in
+order to support binary patch optimization, they will be changed
+using GCC extended inline assembly code.
+- a set of macros for hand written assembly code (.S files)
+For maintenance purpose, the taken approach for .S files is single
+source code and compile multiple times with different macros definitions.
+Each pv_ops instance must define those macros to compile.
+The important thing here is that sensitive, but non-privileged
+instructions must be paravirtualized and that some privileged
+instructions also need paravirtualization for reasonable performance.
+Developers who modify .S files must be aware of that. At this moment
+an easy checker is implemented to detect paravirtualization breakage.
+But it doesn't cover all the cases.
+Sometimes this set of macros is called pv_cpu_asm_op. But there is no
+corresponding structure in the source code.
+Those macros mostly 1:1 correspond to a subset of privileged
+instructions. See linux/include/asm-ia64/native/inst.h.
+And some functions written in assembly also need to be overrided so
+that each pv_ops instance have to define some macros. Again see
+linux/include/asm-ia64/native/inst.h.
+Those structures must be initialized very early before start_kernel.
+Probably initialized in head.S using multi entry point or some other trick.
+For native case implementation see linux/arch/ia64/kernel/paravirt.c.
diff --git a/Documentation/ia64/xen.txt b/Documentation/ia64/xen.txt
new file mode 100644
index 000000000000..c61a99f7c8bb
--- /dev/null
+++ b/Documentation/ia64/xen.txt
@@ -0,0 +1,183 @@
+       Recipe for getting/building/running Xen/ia64 with pv_ops
+       --------------------------------------------------------
+This recipe describes how to get xen-ia64 source and build it,
+and run domU with pv_ops.
+============
+Requirements
+============
+  - python
+  - mercurial
+    it (aka "hg") is an open-source source code
+    management software. See the below.
+    http://www.selenic.com/mercurial/wiki/
+  - git
+  - bridge-utils
+=================================
+Getting and Building Xen and Dom0
+=================================
+  My environment is;
+    Machine  : Tiger4
+    Domain0 OS  : RHEL5
+    DomainU OS  : RHEL5
+ 1. Download source
+    # hg clone http://xenbits.xensource.com/ext/ia64/xen-unstable.hg
+    # cd xen-unstable.hg
+    # hg clone http://xenbits.xensource.com/ext/ia64/linux-2.6.18-xen.hg
+ 2. # make world
+ 3. # make install-tools
+ 4. copy kernels and xen
+    # cp xen/xen.gz /boot/efi/efi/redhat/
+    # cp build-linux-2.6.18-xen_ia64/vmlinux.gz \
+      /boot/efi/efi/redhat/vmlinuz-2.6.18.8-xen
+ 5. make initrd for Dom0/DomU
+    # make -C linux-2.6.18-xen.hg ARCH=ia64 modules_install \
+      O=$(/bin/pwd)/build-linux-2.6.18-xen_ia64
+    # mkinitrd -f /boot/efi/efi/redhat/initrd-2.6.18.8-xen.img \
+      2.6.18.8-xen --builtin mptspi --builtin mptbase \
+      --builtin mptscsih --builtin uhci-hcd --builtin ohci-hcd \
+      --builtin ehci-hcd
+================================
+Making a disk image for guest OS
+================================
+ 1. make file
+    # dd if=/dev/zero of=/root/rhel5.img bs=1M seek=4096 count=0
+    # mke2fs -F -j /root/rhel5.img
+    # mount -o loop /root/rhel5.img /mnt
+    # cp -ax /{dev,var,etc,usr,bin,sbin,lib} /mnt
+    # mkdir /mnt/{root,proc,sys,home,tmp}
+    Note: You may miss some device files. If so, please create them
+    with mknod. Or you can use tar instead of cp.
+ 2. modify DomU's fstab
+    # vi /mnt/etc/fstab
+       /dev/xvda1  /            ext3    defaults        1 1
+       none        /dev/pts     devpts  gid=5,mode=620  0 0
+       none        /dev/shm     tmpfs   defaults        0 0
+       none        /proc        proc    defaults        0 0
+       none        /sys         sysfs   defaults        0 0
+ 3. modify inittab
+    set runlevel to 3 to avoid X trying to start
+    # vi /mnt/etc/inittab
+       id:3:initdefault:
+    Start a getty on the hvc0 console
+       X0:2345:respawn:/sbin/mingetty hvc0
+    tty1-6 mingetty can be commented out
+ 4. add hvc0 into /etc/securetty
+    # vi /mnt/etc/securetty (add hvc0)
+ 5. umount
+    # umount /mnt
+FYI, virt-manager can also make a disk image for guest OS.
+It's GUI tools and easy to make it.
+==================
+Boot Xen & Domain0
+==================
+ 1. replace elilo
+    elilo of RHEL5 can boot Xen and Dom0.
+    If you use old elilo (e.g RHEL4), please download from the below
+    http://elilo.sourceforge.net/cgi-bin/blosxom
+    and copy into /boot/efi/efi/redhat/
+    # cp elilo-3.6-ia64.efi /boot/efi/efi/redhat/elilo.efi
+ 2. modify elilo.conf (like the below)
+    # vi /boot/efi/efi/redhat/elilo.conf
+     prompt
+     timeout=20
+     default=xen
+     relocatable
+     image=vmlinuz-2.6.18.8-xen
+             label=xen
+             vmm=xen.gz
+             initrd=initrd-2.6.18.8-xen.img
+             read-only
+             append=" -- rhgb root=/dev/sda2"
+The append options before "--" are for xen hypervisor,
+the options after "--" are for dom0.
+FYI, your machine may need console options like
+"com1=19200,8n1 console=vga,com1". For example,
+append="com1=19200,8n1 console=vga,com1 -- rhgb console=tty0 \
+console=ttyS0 root=/dev/sda2"
+=====================================
+Getting and Building domU with pv_ops
+=====================================
+ 1. get pv_ops tree
+    # git clone http://people.valinux.co.jp/~yamahata/xen-ia64/linux-2.6-xen-ia64.git/
+ 2. git branch (if necessary)
+    # cd linux-2.6-xen-ia64/
+    # git checkout -b your_branch origin/xen-ia64-domu-minimal-2008may19
+    (Note: The current branch is xen-ia64-domu-minimal-2008may19.
+    But you would find the new branch. You can see with
+    "git branch -r" to get the branch lists.
+    http://people.valinux.co.jp/~yamahata/xen-ia64/for_eagl/linux-2.6-ia64-pv-ops.git/
+    is also available. The tree is based on
+    git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux-2.6 test)
+ 3. copy .config for pv_ops of domU
+    # cp arch/ia64/configs/xen_domu_wip_defconfig .config
+ 4. make kernel with pv_ops
+    # make oldconfig
+    # make
+ 5. install the kernel and initrd
+    # cp vmlinux.gz /boot/efi/efi/redhat/vmlinuz-2.6-pv_ops-xenU
+    # make modules_install
+    # mkinitrd -f /boot/efi/efi/redhat/initrd-2.6-pv_ops-xenU.img \
+      2.6.26-rc3xen-ia64-08941-g1b12161 --builtin mptspi \
+      --builtin mptbase --builtin mptscsih --builtin uhci-hcd \
+      --builtin ohci-hcd --builtin ehci-hcd
+========================
+Boot DomainU with pv_ops
+========================
+ 1. make config of DomU
+   # vi /etc/xen/rhel5
+     kernel = "/boot/efi/efi/redhat/vmlinuz-2.6-pv_ops-xenU"
+     ramdisk = "/boot/efi/efi/redhat/initrd-2.6-pv_ops-xenU.img"
+     vcpus = 1
+     memory = 512
+     name = "rhel5"
+     disk = [ 'file:/root/rhel5.img,xvda1,w' ]
+     root = "/dev/xvda1 ro"
+     extra= "rhgb console=hvc0"
+ 2. After boot xen and dom0, start xend
+   # /etc/init.d/xend start
+   ( In the debugging case, # XEND_DEBUG=1 xend trace_start )
+ 3. start domU
+   # xm create -c rhel5
+=========
+Reference
+=========
+- Wiki of Xen/IA64 upstream merge
+  http://wiki.xensource.com/xenwiki/XenIA64/UpstreamMerge
+Written by Akio Takebe <takebe_akio@jp.fujitsu.com> on 28 May 2008
diff --git a/Documentation/input/cs461x.txt b/Documentation/input/cs461x.txt
index afe0d6543e09..202e9dbacec3 100644
--- a/Documentation/input/cs461x.txt
+++ b/Documentation/input/cs461x.txt
@@ -31,7 +31,7 @@ The driver works with ALSA drivers simultaneously. For example, the xracer
 uses joystick as input device and PCM device as sound output in one time.
 There are no sound or input collisions detected. The source code have
 comments about them; but I've found the joystick can be initialized 
-separately of ALSA modules. So, you canm use only one joystick driver
+separately of ALSA modules. So, you can use only one joystick driver
 without ALSA drivers. The ALSA drivers are not needed to compile or
 run this driver.
diff --git a/Documentation/input/gameport-programming.txt b/Documentation/input/gameport-programming.txt
index 14e0a8b70225..03a74fc3b496 100644
--- a/Documentation/input/gameport-programming.txt
+++ b/Documentation/input/gameport-programming.txt
@@ -1,5 +1,3 @@
-$Id: gameport-programming.txt,v 1.3 2001/04/24 13:51:37 vojtech Exp $
 Programming gameport drivers
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/input/input.txt b/Documentation/input/input.txt
index ff8cea0225f9..686ee9932dff 100644
--- a/Documentation/input/input.txt
+++ b/Documentation/input/input.txt
@@ -1,7 +1,6 @@
                          Linux Input drivers v1.0
               (c) 1999-2001 Vojtech Pavlik <vojtech@ucw.cz>
                             Sponsored by SuSE
-            $Id: input.txt,v 1.8 2002/05/29 03:15:01 bradleym Exp $
 ----------------------------------------------------------------------------
 0. Disclaimer
diff --git a/Documentation/input/joystick-api.txt b/Documentation/input/joystick-api.txt
index acbd32b88454..c507330740cd 100644
--- a/Documentation/input/joystick-api.txt
+++ b/Documentation/input/joystick-api.txt
@@ -5,8 +5,6 @@
                              7 Aug 1998
-        $Id: joystick-api.txt,v 1.2 2001/05/08 21:21:23 vojtech Exp $
 1. Initialization
 ~~~~~~~~~~~~~~~~~
diff --git a/Documentation/input/joystick-parport.txt b/Documentation/input/joystick-parport.txt
index ede5f33daad3..1c856f32ff2c 100644
--- a/Documentation/input/joystick-parport.txt
+++ b/Documentation/input/joystick-parport.txt
@@ -2,7 +2,6 @@
               (c) 1998-2000 Vojtech Pavlik <vojtech@ucw.cz>
               (c) 1998 Andree Borrmann <a.borrmann@tu-bs.de>
                             Sponsored by SuSE
-        $Id: joystick-parport.txt,v 1.6 2001/09/25 09:31:32 vojtech Exp $
 ----------------------------------------------------------------------------
 0. Disclaimer
diff --git a/Documentation/input/joystick.txt b/Documentation/input/joystick.txt
index 389de9bd9878..154d767b2acb 100644
--- a/Documentation/input/joystick.txt
+++ b/Documentation/input/joystick.txt
@@ -1,7 +1,6 @@
                       Linux Joystick driver v2.0.0
               (c) 1996-2000 Vojtech Pavlik <vojtech@ucw.cz>
                             Sponsored by SuSE
-           $Id: joystick.txt,v 1.12 2002/03/03 12:13:07 jdeneux Exp $
 ----------------------------------------------------------------------------
 0. Disclaimer
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index 3bb5f466a90d..b880ce5dbd33 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -92,6 +92,7 @@ Code	Seq#	Include File		Comments
 'J'     00-1F   drivers/scsi/gdth_ioctl.h
 'K'     all     linux/kd.h
 'L'     00-1F   linux/loop.h
+'L'     20-2F   driver/usb/misc/vstusb.h
 'L'     E0-FF   linux/ppdd.h            encrypted disk device driver
                                        <http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'     all     linux/soundcard.h
@@ -105,12 +106,13 @@ Code	Seq#	Include File		Comments
 'T'     all     linux/soundcard.h       conflict!
 'T'     all     asm-i386/ioctls.h       conflict!
 'U'     00-EF   linux/drivers/usb/usb.h
-'U'     F0-FF   drivers/usb/auerswald.c
 'V'     all     linux/vt.h
 'W'     00-1F   linux/watchdog.h        conflict!
 'W'     00-1F   linux/wanrouter.h       conflict!
 'X'     all     linux/xfs_fs.h
 'Y'     all     linux/cyclades.h
+'['     00-07   linux/usb/usbtmc.h      USB Test and Measurement Devices
+                                        <mailto:gregkh@suse.de>
 'a'     all                             ATM on linux
                                        <http://lrcwww.epfl.ch/linux-atm/magic.html>
 'b'     00-FF                           bit3 vme host bridge
diff --git a/Documentation/ioctl/cdrom.txt b/Documentation/ioctl/cdrom.txt
index 62d4af44ec4a..59df81c8da2b 100644
--- a/Documentation/ioctl/cdrom.txt
+++ b/Documentation/ioctl/cdrom.txt
@@ -271,14 +271,14 @@ CDROMCLOSETRAY			pendant of CDROMEJECT
        usage:
-          ioctl(fd, CDROMEJECT, 0);
+          ioctl(fd, CDROMCLOSETRAY, 0);
        inputs:         none
        outputs:        none
        error returns:
-          ENOSYS        cd drive not capable of ejecting
+          ENOSYS        cd drive not capable of closing the tray
          EBUSY         other processes are accessing drive, or door is locked
        notes:
diff --git a/Documentation/ioctl/ioctl-decoding.txt b/Documentation/ioctl/ioctl-decoding.txt
index bfdf7f3ee4f0..e35efb0cec2e 100644
--- a/Documentation/ioctl/ioctl-decoding.txt
+++ b/Documentation/ioctl/ioctl-decoding.txt
@@ -1,6 +1,6 @@
 To decode a hex IOCTL code:
-Most architecures use this generic format, but check
+Most architectures use this generic format, but check
 include/ARCH/ioctl.h for specifics, e.g. powerpc
 uses 3 bits to encode read/write and 13 bits for size.
@@ -18,7 +18,7 @@ uses 3 bits to encode read/write and 13 bits for size.
 7-0    function #
- So for example 0x82187201 is a read with arg length of 0x218,
+So for example 0x82187201 is a read with arg length of 0x218,
 character 'r' function 1. Grepping the source reveals this is:
 #define VFAT_IOCTL_READDIR_BOTH         _IOR('r', 1, struct dirent [2])
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 5925c3cd030d..59a69ec67c40 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -143,7 +143,7 @@ disk and partition statistics are consistent again. Since we still don't
 keep record of the partition-relative address, an operation is attributed to
 the partition which contains the first sector of the request after the
 eventual merges. As requests can be merged across partition, this could lead
-to some (probably insignificant) innacuracy.
+to some (probably insignificant) inaccuracy.
 Additional notes
 ----------------
diff --git a/Documentation/isdn/README.mISDN b/Documentation/isdn/README.mISDN
new file mode 100644
index 000000000000..cd8bf920e77b
--- /dev/null
+++ b/Documentation/isdn/README.mISDN
@@ -0,0 +1,6 @@
+mISDN is a new modular ISDN driver, in the long term it should replace
+the old I4L driver architecture for passiv ISDN cards.
+It was designed to allow a broad range of applications and interfaces
+but only have the basic function in kernel, the interface to the user
+space is based on sockets with a own address family AF_ISDN.
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 488c77fa3aae..0775cf4798b2 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -11,14 +11,14 @@ for non English (read: Japanese) speakers and is not intended as a
 fork. So if you have any comments or updates for this file, please try
 to update the original English file first.
-Last Updated: 2007/11/16
+Last Updated: 2008/08/21
 ==================================
 これは、
-linux-2.6.24/Documentation/HOWTO
+linux-2.6.27/Documentation/HOWTO
 の和訳です。
 翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
-翻訳日： 2007/11/10
+翻訳日： 2008/8/5
 翻訳者： Tsugikazu Shibata <tshibata at ab dot jp dot nec dot com>
 校正者： 松倉さん <nbh--mats at nifty dot com>
         小林 雅典さん (Masanori Kobayasi) <zap03216 at nifty dot ne dot jp>
@@ -287,13 +287,15 @@ Linux カーネルの開発プロセスは現在幾つかの異なるメイン�
    に安定した状態にあると判断したときにリリースされます。目標は毎週新
    しい -rc カーネルをリリースすることです。
-   - 以下の URL で各 -rc リリースに存在する既知の後戻り問題のリスト
-     が追跡されます-
-     http://kernelnewbies.org/known_regressions
  - このプロセスはカーネルが 「準備ができた」と考えられるまで継続しま
    す。このプロセスはだいたい 6週間継続します。
+  - 各リリースでの既知の後戻り問題(regression: このリリースの中で新規
+    に作り込まれた問題を指す) はその都度 Linux-kernel メーリングリスト
+    に投稿されます。ゴールとしては、カーネルが 「準備ができた」と宣言
+    する前にこのリストの長さをゼロに減らすことですが、現実には、数個の
+    後戻り問題がリリース時にたびたび残ってしまいます。
 Andrew Morton が Linux-kernel メーリングリストにカーネルリリースについ
 て書いたことをここで言っておくことは価値があります-
  「カーネルがいつリリースされるかは誰も知りません。なぜなら、これは現
@@ -303,18 +305,20 @@ Andrew Morton が Linux-kernel メーリングリストにカーネルリリー�
 2.6.x.y -stable カーネルツリー
 ---------------------------
-バージョン��4つ目の数字が��い���カーネルは -stable カーネルです。これに
+バージョン番号��4つの数字��分か����い���カーネルは -stable カーネルです。
-は、2.6.x カーネルで見つかったセキュリティ問題や重大な後戻りに対する比
+��れに��、2.6.x カーネルで見つかったセキュリティ問題や重大な後戻りに対
-較的小さい重要な修正が含まれます。
+する比較的小さい重要な修正が含まれます。
 これは、開発/実験的バージョンのテストに協力することに興味が無く、
 最新の安定したカーネルを使いたいユーザに推奨するブランチです。
-もし、2.6.x.y カーネルが存在しない場合には、番号が一番大きい 2.6.x
+もし、2.6.x.y カーネルが存在しない場合には、番号が一番大きい 2.6.x が
-が最新の安定版カーネルです。
+最新の安定版カーネルです。
-2.6.x.y は "stable" チーム <stable@kernel.org> でメンテされており、だ
+2.6.x.y は "stable" チーム <stable@kernel.org> でメンテされており、必
-いたい隔週でリリースされています。
+要に応じてリリースされます。通常のリリース期間は 2週間毎ですが、差し迫っ
+た問題がなければもう少し長くなることもあります。セキュリティ関連の問題
+の場合はこれに対してだいたいの場合、すぐにリリースがされます。
 カーネルツリーに入っている、Documentation/stable_kernel_rules.txt ファ
 イルにはどのような種類の変更が -stable ツリーに受け入れ可能か、またリ
@@ -341,7 +345,9 @@ linux-kernel メーリングリストで収集された多数のパッチと同�
 メインラインへ入れるように Linus にプッシュします。
 メインカーネルツリーに含めるために Linus に送る前に、すべての新しいパッ
-チが -mm ツリーでテストされることが強く推奨されます。
+チが -mm ツリーでテストされることが強く推奨されています。マージウィン
+ドウが開く前に -mm ツリーに現れなかったパッチはメインラインにマージさ
+れることは困難になります。
 これらのカーネルは安定して動作すべきシステムとして使うのには適切ではあ
 りませんし、カーネルブランチの中でももっとも動作にリスクが高いものです。
@@ -395,13 +401,15 @@ linux-kernel メーリングリストで収集された多数のパッチと同�
    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
        git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-    - SCSI, James Bottomley <James.Bottomley@SteelEye.com>
+    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
        git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
+    - x86, Ingo Molnar <mingo@elte.hu>
+        git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
  quilt ツリー-
-    - USB, PCI ドライバコアと I2C, Greg Kroah-Hartman <gregkh@suse.de>
+    - USB, ドライバコアと I2C, Greg Kroah-Hartman <gregkh@suse.de>
        kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
-    - x86-64 と i386 の仲間 Andi Kleen <ak@suse.de>
  その他のカーネルツリーは http://git.kernel.org/ と MAINTAINERS ファ
  イルに一覧表があります。
@@ -412,13 +420,32 @@ linux-kernel メーリングリストで収集された多数のパッチと同�
 bugzilla.kernel.org は Linux カーネル開発者がカーネルのバグを追跡する
 場所です。ユーザは見つけたバグの全てをこのツールで報告すべきです。
 どう kernel bugzilla を使うかの詳細は、以下を参照してください-
-        http://test.kernel.org/bugzilla/faq.html
+        http://bugzilla.kernel.org/page.cgi?id=faq.html
 メインカーネルソースディレクトリにあるファイル REPORTING-BUGS はカーネ
 ルバグらしいものについてどうレポートするかの良いテンプレートであり、問
 題の追跡を助けるためにカーネル開発者にとってどんな情報が必要なのかの詳
 細が書かれています。
+バグレポートの管理
+-------------------
+あなたのハッキングのスキルを訓練する最高の方法のひとつに、他人がレポー
+トしたバグを修正することがあります。あなたがカーネルをより安定化させる
+こに寄与するということだけでなく、あなたは 現実の問題を修正することを
+学び、自分のスキルも強化でき、また他の開発者があなたの存在に気がつき
+ます。バグを修正することは、多くの開発者の中から自分が功績をあげる最善
+の道です、なぜなら多くの人は他人のバグの修正に時間を浪費することを好ま
+ないからです。
+すでにレポートされたバグのために仕事をするためには、
+http://bugzilla.kernel.org に行ってください。もし今後のバグレポートに
+ついてアドバイスを受けたいのであれば、bugme-new メーリングリスト(新し
+いバグレポートだけがここにメールされる) または bugme-janitor メーリン
+グリスト(bugzilla の変更毎にここにメールされる)を購読できます。
+        http://lists.linux-foundation.org/mailman/listinfo/bugme-new
+        http://lists.linux-foundation.org/mailman/listinfo/bugme-janitors
 メーリングリスト
 -------------
diff --git a/Documentation/ja_JP/SubmitChecklist b/Documentation/ja_JP/SubmitChecklist
new file mode 100644
index 000000000000..6c42e071d723
--- /dev/null
+++ b/Documentation/ja_JP/SubmitChecklist
@@ -0,0 +1,111 @@
+NOTE:
+This is a version of Documentation/SubmitChecklist into Japanese.
+This document is maintained by Takenori Nagano <t-nagano@ah.jp.nec.com>
+and the JF Project team <http://www.linux.or.jp/JF/>.
+If you find any difference between this document and the original file
+or a problem with the translation,
+please contact the maintainer of this file or JF project.
+Please also note that the purpose of this file is to be easier to read
+for non English (read: Japanese) speakers and is not intended as a
+fork. So if you have any comments or updates of this file, please try
+to update the original English file first.
+Last Updated: 2008/07/14
+==================================
+これは、
+linux-2.6.26/Documentation/SubmitChecklist の和訳です。
+翻訳団体： JF プロジェクト < http://www.linux.or.jp/JF/ >
+翻訳日： 2008/07/14
+翻訳者： Takenori Nagano <t-nagano at ah dot jp dot nec dot com>
+校正者： Masanori Kobayashi さん <zap03216 at nifty dot ne dot jp>
+==================================
+Linux カーネルパッチ投稿者向けチェックリスト
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+本書では、パッチをより素早く取り込んでもらいたい開発者が実践すべき基本的な事柄
+をいくつか紹介します。ここにある全ての事柄は、Documentation/SubmittingPatches
+などのLinuxカーネルパッチ投稿に際しての心得を補足するものです。
+ 1: 妥当なCONFIGオプションや変更されたCONFIGオプション、つまり =y, =m, =n
+    全てで正しくビルドできることを確認してください。その際、gcc及びリンカが
+    warningやerrorを出していないことも確認してください。
+ 2: allnoconfig, allmodconfig オプションを用いて正しくビルドできることを
+    確認してください。
+ 3: 手許のクロスコンパイルツールやOSDLのPLMのようなものを用いて、複数の
+    アーキテクチャにおいても正しくビルドできることを確認してください。
+ 4: 64bit長の'unsigned long'を使用しているppc64は、クロスコンパイルでの
+    チェックに適当なアーキテクチャです。
+ 5: カーネルコーディングスタイルに準拠しているかどうか確認してください(!)
+ 6: CONFIGオプションの追加・変更をした場合には、CONFIGメニューが壊れていない
+    ことを確認してください。
+ 7: 新しくKconfigのオプションを追加する際には、必ずそのhelpも記述してください。
+ 8: 適切なKconfigの依存関係を考えながら慎重にチェックしてください。
+    ただし、この作業はマシンを使ったテストできちんと行うのがとても困難です。
+    うまくやるには、自分の頭で考えることです。
+ 9: sparseを利用してちゃんとしたコードチェックをしてください。
+10: 'make checkstack' と 'make namespacecheck' を利用し、問題が発見されたら
+    修正してください。'make checkstack' は明示的に問題を示しませんが、どれか
+    １つの関数が512バイトより大きいスタックを使っていれば、修正すべき候補と
+    なります。
+11: グローバルなkernel API を説明する kernel-doc をソースの中に含めてください。
+    ( staticな関数においては必須ではありませんが、含めてもらっても結構です )
+    そして、'make htmldocs' もしくは 'make mandocs' を利用して追記した
+    ドキュメントのチェックを行い、問題が見つかった場合には修正を行ってください。
+12: CONFIG_PREEMPT, CONFIG_DEBUG_PREEMPT, CONFIG_DEBUG_SLAB,
+    CONFIG_DEBUG_PAGEALLOC, CONFIG_DEBUG_MUTEXES, CONFIG_DEBUG_SPINLOCK,
+    CONFIG_DEBUG_SPINLOCK_SLEEP これら全てを同時に有効にして動作確認を
+    行ってください。
+13: CONFIG_SMP, CONFIG_PREEMPT を有効にした場合と無効にした場合の両方で
+    ビルドした上、動作確認を行ってください。
+14: もしパッチがディスクのI/O性能などに影響を与えるようであれば、
+    'CONFIG_LBD'オプションを有効にした場合と無効にした場合の両方で
+    テストを実施してみてください。
+15: lockdepの機能を全て有効にした上で、全てのコードパスを評価してください。
+16: /proc に新しいエントリを追加した場合には、Documentation/ 配下に
+    必ずドキュメントを追加してください。
+17: 新しいブートパラメータを追加した場合には、
+    必ずDocumentation/kernel-parameters.txt に説明を追加してください。
+18: 新しくmoduleにパラメータを追加した場合には、MODULE_PARM_DESC()を
+    利用して必ずその説明を記述してください。
+19: 新しいuserspaceインタフェースを作成した場合には、Documentation/ABI/ に
+    Documentation/ABI/README を参考にして必ずドキュメントを追加してください。
+20: 'make headers_check'を実行して全く問題がないことを確認してください。
+21: 少なくともslabアロケーションとpageアロケーションに失敗した場合の
+    挙動について、fault-injectionを利用して確認してください。
+    Documentation/fault-injection/ を参照してください。
+    追加したコードがかなりの量であったならば、サブシステム特有の
+    fault-injectionを追加したほうが良いかもしれません。
+22: 新たに追加したコードは、`gcc -W'でコンパイルしてください。
+    このオプションは大量の不要なメッセージを出力しますが、
+    "warning: comparison between signed and unsigned" のようなメッセージは、
+    バグを見つけるのに役に立ちます。
+23: 投稿したパッチが -mm パッチセットにマージされた後、全ての既存のパッチや
+    VM, VFS およびその他のサブシステムに関する様々な変更と、現時点でも共存
+    できることを確認するテストを行ってください。
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 9691c7f5166c..3f4bc840da8b 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -65,26 +65,26 @@ Install kexec-tools
 2) Download the kexec-tools user-space package from the following URL:
-http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools-testing.tar.gz
+http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/kexec-tools.tar.gz
-This is a symlink to the latest version, which at the time of writing is
+This is a symlink to the latest version.
-20061214, the only release of kexec-tools-testing so far. As other versions
-are released, the older ones will remain available at
-http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/
-Note: Latest kexec-tools-testing git tree is available at
+The latest kexec-tools git tree is available at:
-git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools-testing.git
+git://git.kernel.org/pub/scm/linux/kernel/git/horms/kexec-tools.git
 or
-http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools-testing.git;a=summary
+http://www.kernel.org/git/?p=linux/kernel/git/horms/kexec-tools.git
+More information about kexec-tools can be found at
+http://www.kernel.org/pub/linux/kernel/people/horms/kexec-tools/README.html
 3) Unpack the tarball with the tar command, as follows:
-   tar xvpzf kexec-tools-testing.tar.gz
+   tar xvpzf kexec-tools.tar.gz
 4) Change to the kexec-tools directory, as follows:
-   cd kexec-tools-testing-VERSION
+   cd kexec-tools-VERSION
 5) Configure the package, as follows:
@@ -109,7 +109,8 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
   no need to build a separate dump-capture kernel. This is possible
   only with the architecutres which support a relocatable kernel. As
-   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   kernel.
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
@@ -207,8 +208,15 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 Dump-capture kernel config options (Arch Dependent, ppc64)
 ----------------------------------------------------------
-*  Make and install the kernel and its modules. DO NOT add this kernel
+1) Enable "Build a kdump crash kernel" support under "Kernel" options:
-   to the boot loader configuration files.
+   CONFIG_CRASH_DUMP=y
+2)   Enable "Build a relocatable kernel" support
+   CONFIG_RELOCATABLE=y
+   Make and install the kernel and its modules.
 Dump-capture kernel config options (Arch Dependent, ia64)
 ----------------------------------------------------------
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 0bd32748a467..c6841eee9598 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -168,10 +168,10 @@ if ($#ARGV < 0) {
 mkdir $ARGV[0],0777;
 $state = 0;
 while (<STDIN>) {
-    if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) {
+    if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
        if ($state == 1) { close OUT }
        $state = 1;
-        $fn = "$ARGV[0]/$1.4";
+        $fn = "$ARGV[0]/$1.9";
        print STDERR "Creating $fn\n";
        open OUT, ">$fn" or die "can't open $fn: $!\n";
        print OUT $_;
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 62b6e8067a5b..63bac584f9cb 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -87,7 +87,8 @@ parameter is applicable:
        SH      SuperH architecture is enabled.
        SMP     The kernel is an SMP kernel.
        SPARC   Sparc architecture is enabled.
-        SWSUSP  Software suspend is enabled.
+        SWSUSP  Software suspend (hibernation) is enabled.
+        SUSPEND System suspend states are enabled.
        TS      Appropriate touchscreen support is enabled.
        USB     USB support is enabled.
        USBHID  USB Human Interface Device support is enabled.
@@ -100,6 +101,7 @@ parameter is applicable:
        X86-64  X86-64 architecture is enabled.
                        More X86-64 boot options can be found in
                        Documentation/x86_64/boot-options.txt .
+        X86     Either 32bit or 64bit x86 (same as X86-32+X86-64)
 In addition, the following text indicates that the option:
@@ -147,10 +149,12 @@ and is between 256 and 4096 characters. It is defined in the file
                        default: 0
        acpi_sleep=     [HW,ACPI] Sleep options
-                        Format: { s3_bios, s3_mode, s3_beep, old_ordering }
+                        Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering }
                        See Documentation/power/video.txt for s3_bios and s3_mode.
                        s3_beep is for debugging; it makes the PC's speaker beep
                        as soon as the kernel's real-mode entry point is called.
+                        s4_nohwsig prevents ACPI hardware signature from being
+                        used during resume from hibernation.
                        old_ordering causes the ACPI 1.0 ordering of the _PTS
                        control method, wrt putting devices into low power
                        states, to be enforced (the ACPI 2.0 ordering of _PTS is
@@ -214,20 +218,47 @@ and is between 256 and 4096 characters. It is defined in the file
        acpi.debug_level=       [HW,ACPI]
                        Format: <int>
                        Each bit of the <int> indicates an ACPI debug level,
-                        1: enable, 0: disable. It is useful for boot time
+                        which corresponds to the level in an ACPI_DEBUG_PRINT
-                        debugging. After system has booted up, it can be set
+                        statement.  After system has booted up, this mask
-                        via /sys/module/acpi/parameters/debug_level.
+                        can be set via /sys/module/acpi/parameters/debug_level.
-                        CONFIG_ACPI_DEBUG must be enabled for this to produce any output.
-                        Available bits (add the numbers together) to enable different
+                        CONFIG_ACPI_DEBUG must be enabled for this to produce
-                        debug output levels of the ACPI subsystem:
+                        any output.  The number can be in decimal or prefixed
-                        0x01 error 0x02 warn 0x04 init 0x08 debug object
+                        with 0x in hex.  Some of these options produce so much
-                        0x10 info 0x20 init names 0x40 parse 0x80 load
+                        output that the system is unusable.
-                        0x100 dispatch 0x200 execute 0x400 names 0x800 operation region
-                        0x1000 bfield 0x2000 tables 0x4000 values 0x8000 objects
+                        The following global components are defined by the
-                        0x10000 resources 0x20000 user requests 0x40000 package.
+                        ACPI CA:
-                        The number can be in decimal or prefixed with 0x in hex.
+                               0x01 error
-                        Warning: Many of these options can produce a lot of
+                               0x02 warn
-                        output and make your system unusable. Be very careful.
+                               0x04 init
+                               0x08 debug object
+                               0x10 info
+                               0x20 init names
+                               0x40 parse
+                               0x80 load
+                              0x100 dispatch
+                              0x200 execute
+                              0x400 names
+                              0x800 operation region
+                             0x1000 bfield
+                             0x2000 tables
+                             0x4000 values
+                             0x8000 objects
+                            0x10000 resources
+                            0x20000 user requests
+                            0x40000 package
+                        The number can be in decimal or prefixed with 0x in hex.
+                        Warning: Many of these options can produce a lot of
+                        output and make your system unusable. Be very careful.
+        acpi.power_nocheck=     [HW,ACPI]
+                        Format: 1/0 enable/disable the check of power state.
+                        On some bogus BIOS the _PSC object/_STA object of
+                        power resource can't return the correct device power
+                        state. In such case it is unneccessary to check its
+                        power state again in power transition.
+                        1 : disable the power state check
        acpi_pm_good    [X86-32,X86-64]
                        Override the pmtimer bug detection: force the kernel
@@ -281,6 +312,11 @@ and is between 256 and 4096 characters. It is defined in the file
                        isolate - enable device isolation (each device, as far
                                  as possible, will get its own protection
                                  domain)
+                        fullflush - enable flushing of IO/TLB entries when
+                                    they are unmapped. Otherwise they are
+                                    flushed before they will be reused, which
+                                    is a lot of faster
        amd_iommu_size= [HW,X86-64]
                        Define the size of the aperture for the AMD IOMMU
                        driver. Possible values are:
@@ -362,6 +398,8 @@ and is between 256 and 4096 characters. It is defined in the file
                        no delay (0).
                        Format: integer
+        bootmem_debug   [KNL] Enable bootmem allocator debug messages.
        bttv.card=      [HW,V4L] bttv (bt848 + bt878 based grabber cards)
        bttv.radio=     Most important insmod options are available as
                        kernel args too.
@@ -458,12 +496,6 @@ and is between 256 and 4096 characters. It is defined in the file
                        Range: 0 - 8192
                        Default: 64
-        disable_8254_timer
-        enable_8254_timer
-                        [IA32/X86_64] Disable/Enable interrupt 0 timer routing
-                        over the 8254 in addition to over the IO-APIC. The
-                        kernel tries to set a sensible default.
        hpet=           [X86-32,HPET] option to control HPET usage
                        Format: { enable (default) | disable | force }
                        disable: disable HPET and use PIT instead
@@ -654,11 +686,12 @@ and is between 256 and 4096 characters. It is defined in the file
        earlyprintk=    [X86-32,X86-64,SH,BLACKFIN]
                        earlyprintk=vga
                        earlyprintk=serial[,ttySn[,baudrate]]
+                        earlyprintk=dbgp
                        Append ",keep" to not disable it when the real console
                        takes over.
-                        Only vga or serial at a time, not both.
+                        Only vga or serial or usb debug port at a time.
                        Currently only ttyS0 and ttyS1 are supported.
@@ -685,7 +718,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        See Documentation/block/as-iosched.txt and
                        Documentation/block/deadline-iosched.txt for details.
-        elfcorehdr=     [X86-32, X86_64]
+        elfcorehdr=     [IA64,PPC,SH,X86-32,X86_64]
                        Specifies physical address of start of kernel core
                        image elf header. Generally kexec loader will
                        pass this option to capture kernel.
@@ -774,9 +807,26 @@ and is between 256 and 4096 characters. It is defined in the file
        hisax=          [HW,ISDN]
                        See Documentation/isdn/README.HiSax.
-        hugepages=      [HW,X86-32,IA-64] Maximal number of HugeTLB pages.
+        hugepages=      [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
-        hugepagesz=     [HW,IA-64,PPC] The size of the HugeTLB pages.
+        hugepagesz=     [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
+                        On x86-64 and powerpc, this option can be specified
+                        multiple times interleaved with hugepages= to reserve
+                        huge pages of different sizes. Valid pages sizes on
+                        x86-64 are 2M (when the CPU supports "pse") and 1G
+                        (when the CPU supports the "pdpe1gb" cpuinfo flag)
+                        Note that 1GB pages can only be allocated at boot time
+                        using hugepages= and not freed afterwards.
+        default_hugepagesz=
+                        [same as hugepagesz=] The size of the default
+                        HugeTLB page size. This is the size represented by
+                        the legacy /proc/ hugepages APIs, used for SHM, and
+                        default size when mounting hugetlbfs filesystems.
+                        Defaults to the default architecture's huge page size
+                        if not specified.
+        hlt             [BUGS=ARM,SH]
+        i8042.debug     [HW] Toggle i8042 debug mode
        i8042.direct    [HW] Put keyboard port into non-translated mode
        i8042.dumbkbd   [HW] Pretend that controller can only read data from
                             keyboard and cannot control its state
@@ -1001,6 +1051,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        (only serial suported for now)
                        Format: <serial_device>[,baud]
+        kmac=           [MIPS] korina ethernet MAC address.
+                        Configure the RouterBoard 532 series on-chip
+                        Ethernet adapter MAC address.
        l2cr=           [PPC]
        l3cr=           [PPC]
@@ -1055,6 +1109,9 @@ and is between 256 and 4096 characters. It is defined in the file
                        * [no]ncq: Turn on or off NCQ.
+                        * nohrst, nosrst, norst: suppress hard, soft
+                          and both resets.
                        If there are multiple matching configurations changing
                        the same attribute, the last one is used.
@@ -1184,6 +1241,10 @@ and is between 256 and 4096 characters. It is defined in the file
        mem=nopentium   [BUGS=X86-32] Disable usage of 4MB pages for kernel
                        memory.
+        memchunk=nn[KMG]
+                        [KNL,SH] Allow user to override the default size for
+                        per-device physically contiguous DMA buffers.
        memmap=exactmap [KNL,X86-32,X86_64] Enable setting of an exact
                        E820 memory map, as specified by the user.
                        Such memmap=exactmap lines can be constructed based on
@@ -1206,7 +1267,30 @@ and is between 256 and 4096 characters. It is defined in the file
                                 or
                                 memmap=0x10000$0x18690000
-        memtest=        [KNL,X86_64] Enable memtest
+        memory_corruption_check=0/1 [X86]
+                        Some BIOSes seem to corrupt the first 64k of
+                        memory when doing things like suspend/resume.
+                        Setting this option will scan the memory
+                        looking for corruption.  Enabling this will
+                        both detect corruption and prevent the kernel
+                        from using the memory being corrupted.
+                        However, its intended as a diagnostic tool; if
+                        repeatable BIOS-originated corruption always
+                        affects the same memory, you can use memmap=
+                        to prevent the kernel from using that memory.
+        memory_corruption_check_size=size [X86]
+                        By default it checks for corruption in the low
+                        64k, making this memory unavailable for normal
+                        use.  Use this parameter to scan for
+                        corruption in more or less memory.
+        memory_corruption_check_period=seconds [X86]
+                        By default it checks for corruption every 60
+                        seconds.  Use this parameter to check at some
+                        other rate.  0 disables periodic checking.
+        memtest=        [KNL,X86] Enable memtest
                        Format: <integer>
                        range: 0,4 : pattern number
                        default : 0 <disable>
@@ -1225,6 +1309,14 @@ and is between 256 and 4096 characters. It is defined in the file
        mga=            [HW,DRM]
+        mminit_loglevel=
+                        [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
+                        parameter allows control of the logging verbosity for
+                        the additional memory initialisation checks. A value
+                        of 0 disables mminit logging and a level of 4 will
+                        log everything. Information is printed at KERN_DEBUG
+                        so loglevel=8 may also need to be specified.
        mousedev.tap_time=
                        [MOUSE] Maximum time between finger touching and
                        leaving touchpad surface for touch to be considered
@@ -1279,6 +1371,13 @@ and is between 256 and 4096 characters. It is defined in the file
                        This usage is only documented in each driver source
                        file if at all.
+        nf_conntrack.acct=
+                        [NETFILTER] Enable connection tracking flow accounting
+                        0 to disable accounting
+                        1 to enable accounting
+                        Default value depends on CONFIG_NF_CT_ACCT that is
+                        going to be removed in 2.6.29.
        nfsaddrs=       [NFS]
                        See Documentation/filesystems/nfsroot.txt.
@@ -1328,6 +1427,8 @@ and is between 256 and 4096 characters. It is defined in the file
        nodisconnect    [HW,SCSI,M68K] Disables SCSI disconnects.
+        nodsp           [SH] Disable hardware DSP at boot time.
        noefi           [X86-32,X86-64] Disable EFI runtime services support.
        noexec          [IA-64]
@@ -1344,13 +1445,15 @@ and is between 256 and 4096 characters. It is defined in the file
                        noexec32=off: disable non-executable mappings
                                read implies executable mappings
+        nofpu           [SH] Disable hardware FPU at boot time.
        nofxsr          [BUGS=X86-32] Disables x86 floating point extended
                        register save and restore. The kernel will only save
                        legacy floating-point registers on task switch.
        noclflush       [BUGS=X86] Don't use the CLFLUSH instruction
-        nohlt           [BUGS=ARM]
+        nohlt           [BUGS=ARM,SH]
        no-hlt          [BUGS=X86-32] Tells the kernel that the hlt
                        instruction doesn't work correctly and not to
@@ -1388,6 +1491,12 @@ and is between 256 and 4096 characters. It is defined in the file
        nolapic_timer   [X86-32,APIC] Do not use the local APIC timer.
+        nox2apic        [X86-64,APIC] Do not enable x2APIC mode.
+        x2apic_phys     [X86-64,APIC] Use x2apic physical mode instead of
+                        default x2apic cluster mode on platforms
+                        supporting x2apic.
        noltlbs         [PPC] Do not use large page/tlb entries for kernel
                        lowmem mapping on PPC40x.
@@ -1507,7 +1616,7 @@ and is between 256 and 4096 characters. It is defined in the file
                        See also Documentation/paride.txt.
        pci=option[,option...]  [PCI] various PCI subsystem options:
-                off             [X86-32] don't probe for the PCI bus
+                off             [X86] don't probe for the PCI bus
                bios            [X86-32] force use of PCI BIOS, don't access
                                the hardware directly. Use this if your machine
                                has a non-standard PCI host bridge.
@@ -1515,9 +1624,9 @@ and is between 256 and 4096 characters. It is defined in the file
                                hardware access methods are allowed. Use this
                                if you experience crashes upon bootup and you
                                suspect they are caused by the BIOS.
-                conf1           [X86-32] Force use of PCI Configuration
+                conf1           [X86] Force use of PCI Configuration
                                Mechanism 1.
-                conf2           [X86-32] Force use of PCI Configuration
+                conf2           [X86] Force use of PCI Configuration
                                Mechanism 2.
                noaer           [PCIE] If the PCIEAER kernel config parameter is
                                enabled, this kernel boot option can be used to
@@ -1548,37 +1657,37 @@ and is between 256 and 4096 characters. It is defined in the file
                                this option if the kernel is unable to allocate
                                IRQs or discover secondary PCI buses on your
                                motherboard.
-                rom             [X86-32] Assign address space to expansion ROMs.
+                rom             [X86] Assign address space to expansion ROMs.
                                Use with caution as certain devices share
                                address decoders between ROMs and other
                                resources.
-                norom           [X86-32,X86_64] Do not assign address space to
+                norom           [X86] Do not assign address space to
                                expansion ROMs that do not already have
                                BIOS assigned address ranges.
-                irqmask=0xMMMM  [X86-32] Set a bit mask of IRQs allowed to be
+                irqmask=0xMMMM  [X86] Set a bit mask of IRQs allowed to be
                                assigned automatically to PCI devices. You can
                                make the kernel exclude IRQs of your ISA cards
                                this way.
-                pirqaddr=0xAAAAA        [X86-32] Specify the physical address
+                pirqaddr=0xAAAAA        [X86] Specify the physical address
                                of the PIRQ table (normally generated
                                by the BIOS) if it is outside the
                                F0000h-100000h range.
-                lastbus=N       [X86-32] Scan all buses thru bus #N. Can be
+                lastbus=N       [X86] Scan all buses thru bus #N. Can be
                                useful if the kernel is unable to find your
                                secondary buses and you want to tell it
                                explicitly which ones they are.
-                assign-busses   [X86-32] Always assign all PCI bus
+                assign-busses   [X86] Always assign all PCI bus
                                numbers ourselves, overriding
                                whatever the firmware may have done.
-                usepirqmask     [X86-32] Honor the possible IRQ mask stored
+                usepirqmask     [X86] Honor the possible IRQ mask stored
                                in the BIOS $PIR table. This is needed on
                                some systems with broken BIOSes, notably
                                some HP Pavilion N5400 and Omnibook XE3
                                notebooks. This will have no effect if ACPI
                                IRQ routing is enabled.
-                noacpi          [X86-32] Do not use ACPI for IRQ routing
+                noacpi          [X86] Do not use ACPI for IRQ routing
                                or for PCI scanning.
-                use_crs         [X86-32] Use _CRS for PCI resource
+                use_crs         [X86] Use _CRS for PCI resource
                                allocation.
                routeirq        Do IRQ routing for all PCI devices.
                                This is normally done in pci_enable_device(),
@@ -1607,6 +1716,12 @@ and is between 256 and 4096 characters. It is defined in the file
                                reserved for the CardBus bridge's memory
                                window. The default value is 64 megabytes.
+        pcie_aspm=      [PCIE] Forcibly enable or disable PCIe Active State Power
+                        Management.
+                off     Disable ASPM.
+                force   Enable ASPM even on devices that claim not to support it.
+                        WARNING: Forcing ASPM on may cause system lockups.
        pcmv=           [HW,PCMCIA] BadgePAD 4
        pd.             [PARIDE]
@@ -1634,6 +1749,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        Override pmtimer IOPort with a hex value.
                        e.g. pmtmr=0x508
+        pnp.debug       [PNP]
+                        Enable PNP debug messages.  This depends on the
+                        CONFIG_PNP_DEBUG_MESSAGES option.
        pnpacpi=        [ACPI]
                        { off }
@@ -1654,6 +1773,11 @@ and is between 256 and 4096 characters. It is defined in the file
                        autoconfiguration.
                        Ranges are in pairs (memory base and size).
+        dynamic_printk
+                        Enables pr_debug()/dev_dbg() calls if
+                        CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled. These can also
+                        be switched on/off via <debugfs>/dynamic_printk/modules
        print-fatal-signals=
                        [KNL] debug: print fatal signals
                        print-fatal-signals=1: print segfault info to
@@ -1856,6 +1980,12 @@ and is between 256 and 4096 characters. It is defined in the file
        shapers=        [NET]
                        Maximal number of shapers.
+        show_msr=       [x86] show boot-time MSR settings
+                        Format: { <integer> }
+                        Show boot-time (BIOS-initialized) MSR settings.
+                        The parameter means the number of CPUs to show,
+                        for example 1 means boot CPU only.
        sim710=         [SCSI,HW]
                        See header of drivers/scsi/sim710.c.
@@ -2038,6 +2168,9 @@ and is between 256 and 4096 characters. It is defined in the file
        snd-ymfpci=     [HW,ALSA]
+        softlockup_panic=
+                        [KNL] Should the soft-lockup detector generate panics.
        sonypi.*=       [HW] Sony Programmable I/O Control Device driver
                        See Documentation/sonypi.txt
@@ -2102,6 +2235,12 @@ and is between 256 and 4096 characters. It is defined in the file
        tdfx=           [HW,DRM]
+        test_suspend=   [SUSPEND]
+                        Specify "mem" (for Suspend-to-RAM) or "standby" (for
+                        standby suspend) as the system sleep state to briefly
+                        enter during system startup.  The system is woken from
+                        this state using a wakeup-capable RTC alarm.
        thash_entries=  [KNL,NET]
                        Set number of hash buckets for TCP connection
@@ -2111,7 +2250,7 @@ and is between 256 and 4096 characters. It is defined in the file
        thermal.crt=    [HW,ACPI]
                        -1: disable all critical trip points in all thermal zones
-                        <degrees C>: lower all critical trip points
+                        <degrees C>: override all critical trip points
        thermal.nocrt=  [HW,ACPI]
                        Set to disable actions on ACPI thermal zone
@@ -2129,13 +2268,6 @@ and is between 256 and 4096 characters. It is defined in the file
                        <deci-seconds>: poll all this frequency
                        0: no polling (default)
-        tipar.timeout=  [HW,PPT]
-                        Set communications timeout in tenths of a second
-                        (default 15).
-        tipar.delay=    [HW,PPT]
-                        Set inter-bit delay in microseconds (default 10).
        tmscsim=        [HW,SCSI]
                        See comment before function dc390_setup() in
                        drivers/scsi/tmscsim.c.
@@ -2169,6 +2301,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        Note that genuine overcurrent events won't be
                        reported either.
+        unknown_nmi_panic
+                        [X86-32,X86-64]
+                        Set unknown_nmi_panic=1 early on boot.
        usbcore.autosuspend=
                        [USB] The autosuspend time delay (in seconds) used
                        for newly-detected USB devices (default 2).  This
@@ -2176,6 +2312,25 @@ and is between 256 and 4096 characters. It is defined in the file
                        autosuspended.  Devices for which the delay is set
                        to a negative value won't be autosuspended at all.
+        usbcore.usbfs_snoop=
+                        [USB] Set to log all usbfs traffic (default 0 = off).
+        usbcore.blinkenlights=
+                        [USB] Set to cycle leds on hubs (default 0 = off).
+        usbcore.old_scheme_first=
+                        [USB] Start with the old device initialization
+                        scheme (default 0 = off).
+        usbcore.use_both_schemes=
+                        [USB] Try the other device initialization scheme
+                        if the first one fails (default 1 = enabled).
+        usbcore.initial_descriptor_timeout=
+                        [USB] Specifies timeout for the initial 64-byte
+                        USB_REQ_GET_DESCRIPTOR request in milliseconds
+                        (default 5000 = 5.0 seconds).
        usbhid.mousepoll=
                        [USBHID] The interval which mice are to be polled at.
diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index d5c7a57d1700..b56aacc1fff8 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -864,7 +864,7 @@ payload contents" for more information.
    request_key_with_auxdata() respectively.
    These two functions return with the key potentially still under
-    construction.  To wait for contruction completion, the following should be
+    construction.  To wait for construction completion, the following should be
    called:
        int wait_for_key_construction(struct key *key, bool intr);
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index 51a8021ee532..f5d2aad65a67 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -118,6 +118,10 @@ the name of the kobject, call kobject_rename():
    int kobject_rename(struct kobject *kobj, const char *new_name);
+Note kobject_rename does perform any locking or have a solid notion of
+what names are valid so the provide must provide their own sanity checking
+and serialization.
 There is a function called kobject_set_name() but that is legacy cruft and
 is being removed.  If your code needs to call this function, it is
 incorrect and needs to be fixed.
diff --git a/Documentation/laptops/acer-wmi.txt b/Documentation/laptops/acer-wmi.txt
index 69b5dd4e5a59..2b3a6b5260bf 100644
--- a/Documentation/laptops/acer-wmi.txt
+++ b/Documentation/laptops/acer-wmi.txt
@@ -1,7 +1,7 @@
 Acer Laptop WMI Extras Driver
 http://code.google.com/p/aceracpi
-Version 0.1
+Version 0.2
-9th February 2008
+18th August 2008
 Copyright 2007-2008 Carlos Corbacho <carlos@strangeworlds.co.uk>
@@ -87,17 +87,7 @@ acer-wmi come with built-in wireless. However, should you feel so inclined to
 ever wish to remove the card, or swap it out at some point, please get in touch
 with me, as we may well be able to gain some data on wireless card detection.
-To read the status of the wireless radio (0=off, 1=on):
+The wireless radio is exposed through rfkill.
-cat /sys/devices/platform/acer-wmi/wireless
-To enable the wireless radio:
-echo 1 > /sys/devices/platform/acer-wmi/wireless
-To disable the wireless radio:
-echo 0 > /sys/devices/platform/acer-wmi/wireless
-To set the state of the wireless radio when loading acer-wmi, pass:
-wireless=X (where X is 0 or 1)
 Bluetooth
 *********
@@ -117,17 +107,7 @@ For the adventurously minded - if you want to buy an internal bluetooth
 module off the internet that is compatible with your laptop and fit it, then
 it will work just fine with acer-wmi.
-To read the status of the bluetooth module (0=off, 1=on):
+Bluetooth is exposed through rfkill.
-cat /sys/devices/platform/acer-wmi/wireless
-To enable the bluetooth module:
-echo 1 > /sys/devices/platform/acer-wmi/bluetooth
-To disable the bluetooth module:
-echo 0 > /sys/devices/platform/acer-wmi/bluetooth
-To set the state of the bluetooth module when loading acer-wmi, pass:
-bluetooth=X (where X is 0 or 1)
 3G
 **
diff --git a/Documentation/laptops/disk-shock-protection.txt b/Documentation/laptops/disk-shock-protection.txt
new file mode 100644
index 000000000000..0e6ba2663834
--- /dev/null
+++ b/Documentation/laptops/disk-shock-protection.txt
@@ -0,0 +1,149 @@
+Hard disk shock protection
+==========================
+Author: Elias Oltmanns <eo@nebensachen.de>
+Last modified: 2008-10-03
+0. Contents
+-----------
+1. Intro
+2. The interface
+3. References
+4. CREDITS
+1. Intro
+--------
+ATA/ATAPI-7 specifies the IDLE IMMEDIATE command with unload feature.
+Issuing this command should cause the drive to switch to idle mode and
+unload disk heads. This feature is being used in modern laptops in
+conjunction with accelerometers and appropriate software to implement
+a shock protection facility. The idea is to stop all I/O operations on
+the internal hard drive and park its heads on the ramp when critical
+situations are anticipated. The desire to have such a feature
+available on GNU/Linux systems has been the original motivation to
+implement a generic disk head parking interface in the Linux kernel.
+Please note, however, that other components have to be set up on your
+system in order to get disk shock protection working (see
+section 3. References below for pointers to more information about
+that).
+2. The interface
+----------------
+For each ATA device, the kernel exports the file
+block/*/device/unload_heads in sysfs (here assumed to be mounted under
+/sys). Access to /sys/block/*/device/unload_heads is denied with
+-EOPNOTSUPP if the device does not support the unload feature.
+Otherwise, writing an integer value to this file will take the heads
+of the respective drive off the platter and block all I/O operations
+for the specified number of milliseconds. When the timeout expires and
+no further disk head park request has been issued in the meantime,
+normal operation will be resumed. The maximal value accepted for a
+timeout is 30000 milliseconds. Exceeding this limit will return
+-EOVERFLOW, but heads will be parked anyway and the timeout will be
+set to 30 seconds. However, you can always change a timeout to any
+value between 0 and 30000 by issuing a subsequent head park request
+before the timeout of the previous one has expired. In particular, the
+total timeout can exceed 30 seconds and, more importantly, you can
+cancel a previously set timeout and resume normal operation
+immediately by specifying a timeout of 0. Values below -2 are rejected
+with -EINVAL (see below for the special meaning of -1 and -2). If the
+timeout specified for a recent head park request has not yet expired,
+reading from /sys/block/*/device/unload_heads will report the number
+of milliseconds remaining until normal operation will be resumed;
+otherwise, reading the unload_heads attribute will return 0.
+For example, do the following in order to park the heads of drive
+/dev/sda and stop all I/O operations for five seconds:
+# echo 5000 > /sys/block/sda/device/unload_heads
+A simple
+# cat /sys/block/sda/device/unload_heads
+will show you how many milliseconds are left before normal operation
+will be resumed.
+A word of caution: The fact that the interface operates on a basis of
+milliseconds may raise expectations that cannot be satisfied in
+reality. In fact, the ATA specs clearly state that the time for an
+unload operation to complete is vendor specific. The hint in ATA-7
+that this will typically be within 500 milliseconds apparently has
+been dropped in ATA-8.
+There is a technical detail of this implementation that may cause some
+confusion and should be discussed here. When a head park request has
+been issued to a device successfully, all I/O operations on the
+controller port this device is attached to will be deferred. That is
+to say, any other device that may be connected to the same port will
+be affected too. The only exception is that a subsequent head unload
+request to that other device will be executed immediately. Further
+operations on that port will be deferred until the timeout specified
+for either device on the port has expired. As far as PATA (old style
+IDE) configurations are concerned, there can only be two devices
+attached to any single port. In SATA world we have port multipliers
+which means that a user-issued head parking request to one device may
+actually result in stopping I/O to a whole bunch of devices. However,
+since this feature is supposed to be used on laptops and does not seem
+to be very useful in any other environment, there will be mostly one
+device per port. Even if the CD/DVD writer happens to be connected to
+the same port as the hard drive, it generally *should* recover just
+fine from the occasional buffer under-run incurred by a head park
+request to the HD. Actually, when you are using an ide driver rather
+than its libata counterpart (i.e. your disk is called /dev/hda
+instead of /dev/sda), then parking the heads of one drive (drive X)
+will generally not affect the mode of operation of another drive
+(drive Y) on the same port as described above. It is only when a port
+reset is required to recover from an exception on drive Y that further
+I/O operations on that drive (and the reset itself) will be delayed
+until drive X is no longer in the parked state.
+Finally, there are some hard drives that only comply with an earlier
+version of the ATA standard than ATA-7, but do support the unload
+feature nonetheless. Unfortunately, there is no safe way Linux can
+detect these devices, so you won't be able to write to the
+unload_heads attribute. If you know that your device really does
+support the unload feature (for instance, because the vendor of your
+laptop or the hard drive itself told you so), then you can tell the
+kernel to enable the usage of this feature for that drive by writing
+the special value -1 to the unload_heads attribute:
+# echo -1 > /sys/block/sda/device/unload_heads
+will enable the feature for /dev/sda, and giving -2 instead of -1 will
+disable it again.
+3. References
+-------------
+There are several laptops from different vendors featuring shock
+protection capabilities. As manufacturers have refused to support open
+source development of the required software components so far, Linux
+support for shock protection varies considerably between different
+hardware implementations. Ideally, this section should contain a list
+of pointers at different projects aiming at an implementation of shock
+protection on different systems. Unfortunately, I only know of a
+single project which, although still considered experimental, is fit
+for use. Please feel free to add projects that have been the victims
+of my ignorance.
+- http://www.thinkwiki.org/wiki/HDAPS
+  See this page for information about Linux support of the hard disk
+  active protection system as implemented in IBM/Lenovo Thinkpads.
+4. CREDITS
+----------
+This implementation of disk head parking has been inspired by a patch
+originally published by Jon Escombe <lists@dresco.co.uk>. My efforts
+to develop an implementation of this feature that is fit to be merged
+into mainline have been aided by various kernel developers, in
+particular by Tejun Heo and Bartlomiej Zolnierkiewicz.
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 64b3f146e4b0..71f0fe1fc1b0 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -1,7 +1,7 @@
                     ThinkPad ACPI Extras Driver
-                            Version 0.20
+                            Version 0.21
-                          April 09th, 2008
+                           May 29th, 2008
               Borislav Deianov <borislav@users.sf.net>
             Henrique de Moraes Holschuh <hmh@hmh.eng.br>
@@ -44,7 +44,7 @@ detailed description):
        - LCD brightness control
        - Volume control
        - Fan control and monitoring: fan speed, fan enable/disable
-        - Experimental: WAN enable and disable
+        - WAN enable and disable
 A compatibility table by model and feature is maintained on the web
 site, http://ibm-acpi.sf.net/. I appreciate any success or failure
@@ -621,7 +621,8 @@ Bluetooth
 ---------
 procfs: /proc/acpi/ibm/bluetooth
-sysfs device attribute: bluetooth_enable
+sysfs device attribute: bluetooth_enable (deprecated)
+sysfs rfkill class: switch "tpacpi_bluetooth_sw"
 This feature shows the presence and current state of a ThinkPad
 Bluetooth device in the internal ThinkPad CDC slot.
@@ -643,8 +644,12 @@ Sysfs notes:
                0: disables Bluetooth / Bluetooth is disabled
                1: enables Bluetooth / Bluetooth is enabled.
-        Note: this interface will be probably be superseded by the
+        Note: this interface has been superseded by the generic rfkill
-        generic rfkill class, so it is NOT to be considered stable yet.
+        class.  It has been deprecated, and it will be removed in year
+        2010.
+        rfkill controller switch "tpacpi_bluetooth_sw": refer to
+        Documentation/rfkill.txt for details.
 Video output control -- /proc/acpi/ibm/video
 --------------------------------------------
@@ -1370,16 +1375,12 @@ with EINVAL, try to set pwm1_enable to 1 and pwm1 to at least 128 (255
 would be the safest choice, though).
-EXPERIMENTAL: WAN
+WAN
-----------------
+---
 procfs: /proc/acpi/ibm/wan
-sysfs device attribute: wwan_enable
+sysfs device attribute: wwan_enable (deprecated)
+sysfs rfkill class: switch "tpacpi_wwan_sw"
-This feature is marked EXPERIMENTAL because the implementation
-directly accesses hardware registers and may not work as expected. USE
-WITH CAUTION! To use this feature, you need to supply the
-experimental=1 parameter when loading the module.
 This feature shows the presence and current state of a W-WAN (Sierra
 Wireless EV-DO) device.
@@ -1404,8 +1405,12 @@ Sysfs notes:
                0: disables WWAN card / WWAN card is disabled
                1: enables WWAN card / WWAN card is enabled.
-        Note: this interface will be probably be superseded by the
+        Note: this interface has been superseded by the generic rfkill
-        generic rfkill class, so it is NOT to be considered stable yet.
+        class.  It has been deprecated, and it will be removed in year
+        2010.
+        rfkill controller switch "tpacpi_wwan_sw": refer to
+        Documentation/rfkill.txt for details.
 Multiple Commands, Module Parameters
 ------------------------------------
diff --git a/Documentation/leds-class.txt b/Documentation/leds-class.txt
index 18860ad9935a..6399557cdab3 100644
--- a/Documentation/leds-class.txt
+++ b/Documentation/leds-class.txt
@@ -59,7 +59,7 @@ Hardware accelerated blink of LEDs
 Some LEDs can be programmed to blink without any CPU interaction. To
 support this feature, a LED driver can optionally implement the
-blink_set() function (see <linux/leds.h>). If implemeted, triggers can
+blink_set() function (see <linux/leds.h>). If implemented, triggers can
 attempt to use it before falling back to software timers. The blink_set()
 function should return 0 if the blink setting is supported, or -EINVAL
 otherwise, which means that LED blinking will be handled by software.
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 82fafe0429fe..7228369d1014 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -36,11 +36,13 @@
 #include <sched.h>
 #include <limits.h>
 #include <stddef.h>
+#include <signal.h>
 #include "linux/lguest_launcher.h"
 #include "linux/virtio_config.h"
 #include "linux/virtio_net.h"
 #include "linux/virtio_blk.h"
 #include "linux/virtio_console.h"
+#include "linux/virtio_rng.h"
 #include "linux/virtio_ring.h"
 #include "asm-x86/bootparam.h"
 /*L:110 We can ignore the 39 include files we need for this program, but I do
@@ -64,8 +66,8 @@ typedef uint8_t u8;
 #endif
 /* We can have up to 256 pages for devices. */
 #define DEVICE_PAGES 256
-/* This will occupy 2 pages: it must be a power of 2. */
+/* This will occupy 3 pages: it must be a power of 2. */
-#define VIRTQUEUE_NUM 128
+#define VIRTQUEUE_NUM 256
 /*L:120 verbose is both a global flag and a macro.  The C preprocessor allows
 * this, and although I wouldn't recommend it, it works quite nicely here. */
@@ -74,12 +76,19 @@ static bool verbose;
        do { if (verbose) printf(args); } while(0)
 /*:*/
-/* The pipe to send commands to the waker process */
+/* File descriptors for the Waker. */
-static int waker_fd;
+struct {
+        int pipe[2];
+        int lguest_fd;
+} waker_fds;
 /* The pointer to the start of guest memory. */
 static void *guest_base;
 /* The maximum guest physical address allowed, and maximum possible. */
 static unsigned long guest_limit, guest_max;
+/* The pipe for signal hander to write to. */
+static int timeoutpipe[2];
+static unsigned int timeout_usec = 500;
 /* a per-cpu variable indicating whose vcpu is currently running */
 static unsigned int __thread cpu_id;
@@ -155,11 +164,14 @@ struct virtqueue
        /* Last available index we saw. */
        u16 last_avail_idx;
-        /* The routine to call when the Guest pings us. */
+        /* The routine to call when the Guest pings us, or timeout. */
-        void (*handle_output)(int fd, struct virtqueue *me);
+        void (*handle_output)(int fd, struct virtqueue *me, bool timeout);
        /* Outstanding buffers */
        unsigned int inflight;
+        /* Is this blocked awaiting a timer? */
+        bool blocked;
 };
 /* Remember the arguments to the program so we can "reboot" */
@@ -190,6 +202,9 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
        return iov->iov_base;
 }
+/* Wrapper for the last available index.  Makes it easier to change. */
+#define lg_last_avail(vq)       ((vq)->last_avail_idx)
 /* The virtio configuration space is defined to be little-endian.  x86 is
 * little-endian too, but it's nice to be explicit so we have these helpers. */
 #define cpu_to_le16(v16) (v16)
@@ -199,6 +214,33 @@ static void *_convert(struct iovec *iov, size_t size, size_t align,
 #define le32_to_cpu(v32) (v32)
 #define le64_to_cpu(v64) (v64)
+/* Is this iovec empty? */
+static bool iov_empty(const struct iovec iov[], unsigned int num_iov)
+{
+        unsigned int i;
+        for (i = 0; i < num_iov; i++)
+                if (iov[i].iov_len)
+                        return false;
+        return true;
+}
+/* Take len bytes from the front of this iovec. */
+static void iov_consume(struct iovec iov[], unsigned num_iov, unsigned len)
+{
+        unsigned int i;
+        for (i = 0; i < num_iov; i++) {
+                unsigned int used;
+                used = iov[i].iov_len < len ? iov[i].iov_len : len;
+                iov[i].iov_base += used;
+                iov[i].iov_len -= used;
+                len -= used;
+        }
+        assert(len == 0);
+}
 /* The device virtqueue descriptors are followed by feature bitmasks. */
 static u8 *get_feature_bits(struct device *dev)
 {
@@ -254,6 +296,7 @@ static void *map_zeroed_pages(unsigned int num)
                    PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, fd, 0);
        if (addr == MAP_FAILED)
                err(1, "Mmaping %u pages of /dev/zero", num);
+        close(fd);
        return addr;
 }
@@ -540,69 +583,64 @@ static void add_device_fd(int fd)
 * watch, but handing a file descriptor mask through to the kernel is fairly
 * icky.
 *
- * Instead, we fork off a process which watches the file descriptors and writes
+ * Instead, we clone off a thread which watches the file descriptors and writes
 * the LHREQ_BREAK command to the /dev/lguest file descriptor to tell the Host
 * stop running the Guest.  This causes the Launcher to return from the
 * /dev/lguest read with -EAGAIN, where it will write to /dev/lguest to reset
 * the LHREQ_BREAK and wake us up again.
 *
 * This, of course, is merely a different *kind* of icky.
+ *
+ * Given my well-known antipathy to threads, I'd prefer to use processes.  But
+ * it's easier to share Guest memory with threads, and trivial to share the
+ * devices.infds as the Launcher changes it.
 */
-static void wake_parent(int pipefd, int lguest_fd)
+static int waker(void *unused)
 {
-        /* Add the pipe from the Launcher to the fdset in the device_list, so
+        /* Close the write end of the pipe: only the Launcher has it open. */
-         * we watch it, too. */
+        close(waker_fds.pipe[1]);
-        add_device_fd(pipefd);
        for (;;) {
                fd_set rfds = devices.infds;
                unsigned long args[] = { LHREQ_BREAK, 1 };
+                unsigned int maxfd = devices.max_infd;
+                /* We also listen to the pipe from the Launcher. */
+                FD_SET(waker_fds.pipe[0], &rfds);
+                if (waker_fds.pipe[0] > maxfd)
+                        maxfd = waker_fds.pipe[0];
                /* Wait until input is ready from one of the devices. */
-                select(devices.max_infd+1, &rfds, NULL, NULL, NULL);
+                select(maxfd+1, &rfds, NULL, NULL, NULL);
-                /* Is it a message from the Launcher? */
-                if (FD_ISSET(pipefd, &rfds)) {
+                /* Message from Launcher? */
-                        int fd;
+                if (FD_ISSET(waker_fds.pipe[0], &rfds)) {
-                        /* If read() returns 0, it means the Launcher has
+                        char c;
-                         * exited.  We silently follow. */
+                        /* If this fails, then assume Launcher has exited.
-                        if (read(pipefd, &fd, sizeof(fd)) == 0)
+                         * Don't do anything on exit: we're just a thread! */
-                                exit(0);
+                        if (read(waker_fds.pipe[0], &c, 1) != 1)
-                        /* Otherwise it's telling us to change what file
+                                _exit(0);
-                         * descriptors we're to listen to.  Positive means
+                        continue;
-                         * listen to a new one, negative means stop
+                }
-                         * listening. */
-                        if (fd >= 0)
+                /* Send LHREQ_BREAK command to snap the Launcher out of it. */
-                                FD_SET(fd, &devices.infds);
+                pwrite(waker_fds.lguest_fd, args, sizeof(args), cpu_id);
-                        else
-                                FD_CLR(-fd - 1, &devices.infds);
-                } else /* Send LHREQ_BREAK command. */
-                        pwrite(lguest_fd, args, sizeof(args), cpu_id);
        }
+        return 0;
 }
 /* This routine just sets up a pipe to the Waker process. */
-static int setup_waker(int lguest_fd)
+static void setup_waker(int lguest_fd)
-{
+{
-        int pipefd[2], child;
+        /* This pipe is closed when Launcher dies, telling Waker. */
+        if (pipe(waker_fds.pipe) != 0)
-        /* We create a pipe to talk to the Waker, and also so it knows when the
+                err(1, "Creating pipe for Waker");
-         * Launcher dies (and closes pipe). */
-        pipe(pipefd);
+        /* Waker also needs to know the lguest fd */
-        child = fork();
+        waker_fds.lguest_fd = lguest_fd;
-        if (child == -1)
-                err(1, "forking");
-        if (child == 0) {
-                /* We are the Waker: close the "writing" end of our copy of the
-                 * pipe and start waiting for input. */
-                close(pipefd[1]);
-                wake_parent(pipefd[0], lguest_fd);
-        }
-        /* Close the reading end of our copy of the pipe. */
-        close(pipefd[0]);
-        /* Here is the fd used to talk to the waker. */
+        if (clone(waker, malloc(4096) + 4096, CLONE_VM | SIGCHLD, NULL) == -1)
-        return pipefd[1];
+                err(1, "Creating Waker");
 }
 /*
@@ -661,19 +699,22 @@ static unsigned get_vq_desc(struct virtqueue *vq,
                            unsigned int *out_num, unsigned int *in_num)
 {
        unsigned int i, head;
+        u16 last_avail;
        /* Check it isn't doing very strange things with descriptor numbers. */
-        if ((u16)(vq->vring.avail->idx - vq->last_avail_idx) > vq->vring.num)
+        last_avail = lg_last_avail(vq);
+        if ((u16)(vq->vring.avail->idx - last_avail) > vq->vring.num)
                errx(1, "Guest moved used index from %u to %u",
-                     vq->last_avail_idx, vq->vring.avail->idx);
+                     last_avail, vq->vring.avail->idx);
        /* If there's nothing new since last we looked, return invalid. */
-        if (vq->vring.avail->idx == vq->last_avail_idx)
+        if (vq->vring.avail->idx == last_avail)
                return vq->vring.num;
        /* Grab the next descriptor number they're advertising, and increment
         * the index we've seen. */
-        head = vq->vring.avail->ring[vq->last_avail_idx++ % vq->vring.num];
+        head = vq->vring.avail->ring[last_avail % vq->vring.num];
+        lg_last_avail(vq)++;
        /* If their number is silly, that's a fatal mistake. */
        if (head >= vq->vring.num)
@@ -821,8 +862,8 @@ static bool handle_console_input(int fd, struct device *dev)
                                unsigned long args[] = { LHREQ_BREAK, 0 };
                                /* Close the fd so Waker will know it has to
                                 * exit. */
-                                close(waker_fd);
+                                close(waker_fds.pipe[1]);
-                                /* Just in case waker is blocked in BREAK, send
+                                /* Just in case Waker is blocked in BREAK, send
                                 * unbreak now. */
                                write(fd, args, sizeof(args));
                                exit(2);
@@ -839,7 +880,7 @@ static bool handle_console_input(int fd, struct device *dev)
 /* Handling output for console is simple: we just get all the output buffers
 * and write them to stdout. */
-static void handle_console_output(int fd, struct virtqueue *vq)
+static void handle_console_output(int fd, struct virtqueue *vq, bool timeout)
 {
        unsigned int head, out, in;
        int len;
@@ -854,6 +895,24 @@ static void handle_console_output(int fd, struct virtqueue *vq)
        }
 }
+/* This is called when we no longer want to hear about Guest changes to a
+ * virtqueue.  This is more efficient in high-traffic cases, but it means we
+ * have to set a timer to check if any more changes have occurred. */
+static void block_vq(struct virtqueue *vq)
+{
+        struct itimerval itm;
+        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+        vq->blocked = true;
+        itm.it_interval.tv_sec = 0;
+        itm.it_interval.tv_usec = 0;
+        itm.it_value.tv_sec = 0;
+        itm.it_value.tv_usec = timeout_usec;
+        setitimer(ITIMER_REAL, &itm, NULL);
+}
 /*
 * The Network
 *
@@ -861,22 +920,39 @@ static void handle_console_output(int fd, struct virtqueue *vq)
 * and write them (ignoring the first element) to this device's file descriptor
 * (/dev/net/tun).
 */
-static void handle_net_output(int fd, struct virtqueue *vq)
+static void handle_net_output(int fd, struct virtqueue *vq, bool timeout)
 {
-        unsigned int head, out, in;
+        unsigned int head, out, in, num = 0;
        int len;
        struct iovec iov[vq->vring.num];
+        static int last_timeout_num;
        /* Keep getting output buffers from the Guest until we run out. */
        while ((head = get_vq_desc(vq, iov, &out, &in)) != vq->vring.num) {
                if (in)
                        errx(1, "Input buffers in output queue?");
-                /* Check header, but otherwise ignore it (we told the Guest we
+                len = writev(vq->dev->fd, iov, out);
-                 * supported no features, so it shouldn't have anything
+                if (len < 0)
-                 * interesting). */
+                        err(1, "Writing network packet to tun");
-                (void)convert(&iov[0], struct virtio_net_hdr);
-                len = writev(vq->dev->fd, iov+1, out-1);
                add_used_and_trigger(fd, vq, head, len);
+                num++;
+        }
+        /* Block further kicks and set up a timer if we saw anything. */
+        if (!timeout && num)
+                block_vq(vq);
+        /* We never quite know how long should we wait before we check the
+         * queue again for more packets.  We start at 500 microseconds, and if
+         * we get fewer packets than last time, we assume we made the timeout
+         * too small and increase it by 10 microseconds.  Otherwise, we drop it
+         * by one microsecond every time.  It seems to work well enough. */
+        if (timeout) {
+                if (num < last_timeout_num)
+                        timeout_usec += 10;
+                else if (timeout_usec > 1)
+                        timeout_usec--;
+                last_timeout_num = num;
        }
 }
@@ -887,7 +963,6 @@ static bool handle_tun_input(int fd, struct device *dev)
        unsigned int head, in_num, out_num;
        int len;
        struct iovec iov[dev->vq->vring.num];
-        struct virtio_net_hdr *hdr;
        /* First we need a network buffer from the Guests's recv virtqueue. */
        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
@@ -896,25 +971,23 @@ static bool handle_tun_input(int fd, struct device *dev)
                 * early, the Guest won't be ready yet.  Wait until the device
                 * status says it's ready. */
                /* FIXME: Actually want DRIVER_ACTIVE here. */
-                if (dev->desc->status & VIRTIO_CONFIG_S_DRIVER_OK)
-                        warn("network: no dma buffer!");
+                /* Now tell it we want to know if new things appear. */
+                dev->vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+                wmb();
                /* We'll turn this back on if input buffers are registered. */
                return false;
        } else if (out_num)
                errx(1, "Output buffers in network recv queue?");
-        /* First element is the header: we set it to 0 (no features). */
-        hdr = convert(&iov[0], struct virtio_net_hdr);
-        hdr->flags = 0;
-        hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
        /* Read the packet from the device directly into the Guest's buffer. */
-        len = readv(dev->fd, iov+1, in_num-1);
+        len = readv(dev->fd, iov, in_num);
        if (len <= 0)
                err(1, "reading network");
        /* Tell the Guest about the new packet. */
-        add_used_and_trigger(fd, dev->vq, head, sizeof(*hdr) + len);
+        add_used_and_trigger(fd, dev->vq, head, len);
        verbose("tun input packet len %i [%02x %02x] (%s)\n", len,
                ((u8 *)iov[1].iov_base)[0], ((u8 *)iov[1].iov_base)[1],
@@ -927,11 +1000,18 @@ static bool handle_tun_input(int fd, struct device *dev)
 /*L:215 This is the callback attached to the network and console input
 * virtqueues: it ensures we try again, in case we stopped console or net
 * delivery because Guest didn't have any buffers. */
-static void enable_fd(int fd, struct virtqueue *vq)
+static void enable_fd(int fd, struct virtqueue *vq, bool timeout)
 {
        add_device_fd(vq->dev->fd);
-        /* Tell waker to listen to it again */
+        /* Snap the Waker out of its select loop. */
-        write(waker_fd, &vq->dev->fd, sizeof(vq->dev->fd));
+        write(waker_fds.pipe[1], "", 1);
+}
+static void net_enable_fd(int fd, struct virtqueue *vq, bool timeout)
+{
+        /* We don't need to know again when Guest refills receive buffer. */
+        vq->vring.used->flags |= VRING_USED_F_NO_NOTIFY;
+        enable_fd(fd, vq, timeout);
 }
 /* When the Guest tells us they updated the status field, we handle it. */
@@ -951,7 +1031,7 @@ static void update_device_status(struct device *dev)
                for (vq = dev->vq; vq; vq = vq->next) {
                        memset(vq->vring.desc, 0,
                               vring_size(vq->config.num, getpagesize()));
-                        vq->last_avail_idx = 0;
+                        lg_last_avail(vq) = 0;
                }
        } else if (dev->desc->status & VIRTIO_CONFIG_S_FAILED) {
                warnx("Device %s configuration FAILED", dev->name);
@@ -960,10 +1040,10 @@ static void update_device_status(struct device *dev)
                verbose("Device %s OK: offered", dev->name);
                for (i = 0; i < dev->desc->feature_len; i++)
-                        verbose(" %08x", get_feature_bits(dev)[i]);
+                        verbose(" %02x", get_feature_bits(dev)[i]);
                verbose(", accepted");
                for (i = 0; i < dev->desc->feature_len; i++)
-                        verbose(" %08x", get_feature_bits(dev)
+                        verbose(" %02x", get_feature_bits(dev)
                                [dev->desc->feature_len+i]);
                if (dev->ready)
@@ -1000,7 +1080,7 @@ static void handle_output(int fd, unsigned long addr)
                        if (strcmp(vq->dev->name, "console") != 0)
                                verbose("Output to %s\n", vq->dev->name);
                        if (vq->handle_output)
-                                vq->handle_output(fd, vq);
+                                vq->handle_output(fd, vq, false);
                        return;
                }
        }
@@ -1014,6 +1094,29 @@ static void handle_output(int fd, unsigned long addr)
              strnlen(from_guest_phys(addr), guest_limit - addr));
 }
+static void handle_timeout(int fd)
+{
+        char buf[32];
+        struct device *i;
+        struct virtqueue *vq;
+        /* Clear the pipe */
+        read(timeoutpipe[0], buf, sizeof(buf));
+        /* Check each device and virtqueue: flush blocked ones. */
+        for (i = devices.dev; i; i = i->next) {
+                for (vq = i->vq; vq; vq = vq->next) {
+                        if (!vq->blocked)
+                                continue;
+                        vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+                        vq->blocked = false;
+                        if (vq->handle_output)
+                                vq->handle_output(fd, vq, true);
+                }
+        }
+}
 /* This is called when the Waker wakes us up: check for incoming file
 * descriptors. */
 static void handle_input(int fd)
@@ -1024,16 +1127,20 @@ static void handle_input(int fd)
        for (;;) {
                struct device *i;
                fd_set fds = devices.infds;
+                int num;
+                num = select(devices.max_infd+1, &fds, NULL, NULL, &poll);
+                /* Could get interrupted */
+                if (num < 0)
+                        continue;
                /* If nothing is ready, we're done. */
-                if (select(devices.max_infd+1, &fds, NULL, NULL, &poll) == 0)
+                if (num == 0)
                        break;
                /* Otherwise, call the device(s) which have readable file
                 * descriptors and a method of handling them.  */
                for (i = devices.dev; i; i = i->next) {
                        if (i->handle_input && FD_ISSET(i->fd, &fds)) {
-                                int dev_fd;
                                if (i->handle_input(fd, i))
                                        continue;
@@ -1043,13 +1150,12 @@ static void handle_input(int fd)
                                 * buffers to deliver into.  Console also uses
                                 * it when it discovers that stdin is closed. */
                                FD_CLR(i->fd, &devices.infds);
-                                /* Tell waker to ignore it too, by sending a
-                                 * negative fd number (-1, since 0 is a valid
-                                 * FD number). */
-                                dev_fd = -i->fd - 1;
-                                write(waker_fd, &dev_fd, sizeof(dev_fd));
                        }
                }
+                /* Is this the timeout fd? */
+                if (FD_ISSET(timeoutpipe[0], &fds))
+                        handle_timeout(fd);
        }
 }
@@ -1098,7 +1204,7 @@ static struct lguest_device_desc *new_dev_desc(u16 type)
 /* Each device descriptor is followed by the description of its virtqueues.  We
 * specify how many descriptors the virtqueue is to have. */
 static void add_virtqueue(struct device *dev, unsigned int num_descs,
-                          void (*handle_output)(int fd, struct virtqueue *me))
+                          void (*handle_output)(int, struct virtqueue *, bool))
 {
        unsigned int pages;
        struct virtqueue **i, *vq = malloc(sizeof(*vq));
@@ -1114,6 +1220,7 @@ static void add_virtqueue(struct device *dev, unsigned int num_descs,
        vq->last_avail_idx = 0;
        vq->dev = dev;
        vq->inflight = 0;
+        vq->blocked = false;
        /* Initialize the configuration. */
        vq->config.num = num_descs;
@@ -1246,6 +1353,24 @@ static void setup_console(void)
 }
 /*:*/
+static void timeout_alarm(int sig)
+{
+        write(timeoutpipe[1], "", 1);
+}
+static void setup_timeout(void)
+{
+        if (pipe(timeoutpipe) != 0)
+                err(1, "Creating timeout pipe");
+        if (fcntl(timeoutpipe[1], F_SETFL,
+                  fcntl(timeoutpipe[1], F_GETFL) | O_NONBLOCK) != 0)
+                err(1, "Making timeout pipe nonblocking");
+        add_device_fd(timeoutpipe[0]);
+        signal(SIGALRM, timeout_alarm);
+}
 /*M:010 Inter-guest networking is an interesting area.  Simplest is to have a
 * --sharenet=<name> option which opens or creates a named pipe.  This can be
 * used to send packets to another guest in a 1:1 manner.
@@ -1264,10 +1389,25 @@ static void setup_console(void)
 static u32 str2ip(const char *ipaddr)
 {
-        unsigned int byte[4];
+        unsigned int b[4];
+        if (sscanf(ipaddr, "%u.%u.%u.%u", &b[0], &b[1], &b[2], &b[3]) != 4)
+                errx(1, "Failed to parse IP address '%s'", ipaddr);
+        return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
+}
-        sscanf(ipaddr, "%u.%u.%u.%u", &byte[0], &byte[1], &byte[2], &byte[3]);
+static void str2mac(const char *macaddr, unsigned char mac[6])
-        return (byte[0] << 24) | (byte[1] << 16) | (byte[2] << 8) | byte[3];
+{
+        unsigned int m[6];
+        if (sscanf(macaddr, "%02x:%02x:%02x:%02x:%02x:%02x",
+                   &m[0], &m[1], &m[2], &m[3], &m[4], &m[5]) != 6)
+                errx(1, "Failed to parse mac address '%s'", macaddr);
+        mac[0] = m[0];
+        mac[1] = m[1];
+        mac[2] = m[2];
+        mac[3] = m[3];
+        mac[4] = m[4];
+        mac[5] = m[5];
 }
 /* This code is "adapted" from libbridge: it attaches the Host end of the
@@ -1288,6 +1428,7 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
                errx(1, "interface %s does not exist!", if_name);
        strncpy(ifr.ifr_name, br_name, IFNAMSIZ);
+        ifr.ifr_name[IFNAMSIZ-1] = '\0';
        ifr.ifr_ifindex = ifidx;
        if (ioctl(fd, SIOCBRADDIF, &ifr) < 0)
                err(1, "can't add %s to bridge %s", if_name, br_name);
@@ -1296,64 +1437,75 @@ static void add_to_bridge(int fd, const char *if_name, const char *br_name)
 /* This sets up the Host end of the network device with an IP address, brings
 * it up so packets will flow, the copies the MAC address into the hwaddr
 * pointer. */
-static void configure_device(int fd, const char *devname, u32 ipaddr,
+static void configure_device(int fd, const char *tapif, u32 ipaddr)
-                             unsigned char hwaddr[6])
 {
        struct ifreq ifr;
        struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
-        /* Don't read these incantations.  Just cut & paste them like I did! */
        memset(&ifr, 0, sizeof(ifr));
-        strcpy(ifr.ifr_name, devname);
+        strcpy(ifr.ifr_name, tapif);
+        /* Don't read these incantations.  Just cut & paste them like I did! */
        sin->sin_family = AF_INET;
        sin->sin_addr.s_addr = htonl(ipaddr);
        if (ioctl(fd, SIOCSIFADDR, &ifr) != 0)
-                err(1, "Setting %s interface address", devname);
+                err(1, "Setting %s interface address", tapif);
        ifr.ifr_flags = IFF_UP;
        if (ioctl(fd, SIOCSIFFLAGS, &ifr) != 0)
-                err(1, "Bringing interface %s up", devname);
+                err(1, "Bringing interface %s up", tapif);
-        /* SIOC stands for Socket I/O Control.  G means Get (vs S for Set
-         * above).  IF means Interface, and HWADDR is hardware address.
-         * Simple! */
-        if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
-                err(1, "getting hw address for %s", devname);
-        memcpy(hwaddr, ifr.ifr_hwaddr.sa_data, 6);
 }
-/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
+static int get_tun_device(char tapif[IFNAMSIZ])
- * routing, but the principle is the same: it uses the "tun" device to inject
- * packets into the Host as if they came in from a normal network card.  We
- * just shunt packets between the Guest and the tun device. */
-static void setup_tun_net(const char *arg)
 {
-        struct device *dev;
        struct ifreq ifr;
-        int netfd, ipfd;
+        int netfd;
-        u32 ip;
-        const char *br_name = NULL;
+        /* Start with this zeroed.  Messy but sure. */
-        struct virtio_net_config conf;
+        memset(&ifr, 0, sizeof(ifr));
        /* We open the /dev/net/tun device and tell it we want a tap device.  A
         * tap device is like a tun device, only somehow different.  To tell
         * the truth, I completely blundered my way through this code, but it
         * works now! */
        netfd = open_or_die("/dev/net/tun", O_RDWR);
-        memset(&ifr, 0, sizeof(ifr));
+        ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR;
-        ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
        strcpy(ifr.ifr_name, "tap%d");
        if (ioctl(netfd, TUNSETIFF, &ifr) != 0)
                err(1, "configuring /dev/net/tun");
+        if (ioctl(netfd, TUNSETOFFLOAD,
+                  TUN_F_CSUM|TUN_F_TSO4|TUN_F_TSO6|TUN_F_TSO_ECN) != 0)
+                err(1, "Could not set features for tun device");
        /* We don't need checksums calculated for packets coming in this
         * device: trust us! */
        ioctl(netfd, TUNSETNOCSUM, 1);
+        memcpy(tapif, ifr.ifr_name, IFNAMSIZ);
+        return netfd;
+}
+/*L:195 Our network is a Host<->Guest network.  This can either use bridging or
+ * routing, but the principle is the same: it uses the "tun" device to inject
+ * packets into the Host as if they came in from a normal network card.  We
+ * just shunt packets between the Guest and the tun device. */
+static void setup_tun_net(char *arg)
+{
+        struct device *dev;
+        int netfd, ipfd;
+        u32 ip = INADDR_ANY;
+        bool bridging = false;
+        char tapif[IFNAMSIZ], *p;
+        struct virtio_net_config conf;
+        netfd = get_tun_device(tapif);
        /* First we create a new network device. */
        dev = new_device("net", VIRTIO_ID_NET, netfd, handle_tun_input);
        /* Network devices need a receive and a send queue, just like
         * console. */
-        add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+        add_virtqueue(dev, VIRTQUEUE_NUM, net_enable_fd);
        add_virtqueue(dev, VIRTQUEUE_NUM, handle_net_output);
        /* We need a socket to perform the magic network ioctls to bring up the
@@ -1364,28 +1516,50 @@ static void setup_tun_net(const char *arg)
        /* If the command line was --tunnet=bridge:<name> do bridging. */
        if (!strncmp(BRIDGE_PFX, arg, strlen(BRIDGE_PFX))) {
-                ip = INADDR_ANY;
+                arg += strlen(BRIDGE_PFX);
-                br_name = arg + strlen(BRIDGE_PFX);
+                bridging = true;
-                add_to_bridge(ipfd, ifr.ifr_name, br_name);
+        }
-        } else /* It is an IP address to set up the device with */
+        /* A mac address may follow the bridge name or IP address */
+        p = strchr(arg, ':');
+        if (p) {
+                str2mac(p+1, conf.mac);
+                add_feature(dev, VIRTIO_NET_F_MAC);
+                *p = '\0';
+        }
+        /* arg is now either an IP address or a bridge name */
+        if (bridging)
+                add_to_bridge(ipfd, tapif, arg);
+        else
                ip = str2ip(arg);
-        /* Set up the tun device, and get the mac address for the interface. */
+        /* Set up the tun device. */
-        configure_device(ipfd, ifr.ifr_name, ip, conf.mac);
+        configure_device(ipfd, tapif, ip);
-        /* Tell Guest what MAC address to use. */
-        add_feature(dev, VIRTIO_NET_F_MAC);
        add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
+        /* Expect Guest to handle everything except UFO */
+        add_feature(dev, VIRTIO_NET_F_CSUM);
+        add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
+        add_feature(dev, VIRTIO_NET_F_GUEST_TSO4);
+        add_feature(dev, VIRTIO_NET_F_GUEST_TSO6);
+        add_feature(dev, VIRTIO_NET_F_GUEST_ECN);
+        add_feature(dev, VIRTIO_NET_F_HOST_TSO4);
+        add_feature(dev, VIRTIO_NET_F_HOST_TSO6);
+        add_feature(dev, VIRTIO_NET_F_HOST_ECN);
        set_config(dev, sizeof(conf), &conf);
        /* We don't need the socket any more; setup is done. */
        close(ipfd);
-        verbose("device %u: tun net %u.%u.%u.%u\n",
+        devices.device_num++;
-                devices.device_num++,
-                (u8)(ip>>24),(u8)(ip>>16),(u8)(ip>>8),(u8)ip);
+        if (bridging)
-        if (br_name)
+                verbose("device %u: tun %s attached to bridge: %s\n",
-                verbose("attached to bridge: %s\n", br_name);
+                        devices.device_num, tapif, arg);
+        else
+                verbose("device %u: tun %s: %s\n",
+                        devices.device_num, tapif, arg);
 }
 /* Our block (disk) device should be really simple: the Guest asks for a block
@@ -1550,7 +1724,7 @@ static bool handle_io_finish(int fd, struct device *dev)
 }
 /* When the Guest submits some I/O, we just need to wake the I/O thread. */
-static void handle_virtblk_output(int fd, struct virtqueue *vq)
+static void handle_virtblk_output(int fd, struct virtqueue *vq, bool timeout)
 {
        struct vblk_info *vblk = vq->dev->priv;
        char c = 0;
@@ -1621,6 +1795,64 @@ static void setup_block_file(const char *filename)
        verbose("device %u: virtblock %llu sectors\n",
                devices.device_num, le64_to_cpu(conf.capacity));
 }
+/* Our random number generator device reads from /dev/random into the Guest's
+ * input buffers.  The usual case is that the Guest doesn't want random numbers
+ * and so has no buffers although /dev/random is still readable, whereas
+ * console is the reverse.
+ *
+ * The same logic applies, however. */
+static bool handle_rng_input(int fd, struct device *dev)
+{
+        int len;
+        unsigned int head, in_num, out_num, totlen = 0;
+        struct iovec iov[dev->vq->vring.num];
+        /* First we need a buffer from the Guests's virtqueue. */
+        head = get_vq_desc(dev->vq, iov, &out_num, &in_num);
+        /* If they're not ready for input, stop listening to this file
+         * descriptor.  We'll start again once they add an input buffer. */
+        if (head == dev->vq->vring.num)
+                return false;
+        if (out_num)
+                errx(1, "Output buffers in rng?");
+        /* This is why we convert to iovecs: the readv() call uses them, and so
+         * it reads straight into the Guest's buffer.  We loop to make sure we
+         * fill it. */
+        while (!iov_empty(iov, in_num)) {
+                len = readv(dev->fd, iov, in_num);
+                if (len <= 0)
+                        err(1, "Read from /dev/random gave %i", len);
+                iov_consume(iov, in_num, len);
+                totlen += len;
+        }
+        /* Tell the Guest about the new input. */
+        add_used_and_trigger(fd, dev->vq, head, totlen);
+        /* Everything went OK! */
+        return true;
+}
+/* And this creates a "hardware" random number device for the Guest. */
+static void setup_rng(void)
+{
+        struct device *dev;
+        int fd;
+        fd = open_or_die("/dev/random", O_RDONLY);
+        /* The device responds to return from I/O thread. */
+        dev = new_device("rng", VIRTIO_ID_RNG, fd, handle_rng_input);
+        /* The device has one virtqueue, where the Guest places inbufs. */
+        add_virtqueue(dev, VIRTQUEUE_NUM, enable_fd);
+        verbose("device %u: rng\n", devices.device_num++);
+}
 /* That's the end of device setup. */
 /*L:230 Reboot is pretty easy: clean up and exec() the Launcher afresh. */
@@ -1628,11 +1860,12 @@ static void __attribute__((noreturn)) restart_guest(void)
 {
        unsigned int i;
-        /* Closing pipes causes the Waker thread and io_threads to die, and
+        /* Since we don't track all open fds, we simply close everything beyond
-         * closing /dev/lguest cleans up the Guest.  Since we don't track all
+         * stderr. */
-         * open fds, we simply close everything beyond stderr. */
        for (i = 3; i < FD_SETSIZE; i++)
                close(i);
+        /* The exec automatically gets rid of the I/O and Waker threads. */
        execv(main_args[0], main_args);
        err(1, "Could not exec %s", main_args[0]);
 }
@@ -1663,7 +1896,7 @@ static void __attribute__((noreturn)) run_guest(int lguest_fd)
                /* ERESTART means that we need to reboot the guest */
                } else if (errno == ERESTART) {
                        restart_guest();
-                /* EAGAIN means the Waker wanted us to look at some input.
+                /* EAGAIN means a signal (timeout).
                 * Anything else means a bug or incompatible change. */
                } else if (errno != EAGAIN)
                        err(1, "Running guest failed");
@@ -1691,13 +1924,14 @@ static struct option opts[] = {
        { "verbose", 0, NULL, 'v' },
        { "tunnet", 1, NULL, 't' },
        { "block", 1, NULL, 'b' },
+        { "rng", 0, NULL, 'r' },
        { "initrd", 1, NULL, 'i' },
        { NULL },
 };
 static void usage(void)
 {
        errx(1, "Usage: lguest [--verbose] "
-             "[--tunnet=(<ipaddr>|bridge:<bridgename>)\n"
+             "[--tunnet=(<ipaddr>:<macaddr>|bridge:<bridgename>:<macaddr>)\n"
             "|--block=<filename>|--initrd=<filename>]...\n"
             "<mem-in-mb> vmlinux [args...]");
 }
@@ -1765,6 +1999,9 @@ int main(int argc, char *argv[])
                case 'b':
                        setup_block_file(optarg);
                        break;
+                case 'r':
+                        setup_rng();
+                        break;
                case 'i':
                        initrd_name = optarg;
                        break;
@@ -1783,6 +2020,9 @@ int main(int argc, char *argv[])
        /* We always have a console device */
        setup_console();
+        /* We can timeout waiting for Guest network transmit. */
+        setup_timeout();
        /* Now we load the kernel */
        start = load_kernel(open_or_die(argv[optind+1], O_RDONLY));
@@ -1826,10 +2066,10 @@ int main(int argc, char *argv[])
         * /dev/lguest file descriptor. */
        lguest_fd = tell_kernel(pgdir, start);
-        /* We fork off a child process, which wakes the Launcher whenever one
+        /* We clone off a thread, which wakes the Launcher whenever one of the
-         * of the input file descriptors needs attention.  We call this the
+         * input file descriptors needs attention.  We call this the Waker, and
-         * Waker, and we'll cover it in a moment. */
+         * we'll cover it in a moment. */
-        waker_fd = setup_waker(lguest_fd);
+        setup_waker(lguest_fd);
        /* Finally, run the Guest.  This doesn't return. */
        run_guest(lguest_fd);
diff --git a/Documentation/local_ops.txt b/Documentation/local_ops.txt
index 4269a1105b37..f4f8b1c6c8ba 100644
--- a/Documentation/local_ops.txt
+++ b/Documentation/local_ops.txt
@@ -36,7 +36,7 @@ It can be done by slightly modifying the standard atomic operations : only
 their UP variant must be kept. It typically means removing LOCK prefix (on
 i386 and x86_64) and any SMP sychronization barrier. If the architecture does
 not have a different behavior between SMP and UP, including asm-generic/local.h
-in your archtecture's local.h is sufficient.
+in your architecture's local.h is sufficient.
 The local_t type is defined as an opaque signed long by embedding an
 atomic_long_t inside a structure. This is made so a cast from this type to a
diff --git a/Documentation/markers.txt b/Documentation/markers.txt
index d9f50a19fa0c..089f6138fcd9 100644
--- a/Documentation/markers.txt
+++ b/Documentation/markers.txt
@@ -50,10 +50,12 @@ Connecting a function (probe) to a marker is done by providing a probe (function
 to call) for the specific marker through marker_probe_register() and can be
 activated by calling marker_arm(). Marker deactivation can be done by calling
 marker_disarm() as many times as marker_arm() has been called. Removing a probe
-is done through marker_probe_unregister(); it will disarm the probe and make
+is done through marker_probe_unregister(); it will disarm the probe.
-sure there is no caller left using the probe when it returns. Probe removal is
+marker_synchronize_unregister() must be called before the end of the module exit
-preempt-safe because preemption is disabled around the probe call. See the
+function to make sure there is no caller left using the probe. This, and the
-"Probe example" section below for a sample probe module.
+fact that preemption is disabled around the probe call, make sure that probe
+removal and module unload are safe. See the "Probe example" section below for a
+sample probe module.
 The marker mechanism supports inserting multiple instances of the same marker.
 Markers can be put in inline functions, inlined static functions, and
diff --git a/Documentation/md.txt b/Documentation/md.txt
index a8b430627473..1da9d1b1793f 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -236,6 +236,11 @@ All md devices contain:
     writing the word for the desired state, however some states
     cannot be explicitly set, and some transitions are not allowed.
+     Select/poll works on this file.  All changes except between
+        active_idle and active (which can be frequent and are not
+        very interesting) are notified.  active->active_idle is
+        reported if the metadata is externally managed.
     clear
         No devices, no size, no level
         Writing is equivalent to STOP_ARRAY ioctl
@@ -292,6 +297,10 @@ Each directory contains:
              writemostly - device will only be subject to read
                         requests if there are no other options.
                         This applies only to raid1 arrays.
+              blocked  - device has failed, metadata is "external",
+                         and the failure hasn't been acknowledged yet.
+                         Writes that would write to this device if
+                         it were not faulty are blocked.
              spare    - device is working, but not a full member.
                         This includes spares that are in the process
                         of being recovered to
@@ -301,6 +310,12 @@ Each directory contains:
        Writing "remove" removes the device from the array.
        Writing "writemostly" sets the writemostly flag.
        Writing "-writemostly" clears the writemostly flag.
+        Writing "blocked" sets the "blocked" flag.
+        Writing "-blocked" clear the "blocked" flag and allows writes
+                to complete.
+        This file responds to select/poll. Any change to 'faulty'
+        or 'blocked' causes an event.
      errors
        An approximate count of read errors that have been detected on
@@ -332,7 +347,7 @@ Each directory contains:
        for storage of data.  This will normally be the same as the
        component_size.  This can be written while assembling an
        array.  If a value less than the current component_size is
-        written, component_size will be reduced to this value.
+        written, it will be rejected.
 An active md device will also contain and entry for each active device
@@ -381,6 +396,19 @@ also have
        'check' and 'repair' will start the appropriate process
           providing the current state is 'idle'.
+      This file responds to select/poll.  Any important change in the value
+      triggers a poll event.  Sometimes the value will briefly be
+      "recover" if a recovery seems to be needed, but cannot be
+      achieved. In that case, the transition to "recover" isn't
+      notified, but the transition away is.
+   degraded
+      This contains a count of the number of devices by which the
+      arrays is degraded.  So an optimal array with show '0'.  A
+      single failed/missing drive will show '1', etc.
+      This file responds to select/poll, any increase or decrease
+      in the count of missing devices will trigger an event.
   mismatch_count
      When performing 'check' and 'repair', and possibly when
      performing 'resync', md will count the number of errors that are
diff --git a/Documentation/moxa-smartio b/Documentation/moxa-smartio
index fe24ecc6372e..5337e80a5b96 100644
--- a/Documentation/moxa-smartio
+++ b/Documentation/moxa-smartio
@@ -1,14 +1,22 @@
 =============================================================================
+          MOXA Smartio/Industio Family Device Driver Installation Guide
-        MOXA Smartio Family Device Driver Ver 1.1 Installation Guide
+                    for Linux Kernel 2.4.x, 2.6.x
-                    for Linux Kernel 2.2.x and 2.0.3x
+               Copyright (C) 2008, Moxa Inc.
-               Copyright (C) 1999, Moxa Technologies Co, Ltd.
 =============================================================================
+Date: 01/21/2008
 Content
 1. Introduction
 2. System Requirement
 3. Installation
+   3.1 Hardware installation
+   3.2 Driver files
+   3.3 Device naming convention
+   3.4 Module driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x.
+   3.6 Custom configuration
+   3.7 Verify driver installation
 4. Utilities
 5. Setserial
 6. Troubleshooting
@@ -16,27 +24,48 @@ Content
 -----------------------------------------------------------------------------
 1. Introduction
-   The Smartio family Linux driver, Ver. 1.1, supports following multiport
+   The Smartio/Industio/UPCI family Linux driver supports following multiport
   boards.
-    -C104P/H/HS, C104H/PCI, C104HS/PCI, CI-104J 4 port multiport board.
+    - 2 ports multiport board
-    -C168P/H/HS, C168H/PCI 8 port multiport board.
+        CP-102U, CP-102UL, CP-102UF
+        CP-132U-I, CP-132UL,
-   This driver has been modified a little and cleaned up from the Moxa
+        CP-132, CP-132I, CP132S, CP-132IS,
-   contributed driver code and merged into Linux 2.2.14pre. In particular
+        CI-132, CI-132I, CI-132IS,
-   official major/minor numbers have been assigned which are different to
+        (C102H, C102HI, C102HIS, C102P, CP-102, CP-102S)
-   those the original Moxa supplied driver used.
+    - 4 ports multiport board
+        CP-104EL,
+        CP-104UL, CP-104JU,
+        CP-134U, CP-134U-I,
+        C104H/PCI, C104HS/PCI,
+        CP-114, CP-114I, CP-114S, CP-114IS, CP-114UL,
+        C104H, C104HS,
+        CI-104J, CI-104JS,
+        CI-134, CI-134I, CI-134IS,
+        (C114HI, CT-114I, C104P)
+        POS-104UL,
+        CB-114,
+        CB-134I
+    - 8 ports multiport board
+        CP-118EL, CP-168EL,
+        CP-118U, CP-168U,
+        C168H/PCI,
+        C168H, C168HS,
+        (C168P),
+        CB-108
   This driver and installation procedure have been developed upon Linux Kernel
-   2.2.5 and backward compatible to 2.0.3x. This driver supports Intel x86 and
+   2.4.x and 2.6.x. This driver supports Intel x86 hardware platform. In order
-   Alpha hardware platform. In order to maintain compatibility, this version
+   to maintain compatibility, this version has also been properly tested with
-   has also been properly tested with RedHat, OpenLinux, TurboLinux and
+   RedHat, Mandrake, Fedora and S.u.S.E Linux. However, if compatibility problem
-   S.u.S.E Linux. However, if compatibility problem occurs, please contact
+   occurs, please contact Moxa at support@moxa.com.tw.
-   Moxa at support@moxa.com.tw.
   In addition to device driver, useful utilities are also provided in this
   version. They are
-    - msdiag     Diagnostic program for detecting installed Moxa Smartio boards.
+    - msdiag     Diagnostic program for displaying installed Moxa
+                 Smartio/Industio boards.
    - msmon      Monitor program to observe data count and line status signals.
    - msterm     A simple terminal program which is useful in testing serial
                 ports.
@@ -47,8 +76,7 @@ Content
   GNU General Public License in this version. Please refer to GNU General
   Public License announcement in each source code file for more detail.
-   In Moxa's ftp sites, you may always find latest driver at
+   In Moxa's Web sites, you may always find latest driver at http://web.moxa.com.
-   ftp://ftp.moxa.com  or ftp://ftp.moxa.com.tw.
   This version of driver can be installed as Loadable Module (Module driver)
   or built-in into kernel (Static driver). You may refer to following
@@ -61,8 +89,8 @@ Content
 -----------------------------------------------------------------------------
 2. System Requirement
-   - Hardware platform: Intel x86 or Alpha machine
+   - Hardware platform: Intel x86 machine
-   - Kernel version: 2.0.3x or 2.2.x
+   - Kernel version: 2.4.x or 2.6.x
   - gcc version 2.72 or later
   - Maximum 4 boards can be installed in combination
@@ -70,9 +98,18 @@ Content
 3. Installation
   3.1 Hardware installation
+   3.2 Driver files
+   3.3 Device naming convention
+   3.4 Module driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x, 2.6.x.
+   3.6 Custom configuration
+   3.7 Verify driver installation
+   3.1 Hardware installation
-       There are two types of buses, ISA and PCI, for Smartio family multiport
+       There are two types of buses, ISA and PCI, for Smartio/Industio
-       board.
+       family multiport board.
       ISA board
       ---------
@@ -81,47 +118,57 @@ Content
       installation procedure in User's Manual before proceed any further.
       Please make sure the JP1 is open after the ISA board is set properly.
-       PCI board
+       PCI/UPCI board
-       ---------
+       --------------
       You may need to adjust IRQ usage in BIOS to avoid from IRQ conflict
       with other ISA devices. Please refer to hardware installation
       procedure in User's Manual in advance.
-       IRQ Sharing
+       PCI IRQ Sharing
       -----------
       Each port within the same multiport board shares the same IRQ. Up to
-       4 Moxa Smartio Family multiport boards can be installed together on
+       4 Moxa Smartio/Industio PCI Family multiport boards can be installed
-       one system and they can share the same IRQ.
+       together on one system and they can share the same IRQ.
-   3.2 Driver files and device naming convention
+   3.2 Driver files
       The driver file may be obtained from ftp, CD-ROM or floppy disk. The
       first step, anyway, is to copy driver file "mxser.tgz" into specified
       directory. e.g. /moxa. The execute commands as below.
+       # cd /
+       # mkdir moxa
       # cd /moxa
-       # tar xvf /dev/fd0 
+       # tar xvf /dev/fd0
       or
+       # cd /
+       # mkdir moxa
       # cd /moxa
       # cp /mnt/cdrom/<driver directory>/mxser.tgz .
       # tar xvfz mxser.tgz
+   3.3 Device naming convention
       You may find all the driver and utilities files in /moxa/mxser.
       Following installation procedure depends on the model you'd like to
-       run the driver. If you prefer module driver, please refer to 3.3.
+       run the driver. If you prefer module driver, please refer to 3.4.
-       If static driver is required, please refer to 3.4.
+       If static driver is required, please refer to 3.5.
       Dialin and callout port
       -----------------------
-       This driver remains traditional serial device properties. There're
+       This driver remains traditional serial device properties. There are
       two special file name for each serial port. One is dial-in port
       which is named "ttyMxx". For callout port, the naming convention
       is "cumxx".
       Device naming when more than 2 boards installed
       -----------------------------------------------
-       Naming convention for each Smartio multiport board is pre-defined
+       Naming convention for each Smartio/Industio multiport board is
-       as below.
+       pre-defined as below.
       Board Num.        Dial-in Port         Callout port
       1st board        ttyM0  - ttyM7        cum0  - cum7
@@ -129,6 +176,12 @@ Content
       3rd board        ttyM16 - ttyM23       cum16 - cum23
       4th board        ttyM24 - ttym31       cum24 - cum31
+       !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
+       Under Kernel 2.6 the cum Device is Obsolete. So use ttyM*
+       device instead.
+       !!!!!!!!!!!!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
       Board sequence
       --------------
       This driver will activate ISA boards according to the parameter set
@@ -138,69 +191,131 @@ Content
       For PCI boards, their sequence will be after ISA boards and C168H/PCI
       has higher priority than C104H/PCI boards.
-   3.3 Module driver configuration
+   3.4 Module driver configuration
       Module driver is easiest way to install. If you prefer static driver
       installation, please skip this paragraph.
-       1. Find "Makefile" in /moxa/mxser, then run
-          # make install
+       ------------- Prepare to use the MOXA driver--------------------
+       3.4.1 Create tty device with correct major number
+          Before using MOXA driver, your system must have the tty devices
+          which are created with driver's major number. We offer one shell
+          script "msmknod" to simplify the procedure.
+          This step is only needed to be executed once. But you still
+          need to do this procedure when:
+          a. You change the driver's major number. Please refer the "3.7"
+             section.
+          b. Your total installed MOXA boards number is changed. Maybe you
+             add/delete one MOXA board.
+          c. You want to change the tty name. This needs to modify the
+             shell script "msmknod"
+          The procedure is:
+          # cd /moxa/mxser/driver
+          # ./msmknod
+          This shell script will require the major number for dial-in
+          device and callout device to create tty device. You also need
+          to specify the total installed MOXA board number. Default major
+          numbers for dial-in device and callout device are 30, 35. If
+          you need to change to other number, please refer section "3.7"
+          for more detailed procedure.
+          Msmknod will delete any special files occupying the same device
+          naming.
+       3.4.2 Build the MOXA driver and utilities
+          Before using the MOXA driver and utilities, you need compile the
+          all the source code. This step is only need to be executed once.
+          But you still re-compile the source code if you modify the source
+          code. For example, if you change the driver's major number (see
+          "3.7" section), then you need to do this step again.
+          Find "Makefile" in /moxa/mxser, then run
+          # make clean; make install
+          !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!
+          For Red Hat 9, Red Hat Enterprise Linux AS3/ES3/WS3 & Fedora Core1:
+          # make clean; make installsp1
+          For Red Hat Enterprise Linux AS4/ES4/WS4:
+          # make clean; make installsp2
+          !!!!!!!!!! NOTE !!!!!!!!!!!!!!!!!
          The driver files "mxser.o" and utilities will be properly compiled
-          and copied to system directories respectively.Then run
+          and copied to system directories respectively.
-          # insmod mxser
+       ------------- Load MOXA driver--------------------
+       3.4.3 Load the MOXA driver
-          to activate the modular driver. You may run "lsmod" to check
+          # modprobe mxser <argument>
-          if "mxser.o" is activated.
-       2. Create special files by executing "msmknod".
+          will activate the module driver. You may run "lsmod" to check
-          # cd /moxa/mxser/driver
+          if "mxser" is activated. If the MOXA board is ISA board, the
-          # ./msmknod
+          <argument> is needed. Please refer to section "3.4.5" for more
+          information.
+       ------------- Load MOXA driver on boot --------------------
+       3.4.4 For the above description, you may manually execute
+          "modprobe mxser" to activate this driver and run
+          "rmmod mxser" to remove it.
+          However, it's better to have a boot time configuration to
+          eliminate manual operation. Boot time configuration can be
+          achieved by rc file. We offer one "rc.mxser" file to simplify
+          the procedure under "moxa/mxser/driver".
-          Default major numbers for dial-in device and callout device are
+          But if you use ISA board, please modify the "modprobe ..." command
-          174, 175. Msmknod will delete any special files occupying the same
+          to add the argument (see "3.4.5" section). After modifying the
-          device naming.
+          rc.mxser, please try to execute "/moxa/mxser/driver/rc.mxser"
+          manually to make sure the modification is ok. If any error
+          encountered, please try to modify again. If the modification is
+          completed, follow the below step.
-       3. Up to now, you may manually execute "insmod mxser" to activate
+          Run following command for setting rc files.
-          this driver and run "rmmod mxser" to remove it. However, it's
-          better to have a boot time configuration to eliminate manual
-          operation.
-          Boot time configuration can be achieved by rc file. Run following
-          command for setting rc files.
          # cd /moxa/mxser/driver
          # cp ./rc.mxser /etc/rc.d
          # cd /etc/rc.d
-          You may have to modify part of the content in rc.mxser to specify
+          Check "rc.serial" is existed or not. If "rc.serial" doesn't exist,
-          parameters for ISA board. Please refer to rc.mxser for more detail.
+          create it by vi, run "chmod 755 rc.serial" to change the permission.
-          Find "rc.serial". If "rc.serial" doesn't exist, create it by vi.
+          Add "/etc/rc.d/rc.mxser" in last line,
-          Add "rc.mxser" in last line. Next, open rc.local by vi
-          and append following content.
-          if [ -f /etc/rc.d/rc.serial ]; then
+          Reboot and check if moxa.o activated by "lsmod" command.
-             sh /etc/rc.d/rc.serial
-          fi
-       4. Reboot and check if mxser.o activated by "lsmod" command.
+       3.4.5. If you'd like to drive Smartio/Industio ISA boards in the system,
-       5. If you'd like to drive Smartio ISA boards in the system, you'll
+          you'll have to add parameter to specify CAP address of given
-          have to add parameter to specify CAP address of given board while
+          board while activating "mxser.o". The format for parameters are
-          activating "mxser.o". The format for parameters are as follows.
+          as follows.
-          insmod mxser ioaddr=0x???,0x???,0x???,0x???
+          modprobe mxser ioaddr=0x???,0x???,0x???,0x???
                                |      |     |    |
                                |      |     |    +- 4th ISA board
                                |      |     +------ 3rd ISA board
                                |      +------------ 2nd ISA board
                                +------------------- 1st ISA board
-   3.4 Static driver configuration
+   3.5 Static driver configuration for Linux kernel 2.4.x and 2.6.x
+       Note: To use static driver, you must install the linux kernel
+             source package.
+       3.5.1 Backup the built-in driver in the kernel.
+          # cd /usr/src/linux/drivers/char
+          # mv mxser.c mxser.c.old
+          For Red Hat 7.x user, you need to create link:
+          # cd /usr/src
+          # ln -s linux-2.4 linux
-       1. Create link
+       3.5.2 Create link
          # cd /usr/src/linux/drivers/char
          # ln -s /moxa/mxser/driver/mxser.c mxser.c
-       2. Add CAP address list for ISA boards
+       3.5.3 Add CAP address list for ISA boards. For PCI boards user,
+          please skip this step.
          In module mode, the CAP address for ISA board is given by
          parameter. In static driver configuration, you'll have to
          assign it within driver's source code. If you will not
@@ -222,73 +337,55 @@ Content
             static int mxserBoardCAP[]
             = {0x280, 0x180, 0x00, 0x00};
-       3. Modify tty_io.c
+       3.5.4 Setup kernel configuration
-          # cd /usr/src/linux/drivers/char/
-          # vi tty_io.c
-            Find pty_init(), insert "mxser_init()" as
-            pty_init();
+          Configure the kernel:
-            mxser_init();
-       4. Modify tty.h
+            # cd /usr/src/linux
-          # cd /usr/src/linux/include/linux
+            # make menuconfig
-          # vi tty.h
-            Find extern int tty_init(void), insert "mxser_init()" as
-            extern int tty_init(void);
+          You will go into a menu-driven system. Please select [Character
-            extern int mxser_init(void);
+          devices][Non-standard serial port support], enable the [Moxa
-     
+          SmartIO support] driver with "[*]" for built-in (not "[M]"), then
-       5. Modify Makefile
+          select [Exit] to exit this program.
-          # cd /usr/src/linux/drivers/char
-          # vi Makefile
-            Find L_OBJS := tty_io.o ...... random.o, add
-            "mxser.o" at last of this line as
-            L_OBJS := tty_io.o ....... mxser.o
-       6. Rebuild kernel
+       3.5.5 Rebuild kernel
-          The following are for Linux kernel rebuilding,for your reference only.
+          The following are for Linux kernel rebuilding, for your
+          reference only.
          For appropriate details, please refer to the Linux document.
-          If 'lilo' utility is installed, please use 'make zlilo' to rebuild
-          kernel. If 'lilo' is not installed, please follow the following steps.
           a. cd /usr/src/linux
-           b. make clean                             /* take a few minutes */
+           b. make clean             /* take a few minutes */
-           c. make bzImage                 /* take probably 10-20 minutes */
+           c. make dep               /* take a few minutes */
-           d. Backup original boot kernel.                /* optional step */
+           d. make bzImage           /* take probably 10-20 minutes */
-           e. cp /usr/src/linux/arch/i386/boot/bzImage /boot/vmlinuz
+           e. make install           /* copy boot image to correct position */
           f. Please make sure the boot kernel (vmlinuz) is in the
-              correct position. If you use 'lilo' utility, you should
+              correct position.
-              check /etc/lilo.conf 'image' item specified the path
+           g. If you use 'lilo' utility, you should check /etc/lilo.conf
-              which is the 'vmlinuz' path, or you will load wrong
+              'image' item specified the path which is the 'vmlinuz' path,
-              (or old) boot kernel image (vmlinuz).
+              or you will load wrong (or old) boot kernel image (vmlinuz).
-           g. chmod 400 /vmlinuz
+              After checking /etc/lilo.conf, please run "lilo".
-           h. lilo
-           i. rdev -R /vmlinuz 1
+          Note that if the result of "make bzImage" is ERROR, then you have to
-           j. sync
+          go back to Linux configuration Setup. Type "make menuconfig" in
+          directory /usr/src/linux.
-          Note that if the result of "make zImage" is ERROR, then you have to
-          go back to Linux configuration Setup. Type "make config" in directory
-          /usr/src/linux or "setup".
+       3.5.6 Make tty device and special file
-          Since system include file, /usr/src/linux/include/linux/interrupt.h,
-          is modified each time the MOXA driver is installed, kernel rebuilding
-          is inevitable. And it takes about 10 to 20 minutes depends on the
-          machine.
-       7. Make utility
-          # cd /moxa/mxser/utility
-          # make install
-       
-       8. Make special file
          # cd /moxa/mxser/driver
          # ./msmknod
-       9. Reboot
+       3.5.7 Make utility
+          # cd /moxa/mxser/utility
+          # make clean; make install
+       3.5.8 Reboot
-   3.5 Custom configuration
+   3.6 Custom configuration
       Although this driver already provides you default configuration, you
-       still can change the device name and major number.The instruction to
+       still can change the device name and major number. The instruction to
       change these parameters are shown as below.
       Change Device name
@@ -306,33 +403,37 @@ Content
       2 free major numbers for this driver. There are 3 steps to change
       major numbers.
-       1. Find free major numbers
+       3.6.1 Find free major numbers
          In /proc/devices, you may find all the major numbers occupied
          in the system. Please select 2 major numbers that are available.
          e.g. 40, 45.
-       2. Create special files
+       3.6.2 Create special files
          Run /moxa/mxser/driver/msmknod to create special files with
          specified major numbers.
-       3. Modify driver with new major number
+       3.6.3 Modify driver with new major number
          Run vi to open /moxa/mxser/driver/mxser.c. Locate the line
          contains "MXSERMAJOR". Change the content as below.
          #define         MXSERMAJOR              40
          #define         MXSERCUMAJOR            45
-       4. Run # make install in /moxa/mxser/driver.
+       3.6.4 Run "make clean; make install" in /moxa/mxser/driver.
-   3.6 Verify driver installation
+   3.7 Verify driver installation
       You may refer to /var/log/messages to check the latest status
       log reported by this driver whenever it's activated.
 -----------------------------------------------------------------------------
 4. Utilities
   There are 3 utilities contained in this driver. They are msdiag, msmon and
   msterm. These 3 utilities are released in form of source code. They should
   be compiled into executable file and copied into /usr/bin.
+   Before using these utilities, please load driver (refer 3.4 & 3.5) and
+   make sure you had run the "msmknod" utility.
   msdiag - Diagnostic
   --------------------
-   This utility provides the function to detect what Moxa Smartio multiport
+   This utility provides the function to display what Moxa Smartio/Industio
-   board exists in the system.
+   board found by driver in the system.
   msmon - Port Monitoring
   -----------------------
@@ -353,12 +454,13 @@ Content
   application, for example, sending AT command to a modem connected to the
   port or used as a terminal for login purpose. Note that this is only a
   dumb terminal emulation without handling full screen operation.
 -----------------------------------------------------------------------------
 5. Setserial
   Supported Setserial parameters are listed as below.
-   uart           set UART type(16450-->disable FIFO, 16550A-->enable FIFO)
+   uart           set UART type(16450-->disable FIFO, 16550A-->enable FIFO)
   close_delay    set the amount of time(in 1/100 of a second) that DTR
                  should be kept low while being closed.
   closing_wait   set the amount of time(in 1/100 of a second) that the
@@ -366,7 +468,13 @@ Content
                  being closed, before the receiver is disable.
   spd_hi         Use  57.6kb  when  the application requests 38.4kb.
   spd_vhi        Use  115.2kb  when  the application requests 38.4kb.
+   spd_shi        Use  230.4kb  when  the application requests 38.4kb.
+   spd_warp       Use  460.8kb  when  the application requests 38.4kb.
   spd_normal     Use  38.4kb  when  the application requests 38.4kb.
+   spd_cust       Use  the custom divisor to set the speed when  the
+                  application requests 38.4kb.
+   divisor        This option set the custom divison.
+   baud_base      This option set the base baud rate.
 -----------------------------------------------------------------------------
 6. Troubleshooting
@@ -375,8 +483,9 @@ Content
   possible. If all the possible solutions fail, please contact our technical
   support team to get more help.
-   Error msg: More than 4 Moxa Smartio family boards found. Fifth board and
-              after are ignored.
+   Error msg: More than 4 Moxa Smartio/Industio family boards found. Fifth board
+              and after are ignored.
   Solution:
   To avoid this problem, please unplug fifth and after board, because Moxa
   driver supports up to 4 boards.
@@ -384,7 +493,7 @@ Content
   Error msg: Request_irq fail, IRQ(?) may be conflict with another device.
   Solution:
   Other PCI or ISA devices occupy the assigned IRQ. If you are not sure
-   which device causes the situation,please check /proc/interrupts to find
+   which device causes the situation, please check /proc/interrupts to find
   free IRQ and simply change another free IRQ for Moxa board.
   Error msg: Board #: C1xx Series(CAP=xxx) interrupt number invalid.
@@ -397,15 +506,18 @@ Content
   Moxa ISA board needs an interrupt vector.Please refer to user's manual
   "Hardware Installation" chapter to set interrupt vector.
-   Error msg: Couldn't install MOXA Smartio family driver!
+   Error msg: Couldn't install MOXA Smartio/Industio family driver!
   Solution:
   Load Moxa driver fail, the major number may conflict with other devices.
-   Please refer to previous section 3.5 to change a free major number for
+   Please refer to previous section 3.7 to change a free major number for
   Moxa driver.
-   Error msg: Couldn't install MOXA Smartio family callout driver!
+   Error msg: Couldn't install MOXA Smartio/Industio family callout driver!
   Solution:
   Load Moxa callout driver fail, the callout device major number may
-   conflict with other devices. Please refer to previous section 3.5 to
+   conflict with other devices. Please refer to previous section 3.7 to
   change a free callout device major number for Moxa driver.
 -----------------------------------------------------------------------------
diff --git a/Documentation/mtd/nand_ecc.txt b/Documentation/mtd/nand_ecc.txt
new file mode 100644
index 000000000000..bdf93b7f0f24
--- /dev/null
+++ b/Documentation/mtd/nand_ecc.txt
@@ -0,0 +1,714 @@
+Introduction
+============
+Having looked at the linux mtd/nand driver and more specific at nand_ecc.c
+I felt there was room for optimisation. I bashed the code for a few hours
+performing tricks like table lookup removing superfluous code etc.
+After that the speed was increased by 35-40%.
+Still I was not too happy as I felt there was additional room for improvement.
+Bad! I was hooked.
+I decided to annotate my steps in this file. Perhaps it is useful to someone
+or someone learns something from it.
+The problem
+===========
+NAND flash (at least SLC one) typically has sectors of 256 bytes.
+However NAND flash is not extremely reliable so some error detection
+(and sometimes correction) is needed.
+This is done by means of a Hamming code. I'll try to explain it in
+laymans terms (and apologies to all the pro's in the field in case I do
+not use the right terminology, my coding theory class was almost 30
+years ago, and I must admit it was not one of my favourites).
+As I said before the ecc calculation is performed on sectors of 256
+bytes. This is done by calculating several parity bits over the rows and
+columns. The parity used is even parity which means that the parity bit = 1
+if the data over which the parity is calculated is 1 and the parity bit = 0
+if the data over which the parity is calculated is 0. So the total
+number of bits over the data over which the parity is calculated + the
+parity bit is even. (see wikipedia if you can't follow this).
+Parity is often calculated by means of an exclusive or operation,
+sometimes also referred to as xor. In C the operator for xor is ^
+Back to ecc.
+Let's give a small figure:
+byte   0:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp2 rp4 ... rp14
+byte   1:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp2 rp4 ... rp14
+byte   2:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp3 rp4 ... rp14
+byte   3:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp3 rp4 ... rp14
+byte   4:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp2 rp5 ... rp14
+....
+byte 254:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp0 rp3 rp5 ... rp15
+byte 255:  bit7 bit6 bit5 bit4 bit3 bit2 bit1 bit0   rp1 rp3 rp5 ... rp15
+           cp1  cp0  cp1  cp0  cp1  cp0  cp1  cp0
+           cp3  cp3  cp2  cp2  cp3  cp3  cp2  cp2
+           cp5  cp5  cp5  cp5  cp4  cp4  cp4  cp4
+This figure represents a sector of 256 bytes.
+cp is my abbreviaton for column parity, rp for row parity.
+Let's start to explain column parity.
+cp0 is the parity that belongs to all bit0, bit2, bit4, bit6.
+so the sum of all bit0, bit2, bit4 and bit6 values + cp0 itself is even.
+Similarly cp1 is the sum of all bit1, bit3, bit5 and bit7.
+cp2 is the parity over bit0, bit1, bit4 and bit5
+cp3 is the parity over bit2, bit3, bit6 and bit7.
+cp4 is the parity over bit0, bit1, bit2 and bit3.
+cp5 is the parity over bit4, bit5, bit6 and bit7.
+Note that each of cp0 .. cp5 is exactly one bit.
+Row parity actually works almost the same.
+rp0 is the parity of all even bytes (0, 2, 4, 6, ... 252, 254)
+rp1 is the parity of all odd bytes (1, 3, 5, 7, ..., 253, 255)
+rp2 is the parity of all bytes 0, 1, 4, 5, 8, 9, ...
+(so handle two bytes, then skip 2 bytes).
+rp3 is covers the half rp2 does not cover (bytes 2, 3, 6, 7, 10, 11, ...)
+for rp4 the rule is cover 4 bytes, skip 4 bytes, cover 4 bytes, skip 4 etc.
+so rp4 calculates parity over bytes 0, 1, 2, 3, 8, 9, 10, 11, 16, ...)
+and rp5 covers the other half, so bytes 4, 5, 6, 7, 12, 13, 14, 15, 20, ..
+The story now becomes quite boring. I guess you get the idea.
+rp6 covers 8 bytes then skips 8 etc
+rp7 skips 8 bytes then covers 8 etc
+rp8 covers 16 bytes then skips 16 etc
+rp9 skips 16 bytes then covers 16 etc
+rp10 covers 32 bytes then skips 32 etc
+rp11 skips 32 bytes then covers 32 etc
+rp12 covers 64 bytes then skips 64 etc
+rp13 skips 64 bytes then covers 64 etc
+rp14 covers 128 bytes then skips 128
+rp15 skips 128 bytes then covers 128
+In the end the parity bits are grouped together in three bytes as
+follows:
+ECC    Bit 7 Bit 6 Bit 5 Bit 4 Bit 3 Bit 2 Bit 1 Bit 0
+ECC 0   rp07  rp06  rp05  rp04  rp03  rp02  rp01  rp00
+ECC 1   rp15  rp14  rp13  rp12  rp11  rp10  rp09  rp08
+ECC 2   cp5   cp4   cp3   cp2   cp1   cp0      1     1
+I detected after writing this that ST application note AN1823
+(http://www.st.com/stonline/books/pdf/docs/10123.pdf) gives a much
+nicer picture.(but they use line parity as term where I use row parity)
+Oh well, I'm graphically challenged, so suffer with me for a moment :-)
+And I could not reuse the ST picture anyway for copyright reasons.
+Attempt 0
+=========
+Implementing the parity calculation is pretty simple.
+In C pseudocode:
+for (i = 0; i < 256; i++)
+{
+    if (i & 0x01)
+       rp1 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
+    else
+       rp0 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp1;
+    if (i & 0x02)
+       rp3 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp3;
+    else
+       rp2 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp2;
+    if (i & 0x04)
+      rp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp5;
+    else
+      rp4 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp4;
+    if (i & 0x08)
+      rp7 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp7;
+    else
+      rp6 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp6;
+    if (i & 0x10)
+      rp9 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp9;
+    else
+      rp8 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp8;
+    if (i & 0x20)
+      rp11 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp11;
+    else
+    rp10 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp10;
+    if (i & 0x40)
+      rp13 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp13;
+    else
+      rp12 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp12;
+    if (i & 0x80)
+      rp15 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp15;
+    else
+      rp14 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ bit3 ^ bit2 ^ bit1 ^ bit0 ^ rp14;
+    cp0 = bit6 ^ bit4 ^ bit2 ^ bit0 ^ cp0;
+    cp1 = bit7 ^ bit5 ^ bit3 ^ bit1 ^ cp1;
+    cp2 = bit5 ^ bit4 ^ bit1 ^ bit0 ^ cp2;
+    cp3 = bit7 ^ bit6 ^ bit3 ^ bit2 ^ cp3
+    cp4 = bit3 ^ bit2 ^ bit1 ^ bit0 ^ cp4
+    cp5 = bit7 ^ bit6 ^ bit5 ^ bit4 ^ cp5
+}
+Analysis 0
+==========
+C does have bitwise operators but not really operators to do the above
+efficiently (and most hardware has no such instructions either).
+Therefore without implementing this it was clear that the code above was
+not going to bring me a Nobel prize :-)
+Fortunately the exclusive or operation is commutative, so we can combine
+the values in any order. So instead of calculating all the bits
+individually, let us try to rearrange things.
+For the column parity this is easy. We can just xor the bytes and in the
+end filter out the relevant bits. This is pretty nice as it will bring
+all cp calculation out of the if loop.
+Similarly we can first xor the bytes for the various rows.
+This leads to:
+Attempt 1
+=========
+const char parity[256] = {
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1,
+    0, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0
+};
+void ecc1(const unsigned char *buf, unsigned char *code)
+{
+    int i;
+    const unsigned char *bp = buf;
+    unsigned char cur;
+    unsigned char rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
+    unsigned char rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15;
+    unsigned char par;
+    par = 0;
+    rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0;
+    rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0;
+    rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0;
+    rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0;
+    for (i = 0; i < 256; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        if (i & 0x01) rp1 ^= cur; else rp0 ^= cur;
+        if (i & 0x02) rp3 ^= cur; else rp2 ^= cur;
+        if (i & 0x04) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x08) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x10) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x20) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x40) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x80) rp15 ^= cur; else rp14 ^= cur;
+    }
+    code[0] =
+        (parity[rp7] << 7) |
+        (parity[rp6] << 6) |
+        (parity[rp5] << 5) |
+        (parity[rp4] << 4) |
+        (parity[rp3] << 3) |
+        (parity[rp2] << 2) |
+        (parity[rp1] << 1) |
+        (parity[rp0]);
+    code[1] =
+        (parity[rp15] << 7) |
+        (parity[rp14] << 6) |
+        (parity[rp13] << 5) |
+        (parity[rp12] << 4) |
+        (parity[rp11] << 3) |
+        (parity[rp10] << 2) |
+        (parity[rp9]  << 1) |
+        (parity[rp8]);
+    code[2] =
+        (parity[par & 0xf0] << 7) |
+        (parity[par & 0x0f] << 6) |
+        (parity[par & 0xcc] << 5) |
+        (parity[par & 0x33] << 4) |
+        (parity[par & 0xaa] << 3) |
+        (parity[par & 0x55] << 2);
+    code[0] = ~code[0];
+    code[1] = ~code[1];
+    code[2] = ~code[2];
+}
+Still pretty straightforward. The last three invert statements are there to
+give a checksum of 0xff 0xff 0xff for an empty flash. In an empty flash
+all data is 0xff, so the checksum then matches.
+I also introduced the parity lookup. I expected this to be the fastest
+way to calculate the parity, but I will investigate alternatives later
+on.
+Analysis 1
+==========
+The code works, but is not terribly efficient. On my system it took
+almost 4 times as much time as the linux driver code. But hey, if it was
+*that* easy this would have been done long before.
+No pain. no gain.
+Fortunately there is plenty of room for improvement.
+In step 1 we moved from bit-wise calculation to byte-wise calculation.
+However in C we can also use the unsigned long data type and virtually
+every modern microprocessor supports 32 bit operations, so why not try
+to write our code in such a way that we process data in 32 bit chunks.
+Of course this means some modification as the row parity is byte by
+byte. A quick analysis:
+for the column parity we use the par variable. When extending to 32 bits
+we can in the end easily calculate p0 and p1 from it.
+(because par now consists of 4 bytes, contributing to rp1, rp0, rp1, rp0
+respectively)
+also rp2 and rp3 can be easily retrieved from par as rp3 covers the
+first two bytes and rp2 the last two bytes.
+Note that of course now the loop is executed only 64 times (256/4).
+And note that care must taken wrt byte ordering. The way bytes are
+ordered in a long is machine dependent, and might affect us.
+Anyway, if there is an issue: this code is developed on x86 (to be
+precise: a DELL PC with a D920 Intel CPU)
+And of course the performance might depend on alignment, but I expect
+that the I/O buffers in the nand driver are aligned properly (and
+otherwise that should be fixed to get maximum performance).
+Let's give it a try...
+Attempt 2
+=========
+extern const char parity[256];
+void ecc2(const unsigned char *buf, unsigned char *code)
+{
+    int i;
+    const unsigned long *bp = (unsigned long *)buf;
+    unsigned long cur;
+    unsigned long rp0, rp1, rp2, rp3, rp4, rp5, rp6, rp7;
+    unsigned long rp8, rp9, rp10, rp11, rp12, rp13, rp14, rp15;
+    unsigned long par;
+    par = 0;
+    rp0 = 0; rp1 = 0; rp2 = 0; rp3 = 0;
+    rp4 = 0; rp5 = 0; rp6 = 0; rp7 = 0;
+    rp8 = 0; rp9 = 0; rp10 = 0; rp11 = 0;
+    rp12 = 0; rp13 = 0; rp14 = 0; rp15 = 0;
+    for (i = 0; i < 64; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        if (i & 0x01) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x02) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x04) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x08) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x10) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x20) rp15 ^= cur; else rp14 ^= cur;
+    }
+    /*
+       we need to adapt the code generation for the fact that rp vars are now
+       long; also the column parity calculation needs to be changed.
+       we'll bring rp4 to 15 back to single byte entities by shifting and
+       xoring
+    */
+    rp4 ^= (rp4 >> 16); rp4 ^= (rp4 >> 8); rp4 &= 0xff;
+    rp5 ^= (rp5 >> 16); rp5 ^= (rp5 >> 8); rp5 &= 0xff;
+    rp6 ^= (rp6 >> 16); rp6 ^= (rp6 >> 8); rp6 &= 0xff;
+    rp7 ^= (rp7 >> 16); rp7 ^= (rp7 >> 8); rp7 &= 0xff;
+    rp8 ^= (rp8 >> 16); rp8 ^= (rp8 >> 8); rp8 &= 0xff;
+    rp9 ^= (rp9 >> 16); rp9 ^= (rp9 >> 8); rp9 &= 0xff;
+    rp10 ^= (rp10 >> 16); rp10 ^= (rp10 >> 8); rp10 &= 0xff;
+    rp11 ^= (rp11 >> 16); rp11 ^= (rp11 >> 8); rp11 &= 0xff;
+    rp12 ^= (rp12 >> 16); rp12 ^= (rp12 >> 8); rp12 &= 0xff;
+    rp13 ^= (rp13 >> 16); rp13 ^= (rp13 >> 8); rp13 &= 0xff;
+    rp14 ^= (rp14 >> 16); rp14 ^= (rp14 >> 8); rp14 &= 0xff;
+    rp15 ^= (rp15 >> 16); rp15 ^= (rp15 >> 8); rp15 &= 0xff;
+    rp3 = (par >> 16); rp3 ^= (rp3 >> 8); rp3 &= 0xff;
+    rp2 = par & 0xffff; rp2 ^= (rp2 >> 8); rp2 &= 0xff;
+    par ^= (par >> 16);
+    rp1 = (par >> 8); rp1 &= 0xff;
+    rp0 = (par & 0xff);
+    par ^= (par >> 8); par &= 0xff;
+    code[0] =
+        (parity[rp7] << 7) |
+        (parity[rp6] << 6) |
+        (parity[rp5] << 5) |
+        (parity[rp4] << 4) |
+        (parity[rp3] << 3) |
+        (parity[rp2] << 2) |
+        (parity[rp1] << 1) |
+        (parity[rp0]);
+    code[1] =
+        (parity[rp15] << 7) |
+        (parity[rp14] << 6) |
+        (parity[rp13] << 5) |
+        (parity[rp12] << 4) |
+        (parity[rp11] << 3) |
+        (parity[rp10] << 2) |
+        (parity[rp9]  << 1) |
+        (parity[rp8]);
+    code[2] =
+        (parity[par & 0xf0] << 7) |
+        (parity[par & 0x0f] << 6) |
+        (parity[par & 0xcc] << 5) |
+        (parity[par & 0x33] << 4) |
+        (parity[par & 0xaa] << 3) |
+        (parity[par & 0x55] << 2);
+    code[0] = ~code[0];
+    code[1] = ~code[1];
+    code[2] = ~code[2];
+}
+The parity array is not shown any more. Note also that for these
+examples I kinda deviated from my regular programming style by allowing
+multiple statements on a line, not using { } in then and else blocks
+with only a single statement and by using operators like ^=
+Analysis 2
+==========
+The code (of course) works, and hurray: we are a little bit faster than
+the linux driver code (about 15%). But wait, don't cheer too quickly.
+THere is more to be gained.
+If we look at e.g. rp14 and rp15 we see that we either xor our data with
+rp14 or with rp15. However we also have par which goes over all data.
+This means there is no need to calculate rp14 as it can be calculated from
+rp15 through rp14 = par ^ rp15;
+(or if desired we can avoid calculating rp15 and calculate it from
+rp14).  That is why some places refer to inverse parity.
+Of course the same thing holds for rp4/5, rp6/7, rp8/9, rp10/11 and rp12/13.
+Effectively this means we can eliminate the else clause from the if
+statements. Also we can optimise the calculation in the end a little bit
+by going from long to byte first. Actually we can even avoid the table
+lookups
+Attempt 3
+=========
+Odd replaced:
+        if (i & 0x01) rp5 ^= cur; else rp4 ^= cur;
+        if (i & 0x02) rp7 ^= cur; else rp6 ^= cur;
+        if (i & 0x04) rp9 ^= cur; else rp8 ^= cur;
+        if (i & 0x08) rp11 ^= cur; else rp10 ^= cur;
+        if (i & 0x10) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x20) rp15 ^= cur; else rp14 ^= cur;
+with
+        if (i & 0x01) rp5 ^= cur;
+        if (i & 0x02) rp7 ^= cur;
+        if (i & 0x04) rp9 ^= cur;
+        if (i & 0x08) rp11 ^= cur;
+        if (i & 0x10) rp13 ^= cur;
+        if (i & 0x20) rp15 ^= cur;
+        and outside the loop added:
+    rp4  = par ^ rp5;
+    rp6  = par ^ rp7;
+    rp8  = par ^ rp9;
+    rp10  = par ^ rp11;
+    rp12  = par ^ rp13;
+    rp14  = par ^ rp15;
+And after that the code takes about 30% more time, although the number of
+statements is reduced. This is also reflected in the assembly code.
+Analysis 3
+==========
+Very weird. Guess it has to do with caching or instruction parallellism
+or so. I also tried on an eeePC (Celeron, clocked at 900 Mhz). Interesting
+observation was that this one is only 30% slower (according to time)
+executing the code as my 3Ghz D920 processor.
+Well, it was expected not to be easy so maybe instead move to a
+different track: let's move back to the code from attempt2 and do some
+loop unrolling. This will eliminate a few if statements. I'll try
+different amounts of unrolling to see what works best.
+Attempt 4
+=========
+Unrolled the loop 1, 2, 3 and 4 times.
+For 4 the code starts with:
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++;
+        par ^= cur;
+        rp4 ^= cur;
+        rp6 ^= cur;
+        rp8 ^= cur;
+        rp10 ^= cur;
+        if (i & 0x1) rp13 ^= cur; else rp12 ^= cur;
+        if (i & 0x2) rp15 ^= cur; else rp14 ^= cur;
+        cur = *bp++;
+        par ^= cur;
+        rp5 ^= cur;
+        rp6 ^= cur;
+        ...
+Analysis 4
+==========
+Unrolling once gains about 15%
+Unrolling twice keeps the gain at about 15%
+Unrolling three times gives a gain of 30% compared to attempt 2.
+Unrolling four times gives a marginal improvement compared to unrolling
+three times.
+I decided to proceed with a four time unrolled loop anyway. It was my gut
+feeling that in the next steps I would obtain additional gain from it.
+The next step was triggered by the fact that par contains the xor of all
+bytes and rp4 and rp5 each contain the xor of half of the bytes.
+So in effect par = rp4 ^ rp5. But as xor is commutative we can also say
+that rp5 = par ^ rp4. So no need to keep both rp4 and rp5 around. We can
+eliminate rp5 (or rp4, but I already foresaw another optimisation).
+The same holds for rp6/7, rp8/9, rp10/11 rp12/13 and rp14/15.
+Attempt 5
+=========
+Effectively so all odd digit rp assignments in the loop were removed.
+This included the else clause of the if statements.
+Of course after the loop we need to correct things by adding code like:
+    rp5 = par ^ rp4;
+Also the initial assignments (rp5 = 0; etc) could be removed.
+Along the line I also removed the initialisation of rp0/1/2/3.
+Analysis 5
+==========
+Measurements showed this was a good move. The run-time roughly halved
+compared with attempt 4 with 4 times unrolled, and we only require 1/3rd
+of the processor time compared to the current code in the linux kernel.
+However, still I thought there was more. I didn't like all the if
+statements. Why not keep a running parity and only keep the last if
+statement. Time for yet another version!
+Attempt 6
+=========
+THe code within the for loop was changed to:
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++; tmppar  = cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+            cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur; rp8 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+            par ^= tmppar;
+        if ((i & 0x1) == 0) rp12 ^= tmppar;
+        if ((i & 0x2) == 0) rp14 ^= tmppar;
+    }
+As you can see tmppar is used to accumulate the parity within a for
+iteration. In the last 3 statements is is added to par and, if needed,
+to rp12 and rp14.
+While making the changes I also found that I could exploit that tmppar
+contains the running parity for this iteration. So instead of having:
+rp4 ^= cur; rp6 = cur;
+I removed the rp6 = cur; statement and did rp6 ^= tmppar; on next
+statement. A similar change was done for rp8 and rp10
+Analysis 6
+==========
+Measuring this code again showed big gain. When executing the original
+linux code 1 million times, this took about 1 second on my system.
+(using time to measure the performance). After this iteration I was back
+to 0.075 sec. Actually I had to decide to start measuring over 10
+million interations in order not to loose too much accuracy. This one
+definitely seemed to be the jackpot!
+There is a little bit more room for improvement though. There are three
+places with statements:
+rp4 ^= cur; rp6 ^= cur;
+It seems more efficient to also maintain a variable rp4_6 in the while
+loop; This eliminates 3 statements per loop. Of course after the loop we
+need to correct by adding:
+    rp4 ^= rp4_6;
+    rp6 ^= rp4_6
+Furthermore there are 4 sequential assingments to rp8. This can be
+encoded slightly more efficient by saving tmppar before those 4 lines
+and later do rp8 = rp8 ^ tmppar ^ notrp8;
+(where notrp8 is the value of rp8 before those 4 lines).
+Again a use of the commutative property of xor.
+Time for a new test!
+Attempt 7
+=========
+The new code now looks like:
+    for (i = 0; i < 4; i++)
+    {
+        cur = *bp++; tmppar  = cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp8 ^= tmppar;
+        cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp10 ^= tmppar;
+            notrp8 = tmppar;
+            cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+            cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+            rp8 = rp8 ^ tmppar ^ notrp8;
+        cur = *bp++; tmppar ^= cur; rp4_6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp6 ^= cur;
+        cur = *bp++; tmppar ^= cur; rp4 ^= cur;
+        cur = *bp++; tmppar ^= cur;
+            par ^= tmppar;
+        if ((i & 0x1) == 0) rp12 ^= tmppar;
+        if ((i & 0x2) == 0) rp14 ^= tmppar;
+    }
+    rp4 ^= rp4_6;
+    rp6 ^= rp4_6;
+Not a big change, but every penny counts :-)
+Analysis 7
+==========
+Acutally this made things worse. Not very much, but I don't want to move
+into the wrong direction. Maybe something to investigate later. Could
+have to do with caching again.
+Guess that is what there is to win within the loop. Maybe unrolling one
+more time will help. I'll keep the optimisations from 7 for now.
+Attempt 8
+=========
+Unrolled the loop one more time.
+Analysis 8
+==========
+This makes things worse. Let's stick with attempt 6 and continue from there.
+Although it seems that the code within the loop cannot be optimised
+further there is still room to optimize the generation of the ecc codes.
+We can simply calcualate the total parity. If this is 0 then rp4 = rp5
+etc. If the parity is 1, then rp4 = !rp5;
+But if rp4 = rp5 we do not need rp5 etc. We can just write the even bits
+in the result byte and then do something like
+    code[0] |= (code[0] << 1);
+Lets test this.
+Attempt 9
+=========
+Changed the code but again this slightly degrades performance. Tried all
+kind of other things, like having dedicated parity arrays to avoid the
+shift after parity[rp7] << 7; No gain.
+Change the lookup using the parity array by using shift operators (e.g.
+replace parity[rp7] << 7 with:
+rp7 ^= (rp7 << 4);
+rp7 ^= (rp7 << 2);
+rp7 ^= (rp7 << 1);
+rp7 &= 0x80;
+No gain.
+The only marginal change was inverting the parity bits, so we can remove
+the last three invert statements.
+Ah well, pity this does not deliver more. Then again 10 million
+iterations using the linux driver code takes between 13 and 13.5
+seconds, whereas my code now takes about 0.73 seconds for those 10
+million iterations. So basically I've improved the performance by a
+factor 18 on my system. Not that bad. Of course on different hardware
+you will get different results. No warranties!
+But of course there is no such thing as a free lunch. The codesize almost
+tripled (from 562 bytes to 1434 bytes). Then again, it is not that much.
+Correcting errors
+=================
+For correcting errors I again used the ST application note as a starter,
+but I also peeked at the existing code.
+The algorithm itself is pretty straightforward. Just xor the given and
+the calculated ecc. If all bytes are 0 there is no problem. If 11 bits
+are 1 we have one correctable bit error. If there is 1 bit 1, we have an
+error in the given ecc code.
+It proved to be fastest to do some table lookups. Performance gain
+introduced by this is about a factor 2 on my system when a repair had to
+be done, and 1% or so if no repair had to be done.
+Code size increased from 330 bytes to 686 bytes for this function.
+(gcc 4.2, -O3)
+Conclusion
+==========
+The gain when calculating the ecc is tremendous. Om my development hardware
+a speedup of a factor of 18 for ecc calculation was achieved. On a test on an
+embedded system with a MIPS core a factor 7 was obtained.
+On  a test with a Linksys NSLU2 (ARMv5TE processor) the speedup was a factor
+5 (big endian mode, gcc 4.1.2, -O3)
+For correction not much gain could be obtained (as bitflips are rare). Then
+again there are also much less cycles spent there.
+It seems there is not much more gain possible in this, at least when
+programmed in C. Of course it might be possible to squeeze something more
+out of it with an assembler program, but due to pipeline behaviour etc
+this is very tricky (at least for intel hw).
+Author: Frans Meulenbroeks
+Copyright (C) 2008 Koninklijke Philips Electronics NV.
diff --git a/Documentation/networking/LICENSE.qlge b/Documentation/networking/LICENSE.qlge
new file mode 100644
index 000000000000..123b6edd7f18
--- /dev/null
+++ b/Documentation/networking/LICENSE.qlge
@@ -0,0 +1,46 @@
+Copyright (c)  2003-2008 QLogic Corporation
+QLogic Linux Networking HBA Driver
+This program includes a device driver for Linux 2.6 that may be
+distributed with QLogic hardware specific firmware binary file.
+You may modify and redistribute the device driver code under the
+GNU General Public License as published by the Free Software
+Foundation (version 2 or a later version).
+You may redistribute the hardware specific firmware binary file
+under the following terms:
+        1. Redistribution of source code (only if applicable),
+           must retain the above copyright notice, this list of
+           conditions and the following disclaimer.
+        2. Redistribution in binary form must reproduce the above
+           copyright notice, this list of conditions and the
+           following disclaimer in the documentation and/or other
+           materials provided with the distribution.
+        3. The name of QLogic Corporation may not be used to
+           endorse or promote products derived from this software
+           without specific prior written permission
+REGARDLESS OF WHAT LICENSING MECHANISM IS USED OR APPLICABLE,
+THIS PROGRAM IS PROVIDED BY QLOGIC CORPORATION "AS IS'' AND ANY
+EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR
+BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
+TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+USER ACKNOWLEDGES AND AGREES THAT USE OF THIS PROGRAM WILL NOT
+CREATE OR GIVE GROUNDS FOR A LICENSE BY IMPLICATION, ESTOPPEL, OR
+OTHERWISE IN ANY INTELLECTUAL PROPERTY RIGHTS (PATENT, COPYRIGHT,
+TRADE SECRET, MASK WORK, OR OTHER PROPRIETARY RIGHT) EMBODIED IN
+ANY OTHER QLOGIC HARDWARE OR SOFTWARE EITHER SOLELY OR IN
+COMBINATION WITH THIS PROGRAM.
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
new file mode 100644
index 000000000000..6d8af1ac56c4
--- /dev/null
+++ b/Documentation/networking/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := ifenslave
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index a0cda062bc33..688dfe1e6b70 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -289,35 +289,73 @@ downdelay
 fail_over_mac
        Specifies whether active-backup mode should set all slaves to
-        the same MAC address (the traditional behavior), or, when
+        the same MAC address at enslavement (the traditional
-        enabled, change the bond's MAC address when changing the
+        behavior), or, when enabled, perform special handling of the
-        active interface (i.e., fail over the MAC address itself).
+        bond's MAC address in accordance with the selected policy.
-        Fail over MAC is useful for devices that cannot ever alter
+        Possible values are:
-        their MAC address, or for devices that refuse incoming
-        broadcasts with their own source MAC (which interferes with
+        none or 0
-        the ARP monitor).
+                This setting disables fail_over_mac, and causes
-        The down side of fail over MAC is that every device on the
+                bonding to set all slaves of an active-backup bond to
-        network must be updated via gratuitous ARP, vs. just updating
+                the same MAC address at enslavement time.  This is the
-        a switch or set of switches (which often takes place for any
+                default.
-        traffic, not just ARP traffic, if the switch snoops incoming
-        traffic to update its tables) for the traditional method.  If
+        active or 1
-        the gratuitous ARP is lost, communication may be disrupted.
+                The "active" fail_over_mac policy indicates that the
-        When fail over MAC is used in conjuction with the mii monitor,
+                MAC address of the bond should always be the MAC
-        devices which assert link up prior to being able to actually
+                address of the currently active slave.  The MAC
-        transmit and receive are particularly susecptible to loss of
+                address of the slaves is not changed; instead, the MAC
-        the gratuitous ARP, and an appropriate updelay setting may be
+                address of the bond changes during a failover.
-        required.
+                This policy is useful for devices that cannot ever
-        A value of 0 disables fail over MAC, and is the default.  A
+                alter their MAC address, or for devices that refuse
-        value of 1 enables fail over MAC.  This option is enabled
+                incoming broadcasts with their own source MAC (which
-        automatically if the first slave added cannot change its MAC
+                interferes with the ARP monitor).
-        address.  This option may be modified via sysfs only when no
-        slaves are present in the bond.
+                The down side of this policy is that every device on
+                the network must be updated via gratuitous ARP,
-        This option was added in bonding version 3.2.0.
+                vs. just updating a switch or set of switches (which
+                often takes place for any traffic, not just ARP
+                traffic, if the switch snoops incoming traffic to
+                update its tables) for the traditional method.  If the
+                gratuitous ARP is lost, communication may be
+                disrupted.
+                When this policy is used in conjuction with the mii
+                monitor, devices which assert link up prior to being
+                able to actually transmit and receive are particularly
+                susecptible to loss of the gratuitous ARP, and an
+                appropriate updelay setting may be required.
+        follow or 2
+                The "follow" fail_over_mac policy causes the MAC
+                address of the bond to be selected normally (normally
+                the MAC address of the first slave added to the bond).
+                However, the second and subsequent slaves are not set
+                to this MAC address while they are in a backup role; a
+                slave is programmed with the bond's MAC address at
+                failover time (and the formerly active slave receives
+                the newly active slave's MAC address).
+                This policy is useful for multiport devices that
+                either become confused or incur a performance penalty
+                when multiple ports are programmed with the same MAC
+                address.
+        The default policy is none, unless the first slave cannot
+        change its MAC address, in which case the active policy is
+        selected by default.
+        This option may be modified via sysfs only when no slaves are
+        present in the bond.
+        This option was added in bonding version 3.2.0.  The "follow"
+        policy was added in bonding version 3.3.0.
 lacp_rate
@@ -338,7 +376,8 @@ max_bonds
        Specifies the number of bonding devices to create for this
        instance of the bonding driver.  E.g., if max_bonds is 3, and
        the bonding driver is not already loaded, then bond0, bond1
-        and bond2 will be created.  The default value is 1.
+        and bond2 will be created.  The default value is 1.  Specifying
+        a value of 0 will load bonding, but will not create any devices.
 miimon
@@ -501,6 +540,17 @@ mode
                swapped with the new curr_active_slave that was
                chosen.
+num_grat_arp
+        Specifies the number of gratuitous ARPs to be issued after a
+        failover event.  One gratuitous ARP is issued immediately after
+        the failover, subsequent ARPs are sent at a rate of one per link
+        monitor interval (arp_interval or miimon, whichever is active).
+        The valid range is 0 - 255; the default value is 1.  This option
+        affects only the active-backup mode.  This option was added for
+        bonding version 3.3.0.
 primary
        A string (eth0, eth2, etc) specifying which slave is the
@@ -581,7 +631,7 @@ xmit_hash_policy
                in environments where a layer3 gateway device is
                required to reach most destinations.
-                This algorithm is 802.3ad complient.
+                This algorithm is 802.3ad compliant.
        layer3+4
diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt
index 641d2afacffa..2035bc4932f2 100644
--- a/Documentation/networking/can.txt
+++ b/Documentation/networking/can.txt
@@ -35,8 +35,9 @@ This file contains
    6.1 general settings
    6.2 local loopback of sent frames
    6.3 CAN controller hardware filters
-    6.4 currently supported CAN hardware
+    6.4 The virtual CAN driver (vcan)
-    6.5 todo
+    6.5 currently supported CAN hardware
+    6.6 todo
  7 Credits
@@ -186,7 +187,7 @@ solution for a couple of reasons:
  The Linux network devices (by default) just can handle the
  transmission and reception of media dependent frames. Due to the
-  arbritration on the CAN bus the transmission of a low prio CAN-ID
+  arbitration on the CAN bus the transmission of a low prio CAN-ID
  may be delayed by the reception of a high prio CAN frame. To
  reflect the correct* traffic on the node the loopback of the sent
  data has to be performed right after a successful transmission. If
@@ -481,7 +482,7 @@ solution for a couple of reasons:
  - stats_timer: To calculate the Socket CAN core statistics
    (e.g. current/maximum frames per second) this 1 second timer is
    invoked at can.ko module start time by default. This timer can be
-    disabled by using stattimer=0 on the module comandline.
+    disabled by using stattimer=0 on the module commandline.
  - debug: (removed since SocketCAN SVN r546)
@@ -584,7 +585,42 @@ solution for a couple of reasons:
  @133MHz with four SJA1000 CAN controllers from 2002 under heavy bus
  load without any problems ...
-  6.4 currently supported CAN hardware (September 2007)
+  6.4 The virtual CAN driver (vcan)
+  Similar to the network loopback devices, vcan offers a virtual local
+  CAN interface. A full qualified address on CAN consists of
+  - a unique CAN Identifier (CAN ID)
+  - the CAN bus this CAN ID is transmitted on (e.g. can0)
+  so in common use cases more than one virtual CAN interface is needed.
+  The virtual CAN interfaces allow the transmission and reception of CAN
+  frames without real CAN controller hardware. Virtual CAN network
+  devices are usually named 'vcanX', like vcan0 vcan1 vcan2 ...
+  When compiled as a module the virtual CAN driver module is called vcan.ko
+  Since Linux Kernel version 2.6.24 the vcan driver supports the Kernel
+  netlink interface to create vcan network devices. The creation and
+  removal of vcan network devices can be managed with the ip(8) tool:
+  - Create a virtual CAN network interface:
+       ip link add type vcan
+  - Create a virtual CAN network interface with a specific name 'vcan42':
+       ip link add dev vcan42 type vcan
+  - Remove a (virtual CAN) network interface 'vcan42':
+       ip link del vcan42
+  The tool 'vcan' from the SocketCAN SVN repository on BerliOS is obsolete.
+  Virtual CAN network device creation in older Kernels:
+  In Linux Kernel versions < 2.6.24 the vcan driver creates 4 vcan
+  netdevices at module load time by default. This value can be changed
+  with the module parameter 'numdev'. E.g. 'modprobe vcan numdev=8'
+  6.5 currently supported CAN hardware
  On the project website http://developer.berlios.de/projects/socketcan
  there are different drivers available:
@@ -603,7 +639,7 @@ solution for a couple of reasons:
  Please check the Mailing Lists on the berlios OSS project website.
-  6.5 todo (September 2007)
+  6.6 todo
  The configuration interface for CAN network drivers is still an open
  issue that has not been finalized in the socketcan project. Also the
diff --git a/Documentation/networking/cs89x0.txt b/Documentation/networking/cs89x0.txt
index 6387d3decf85..c725d33b316f 100644
--- a/Documentation/networking/cs89x0.txt
+++ b/Documentation/networking/cs89x0.txt
@@ -3,7 +3,7 @@ NOTE
 ----
 This document was contributed by Cirrus Logic for kernel 2.2.5.  This version
-has been updated for 2.3.48 by Andrew Morton <andrewm@uow.edu.au>
+has been updated for 2.3.48 by Andrew Morton.
 Cirrus make a copy of this driver available at their website, as
 described below.  In general, you should use the driver version which
@@ -690,7 +690,7 @@ latest drivers and technical publications.
 6.4 Current maintainer
 In February 2000 the maintenance of this driver was assumed by Andrew
-Morton <akpm@zip.com.au>
+Morton.
 6.5 Kernel module parameters
diff --git a/Documentation/networking/dm9000.txt b/Documentation/networking/dm9000.txt
new file mode 100644
index 000000000000..65df3dea5561
--- /dev/null
+++ b/Documentation/networking/dm9000.txt
@@ -0,0 +1,167 @@
+DM9000 Network driver
+=====================
+Copyright 2008 Simtec Electronics,
+          Ben Dooks <ben@simtec.co.uk> <ben-linux@fluff.org>
+Introduction
+------------
+This file describes how to use the DM9000 platform-device based network driver
+that is contained in the files drivers/net/dm9000.c and drivers/net/dm9000.h.
+The driver supports three DM9000 variants, the DM9000E which is the first chip
+supported as well as the newer DM9000A and DM9000B devices. It is currently
+maintained and tested by Ben Dooks, who should be CC: to any patches for this
+driver.
+Defining the platform device
+----------------------------
+The minimum set of resources attached to the platform device are as follows:
+    1) The physical address of the address register
+    2) The physical address of the data register
+    3) The IRQ line the device's interrupt pin is connected to.
+These resources should be specified in that order, as the ordering of the
+two address regions is important (the driver expects these to be address
+and then data).
+An example from arch/arm/mach-s3c2410/mach-bast.c is:
+static struct resource bast_dm9k_resource[] = {
+        [0] = {
+                .start = S3C2410_CS5 + BAST_PA_DM9000,
+                .end   = S3C2410_CS5 + BAST_PA_DM9000 + 3,
+                .flags = IORESOURCE_MEM,
+        },
+        [1] = {
+                .start = S3C2410_CS5 + BAST_PA_DM9000 + 0x40,
+                .end   = S3C2410_CS5 + BAST_PA_DM9000 + 0x40 + 0x3f,
+                .flags = IORESOURCE_MEM,
+        },
+        [2] = {
+                .start = IRQ_DM9000,
+                .end   = IRQ_DM9000,
+                .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL,
+        }
+};
+static struct platform_device bast_device_dm9k = {
+        .name           = "dm9000",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(bast_dm9k_resource),
+        .resource       = bast_dm9k_resource,
+};
+Note the setting of the IRQ trigger flag in bast_dm9k_resource[2].flags,
+as this will generate a warning if it is not present. The trigger from
+the flags field will be passed to request_irq() when registering the IRQ
+handler to ensure that the IRQ is setup correctly.
+This shows a typical platform device, without the optional configuration
+platform data supplied. The next example uses the same resources, but adds
+the optional platform data to pass extra configuration data:
+static struct dm9000_plat_data bast_dm9k_platdata = {
+        .flags          = DM9000_PLATF_16BITONLY,
+};
+static struct platform_device bast_device_dm9k = {
+        .name           = "dm9000",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(bast_dm9k_resource),
+        .resource       = bast_dm9k_resource,
+        .dev            = {
+                .platform_data = &bast_dm9k_platdata,
+        }
+};
+The platform data is defined in include/linux/dm9000.h and described below.
+Platform data
+-------------
+Extra platform data for the DM9000 can describe the IO bus width to the
+device, whether or not an external PHY is attached to the device and
+the availability of an external configuration EEPROM.
+The flags for the platform data .flags field are as follows:
+DM9000_PLATF_8BITONLY
+        The IO should be done with 8bit operations.
+DM9000_PLATF_16BITONLY
+        The IO should be done with 16bit operations.
+DM9000_PLATF_32BITONLY
+        The IO should be done with 32bit operations.
+DM9000_PLATF_EXT_PHY
+        The chip is connected to an external PHY.
+DM9000_PLATF_NO_EEPROM
+        This can be used to signify that the board does not have an
+        EEPROM, or that the EEPROM should be hidden from the user.
+DM9000_PLATF_SIMPLE_PHY
+        Switch to using the simpler PHY polling method which does not
+        try and read the MII PHY state regularly. This is only available
+        when using the internal PHY. See the section on link state polling
+        for more information.
+        The config symbol DM9000_FORCE_SIMPLE_PHY_POLL, Kconfig entry
+        "Force simple NSR based PHY polling" allows this flag to be
+        forced on at build time.
+PHY Link state polling
+----------------------
+The driver keeps track of the link state and informs the network core
+about link (carrier) availablilty. This is managed by several methods
+depending on the version of the chip and on which PHY is being used.
+For the internal PHY, the original (and currently default) method is
+to read the MII state, either when the status changes if we have the
+necessary interrupt support in the chip or every two seconds via a
+periodic timer.
+To reduce the overhead for the internal PHY, there is now the option
+of using the DM9000_FORCE_SIMPLE_PHY_POLL config, or DM9000_PLATF_SIMPLE_PHY
+platform data option to read the summary information without the
+expensive MII accesses. This method is faster, but does not print
+as much information.
+When using an external PHY, the driver currently has to poll the MII
+link status as there is no method for getting an interrupt on link change.
+DM9000A / DM9000B
+-----------------
+These chips are functionally similar to the DM9000E and are supported easily
+by the same driver. The features are:
+   1) Interrupt on internal PHY state change. This means that the periodic
+      polling of the PHY status may be disabled on these devices when using
+      the internal PHY.
+   2) TCP/UDP checksum offloading, which the driver does not currently support.
+ethtool
+-------
+The driver supports the ethtool interface for access to the driver
+state information, the PHY state and the EEPROM.
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 61b171cf5313..2df71861e578 100644
--- a/Documentation/networking/e1000.txt
+++ b/Documentation/networking/e1000.txt
@@ -513,21 +513,11 @@ Additional Configurations
  Intel(R) PRO/1000 PT Dual Port Server Connection
  Intel(R) PRO/1000 PT Dual Port Server Adapter
  Intel(R) PRO/1000 PF Dual Port Server Adapter
-  Intel(R) PRO/1000 PT Quad Port Server Adapter 
+  Intel(R) PRO/1000 PT Quad Port Server Adapter
  NAPI
  ----
-  NAPI (Rx polling mode) is supported in the e1000 driver.  NAPI is enabled
+  NAPI (Rx polling mode) is enabled in the e1000 driver.
-  or disabled based on the configuration of the kernel.  To override
-  the default, use the following compile-time flags.
-  To enable NAPI, compile the driver module, passing in a configuration option:
-       make CFLAGS_EXTRA=-DE1000_NAPI install
-  To disable NAPI, compile the driver module, passing in a configuration option:
-       make CFLAGS_EXTRA=-DE1000_NO_NAPI install
  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c
index a12059886755..1b96ccda3836 100644
--- a/Documentation/networking/ifenslave.c
+++ b/Documentation/networking/ifenslave.c
@@ -1081,7 +1081,7 @@ static int set_if_addr(char *master_ifname, char *slave_ifname)
                }
-                ipaddr = ifr.ifr_addr.sa_data;
+                ipaddr = (unsigned char *)ifr.ifr_addr.sa_data;
                v_print("Interface '%s': set IP %s to %d.%d.%d.%d\n",
                        slave_ifname, ifra[i].desc,
                        ipaddr[0], ipaddr[1], ipaddr[2], ipaddr[3]);
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 946b66e1b652..d84932650fd3 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -551,8 +551,9 @@ icmp_echo_ignore_broadcasts - BOOLEAN
 icmp_ratelimit - INTEGER
        Limit the maximal rates for sending ICMP packets whose type matches
        icmp_ratemask (see below) to specific targets.
-        0 to disable any limiting, otherwise the maximal rate in jiffies(1)
+        0 to disable any limiting,
-        Default: 100
+        otherwise the minimal space between responses in milliseconds.
+        Default: 1000
 icmp_ratemask - INTEGER
        Mask made of ICMP types for which rates are being limited.
@@ -1023,11 +1024,23 @@ max_addresses - INTEGER
        autoconfigured addresses.
        Default: 16
+disable_ipv6 - BOOLEAN
+        Disable IPv6 operation.
+        Default: FALSE (enable IPv6 operation)
+accept_dad - INTEGER
+        Whether to accept DAD (Duplicate Address Detection).
+        0: Disable DAD
+        1: Enable DAD (default)
+        2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
+           link-local address has been found.
 icmp/*:
 ratelimit - INTEGER
        Limit the maximal rates for sending ICMPv6 packets.
-        0 to disable any limiting, otherwise the maximal rate in jiffies(1)
+        0 to disable any limiting,
-        Default: 100
+        otherwise the minimal space between responses in milliseconds.
+        Default: 1000
 IPv6 Update by:
diff --git a/Documentation/networking/ixgb.txt b/Documentation/networking/ixgb.txt
index 7c98277777eb..a0d0ffb5e584 100644
--- a/Documentation/networking/ixgb.txt
+++ b/Documentation/networking/ixgb.txt
@@ -1,7 +1,7 @@
-Linux* Base Driver for the Intel(R) PRO/10GbE Family of Adapters
+Linux Base Driver for 10 Gigabit Intel(R) Network Connection
-================================================================
+=============================================================
-November 17, 2004
+October 9, 2007
 Contents
@@ -9,94 +9,151 @@ Contents
 - In This Release
 - Identifying Your Adapter
+- Building and Installation
 - Command Line Parameters
 - Improving Performance
+- Additional Configurations
+- Known Issues/Troubleshooting
 - Support
 In This Release
 ===============
-This file describes the Linux* Base Driver for the Intel(R) PRO/10GbE Family 
+This file describes the ixgb Linux Base Driver for the 10 Gigabit Intel(R)
-of Adapters, version 1.0.x.  
+Network Connection.  This driver includes support for Itanium(R)2-based
+systems.
+For questions related to hardware requirements, refer to the documentation
+supplied with your 10 Gigabit adapter.  All hardware requirements listed apply
+to use with Linux.
+The following features are available in this kernel:
+ - Native VLANs
+ - Channel Bonding (teaming)
+ - SNMP
+Channel Bonding documentation can be found in the Linux kernel source:
+/Documentation/networking/bonding.txt
+The driver information previously displayed in the /proc filesystem is not
+supported in this release.  Alternatively, you can use ethtool (version 1.6
+or later), lspci, and ifconfig to obtain the same information.
+Instructions on updating ethtool can be found in the section "Additional
+Configurations" later in this document.
-For questions related to hardware requirements, refer to the documentation 
-supplied with your Intel PRO/10GbE adapter. All hardware requirements listed 
-apply to use with Linux.
 Identifying Your Adapter
 ========================
-To verify your Intel adapter is supported, find the board ID number on the 
+The following Intel network adapters are compatible with the drivers in this
-adapter. Look for a label that has a barcode and a number in the format  
+release:
-A12345-001. 
+Controller  Adapter Name                 Physical Layer
+----------  ------------                 --------------
+82597EX     Intel(R) PRO/10GbE LR/SR/CX4 10G Base-LR (1310 nm optical fiber)
+            Server Adapters              10G Base-SR (850 nm optical fiber)
+                                         10G Base-CX4(twin-axial copper cabling)
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+    http://support.intel.com/support/network/sb/CS-012904.htm
+Building and Installation
+=========================
+select m for "Intel(R) PRO/10GbE support" located at:
+      Location:
+        -> Device Drivers
+          -> Network device support (NETDEVICES [=y])
+            -> Ethernet (10000 Mbit) (NETDEV_10000 [=y])
+1. make modules && make modules_install
+2. Load the module:
+    modprobe ixgb <parameter>=<value>
+   The insmod command can be used if the full
+   path to the driver module is specified.  For example:
+     insmod /lib/modules/<KERNEL VERSION>/kernel/drivers/net/ixgb/ixgb.ko
+   With 2.6 based kernels also make sure that older ixgb drivers are
+   removed from the kernel, before loading the new module:
-Use the above information and the Adapter & Driver ID Guide at:
+     rmmod ixgb; modprobe ixgb
-  http://support.intel.com/support/network/adapter/pro100/21397.htm
+3. Assign an IP address to the interface by entering the following, where
+   x is the interface number:
-For the latest Intel network drivers for Linux, go to:
+     ifconfig ethx <IP_address>
+4. Verify that the interface works. Enter the following, where <IP_address>
+   is the IP address for another machine on the same subnet as the interface
+   that is being tested:
+     ping  <IP_address>
-    http://downloadfinder.intel.com/scripts-df/support_intel.asp
 Command Line Parameters
 =======================
-If the driver is built as a module, the  following optional parameters are 
+If the driver is built as a module, the  following optional parameters are
-used by entering them on the command line with the modprobe or insmod command
+used by entering them on the command line with the modprobe command using
-using this syntax:
+this syntax:
     modprobe ixgb [<option>=<VAL1>,<VAL2>,...]
-     insmod ixgb [<option>=<VAL1>,<VAL2>,...]
+For example, with two 10GbE PCI adapters, entering:
-For example, with two PRO/10GbE PCI adapters, entering:
+     modprobe ixgb TxDescriptors=80,128
-    insmod ixgb TxDescriptors=80,128
+loads the ixgb driver with 80 TX resources for the first adapter and 128 TX
-loads the ixgb driver with 80 TX resources for the first adapter and 128 TX 
 resources for the second adapter.
 The default value for each parameter is generally the recommended setting,
-unless otherwise noted. Also, if the driver is statically built into the
+unless otherwise noted.
-kernel, the driver is loaded with the default values for all the parameters.
-Ethtool can be used to change some of the parameters at runtime.
 FlowControl
 Valid Range: 0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
 Default: Read from the EEPROM
-         If EEPROM is not detected, default is 3
+         If EEPROM is not detected, default is 1
-    This parameter controls the automatic generation(Tx) and response(Rx) to 
+    This parameter controls the automatic generation(Tx) and response(Rx) to
-    Ethernet PAUSE frames.
+    Ethernet PAUSE frames.  There are hardware bugs associated with enabling
+    Tx flow control so beware.
 RxDescriptors
 Valid Range: 64-512
 Default Value: 512
-    This value is the number of receive descriptors allocated by the driver. 
+    This value is the number of receive descriptors allocated by the driver.
-    Increasing this value allows the driver to buffer more incoming packets. 
+    Increasing this value allows the driver to buffer more incoming packets.
-    Each descriptor is 16 bytes.  A receive buffer is also allocated for 
+    Each descriptor is 16 bytes.  A receive buffer is also allocated for
-    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes, 
+    each descriptor and can be either 2048, 4056, 8192, or 16384 bytes,
-    depending on the MTU setting. When the MTU size is 1500 or less, the 
+    depending on the MTU setting.  When the MTU size is 1500 or less, the
    receive buffer size is 2048 bytes. When the MTU is greater than 1500 the
-    receive buffer size will be either 4056, 8192, or 16384 bytes. The 
+    receive buffer size will be either 4056, 8192, or 16384 bytes.  The
    maximum MTU size is 16114.
 RxIntDelay
 Valid Range: 0-65535 (0=off)
-Default Value: 6
+Default Value: 72
-    This value delays the generation of receive interrupts in units of 
+    This value delays the generation of receive interrupts in units of
-    0.8192 microseconds.  Receive interrupt reduction can improve CPU 
+    0.8192 microseconds.  Receive interrupt reduction can improve CPU
-    efficiency if properly tuned for specific network traffic. Increasing 
+    efficiency if properly tuned for specific network traffic.  Increasing
-    this value adds extra latency to frame reception and can end up 
+    this value adds extra latency to frame reception and can end up
-    decreasing the throughput of TCP traffic. If the system is reporting 
+    decreasing the throughput of TCP traffic.  If the system is reporting
-    dropped receives, this value may be set too high, causing the driver to 
+    dropped receives, this value may be set too high, causing the driver to
    run out of available receive descriptors.
 TxDescriptors
 Valid Range: 64-4096
 Default Value: 256
    This value is the number of transmit descriptors allocated by the driver.
-    Increasing this value allows the driver to queue more transmits. Each 
+    Increasing this value allows the driver to queue more transmits.  Each
    descriptor is 16 bytes.
 XsumRX
@@ -105,51 +162,49 @@ Default Value: 1
    A value of '1' indicates that the driver should enable IP checksum
    offload for received packets (both UDP and TCP) to the adapter hardware.
-XsumTX
-Valid Range: 0-1
-Default Value: 1
-    A value of '1' indicates that the driver should enable IP checksum
-    offload for transmitted packets (both UDP and TCP) to the adapter 
-    hardware.
 Improving Performance
 =====================
-With the Intel PRO/10 GbE adapter, the default Linux configuration will very 
+With the 10 Gigabit server adapters, the default Linux configuration will
-likely limit the total available throughput artificially.  There is a set of 
+very likely limit the total available throughput artificially.  There is a set
-things that when applied together increase the ability of Linux to transmit 
+of configuration changes that, when applied together, will increase the ability
-and receive data.  The following enhancements were originally acquired from
+of Linux to transmit and receive data.  The following enhancements were
-settings published at http://www.spec.org/web99 for various submitted results 
+originally acquired from settings published at http://www.spec.org/web99/ for
-using Linux.
+various submitted results using Linux.
-NOTE: These changes are only suggestions, and serve as a starting point for 
+NOTE: These changes are only suggestions, and serve as a starting point for
-tuning your network performance.
+      tuning your network performance.
 The changes are made in three major ways, listed in order of greatest effect:
- Use ifconfig to modify the mtu (maximum transmission unit) and the txqueuelen 
+- Use ifconfig to modify the mtu (maximum transmission unit) and the txqueuelen
  parameter.
 - Use sysctl to modify /proc parameters (essentially kernel tuning)
- Use setpci to modify the MMRBC field in PCI-X configuration space to increase 
+- Use setpci to modify the MMRBC field in PCI-X configuration space to increase
  transmit burst lengths on the bus.
-NOTE: setpci modifies the adapter's configuration registers to allow it to read 
+NOTE: setpci modifies the adapter's configuration registers to allow it to read
-up to 4k bytes at a time (for transmits).  However, for some systems the 
+up to 4k bytes at a time (for transmits).  However, for some systems the
-behavior after modifying this register may be undefined (possibly errors of some 
+behavior after modifying this register may be undefined (possibly errors of
-kind). A power-cycle, hard reset or explicitly setting the e6 register back to 
+some kind).  A power-cycle, hard reset or explicitly setting the e6 register
-22 (setpci -d 8086:1048 e6.b=22) may be required to get back to a stable 
+back to 22 (setpci -d 8086:1a48 e6.b=22) may be required to get back to a
-configuration.
+stable configuration.
 - COPY these lines and paste them into ixgb_perf.sh:
 #!/bin/bash
-echo "configuring network performance , edit this file to change the interface"
+echo "configuring network performance , edit this file to change the interface
+or device ID of 10GbE card"
 # set mmrbc to 4k reads, modify only Intel 10GbE device IDs
-setpci -d 8086:1048 e6.b=2e
+# replace 1a48 with appropriate 10GbE device's ID installed on the system,
-# set the MTU (max transmission unit) - it requires your switch and clients to change too!
+# if needed.
+setpci -d 8086:1a48 e6.b=2e
+# set the MTU (max transmission unit) - it requires your switch and clients
+# to change as well.
 # set the txqueuelen
 # your ixgb adapter should be loaded as eth1 for this to work, change if needed
 ifconfig eth1 mtu 9000 txqueuelen 1000 up
-# call the sysctl utility to modify /proc/sys entries 
+# call the sysctl utility to modify /proc/sys entries
-sysctl -p ./sysctl_ixgb.conf 
+sysctl -p ./sysctl_ixgb.conf
 - END ixgb_perf.sh
 - COPY these lines and paste them into sysctl_ixgb.conf:
@@ -159,54 +214,220 @@ sysctl -p ./sysctl_ixgb.conf
 # several network benchmark tests, your mileage may vary
 ### IPV4 specific settings
-net.ipv4.tcp_timestamps = 0 # turns TCP timestamp support off, default 1, reduces CPU use
+# turn TCP timestamp support off, default 1, reduces CPU use
-net.ipv4.tcp_sack = 0 # turn SACK support off, default on
+net.ipv4.tcp_timestamps = 0
-# on systems with a VERY fast bus -> memory interface this is the big gainer 
+# turn SACK support off, default on
-net.ipv4.tcp_rmem = 10000000 10000000 10000000 # sets min/default/max TCP read buffer, default 4096 87380 174760
+# on systems with a VERY fast bus -> memory interface this is the big gainer
-net.ipv4.tcp_wmem = 10000000 10000000 10000000 # sets min/pressure/max TCP write buffer, default 4096 16384 131072
+net.ipv4.tcp_sack = 0
-net.ipv4.tcp_mem = 10000000 10000000 10000000 # sets min/pressure/max TCP buffer space, default 31744 32256 32768
+# set min/default/max TCP read buffer, default 4096 87380 174760
+net.ipv4.tcp_rmem = 10000000 10000000 10000000
+# set min/pressure/max TCP write buffer, default 4096 16384 131072
+net.ipv4.tcp_wmem = 10000000 10000000 10000000
+# set min/pressure/max TCP buffer space, default 31744 32256 32768
+net.ipv4.tcp_mem = 10000000 10000000 10000000
 ### CORE settings (mostly for socket and UDP effect)
-net.core.rmem_max = 524287 # maximum receive socket buffer size, default 131071
+# set maximum receive socket buffer size, default 131071
-net.core.wmem_max = 524287 # maximum send socket buffer size, default 131071
+net.core.rmem_max = 524287
-net.core.rmem_default = 524287 # default receive socket buffer size, default 65535
+# set maximum send socket buffer size, default 131071
-net.core.wmem_default = 524287 # default send socket buffer size, default 65535
+net.core.wmem_max = 524287
-net.core.optmem_max = 524287 # maximum amount of option memory buffers, default 10240
+# set default receive socket buffer size, default 65535
-net.core.netdev_max_backlog = 300000 # number of unprocessed input packets before kernel starts dropping them, default 300
+net.core.rmem_default = 524287
+# set default send socket buffer size, default 65535
+net.core.wmem_default = 524287
+# set maximum amount of option memory buffers, default 10240
+net.core.optmem_max = 524287
+# set number of unprocessed input packets before kernel starts dropping them; default 300
+net.core.netdev_max_backlog = 300000
 - END sysctl_ixgb.conf
-Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface 
+Edit the ixgb_perf.sh script if necessary to change eth1 to whatever interface
-your ixgb driver is using.
+your ixgb driver is using and/or replace '1a48' with appropriate 10GbE device's
+ID installed on the system.
-NOTE: Unless these scripts are added to the boot process, these changes will 
+NOTE: Unless these scripts are added to the boot process, these changes will
-only last only until the next system reboot.
+      only last only until the next system reboot.
 Resolving Slow UDP Traffic
 --------------------------
+If your server does not seem to be able to receive UDP traffic as fast as it
+can receive TCP traffic, it could be because Linux, by default, does not set
+the network stack buffers as large as they need to be to support high UDP
+transfer rates.  One way to alleviate this problem is to allow more memory to
+be used by the IP stack to store incoming data.
-If your server does not seem to be able to receive UDP traffic as fast as it 
+For instance, use the commands:
-can receive TCP traffic, it could be because Linux, by default, does not set 
-the network stack buffers as large as they need to be to support high UDP 
-transfer rates. One way to alleviate this problem is to allow more memory to 
-be used by the IP stack to store incoming data. 
-For instance, use the commands: 
    sysctl -w net.core.rmem_max=262143
 and
    sysctl -w net.core.rmem_default=262143
-to increase the read buffer memory max and default to 262143 (256k - 1) from 
+to increase the read buffer memory max and default to 262143 (256k - 1) from
-defaults of max=131071 (128k - 1) and default=65535 (64k - 1). These variables 
+defaults of max=131071 (128k - 1) and default=65535 (64k - 1).  These variables
-will increase the amount of memory used by the network stack for receives, and 
+will increase the amount of memory used by the network stack for receives, and
 can be increased significantly more if necessary for your application.
+Additional Configurations
+=========================
+  Configuring the Driver on Different Distributions
+  -------------------------------------------------
+  Configuring a network driver to load properly when the system is started is
+  distribution dependent. Typically, the configuration process involves adding
+  an alias line to /etc/modprobe.conf as well as editing other system startup
+  scripts and/or configuration files.  Many popular Linux distributions ship
+  with tools to make these changes for you.  To learn the proper way to
+  configure a network device for your system, refer to your distribution
+  documentation.  If during this process you are asked for the driver or module
+  name, the name for the Linux Base Driver for the Intel 10GbE Family of
+  Adapters is ixgb.
+  Viewing Link Messages
+  ---------------------
+  Link messages will not be displayed to the console if the distribution is
+  restricting system messages. In order to see network driver link messages on
+  your console, set dmesg to eight by entering the following:
+       dmesg -n 8
+  NOTE: This setting is not saved across reboots.
+  Jumbo Frames
+  ------------
+  The driver supports Jumbo Frames for all adapters. Jumbo Frames support is
+  enabled by changing the MTU to a value larger than the default of 1500.
+  The maximum value for the MTU is 16114.  Use the ifconfig command to
+  increase the MTU size.  For example:
+        ifconfig ethx mtu 9000 up
+  The maximum MTU setting for Jumbo Frames is 16114.  This value coincides
+  with the maximum Jumbo Frames size of 16128.
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  Ethtool
+  version 1.6 or later is required for this functionality.
+  The latest release of ethtool can be found from
+  http://sourceforge.net/projects/gkernel
+  NOTE: Ethtool 1.6 only supports a limited set of ethtool options. Support
+        for a more complete ethtool feature set can be enabled by upgrading
+        to the latest version.
+  NAPI
+  ----
+  NAPI (Rx polling mode) is supported in the ixgb driver.  NAPI is enabled
+  or disabled based on the configuration of the kernel.  see CONFIG_IXGB_NAPI
+  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
+Known Issues/Troubleshooting
+============================
+  NOTE: After installing the driver, if your Intel Network Connection is not
+  working, verify in the "In This Release" section of the readme that you have
+  installed the correct driver.
+  Intel(R) PRO/10GbE CX4 Server Adapter Cable Interoperability Issue with
+  Fujitsu XENPAK Module in SmartBits Chassis
+  ---------------------------------------------------------------------
+  Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4
+  Server adapter is connected to a Fujitsu XENPAK CX4 module in a SmartBits
+  chassis using 15 m/24AWG cable assemblies manufactured by Fujitsu or Leoni.
+  The CRC errors may be received either by the Intel(R) PRO/10GbE CX4
+  Server adapter or the SmartBits. If this situation occurs using a different
+  cable assembly may resolve the issue.
+  CX4 Server Adapter Cable Interoperability Issues with HP Procurve 3400cl
+  Switch Port
+  ------------------------------------------------------------------------
+  Excessive CRC errors may be observed if the Intel(R) PRO/10GbE CX4 Server
+  adapter is connected to an HP Procurve 3400cl switch port using short cables
+  (1 m or shorter). If this situation occurs, using a longer cable may resolve
+  the issue.
+  Excessive CRC errors may be observed using Fujitsu 24AWG cable assemblies that
+  Are 10 m or longer or where using a Leoni 15 m/24AWG cable assembly. The CRC
+  errors may be received either by the CX4 Server adapter or at the switch. If
+  this situation occurs, using a different cable assembly may resolve the issue.
+  Jumbo Frames System Requirement
+  -------------------------------
+  Memory allocation failures have been observed on Linux systems with 64 MB
+  of RAM or less that are running Jumbo Frames.  If you are using Jumbo
+  Frames, your system may require more than the advertised minimum
+  requirement of 64 MB of system memory.
+  Performance Degradation with Jumbo Frames
+  -----------------------------------------
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments.  If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
+  Allocating Rx Buffers when Using Jumbo Frames
+  ---------------------------------------------
+  Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if
+  the available memory is heavily fragmented. This issue may be seen with PCI-X
+  adapters or with packet split disabled. This can be reduced or eliminated
+  by changing the amount of available memory for receive buffer allocation, by
+  increasing /proc/sys/vm/min_free_kbytes.
+  Multiple Interfaces on Same Ethernet Broadcast Network
+  ------------------------------------------------------
+  Due to the default ARP behavior on Linux, it is not possible to have
+  one system on two IP networks in the same Ethernet broadcast domain
+  (non-partitioned switch) behave as expected.  All Ethernet interfaces
+  will respond to IP traffic for any IP address assigned to the system.
+  This results in unbalanced receive traffic.
+  If you have multiple interfaces in a server, do either of the following:
+  - Turn on ARP filtering by entering:
+      echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+  - Install the interfaces in separate broadcast domains - either in
+    different switches or in a switch partitioned to VLANs.
+  UDP Stress Test Dropped Packet Issue
+  --------------------------------------
+  Under small packets UDP stress test with 10GbE driver, the Linux system
+  may drop UDP packets due to the fullness of socket buffers. You may want
+  to change the driver's Flow Control variables to the minimum value for
+  controlling packet reception.
+  Tx Hangs Possible Under Stress
+  ------------------------------
+  Under stress conditions, if TX hangs occur, turning off TSO
+  "ethtool -K eth0 tso off" may resolve the problem.
 Support
 =======
-For general information and support, go to the Intel support website at:
+For general information, go to the Intel support website at:
    http://support.intel.com
+or the Intel Wired Networking project hosted by Sourceforge at:
+    http://sourceforge.net/projects/e1000
 If an issue is identified with the released source code on the supported
-kernel with a supported adapter, email the specific information related to 
+kernel with a supported adapter, email the specific information related
-the issue to linux.nics@intel.com.
+to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/mac80211_hwsim/README b/Documentation/networking/mac80211_hwsim/README
new file mode 100644
index 000000000000..2ff8ccb8dc37
--- /dev/null
+++ b/Documentation/networking/mac80211_hwsim/README
@@ -0,0 +1,67 @@
+mac80211_hwsim - software simulator of 802.11 radio(s) for mac80211
+Copyright (c) 2008, Jouni Malinen <j@w1.fi>
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
+Introduction
+mac80211_hwsim is a Linux kernel module that can be used to simulate
+arbitrary number of IEEE 802.11 radios for mac80211. It can be used to
+test most of the mac80211 functionality and user space tools (e.g.,
+hostapd and wpa_supplicant) in a way that matches very closely with
+the normal case of using real WLAN hardware. From the mac80211 view
+point, mac80211_hwsim is yet another hardware driver, i.e., no changes
+to mac80211 are needed to use this testing tool.
+The main goal for mac80211_hwsim is to make it easier for developers
+to test their code and work with new features to mac80211, hostapd,
+and wpa_supplicant. The simulated radios do not have the limitations
+of real hardware, so it is easy to generate an arbitrary test setup
+and always reproduce the same setup for future tests. In addition,
+since all radio operation is simulated, any channel can be used in
+tests regardless of regulatory rules.
+mac80211_hwsim kernel module has a parameter 'radios' that can be used
+to select how many radios are simulated (default 2). This allows
+configuration of both very simply setups (e.g., just a single access
+point and a station) or large scale tests (multiple access points with
+hundreds of stations).
+mac80211_hwsim works by tracking the current channel of each virtual
+radio and copying all transmitted frames to all other radios that are
+currently enabled and on the same channel as the transmitting
+radio. Software encryption in mac80211 is used so that the frames are
+actually encrypted over the virtual air interface to allow more
+complete testing of encryption.
+A global monitoring netdev, hwsim#, is created independent of
+mac80211. This interface can be used to monitor all transmitted frames
+regardless of channel.
+Simple example
+This example shows how to use mac80211_hwsim to simulate two radios:
+one to act as an access point and the other as a station that
+associates with the AP. hostapd and wpa_supplicant are used to take
+care of WPA2-PSK authentication. In addition, hostapd is also
+processing access point side of association.
+Please note that the current Linux kernel does not enable AP mode, so a
+simple patch is needed to enable AP mode selection:
+http://johannes.sipsolutions.net/patches/kernel/all/LATEST/006-allow-ap-vlan-modes.patch
+# Build mac80211_hwsim as part of kernel configuration
+# Load the module
+modprobe mac80211_hwsim
+# Run hostapd (AP) for wlan0
+hostapd hostapd.conf
+# Run wpa_supplicant (station) for wlan1
+wpa_supplicant -Dwext -iwlan1 -c wpa_supplicant.conf
diff --git a/Documentation/networking/mac80211_hwsim/hostapd.conf b/Documentation/networking/mac80211_hwsim/hostapd.conf
new file mode 100644
index 000000000000..08cde7e35f2e
--- /dev/null
+++ b/Documentation/networking/mac80211_hwsim/hostapd.conf
@@ -0,0 +1,11 @@
+interface=wlan0
+driver=nl80211
+hw_mode=g
+channel=1
+ssid=mac80211 test
+wpa=2
+wpa_key_mgmt=WPA-PSK
+wpa_pairwise=CCMP
+wpa_passphrase=12345678
diff --git a/Documentation/networking/mac80211_hwsim/wpa_supplicant.conf b/Documentation/networking/mac80211_hwsim/wpa_supplicant.conf
new file mode 100644
index 000000000000..299128cff035
--- /dev/null
+++ b/Documentation/networking/mac80211_hwsim/wpa_supplicant.conf
@@ -0,0 +1,10 @@
+ctrl_interface=/var/run/wpa_supplicant
+network={
+        ssid="mac80211 test"
+        psk="12345678"
+        key_mgmt=WPA-PSK
+        proto=WPA2
+        pairwise=CCMP
+        group=CCMP
+}
diff --git a/Documentation/networking/multiqueue.txt b/Documentation/networking/multiqueue.txt
index ea5a42e8f79f..4caa0e314cc2 100644
--- a/Documentation/networking/multiqueue.txt
+++ b/Documentation/networking/multiqueue.txt
@@ -3,19 +3,11 @@
                ===========================================
 Section 1: Base driver requirements for implementing multiqueue support
-Section 2: Qdisc support for multiqueue devices
-Section 3: Brief howto using PRIO or RR for multiqueue devices
 Intro: Kernel support for multiqueue devices
 ---------------------------------------------------------
-Kernel support for multiqueue devices is only an API that is presented to the
+Kernel support for multiqueue devices is always present.
-netdevice layer for base drivers to implement.  This feature is part of the
-core networking stack, and all network devices will be running on the
-multiqueue-aware stack.  If a base driver only has one queue, then these
-changes are transparent to that driver.
 Section 1: Base driver requirements for implementing multiqueue support
 -----------------------------------------------------------------------
@@ -32,84 +24,56 @@ netif_{start|stop|wake}_subqueue() functions to manage each queue while the
 device is still operational.  netdev->queue_lock is still used when the device
 comes online or when it's completely shut down (unregister_netdev(), etc.).
-Finally, the base driver should indicate that it is a multiqueue device.  The
-feature flag NETIF_F_MULTI_QUEUE should be added to the netdev->features
-bitmap on device initialization.  Below is an example from e1000:
-#ifdef CONFIG_E1000_MQ
-        if ( (adapter->hw.mac.type == e1000_82571) ||
-             (adapter->hw.mac.type == e1000_82572) ||
-             (adapter->hw.mac.type == e1000_80003es2lan))
-                netdev->features |= NETIF_F_MULTI_QUEUE;
-#endif
 Section 2: Qdisc support for multiqueue devices
-----------------------------------------------
-Currently two qdiscs support multiqueue devices.  A new round-robin qdisc,
+-----------------------------------------------
-sch_rr, and sch_prio. The qdisc is responsible for classifying the skb's to
-bands and queues, and will store the queue mapping into skb->queue_mapping.
-Use this field in the base driver to determine which queue to send the skb
-to.
-sch_rr has been added for hardware that doesn't want scheduling policies from
+Currently two qdiscs are optimized for multiqueue devices.  The first is the
-software, so it's a straight round-robin qdisc.  It uses the same syntax and
+default pfifo_fast qdisc.  This qdisc supports one qdisc per hardware queue.
-classification priomap that sch_prio uses, so it should be intuitive to
+A new round-robin qdisc, sch_multiq also supports multiple hardware queues. The
-configure for people who've used sch_prio.
+qdisc is responsible for classifying the skb's and then directing the skb's to
+bands and queues based on the value in skb->queue_mapping.  Use this field in
+the base driver to determine which queue to send the skb to.
-In order to utilitize the multiqueue features of the qdiscs, the network
+sch_multiq has been added for hardware that wishes to avoid head-of-line
-device layer needs to enable multiple queue support.  This can be done by
+blocking.  It will cycle though the bands and verify that the hardware queue
-selecting NETDEVICES_MULTIQUEUE under Drivers.
+associated with the band is not stopped prior to dequeuing a packet.
-The PRIO qdisc naturally plugs into a multiqueue device.  If
+On qdisc load, the number of bands is based on the number of queues on the
-NETDEVICES_MULTIQUEUE is selected, then on qdisc load, the number of
+hardware.  Once the association is made, any skb with skb->queue_mapping set,
-bands requested is compared to the number of queues on the hardware.  If they
+will be queued to the band associated with the hardware queue.
-are equal, it sets a one-to-one mapping up between the queues and bands.  If
-they're not equal, it will not load the qdisc.  This is the same behavior
-for RR.  Once the association is made, any skb that is classified will have
-skb->queue_mapping set, which will allow the driver to properly queue skb's
-to multiple queues.
-Section 3: Brief howto using PRIO and RR for multiqueue devices
+Section 3: Brief howto using MULTIQ for multiqueue devices
 ---------------------------------------------------------------
 The userspace command 'tc,' part of the iproute2 package, is used to configure
-qdiscs.  To add the PRIO qdisc to your network device, assuming the device is
+qdiscs.  To add the MULTIQ qdisc to your network device, assuming the device
-called eth0, run the following command:
+is called eth0, run the following command:
-# tc qdisc add dev eth0 root handle 1: prio bands 4 multiqueue
+# tc qdisc add dev eth0 root handle 1: multiq
-This will create 4 bands, 0 being highest priority, and associate those bands
+The qdisc will allocate the number of bands to equal the number of queues that
-to the queues on your NIC.  Assuming eth0 has 4 Tx queues, the band mapping
+the device reports, and bring the qdisc online.  Assuming eth0 has 4 Tx
-would look like:
+queues, the band mapping would look like:
 band 0 => queue 0
 band 1 => queue 1
 band 2 => queue 2
 band 3 => queue 3
-Traffic will begin flowing through each queue if your TOS values are assigning
+Traffic will begin flowing through each queue based on either the simple_tx_hash
-traffic across the various bands.  For example, ssh traffic will always try to
+function or based on netdev->select_queue() if you have it defined.
-go out band 0 based on TOS -> Linux priority conversion (realtime traffic),
-so it will be sent out queue 0.  ICMP traffic (pings) fall into the "normal"
-traffic classification, which is band 1.  Therefore pings will be send out
-queue 1 on the NIC.
-Note the use of the multiqueue keyword.  This is only in versions of iproute2
-that support multiqueue networking devices; if this is omitted when loading
-a qdisc onto a multiqueue device, the qdisc will load and operate the same
-if it were loaded onto a single-queue device (i.e. - sends all traffic to
-queue 0).
-Another alternative to multiqueue band allocation can be done by using the
-multiqueue option and specify 0 bands.  If this is the case, the qdisc will
-allocate the number of bands to equal the number of queues that the device
-reports, and bring the qdisc online.
-The behavior of tc filters remains the same, where it will override TOS priority
+The behavior of tc filters remains the same.  However a new tc action,
-classification.
+skbedit, has been added.  Assuming you wanted to route all traffic to a
+specific host, for example 192.168.0.3, through a specific queue you could use
+this action and establish a filter such as:
+tc filter add dev eth0 parent 1: protocol ip prio 1 u32 \
+        match ip dst 192.168.0.3 \
+        action skbedit queue_mapping 3
-Author: Peter P. Waskiewicz Jr. <peter.p.waskiewicz.jr@intel.com>
+Author: Alexander Duyck <alexander.h.duyck@intel.com>
+Original Author: Peter P. Waskiewicz Jr. <peter.p.waskiewicz.jr@intel.com>
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index db0cd5169581..07c53d596035 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -326,7 +326,7 @@ just one call to mmap is needed:
    mmap(0, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
 If tp_frame_size is a divisor of tp_block_size frames will be 
-contiguosly spaced by tp_frame_size bytes. If not, each 
+contiguously spaced by tp_frame_size bytes. If not, each
 tp_block_size/tp_frame_size frames there will be a gap between 
 the frames. This is because a frame cannot be spawn across two
 blocks. 
diff --git a/Documentation/networking/phonet.txt b/Documentation/networking/phonet.txt
new file mode 100644
index 000000000000..6a07e45d4a93
--- /dev/null
+++ b/Documentation/networking/phonet.txt
@@ -0,0 +1,175 @@
+Linux Phonet protocol family
+============================
+Introduction
+------------
+Phonet is a packet protocol used by Nokia cellular modems for both IPC
+and RPC. With the Linux Phonet socket family, Linux host processes can
+receive and send messages from/to the modem, or any other external
+device attached to the modem. The modem takes care of routing.
+Phonet packets can be exchanged through various hardware connections
+depending on the device, such as:
+  - USB with the CDC Phonet interface,
+  - infrared,
+  - Bluetooth,
+  - an RS232 serial port (with a dedicated "FBUS" line discipline),
+  - the SSI bus with some TI OMAP processors.
+Packets format
+--------------
+Phonet packets have a common header as follows:
+  struct phonethdr {
+    uint8_t  pn_media;  /* Media type (link-layer identifier) */
+    uint8_t  pn_rdev;   /* Receiver device ID */
+    uint8_t  pn_sdev;   /* Sender device ID */
+    uint8_t  pn_res;    /* Resource ID or function */
+    uint16_t pn_length; /* Big-endian message byte length (minus 6) */
+    uint8_t  pn_robj;   /* Receiver object ID */
+    uint8_t  pn_sobj;   /* Sender object ID */
+  };
+On Linux, the link-layer header includes the pn_media byte (see below).
+The next 7 bytes are part of the network-layer header.
+The device ID is split: the 6 higher-order bits consitute the device
+address, while the 2 lower-order bits are used for multiplexing, as are
+the 8-bit object identifiers. As such, Phonet can be considered as a
+network layer with 6 bits of address space and 10 bits for transport
+protocol (much like port numbers in IP world).
+The modem always has address number zero. All other device have a their
+own 6-bit address.
+Link layer
+----------
+Phonet links are always point-to-point links. The link layer header
+consists of a single Phonet media type byte. It uniquely identifies the
+link through which the packet is transmitted, from the modem's
+perspective. Each Phonet network device shall prepend and set the media
+type byte as appropriate. For convenience, a common phonet_header_ops
+link-layer header operations structure is provided. It sets the
+media type according to the network device hardware address.
+Linux Phonet network interfaces support a dedicated link layer packets
+type (ETH_P_PHONET) which is out of the Ethernet type range. They can
+only send and receive Phonet packets.
+The virtual TUN tunnel device driver can also be used for Phonet. This
+requires IFF_TUN mode, _without_ the IFF_NO_PI flag. In this case,
+there is no link-layer header, so there is no Phonet media type byte.
+Note that Phonet interfaces are not allowed to re-order packets, so
+only the (default) Linux FIFO qdisc should be used with them.
+Network layer
+-------------
+The Phonet socket address family maps the Phonet packet header:
+  struct sockaddr_pn {
+    sa_family_t spn_family;    /* AF_PHONET */
+    uint8_t     spn_obj;       /* Object ID */
+    uint8_t     spn_dev;       /* Device ID */
+    uint8_t     spn_resource;  /* Resource or function */
+    uint8_t     spn_zero[...]; /* Padding */
+  };
+The resource field is only used when sending and receiving;
+It is ignored by bind() and getsockname().
+Low-level datagram protocol
+---------------------------
+Applications can send Phonet messages using the Phonet datagram socket
+protocol from the PF_PHONET family. Each socket is bound to one of the
+2^10 object IDs available, and can send and receive packets with any
+other peer.
+  struct sockaddr_pn addr = { .spn_family = AF_PHONET, };
+  ssize_t len;
+  socklen_t addrlen = sizeof(addr);
+  int fd;
+  fd = socket(PF_PHONET, SOCK_DGRAM, 0);
+  bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+  /* ... */
+  sendto(fd, msg, msglen, 0, (struct sockaddr *)&addr, sizeof(addr));
+  len = recvfrom(fd, buf, sizeof(buf), 0,
+                 (struct sockaddr *)&addr, &addrlen);
+This protocol follows the SOCK_DGRAM connection-less semantics.
+However, connect() and getpeername() are not supported, as they did
+not seem useful with Phonet usages (could be added easily).
+Phonet Pipe protocol
+--------------------
+The Phonet Pipe protocol is a simple sequenced packets protocol
+with end-to-end congestion control. It uses the passive listening
+socket paradigm. The listening socket is bound to an unique free object
+ID. Each listening socket can handle up to 255 simultaneous
+connections, one per accept()'d socket.
+  int lfd, cfd;
+  lfd = socket(PF_PHONET, SOCK_SEQPACKET, PN_PROTO_PIPE);
+  listen (lfd, INT_MAX);
+  /* ... */
+  cfd = accept(lfd, NULL, NULL);
+  for (;;)
+  {
+    char buf[...];
+    ssize_t len = read(cfd, buf, sizeof(buf));
+    /* ... */
+    write(cfd, msg, msglen);
+  }
+Connections are established between two endpoints by a "third party"
+application. This means that both endpoints are passive; so connect()
+is not possible.
+WARNING:
+When polling a connected pipe socket for writability, there is an
+intrinsic race condition whereby writability might be lost between the
+polling and the writing system calls. In this case, the socket will
+block until write becomes possible again, unless non-blocking mode
+is enabled.
+The pipe protocol provides two socket options at the SOL_PNPIPE level:
+  PNPIPE_ENCAP accepts one integer value (int) of:
+    PNPIPE_ENCAP_NONE: The socket operates normally (default).
+    PNPIPE_ENCAP_IP: The socket is used as a backend for a virtual IP
+      interface. This requires CAP_NET_ADMIN capability. GPRS data
+      support on Nokia modems can use this. Note that the socket cannot
+      be reliably poll()'d or read() from while in this mode.
+  PNPIPE_IFINDEX is a read-only integer value. It contains the
+    interface index of the network interface created by PNPIPE_ENCAP,
+    or zero if encapsulation is off.
+Authors
+-------
+Linux Phonet was initially written by Sakari Ailus.
+Other contributors include Mikä Liljeberg, Andras Domokos,
+Carlos Chinea and Rémi Denis-Courmont.
+Copyright (C) 2008 Nokia Corporation.
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
new file mode 100644
index 000000000000..a96989a8ff35
--- /dev/null
+++ b/Documentation/networking/regulatory.txt
@@ -0,0 +1,194 @@
+Linux wireless regulatory documentation
+---------------------------------------
+This document gives a brief review over how the Linux wireless
+regulatory infrastructure works.
+More up to date information can be obtained at the project's web page:
+http://wireless.kernel.org/en/developers/Regulatory
+Keeping regulatory domains in userspace
+---------------------------------------
+Due to the dynamic nature of regulatory domains we keep them
+in userspace and provide a framework for userspace to upload
+to the kernel one regulatory domain to be used as the central
+core regulatory domain all wireless devices should adhere to.
+How to get regulatory domains to the kernel
+-------------------------------------------
+Userspace gets a regulatory domain in the kernel by having
+a userspace agent build it and send it via nl80211. Only
+expected regulatory domains will be respected by the kernel.
+A currently available userspace agent which can accomplish this
+is CRDA - central regulatory domain agent. Its documented here:
+http://wireless.kernel.org/en/developers/Regulatory/CRDA
+Essentially the kernel will send a udev event when it knows
+it needs a new regulatory domain. A udev rule can be put in place
+to trigger crda to send the respective regulatory domain for a
+specific ISO/IEC 3166 alpha2.
+Below is an example udev rule which can be used:
+# Example file, should be put in /etc/udev/rules.d/regulatory.rules
+KERNEL=="regulatory*", ACTION=="change", SUBSYSTEM=="platform", RUN+="/sbin/crda"
+The alpha2 is passed as an environment variable under the variable COUNTRY.
+Who asks for regulatory domains?
+--------------------------------
+* Users
+Users can use iw:
+http://wireless.kernel.org/en/users/Documentation/iw
+An example:
+  # set regulatory domain to "Costa Rica"
+  iw reg set CR
+This will request the kernel to set the regulatory domain to
+the specificied alpha2. The kernel in turn will then ask userspace
+to provide a regulatory domain for the alpha2 specified by the user
+by sending a uevent.
+* Wireless subsystems for Country Information elements
+The kernel will send a uevent to inform userspace a new
+regulatory domain is required. More on this to be added
+as its integration is added.
+* Drivers
+If drivers determine they need a specific regulatory domain
+set they can inform the wireless core using regulatory_hint().
+They have two options -- they either provide an alpha2 so that
+crda can provide back a regulatory domain for that country or
+they can build their own regulatory domain based on internal
+custom knowledge so the wireless core can respect it.
+*Most* drivers will rely on the first mechanism of providing a
+regulatory hint with an alpha2. For these drivers there is an additional
+check that can be used to ensure compliance based on custom EEPROM
+regulatory data. This additional check can be used by drivers by
+registering on its struct wiphy a reg_notifier() callback. This notifier
+is called when the core's regulatory domain has been changed. The driver
+can use this to review the changes made and also review who made them
+(driver, user, country IE) and determine what to allow based on its
+internal EEPROM data. Devices drivers wishing to be capable of world
+roaming should use this callback. More on world roaming will be
+added to this document when its support is enabled.
+Device drivers who provide their own built regulatory domain
+do not need a callback as the channels registered by them are
+the only ones that will be allowed and therefore *additional*
+cannels cannot be enabled.
+Example code - drivers hinting an alpha2:
+------------------------------------------
+This example comes from the zd1211rw device driver. You can start
+by having a mapping of your device's EEPROM country/regulatory
+domain value to to a specific alpha2 as follows:
+static struct zd_reg_alpha2_map reg_alpha2_map[] = {
+        { ZD_REGDOMAIN_FCC, "US" },
+        { ZD_REGDOMAIN_IC, "CA" },
+        { ZD_REGDOMAIN_ETSI, "DE" }, /* Generic ETSI, use most restrictive */
+        { ZD_REGDOMAIN_JAPAN, "JP" },
+        { ZD_REGDOMAIN_JAPAN_ADD, "JP" },
+        { ZD_REGDOMAIN_SPAIN, "ES" },
+        { ZD_REGDOMAIN_FRANCE, "FR" },
+Then you can define a routine to map your read EEPROM value to an alpha2,
+as follows:
+static int zd_reg2alpha2(u8 regdomain, char *alpha2)
+{
+        unsigned int i;
+        struct zd_reg_alpha2_map *reg_map;
+                for (i = 0; i < ARRAY_SIZE(reg_alpha2_map); i++) {
+                        reg_map = &reg_alpha2_map[i];
+                        if (regdomain == reg_map->reg) {
+                        alpha2[0] = reg_map->alpha2[0];
+                        alpha2[1] = reg_map->alpha2[1];
+                        return 0;
+                }
+        }
+        return 1;
+}
+Lastly, you can then hint to the core of your discovered alpha2, if a match
+was found. You need to do this after you have registered your wiphy. You
+are expected to do this during initialization.
+        r = zd_reg2alpha2(mac->regdomain, alpha2);
+        if (!r)
+                regulatory_hint(hw->wiphy, alpha2, NULL);
+Example code - drivers providing a built in regulatory domain:
+--------------------------------------------------------------
+If you have regulatory information you can obtain from your
+driver and you *need* to use this we let you build a regulatory domain
+structure and pass it to the wireless core. To do this you should
+kmalloc() a structure big enough to hold your regulatory domain
+structure and you should then fill it with your data. Finally you simply
+call regulatory_hint() with the regulatory domain structure in it.
+Bellow is a simple example, with a regulatory domain cached using the stack.
+Your implementation may vary (read EEPROM cache instead, for example).
+Example cache of some regulatory domain
+struct ieee80211_regdomain mydriver_jp_regdom = {
+        .n_reg_rules = 3,
+        .alpha2 =  "JP",
+        //.alpha2 =  "99", /* If I have no alpha2 to map it to */
+        .reg_rules = {
+                /* IEEE 802.11b/g, channels 1..14 */
+                REG_RULE(2412-20, 2484+20, 40, 6, 20, 0),
+                /* IEEE 802.11a, channels 34..48 */
+                REG_RULE(5170-20, 5240+20, 40, 6, 20,
+                        NL80211_RRF_PASSIVE_SCAN),
+                /* IEEE 802.11a, channels 52..64 */
+                REG_RULE(5260-20, 5320+20, 40, 6, 20,
+                        NL80211_RRF_NO_IBSS |
+                        NL80211_RRF_DFS),
+        }
+};
+Then in some part of your code after your wiphy has been registered:
+        int r;
+        struct ieee80211_regdomain *rd;
+        int size_of_regd;
+        int num_rules = mydriver_jp_regdom.n_reg_rules;
+        unsigned int i;
+        size_of_regd = sizeof(struct ieee80211_regdomain) +
+                (num_rules * sizeof(struct ieee80211_reg_rule));
+        rd = kzalloc(size_of_regd, GFP_KERNEL);
+        if (!rd)
+        return -ENOMEM;
+        memcpy(rd, &mydriver_jp_regdom, sizeof(struct ieee80211_regdomain));
+        for (i=0; i < num_rules; i++) {
+                memcpy(&rd->reg_rules[i], &mydriver_jp_regdom.reg_rules[i],
+                        sizeof(struct ieee80211_reg_rule));
+        }
+        r = regulatory_hint(hw->wiphy, NULL, rd);
+        if (r) {
+                kfree(rd);
+                return r;
+        }
diff --git a/Documentation/networking/s2io.txt b/Documentation/networking/s2io.txt
index 1e28e2ddb90a..c3d6b4d5d014 100644
--- a/Documentation/networking/s2io.txt
+++ b/Documentation/networking/s2io.txt
@@ -52,13 +52,10 @@ d. MSI/MSI-X. Can be enabled on platforms which support this feature
 (IA64, Xeon) resulting in noticeable performance improvement(upto 7%
 on certain platforms).
-e. NAPI. Compile-time option(CONFIG_S2IO_NAPI) for better Rx interrupt 
+e. Statistics. Comprehensive MAC-level and software statistics displayed
-moderation.
-f. Statistics. Comprehensive MAC-level and software statistics displayed
 using "ethtool -S" option.
-g. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings, 
+f. Multi-FIFO/Ring. Supports up to 8 transmit queues and receive rings,
 with multiple steering options.
 4.  Command line parameters
diff --git a/Documentation/networking/tc-actions-env-rules.txt b/Documentation/networking/tc-actions-env-rules.txt
index 01e716d185f4..dcadf6f88e34 100644
--- a/Documentation/networking/tc-actions-env-rules.txt
+++ b/Documentation/networking/tc-actions-env-rules.txt
@@ -4,26 +4,27 @@ The "enviromental" rules for authors of any new tc actions are:
 1) If you stealeth or borroweth any packet thou shalt be branching
 from the righteous path and thou shalt cloneth.
-For example if your action queues a packet to be processed later
+For example if your action queues a packet to be processed later,
-or intentionaly branches by redirecting a packet then you need to
+or intentionally branches by redirecting a packet, then you need to
 clone the packet.
 There are certain fields in the skb tc_verd that need to be reset so we
-avoid loops etc. A few are generic enough so much so that skb_act_clone()
+avoid loops, etc.  A few are generic enough that skb_act_clone()
-resets them for you. So invoke skb_act_clone() rather than skb_clone()
+resets them for you, so invoke skb_act_clone() rather than skb_clone().
 2) If you munge any packet thou shalt call pskb_expand_head in the case
 someone else is referencing the skb. After that you "own" the skb.
 You must also tell us if it is ok to munge the packet (TC_OK2MUNGE),
 this way any action downstream can stomp on the packet.
-3) dropping packets you dont own is a nono. You simply return
+3) Dropping packets you don't own is a no-no. You simply return
 TC_ACT_SHOT to the caller and they will drop it.
 The "enviromental" rules for callers of actions (qdiscs etc) are:
-*) thou art responsible for freeing anything returned as being
+*) Thou art responsible for freeing anything returned as being
 TC_ACT_SHOT/STOLEN/QUEUED. If none of TC_ACT_SHOT/STOLEN/QUEUED is
-returned then all is great and you dont need to do anything.
+returned, then all is great and you don't need to do anything.
 Post on netdev if something is unclear.
diff --git a/Documentation/networking/tproxy.txt b/Documentation/networking/tproxy.txt
new file mode 100644
index 000000000000..7b5996d9357e
--- /dev/null
+++ b/Documentation/networking/tproxy.txt
@@ -0,0 +1,85 @@
+Transparent proxy support
+=========================
+This feature adds Linux 2.2-like transparent proxy support to current kernels.
+To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in
+your kernel config. You will need policy routing too, so be sure to enable that
+as well.
+1. Making non-local sockets work
+================================
+The idea is that you identify packets with destination address matching a local
+socket on your box, set the packet mark to a certain value, and then match on that
+value using policy routing to have those packets delivered locally:
+# iptables -t mangle -N DIVERT
+# iptables -t mangle -A PREROUTING -p tcp -m socket -j DIVERT
+# iptables -t mangle -A DIVERT -j MARK --set-mark 1
+# iptables -t mangle -A DIVERT -j ACCEPT
+# ip rule add fwmark 1 lookup 100
+# ip route add local 0.0.0.0/0 dev lo table 100
+Because of certain restrictions in the IPv4 routing output code you'll have to
+modify your application to allow it to send datagrams _from_ non-local IP
+addresses. All you have to do is enable the (SOL_IP, IP_TRANSPARENT) socket
+option before calling bind:
+fd = socket(AF_INET, SOCK_STREAM, 0);
+/* - 8< -*/
+int value = 1;
+setsockopt(fd, SOL_IP, IP_TRANSPARENT, &value, sizeof(value));
+/* - 8< -*/
+name.sin_family = AF_INET;
+name.sin_port = htons(0xCAFE);
+name.sin_addr.s_addr = htonl(0xDEADBEEF);
+bind(fd, &name, sizeof(name));
+A trivial patch for netcat is available here:
+http://people.netfilter.org/hidden/tproxy/netcat-ip_transparent-support.patch
+2. Redirecting traffic
+======================
+Transparent proxying often involves "intercepting" traffic on a router. This is
+usually done with the iptables REDIRECT target; however, there are serious
+limitations of that method. One of the major issues is that it actually
+modifies the packets to change the destination address -- which might not be
+acceptable in certain situations. (Think of proxying UDP for example: you won't
+be able to find out the original destination address. Even in case of TCP
+getting the original destination address is racy.)
+The 'TPROXY' target provides similar functionality without relying on NAT. Simply
+add rules like this to the iptables ruleset above:
+# iptables -t mangle -A PREROUTING -p tcp --dport 80 -j TPROXY \
+  --tproxy-mark 0x1/0x1 --on-port 50080
+Note that for this to work you'll have to modify the proxy to enable (SOL_IP,
+IP_TRANSPARENT) for the listening socket.
+3. Iptables extensions
+======================
+To use tproxy you'll need to have the 'socket' and 'TPROXY' modules
+compiled for iptables. A patched version of iptables is available
+here: http://git.balabit.hu/?p=bazsi/iptables-tproxy.git
+4. Application support
+======================
+4.1. Squid
+----------
+Squid 3.HEAD has support built-in. To use it, pass
+'--enable-linux-netfilter' to configure and set the 'tproxy' option on
+the HTTP listener you redirect traffic to with the TPROXY iptables
+target.
+For more information please consult the following page on the Squid
+wiki: http://wiki.squid-cache.org/Features/Tproxy4
diff --git a/Documentation/networking/udplite.txt b/Documentation/networking/udplite.txt
index 3870f280280b..855d8da57a23 100644
--- a/Documentation/networking/udplite.txt
+++ b/Documentation/networking/udplite.txt
@@ -148,7 +148,7 @@
        getsockopt(sockfd, SOL_SOCKET, SO_NO_CHECK, &value, ...);
  is meaningless (as in TCP). Packets with a zero checksum field are
-  illegal (cf. RFC 3828, sec. 3.1) will be silently discarded.
+  illegal (cf. RFC 3828, sec. 3.1) and will be silently discarded.
  4) Fragmentation
diff --git a/Documentation/networking/vortex.txt b/Documentation/networking/vortex.txt
index 6356d3faed36..bd70976b8160 100644
--- a/Documentation/networking/vortex.txt
+++ b/Documentation/networking/vortex.txt
@@ -1,5 +1,5 @@
 Documentation/networking/vortex.txt
-Andrew Morton <andrewm@uow.edu.au>
+Andrew Morton
 30 April 2000
@@ -11,7 +11,7 @@ The driver was written by Donald Becker <becker@scyld.com>
 Don is no longer the prime maintainer of this version of the driver. 
 Please report problems to one or more of:
-  Andrew Morton <akpm@osdl.org>
+  Andrew Morton
  Netdev mailing list <netdev@vger.kernel.org>
  Linux kernel mailing list <linux-kernel@vger.kernel.org>
@@ -305,11 +305,6 @@ Donald's wake-on-LAN page:
        ftp://ftp.3com.com/pub/nic/3c90x/3c90xx2.exe
-Driver updates and a detailed changelog for the modifications which
-were made for the 2.3/2,4 series kernel is available at
-     http://www.zip.com.au/~akpm/linux/#3c59x-bc
 Autonegotiation notes
 ---------------------
diff --git a/Documentation/pcmcia/Makefile b/Documentation/pcmcia/Makefile
new file mode 100644
index 000000000000..accde871ae77
--- /dev/null
+++ b/Documentation/pcmcia/Makefile
@@ -0,0 +1,10 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := crc32hash
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_crc32hash.o += -I$(objtree)/usr/include
diff --git a/Documentation/pcmcia/crc32hash.c b/Documentation/pcmcia/crc32hash.c
index cbc36d299af8..4210e5abab8a 100644
--- a/Documentation/pcmcia/crc32hash.c
+++ b/Documentation/pcmcia/crc32hash.c
@@ -26,7 +26,7 @@ int main(int argc, char **argv) {
                printf("no string passed as argument\n");
                return -1;
        }
-        result = crc32(argv[1], strlen(argv[1]));
+        result = crc32((unsigned char const *)argv[1], strlen(argv[1]));
        printf("0x%x\n", result);
        return 0;
 }
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 96f155e68750..059934363caf 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,5 +1,11 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* New configuration loop helper (as of 2.6.28)
+   By calling pcmcia_loop_config(), a driver can iterate over all available
+   configuration options. During a driver's probe() phase, one doesn't need
+   to use pcmcia_get_{first,next}_tuple, pcmcia_get_tuple_data and
+   pcmcia_parse_tuple directly in most if not all cases.
 * New release helper (as of 2.6.17)
   Instead of calling pcmcia_release_{configuration,io,irq,win}, all that's
   necessary now is calling pcmcia_disable_device. As there is no valid
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index a55d7f1c836d..fb742c213c9e 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
        - This file
+apm-acpi.txt
+        - basic info about the APM and ACPI support.
 basic-pm-debugging.txt
        - Debugging suspend and resume
 devices.txt
@@ -14,8 +16,6 @@ notifiers.txt
        - Registering suspend notifiers in device drivers
 pci.txt
        - How the PCI Subsystem Does Power Management
-pm.txt
-        - info on Linux power management support.
 pm_qos_interface.txt
        - info on Linux PM Quality of Service interface
 power_supply_class.txt
diff --git a/Documentation/power/apm-acpi.txt b/Documentation/power/apm-acpi.txt
new file mode 100644
index 000000000000..1bd799dc17e8
--- /dev/null
+++ b/Documentation/power/apm-acpi.txt
@@ -0,0 +1,32 @@
+APM or ACPI?
+------------
+If you have a relatively recent x86 mobile, desktop, or server system,
+odds are it supports either Advanced Power Management (APM) or
+Advanced Configuration and Power Interface (ACPI).  ACPI is the newer
+of the two technologies and puts power management in the hands of the
+operating system, allowing for more intelligent power management than
+is possible with BIOS controlled APM.
+The best way to determine which, if either, your system supports is to
+build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is
+enabled by default).  If a working ACPI implementation is found, the
+ACPI driver will override and disable APM, otherwise the APM driver
+will be used.
+No, sorry, you cannot have both ACPI and APM enabled and running at
+once.  Some people with broken ACPI or broken APM implementations
+would like to use both to get a full set of working features, but you
+simply cannot mix and match the two.  Only one power management
+interface can be in control of the machine at once.  Think about it..
+User-space Daemons
+------------------
+Both APM and ACPI rely on user-space daemons, apmd and acpid
+respectively, to be completely functional.  Obtain both of these
+daemons from your Linux distribution or from the Internet (see below)
+and be sure that they are started sometime in the system boot process.
+Go ahead and start both.  If ACPI or APM is not available on your
+system the associated daemon will exit gracefully.
+  apmd:   http://worldvisions.ca/~apenwarr/apmd/
+  acpid:  http://acpid.sf.net/
diff --git a/Documentation/power/pm.txt b/Documentation/power/pm.txt
deleted file mode 100644
index be841507e43f..000000000000
--- a/Documentation/power/pm.txt
+++ /dev/null
@@ -1,257 +0,0 @@
-               Linux Power Management Support
-This document briefly describes how to use power management with your
-Linux system and how to add power management support to Linux drivers.
-APM or ACPI?
------------
-If you have a relatively recent x86 mobile, desktop, or server system,
-odds are it supports either Advanced Power Management (APM) or
-Advanced Configuration and Power Interface (ACPI).  ACPI is the newer
-of the two technologies and puts power management in the hands of the
-operating system, allowing for more intelligent power management than
-is possible with BIOS controlled APM.
-The best way to determine which, if either, your system supports is to
-build a kernel with both ACPI and APM enabled (as of 2.3.x ACPI is
-enabled by default).  If a working ACPI implementation is found, the
-ACPI driver will override and disable APM, otherwise the APM driver
-will be used.
-No, sorry, you cannot have both ACPI and APM enabled and running at
-once.  Some people with broken ACPI or broken APM implementations
-would like to use both to get a full set of working features, but you
-simply cannot mix and match the two.  Only one power management
-interface can be in control of the machine at once.  Think about it..
-User-space Daemons
------------------
-Both APM and ACPI rely on user-space daemons, apmd and acpid
-respectively, to be completely functional.  Obtain both of these
-daemons from your Linux distribution or from the Internet (see below)
-and be sure that they are started sometime in the system boot process.
-Go ahead and start both.  If ACPI or APM is not available on your
-system the associated daemon will exit gracefully.
-  apmd:   http://worldvisions.ca/~apenwarr/apmd/
-  acpid:  http://acpid.sf.net/
-Driver Interface -- OBSOLETE, DO NOT USE!
----------------*************************
-Note: pm_register(), pm_access(), pm_dev_idle() and friends are
-obsolete. Please do not use them. Instead you should properly hook
-your driver into the driver model, and use its suspend()/resume()
-callbacks to do this kind of stuff.
-If you are writing a new driver or maintaining an old driver, it
-should include power management support.  Without power management
-support, a single driver may prevent a system with power management
-capabilities from ever being able to suspend (safely).
-Overview:
-1) Register each instance of a device with "pm_register"
-2) Call "pm_access" before accessing the hardware.
-   (this will ensure that the hardware is awake and ready)
-3) Your "pm_callback" is called before going into a
-   suspend state (ACPI D1-D3) or after resuming (ACPI D0)
-   from a suspend.
-4) Call "pm_dev_idle" when the device is not being used
-   (optional but will improve device idle detection)
-5) When unloaded, unregister the device with "pm_unregister"
-/*
- * Description: Register a device with the power-management subsystem
- *
- * Parameters:
- *   type - device type (PCI device, system device, ...)
- *   id - instance number or unique identifier
- *   cback - request handler callback (suspend, resume, ...)
- *
- * Returns: Registered PM device or NULL on error
- *
- * Examples:
- *   dev = pm_register(PM_SYS_DEV, PM_SYS_VGA, vga_callback);
- *
- *   struct pci_dev *pci_dev = pci_find_dev(...);
- *   dev = pm_register(PM_PCI_DEV, PM_PCI_ID(pci_dev), callback);
- */
-struct pm_dev *pm_register(pm_dev_t type, unsigned long id, pm_callback cback);
-/*
- * Description: Unregister a device with the power management subsystem
- *
- * Parameters:
- *   dev - PM device previously returned from pm_register
- */
-void pm_unregister(struct pm_dev *dev);
-/*
- * Description: Unregister all devices with a matching callback function
- *
- * Parameters:
- *   cback - previously registered request callback
- *
- * Notes: Provided for easier porting from old APM interface
- */
-void pm_unregister_all(pm_callback cback);
-/*
- * Power management request callback
- *
- * Parameters:
- *   dev - PM device previously returned from pm_register
- *   rqst - request type
- *   data - data, if any, associated with the request
- *
- * Returns: 0 if the request is successful
- *          EINVAL if the request is not supported
- *          EBUSY if the device is now busy and cannot handle the request
- *          ENOMEM if the device was unable to handle the request due to memory
- *
- * Details: The device request callback will be called before the
- *          device/system enters a suspend state (ACPI D1-D3) or
- *          or after the device/system resumes from suspend (ACPI D0).
- *          For PM_SUSPEND, the ACPI D-state being entered is passed
- *          as the "data" argument to the callback.  The device
- *          driver should save (PM_SUSPEND) or restore (PM_RESUME)
- *          device context when the request callback is called.
- *
- *          Once a driver returns 0 (success) from a suspend
- *          request, it should not process any further requests or
- *          access the device hardware until a call to "pm_access" is made.
- */
-typedef int (*pm_callback)(struct pm_dev *dev, pm_request_t rqst, void *data);
-Driver Details
--------------
-This is just a quick Q&A as a stopgap until a real driver writers'
-power management guide is available.
-Q: When is a device suspended?
-Devices can be suspended based on direct user request (eg. laptop lid
-closes), system power policy (eg.  sleep after 30 minutes of console
-inactivity), or device power policy (eg. power down device after 5
-minutes of inactivity)
-Q: Must a driver honor a suspend request?
-No, a driver can return -EBUSY from a suspend request and this
-will stop the system from suspending.  When a suspend request
-fails, all suspended devices are resumed and the system continues
-to run.  Suspend can be retried at a later time.
-Q: Can the driver block suspend/resume requests?
-Yes, a driver can delay its return from a suspend or resume
-request until the device is ready to handle requests.  It
-is advantageous to return as quickly as possible from a
-request as suspend/resume are done serially.
-Q: What context is a suspend/resume initiated from?
-A suspend or resume is initiated from a kernel thread context.
-It is safe to block, allocate memory, initiate requests
-or anything else you can do within the kernel.
-Q: Will requests continue to arrive after a suspend?
-Possibly.  It is the driver's responsibility to queue(*),
-fail, or drop any requests that arrive after returning
-success to a suspend request.  It is important that the
-driver not access its device until after it receives
-a resume request as the device's bus may no longer
-be active.
-(*) If a driver queues requests for processing after
-    resume be aware that the device, network, etc.
-    might be in a different state than at suspend time.
-    It's probably better to drop requests unless
-    the driver is a storage device.
-Q: Do I have to manage bus-specific power management registers
-No.  It is the responsibility of the bus driver to manage
-PCI, USB, etc. power management registers.  The bus driver
-or the power management subsystem will also enable any
-wake-on functionality that the device has.
-Q: So, really, what do I need to do to support suspend/resume?
-You need to save any device context that would
-be lost if the device was powered off and then restore
-it at resume time.  When ACPI is active, there are
-three levels of device suspend states; D1, D2, and D3.
-(The suspend state is passed as the "data" argument
-to the device callback.)  With D3, the device is powered
-off and loses all context, D1 and D2 are shallower power
-states and require less device context to be saved.  To
-play it safe, just save everything at suspend and restore
-everything at resume.
-Q: Where do I store device context for suspend?
-Anywhere in memory, kmalloc a buffer or store it
-in the device descriptor.  You are guaranteed that the
-contents of memory will be restored and accessible
-before resume, even when the system suspends to disk.
-Q: What do I need to do for ACPI vs. APM vs. etc?
-Drivers need not be aware of the specific power management
-technology that is active.  They just need to be aware
-of when the overlying power management system requests
-that they suspend or resume.
-Q: What about device dependencies?
-When a driver registers a device, the power management
-subsystem uses the information provided to build a
-tree of device dependencies (eg. USB device X is on
-USB controller Y which is on PCI bus Z)  When power
-management wants to suspend a device, it first sends
-a suspend request to its driver, then the bus driver,
-and so on up to the system bus.  Device resumes
-proceed in the opposite direction.
-Q: Who do I contact for additional information about
-   enabling power management for my specific driver/device?
-ACPI Development mailing list: linux-acpi@vger.kernel.org
-System Interface -- OBSOLETE, DO NOT USE!
----------------*************************
-If you are providing new power management support to Linux (ie.
-adding support for something like APM or ACPI), you should
-communicate with drivers through the existing generic power
-management interface.
-/*
- * Send a request to all devices
- *
- * Parameters:
- *   rqst - request type
- *   data - data, if any, associated with the request
- *
- * Returns: 0 if the request is successful
- *          See "pm_callback" return for errors
- *
- * Details: Walk list of registered devices and call pm_send
- *          for each until complete or an error is encountered.
- *          If an error is encountered for a suspend request,
- *          return all devices to the state they were in before
- *          the suspend request.
- */
-int pm_send_all(pm_request_t rqst, void *data);
-/*
- * Find a matching device
- *
- * Parameters:
- *   type - device type (PCI device, system device, or 0 to match all devices)
- *   from - previous match or NULL to start from the beginning
- *
- * Returns: Matching device or NULL if none found
- */
-struct pm_dev *pm_find(pm_dev_t type, struct pm_dev *from);
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index 49adb1a33514..c40866e8b957 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -1,4 +1,4 @@
-PM quality of Service interface.
+PM Quality Of Service Interface.
 This interface provides a kernel and user mode interface for registering
 performance expectations by drivers, subsystems and user space applications on
@@ -7,6 +7,11 @@ one of the parameters.
 Currently we have {cpu_dma_latency, network_latency, network_throughput} as the
 initial set of pm_qos parameters.
+Each parameters have defined units:
+ * latency: usec
+ * timeout: usec
+ * throughput: kbs (kilo bit / sec)
 The infrastructure exposes multiple misc device nodes one per implemented
 parameter.  The set of parameters implement is defined by pm_qos_power_init()
 and pm_qos_params.h.  This is done because having the available parameters
diff --git a/Documentation/power/power_supply_class.txt b/Documentation/power/power_supply_class.txt
index a8686e5a6857..c6cd4956047c 100644
--- a/Documentation/power/power_supply_class.txt
+++ b/Documentation/power/power_supply_class.txt
@@ -101,6 +101,10 @@ of charge when battery became full/empty". It also could mean "value of
 charge when battery considered full/empty at given conditions (temperature,
 age)". I.e. these attributes represents real thresholds, not design values.
+CHARGE_COUNTER - the current charge counter (in µAh).  This could easily
+be negative; there is no empty or full value.  It is only useful for
+relative, time-based measurements.
 ENERGY_FULL, ENERGY_EMPTY - same as above but for energy.
 CAPACITY - capacity in percents.
diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt
new file mode 100644
index 000000000000..82b7a43aadba
--- /dev/null
+++ b/Documentation/power/regulator/consumer.txt
@@ -0,0 +1,182 @@
+Regulator Consumer Driver Interface
+===================================
+This text describes the regulator interface for consumer device drivers.
+Please see overview.txt for a description of the terms used in this text.
+1. Consumer Regulator Access (static & dynamic drivers)
+=======================================================
+A consumer driver can get access to it's supply regulator by calling :-
+regulator = regulator_get(dev, "Vcc");
+The consumer passes in it's struct device pointer and power supply ID. The core
+then finds the correct regulator by consulting a machine specific lookup table.
+If the lookup is successful then this call will return a pointer to the struct
+regulator that supplies this consumer.
+To release the regulator the consumer driver should call :-
+regulator_put(regulator);
+Consumers can be supplied by more than one regulator e.g. codec consumer with
+analog and digital supplies :-
+digital = regulator_get(dev, "Vcc");  /* digital core */
+analog = regulator_get(dev, "Avdd");  /* analog */
+The regulator access functions regulator_get() and regulator_put() will
+usually be called in your device drivers probe() and remove() respectively.
+2. Regulator Output Enable & Disable (static & dynamic drivers)
+====================================================================
+A consumer can enable it's power supply by calling:-
+int regulator_enable(regulator);
+NOTE: The supply may already be enabled before regulator_enabled() is called.
+This may happen if the consumer shares the regulator or the regulator has been
+previously enabled by bootloader or kernel board initialization code.
+A consumer can determine if a regulator is enabled by calling :-
+int regulator_is_enabled(regulator);
+This will return > zero when the regulator is enabled.
+A consumer can disable it's supply when no longer needed by calling :-
+int regulator_disable(regulator);
+NOTE: This may not disable the supply if it's shared with other consumers. The
+regulator will only be disabled when the enabled reference count is zero.
+Finally, a regulator can be forcefully disabled in the case of an emergency :-
+int regulator_force_disable(regulator);
+NOTE: this will immediately and forcefully shutdown the regulator output. All
+consumers will be powered off.
+3. Regulator Voltage Control & Status (dynamic drivers)
+======================================================
+Some consumer drivers need to be able to dynamically change their supply
+voltage to match system operating points. e.g. CPUfreq drivers can scale
+voltage along with frequency to save power, SD drivers may need to select the
+correct card voltage, etc.
+Consumers can control their supply voltage by calling :-
+int regulator_set_voltage(regulator, min_uV, max_uV);
+Where min_uV and max_uV are the minimum and maximum acceptable voltages in
+microvolts.
+NOTE: this can be called when the regulator is enabled or disabled. If called
+when enabled, then the voltage changes instantly, otherwise the voltage
+configuration changes and the voltage is physically set when the regulator is
+next enabled.
+The regulators configured voltage output can be found by calling :-
+int regulator_get_voltage(regulator);
+NOTE: get_voltage() will return the configured output voltage whether the
+regulator is enabled or disabled and should NOT be used to determine regulator
+output state. However this can be used in conjunction with is_enabled() to
+determine the regulator physical output voltage.
+4. Regulator Current Limit Control & Status (dynamic drivers)
+===========================================================
+Some consumer drivers need to be able to dynamically change their supply
+current limit to match system operating points. e.g. LCD backlight driver can
+change the current limit to vary the backlight brightness, USB drivers may want
+to set the limit to 500mA when supplying power.
+Consumers can control their supply current limit by calling :-
+int regulator_set_current_limit(regulator, min_uV, max_uV);
+Where min_uA and max_uA are the minimum and maximum acceptable current limit in
+microamps.
+NOTE: this can be called when the regulator is enabled or disabled. If called
+when enabled, then the current limit changes instantly, otherwise the current
+limit configuration changes and the current limit is physically set when the
+regulator is next enabled.
+A regulators current limit can be found by calling :-
+int regulator_get_current_limit(regulator);
+NOTE: get_current_limit() will return the current limit whether the regulator
+is enabled or disabled and should not be used to determine regulator current
+load.
+5. Regulator Operating Mode Control & Status (dynamic drivers)
+=============================================================
+Some consumers can further save system power by changing the operating mode of
+their supply regulator to be more efficient when the consumers operating state
+changes. e.g. consumer driver is idle and subsequently draws less current
+Regulator operating mode can be changed indirectly or directly.
+Indirect operating mode control.
+--------------------------------
+Consumer drivers can request a change in their supply regulator operating mode
+by calling :-
+int regulator_set_optimum_mode(struct regulator *regulator, int load_uA);
+This will cause the core to recalculate the total load on the regulator (based
+on all it's consumers) and change operating mode (if necessary and permitted)
+to best match the current operating load.
+The load_uA value can be determined from the consumers datasheet. e.g.most
+datasheets have tables showing the max current consumed in certain situations.
+Most consumers will use indirect operating mode control since they have no
+knowledge of the regulator or whether the regulator is shared with other
+consumers.
+Direct operating mode control.
+------------------------------
+Bespoke or tightly coupled drivers may want to directly control regulator
+operating mode depending on their operating point. This can be achieved by
+calling :-
+int regulator_set_mode(struct regulator *regulator, unsigned int mode);
+unsigned int regulator_get_mode(struct regulator *regulator);
+Direct mode will only be used by consumers that *know* about the regulator and
+are not sharing the regulator with other consumers.
+6. Regulator Events
+===================
+Regulators can notify consumers of external events. Events could be received by
+consumers under regulator stress or failure conditions.
+Consumers can register interest in regulator events by calling :-
+int regulator_register_notifier(struct regulator *regulator,
+                              struct notifier_block *nb);
+Consumers can uregister interest by calling :-
+int regulator_unregister_notifier(struct regulator *regulator,
+                                struct notifier_block *nb);
+Regulators use the kernel notifier framework to send event to thier interested
+consumers.
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
new file mode 100644
index 000000000000..ce3487d99abe
--- /dev/null
+++ b/Documentation/power/regulator/machine.txt
@@ -0,0 +1,93 @@
+Regulator Machine Driver Interface
+===================================
+The regulator machine driver interface is intended for board/machine specific
+initialisation code to configure the regulator subsystem.
+Consider the following machine :-
+  Regulator-1 -+-> Regulator-2 --> [Consumer A @ 1.8 - 2.0V]
+               |
+               +-> [Consumer B @ 3.3V]
+The drivers for consumers A & B must be mapped to the correct regulator in
+order to control their power supply. This mapping can be achieved in machine
+initialisation code by creating a struct regulator_consumer_supply for
+each regulator.
+struct regulator_consumer_supply {
+        struct device *dev;     /* consumer */
+        const char *supply;     /* consumer supply - e.g. "vcc" */
+};
+e.g. for the machine above
+static struct regulator_consumer_supply regulator1_consumers[] = {
+{
+        .dev    = &platform_consumerB_device.dev,
+        .supply = "Vcc",
+},};
+static struct regulator_consumer_supply regulator2_consumers[] = {
+{
+        .dev    = &platform_consumerA_device.dev,
+        .supply = "Vcc",
+},};
+This maps Regulator-1 to the 'Vcc' supply for Consumer B and maps Regulator-2
+to the 'Vcc' supply for Consumer A.
+Constraints can now be registered by defining a struct regulator_init_data
+for each regulator power domain. This structure also maps the consumers
+to their supply regulator :-
+static struct regulator_init_data regulator1_data = {
+        .constraints = {
+                .min_uV = 3300000,
+                .max_uV = 3300000,
+                .valid_modes_mask = REGULATOR_MODE_NORMAL,
+        },
+        .num_consumer_supplies = ARRAY_SIZE(regulator1_consumers),
+        .consumer_supplies = regulator1_consumers,
+};
+Regulator-1 supplies power to Regulator-2. This relationship must be registered
+with the core so that Regulator-1 is also enabled when Consumer A enables it's
+supply (Regulator-2). The supply regulator is set by the supply_regulator_dev
+field below:-
+static struct regulator_init_data regulator2_data = {
+        .supply_regulator_dev = &platform_regulator1_device.dev,
+        .constraints = {
+                .min_uV = 1800000,
+                .max_uV = 2000000,
+                .valid_ops_mask = REGULATOR_CHANGE_VOLTAGE,
+                .valid_modes_mask = REGULATOR_MODE_NORMAL,
+        },
+        .num_consumer_supplies = ARRAY_SIZE(regulator2_consumers),
+        .consumer_supplies = regulator2_consumers,
+};
+Finally the regulator devices must be registered in the usual manner.
+static struct platform_device regulator_devices[] = {
+{
+        .name = "regulator",
+        .id = DCDC_1,
+        .dev = {
+                .platform_data = &regulator1_data,
+        },
+},
+{
+        .name = "regulator",
+        .id = DCDC_2,
+        .dev = {
+                .platform_data = &regulator2_data,
+        },
+},
+};
+/* register regulator 1 device */
+platform_device_register(&wm8350_regulator_devices[0]);
+/* register regulator 2 device */
+platform_device_register(&wm8350_regulator_devices[1]);
diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt
new file mode 100644
index 000000000000..bdcb332bd7fb
--- /dev/null
+++ b/Documentation/power/regulator/overview.txt
@@ -0,0 +1,171 @@
+Linux voltage and current regulator framework
+=============================================
+About
+=====
+This framework is designed to provide a standard kernel interface to control
+voltage and current regulators.
+The intention is to allow systems to dynamically control regulator power output
+in order to save power and prolong battery life. This applies to both voltage
+regulators (where voltage output is controllable) and current sinks (where
+current limit is controllable).
+(C) 2008  Wolfson Microelectronics PLC.
+Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Nomenclature
+============
+Some terms used in this document:-
+  o Regulator    - Electronic device that supplies power to other devices.
+                   Most regulators can enable and disable their output whilst
+                   some can control their output voltage and or current.
+                   Input Voltage -> Regulator -> Output Voltage
+  o PMIC         - Power Management IC. An IC that contains numerous regulators
+                   and often contains other susbsystems.
+  o Consumer     - Electronic device that is supplied power by a regulator.
+                   Consumers can be classified into two types:-
+                   Static: consumer does not change it's supply voltage or
+                   current limit. It only needs to enable or disable it's
+                   power supply. It's supply voltage is set by the hardware,
+                   bootloader, firmware or kernel board initialisation code.
+                   Dynamic: consumer needs to change it's supply voltage or
+                   current limit to meet operation demands.
+  o Power Domain - Electronic circuit that is supplied it's input power by the
+                   output power of a regulator, switch or by another power
+                   domain.
+                   The supply regulator may be behind a switch(s). i.e.
+                   Regulator -+-> Switch-1 -+-> Switch-2 --> [Consumer A]
+                              |             |
+                              |             +-> [Consumer B], [Consumer C]
+                              |
+                              +-> [Consumer D], [Consumer E]
+                   That is one regulator and three power domains:
+                   Domain 1: Switch-1, Consumers D & E.
+                   Domain 2: Switch-2, Consumers B & C.
+                   Domain 3: Consumer A.
+                   and this represents a "supplies" relationship:
+                   Domain-1 --> Domain-2 --> Domain-3.
+                   A power domain may have regulators that are supplied power
+                   by other regulators. i.e.
+                   Regulator-1 -+-> Regulator-2 -+-> [Consumer A]
+                                |
+                                +-> [Consumer B]
+                   This gives us two regulators and two power domains:
+                   Domain 1: Regulator-2, Consumer B.
+                   Domain 2: Consumer A.
+                   and a "supplies" relationship:
+                   Domain-1 --> Domain-2
+  o Constraints  - Constraints are used to define power levels for performance
+                   and hardware protection. Constraints exist at three levels:
+                   Regulator Level: This is defined by the regulator hardware
+                   operating parameters and is specified in the regulator
+                   datasheet. i.e.
+                     - voltage output is in the range 800mV -> 3500mV.
+                     - regulator current output limit is 20mA @ 5V but is
+                       10mA @ 10V.
+                   Power Domain Level: This is defined in software by kernel
+                   level board initialisation code. It is used to constrain a
+                   power domain to a particular power range. i.e.
+                     - Domain-1 voltage is 3300mV
+                     - Domain-2 voltage is 1400mV -> 1600mV
+                     - Domain-3 current limit is 0mA -> 20mA.
+                   Consumer Level: This is defined by consumer drivers
+                   dynamically setting voltage or current limit levels.
+                   e.g. a consumer backlight driver asks for a current increase
+                   from 5mA to 10mA to increase LCD illumination. This passes
+                   to through the levels as follows :-
+                   Consumer: need to increase LCD brightness. Lookup and
+                   request next current mA value in brightness table (the
+                   consumer driver could be used on several different
+                   personalities based upon the same reference device).
+                   Power Domain: is the new current limit within the domain
+                   operating limits for this domain and system state (e.g.
+                   battery power, USB power)
+                   Regulator Domains: is the new current limit within the
+                   regulator operating parameters for input/ouput voltage.
+                   If the regulator request passes all the constraint tests
+                   then the new regulator value is applied.
+Design
+======
+The framework is designed and targeted at SoC based devices but may also be
+relevant to non SoC devices and is split into the following four interfaces:-
+   1. Consumer driver interface.
+      This uses a similar API to the kernel clock interface in that consumer
+      drivers can get and put a regulator (like they can with clocks atm) and
+      get/set voltage, current limit, mode, enable and disable. This should
+      allow consumers complete control over their supply voltage and current
+      limit. This also compiles out if not in use so drivers can be reused in
+      systems with no regulator based power control.
+        See Documentation/power/regulator/consumer.txt
+   2. Regulator driver interface.
+      This allows regulator drivers to register their regulators and provide
+      operations to the core. It also has a notifier call chain for propagating
+      regulator events to clients.
+        See Documentation/power/regulator/regulator.txt
+   3. Machine interface.
+      This interface is for machine specific code and allows the creation of
+      voltage/current domains (with constraints) for each regulator. It can
+      provide regulator constraints that will prevent device damage through
+      overvoltage or over current caused by buggy client drivers. It also
+      allows the creation of a regulator tree whereby some regulators are
+      supplied by others (similar to a clock tree).
+        See Documentation/power/regulator/machine.txt
+   4. Userspace ABI.
+      The framework also exports a lot of useful voltage/current/opmode data to
+      userspace via sysfs. This could be used to help monitor device power
+      consumption and status.
+        See Documentation/ABI/testing/regulator-sysfs.txt
diff --git a/Documentation/power/regulator/regulator.txt b/Documentation/power/regulator/regulator.txt
new file mode 100644
index 000000000000..4200accb9bba
--- /dev/null
+++ b/Documentation/power/regulator/regulator.txt
@@ -0,0 +1,30 @@
+Regulator Driver Interface
+==========================
+The regulator driver interface is relatively simple and designed to allow
+regulator drivers to register their services with the core framework.
+Registration
+============
+Drivers can register a regulator by calling :-
+struct regulator_dev *regulator_register(struct device *dev,
+        struct regulator_desc *regulator_desc);
+This will register the regulators capabilities and operations to the regulator
+core.
+Regulators can be unregistered by calling :-
+void regulator_unregister(struct regulator_dev *rdev);
+Regulator Events
+================
+Regulators can send events (e.g. over temp, under voltage, etc) to consumer
+drivers by calling :-
+int regulator_notifier_call_chain(struct regulator_dev *rdev,
+                                  unsigned long event, void *data);
diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt
index b05f512130ea..2ebdc6091ce1 100644
--- a/Documentation/power/s2ram.txt
+++ b/Documentation/power/s2ram.txt
@@ -54,3 +54,21 @@ 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
 PLL's, and it just _hangs_. Using the regular VGA console and letting X
 resume it instead works fine.
+NOTE
+====
+pm_trace uses the system's Real Time Clock (RTC) to save the magic number.
+Reason for this is that the RTC is the only reliably available piece of
+hardware during resume operations where a value can be set that will
+survive a reboot.
+Consequence is that after a resume (even if it is successful) your system
+clock will have a value corresponding to the magic mumber instead of the
+correct date/time! It is therefore advisable to use a program like ntp-date
+or rdate to reset the correct date/time from an external time source when
+using this trace option.
+As the clock keeps ticking it is also essential that the reboot is done
+quickly after the resume failure. The trace option does not use the seconds
+or the low order bits of the minutes of the RTC, but a too long delay will
+corrupt the magic value.
diff --git a/Documentation/powerpc/00-INDEX b/Documentation/powerpc/00-INDEX
index 3be84aa38dfe..e3960b8c8689 100644
--- a/Documentation/powerpc/00-INDEX
+++ b/Documentation/powerpc/00-INDEX
@@ -18,12 +18,6 @@ mpc52xx.txt
        - Linux 2.6.x on MPC52xx family
 mpc52xx-device-tree-bindings.txt
        - MPC5200 Device Tree Bindings
-ppc_htab.txt
-        - info about the Linux/PPC /proc/ppc_htab entry
-SBC8260_memory_mapping.txt
-        - EST SBC8260 board info
-smp.txt
-        - use and state info about Linux/PPC on MP machines
 sound.txt
        - info on sound support under Linux/PPC
 zImage_layout.txt
diff --git a/Documentation/powerpc/SBC8260_memory_mapping.txt b/Documentation/powerpc/SBC8260_memory_mapping.txt
deleted file mode 100644
index e6e9ee0506c3..000000000000
--- a/Documentation/powerpc/SBC8260_memory_mapping.txt
+++ /dev/null
@@ -1,197 +0,0 @@
-Please mail me (Jon Diekema, diekema_jon@si.com or diekema@cideas.com)
-if you have questions, comments or corrections.
-        * EST SBC8260 Linux memory mapping rules
-        http://www.estc.com/ 
-        http://www.estc.com/products/boards/SBC8260-8240_ds.html
-        Initial conditions:
-        -------------------
-        
-        Tasks that need to be perform by the boot ROM before control is
-        transferred to zImage (compressed Linux kernel):
-        - Define the IMMR to 0xf0000000
-        - Initialize the memory controller so that RAM is available at
-          physical address 0x00000000.  On the SBC8260 is this 16M (64M)
-          SDRAM.
-        - The boot ROM should only clear the RAM that it is using.
-          The reason for doing this is to enhances the chances of a
-          successful post mortem on a Linux panic.  One of the first
-          items to examine is the 16k (LOG_BUF_LEN) circular console
-          buffer called log_buf which is defined in kernel/printk.c.
-        - To enhance boot ROM performance, the I-cache can be enabled.
-          Date: Mon, 22 May 2000 14:21:10 -0700
-          From: Neil Russell <caret@c-side.com>
-          LiMon (LInux MONitor) runs with and starts Linux with MMU
-          off, I-cache enabled, D-cache disabled.  The I-cache doesn't
-          need hints from the MMU to work correctly as the D-cache
-          does.  No D-cache means no special code to handle devices in
-          the presence of cache (no snooping, etc). The use of the
-          I-cache means that the monitor can run acceptably fast
-          directly from ROM, rather than having to copy it to RAM.
-        - Build the board information structure (see 
-          include/asm-ppc/est8260.h for its definition)
-        - The compressed Linux kernel (zImage) contains a bootstrap loader 
-          that is position independent; you can load it into any RAM, 
-          ROM or FLASH memory address >= 0x00500000 (above 5 MB), or
-          at its link address of 0x00400000 (4 MB).
-          Note: If zImage is loaded at its link address of 0x00400000 (4 MB),
-                then zImage will skip the step of moving itself to 
-                its link address.
-        - Load R3 with the address of the board information structure
-        - Transfer control to zImage
-        - The Linux console port is SMC1, and the baud rate is controlled
-          from the bi_baudrate field of the board information structure.
-          On thing to keep in mind when picking the baud rate, is that
-          there is no flow control on the SMC ports.  I would stick
-          with something safe and standard like 19200.
-          On the EST SBC8260, the SMC1 port is on the COM1 connector of
-          the board.
-        
-        EST SBC8260 defaults:
-        ---------------------
-                                Chip
-        Memory                  Sel  Bus   Use
-        ---------------------   ---  ---   ----------------------------------
-        0x00000000-0x03FFFFFF   CS2  60x   (16M or 64M)/64M SDRAM
-        0x04000000-0x04FFFFFF   CS4  local  4M/16M SDRAM (soldered to the board)
-        0x21000000-0x21000000   CS7  60x    1B/64K Flash present detect (from the flash SIMM)
-        0x21000001-0x21000001   CS7  60x    1B/64K Switches (read) and LEDs (write)
-        0x22000000-0x2200FFFF   CS5  60x    8K/64K EEPROM
-        0xFC000000-0xFCFFFFFF   CS6  60x    2M/16M flash (8 bits wide, soldered to the board)
-        0xFE000000-0xFFFFFFFF   CS0  60x    4M/16M flash (SIMM)
-        Notes:
-        ------
-        - The chip selects can map 32K blocks and up (powers of 2)
-        - The SDRAM machine can handled up to 128Mbytes per chip select
-        - Linux uses the 60x bus memory (the SDRAM DIMM) for the 
-          communications buffers.
-        - BATs can map 128K-256Mbytes each.  There are four data BATs and
-          four instruction BATs.  Generally the data and instruction BATs
-          are mapped the same.
-        - The IMMR must be set above the kernel virtual memory addresses,
-          which start at 0xC0000000.  Otherwise, the kernel may crash as
-          soon as you start any threads or processes due to VM collisions 
-          in the kernel or user process space.
-          Details from Dan Malek <dan_malek@mvista.com> on 10/29/1999:
-          The user application virtual space consumes the first 2 Gbytes
-          (0x00000000 to 0x7FFFFFFF).  The kernel virtual text starts at
-          0xC0000000, with data following.  There is a "protection hole"
-          between the end of kernel data and the start of the kernel
-          dynamically allocated space, but this space is still within
-          0xCxxxxxxx.
-          Obviously the kernel can't map any physical addresses 1:1 in
-          these ranges.
-          Details from Dan Malek <dan_malek@mvista.com> on 5/19/2000:
-          During the early kernel initialization, the kernel virtual
-          memory allocator is not operational.  Prior to this KVM
-          initialization, we choose to map virtual to physical addresses
-          1:1.  That is, the kernel virtual address exactly matches the
-          physical address on the bus.  These mappings are typically done
-          in arch/ppc/kernel/head.S, or arch/ppc/mm/init.c.  Only
-          absolutely necessary mappings should be done at this time, for
-          example board control registers or a serial uart.  Normal device
-          driver initialization should map resources later when necessary.
-          Although platform dependent, and certainly the case for embedded
-          8xx, traditionally memory is mapped at physical address zero,
-          and I/O devices above physical address 0x80000000.  The lowest
-          and highest (above 0xf0000000) I/O addresses are traditionally 
-          used for devices or registers we need to map during kernel 
-          initialization and prior to KVM operation.  For this reason, 
-          and since it followed prior PowerPC platform examples, I chose 
-          to map the embedded 8xx kernel to the 0xc0000000 virtual address.
-          This way, we can enable the MMU to map the kernel for proper 
-          operation, and still map a few windows before the KVM is operational.
-          On some systems, you could possibly run the kernel at the 
-          0x80000000 or any other virtual address.  It just depends upon 
-          mapping that must be done prior to KVM operational.  You can never 
-          map devices or kernel spaces that overlap with the user virtual 
-          space.  This is why default IMMR mapping used by most BDM tools 
-          won't work.  They put the IMMR at something like 0x10000000 or 
-          0x02000000 for example.  You simply can't map these addresses early
-          in the kernel, and continue proper system operation.
-          The embedded 8xx/82xx kernel is mature enough that all you should 
-          need to do is map the IMMR someplace at or above 0xf0000000 and it 
-          should boot far enough to get serial console messages and KGDB 
-          connected on any platform.  There are lots of other subtle memory 
-          management design features that you simply don't need to worry 
-          about.  If you are changing functions related to MMU initialization,
-          you are likely breaking things that are known to work and are 
-          heading down a path of disaster and frustration.  Your changes 
-          should be to make the flexibility of the processor fit Linux, 
-          not force arbitrary and non-workable memory mappings into Linux.
-        - You don't want to change KERNELLOAD or KERNELBASE, otherwise the
-          virtual memory and MMU code will get confused.
-        
-          arch/ppc/Makefile:KERNELLOAD = 0xc0000000
-          include/asm-ppc/page.h:#define PAGE_OFFSET    0xc0000000
-          include/asm-ppc/page.h:#define KERNELBASE     PAGE_OFFSET
-        - RAM is at physical address 0x00000000, and gets mapped to 
-          virtual address 0xC0000000 for the kernel.
-        Physical addresses used by the Linux kernel:
-        --------------------------------------------
-        0x00000000-0x3FFFFFFF   1GB reserved for RAM
-        0xF0000000-0xF001FFFF   128K IMMR  64K used for dual port memory,
-                                 64K for 8260 registers
-        
-        Logical addresses used by the Linux kernel:
-        -------------------------------------------
-        0xF0000000-0xFFFFFFFF   256M BAT0 (IMMR: dual port RAM, registers)
-        0xE0000000-0xEFFFFFFF   256M BAT1 (I/O space for custom boards)
-        0xC0000000-0xCFFFFFFF   256M BAT2 (RAM)
-        0xD0000000-0xDFFFFFFF   256M BAT3 (if RAM > 256MByte)
-        EST SBC8260 Linux mapping:
-        --------------------------
-        DBAT0, IBAT0, cache inhibited:
-                                Chip
-        Memory                  Sel  Use
-        ---------------------   ---  ---------------------------------
-        0xF0000000-0xF001FFFF   n/a  IMMR: dual port RAM, registers
-        DBAT1, IBAT1, cache inhibited:
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index de2e5c05d6e7..02ea9a971b8e 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -41,12 +41,25 @@ Table of Contents
  VI - System-on-a-chip devices and nodes
    1) Defining child nodes of an SOC
    2) Representing devices without a current OF specification
-      a) PHY nodes
+      a) MDIO IO device
-      b) Interrupt controllers
+      b) Gianfar-compatible ethernet nodes
-      c) CFI or JEDEC memory-mapped NOR flash
+      c) PHY nodes
-      d) 4xx/Axon EMAC ethernet nodes
+      d) Interrupt controllers
-      e) Xilinx IP cores
+      e) I2C
-      f) USB EHCI controllers
+      f) Freescale SOC USB controllers
+      g) Freescale SOC SEC Security Engines
+      h) Board Control and Status (BCSR)
+      i) Freescale QUICC Engine module (QE)
+      j) CFI or JEDEC memory-mapped NOR flash
+      k) Global Utilities Block
+      l) Freescale Communications Processor Module
+      m) Chipselect/Local Bus
+      n) 4xx/Axon EMAC ethernet nodes
+      o) Xilinx IP cores
+      p) Freescale Synchronous Serial Interface
+          q) USB EHCI controllers
+      r) MDIO on GPIOs
+      s) SPI busses
  VII - Marvell Discovery mv64[345]6x System Controller chips
    1) The /system-controller node
@@ -77,10 +90,12 @@ Table of Contents
    3) OpenPIC Interrupt Controllers
    4) ISA Interrupt Controllers
-  VIII - Specifying GPIO information for devices
+  IX - Specifying GPIO information for devices
    1) gpios property
    2) gpio-controller nodes
+  X - Specifying device power management information (sleep property)
  Appendix A - Sample SOC node for MPC8540
@@ -263,7 +278,7 @@ it with special cases.
        a 64-bit platform.
        d) request and get assigned a platform number (see PLATFORM_*
-        constants in include/asm-powerpc/processor.h
+        constants in arch/powerpc/include/asm/processor.h
 32-bit embedded kernels:
@@ -325,7 +340,7 @@ the block to RAM before passing it to the kernel.
 ---------
   The kernel is entered with r3 pointing to an area of memory that is
-   roughly described in include/asm-powerpc/prom.h by the structure
+   roughly described in arch/powerpc/include/asm/prom.h by the structure
   boot_param_header:
 struct boot_param_header {
@@ -693,7 +708,7 @@ device or bus to be described by the device tree.
 In general, the format of an address for a device is defined by the
 parent bus type, based on the #address-cells and #size-cells
 properties.  Note that the parent's parent definitions of #address-cells
-and #size-cells are not inhereted so every node with children must specify
+and #size-cells are not inherited so every node with children must specify
 them.  The kernel requires the root node to have those properties defining
 addresses format for devices directly mapped on the processor bus.
@@ -1762,7 +1777,7 @@ platforms are moved over to use the flattened-device-tree model.
      Xilinx uartlite devices are simple fixed speed serial ports.
-      Requred properties:
+      Required properties:
       - current-speed : Baud rate of uartlite
      v) Xilinx hwicap
@@ -1784,7 +1799,7 @@ platforms are moved over to use the flattened-device-tree model.
      Xilinx UART 16550 devices are very similar to the NS16550 but with
      different register spacing and an offset from the base address.
-      Requred properties:
+      Required properties:
       - clock-frequency : Frequency of the clock input
       - reg-offset : A value of 3 is required
       - reg-shift : A value of 2 is required
@@ -1815,6 +1830,118 @@ platforms are moved over to use the flattened-device-tree model.
                   big-endian;
           };
+    r) Freescale Display Interface Unit
+    The Freescale DIU is a LCD controller, with proper hardware, it can also
+    drive DVI monitors.
+    Required properties:
+    - compatible : should be "fsl-diu".
+    - reg : should contain at least address and length of the DIU register
+      set.
+    - Interrupts : one DIU interrupt should be describe here.
+    Example (MPC8610HPCD)
+        display@2c000 {
+                compatible = "fsl,diu";
+                reg = <0x2c000 100>;
+                interrupts = <72 2>;
+                interrupt-parent = <&mpic>;
+        };
+    s) Freescale on board FPGA
+    This is the memory-mapped registers for on board FPGA.
+    Required properities:
+    - compatible : should be "fsl,fpga-pixis".
+    - reg : should contain the address and the lenght of the FPPGA register
+      set.
+    Example (MPC8610HPCD)
+        board-control@e8000000 {
+                compatible = "fsl,fpga-pixis";
+                reg = <0xe8000000 32>;
+        };
+   r) MDIO on GPIOs
+   Currently defined compatibles:
+   - virtual,gpio-mdio
+   MDC and MDIO lines connected to GPIO controllers are listed in the
+   gpios property as described in section VIII.1 in the following order:
+   MDC, MDIO.
+   Example:
+        mdio {
+                compatible = "virtual,mdio-gpio";
+                #address-cells = <1>;
+                #size-cells = <0>;
+                gpios = <&qe_pio_a 11
+                         &qe_pio_c 6>;
+        };
+    s) SPI (Serial Peripheral Interface) busses
+    SPI busses can be described with a node for the SPI master device
+    and a set of child nodes for each SPI slave on the bus.  For this
+    discussion, it is assumed that the system's SPI controller is in
+    SPI master mode.  This binding does not describe SPI controllers
+    in slave mode.
+    The SPI master node requires the following properties:
+    - #address-cells  - number of cells required to define a chip select
+                        address on the SPI bus.
+    - #size-cells     - should be zero.
+    - compatible      - name of SPI bus controller following generic names
+                        recommended practice.
+    No other properties are required in the SPI bus node.  It is assumed
+    that a driver for an SPI bus device will understand that it is an SPI bus.
+    However, the binding does not attempt to define the specific method for
+    assigning chip select numbers.  Since SPI chip select configuration is
+    flexible and non-standardized, it is left out of this binding with the
+    assumption that board specific platform code will be used to manage
+    chip selects.  Individual drivers can define additional properties to
+    support describing the chip select layout.
+    SPI slave nodes must be children of the SPI master node and can
+    contain the following properties.
+    - reg             - (required) chip select address of device.
+    - compatible      - (required) name of SPI device following generic names
+                        recommended practice
+    - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
+    - spi-cpol        - (optional) Empty property indicating device requires
+                        inverse clock polarity (CPOL) mode
+    - spi-cpha        - (optional) Empty property indicating device requires
+                        shifted clock phase (CPHA) mode
+    - spi-cs-high     - (optional) Empty property indicating device requires
+                        chip select active high
+    SPI example for an MPC5200 SPI bus:
+                spi@f00 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
+                        reg = <0xf00 0x20>;
+                        interrupts = <2 13 0 2 14 0>;
+                        interrupt-parent = <&mpc5200_pic>;
+                        ethernet-switch@0 {
+                                compatible = "micrel,ks8995m";
+                                spi-max-frequency = <1000000>;
+                                reg = <0>;
+                        };
+                        codec@1 {
+                                compatible = "ti,tlv320aic26";
+                                spi-max-frequency = <100000>;
+                                reg = <1>;
+                        };
+                };
 VII - Marvell Discovery mv64[345]6x System Controller chips
 ===========================================================
@@ -1828,7 +1955,7 @@ prefixed with the string "marvell,", for Marvell Technology Group Ltd.
 1) The /system-controller node
  This node is used to represent the system-controller and must be
-  present when the system uses a system contller chip. The top-level
+  present when the system uses a system controller chip. The top-level
  system-controller node contains information that is global to all
  devices within the system controller chip. The node name begins
  with "system-controller" followed by the unit address, which is
@@ -2422,8 +2549,8 @@ encodings listed below:
        2 =  high to low edge sensitive type enabled
        3 =  low to high edge sensitive type enabled
-VIII - Specifying GPIO information for devices
+IX - Specifying GPIO information for devices
-==============================================
+============================================
 1) gpios property
 -----------------
@@ -2471,116 +2598,151 @@ Example of two SOC GPIO banks defined as gpio-controller nodes:
                gpio-controller;
        };
+X - Specifying Device Power Management Information (sleep property)
+===================================================================
+Devices on SOCs often have mechanisms for placing devices into low-power
+states that are decoupled from the devices' own register blocks.  Sometimes,
+this information is more complicated than a cell-index property can
+reasonably describe.  Thus, each device controlled in such a manner
+may contain a "sleep" property which describes these connections.
+The sleep property consists of one or more sleep resources, each of
+which consists of a phandle to a sleep controller, followed by a
+controller-specific sleep specifier of zero or more cells.
+The semantics of what type of low power modes are possible are defined
+by the sleep controller.  Some examples of the types of low power modes
+that may be supported are:
+ - Dynamic: The device may be disabled or enabled at any time.
+ - System Suspend: The device may request to be disabled or remain
+   awake during system suspend, but will not be disabled until then.
+ - Permanent: The device is disabled permanently (until the next hard
+   reset).
+Some devices may share a clock domain with each other, such that they should
+only be suspended when none of the devices are in use.  Where reasonable,
+such nodes should be placed on a virtual bus, where the bus has the sleep
+property.  If the clock domain is shared among devices that cannot be
+reasonably grouped in this manner, then create a virtual sleep controller
+(similar to an interrupt nexus, except that defining a standardized
+sleep-map should wait until its necessity is demonstrated).
 Appendix A - Sample SOC node for MPC8540
 ========================================
-Note that the #address-cells and #size-cells for the SoC node
+        soc@e0000000 {
-in this example have been explicitly listed; these are likely
-not necessary as they are usually the same as the root node.
-        soc8540@e0000000 {
                #address-cells = <1>;
                #size-cells = <1>;
-                #interrupt-cells = <2>;
+                compatible = "fsl,mpc8540-ccsr", "simple-bus";
                device_type = "soc";
-                ranges = <00000000 e0000000 00100000>
+                ranges = <0x00000000 0xe0000000 0x00100000>
-                reg = <e0000000 00003000>;
                bus-frequency = <0>;
+                interrupt-parent = <&pic>;
-                mdio@24520 {
-                        reg = <24520 20>;
-                        device_type = "mdio";
-                        compatible = "gianfar";
-                        ethernet-phy@0 {
-                                linux,phandle = <2452000>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <0>;
-                                device_type = "ethernet-phy";
-                        };
-                        ethernet-phy@1 {
-                                linux,phandle = <2452001>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <1>;
-                                device_type = "ethernet-phy";
-                        };
-                        ethernet-phy@3 {
-                                linux,phandle = <2452002>
-                                interrupt-parent = <40000>;
-                                interrupts = <35 1>;
-                                reg = <3>;
-                                device_type = "ethernet-phy";
-                        };
-                };
                ethernet@24000 {
-                        #size-cells = <0>;
+                        #address-cells = <1>;
+                        #size-cells = <1>;
                        device_type = "network";
                        model = "TSEC";
-                        compatible = "gianfar";
+                        compatible = "gianfar", "simple-bus";
-                        reg = <24000 1000>;
+                        reg = <0x24000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 00 ];
+                        local-mac-address = [ 00 E0 0C 00 73 00 ];
-                        interrupts = <d 3 e 3 12 3>;
+                        interrupts = <29 2 30 2 34 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy0>;
-                        phy-handle = <2452000>;
+                        sleep = <&pmc 00000080>;
+                        ranges;
+                        mdio@24520 {
+                                reg = <0x24520 0x20>;
+                                compatible = "fsl,gianfar-mdio";
+                                phy0: ethernet-phy@0 {
+                                        interrupts = <5 1>;
+                                        reg = <0>;
+                                        device_type = "ethernet-phy";
+                                };
+                                phy1: ethernet-phy@1 {
+                                        interrupts = <5 1>;
+                                        reg = <1>;
+                                        device_type = "ethernet-phy";
+                                };
+                                phy3: ethernet-phy@3 {
+                                        interrupts = <7 1>;
+                                        reg = <3>;
+                                        device_type = "ethernet-phy";
+                                };
+                        };
                };
                ethernet@25000 {
-                        #address-cells = <1>;
-                        #size-cells = <0>;
                        device_type = "network";
                        model = "TSEC";
                        compatible = "gianfar";
-                        reg = <25000 1000>;
+                        reg = <0x25000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 01 ];
+                        local-mac-address = [ 00 E0 0C 00 73 01 ];
-                        interrupts = <13 3 14 3 18 3>;
+                        interrupts = <13 2 14 2 18 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy1>;
-                        phy-handle = <2452001>;
+                        sleep = <&pmc 00000040>;
                };
                ethernet@26000 {
-                        #address-cells = <1>;
-                        #size-cells = <0>;
                        device_type = "network";
                        model = "FEC";
                        compatible = "gianfar";
-                        reg = <26000 1000>;
+                        reg = <0x26000 0x1000>;
-                        mac-address = [ 00 E0 0C 00 73 02 ];
+                        local-mac-address = [ 00 E0 0C 00 73 02 ];
-                        interrupts = <19 3>;
+                        interrupts = <41 2>;
-                        interrupt-parent = <40000>;
+                        phy-handle = <&phy3>;
-                        phy-handle = <2452002>;
+                        sleep = <&pmc 00000020>;
                };
                serial@4500 {
-                        device_type = "serial";
+                        #address-cells = <1>;
-                        compatible = "ns16550";
+                        #size-cells = <1>;
-                        reg = <4500 100>;
+                        compatible = "fsl,mpc8540-duart", "simple-bus";
-                        clock-frequency = <0>;
+                        sleep = <&pmc 00000002>;
-                        interrupts = <1a 3>;
+                        ranges;
-                        interrupt-parent = <40000>;
+                        serial@4500 {
+                                device_type = "serial";
+                                compatible = "ns16550";
+                                reg = <0x4500 0x100>;
+                                clock-frequency = <0>;
+                                interrupts = <42 2>;
+                        };
+                        serial@4600 {
+                                device_type = "serial";
+                                compatible = "ns16550";
+                                reg = <0x4600 0x100>;
+                                clock-frequency = <0>;
+                                interrupts = <42 2>;
+                        };
                };
-                pic@40000 {
+                pic: pic@40000 {
-                        linux,phandle = <40000>;
                        interrupt-controller;
                        #address-cells = <0>;
-                        reg = <40000 40000>;
+                        #interrupt-cells = <2>;
+                        reg = <0x40000 0x40000>;
                        compatible = "chrp,open-pic";
                        device_type = "open-pic";
                };
                i2c@3000 {
-                        interrupt-parent = <40000>;
+                        interrupts = <43 2>;
-                        interrupts = <1b 3>;
+                        reg = <0x3000 0x100>;
-                        reg = <3000 18>;
-                        device_type = "i2c";
                        compatible  = "fsl-i2c";
                        dfsrr;
+                        sleep = <&pmc 00000004>;
                };
+                pmc: power@e0070 {
+                        compatible = "fsl,mpc8540-pmc", "fsl,mpc8548-pmc";
+                        reg = <0xe0070 0x20>;
+                };
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/83xx-512x-pci.txt b/Documentation/powerpc/dts-bindings/fsl/83xx-512x-pci.txt
new file mode 100644
index 000000000000..35a465362408
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/83xx-512x-pci.txt
@@ -0,0 +1,40 @@
+* Freescale 83xx and 512x PCI bridges
+Freescale 83xx and 512x SOCs include the same pci bridge core.
+83xx/512x specific notes:
+- reg: should contain two address length tuples
+    The first is for the internal pci bridge registers
+    The second is for the pci config space access registers
+Example (MPC8313ERDB)
+        pci0: pci@e0008500 {
+                cell-index = <1>;
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+                                /* IDSEL 0x0E -mini PCI */
+                                 0x7000 0x0 0x0 0x1 &ipic 18 0x8
+                                 0x7000 0x0 0x0 0x2 &ipic 18 0x8
+                                 0x7000 0x0 0x0 0x3 &ipic 18 0x8
+                                 0x7000 0x0 0x0 0x4 &ipic 18 0x8
+                                /* IDSEL 0x0F - PCI slot */
+                                 0x7800 0x0 0x0 0x1 &ipic 17 0x8
+                                 0x7800 0x0 0x0 0x2 &ipic 18 0x8
+                                 0x7800 0x0 0x0 0x3 &ipic 17 0x8
+                                 0x7800 0x0 0x0 0x4 &ipic 18 0x8>;
+                interrupt-parent = <&ipic>;
+                interrupts = <66 0x8>;
+                bus-range = <0x0 0x0>;
+                ranges = <0x02000000 0x0 0x90000000 0x90000000 0x0 0x10000000
+                          0x42000000 0x0 0x80000000 0x80000000 0x0 0x10000000
+                          0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>;
+                clock-frequency = <66666666>;
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                reg = <0xe0008500 0x100         /* internal registers */
+                       0xe0008300 0x8>;         /* config space access registers */
+                compatible = "fsl,mpc8349-pci";
+                device_type = "pci";
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt b/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt
new file mode 100644
index 000000000000..d015dcec4011
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt
@@ -0,0 +1,40 @@
+GPIO controllers on MPC8xxx SoCs
+This is for the non-QE/CPM/GUTs GPIO controllers as found on
+8349, 8572, 8610 and compatible.
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+Required properties:
+- compatible : "fsl,<CHIP>-gpio" followed by "fsl,mpc8349-gpio" for
+  83xx, "fsl,mpc8572-gpio" for 85xx and "fsl,mpc8610-gpio" for 86xx.
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional parameters (currently unused).
+ - interrupts : Interrupt mapping for GPIO IRQ (currently unused).
+ - interrupt-parent : Phandle for the interrupt controller that
+   services interrupts for this device.
+- gpio-controller : Marks the port as GPIO controller.
+Example of gpio-controller nodes for a MPC8347 SoC:
+        gpio1: gpio-controller@c00 {
+                #gpio-cells = <2>;
+                compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
+                reg = <0xc00 0x100>;
+                interrupts = <74 0x8>;
+                interrupt-parent = <&ipic>;
+                gpio-controller;
+        };
+        gpio2: gpio-controller@d00 {
+                #gpio-cells = <2>;
+                compatible = "fsl,mpc8347-gpio", "fsl,mpc8349-gpio";
+                reg = <0xd00 0x100>;
+                interrupts = <75 0x8>;
+                interrupt-parent = <&ipic>;
+                gpio-controller;
+        };
+See booting-without-of.txt for details of how to specify GPIO
+information for devices.
diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt
index 74ae6f1cd2d6..81a917ef96e9 100644
--- a/Documentation/powerpc/dts-bindings/fsl/board.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/board.txt
@@ -2,13 +2,13 @@
 Required properties:
- - device_type : Should be "board-control"
+ - compatible : Should be "fsl,<board>-bcsr"
 - reg : Offset and length of the register set for the device
 Example:
        bcsr@f8000000 {
-                device_type = "board-control";
+                compatible = "fsl,mpc8360mds-bcsr";
                reg = <f8000000 8000>;
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
new file mode 100644
index 000000000000..1815dfede1bc
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/gpio.txt
@@ -0,0 +1,38 @@
+Every GPIO controller node must have #gpio-cells property defined,
+this information will be used to translate gpio-specifiers.
+On CPM1 devices, all ports are using slightly different register layouts.
+Ports A, C and D are 16bit ports and Ports B and E are 32bit ports.
+On CPM2 devices, all ports are 32bit ports and use a common register layout.
+Required properties:
+- compatible : "fsl,cpm1-pario-bank-a", "fsl,cpm1-pario-bank-b",
+  "fsl,cpm1-pario-bank-c", "fsl,cpm1-pario-bank-d",
+  "fsl,cpm1-pario-bank-e", "fsl,cpm2-pario-bank"
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional paramters (currently unused).
+- gpio-controller : Marks the port as GPIO controller.
+Example of three SOC GPIO banks defined as gpio-controller nodes:
+        CPM1_PIO_A: gpio-controller@950 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-a";
+                reg = <0x950 0x10>;
+                gpio-controller;
+        };
+        CPM1_PIO_B: gpio-controller@ab8 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-b";
+                reg = <0xab8 0x10>;
+                gpio-controller;
+        };
+        CPM1_PIO_E: gpio-controller@ac8 {
+                #gpio-cells = <2>;
+                compatible = "fsl,cpm1-pario-bank-e";
+                reg = <0xac8 0x18>;
+                gpio-controller;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt
index c8f44d6bcbcf..9ccd5f30405b 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/usb.txt
@@ -1,22 +1,37 @@
-* USB (Universal Serial Bus Controller)
+Freescale QUICC Engine USB Controller
 Required properties:
- compatible : could be "qe_udc" or "fhci-hcd".
+- compatible : should be "fsl,<chip>-qe-usb", "fsl,mpc8323-qe-usb".
- mode : the could be "host" or "slave".
+- reg : the first two cells should contain usb registers location and
- reg : Offset and length of the register set for the device
+  length, the next two two cells should contain PRAM location and
- interrupts : <a b> where a is the interrupt number and b is a
+  length.
-  field that represents an encoding of the sense and level
+- interrupts : should contain USB interrupt.
-  information for the interrupt.  This should be encoded based on
+- interrupt-parent : interrupt source phandle.
-  the information in section 2) depending on the type of interrupt
+- fsl,fullspeed-clock : specifies the full speed USB clock source:
-  controller you have.
+  "none": clock source is disabled
- interrupt-parent : the phandle for the interrupt controller that
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
-  services interrupts for this device.
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- fsl,lowspeed-clock : specifies the low speed USB clock source:
+  "none": clock source is disabled
+  "brg1" through "brg16": clock source is BRG1-BRG16, respectively
+  "clk1" through "clk24": clock source is CLK1-CLK24, respectively
+- hub-power-budget : USB power budget for the root hub, in mA.
+- gpios : should specify GPIOs in this order: USBOE, USBTP, USBTN, USBRP,
+  USBRN, SPEED (optional), and POWER (optional).
-Example(slave):
+Example:
-        usb@6c0 {
-                compatible = "qe_udc";
+usb@6c0 {
-                reg = <6c0 40>;
+        compatible = "fsl,mpc8360-qe-usb", "fsl,mpc8323-qe-usb";
-                interrupts = <8b 0>;
+        reg = <0x6c0 0x40 0x8b00 0x100>;
-                interrupt-parent = <700>;
+        interrupts = <11>;
-                mode = "slave";
+        interrupt-parent = <&qeic>;
-        };
+        fsl,fullspeed-clock = "clk21";
+        gpios = <&qe_pio_b  2 0 /* USBOE */
+                 &qe_pio_b  3 0 /* USBTP */
+                 &qe_pio_b  8 0 /* USBTN */
+                 &qe_pio_b  9 0 /* USBRP */
+                 &qe_pio_b 11 0 /* USBRN */
+                 &qe_pio_e 20 0 /* SPEED */
+                 &qe_pio_e 21 0 /* POWER */>;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt
index b35f3482e3e4..2ea76d9d137c 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/serial.txt
@@ -7,6 +7,15 @@ Currently defined compatibles:
 - fsl,cpm2-scc-uart
 - fsl,qe-uart
+Modem control lines connected to GPIO controllers are listed in the gpios
+property as described in booting-without-of.txt, section IX.1 in the following
+order:
+CTS, RTS, DCD, DSR, DTR, and RI.
+The gpios property is optional and can be left out when control lines are
+not used.
 Example:
        serial@11a00 {
@@ -18,4 +27,6 @@ Example:
                interrupt-parent = <&PIC>;
                fsl,cpm-brg = <1>;
                fsl,cpm-command = <00800000>;
+                gpios = <&gpio_c 15 0
+                         &gpio_d 29 0>;
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
index 86826df00e64..cc453110fc46 100644
--- a/Documentation/powerpc/dts-bindings/fsl/dma.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -20,7 +20,7 @@ Required properties:
        - compatible        : compatible list, contains 2 entries, first is
                         "fsl,CHIP-dma-channel", where CHIP is the processor
                         (mpc8349, mpc8350, etc.) and the second is
-                         "fsl,elo-dma-channel"
+                         "fsl,elo-dma-channel". However, see note below.
        - reg               : <registers mapping for channel>
        - cell-index        : dma channel index starts at 0.
@@ -82,7 +82,7 @@ Required properties:
        - compatible        : compatible list, contains 2 entries, first is
                         "fsl,CHIP-dma-channel", where CHIP is the processor
                         (mpc8540, mpc8560, etc.) and the second is
-                         "fsl,eloplus-dma-channel"
+                         "fsl,eloplus-dma-channel". However, see note below.
        - cell-index        : dma channel index starts at 0.
        - reg               : <registers mapping for channel>
        - interrupts        : <interrupt mapping for DMA channel IRQ>
@@ -125,3 +125,12 @@ Example:
                        interrupts = <17 2>;
                };
        };
+Note on DMA channel compatible properties: The compatible property must say
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel" to be used by the Elo DMA
+driver (fsldma).  Any DMA channel used by fsldma cannot be used by another
+DMA driver, such as the SSI sound drivers for the MPC8610.  Therefore, any DMA
+channel that should be used for another driver should not use
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel".  For the SSI drivers, for
+example, the compatible property should be "fsl,ssi-dma-channel".  See ssi.txt
+for more information.
diff --git a/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt b/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt
new file mode 100644
index 000000000000..0f766333b6eb
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mcu-mpc8349emitx.txt
@@ -0,0 +1,17 @@
+Freescale MPC8349E-mITX-compatible Power Management Micro Controller Unit (MCU)
+Required properties:
+- compatible : "fsl,<mcu-chip>-<board>", "fsl,mcu-mpc8349emitx".
+- reg : should specify I2C address (0x0a).
+- #gpio-cells : should be 2.
+- gpio-controller : should be present.
+Example:
+mcu@0a {
+        #gpio-cells = <2>;
+        compatible = "fsl,mc9s08qg8-mpc8349emitx",
+                     "fsl,mcu-mpc8349emitx";
+        reg = <0x0a>;
+        gpio-controller;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/pmc.txt b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
new file mode 100644
index 000000000000..02f6f43ee1b7
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/pmc.txt
@@ -0,0 +1,63 @@
+* Power Management Controller
+Properties:
+- compatible: "fsl,<chip>-pmc".
+  "fsl,mpc8349-pmc" should be listed for any chip whose PMC is
+  compatible.  "fsl,mpc8313-pmc" should also be listed for any chip
+  whose PMC is compatible, and implies deep-sleep capability.
+  "fsl,mpc8548-pmc" should be listed for any chip whose PMC is
+  compatible.  "fsl,mpc8536-pmc" should also be listed for any chip
+  whose PMC is compatible, and implies deep-sleep capability.
+  "fsl,mpc8641d-pmc" should be listed for any chip whose PMC is
+  compatible; all statements below that apply to "fsl,mpc8548-pmc" also
+  apply to "fsl,mpc8641d-pmc".
+  Compatibility does not include bit assigments in SCCR/PMCDR/DEVDISR; these
+  bit assigments are indicated via the sleep specifier in each device's
+  sleep property.
+- reg: For devices compatible with "fsl,mpc8349-pmc", the first resource
+  is the PMC block, and the second resource is the Clock Configuration
+  block.
+  For devices compatible with "fsl,mpc8548-pmc", the first resource
+  is a 32-byte block beginning with DEVDISR.
+- interrupts: For "fsl,mpc8349-pmc"-compatible devices, the first
+  resource is the PMC block interrupt.
+- fsl,mpc8313-wakeup-timer: For "fsl,mpc8313-pmc"-compatible devices,
+  this is a phandle to an "fsl,gtm" node on which timer 4 can be used as
+  a wakeup source from deep sleep.
+Sleep specifiers:
+  fsl,mpc8349-pmc: Sleep specifiers consist of one cell.  For each bit
+  that is set in the cell, the corresponding bit in SCCR will be saved
+  and cleared on suspend, and restored on resume.  This sleep controller
+  supports disabling and resuming devices at any time.
+  fsl,mpc8536-pmc: Sleep specifiers consist of three cells, the third of
+  which will be ORed into PMCDR upon suspend, and cleared from PMCDR
+  upon resume.  The first two cells are as described for fsl,mpc8578-pmc.
+  This sleep controller only supports disabling devices during system
+  sleep, or permanently.
+  fsl,mpc8548-pmc: Sleep specifiers consist of one or two cells, the
+  first of which will be ORed into DEVDISR (and the second into
+  DEVDISR2, if present -- this cell should be zero or absent if the
+  hardware does not have DEVDISR2) upon a request for permanent device
+  disabling.  This sleep controller does not support configuring devices
+  to disable during system sleep (unless supported by another compatible
+  match), or dynamically.
+Example:
+        power@b00 {
+                compatible = "fsl,mpc8313-pmc", "fsl,mpc8349-pmc";
+                reg = <0xb00 0x100 0xa00 0x100>;
+                interrupts = <80 8>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/ssi.txt b/Documentation/powerpc/dts-bindings/fsl/ssi.txt
index d100555d488a..a2d963998a65 100644
--- a/Documentation/powerpc/dts-bindings/fsl/ssi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/ssi.txt
@@ -24,6 +24,12 @@ Required properties:
                    "rj-master" - r.j., SSI is clock master
                    "ac97-slave" - AC97 mode, SSI is clock slave
                    "ac97-master" - AC97 mode, SSI is clock master
+- fsl,playback-dma: phandle to a node for the DMA channel to use for
+                    playback of audio.  This is typically dictated by SOC
+                    design.  See the notes below.
+- fsl,capture-dma:  phandle to a node for the DMA channel to use for
+                    capture (recording) of audio.  This is typically dictated
+                    by SOC design.  See the notes below.
 Optional properties:
 - codec-handle    : phandle to a 'codec' node that defines an audio
@@ -36,3 +42,20 @@ Child 'codec' node required properties:
 Child 'codec' node optional properties:
 - clock-frequency  : The frequency of the input clock, which typically
                     comes from an on-board dedicated oscillator.
+Notes on fsl,playback-dma and fsl,capture-dma:
+On SOCs that have an SSI, specific DMA channels are hard-wired for playback
+and capture.  On the MPC8610, for example, SSI1 must use DMA channel 0 for
+playback and DMA channel 1 for capture.  SSI2 must use DMA channel 2 for
+playback and DMA channel 3 for capture.  The developer can choose which
+DMA controller to use, but the channels themselves are hard-wired.  The
+purpose of these two properties is to represent this hardware design.
+The device tree nodes for the DMA channels that are referenced by
+"fsl,playback-dma" and "fsl,capture-dma" must be marked as compatible with
+"fsl,ssi-dma-channel".  The SOC-specific compatible string (e.g.
+"fsl,mpc8610-dma-channel") can remain.  If these nodes are left as
+"fsl,elo-dma-channel" or "fsl,eloplus-dma-channel", then the generic Elo DMA
+drivers (fsldma) will attempt to use them, and it will conflict with the
+sound drivers.
diff --git a/Documentation/powerpc/dts-bindings/fsl/tsec.txt b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
index 583ef6b56c43..cf55fa4112d2 100644
--- a/Documentation/powerpc/dts-bindings/fsl/tsec.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/tsec.txt
@@ -24,46 +24,39 @@ Example:
 * Gianfar-compatible ethernet nodes
-Required properties:
+Properties:
  - device_type : Should be "network"
  - model : Model of the device.  Can be "TSEC", "eTSEC", or "FEC"
  - compatible : Should be "gianfar"
  - reg : Offset and length of the register set for the device
-  - mac-address : List of bytes representing the ethernet address of
+  - local-mac-address : List of bytes representing the ethernet address of
    this controller
-  - interrupts : <a b> where a is the interrupt number and b is a
+  - interrupts : For FEC devices, the first interrupt is the device's
-    field that represents an encoding of the sense and level
+    interrupt.  For TSEC and eTSEC devices, the first interrupt is
-    information for the interrupt.  This should be encoded based on
+    transmit, the second is receive, and the third is error.
-    the information in section 2) depending on the type of interrupt
-    controller you have.
-  - interrupt-parent : the phandle for the interrupt controller that
-    services interrupts for this device.
  - phy-handle : The phandle for the PHY connected to this ethernet
    controller.
  - fixed-link : <a b c d e> where a is emulated phy id - choose any,
    but unique to the all specified fixed-links, b is duplex - 0 half,
    1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no
    pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause.
-Recommended properties:
  - phy-connection-type : a string naming the controller/PHY interface type,
    i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii",
    "tbi", or "rtbi".  This property is only really needed if the connection
    is of type "rgmii-id", as all other connection types are detected by
    hardware.
+  - fsl,magic-packet : If present, indicates that the hardware supports
+    waking up via magic packet.
 Example:
        ethernet@24000 {
-                #size-cells = <0>;
                device_type = "network";
                model = "TSEC";
                compatible = "gianfar";
-                reg = <24000 1000>;
+                reg = <0x24000 0x1000>;
-                mac-address = [ 00 E0 0C 00 73 00 ];
+                local-mac-address = [ 00 E0 0C 00 73 00 ];
-                interrupts = <d 3 e 3 12 3>;
+                interrupts = <29 2 30 2 34 2>;
-                interrupt-parent = <40000>;
+                interrupt-parent = <&mpic>;
-                phy-handle = <2452000>
+                phy-handle = <&phy0>
        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
new file mode 100644
index 000000000000..84a04d5eb8e6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/upm-nand.txt
@@ -0,0 +1,28 @@
+Freescale Localbus UPM programmed to work with NAND flash
+Required properties:
+- compatible : "fsl,upm-nand".
+- reg : should specify localbus chip select and size used for the chip.
+- fsl,upm-addr-offset : UPM pattern offset for the address latch.
+- fsl,upm-cmd-offset : UPM pattern offset for the command latch.
+- gpios : may specify optional GPIO connected to the Ready-Not-Busy pin.
+Example:
+upm@1,0 {
+        compatible = "fsl,upm-nand";
+        reg = <1 0 1>;
+        fsl,upm-addr-offset = <16>;
+        fsl,upm-cmd-offset = <8>;
+        gpios = <&qe_pio_e 18 0>;
+        flash {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "...";
+                partition@0 {
+                        ...
+                };
+        };
+};
diff --git a/Documentation/powerpc/dts-bindings/gpio/led.txt b/Documentation/powerpc/dts-bindings/gpio/led.txt
new file mode 100644
index 000000000000..ff51f4c0fa9d
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/gpio/led.txt
@@ -0,0 +1,15 @@
+LED connected to GPIO
+Required properties:
+- compatible : should be "gpio-led".
+- label : (optional) the label for this LED. If omitted, the label is
+  taken from the node name (excluding the unit address).
+- gpios : should specify LED GPIO.
+Example:
+led@0 {
+        compatible = "gpio-led";
+        label = "hdd";
+        gpios = <&mcu_pio 0 1>;
+};
diff --git a/Documentation/powerpc/eeh-pci-error-recovery.txt b/Documentation/powerpc/eeh-pci-error-recovery.txt
index df7afe43d462..9d4e33df624c 100644
--- a/Documentation/powerpc/eeh-pci-error-recovery.txt
+++ b/Documentation/powerpc/eeh-pci-error-recovery.txt
@@ -133,7 +133,7 @@ error.  Given an arbitrary address, the routine
 pci_get_device_by_addr() will find the pci device associated
 with that address (if any).
-The default include/asm-powerpc/io.h macros readb(), inb(), insb(),
+The default arch/powerpc/include/asm/io.h macros readb(), inb(), insb(),
 etc. include a check to see if the i/o read returned all-0xff's.
 If so, these make a call to eeh_dn_check_failure(), which in turn
 asks the firmware if the all-ff's value is the sign of a true EEH
diff --git a/Documentation/powerpc/ppc_htab.txt b/Documentation/powerpc/ppc_htab.txt
deleted file mode 100644
index 8b8c7df29fa9..000000000000
--- a/Documentation/powerpc/ppc_htab.txt
+++ /dev/null
@@ -1,118 +0,0 @@
-                 Information about /proc/ppc_htab
-=====================================================================
-This document and the related code was written by me (Cort Dougan), please
-email me (cort@fsmlabs.com) if you have questions, comments or corrections.
-Last Change: 2.16.98
-This entry in the proc directory is readable by all users but only
-writable by root.
-The ppc_htab interface is a user level way of accessing the
-performance monitoring registers as well as providing information
-about the PTE hash table.
-1. Reading
-  Reading this file will give you information about the memory management
-  hash table that serves as an extended tlb for page translation on the
-  powerpc.  It will also give you information about performance measurement
-  specific to the cpu that you are using.
-  Explanation of the 604 Performance Monitoring Fields:
-    MMCR0 - the current value of the MMCR0 register
-    PMC1
-    PMC2 - the value of the performance counters and a
-           description of what events they are counting
-           which are based on MMCR0 bit settings.
-  Explanation of the PTE Hash Table fields:
-    Size - hash table size in Kb.
-    Buckets -  number of buckets in the table.
-    Address - the virtual kernel address of the hash table base.
-    Entries - the number of ptes that can be stored in the hash table.
-    User/Kernel - how many pte's are in use by the kernel or user at that time.
-    Overflows - How many of the entries are in their secondary hash location.
-    Percent full - ratio of free pte entries to in use entries.
-    Reloads - Count of how many hash table misses have occurred
-              that were fixed with a reload from the linux tables.
-              Should always be 0 on 603 based machines.
-    Non-error Misses - Count of how many hash table misses have occurred
-              that were completed with the creation of a pte in the linux
-              tables with a call to do_page_fault().
-    Error Misses - Number of misses due to errors such as bad address
-              and permission violations.  This includes kernel access of
-              bad user addresses that are fixed up by the trap handler.
-  Note that calculation of the data displayed from /proc/ppc_htab takes
-  a long time and spends a great deal of time in the kernel.  It would
-  be quite hard on performance to read this file constantly.  In time
-  there may be a counter in the kernel that allows successive reads from
-  this file only after a given amount of time has passed to reduce the
-  possibility of a user slowing the system by reading this file.
-2. Writing
-  Writing to the ppc_htab allows you to change the characteristics of
-  the powerpc PTE hash table and setup performance monitoring.
-  Resizing the PTE hash table is not enabled right now due to many
-  complications with moving the hash table, rehashing the entries
-  and many many SMP issues that would have to be dealt with.
-  Write options to ppc_htab:
-  
-   - To set the size of the hash table to 64Kb:
-      echo 'size 64' > /proc/ppc_htab
-     The size must be a multiple of 64 and must be greater than or equal to
-     64.
-   - To turn off performance monitoring:
-      echo 'off' > /proc/ppc_htab
-   - To reset the counters without changing what they're counting:
-      echo 'reset' > /proc/ppc_htab
-     Note that counting will continue after the reset if it is enabled.
-   - To count only events in user mode or only in kernel mode:
-      echo 'user' > /proc/ppc_htab
-       ...or...
-      echo 'kernel' > /proc/ppc_htab
-     Note that these two options are exclusive of one another and the
-     lack of either of these options counts user and kernel.
-     Using 'reset' and 'off' reset these flags.
-   - The 604 has 2 performance counters which can each count events from
-     a specific set of events.  These sets are disjoint so it is not
-     possible to count _any_ combination of 2 events.  One event can
-     be counted by PMC1 and one by PMC2.
-     To start counting a particular event use:
-      echo 'event' > /proc/ppc_htab
-     and choose from these events:
-     PMC1
-     ----
-      'ic miss' - instruction cache misses
-      'dtlb' - data tlb misses (not hash table misses)
-     PMC2
-     ----
-      'dc miss' - data cache misses
-      'itlb' - instruction tlb misses (not hash table misses)
-      'load miss time' - cycles to complete a load miss
-3. Bugs
-  The PMC1 and PMC2 counters can overflow and give no indication of that
-  in /proc/ppc_htab.
diff --git a/Documentation/powerpc/qe_firmware.txt b/Documentation/powerpc/qe_firmware.txt
index 896266432d33..06da4d4b44f9 100644
--- a/Documentation/powerpc/qe_firmware.txt
+++ b/Documentation/powerpc/qe_firmware.txt
@@ -217,7 +217,7 @@ Although it is not recommended, you can specify '0' in the soc.model
 field to skip matching SOCs altogether.
 The 'model' field is a 16-bit number that matches the actual SOC. The
-'major' and 'minor' fields are the major and minor revision numbrs,
+'major' and 'minor' fields are the major and minor revision numbers,
 respectively, of the SOC.
 For example, to match the 8323, revision 1.0:
diff --git a/Documentation/powerpc/smp.txt b/Documentation/powerpc/smp.txt
deleted file mode 100644
index 5b581b849ff7..000000000000
--- a/Documentation/powerpc/smp.txt
+++ /dev/null
@@ -1,34 +0,0 @@
-                 Information about Linux/PPC SMP mode
-=====================================================================
-This document and the related code was written by me
-(Cort Dougan, cort@fsmlabs.com) please email me if you have questions,
-comments or corrections.
-Last Change: 3.31.99
-If you want to help by writing code or testing different hardware please
-email me!
-1. State of Supported Hardware
-  PowerSurge Architecture - tested on UMAX s900, Apple 9600
-    The second processor on this machine boots up just fine and
-    enters its idle loop.  Hopefully a completely working SMP kernel
-    on this machine will be done shortly.
-    The code makes the assumption of only two processors.  The changes
-    necessary to work with any number would not be overly difficult but
-    I don't have any machines with >2 processors so it's not high on my
-    list of priorities.  If anyone else would like do to the work email
-    me and I can point out the places that need changed.  If you have >2
-    processors and don't want to add support yourself let me know and I
-    can take a look into it.
-  BeBox
-    BeBox support hasn't been added to the 2.1.X kernels from 2.0.X
-    but work is being done and SMP support for BeBox is in the works.
-  CHRP
-    CHRP SMP works and is fairly solid.  It's been tested on the IBM F50
-    with 4 processors for quite some time now.
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index a83ff23cd68c..b65f0799df48 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -1,89 +1,569 @@
 rfkill - RF switch subsystem support
 ====================================
-1 Implementation details
+1 Introduction
-2 Driver support
+2 Implementation details
-3 Userspace support
+3 Kernel driver guidelines
+3.1 wireless device drivers
+3.2 platform/switch drivers
+3.3 input device drivers
+4 Kernel API
+5 Userspace support
-===============================================================================
-1: Implementation details
-The rfkill switch subsystem offers support for keys often found on laptops
+1. Introduction:
-to enable wireless devices like WiFi and Bluetooth.
+The rfkill switch subsystem exists to add a generic interface to circuitry that
+can enable or disable the signal output of a wireless *transmitter* of any
+type.  By far, the most common use is to disable radio-frequency transmitters.
-This is done by providing the user 3 possibilities:
+Note that disabling the signal output means that the the transmitter is to be
- 1 - The rfkill system handles all events; userspace is not aware of events.
+made to not emit any energy when "blocked".  rfkill is not about blocking data
- 2 - The rfkill system handles all events; userspace is informed about the events.
+transmissions, it is about blocking energy emission.
- 3 - The rfkill system does not handle events; userspace handles all events.
-The buttons to enable and disable the wireless radios are important in
+The rfkill subsystem offers support for keys and switches often found on
+laptops to enable wireless devices like WiFi and Bluetooth, so that these keys
+and switches actually perform an action in all wireless devices of a given type
+attached to the system.
+The buttons to enable and disable the wireless transmitters are important in
 situations where the user is for example using his laptop on a location where
-wireless radios _must_ be disabled (e.g. airplanes).
+radio-frequency transmitters _must_ be disabled (e.g. airplanes).
-Because of this requirement, userspace support for the keys should not be
-made mandatory. Because userspace might want to perform some additional smarter
+Because of this requirement, userspace support for the keys should not be made
-tasks when the key is pressed, rfkill still provides userspace the possibility
+mandatory.  Because userspace might want to perform some additional smarter
-to take over the task to handle the key events.
+tasks when the key is pressed, rfkill provides userspace the possibility to
+take over the task to handle the key events.
+===============================================================================
+2: Implementation details
+The rfkill subsystem is composed of various components: the rfkill class, the
+rfkill-input module (an input layer handler), and some specific input layer
+events.
+The rfkill class provides kernel drivers with an interface that allows them to
+know when they should enable or disable a wireless network device transmitter.
+This is enabled by the CONFIG_RFKILL Kconfig option.
+The rfkill class support makes sure userspace will be notified of all state
+changes on rfkill devices through uevents.  It provides a notification chain
+for interested parties in the kernel to also get notified of rfkill state
+changes in other drivers.  It creates several sysfs entries which can be used
+by userspace.  See section "Userspace support".
+The rfkill-input module provides the kernel with the ability to implement a
+basic response when the user presses a key or button (or toggles a switch)
+related to rfkill functionality.  It is an in-kernel implementation of default
+policy of reacting to rfkill-related input events and neither mandatory nor
+required for wireless drivers to operate.  It is enabled by the
+CONFIG_RFKILL_INPUT Kconfig option.
+rfkill-input is a rfkill-related events input layer handler.  This handler will
+listen to all rfkill key events and will change the rfkill state of the
+wireless devices accordingly.  With this option enabled userspace could either
+do nothing or simply perform monitoring tasks.
+The rfkill-input module also provides EPO (emergency power-off) functionality
+for all wireless transmitters.  This function cannot be overridden, and it is
+always active.  rfkill EPO is related to *_RFKILL_ALL input layer events.
+Important terms for the rfkill subsystem:
+In order to avoid confusion, we avoid the term "switch" in rfkill when it is
+referring to an electronic control circuit that enables or disables a
+transmitter.  We reserve it for the physical device a human manipulates
+(which is an input device, by the way):
+rfkill switch:
+        A physical device a human manipulates.  Its state can be perceived by
+        the kernel either directly (through a GPIO pin, ACPI GPE) or by its
+        effect on a rfkill line of a wireless device.
+rfkill controller:
+        A hardware circuit that controls the state of a rfkill line, which a
+        kernel driver can interact with *to modify* that state (i.e. it has
+        either write-only or read/write access).
+rfkill line:
+        An input channel (hardware or software) of a wireless device, which
+        causes a wireless transmitter to stop emitting energy (BLOCK) when it
+        is active.  Point of view is extremely important here: rfkill lines are
+        always seen from the PoV of a wireless device (and its driver).
+soft rfkill line/software rfkill line:
+        A rfkill line the wireless device driver can directly change the state
+        of.  Related to rfkill_state RFKILL_STATE_SOFT_BLOCKED.
+hard rfkill line/hardware rfkill line:
+        A rfkill line that works fully in hardware or firmware, and that cannot
+        be overridden by the kernel driver.  The hardware device or the
+        firmware just exports its status to the driver, but it is read-only.
+        Related to rfkill_state RFKILL_STATE_HARD_BLOCKED.
+The enum rfkill_state describes the rfkill state of a transmitter:
+When a rfkill line or rfkill controller is in the RFKILL_STATE_UNBLOCKED state,
+the wireless transmitter (radio TX circuit for example) is *enabled*.  When the
+it is in the RFKILL_STATE_SOFT_BLOCKED or RFKILL_STATE_HARD_BLOCKED, the
+wireless transmitter is to be *blocked* from operating.
+RFKILL_STATE_SOFT_BLOCKED indicates that a call to toggle_radio() can change
+that state.  RFKILL_STATE_HARD_BLOCKED indicates that a call to toggle_radio()
+will not be able to change the state and will return with a suitable error if
+attempts are made to set the state to RFKILL_STATE_UNBLOCKED.
+RFKILL_STATE_HARD_BLOCKED is used by drivers to signal that the device is
+locked in the BLOCKED state by a hardwire rfkill line (typically an input pin
+that, when active, forces the transmitter to be disabled) which the driver
+CANNOT override.
+Full rfkill functionality requires two different subsystems to cooperate: the
+input layer and the rfkill class.  The input layer issues *commands* to the
+entire system requesting that devices registered to the rfkill class change
+state.  The way this interaction happens is not complex, but it is not obvious
+either:
+Kernel Input layer:
+        * Generates KEY_WWAN, KEY_WLAN, KEY_BLUETOOTH, SW_RFKILL_ALL, and
+          other such events when the user presses certain keys, buttons, or
+          toggles certain physical switches.
-The system inside the kernel has been split into 2 separate sections:
+        THE INPUT LAYER IS NEVER USED TO PROPAGATE STATUS, NOTIFICATIONS OR THE
-        1 - RFKILL
+        KIND OF STUFF AN ON-SCREEN-DISPLAY APPLICATION WOULD REPORT.  It is
-        2 - RFKILL_INPUT
+        used to issue *commands* for the system to change behaviour, and these
+        commands may or may not be carried out by some kernel driver or
+        userspace application.  It follows that doing user feedback based only
+        on input events is broken, as there is no guarantee that an input event
+        will be acted upon.
-The first option enables rfkill support and will make sure userspace will
+        Most wireless communication device drivers implementing rfkill
-be notified of any events through the input device. It also creates several
+        functionality MUST NOT generate these events, and have no reason to
-sysfs entries which can be used by userspace. See section "Userspace support".
+        register themselves with the input layer.  Doing otherwise is a common
+        misconception.  There is an API to propagate rfkill status change
+        information, and it is NOT the input layer.
-The second option provides an rfkill input handler. This handler will
+rfkill class:
-listen to all rfkill key events and will toggle the radio accordingly.
-With this option enabled userspace could either do nothing or simply
-perform monitoring tasks.
+        * Calls a hook in a driver to effectively change the wireless
+          transmitter state;
+        * Keeps track of the wireless transmitter state (with help from
+          the driver);
+        * Generates userspace notifications (uevents) and a call to a
+          notification chain (kernel) when there is a wireless transmitter
+          state change;
+        * Connects a wireless communications driver with the common rfkill
+          control system, which, for example, allows actions such as
+          "switch all bluetooth devices offline" to be carried out by
+          userspace or by rfkill-input.
+        THE RFKILL CLASS NEVER ISSUES INPUT EVENTS.  THE RFKILL CLASS DOES
+        NOT LISTEN TO INPUT EVENTS.  NO DRIVER USING THE RFKILL CLASS SHALL
+        EVER LISTEN TO, OR ACT ON RFKILL INPUT EVENTS.  Doing otherwise is
+        a layering violation.
+        Most wireless data communication drivers in the kernel have just to
+        implement the rfkill class API to work properly.  Interfacing to the
+        input layer is not often required (and is very often a *bug*) on
+        wireless drivers.
+        Platform drivers often have to attach to the input layer to *issue*
+        (but never to listen to) rfkill events for rfkill switches, and also to
+        the rfkill class to export a control interface for the platform rfkill
+        controllers to the rfkill subsystem.  This does NOT mean the rfkill
+        switch is attached to a rfkill class (doing so is almost always wrong).
+        It just means the same kernel module is the driver for different
+        devices (rfkill switches and rfkill controllers).
+Userspace input handlers (uevents) or kernel input handlers (rfkill-input):
+        * Implements the policy of what should happen when one of the input
+          layer events related to rfkill operation is received.
+        * Uses the sysfs interface (userspace) or private rfkill API calls
+          to tell the devices registered with the rfkill class to change
+          their state (i.e. translates the input layer event into real
+          action).
+        * rfkill-input implements EPO by handling EV_SW SW_RFKILL_ALL 0
+          (power off all transmitters) in a special way: it ignores any
+          overrides and local state cache and forces all transmitters to the
+          RFKILL_STATE_SOFT_BLOCKED state (including those which are already
+          supposed to be BLOCKED).  Note that the opposite event (power on all
+          transmitters) is handled normally.
+Userspace uevent handler or kernel platform-specific drivers hooked to the
+rfkill notifier chain:
+        * Taps into the rfkill notifier chain or to KOBJ_CHANGE uevents,
+          in order to know when a device that is registered with the rfkill
+          class changes state;
+        * Issues feedback notifications to the user;
+        * In the rare platforms where this is required, synthesizes an input
+          event to command all *OTHER* rfkill devices to also change their
+          statues when a specific rfkill device changes state.
+===============================================================================
+3: Kernel driver guidelines
+Remember: point-of-view is everything for a driver that connects to the rfkill
+subsystem.  All the details below must be measured/perceived from the point of
+view of the specific driver being modified.
+The first thing one needs to know is whether his driver should be talking to
+the rfkill class or to the input layer.  In rare cases (platform drivers), it
+could happen that you need to do both, as platform drivers often handle a
+variety of devices in the same driver.
+Do not mistake input devices for rfkill controllers.  The only type of "rfkill
+switch" device that is to be registered with the rfkill class are those
+directly controlling the circuits that cause a wireless transmitter to stop
+working (or the software equivalent of them), i.e. what we call a rfkill
+controller.  Every other kind of "rfkill switch" is just an input device and
+MUST NOT be registered with the rfkill class.
+A driver should register a device with the rfkill class when ALL of the
+following conditions are met (they define a rfkill controller):
+1. The device is/controls a data communications wireless transmitter;
+2. The kernel can interact with the hardware/firmware to CHANGE the wireless
+   transmitter state (block/unblock TX operation);
+3. The transmitter can be made to not emit any energy when "blocked":
+   rfkill is not about blocking data transmissions, it is about blocking
+   energy emission;
+A driver should register a device with the input subsystem to issue
+rfkill-related events (KEY_WLAN, KEY_BLUETOOTH, KEY_WWAN, KEY_WIMAX,
+SW_RFKILL_ALL, etc) when ALL of the folowing conditions are met:
+1. It is directly related to some physical device the user interacts with, to
+   command the O.S./firmware/hardware to enable/disable a data communications
+   wireless transmitter.
+   Examples of the physical device are: buttons, keys and switches the user
+   will press/touch/slide/switch to enable or disable the wireless
+   communication device.
+2. It is NOT slaved to another device, i.e. there is no other device that
+   issues rfkill-related input events in preference to this one.
+   Please refer to the corner cases and examples section for more details.
+When in doubt, do not issue input events.  For drivers that should generate
+input events in some platforms, but not in others (e.g. b43), the best solution
+is to NEVER generate input events in the first place.  That work should be
+deferred to a platform-specific kernel module (which will know when to generate
+events through the rfkill notifier chain) or to userspace.  This avoids the
+usual maintenance problems with DMI whitelisting.
+Corner cases and examples:
 ====================================
-2: Driver support
-To build a driver with rfkill subsystem support, the driver should
+1. If the device is an input device that, because of hardware or firmware,
-depend on the Kconfig symbol RFKILL; it should _not_ depend on
+causes wireless transmitters to be blocked regardless of the kernel's will, it
-RKFILL_INPUT.
+is still just an input device, and NOT to be registered with the rfkill class.
-Unless key events trigger an interrupt to which the driver listens, polling
+2. If the wireless transmitter switch control is read-only, it is an input
-will be required to determine the key state changes. For this the input
+device and not to be registered with the rfkill class (and maybe not to be made
-layer providers the input-polldev handler.
+an input layer event source either, see below).
-A driver should implement a few steps to correctly make use of the
+3. If there is some other device driver *closer* to the actual hardware the
-rfkill subsystem. First for non-polling drivers:
+user interacted with (the button/switch/key) to issue an input event, THAT is
+the device driver that should be issuing input events.
-        - rfkill_allocate()
+E.g:
-        - input_allocate_device()
+  [RFKILL slider switch] -- [GPIO hardware] -- [WLAN card rf-kill input]
-        - rfkill_register()
+                           (platform driver)    (wireless card driver)
-        - input_register_device()
+The user is closer to the RFKILL slide switch plaform driver, so the driver
+which must issue input events is the platform driver looking at the GPIO
+hardware, and NEVER the wireless card driver (which is just a slave).  It is
+very likely that there are other leaves than just the WLAN card rf-kill input
+(e.g. a bluetooth card, etc)...
+On the other hand, some embedded devices do this:
+  [RFKILL slider switch] -- [WLAN card rf-kill input]
+                             (wireless card driver)
-For polling drivers:
+In this situation, the wireless card driver *could* register itself as an input
+device and issue rf-kill related input events... but in order to AVOID the need
+for DMI whitelisting, the wireless card driver does NOT do it.  Userspace (HAL)
+or a platform driver (that exists only on these embedded devices) will do the
+dirty job of issuing the input events.
+COMMON MISTAKES in kernel drivers, related to rfkill:
+====================================
+1. NEVER confuse input device keys and buttons with input device switches.
+  1a. Switches are always set or reset.  They report the current state
+      (on position or off position).
+  1b. Keys and buttons are either in the pressed or not-pressed state, and
+      that's it.  A "button" that latches down when you press it, and
+      unlatches when you press it again is in fact a switch as far as input
+      devices go.
+Add the SW_* events you need for switches, do NOT try to emulate a button using
+KEY_* events just because there is no such SW_* event yet.  Do NOT try to use,
+for example, KEY_BLUETOOTH when you should be using SW_BLUETOOTH instead.
+2. Input device switches (sources of EV_SW events) DO store their current state
+(so you *must* initialize it by issuing a gratuitous input layer event on
+driver start-up and also when resuming from sleep), and that state CAN be
+queried from userspace through IOCTLs.  There is no sysfs interface for this,
+but that doesn't mean you should break things trying to hook it to the rfkill
+class to get a sysfs interface :-)
+3. Do not issue *_RFKILL_ALL events by default, unless you are sure it is the
+correct event for your switch/button.  These events are emergency power-off
+events when they are trying to turn the transmitters off.  An example of an
+input device which SHOULD generate *_RFKILL_ALL events is the wireless-kill
+switch in a laptop which is NOT a hotkey, but a real switch that kills radios
+in hardware, even if the O.S. has gone to lunch.  An example of an input device
+which SHOULD NOT generate *_RFKILL_ALL events by default, is any sort of hot
+key that does nothing by itself, as well as any hot key that is type-specific
+(e.g. the one for WLAN).
+3.1 Guidelines for wireless device drivers
+------------------------------------------
+(in this text, rfkill->foo means the foo field of struct rfkill).
+1. Each independent transmitter in a wireless device (usually there is only one
+transmitter per device) should have a SINGLE rfkill class attached to it.
+2. If the device does not have any sort of hardware assistance to allow the
+driver to rfkill the device, the driver should emulate it by taking all actions
+required to silence the transmitter.
+3. If it is impossible to silence the transmitter (i.e. it still emits energy,
+even if it is just in brief pulses, when there is no data to transmit and there
+is no hardware support to turn it off) do NOT lie to the users.  Do not attach
+it to a rfkill class.  The rfkill subsystem does not deal with data
+transmission, it deals with energy emission.  If the transmitter is emitting
+energy, it is not blocked in rfkill terms.
+4. It doesn't matter if the device has multiple rfkill input lines affecting
+the same transmitter, their combined state is to be exported as a single state
+per transmitter (see rule 1).
+This rule exists because users of the rfkill subsystem expect to get (and set,
+when possible) the overall transmitter rfkill state, not of a particular rfkill
+line.
+5. The wireless device driver MUST NOT leave the transmitter enabled during
+suspend and hibernation unless:
+        5.1. The transmitter has to be enabled for some sort of functionality
+        like wake-on-wireless-packet or autonomous packed forwarding in a mesh
+        network, and that functionality is enabled for this suspend/hibernation
+        cycle.
+AND
+        5.2. The device was not on a user-requested BLOCKED state before
+        the suspend (i.e. the driver must NOT unblock a device, not even
+        to support wake-on-wireless-packet or remain in the mesh).
+In other words, there is absolutely no allowed scenario where a driver can
+automatically take action to unblock a rfkill controller (obviously, this deals
+with scenarios where soft-blocking or both soft and hard blocking is happening.
+Scenarios where hardware rfkill lines are the only ones blocking the
+transmitter are outside of this rule, since the wireless device driver does not
+control its input hardware rfkill lines in the first place).
+6. During resume, rfkill will try to restore its previous state.
+7. After a rfkill class is suspended, it will *not* call rfkill->toggle_radio
+until it is resumed.
+Example of a WLAN wireless driver connected to the rfkill subsystem:
+--------------------------------------------------------------------
+A certain WLAN card has one input pin that causes it to block the transmitter
+and makes the status of that input pin available (only for reading!) to the
+kernel driver.  This is a hard rfkill input line (it cannot be overridden by
+the kernel driver).
+The card also has one PCI register that, if manipulated by the driver, causes
+it to block the transmitter.  This is a soft rfkill input line.
+It has also a thermal protection circuitry that shuts down its transmitter if
+the card overheats, and makes the status of that protection available (only for
+reading!) to the kernel driver.  This is also a hard rfkill input line.
+If either one of these rfkill lines are active, the transmitter is blocked by
+the hardware and forced offline.
+The driver should allocate and attach to its struct device *ONE* instance of
+the rfkill class (there is only one transmitter).
+It can implement the get_state() hook, and return RFKILL_STATE_HARD_BLOCKED if
+either one of its two hard rfkill input lines are active.  If the two hard
+rfkill lines are inactive, it must return RFKILL_STATE_SOFT_BLOCKED if its soft
+rfkill input line is active.  Only if none of the rfkill input lines are
+active, will it return RFKILL_STATE_UNBLOCKED.
+Since the device has a hardware rfkill line, it IS subject to state changes
+external to rfkill.  Therefore, the driver must make sure that it calls
+rfkill_force_state() to keep the status always up-to-date, and it must do a
+rfkill_force_state() on resume from sleep.
+Every time the driver gets a notification from the card that one of its rfkill
+lines changed state (polling might be needed on badly designed cards that don't
+generate interrupts for such events), it recomputes the rfkill state as per
+above, and calls rfkill_force_state() to update it.
+The driver should implement the toggle_radio() hook, that:
+1. Returns an error if one of the hardware rfkill lines are active, and the
+caller asked for RFKILL_STATE_UNBLOCKED.
+2. Activates the soft rfkill line if the caller asked for state
+RFKILL_STATE_SOFT_BLOCKED.  It should do this even if one of the hard rfkill
+lines are active, effectively double-blocking the transmitter.
+3. Deactivates the soft rfkill line if none of the hardware rfkill lines are
+active and the caller asked for RFKILL_STATE_UNBLOCKED.
+===============================================================================
+4: Kernel API
+To build a driver with rfkill subsystem support, the driver should depend on
+(or select) the Kconfig symbol RFKILL; it should _not_ depend on RKFILL_INPUT.
+The hardware the driver talks to may be write-only (where the current state
+of the hardware is unknown), or read-write (where the hardware can be queried
+about its current state).
+The rfkill class will call the get_state hook of a device every time it needs
+to know the *real* current state of the hardware.  This can happen often, but
+it does not do any polling, so it is not enough on hardware that is subject
+to state changes outside of the rfkill subsystem.
+Therefore, calling rfkill_force_state() when a state change happens is
+mandatory when the device has a hardware rfkill line, or when something else
+like the firmware could cause its state to be changed without going through the
+rfkill class.
+Some hardware provides events when its status changes.  In these cases, it is
+best for the driver to not provide a get_state hook, and instead register the
+rfkill class *already* with the correct status, and keep it updated using
+rfkill_force_state() when it gets an event from the hardware.
+rfkill_force_state() must be used on the device resume handlers to update the
+rfkill status, should there be any chance of the device status changing during
+the sleep.
+There is no provision for a statically-allocated rfkill struct.  You must
+use rfkill_allocate() to allocate one.
+You should:
        - rfkill_allocate()
-        - input_allocate_polled_device()
+        - modify rfkill fields (flags, name)
+        - modify state to the current hardware state (THIS IS THE ONLY TIME
+          YOU CAN ACCESS state DIRECTLY)
        - rfkill_register()
-        - input_register_polled_device()
-When a key event has been detected, the correct event should be
+The only way to set a device to the RFKILL_STATE_HARD_BLOCKED state is through
-sent over the input device which has been registered by the driver.
+a suitable return of get_state() or through rfkill_force_state().
-====================================
+When a device is in the RFKILL_STATE_HARD_BLOCKED state, the only way to switch
-3: Userspace support
+it to a different state is through a suitable return of get_state() or through
+rfkill_force_state().
-For each key an input device will be created which will send out the correct
+If toggle_radio() is called to set a device to state RFKILL_STATE_SOFT_BLOCKED
-key event when the rfkill key has been pressed.
+when that device is already at the RFKILL_STATE_HARD_BLOCKED state, it should
+not return an error.  Instead, it should try to double-block the transmitter,
+so that its state will change from RFKILL_STATE_HARD_BLOCKED to
+RFKILL_STATE_SOFT_BLOCKED should the hardware blocking cease.
+Please refer to the source for more documentation.
+===============================================================================
+5: Userspace support
+rfkill devices issue uevents (with an action of "change"), with the following
+environment variables set:
+RFKILL_NAME
+RFKILL_STATE
+RFKILL_TYPE
+The ABI for these variables is defined by the sysfs attributes.  It is best
+to take a quick look at the source to make sure of the possible values.
+It is expected that HAL will trap those, and bridge them to DBUS, etc.  These
+events CAN and SHOULD be used to give feedback to the user about the rfkill
+status of the system.
+Input devices may issue events that are related to rfkill.  These are the
+various KEY_* events and SW_* events supported by rfkill-input.c.
+******IMPORTANT******
+When rfkill-input is ACTIVE, userspace is NOT TO CHANGE THE STATE OF AN RFKILL
+SWITCH IN RESPONSE TO AN INPUT EVENT also handled by rfkill-input, unless it
+has set to true the user_claim attribute for that particular switch.  This rule
+is *absolute*; do NOT violate it.
+******IMPORTANT******
+Userspace must not assume it is the only source of control for rfkill switches.
+Their state CAN and WILL change due to firmware actions, direct user actions,
+and the rfkill-input EPO override for *_RFKILL_ALL.
+When rfkill-input is not active, userspace must initiate a rfkill status
+change by writing to the "state" attribute in order for anything to happen.
+Take particular care to implement EV_SW SW_RFKILL_ALL properly.  When that
+switch is set to OFF, *every* rfkill device *MUST* be immediately put into the
+RFKILL_STATE_SOFT_BLOCKED state, no questions asked.
 The following sysfs entries will be created:
        name: Name assigned by driver to this key (interface or driver name).
        type: Name of the key type ("wlan", "bluetooth", etc).
-        state: Current state of the key. 1: On, 0: Off.
+        state: Current state of the transmitter
+                0: RFKILL_STATE_SOFT_BLOCKED
+                        transmitter is forced off, but one can override it
+                        by a write to the state attribute;
+                1: RFKILL_STATE_UNBLOCKED
+                        transmiter is NOT forced off, and may operate if
+                        all other conditions for such operation are met
+                        (such as interface is up and configured, etc);
+                2: RFKILL_STATE_HARD_BLOCKED
+                        transmitter is forced off by something outside of
+                        the driver's control.  One cannot set a device to
+                        this state through writes to the state attribute;
        claim: 1: Userspace handles events, 0: Kernel handles events
 Both the "state" and "claim" entries are also writable. For the "state" entry
-this means that when 1 or 0 is written all radios, not yet in the requested
+this means that when 1 or 0 is written, the device rfkill state (if not yet in
-state, will be will be toggled accordingly.
+the requested state), will be will be toggled accordingly.
 For the "claim" entry writing 1 to it means that the kernel no longer handles
 key events even though RFKILL_INPUT input was enabled. When "claim" has been
 set to 0, userspace should make sure that it listens for the input events or
-check the sysfs "state" entry regularly to correctly perform the required
+check the sysfs "state" entry regularly to correctly perform the required tasks
-tasks when the rkfill key is pressed.
+when the rkfill key is pressed.
+A note about input devices and EV_SW events:
+In order to know the current state of an input device switch (like
+SW_RFKILL_ALL), you will need to use an IOCTL.  That information is not
+available through sysfs in a generic way at this time, and it is not available
+through the rfkill class AT ALL.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index bf0baa19ec24..339207d11d95 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -70,13 +70,19 @@ Command line parameters
  Note: While already known devices can be added to the list of devices to be
        ignored, there will be no effect on then. However, if such a device
-        disappears and then reappears, it will then be ignored.
+        disappears and then reappears, it will then be ignored. To make
+        known devices go away, you need the "purge" command (see below).
  For example,
        "echo add 0.0.a000-0.0.accc, 0.0.af00-0.0.afff > /proc/cio_ignore"
  will add 0.0.a000-0.0.accc and 0.0.af00-0.0.afff to the list of ignored
  devices.
+  You can remove already known but now ignored devices via
+        "echo purge > /proc/cio_ignore"
+  All devices ignored but still registered and not online (= not in use)
+  will be deregistered and thus removed from the system.
  The devices can be specified either by bus id (0.x.abcd) or, for 2.4 backward
  compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
  numbers given as 0xabcd will be interpreted as 0.0.abcd.
@@ -98,8 +104,7 @@ debugfs entries
    handling).
  - /sys/kernel/debug/s390dbf/cio_msg/sprintf
-    Various debug messages from the common I/O-layer, including messages
+    Various debug messages from the common I/O-layer.
-    printed when cio_msg=yes.
  - /sys/kernel/debug/s390dbf/cio_trace/hex_ascii
    Logs the calling of functions in the common I/O-layer and, if applicable, 
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index e938c442277d..bde473df748d 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -25,7 +25,7 @@ device 4711 via subchannel 1 in subchannel set 0, and subchannel 2 is a non-I/O
 subchannel. Device 1234 is accessed via subchannel 0 in subchannel set 1.
 The subchannel named 'defunct' does not represent any real subchannel on the
-system; it is a pseudo subchannel where disconnnected ccw devices are moved to
+system; it is a pseudo subchannel where disconnected ccw devices are moved to
 if they are displaced by another ccw device becoming operational on their
 former subchannel. The ccw devices will be moved again to a proper subchannel
 if they become operational again on that subchannel.
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 88bcb8767335..9d8eb553884c 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -1,151 +1,242 @@
+                      =============
+                      CFS Scheduler
+                      =============
-This is the CFS scheduler.
-80% of CFS's design can be summed up in a single sentence: CFS basically
-models an "ideal, precise multi-tasking CPU" on real hardware.
-"Ideal multi-tasking CPU" is a (non-existent  :-))  CPU that has 100%
-physical power and which can run each task at precise equal speed, in
-parallel, each at 1/nr_running speed. For example: if there are 2 tasks
-running then it runs each at 50% physical power - totally in parallel.
-On real hardware, we can run only a single task at once, so while that
-one task runs, the other tasks that are waiting for the CPU are at a
-disadvantage - the current task gets an unfair amount of CPU time. In
-CFS this fairness imbalance is expressed and tracked via the per-task
-p->wait_runtime (nanosec-unit) value. "wait_runtime" is the amount of
-time the task should now run on the CPU for it to become completely fair
-and balanced.
-( small detail: on 'ideal' hardware, the p->wait_runtime value would
-  always be zero - no task would ever get 'out of balance' from the
-  'ideal' share of CPU time. )
-CFS's task picking logic is based on this p->wait_runtime value and it
-is thus very simple: it always tries to run the task with the largest
-p->wait_runtime value. In other words, CFS tries to run the task with
-the 'gravest need' for more CPU time. So CFS always tries to split up
-CPU time between runnable tasks as close to 'ideal multitasking
-hardware' as possible.
-Most of the rest of CFS's design just falls out of this really simple
-concept, with a few add-on embellishments like nice levels,
-multiprocessing and various algorithm variants to recognize sleepers.
-In practice it works like this: the system runs a task a bit, and when
-the task schedules (or a scheduler tick happens) the task's CPU usage is
-'accounted for': the (small) time it just spent using the physical CPU
-is deducted from p->wait_runtime. [minus the 'fair share' it would have
-gotten anyway]. Once p->wait_runtime gets low enough so that another
-task becomes the 'leftmost task' of the time-ordered rbtree it maintains
-(plus a small amount of 'granularity' distance relative to the leftmost
-task so that we do not over-schedule tasks and trash the cache) then the
-new leftmost task is picked and the current task is preempted.
-The rq->fair_clock value tracks the 'CPU time a runnable task would have
-fairly gotten, had it been runnable during that time'. So by using
-rq->fair_clock values we can accurately timestamp and measure the
-'expected CPU time' a task should have gotten. All runnable tasks are
-sorted in the rbtree by the "rq->fair_clock - p->wait_runtime" key, and
-CFS picks the 'leftmost' task and sticks to it. As the system progresses
-forwards, newly woken tasks are put into the tree more and more to the
-right - slowly but surely giving a chance for every task to become the
-'leftmost task' and thus get on the CPU within a deterministic amount of
-time.
-Some implementation details:
- - the introduction of Scheduling Classes: an extensible hierarchy of
-   scheduler modules. These modules encapsulate scheduling policy
-   details and are handled by the scheduler core without the core
-   code assuming about them too much.
- - sched_fair.c implements the 'CFS desktop scheduler': it is a
-   replacement for the vanilla scheduler's SCHED_OTHER interactivity
-   code.
-   I'd like to give credit to Con Kolivas for the general approach here:
-   he has proven via RSDL/SD that 'fair scheduling' is possible and that
-   it results in better desktop scheduling. Kudos Con!
-   The CFS patch uses a completely different approach and implementation
-   from RSDL/SD. My goal was to make CFS's interactivity quality exceed
-   that of RSDL/SD, which is a high standard to meet :-) Testing
-   feedback is welcome to decide this one way or another. [ and, in any
-   case, all of SD's logic could be added via a kernel/sched_sd.c module
-   as well, if Con is interested in such an approach. ]
-   CFS's design is quite radical: it does not use runqueues, it uses a
-   time-ordered rbtree to build a 'timeline' of future task execution,
-   and thus has no 'array switch' artifacts (by which both the vanilla
-   scheduler and RSDL/SD are affected).
-   CFS uses nanosecond granularity accounting and does not rely on any
-   jiffies or other HZ detail. Thus the CFS scheduler has no notion of
-   'timeslices' and has no heuristics whatsoever. There is only one
-   central tunable (you have to switch on CONFIG_SCHED_DEBUG):
-         /proc/sys/kernel/sched_granularity_ns
-   which can be used to tune the scheduler from 'desktop' (low
-   latencies) to 'server' (good batching) workloads. It defaults to a
-   setting suitable for desktop workloads. SCHED_BATCH is handled by the
-   CFS scheduler module too.
-   Due to its design, the CFS scheduler is not prone to any of the
-   'attacks' that exist today against the heuristics of the stock
-   scheduler: fiftyp.c, thud.c, chew.c, ring-test.c, massive_intr.c all
-   work fine and do not impact interactivity and produce the expected
-   behavior.
-   the CFS scheduler has a much stronger handling of nice levels and
-   SCHED_BATCH: both types of workloads should be isolated much more
-   agressively than under the vanilla scheduler.
-   ( another detail: due to nanosec accounting and timeline sorting,
-     sched_yield() support is very simple under CFS, and in fact under
-     CFS sched_yield() behaves much better than under any other
-     scheduler i have tested so far. )
- - sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler
-   way than the vanilla scheduler does. It uses 100 runqueues (for all
-   100 RT priority levels, instead of 140 in the vanilla scheduler)
-   and it needs no expired array.
- - reworked/sanitized SMP load-balancing: the runqueue-walking
-   assumptions are gone from the load-balancing code now, and
-   iterators of the scheduling modules are used. The balancing code got
-   quite a bit simpler as a result.
-Group scheduler extension to CFS
-================================
-Normally the scheduler operates on individual tasks and strives to provide
-fair CPU time to each task. Sometimes, it may be desirable to group tasks
-and provide fair CPU time to each such task group. For example, it may
-be desirable to first provide fair CPU time to each user on the system
-and then to each task belonging to a user.
-CONFIG_FAIR_GROUP_SCHED strives to achieve exactly that. It lets
-SCHED_NORMAL/BATCH tasks be be grouped and divides CPU time fairly among such
-groups. At present, there are two (mutually exclusive) mechanisms to group
-tasks for CPU bandwidth control purpose:
-        - Based on user id (CONFIG_FAIR_USER_SCHED)
-                In this option, tasks are grouped according to their user id.
-        - Based on "cgroup" pseudo filesystem (CONFIG_FAIR_CGROUP_SCHED)
-                This options lets the administrator create arbitrary groups
-                of tasks, using the "cgroup" pseudo filesystem. See
-                Documentation/cgroups.txt for more information about this
-                filesystem.
-Only one of these options to group tasks can be chosen and not both.
+1.  OVERVIEW
+CFS stands for "Completely Fair Scheduler," and is the new "desktop" process
+scheduler implemented by Ingo Molnar and merged in Linux 2.6.23.  It is the
+replacement for the previous vanilla scheduler's SCHED_OTHER interactivity
+code.
+80% of CFS's design can be summed up in a single sentence: CFS basically models
+an "ideal, precise multi-tasking CPU" on real hardware.
+"Ideal multi-tasking CPU" is a (non-existent  :-)) CPU that has 100% physical
+power and which can run each task at precise equal speed, in parallel, each at
+1/nr_running speed.  For example: if there are 2 tasks running, then it runs
+each at 50% physical power --- i.e., actually in parallel.
+On real hardware, we can run only a single task at once, so we have to
+introduce the concept of "virtual runtime."  The virtual runtime of a task
+specifies when its next timeslice would start execution on the ideal
+multi-tasking CPU described above.  In practice, the virtual runtime of a task
+is its actual runtime normalized to the total number of running tasks.
+2.  FEW IMPLEMENTATION DETAILS
+In CFS the virtual runtime is expressed and tracked via the per-task
+p->se.vruntime (nanosec-unit) value.  This way, it's possible to accurately
+timestamp and measure the "expected CPU time" a task should have gotten.
+[ small detail: on "ideal" hardware, at any time all tasks would have the same
+  p->se.vruntime value --- i.e., tasks would execute simultaneously and no task
+  would ever get "out of balance" from the "ideal" share of CPU time.  ]
+CFS's task picking logic is based on this p->se.vruntime value and it is thus
+very simple: it always tries to run the task with the smallest p->se.vruntime
+value (i.e., the task which executed least so far).  CFS always tries to split
+up CPU time between runnable tasks as close to "ideal multitasking hardware" as
+possible.
+Most of the rest of CFS's design just falls out of this really simple concept,
+with a few add-on embellishments like nice levels, multiprocessing and various
+algorithm variants to recognize sleepers.
+3.  THE RBTREE
+CFS's design is quite radical: it does not use the old data structures for the
+runqueues, but it uses a time-ordered rbtree to build a "timeline" of future
+task execution, and thus has no "array switch" artifacts (by which both the
+previous vanilla scheduler and RSDL/SD are affected).
+CFS also maintains the rq->cfs.min_vruntime value, which is a monotonic
+increasing value tracking the smallest vruntime among all tasks in the
+runqueue.  The total amount of work done by the system is tracked using
+min_vruntime; that value is used to place newly activated entities on the left
+side of the tree as much as possible.
+The total number of running tasks in the runqueue is accounted through the
+rq->cfs.load value, which is the sum of the weights of the tasks queued on the
+runqueue.
+CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
+p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
+account for possible wraparounds).  CFS picks the "leftmost" task from this
+tree and sticks to it.
+As the system progresses forwards, the executed tasks are put into the tree
+more and more to the right --- slowly but surely giving a chance for every task
+to become the "leftmost task" and thus get on the CPU within a deterministic
+amount of time.
+Summing up, CFS works like this: it runs a task a bit, and when the task
+schedules (or a scheduler tick happens) the task's CPU usage is "accounted
+for": the (small) time it just spent using the physical CPU is added to
+p->se.vruntime.  Once p->se.vruntime gets high enough so that another task
+becomes the "leftmost task" of the time-ordered rbtree it maintains (plus a
+small amount of "granularity" distance relative to the leftmost task so that we
+do not over-schedule tasks and trash the cache), then the new leftmost task is
+picked and the current task is preempted.
+4.  SOME FEATURES OF CFS
+CFS uses nanosecond granularity accounting and does not rely on any jiffies or
+other HZ detail.  Thus the CFS scheduler has no notion of "timeslices" in the
+way the previous scheduler had, and has no heuristics whatsoever.  There is
+only one central tunable (you have to switch on CONFIG_SCHED_DEBUG):
+   /proc/sys/kernel/sched_granularity_ns
+which can be used to tune the scheduler from "desktop" (i.e., low latencies) to
+"server" (i.e., good batching) workloads.  It defaults to a setting suitable
+for desktop workloads.  SCHED_BATCH is handled by the CFS scheduler module too.
+Due to its design, the CFS scheduler is not prone to any of the "attacks" that
+exist today against the heuristics of the stock scheduler: fiftyp.c, thud.c,
+chew.c, ring-test.c, massive_intr.c all work fine and do not impact
+interactivity and produce the expected behavior.
+The CFS scheduler has a much stronger handling of nice levels and SCHED_BATCH
+than the previous vanilla scheduler: both types of workloads are isolated much
+more aggressively.
+SMP load-balancing has been reworked/sanitized: the runqueue-walking
+assumptions are gone from the load-balancing code now, and iterators of the
+scheduling modules are used.  The balancing code got quite a bit simpler as a
+result.
+5. Scheduling policies
+CFS implements three scheduling policies:
+  - SCHED_NORMAL (traditionally called SCHED_OTHER): The scheduling
+    policy that is used for regular tasks.
+  - SCHED_BATCH: Does not preempt nearly as often as regular tasks
+    would, thereby allowing tasks to run longer and make better use of
+    caches but at the cost of interactivity. This is well suited for
+    batch jobs.
+  - SCHED_IDLE: This is even weaker than nice 19, but its not a true
+    idle timer scheduler in order to avoid to get into priority
+    inversion problems which would deadlock the machine.
+SCHED_FIFO/_RR are implemented in sched_rt.c and are as specified by
+POSIX.
+The command chrt from util-linux-ng 2.13.1.1 can set all of these except
+SCHED_IDLE.
-Group scheduler tunables:
-When CONFIG_FAIR_USER_SCHED is defined, a directory is created in sysfs for
-each new user and a "cpu_share" file is added in that directory.
+6.  SCHEDULING CLASSES
+The new CFS scheduler has been designed in such a way to introduce "Scheduling
+Classes," an extensible hierarchy of scheduler modules.  These modules
+encapsulate scheduling policy details and are handled by the scheduler core
+without the core code assuming too much about them.
+sched_fair.c implements the CFS scheduler described above.
+sched_rt.c implements SCHED_FIFO and SCHED_RR semantics, in a simpler way than
+the previous vanilla scheduler did.  It uses 100 runqueues (for all 100 RT
+priority levels, instead of 140 in the previous scheduler) and it needs no
+expired array.
+Scheduling classes are implemented through the sched_class structure, which
+contains hooks to functions that must be called whenever an interesting event
+occurs.
+This is the (partial) list of the hooks:
+ - enqueue_task(...)
+   Called when a task enters a runnable state.
+   It puts the scheduling entity (task) into the red-black tree and
+   increments the nr_running variable.
+ - dequeue_tree(...)
+   When a task is no longer runnable, this function is called to keep the
+   corresponding scheduling entity out of the red-black tree.  It decrements
+   the nr_running variable.
+ - yield_task(...)
+   This function is basically just a dequeue followed by an enqueue, unless the
+   compat_yield sysctl is turned on; in that case, it places the scheduling
+   entity at the right-most end of the red-black tree.
+ - check_preempt_curr(...)
+   This function checks if a task that entered the runnable state should
+   preempt the currently running task.
+ - pick_next_task(...)
+   This function chooses the most appropriate task eligible to run next.
+ - set_curr_task(...)
+   This function is called when a task changes its scheduling class or changes
+   its task group.
+ - task_tick(...)
+   This function is mostly called from time tick functions; it might lead to
+   process switch.  This drives the running preemption.
+ - task_new(...)
+   The core scheduler gives the scheduling module an opportunity to manage new
+   task startup.  The CFS scheduling module uses it for group scheduling, while
+   the scheduling module for a real-time task does not use it.
+7.  GROUP SCHEDULER EXTENSIONS TO CFS
+Normally, the scheduler operates on individual tasks and strives to provide
+fair CPU time to each task.  Sometimes, it may be desirable to group tasks and
+provide fair CPU time to each such task group.  For example, it may be
+desirable to first provide fair CPU time to each user on the system and then to
+each task belonging to a user.
+CONFIG_GROUP_SCHED strives to achieve exactly that.  It lets tasks to be
+grouped and divides CPU time fairly among such groups.
+CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
+SCHED_RR) tasks.
+CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
+SCHED_BATCH) tasks.
+At present, there are two (mutually exclusive) mechanisms to group tasks for
+CPU bandwidth control purposes:
+ - Based on user id (CONFIG_USER_SCHED)
+   With this option, tasks are grouped according to their user id.
+ - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
+   This options needs CONFIG_CGROUPS to be defined, and lets the administrator
+   create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
+   Documentation/cgroups.txt for more information about this filesystem.
+Only one of these options to group tasks can be chosen and not both.
+When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
+user and a "cpu_share" file is added in that directory.
        # cd /sys/kernel/uids
        # cat 512/cpu_share             # Display user 512's CPU share
@@ -155,16 +246,14 @@ each new user and a "cpu_share" file is added in that directory.
        2048
        #
-CPU bandwidth between two users are divided in the ratio of their CPU shares.
+CPU bandwidth between two users is divided in the ratio of their CPU shares.
-For ex: if you would like user "root" to get twice the bandwidth of user
+For example: if you would like user "root" to get twice the bandwidth of user
-"guest", then set the cpu_share for both the users such that "root"'s
+"guest," then set the cpu_share for both the users such that "root"'s cpu_share
-cpu_share is twice "guest"'s cpu_share
+is twice "guest"'s cpu_share.
-When CONFIG_FAIR_CGROUP_SCHED is defined, a "cpu.shares" file is created
+When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
-for each group created using the pseudo filesystem. See example steps
+group created using the pseudo filesystem.  See example steps below to create
-below to create task groups and modify their CPU share using the "cgroups"
+task groups and modify their CPU share using the "cgroups" pseudo filesystem.
-pseudo filesystem
        # mkdir /dev/cpuctl
        # mount -t cgroup -ocpu none /dev/cpuctl
diff --git a/Documentation/scsi/ChangeLog.megaraid b/Documentation/scsi/ChangeLog.megaraid
index 37796fe45bd0..eaa4801f2ce6 100644
--- a/Documentation/scsi/ChangeLog.megaraid
+++ b/Documentation/scsi/ChangeLog.megaraid
@@ -409,7 +409,7 @@ i.	Function reordering so that inline functions are defined before they
        megaraid_mbox_prepare_pthru, megaraid_mbox_prepare_epthru,
        megaraid_busywait_mbox
-                - Andrew Morton <akpm@osdl.org>, 08.19.2004
+                - Andrew Morton, 08.19.2004
                linux-scsi mailing list
        "Something else to clean up after inclusion: every instance of an
@@ -471,13 +471,13 @@ vi.	Add support for 64-bit applications. Current drivers assume only
 vii.    Move the function declarations for the management module from
        megaraid_mm.h to megaraid_mm.c
-                - Andrew Morton <akpm@osdl.org>, 08.19.2004
+                - Andrew Morton, 08.19.2004
                linux-scsi mailing list
 viii.   Change default values for MEGARAID_NEWGEN, MEGARAID_MM, and
        MEGARAID_MAILBOX to 'n' in Kconfig.megaraid
-                - Andrew Morton <akpm@osdl.org>, 08.19.2004
+                - Andrew Morton, 08.19.2004
                linux-scsi mailing list
 ix.     replace udelay with msleep
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 716fcc1cafb5..c851ef497795 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,26 @@
+1 Release Date    : Thur.July. 24 11:41:51 PST 2008 -
+                       (emaild-id:megaraidlinux@lsi.com)
+                       Sumant Patro
+                       Bo Yang
+2 Current Version : 00.00.04.01
+3 Older Version   : 00.00.03.22
+1. Add the new controller (0078, 0079) support to the driver
+       Those controllers are LSI's next generatation(gen2) SAS controllers.
+1 Release Date    : Mon.June. 23 10:12:45 PST 2008 -
+                       (emaild-id:megaraidlinux@lsi.com)
+                       Sumant Patro
+                       Bo Yang
+2 Current Version : 00.00.03.22
+3 Older Version   : 00.00.03.20
+1. Add shutdown DCMD cmd to the shutdown routine to make FW shutdown proper.
+2. Unexpected interrupt occurs in HWR Linux driver, add the dumy readl pci flush will fix this issue.
 1 Release Date    : Mon. March 10 11:02:31 PDT 2008 -
                        (emaild-id:megaraidlinux@lsi.com)
                        Sumant Patro
diff --git a/Documentation/scsi/ibmmca.txt b/Documentation/scsi/ibmmca.txt
index a810421f1fb3..3920f28710c4 100644
--- a/Documentation/scsi/ibmmca.txt
+++ b/Documentation/scsi/ibmmca.txt
@@ -524,7 +524,7 @@
   - Michael Lang
 
   June 25 1997: (v1.8b)
-   1) Some cosmetical changes for the handling of SCSI-device-types.
+   1) Some cosmetic changes for the handling of SCSI-device-types.
      Now, also CD-Burners / WORMs and SCSI-scanners should work. For
      MO-drives I have no experience, therefore not yet supported.
      In logical_devices I changed from different type-variables to one
@@ -914,7 +914,7 @@
      in version 4.0. This was never really necessary, as all troubles were
      based on non-command related reasons up to now, so bypassing commands
      did not help to avoid any bugs. It is kept in 3.2X for debugging reasons.
-   5) Dynamical reassignment of ldns was again verified and analyzed to be
+   5) Dynamic reassignment of ldns was again verified and analyzed to be
      completely inoperational. This is corrected and should work now.
   6) All commands that get sent to the SCSI adapter were verified and
      completed in such a way, that they are now completely conform to the
@@ -1386,7 +1386,7 @@
   concerning the Linux-kernel in special, this SCSI-driver comes without any
   warranty. Its functionality is tested as good as possible on certain 
   machines and combinations of computer hardware, which does not exclude,
-   that dataloss or severe damage of hardware is possible while using this
+   that data loss or severe damage of hardware is possible while using this
   part of software on some arbitrary computer hardware or in combination 
   with other software packages. It is highly recommended to make backup
   copies of your data before using this software. Furthermore, personal
diff --git a/Documentation/scsi/lpfc.txt b/Documentation/scsi/lpfc.txt
index 4dbe41370a6d..5741ea8aa88a 100644
--- a/Documentation/scsi/lpfc.txt
+++ b/Documentation/scsi/lpfc.txt
@@ -36,7 +36,7 @@ Cable pull and temporary device Loss:
  being removed, a switch rebooting, or a device reboot), the driver could
  hide the disappearance of the device from the midlayer. I/O's issued to
  the LLDD would simply be queued for a short duration, allowing the device
-  to reappear or link come back alive, with no inadvertant side effects
+  to reappear or link come back alive, with no inadvertent side effects
  to the system. If the driver did not hide these conditions, i/o would be
  errored by the driver, the mid-layer would exhaust its retries, and the
  device would be taken offline. Manual intervention would be required to
diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt
index d403e46d8463..38d324d62b25 100644
--- a/Documentation/scsi/scsi_fc_transport.txt
+++ b/Documentation/scsi/scsi_fc_transport.txt
@@ -65,7 +65,7 @@ Overview:
    discussion will concentrate on NPIV.
  Note: World Wide Name assignment (and uniqueness guarantees) are left
-    up to an administrative entity controling the vport. For example,
+    up to an administrative entity controlling the vport. For example,
    if vports are to be associated with virtual machines, a XEN mgmt
    utility would be responsible for creating wwpn/wwnn's for the vport,
    using it's own naming authority and OUI. (Note: it already does this
@@ -91,7 +91,7 @@ Device Trees and Vport Objects:
  Here's what to expect in the device tree :
   The typical Physical Port's Scsi_Host:
     /sys/devices/.../host17/
-   and it has the typical decendent tree:
+   and it has the typical descendant tree:
     /sys/devices/.../host17/rport-17:0-0/target17:0:0/17:0:0:0:
   and then the vport is created on the Physical Port:
     /sys/devices/.../host17/vport-17:0-0
@@ -192,7 +192,7 @@ Vport States:
      independent of the adapter's link state.
    - Instantiation of the vport on the FC link via ELS traffic, etc.
      This is equivalent to a "link up" and successfull link initialization.
-  Futher information can be found in the interfaces section below for
+  Further information can be found in the interfaces section below for
  Vport Creation.
  Once a vport has been instantiated with the kernel/LLDD, a vport state
@@ -436,6 +436,42 @@ Other:
    was updated to remove all vports for the fc_host as well.
+Transport supplied functions
+----------------------------
+The following functions are supplied by the FC-transport for use by LLDs.
+   fc_vport_create - create a vport
+   fc_vport_terminate - detach and remove a vport
+Details:
+/**
+ * fc_vport_create - Admin App or LLDD requests creation of a vport
+ * @shost:     scsi host the virtual port is connected to.
+ * @ids:       The world wide names, FC4 port roles, etc for
+ *              the virtual port.
+ *
+ * Notes:
+ *     This routine assumes no locks are held on entry.
+ */
+struct fc_vport *
+fc_vport_create(struct Scsi_Host *shost, struct fc_vport_identifiers *ids)
+/**
+ * fc_vport_terminate - Admin App or LLDD requests termination of a vport
+ * @vport:      fc_vport to be terminated
+ *
+ * Calls the LLDD vport_delete() function, then deallocates and removes
+ * the vport from the shost and object tree.
+ *
+ * Notes:
+ *      This routine assumes no locks are held on entry.
+ */
+int
+fc_vport_terminate(struct fc_vport *vport)
 Credits
 =======
 The following people have contributed to this document:
diff --git a/Documentation/serial/driver b/Documentation/serial/driver
index 88ad615dd338..77ba0afbe4db 100644
--- a/Documentation/serial/driver
+++ b/Documentation/serial/driver
@@ -186,6 +186,17 @@ hardware.
        Locking: port_sem taken.
        Interrupts: caller dependent.
+  flush_buffer(port)
+        Flush any write buffers, reset any DMA state and stop any
+        ongoing DMA transfers.
+        This will be called whenever the port->info->xmit circular
+        buffer is cleared.
+        Locking: port->lock taken.
+        Interrupts: locally disabled.
+        This call must not sleep
  set_termios(port,termios,oldtermios)
        Change the port parameters, including word length, parity, stop
        bits.  Update read_status_mask and ignore_status_mask to indicate
diff --git a/Documentation/sh/clk.txt b/Documentation/sh/clk.txt
index 9aef710e9a4b..114b595cfa97 100644
--- a/Documentation/sh/clk.txt
+++ b/Documentation/sh/clk.txt
@@ -12,7 +12,7 @@ means no changes to adjanced clock
 Internally, the clk_set_rate_ex forwards request to clk->ops->set_rate method,
 if it is present in ops structure. The method should set the clock rate and adjust
 all needed clocks according to the passed algo_id.
-Exact values for algo_id are machine-dependend. For the sh7722, the following
+Exact values for algo_id are machine-dependent. For the sh7722, the following
 values are defined:
        NO_CHANGE       = 0,
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 72aff61e7315..e0e54a27fc10 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -746,8 +746,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
  Module snd-hda-intel
  --------------------
-    Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8),
+    Module for Intel HD Audio (ICH6, ICH6M, ESB2, ICH7, ICH8, ICH9, ICH10,
-                ATI SB450, SB600, RS600,
+                        PCH, SCH),
+                ATI SB450, SB600, R600, RS600, RS690, RS780, RV610, RV620,
+                        RV630, RV635, RV670, RV770,
                VIA VT8251/VT8237A,
                SIS966, ULI M5461
@@ -807,6 +809,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
        ALC260
          hp            HP machines
          hp-3013       HP machines (3013-variant)
+          hp-dc7600     HP DC7600
          fujitsu       Fujitsu S7020
          acer          Acer TravelMate
          will          Will laptops (PB V7900)
@@ -828,8 +831,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          hippo         Hippo (ATI) with jack detection, Sony UX-90s
          hippo_1       Hippo (Benq) with jack detection
          sony-assamd   Sony ASSAMD
+          toshiba-s06   Toshiba S06
+          toshiba-rx1   Toshiba RX1
          ultra         Samsung Q1 Ultra Vista model
          lenovo-3000   Lenovo 3000 y410
+          nec           NEC Versa S9100
          basic         fixed pin assignment w/o SPDIF
          auto          auto-config reading BIOS (default)
@@ -838,6 +844,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          3stack        3-stack model
          toshiba       Toshiba A205
          acer          Acer laptops
+          acer-aspire   Acer Aspire One
          dell          Dell OEM laptops (Vostro 1200)
          zepto         Zepto laptops
          test          for testing/debugging purpose, almost all controls can
@@ -847,6 +854,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
        ALC269
          basic         Basic preset
+          quanta        Quanta FL1
+          eeepc-p703    ASUS Eeepc P703 P900A
+          eeepc-p901    ASUS Eeepc P901 S101
        ALC662/663
          3stack-dig    3-stack (2-channel) with SPDIF
@@ -856,10 +866,17 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          lenovo-101e    Lenovo laptop
          eeepc-p701    ASUS Eeepc P701
          eeepc-ep20    ASUS Eeepc EP20
+          ecs           ECS/Foxconn mobo
          m51va         ASUS M51VA
          g71v          ASUS G71V
          h13           ASUS H13
          g50v          ASUS G50V
+          asus-mode1    ASUS
+          asus-mode2    ASUS
+          asus-mode3    ASUS
+          asus-mode4    ASUS
+          asus-mode5    ASUS
+          asus-mode6    ASUS
          auto          auto-config reading BIOS (default)
        ALC882/885
@@ -891,12 +908,14 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          lenovo-101e   Lenovo 101E
          lenovo-nb0763 Lenovo NB0763
          lenovo-ms7195-dig Lenovo MS7195
+          lenovo-sky    Lenovo Sky
          haier-w66     Haier W66
          3stack-hp     HP machines with 3stack (Lucknow, Samba boards)
          6stack-dell   Dell machines with 6stack (Inspiron 530)
          mitac         Mitac 8252D
          clevo-m720    Clevo M720 laptop series
          fujitsu-pi2515 Fujitsu AMILO Pi2515
+          3stack-6ch-intel Intel DG33* boards
          auto          auto-config reading BIOS (default)
        ALC861/660
@@ -929,7 +948,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          allout        5-jack in back, 2-jack in front, SPDIF out
          auto          auto-config reading BIOS (default)
-        AD1882
+        AD1882 / AD1882A
          3stack        3-stack mode (default)
          6stack        6-stack mode
@@ -1024,6 +1043,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
          intel-mac-v3  Intel Mac Type 3
          intel-mac-v4  Intel Mac Type 4
          intel-mac-v5  Intel Mac Type 5
+          intel-mac-auto Intel Mac (detect type according to subsystem id)
          macmini       Intel Mac Mini (equivalent with type 3)
          macbook       Intel Mac Book (eq. type 5)
          macbook-pro-v1 Intel Mac Book Pro 1st generation (eq. type 3)
@@ -1078,7 +1098,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
            register value without FIFO size correction as the current
            DMA pointer.  position_fix=2 will make the driver to use
            the position buffer instead of reading SD_LPIB register.
-            (Usually SD_LPLIB register is more accurate than the
+            (Usually SD_LPIB register is more accurate than the
            position buffer.)
    NB: If you get many "azx_get_response timeout" messages at
@@ -1143,8 +1163,6 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    This module supports autoprobe and multiple cards.
-    Power management is _not_ supported.
  Module snd-ice1712
  ------------------
@@ -1167,6 +1185,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                        * Event Electronics, EZ8
                        * Digigram VX442
                        * Lionstracs, Mediastaton
+                        * Terrasoniq TS 88
    model       - Use the given board model, one of the following:
                  delta1010, dio2496, delta66, delta44, audiophile, delta410,
@@ -1201,7 +1220,10 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                        * TerraTec Phase 22
                        * TerraTec Phase 28
                        * AudioTrak Prodigy 7.1
-                        * AudioTrak Prodigy 7.1LT
+                        * AudioTrak Prodigy 7.1 LT
+                        * AudioTrak Prodigy 7.1 XT
+                        * AudioTrak Prodigy 7.1 HIFI
+                        * AudioTrak Prodigy 7.1 HD2
                        * AudioTrak Prodigy 192
                        * Pontis MS300
                        * Albatron K8X800 Pro II 
@@ -1212,12 +1234,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                        * Shuttle SN25P
                        * Onkyo SE-90PCI
                        * Onkyo SE-200PCI
+                        * ESI Juli@
+                        * Hercules Fortissimo IV
+                        * EGO-SYS WaveTerminal 192M
    model       - Use the given board model, one of the following:
                  revo51, revo71, amp2000, prodigy71, prodigy71lt,
-                  prodigy192, aureon51, aureon71, universe, ap192,
+                  prodigy71xt, prodigy71hifi, prodigyhd2, prodigy192,
-                  k8x800, phase22, phase28, ms300, av710, se200pci,
+                  juli, aureon51, aureon71, universe, ap192, k8x800,
-                  se90pci
+                  phase22, phase28, ms300, av710, se200pci, se90pci,
+                  fortissimo4, sn25p, WT192M
    This module supports multiple cards and autoprobe.
@@ -1256,7 +1282,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    Module for AC'97 motherboards from Intel and compatibles.
                        * Intel i810/810E, i815, i820, i830, i84x, MX440
-                                ICH5, ICH6, ICH7, ESB2
+                                ICH5, ICH6, ICH7, 6300ESB, ESB2
                        * SiS 7012 (SiS 735)
                        * NVidia NForce, NForce2, NForce3, MCP04, CK804
                                 CK8, CK8S, MCP501
@@ -1627,8 +1653,6 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    This module supports autoprobe and multiple cards.
-    Power management is _not_ supported.
  Module snd-pcsp
  -----------------
@@ -1954,6 +1978,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
                        * CHIC  True Sound 4Dwave
                        * Shark  Predator4D-PCI
                        * Jaton  SonicWave 4D
+                        * SiS SI7018 PCI Audio
+                        * Hoontech SoundTrack Digital 4DWave NX
    pcm_channels   - max channels (voices) reserved for PCM
    wavetable_size - max wavetable size in kB (4-?kb)
@@ -1969,12 +1995,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
    vid             - Vendor ID for the device (optional)
    pid             - Product ID for the device (optional)
+    nrpacks         - Max. number of packets per URB (default: 8)
+    async_unlink    - Use async unlink mode (default: yes)
    device_setup    - Device specific magic number (optional)
                    - Influence depends on the device
                    - Default: 0x0000 
+    ignore_ctl_error - Ignore any USB-controller regarding mixer
+                       interface (default: no)
    This module supports multiple devices, autoprobe and hotplugging.
+    NB: nrpacks parameter can be modified dynamically via sysfs.
+        Don't put the value over 20.  Changing via sysfs has no sanity
+        check.
+    NB: async_unlink=0 would cause Oops.  It remains just for
+        debugging purpose (if any).
+    NB: ignore_ctl_error=1 may help when you get an error at accessing
+        the mixer element such as URB error -22.  This happens on some
+        buggy USB device or the controller.
  Module snd-usb-caiaq
  --------------------
@@ -2080,13 +2119,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
  Module snd-virtuoso
  -------------------
-    Module for sound cards based on the Asus AV200 chip, i.e.,
+    Module for sound cards based on the Asus AV100/AV200 chips,
-    Xonar D2 and Xonar D2X.
+    i.e., Xonar D1, DX, D2, D2X and HDAV1.3 (Deluxe).
    This module supports autoprobe and multiple cards.
-    Power management is _not_ supported.
  Module snd-vx222
  ----------------
diff --git a/Documentation/sound/alsa/Audiophile-Usb.txt b/Documentation/sound/alsa/Audiophile-Usb.txt
index 2ad5e6306c44..a4c53d8961e1 100644
--- a/Documentation/sound/alsa/Audiophile-Usb.txt
+++ b/Documentation/sound/alsa/Audiophile-Usb.txt
@@ -236,15 +236,15 @@ The parameter can be given:
       alias snd-card-1 snd-usb-audio
       options snd-usb-audio index=1 device_setup=0x09
-CAUTION when initializaing the device
+CAUTION when initializing the device
 -------------------------------------
 * Correct initialization on the device requires that device_setup is given to
   the module BEFORE the device is turned on. So, if you use the "manual probing"
   method described above, take care to power-on the device AFTER this initialization.
- * Failing to respect this will lead in a misconfiguration of the device. In this case
+ * Failing to respect this will lead to a misconfiguration of the device. In this case
-   turn off the device, unproble the snd-usb-audio module, then probe it again with 
+   turn off the device, unprobe the snd-usb-audio module, then probe it again with
   correct device_setup parameter and then (and only then) turn on the device again.
 * If you've correctly initialized the device in a valid mode and then want to switch
@@ -388,9 +388,9 @@ There are 2 main potential issues when using Jackd with the device:
 Jack supports big endian devices only in recent versions (thanks to
 Andreas Steinmetz for his first big-endian patch). I can't remember 
-extacly when this support was released into jackd, let's just say that 
+exactly when this support was released into jackd, let's just say that
 with jackd version 0.103.0 it's almost ok (just a small bug is affecting 
-16bits Big-Endian devices, but since you've read  carefully the above 
+16bits Big-Endian devices, but since you've read carefully the above
 paragraphs, you're now using kernel >= 2.6.23 and your 16bits devices 
 are now Little Endians ;-) ).
diff --git a/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl b/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
index c4d2e3507af9..9d644f7e241e 100644
--- a/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
+++ b/Documentation/sound/alsa/DocBook/alsa-driver-api.tmpl
@@ -42,7 +42,7 @@
     <sect1><title>Device Components</title>
 !Esound/core/device.c
     </sect1>
-     <sect1><title>KMOD and Device File Entries</title>
+     <sect1><title>Module requests and Device File Entries</title>
 !Esound/core/sound.c
     </sect1>
     <sect1><title>Memory Management Helpers</title>
diff --git a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
index e13c4e67029f..87a7c07ab658 100644
--- a/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
+++ b/Documentation/sound/alsa/DocBook/writing-an-alsa-driver.tmpl
@@ -5073,8 +5073,7 @@ struct _snd_pcm_runtime {
      with <constant>SNDRV_DMA_TYPE_CONTINUOUS</constant> type and the
      <function>snd_dma_continuous_data(GFP_KERNEL)</function> device pointer,
      where <constant>GFP_KERNEL</constant> is the kernel allocation flag to
-      use.  For the SBUS, <constant>SNDRV_DMA_TYPE_SBUS</constant> and
+      use.
-      <function>snd_dma_sbus_data(sbus_dev)</function> are used instead.
      For the PCI scatter-gather buffers, use
      <constant>SNDRV_DMA_TYPE_DEV_SG</constant> with
      <function>snd_dma_pci_data(pci)</function>
@@ -6135,44 +6134,58 @@ struct _snd_pcm_runtime {
      </para>
    </section>
-    <section id="useful-functions-snd-assert">
+    <section id="useful-functions-snd-bug">
-      <title><function>snd_assert()</function></title>
+      <title><function>snd_BUG()</function></title>
      <para>
-        <function>snd_assert()</function> macro is similar with the
+        It shows the <computeroutput>BUG?</computeroutput> message and
-      normal <function>assert()</function> macro. For example,  
+      stack trace as well as <function>snd_BUG_ON</function> at the point.
+      It's useful to show that a fatal error happens there. 
+      </para>
+      <para>
+         When no debug flag is set, this macro is ignored. 
+      </para>
+    </section>
+    <section id="useful-functions-snd-bug-on">
+      <title><function>snd_BUG_ON()</function></title>
+      <para>
+        <function>snd_BUG_ON()</function> macro is similar with
+        <function>WARN_ON()</function> macro. For example,  
        <informalexample>
          <programlisting>
 <![CDATA[
-  snd_assert(pointer != NULL, return -EINVAL);
+  snd_BUG_ON(!pointer);
 ]]>
          </programlisting>
        </informalexample>
-      </para>
-      <para>
+        or it can be used as the condition,
-        The first argument is the expression to evaluate, and the
+        <informalexample>
-      second argument is the action if it fails. When
+          <programlisting>
-      <constant>CONFIG_SND_DEBUG</constant>, is set, it will show an
+<![CDATA[
-      error message such as <computeroutput>BUG? (xxx)</computeroutput>
+  if (snd_BUG_ON(non_zero_is_bug))
-      together with stack trace.
+          return -EINVAL;
-      </para>
+]]>
-      <para>
+          </programlisting>
-         When no debug flag is set, this macro is ignored. 
+        </informalexample>
-      </para>
-    </section>
-    <section id="useful-functions-snd-bug">
-      <title><function>snd_BUG()</function></title>
-      <para>
-        It shows the <computeroutput>BUG?</computeroutput> message and
-      stack trace as well as <function>snd_assert</function> at the point.
-      It's useful to show that a fatal error happens there. 
      </para>
      <para>
-         When no debug flag is set, this macro is ignored. 
+        The macro takes an conditional expression to evaluate.
+        When <constant>CONFIG_SND_DEBUG</constant>, is set, the
+        expression is actually evaluated. If it's non-zero, it shows
+        the warning message such as
+        <computeroutput>BUG? (xxx)</computeroutput>
+        normally followed by stack trace.  It returns the evaluated
+        value.
+        When no <constant>CONFIG_SND_DEBUG</constant> is set, this
+        macro always returns zero.
      </para>
    </section>
  </chapter>
diff --git a/Documentation/sound/alsa/hda_codec.txt b/Documentation/sound/alsa/hda_codec.txt
index 8e1b02526698..34e87ec1379c 100644
--- a/Documentation/sound/alsa/hda_codec.txt
+++ b/Documentation/sound/alsa/hda_codec.txt
@@ -67,7 +67,7 @@ CONFIG_SND_HDA_POWER_SAVE kconfig.  It's called when the codec needs
 to power up or may power down.  The controller should check the all
 belonging codecs on the bus whether they are actually powered off
 (check codec->power_on), and optionally the driver may power down the
-contoller side, too.
+controller side, too.
 The bus instance is created via snd_hda_bus_new().  You need to pass
 the card instance, the template, and the pointer to store the
diff --git a/Documentation/sound/alsa/soc/dapm.txt b/Documentation/sound/alsa/soc/dapm.txt
index c784a18b94dc..46f9684d0b29 100644
--- a/Documentation/sound/alsa/soc/dapm.txt
+++ b/Documentation/sound/alsa/soc/dapm.txt
@@ -68,7 +68,7 @@ Audio DAPM widgets fall into a number of types:-
 (Widgets are defined in include/sound/soc-dapm.h)
 Widgets are usually added in the codec driver and the machine driver. There are
-convience macros defined in soc-dapm.h that can be used to quickly build a
+convenience macros defined in soc-dapm.h that can be used to quickly build a
 list of widgets of the codecs and machines DAPM widgets.
 Most widgets have a name, register, shift and invert. Some widgets have extra
@@ -135,11 +135,7 @@ when the Mic is inserted:-
 static int spitz_mic_bias(struct snd_soc_dapm_widget* w, int event)
 {
-        if(SND_SOC_DAPM_EVENT_ON(event))
+        gpio_set_value(SPITZ_GPIO_MIC_BIAS, SND_SOC_DAPM_EVENT_ON(event));
-                set_scoop_gpio(&spitzscoop2_device.dev, SPITZ_SCP2_MIC_BIAS);
-        else
-                reset_scoop_gpio(&spitzscoop2_device.dev, SPITZ_SCP2_MIC_BIAS);
        return 0;
 }
@@ -269,11 +265,7 @@ powered only when the spk is in use.
 /* turn speaker amplifier on/off depending on use */
 static int corgi_amp_event(struct snd_soc_dapm_widget *w, int event)
 {
-        if (SND_SOC_DAPM_EVENT_ON(event))
+        gpio_set_value(CORGI_GPIO_APM_ON, SND_SOC_DAPM_EVENT_ON(event));
-                set_scoop_gpio(&corgiscoop_device.dev, CORGI_SCP_APM_ON);
-        else
-                reset_scoop_gpio(&corgiscoop_device.dev, CORGI_SCP_APM_ON);
        return 0;
 }
diff --git a/Documentation/sparc/sbus_drivers.txt b/Documentation/sparc/sbus_drivers.txt
deleted file mode 100644
index eb1e28ad8822..000000000000
--- a/Documentation/sparc/sbus_drivers.txt
+++ /dev/null
@@ -1,309 +0,0 @@
-                Writing SBUS Drivers
-            David S. Miller (davem@redhat.com)
-        The SBUS driver interfaces of the Linux kernel have been
-revamped completely for 2.4.x for several reasons.  Foremost were
-performance and complexity concerns.  This document details these
-new interfaces and how they are used to write an SBUS device driver.
-        SBUS drivers need to include <asm/sbus.h> to get access
-to functions and structures described here.
-                Probing and Detection
-        Each SBUS device inside the machine is described by a
-structure called "struct sbus_dev".  Likewise, each SBUS bus
-found in the system is described by a "struct sbus_bus".  For
-each SBUS bus, the devices underneath are hung in a tree-like
-fashion off of the bus structure.
-        The SBUS device structure contains enough information
-for you to implement your device probing algorithm and obtain
-the bits necessary to run your device.  The most commonly
-used members of this structure, and their typical usage,
-will be detailed below.
-        Here is a piece of skeleton code for performing a device
-probe in an SBUS driver under Linux:
-        static int __devinit mydevice_probe_one(struct sbus_dev *sdev)
-        {
-                struct mysdevice *mp = kzalloc(sizeof(*mp), GFP_KERNEL);
-                if (!mp)
-                        return -ENODEV;
-                ...
-                dev_set_drvdata(&sdev->ofdev.dev, mp);
-                return 0;
-                ...
-        }
-        static int __devinit mydevice_probe(struct of_device *dev,
-                                            const struct of_device_id *match)
-        {
-                struct sbus_dev *sdev = to_sbus_device(&dev->dev);
-                return mydevice_probe_one(sdev);
-        }
-        static int __devexit mydevice_remove(struct of_device *dev)
-        {
-                struct sbus_dev *sdev = to_sbus_device(&dev->dev);
-                struct mydevice *mp = dev_get_drvdata(&dev->dev);
-                return mydevice_remove_one(sdev, mp);
-        }
-        static struct of_device_id mydevice_match[] = {
-                {
-                        .name = "mydevice",
-                },
-                {},
-        };
-        MODULE_DEVICE_TABLE(of, mydevice_match);
-        static struct of_platform_driver mydevice_driver = {
-                .match_table    = mydevice_match,
-                .probe          = mydevice_probe,
-                .remove         = __devexit_p(mydevice_remove),
-                .driver         = {
-                        .name           = "mydevice",
-                },
-        };
-        static int __init mydevice_init(void)
-        {
-                return of_register_driver(&mydevice_driver, &sbus_bus_type);
-        }
-        static void __exit mydevice_exit(void)
-        {
-                of_unregister_driver(&mydevice_driver);
-        }
-        module_init(mydevice_init);
-        module_exit(mydevice_exit);
-        The mydevice_match table is a series of entries which
-describes what SBUS devices your driver is meant for.  In the
-simplest case you specify a string for the 'name' field.  Every
-SBUS device with a 'name' property matching your string will
-be passed one-by-one to your .probe method.
-        You should store away your device private state structure
-pointer in the drvdata area so that you can retrieve it later on
-in your .remove method.
-        Any memory allocated, registers mapped, IRQs registered,
-etc. must be undone by your .remove method so that all resources
-of your device are released by the time it returns.
-        You should _NOT_ use the for_each_sbus(), for_each_sbusdev(),
-and for_all_sbusdev() interfaces.  They are deprecated, will be
-removed, and no new driver should reference them ever.
-                Mapping and Accessing I/O Registers
-        Each SBUS device structure contains an array of descriptors
-which describe each register set. We abuse struct resource for that.
-They each correspond to the "reg" properties provided by the OBP firmware.
-        Before you can access your device's registers you must map
-them.  And later if you wish to shutdown your driver (for module
-unload or similar) you must unmap them.  You must treat them as
-a resource, which you allocate (map) before using and free up
-(unmap) when you are done with it.
-        The mapping information is stored in an opaque value
-typed as an "unsigned long".  This is the type of the return value
-of the mapping interface, and the arguments to the unmapping
-interface.  Let's say you want to map the first set of registers.
-Perhaps part of your driver software state structure looks like:
-        struct mydevice {
-                unsigned long control_regs;
-           ...
-                struct sbus_dev *sdev;
-           ...
-        };
-        At initialization time you then use the sbus_ioremap
-interface to map in your registers, like so:
-        static void init_one_mydevice(struct sbus_dev *sdev)
-        {
-                struct mydevice *mp;
-                ...
-                mp->control_regs = sbus_ioremap(&sdev->resource[0], 0,
-                                        CONTROL_REGS_SIZE, "mydevice regs");
-                if (!mp->control_regs) {
-                        /* Failure, cleanup and return. */
-                }
-        }
-        Second argument to sbus_ioremap is an offset for
-cranky devices with broken OBP PROM. The sbus_ioremap uses only
-a start address and flags from the resource structure.
-Therefore it is possible to use the same resource to map
-several sets of registers or even to fabricate a resource
-structure if driver gets physical address from some private place.
-This practice is discouraged though. Use whatever OBP PROM
-provided to you.
-        And here is how you might unmap these registers later at
-driver shutdown or module unload time, using the sbus_iounmap
-interface:
-        static void mydevice_unmap_regs(struct mydevice *mp)
-        {
-                sbus_iounmap(mp->control_regs, CONTROL_REGS_SIZE);
-        }
-        Finally, to actually access your registers there are 6
-interface routines at your disposal.  Accesses are byte (8 bit),
-word (16 bit), or longword (32 bit) sized.  Here they are:
-        u8 sbus_readb(unsigned long reg)                /* read byte */
-        u16 sbus_readw(unsigned long reg)               /* read word */
-        u32 sbus_readl(unsigned long reg)               /* read longword */
-        void sbus_writeb(u8 value, unsigned long reg)   /* write byte */
-        void sbus_writew(u16 value, unsigned long reg)  /* write word */
-        void sbus_writel(u32 value, unsigned long reg)  /* write longword */
-        So, let's say your device has a control register of some sort
-at offset zero.  The following might implement resetting your device:
-        #define CONTROL         0x00UL
-        #define CONTROL_RESET   0x00000001      /* Reset hardware */
-        static void mydevice_reset(struct mydevice *mp)
-        {
-                sbus_writel(CONTROL_RESET, mp->regs + CONTROL);
-        }
-        Or perhaps there is a data port register at an offset of
-16 bytes which allows you to read bytes from a fifo in the device:
-        #define DATA            0x10UL
-        static u8 mydevice_get_byte(struct mydevice *mp)
-        {
-                return sbus_readb(mp->regs + DATA);
-        }
-        It's pretty straightforward, and clueful readers may have
-noticed that these interfaces mimick the PCI interfaces of the
-Linux kernel.  This was not by accident.
-        WARNING:
-                DO NOT try to treat these opaque register mapping
-                values as a memory mapped pointer to some structure
-                which you can dereference.
-                It may be memory mapped, it may not be.  In fact it
-                could be a physical address, or it could be the time
-                of day xor'd with 0xdeadbeef.  :-)
-                Whatever it is, it's an implementation detail.  The
-                interface was done this way to shield the driver
-                author from such complexities.
-                        Doing DVMA
-        SBUS devices can perform DMA transactions in a way similar
-to PCI but dissimilar to ISA, e.g. DMA masters supply address.
-In contrast to PCI, however, that address (a bus address) is
-translated by IOMMU before a memory access is performed and therefore
-it is virtual. Sun calls this procedure DVMA.
-        Linux supports two styles of using SBUS DVMA: "consistent memory"
-and "streaming DVMA". CPU view of consistent memory chunk is, well,
-consistent with a view of a device. Think of it as an uncached memory.
-Typically this way of doing DVMA is not very fast and drivers use it
-mostly for control blocks or queues. On some CPUs we cannot flush or
-invalidate individual pages or cache lines and doing explicit flushing
-over ever little byte in every control block would be wasteful.
-Streaming DVMA is a preferred way to transfer large amounts of data.
-This process works in the following way:
-1. a CPU stops accessing a certain part of memory,
-   flushes its caches covering that memory;
-2. a device does DVMA accesses, then posts an interrupt;
-3. CPU invalidates its caches and starts to access the memory.
-A single streaming DVMA operation can touch several discontiguous
-regions of a virtual bus address space. This is called a scatter-gather
-DVMA.
-[TBD: Why do not we neither Solaris attempt to map disjoint pages
-into a single virtual chunk with the help of IOMMU, so that non SG
-DVMA masters would do SG? It'd be very helpful for RAID.]
-        In order to perform a consistent DVMA a driver does something
-like the following:
-        char *mem;              /* Address in the CPU space */
-        u32 busa;               /* Address in the SBus space */
-        mem = (char *) sbus_alloc_consistent(sdev, MYMEMSIZE, &busa);
-        Then mem is used when CPU accesses this memory and u32
-is fed to the device so that it can do DVMA. This is typically
-done with an sbus_writel() into some device register.
-        Do not forget to free the DVMA resources once you are done:
-        sbus_free_consistent(sdev, MYMEMSIZE, mem, busa);
-        Streaming DVMA is more interesting. First you allocate some
-memory suitable for it or pin down some user pages. Then it all works
-like this:
-        char *mem = argumen1;
-        unsigned int size = argument2;
-        u32 busa;               /* Address in the SBus space */
-        *mem = 1;               /* CPU can access */
-        busa = sbus_map_single(sdev, mem, size);
-        if (busa == 0) .......
-        /* Tell the device to use busa here */
-        /* CPU cannot access the memory without sbus_dma_sync_single() */
-        sbus_unmap_single(sdev, busa, size);
-        if (*mem == 0) ....     /* CPU can access again */
-        It is possible to retain mappings and ask the device to
-access data again and again without calling sbus_unmap_single.
-However, CPU caches must be invalidated with sbus_dma_sync_single
-before such access.
-[TBD but what about writeback caches here... do we have any?]
-        There is an equivalent set of functions doing the same thing
-only with several memory segments at once for devices capable of
-scatter-gather transfers. Use the Source, Luke.
-                        Examples
-        drivers/net/sunhme.c
-        This is a complicated driver which illustrates many concepts
-discussed above and plus it handles both PCI and SBUS boards.
-        drivers/scsi/esp.c
-        Check it out for scatter-gather DVMA.
-        drivers/sbus/char/bpp.c
-        A non-DVMA device.
-        drivers/net/sunlance.c
-        Lance driver abuses consistent mappings for data transfer.
-It is a nifty trick which we do not particularly recommend...
-Just check it out and know that it's legal.
diff --git a/Documentation/sparse.txt b/Documentation/sparse.txt
index 1a3bdc27d95e..42f43fa59f24 100644
--- a/Documentation/sparse.txt
+++ b/Documentation/sparse.txt
@@ -73,10 +73,10 @@ recompiled, or use "make C=2" to run sparse on the files whether they need to
 be recompiled or not.  The latter is a fast way to check the whole tree if you
 have already built it.
-The optional make variable CHECKFLAGS can be used to pass arguments to sparse.
+The optional make variable CF can be used to pass arguments to sparse.  The
-The build system passes -Wbitwise to sparse automatically.  To perform
+build system passes -Wbitwise to sparse automatically.  To perform endianness
-endianness checks, you may define __CHECK_ENDIAN__:
+checks, you may define __CHECK_ENDIAN__:
-        make C=2 CHECKFLAGS="-D__CHECK_ENDIAN__"
+        make C=2 CF="-D__CHECK_ENDIAN__"
 These checks are disabled by default as they generate a host of warnings.
diff --git a/Documentation/specialix.txt b/Documentation/specialix.txt
index 4a4b428ce8f6..6eb6f3a3331c 100644
--- a/Documentation/specialix.txt
+++ b/Documentation/specialix.txt
@@ -270,8 +270,8 @@ The pinout of the connectors on the IO8+ is:
 Hardware handshaking issues.
 ============================
-The driver can be compiled in two different ways. The default
+The driver can be told to operate in two different ways. The default
-("Specialix DTR/RTS pin is RTS" is off) the pin behaves as DTR when
+behaviour is specialix.sx_rtscts = 0 where the pin behaves as DTR when
 hardware handshaking is off. It behaves as the RTS hardware
 handshaking signal when hardware handshaking is selected.
@@ -280,7 +280,7 @@ cable will either be compatible with hardware handshaking or with
 software handshaking. So switching on the fly is not really an
 option.
-I actually prefer to use the "Specialix DTR/RTS pin is RTS" option.
+I actually prefer to use the "specialix.sx_rtscts=1" option.
 This makes the DTR/RTS pin always an RTS pin, and ioctls to
 change DTR are always ignored. I have a cable that is configured
 for this. 
@@ -379,7 +379,5 @@ it doesn't fit in your computer, bring back the card.
            You have to WRITE to the address register to even 
            read-probe a CD186x register. Disable autodetection?
         -- Specialix: any suggestions?
-       - Arbitrary baud rates are not implemented yet. 
-            If you need this, bug me about it. 
diff --git a/Documentation/spi/Makefile b/Documentation/spi/Makefile
new file mode 100644
index 000000000000..a5b03c88beae
--- /dev/null
+++ b/Documentation/spi/Makefile
@@ -0,0 +1,11 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := spidev_test spidev_fdx
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+HOSTCFLAGS_spidev_test.o += -I$(objtree)/usr/include
+HOSTCFLAGS_spidev_fdx.o += -I$(objtree)/usr/include
diff --git a/Documentation/spi/pxa2xx b/Documentation/spi/pxa2xx
index f3853cc37bde..6bb916d57c95 100644
--- a/Documentation/spi/pxa2xx
+++ b/Documentation/spi/pxa2xx
@@ -19,7 +19,7 @@ Declaring PXA2xx Master Controllers
 -----------------------------------
 Typically a SPI master is defined in the arch/.../mach-*/board-*.c as a
 "platform device".  The master configuration is passed to the driver via a table
-found in include/asm-arm/arch-pxa/pxa2xx_spi.h:
+found in arch/arm/mach-pxa/include/mach/pxa2xx_spi.h:
 struct pxa2xx_spi_master {
        enum pxa_ssp_type ssp_type;
@@ -94,9 +94,9 @@ using the "spi_board_info" structure found in "linux/spi/spi.h". See
 Each slave device attached to the PXA must provide slave specific configuration
 information via the structure "pxa2xx_spi_chip" found in
-"include/asm-arm/arch-pxa/pxa2xx_spi.h".  The pxa2xx_spi master controller driver
+"arch/arm/mach-pxa/include/mach/pxa2xx_spi.h".  The pxa2xx_spi master controller driver
 will uses the configuration whenever the driver communicates with the slave
-device.
+device. All fields are optional.
 struct pxa2xx_spi_chip {
        u8 tx_threshold;
@@ -112,14 +112,17 @@ used to configure the SSP hardware fifo.  These fields are critical to the
 performance of pxa2xx_spi driver and misconfiguration will result in rx
 fifo overruns (especially in PIO mode transfers). Good default values are
-        .tx_threshold = 12,
+        .tx_threshold = 8,
-        .rx_threshold = 4,
+        .rx_threshold = 8,
+The range is 1 to 16 where zero indicates "use default".
 The "pxa2xx_spi_chip.dma_burst_size" field is used to configure PXA2xx DMA
 engine and is related the "spi_device.bits_per_word" field.  Read and understand
 the PXA2xx "Developer Manual" sections on the DMA controller and SSP Controllers
 to determine the correct value. An SSP configured for byte-wide transfers would
-use a value of 8.
+use a value of 8. The driver will determine a reasonable default if
+dma_burst_size == 0.
 The "pxa2xx_spi_chip.timeout" fields is used to efficiently handle
 trailing bytes in the SSP receiver fifo.  The correct value for this field is
@@ -137,7 +140,13 @@ function for asserting/deasserting a slave device chip select.  If the field is
 NULL, the pxa2xx_spi master controller driver assumes that the SSP port is
 configured to use SSPFRM instead.
-NSSP SALVE SAMPLE
+NOTE: the SPI driver cannot control the chip select if SSPFRM is used, so the
+chipselect is dropped after each spi_transfer.  Most devices need chip select
+asserted around the complete message.  Use SSPFRM as a GPIO (through cs_control)
+to accomodate these chips.
+NSSP SLAVE SAMPLE
 -----------------
 The pxa2xx_spi_chip structure is passed to the pxa2xx_spi driver in the
 "spi_board_info.controller_data" field. Below is a sample configuration using
@@ -206,18 +215,21 @@ static void __init streetracer_init(void)
 DMA and PIO I/O Support
 -----------------------
-The pxa2xx_spi driver support both DMA and interrupt driven PIO message
+The pxa2xx_spi driver supports both DMA and interrupt driven PIO message
-transfers.  The driver defaults to PIO mode and DMA transfers must enabled by
+transfers.  The driver defaults to PIO mode and DMA transfers must be enabled
-setting the "enable_dma" flag in the "pxa2xx_spi_master" structure and
+by setting the "enable_dma" flag in the "pxa2xx_spi_master" structure.  The DMA
-ensuring that the "pxa2xx_spi_chip.dma_burst_size" field is non-zero.  The DMA
+mode supports both coherent and stream based DMA mappings.
-mode support both coherent and stream based DMA mappings.
 The following logic is used to determine the type of I/O to be used on
 a per "spi_transfer" basis:
-if !enable_dma or dma_burst_size == 0 then
+if !enable_dma then
        always use PIO transfers
+if spi_message.len > 8191 then
+        print "rate limited" warning
+        use PIO transfers
 if spi_message.is_dma_mapped and rx_dma_buf != 0 and tx_dma_buf != 0 then
        use coherent DMA mode
diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary
index 6d5f18143c50..8bae2f018d34 100644
--- a/Documentation/spi/spi-summary
+++ b/Documentation/spi/spi-summary
@@ -210,7 +210,7 @@ board should normally be set up and registered.
 So for example arch/.../mach-*/board-*.c files might have code like:
-        #include <asm/arch/spi.h>       /* for mysoc_spi_data */
+        #include <mach/spi.h>   /* for mysoc_spi_data */
        /* if your mach-* infrastructure doesn't support kernels that can
         * run on multiple boards, pdata wouldn't benefit from "__init".
@@ -227,7 +227,7 @@ So for example arch/.../mach-*/board-*.c files might have code like:
 And SOC-specific utility code might look something like:
-        #include <asm/arch/spi.h>
+        #include <mach/spi.h>
        static struct platform_device spi2 = { ... };
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 276a7e637822..bde799e06598 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -351,9 +351,10 @@ kernel.  This value defaults to SHMMAX.
 softlockup_thresh:
-This value can be used to lower the softlockup tolerance
+This value can be used to lower the softlockup tolerance threshold.  The
-threshold. The default threshold is 10s.  If a cpu is locked up
+default threshold is 60 seconds.  If a cpu is locked up for 60 seconds,
-for 10s, the kernel complains.  Valid values are 1-60s.
+the kernel complains.  Valid values are 1-60 seconds.  Setting this
+tunable to zero will disable the softlockup detection altogether.
 ==============================================================
@@ -368,4 +369,5 @@ can be ORed together:
  2 - A module was force loaded by insmod -f.
      Set by modutils >= 2.4.9 and module-init-tools.
  4 - Unsafe SMP processors: SMP with CPUs not designed for SMP.
+ 64 - A module from drivers/staging was loaded.
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 8a4863c4edd4..d79eeda7a699 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -116,7 +116,7 @@ of kilobytes free.  The VM uses this number to compute a pages_min
 value for each lowmem zone in the system.  Each lowmem zone gets 
 a number of reserved free pages based proportionally on its size.
-Some minimal ammount of memory is needed to satisfy PF_MEMALLOC
+Some minimal amount of memory is needed to satisfy PF_MEMALLOC
 allocations; if you set this to lower than 1024KB, your system will
 become subtly broken, and prone to deadlock under high loads.
diff --git a/Documentation/sysfs-rules.txt b/Documentation/sysfs-rules.txt
index 80ef562160bb..6049a2a84dda 100644
--- a/Documentation/sysfs-rules.txt
+++ b/Documentation/sysfs-rules.txt
@@ -3,9 +3,8 @@ Rules on how to access information in the Linux kernel sysfs
 The kernel-exported sysfs exports internal kernel implementation details
 and depends on internal kernel structures and layout. It is agreed upon
 by the kernel developers that the Linux kernel does not provide a stable
-internal API. As sysfs is a direct export of kernel internal
+internal API. Therefore, there are aspects of the sysfs interface that
-structures, the sysfs interface cannot provide a stable interface either;
+may not be stable across kernel releases.
-it may always change along with internal kernel changes.
 To minimize the risk of breaking users of sysfs, which are in most cases
 low-level userspace applications, with a new kernel release, the users
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 5ce0952aa065..10a0263ebb3f 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -95,7 +95,9 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'p'     - Will dump the current registers and flags to your console.
-'q'     - Will dump a list of all running timers.
+'q'     - Will dump per CPU lists of all armed hrtimers (but NOT regular
+          timer_list timers) and detailed information about all
+          clockevent devices.
 'r'     - Turns off keyboard raw mode and sets it to XLATE.
diff --git a/Documentation/telephony/ixj.txt b/Documentation/telephony/ixj.txt
index 621024fd3a18..44d124005bad 100644
--- a/Documentation/telephony/ixj.txt
+++ b/Documentation/telephony/ixj.txt
@@ -305,21 +305,14 @@ driver, like this:
 which will result in the needed drivers getting loaded automatically.
-   g.  if you are planning on using kerneld to automatically load the 
+   g.  if you are planning on having the kernel automatically request
-module for you, then you need to edit /etc/conf.modules and add the 
+the module for you, then you need to edit /etc/conf.modules and add the
 following lines:
        options ixj dspio=0x340 xio=0x330 ixjdebug=0
 If you do this, then when you execute an application that uses the
-module kerneld will load the module for you.  Note that to do this,
+module the kernel will request that it is loaded.
-you need to have your kernel set to support kerneld.  You can check
-for this by looking at /usr/src/linux/.config and you should see this:
-        # Loadable module support
-        #
-        <snip>
-        CONFIG_KMOD=y
  h.  if you want non-root users to be able to read and write to the 
 ixj devices (this is a good idea!) you should do the following:
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
new file mode 100644
index 000000000000..397dc35e1323
--- /dev/null
+++ b/Documentation/timers/00-INDEX
@@ -0,0 +1,10 @@
+00-INDEX
+        - this file
+highres.txt
+        - High resolution timers and dynamic ticks design notes
+hpet.txt
+        - High Precision Event Timer Driver for Linux
+hrtimers.txt
+        - subsystem for high-resolution kernel timers
+timer_stats.txt
+        - timer usage statistics
diff --git a/Documentation/timers/highres.txt b/Documentation/timers/highres.txt
index a73ecf5b4bdb..21332233cef1 100644
--- a/Documentation/timers/highres.txt
+++ b/Documentation/timers/highres.txt
@@ -125,7 +125,7 @@ increase of flexibility and the avoidance of duplicated code across
 architectures justifies the slight increase of the binary size.
 The conversion of an architecture has no functional impact, but allows to
-utilize the high resolution and dynamic tick functionalites without any change
+utilize the high resolution and dynamic tick functionalities without any change
 to the clock event device and timer interrupt code. After the conversion the
 enabling of high resolution timers and dynamic ticks is simply provided by
 adding the kernel/time/Kconfig file to the architecture specific Kconfig and
diff --git a/Documentation/hpet.txt b/Documentation/timers/hpet.txt
index 6ad52d9dad6c..e7c09abcfab4 100644
--- a/Documentation/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -1,21 +1,32 @@
                High Precision Event Timer Driver for Linux
-The High Precision Event Timer (HPET) hardware is the future replacement
+The High Precision Event Timer (HPET) hardware follows a specification
-for the 8254 and Real Time Clock (RTC) periodic timer functionality.
+by Intel and Microsoft which can be found at
-Each HPET can have up to 32 timers.  It is possible to configure the
-first two timers as legacy replacements for 8254 and RTC periodic timers.
+        http://www.intel.com/technology/architecture/hpetspec.htm
-A specification done by Intel and Microsoft can be found at
-<http://www.intel.com/technology/architecture/hpetspec.htm>.
+Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
+and up to 32 comparators.  Normally three or more comparators are provided,
+each of which can generate oneshot interupts and at least one of which has
+additional hardware to support periodic interrupts.  The comparators are
+also called "timers", which can be misleading since usually timers are
+independent of each other ... these share a counter, complicating resets.
+HPET devices can support two interrupt routing modes.  In one mode, the
+comparators are additional interrupt sources with no particular system
+role.  Many x86 BIOS writers don't route HPET interrupts at all, which
+prevents use of that mode.  They support the other "legacy replacement"
+mode where the first two comparators block interrupts from 8254 timers
+and from the RTC.
 The driver supports detection of HPET driver allocation and initialization
 of the HPET before the driver module_init routine is called.  This enables
 platform code which uses timer 0 or 1 as the main timer to intercept HPET
 initialization.  An example of this initialization can be found in
-arch/i386/kernel/time_hpet.c.
+arch/x86/kernel/hpet.c.
-The driver provides two APIs which are very similar to the API found in
+The driver provides a userspace API which resembles the API found in the
-the rtc.c driver.  There is a user space API and a kernel space API.
+RTC driver framework.  An example user space program is provided below.
-An example user space program is provided below.
 #include <stdio.h>
 #include <stdlib.h>
@@ -286,15 +297,3 @@ out:
        return;
 }
-The kernel API has three interfaces exported from the driver:
-        hpet_register(struct hpet_task *tp, int periodic)
-        hpet_unregister(struct hpet_task *tp)
-        hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg)
-The kernel module using this interface fills in the ht_func and ht_data
-members of the hpet_task structure before calling hpet_register.
-hpet_control simply vectors to the hpet_ioctl routine and has the same
-commands and respective arguments as the user API.  hpet_unregister
-is used to terminate usage of the HPET timer reserved by hpet_register.
diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt
new file mode 100644
index 000000000000..5d354e167494
--- /dev/null
+++ b/Documentation/tracepoints.txt
@@ -0,0 +1,101 @@
+                     Using the Linux Kernel Tracepoints
+                            Mathieu Desnoyers
+This document introduces Linux Kernel Tracepoints and their use. It provides
+examples of how to insert tracepoints in the kernel and connect probe functions
+to them and provides some examples of probe functions.
+* Purpose of tracepoints
+A tracepoint placed in code provides a hook to call a function (probe) that you
+can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
+"off" (no probe is attached). When a tracepoint is "off" it has no effect,
+except for adding a tiny time penalty (checking a condition for a branch) and
+space penalty (adding a few bytes for the function call at the end of the
+instrumented function and adds a data structure in a separate section).  When a
+tracepoint is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function provided
+ends its execution, it returns to the caller (continuing from the tracepoint
+site).
+You can put tracepoints at important locations in the code. They are
+lightweight hooks that can pass an arbitrary number of parameters,
+which prototypes are described in a tracepoint declaration placed in a header
+file.
+They can be used for tracing and performance accounting.
+* Usage
+Two elements are required for tracepoints :
+- A tracepoint definition, placed in a header file.
+- The tracepoint statement, in C code.
+In order to use tracepoints, you should include linux/tracepoint.h.
+In include/trace/subsys.h :
+#include <linux/tracepoint.h>
+DEFINE_TRACE(subsys_eventname,
+        TPPTOTO(int firstarg, struct task_struct *p),
+        TPARGS(firstarg, p));
+In subsys/file.c (where the tracing statement must be added) :
+#include <trace/subsys.h>
+void somefct(void)
+{
+        ...
+        trace_subsys_eventname(arg, task);
+        ...
+}
+Where :
+- subsys_eventname is an identifier unique to your event
+    - subsys is the name of your subsystem.
+    - eventname is the name of the event to trace.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
+  called by this tracepoint.
+- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
+Connecting a function (probe) to a tracepoint is done by providing a probe
+(function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe sure there is no
+caller left using the probe when it returns. Probe removal is preempt-safe
+because preemption is disabled around the probe call. See the "Probe example"
+section below for a sample probe module.
+The tracepoint mechanism supports inserting multiple instances of the same
+tracepoint, but a single definition must be made of a given tracepoint name over
+all the kernel to make sure no type conflict will occur. Name mangling of the
+tracepoints is done using the prototypes to make sure typing is correct.
+Verification of probe type correctness is done at the registration site by the
+compiler. Tracepoints can be put in inline functions, inlined static functions,
+and unrolled loops as well as regular functions.
+The naming scheme "subsys_event" is suggested here as a convention intended
+to limit collisions. Tracepoint names are global to the kernel: they are
+considered as being the same whether they are in the core kernel image or in
+modules.
+* Probe / tracepoint example
+See the example provided in samples/tracepoints/src
+Compile them with your kernel.
+Run, as root :
+modprobe tracepoint-example (insmod order is not important)
+modprobe tracepoint-probe-example
+cat /proc/tracepoint-example (returns an expected error)
+rmmod tracepoint-example tracepoint-probe-example
+dmesg
diff --git a/Documentation/tracers/mmiotrace.txt b/Documentation/tracers/mmiotrace.txt
index a4afb560a45b..5bbbe2096223 100644
--- a/Documentation/tracers/mmiotrace.txt
+++ b/Documentation/tracers/mmiotrace.txt
@@ -36,7 +36,7 @@ $ mount -t debugfs debugfs /debug
 $ echo mmiotrace > /debug/tracing/current_tracer
 $ cat /debug/tracing/trace_pipe > mydump.txt &
 Start X or whatever.
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 $ echo none > /debug/tracing/current_tracer
 Check for lost events.
@@ -59,9 +59,8 @@ The 'cat' process should stay running (sleeping) in the background.
 Load the driver you want to trace and use it. Mmiotrace will only catch MMIO
 accesses to areas that are ioremapped while mmiotrace is active.
-[Unimplemented feature:]
 During tracing you can place comments (markers) into the trace by
-$ echo "X is up" > /debug/tracing/marker
+$ echo "X is up" > /debug/tracing/trace_marker
 This makes it easier to see which part of the (huge) trace corresponds to
 which action. It is recommended to place descriptive markers about what you
 do.
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index b0472ac5226a..f866c72291bf 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -218,9 +218,35 @@ If use of such macros is not convenient, another option is to use memcpy(),
 where the source or destination (or both) are of type u8* or unsigned char*.
 Due to the byte-wise nature of this operation, unaligned accesses are avoided.
+Alignment vs. Networking
+========================
+On architectures that require aligned loads, networking requires that the IP
+header is aligned on a four-byte boundary to optimise the IP stack. For
+regular ethernet hardware, the constant NET_IP_ALIGN is used. On most
+architectures this constant has the value 2 because the normal ethernet
+header is 14 bytes long, so in order to get proper alignment one needs to
+DMA to an address which can be expressed as 4*n + 2. One notable exception
+here is powerpc which defines NET_IP_ALIGN to 0 because DMA to unaligned
+addresses can be very expensive and dwarf the cost of unaligned loads.
+For some ethernet hardware that cannot DMA to unaligned addresses like
+4*n+2 or non-ethernet hardware, this can be a problem, and it is then
+required to copy the incoming frame into an aligned buffer. Because this is
+unnecessary on architectures that can do unaligned accesses, the code can be
+made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so:
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+        skb = original skb
+#else
+        skb = copy skb
+#endif
 --
-Author: Daniel Drake <dsd@gentoo.org>
+Authors: Daniel Drake <dsd@gentoo.org>,
+         Johannes Berg <johannes@sipsolutions.net>
 With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt,
-Johannes Berg, Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock,
+Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz,
-Uli Kunitz, Vadim Lobanov
+Vadim Lobanov
diff --git a/Documentation/usb/WUSB-Design-overview.txt b/Documentation/usb/WUSB-Design-overview.txt
new file mode 100644
index 000000000000..4c3d62c7843a
--- /dev/null
+++ b/Documentation/usb/WUSB-Design-overview.txt
@@ -0,0 +1,448 @@
+Linux UWB + Wireless USB + WiNET
+   (C) 2005-2006 Intel Corporation
+   Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+   This program is free software; you can redistribute it and/or
+   modify it under the terms of the GNU General Public License version
+   2 as published by the Free Software Foundation.
+   This program is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+   You should have received a copy of the GNU General Public License
+   along with this program; if not, write to the Free Software
+   Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+   02110-1301, USA.
+Please visit http://bughost.org/thewiki/Design-overview.txt-1.8 for
+updated content.
+    * Design-overview.txt-1.8
+This code implements a Ultra Wide Band stack for Linux, as well as
+drivers for the the USB based UWB radio controllers defined in the
+Wireless USB 1.0 specification (including Wireless USB host controller
+and an Intel WiNET controller).
+   1. Introduction
+         1. HWA: Host Wire adapters, your Wireless USB dongle
+         2. DWA: Device Wired Adaptor, a Wireless USB hub for wired
+            devices
+         3. WHCI: Wireless Host Controller Interface, the PCI WUSB host
+            adapter
+   2. The UWB stack
+         1. Devices and hosts: the basic structure
+         2. Host Controller life cycle
+         3. On the air: beacons and enumerating the radio neighborhood
+         4. Device lists
+         5. Bandwidth allocation
+   3. Wireless USB Host Controller drivers
+   4. Glossary
+    Introduction
+UWB is a wide-band communication protocol that is to serve also as the
+low-level protocol for others (much like TCP sits on IP). Currently
+these others are Wireless USB and TCP/IP, but seems Bluetooth and
+Firewire/1394 are coming along.
+UWB uses a band from roughly 3 to 10 GHz, transmitting at a max of
+~-41dB (or 0.074 uW/MHz--geography specific data is still being
+negotiated w/ regulators, so watch for changes). That band is divided in
+a bunch of ~1.5 GHz wide channels (or band groups) composed of three
+subbands/subchannels (528 MHz each). Each channel is independent of each
+other, so you could consider them different "busses". Initially this
+driver considers them all a single one.
+Radio time is divided in 65536 us long /superframes/, each one divided
+in 256 256us long /MASs/ (Media Allocation Slots), which are the basic
+time/media allocation units for transferring data. At the beginning of
+each superframe there is a Beacon Period (BP), where every device
+transmit its beacon on a single MAS. The length of the BP depends on how
+many devices are present and the length of their beacons.
+Devices have a MAC (fixed, 48 bit address) and a device (changeable, 16
+bit address) and send periodic beacons to advertise themselves and pass
+info on what they are and do. They advertise their capabilities and a
+bunch of other stuff.
+The different logical parts of this driver are:
+    *
+      *UWB*: the Ultra-Wide-Band stack -- manages the radio and
+      associated spectrum to allow for devices sharing it. Allows to
+      control bandwidth assingment, beaconing, scanning, etc
+    *
+      *WUSB*: the layer that sits on top of UWB to provide Wireless USB.
+      The Wireless USB spec defines means to control a UWB radio and to
+      do the actual WUSB.
+      HWA: Host Wire adapters, your Wireless USB dongle
+WUSB also defines a device called a Host Wire Adaptor (HWA), which in
+mere terms is a USB dongle that enables your PC to have UWB and Wireless
+USB. The Wireless USB Host Controller in a HWA looks to the host like a
+[Wireless] USB controller connected via USB (!)
+The HWA itself is broken in two or three main interfaces:
+    *
+      *RC*: Radio control -- this implements an interface to the
+      Ultra-Wide-Band radio controller. The driver for this implements a
+      USB-based UWB Radio Controller to the UWB stack.
+    *
+      *HC*: the wireless USB host controller. It looks like a USB host
+      whose root port is the radio and the WUSB devices connect to it.
+      To the system it looks like a separate USB host. The driver (will)
+      implement a USB host controller (similar to UHCI, OHCI or EHCI)
+      for which the root hub is the radio...To reiterate: it is a USB
+      controller that is connected via USB instead of PCI.
+    *
+      *WINET*: some HW provide a WiNET interface (IP over UWB). This
+      package provides a driver for it (it looks like a network
+      interface, winetX). The driver detects when there is a link up for
+      their type and kick into gear.
+      DWA: Device Wired Adaptor, a Wireless USB hub for wired devices
+These are the complement to HWAs. They are a USB host for connecting
+wired devices, but it is connected to your PC connected via Wireless
+USB. To the system it looks like yet another USB host. To the untrained
+eye, it looks like a hub that connects upstream wirelessly.
+We still offer no support for this; however, it should share a lot of
+code with the HWA-RC driver; there is a bunch of factorization work that
+has been done to support that in upcoming releases.
+      WHCI: Wireless Host Controller Interface, the PCI WUSB host adapter
+This is your usual PCI device that implements WHCI. Similar in concept
+to EHCI, it allows your wireless USB devices (including DWAs) to connect
+to your host via a PCI interface. As in the case of the HWA, it has a
+Radio Control interface and the WUSB Host Controller interface per se.
+There is still no driver support for this, but will be in upcoming
+releases.
+    The UWB stack
+The main mission of the UWB stack is to keep a tally of which devices
+are in radio proximity to allow drivers to connect to them. As well, it
+provides an API for controlling the local radio controllers (RCs from
+now on), such as to start/stop beaconing, scan, allocate bandwidth, etc.
+      Devices and hosts: the basic structure
+The main building block here is the UWB device (struct uwb_dev). For
+each device that pops up in radio presence (ie: the UWB host receives a
+beacon from it) you get a struct uwb_dev that will show up in
+/sys/class/uwb and in /sys/bus/uwb/devices.
+For each RC that is detected, a new struct uwb_rc is created. In turn, a
+RC is also a device, so they also show in /sys/class/uwb and
+/sys/bus/uwb/devices, but at the same time, only radio controllers show
+up in /sys/class/uwb_rc.
+    *
+      [*] The reason for RCs being also devices is that not only we can
+      see them while enumerating the system device tree, but also on the
+      radio (their beacons and stuff), so the handling has to be
+      likewise to that of a device.
+Each RC driver is implemented by a separate driver that plugs into the
+interface that the UWB stack provides through a struct uwb_rc_ops. The
+spec creators have been nice enough to make the message format the same
+for HWA and WHCI RCs, so the driver is really a very thin transport that
+moves the requests from the UWB API to the device [/uwb_rc_ops->cmd()/]
+and sends the replies and notifications back to the API
+[/uwb_rc_neh_grok()/]. Notifications are handled to the UWB daemon, that
+is chartered, among other things, to keep the tab of how the UWB radio
+neighborhood looks, creating and destroying devices as they show up or
+dissapear.
+Command execution is very simple: a command block is sent and a event
+block or reply is expected back. For sending/receiving command/events, a
+handle called /neh/ (Notification/Event Handle) is opened with
+/uwb_rc_neh_open()/.
+The HWA-RC (USB dongle) driver (drivers/uwb/hwa-rc.c) does this job for
+the USB connected HWA. Eventually, drivers/whci-rc.c will do the same
+for the PCI connected WHCI controller.
+      Host Controller life cycle
+So let's say we connect a dongle to the system: it is detected and
+firmware uploaded if needed [for Intel's i1480
+/drivers/uwb/ptc/usb.c:ptc_usb_probe()/] and then it is reenumerated.
+Now we have a real HWA device connected and
+/drivers/uwb/hwa-rc.c:hwarc_probe()/ picks it up, that will set up the
+Wire-Adaptor environment and then suck it into the UWB stack's vision of
+the world [/drivers/uwb/lc-rc.c:uwb_rc_add()/].
+    *
+      [*] The stack should put a new RC to scan for devices
+      [/uwb_rc_scan()/] so it finds what's available around and tries to
+      connect to them, but this is policy stuff and should be driven
+      from user space. As of now, the operator is expected to do it
+      manually; see the release notes for documentation on the procedure.
+When a dongle is disconnected, /drivers/uwb/hwa-rc.c:hwarc_disconnect()/
+takes time of tearing everything down safely (or not...).
+      On the air: beacons and enumerating the radio neighborhood
+So assuming we have devices and we have agreed for a channel to connect
+on (let's say 9), we put the new RC to beacon:
+    *
+            $ echo 9 0 > /sys/class/uwb_rc/uwb0/beacon
+Now it is visible. If there were other devices in the same radio channel
+and beacon group (that's what the zero is for), the dongle's radio
+control interface will send beacon notifications on its
+notification/event endpoint (NEEP). The beacon notifications are part of
+the event stream that is funneled into the API with
+/drivers/uwb/neh.c:uwb_rc_neh_grok()/ and delivered to the UWBD, the UWB
+daemon through a notification list.
+UWBD wakes up and scans the event list; finds a beacon and adds it to
+the BEACON CACHE (/uwb_beca/). If he receives a number of beacons from
+the same device, he considers it to be 'onair' and creates a new device
+[/drivers/uwb/lc-dev.c:uwbd_dev_onair()/]. Similarly, when no beacons
+are received in some time, the device is considered gone and wiped out
+[uwbd calls periodically /uwb/beacon.c:uwb_beca_purge()/ that will purge
+the beacon cache of dead devices].
+      Device lists
+All UWB devices are kept in the list of the struct bus_type uwb_bus.
+      Bandwidth allocation
+The UWB stack maintains a local copy of DRP availability through
+processing of incoming *DRP Availability Change* notifications. This
+local copy is currently used to present the current bandwidth
+availability to the user through the sysfs file
+/sys/class/uwb_rc/uwbx/bw_avail. In the future the bandwidth
+availability information will be used by the bandwidth reservation
+routines.
+The bandwidth reservation routines are in progress and are thus not
+present in the current release. When completed they will enable a user
+to initiate DRP reservation requests through interaction with sysfs. DRP
+reservation requests from remote UWB devices will also be handled. The
+bandwidth management done by the UWB stack will include callbacks to the
+higher layers will enable the higher layers to use the reservations upon
+completion. [Note: The bandwidth reservation work is in progress and
+subject to change.]
+    Wireless USB Host Controller drivers
+*WARNING* This section needs a lot of work!
+As explained above, there are three different types of HCs in the WUSB
+world: HWA-HC, DWA-HC and WHCI-HC.
+HWA-HC and DWA-HC share that they are Wire-Adapters (USB or WUSB
+connected controllers), and their transfer management system is almost
+identical. So is their notification delivery system.
+HWA-HC and WHCI-HC share that they are both WUSB host controllers, so
+they have to deal with WUSB device life cycle and maintenance, wireless
+root-hub
+HWA exposes a Host Controller interface (HWA-HC 0xe0/02/02). This has
+three endpoints (Notifications, Data Transfer In and Data Transfer
+Out--known as NEP, DTI and DTO in the code).
+We reserve UWB bandwidth for our Wireless USB Cluster, create a Cluster
+ID and tell the HC to use all that. Then we start it. This means the HC
+starts sending MMCs.
+    *
+      The MMCs are blocks of data defined somewhere in the WUSB1.0 spec
+      that define a stream in the UWB channel time allocated for sending
+      WUSB IEs (host to device commands/notifications) and Device
+      Notifications (device initiated to host). Each host defines a
+      unique Wireless USB cluster through MMCs. Devices can connect to a
+      single cluster at the time. The IEs are Information Elements, and
+      among them are the bandwidth allocations that tell each device
+      when can they transmit or receive.
+Now it all depends on external stimuli.
+*New device connection*
+A new device pops up, it scans the radio looking for MMCs that give out
+the existence of Wireless USB channels. Once one (or more) are found,
+selects which one to connect to. Sends a /DN_Connect/ (device
+notification connect) during the DNTS (Device Notification Time
+Slot--announced in the MMCs
+HC picks the /DN_Connect/ out (nep module sends to notif.c for delivery
+into /devconnect/). This process starts the authentication process for
+the device. First we allocate a /fake port/ and assign an
+unauthenticated address (128 to 255--what we really do is
+0x80 | fake_port_idx). We fiddle with the fake port status and /khubd/
+sees a new connection, so he moves on to enable the fake port with a reset.
+So now we are in the reset path -- we know we have a non-yet enumerated
+device with an unauthorized address; we ask user space to authenticate
+(FIXME: not yet done, similar to bluetooth pairing), then we do the key
+exchange (FIXME: not yet done) and issue a /set address 0/ to bring the
+device to the default state. Device is authenticated.
+From here, the USB stack takes control through the usb_hcd ops. khubd
+has seen the port status changes, as we have been toggling them. It will
+start enumerating and doing transfers through usb_hcd->urb_enqueue() to
+read descriptors and move our data.
+*Device life cycle and keep alives*
+Everytime there is a succesful transfer to/from a device, we update a
+per-device activity timestamp. If not, every now and then we check and
+if the activity timestamp gets old, we ping the device by sending it a
+Keep Alive IE; it responds with a /DN_Alive/ pong during the DNTS (this
+arrives to us as a notification through
+devconnect.c:wusb_handle_dn_alive(). If a device times out, we
+disconnect it from the system (cleaning up internal information and
+toggling the bits in the fake hub port, which kicks khubd into removing
+the rest of the stuff).
+This is done through devconnect:__wusb_check_devs(), which will scan the
+device list looking for whom needs refreshing.
+If the device wants to disconnect, it will either die (ugly) or send a
+/DN_Disconnect/ that will prompt a disconnection from the system.
+*Sending and receiving data*
+Data is sent and received through /Remote Pipes/ (rpipes). An rpipe is
+/aimed/ at an endpoint in a WUSB device. This is the same for HWAs and
+DWAs.
+Each HC has a number of rpipes and buffers that can be assigned to them;
+when doing a data transfer (xfer), first the rpipe has to be aimed and
+prepared (buffers assigned), then we can start queueing requests for
+data in or out.
+Data buffers have to be segmented out before sending--so we send first a
+header (segment request) and then if there is any data, a data buffer
+immediately after to the DTI interface (yep, even the request). If our
+buffer is bigger than the max segment size, then we just do multiple
+requests.
+[This sucks, because doing USB scatter gatter in Linux is resource
+intensive, if any...not that the current approach is not. It just has to
+be cleaned up a lot :)].
+If reading, we don't send data buffers, just the segment headers saying
+we want to read segments.
+When the xfer is executed, we receive a notification that says data is
+ready in the DTI endpoint (handled through
+xfer.c:wa_handle_notif_xfer()). In there we read from the DTI endpoint a
+descriptor that gives us the status of the transfer, its identification
+(given when we issued it) and the segment number. If it was a data read,
+we issue another URB to read into the destination buffer the chunk of
+data coming out of the remote endpoint. Done, wait for the next guy. The
+callbacks for the URBs issued from here are the ones that will declare
+the xfer complete at some point and call it's callback.
+Seems simple, but the implementation is not trivial.
+    *
+      *WARNING* Old!!
+The main xfer descriptor, wa_xfer (equivalent to a URB) contains an
+array of segments, tallys on segments and buffers and callback
+information. Buried in there is a lot of URBs for executing the segments
+and buffer transfers.
+For OUT xfers, there is an array of segments, one URB for each, another
+one of buffer URB. When submitting, we submit URBs for segment request
+1, buffer 1, segment 2, buffer 2...etc. Then we wait on the DTI for xfer
+result data; when all the segments are complete, we call the callback to
+finalize the transfer.
+For IN xfers, we only issue URBs for the segments we want to read and
+then wait for the xfer result data.
+*URB mapping into xfers*
+This is done by hwahc_op_urb_[en|de]queue(). In enqueue() we aim an
+rpipe to the endpoint where we have to transmit, create a transfer
+context (wa_xfer) and submit it. When the xfer is done, our callback is
+called and we assign the status bits and release the xfer resources.
+In dequeue() we are basically cancelling/aborting the transfer. We issue
+a xfer abort request to the HC, cancell all the URBs we had submitted
+and not yet done and when all that is done, the xfer callback will be
+called--this will call the URB callback.
+    Glossary
+*DWA* -- Device Wire Adapter
+USB host, wired for downstream devices, upstream connects wirelessly
+with Wireless USB.
+*EVENT* -- Response to a command on the NEEP
+*HWA* -- Host Wire Adapter / USB dongle for UWB and Wireless USB
+*NEH* -- Notification/Event Handle
+Handle/file descriptor for receiving notifications or events. The WA
+code requires you to get one of this to listen for notifications or
+events on the NEEP.
+*NEEP* -- Notification/Event EndPoint
+Stuff related to the management of the first endpoint of a HWA USB
+dongle that is used to deliver an stream of events and notifications to
+the host.
+*NOTIFICATION* -- Message coming in the NEEP as response to something.
+*RC* -- Radio Control
+Design-overview.txt-1.8 (last edited 2006-11-04 12:22:24 by
+InakyPerezGonzalez)
diff --git a/Documentation/usb/anchors.txt b/Documentation/usb/anchors.txt
index 7304bcf5a306..6f24f566955a 100644
--- a/Documentation/usb/anchors.txt
+++ b/Documentation/usb/anchors.txt
@@ -42,9 +42,38 @@ This function kills all URBs associated with an anchor. The URBs
 are called in the reverse temporal order they were submitted.
 This way no data can be reordered.
+usb_unlink_anchored_urbs()
+--------------------------
+This function unlinks all URBs associated with an anchor. The URBs
+are processed in the reverse temporal order they were submitted.
+This is similar to usb_kill_anchored_urbs(), but it will not sleep.
+Therefore no guarantee is made that the URBs have been unlinked when
+the call returns. They may be unlinked later but will be unlinked in
+finite time.
+usb_scuttle_anchored_urbs()
+---------------------------
+All URBs of an anchor are unanchored en masse.
 usb_wait_anchor_empty_timeout()
 -------------------------------
 This function waits for all URBs associated with an anchor to finish
 or a timeout, whichever comes first. Its return value will tell you
 whether the timeout was reached.
+usb_anchor_empty()
+------------------
+Returns true if no URBs are associated with an anchor. Locking
+is the caller's responsibility.
+usb_get_from_anchor()
+---------------------
+Returns the oldest anchored URB of an anchor. The URB is unanchored
+and returned with a reference. As you may mix URBs to several
+destinations in one anchor you have no guarantee the chronologically
+first submitted URB is returned.
+\ No newline at end of file
diff --git a/Documentation/usb/auerswald.txt b/Documentation/usb/auerswald.txt
deleted file mode 100644
index 7ee4d8f69116..000000000000
--- a/Documentation/usb/auerswald.txt
+++ /dev/null
@@ -1,30 +0,0 @@
-                Auerswald USB kernel driver
-                ===========================
-What is it? What can I do with it?
-==================================
-The auerswald USB kernel driver connects your linux 2.4.x
-system to the auerswald usb-enabled devices.
-There are two types of auerswald usb devices:
-a) small PBX systems (ISDN)
-b) COMfort system telephones (ISDN)
-The driver installation creates the devices
-/dev/usb/auer0..15. These devices carry a vendor-
-specific protocol. You may run all auerswald java
-software on it. The java software needs a native
-library "libAuerUsbJNINative.so" installed on
-your system. This library is available from
-auerswald and shipped as part of the java software.
-You may create the devices with:
-        mknod -m 666 /dev/usb/auer0 c 180 112
-        ...
-        mknod -m 666 /dev/usb/auer15 c 180 127
-Future plans
-============
- Connection to ISDN4LINUX (the hisax interface)
-The maintainer of this driver is wolfgang@iksw-muees.de
diff --git a/Documentation/usb/authorization.txt b/Documentation/usb/authorization.txt
index 2af400609498..381b22ee7834 100644
--- a/Documentation/usb/authorization.txt
+++ b/Documentation/usb/authorization.txt
@@ -8,7 +8,7 @@ not) in a system. This feature will allow you to implement a lock-down
 of USB devices, fully controlled by user space.
 As of now, when a USB device is connected it is configured and
-it's interfaces inmediately made available to the users. With this
+its interfaces are immediately made available to the users.  With this
 modification, only if root authorizes the device to be configured will
 then it be possible to use it.
diff --git a/Documentation/usb/gadget_serial.txt b/Documentation/usb/gadget_serial.txt
index 815f5c2301ff..9b22bd14c348 100644
--- a/Documentation/usb/gadget_serial.txt
+++ b/Documentation/usb/gadget_serial.txt
@@ -1,6 +1,7 @@
                 Linux Gadget Serial Driver v2.0
                           11/20/2004
+                  (updated 8-May-2008 for v2.3)
 License and Disclaimer
@@ -31,7 +32,7 @@ Prerequisites
 -------------
 Versions of the gadget serial driver are available for the
 2.4 Linux kernels, but this document assumes you are using
-version 2.0 or later of the gadget serial driver in a 2.6
+version 2.3 or later of the gadget serial driver in a 2.6
 Linux kernel.
 This document assumes that you are familiar with Linux and
@@ -40,6 +41,12 @@ standard utilities, use minicom and HyperTerminal, and work with
 USB and serial devices.  It also assumes you configure the Linux
 gadget and usb drivers as modules.
+With version 2.3 of the driver, major and minor device nodes are
+no longer statically defined.  Your Linux based system should mount
+sysfs in /sys, and use "mdev" (in Busybox) or "udev" to make the
+/dev nodes matching the sysfs /sys/class/tty files.
 Overview
 --------
@@ -104,15 +111,8 @@ driver.  All this are listed under "USB Gadget Support" when
 configuring the kernel.  Then rebuild and install the kernel or
 modules.
-The gadget serial driver uses major number 127, for now.  So you
-will need to create a device node for it, like this:
-  mknod /dev/ttygserial c 127 0
-You only need to do this once.
 Then you must load the gadget serial driver.  To load it as an
-ACM device, do this:
+ACM device (recommended for interoperability), do this:
  modprobe g_serial use_acm=1
@@ -125,6 +125,23 @@ controller driver.  This must be done each time you reboot the gadget
 side Linux system.  You can add this to the start up scripts, if
 desired.
+Your system should use mdev (from busybox) or udev to make the
+device nodes.  After this gadget driver has been set up you should
+then see a /dev/ttyGS0 node:
+  # ls -l /dev/ttyGS0 | cat
+  crw-rw----    1 root     root     253,   0 May  8 14:10 /dev/ttyGS0
+  #
+Note that the major number (253, above) is system-specific.  If
+you need to create /dev nodes by hand, the right numbers to use
+will be in the /sys/class/tty/ttyGS0/dev file.
+When you link this gadget driver early, perhaps even statically,
+you may want to set up an /etc/inittab entry to run "getty" on it.
+The /dev/ttyGS0 line should work like most any other serial port.
 If gadget serial is loaded as an ACM device you will want to use
 either the Windows or Linux ACM driver on the host side.  If gadget
 serial is loaded as a bulk in/out device, you will want to use the
diff --git a/Documentation/usb/misc_usbsevseg.txt b/Documentation/usb/misc_usbsevseg.txt
new file mode 100644
index 000000000000..0f6be4f9930b
--- /dev/null
+++ b/Documentation/usb/misc_usbsevseg.txt
@@ -0,0 +1,46 @@
+USB 7-Segment Numeric Display
+Manufactured by Delcom Engineering
+Device Information
+------------------
+USB VENDOR_ID   0x0fc5
+USB PRODUCT_ID  0x1227
+Both the 6 character and 8 character displays have PRODUCT_ID,
+and according to Delcom Engineering no queryable information
+can be obtained from the device to tell them apart.
+Device Modes
+------------
+By default, the driver assumes the display is only 6 characters
+The mode for 6 characters is:
+        MSB 0x06; LSB 0x3f
+For the 8 character display:
+        MSB 0x08; LSB 0xff
+The device can accept "text" either in raw, hex, or ascii textmode.
+raw controls each segment manually,
+hex expects a value between 0-15 per character,
+ascii expects a value between '0'-'9' and 'A'-'F'.
+The default is ascii.
+Device Operation
+----------------
+1.      Turn on the device:
+        echo 1 > /sys/bus/usb/.../powered
+2.      Set the device's mode:
+        echo $mode_msb > /sys/bus/usb/.../mode_msb
+        echo $mode_lsb > /sys/bus/usb/.../mode_lsb
+3.      Set the textmode:
+        echo $textmode > /sys/bus/usb/.../textmode
+4.      set the text (for example):
+        echo "123ABC" > /sys/bus/usb/.../text (ascii)
+        echo "A1B2" > /sys/bus/usb/.../text (ascii)
+        echo -ne "\x01\x02\x03" > /sys/bus/usb/.../text (hex)
+5.      Set the decimal places.
+        The device has either 6 or 8 decimal points.
+        to set the nth decimal place calculate 10 ** n
+        and echo it in to /sys/bus/usb/.../decimals
+        To set multiple decimals points sum up each power.
+        For example, to set the 0th and 3rd decimal place
+        echo 1001 > /sys/bus/usb/.../decimals
diff --git a/Documentation/usb/persist.txt b/Documentation/usb/persist.txt
index d56cb1a11550..074b159b77c2 100644
--- a/Documentation/usb/persist.txt
+++ b/Documentation/usb/persist.txt
@@ -81,8 +81,11 @@ re-enumeration shows that the device now attached to that port has the
 same descriptors as before, including the Vendor and Product IDs, then
 the kernel continues to use the same device structure.  In effect, the
 kernel treats the device as though it had merely been reset instead of
-unplugged.  The same thing happens if the host controller is in the
+unplugged.
-expected state but a USB device was unplugged and then replugged.
+The same thing happens if the host controller is in the expected state
+but a USB device was unplugged and then replugged, or if a USB device
+fails to carry out a normal resume.
 If no device is now attached to the port, or if the descriptors are
 different from what the kernel remembers, then the treatment is what
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index b2fc4d4a9917..e48ea1d51010 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -350,12 +350,12 @@ without holding the mutex.
 There also are a couple of utility routines drivers can use:
-        usb_autopm_enable() sets pm_usage_cnt to 1 and then calls
+        usb_autopm_enable() sets pm_usage_cnt to 0 and then calls
-        usb_autopm_set_interface(), which will attempt an autoresume.
-        usb_autopm_disable() sets pm_usage_cnt to 0 and then calls
        usb_autopm_set_interface(), which will attempt an autosuspend.
+        usb_autopm_disable() sets pm_usage_cnt to 1 and then calls
+        usb_autopm_set_interface(), which will attempt an autoresume.
 The conventional usage pattern is that a driver calls
 usb_autopm_get_interface() in its open routine and
 usb_autopm_put_interface() in its close or release routine.  But
@@ -436,7 +436,12 @@ post_reset; the USB core guarantees that this is true of internal
 suspend/resume events as well.
 If a driver wants to block all suspend/resume calls during some
-critical section, it can simply acquire udev->pm_mutex.
+critical section, it can simply acquire udev->pm_mutex. Note that
+calls to resume may be triggered indirectly. Block IO due to memory
+allocations can make the vm subsystem resume a device. Thus while
+holding this lock you must not allocate memory with GFP_KERNEL or
+GFP_NOFS.
 Alternatively, if the critical section might call some of the
 usb_autopm_* routines, the driver can avoid deadlock by doing:
diff --git a/Documentation/usb/uhci.txt b/Documentation/usb/uhci.txt
deleted file mode 100644
index 2f25952c86c6..000000000000
--- a/Documentation/usb/uhci.txt
+++ /dev/null
@@ -1,165 +0,0 @@
-Specification and Internals for the New UHCI Driver (Whitepaper...)
-        brought to you by
-        Georg Acher, acher@in.tum.de (executive slave) (base guitar)
-        Deti Fliegl, deti@fliegl.de (executive slave) (lead voice)
-        Thomas Sailer, sailer@ife.ee.ethz.ch (chief consultant) (cheer leader)
- 
-        $Id: README.uhci,v 1.1 1999/12/14 14:03:02 fliegl Exp $
-This document and the new uhci sources can be found on
-                http://hotswap.in.tum.de/usb
-1. General issues
-1.1 Why a new UHCI driver, we already have one?!?
-Correct, but its internal structure got more and more mixed up by the (still
-ongoing) efforts to get isochronous transfers (ISO) to work.
-Since there is an increasing need for reliable ISO-transfers (especially 
-for USB-audio needed by TS and for a DAB-USB-Receiver build by GA and DF), 
-this state was a bit unsatisfying in our opinion, so we've decided (based
-on knowledge and experiences with the old UHCI driver) to start 
-from scratch with a new approach, much simpler but at the same time more 
-powerful.
-It is inspired by the way Win98/Win2000 handles USB requests via URBs,
-but it's definitely 100% free of MS-code and doesn't crash while 
-unplugging an used ISO-device like Win98 ;-)
-Some code for HW setup and root hub management was taken from the 
-original UHCI driver, but heavily modified to fit into the new code.
-The invention of the basic concept, and major coding were completed in two 
-days (and nights) on the 16th and 17th of October 1999, now known as the
-great USB-October-Revolution started by GA, DF, and TS ;-)
-Since the concept is in no way UHCI dependent, we hope that it will also be 
-transferred to the OHCI-driver, so both drivers share a common API.
-1.2. Advantages and disadvantages
-+ All USB transfer types work now!
-+ Asynchronous operation
-+ Simple, but powerful interface (only two calls for start and cancel)
-+ Easy migration to the new API, simplified by a compatibility API
-+ Simple usage of ISO transfers
-+ Automatic linking of requests
-+ ISO transfers allow variable length for each frame and striping
-+ No CPU dependent and non-portable atomic memory access, no asm()-inlines
-+ Tested on x86 and Alpha
- Rewriting for ISO transfers needed
-1.3. Is there some compatibility to the old API?
-Yes, but only for control, bulk and interrupt transfers. We've implemented 
-some wrapper calls for these transfer types. The usbcore works fine with 
-these wrappers. For ISO there's no compatibility, because the old ISO-API 
-and its semantics were unnecessary complicated in our opinion.
-1.4. What's really working?
-As said above, CTRL and BULK already work fine even with the wrappers,
-so legacy code wouldn't notice the change.
-Regarding to Thomas, ISO transfers now run stable with USB audio.
-INT transfers (e.g. mouse driver) work fine, too.
-1.5. Are there any bugs?
-No ;-)
-Hm...
-Well, of course this implementation needs extensive testing on all available
-hardware, but we believe that any fixes shouldn't harm the overall concept.
-1.6. What should be done next?
-A large part of the request handling seems to be identical for UHCI and 
-OHCI, so it would be a good idea to extract the common parts and have only 
-the HW specific stuff in uhci.c. Furthermore, all other USB device drivers
-should need URBification, if they use isochronous or interrupt transfers.
-One thing missing in the current implementation (and the old UHCI driver) 
-is fair queueing for BULK transfers. Since this would need (in principle) 
-the alteration of already constructed TD chains (to switch from depth to 
-breadth execution), another way has to be found. Maybe some simple 
-heuristics work with the same effect.
---------------------------------------------------------------------------
-2. Internal structure and mechanisms
-To get quickly familiar with the internal structures, here's a short
-description how the new UHCI driver works. However, the ultimate source of
-truth is only uhci.c!
-2.1. Descriptor structure (QHs and TDs)
-During initialization, the following skeleton is allocated in init_skel:
-         framespecific           |           common chain     
-framelist[]
-[  0 ]-----> TD --> TD -------\
-[  1 ]-----> TD --> TD --------> TD ----> QH -------> QH -------> QH ---> NULL
-  ...        TD --> TD -------/
-[1023]-----> TD --> TD ------/
-             
-             ^^     ^^           ^^       ^^          ^^          ^^
-   1024 TDs for   7 TDs for    1 TD for   Start of    Start of    End Chain
-            ISO  INT (2-128ms) 1ms-INT    CTRL Chain  BULK Chain
-For each CTRL or BULK transfer a new QH is allocated and the containing data
-transfers are appended as (vertical) TDs. After building the whole QH with its
-dangling TDs, the QH is inserted before the BULK Chain QH (for CTRL) or
-before the End Chain QH (for BULK). Since only the QH->next pointers are
-affected, no atomic memory operation is required. The three QHs in the
-common chain are never equipped with TDs!
-For ISO or INT, the TD for each frame is simply inserted into the appropriate
-ISO/INT-TD-chain for the desired frame. The 7 skeleton INT-TDs are scattered
-among the 1024 frames similar to the old UHCI driver.
-For CTRL/BULK/ISO, the last TD in the transfer has the IOC-bit set. For INT,
-every TD (there is only one...) has the IOC-bit set.
-Besides the data for the UHCI controller (2 or 4 32bit words), the descriptors
-are double-linked through the .vertical and .horizontal elements in the 
-SW data of the descriptor (using the double-linked list structures and 
-operations), but SW-linking occurs only in closed domains, i.e. for each of
-the 1024 ISO-chains and the 8 INT-chains there is a closed cycle. This 
-simplifies all insertions and unlinking operations and avoids costly 
-bus_to_virt()-calls.
-2.2. URB structure and linking to QH/TDs
-During assembly of the QH and TDs of the requested action, these descriptors
-are stored in urb->urb_list, so the allocated QH/TD descriptors are bound to
-this URB.
-If the assembly was successful and the descriptors were added to the HW chain,
-the corresponding URB is inserted into a global URB list for this controller.
-This list stores all pending URBs.
-2.3. Interrupt processing
-Since UHCI provides no means to directly detect completed transactions, the
-following is done in each UHCI interrupt (uhci_interrupt()):
-For each URB in the pending queue (process_urb()), the ACTIVE-flag of the 
-associated TDs are processed (depending on the transfer type 
-process_{transfer|interrupt|iso}()). If the TDs are not active anymore, 
-they indicate the completion of the transaction and the status is calculated. 
-Inactive QH/TDs are removed from the HW chain (since the host controller
-already removed the TDs from the QH, no atomic access is needed) and 
-eventually the URB is marked as completed (OK or errors) and removed from the 
-pending queue. Then the next linked URB is submitted. After (or immediately 
-before) that, the completion handler is called.
-2.4. Unlinking URBs
-First, all QH/TDs stored in the URB are unlinked from the HW chain. 
-To ensure that the host controller really left a vertical TD chain, we 
-wait for one frame. After that, the TDs are physically destroyed.
-2.5. URB linking and the consequences
-Since URBs can be linked and the corresponding submit_urb is called in
-the UHCI-interrupt, all work associated with URB/QH/TD assembly has to be
-interrupt save. This forces kmalloc to use GFP_ATOMIC in the interrupt.
diff --git a/Documentation/usb/wusb-cbaf b/Documentation/usb/wusb-cbaf
new file mode 100644
index 000000000000..2e78b70f3adc
--- /dev/null
+++ b/Documentation/usb/wusb-cbaf
@@ -0,0 +1,139 @@
+#! /bin/bash
+#
+set -e
+progname=$(basename $0)
+function help
+{
+    cat <<EOF
+Usage: $progname COMMAND DEVICEs [ARGS]
+Command for manipulating the pairing/authentication credentials of a
+Wireless USB device that supports wired-mode Cable-Based-Association.
+Works in conjunction with the wusb-cba.ko driver from http://linuxuwb.org.
+DEVICE
+ sysfs path to the device to authenticate; for example, both this
+ guys are the same:
+ /sys/devices/pci0000:00/0000:00:1d.7/usb1/1-4/1-4.4/1-4.4:1.1
+ /sys/bus/usb/drivers/wusb-cbaf/1-4.4:1.1
+COMMAND/ARGS are
+ start
+   Start a WUSB host controller (by setting up a CHID)
+ set-chid DEVICE HOST-CHID HOST-BANDGROUP HOST-NAME
+   Sets host information in the device; after this you can call the
+   get-cdid to see how does this device report itself to us.
+ get-cdid DEVICE
+   Get the device ID associated to the HOST-CHDI we sent with
+   'set-chid'. We might not know about it.
+ set-cc DEVICE
+   If we allow the device to connect, set a random new CDID and CK
+   (connection key). Device saves them for the next time it wants to
+   connect wireless. We save them for that next time also so we can
+   authenticate the device (when we see the CDID he uses to id
+   itself) and the CK to crypto talk to it.
+CHID is always 16 hex bytes in 'XX YY ZZ...' form
+BANDGROUP is almost always 0001
+Examples:
+  You can default most arguments to '' to get a sane value:
+  $ $progname set-chid '' '' '' "My host name"
+  A full sequence:
+  $ $progname set-chid '' '' '' "My host name"
+  $ $progname get-cdid ''
+  $ $progname set-cc ''
+EOF
+}
+# Defaults
+# FIXME: CHID should come from a database :), band group from the host
+host_CHID="00 11 22 33 44 55 66 77 88 99 aa bb cc dd ee ff"
+host_band_group="0001"
+host_name=$(hostname)
+devs="$(echo /sys/bus/usb/drivers/wusb-cbaf/[0-9]*)"
+hdevs="$(for h in /sys/class/uwb_rc/*/wusbhc; do readlink -f $h; done)"
+result=0
+case $1 in
+    start)
+        for dev in ${2:-$hdevs}
+          do
+          uwb_rc=$(readlink -f $dev/uwb_rc)
+          if cat $uwb_rc/beacon | grep -q -- "-1"
+              then
+              echo 13 0 > $uwb_rc/beacon
+              echo I: started beaconing on ch 13 on $(basename $uwb_rc) >&2
+          fi
+          echo $host_CHID > $dev/wusb_chid
+          echo I: started host $(basename $dev) >&2
+        done
+        ;;
+    stop)
+        for dev in ${2:-$hdevs}
+          do
+          echo 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 > $dev/wusb_chid
+          echo I: stopped host $(basename $dev) >&2
+          uwb_rc=$(readlink -f $dev/uwb_rc)
+          echo -1 | cat > $uwb_rc/beacon
+          echo I: stopped beaconing on $(basename $uwb_rc) >&2
+        done
+        ;;
+    set-chid)
+        shift
+        for dev in ${2:-$devs}; do
+            echo "${4:-$host_name}" > $dev/wusb_host_name
+            echo "${3:-$host_band_group}" > $dev/wusb_host_band_groups
+            echo ${2:-$host_CHID} > $dev/wusb_chid
+        done
+        ;;
+    get-cdid)
+        for dev in ${2:-$devs}
+          do
+          cat $dev/wusb_cdid
+        done
+        ;;
+    set-cc)
+        for dev in ${2:-$devs}; do
+            shift
+            CDID="$(head --bytes=16 /dev/urandom  | od -tx1 -An)"
+            CK="$(head --bytes=16 /dev/urandom  | od -tx1 -An)"
+            echo "$CDID" > $dev/wusb_cdid
+            echo "$CK" > $dev/wusb_ck
+            echo I: CC set >&2
+            echo "CHID: $(cat $dev/wusb_chid)"
+            echo "CDID:$CDID"
+            echo "CK:  $CK"
+        done
+        ;;
+    help|h|--help|-h)
+        help
+        ;;
+    *)
+        echo "E: Unknown usage" 1>&2
+        help 1>&2
+        result=1
+esac
+exit $result
diff --git a/Documentation/video4linux/CARDLIST.au0828 b/Documentation/video4linux/CARDLIST.au0828
index 86d1c8e7b18f..d5cb4ea287b2 100644
--- a/Documentation/video4linux/CARDLIST.au0828
+++ b/Documentation/video4linux/CARDLIST.au0828
@@ -1,4 +1,6 @@
  0 -> Unknown board                            (au0828)
-  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200,2040:7210,2040:7217,2040:721b,2040:721f,2040:7280,0fd9:0008]
+  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200,2040:7210,2040:7217,2040:721b,2040:721e,2040:721f,2040:7280,0fd9:0008]
  2 -> Hauppauge HVR850                         (au0828)        [2040:7240]
  3 -> DViCO FusionHDTV USB                     (au0828)        [0fe9:d620]
+  4 -> Hauppauge HVR950Q rev xxF8               (au0828)        [2040:7201,2040:7211,2040:7281]
+  5 -> Hauppauge Woodbury                       (au0828)        [2040:8200]
diff --git a/Documentation/video4linux/CARDLIST.bttv b/Documentation/video4linux/CARDLIST.bttv
index f32efb6fb12c..60ba66836038 100644
--- a/Documentation/video4linux/CARDLIST.bttv
+++ b/Documentation/video4linux/CARDLIST.bttv
@@ -150,3 +150,4 @@
 149 -> Typhoon TV-Tuner PCI (50684)
 150 -> Geovision GV-600                                    [008a:763c]
 151 -> Kozumi KTV-01C
+152 -> Encore ENL TV-FM-2                                  [1000:1801]
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 191194ea1e25..64823ccacd69 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -8,3 +8,6 @@
  7 -> Hauppauge WinTV-HVR1200                             [0070:71d1,0070:71d3]
  8 -> Hauppauge WinTV-HVR1700                             [0070:8101]
  9 -> Hauppauge WinTV-HVR1400                             [0070:8010]
+ 10 -> DViCO FusionHDTV7 Dual Express                      [18ac:d618]
+ 11 -> DViCO FusionHDTV DVB-T Dual Express                 [18ac:db78]
+ 12 -> Leadtek Winfast PxDVR3200 H                         [107d:6681]
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index 7cf5685d3645..a5227e308f4a 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -66,3 +66,11 @@
 65 -> DViCO FusionHDTV 7 Gold                             [18ac:d610]
 66 -> Prolink Pixelview MPEG 8000GT                       [1554:4935]
 67 -> Kworld PlusTV HD PCI 120 (ATSC 120)                 [17de:08c1]
+ 68 -> Hauppauge WinTV-HVR4000 DVB-S/S2/T/Hybrid           [0070:6900,0070:6904,0070:6902]
+ 69 -> Hauppauge WinTV-HVR4000(Lite) DVB-S/S2              [0070:6905,0070:6906]
+ 70 -> TeVii S460 DVB-S/S2                                 [d460:9022]
+ 71 -> Omicom SS4 DVB-S/S2 PCI                             [A044:2011]
+ 72 -> TBS 8920 DVB-S/S2                                   [8920:8888]
+ 73 -> TeVii S420 DVB-S                                    [d420:9022]
+ 74 -> Prolink Pixelview Global Extreme                    [1554:4976]
+ 75 -> PROF 7300 DVB-S/S2                                  [B033:3033]
diff --git a/Documentation/video4linux/CARDLIST.em28xx b/Documentation/video4linux/CARDLIST.em28xx
index 1d6a245c828f..187cc48d0924 100644
--- a/Documentation/video4linux/CARDLIST.em28xx
+++ b/Documentation/video4linux/CARDLIST.em28xx
@@ -1,17 +1,59 @@
  0 -> Unknown EM2800 video grabber             (em2800)        [eb1a:2800]
-  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2750,eb1a:2820,eb1a:2821,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
+  1 -> Unknown EM2750/28xx video grabber        (em2820/em2840) [eb1a:2820,eb1a:2860,eb1a:2861,eb1a:2870,eb1a:2881,eb1a:2883]
  2 -> Terratec Cinergy 250 USB                 (em2820/em2840) [0ccd:0036]
  3 -> Pinnacle PCTV USB 2                      (em2820/em2840) [2304:0208]
  4 -> Hauppauge WinTV USB 2                    (em2820/em2840) [2040:4200,2040:4201]
  5 -> MSI VOX USB 2.0                          (em2820/em2840)
  6 -> Terratec Cinergy 200 USB                 (em2800)
-  7 -> Leadtek Winfast USB II                   (em2800)
+  7 -> Leadtek Winfast USB II                   (em2800)        [0413:6023]
  8 -> Kworld USB2800                           (em2800)
  9 -> Pinnacle Dazzle DVC 90/DVC 100           (em2820/em2840) [2304:0207,2304:021a]
- 10 -> Hauppauge WinTV HVR 900                  (em2880)        [2040:6500,2040:6502]
+ 10 -> Hauppauge WinTV HVR 900                  (em2880)        [2040:6500]
 11 -> Terratec Hybrid XS                       (em2880)        [0ccd:0042]
 12 -> Kworld PVR TV 2800 RF                    (em2820/em2840)
 13 -> Terratec Prodigy XS                      (em2880)        [0ccd:0047]
- 14 -> Pixelview Prolink PlayTV USB 2.0         (em2820/em2840)
+ 14 -> Pixelview Prolink PlayTV USB 2.0         (em2820/em2840) [eb1a:2821]
 15 -> V-Gear PocketTV                          (em2800)
- 16 -> Hauppauge WinTV HVR 950                  (em2880)        [2040:6513,2040:6517,2040:651b,2040:651f]
+ 16 -> Hauppauge WinTV HVR 950                  (em2883)        [2040:6513,2040:6517,2040:651b,2040:651f]
+ 17 -> Pinnacle PCTV HD Pro Stick               (em2880)        [2304:0227]
+ 18 -> Hauppauge WinTV HVR 900 (R2)             (em2880)        [2040:6502]
+ 19 -> PointNix Intra-Oral Camera               (em2860)
+ 20 -> AMD ATI TV Wonder HD 600                 (em2880)        [0438:b002]
+ 21 -> eMPIA Technology, Inc. GrabBeeX+ Video Encoder (em2800)        [eb1a:2801]
+ 22 -> Unknown EM2750/EM2751 webcam grabber     (em2750)        [eb1a:2750,eb1a:2751]
+ 23 -> Huaqi DLCW-130                           (em2750)
+ 24 -> D-Link DUB-T210 TV Tuner                 (em2820/em2840) [2001:f112]
+ 25 -> Gadmei UTV310                            (em2820/em2840)
+ 26 -> Hercules Smart TV USB 2.0                (em2820/em2840)
+ 27 -> Pinnacle PCTV USB 2 (Philips FM1216ME)   (em2820/em2840)
+ 28 -> Leadtek Winfast USB II Deluxe            (em2820/em2840)
+ 29 -> Pinnacle Dazzle DVC 100                  (em2820/em2840)
+ 30 -> Videology 20K14XUSB USB2.0               (em2820/em2840)
+ 31 -> Usbgear VD204v9                          (em2821)
+ 32 -> Supercomp USB 2.0 TV                     (em2821)
+ 33 -> SIIG AVTuner-PVR/Prolink PlayTV USB 2.0  (em2821)
+ 34 -> Terratec Cinergy A Hybrid XS             (em2860)        [0ccd:004f]
+ 35 -> Typhoon DVD Maker                        (em2860)
+ 36 -> NetGMBH Cam                              (em2860)
+ 37 -> Gadmei UTV330                            (em2860)
+ 38 -> Yakumo MovieMixer                        (em2861)
+ 39 -> KWorld PVRTV 300U                        (em2861)        [eb1a:e300]
+ 40 -> Plextor ConvertX PX-TV100U               (em2861)        [093b:a005]
+ 41 -> Kworld 350 U DVB-T                       (em2870)        [eb1a:e350]
+ 42 -> Kworld 355 U DVB-T                       (em2870)        [eb1a:e355,eb1a:e357]
+ 43 -> Terratec Cinergy T XS                    (em2870)        [0ccd:0043]
+ 44 -> Terratec Cinergy T XS (MT2060)           (em2870)
+ 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]
+ 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]
+ 52 -> DNT DA2 Hybrid                           (em2881)
+ 53 -> Pinnacle Hybrid Pro                      (em2881)
+ 54 -> Kworld VS-DVB-T 323UR                    (em2882)        [eb1a:e323]
+ 55 -> Terratec Hybrid XS (em2882)              (em2882)        [0ccd:005e]
+ 56 -> Pinnacle Hybrid Pro (2)                  (em2882)        [2304:0226]
+ 57 -> Kworld PlusTV HD Hybrid 330              (em2883)        [eb1a:a316]
+ 58 -> Compro VideoMate ForYou/Stereo           (em2820/em2840) [185b:2041]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 67937df1e974..dc67eef38ff9 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -37,7 +37,7 @@
 36 -> UPMOST PURPLE TV                         [12ab:0800]
 37 -> Items MuchTV Plus / IT-005
 38 -> Terratec Cinergy 200 TV                  [153b:1152]
- 39 -> LifeView FlyTV Platinum Mini             [5168:0212,4e42:0212]
+ 39 -> LifeView FlyTV Platinum Mini             [5168:0212,4e42:0212,5169:1502]
 40 -> Compro VideoMate TV PVR/FM               [185b:c100]
 41 -> Compro VideoMate TV Gold+                [185b:c100]
 42 -> Sabrent SBT-TVFM (saa7130)
@@ -76,7 +76,7 @@
 75 -> AVerMedia AVerTVHD MCE A180              [1461:1044]
 76 -> SKNet MonsterTV Mobile                   [1131:4ee9]
 77 -> Pinnacle PCTV 40i/50i/110i (saa7133)     [11bd:002e]
- 78 -> ASUSTeK P7131 Dual                       [1043:4862,1043:4857]
+ 78 -> ASUSTeK P7131 Dual                       [1043:4862]
 79 -> Sedna/MuchTV PC TV Cardbus TV/Radio (ITO25 Rev:2B)
 80 -> ASUS Digimatrix TV                       [1043:0210]
 81 -> Philips Tiger reference design           [1131:2018]
@@ -128,7 +128,7 @@
 127 -> Beholder BeholdTV 507 FM/RDS / BeholdTV 509 FM [0000:5071,0000:507B,5ace:5070,5ace:5090]
 128 -> Beholder BeholdTV Columbus TVFM          [0000:5201]
 129 -> Beholder BeholdTV 607 / BeholdTV 609     [5ace:6070,5ace:6071,5ace:6072,5ace:6073,5ace:6090,5ace:6091,5ace:6092,5ace:6093]
-130 -> Beholder BeholdTV M6 / BeholdTV M6 Extra [5ace:6190,5ace:6193,5ace:6191]
+130 -> Beholder BeholdTV M6                     [5ace:6190]
 131 -> Twinhan Hybrid DTV-DVB 3056 PCI          [1822:0022]
 132 -> Genius TVGO AM11MCE
 133 -> NXP Snake DVB-S reference design
@@ -141,3 +141,13 @@
 140 -> Avermedia DVB-S Pro A700                 [1461:a7a1]
 141 -> Avermedia DVB-S Hybrid+FM A700           [1461:a7a2]
 142 -> Beholder BeholdTV H6                     [5ace:6290]
+143 -> Beholder BeholdTV M63                    [5ace:6191]
+144 -> Beholder BeholdTV M6 Extra               [5ace:6193]
+145 -> AVerMedia MiniPCI DVB-T Hybrid M103      [1461:f636]
+146 -> ASUSTeK P7131 Analog
+147 -> Asus Tiger 3in1                          [1043:4878]
+148 -> Encore ENLTV-FM v5.3                     [1a7f:2008]
+149 -> Avermedia PCI pure analog (M135A)        [1461:f11d]
+150 -> Zogis Real Angel 220
+151 -> ADS Tech Instant HDTV                    [1421:0380]
+152 -> Asus Tiger Rev:1.00                      [1043:4857]
diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index 0e2394695bb8..691d2f37dc57 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -74,3 +74,5 @@ tuner=72 - Thomson FE6600
 tuner=73 - Samsung TCPG 6121P30A
 tuner=75 - Philips TEA5761 FM Radio
 tuner=76 - Xceive 5000 tuner
+tuner=77 - TCL tuner MF02GIP-5N-E
+tuner=78 - Philips FMD1216MEX MK3 Hybrid Tuner
diff --git a/Documentation/video4linux/Makefile b/Documentation/video4linux/Makefile
new file mode 100644
index 000000000000..1ed0e98d057d
--- /dev/null
+++ b/Documentation/video4linux/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := v4lgrab
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/video4linux/cx18.txt b/Documentation/video4linux/cx18.txt
index 6842c262890f..914cb7e734a2 100644
--- a/Documentation/video4linux/cx18.txt
+++ b/Documentation/video4linux/cx18.txt
@@ -1,36 +1,30 @@
 Some notes regarding the cx18 driver for the Conexant CX23418 MPEG
 encoder chip:
-1) The only hardware currently supported is the Hauppauge HVR-1600
+1) Currently supported are:
-   card and the Compro VideoMate H900 (note that this card only
-   supports analog input, it has no digital tuner!).
-2) Some people have problems getting the i2c bus to work. Cause unknown.
+        - Hauppauge HVR-1600
-   The symptom is that the eeprom cannot be read and the card is
+        - Compro VideoMate H900
-   unusable.
+        - Yuan MPC718
+        - Conexant Raptor PAL/SECAM devkit
-3) The audio from the analog tuner is mono only. Probably caused by
+2) Some people have problems getting the i2c bus to work.
-   incorrect audio register information in the datasheet. We are
+   The symptom is that the eeprom cannot be read and the card is
-   waiting for updated information from Conexant.
+   unusable. This is probably fixed, but if you have problems
+   then post to the video4linux or ivtv-users mailinglist.
-4) VBI (raw or sliced) has not yet been implemented.
+3) VBI (raw or sliced) has not yet been implemented.
-5) MPEG indexing is not yet implemented.
+4) MPEG indexing is not yet implemented.
-6) The driver is still a bit rough around the edges, this should
+5) The driver is still a bit rough around the edges, this should
   improve over time.
 Firmware:
-The firmware needs to be extracted from the Windows Hauppauge HVR-1600
+You can obtain the firmware files here:
-driver, available here:
-http://hauppauge.lightpath.net/software/install_cd/hauppauge_cd_3.4d1.zip
-Unzip, then copy the following files to the firmware directory
+http://dl.ivtvdriver.org/ivtv/firmware/cx18-firmware.tar.gz
-and rename them as follows:
-Drivers/Driver18/hcw18apu.rom -> v4l-cx23418-apu.fw
+Untar and copy the .fw files to your firmware directory.
-Drivers/Driver18/hcw18enc.rom -> v4l-cx23418-cpu.fw
-Drivers/Driver18/hcw18mlC.rom -> v4l-cx23418-dig.fw
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
new file mode 100644
index 000000000000..004818fab040
--- /dev/null
+++ b/Documentation/video4linux/gspca.txt
@@ -0,0 +1,274 @@
+List of the webcams known by gspca.
+The modules are:
+        gspca_main      main driver
+        gspca_xxxx      subdriver module with xxxx as follows
+xxxx            vend:prod
+----
+spca501         0000:0000       MystFromOri Unknow Camera
+m5602           0402:5602       ALi Video Camera Controller
+spca501         040a:0002       Kodak DVC-325
+spca500         040a:0300       Kodak EZ200
+zc3xx           041e:041e       Creative WebCam Live!
+spca500         041e:400a       Creative PC-CAM 300
+sunplus         041e:400b       Creative PC-CAM 600
+sunplus         041e:4012       PC-Cam350
+sunplus         041e:4013       Creative Pccam750
+zc3xx           041e:4017       Creative Webcam Mobile PD1090
+spca508         041e:4018       Creative Webcam Vista (PD1100)
+spca561         041e:401a       Creative Webcam Vista (PD1100)
+zc3xx           041e:401c       Creative NX
+spca505         041e:401d       Creative Webcam NX ULTRA
+zc3xx           041e:401e       Creative Nx Pro
+zc3xx           041e:401f       Creative Webcam Notebook PD1171
+pac207          041e:4028       Creative Webcam Vista Plus
+zc3xx           041e:4029       Creative WebCam Vista Pro
+zc3xx           041e:4034       Creative Instant P0620
+zc3xx           041e:4035       Creative Instant P0620D
+zc3xx           041e:4036       Creative Live !
+zc3xx           041e:403a       Creative Nx Pro 2
+spca561         041e:403b       Creative Webcam Vista (VF0010)
+zc3xx           041e:4051       Creative Live!Cam Notebook Pro (VF0250)
+ov519           041e:4052       Creative Live! VISTA IM
+zc3xx           041e:4053       Creative Live!Cam Video IM
+ov519           041e:405f       Creative Live! VISTA VF0330
+ov519           041e:4060       Creative Live! VISTA VF0350
+ov519           041e:4061       Creative Live! VISTA VF0400
+ov519           041e:4064       Creative Live! VISTA VF0420
+ov519           041e:4068       Creative Live! VISTA VF0470
+spca561         0458:7004       Genius VideoCAM Express V2
+sunplus         0458:7006       Genius Dsc 1.3 Smart
+zc3xx           0458:7007       Genius VideoCam V2
+zc3xx           0458:700c       Genius VideoCam V3
+zc3xx           0458:700f       Genius VideoCam Web V2
+sonixj          0458:7025       Genius Eye 311Q
+sonixj          0458:702e       Genius Slim 310 NB
+sonixj          045e:00f5       MicroSoft VX3000
+sonixj          045e:00f7       MicroSoft VX1000
+ov519           045e:028c       Micro$oft xbox cam
+spca508         0461:0815       Micro Innovation IC200
+sunplus         0461:0821       Fujifilm MV-1
+zc3xx           0461:0a00       MicroInnovation WebCam320
+spca500         046d:0890       Logitech QuickCam traveler
+vc032x          046d:0892       Logitech Orbicam
+vc032x          046d:0896       Logitech Orbicam
+zc3xx           046d:08a0       Logitech QC IM
+zc3xx           046d:08a1       Logitech QC IM 0x08A1 +sound
+zc3xx           046d:08a2       Labtec Webcam Pro
+zc3xx           046d:08a3       Logitech QC Chat
+zc3xx           046d:08a6       Logitech QCim
+zc3xx           046d:08a7       Logitech QuickCam Image
+zc3xx           046d:08a9       Logitech Notebook Deluxe
+zc3xx           046d:08aa       Labtec Webcam  Notebook
+zc3xx           046d:08ac       Logitech QuickCam Cool
+zc3xx           046d:08ad       Logitech QCCommunicate STX
+zc3xx           046d:08ae       Logitech QuickCam for Notebooks
+zc3xx           046d:08af       Logitech QuickCam Cool
+zc3xx           046d:08b9       Logitech QC IM ???
+zc3xx           046d:08d7       Logitech QCam STX
+zc3xx           046d:08d9       Logitech QuickCam IM/Connect
+zc3xx           046d:08d8       Logitech Notebook Deluxe
+zc3xx           046d:08da       Logitech QuickCam Messenger
+zc3xx           046d:08dd       Logitech QuickCam for Notebooks
+spca500         046d:0900       Logitech Inc. ClickSmart 310
+spca500         046d:0901       Logitech Inc. ClickSmart 510
+sunplus         046d:0905       Logitech ClickSmart 820
+tv8532          046d:0920       QC Express
+tv8532          046d:0921       Labtec Webcam
+spca561         046d:0928       Logitech QC Express Etch2
+spca561         046d:0929       Labtec Webcam Elch2
+spca561         046d:092a       Logitech QC for Notebook
+spca561         046d:092b       Labtec Webcam Plus
+spca561         046d:092c       Logitech QC chat Elch2
+spca561         046d:092d       Logitech QC Elch2
+spca561         046d:092e       Logitech QC Elch2
+spca561         046d:092f       Logitech  QuickCam Express Plus
+sunplus         046d:0960       Logitech ClickSmart 420
+sunplus         0471:0322       Philips DMVC1300K
+zc3xx           0471:0325       Philips SPC 200 NC
+zc3xx           0471:0326       Philips SPC 300 NC
+sonixj          0471:0327       Philips SPC 600 NC
+sonixj          0471:0328       Philips SPC 700 NC
+zc3xx           0471:032d       Philips SPC 210 NC
+zc3xx           0471:032e       Philips SPC 315 NC
+sonixj          0471:0330       Philips SPC 710 NC
+spca501         0497:c001       Smile International
+sunplus         04a5:3003       Benq DC 1300
+sunplus         04a5:3008       Benq DC 1500
+sunplus         04a5:300a       Benq DC 3410
+spca500         04a5:300c       Benq DC 1016
+finepix         04cb:0104       Fujifilm FinePix 4800
+finepix         04cb:0109       Fujifilm FinePix A202
+finepix         04cb:010b       Fujifilm FinePix A203
+finepix         04cb:010f       Fujifilm FinePix A204
+finepix         04cb:0111       Fujifilm FinePix A205
+finepix         04cb:0113       Fujifilm FinePix A210
+finepix         04cb:0115       Fujifilm FinePix A303
+finepix         04cb:0117       Fujifilm FinePix A310
+finepix         04cb:0119       Fujifilm FinePix F401
+finepix         04cb:011b       Fujifilm FinePix F402
+finepix         04cb:011d       Fujifilm FinePix F410
+finepix         04cb:0121       Fujifilm FinePix F601
+finepix         04cb:0123       Fujifilm FinePix F700
+finepix         04cb:0125       Fujifilm FinePix M603
+finepix         04cb:0127       Fujifilm FinePix S300
+finepix         04cb:0129       Fujifilm FinePix S304
+finepix         04cb:012b       Fujifilm FinePix S500
+finepix         04cb:012d       Fujifilm FinePix S602
+finepix         04cb:012f       Fujifilm FinePix S700
+finepix         04cb:0131       Fujifilm FinePix unknown model
+finepix         04cb:013b       Fujifilm FinePix unknown model
+finepix         04cb:013d       Fujifilm FinePix unknown model
+finepix         04cb:013f       Fujifilm FinePix F420
+sunplus         04f1:1001       JVC GC A50
+spca561         04fc:0561       Flexcam 100
+sunplus         04fc:500c       Sunplus CA500C
+sunplus         04fc:504a       Aiptek Mini PenCam 1.3
+sunplus         04fc:504b       Maxell MaxPocket LE 1.3
+sunplus         04fc:5330       Digitrex 2110
+sunplus         04fc:5360       Sunplus Generic
+spca500         04fc:7333       PalmPixDC85
+sunplus         04fc:ffff       Pure DigitalDakota
+spca501         0506:00df       3Com HomeConnect Lite
+sunplus         052b:1513       Megapix V4
+tv8532          0545:808b       Veo Stingray
+tv8532          0545:8333       Veo Stingray
+sunplus         0546:3155       Polaroid PDC3070
+sunplus         0546:3191       Polaroid Ion 80
+sunplus         0546:3273       Polaroid PDC2030
+ov519           054c:0154       Sonny toy4
+ov519           054c:0155       Sonny toy5
+zc3xx           055f:c005       Mustek Wcam300A
+spca500         055f:c200       Mustek Gsmart 300
+sunplus         055f:c211       Kowa Bs888e Microcamera
+spca500         055f:c220       Gsmart Mini
+sunplus         055f:c230       Mustek Digicam 330K
+sunplus         055f:c232       Mustek MDC3500
+sunplus         055f:c360       Mustek DV4000 Mpeg4
+sunplus         055f:c420       Mustek gSmart Mini 2
+sunplus         055f:c430       Mustek Gsmart LCD 2
+sunplus         055f:c440       Mustek DV 3000
+sunplus         055f:c520       Mustek gSmart Mini 3
+sunplus         055f:c530       Mustek Gsmart LCD 3
+sunplus         055f:c540       Gsmart D30
+sunplus         055f:c630       Mustek MDC4000
+sunplus         055f:c650       Mustek MDC5500Z
+zc3xx           055f:d003       Mustek WCam300A
+zc3xx           055f:d004       Mustek WCam300 AN
+conex           0572:0041       Creative Notebook cx11646
+ov519           05a9:0519       OmniVision
+ov519           05a9:0530       OmniVision
+ov519           05a9:4519       OmniVision
+ov519           05a9:8519       OmniVision
+sunplus         05da:1018       Digital Dream Enigma 1.3
+stk014          05e1:0893       Syntek DV4000
+spca561         060b:a001       Maxell Compact Pc PM3
+zc3xx           0698:2003       CTX M730V built in
+spca500         06bd:0404       Agfa CL20
+spca500         06be:0800       Optimedia
+sunplus         06d6:0031       Trust 610 LCD PowerC@m Zoom
+spca506         06e1:a190       ADS Instant VCD
+spca508         0733:0110       ViewQuest VQ110
+spca508         0130:0130       Clone Digital Webcam 11043
+spca501         0733:0401       Intel Create and Share
+spca501         0733:0402       ViewQuest M318B
+spca505         0733:0430       Intel PC Camera Pro
+sunplus         0733:1311       Digital Dream Epsilon 1.3
+sunplus         0733:1314       Mercury 2.1MEG Deluxe Classic Cam
+sunplus         0733:2211       Jenoptik jdc 21 LCD
+sunplus         0733:2221       Mercury Digital Pro 3.1p
+sunplus         0733:3261       Concord 3045 spca536a
+sunplus         0733:3281       Cyberpix S550V
+spca506         0734:043b       3DeMon USB Capture aka
+spca500         084d:0003       D-Link DSC-350
+spca500         08ca:0103       Aiptek PocketDV
+sunplus         08ca:0104       Aiptek PocketDVII 1.3
+sunplus         08ca:0106       Aiptek Pocket DV3100+
+sunplus         08ca:2008       Aiptek Mini PenCam 2 M
+sunplus         08ca:2010       Aiptek PocketCam 3M
+sunplus         08ca:2016       Aiptek PocketCam 2 Mega
+sunplus         08ca:2018       Aiptek Pencam SD 2M
+sunplus         08ca:2020       Aiptek Slim 3000F
+sunplus         08ca:2022       Aiptek Slim 3200
+sunplus         08ca:2024       Aiptek DV3500 Mpeg4
+sunplus         08ca:2028       Aiptek PocketCam4M
+sunplus         08ca:2040       Aiptek PocketDV4100M
+sunplus         08ca:2042       Aiptek PocketDV5100
+sunplus         08ca:2050       Medion MD 41437
+sunplus         08ca:2060       Aiptek PocketDV5300
+tv8532          0923:010f       ICM532 cams
+mars            093a:050f       Mars-Semi Pc-Camera
+pac207          093a:2460       PAC207 Qtec Webcam 100
+pac207          093a:2463       Philips SPC 220 NC
+pac207          093a:2464       Labtec Webcam 1200
+pac207          093a:2468       PAC207
+pac207          093a:2470       Genius GF112
+pac207          093a:2471       Genius VideoCam ge111
+pac207          093a:2472       Genius VideoCam ge110
+pac207          093a:2476       Genius e-Messenger 112
+pac7311         093a:2600       PAC7311 Typhoon
+pac7311         093a:2601       Philips SPC 610 NC
+pac7311         093a:2603       PAC7312
+pac7311         093a:2608       Trust WB-3300p
+pac7311         093a:260e       Gigaware VGA PC Camera, Trust WB-3350p, SIGMA cam 2350
+pac7311         093a:260f       SnakeCam
+pac7311         093a:2621       PAC731x
+pac7311         093a:2624       PAC7302
+pac7311         093a:2626       Labtec 2200
+pac7311         093a:262a       Webcam 300k
+zc3xx           0ac8:0302       Z-star Vimicro zc0302
+vc032x          0ac8:0321       Vimicro generic vc0321
+vc032x          0ac8:0323       Vimicro Vc0323
+vc032x          0ac8:0328       A4Tech PK-130MG
+zc3xx           0ac8:301b       Z-Star zc301b
+zc3xx           0ac8:303b       Vimicro 0x303b
+zc3xx           0ac8:305b       Z-star Vimicro zc0305b
+zc3xx           0ac8:307b       Ldlc VC302+Ov7620
+vc032x          0ac8:c001       Sony embedded vimicro
+vc032x          0ac8:c002       Sony embedded vimicro
+spca508         0af9:0010       Hama USB Sightcam 100
+spca508         0af9:0011       Hama USB Sightcam 100
+sonixb          0c45:6001       Genius VideoCAM NB
+sonixb          0c45:6005       Microdia Sweex Mini Webcam
+sonixb          0c45:6007       Sonix sn9c101 + Tas5110D
+sonixb          0c45:6009       spcaCam@120
+sonixb          0c45:600d       spcaCam@120
+sonixb          0c45:6011       Microdia PC Camera (SN9C102)
+sonixb          0c45:6019       Generic Sonix OV7630
+sonixb          0c45:6024       Generic Sonix Tas5130c
+sonixb          0c45:6025       Xcam Shanga
+sonixb          0c45:6028       Sonix Btc Pc380
+sonixb          0c45:6029       spcaCam@150
+sonixb          0c45:602c       Generic Sonix OV7630
+sonixb          0c45:602d       LIC-200 LG
+sonixb          0c45:602e       Genius VideoCam Messenger
+sonixj          0c45:6040       Speed NVC 350K
+sonixj          0c45:607c       Sonix sn9c102p Hv7131R
+sonixj          0c45:60c0       Sangha Sn535
+sonixj          0c45:60ec       SN9C105+MO4000
+sonixj          0c45:60fb       Surfer NoName
+sonixj          0c45:60fc       LG-LIC300
+sonixj          0c45:6128       Microdia/Sonix SNP325
+sonixj          0c45:612a       Avant Camera
+sonixj          0c45:612c       Typhoon Rasy Cam 1.3MPix
+sonixj          0c45:6130       Sonix Pccam
+sonixj          0c45:6138       Sn9c120 Mo4000
+sonixj          0c45:613b       Surfer SN-206
+sonixj          0c45:613c       Sonix Pccam168
+sonixj          0c45:6143       Sonix Pccam168
+sunplus         0d64:0303       Sunplus FashionCam DXG
+etoms           102c:6151       Qcam Sangha CIF
+etoms           102c:6251       Qcam xxxxxx VGA
+zc3xx           10fd:0128       Typhoon Webshot II USB 300k 0x0128
+spca561         10fd:7e50       FlyCam Usb 100
+zc3xx           10fd:8050       Typhoon Webshot II USB 300k
+spca501         1776:501c       Arowana 300K CMOS Camera
+t613            17a1:0128       TASCORP JPEG Webcam, NGS Cyclops
+vc032x          17ef:4802       Lenovo Vc0323+MI1310_SOC
+pac207          2001:f115       D-Link DSB-C120
+spca500         2899:012c       Toptro Industrial
+spca508         8086:0110       Intel Easy PC Camera
+spca500         8086:0630       Intel Pocket PC Camera
+spca506         99fa:8988       Grandtec V.cap
+spca561         abcd:cdee       Petcam
diff --git a/Documentation/video4linux/m5602.txt b/Documentation/video4linux/m5602.txt
new file mode 100644
index 000000000000..4450ab13f37b
--- /dev/null
+++ b/Documentation/video4linux/m5602.txt
@@ -0,0 +1,12 @@
+This document describes the ALi m5602 bridge connected
+to the following supported sensors:
+OmniVision OV9650,
+Samsung s5k83a,
+Samsung s5k4aa,
+Micron mt9m111,
+Pixel plus PO1030
+This driver mimics the windows drivers, which have a braindead implementation sending bayer-encoded frames at VGA resolution.
+In a perfect world we should be able to reprogram the m5602 and the connected sensor in hardware instead, supporting a range of resolutions and pixelformats
+Anyway, have fun and please report any bugs to m560x-driver-devel@lists.sourceforge.net
diff --git a/Documentation/video4linux/sn9c102.txt b/Documentation/video4linux/sn9c102.txt
index b26f5195af51..73de4050d637 100644
--- a/Documentation/video4linux/sn9c102.txt
+++ b/Documentation/video4linux/sn9c102.txt
@@ -157,7 +157,7 @@ Loading can be done as shown below:
        [root@localhost home]# modprobe sn9c102
-Note that the module is called "sn9c102" for historic reasons, althought it
+Note that the module is called "sn9c102" for historic reasons, although it
 does not just support the SN9C102.
 At this point all the devices supported by the driver and connected to the USB
diff --git a/Documentation/video4linux/soc-camera.txt b/Documentation/video4linux/soc-camera.txt
new file mode 100644
index 000000000000..178ef3c5e579
--- /dev/null
+++ b/Documentation/video4linux/soc-camera.txt
@@ -0,0 +1,120 @@
+                        Soc-Camera Subsystem
+                        ====================
+Terminology
+-----------
+The following terms are used in this document:
+ - camera / camera device / camera sensor - a video-camera sensor chip, capable
+   of connecting to a variety of systems and interfaces, typically uses i2c for
+   control and configuration, and a parallel or a serial bus for data.
+ - camera host - an interface, to which a camera is connected. Typically a
+   specialised interface, present on many SoCs, e.g., PXA27x and PXA3xx, SuperH,
+   AVR32, i.MX27, i.MX31.
+ - camera host bus - a connection between a camera host and a camera. Can be
+   parallel or serial, consists of data and control lines, e.g., clock, vertical
+   and horizontal synchronization signals.
+Purpose of the soc-camera subsystem
+-----------------------------------
+The soc-camera subsystem provides a unified API between camera host drivers and
+camera sensor drivers. It implements a V4L2 interface to the user, currently
+only the mmap method is supported.
+This subsystem has been written to connect drivers for System-on-Chip (SoC)
+video capture interfaces with drivers for CMOS camera sensor chips to enable
+the reuse of sensor drivers with various hosts. The subsystem has been designed
+to support multiple camera host interfaces and multiple cameras per interface,
+although most applications have only one camera sensor.
+Existing drivers
+----------------
+As of 2.6.27-rc4 there are two host drivers in the mainline: pxa_camera.c for
+PXA27x SoCs and sh_mobile_ceu_camera.c for SuperH SoCs, and four sensor drivers:
+mt9m001.c, mt9m111.c, mt9v022.c and a generic soc_camera_platform.c driver. This
+list is not supposed to be updated, look for more examples in your tree.
+Camera host API
+---------------
+A host camera driver is registered using the
+soc_camera_host_register(struct soc_camera_host *);
+function. The host object can be initialized as follows:
+static struct soc_camera_host pxa_soc_camera_host = {
+        .drv_name       = PXA_CAM_DRV_NAME,
+        .ops            = &pxa_soc_camera_host_ops,
+};
+All camera host methods are passed in a struct soc_camera_host_ops:
+static struct soc_camera_host_ops pxa_soc_camera_host_ops = {
+        .owner          = THIS_MODULE,
+        .add            = pxa_camera_add_device,
+        .remove         = pxa_camera_remove_device,
+        .suspend        = pxa_camera_suspend,
+        .resume         = pxa_camera_resume,
+        .set_fmt_cap    = pxa_camera_set_fmt_cap,
+        .try_fmt_cap    = pxa_camera_try_fmt_cap,
+        .init_videobuf  = pxa_camera_init_videobuf,
+        .reqbufs        = pxa_camera_reqbufs,
+        .poll           = pxa_camera_poll,
+        .querycap       = pxa_camera_querycap,
+        .try_bus_param  = pxa_camera_try_bus_param,
+        .set_bus_param  = pxa_camera_set_bus_param,
+};
+.add and .remove methods are called when a sensor is attached to or detached
+from the host, apart from performing host-internal tasks they shall also call
+sensor driver's .init and .release methods respectively. .suspend and .resume
+methods implement host's power-management functionality and its their
+responsibility to call respective sensor's methods. .try_bus_param and
+.set_bus_param are used to negotiate physical connection parameters between the
+host and the sensor. .init_videobuf is called by soc-camera core when a
+video-device is opened, further video-buffer management is implemented completely
+by the specific camera host driver. The rest of the methods are called from
+respective V4L2 operations.
+Camera API
+----------
+Sensor drivers can use struct soc_camera_link, typically provided by the
+platform, and used to specify to which camera host bus the sensor is connected,
+and arbitrarily provide platform .power and .reset methods for the camera.
+soc_camera_device_register() and soc_camera_device_unregister() functions are
+used to add a sensor driver to or remove one from the system. The registration
+function takes a pointer to struct soc_camera_device as the only parameter.
+This struct can be initialized as follows:
+        /* link to driver operations */
+        icd->ops        = &mt9m001_ops;
+        /* link to the underlying physical (e.g., i2c) device */
+        icd->control    = &client->dev;
+        /* window geometry */
+        icd->x_min      = 20;
+        icd->y_min      = 12;
+        icd->x_current  = 20;
+        icd->y_current  = 12;
+        icd->width_min  = 48;
+        icd->width_max  = 1280;
+        icd->height_min = 32;
+        icd->height_max = 1024;
+        icd->y_skip_top = 1;
+        /* camera bus ID, typically obtained from platform data */
+        icd->iface      = icl->bus_id;
+struct soc_camera_ops provides .probe and .remove methods, which are called by
+the soc-camera core, when a camera is matched against or removed from a camera
+host bus, .init, .release, .suspend, and .resume are called from the camera host
+driver as discussed above. Other members of this struct provide respective V4L2
+functionality.
+struct soc_camera_device also links to an array of struct soc_camera_data_format,
+listing pixel formats, supported by the camera.
+--
+Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
diff --git a/Documentation/video4linux/w9968cf.txt b/Documentation/video4linux/w9968cf.txt
index e0bba8393c77..05138e8aea07 100644
--- a/Documentation/video4linux/w9968cf.txt
+++ b/Documentation/video4linux/w9968cf.txt
@@ -193,9 +193,6 @@ Description:     Automatic 'ovcamchip' module loading: 0 disabled, 1 enabled.
                 loads that module automatically. This action is performed as
                 once soon as the 'w9968cf' module is loaded into memory.
 Default:         1
-Note:            The kernel must be compiled with the CONFIG_KMOD option
-                 enabled for the 'ovcamchip' module to be loaded and for
-                 this parameter to be present.
 -------------------------------------------------------------------------------
 Name:           simcams
 Type:           int
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
new file mode 100644
index 000000000000..6f562f778b28
--- /dev/null
+++ b/Documentation/vm/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := slabinfo
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index 3102b81bef88..ea8714fcc3ad 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -77,7 +77,7 @@ memory that is preset in system at this time.  System administrators may want
 to put this command in one of the local rc init files.  This will enable the
 kernel to request huge pages early in the boot process (when the possibility
 of getting physical contiguous pages is still very high). In either
-case, adminstrators will want to verify the number of hugepages actually
+case, administrators will want to verify the number of hugepages actually
 allocated by checking the sysctl or meminfo.
 /proc/sys/vm/nr_overcommit_hugepages indicates how large the pool of
@@ -95,6 +95,29 @@ this condition holds, however, no more surplus huge pages will be
 allowed on the system until one of the two sysctls are increased
 sufficiently, or the surplus huge pages go out of use and are freed.
+With support for multiple hugepage pools at run-time available, much of
+the hugepage userspace interface has been duplicated in sysfs. The above
+information applies to the default hugepage size (which will be
+controlled by the proc interfaces for backwards compatibility). The root
+hugepage control directory is
+        /sys/kernel/mm/hugepages
+For each hugepage size supported by the running kernel, a subdirectory
+will exist, of the form
+        hugepages-${size}kB
+Inside each of these directories, the same set of files will exist:
+        nr_hugepages
+        nr_overcommit_hugepages
+        free_hugepages
+        resv_hugepages
+        surplus_hugepages
+which function as described above for the default hugepage-sized case.
 If the user applications are going to request hugepages using mmap system
 call, then it is required that system administrator mount a file system of
 type hugetlbfs:
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index bad16d3f6a47..6aaaeb38730c 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -58,7 +58,7 @@ most general to most specific:
        the policy at the time they were allocated.
    VMA Policy:  A "VMA" or "Virtual Memory Area" refers to a range of a task's
-    virtual adddress space.  A task may define a specific policy for a range
+    virtual address space.  A task may define a specific policy for a range
    of its virtual address space.   See the MEMORY POLICIES APIS section,
    below, for an overview of the mbind() system call used to set a VMA
    policy.
@@ -353,7 +353,7 @@ follows:
   Because of this extra reference counting, and because we must lookup
   shared policies in a tree structure under spinlock, shared policies are
-   more expensive to use in the page allocation path.  This is expecially
+   more expensive to use in the page allocation path.  This is especially
   true for shared policies on shared memory regions shared by tasks running
   on different NUMA nodes.  This extra overhead can be avoided by always
   falling back to task or system default policy for shared memory regions,
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration
index 99f89aa10169..d5fdfd34bbaf 100644
--- a/Documentation/vm/page_migration
+++ b/Documentation/vm/page_migration
@@ -18,10 +18,11 @@ migrate_pages function call takes two sets of nodes and moves pages of a
 process that are located on the from nodes to the destination nodes.
 Page migration functions are provided by the numactl package by Andi Kleen
 (a version later than 0.9.3 is required. Get it from
-ftp://ftp.suse.com/pub/people/ak). numactl provided libnuma which
+ftp://oss.sgi.com/www/projects/libnuma/download/). numactl provides libnuma
-provides an interface similar to other numa functionality for page migration.
+which provides an interface similar to other numa functionality for page
-cat /proc/<pid>/numa_maps allows an easy review of where the pages of
+migration.  cat /proc/<pid>/numa_maps allows an easy review of where the
-a process are located. See also the numa_maps manpage in the numactl package.
+pages of a process are located. See also the numa_maps documentation in the
+proc(5) man page.
 Manual migration is useful if for example the scheduler has relocated
 a process to a processor on a distant node. A batch scheduler or an
diff --git a/Documentation/vm/unevictable-lru.txt b/Documentation/vm/unevictable-lru.txt
new file mode 100644
index 000000000000..125eed560e5a
--- /dev/null
+++ b/Documentation/vm/unevictable-lru.txt
@@ -0,0 +1,615 @@
+This document describes the Linux memory management "Unevictable LRU"
+infrastructure and the use of this infrastructure to manage several types
+of "unevictable" pages.  The document attempts to provide the overall
+rationale behind this mechanism and the rationale for some of the design
+decisions that drove the implementation.  The latter design rationale is
+discussed in the context of an implementation description.  Admittedly, one
+can obtain the implementation details--the "what does it do?"--by reading the
+code.  One hopes that the descriptions below add value by provide the answer
+to "why does it do that?".
+Unevictable LRU Infrastructure:
+The Unevictable LRU adds an additional LRU list to track unevictable pages
+and to hide these pages from vmscan.  This mechanism is based on a patch by
+Larry Woodman of Red Hat to address several scalability problems with page
+reclaim in Linux.  The problems have been observed at customer sites on large
+memory x86_64 systems.  For example, a non-numal x86_64 platform with 128GB
+of main memory will have over 32 million 4k pages in a single zone.  When a
+large fraction of these pages are not evictable for any reason [see below],
+vmscan will spend a lot of time scanning the LRU lists looking for the small
+fraction of pages that are evictable.  This can result in a situation where
+all cpus are spending 100% of their time in vmscan for hours or days on end,
+with the system completely unresponsive.
+The Unevictable LRU infrastructure addresses the following classes of
+unevictable pages:
+ page owned by ramfs
+ page mapped into SHM_LOCKed shared memory regions
+ page mapped into VM_LOCKED [mlock()ed] vmas
+The infrastructure might be able to handle other conditions that make pages
+unevictable, either by definition or by circumstance, in the future.
+The Unevictable LRU List
+The Unevictable LRU infrastructure consists of an additional, per-zone, LRU list
+called the "unevictable" list and an associated page flag, PG_unevictable, to
+indicate that the page is being managed on the unevictable list.  The
+PG_unevictable flag is analogous to, and mutually exclusive with, the PG_active
+flag in that it indicates on which LRU list a page resides when PG_lru is set.
+The unevictable LRU list is source configurable based on the UNEVICTABLE_LRU
+Kconfig option.
+The Unevictable LRU infrastructure maintains unevictable pages on an additional
+LRU list for a few reasons:
+1) We get to "treat unevictable pages just like we treat other pages in the
+   system, which means we get to use the same code to manipulate them, the
+   same code to isolate them (for migrate, etc.), the same code to keep track
+   of the statistics, etc..." [Rik van Riel]
+2) We want to be able to migrate unevictable pages between nodes--for memory
+   defragmentation, workload management and memory hotplug.  The linux kernel
+   can only migrate pages that it can successfully isolate from the lru lists.
+   If we were to maintain pages elsewise than on an lru-like list, where they
+   can be found by isolate_lru_page(), we would prevent their migration, unless
+   we reworked migration code to find the unevictable pages.
+The unevictable LRU list does not differentiate between file backed and swap
+backed [anon] pages.  This differentiation is only important while the pages
+are, in fact, evictable.
+The unevictable LRU list benefits from the "arrayification" of the per-zone
+LRU lists and statistics originally proposed and posted by Christoph Lameter.
+The unevictable list does not use the lru pagevec mechanism. Rather,
+unevictable pages are placed directly on the page's zone's unevictable
+list under the zone lru_lock.  The reason for this is to prevent stranding
+of pages on the unevictable list when one task has the page isolated from the
+lru and other tasks are changing the "evictability" state of the page.
+Unevictable LRU and Memory Controller Interaction
+The memory controller data structure automatically gets a per zone unevictable
+lru list as a result of the "arrayification" of the per-zone LRU lists.  The
+memory controller tracks the movement of pages to and from the unevictable list.
+When a memory control group comes under memory pressure, the controller will
+not attempt to reclaim pages on the unevictable list.  This has a couple of
+effects.  Because the pages are "hidden" from reclaim on the unevictable list,
+the reclaim process can be more efficient, dealing only with pages that have
+a chance of being reclaimed.  On the other hand, if too many of the pages
+charged to the control group are unevictable, the evictable portion of the
+working set of the tasks in the control group may not fit into the available
+memory.  This can cause the control group to thrash or to oom-kill tasks.
+Unevictable LRU:  Detecting Unevictable Pages
+The function page_evictable(page, vma) in vmscan.c determines whether a
+page is evictable or not.  For ramfs pages and pages in SHM_LOCKed regions,
+page_evictable() tests a new address space flag, AS_UNEVICTABLE, in the page's
+address space using a wrapper function.  Wrapper functions are used to set,
+clear and test the flag to reduce the requirement for #ifdef's throughout the
+source code.  AS_UNEVICTABLE is set on ramfs inode/mapping when it is created.
+This flag remains for the life of the inode.
+For shared memory regions, AS_UNEVICTABLE is set when an application
+successfully SHM_LOCKs the region and is removed when the region is
+SHM_UNLOCKed.  Note that shmctl(SHM_LOCK, ...) does not populate the page
+tables for the region as does, for example, mlock().   So, we make no special
+effort to push any pages in the SHM_LOCKed region to the unevictable list.
+Vmscan will do this when/if it encounters the pages during reclaim.  On
+SHM_UNLOCK, shmctl() scans the pages in the region and "rescues" them from the
+unevictable list if no other condition keeps them unevictable.  If a SHM_LOCKed
+region is destroyed, the pages are also "rescued" from the unevictable list in
+the process of freeing them.
+page_evictable() detects mlock()ed pages by testing an additional page flag,
+PG_mlocked via the PageMlocked() wrapper.  If the page is NOT mlocked, and a
+non-NULL vma is supplied, page_evictable() will check whether the vma is
+VM_LOCKED via is_mlocked_vma().  is_mlocked_vma() will SetPageMlocked() and
+update the appropriate statistics if the vma is VM_LOCKED.  This method allows
+efficient "culling" of pages in the fault path that are being faulted in to
+VM_LOCKED vmas.
+Unevictable Pages and Vmscan [shrink_*_list()]
+If unevictable pages are culled in the fault path, or moved to the unevictable
+list at mlock() or mmap() time, vmscan will never encounter the pages until
+they have become evictable again, for example, via munlock() and have been
+"rescued" from the unevictable list.  However, there may be situations where we
+decide, for the sake of expediency, to leave a unevictable page on one of the
+regular active/inactive LRU lists for vmscan to deal with.  Vmscan checks for
+such pages in all of the shrink_{active|inactive|page}_list() functions and
+will "cull" such pages that it encounters--that is, it diverts those pages to
+the unevictable list for the zone being scanned.
+There may be situations where a page is mapped into a VM_LOCKED vma, but the
+page is not marked as PageMlocked.  Such pages will make it all the way to
+shrink_page_list() where they will be detected when vmscan walks the reverse
+map in try_to_unmap().  If try_to_unmap() returns SWAP_MLOCK, shrink_page_list()
+will cull the page at that point.
+Note that for anonymous pages, shrink_page_list() attempts to add the page to
+the swap cache before it tries to unmap the page.  To avoid this unnecessary
+consumption of swap space, shrink_page_list() calls try_to_munlock() to check
+whether any VM_LOCKED vmas map the page without attempting to unmap the page.
+If try_to_munlock() returns SWAP_MLOCK, shrink_page_list() will cull the page
+without consuming swap space.  try_to_munlock() will be described below.
+To "cull" an unevictable page, vmscan simply puts the page back on the lru
+list using putback_lru_page()--the inverse operation to isolate_lru_page()--
+after dropping the page lock.  Because the condition which makes the page
+unevictable may change once the page is unlocked, putback_lru_page() will
+recheck the unevictable state of a page that it places on the unevictable lru
+list.  If the page has become unevictable, putback_lru_page() removes it from
+the list and retries, including the page_unevictable() test.  Because such a
+race is a rare event and movement of pages onto the unevictable list should be
+rare, these extra evictabilty checks should not occur in the majority of calls
+to putback_lru_page().
+Mlocked Page:  Prior Work
+The "Unevictable Mlocked Pages" infrastructure is based on work originally
+posted by Nick Piggin in an RFC patch entitled "mm: mlocked pages off LRU".
+Nick posted his patch as an alternative to a patch posted by Christoph
+Lameter to achieve the same objective--hiding mlocked pages from vmscan.
+In Nick's patch, he used one of the struct page lru list link fields as a count
+of VM_LOCKED vmas that map the page.  This use of the link field for a count
+prevented the management of the pages on an LRU list.  Thus, mlocked pages were
+not migratable as isolate_lru_page() could not find them and the lru list link
+field was not available to the migration subsystem.  Nick resolved this by
+putting mlocked pages back on the lru list before attempting to isolate them,
+thus abandoning the count of VM_LOCKED vmas.  When Nick's patch was integrated
+with the Unevictable LRU work, the count was replaced by walking the reverse
+map to determine whether any VM_LOCKED vmas mapped the page.  More on this
+below.
+Mlocked Pages:  Basic Management
+Mlocked pages--pages mapped into a VM_LOCKED vma--represent one class of
+unevictable pages.  When such a page has been "noticed" by the memory
+management subsystem, the page is marked with the PG_mlocked [PageMlocked()]
+flag.  A PageMlocked() page will be placed on the unevictable LRU list when
+it is added to the LRU.   Pages can be "noticed" by memory management in
+several places:
+1) in the mlock()/mlockall() system call handlers.
+2) in the mmap() system call handler when mmap()ing a region with the
+   MAP_LOCKED flag, or mmap()ing a region in a task that has called
+   mlockall() with the MCL_FUTURE flag.  Both of these conditions result
+   in the VM_LOCKED flag being set for the vma.
+3) in the fault path, if mlocked pages are "culled" in the fault path,
+   and when a VM_LOCKED stack segment is expanded.
+4) as mentioned above, in vmscan:shrink_page_list() with attempting to
+   reclaim a page in a VM_LOCKED vma--via try_to_unmap() or try_to_munlock().
+Mlocked pages become unlocked and rescued from the unevictable list when:
+1) mapped in a range unlocked via the munlock()/munlockall() system calls.
+2) munmapped() out of the last VM_LOCKED vma that maps the page, including
+   unmapping at task exit.
+3) when the page is truncated from the last VM_LOCKED vma of an mmap()ed file.
+4) before a page is COWed in a VM_LOCKED vma.
+Mlocked Pages:  mlock()/mlockall() System Call Handling
+Both [do_]mlock() and [do_]mlockall() system call handlers call mlock_fixup()
+for each vma in the range specified by the call.  In the case of mlockall(),
+this is the entire active address space of the task.  Note that mlock_fixup()
+is used for both mlock()ing and munlock()ing a range of memory.  A call to
+mlock() an already VM_LOCKED vma, or to munlock() a vma that is not VM_LOCKED
+is treated as a no-op--mlock_fixup() simply returns.
+If the vma passes some filtering described in "Mlocked Pages:  Filtering Vmas"
+below, mlock_fixup() will attempt to merge the vma with its neighbors or split
+off a subset of the vma if the range does not cover the entire vma.  Once the
+vma has been merged or split or neither, mlock_fixup() will call
+__mlock_vma_pages_range() to fault in the pages via get_user_pages() and
+to mark the pages as mlocked via mlock_vma_page().
+Note that the vma being mlocked might be mapped with PROT_NONE.  In this case,
+get_user_pages() will be unable to fault in the pages.  That's OK.  If pages
+do end up getting faulted into this VM_LOCKED vma, we'll handle them in the
+fault path or in vmscan.
+Also note that a page returned by get_user_pages() could be truncated or
+migrated out from under us, while we're trying to mlock it.  To detect
+this, __mlock_vma_pages_range() tests the page_mapping after acquiring
+the page lock.  If the page is still associated with its mapping, we'll
+go ahead and call mlock_vma_page().  If the mapping is gone, we just
+unlock the page and move on.  Worse case, this results in page mapped
+in a VM_LOCKED vma remaining on a normal LRU list without being
+PageMlocked().  Again, vmscan will detect and cull such pages.
+mlock_vma_page(), called with the page locked [N.B., not "mlocked"], will
+TestSetPageMlocked() for each page returned by get_user_pages().  We use
+TestSetPageMlocked() because the page might already be mlocked by another
+task/vma and we don't want to do extra work.  We especially do not want to
+count an mlocked page more than once in the statistics.  If the page was
+already mlocked, mlock_vma_page() is done.
+If the page was NOT already mlocked, mlock_vma_page() attempts to isolate the
+page from the LRU, as it is likely on the appropriate active or inactive list
+at that time.  If the isolate_lru_page() succeeds, mlock_vma_page() will
+putback the page--putback_lru_page()--which will notice that the page is now
+mlocked and divert the page to the zone's unevictable LRU list.  If
+mlock_vma_page() is unable to isolate the page from the LRU, vmscan will handle
+it later if/when it attempts to reclaim the page.
+Mlocked Pages:  Filtering Special Vmas
+mlock_fixup() filters several classes of "special" vmas:
+1) vmas with VM_IO|VM_PFNMAP set are skipped entirely.  The pages behind
+   these mappings are inherently pinned, so we don't need to mark them as
+   mlocked.  In any case, most of the pages have no struct page in which to
+   so mark the page.  Because of this, get_user_pages() will fail for these
+   vmas, so there is no sense in attempting to visit them.
+2) vmas mapping hugetlbfs page are already effectively pinned into memory.
+   We don't need nor want to mlock() these pages.  However, to preserve the
+   prior behavior of mlock()--before the unevictable/mlock changes--mlock_fixup()
+   will call make_pages_present() in the hugetlbfs vma range to allocate the
+   huge pages and populate the ptes.
+3) vmas with VM_DONTEXPAND|VM_RESERVED are generally user space mappings of
+   kernel pages, such as the vdso page, relay channel pages, etc.  These pages
+   are inherently unevictable and are not managed on the LRU lists.
+   mlock_fixup() treats these vmas the same as hugetlbfs vmas.  It calls
+   make_pages_present() to populate the ptes.
+Note that for all of these special vmas, mlock_fixup() does not set the
+VM_LOCKED flag.  Therefore, we won't have to deal with them later during
+munlock() or munmap()--for example, at task exit.  Neither does mlock_fixup()
+account these vmas against the task's "locked_vm".
+Mlocked Pages:  Downgrading the Mmap Semaphore.
+mlock_fixup() must be called with the mmap semaphore held for write, because
+it may have to merge or split vmas.  However, mlocking a large region of
+memory can take a long time--especially if vmscan must reclaim pages to
+satisfy the regions requirements.  Faulting in a large region with the mmap
+semaphore held for write can hold off other faults on the address space, in
+the case of a multi-threaded task.  It can also hold off scans of the task's
+address space via /proc.  While testing under heavy load, it was observed that
+the ps(1) command could be held off for many minutes while a large segment was
+mlock()ed down.
+To address this issue, and to make the system more responsive during mlock()ing
+of large segments, mlock_fixup() downgrades the mmap semaphore to read mode
+during the call to __mlock_vma_pages_range().  This works fine.  However, the
+callers of mlock_fixup() expect the semaphore to be returned in write mode.
+So, mlock_fixup() "upgrades" the semphore to write mode.  Linux does not
+support an atomic upgrade_sem() call, so mlock_fixup() must drop the semaphore
+and reacquire it in write mode.  In a multi-threaded task, it is possible for
+the task memory map to change while the semaphore is dropped.  Therefore,
+mlock_fixup() looks up the vma at the range start address after reacquiring
+the semaphore in write mode and verifies that it still covers the original
+range.  If not, mlock_fixup() returns an error [-EAGAIN].  All callers of
+mlock_fixup() have been changed to deal with this new error condition.
+Note:  when munlocking a region, all of the pages should already be resident--
+unless we have racing threads mlocking() and munlocking() regions.  So,
+unlocking should not have to wait for page allocations nor faults  of any kind.
+Therefore mlock_fixup() does not downgrade the semaphore for munlock().
+Mlocked Pages:  munlock()/munlockall() System Call Handling
+The munlock() and munlockall() system calls are handled by the same functions--
+do_mlock[all]()--as the mlock() and mlockall() system calls with the unlock
+vs lock operation indicated by an argument.  So, these system calls are also
+handled by mlock_fixup().  Again, if called for an already munlock()ed vma,
+mlock_fixup() simply returns.  Because of the vma filtering discussed above,
+VM_LOCKED will not be set in any "special" vmas.  So, these vmas will be
+ignored for munlock.
+If the vma is VM_LOCKED, mlock_fixup() again attempts to merge or split off
+the specified range.  The range is then munlocked via the function
+__mlock_vma_pages_range()--the same function used to mlock a vma range--
+passing a flag to indicate that munlock() is being performed.
+Because the vma access protections could have been changed to PROT_NONE after
+faulting in and mlocking some pages, get_user_pages() was unreliable for visiting
+these pages for munlocking.  Because we don't want to leave pages mlocked(),
+get_user_pages() was enhanced to accept a flag to ignore the permissions when
+fetching the pages--all of which should be resident as a result of previous
+mlock()ing.
+For munlock(), __mlock_vma_pages_range() unlocks individual pages by calling
+munlock_vma_page().  munlock_vma_page() unconditionally clears the PG_mlocked
+flag using TestClearPageMlocked().  As with mlock_vma_page(), munlock_vma_page()
+use the Test*PageMlocked() function to handle the case where the page might
+have already been unlocked by another task.  If the page was mlocked,
+munlock_vma_page() updates that zone statistics for the number of mlocked
+pages.  Note, however, that at this point we haven't checked whether the page
+is mapped by other VM_LOCKED vmas.
+We can't call try_to_munlock(), the function that walks the reverse map to check
+for other VM_LOCKED vmas, without first isolating the page from the LRU.
+try_to_munlock() is a variant of try_to_unmap() and thus requires that the page
+not be on an lru list.  [More on these below.]  However, the call to
+isolate_lru_page() could fail, in which case we couldn't try_to_munlock().
+So, we go ahead and clear PG_mlocked up front, as this might be the only chance
+we have.  If we can successfully isolate the page, we go ahead and
+try_to_munlock(), which will restore the PG_mlocked flag and update the zone
+page statistics if it finds another vma holding the page mlocked.  If we fail
+to isolate the page, we'll have left a potentially mlocked page on the LRU.
+This is fine, because we'll catch it later when/if vmscan tries to reclaim the
+page.  This should be relatively rare.
+Mlocked Pages:  Migrating Them...
+A page that is being migrated has been isolated from the lru lists and is
+held locked across unmapping of the page, updating the page's mapping
+[address_space] entry and copying the contents and state, until the
+page table entry has been replaced with an entry that refers to the new
+page.  Linux supports migration of mlocked pages and other unevictable
+pages.  This involves simply moving the PageMlocked and PageUnevictable states
+from the old page to the new page.
+Note that page migration can race with mlocking or munlocking of the same
+page.  This has been discussed from the mlock/munlock perspective in the
+respective sections above.  Both processes [migration, m[un]locking], hold
+the page locked.  This provides the first level of synchronization.  Page
+migration zeros out the page_mapping of the old page before unlocking it,
+so m[un]lock can skip these pages by testing the page mapping under page
+lock.
+When completing page migration, we place the new and old pages back onto the
+lru after dropping the page lock.  The "unneeded" page--old page on success,
+new page on failure--will be freed when the reference count held by the
+migration process is released.  To ensure that we don't strand pages on the
+unevictable list because of a race between munlock and migration, page
+migration uses the putback_lru_page() function to add migrated pages back to
+the lru.
+Mlocked Pages:  mmap(MAP_LOCKED) System Call Handling
+In addition the the mlock()/mlockall() system calls, an application can request
+that a region of memory be mlocked using the MAP_LOCKED flag with the mmap()
+call.  Furthermore, any mmap() call or brk() call that expands the heap by a
+task that has previously called mlockall() with the MCL_FUTURE flag will result
+in the newly mapped memory being mlocked.  Before the unevictable/mlock changes,
+the kernel simply called make_pages_present() to allocate pages and populate
+the page table.
+To mlock a range of memory under the unevictable/mlock infrastructure, the
+mmap() handler and task address space expansion functions call
+mlock_vma_pages_range() specifying the vma and the address range to mlock.
+mlock_vma_pages_range() filters vmas like mlock_fixup(), as described above in
+"Mlocked Pages:  Filtering Vmas".  It will clear the VM_LOCKED flag, which will
+have already been set by the caller, in filtered vmas.  Thus these vma's need
+not be visited for munlock when the region is unmapped.
+For "normal" vmas, mlock_vma_pages_range() calls __mlock_vma_pages_range() to
+fault/allocate the pages and mlock them.  Again, like mlock_fixup(),
+mlock_vma_pages_range() downgrades the mmap semaphore to read mode before
+attempting to fault/allocate and mlock the pages; and "upgrades" the semaphore
+back to write mode before returning.
+The callers of mlock_vma_pages_range() will have already added the memory
+range to be mlocked to the task's "locked_vm".  To account for filtered vmas,
+mlock_vma_pages_range() returns the number of pages NOT mlocked.  All of the
+callers then subtract a non-negative return value from the task's locked_vm.
+A negative return value represent an error--for example, from get_user_pages()
+attempting to fault in a vma with PROT_NONE access.  In this case, we leave
+the memory range accounted as locked_vm, as the protections could be changed
+later and pages allocated into that region.
+Mlocked Pages:  munmap()/exit()/exec() System Call Handling
+When unmapping an mlocked region of memory, whether by an explicit call to
+munmap() or via an internal unmap from exit() or exec() processing, we must
+munlock the pages if we're removing the last VM_LOCKED vma that maps the pages.
+Before the unevictable/mlock changes, mlocking did not mark the pages in any way,
+so unmapping them required no processing.
+To munlock a range of memory under the unevictable/mlock infrastructure, the
+munmap() hander and task address space tear down function call
+munlock_vma_pages_all().  The name reflects the observation that one always
+specifies the entire vma range when munlock()ing during unmap of a region.
+Because of the vma filtering when mlocking() regions, only "normal" vmas that
+actually contain mlocked pages will be passed to munlock_vma_pages_all().
+munlock_vma_pages_all() clears the VM_LOCKED vma flag and, like mlock_fixup()
+for the munlock case, calls __munlock_vma_pages_range() to walk the page table
+for the vma's memory range and munlock_vma_page() each resident page mapped by
+the vma.  This effectively munlocks the page, only if this is the last
+VM_LOCKED vma that maps the page.
+Mlocked Page:  try_to_unmap()
+[Note:  the code changes represented by this section are really quite small
+compared to the text to describe what happening and why, and to discuss the
+implications.]
+Pages can, of course, be mapped into multiple vmas.  Some of these vmas may
+have VM_LOCKED flag set.  It is possible for a page mapped into one or more
+VM_LOCKED vmas not to have the PG_mlocked flag set and therefore reside on one
+of the active or inactive LRU lists.  This could happen if, for example, a
+task in the process of munlock()ing the page could not isolate the page from
+the LRU.  As a result, vmscan/shrink_page_list() might encounter such a page
+as described in "Unevictable Pages and Vmscan [shrink_*_list()]".  To
+handle this situation, try_to_unmap() has been enhanced to check for VM_LOCKED
+vmas while it is walking a page's reverse map.
+try_to_unmap() is always called, by either vmscan for reclaim or for page
+migration, with the argument page locked and isolated from the LRU.  BUG_ON()
+assertions enforce this requirement.  Separate functions handle anonymous and
+mapped file pages, as these types of pages have different reverse map
+mechanisms.
+        try_to_unmap_anon()
+To unmap anonymous pages, each vma in the list anchored in the anon_vma must be
+visited--at least until a VM_LOCKED vma is encountered.  If the page is being
+unmapped for migration, VM_LOCKED vmas do not stop the process because mlocked
+pages are migratable.  However, for reclaim, if the page is mapped into a
+VM_LOCKED vma, the scan stops.  try_to_unmap() attempts to acquire the mmap
+semphore of the mm_struct to which the vma belongs in read mode.  If this is
+successful, try_to_unmap() will mlock the page via mlock_vma_page()--we
+wouldn't have gotten to try_to_unmap() if the page were already mlocked--and
+will return SWAP_MLOCK, indicating that the page is unevictable.  If the
+mmap semaphore cannot be acquired, we are not sure whether the page is really
+unevictable or not.  In this case, try_to_unmap() will return SWAP_AGAIN.
+        try_to_unmap_file() -- linear mappings
+Unmapping of a mapped file page works the same, except that the scan visits
+all vmas that maps the page's index/page offset in the page's mapping's
+reverse map priority search tree.  It must also visit each vma in the page's
+mapping's non-linear list, if the list is non-empty.  As for anonymous pages,
+on encountering a VM_LOCKED vma for a mapped file page, try_to_unmap() will
+attempt to acquire the associated mm_struct's mmap semaphore to mlock the page,
+returning SWAP_MLOCK if this is successful, and SWAP_AGAIN, if not.
+        try_to_unmap_file() -- non-linear mappings
+If a page's mapping contains a non-empty non-linear mapping vma list, then
+try_to_un{map|lock}() must also visit each vma in that list to determine
+whether the page is mapped in a VM_LOCKED vma.  Again, the scan must visit
+all vmas in the non-linear list to ensure that the pages is not/should not be
+mlocked.  If a VM_LOCKED vma is found in the list, the scan could terminate.
+However, there is no easy way to determine whether the page is actually mapped
+in a given vma--either for unmapping or testing whether the VM_LOCKED vma
+actually pins the page.
+So, try_to_unmap_file() handles non-linear mappings by scanning a certain
+number of pages--a "cluster"--in each non-linear vma associated with the page's
+mapping, for each file mapped page that vmscan tries to unmap.  If this happens
+to unmap the page we're trying to unmap, try_to_unmap() will notice this on
+return--(page_mapcount(page) == 0)--and return SWAP_SUCCESS.  Otherwise, it
+will return SWAP_AGAIN, causing vmscan to recirculate this page.  We take
+advantage of the cluster scan in try_to_unmap_cluster() as follows:
+For each non-linear vma, try_to_unmap_cluster() attempts to acquire the mmap
+semaphore of the associated mm_struct for read without blocking.  If this
+attempt is successful and the vma is VM_LOCKED, try_to_unmap_cluster() will
+retain the mmap semaphore for the scan; otherwise it drops it here.  Then,
+for each page in the cluster, if we're holding the mmap semaphore for a locked
+vma, try_to_unmap_cluster() calls mlock_vma_page() to mlock the page.  This
+call is a no-op if the page is already locked, but will mlock any pages in
+the non-linear mapping that happen to be unlocked.  If one of the pages so
+mlocked is the page passed in to try_to_unmap(), try_to_unmap_cluster() will
+return SWAP_MLOCK, rather than the default SWAP_AGAIN.  This will allow vmscan
+to cull the page, rather than recirculating it on the inactive list.  Again,
+if try_to_unmap_cluster() cannot acquire the vma's mmap sem, it returns
+SWAP_AGAIN, indicating that the page is mapped by a VM_LOCKED vma, but
+couldn't be mlocked.
+Mlocked pages:  try_to_munlock() Reverse Map Scan
+TODO/FIXME:  a better name might be page_mlocked()--analogous to the
+page_referenced() reverse map walker--especially if we continue to call this
+from shrink_page_list().  See related TODO/FIXME below.
+When munlock_vma_page()--see "Mlocked Pages:  munlock()/munlockall() System
+Call Handling" above--tries to munlock a page, or when shrink_page_list()
+encounters an anonymous page that is not yet in the swap cache, they need to
+determine whether or not the page is mapped by any VM_LOCKED vma, without
+actually attempting to unmap all ptes from the page.  For this purpose, the
+unevictable/mlock infrastructure introduced a variant of try_to_unmap() called
+try_to_munlock().
+try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
+mapped file pages with an additional argument specifing unlock versus unmap
+processing.  Again, these functions walk the respective reverse maps looking
+for VM_LOCKED vmas.  When such a vma is found for anonymous pages and file
+pages mapped in linear VMAs, as in the try_to_unmap() case, the functions
+attempt to acquire the associated mmap semphore, mlock the page via
+mlock_vma_page() and return SWAP_MLOCK.  This effectively undoes the
+pre-clearing of the page's PG_mlocked done by munlock_vma_page() and informs
+shrink_page_list() that the anonymous page should be culled rather than added
+to the swap cache in preparation for a try_to_unmap() that will almost
+certainly fail.
+If try_to_unmap() is unable to acquire a VM_LOCKED vma's associated mmap
+semaphore, it will return SWAP_AGAIN.  This will allow shrink_page_list()
+to recycle the page on the inactive list and hope that it has better luck
+with the page next time.
+For file pages mapped into non-linear vmas, the try_to_munlock() logic works
+slightly differently.  On encountering a VM_LOCKED non-linear vma that might
+map the page, try_to_munlock() returns SWAP_AGAIN without actually mlocking
+the page.  munlock_vma_page() will just leave the page unlocked and let
+vmscan deal with it--the usual fallback position.
+Note that try_to_munlock()'s reverse map walk must visit every vma in a pages'
+reverse map to determine that a page is NOT mapped into any VM_LOCKED vma.
+However, the scan can terminate when it encounters a VM_LOCKED vma and can
+successfully acquire the vma's mmap semphore for read and mlock the page.
+Although try_to_munlock() can be called many [very many!] times when
+munlock()ing a large region or tearing down a large address space that has been
+mlocked via mlockall(), overall this is a fairly rare event.  In addition,
+although shrink_page_list() calls try_to_munlock() for every anonymous page that
+it handles that is not yet in the swap cache, on average anonymous pages will
+have very short reverse map lists.
+Mlocked Page:  Page Reclaim in shrink_*_list()
+shrink_active_list() culls any obviously unevictable pages--i.e.,
+!page_evictable(page, NULL)--diverting these to the unevictable lru
+list.  However, shrink_active_list() only sees unevictable pages that
+made it onto the active/inactive lru lists.  Note that these pages do not
+have PageUnevictable set--otherwise, they would be on the unevictable list and
+shrink_active_list would never see them.
+Some examples of these unevictable pages on the LRU lists are:
+1) ramfs pages that have been placed on the lru lists when first allocated.
+2) SHM_LOCKed shared memory pages.  shmctl(SHM_LOCK) does not attempt to
+   allocate or fault in the pages in the shared memory region.  This happens
+   when an application accesses the page the first time after SHM_LOCKing
+   the segment.
+3) Mlocked pages that could not be isolated from the lru and moved to the
+   unevictable list in mlock_vma_page().
+3) Pages mapped into multiple VM_LOCKED vmas, but try_to_munlock() couldn't
+   acquire the vma's mmap semaphore to test the flags and set PageMlocked.
+   munlock_vma_page() was forced to let the page back on to the normal
+   LRU list for vmscan to handle.
+shrink_inactive_list() also culls any unevictable pages that it finds
+on the inactive lists, again diverting them to the appropriate zone's unevictable
+lru list.  shrink_inactive_list() should only see SHM_LOCKed pages that became
+SHM_LOCKed after shrink_active_list() had moved them to the inactive list, or
+pages mapped into VM_LOCKED vmas that munlock_vma_page() couldn't isolate from
+the lru to recheck via try_to_munlock().  shrink_inactive_list() won't notice
+the latter, but will pass on to shrink_page_list().
+shrink_page_list() again culls obviously unevictable pages that it could
+encounter for similar reason to shrink_inactive_list().  As already discussed,
+shrink_page_list() proactively looks for anonymous pages that should have
+PG_mlocked set but don't--these would not be detected by page_evictable()--to
+avoid adding them to the swap cache unnecessarily.  File pages mapped into
+VM_LOCKED vmas but without PG_mlocked set will make it all the way to
+try_to_unmap().  shrink_page_list() will divert them to the unevictable list when
+try_to_unmap() returns SWAP_MLOCK, as discussed above.
+TODO/FIXME:  If we can enhance the swap cache to reliably remove entries
+with page_count(page) > 2, as long as all ptes are mapped to the page and
+not the swap entry, we can probably remove the call to try_to_munlock() in
+shrink_page_list() and just remove the page from the swap cache when
+try_to_unmap() returns SWAP_MLOCK.   Currently, remove_exclusive_swap_page()
+doesn't seem to allow that.
diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt
index 10c2e411cca8..991c26a6ef64 100644
--- a/Documentation/volatile-considered-harmful.txt
+++ b/Documentation/volatile-considered-harmful.txt
@@ -114,6 +114,6 @@ CREDITS
 Original impetus and research by Randy Dunlap
 Written by Jonathan Corbet
-Improvements via coments from Satyam Sharma, Johannes Stezenbach, Jesper
+Improvements via comments from Satyam Sharma, Johannes Stezenbach, Jesper
        Juhl, Heikki Orsila, H. Peter Anvin, Philipp Hahn, and Stefan
        Richter.
diff --git a/Documentation/w1/00-INDEX b/Documentation/w1/00-INDEX
index 5270cf4cb109..cb49802745dc 100644
--- a/Documentation/w1/00-INDEX
+++ b/Documentation/w1/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
        - This file
+slaves/
+        - Drivers that provide support for specific family codes.
 masters/
        - Individual chips providing 1-wire busses.
 w1.generic
diff --git a/Documentation/w1/masters/ds2490 b/Documentation/w1/masters/ds2490
index 239f9ae01843..28176def3d6f 100644
--- a/Documentation/w1/masters/ds2490
+++ b/Documentation/w1/masters/ds2490
@@ -16,3 +16,55 @@ which allows to build USB <-> W1 bridges.
 DS9490(R) is a USB <-> W1 bus master device
 which has 0x81 family ID integrated chip and DS2490
 low-level operational chip.
+Notes and limitations.
+- The weak pullup current is a minimum of 0.9mA and maximum of 6.0mA.
+- The 5V strong pullup is supported with a minimum of 5.9mA and a
+  maximum of 30.4 mA.  (From DS2490.pdf)
+- While the ds2490 supports a hardware search the code doesn't take
+  advantage of it (in tested case it only returned first device).
+- The hardware will detect when devices are attached to the bus on the
+  next bus (reset?) operation, however only a message is printed as
+  the core w1 code doesn't make use of the information.  Connecting
+  one device tends to give multiple new device notifications.
+- The number of USB bus transactions could be reduced if w1_reset_send
+  was added to the API.  The name is just a suggestion.  It would take
+  a write buffer and a read buffer (along with sizes) as arguments.
+  The ds2490 block I/O command supports reset, write buffer, read
+  buffer, and strong pullup all in one command, instead of the current
+  1 reset bus, 2 write the match rom command and slave rom id, 3 block
+  write and read data.  The write buffer needs to have the match rom
+  command and slave rom id prepended to the front of the requested
+  write buffer, both of which are known to the driver.
+- The hardware supports normal, flexible, and overdrive bus
+  communication speeds, but only the normal is supported.
+- The registered w1_bus_master functions don't define error
+  conditions.  If a bus search is in progress and the ds2490 is
+  removed it can produce a good amount of error output before the bus
+  search finishes.
+- The hardware supports detecting some error conditions, such as
+  short, alarming presence on reset, and no presence on reset, but the
+  driver doesn't query those values.
+- The ds2490 specification doesn't cover short bulk in reads in
+  detail, but my observation is if fewer bytes are requested than are
+  available, the bulk read will return an error and the hardware will
+  clear the entire bulk in buffer.  It would be possible to read the
+  maximum buffer size to not run into this error condition, only extra
+  bytes in the buffer is a logic error in the driver.  The code should
+  should match reads and writes as well as data sizes.  Reads and
+  writes are serialized and the status verifies that the chip is idle
+  (and data is available) before the read is executed, so it should
+  not happen.
+- Running x86_64 2.6.24 UHCI under qemu 0.9.0 under x86_64 2.6.22-rc6
+  with a OHCI controller, ds2490 running in the guest would operate
+  normally the first time the module was loaded after qemu attached
+  the ds2490 hardware, but if the module was unloaded, then reloaded
+  most of the time one of the bulk out or in, and usually the bulk in
+  would fail.  qemu sets a 50ms timeout and the bulk in would timeout
+  even when the status shows data available.  A bulk out write would
+  show a successful completion, but the ds2490 status register would
+  show 0 bytes written.  Detaching qemu from the ds2490 hardware and
+  reattaching would clear the problem.  usbmon output in the guest and
+  host did not explain the problem.  My guess is a bug in either qemu
+  or the host OS and more likely the host OS.
+-- 03-06-2008 David Fries <David@Fries.net>
diff --git a/Documentation/w1/slaves/00-INDEX b/Documentation/w1/slaves/00-INDEX
new file mode 100644
index 000000000000..f8101d6b07b7
--- /dev/null
+++ b/Documentation/w1/slaves/00-INDEX
@@ -0,0 +1,4 @@
+00-INDEX
+        - This file
+w1_therm
+        - The Maxim/Dallas Semiconductor ds18*20 temperature sensor.
diff --git a/Documentation/w1/slaves/w1_therm b/Documentation/w1/slaves/w1_therm
new file mode 100644
index 000000000000..0403aaaba878
--- /dev/null
+++ b/Documentation/w1/slaves/w1_therm
@@ -0,0 +1,41 @@
+Kernel driver w1_therm
+====================
+Supported chips:
+  * Maxim ds18*20 based temperature sensors.
+Author: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+Description
+-----------
+w1_therm provides basic temperature conversion for ds18*20 devices.
+supported family codes:
+W1_THERM_DS18S20        0x10
+W1_THERM_DS1822         0x22
+W1_THERM_DS18B20        0x28
+Support is provided through the sysfs w1_slave file.  Each open and
+read sequence will initiate a temperature conversion then provide two
+lines of ASCII output.  The first line contains the nine hex bytes
+read along with a calculated crc value and YES or NO if it matched.
+If the crc matched the returned values are retained.  The second line
+displays the retained values along with a temperature in millidegrees
+Centigrade after t=.
+Parasite powered devices are limited to one slave performing a
+temperature conversion at a time.  If none of the devices are parasite
+powered it would be possible to convert all the devices at the same
+time and then go back to read individual sensors.  That isn't
+currently supported.  The driver also doesn't support reduced
+precision (which would also reduce the conversion time).
+The module parameter strong_pullup can be set to 0 to disable the
+strong pullup or 1 to enable.  If enabled the 5V strong pullup will be
+enabled when the conversion is taking place provided the master driver
+must support the strong pullup (or it falls back to a pullup
+resistor).  The DS18b20 temperature sensor specification lists a
+maximum current draw of 1.5mA and that a 5k pullup resistor is not
+sufficient.  The strong pullup is designed to provide the additional
+current required.
diff --git a/Documentation/w1/w1.generic b/Documentation/w1/w1.generic
index 4c6509dd4789..e3333eec4320 100644
--- a/Documentation/w1/w1.generic
+++ b/Documentation/w1/w1.generic
@@ -79,10 +79,13 @@ w1 master sysfs interface
 <xx-xxxxxxxxxxxxx> - a directory for a found device. The format is family-serial
 bus                - (standard) symlink to the w1 bus
 driver             - (standard) symlink to the w1 driver
+w1_master_add      - Manually register a slave device
 w1_master_attempts - the number of times a search was attempted
 w1_master_max_slave_count
                   - the maximum slaves that may be attached to a master
 w1_master_name     - the name of the device (w1_bus_masterX)
+w1_master_pullup   - 5V strong pullup 0 enabled, 1 disabled
+w1_master_remove   - Manually remove a slave device
 w1_master_search   - the number of searches left to do, -1=continual (default)
 w1_master_slave_count
                   - the number of slaves found
@@ -90,7 +93,13 @@ w1_master_slaves   - the names of the slaves, one per line
 w1_master_timeout  - the delay in seconds between searches
 If you have a w1 bus that never changes (you don't add or remove devices),
-you can set w1_master_search to a positive value to disable searches.
+you can set the module parameter search_count to a small positive number
+for an initially small number of bus searches.  Alternatively it could be
+set to zero, then manually add the slave device serial numbers by
+w1_master_add device file.  The w1_master_add and w1_master_remove files
+generally only make sense when searching is disabled, as a search will
+redetect manually removed devices that are present and timeout manually
+added devices that aren't on the bus.
 w1 slave sysfs interface
diff --git a/Documentation/watchdog/src/Makefile b/Documentation/watchdog/src/Makefile
new file mode 100644
index 000000000000..40e5f46e4740
--- /dev/null
+++ b/Documentation/watchdog/src/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+# List of programs to build
+hostprogs-y := watchdog-simple watchdog-test
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX
new file mode 100644
index 000000000000..dbe3377754af
--- /dev/null
+++ b/Documentation/x86/00-INDEX
@@ -0,0 +1,4 @@
+00-INDEX
+        - this file
+mtrr.txt
+        - how to use x86 Memory Type Range Registers to increase performance
diff --git a/Documentation/x86/i386/boot.txt b/Documentation/x86/boot.txt
index 147bfe511cdd..83c0033ee9e0 100644
--- a/Documentation/x86/i386/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -308,7 +308,7 @@ Protocol:	2.00+
 Field name:     start_sys
 Type:           read
-Offset/size:    0x20c/4
+Offset/size:    0x20c/2
 Protocol:       2.00+
  The load low segment (0x1000).  Obsolete.
diff --git a/Documentation/mtrr.txt b/Documentation/x86/mtrr.txt
index c39ac395970e..cc071dc333c2 100644
--- a/Documentation/mtrr.txt
+++ b/Documentation/x86/mtrr.txt
@@ -18,7 +18,7 @@ Richard Gooch
  The AMD K6-2 (stepping 8 and above) and K6-3 processors have two
  MTRRs. These are supported.  The AMD Athlon family provide 8 Intel
  style MTRRs.
-  
  The Centaur C6 (WinChip) has 8 MCRs, allowing write-combining. These
  are supported.
@@ -87,7 +87,7 @@ reg00: base=0x00000000 (   0MB), size=  64MB: write-back, count=1
 reg01: base=0xfb000000 (4016MB), size=  16MB: write-combining, count=1
 reg02: base=0xfb000000 (4016MB), size=   4kB: uncachable, count=1
-Some cards (especially Voodoo Graphics boards) need this 4 kB area 
+Some cards (especially Voodoo Graphics boards) need this 4 kB area
 excluded from the beginning of the region because it is used for
 registers.
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 17965f927c15..c93ff5f4c0dd 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -14,6 +14,10 @@ PAT allows for different types of memory attributes. The most commonly used
 ones that will be supported at this time are Write-back, Uncached,
 Write-combined and Uncached Minus.
+PAT APIs
+--------
 There are many different APIs in the kernel that allows setting of memory
 attributes at the page level. In order to avoid aliasing, these interfaces
 should be used thoughtfully. Below is a table of interfaces available,
@@ -26,38 +30,38 @@ address range to avoid any aliasing.
 API                    |    RAM   |  ACPI,...  |  Reserved/Holes  |
 -----------------------|----------|------------|------------------|
                       |          |            |                  |
-ioremap                |    --    |    UC      |       UC         |
+ioremap                |    --    |    UC-     |       UC-        |
                       |          |            |                  |
 ioremap_cache          |    --    |    WB      |       WB         |
                       |          |            |                  |
-ioremap_nocache        |    --    |    UC      |       UC         |
+ioremap_nocache        |    --    |    UC-     |       UC-        |
                       |          |            |                  |
 ioremap_wc             |    --    |    --      |       WC         |
                       |          |            |                  |
-set_memory_uc          |    UC    |    --      |       --         |
+set_memory_uc          |    UC-   |    --      |       --         |
 set_memory_wb         |          |            |                  |
                       |          |            |                  |
 set_memory_wc          |    WC    |    --      |       --         |
 set_memory_wb         |          |            |                  |
                       |          |            |                  |
-pci sysfs resource     |    --    |    --      |       UC         |
+pci sysfs resource     |    --    |    --      |       UC-        |
                       |          |            |                  |
 pci sysfs resource_wc  |    --    |    --      |       WC         |
 is IORESOURCE_PREFETCH|          |            |                  |
                       |          |            |                  |
-pci proc               |    --    |    --      |       UC         |
+pci proc               |    --    |    --      |       UC-        |
 !PCIIOC_WRITE_COMBINE |          |            |                  |
                       |          |            |                  |
 pci proc               |    --    |    --      |       WC         |
 PCIIOC_WRITE_COMBINE  |          |            |                  |
                       |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
 read-write            |          |            |                  |
                       |          |            |                  |
-/dev/mem               |    --    |    UC      |       UC         |
+/dev/mem               |    --    |    UC-     |       UC-        |
 mmap SYNC flag        |          |            |                  |
                       |          |            |                  |
-/dev/mem               |    --    |  WB/WC/UC  |    WB/WC/UC      |
+/dev/mem               |    --    |  WB/WC/UC- |    WB/WC/UC-     |
 mmap !SYNC flag       |          |(from exist-|  (from exist-    |
 and                   |          |  ing alias)|    ing alias)    |
 any alias to this area|          |            |                  |
@@ -68,7 +72,7 @@ pci proc               |    --    |    --      |       WC         |
 and                   |          |            |                  |
 MTRR says WB          |          |            |                  |
                       |          |            |                  |
-/dev/mem               |    --    |    --      |    UC_MINUS      |
+/dev/mem               |    --    |    --      |       UC-        |
 mmap !SYNC flag       |          |            |                  |
 no alias to this area |          |            |                  |
 and                   |          |            |                  |
@@ -98,3 +102,35 @@ types.
 Drivers should use set_memory_[uc|wc] to set access type for RAM ranges.
+PAT debugging
+-------------
+With CONFIG_DEBUG_FS enabled, PAT memtype list can be examined by
+# mount -t debugfs debugfs /sys/kernel/debug
+# cat /sys/kernel/debug/x86/pat_memtype_list
+PAT memtype list:
+uncached-minus @ 0x7fadf000-0x7fae0000
+uncached-minus @ 0x7fb19000-0x7fb1a000
+uncached-minus @ 0x7fb1a000-0x7fb1b000
+uncached-minus @ 0x7fb1b000-0x7fb1c000
+uncached-minus @ 0x7fb1c000-0x7fb1d000
+uncached-minus @ 0x7fb1d000-0x7fb1e000
+uncached-minus @ 0x7fb1e000-0x7fb25000
+uncached-minus @ 0x7fb25000-0x7fb26000
+uncached-minus @ 0x7fb26000-0x7fb27000
+uncached-minus @ 0x7fb27000-0x7fb28000
+uncached-minus @ 0x7fb28000-0x7fb2e000
+uncached-minus @ 0x7fb2e000-0x7fb2f000
+uncached-minus @ 0x7fb2f000-0x7fb30000
+uncached-minus @ 0x7fb31000-0x7fb32000
+uncached-minus @ 0x80000000-0x90000000
+This list shows physical address ranges and various PAT settings used to
+access those physical address ranges.
+Another, more verbose way of getting PAT related debug messages is with
+"debugpat" boot parameter. With this parameter, various debug messages are
+printed to dmesg log.
diff --git a/Documentation/x86/i386/usb-legacy-support.txt b/Documentation/x86/usb-legacy-support.txt
index 1894cdfc69d9..1894cdfc69d9 100644
--- a/Documentation/x86/i386/usb-legacy-support.txt
+++ b/Documentation/x86/usb-legacy-support.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index b0c7b6c4abda..72ffb5373ec7 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -54,10 +54,6 @@ APICs
                 apicmaintimer. Useful when your PIT timer is totally
                 broken.
-   disable_8254_timer / enable_8254_timer
-                 Enable interrupt 0 timer routing over the 8254 in addition to over
-                 the IO-APIC. The kernel tries to set a sensible default.
 Early Console
   syntax: earlyprintk=vga
diff --git a/Documentation/x86/i386/zero-page.txt b/Documentation/x86/zero-page.txt
index 169ad423a3d1..169ad423a3d1 100644
--- a/Documentation/x86/i386/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
author	Ingo Molnar <mingo@elte.hu>	2008-10-28 11:26:12 -0400
committer	Ingo Molnar <mingo@elte.hu>	2008-10-28 11:26:12 -0400
commit	7a9787e1eba95a166265e6a260cf30af04ef0a99 (patch)
tree	e730a4565e0318140d2fbd2f0415d18a339d7336 /Documentation
parent	41b9eb264c8407655db57b60b4457fe1b2ec9977 (diff)
parent	0173a3265b228da319ceb9c1ec6a5682fd1b2d92 (diff)