177 files changed, 6359 insertions, 2252 deletions

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
new file mode 100644
index 000000000000..49b82cad7003
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -0,0 +1,7 @@
+What:           /sys/devices/system/node/nodeX
+Date:           October 2002
+Contact:        Linux Memory Management list <linux-mm@kvack.org>
+Description:
+                When CONFIG_NUMA is enabled, this is a directory containing
+                information on node X such as what CPUs are local to the
+                node.
diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index d2f90334bb93..4873c759d535 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -128,3 +128,17 @@ Description:
                 preferred request size for workloads where sustained
                 throughput is desired.  If no optimal I/O size is
                 reported this file contains 0.
+
+What:           /sys/block/<disk>/queue/nomerges
+Date:           January 2010
+Contact:
+Description:
+                Standard I/O elevator operations include attempts to
+                merge contiguous I/Os. For known random I/O loads these
+                attempts will always fail and result in extra cycles
+                being spent in the kernel. This allows one to turn off
+                this behavior on one of two ways: When set to 1, complex
+                merge checks are disabled, but the simple one-shot merges
+                with the previous I/O request are enabled. When set to 2,
+                all merge tries are disabled. The default value is 0 -
+                which enables all types of merge tries.
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index a07c0f366f91..bcebb9eaedce 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -159,3 +159,14 @@ Description:
                 device.  This is useful to ensure auto probing won't
                 match the driver to the device.  For example:
                 # echo "046d c315" > /sys/bus/usb/drivers/foo/remove_id
+
+What:           /sys/bus/usb/device/.../avoid_reset_quirk
+Date:           December 2009
+Contact:        Oliver Neukum <oliver@neukum.org>
+Description:
+                Writing 1 to this file tells the kernel that this
+                device will morph into another mode when it is reset.
+                Drivers will not use reset for error handling for
+                such devices.
+Users:
+                usb_modeswitch
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
new file mode 100644
index 000000000000..6123c523bfd7
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -0,0 +1,79 @@
+What:           /sys/devices/.../power/
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power directory contains attributes
+                allowing the user space to check and modify some power
+                management related properties of given device.
+
+What:           /sys/devices/.../power/wakeup
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power/wakeup attribute allows the user
+                space to check if the device is enabled to wake up the system
+                from sleep states, such as the memory sleep state (suspend to
+                RAM) and hibernation (suspend to disk), and to enable or disable
+                it to do that as desired.
+
+                Some devices support "wakeup" events, which are hardware signals
+                used to activate the system from a sleep state.  Such devices
+                have one of the following two values for the sysfs power/wakeup
+                file:
+
+                + "enabled\n" to issue the events;
+                + "disabled\n" not to do so;
+
+                In that cases the user space can change the setting represented
+                by the contents of this file by writing either "enabled", or
+                "disabled" to it.
+
+                For the devices that are not capable of generating system wakeup
+                events this file contains "\n".  In that cases the user space
+                cannot modify the contents of this file and the device cannot be
+                enabled to wake up the system.
+
+What:           /sys/devices/.../power/control
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../power/control attribute allows the user
+                space to control the run-time power management of the device.
+
+                All devices have one of the following two values for the
+                power/control file:
+
+                + "auto\n" to allow the device to be power managed at run time;
+                + "on\n" to prevent the device from being power managed;
+
+                The default for all devices is "auto", which means that they may
+                be subject to automatic power management, depending on their
+                drivers.  Changing this attribute to "on" prevents the driver
+                from power managing the device at run time.  Doing that while
+                the device is suspended causes it to be woken up.
+
+What:           /sys/devices/.../power/async
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../async attribute allows the user space to
+                enable or diasble the device's suspend and resume callbacks to
+                be executed asynchronously (ie. in separate threads, in parallel
+                with the main suspend/resume thread) during system-wide power
+                transitions (eg. suspend to RAM, hibernation).
+
+                All devices have one of the following two values for the
+                power/async file:
+
+                + "enabled\n" to permit the asynchronous suspend/resume;
+                + "disabled\n" to forbid it;
+
+                The value of this attribute may be changed by writing either
+                "enabled", or "disabled" to it.
+
+                It generally is unsafe to permit the asynchronous suspend/resume
+                of a device unless it is certain that all of the PM dependencies
+                of the device are known to the PM core.  However, for some
+                devices this attribute is set to "enabled" by bus type code or
+                device drivers and in that cases it should be safe to leave the
+                default value.
diff --git a/Documentation/ABI/testing/sysfs-platform-asus-laptop b/Documentation/ABI/testing/sysfs-platform-asus-laptop
index a1cb660c50cf..1d775390e856 100644
--- a/Documentation/ABI/testing/sysfs-platform-asus-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-asus-laptop
@@ -1,4 +1,4 @@
-What:           /sys/devices/platform/asus-laptop/display
+What:           /sys/devices/platform/asus_laptop/display
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -13,7 +13,7 @@ Description:
                 Ex: - 0 (0000b) means no display
                     - 3 (0011b) CRT+LCD.
 
-What:           /sys/devices/platform/asus-laptop/gps
+What:           /sys/devices/platform/asus_laptop/gps
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -21,7 +21,7 @@ Description:
                 Control the gps device. 1 means on, 0 means off.
 Users:          Lapsus
 
-What:           /sys/devices/platform/asus-laptop/ledd
+What:           /sys/devices/platform/asus_laptop/ledd
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -29,11 +29,11 @@ Description:
                 Some models like the W1N have a LED display that can be
                 used to display several informations.
                 To control the LED display, use the following :
-                    echo 0x0T000DDD > /sys/devices/platform/asus-laptop/
+                    echo 0x0T000DDD > /sys/devices/platform/asus_laptop/
                 where T control the 3 letters display, and DDD the 3 digits display.
                 The DDD table can be found in Documentation/laptops/asus-laptop.txt
 
-What:           /sys/devices/platform/asus-laptop/bluetooth
+What:           /sys/devices/platform/asus_laptop/bluetooth
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
                 This may control the led, the device or both.
 Users:          Lapsus
 
-What:           /sys/devices/platform/asus-laptop/wlan
+What:           /sys/devices/platform/asus_laptop/wlan
 Date:           January 2007
 KernelVersion:  2.6.20
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
index 7445dfb321b5..5b026c69587a 100644
--- a/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
+++ b/Documentation/ABI/testing/sysfs-platform-eeepc-laptop
@@ -1,4 +1,4 @@
-What:           /sys/devices/platform/eeepc-laptop/disp
+What:           /sys/devices/platform/eeepc/disp
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -9,21 +9,21 @@ Description:
                 - 3 = LCD+CRT
                 If you run X11, you should use xrandr instead.
 
-What:           /sys/devices/platform/eeepc-laptop/camera
+What:           /sys/devices/platform/eeepc/camera
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
 Description:
                 Control the camera. 1 means on, 0 means off.
 
-What:           /sys/devices/platform/eeepc-laptop/cardr
+What:           /sys/devices/platform/eeepc/cardr
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
 Description:
                 Control the card reader. 1 means on, 0 means off.
 
-What:           /sys/devices/platform/eeepc-laptop/cpufv
+What:           /sys/devices/platform/eeepc/cpufv
 Date:           Jun 2009
 KernelVersion:  2.6.31
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
@@ -42,7 +42,7 @@ Description:
                     `------------ Availables modes
                 For example, 0x301 means: mode 1 selected, 3 available modes.
 
-What:           /sys/devices/platform/eeepc-laptop/available_cpufv
+What:           /sys/devices/platform/eeepc/available_cpufv
 Date:           Jun 2009
 KernelVersion:  2.6.31
 Contact:        "Corentin Chary" <corentincj@iksaif.net>
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index dcff4d0623ad..d6a801f45b48 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -101,3 +101,16 @@ Description:
 
                 CAUTION: Using it will cause your machine's real-time (CMOS)
                 clock to be set to a random invalid time after a resume.
+
+What:           /sys/power/pm_async
+Date:           January 2009
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/power/pm_async file controls the switch allowing the
+                user space to enable or disable asynchronous suspend and resume
+                of devices.  If enabled, this feature will cause some device
+                drivers' suspend and resume callbacks to be executed in parallel
+                with each other and with the main suspend thread.  It is enabled
+                if this file contains "1", which is the default.  It may be
+                disabled by writing "0" to this file, in which case all devices
+                will be suspended and resumed synchronously.
diff --git a/Documentation/PCI/PCI-DMA-mapping.txt b/Documentation/DMA-API-HOWTO.txt
index ecad88d9fe59..52618ab069ad 100644
--- a/Documentation/PCI/PCI-DMA-mapping.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -1,12 +1,12 @@
-                        Dynamic DMA mapping
-                        ===================
+                     Dynamic DMA mapping Guide
+                     =========================
 
                  David S. Miller <davem@redhat.com>
                  Richard Henderson <rth@cygnus.com>
                   Jakub Jelinek <jakub@redhat.com>
 
-This document describes the DMA mapping system in terms of the pci_
-API.  For a similar API that works for generic devices, see
+This is a guide to device driver writers on how to use the DMA API
+with example pseudo-code.  For a concise description of the API, see
 DMA-API.txt.
 
 Most of the 64bit platforms have special hardware that translates bus
@@ -26,12 +26,15 @@ mapped only for the time they are actually used and unmapped after the DMA
 transfer.
 
 The following API will work of course even on platforms where no such
-hardware exists, see e.g. arch/x86/include/asm/pci.h for how it is implemented on
-top of the virt_to_bus interface.
+hardware exists.
+
+Note that the DMA API works with any bus independent of the underlying
+microprocessor architecture. You should use the DMA API rather than
+the bus specific DMA API (e.g. pci_dma_*).
 
 First of all, you should make sure
 
-#include <linux/pci.h>
+#include <linux/dma-mapping.h>
 
 is in your driver. This file will obtain for you the definition of the
 dma_addr_t (which can hold any valid DMA address for the platform)
@@ -78,44 +81,43 @@ for you to DMA from/to.
                         DMA addressing limitations
 
 Does your device have any DMA addressing limitations?  For example, is
-your device only capable of driving the low order 24-bits of address
-on the PCI bus for SAC DMA transfers?  If so, you need to inform the
-PCI layer of this fact.
+your device only capable of driving the low order 24-bits of address?
+If so, you need to inform the kernel of this fact.
 
 By default, the kernel assumes that your device can address the full
-32-bits in a SAC cycle.  For a 64-bit DAC capable device, this needs
-to be increased.  And for a device with limitations, as discussed in
-the previous paragraph, it needs to be decreased.
-
-pci_alloc_consistent() by default will return 32-bit DMA addresses.
-PCI-X specification requires PCI-X devices to support 64-bit
-addressing (DAC) for all transactions. And at least one platform (SGI
-SN2) requires 64-bit consistent allocations to operate correctly when
-the IO bus is in PCI-X mode. Therefore, like with pci_set_dma_mask(),
-it's good practice to call pci_set_consistent_dma_mask() to set the
-appropriate mask even if your device only supports 32-bit DMA
-(default) and especially if it's a PCI-X device.
-
-For correct operation, you must interrogate the PCI layer in your
-device probe routine to see if the PCI controller on the machine can
-properly support the DMA addressing limitation your device has.  It is
-good style to do this even if your device holds the default setting,
+32-bits.  For a 64-bit capable device, this needs to be increased.
+And for a device with limitations, as discussed in the previous
+paragraph, it needs to be decreased.
+
+Special note about PCI: PCI-X specification requires PCI-X devices to
+support 64-bit addressing (DAC) for all transactions.  And at least
+one platform (SGI SN2) requires 64-bit consistent allocations to
+operate correctly when the IO bus is in PCI-X mode.
+
+For correct operation, you must interrogate the kernel in your device
+probe routine to see if the DMA controller on the machine can properly
+support the DMA addressing limitation your device has.  It is good
+style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to pci_set_dma_mask():
+The query is performed via a call to dma_set_mask():
 
-        int pci_set_dma_mask(struct pci_dev *pdev, u64 device_mask);
+        int dma_set_mask(struct device *dev, u64 mask);
 
 The query for consistent allocations is performed via a call to
-pci_set_consistent_dma_mask():
+dma_set_coherent_mask():
 
-        int pci_set_consistent_dma_mask(struct pci_dev *pdev, u64 device_mask);
+        int dma_set_coherent_mask(struct device *dev, u64 mask);
 
-Here, pdev is a pointer to the PCI device struct of your device, and
-device_mask is a bit mask describing which bits of a PCI address your
-device supports.  It returns zero if your card can perform DMA
-properly on the machine given the address mask you provided.
+Here, dev is a pointer to the device struct of your device, and mask
+is a bit mask describing which bits of an address your device
+supports.  It returns zero if your card can perform DMA properly on
+the machine given the address mask you provided.  In general, the
+device struct of your device is embedded in the bus specific device
+struct of your device.  For example, a pointer to the device struct of
+your PCI device is pdev->dev (pdev is a pointer to the PCI device
+struct of your device).
 
 If it returns non-zero, your device cannot perform DMA properly on
 this platform, and attempting to do so will result in undefined
@@ -133,31 +135,30 @@ of your driver reports that performance is bad or that the device is not
 even detected, you can ask them for the kernel messages to find out
 exactly why.
 
-The standard 32-bit addressing PCI device would do something like
-this:
+The standard 32-bit addressing device would do something like this:
 
-        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+        if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
                 printk(KERN_WARNING
                        "mydev: No suitable DMA available.\n");
                 goto ignore_this_device;
         }
 
-Another common scenario is a 64-bit capable device.  The approach
-here is to try for 64-bit DAC addressing, but back down to a
-32-bit mask should that fail.  The PCI platform code may fail the
-64-bit mask not because the platform is not capable of 64-bit
-addressing.  Rather, it may fail in this case simply because
-32-bit SAC addressing is done more efficiently than DAC addressing.
-Sparc64 is one platform which behaves in this way.
+Another common scenario is a 64-bit capable device.  The approach here
+is to try for 64-bit addressing, but back down to a 32-bit mask that
+should not fail.  The kernel may fail the 64-bit mask not because the
+platform is not capable of 64-bit addressing.  Rather, it may fail in
+this case simply because 32-bit addressing is done more efficiently
+than 64-bit addressing.  For example, Sparc64 PCI SAC addressing is
+more efficient than DAC addressing.
 
 Here is how you would handle a 64-bit capable device which can drive
 all 64-bits when accessing streaming DMA:
 
         int using_dac;
 
-        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+        if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
                 using_dac = 1;
-        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+        } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
                 using_dac = 0;
         } else {
                 printk(KERN_WARNING
@@ -170,36 +171,36 @@ the case would look like this:
 
         int using_dac, consistent_using_dac;
 
-        if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
+        if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
                 using_dac = 1;
                 consistent_using_dac = 1;
-                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-        } else if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(32))) {
+                dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
+        } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
                 using_dac = 0;
                 consistent_using_dac = 0;
-                pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+                dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
         } else {
                 printk(KERN_WARNING
                        "mydev: No suitable DMA available.\n");
                 goto ignore_this_device;
         }
 
-pci_set_consistent_dma_mask() will always be able to set the same or a
-smaller mask as pci_set_dma_mask(). However for the rare case that a
+dma_set_coherent_mask() will always be able to set the same or a
+smaller mask as dma_set_mask(). However for the rare case that a
 device driver only uses consistent allocations, one would have to
-check the return value from pci_set_consistent_dma_mask().
+check the return value from dma_set_coherent_mask().
 
 Finally, if your device can only drive the low 24-bits of
-address during PCI bus mastering you might do something like:
+address you might do something like:
 
-        if (pci_set_dma_mask(pdev, DMA_BIT_MASK(24))) {
+        if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
                 printk(KERN_WARNING
                        "mydev: 24-bit DMA addressing not available.\n");
                 goto ignore_this_device;
         }
 
-When pci_set_dma_mask() is successful, and returns zero, the PCI layer
-saves away this mask you have provided.  The PCI layer will use this
+When dma_set_mask() is successful, and returns zero, the kernel saves
+away this mask you have provided.  The kernel will use this
 information later when you make DMA mappings.
 
 There is a case which we are aware of at this time, which is worth
@@ -208,7 +209,7 @@ functions (for example a sound card provides playback and record
 functions) and the various different functions have _different_
 DMA addressing limitations, you may wish to probe each mask and
 only provide the functionality which the machine can handle.  It
-is important that the last call to pci_set_dma_mask() be for the
+is important that the last call to dma_set_mask() be for the
 most specific mask.
 
 Here is pseudo-code showing how this might be done:
@@ -217,17 +218,17 @@ Here is pseudo-code showing how this might be done:
         #define RECORD_ADDRESS_BITS     DMA_BIT_MASK(24)
 
         struct my_sound_card *card;
-        struct pci_dev *pdev;
+        struct device *dev;
 
         ...
-        if (!pci_set_dma_mask(pdev, PLAYBACK_ADDRESS_BITS)) {
+        if (!dma_set_mask(dev, PLAYBACK_ADDRESS_BITS)) {
                 card->playback_enabled = 1;
         } else {
                 card->playback_enabled = 0;
                 printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n",
                        card->name);
         }
-        if (!pci_set_dma_mask(pdev, RECORD_ADDRESS_BITS)) {
+        if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) {
                 card->record_enabled = 1;
         } else {
                 card->record_enabled = 0;
@@ -252,8 +253,8 @@ There are two types of DMA mappings:
   Think of "consistent" as "synchronous" or "coherent".
 
   The current default is to return consistent memory in the low 32
-  bits of the PCI bus space.  However, for future compatibility you
-  should set the consistent mask even if this default is fine for your
+  bits of the bus space.  However, for future compatibility you should
+  set the consistent mask even if this default is fine for your
   driver.
 
   Good examples of what to use consistent mappings for are:
@@ -285,9 +286,9 @@ There are two types of DMA mappings:
              found in PCI bridges (such as by reading a register's value
              after writing it).
 
-- Streaming DMA mappings which are usually mapped for one DMA transfer,
-  unmapped right after it (unless you use pci_dma_sync_* below) and for which
-  hardware can optimize for sequential accesses.
+- Streaming DMA mappings which are usually mapped for one DMA
+  transfer, unmapped right after it (unless you use dma_sync_* below)
+  and for which hardware can optimize for sequential accesses.
 
   This of "streaming" as "asynchronous" or "outside the coherency
   domain".
@@ -302,8 +303,8 @@ There are two types of DMA mappings:
   optimizations the hardware allows.  To this end, when using
   such mappings you must be explicit about what you want to happen.
 
-Neither type of DMA mapping has alignment restrictions that come
-from PCI, although some devices may have such restrictions.
+Neither type of DMA mapping has alignment restrictions that come from
+the underlying bus, although some devices may have such restrictions.
 Also, systems with caches that aren't DMA-coherent will work better
 when the underlying buffers don't share cache lines with other data.
 
@@ -315,33 +316,27 @@ you should do:
 
         dma_addr_t dma_handle;
 
-        cpu_addr = pci_alloc_consistent(pdev, size, &dma_handle);
-
-where pdev is a struct pci_dev *. This may be called in interrupt context.
-You should use dma_alloc_coherent (see DMA-API.txt) for buses
-where devices don't have struct pci_dev (like ISA, EISA).
+        cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
 
-This argument is needed because the DMA translations may be bus
-specific (and often is private to the bus which the device is attached
-to).
+where device is a struct device *. This may be called in interrupt
+context with the GFP_ATOMIC flag.
 
 Size is the length of the region you want to allocate, in bytes.
 
 This routine will allocate RAM for that region, so it acts similarly to
 __get_free_pages (but takes size instead of a page order).  If your
 driver needs regions sized smaller than a page, you may prefer using
-the pci_pool interface, described below.
-
-The consistent DMA mapping interfaces, for non-NULL pdev, will by
-default return a DMA address which is SAC (Single Address Cycle)
-addressable.  Even if the device indicates (via PCI dma mask) that it
-may address the upper 32-bits and thus perform DAC cycles, consistent
-allocation will only return > 32-bit PCI addresses for DMA if the
-consistent dma mask has been explicitly changed via
-pci_set_consistent_dma_mask().  This is true of the pci_pool interface
-as well.
-
-pci_alloc_consistent returns two values: the virtual address which you
+the dma_pool interface, described below.
+
+The consistent DMA mapping interfaces, for non-NULL dev, will by
+default return a DMA address which is 32-bit addressable.  Even if the
+device indicates (via DMA mask) that it may address the upper 32-bits,
+consistent allocation will only return > 32-bit addresses for DMA if
+the consistent DMA mask has been explicitly changed via
+dma_set_coherent_mask().  This is true of the dma_pool interface as
+well.
+
+dma_alloc_coherent returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the
 card.
 
@@ -354,54 +349,54 @@ buffer you receive will not cross a 64K boundary.
 
 To unmap and free such a DMA region, you call:
 
-        pci_free_consistent(pdev, size, cpu_addr, dma_handle);
+        dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
-where pdev, size are the same as in the above call and cpu_addr and
-dma_handle are the values pci_alloc_consistent returned to you.
+where dev, size are the same as in the above call and cpu_addr and
+dma_handle are the values dma_alloc_coherent returned to you.
 This function may not be called in interrupt context.
 
 If your driver needs lots of smaller memory regions, you can write
-custom code to subdivide pages returned by pci_alloc_consistent,
-or you can use the pci_pool API to do that.  A pci_pool is like
-a kmem_cache, but it uses pci_alloc_consistent not __get_free_pages.
+custom code to subdivide pages returned by dma_alloc_coherent,
+or you can use the dma_pool API to do that.  A dma_pool is like
+a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages.
 Also, it understands common hardware constraints for alignment,
 like queue heads needing to be aligned on N byte boundaries.
 
-Create a pci_pool like this:
+Create a dma_pool like this:
 
-        struct pci_pool *pool;
+        struct dma_pool *pool;
 
-        pool = pci_pool_create(name, pdev, size, align, alloc);
+        pool = dma_pool_create(name, dev, size, align, alloc);
 
-The "name" is for diagnostics (like a kmem_cache name); pdev and size
+The "name" is for diagnostics (like a kmem_cache name); dev and size
 are as above.  The device's hardware alignment requirement for this
 type of data is "align" (which is expressed in bytes, and must be a
 power of two).  If your device has no boundary crossing restrictions,
 pass 0 for alloc; passing 4096 says memory allocated from this pool
 must not cross 4KByte boundaries (but at that time it may be better to
-go for pci_alloc_consistent directly instead).
+go for dma_alloc_coherent directly instead).
 
-Allocate memory from a pci pool like this:
+Allocate memory from a dma pool like this:
 
-        cpu_addr = pci_pool_alloc(pool, flags, &dma_handle);
+        cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
 
 flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor
-holding SMP locks), SLAB_ATOMIC otherwise.  Like pci_alloc_consistent,
+holding SMP locks), SLAB_ATOMIC otherwise.  Like dma_alloc_coherent,
 this returns two values, cpu_addr and dma_handle.
 
-Free memory that was allocated from a pci_pool like this:
+Free memory that was allocated from a dma_pool like this:
 
-        pci_pool_free(pool, cpu_addr, dma_handle);
+        dma_pool_free(pool, cpu_addr, dma_handle);
 
-where pool is what you passed to pci_pool_alloc, and cpu_addr and
-dma_handle are the values pci_pool_alloc returned. This function
+where pool is what you passed to dma_pool_alloc, and cpu_addr and
+dma_handle are the values dma_pool_alloc returned. This function
 may be called in interrupt context.
 
-Destroy a pci_pool by calling:
+Destroy a dma_pool by calling:
 
-        pci_pool_destroy(pool);
+        dma_pool_destroy(pool);
 
-Make sure you've called pci_pool_free for all memory allocated
+Make sure you've called dma_pool_free for all memory allocated
 from a pool before you destroy the pool. This function may not
 be called in interrupt context.
 
@@ -411,15 +406,15 @@ The interfaces described in subsequent portions of this document
 take a DMA direction argument, which is an integer and takes on
 one of the following values:
 
- PCI_DMA_BIDIRECTIONAL
- PCI_DMA_TODEVICE
- PCI_DMA_FROMDEVICE
- PCI_DMA_NONE
+ DMA_BIDIRECTIONAL
+ DMA_TO_DEVICE
+ DMA_FROM_DEVICE
+ DMA_NONE
 
 One should provide the exact DMA direction if you know it.
 
-PCI_DMA_TODEVICE means "from main memory to the PCI device"
-PCI_DMA_FROMDEVICE means "from the PCI device to main memory"
+DMA_TO_DEVICE means "from main memory to the device"
+DMA_FROM_DEVICE means "from the device to main memory"
 It is the direction in which the data moves during the DMA
 transfer.
 
@@ -427,12 +422,12 @@ You are _strongly_ encouraged to specify this as precisely
 as you possibly can.
 
 If you absolutely cannot know the direction of the DMA transfer,
-specify PCI_DMA_BIDIRECTIONAL.  It means that the DMA can go in
+specify DMA_BIDIRECTIONAL.  It means that the DMA can go in
 either direction.  The platform guarantees that you may legally
 specify this, and that it will work, but this may be at the
 cost of performance for example.
 
-The value PCI_DMA_NONE is to be used for debugging.  One can
+The value DMA_NONE is to be used for debugging.  One can
 hold this in a data structure before you come to know the
 precise direction, and this will help catch cases where your
 direction tracking logic has failed to set things up properly.
@@ -442,21 +437,21 @@ potential platform-specific optimizations of such) is for debugging.
 Some platforms actually have a write permission boolean which DMA
 mappings can be marked with, much like page protections in the user
 program address space.  Such platforms can and do report errors in the
-kernel logs when the PCI controller hardware detects violation of the
+kernel logs when the DMA controller hardware detects violation of the
 permission setting.
 
 Only streaming mappings specify a direction, consistent mappings
 implicitly have a direction attribute setting of
-PCI_DMA_BIDIRECTIONAL.
+DMA_BIDIRECTIONAL.
 
 The SCSI subsystem tells you the direction to use in the
 'sc_data_direction' member of the SCSI command your driver is
 working on.
 
 For Networking drivers, it's a rather simple affair.  For transmit
-packets, map/unmap them with the PCI_DMA_TODEVICE direction
+packets, map/unmap them with the DMA_TO_DEVICE direction
 specifier.  For receive packets, just the opposite, map/unmap them
-with the PCI_DMA_FROMDEVICE direction specifier.
+with the DMA_FROM_DEVICE direction specifier.
 
                   Using Streaming DMA mappings
 
@@ -467,43 +462,43 @@ scatterlist.
 
 To map a single region, you do:
 
-        struct pci_dev *pdev = mydev->pdev;
+        struct device *dev = &my_dev->dev;
         dma_addr_t dma_handle;
         void *addr = buffer->ptr;
         size_t size = buffer->len;
 
-        dma_handle = pci_map_single(pdev, addr, size, direction);
+        dma_handle = dma_map_single(dev, addr, size, direction);
 
 and to unmap it:
 
-        pci_unmap_single(pdev, dma_handle, size, direction);
+        dma_unmap_single(dev, dma_handle, size, direction);
 
-You should call pci_unmap_single when the DMA activity is finished, e.g.
+You should call dma_unmap_single when the DMA activity is finished, e.g.
 from the interrupt which told you that the DMA transfer is done.
 
 Using cpu pointers like this for single mappings has a disadvantage,
 you cannot reference HIGHMEM memory in this way.  Thus, there is a
-map/unmap interface pair akin to pci_{map,unmap}_single.  These
+map/unmap interface pair akin to dma_{map,unmap}_single.  These
 interfaces deal with page/offset pairs instead of cpu pointers.
 Specifically:
 
-        struct pci_dev *pdev = mydev->pdev;
+        struct device *dev = &my_dev->dev;
         dma_addr_t dma_handle;
         struct page *page = buffer->page;
         unsigned long offset = buffer->offset;
         size_t size = buffer->len;
 
-        dma_handle = pci_map_page(pdev, page, offset, size, direction);
+        dma_handle = dma_map_page(dev, page, offset, size, direction);
 
         ...
 
-        pci_unmap_page(pdev, dma_handle, size, direction);
+        dma_unmap_page(dev, dma_handle, size, direction);
 
 Here, "offset" means byte offset within the given page.
 
 With scatterlists, you map a region gathered from several regions by:
 
-        int i, count = pci_map_sg(pdev, sglist, nents, direction);
+        int i, count = dma_map_sg(dev, sglist, nents, direction);
         struct scatterlist *sg;
 
         for_each_sg(sglist, sg, count, i) {
@@ -527,16 +522,16 @@ accessed sg->address and sg->length as shown above.
 
 To unmap a scatterlist, just call:
 
-        pci_unmap_sg(pdev, sglist, nents, direction);
+        dma_unmap_sg(dev, sglist, nents, direction);
 
 Again, make sure DMA activity has already finished.
 
-PLEASE NOTE:  The 'nents' argument to the pci_unmap_sg call must be
-              the _same_ one you passed into the pci_map_sg call,
+PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
+              the _same_ one you passed into the dma_map_sg call,
               it should _NOT_ be the 'count' value _returned_ from the
-              pci_map_sg call.
+              dma_map_sg call.
 
-Every pci_map_{single,sg} call should have its pci_unmap_{single,sg}
+Every dma_map_{single,sg} call should have its dma_unmap_{single,sg}
 counterpart, because the bus address space is a shared resource (although
 in some ports the mapping is per each BUS so less devices contend for the
 same bus address space) and you could render the machine unusable by eating
@@ -547,14 +542,14 @@ the data in between the DMA transfers, the buffer needs to be synced
 properly in order for the cpu and device to see the most uptodate and
 correct copy of the DMA buffer.
 
-So, firstly, just map it with pci_map_{single,sg}, and after each DMA
+So, firstly, just map it with dma_map_{single,sg}, and after each DMA
 transfer call either:
 
-        pci_dma_sync_single_for_cpu(pdev, dma_handle, size, direction);
+        dma_sync_single_for_cpu(dev, dma_handle, size, direction);
 
 or:
 
-        pci_dma_sync_sg_for_cpu(pdev, sglist, nents, direction);
+        dma_sync_sg_for_cpu(dev, sglist, nents, direction);
 
 as appropriate.
 
@@ -562,27 +557,27 @@ Then, if you wish to let the device get at the DMA area again,
 finish accessing the data with the cpu, and then before actually
 giving the buffer to the hardware call either:
 
-        pci_dma_sync_single_for_device(pdev, dma_handle, size, direction);
+        dma_sync_single_for_device(dev, dma_handle, size, direction);
 
 or:
 
-        pci_dma_sync_sg_for_device(dev, sglist, nents, direction);
+        dma_sync_sg_for_device(dev, sglist, nents, direction);
 
 as appropriate.
 
 After the last DMA transfer call one of the DMA unmap routines
-pci_unmap_{single,sg}. If you don't touch the data from the first pci_map_*
-call till pci_unmap_*, then you don't have to call the pci_dma_sync_*
+dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_*
+call till dma_unmap_*, then you don't have to call the dma_sync_*
 routines at all.
 
 Here is pseudo code which shows a situation in which you would need
-to use the pci_dma_sync_*() interfaces.
+to use the dma_sync_*() interfaces.
 
         my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
         {
                 dma_addr_t mapping;
 
-                mapping = pci_map_single(cp->pdev, buffer, len, PCI_DMA_FROMDEVICE);
+                mapping = dma_map_single(cp->dev, buffer, len, DMA_FROM_DEVICE);
 
                 cp->rx_buf = buffer;
                 cp->rx_len = len;
@@ -606,25 +601,25 @@ to use the pci_dma_sync_*() interfaces.
                          * the DMA transfer with the CPU first
                          * so that we see updated contents.
                          */
-                        pci_dma_sync_single_for_cpu(cp->pdev, cp->rx_dma,
-                                                    cp->rx_len,
-                                                    PCI_DMA_FROMDEVICE);
+                        dma_sync_single_for_cpu(&cp->dev, cp->rx_dma,
+                                                cp->rx_len,
+                                                DMA_FROM_DEVICE);
 
                         /* Now it is safe to examine the buffer. */
                         hp = (struct my_card_header *) cp->rx_buf;
                         if (header_is_ok(hp)) {
-                                pci_unmap_single(cp->pdev, cp->rx_dma, cp->rx_len,
-                                                 PCI_DMA_FROMDEVICE);
+                                dma_unmap_single(&cp->dev, cp->rx_dma, cp->rx_len,
+                                                 DMA_FROM_DEVICE);
                                 pass_to_upper_layers(cp->rx_buf);
                                 make_and_setup_new_rx_buf(cp);
                         } else {
                                 /* Just sync the buffer and give it back
                                  * to the card.
                                  */
-                                pci_dma_sync_single_for_device(cp->pdev,
-                                                               cp->rx_dma,
-                                                               cp->rx_len,
-                                                               PCI_DMA_FROMDEVICE);
+                                dma_sync_single_for_device(&cp->dev,
+                                                           cp->rx_dma,
+                                                           cp->rx_len,
+                                                           DMA_FROM_DEVICE);
                                 give_rx_buf_to_card(cp);
                         }
                 }
@@ -634,19 +629,19 @@ Drivers converted fully to this interface should not use virt_to_bus any
 longer, nor should they use bus_to_virt. Some drivers have to be changed a
 little bit, because there is no longer an equivalent to bus_to_virt in the
 dynamic DMA mapping scheme - you have to always store the DMA addresses
-returned by the pci_alloc_consistent, pci_pool_alloc, and pci_map_single
-calls (pci_map_sg stores them in the scatterlist itself if the platform
+returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single
+calls (dma_map_sg stores them in the scatterlist itself if the platform
 supports dynamic DMA mapping in hardware) in your driver structures and/or
 in the card registers.
 
-All PCI drivers should be using these interfaces with no exceptions.
-It is planned to completely remove virt_to_bus() and bus_to_virt() as
+All drivers should be using these interfaces with no exceptions.  It
+is planned to completely remove virt_to_bus() and bus_to_virt() as
 they are entirely deprecated.  Some ports already do not provide these
 as it is impossible to correctly support them.
 
                 Optimizing Unmap State Space Consumption
 
-On many platforms, pci_unmap_{single,page}() is simply a nop.
+On many platforms, dma_unmap_{single,page}() is simply a nop.
 Therefore, keeping track of the mapping address and length is a waste
 of space.  Instead of filling your drivers up with ifdefs and the like
 to "work around" this (which would defeat the whole purpose of a
@@ -655,7 +650,7 @@ portable API) the following facilities are provided.
 Actually, instead of describing the macros one by one, we'll
 transform some example code.
 
-1) Use DECLARE_PCI_UNMAP_{ADDR,LEN} in state saving structures.
+1) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
    Example, before:
 
         struct ring_state {
@@ -668,14 +663,11 @@ transform some example code.
 
         struct ring_state {
                 struct sk_buff *skb;
-                DECLARE_PCI_UNMAP_ADDR(mapping)
-                DECLARE_PCI_UNMAP_LEN(len)
+                DEFINE_DMA_UNMAP_ADDR(mapping);
+                DEFINE_DMA_UNMAP_LEN(len);
         };
 
-   NOTE: DO NOT put a semicolon at the end of the DECLARE_*()
-         macro.
-
-2) Use pci_unmap_{addr,len}_set to set these values.
+2) Use dma_unmap_{addr,len}_set to set these values.
    Example, before:
 
         ringp->mapping = FOO;
@@ -683,21 +675,21 @@ transform some example code.
 
    after:
 
-        pci_unmap_addr_set(ringp, mapping, FOO);
-        pci_unmap_len_set(ringp, len, BAR);
+        dma_unmap_addr_set(ringp, mapping, FOO);
+        dma_unmap_len_set(ringp, len, BAR);
 
-3) Use pci_unmap_{addr,len} to access these values.
+3) Use dma_unmap_{addr,len} to access these values.
    Example, before:
 
-        pci_unmap_single(pdev, ringp->mapping, ringp->len,
-                         PCI_DMA_FROMDEVICE);
+        dma_unmap_single(dev, ringp->mapping, ringp->len,
+                         DMA_FROM_DEVICE);
 
    after:
 
-        pci_unmap_single(pdev,
-                         pci_unmap_addr(ringp, mapping),
-                         pci_unmap_len(ringp, len),
-                         PCI_DMA_FROMDEVICE);
+        dma_unmap_single(dev,
+                         dma_unmap_addr(ringp, mapping),
+                         dma_unmap_len(ringp, len),
+                         DMA_FROM_DEVICE);
 
 It really should be self-explanatory.  We treat the ADDR and LEN
 separately, because it is possible for an implementation to only
@@ -732,15 +724,15 @@ to "Closing".
 DMA address space is limited on some architectures and an allocation
 failure can be determined by:
 
-- checking if pci_alloc_consistent returns NULL or pci_map_sg returns 0
+- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0
 
-- checking the returned dma_addr_t of pci_map_single and pci_map_page
-  by using pci_dma_mapping_error():
+- checking the returned dma_addr_t of dma_map_single and dma_map_page
+  by using dma_mapping_error():
 
         dma_addr_t dma_handle;
 
-        dma_handle = pci_map_single(pdev, addr, size, direction);
-        if (pci_dma_mapping_error(pdev, dma_handle)) {
+        dma_handle = dma_map_single(dev, addr, size, direction);
+        if (dma_mapping_error(dev, dma_handle)) {
                 /*
                  * reduce current DMA mapping usage,
                  * delay and try again later or
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 5aceb88b3f8b..05e2ae236865 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -4,20 +4,18 @@
         James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 
 This document describes the DMA API.  For a more gentle introduction
-phrased in terms of the pci_ equivalents (and actual examples) see
-Documentation/PCI/PCI-DMA-mapping.txt.
+of the API (and actual examples) see
+Documentation/DMA-API-HOWTO.txt.
 
-This API is split into two pieces.  Part I describes the API and the
-corresponding pci_ API.  Part II describes the extensions to the API
-for supporting non-consistent memory machines.  Unless you know that
-your driver absolutely has to support non-consistent platforms (this
-is usually only legacy platforms) you should only use the API
-described in part I.
+This API is split into two pieces.  Part I describes the API.  Part II
+describes the extensions to the API for supporting non-consistent
+memory machines.  Unless you know that your driver absolutely has to
+support non-consistent platforms (this is usually only legacy
+platforms) you should only use the API described in part I.
 
-Part I - pci_ and dma_ Equivalent API 
+Part I - dma_ API
 -------------------------------------
 
-To get the pci_ API, you must #include <linux/pci.h>
 To get the dma_ API, you must #include <linux/dma-mapping.h>
 
 
@@ -27,9 +25,6 @@ Part Ia - Using large dma-coherent buffers
 void *
 dma_alloc_coherent(struct device *dev, size_t size,
                              dma_addr_t *dma_handle, gfp_t flag)
-void *
-pci_alloc_consistent(struct pci_dev *dev, size_t size,
-                             dma_addr_t *dma_handle)
 
 Consistent memory is memory for which a write by either the device or
 the processor can immediately be read by the processor or device
@@ -53,15 +48,11 @@ The simplest way to do that is to use the dma_pool calls (see below).
 The flag parameter (dma_alloc_coherent only) allows the caller to
 specify the GFP_ flags (see kmalloc) for the allocation (the
 implementation may choose to ignore flags that affect the location of
-the returned memory, like GFP_DMA).  For pci_alloc_consistent, you
-must assume GFP_ATOMIC behaviour.
+the returned memory, like GFP_DMA).
 
 void
 dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
                            dma_addr_t dma_handle)
-void
-pci_free_consistent(struct pci_dev *dev, size_t size, void *cpu_addr,
-                           dma_addr_t dma_handle)
 
 Free the region of consistent memory you previously allocated.  dev,
 size and dma_handle must all be the same as those passed into the
@@ -89,10 +80,6 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries.
         dma_pool_create(const char *name, struct device *dev,
                         size_t size, size_t align, size_t alloc);
 
-        struct pci_pool *
-        pci_pool_create(const char *name, struct pci_device *dev,
-                        size_t size, size_t align, size_t alloc);
-
 The pool create() routines initialize a pool of dma-coherent buffers
 for use with a given device.  It must be called in a context which
 can sleep.
@@ -108,9 +95,6 @@ from this pool must not cross 4KByte boundaries.
         void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
                         dma_addr_t *dma_handle);
 
-        void *pci_pool_alloc(struct pci_pool *pool, gfp_t gfp_flags,
-                        dma_addr_t *dma_handle);
-
 This allocates memory from the pool; the returned memory will meet the size
 and alignment requirements specified at creation time.  Pass GFP_ATOMIC to
 prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks),
@@ -122,9 +106,6 @@ pool's device.
         void dma_pool_free(struct dma_pool *pool, void *vaddr,
                         dma_addr_t addr);
 
-        void pci_pool_free(struct pci_pool *pool, void *vaddr,
-                        dma_addr_t addr);
-
 This puts memory back into the pool.  The pool is what was passed to
 the pool allocation routine; the cpu (vaddr) and dma addresses are what
 were returned when that routine allocated the memory being freed.
@@ -132,8 +113,6 @@ were returned when that routine allocated the memory being freed.
 
         void dma_pool_destroy(struct dma_pool *pool);
 
-        void pci_pool_destroy(struct pci_pool *pool);
-
 The pool destroy() routines free the resources of the pool.  They must be
 called in a context which can sleep.  Make sure you've freed all allocated
 memory back to the pool before you destroy it.
@@ -144,8 +123,6 @@ Part Ic - DMA addressing limitations
 
 int
 dma_supported(struct device *dev, u64 mask)
-int
-pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -159,8 +136,14 @@ driver writers.
 
 int
 dma_set_mask(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
-pci_set_dma_mask(struct pci_device *dev, u64 mask)
+dma_set_coherent_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 parameters if it is.
@@ -187,9 +170,6 @@ Part Id - Streaming DMA mappings
 dma_addr_t
 dma_map_single(struct device *dev, void *cpu_addr, size_t size,
                       enum dma_data_direction direction)
-dma_addr_t
-pci_map_single(struct pci_dev *hwdev, void *cpu_addr, size_t size,
-                      int direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
 device and returns the physical handle of the memory.
@@ -198,14 +178,10 @@ The direction for both api's may be converted freely by casting.
 However the dma_ API uses a strongly typed enumerator for its
 direction:
 
-DMA_NONE                = PCI_DMA_NONE          no direction (used for
-                                                debugging)
-DMA_TO_DEVICE           = PCI_DMA_TODEVICE      data is going from the
-                                                memory to the device
-DMA_FROM_DEVICE         = PCI_DMA_FROMDEVICE    data is coming from
-                                                the device to the
-                                                memory
-DMA_BIDIRECTIONAL       = PCI_DMA_BIDIRECTIONAL direction isn't known
+DMA_NONE                no direction (used for debugging)
+DMA_TO_DEVICE           data is going from the memory to the device
+DMA_FROM_DEVICE         data is coming from the device to the memory
+DMA_BIDIRECTIONAL       direction isn't known
 
 Notes:  Not all memory regions in a machine can be mapped by this
 API.  Further, regions that appear to be physically contiguous in
@@ -268,9 +244,6 @@ cache lines are updated with data that the device may have changed).
 void
 dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
                  enum dma_data_direction direction)
-void
-pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr,
-                 size_t size, int direction)
 
 Unmaps the region previously mapped.  All the parameters passed in
 must be identical to those passed in (and returned) by the mapping
@@ -280,15 +253,9 @@ dma_addr_t
 dma_map_page(struct device *dev, struct page *page,
                     unsigned long offset, size_t size,
                     enum dma_data_direction direction)
-dma_addr_t
-pci_map_page(struct pci_dev *hwdev, struct page *page,
-                    unsigned long offset, size_t size, int direction)
 void
 dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
                enum dma_data_direction direction)
-void
-pci_unmap_page(struct pci_dev *hwdev, dma_addr_t dma_address,
-               size_t size, int direction)
 
 API for mapping and unmapping for pages.  All the notes and warnings
 for the other mapping APIs apply here.  Also, although the <offset>
@@ -299,9 +266,6 @@ cache width is.
 int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
-int
-pci_dma_mapping_error(struct pci_dev *hwdev, dma_addr_t dma_addr)
-
 In some circumstances dma_map_single and dma_map_page will fail to create
 a mapping. A driver can check for these errors by testing the returned
 dma address with dma_mapping_error(). A non-zero return value means the mapping
@@ -311,9 +275,6 @@ reduce current DMA mapping usage or delay and try again later).
         int
         dma_map_sg(struct device *dev, struct scatterlist *sg,
                 int nents, enum dma_data_direction direction)
-        int
-        pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-                int nents, int direction)
 
 Returns: the number of physical segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
@@ -353,9 +314,6 @@ accessed sg->address and sg->length as shown above.
         void
         dma_unmap_sg(struct device *dev, struct scatterlist *sg,
                 int nhwentries, enum dma_data_direction direction)
-        void
-        pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-                int nents, int direction)
 
 Unmap the previously mapped scatter/gather list.  All the parameters
 must be the same as those and passed in to the scatter/gather mapping
@@ -365,21 +323,23 @@ Note: <nents> must be the number you passed in, *not* the number of
 physical entries returned.
 
 void
-dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
-                enum dma_data_direction direction)
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+                        enum dma_data_direction direction)
 void
-pci_dma_sync_single(struct pci_dev *hwdev, dma_addr_t dma_handle,
-                           size_t size, int direction)
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
+                           enum dma_data_direction direction)
 void
-dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
-                          enum dma_data_direction direction)
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+                    enum dma_data_direction direction)
 void
-pci_dma_sync_sg(struct pci_dev *hwdev, struct scatterlist *sg,
-                       int nelems, int direction)
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+                       enum dma_data_direction direction)
 
-Synchronise a single contiguous or scatter/gather mapping.  All the
-parameters must be the same as those passed into the single mapping
-API.
+Synchronise a single contiguous or scatter/gather mapping for the cpu
+and device. With the sync_sg API, all the parameters must be the same
+as those passed into the single mapping API. With the sync_single API,
+you can use dma_handle and size parameters that aren't identical to
+those passed into the single mapping API to do a partial sync.
 
 Notes:  You must do this:
 
@@ -461,9 +421,9 @@ void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
 Part II - Advanced dma_ usage
 -----------------------------
 
-Warning: These pieces of the DMA API have no PCI equivalent.  They
-should also not be used in the majority of cases, since they cater for
-unlikely corner cases that don't belong in usual drivers.
+Warning: These pieces of the DMA API should not be used in the
+majority of cases, since they cater for unlikely corner cases that
+don't belong in usual drivers.
 
 If you don't understand how cache line coherency works between a
 processor and an I/O device, you should not be using this part of the
@@ -514,16 +474,6 @@ into the width returned by this call.  It will also always be a power
 of two for easy alignment.
 
 void
-dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
-                      unsigned long offset, size_t size,
-                      enum dma_data_direction direction)
-
-Does a partial sync, starting at offset and continuing for size.  You
-must be careful to observe the cache alignment and width when doing
-anything like this.  You must also be extra careful about accessing
-memory you intend to sync partially.
-
-void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
                enum dma_data_direction direction)
 
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index f9a6e2c75f12..1b2dd4fc3db2 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -45,7 +45,7 @@
      </sect1>
 
      <sect1><title>Atomic and pointer manipulation</title>
-!Iarch/x86/include/asm/atomic_32.h
+!Iarch/x86/include/asm/atomic.h
 !Iarch/x86/include/asm/unaligned.h
      </sect1>
 
diff --git a/Documentation/DocBook/deviceiobook.tmpl b/Documentation/DocBook/deviceiobook.tmpl
index 3ed88126ab8f..c1ed6a49e598 100644
--- a/Documentation/DocBook/deviceiobook.tmpl
+++ b/Documentation/DocBook/deviceiobook.tmpl
@@ -316,7 +316,7 @@ CPU B:  spin_unlock_irqrestore(&amp;dev_lock, flags)
 
   <chapter id="pubfunctions">
      <title>Public Functions Provided</title>
-!Iarch/x86/include/asm/io_32.h
+!Iarch/x86/include/asm/io.h
 !Elib/iomap.c
   </chapter>
 
diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index ba9975771503..ff3e5bec1c24 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -107,10 +107,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
         issue of SET FEATURES - XFER MODE, and prior to operation.
         </para>
         <para>
-        Called by ata_device_add() after ata_dev_identify() determines
-        a device is present.
-        </para>
-        <para>
         This entry may be specified as NULL in ata_port_operations.
         </para>
 
@@ -154,8 +150,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in
 
         <sect2><title>Taskfile read/write</title>
         <programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
         </programlisting>
 
         <para>
@@ -164,36 +160,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
         hardware registers / DMA buffers, to obtain the current set of
         taskfile register values.
         Most drivers for taskfile-based hardware (PIO or MMIO) use
-        ata_tf_load() and ata_tf_read() for these hooks.
+        ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
         </para>
 
         </sect2>
 
         <sect2><title>PIO data read/write</title>
         <programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
         </programlisting>
 
         <para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
-ata_mmio_data_xfer().
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
         </para>
 
         </sect2>
 
         <sect2><title>ATA command execute</title>
         <programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
         </programlisting>
 
         <para>
         causes an ATA command, previously loaded with
         ->tf_load(), to be initiated in hardware.
-        Most drivers for taskfile-based hardware use ata_exec_command()
+        Most drivers for taskfile-based hardware use ata_sff_exec_command()
         for this hook.
         </para>
 
@@ -218,8 +213,8 @@ command.
 
         <sect2><title>Read specific ATA shadow registers</title>
         <programlisting>
-u8   (*check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
         </programlisting>
 
         <para>
@@ -227,20 +222,14 @@ u8   (*check_altstatus)(struct ata_port *ap);
         hardware.  On some hardware, reading the Status register has
         the side effect of clearing the interrupt condition.
         Most drivers for taskfile-based hardware use
-        ata_check_status() for this hook.
-        </para>
-        <para>
-        Note that because this is called from ata_device_add(), at
-        least a dummy function that clears device interrupts must be
-        provided for all drivers, even if the controller doesn't
-        actually have a taskfile status register.
+        ata_sff_check_status() for this hook.
         </para>
 
         </sect2>
 
         <sect2><title>Select ATA device on bus</title>
         <programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
         </programlisting>
 
         <para>
@@ -251,9 +240,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
         </para>
         <para>
         Most drivers for taskfile-based hardware use
-        ata_std_dev_select() for this hook.  Controllers which do not
-        support second drives on a port (such as SATA contollers) will
-        use ata_noop_dev_select().
+        ata_sff_dev_select() for this hook.
         </para>
 
         </sect2>
@@ -441,13 +428,13 @@ void (*irq_clear) (struct ata_port *);
         to struct ata_host_set.
         </para>
         <para>
-        Most legacy IDE drivers use ata_interrupt() for the
+        Most legacy IDE drivers use ata_sff_interrupt() for the
         irq_handler hook, which scans all ports in the host_set,
         determines which queued command was active (if any), and calls
-        ata_host_intr(ap,qc).
+        ata_sff_host_intr(ap,qc).
         </para>
         <para>
-        Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+        Most legacy IDE drivers use ata_sff_irq_clear() for the
         irq_clear() hook, which simply clears the interrupt and error
         flags in the DMA status register.
         </para>
@@ -496,10 +483,6 @@ void (*host_stop) (struct ata_host_set *host_set);
         data from port at this time.
         </para>
         <para>
-        Many drivers use ata_port_stop() as this hook, which frees the
-        PRD table.
-        </para>
-        <para>
         ->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.
diff --git a/Documentation/DocBook/mac80211.tmpl b/Documentation/DocBook/mac80211.tmpl
index f3f37f141dbd..affb15a344a1 100644
--- a/Documentation/DocBook/mac80211.tmpl
+++ b/Documentation/DocBook/mac80211.tmpl
@@ -144,7 +144,7 @@ usage should require reading the full document.
         this though and the recommendation to allow only a single
         interface in STA mode at first!
       </para>
-!Finclude/net/mac80211.h ieee80211_if_init_conf
+!Finclude/net/mac80211.h ieee80211_vif
     </chapter>
 
     <chapter id="rx-tx">
@@ -234,7 +234,6 @@ usage should require reading the full document.
       <title>Multiple queues and QoS support</title>
       <para>TBD</para>
 !Finclude/net/mac80211.h ieee80211_tx_queue_params
-!Finclude/net/mac80211.h ieee80211_tx_queue_stats
     </chapter>
 
     <chapter id="AP">
diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index 5e7d84b48505..133cd6c3f3c1 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -488,7 +488,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
                                 The ECC bytes must be placed immidiately after the data
                                 bytes in order to make the syndrome generator work. This
                                 is contrary to the usual layout used by software ECC. The
-                                seperation of data and out of band area is not longer
+                                separation of data and out of band area is not longer
                                 possible. The nand driver code handles this layout and
                                 the remaining free bytes in the oob area are managed by 
                                 the autoplacement code. Provide a matching oob-layout
@@ -560,7 +560,7 @@ static void board_select_chip (struct mtd_info *mtd, int chip)
                                 bad blocks. They have factory marked good blocks. The marker pattern
                                 is erased when the block is erased to be reused. So in case of
                                 powerloss before writing the pattern back to the chip this block 
-                                would be lost and added to the bad blocks. Therefor we scan the 
+                                would be lost and added to the bad blocks. Therefore we scan the 
                                 chip(s) when we detect them the first time for good blocks and 
                                 store this information in a bad block table before erasing any 
                                 of the blocks.
@@ -1094,7 +1094,7 @@ in this page</entry>
                 manufacturers specifications. This applies similar to the spare area. 
         </para>
         <para>
-                Therefor NAND aware filesystems must either write in page size chunks
+                Therefore NAND aware filesystems must either write in page size chunks
                 or hold a writebuffer to collect smaller writes until they sum up to 
                 pagesize. Available NAND aware filesystems: JFFS2, YAFFS.               
         </para>
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
index 8bca1d5cec09..e8473eae2a20 100644
--- a/Documentation/DocBook/tracepoint.tmpl
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -16,6 +16,15 @@
      </address>
     </affiliation>
    </author>
+   <author>
+    <firstname>William</firstname>
+    <surname>Cohen</surname>
+    <affiliation>
+     <address>
+      <email>wcohen@redhat.com</email>
+     </address>
+    </affiliation>
+   </author>
   </authorgroup>
 
   <legalnotice>
@@ -91,4 +100,8 @@
 !Iinclude/trace/events/signal.h
   </chapter>
 
+  <chapter id="block">
+   <title>Block IO</title>
+!Iinclude/trace/events/block.h
+  </chapter>
 </book>
diff --git a/Documentation/DocBook/v4l/common.xml b/Documentation/DocBook/v4l/common.xml
index c65f0ac9b6ee..cea23e1c4fc6 100644
--- a/Documentation/DocBook/v4l/common.xml
+++ b/Documentation/DocBook/v4l/common.xml
@@ -1170,7 +1170,7 @@ frames per second. If less than this number of frames is to be
 captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the &func-read; or &func-write;, which are not augmented by timestamps
-or sequence counters, and to avoid unneccessary data copying.</para>
+or sequence counters, and to avoid unnecessary data copying.</para>
 
     <para>Finally these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/DocBook/v4l/io.xml b/Documentation/DocBook/v4l/io.xml
index f92f24323b2a..e870330cbf77 100644
--- a/Documentation/DocBook/v4l/io.xml
+++ b/Documentation/DocBook/v4l/io.xml
@@ -589,7 +589,8 @@ number of a video input as in &v4l2-input; field
             <entry></entry>
             <entry>A place holder for future extensions and custom
 (driver defined) buffer types
-<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher.</entry>
+<constant>V4L2_BUF_TYPE_PRIVATE</constant> and higher. Applications
+should set this to 0.</entry>
           </row>
         </tbody>
       </tgroup>
diff --git a/Documentation/DocBook/v4l/vidioc-g-parm.xml b/Documentation/DocBook/v4l/vidioc-g-parm.xml
index 78332d365ce9..392aa9e5571e 100644
--- a/Documentation/DocBook/v4l/vidioc-g-parm.xml
+++ b/Documentation/DocBook/v4l/vidioc-g-parm.xml
@@ -55,7 +55,7 @@ captured or output, applications can request frame skipping or
 duplicating on the driver side. This is especially useful when using
 the <function>read()</function> or <function>write()</function>, which
 are not augmented by timestamps or sequence counters, and to avoid
-unneccessary data copying.</para>
+unnecessary data copying.</para>
 
     <para>Further these ioctls can be used to determine the number of
 buffers used internally by a driver in read/write mode. For
diff --git a/Documentation/DocBook/v4l/vidioc-qbuf.xml b/Documentation/DocBook/v4l/vidioc-qbuf.xml
index 187081778154..b843bd7b3897 100644
--- a/Documentation/DocBook/v4l/vidioc-qbuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-qbuf.xml
@@ -54,12 +54,10 @@ to enqueue an empty (capturing) or filled (output) buffer in the
 driver's incoming queue. The semantics depend on the selected I/O
 method.</para>
 
-    <para>To enqueue a <link linkend="mmap">memory mapped</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_MMAP</constant> and the
+    <para>To enqueue a buffer applications set the <structfield>type</structfield>
+field of a &v4l2-buffer; to the same buffer type as was previously used
+with &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
+<structfield>type</structfield>. Applications must also set the
 <structfield>index</structfield> field. Valid index numbers range from
 zero to the number of buffers allocated with &VIDIOC-REQBUFS;
 (&v4l2-requestbuffers; <structfield>count</structfield>) minus one. The
@@ -70,8 +68,19 @@ intended for output (<structfield>type</structfield> is
 <constant>V4L2_BUF_TYPE_VBI_OUTPUT</constant>) applications must also
 initialize the <structfield>bytesused</structfield>,
 <structfield>field</structfield> and
-<structfield>timestamp</structfield> fields. See <xref
-        linkend="buffer" /> for details. When
+<structfield>timestamp</structfield> fields, see <xref
+linkend="buffer" /> for details.
+Applications must also set <structfield>flags</structfield> to 0. If a driver
+supports capturing from specific video inputs and you want to specify a video
+input, then <structfield>flags</structfield> should be set to
+<constant>V4L2_BUF_FLAG_INPUT</constant> and the field
+<structfield>input</structfield> must be initialized to the desired input.
+The <structfield>reserved</structfield> field must be set to 0.
+</para>
+
+    <para>To enqueue a <link linkend="mmap">memory mapped</link>
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_MMAP</constant>. When
 <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the
 <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -81,14 +90,10 @@ structure the driver sets the
 &EINVAL;.</para>
 
     <para>To enqueue a <link linkend="userp">user pointer</link>
-buffer applications set the <structfield>type</structfield> field of a
-&v4l2-buffer; to the same buffer type as previously &v4l2-format;
-<structfield>type</structfield> and &v4l2-requestbuffers;
-<structfield>type</structfield>, the <structfield>memory</structfield>
-field to <constant>V4L2_MEMORY_USERPTR</constant> and the
+buffer applications set the <structfield>memory</structfield>
+field to <constant>V4L2_MEMORY_USERPTR</constant>, the
 <structfield>m.userptr</structfield> field to the address of the
-buffer and <structfield>length</structfield> to its size. When the
-buffer is intended for output additional fields must be set as above.
+buffer and <structfield>length</structfield> to its size.
 When <constant>VIDIOC_QBUF</constant> is called with a pointer to this
 structure the driver sets the <constant>V4L2_BUF_FLAG_QUEUED</constant>
 flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
@@ -96,13 +101,14 @@ flag and clears the <constant>V4L2_BUF_FLAG_MAPPED</constant> and
 <structfield>flags</structfield> field, or it returns an error code.
 This ioctl locks the memory pages of the buffer in physical memory,
 they cannot be swapped out to disk. Buffers remain locked until
-dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl are
+dequeued, until the &VIDIOC-STREAMOFF; or &VIDIOC-REQBUFS; ioctl is
 called, or until the device is closed.</para>
 
     <para>Applications call the <constant>VIDIOC_DQBUF</constant>
 ioctl to dequeue a filled (capturing) or displayed (output) buffer
 from the driver's outgoing queue. They just set the
-<structfield>type</structfield> and <structfield>memory</structfield>
+<structfield>type</structfield>, <structfield>memory</structfield>
+and <structfield>reserved</structfield>
 fields of a &v4l2-buffer; as above, when <constant>VIDIOC_DQBUF</constant>
 is called with a pointer to this structure the driver fills the
 remaining fields or returns an error code.</para>
diff --git a/Documentation/DocBook/v4l/vidioc-querybuf.xml b/Documentation/DocBook/v4l/vidioc-querybuf.xml
index d834993e6191..e649805a4908 100644
--- a/Documentation/DocBook/v4l/vidioc-querybuf.xml
+++ b/Documentation/DocBook/v4l/vidioc-querybuf.xml
@@ -54,12 +54,13 @@ buffer at any time after buffers have been allocated with the
 &VIDIOC-REQBUFS; ioctl.</para>
 
     <para>Applications set the <structfield>type</structfield> field
-    of a &v4l2-buffer; to the same buffer type as previously
+    of a &v4l2-buffer; to the same buffer type as was previously used with
 &v4l2-format; <structfield>type</structfield> and &v4l2-requestbuffers;
 <structfield>type</structfield>, and the <structfield>index</structfield>
     field. Valid index numbers range from zero
 to the number of buffers allocated with &VIDIOC-REQBUFS;
     (&v4l2-requestbuffers; <structfield>count</structfield>) minus one.
+The <structfield>reserved</structfield> field should to set to 0.
 After calling <constant>VIDIOC_QUERYBUF</constant> with a pointer to
     this structure drivers return an error code or fill the rest of
 the structure.</para>
@@ -68,8 +69,8 @@ the structure.</para>
 <constant>V4L2_BUF_FLAG_MAPPED</constant>,
 <constant>V4L2_BUF_FLAG_QUEUED</constant> and
 <constant>V4L2_BUF_FLAG_DONE</constant> flags will be valid. The
-<structfield>memory</structfield> field will be set to
-<constant>V4L2_MEMORY_MMAP</constant>, the <structfield>m.offset</structfield>
+<structfield>memory</structfield> field will be set to the current
+I/O method, the <structfield>m.offset</structfield>
 contains the offset of the buffer from the start of the device memory,
 the <structfield>length</structfield> field its size. The driver may
 or may not set the remaining fields and flags, they are meaningless in
diff --git a/Documentation/DocBook/v4l/vidioc-reqbufs.xml b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
index bab38084454f..1c0816372074 100644
--- a/Documentation/DocBook/v4l/vidioc-reqbufs.xml
+++ b/Documentation/DocBook/v4l/vidioc-reqbufs.xml
@@ -54,23 +54,23 @@ I/O. Memory mapped buffers are located in device memory and must be
 allocated with this ioctl before they can be mapped into the
 application's address space. User buffers are allocated by
 applications themselves, and this ioctl is merely used to switch the
-driver into user pointer I/O mode.</para>
+driver into user pointer I/O mode and to setup some internal structures.</para>
 
-    <para>To allocate device buffers applications initialize three
-fields of a <structname>v4l2_requestbuffers</structname> structure.
+    <para>To allocate device buffers applications initialize all
+fields of the <structname>v4l2_requestbuffers</structname> structure.
 They set the <structfield>type</structfield> field to the respective
 stream or buffer type, the <structfield>count</structfield> field to
-the desired number of buffers, and <structfield>memory</structfield>
-must be set to <constant>V4L2_MEMORY_MMAP</constant>. When the ioctl
-is called with a pointer to this structure the driver attempts to
-allocate the requested number of buffers and stores the actual number
+the desired number of buffers, <structfield>memory</structfield>
+must be set to the requested I/O method and the reserved array
+must be zeroed. When the ioctl
+is called with a pointer to this structure the driver will attempt to allocate
+the requested number of buffers and it stores the actual number
 allocated in the <structfield>count</structfield> field. It can be
 smaller than the number requested, even zero, when the driver runs out
-of free memory. A larger number is possible when the driver requires
-more buffers to function correctly.<footnote>
-        <para>For example video output requires at least two buffers,
+of free memory. A larger number is also possible when the driver requires
+more buffers to function correctly. For example video output requires at least two buffers,
 one displayed and one filled by the application.</para>
-        </footnote> When memory mapping I/O is not supported the ioctl
+    <para>When the I/O method is not supported the ioctl
 returns an &EINVAL;.</para>
 
     <para>Applications can call <constant>VIDIOC_REQBUFS</constant>
@@ -81,14 +81,6 @@ in progress, an implicit &VIDIOC-STREAMOFF;. <!-- mhs: I see no
 reason why munmap()ping one or even all buffers must imply
 streamoff.--></para>
 
-    <para>To negotiate user pointer I/O, applications initialize only
-the <structfield>type</structfield> field and set
-<structfield>memory</structfield> to
-<constant>V4L2_MEMORY_USERPTR</constant>. When the ioctl is called
-with a pointer to this structure the driver prepares for user pointer
-I/O, when this I/O method is not supported the ioctl returns an
-&EINVAL;.</para>
-
     <table pgwide="1" frame="none" id="v4l2-requestbuffers">
       <title>struct <structname>v4l2_requestbuffers</structname></title>
       <tgroup cols="3">
@@ -97,9 +89,7 @@ I/O, when this I/O method is not supported the ioctl returns an
           <row>
             <entry>__u32</entry>
             <entry><structfield>count</structfield></entry>
-            <entry>The number of buffers requested or granted. This
-field is only used when <structfield>memory</structfield> is set to
-<constant>V4L2_MEMORY_MMAP</constant>.</entry>
+            <entry>The number of buffers requested or granted.</entry>
           </row>
           <row>
             <entry>&v4l2-buf-type;</entry>
@@ -120,7 +110,7 @@ as the &v4l2-format; <structfield>type</structfield> field. See <xref
             <entry><structfield>reserved</structfield>[2]</entry>
             <entry>A place holder for future extensions and custom
 (driver defined) buffer types <constant>V4L2_BUF_TYPE_PRIVATE</constant> and
-higher.</entry>
+higher. This array should be zeroed by applications.</entry>
           </row>
         </tbody>
       </tgroup>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 8495fc970391..40ada93b820a 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -221,8 +221,8 @@ branches.  These different branches are:
   - main 2.6.x kernel tree
   - 2.6.x.y -stable kernel tree
   - 2.6.x -git kernel patches
-  - 2.6.x -mm kernel patches
   - subsystem specific kernel trees and patches
+  - the 2.6.x -next kernel tree for integration tests
 
 2.6.x kernel tree
 -----------------
@@ -232,9 +232,9 @@ process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
     Linus, usually the patches that have already been included in the
-    -mm kernel for a few weeks.  The preferred way to submit big changes
+    -next kernel for a few weeks.  The preferred way to submit big changes
     is using git (the kernel's source management tool, more information
-    can be found at http://git.or.cz/) but plain patches are also just
+    can be found at http://git-scm.com/) but plain patches are also just
     fine.
   - After two weeks a -rc1 kernel is released it is now possible to push
     only patches that do not include new features that could affect the
@@ -293,84 +293,43 @@ daily and represent the current state of Linus' tree.  They are more
 experimental than -rc kernels since they are generated automatically
 without even a cursory glance to see if they are sane.
 
-2.6.x -mm kernel patches
-------------------------
-These are experimental kernel patches released by Andrew Morton.  Andrew
-takes all of the different subsystem kernel trees and patches and mushes
-them together, along with a lot of patches that have been plucked from
-the linux-kernel mailing list.  This tree serves as a proving ground for
-new features and patches.  Once a patch has proved its worth in -mm for
-a while Andrew or the subsystem maintainer pushes it on to Linus for
-inclusion in mainline.
-
-It is heavily encouraged that all new patches get tested in the -mm tree
-before they are sent to Linus for inclusion in the main kernel tree.  Code
-which does not make an appearance in -mm before the opening of the merge
-window will prove hard to merge into the mainline.
-
-These kernels are not appropriate for use on systems that are supposed
-to be stable and they are more risky to run than any of the other
-branches.
-
-If you wish to help out with the kernel development process, please test
-and use these kernel releases and provide feedback to the linux-kernel
-mailing list if you have any problems, and if everything works properly.
-
-In addition to all the other experimental patches, these kernels usually
-also contain any changes in the mainline -git kernels available at the
-time of release.
-
-The -mm kernels are not released on a fixed schedule, but usually a few
--mm kernels are released in between each -rc kernel (1 to 3 is common).
-
 Subsystem Specific kernel trees and patches
 -------------------------------------------
-A number of the different kernel subsystem developers expose their
-development trees so that others can see what is happening in the
-different areas of the kernel.  These trees are pulled into the -mm
-kernel releases as described above.
-
-Here is a list of some of the different kernel trees available:
-  git trees:
-    - Kbuild development tree, Sam Ravnborg <sam@ravnborg.org>
-        git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
-
-    - ACPI development tree, Len Brown <len.brown@intel.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
-
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
-
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
-        git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
-
-    - ia64 development tree, Tony Luck <tony.luck@intel.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
-
-    - infiniband, Roland Dreier <rolandd@cisco.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
-
-    - libata, Jeff Garzik <jgarzik@pobox.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
-
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
-
-    - pcmcia, Dominik Brodowski <linux@dominikbrodowski.net>
-        git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-
-    - SCSI, James Bottomley <James.Bottomley@hansenpartnership.com>
-        git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-
-    - x86, Ingo Molnar <mingo@elte.hu>
-        git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git
-
-  quilt trees:
-    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
-        kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+The maintainers of the various kernel subsystems --- and also many
+kernel subsystem developers --- expose their current state of
+development in source repositories.  That way, others can see what is
+happening in the different areas of the kernel.  In areas where
+development is rapid, a developer may be asked to base his submissions
+onto such a subsystem kernel tree so that conflicts between the
+submission and other already ongoing work are avoided.
+
+Most of these repositories are git trees, but there are also other SCMs
+in use, or patch queues being published as quilt series.  Addresses of
+these subsystem repositories are listed in the MAINTAINERS file.  Many
+of them can be browsed at http://git.kernel.org/.
+
+Before a proposed patch is committed to such a subsystem tree, it is
+subject to review which primarily happens on mailing lists (see the
+respective section below).  For several kernel subsystems, this review
+process is tracked with the tool patchwork.  Patchwork offers a web
+interface which shows patch postings, any comments on a patch or
+revisions to it, and maintainers can mark patches as under review,
+accepted, or rejected.  Most of these patchwork sites are listed at
+http://patchwork.kernel.org/ or http://patchwork.ozlabs.org/.
+
+2.6.x -next kernel tree for integration tests
+---------------------------------------------
+Before updates from subsystem trees are merged into the mainline 2.6.x
+tree, they need to be integration-tested.  For this purpose, a special
+testing repository exists into which virtually all subsystem trees are
+pulled on an almost daily basis:
+        http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+        http://linux.f-seidel.de/linux-next/pmwiki/
+
+This way, the -next kernel gives a summary outlook onto what will be
+expected to go into the mainline kernel at the next merge period.
+Adventurous testers are very welcome to runtime-test the -next kernel.
 
-  Other kernel trees can be found listed at http://git.kernel.org/ and in
-  the MAINTAINERS file.
 
 Bug Reporting
 -------------
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index bc38283379f0..69dd29ed824e 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -365,6 +365,7 @@ You can change this at module load time (for a module) with:
        regshifts=<shift1>,<shift2>,...
        slave_addrs=<addr1>,<addr2>,...
        force_kipmid=<enable1>,<enable2>,...
+       kipmid_max_busy_us=<ustime1>,<ustime2>,...
        unload_when_empty=[0|1]
 
 Each of these except si_trydefaults is a list, the first item for the
@@ -433,6 +434,7 @@ kernel command line as:
        ipmi_si.regshifts=<shift1>,<shift2>,...
        ipmi_si.slave_addrs=<addr1>,<addr2>,...
        ipmi_si.force_kipmid=<enable1>,<enable2>,...
+       ipmi_si.kipmid_max_busy_us=<ustime1>,<ustime2>,...
 
 It works the same as the module parameters of the same names.
 
@@ -450,6 +452,16 @@ force this thread on or off.  If you force it off and don't have
 interrupts, the driver will run VERY slowly.  Don't blame me,
 these interfaces suck.
 
+Unfortunately, this thread can use a lot of CPU depending on the
+interface's performance.  This can waste a lot of CPU and cause
+various issues with detecting idle CPU and using extra power.  To
+avoid this, the kipmid_max_busy_us sets the maximum amount of time, in
+microseconds, that kipmid will spin before sleeping for a tick.  This
+value sets a balance between performance and CPU waste and needs to be
+tuned to your needs.  Maybe, someday, auto-tuning will be added, but
+that's not a simple thing and even the auto-tuning would need to be
+tuned to the user's desired performance.
+
 The driver supports a hot add and remove of interfaces.  This way,
 interfaces can be added or removed after the kernel is up and running.
 This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a
diff --git a/Documentation/Makefile b/Documentation/Makefile
index 94b945733534..6fc7ea1d1f9d 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -1,3 +1,3 @@
 obj-m := DocBook/ accounting/ auxdisplay/ connector/ \
-        filesystems/configfs/ ia64/ networking/ \
-        pcmcia/ spi/ video4linux/ vm/ watchdog/src/
+        filesystems/ filesystems/configfs/ ia64/ laptops/ networking/ \
+        pcmcia/ spi/ timers/ video4linux/ vm/ watchdog/src/
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 9bb62f7b89c3..71b6f500ddb9 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -6,16 +6,22 @@ checklist.txt
         - Review Checklist for RCU Patches
 listRCU.txt
         - Using RCU to Protect Read-Mostly Linked Lists
+lockdep.txt
+        - RCU and lockdep checking
 NMI-RCU.txt
         - Using RCU to Protect Dynamic NMI Handlers
+rcubarrier.txt
+        - RCU and Unloadable Modules
+rculist_nulls.txt
+        - RCU list primitives for use with SLAB_DESTROY_BY_RCU
 rcuref.txt
         - Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt
         - RCU Concepts
-rcubarrier.txt
-        - Unloading modules that use RCU callbacks
 RTFP.txt
         - List of RCU papers (bibliography) going back to 1980.
+stallwarn.txt
+        - RCU CPU stall warnings (CONFIG_RCU_CPU_STALL_DETECTOR)
 torture.txt
         - RCU Torture Test Operation (CONFIG_RCU_TORTURE_TEST)
 trace.txt
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index a6d32e65d222..a8536cb88091 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -34,7 +34,7 @@ NMI handler.
                 cpu = smp_processor_id();
                 ++nmi_count(cpu);
 
-                if (!rcu_dereference(nmi_callback)(regs, cpu))
+                if (!rcu_dereference_sched(nmi_callback)(regs, cpu))
                         default_do_nmi(regs);
 
                 nmi_exit();
@@ -47,12 +47,13 @@ function pointer.  If this handler returns zero, do_nmi() invokes the
 default_do_nmi() function to handle a machine-specific NMI.  Finally,
 preemption is restored.
 
-Strictly speaking, rcu_dereference() is not needed, since this code runs
-only on i386, which does not need rcu_dereference() anyway.  However,
-it is a good documentation aid, particularly for anyone attempting to
-do something similar on Alpha.
+In theory, rcu_dereference_sched() is not needed, since this code runs
+only on i386, which in theory does not need rcu_dereference_sched()
+anyway.  However, in practice it is a good documentation aid, particularly
+for anyone attempting to do something similar on Alpha or on systems
+with aggressive optimizing compilers.
 
-Quick Quiz:  Why might the rcu_dereference() be necessary on Alpha,
+Quick Quiz:  Why might the rcu_dereference_sched() be necessary on Alpha,
              given that the code referenced by the pointer is read-only?
 
 
@@ -99,17 +100,21 @@ invoke irq_enter() and irq_exit() on NMI entry and exit, respectively.
 
 Answer to Quick Quiz
 
-        Why might the rcu_dereference() be necessary on Alpha, given
+        Why might the rcu_dereference_sched() be necessary on Alpha, given
         that the code referenced by the pointer is read-only?
 
         Answer: The caller to set_nmi_callback() might well have
-                initialized some data that is to be used by the
-                new NMI handler.  In this case, the rcu_dereference()
-                would be needed, because otherwise a CPU that received
-                an NMI just after the new handler was set might see
-                the pointer to the new NMI handler, but the old
-                pre-initialized version of the handler's data.
-
-                More important, the rcu_dereference() makes it clear
-                to someone reading the code that the pointer is being
-                protected by RCU.
+                initialized some data that is to be used by the new NMI
+                handler.  In this case, the rcu_dereference_sched() would
+                be needed, because otherwise a CPU that received an NMI
+                just after the new handler was set might see the pointer
+                to the new NMI handler, but the old pre-initialized
+                version of the handler's data.
+
+                This same sad story can happen on other CPUs when using
+                a compiler with aggressive pointer-value speculation
+                optimizations.
+
+                More important, the rcu_dereference_sched() makes it
+                clear to someone reading the code that the pointer is
+                being protected by RCU-sched.
diff --git a/Documentation/RCU/RTFP.txt b/Documentation/RCU/RTFP.txt
index d2b85237c76e..5aea459e3dd6 100644
--- a/Documentation/RCU/RTFP.txt
+++ b/Documentation/RCU/RTFP.txt
@@ -25,10 +25,10 @@ to be referencing the data structure.  However, this mechanism was not
 optimized for modern computer systems, which is not surprising given
 that these overheads were not so expensive in the mid-80s.  Nonetheless,
 passive serialization appears to be the first deferred-destruction
-mechanism to be used in production.  Furthermore, the relevant patent has
-lapsed, so this approach may be used in non-GPL software, if desired.
-(In contrast, use of RCU is permitted only in software licensed under
-GPL.  Sorry!!!)
+mechanism to be used in production.  Furthermore, the relevant patent
+has lapsed, so this approach may be used in non-GPL software, if desired.
+(In contrast, implementation of RCU is permitted only in software licensed
+under either GPL or LGPL.  Sorry!!!)
 
 In 1990, Pugh [Pugh90] noted that explicitly tracking which threads
 were reading a given data structure permitted deferred free to operate
@@ -150,6 +150,18 @@ preemptible RCU [PaulEMcKenney2007PreemptibleRCU], and the three-part
 LWN "What is RCU?" series [PaulEMcKenney2007WhatIsRCUFundamentally,
 PaulEMcKenney2008WhatIsRCUUsage, and PaulEMcKenney2008WhatIsRCUAPI].
 
+2008 saw a journal paper on real-time RCU [DinakarGuniguntala2008IBMSysJ],
+a history of how Linux changed RCU more than RCU changed Linux
+[PaulEMcKenney2008RCUOSR], and a design overview of hierarchical RCU
+[PaulEMcKenney2008HierarchicalRCU].
+
+2009 introduced user-level RCU algorithms [PaulEMcKenney2009MaliciousURCU],
+which Mathieu Desnoyers is now maintaining [MathieuDesnoyers2009URCU]
+[MathieuDesnoyersPhD].  TINY_RCU [PaulEMcKenney2009BloatWatchRCU] made
+its appearance, as did expedited RCU [PaulEMcKenney2009expeditedRCU].
+The problem of resizeable RCU-protected hash tables may now be on a path
+to a solution [JoshTriplett2009RPHash].
+
 Bibtex Entries
 
 @article{Kung80
@@ -730,6 +742,11 @@ Revised:
 "
 }
 
+#
+#       "What is RCU?" LWN series.
+#
+########################################################################
+
 @article{DinakarGuniguntala2008IBMSysJ
 ,author="D. Guniguntala and P. E. McKenney and J. Triplett and J. Walpole"
 ,title="The read-copy-update mechanism for supporting real-time applications on shared-memory multiprocessor systems with {Linux}"
@@ -820,3 +837,39 @@ Revised:
         Uniprocessor assumptions allow simplified RCU implementation.
 "
 }
+
+@unpublished{PaulEMcKenney2009expeditedRCU
+,Author="Paul E. McKenney"
+,Title="[{PATCH} -tip 0/3] expedited 'big hammer' {RCU} grace periods"
+,month="June"
+,day="25"
+,year="2009"
+,note="Available:
+\url{http://lkml.org/lkml/2009/6/25/306}
+[Viewed August 16, 2009]"
+,annotation="
+        First posting of expedited RCU to be accepted into -tip.
+"
+}
+
+@unpublished{JoshTriplett2009RPHash
+,Author="Josh Triplett"
+,Title="Scalable concurrent hash tables via relativistic programming"
+,month="September"
+,year="2009"
+,note="Linux Plumbers Conference presentation"
+,annotation="
+        RP fun with hash tables.
+"
+}
+
+@phdthesis{MathieuDesnoyersPhD
+, title  = "Low-Impact Operating System Tracing"
+, author = "Mathieu Desnoyers"
+, school = "Ecole Polytechnique de Montr\'{e}al"
+, month  = "December"
+, year   = 2009
+,note="Available:
+\url{http://www.lttng.org/pub/thesis/desnoyers-dissertation-2009-12.pdf}
+[Viewed December 9, 2009]"
+}
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 51525a30e8b4..790d1a812376 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -8,13 +8,12 @@ would cause.  This list is based on experiences reviewing such patches
 over a rather long period of time, but improvements are always welcome!
 
 0.      Is RCU being applied to a read-mostly situation?  If the data
-        structure is updated more than about 10% of the time, then
-        you should strongly consider some other approach, unless
-        detailed performance measurements show that RCU is nonetheless
-        the right tool for the job.  Yes, you might think of RCU
-        as simply cutting overhead off of the readers and imposing it
-        on the writers.  That is exactly why normal uses of RCU will
-        do much more reading than updating.
+        structure is updated more than about 10% of the time, then you
+        should strongly consider some other approach, unless detailed
+        performance measurements show that RCU is nonetheless the right
+        tool for the job.  Yes, RCU does reduce read-side overhead by
+        increasing write-side overhead, which is exactly why normal uses
+        of RCU will do much more reading than updating.
 
         Another exception is where performance is not an issue, and RCU
         provides a simpler implementation.  An example of this situation
@@ -35,13 +34,13 @@ over a rather long period of time, but improvements are always welcome!
 
         If you choose #b, be prepared to describe how you have handled
         memory barriers on weakly ordered machines (pretty much all of
-        them -- even x86 allows reads to be reordered), and be prepared
-        to explain why this added complexity is worthwhile.  If you
-        choose #c, be prepared to explain how this single task does not
-        become a major bottleneck on big multiprocessor machines (for
-        example, if the task is updating information relating to itself
-        that other tasks can read, there by definition can be no
-        bottleneck).
+        them -- even x86 allows later loads to be reordered to precede
+        earlier stores), and be prepared to explain why this added
+        complexity is worthwhile.  If you choose #c, be prepared to
+        explain how this single task does not become a major bottleneck on
+        big multiprocessor machines (for example, if the task is updating
+        information relating to itself that other tasks can read, there
+        by definition can be no bottleneck).
 
 2.      Do the RCU read-side critical sections make proper use of
         rcu_read_lock() and friends?  These primitives are needed
@@ -51,8 +50,10 @@ over a rather long period of time, but improvements are always welcome!
         actuarial risk of your kernel.
 
         As a rough rule of thumb, any dereference of an RCU-protected
-        pointer must be covered by rcu_read_lock() or rcu_read_lock_bh()
-        or by the appropriate update-side lock.
+        pointer must be covered by rcu_read_lock(), rcu_read_lock_bh(),
+        rcu_read_lock_sched(), or by the appropriate update-side lock.
+        Disabling of preemption can serve as rcu_read_lock_sched(), but
+        is less readable.
 
 3.      Does the update code tolerate concurrent accesses?
 
@@ -62,25 +63,27 @@ over a rather long period of time, but improvements are always welcome!
         of ways to handle this concurrency, depending on the situation:
 
         a.      Use the RCU variants of the list and hlist update
-                primitives to add, remove, and replace elements on an
-                RCU-protected list.  Alternatively, use the RCU-protected
-                trees that have been added to the Linux kernel.
+                primitives to add, remove, and replace elements on
+                an RCU-protected list.  Alternatively, use the other
+                RCU-protected data structures that have been added to
+                the Linux kernel.
 
                 This is almost always the best approach.
 
         b.      Proceed as in (a) above, but also maintain per-element
                 locks (that are acquired by both readers and writers)
                 that guard per-element state.  Of course, fields that
-                the readers refrain from accessing can be guarded by the
-                update-side lock.
+                the readers refrain from accessing can be guarded by
+                some other lock acquired only by updaters, if desired.
 
                 This works quite well, also.
 
         c.      Make updates appear atomic to readers.  For example,
-                pointer updates to properly aligned fields will appear
-                atomic, as will individual atomic primitives.  Operations
-                performed under a lock and sequences of multiple atomic
-                primitives will -not- appear to be atomic.
+                pointer updates to properly aligned fields will
+                appear atomic, as will individual atomic primitives.
+                Sequences of perations performed under a lock will -not-
+                appear to be atomic to RCU readers, nor will sequences
+                of multiple atomic primitives.
 
                 This can work, but is starting to get a bit tricky.
 
@@ -98,9 +101,9 @@ over a rather long period of time, but improvements are always welcome!
                 a new structure containing updated values.
 
 4.      Weakly ordered CPUs pose special challenges.  Almost all CPUs
-        are weakly ordered -- even i386 CPUs allow reads to be reordered.
-        RCU code must take all of the following measures to prevent
-        memory-corruption problems:
+        are weakly ordered -- even x86 CPUs allow later loads to be
+        reordered to precede earlier stores.  RCU code must take all of
+        the following measures to prevent memory-corruption problems:
 
         a.      Readers must maintain proper ordering of their memory
                 accesses.  The rcu_dereference() primitive ensures that
@@ -113,14 +116,25 @@ over a rather long period of time, but improvements are always welcome!
                 The rcu_dereference() primitive is also an excellent
                 documentation aid, letting the person reading the code
                 know exactly which pointers are protected by RCU.
-
-                The rcu_dereference() primitive is used by the various
-                "_rcu()" list-traversal primitives, such as the
-                list_for_each_entry_rcu().  Note that it is perfectly
-                legal (if redundant) for update-side code to use
-                rcu_dereference() and the "_rcu()" list-traversal
-                primitives.  This is particularly useful in code
-                that is common to readers and updaters.
+                Please note that compilers can also reorder code, and
+                they are becoming increasingly aggressive about doing
+                just that.  The rcu_dereference() primitive therefore
+                also prevents destructive compiler optimizations.
+
+                The rcu_dereference() primitive is used by the
+                various "_rcu()" list-traversal primitives, such
+                as the list_for_each_entry_rcu().  Note that it is
+                perfectly legal (if redundant) for update-side code to
+                use rcu_dereference() and the "_rcu()" list-traversal
+                primitives.  This is particularly useful in code that
+                is common to readers and updaters.  However, lockdep
+                will complain if you access rcu_dereference() outside
+                of an RCU read-side critical section.  See lockdep.txt
+                to learn what to do about this.
+
+                Of course, neither rcu_dereference() nor the "_rcu()"
+                list-traversal primitives can substitute for a good
+                concurrency design coordinating among multiple updaters.
 
         b.      If the list macros are being used, the list_add_tail_rcu()
                 and list_add_rcu() primitives must be used in order
@@ -135,11 +149,14 @@ over a rather long period of time, but improvements are always welcome!
                 readers.  Similarly, if the hlist macros are being used,
                 the hlist_del_rcu() primitive is required.
 
-                The list_replace_rcu() primitive may be used to
-                replace an old structure with a new one in an
-                RCU-protected list.
+                The list_replace_rcu() and hlist_replace_rcu() primitives
+                may be used to replace an old structure with a new one
+                in their respective types of RCU-protected lists.
+
+        d.      Rules similar to (4b) and (4c) apply to the "hlist_nulls"
+                type of RCU-protected linked lists.
 
-        d.      Updates must ensure that initialization of a given
+        e.      Updates must ensure that initialization of a given
                 structure happens before pointers to that structure are
                 publicized.  Use the rcu_assign_pointer() primitive
                 when publicizing a pointer to a structure that can
@@ -151,16 +168,31 @@ over a rather long period of time, but improvements are always welcome!
         it cannot block.
 
 6.      Since synchronize_rcu() can block, it cannot be called from
-        any sort of irq context.  Ditto for synchronize_sched() and
-        synchronize_srcu().
-
-7.      If the updater uses call_rcu(), then the corresponding readers
-        must use rcu_read_lock() and rcu_read_unlock().  If the updater
-        uses call_rcu_bh(), then the corresponding readers must use
-        rcu_read_lock_bh() and rcu_read_unlock_bh().  If the updater
-        uses call_rcu_sched(), then the corresponding readers must
-        disable preemption.  Mixing things up will result in confusion
-        and broken kernels.
+        any sort of irq context.  The same rule applies for
+        synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+        synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
+        synchronize_sched_expedite(), and synchronize_srcu_expedited().
+
+        The expedited forms of these primitives have the same semantics
+        as the non-expedited forms, but expediting is both expensive
+        and unfriendly to real-time workloads.  Use of the expedited
+        primitives should be restricted to rare configuration-change
+        operations that would not normally be undertaken while a real-time
+        workload is running.
+
+7.      If the updater uses call_rcu() or synchronize_rcu(), then the
+        corresponding readers must use rcu_read_lock() and
+        rcu_read_unlock().  If the updater uses call_rcu_bh() or
+        synchronize_rcu_bh(), then the corresponding readers must
+        use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+        updater uses call_rcu_sched() or synchronize_sched(), then
+        the corresponding readers must disable preemption, possibly
+        by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+        If the updater uses synchronize_srcu(), the the corresponding
+        readers must use srcu_read_lock() and srcu_read_unlock(),
+        and with the same srcu_struct.  The rules for the expedited
+        primitives are the same as for their non-expedited counterparts.
+        Mixing things up will result in confusion and broken kernels.
 
         One exception to this rule: rcu_read_lock() and rcu_read_unlock()
         may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -212,6 +244,8 @@ over a rather long period of time, but improvements are always welcome!
         e.      Periodically invoke synchronize_rcu(), permitting a limited
                 number of updates per grace period.
 
+        The same cautions apply to call_rcu_bh() and call_rcu_sched().
+
 9.      All RCU list-traversal primitives, which include
         rcu_dereference(), list_for_each_entry_rcu(),
         list_for_each_continue_rcu(), and list_for_each_safe_rcu(),
@@ -219,17 +253,21 @@ over a rather long period of time, but improvements are always welcome!
         must be protected by appropriate update-side locks.  RCU
         read-side critical sections are delimited by rcu_read_lock()
         and rcu_read_unlock(), or by similar primitives such as
-        rcu_read_lock_bh() and rcu_read_unlock_bh().
+        rcu_read_lock_bh() and rcu_read_unlock_bh(), in which case
+        the matching rcu_dereference() primitive must be used in order
+        to keep lockdep happy, in this case, rcu_dereference_bh().
 
         The reason that it is permissible to use RCU list-traversal
         primitives when the update-side lock is held is that doing so
         can be quite helpful in reducing code bloat when common code is
-        shared between readers and updaters.
+        shared between readers and updaters.  Additional primitives
+        are provided for this case, as discussed in lockdep.txt.
 
 10.     Conversely, if you are in an RCU read-side critical section,
         and you don't hold the appropriate update-side lock, you -must-
         use the "_rcu()" variants of the list macros.  Failing to do so
-        will break Alpha and confuse people reading your code.
+        will break Alpha, cause aggressive compilers to generate bad code,
+        and confuse people trying to read your code.
 
 11.     Note that synchronize_rcu() -only- guarantees to wait until
         all currently executing rcu_read_lock()-protected RCU read-side
@@ -239,15 +277,21 @@ over a rather long period of time, but improvements are always welcome!
         rcu_read_lock()-protected read-side critical sections, do -not-
         use synchronize_rcu().
 
-        If you want to wait for some of these other things, you might
-        instead need to use synchronize_irq() or synchronize_sched().
+        Similarly, disabling preemption is not an acceptable substitute
+        for rcu_read_lock().  Code that attempts to use preemption
+        disabling where it should be using rcu_read_lock() will break
+        in real-time kernel builds.
+
+        If you want to wait for interrupt handlers, NMI handlers, and
+        code under the influence of preempt_disable(), you instead
+        need to use synchronize_irq() or synchronize_sched().
 
 12.     Any lock acquired by an RCU callback must be acquired elsewhere
         with softirq disabled, e.g., via spin_lock_irqsave(),
         spin_lock_bh(), etc.  Failing to disable irq on a given
-        acquisition of that lock will result in deadlock as soon as the
-        RCU callback happens to interrupt that acquisition's critical
-        section.
+        acquisition of that lock will result in deadlock as soon as
+        the RCU softirq handler happens to run your RCU callback while
+        interrupting that acquisition's critical section.
 
 13.     RCU callbacks can be and are executed in parallel.  In many cases,
         the callback code simply wrappers around kfree(), so that this
@@ -265,29 +309,30 @@ over a rather long period of time, but improvements are always welcome!
         not the case, a self-spawning RCU callback would prevent the
         victim CPU from ever going offline.)
 
-14.     SRCU (srcu_read_lock(), srcu_read_unlock(), and synchronize_srcu())
-        may only be invoked from process context.  Unlike other forms of
-        RCU, it -is- permissible to block in an SRCU read-side critical
-        section (demarked by srcu_read_lock() and srcu_read_unlock()),
-        hence the "SRCU": "sleepable RCU".  Please note that if you
-        don't need to sleep in read-side critical sections, you should
-        be using RCU rather than SRCU, because RCU is almost always
-        faster and easier to use than is SRCU.
+14.     SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(),
+        synchronize_srcu(), and synchronize_srcu_expedited()) may only
+        be invoked from process context.  Unlike other forms of RCU, it
+        -is- permissible to block in an SRCU read-side critical section
+        (demarked by srcu_read_lock() and srcu_read_unlock()), hence the
+        "SRCU": "sleepable RCU".  Please note that if you don't need
+        to sleep in read-side critical sections, you should be using
+        RCU rather than SRCU, because RCU is almost always faster and
+        easier to use than is SRCU.
 
         Also unlike other forms of RCU, explicit initialization
         and cleanup is required via init_srcu_struct() and
         cleanup_srcu_struct().  These are passed a "struct srcu_struct"
         that defines the scope of a given SRCU domain.  Once initialized,
         the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock()
-        and synchronize_srcu().  A given synchronize_srcu() waits only
-        for SRCU read-side critical sections governed by srcu_read_lock()
-        and srcu_read_unlock() calls that have been passd the same
-        srcu_struct.  This property is what makes sleeping read-side
-        critical sections tolerable -- a given subsystem delays only
-        its own updates, not those of other subsystems using SRCU.
-        Therefore, SRCU is less prone to OOM the system than RCU would
-        be if RCU's read-side critical sections were permitted to
-        sleep.
+        synchronize_srcu(), and synchronize_srcu_expedited().  A given
+        synchronize_srcu() waits only for SRCU read-side critical
+        sections governed by srcu_read_lock() and srcu_read_unlock()
+        calls that have been passed the same srcu_struct.  This property
+        is what makes sleeping read-side critical sections tolerable --
+        a given subsystem delays only its own updates, not those of other
+        subsystems using SRCU.  Therefore, SRCU is less prone to OOM the
+        system than RCU would be if RCU's read-side critical sections
+        were permitted to sleep.
 
         The ability to sleep in read-side critical sections does not
         come for free.  First, corresponding srcu_read_lock() and
@@ -300,8 +345,8 @@ over a rather long period of time, but improvements are always welcome!
         requiring SRCU's read-side deadlock immunity or low read-side
         realtime latency.
 
-        Note that, rcu_assign_pointer() and rcu_dereference() relate to
-        SRCU just as they do to other forms of RCU.
+        Note that, rcu_assign_pointer() relates to SRCU just as they do
+        to other forms of RCU.
 
 15.     The whole point of call_rcu(), synchronize_rcu(), and friends
         is to wait until all pre-existing readers have finished before
@@ -311,12 +356,12 @@ over a rather long period of time, but improvements are always welcome!
         destructive operation, and -only- -then- invoke call_rcu(),
         synchronize_rcu(), or friends.
 
-        Because these primitives only wait for pre-existing readers,
-        it is the caller's responsibility to guarantee safety to
-        any subsequent readers.
+        Because these primitives only wait for pre-existing readers, it
+        is the caller's responsibility to guarantee that any subsequent
+        readers will execute safely.
 
-16.     The various RCU read-side primitives do -not- contain memory
-        barriers.  The CPU (and in some cases, the compiler) is free
-        to reorder code into and out of RCU read-side critical sections.
-        It is the responsibility of the RCU update-side primitives to
-        deal with this.
+16.     The various RCU read-side primitives do -not- necessarily contain
+        memory barriers.  You should therefore plan for the CPU
+        and the compiler to freely reorder code into and out of RCU
+        read-side critical sections.  It is the responsibility of the
+        RCU update-side primitives to deal with this.
diff --git a/Documentation/RCU/lockdep.txt b/Documentation/RCU/lockdep.txt
new file mode 100644
index 000000000000..d7a49b2f6994
--- /dev/null
+++ b/Documentation/RCU/lockdep.txt
@@ -0,0 +1,91 @@
+RCU and lockdep checking
+
+All flavors of RCU have lockdep checking available, so that lockdep is
+aware of when each task enters and leaves any flavor of RCU read-side
+critical section.  Each flavor of RCU is tracked separately (but note
+that this is not the case in 2.6.32 and earlier).  This allows lockdep's
+tracking to include RCU state, which can sometimes help when debugging
+deadlocks and the like.
+
+In addition, RCU provides the following primitives that check lockdep's
+state:
+
+        rcu_read_lock_held() for normal RCU.
+        rcu_read_lock_bh_held() for RCU-bh.
+        rcu_read_lock_sched_held() for RCU-sched.
+        srcu_read_lock_held() for SRCU.
+
+These functions are conservative, and will therefore return 1 if they
+aren't certain (for example, if CONFIG_DEBUG_LOCK_ALLOC is not set).
+This prevents things like WARN_ON(!rcu_read_lock_held()) from giving false
+positives when lockdep is disabled.
+
+In addition, a separate kernel config parameter CONFIG_PROVE_RCU enables
+checking of rcu_dereference() primitives:
+
+        rcu_dereference(p):
+                Check for RCU read-side critical section.
+        rcu_dereference_bh(p):
+                Check for RCU-bh read-side critical section.
+        rcu_dereference_sched(p):
+                Check for RCU-sched read-side critical section.
+        srcu_dereference(p, sp):
+                Check for SRCU read-side critical section.
+        rcu_dereference_check(p, c):
+                Use explicit check expression "c".  This is useful in
+                code that is invoked by both readers and updaters.
+        rcu_dereference_raw(p)
+                Don't check.  (Use sparingly, if at all.)
+        rcu_dereference_protected(p, c):
+                Use explicit check expression "c", and omit all barriers
+                and compiler constraints.  This is useful when the data
+                structure cannot change, for example, in code that is
+                invoked only by updaters.
+        rcu_access_pointer(p):
+                Return the value of the pointer and omit all barriers,
+                but retain the compiler constraints that prevent duplicating
+                or coalescsing.  This is useful when when testing the
+                value of the pointer itself, for example, against NULL.
+
+The rcu_dereference_check() check expression can be any boolean
+expression, but would normally include one of the rcu_read_lock_held()
+family of functions and a lockdep expression.  However, any boolean
+expression can be used.  For a moderately ornate example, consider
+the following:
+
+        file = rcu_dereference_check(fdt->fd[fd],
+                                     rcu_read_lock_held() ||
+                                     lockdep_is_held(&files->file_lock) ||
+                                     atomic_read(&files->count) == 1);
+
+This expression picks up the pointer "fdt->fd[fd]" in an RCU-safe manner,
+and, if CONFIG_PROVE_RCU is configured, verifies that this expression
+is used in:
+
+1.      An RCU read-side critical section, or
+2.      with files->file_lock held, or
+3.      on an unshared files_struct.
+
+In case (1), the pointer is picked up in an RCU-safe manner for vanilla
+RCU read-side critical sections, in case (2) the ->file_lock prevents
+any change from taking place, and finally, in case (3) the current task
+is the only task accessing the file_struct, again preventing any change
+from taking place.  If the above statement was invoked only from updater
+code, it could instead be written as follows:
+
+        file = rcu_dereference_protected(fdt->fd[fd],
+                                         lockdep_is_held(&files->file_lock) ||
+                                         atomic_read(&files->count) == 1);
+
+This would verify cases #2 and #3 above, and furthermore lockdep would
+complain if this was used in an RCU read-side critical section unless one
+of these two cases held.  Because rcu_dereference_protected() omits all
+barriers and compiler constraints, it generates better code than do the
+other flavors of rcu_dereference().  On the other hand, it is illegal
+to use rcu_dereference_protected() if either the RCU-protected pointer
+or the RCU-protected data that it points to can change concurrently.
+
+There are currently only "universal" versions of the rcu_assign_pointer()
+and RCU list-/tree-traversal primitives, which do not (yet) check for
+being in an RCU read-side critical section.  In the future, separate
+versions of these primitives might be created.
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 2a23523ce471..31852705b586 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -75,6 +75,8 @@ o	I hear that RCU is patented?  What is with that?
         search for the string "Patent" in RTFP.txt to find them.
         Of these, one was allowed to lapse by the assignee, and the
         others have been contributed to the Linux kernel under GPL.
+        There are now also LGPL implementations of user-level RCU
+        available (http://lttng.org/?q=node/18).
 
 o       I hear that RCU needs work in order to support realtime kernels?
 
@@ -91,48 +93,4 @@ o	Where can I find more information on RCU?
 
 o       What are all these files in this directory?
 
-
-        NMI-RCU.txt
-
-                Describes how to use RCU to implement dynamic
-                NMI handlers, which can be revectored on the fly,
-                without rebooting.
-
-        RTFP.txt
-
-                List of RCU-related publications and web sites.
-
-        UP.txt
-
-                Discussion of RCU usage in UP kernels.
-
-        arrayRCU.txt
-
-                Describes how to use RCU to protect arrays, with
-                resizeable arrays whose elements reference other
-                data structures being of the most interest.
-
-        checklist.txt
-
-                Lists things to check for when inspecting code that
-                uses RCU.
-
-        listRCU.txt
-
-                Describes how to use RCU to protect linked lists.
-                This is the simplest and most common use of RCU
-                in the Linux kernel.
-
-        rcu.txt
-
-                You are reading it!
-
-        rcuref.txt
-
-                Describes how to combine use of reference counts
-                with RCU.
-
-        whatisRCU.txt
-
-                Overview of how the RCU implementation works.  Along
-                the way, presents a conceptual view of RCU.
+        See 00-INDEX for the list.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
new file mode 100644
index 000000000000..44c6dcc93d6d
--- /dev/null
+++ b/Documentation/RCU/stallwarn.txt
@@ -0,0 +1,106 @@
+Using RCU's CPU Stall Detector
+
+The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
+RCU's CPU stall detector, which detects conditions that unduly delay
+RCU grace periods.  The stall detector's idea of what constitutes
+"unduly delayed" is controlled by a set of C preprocessor macros:
+
+RCU_SECONDS_TILL_STALL_CHECK
+
+        This macro defines the period of time that RCU will wait from
+        the beginning of a grace period until it issues an RCU CPU
+        stall warning.  This time period is normally ten seconds.
+
+RCU_SECONDS_TILL_STALL_RECHECK
+
+        This macro defines the period of time that RCU will wait after
+        issuing a stall warning until it issues another stall warning
+        for the same stall.  This time period is normally set to thirty
+        seconds.
+
+RCU_STALL_RAT_DELAY
+
+        The CPU stall detector tries to make the offending CPU print its
+        own warnings, as this often gives better-quality stack traces.
+        However, if the offending CPU does not detect its own stall in
+        the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+        some other CPU will complain.  This delay is normally set to
+        two jiffies.
+
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched.  This message will normally be
+followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh.  This message
+will normally be followed by stack dumps for each CPU.  Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+
+This is rare, but does happen from time to time in real life.
+
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
+
+o       A CPU looping in an RCU read-side critical section.
+        
+o       A CPU looping with interrupts disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
+
+o       A CPU looping with preemption disabled.  This condition can
+        result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+        stalls.
+
+o       A CPU looping with bottom halves disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
+
+o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+        without invoking schedule().
+
+o       A bug in the RCU implementation.
+
+o       A hardware failure.  This is quite unlikely, but has occurred
+        at least once in real life.  A CPU failed in a running system,
+        becoming unresponsive, but not causing an immediate crash.
+        This resulted in a series of RCU CPU stall warnings, eventually
+        leading the realization that the CPU had failed.
+
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning.  SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls.  Please note that RCU only detects
+CPU stalls when there is a grace period in progress.  No grace period,
+no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
+
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 9dba3bb90e60..5d9016795fd8 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -30,6 +30,18 @@ MODULE PARAMETERS
 
 This module has the following parameters:
 
+fqs_duration    Duration (in microseconds) of artificially induced bursts
+                of force_quiescent_state() invocations.  In RCU
+                implementations having force_quiescent_state(), these
+                bursts help force races between forcing a given grace
+                period and that grace period ending on its own.
+
+fqs_holdoff     Holdoff time (in microseconds) between consecutive calls
+                to force_quiescent_state() within a burst.
+
+fqs_stutter     Wait time (in seconds) between consecutive bursts
+                of calls to force_quiescent_state().
+
 irqreaders      Says to invoke RCU readers from irq level.  This is currently
                 done via timers.  Defaults to "1" for variants of RCU that
                 permit this.  (Or, more accurately, variants of RCU that do
@@ -170,16 +182,6 @@ Similarly, sched_expedited RCU provides the following:
         sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
         sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
         sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
-        state: -1 / 0:0 3:0 4:0
-
-As before, the first four lines are similar to those for RCU.
-The last line shows the task-migration state.  The first number is
--1 if synchronize_sched_expedited() is idle, -2 if in the process of
-posting wakeups to the migration kthreads, and N when waiting on CPU N.
-Each of the colon-separated fields following the "/" is a CPU:state pair.
-Valid states are "0" for idle, "1" for waiting for quiescent state,
-"2" for passed through quiescent state, and "3" when a race with a
-CPU-hotplug event forces use of the synchronize_sched() primitive.
 
 
 USAGE
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd85e921..efd8cc95c06b 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 The output of "cat rcu/rcu_pending" looks as follows:
 
 rcu_sched:
-  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@ o	"np" is the number of times that __rcu_pending() has been invoked
 o       "qsp" is the number of times that the RCU was waiting for a
         quiescent state from this CPU.
 
+o       "rpq" is the number of times that the CPU had passed through
+        a quiescent state, but not yet reported it to RCU.
+
 o       "cbr" is the number of times that this CPU had RCU callbacks
         that had passed through a grace period, and were thus ready
         to be invoked.
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index d542ca243b80..cfaac34c4557 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -323,14 +323,17 @@ used as follows:
         Defer                   Protect
 
 a.      synchronize_rcu()       rcu_read_lock() / rcu_read_unlock()
-        call_rcu()
+        call_rcu()              rcu_dereference()
 
 b.      call_rcu_bh()           rcu_read_lock_bh() / rcu_read_unlock_bh()
+                                rcu_dereference_bh()
 
-c.      synchronize_sched()     preempt_disable() / preempt_enable()
+c.      synchronize_sched()     rcu_read_lock_sched() / rcu_read_unlock_sched()
+                                preempt_disable() / preempt_enable()
                                 local_irq_save() / local_irq_restore()
                                 hardirq enter / hardirq exit
                                 NMI enter / NMI exit
+                                rcu_dereference_sched()
 
 These three mechanisms are used as follows:
 
@@ -780,9 +783,8 @@ Linux-kernel source code, but it helps to have a full list of the
 APIs, since there does not appear to be a way to categorize them
 in docbook.  Here is the list, by category.
 
-RCU pointer/list traversal:
+RCU list traversal:
 
-        rcu_dereference
         list_for_each_entry_rcu
         hlist_for_each_entry_rcu
         hlist_nulls_for_each_entry_rcu
@@ -808,7 +810,7 @@ RCU:	Critical sections	Grace period		Barrier
 
         rcu_read_lock           synchronize_net         rcu_barrier
         rcu_read_unlock         synchronize_rcu
-                                synchronize_rcu_expedited
+        rcu_dereference         synchronize_rcu_expedited
                                 call_rcu
 
 
@@ -816,7 +818,7 @@ bh:	Critical sections	Grace period		Barrier
 
         rcu_read_lock_bh        call_rcu_bh             rcu_barrier_bh
         rcu_read_unlock_bh      synchronize_rcu_bh
-                                synchronize_rcu_bh_expedited
+        rcu_dereference_bh      synchronize_rcu_bh_expedited
 
 
 sched:  Critical sections       Grace period            Barrier
@@ -825,17 +827,25 @@ sched:	Critical sections	Grace period		Barrier
         rcu_read_unlock_sched   call_rcu_sched
         [preempt_disable]       synchronize_sched_expedited
         [and friends]
+        rcu_dereference_sched
 
 
 SRCU:   Critical sections       Grace period            Barrier
 
         srcu_read_lock          synchronize_srcu        N/A
         srcu_read_unlock        synchronize_srcu_expedited
+        srcu_dereference
 
 SRCU:   Initialization/cleanup
         init_srcu_struct
         cleanup_srcu_struct
 
+All:  lockdep-checked RCU-protected pointer access
+
+        rcu_dereference_check
+        rcu_dereference_protected
+        rcu_access_pointer
+
 See the comment headers in the source code (or the docbook generated
 from them) for more information.
 
diff --git a/Documentation/SubmitChecklist b/Documentation/SubmitChecklist
index 1053a56be3b1..8916ca48bc95 100644
--- a/Documentation/SubmitChecklist
+++ b/Documentation/SubmitChecklist
@@ -9,10 +9,14 @@ Documentation/SubmittingPatches and elsewhere regarding submitting Linux
 kernel patches.
 
 
-1: Builds cleanly with applicable or modified CONFIG options =y, =m, and
+1: If you use a facility then #include the file that defines/declares
+   that facility.  Don't depend on other header files pulling in ones
+   that you use.
+
+2: Builds cleanly with applicable or modified CONFIG options =y, =m, and
    =n.  No gcc warnings/errors, no linker warnings/errors.
 
-2: Passes allnoconfig, allmodconfig
+2b: Passes allnoconfig, allmodconfig
 
 3: Builds on multiple CPU architectures by using local cross-compile tools
    or some other build farm.
diff --git a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
index 76b3a11e90be..fa968aa99d67 100644
--- a/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
+++ b/Documentation/arm/Samsung-S3C24XX/CPUfreq.txt
@@ -14,8 +14,8 @@ Introduction
  how the clocks are arranged. The first implementation used as single
  PLL to feed the ARM, memory and peripherals via a series of dividers
  and muxes and this is the implementation that is documented here. A
- newer version where there is a seperate PLL and clock divider for the
- ARM core is available as a seperate driver.
+ newer version where there is a separate PLL and clock divider for the
+ ARM core is available as a separate driver.
 
 
 Layout
diff --git a/Documentation/arm/Samsung/Overview.txt b/Documentation/arm/Samsung/Overview.txt
new file mode 100644
index 000000000000..7cced1fea9c3
--- /dev/null
+++ b/Documentation/arm/Samsung/Overview.txt
@@ -0,0 +1,86 @@
+                Samsung ARM Linux Overview
+                ==========================
+
+Introduction
+------------
+
+  The Samsung range of ARM SoCs spans many similar devices, from the initial
+  ARM9 through to the newest ARM cores. This document shows an overview of
+  the current kernel support, how to use it and where to find the code
+  that supports this.
+
+  The currently supported SoCs are:
+
+  - S3C24XX: See Documentation/arm/Samsung-S3C24XX/Overview.txt for full list
+  - S3C64XX: S3C6400 and S3C6410
+  - S5PC6440
+
+  S5PC100 and S5PC110 support is currently being merged
+
+
+S3C24XX Systems
+---------------
+
+  There is still documentation in Documnetation/arm/Samsung-S3C24XX/ which
+  deals with the architecture and drivers specific to these devices.
+
+  See Documentation/arm/Samsung-S3C24XX/Overview.txt for more information
+  on the implementation details and specific support.
+
+
+Configuration
+-------------
+
+  A number of configurations are supplied, as there is no current way of
+  unifying all the SoCs into one kernel.
+
+  s5p6440_defconfig - S5P6440 specific default configuration
+  s5pc100_defconfig - S5PC100 specific default configuration
+
+
+Layout
+------
+
+  The directory layout is currently being restructured, and consists of
+  several platform directories and then the machine specific directories
+  of the CPUs being built for.
+
+  plat-samsung provides the base for all the implementations, and is the
+  last in the line of include directories that are processed for the build
+  specific information. It contains the base clock, GPIO and device definitions
+  to get the system running.
+
+  plat-s3c is the s3c24xx/s3c64xx platform directory, although it is currently
+  involved in other builds this will be phased out once the relevant code is
+  moved elsewhere.
+
+  plat-s3c24xx is for s3c24xx specific builds, see the S3C24XX docs.
+
+  plat-s3c64xx is for the s3c64xx specific bits, see the S3C24XX docs.
+
+  plat-s5p is for s5p specific builds, more to be added.
+
+
+  [ to finish ]
+
+
+Port Contributors
+-----------------
+
+  Ben Dooks (BJD)
+  Vincent Sanders
+  Herbert Potzl
+  Arnaud Patard (RTP)
+  Roc Wu
+  Klaus Fetscher
+  Dimitry Andric
+  Shannon Holland
+  Guillaume Gourat (NexVision)
+  Christer Weinigel (wingel) (Acer N30)
+  Lucas Correia Villa Real (S3C2400 port)
+
+
+Document Author
+---------------
+
+Copyright 2009-2010 Ben Dooks <ben-linux@fluff.org>
diff --git a/Documentation/arm/Samsung/clksrc-change-registers.awk b/Documentation/arm/Samsung/clksrc-change-registers.awk
new file mode 100755
index 000000000000..0c50220851fb
--- /dev/null
+++ b/Documentation/arm/Samsung/clksrc-change-registers.awk
@@ -0,0 +1,167 @@
+#!/usr/bin/awk -f
+#
+# Copyright 2010 Ben Dooks <ben-linux@fluff.org>
+#
+# Released under GPLv2
+
+# example usage
+# ./clksrc-change-registers.awk arch/arm/plat-s5pc1xx/include/plat/regs-clock.h < src > dst
+
+function extract_value(s)
+{
+    eqat = index(s, "=")
+    comat = index(s, ",")
+    return substr(s, eqat+2, (comat-eqat)-2)
+}
+
+function remove_brackets(b)
+{
+    return substr(b, 2, length(b)-2)
+}
+
+function splitdefine(l, p)
+{
+    r = split(l, tp)
+
+    p[0] = tp[2]
+    p[1] = remove_brackets(tp[3])
+}
+
+function find_length(f)
+{
+    if (0)
+        printf "find_length " f "\n" > "/dev/stderr"
+
+    if (f ~ /0x1/)
+        return 1
+    else if (f ~ /0x3/)
+        return 2
+    else if (f ~ /0x7/)
+        return 3
+    else if (f ~ /0xf/)
+        return 4
+
+    printf "unknown legnth " f "\n" > "/dev/stderr"
+    exit
+}
+
+function find_shift(s)
+{
+    id = index(s, "<")
+    if (id <= 0) {
+        printf "cannot find shift " s "\n" > "/dev/stderr"
+        exit
+    }
+
+    return substr(s, id+2)
+}
+
+
+BEGIN {
+    if (ARGC < 2) {
+        print "too few arguments" > "/dev/stderr"
+        exit
+    }
+
+# read the header file and find the mask values that we will need
+# to replace and create an associative array of values
+
+    while (getline line < ARGV[1] > 0) {
+        if (line ~ /\#define.*_MASK/ &&
+            !(line ~ /S5PC100_EPLL_MASK/) &&
+            !(line ~ /USB_SIG_MASK/)) {
+            splitdefine(line, fields)
+            name = fields[0]
+            if (0)
+                printf "MASK " line "\n" > "/dev/stderr"
+            dmask[name,0] = find_length(fields[1])
+            dmask[name,1] = find_shift(fields[1])
+            if (0)
+                printf "=> '" name "' LENGTH=" dmask[name,0] " SHIFT=" dmask[name,1] "\n" > "/dev/stderr"
+        } else {
+        }
+    }
+
+    delete ARGV[1]
+}
+
+/clksrc_clk.*=.*{/ {
+    shift=""
+    mask=""
+    divshift=""
+    reg_div=""
+    reg_src=""
+    indent=1
+
+    print $0
+
+    for(; indent >= 1;) {
+        if ((getline line) <= 0) {
+            printf "unexpected end of file" > "/dev/stderr"
+            exit 1;
+        }
+
+        if (line ~ /\.shift/) {
+            shift = extract_value(line)
+        } else if (line ~ /\.mask/) {
+            mask = extract_value(line)
+        } else if (line ~ /\.reg_divider/) {
+            reg_div = extract_value(line)
+        } else if (line ~ /\.reg_source/) {
+            reg_src = extract_value(line)
+        } else if (line ~ /\.divider_shift/) {
+            divshift = extract_value(line)
+        } else if (line ~ /{/) {
+                indent++
+                print line
+            } else if (line ~ /}/) {
+            indent--
+
+            if (indent == 0) {
+                if (0) {
+                    printf "shift '" shift   "' ='" dmask[shift,0] "'\n" > "/dev/stderr"
+                    printf "mask  '" mask    "'\n" > "/dev/stderr"
+                    printf "dshft '" divshift "'\n" > "/dev/stderr"
+                    printf "rdiv  '" reg_div "'\n" > "/dev/stderr"
+                    printf "rsrc  '" reg_src "'\n" > "/dev/stderr"
+                }
+
+                generated = mask
+                sub(reg_src, reg_div, generated)
+
+                if (0) {
+                    printf "/* rsrc " reg_src " */\n"
+                    printf "/* rdiv " reg_div " */\n"
+                    printf "/* shift " shift " */\n"
+                    printf "/* mask " mask " */\n"
+                    printf "/* generated " generated " */\n"
+                }
+
+                if (reg_div != "") {
+                    printf "\t.reg_div = { "
+                    printf ".reg = " reg_div ", "
+                    printf ".shift = " dmask[generated,1] ", "
+                    printf ".size = " dmask[generated,0] ", "
+                    printf "},\n"
+                }
+
+                printf "\t.reg_src = { "
+                printf ".reg = " reg_src ", "
+                printf ".shift = " dmask[mask,1] ", "
+                printf ".size = " dmask[mask,0] ", "
+
+                printf "},\n"
+
+            }
+
+            print line
+        } else {
+            print line
+        }
+
+        if (0)
+            printf indent ":" line "\n" > "/dev/stderr"
+    }
+}
+
+// && ! /clksrc_clk.*=.*{/ { print $0 }
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 9d58c7c5eddd..eb0fae18ffb1 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -59,7 +59,11 @@ PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
                                 This maps the platforms RAM, and typically
                                 maps all platform RAM in a 1:1 relationship.
 
-TASK_SIZE       PAGE_OFFSET-1   Kernel module space
+PKMAP_BASE      PAGE_OFFSET-1   Permanent kernel mappings
+                                One way of mapping HIGHMEM pages into kernel
+                                space.
+
+MODULES_VADDR   MODULES_END-1   Kernel module space
                                 Kernel modules inserted via insmod are
                                 placed here using dynamic mappings.
 
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 6fab97ea7e6b..508b5b2b0289 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -1162,8 +1162,8 @@ where a driver received a request ala this before:
 
 As mentioned, there is no virtual mapping of a bio. For DMA, this is
 not a problem as the driver probably never will need a virtual mapping.
-Instead it needs a bus mapping (pci_map_page for a single segment or
-use blk_rq_map_sg for scatter gather) to be able to ship it to the driver. For
+Instead it needs a bus mapping (dma_map_page for a single segment or
+use dma_map_sg for scatter gather) to be able to ship it to the driver. For
 PIO drivers (or drivers that need to revert to PIO transfer once in a
 while (IDE for example)), where the CPU is doing the actual data
 transfer a virtual mapping is needed. If the driver supports highmem I/O,
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index e164403f60e1..f65274081c8d 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -25,11 +25,11 @@ size allowed by the hardware.
 
 nomerges (RW)
 -------------
-This enables the user to disable the lookup logic involved with IO merging
-requests in the block layer. Merging may still occur through a direct
-1-hit cache, since that comes for (almost) free. The IO scheduler will not
-waste cycles doing tree/hash lookups for merges if nomerges is 1. Defaults
-to 0, enabling all merges.
+This enables the user to disable the lookup logic involved with IO
+merging requests in the block layer. By default (0) all merges are
+enabled. When set to 1 only simple one-hit merges will be tried. When
+set to 2 no merge algorithms will be tried (including one-hit or more
+complex tree/hash lookups).
 
 nr_requests (RW)
 ----------------
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index da42ab414c48..2b5f823abd03 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -88,12 +88,12 @@ changes occur:
         This is used primarily during fault processing.
 
 5) void update_mmu_cache(struct vm_area_struct *vma,
-                         unsigned long address, pte_t pte)
+                         unsigned long address, pte_t *ptep)
 
         At the end of every page fault, this routine is invoked to
         tell the architecture specific code that a translation
-        described by "pte" now exists at virtual address "address"
-        for address space "vma->vm_mm", in the software page tables.
+        now exists at virtual address "address" for address space
+        "vma->vm_mm", in the software page tables.
 
         A port may use this information in any way it so chooses.
         For example, it could use this event to pre-load TLB
@@ -377,3 +377,27 @@ maps this page at its virtual address.
         All the functionality of flush_icache_page can be implemented in
         flush_dcache_page and update_mmu_cache. In 2.7 the hope is to
         remove this interface completely.
+
+The final category of APIs is for I/O to deliberately aliased address
+ranges inside the kernel.  Such aliases are set up by use of the
+vmap/vmalloc API.  Since kernel I/O goes via physical pages, the I/O
+subsystem assumes that the user mapping and kernel offset mapping are
+the only aliases.  This isn't true for vmap aliases, so anything in
+the kernel trying to do I/O to vmap areas must manually manage
+coherency.  It must do this by flushing the vmap range before doing
+I/O and invalidating it after the I/O returns.
+
+  void flush_kernel_vmap_range(void *vaddr, int size)
+       flushes the kernel cache for a given virtual address range in
+       the vmap area.  This is to make sure that any data the kernel
+       modified in the vmap range is made visible to the physical
+       page.  The design is to make this area safe to perform I/O on.
+       Note that this API does *not* also flush the offset map alias
+       of the area.
+
+  void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates
+       the cache for a given virtual address range in the vmap area
+       which prevents the processor from making the cache stale by
+       speculatively reading data while the I/O was occurring to the
+       physical pages.  This is only necessary for data reads into the
+       vmap area.
diff --git a/Documentation/cdrom/ide-cd b/Documentation/cdrom/ide-cd
index 2c558cd6c1ef..f4dc9de2694e 100644
--- a/Documentation/cdrom/ide-cd
+++ b/Documentation/cdrom/ide-cd
@@ -159,42 +159,7 @@ two arguments:  the CDROM device, and the slot number to which you wish
 to change.  If the slot number is -1, the drive is unloaded.
 
 
-4. Compilation options
-----------------------
-
-There are a few additional options which can be set when compiling the
-driver.  Most people should not need to mess with any of these; they
-are listed here simply for completeness.  A compilation option can be
-enabled by adding a line of the form `#define <option> 1' to the top
-of ide-cd.c.  All these options are disabled by default.
-
-VERBOSE_IDE_CD_ERRORS
-  If this is set, ATAPI error codes will be translated into textual
-  descriptions.  In addition, a dump is made of the command which
-  provoked the error.  This is off by default to save the memory used
-  by the (somewhat long) table of error descriptions.  
-
-STANDARD_ATAPI
-  If this is set, the code needed to deal with certain drives which do
-  not properly implement the ATAPI spec will be disabled.  If you know
-  your drive implements ATAPI properly, you can turn this on to get a
-  slightly smaller kernel.
-
-NO_DOOR_LOCKING
-  If this is set, the driver will never attempt to lock the door of
-  the drive.
-
-CDROM_NBLOCKS_BUFFER
-  This sets the size of the buffer to be used for a CDROMREADAUDIO
-  ioctl.  The default is 8.
-
-TEST
-  This currently enables an additional ioctl which enables a user-mode
-  program to execute an arbitrary packet command.  See the source for
-  details.  This should be left off unless you know what you're doing.
-
-
-5. Common problems
+4. Common problems
 ------------------
 
 This section discusses some common problems encountered when trying to
@@ -371,7 +336,7 @@ f. Data corruption.
     expense of low system performance.
 
 
-6. cdchange.c
+5. cdchange.c
 -------------
 
 /*
diff --git a/Documentation/cgroups/cgroup_event_listener.c b/Documentation/cgroups/cgroup_event_listener.c
new file mode 100644
index 000000000000..8c2bfc4a6358
--- /dev/null
+++ b/Documentation/cgroups/cgroup_event_listener.c
@@ -0,0 +1,110 @@
+/*
+ * cgroup_event_listener.c - Simple listener of cgroup events
+ *
+ * Copyright (C) Kirill A. Shutemov <kirill@shutemov.name>
+ */
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/eventfd.h>
+
+#define USAGE_STR "Usage: cgroup_event_listener <path-to-control-file> <args>\n"
+
+int main(int argc, char **argv)
+{
+        int efd = -1;
+        int cfd = -1;
+        int event_control = -1;
+        char event_control_path[PATH_MAX];
+        char line[LINE_MAX];
+        int ret;
+
+        if (argc != 3) {
+                fputs(USAGE_STR, stderr);
+                return 1;
+        }
+
+        cfd = open(argv[1], O_RDONLY);
+        if (cfd == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", argv[1],
+                                strerror(errno));
+                goto out;
+        }
+
+        ret = snprintf(event_control_path, PATH_MAX, "%s/cgroup.event_control",
+                        dirname(argv[1]));
+        if (ret >= PATH_MAX) {
+                fputs("Path to cgroup.event_control is too long\n", stderr);
+                goto out;
+        }
+
+        event_control = open(event_control_path, O_WRONLY);
+        if (event_control == -1) {
+                fprintf(stderr, "Cannot open %s: %s\n", event_control_path,
+                                strerror(errno));
+                goto out;
+        }
+
+        efd = eventfd(0, 0);
+        if (efd == -1) {
+                perror("eventfd() failed");
+                goto out;
+        }
+
+        ret = snprintf(line, LINE_MAX, "%d %d %s", efd, cfd, argv[2]);
+        if (ret >= LINE_MAX) {
+                fputs("Arguments string is too long\n", stderr);
+                goto out;
+        }
+
+        ret = write(event_control, line, strlen(line) + 1);
+        if (ret == -1) {
+                perror("Cannot write to cgroup.event_control");
+                goto out;
+        }
+
+        while (1) {
+                uint64_t result;
+
+                ret = read(efd, &result, sizeof(result));
+                if (ret == -1) {
+                        if (errno == EINTR)
+                                continue;
+                        perror("Cannot read from eventfd");
+                        break;
+                }
+                assert(ret == sizeof(result));
+
+                ret = access(event_control_path, W_OK);
+                if ((ret == -1) && (errno == ENOENT)) {
+                                puts("The cgroup seems to have removed.");
+                                ret = 0;
+                                break;
+                }
+
+                if (ret == -1) {
+                        perror("cgroup.event_control "
+                                        "is not accessable any more");
+                        break;
+                }
+
+                printf("%s %s: crossed\n", argv[1], argv[2]);
+        }
+
+out:
+        if (efd >= 0)
+                close(efd);
+        if (event_control >= 0)
+                close(event_control);
+        if (cfd >= 0)
+                close(cfd);
+
+        return (ret != 0);
+}
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 0b33bfe7dde9..a1ca5924faff 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -22,6 +22,8 @@ CONTENTS:
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Attaching processes
+  2.3 Mounting hierarchies by name
+  2.4 Notification API
 3. Kernel API
   3.1 Overview
   3.2 Synchronization
@@ -233,8 +235,7 @@ containing the following files describing that cgroup:
  - cgroup.procs: list of tgids in the cgroup.  This list is not
    guaranteed to be sorted or free of duplicate tgids, and userspace
    should sort/uniquify the list if this property is required.
-   Writing a tgid into this file moves all threads with that tgid into
-   this cgroup.
+   This is a read-only file, for now.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -434,6 +435,25 @@ you give a subsystem a name.
 The name of the subsystem appears as part of the hierarchy description
 in /proc/mounts and /proc/<pid>/cgroups.
 
+2.4 Notification API
+--------------------
+
+There is mechanism which allows to get notifications about changing
+status of a cgroup.
+
+To register new notification handler you need:
+ - create a file descriptor for event notification using eventfd(2);
+ - open a control file to be monitored (e.g. memory.usage_in_bytes);
+ - write "<event_fd> <control_fd> <args>" to cgroup.event_control.
+   Interpretation of args is defined by control file implementation;
+
+eventfd will be woken up by control file implementation or when the
+cgroup is removed.
+
+To unregister notification handler just close eventfd.
+
+NOTE: Support of notifications should be implemented for the control
+file. See documentation for the subsystem.
 
 3. Kernel API
 =============
@@ -488,6 +508,11 @@ Each subsystem should:
 - add an entry in linux/cgroup_subsys.h
 - define a cgroup_subsys object called <name>_subsys
 
+If a subsystem can be compiled as a module, it should also have in its
+module initcall a call to cgroup_load_subsys(), and in its exitcall a
+call to cgroup_unload_subsys(). It should also set its_subsys.module =
+THIS_MODULE in its .c file.
+
 Each subsystem may export the following methods. The only mandatory
 methods are create/destroy. Any others that are null are presumed to
 be successful no-ops.
@@ -536,10 +561,21 @@ returns an error, this will abort the attach operation.  If a NULL
 task is passed, then a successful result indicates that *any*
 unspecified task can be moved into the cgroup. Note that this isn't
 called on a fork. If this method returns 0 (success) then this should
-remain valid while the caller holds cgroup_mutex. If threadgroup is
+remain valid while the caller holds cgroup_mutex and it is ensured that either
+attach() or cancel_attach() will be called in future. If threadgroup is
 true, then a successful result indicates that all threads in the given
 thread's threadgroup can be moved together.
 
+void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+               struct task_struct *task, bool threadgroup)
+(cgroup_mutex held by caller)
+
+Called when a task attach operation has failed after can_attach() has succeeded.
+A subsystem whose can_attach() has some side-effects should provide this
+function, so that the subsytem can implement a rollback. If not, not necessary.
+This will be called only about subsystems whose can_attach() operation have
+succeeded.
+
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
             struct cgroup *old_cgrp, struct task_struct *task,
             bool threadgroup)
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 1d7e9784439a..4160df82b3f5 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -168,20 +168,20 @@ Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
 files describing that cpuset:
 
- - cpus: list of CPUs in that cpuset
- - mems: list of Memory Nodes in that cpuset
- - memory_migrate flag: if set, move pages to cpusets nodes
- - cpu_exclusive flag: is cpu placement exclusive?
- - mem_exclusive flag: is memory placement exclusive?
- - mem_hardwall flag:  is memory allocation hardwalled
- - memory_pressure: measure of how much paging pressure in cpuset
- - memory_spread_page flag: if set, spread page cache evenly on allowed nodes
- - memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
- - sched_load_balance flag: if set, load balance within CPUs on that cpuset
- - sched_relax_domain_level: the searching range when migrating tasks
+ - cpuset.cpus: list of CPUs in that cpuset
+ - cpuset.mems: list of Memory Nodes in that cpuset
+ - cpuset.memory_migrate flag: if set, move pages to cpusets nodes
+ - cpuset.cpu_exclusive flag: is cpu placement exclusive?
+ - cpuset.mem_exclusive flag: is memory placement exclusive?
+ - cpuset.mem_hardwall flag:  is memory allocation hardwalled
+ - cpuset.memory_pressure: measure of how much paging pressure in cpuset
+ - cpuset.memory_spread_page flag: if set, spread page cache evenly on allowed nodes
+ - cpuset.memory_spread_slab flag: if set, spread slab cache evenly on allowed nodes
+ - cpuset.sched_load_balance flag: if set, load balance within CPUs on that cpuset
+ - cpuset.sched_relax_domain_level: the searching range when migrating tasks
 
 In addition, the root cpuset only has the following file:
- - memory_pressure_enabled flag: compute memory_pressure?
+ - cpuset.memory_pressure_enabled flag: compute memory_pressure?
 
 New cpusets are created using the mkdir system call or shell
 command.  The properties of a cpuset, such as its flags, allowed
@@ -229,7 +229,7 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendant, may share any of the same CPUs or
 Memory Nodes.
 
-A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
+A cpuset that is cpuset.mem_exclusive *or* cpuset.mem_hardwall is "hardwalled",
 i.e. it restricts kernel allocations for page, buffer and other data
 commonly shared by the kernel across multiple users.  All cpusets,
 whether hardwalled or not, restrict allocations of memory for user
@@ -304,15 +304,15 @@ times 1000.
 ---------------------------
 There are two boolean flag files per cpuset that control where the
 kernel allocates pages for the file system buffers and related in
-kernel data structures.  They are called 'memory_spread_page' and
-'memory_spread_slab'.
+kernel data structures.  They are called 'cpuset.memory_spread_page' and
+'cpuset.memory_spread_slab'.
 
-If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+If the per-cpuset boolean flag file 'cpuset.memory_spread_page' is set, then
 the kernel will spread the file system buffers (page cache) evenly
 over all the nodes that the faulting task is allowed to use, instead
 of preferring to put those pages on the node where the task is running.
 
-If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+If the per-cpuset boolean flag file 'cpuset.memory_spread_slab' is set,
 then the kernel will spread some file system related slab caches,
 such as for inodes and dentries evenly over all the nodes that the
 faulting task is allowed to use, instead of preferring to put those
@@ -337,21 +337,21 @@ their containing tasks memory spread settings.  If memory spreading
 is turned off, then the currently specified NUMA mempolicy once again
 applies to memory page allocations.
 
-Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+Both 'cpuset.memory_spread_page' and 'cpuset.memory_spread_slab' are boolean flag
 files.  By default they contain "0", meaning that the feature is off
 for that cpuset.  If a "1" is written to that file, then that turns
 the named feature on.
 
 The implementation is simple.
 
-Setting the flag 'memory_spread_page' turns on a per-process flag
+Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag
 PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
 joins that cpuset.  The page allocation calls for the page cache
 is modified to perform an inline check for this PF_SPREAD_PAGE task
 flag, and if set, a call to a new routine cpuset_mem_spread_node()
 returns the node to prefer for the allocation.
 
-Similarly, setting 'memory_spread_slab' turns on the flag
+Similarly, setting 'cpuset.memory_spread_slab' turns on the flag
 PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
 pages from the node returned by cpuset_mem_spread_node().
 
@@ -404,24 +404,24 @@ the following two situations:
     system overhead on those CPUs, including avoiding task load
     balancing if that is not needed.
 
-When the per-cpuset flag "sched_load_balance" is enabled (the default
-setting), it requests that all the CPUs in that cpusets allowed 'cpus'
+When the per-cpuset flag "cpuset.sched_load_balance" is enabled (the default
+setting), it requests that all the CPUs in that cpusets allowed 'cpuset.cpus'
 be contained in a single sched domain, ensuring that load balancing
 can move a task (not otherwised pinned, as by sched_setaffinity)
 from any CPU in that cpuset to any other.
 
-When the per-cpuset flag "sched_load_balance" is disabled, then the
+When the per-cpuset flag "cpuset.sched_load_balance" is disabled, then the
 scheduler will avoid load balancing across the CPUs in that cpuset,
 --except-- in so far as is necessary because some overlapping cpuset
 has "sched_load_balance" enabled.
 
-So, for example, if the top cpuset has the flag "sched_load_balance"
+So, for example, if the top cpuset has the flag "cpuset.sched_load_balance"
 enabled, then the scheduler will have one sched domain covering all
-CPUs, and the setting of the "sched_load_balance" flag in any other
+CPUs, and the setting of the "cpuset.sched_load_balance" flag in any other
 cpusets won't matter, as we're already fully load balancing.
 
 Therefore in the above two situations, the top cpuset flag
-"sched_load_balance" should be disabled, and only some of the smaller,
+"cpuset.sched_load_balance" should be disabled, and only some of the smaller,
 child cpusets have this flag enabled.
 
 When doing this, you don't usually want to leave any unpinned tasks in
@@ -433,7 +433,7 @@ scheduler might not consider the possibility of load balancing that
 task to that underused CPU.
 
 Of course, tasks pinned to a particular CPU can be left in a cpuset
-that disables "sched_load_balance" as those tasks aren't going anywhere
+that disables "cpuset.sched_load_balance" as those tasks aren't going anywhere
 else anyway.
 
 There is an impedance mismatch here, between cpusets and sched domains.
@@ -443,19 +443,19 @@ overlap and each CPU is in at most one sched domain.
 It is necessary for sched domains to be flat because load balancing
 across partially overlapping sets of CPUs would risk unstable dynamics
 that would be beyond our understanding.  So if each of two partially
-overlapping cpusets enables the flag 'sched_load_balance', then we
+overlapping cpusets enables the flag 'cpuset.sched_load_balance', then we
 form a single sched domain that is a superset of both.  We won't move
 a task to a CPU outside it cpuset, but the scheduler load balancing
 code might waste some compute cycles considering that possibility.
 
 This mismatch is why there is not a simple one-to-one relation
-between which cpusets have the flag "sched_load_balance" enabled,
+between which cpusets have the flag "cpuset.sched_load_balance" enabled,
 and the sched domain configuration.  If a cpuset enables the flag, it
 will get balancing across all its CPUs, but if it disables the flag,
 it will only be assured of no load balancing if no other overlapping
 cpuset enables the flag.
 
-If two cpusets have partially overlapping 'cpus' allowed, and only
+If two cpusets have partially overlapping 'cpuset.cpus' allowed, and only
 one of them has this flag enabled, then the other may find its
 tasks only partially load balanced, just on the overlapping CPUs.
 This is just the general case of the top_cpuset example given a few
@@ -468,23 +468,23 @@ load balancing to the other CPUs.
 1.7.1 sched_load_balance implementation details.
 ------------------------------------------------
 
-The per-cpuset flag 'sched_load_balance' defaults to enabled (contrary
+The per-cpuset flag 'cpuset.sched_load_balance' defaults to enabled (contrary
 to most cpuset flags.)  When enabled for a cpuset, the kernel will
 ensure that it can load balance across all the CPUs in that cpuset
 (makes sure that all the CPUs in the cpus_allowed of that cpuset are
 in the same sched domain.)
 
-If two overlapping cpusets both have 'sched_load_balance' enabled,
+If two overlapping cpusets both have 'cpuset.sched_load_balance' enabled,
 then they will be (must be) both in the same sched domain.
 
-If, as is the default, the top cpuset has 'sched_load_balance' enabled,
+If, as is the default, the top cpuset has 'cpuset.sched_load_balance' enabled,
 then by the above that means there is a single sched domain covering
 the whole system, regardless of any other cpuset settings.
 
 The kernel commits to user space that it will avoid load balancing
 where it can.  It will pick as fine a granularity partition of sched
 domains as it can while still providing load balancing for any set
-of CPUs allowed to a cpuset having 'sched_load_balance' enabled.
+of CPUs allowed to a cpuset having 'cpuset.sched_load_balance' enabled.
 
 The internal kernel cpuset to scheduler interface passes from the
 cpuset code to the scheduler code a partition of the load balanced
@@ -495,9 +495,9 @@ all the CPUs that must be load balanced.
 The cpuset code builds a new such partition and passes it to the
 scheduler sched domain setup code, to have the sched domains rebuilt
 as necessary, whenever:
- - the 'sched_load_balance' flag of a cpuset with non-empty CPUs changes,
+ - the 'cpuset.sched_load_balance' flag of a cpuset with non-empty CPUs changes,
  - or CPUs come or go from a cpuset with this flag enabled,
- - or 'sched_relax_domain_level' value of a cpuset with non-empty CPUs
+ - or 'cpuset.sched_relax_domain_level' value of a cpuset with non-empty CPUs
    and with this flag enabled changes,
  - or a cpuset with non-empty CPUs and with this flag enabled is removed,
  - or a cpu is offlined/onlined.
@@ -542,7 +542,7 @@ As the result, task B on CPU X need to wait task A or wait load balance
 on the next tick.  For some applications in special situation, waiting
 1 tick may be too long.
 
-The 'sched_relax_domain_level' file allows you to request changing
+The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
 indicates size of searching range in levels ideally as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
@@ -559,8 +559,8 @@ The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 
 This file is per-cpuset and affect the sched domain where the cpuset
-belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
-is disabled, then 'sched_relax_domain_level' have no effect since
+belongs to.  Therefore if the flag 'cpuset.sched_load_balance' of a cpuset
+is disabled, then 'cpuset.sched_relax_domain_level' have no effect since
 there is no sched domain belonging the cpuset.
 
 If multiple cpusets are overlapping and hence they form a single sched
@@ -607,9 +607,9 @@ from one cpuset to another, then the kernel will adjust the tasks
 memory placement, as above, the next time that the kernel attempts
 to allocate a page of memory for that task.
 
-If a cpuset has its 'cpus' modified, then each task in that cpuset
+If a cpuset has its 'cpuset.cpus' modified, then each task in that cpuset
 will have its allowed CPU placement changed immediately.  Similarly,
-if a tasks pid is written to another cpusets 'tasks' file, then its
+if a tasks pid is written to another cpusets 'cpuset.tasks' file, then its
 allowed CPU placement is changed immediately.  If such a task had been
 bound to some subset of its cpuset using the sched_setaffinity() call,
 the task will be allowed to run on any CPU allowed in its new cpuset,
@@ -622,8 +622,8 @@ and the processor placement is updated immediately.
 Normally, once a page is allocated (given a physical page
 of main memory) then that page stays on whatever node it
 was allocated, so long as it remains allocated, even if the
-cpusets memory placement policy 'mems' subsequently changes.
-If the cpuset flag file 'memory_migrate' is set true, then when
+cpusets memory placement policy 'cpuset.mems' subsequently changes.
+If the cpuset flag file 'cpuset.memory_migrate' is set true, then when
 tasks are attached to that cpuset, any pages that task had
 allocated to it on nodes in its previous cpuset are migrated
 to the tasks new cpuset. The relative placement of the page within
@@ -631,12 +631,12 @@ the cpuset is preserved during these migration operations if possible.
 For example if the page was on the second valid node of the prior cpuset
 then the page will be placed on the second valid node of the new cpuset.
 
-Also if 'memory_migrate' is set true, then if that cpusets
-'mems' file is modified, pages allocated to tasks in that
-cpuset, that were on nodes in the previous setting of 'mems',
+Also if 'cpuset.memory_migrate' is set true, then if that cpusets
+'cpuset.mems' file is modified, pages allocated to tasks in that
+cpuset, that were on nodes in the previous setting of 'cpuset.mems',
 will be moved to nodes in the new setting of 'mems.'
 Pages that were not in the tasks prior cpuset, or in the cpusets
-prior 'mems' setting, will not be moved.
+prior 'cpuset.mems' setting, will not be moved.
 
 There is an exception to the above.  If hotplug functionality is used
 to remove all the CPUs that are currently assigned to a cpuset,
@@ -678,8 +678,8 @@ and then start a subshell 'sh' in that cpuset:
   cd /dev/cpuset
   mkdir Charlie
   cd Charlie
-  /bin/echo 2-3 > cpus
-  /bin/echo 1 > mems
+  /bin/echo 2-3 > cpuset.cpus
+  /bin/echo 1 > cpuset.mems
   /bin/echo $$ > tasks
   sh
   # The subshell 'sh' is now running in cpuset Charlie
@@ -725,10 +725,13 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpu_exclusive  memory_migrate      mems                      tasks
-cpus           memory_pressure     notify_on_release
-mem_exclusive  memory_spread_page  sched_load_balance
-mem_hardwall   memory_spread_slab  sched_relax_domain_level
+cpuset.cpu_exclusive       cpuset.memory_spread_slab
+cpuset.cpus                cpuset.mems
+cpuset.mem_exclusive       cpuset.sched_load_balance
+cpuset.mem_hardwall        cpuset.sched_relax_domain_level
+cpuset.memory_migrate      notify_on_release
+cpuset.memory_pressure     tasks
+cpuset.memory_spread_page
 
 Reading them will give you information about the state of this cpuset:
 the CPUs and Memory Nodes it can use, the processes that are using
@@ -736,13 +739,13 @@ it, its properties.  By writing to these files you can manipulate
 the cpuset.
 
 Set some flags:
-# /bin/echo 1 > cpu_exclusive
+# /bin/echo 1 > cpuset.cpu_exclusive
 
 Add some cpus:
-# /bin/echo 0-7 > cpus
+# /bin/echo 0-7 > cpuset.cpus
 
 Add some mems:
-# /bin/echo 0-7 > mems
+# /bin/echo 0-7 > cpuset.mems
 
 Now attach your shell to this cpuset:
 # /bin/echo $$ > tasks
@@ -774,28 +777,28 @@ echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
 This is the syntax to use when writing in the cpus or mems files
 in cpuset directories:
 
-# /bin/echo 1-4 > cpus          -> set cpus list to cpus 1,2,3,4
-# /bin/echo 1,2,3,4 > cpus      -> set cpus list to cpus 1,2,3,4
+# /bin/echo 1-4 > cpuset.cpus           -> set cpus list to cpus 1,2,3,4
+# /bin/echo 1,2,3,4 > cpuset.cpus       -> set cpus list to cpus 1,2,3,4
 
 To add a CPU to a cpuset, write the new list of CPUs including the
 CPU to be added. To add 6 to the above cpuset:
 
-# /bin/echo 1-4,6 > cpus        -> set cpus list to cpus 1,2,3,4,6
+# /bin/echo 1-4,6 > cpuset.cpus -> set cpus list to cpus 1,2,3,4,6
 
 Similarly to remove a CPU from a cpuset, write the new list of CPUs
 without the CPU to be removed.
 
 To remove all the CPUs:
 
-# /bin/echo "" > cpus           -> clear cpus list
+# /bin/echo "" > cpuset.cpus            -> clear cpus list
 
 2.3 Setting flags
 -----------------
 
 The syntax is very simple:
 
-# /bin/echo 1 > cpu_exclusive   -> set flag 'cpu_exclusive'
-# /bin/echo 0 > cpu_exclusive   -> unset flag 'cpu_exclusive'
+# /bin/echo 1 > cpuset.cpu_exclusive    -> set flag 'cpuset.cpu_exclusive'
+# /bin/echo 0 > cpuset.cpu_exclusive    -> unset flag 'cpuset.cpu_exclusive'
 
 2.4 Attaching processes
 -----------------------
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 72db89ed0609..f7f68b2ac199 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,6 +1,6 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/20
-Base Kernel Version: based on 2.6.29-rc2.
+Last Updated: 2010/2
+Base Kernel Version: based on 2.6.33-rc7-mm(candidate for 34).
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
 is complex. This is a document for memcg's internal behavior.
@@ -337,7 +337,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
         race and lock dependency with other cgroup subsystems.
 
         example)
-        # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+        # mount -t cgroup none /cgroup -o cpuset,memory,cpu,devices
 
         and do task move, mkdir, rmdir etc...under this.
 
@@ -348,7 +348,7 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
         For example, test like following is good.
         (Shell-A)
-        # mount -t cgroup none /cgroup -t memory
+        # mount -t cgroup none /cgroup -o memory
         # mkdir /cgroup/test
         # echo 40M > /cgroup/test/memory.limit_in_bytes
         # echo 0 > /cgroup/test/tasks
@@ -378,3 +378,42 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
         #echo 50M > memory.limit_in_bytes
         #echo 50M > memory.memsw.limit_in_bytes
         run 51M of malloc
+
+ 9.9 Move charges at task migration
+        Charges associated with a task can be moved along with task migration.
+
+        (Shell-A)
+        #mkdir /cgroup/A
+        #echo $$ >/cgroup/A/tasks
+        run some programs which uses some amount of memory in /cgroup/A.
+
+        (Shell-B)
+        #mkdir /cgroup/B
+        #echo 1 >/cgroup/B/memory.move_charge_at_immigrate
+        #echo "pid of the program running in group A" >/cgroup/B/tasks
+
+        You can see charges have been moved by reading *.usage_in_bytes or
+        memory.stat of both A and B.
+        See 8.2 of Documentation/cgroups/memory.txt to see what value should be
+        written to move_charge_at_immigrate.
+
+ 9.10 Memory thresholds
+        Memory controler implements memory thresholds using cgroups notification
+        API. You can use Documentation/cgroups/cgroup_event_listener.c to test
+        it.
+
+        (Shell-A) Create cgroup and run event listener
+        # mkdir /cgroup/A
+        # ./cgroup_event_listener /cgroup/A/memory.usage_in_bytes 5M
+
+        (Shell-B) Add task to cgroup and try to allocate and free memory
+        # echo $$ >/cgroup/A/tasks
+        # a="$(dd if=/dev/zero bs=1M count=10)"
+        # a=
+
+        You will see message from cgroup_event_listener every time you cross
+        the thresholds.
+
+        Use /cgroup/A/memory.memsw.usage_in_bytes to test memsw thresholds.
+
+        It's good idea to test root cgroup as well.
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index b871f2552b45..3a6aecd078ba 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -182,6 +182,8 @@ list.
 NOTE: Reclaim does not work for the root cgroup, since we cannot set any
 limits on the root cgroup.
 
+Note2: When panic_on_oom is set to "2", the whole system will panic.
+
 2. Locking
 
 The memory controller uses the following hierarchy
@@ -262,10 +264,12 @@ some of the pages cached in the cgroup (page cache pages).
 4.2 Task migration
 
 When a task migrates from one cgroup to another, it's charge is not
-carried forward. The pages allocated from the original cgroup still
+carried forward by default. The pages allocated from the original cgroup still
 remain charged to it, the charge is dropped when the page is freed or
 reclaimed.
 
+Note: You can move charges of a task along with task migration. See 8.
+
 4.3 Removing a cgroup
 
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
@@ -336,7 +340,7 @@ Note:
 5.3 swappiness
   Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
 
-  Following cgroups' swapiness can't be changed.
+  Following cgroups' swappiness can't be changed.
   - root cgroup (uses /proc/sys/vm/swappiness).
   - a cgroup which uses hierarchy and it has child cgroup.
   - a cgroup which uses hierarchy and not the root of hierarchy.
@@ -377,7 +381,8 @@ The feature can be disabled by
 NOTE1: Enabling/disabling will fail if the cgroup already has other
 cgroups created below it.
 
-NOTE2: This feature can be enabled/disabled per subtree.
+NOTE2: When panic_on_oom is set to "2", the whole system will panic in
+case of an oom event in any cgroup.
 
 7. Soft limits
 
@@ -414,7 +419,76 @@ NOTE1: Soft limits take effect over a long period of time, since they involve
 NOTE2: It is recommended to set the soft limit always below the hard limit,
        otherwise the hard limit will take precedence.
 
-8. TODO
+8. Move charges at task migration
+
+Users can move charges associated with a task along with task migration, that
+is, uncharge task's pages from the old cgroup and charge them to the new cgroup.
+This feature is not supported in !CONFIG_MMU environments because of lack of
+page tables.
+
+8.1 Interface
+
+This feature is disabled by default. It can be enabled(and disabled again) by
+writing to memory.move_charge_at_immigrate of the destination cgroup.
+
+If you want to enable it:
+
+# echo (some positive value) > memory.move_charge_at_immigrate
+
+Note: Each bits of move_charge_at_immigrate has its own meaning about what type
+      of charges should be moved. See 8.2 for details.
+Note: Charges are moved only when you move mm->owner, IOW, a leader of a thread
+      group.
+Note: If we cannot find enough space for the task in the destination cgroup, we
+      try to make space by reclaiming memory. Task migration may fail if we
+      cannot make enough space.
+Note: It can take several seconds if you move charges in giga bytes order.
+
+And if you want disable it again:
+
+# echo 0 > memory.move_charge_at_immigrate
+
+8.2 Type of charges which can be move
+
+Each bits of move_charge_at_immigrate has its own meaning about what type of
+charges should be moved.
+
+  bit | what type of charges would be moved ?
+ -----+------------------------------------------------------------------------
+   0  | A charge of an anonymous page(or swap of it) used by the target task.
+      | Those pages and swaps must be used only by the target task. You must
+      | enable Swap Extension(see 2.4) to enable move of swap charges.
+
+Note: Those pages and swaps must be charged to the old cgroup.
+Note: More type of pages(e.g. file cache, shmem,) will be supported by other
+      bits in future.
+
+8.3 TODO
+
+- Add support for other types of pages(e.g. file cache, shmem, etc.).
+- Implement madvise(2) to let users decide the vma to be moved or not to be
+  moved.
+- All of moving charge operations are done under cgroup_mutex. It's not good
+  behavior to hold the mutex too long, so we may need some trick.
+
+9. Memory thresholds
+
+Memory controler implements memory thresholds using cgroups notification
+API (see cgroups.txt). It allows to register multiple memory and memsw
+thresholds and gets notifications when it crosses.
+
+To register a threshold application need:
+ - create an eventfd using eventfd(2);
+ - open memory.usage_in_bytes or memory.memsw.usage_in_bytes;
+ - write string like "<event_fd> <memory.usage_in_bytes> <threshold>" to
+   cgroup.event_control.
+
+Application will be notified through eventfd when memory usage crosses
+threshold in any direction.
+
+It's applicable for root and non-root cgroup.
+
+10. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
new file mode 100644
index 000000000000..8117e5bf6065
--- /dev/null
+++ b/Documentation/circular-buffers.txt
@@ -0,0 +1,234 @@
+                               ================
+                               CIRCULAR BUFFERS
+                               ================
+
+By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+
+
+Linux provides a number of features that can be used to implement circular
+buffering.  There are two sets of such features:
+
+ (1) Convenience functions for determining information about power-of-2 sized
+     buffers.
+
+ (2) Memory barriers for when the producer and the consumer of objects in the
+     buffer don't want to share a lock.
+
+To use these facilities, as discussed below, there needs to be just one
+producer and just one consumer.  It is possible to handle multiple producers by
+serialising them, and to handle multiple consumers by serialising them.
+
+
+Contents:
+
+ (*) What is a circular buffer?
+
+ (*) Measuring power-of-2 buffers.
+
+ (*) Using memory barriers with circular buffers.
+     - The producer.
+     - The consumer.
+
+
+==========================
+WHAT IS A CIRCULAR BUFFER?
+==========================
+
+First of all, what is a circular buffer?  A circular buffer is a buffer of
+fixed, finite size into which there are two indices:
+
+ (1) A 'head' index - the point at which the producer inserts items into the
+     buffer.
+
+ (2) A 'tail' index - the point at which the consumer finds the next item in
+     the buffer.
+
+Typically when the tail pointer is equal to the head pointer, the buffer is
+empty; and the buffer is full when the head pointer is one less than the tail
+pointer.
+
+The head index is incremented when items are added, and the tail index when
+items are removed.  The tail index should never jump the head index, and both
+indices should be wrapped to 0 when they reach the end of the buffer, thus
+allowing an infinite amount of data to flow through the buffer.
+
+Typically, items will all be of the same unit size, but this isn't strictly
+required to use the techniques below.  The indices can be increased by more
+than 1 if multiple items or variable-sized items are to be included in the
+buffer, provided that neither index overtakes the other.  The implementer must
+be careful, however, as a region more than one unit in size may wrap the end of
+the buffer and be broken into two segments.
+
+
+============================
+MEASURING POWER-OF-2 BUFFERS
+============================
+
+Calculation of the occupancy or the remaining capacity of an arbitrarily sized
+circular buffer would normally be a slow operation, requiring the use of a
+modulus (divide) instruction.  However, if the buffer is of a power-of-2 size,
+then a much quicker bitwise-AND instruction can be used instead.
+
+Linux provides a set of macros for handling power-of-2 circular buffers.  These
+can be made use of by:
+
+        #include <linux/circ_buf.h>
+
+The macros are:
+
+ (*) Measure the remaining capacity of a buffer:
+
+        CIRC_SPACE(head_index, tail_index, buffer_size);
+
+     This returns the amount of space left in the buffer[1] into which items
+     can be inserted.
+
+
+ (*) Measure the maximum consecutive immediate space in a buffer:
+
+        CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the amount of consecutive space left in the buffer[1] into
+     which items can be immediately inserted without having to wrap back to the
+     beginning of the buffer.
+
+
+ (*) Measure the occupancy of a buffer:
+
+        CIRC_CNT(head_index, tail_index, buffer_size);
+
+     This returns the number of items currently occupying a buffer[2].
+
+
+ (*) Measure the non-wrapping occupancy of a buffer:
+
+        CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
+
+     This returns the number of consecutive items[2] that can be extracted from
+     the buffer without having to wrap back to the beginning of the buffer.
+
+
+Each of these macros will nominally return a value between 0 and buffer_size-1,
+however:
+
+ [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+     they will return a lower bound as the producer controls the head index,
+     but the consumer may still be depleting the buffer on another CPU and
+     moving the tail index.
+
+     To the consumer it will show an upper bound as the producer may be busy
+     depleting the space.
+
+ [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+     will return a lower bound as the consumer controls the tail index, but the
+     producer may still be filling the buffer on another CPU and moving the
+     head index.
+
+     To the producer it will show an upper bound as the consumer may be busy
+     emptying the buffer.
+
+ [3] To a third party, the order in which the writes to the indices by the
+     producer and consumer become visible cannot be guaranteed as they are
+     independent and may be made on different CPUs - so the result in such a
+     situation will merely be a guess, and may even be negative.
+
+
+===========================================
+USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+===========================================
+
+By using memory barriers in conjunction with circular buffers, you can avoid
+the need to:
+
+ (1) use a single lock to govern access to both ends of the buffer, thus
+     allowing the buffer to be filled and emptied at the same time; and
+
+ (2) use atomic counter operations.
+
+There are two sides to this: the producer that fills the buffer, and the
+consumer that empties it.  Only one thing should be filling a buffer at any one
+time, and only one thing should be emptying a buffer at any one time, but the
+two sides can operate simultaneously.
+
+
+THE PRODUCER
+------------
+
+The producer will look something like this:
+
+        spin_lock(&producer_lock);
+
+        unsigned long head = buffer->head;
+        unsigned long tail = ACCESS_ONCE(buffer->tail);
+
+        if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
+                /* insert one item into the buffer */
+                struct item *item = buffer[head];
+
+                produce_item(item);
+
+                smp_wmb(); /* commit the item before incrementing the head */
+
+                buffer->head = (head + 1) & (buffer->size - 1);
+
+                /* wake_up() will make sure that the head is committed before
+                 * waking anyone up */
+                wake_up(consumer);
+        }
+
+        spin_unlock(&producer_lock);
+
+This will instruct the CPU that the contents of the new item must be written
+before the head index makes it available to the consumer and then instructs the
+CPU that the revised head index must be written before the consumer is woken.
+
+Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+is used must guarantee a (write) memory barrier between the update of the head
+index and the change of state of the consumer, if a change of state occurs.
+
+
+THE CONSUMER
+------------
+
+The consumer will look something like this:
+
+        spin_lock(&consumer_lock);
+
+        unsigned long head = ACCESS_ONCE(buffer->head);
+        unsigned long tail = buffer->tail;
+
+        if (CIRC_CNT(head, tail, buffer->size) >= 1) {
+                /* read index before reading contents at that index */
+                smp_read_barrier_depends();
+
+                /* extract one item from the buffer */
+                struct item *item = buffer[tail];
+
+                consume_item(item);
+
+                smp_mb(); /* finish reading descriptor before incrementing tail */
+
+                buffer->tail = (tail + 1) & (buffer->size - 1);
+        }
+
+        spin_unlock(&consumer_lock);
+
+This will instruct the CPU to make sure the index is up to date before reading
+the new item, and then it shall make sure the CPU has finished reading the item
+before it writes the new tail pointer, which will erase the item.
+
+
+Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+This prevents the compiler from discarding and reloading its cached value -
+which some compilers will do across smp_read_barrier_depends().  This isn't
+strictly needed if you can be sure that the opposition index will _only_ be
+used the once.
+
+
+===============
+FURTHER READING
+===============
+
+See also Documentation/memory-barriers.txt for a description of Linux's memory
+barrier facilities.
diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c
index b07add3467f1..7764594778d4 100644
--- a/Documentation/connector/cn_test.c
+++ b/Documentation/connector/cn_test.c
@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/skbuff.h>
+#include <linux/slab.h>
 #include <linux/timer.h>
 
 #include <linux/connector.h>
diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt
index 877a1b26cc3d..926cf1b5e63e 100644
--- a/Documentation/console/console.txt
+++ b/Documentation/console/console.txt
@@ -74,7 +74,7 @@ driver takes over the consoles vacated by the driver. Binding, on the other
 hand, will bind the driver to the consoles that are currently occupied by a
 system driver.
 
-NOTE1: Binding and binding must be selected in Kconfig. It's under:
+NOTE1: Binding and unbinding must be selected in Kconfig. It's under:
 
 Device Drivers -> Character devices -> Support for binding and unbinding
 console drivers
diff --git a/Documentation/cpu-freq/pcc-cpufreq.txt b/Documentation/cpu-freq/pcc-cpufreq.txt
new file mode 100644
index 000000000000..9e3c3b33514c
--- /dev/null
+++ b/Documentation/cpu-freq/pcc-cpufreq.txt
@@ -0,0 +1,207 @@
+/*
+ *  pcc-cpufreq.txt - PCC interface documentation
+ *
+ *  Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *      Nagananda Chumbalkar <nagananda.chumbalkar@hp.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or NON
+ *  INFRINGEMENT. See the GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+
+                        Processor Clocking Control Driver
+                        ---------------------------------
+
+Contents:
+---------
+1.      Introduction
+1.1     PCC interface
+1.1.1   Get Average Frequency
+1.1.2   Set Desired Frequency
+1.2     Platforms affected
+2.      Driver and /sys details
+2.1     scaling_available_frequencies
+2.2     cpuinfo_transition_latency
+2.3     cpuinfo_cur_freq
+2.4     related_cpus
+3.      Caveats
+
+1. Introduction:
+----------------
+Processor Clocking Control (PCC) is an interface between the platform
+firmware and OSPM. It is a mechanism for coordinating processor
+performance (ie: frequency) between the platform firmware and the OS.
+
+The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
+interface.
+
+OS utilizes the PCC interface to inform platform firmware what frequency the
+OS wants for a logical processor. The platform firmware attempts to achieve
+the requested frequency. If the request for the target frequency could not be
+satisfied by platform firmware, then it usually means that power budget
+conditions are in place, and "power capping" is taking place.
+
+1.1 PCC interface:
+------------------
+The complete PCC specification is available here:
+http://www.acpica.org/download/Processor-Clocking-Control-v1p0.pdf
+
+PCC relies on a shared memory region that provides a channel for communication
+between the OS and platform firmware. PCC also implements a "doorbell" that
+is used by the OS to inform the platform firmware that a command has been
+sent.
+
+The ACPI PCCH() method is used to discover the location of the PCC shared
+memory region. The shared memory region header contains the "command" and
+"status" interface. PCCH() also contains details on how to access the platform
+doorbell.
+
+The following commands are supported by the PCC interface:
+* Get Average Frequency
+* Set Desired Frequency
+
+The ACPI PCCP() method is implemented for each logical processor and is
+used to discover the offsets for the input and output buffers in the shared
+memory region.
+
+When PCC mode is enabled, the platform will not expose processor performance
+or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
+the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
+AMD) will not load.
+
+However, OSPM remains in control of policy. The governor (eg: "ondemand")
+computes the required performance for each processor based on server workload.
+The PCC driver fills in the command interface, and the input buffer and
+communicates the request to the platform firmware. The platform firmware is
+responsible for delivering the requested performance.
+
+Each PCC command is "global" in scope and can affect all the logical CPUs in
+the system. Therefore, PCC is capable of performing "group" updates. With PCC
+the OS is capable of getting/setting the frequency of all the logical CPUs in
+the system with a single call to the BIOS.
+
+1.1.1 Get Average Frequency:
+----------------------------
+This command is used by the OSPM to query the running frequency of the
+processor since the last time this command was completed. The output buffer
+indicates the average unhalted frequency of the logical processor expressed as
+a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
+also signifies if the CPU frequency is limited by a power budget condition.
+
+1.1.2 Set Desired Frequency:
+----------------------------
+This command is used by the OSPM to communicate to the platform firmware the
+desired frequency for a logical processor. The output buffer is currently
+ignored by OSPM. The next invocation of "Get Average Frequency" will inform
+OSPM if the desired frequency was achieved or not.
+
+1.2 Platforms affected:
+-----------------------
+The PCC driver will load on any system where the platform firmware:
+* supports the PCC interface, and the associated PCCH() and PCCP() methods
+* assumes responsibility for managing the hardware clocking controls in order
+to deliver the requested processor performance
+
+Currently, certain HP ProLiant platforms implement the PCC interface. On those
+platforms PCC is the "default" choice.
+
+However, it is possible to disable this interface via a BIOS setting. In
+such an instance, as is also the case on platforms where the PCC interface
+is not implemented, the PCC driver will fail to load silently.
+
+2. Driver and /sys details:
+---------------------------
+When the driver loads, it merely prints the lowest and the highest CPU
+frequencies supported by the platform firmware.
+
+The PCC driver loads with a message such as:
+pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
+MHz
+
+This means that the OPSM can request the CPU to run at any frequency in
+between the limits (1600 MHz, and 2933 MHz) specified in the message.
+
+Internally, there is no need for the driver to convert the "target" frequency
+to a corresponding P-state.
+
+The VERSION number for the driver will be of the format v.xy.ab.
+eg: 1.00.02
+   ----- --
+    |    |
+    |    -- this will increase with bug fixes/enhancements to the driver
+    |-- this is the version of the PCC specification the driver adheres to
+
+
+The following is a brief discussion on some of the fields exported via the
+/sys filesystem and how their values are affected by the PCC driver:
+
+2.1 scaling_available_frequencies:
+----------------------------------
+scaling_available_frequencies is not created in /sys. No intermediate
+frequencies need to be listed because the BIOS will try to achieve any
+frequency, within limits, requested by the governor. A frequency does not have
+to be strictly associated with a P-state.
+
+2.2 cpuinfo_transition_latency:
+-------------------------------
+The cpuinfo_transition_latency field is 0. The PCC specification does
+not include a field to expose this value currently.
+
+2.3 cpuinfo_cur_freq:
+---------------------
+A) Often cpuinfo_cur_freq will show a value different than what is declared
+in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
+This is due to "turbo boost" available on recent Intel processors. If certain
+conditions are met the BIOS can achieve a slightly higher speed than requested
+by OSPM. An example:
+
+scaling_cur_freq        : 2933000
+cpuinfo_cur_freq        : 3196000
+
+B) There is a round-off error associated with the cpuinfo_cur_freq value.
+Since the driver obtains the current frequency as a "percentage" (%) of the
+nominal frequency from the BIOS, sometimes, the values displayed by
+scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
+
+scaling_cur_freq        : 1600000
+cpuinfo_cur_freq        : 1583000
+
+In this example, the nominal frequency is 2933 MHz. The driver obtains the
+current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
+
+        54% of 2933 MHz = 1583 MHz
+
+Nominal frequency is the maximum frequency of the processor, and it usually
+corresponds to the frequency of the P0 P-state.
+
+2.4 related_cpus:
+-----------------
+The related_cpus field is identical to affected_cpus.
+
+affected_cpus   : 4
+related_cpus    : 4
+
+Currently, the PCC driver does not evaluate _PSD. The platforms that support
+PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
+to ensure that the same frequency is requested of all dependent CPUs.
+
+3. Caveats:
+-----------
+The "cpufreq_stats" module in its present form cannot be loaded and
+expected to work with the PCC driver. Since the "cpufreq_stats" module
+provides information wrt each P-state, it is not applicable to the PCC driver.
diff --git a/Documentation/device-mapper/snapshot.txt b/Documentation/device-mapper/snapshot.txt
index e3a77b215135..0d5bc46dc167 100644
--- a/Documentation/device-mapper/snapshot.txt
+++ b/Documentation/device-mapper/snapshot.txt
@@ -122,3 +122,47 @@ volumeGroup-base: 0 2097152 snapshot-merge 254:11 254:12 P 16
 brw-------  1 root root 254, 11 29 ago 18:15 /dev/mapper/volumeGroup-base-real
 brw-------  1 root root 254, 12 29 ago 18:16 /dev/mapper/volumeGroup-base-cow
 brw-------  1 root root 254, 10 29 ago 18:16 /dev/mapper/volumeGroup-base
+
+
+How to determine when a merging is complete
+===========================================
+The snapshot-merge and snapshot status lines end with:
+  <sectors_allocated>/<total_sectors> <metadata_sectors>
+
+Both <sectors_allocated> and <total_sectors> include both data and metadata.
+During merging, the number of sectors allocated gets smaller and
+smaller.  Merging has finished when the number of sectors holding data
+is zero, in other words <sectors_allocated> == <metadata_sectors>.
+
+Here is a practical example (using a hybrid of lvm and dmsetup commands):
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
+  snap    volumeGroup swi-a- 1.00g base  18.97
+
+# dmsetup status volumeGroup-snap
+0 8388608 snapshot 397896/2097152 1560
+                                  ^^^^ metadata sectors
+
+# lvconvert --merge -b volumeGroup/snap
+  Merging of volume snap started.
+
+# lvs volumeGroup/snap
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup Owi-a- 4.00g          17.23
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 281688/2097152 1104
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 180480/2097152 712
+
+# dmsetup status volumeGroup-base
+0 8388608 snapshot-merge 16/2097152 16
+
+Merging has finished.
+
+# lvs
+  LV      VG          Attr   LSize Origin  Snap%  Move Log Copy%  Convert
+  base    volumeGroup owi-a- 4.00g
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 3ad6acead949..d9bcffd59433 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -69,7 +69,6 @@ av_permissions.h
 bbootsect
 bin2c
 binkernel.spec
-binoffset
 bootsect
 bounds.h
 bsetup
diff --git a/Documentation/driver-model/platform.txt b/Documentation/driver-model/platform.txt
index 2e2c2ea90ceb..41f41632ee55 100644
--- a/Documentation/driver-model/platform.txt
+++ b/Documentation/driver-model/platform.txt
@@ -192,7 +192,7 @@ command line. This will execute all matching early_param() callbacks.
 User specified early platform devices will be registered at this point.
 For the early serial console case the user can specify port on the
 kernel command line as "earlyprintk=serial.0" where "earlyprintk" is
-the class string, "serial" is the name of the platfrom driver and
+the class string, "serial" is the name of the platform driver and
 0 is the platform device id. If the id is -1 then the dot and the
 id can be omitted.
 
diff --git a/Documentation/dvb/get_dvb_firmware b/Documentation/dvb/get_dvb_firmware
index 14b7b5a3bcb9..239cbdbf4d12 100644
--- a/Documentation/dvb/get_dvb_firmware
+++ b/Documentation/dvb/get_dvb_firmware
@@ -26,7 +26,7 @@ use IO::Handle;
                 "dec3000s", "vp7041", "dibusb", "nxt2002", "nxt2004",
                 "or51211", "or51132_qam", "or51132_vsb", "bluebird",
                 "opera1", "cx231xx", "cx18", "cx23885", "pvrusb2", "mpc718",
-                "af9015");
+                "af9015", "ngene");
 
 # Check args
 syntax() if (scalar(@ARGV) != 1);
@@ -39,7 +39,7 @@ for ($i=0; $i < scalar(@components); $i++) {
         die $@ if $@;
         print STDERR <<EOF;
 Firmware(s) $outfile extracted successfully.
-Now copy it(they) to either /usr/lib/hotplug/firmware or /lib/firmware
+Now copy it(them) to either /usr/lib/hotplug/firmware or /lib/firmware
 (depending on configuration of firmware hotplug).
 EOF
         exit(0);
@@ -549,6 +549,24 @@ sub af9015 {
         close INFILE;
 }
 
+sub ngene {
+    my $url = "http://www.digitaldevices.de/download/";
+    my $file1 = "ngene_15.fw";
+    my $hash1 = "d798d5a757121174f0dbc5f2833c0c85";
+    my $file2 = "ngene_17.fw";
+    my $hash2 = "26b687136e127b8ac24b81e0eeafc20b";
+
+    checkstandard();
+
+    wgetfile($file1, $url . $file1);
+    verify($file1, $hash1);
+
+    wgetfile($file2, $url . $file2);
+    verify($file2, $hash2);
+
+    "$file1, $file2";
+}
+
 # ---------------------------------------------------------------
 # Utilities
 
@@ -667,6 +685,7 @@ sub delzero{
 sub syntax() {
     print STDERR "syntax: get_dvb_firmware <component>\n";
     print STDERR "Supported components:\n";
+    @components = sort @components;
     for($i=0; $i < scalar(@components); $i++) {
         print STDERR "\t" . $components[$i] . "\n";
     }
diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt
index 60e361ba08c0..f297fc1202ae 100644
--- a/Documentation/eisa.txt
+++ b/Documentation/eisa.txt
@@ -171,7 +171,7 @@ device.
 virtual_root.force_probe :
 
 Force the probing code to probe EISA slots even when it cannot find an
-EISA compliant mainboard (nothing appears on slot 0). Defaultd to 0
+EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
 (don't force), and set to 1 (force probing) when either
 CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
 
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index a618efab7b15..945ff3fda433 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -216,26 +216,14 @@ Works.  Use "Insert file..." or external editor.
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Gmail (Web GUI)
 
-If you just have to use Gmail to send patches, it CAN be made to work.  It
-requires a bit of external help, though.
-
-The first problem is that Gmail converts tabs to spaces.  This will
-totally break your patches.  To prevent this, you have to use a different
-editor.  There is a firefox extension called "ViewSourceWith"
-(https://addons.mozilla.org/en-US/firefox/addon/394) which allows you to
-edit any text box in the editor of your choice.  Configure it to launch
-your favorite editor.  When you want to send a patch, use this technique.
-Once you have crafted your messsage + patch, save and exit the editor,
-which should reload the Gmail edit box.  GMAIL WILL PRESERVE THE TABS.
-Hoorah.  Apparently you can cut-n-paste literal tabs, but Gmail will
-convert those to spaces upon sending!
-
-The second problem is that Gmail converts tabs to spaces on replies.  If
-you reply to a patch, don't expect to be able to apply it as a patch.
-
-The last problem is that Gmail will base64-encode any message that has a
-non-ASCII character.  That includes things like European names.  Be aware.
-
-Gmail is not convenient for lkml patches, but CAN be made to work.
+Does not work for sending patches.
+
+Gmail web client converts tabs to spaces automatically.
+
+At the same time it wraps lines every 78 chars with CRLF style line breaks
+although tab2space problem can be solved with external editor.
+
+Another problem is that Gmail will base64-encode any message that has a
+non-ASCII character. That includes things like European names.
 
                                 ###
diff --git a/Documentation/fault-injection/provoke-crashes.txt b/Documentation/fault-injection/provoke-crashes.txt
new file mode 100644
index 000000000000..7a9d3d81525b
--- /dev/null
+++ b/Documentation/fault-injection/provoke-crashes.txt
@@ -0,0 +1,38 @@
+The lkdtm module provides an interface to crash or injure the kernel at
+predefined crashpoints to evaluate the reliability of crash dumps obtained
+using different dumping solutions. The module uses KPROBEs to instrument
+crashing points, but can also crash the kernel directly without KRPOBE
+support.
+
+
+You can provide the way either through module arguments when inserting
+the module, or through a debugfs interface.
+
+Usage: insmod lkdtm.ko [recur_count={>0}] cpoint_name=<> cpoint_type=<>
+                                [cpoint_count={>0}]
+
+  recur_count : Recursion level for the stack overflow test. Default is 10.
+
+  cpoint_name : Crash point where the kernel is to be crashed. It can be
+         one of INT_HARDWARE_ENTRY, INT_HW_IRQ_EN, INT_TASKLET_ENTRY,
+         FS_DEVRW, MEM_SWAPOUT, TIMERADD, SCSI_DISPATCH_CMD,
+         IDE_CORE_CP, DIRECT
+
+  cpoint_type : Indicates the action to be taken on hitting the crash point.
+     It can be one of PANIC, BUG, EXCEPTION, LOOP, OVERFLOW,
+     CORRUPT_STACK, UNALIGNED_LOAD_STORE_WRITE, OVERWRITE_ALLOCATION,
+     WRITE_AFTER_FREE,
+
+  cpoint_count : Indicates the number of times the crash point is to be hit
+    to trigger an action. The default is 10.
+
+You can also induce failures by mounting debugfs and writing the type to
+<mountpoint>/provoke-crash/<crashpoint>. E.g.,
+
+  mount -t debugfs debugfs /mnt
+  echo EXCEPTION > /mnt/provoke-crash/INT_HARDWARE_ENTRY
+
+
+A special file is `DIRECT' which will induce the crash directly without
+KPROBE instrumentation. This mode is the only one available when the module
+is built on a kernel without KPROBEs support.
diff --git a/Documentation/fb/imacfb.txt b/Documentation/fb/efifb.txt
index 316ec9bb7deb..a59916c29b33 100644
--- a/Documentation/fb/imacfb.txt
+++ b/Documentation/fb/efifb.txt
@@ -1,9 +1,9 @@
 
-What is imacfb?
+What is efifb?
 ===============
 
 This is a generic EFI platform driver for Intel based Apple computers.
-Imacfb is only for EFI booted Intel Macs.
+efifb is only for EFI booted Intel Macs.
 
 Supported Hardware
 ==================
@@ -16,16 +16,16 @@ MacMini
 How to use it?
 ==============
 
-Imacfb does not have any kind of autodetection of your machine.
+efifb does not have any kind of autodetection of your machine.
 You have to add the following kernel parameters in your elilo.conf:
         Macbook :
-                video=imacfb:macbook
+                video=efifb:macbook
         MacMini :
-                video=imacfb:mini
+                video=efifb:mini
         Macbook Pro 15", iMac 17" :
-                video=imacfb:i17
+                video=efifb:i17
         Macbook Pro 17", iMac 20" :
-                video=imacfb:i20
+                video=efifb:i20
 
 --
 Edgar Hucek <gimli@dark-green.com>
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 0a46833c1b76..05df0b7514b6 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,21 +6,6 @@ be removed from this file.
 
 ---------------------------
 
-What:   USER_SCHED
-When:   2.6.34
-
-Why:    USER_SCHED was implemented as a proof of concept for group scheduling.
-        The effect of USER_SCHED can already be achieved from userspace with
-        the help of libcgroup. The removal of USER_SCHED will also simplify
-        the scheduler code with the removal of one major ifdef. There are also
-        issues USER_SCHED has with USER_NS. A decision was taken not to fix
-        those and instead remove USER_SCHED. Also new group scheduling
-        features will not be implemented for USER_SCHED.
-
-Who:    Dhaval Giani <dhaval@linux.vnet.ibm.com>
-
----------------------------
-
 What:   PRISM54
 When:   2.6.34
 
@@ -64,6 +49,17 @@ Who:	Robin Getz <rgetz@blackfin.uclinux.org> & Matt Mackall <mpm@selenic.com>
 
 ---------------------------
 
+What:   Deprecated snapshot ioctls
+When:   2.6.36
+
+Why:    The ioctls in kernel/power/user.c were marked as deprecated long time
+        ago. Now they notify users about that so that they need to replace
+        their userspace. After some more time, remove them completely.
+
+Who:    Jiri Slaby <jirislaby@gmail.com>
+
+---------------------------
+
 What:   The ieee80211_regdom module parameter
 When:   March 2010 / desktop catchup
 
@@ -88,27 +84,6 @@ Who:	Luis R. Rodriguez <lrodriguez@atheros.com>
 
 ---------------------------
 
-What:   CONFIG_WIRELESS_OLD_REGULATORY - old static regulatory information
-When:   March 2010 / desktop catchup
-
-Why:    The old regulatory infrastructure has been replaced with a new one
-        which does not require statically defined regulatory domains. We do
-        not want to keep static regulatory domains in the kernel due to the
-        the dynamic nature of regulatory law and localization. We kept around
-        the old static definitions for the regulatory domains of:
-
-                * US
-                * JP
-                * EU
-
-        and used by default the US when CONFIG_WIRELESS_OLD_REGULATORY was
-        set. We will remove this option once the standard Linux desktop catches
-        up with the new userspace APIs we have implemented.
-
-Who:    Luis R. Rodriguez <lrodriguez@atheros.com>
-
----------------------------
-
 What:   dev->power.power_state
 When:   July 2007
 Why:    Broken design for runtime control over driver power states, confusing
@@ -142,19 +117,25 @@ Who:	Mauro Carvalho Chehab <mchehab@infradead.org>
 ---------------------------
 
 What:   PCMCIA control ioctl (needed for pcmcia-cs [cardmgr, cardctl])
-When:   November 2005
+When:   2.6.35/2.6.36
 Files:  drivers/pcmcia/: pcmcia_ioctl.c
 Why:    With the 16-bit PCMCIA subsystem now behaving (almost) like a
         normal hotpluggable bus, and with it using the default kernel
         infrastructure (hotplug, driver core, sysfs) keeping the PCMCIA
         control ioctl needed by cardmgr and cardctl from pcmcia-cs is
-        unnecessary, and makes further cleanups and integration of the
+        unnecessary and potentially harmful (it does not provide for
+        proper locking), and makes further cleanups and integration of the
         PCMCIA subsystem into the Linux kernel device driver model more
         difficult. The features provided by cardmgr and cardctl are either
         handled by the kernel itself now or are available in the new
         pcmciautils package available at
         http://kernel.org/pub/linux/utils/kernel/pcmcia/
-Who:    Dominik Brodowski <linux@brodo.de>
+
+        For all architectures except ARM, the associated config symbol
+        has been removed from kernel 2.6.34; for ARM, it will be likely
+        be removed from kernel 2.6.35. The actual code will then likely
+        be removed from kernel 2.6.36.
+Who:    Dominik Brodowski <linux@dominikbrodowski.net>
 
 ---------------------------
 
@@ -468,12 +449,6 @@ Who:	Alok N Kataria <akataria@vmware.com>
 
 ----------------------------
 
-What:   adt7473 hardware monitoring driver
-When:   February 2010
-Why:    Obsoleted by the adt7475 driver.
-Who:    Jean Delvare <khali@linux-fr.org>
-
----------------------------
 What:   Support for lcd_switch and display_get in asus-laptop driver
 When:   March 2010
 Why:    These two features use non-standard interfaces. There are the
@@ -542,3 +517,98 @@ Why:	Duplicate functionality with the gspca_zc3xx driver, zc0301 only
         sensors) wich are also supported by the gspca_zc3xx driver
         (which supports 53 USB-ID's in total)
 Who:    Hans de Goede <hdegoede@redhat.com>
+
+----------------------------
+
+What:   corgikbd, spitzkbd, tosakbd driver
+When:   2.6.35
+Files:  drivers/input/keyboard/{corgi,spitz,tosa}kbd.c
+Why:    We now have a generic GPIO based matrix keyboard driver that
+        are fully capable of handling all the keys on these devices.
+        The original drivers manipulate the GPIO registers directly
+        and so are difficult to maintain.
+Who:    Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:   corgi_ssp and corgi_ts driver
+When:   2.6.35
+Files:  arch/arm/mach-pxa/corgi_ssp.c, drivers/input/touchscreen/corgi_ts.c
+Why:    The corgi touchscreen is now deprecated in favour of the generic
+        ads7846.c driver. The noise reduction technique used in corgi_ts.c,
+        that's to wait till vsync before ADC sampling, is also integrated into
+        ads7846 driver now. Provided that the original driver is not generic
+        and is difficult to maintain, it will be removed later.
+Who:    Eric Miao <eric.y.miao@gmail.com>
+
+----------------------------
+
+What:   capifs
+When:   February 2011
+Files:  drivers/isdn/capi/capifs.*
+Why:    udev fully replaces this special file system that only contains CAPI
+        NCCI TTY device nodes. User space (pppdcapiplugin) works without
+        noticing the difference.
+Who:    Jan Kiszka <jan.kiszka@web.de>
+
+----------------------------
+
+What:   KVM memory aliases support
+When:   July 2010
+Why:    Memory aliasing support is used for speeding up guest vga access
+        through the vga windows.
+
+        Modern userspace no longer uses this feature, so it's just bitrotted
+        code and can be removed with no impact.
+Who:    Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:   KVM kernel-allocated memory slots
+When:   July 2010
+Why:    Since 2.6.25, kvm supports user-allocated memory slots, which are
+        much more flexible than kernel-allocated slots.  All current userspace
+        supports the newer interface and this code can be removed with no
+        impact.
+Who:    Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:   KVM paravirt mmu host support
+When:   January 2011
+Why:    The paravirt mmu host support is slower than non-paravirt mmu, both
+        on newer and older hardware.  It is already not exposed to the guest,
+        and kept only for live migration purposes.
+Who:    Avi Kivity <avi@redhat.com>
+
+----------------------------
+
+What:   "acpi=ht" boot option
+When:   2.6.35
+Why:    Useful in 2003, implementation is a hack.
+        Generally invoked by accident today.
+        Seen as doing more harm than good.
+Who:    Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:   video4linux /dev/vtx teletext API support
+When:   2.6.35
+Files:  drivers/media/video/saa5246a.c drivers/media/video/saa5249.c
+        include/linux/videotext.h
+Why:    The vtx device nodes have been superseded by vbi device nodes
+        for many years. No applications exist that use the vtx support.
+        Of the two i2c drivers that actually support this API the saa5249
+        has been impossible to use for a year now and no known hardware
+        that supports this device exists. The saa5246a is theoretically
+        supported by the old mxb boards, but it never actually worked.
+
+        In summary: there is no hardware that can use this API and there
+        are no applications actually implementing this API.
+
+        The vtx support still reserves minors 192-223 and we would really
+        like to reuse those for upcoming new functionality. In the unlikely
+        event that new hardware appears that wants to use the functionality
+        provided by the vtx API, then that functionality should be build
+        around the sliced VBI API instead.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 875d49696b6e..4303614b5add 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -16,6 +16,8 @@ befs.txt
         - information about the BeOS filesystem for Linux.
 bfs.txt
         - info for the SCO UnixWare Boot Filesystem (BFS).
+ceph.txt
+        - info for the Ceph Distributed File System
 cifs.txt
         - description of the CIFS filesystem.
 coda.txt
@@ -32,6 +34,8 @@ dlmfs.txt
         - info on the userspace interface to the OCFS2 DLM.
 dnotify.txt
         - info about directory notification in Linux.
+dnotify_test.c
+        - example program for dnotify
 ecryptfs.txt
         - docs on eCryptfs: stacked cryptographic filesystem for Linux.
 exofs.txt
@@ -62,6 +66,8 @@ jfs.txt
         - info and mount options for the JFS filesystem.
 locks.txt
         - info on file locking implementations, flock() vs. fcntl(), etc.
+logfs.txt
+        - info on the LogFS flash filesystem.
 mandatory-locking.txt
         - info on the Linux implementation of Sys V mandatory file locking.
 ncpfs.txt
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index 57e0b80a5274..c0236e753bc8 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -37,6 +37,15 @@ For Plan 9 From User Space applications (http://swtch.com/plan9)
 
         mount -t 9p `namespace`/acme /mnt/9 -o trans=unix,uname=$USER
 
+For server running on QEMU host with virtio transport:
+
+        mount -t 9p -o trans=virtio <mount_tag> /mnt/9
+
+where mount_tag is the tag associated by the server to each of the exported
+mount points. Each 9P export is seen by the client as a virtio device with an
+associated "mount_tag" property. Available mount tags can be
+seen by reading /sys/bus/virtio/drivers/9pnet_virtio/virtio<n>/mount_tag files.
+
 OPTIONS
 =======
 
@@ -47,7 +56,7 @@ OPTIONS
                         fd      - used passed file descriptors for connection
                                 (see rfdno and wfdno)
                         virtio  - connect to the next virtio channel available
-                                (from lguest or KVM with trans_virtio module)
+                                (from QEMU with trans_virtio module)
                         rdma    - connect to a specified RDMA channel
 
   uname=name    user name to attempt mount as on the remote server.  The
@@ -85,7 +94,12 @@ OPTIONS
 
   port=n        port to connect to on the remote server
 
-  noextend      force legacy mode (no 9p2000.u semantics)
+  noextend      force legacy mode (no 9p2000.u or 9p2000.L semantics)
+
+  version=name  Select 9P protocol version. Valid options are:
+                        9p2000          - Legacy mode (same as noextend)
+                        9p2000.u        - Use 9P2000.u protocol
+                        9p2000.L        - Use 9P2000.L protocol
 
   dfltuid       attempt to mount as a particular uid
 
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 18b9d0ca0630..06bbbed71206 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -460,13 +460,6 @@ in sys_read() and friends.
 
 --------------------------- dquot_operations -------------------------------
 prototypes:
-        int (*initialize) (struct inode *, int);
-        int (*drop) (struct inode *);
-        int (*alloc_space) (struct inode *, qsize_t, int);
-        int (*alloc_inode) (const struct inode *, unsigned long);
-        int (*free_space) (struct inode *, qsize_t);
-        int (*free_inode) (const struct inode *, unsigned long);
-        int (*transfer) (struct inode *, struct iattr *);
         int (*write_dquot) (struct dquot *);
         int (*acquire_dquot) (struct dquot *);
         int (*release_dquot) (struct dquot *);
@@ -479,13 +472,6 @@ a proper locking wrt the filesystem and call the generic quota operations.
 What filesystem should expect from the generic quota functions:
 
                 FS recursion    Held locks when called
-initialize:     yes             maybe dqonoff_sem
-drop:           yes             -
-alloc_space:    ->mark_dirty()  -
-alloc_inode:    ->mark_dirty()  -
-free_space:     ->mark_dirty()  -
-free_inode:     ->mark_dirty()  -
-transfer:       yes             -
 write_dquot:    yes             dqonoff_sem or dqptr_sem
 acquire_dquot:  yes             dqonoff_sem or dqptr_sem
 release_dquot:  yes             dqonoff_sem or dqptr_sem
@@ -495,10 +481,6 @@ write_info:	yes		dqonoff_sem
 FS recursion means calling ->quota_read() and ->quota_write() from superblock
 operations.
 
-->alloc_space(), ->alloc_inode(), ->free_space(), ->free_inode() are called
-only directly by the filesystem and do not call any fs functions only
-the ->mark_dirty() operation.
-
 More details about quota locking can be found in fs/dquot.c.
 
 --------------------------- vm_operations_struct -----------------------------
diff --git a/Documentation/filesystems/Makefile b/Documentation/filesystems/Makefile
new file mode 100644
index 000000000000..a5dd114da14f
--- /dev/null
+++ b/Documentation/filesystems/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := dnotify_test
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt
new file mode 100644
index 000000000000..0660c9f5deef
--- /dev/null
+++ b/Documentation/filesystems/ceph.txt
@@ -0,0 +1,140 @@
+Ceph Distributed File System
+============================
+
+Ceph is a distributed network file system designed to provide good
+performance, reliability, and scalability.
+
+Basic features include:
+
+ * POSIX semantics
+ * Seamless scaling from 1 to many thousands of nodes
+ * High availability and reliability.  No single point of failure.
+ * N-way replication of data across storage nodes
+ * Fast recovery from node failures
+ * Automatic rebalancing of data on node addition/removal
+ * Easy deployment: most FS components are userspace daemons
+
+Also,
+ * Flexible snapshots (on any directory)
+ * Recursive accounting (nested files, directories, bytes)
+
+In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely
+on symmetric access by all clients to shared block devices, Ceph
+separates data and metadata management into independent server
+clusters, similar to Lustre.  Unlike Lustre, however, metadata and
+storage nodes run entirely as user space daemons.  Storage nodes
+utilize btrfs to store data objects, leveraging its advanced features
+(checksumming, metadata replication, etc.).  File data is striped
+across storage nodes in large chunks to distribute workload and
+facilitate high throughputs.  When storage nodes fail, data is
+re-replicated in a distributed fashion by the storage nodes themselves
+(with some minimal coordination from a cluster monitor), making the
+system extremely efficient and scalable.
+
+Metadata servers effectively form a large, consistent, distributed
+in-memory cache above the file namespace that is extremely scalable,
+dynamically redistributes metadata in response to workload changes,
+and can tolerate arbitrary (well, non-Byzantine) node failures.  The
+metadata server takes a somewhat unconventional approach to metadata
+storage to significantly improve performance for common workloads.  In
+particular, inodes with only a single link are embedded in
+directories, allowing entire directories of dentries and inodes to be
+loaded into its cache with a single I/O operation.  The contents of
+extremely large directories can be fragmented and managed by
+independent metadata servers, allowing scalable concurrent access.
+
+The system offers automatic data rebalancing/migration when scaling
+from a small cluster of just a few nodes to many hundreds, without
+requiring an administrator carve the data set into static volumes or
+go through the tedious process of migrating data between servers.
+When the file system approaches full, new nodes can be easily added
+and things will "just work."
+
+Ceph includes flexible snapshot mechanism that allows a user to create
+a snapshot on any subdirectory (and its nested contents) in the
+system.  Snapshot creation and deletion are as simple as 'mkdir
+.snap/foo' and 'rmdir .snap/foo'.
+
+Ceph also provides some recursive accounting on directories for nested
+files and bytes.  That is, a 'getfattr -d foo' on any directory in the
+system will reveal the total number of nested regular files and
+subdirectories, and a summation of all nested file sizes.  This makes
+the identification of large disk space consumers relatively quick, as
+no 'du' or similar recursive scan of the file system is required.
+
+
+Mount Syntax
+============
+
+The basic mount syntax is:
+
+ # mount -t ceph monip[:port][,monip2[:port]...]:/[subdir] mnt
+
+You only need to specify a single monitor, as the client will get the
+full list when it connects.  (However, if the monitor you specify
+happens to be down, the mount won't succeed.)  The port can be left
+off if the monitor is using the default.  So if the monitor is at
+1.2.3.4,
+
+ # mount -t ceph 1.2.3.4:/ /mnt/ceph
+
+is sufficient.  If /sbin/mount.ceph is installed, a hostname can be
+used instead of an IP address.
+
+
+
+Mount Options
+=============
+
+  ip=A.B.C.D[:N]
+        Specify the IP and/or port the client should bind to locally.
+        There is normally not much reason to do this.  If the IP is not
+        specified, the client's IP address is determined by looking at the
+        address it's connection to the monitor originates from.
+
+  wsize=X
+        Specify the maximum write size in bytes.  By default there is no
+        maximum.  Ceph will normally size writes based on the file stripe
+        size.
+
+  rsize=X
+        Specify the maximum readahead.
+
+  mount_timeout=X
+        Specify the timeout value for mount (in seconds), in the case
+        of a non-responsive Ceph file system.  The default is 30
+        seconds.
+
+  rbytes
+        When stat() is called on a directory, set st_size to 'rbytes',
+        the summation of file sizes over all files nested beneath that
+        directory.  This is the default.
+
+  norbytes
+        When stat() is called on a directory, set st_size to the
+        number of entries in that directory.
+
+  nocrc
+        Disable CRC32C calculation for data writes.  If set, the storage node
+        must rely on TCP's error correction to detect data corruption
+        in the data payload.
+
+  noasyncreaddir
+        Disable client's use its local cache to satisfy readdir
+        requests.  (This does not change correctness; the client uses
+        cached metadata only when a lease or capability ensures it is
+        valid.)
+
+
+More Information
+================
+
+For more information on Ceph, see the home page at
+        http://ceph.newdream.net/
+
+The Linux kernel client source tree is available at
+        git://ceph.newdream.net/git/ceph-client.git
+        git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+
+and the source for the full system is at
+        git://ceph.newdream.net/git/ceph.git
diff --git a/Documentation/filesystems/dentry-locking.txt b/Documentation/filesystems/dentry-locking.txt
index 4c0c575a4012..79334ed5daa7 100644
--- a/Documentation/filesystems/dentry-locking.txt
+++ b/Documentation/filesystems/dentry-locking.txt
@@ -62,7 +62,8 @@ changes are :
 2. Insertion of a dentry into the hash table is done using
    hlist_add_head_rcu() which take care of ordering the writes - the
    writes to the dentry must be visible before the dentry is
-   inserted. This works in conjunction with hlist_for_each_rcu() while
+   inserted. This works in conjunction with hlist_for_each_rcu(),
+   which has since been replaced by hlist_for_each_entry_rcu(), while
    walking the hash chain. The only requirement is that all
    initialization to the dentry must be done before
    hlist_add_head_rcu() since we don't have dcache_lock protection
diff --git a/Documentation/filesystems/dnotify.txt b/Documentation/filesystems/dnotify.txt
index 9f5d338ddbb8..6baf88f46859 100644
--- a/Documentation/filesystems/dnotify.txt
+++ b/Documentation/filesystems/dnotify.txt
@@ -62,38 +62,9 @@ disabled, fcntl(fd, F_NOTIFY, ...) will return -EINVAL.
 
 Example
 -------
+See Documentation/filesystems/dnotify_test.c for an example.
 
-        #define _GNU_SOURCE     /* needed to get the defines */
-        #include <fcntl.h>      /* in glibc 2.2 this has the needed
-                                           values defined */
-        #include <signal.h>
-        #include <stdio.h>
-        #include <unistd.h>
-
-        static volatile int event_fd;
-
-        static void handler(int sig, siginfo_t *si, void *data)
-        {
-                event_fd = si->si_fd;
-        }
-
-        int main(void)
-        {
-                struct sigaction act;
-                int fd;
-
-                act.sa_sigaction = handler;
-                sigemptyset(&act.sa_mask);
-                act.sa_flags = SA_SIGINFO;
-                sigaction(SIGRTMIN + 1, &act, NULL);
-
-                fd = open(".", O_RDONLY);
-                fcntl(fd, F_SETSIG, SIGRTMIN + 1);
-                fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
-                /* we will now be notified if any of the files
-                   in "." is modified or new files are created */
-                while (1) {
-                        pause();
-                        printf("Got event on fd=%d\n", event_fd);
-                }
-        }
+NOTE
+----
+Beginning with Linux 2.6.13, dnotify has been replaced by inotify.
+See Documentation/filesystems/inotify.txt for more information on it.
diff --git a/Documentation/filesystems/dnotify_test.c b/Documentation/filesystems/dnotify_test.c
new file mode 100644
index 000000000000..8b37b4a1e18d
--- /dev/null
+++ b/Documentation/filesystems/dnotify_test.c
@@ -0,0 +1,34 @@
+#define _GNU_SOURCE     /* needed to get the defines */
+#include <fcntl.h>      /* in glibc 2.2 this has the needed
+                                   values defined */
+#include <signal.h>
+#include <stdio.h>
+#include <unistd.h>
+
+static volatile int event_fd;
+
+static void handler(int sig, siginfo_t *si, void *data)
+{
+        event_fd = si->si_fd;
+}
+
+int main(void)
+{
+        struct sigaction act;
+        int fd;
+
+        act.sa_sigaction = handler;
+        sigemptyset(&act.sa_mask);
+        act.sa_flags = SA_SIGINFO;
+        sigaction(SIGRTMIN + 1, &act, NULL);
+
+        fd = open(".", O_RDONLY);
+        fcntl(fd, F_SETSIG, SIGRTMIN + 1);
+        fcntl(fd, F_NOTIFY, DN_MODIFY|DN_CREATE|DN_MULTISHOT);
+        /* we will now be notified if any of the files
+           in "." is modified or new files are created */
+        while (1) {
+                pause();
+                printf("Got event on fd=%d\n", event_fd);
+        }
+}
diff --git a/Documentation/filesystems/logfs.txt b/Documentation/filesystems/logfs.txt
new file mode 100644
index 000000000000..e64c94ba401a
--- /dev/null
+++ b/Documentation/filesystems/logfs.txt
@@ -0,0 +1,241 @@
+
+The LogFS Flash Filesystem
+==========================
+
+Specification
+=============
+
+Superblocks
+-----------
+
+Two superblocks exist at the beginning and end of the filesystem.
+Each superblock is 256 Bytes large, with another 3840 Bytes reserved
+for future purposes, making a total of 4096 Bytes.
+
+Superblock locations may differ for MTD and block devices.  On MTD the
+first non-bad block contains a superblock in the first 4096 Bytes and
+the last non-bad block contains a superblock in the last 4096 Bytes.
+On block devices, the first 4096 Bytes of the device contain the first
+superblock and the last aligned 4096 Byte-block contains the second
+superblock.
+
+For the most part, the superblocks can be considered read-only.  They
+are written only to correct errors detected within the superblocks,
+move the journal and change the filesystem parameters through tunefs.
+As a result, the superblock does not contain any fields that require
+constant updates, like the amount of free space, etc.
+
+Segments
+--------
+
+The space in the device is split up into equal-sized segments.
+Segments are the primary write unit of LogFS.  Within each segments,
+writes happen from front (low addresses) to back (high addresses.  If
+only a partial segment has been written, the segment number, the
+current position within and optionally a write buffer are stored in
+the journal.
+
+Segments are erased as a whole.  Therefore Garbage Collection may be
+required to completely free a segment before doing so.
+
+Journal
+--------
+
+The journal contains all global information about the filesystem that
+is subject to frequent change.  At mount time, it has to be scanned
+for the most recent commit entry, which contains a list of pointers to
+all currently valid entries.
+
+Object Store
+------------
+
+All space except for the superblocks and journal is part of the object
+store.  Each segment contains a segment header and a number of
+objects, each consisting of the object header and the payload.
+Objects are either inodes, directory entries (dentries), file data
+blocks or indirect blocks.
+
+Levels
+------
+
+Garbage collection (GC) may fail if all data is written
+indiscriminately.  One requirement of GC is that data is seperated
+roughly according to the distance between the tree root and the data.
+Effectively that means all file data is on level 0, indirect blocks
+are on levels 1, 2, 3 4 or 5 for 1x, 2x, 3x, 4x or 5x indirect blocks,
+respectively.  Inode file data is on level 6 for the inodes and 7-11
+for indirect blocks.
+
+Each segment contains objects of a single level only.  As a result,
+each level requires its own seperate segment to be open for writing.
+
+Inode File
+----------
+
+All inodes are stored in a special file, the inode file.  Single
+exception is the inode file's inode (master inode) which for obvious
+reasons is stored in the journal instead.  Instead of data blocks, the
+leaf nodes of the inode files are inodes.
+
+Aliases
+-------
+
+Writes in LogFS are done by means of a wandering tree.  A naïve
+implementation would require that for each write or a block, all
+parent blocks are written as well, since the block pointers have
+changed.  Such an implementation would not be very efficient.
+
+In LogFS, the block pointer changes are cached in the journal by means
+of alias entries.  Each alias consists of its logical address - inode
+number, block index, level and child number (index into block) - and
+the changed data.  Any 8-byte word can be changes in this manner.
+
+Currently aliases are used for block pointers, file size, file used
+bytes and the height of an inodes indirect tree.
+
+Segment Aliases
+---------------
+
+Related to regular aliases, these are used to handle bad blocks.
+Initially, bad blocks are handled by moving the affected segment
+content to a spare segment and noting this move in the journal with a
+segment alias, a simple (to, from) tupel.  GC will later empty this
+segment and the alias can be removed again.  This is used on MTD only.
+
+Vim
+---
+
+By cleverly predicting the life time of data, it is possible to
+seperate long-living data from short-living data and thereby reduce
+the GC overhead later.  Each type of distinc life expectency (vim) can
+have a seperate segment open for writing.  Each (level, vim) tupel can
+be open just once.  If an open segment with unknown vim is encountered
+at mount time, it is closed and ignored henceforth.
+
+Indirect Tree
+-------------
+
+Inodes in LogFS are similar to FFS-style filesystems with direct and
+indirect block pointers.  One difference is that LogFS uses a single
+indirect pointer that can be either a 1x, 2x, etc. indirect pointer.
+A height field in the inode defines the height of the indirect tree
+and thereby the indirection of the pointer.
+
+Another difference is the addressing of indirect blocks.  In LogFS,
+the first 16 pointers in the first indirect block are left empty,
+corresponding to the 16 direct pointers in the inode.  In ext2 (maybe
+others as well) the first pointer in the first indirect block
+corresponds to logical block 12, skipping the 12 direct pointers.
+So where ext2 is using arithmetic to better utilize space, LogFS keeps
+arithmetic simple and uses compression to save space.
+
+Compression
+-----------
+
+Both file data and metadata can be compressed.  Compression for file
+data can be enabled with chattr +c and disabled with chattr -c.  Doing
+so has no effect on existing data, but new data will be stored
+accordingly.  New inodes will inherit the compression flag of the
+parent directory.
+
+Metadata is always compressed.  However, the space accounting ignores
+this and charges for the uncompressed size.  Failing to do so could
+result in GC failures when, after moving some data, indirect blocks
+compress worse than previously.  Even on a 100% full medium, GC may
+not consume any extra space, so the compression gains are lost space
+to the user.
+
+However, they are not lost space to the filesystem internals.  By
+cheating the user for those bytes, the filesystem gained some slack
+space and GC will run less often and faster.
+
+Garbage Collection and Wear Leveling
+------------------------------------
+
+Garbage collection is invoked whenever the number of free segments
+falls below a threshold.  The best (known) candidate is picked based
+on the least amount of valid data contained in the segment.  All
+remaining valid data is copied elsewhere, thereby invalidating it.
+
+The GC code also checks for aliases and writes then back if their
+number gets too large.
+
+Wear leveling is done by occasionally picking a suboptimal segment for
+garbage collection.  If a stale segments erase count is significantly
+lower than the active segments' erase counts, it will be picked.  Wear
+leveling is rate limited, so it will never monopolize the device for
+more than one segment worth at a time.
+
+Values for "occasionally", "significantly lower" are compile time
+constants.
+
+Hashed directories
+------------------
+
+To satisfy efficient lookup(), directory entries are hashed and
+located based on the hash.  In order to both support large directories
+and not be overly inefficient for small directories, several hash
+tables of increasing size are used.  For each table, the hash value
+modulo the table size gives the table index.
+
+Tables sizes are chosen to limit the number of indirect blocks with a
+fully populated table to 0, 1, 2 or 3 respectively.  So the first
+table contains 16 entries, the second 512-16, etc.
+
+The last table is special in several ways.  First its size depends on
+the effective 32bit limit on telldir/seekdir cookies.  Since logfs
+uses the upper half of the address space for indirect blocks, the size
+is limited to 2^31.  Secondly the table contains hash buckets with 16
+entries each.
+
+Using single-entry buckets would result in birthday "attacks".  At
+just 2^16 used entries, hash collisions would be likely (P >= 0.5).
+My math skills are insufficient to do the combinatorics for the 17x
+collisions necessary to overflow a bucket, but testing showed that in
+10,000 runs the lowest directory fill before a bucket overflow was
+188,057,130 entries with an average of 315,149,915 entries.  So for
+directory sizes of up to a million, bucket overflows should be
+virtually impossible under normal circumstances.
+
+With carefully chosen filenames, it is obviously possible to cause an
+overflow with just 21 entries (4 higher tables + 16 entries + 1).  So
+there may be a security concern if a malicious user has write access
+to a directory.
+
+Open For Discussion
+===================
+
+Device Address Space
+--------------------
+
+A device address space is used for caching.  Both block devices and
+MTD provide functions to either read a single page or write a segment.
+Partial segments may be written for data integrity, but where possible
+complete segments are written for performance on simple block device
+flash media.
+
+Meta Inodes
+-----------
+
+Inodes are stored in the inode file, which is just a regular file for
+most purposes.  At umount time, however, the inode file needs to
+remain open until all dirty inodes are written.  So
+generic_shutdown_super() may not close this inode, but shouldn't
+complain about remaining inodes due to the inode file either.  Same
+goes for mapping inode of the device address space.
+
+Currently logfs uses a hack that essentially copies part of fs/inode.c
+code over.  A general solution would be preferred.
+
+Indirect block mapping
+----------------------
+
+With compression, the block device (or mapping inode) cannot be used
+to cache indirect blocks.  Some other place is required.  Currently
+logfs uses the top half of each inode's address space.  The low 8TB
+(on 32bit) are filled with file data, the high 8TB are used for
+indirect blocks.
+
+One problem is that 16TB files created on 64bit systems actually have
+data in the top 8TB.  But files >16TB would cause problems anyway, so
+only the limit has changed.
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 1bd0d0c05171..6a53a84afc72 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -17,8 +17,7 @@ kernels must turn 4.1 on or off *before* turning support for version 4
 on or off; rpc.nfsd does this correctly.)
 
 The NFSv4 minorversion 1 (NFSv4.1) implementation in nfsd is based
-on the latest NFSv4.1 Internet Draft:
-http://tools.ietf.org/html/draft-ietf-nfsv4-minorversion1-29
+on RFC 5661.
 
 From the many new features in NFSv4.1 the current implementation
 focuses on the mandatory-to-implement NFSv4.1 Sessions, providing
@@ -44,7 +43,7 @@ interoperability problems with future clients.  Known issues:
           trunking, but this is a mandatory feature, and its use is
           recommended to clients in a number of places.  (E.g. to ensure
           timely renewal in case an existing connection's retry timeouts
-          have gotten too long; see section 8.3 of the draft.)
+          have gotten too long; see section 8.3 of the RFC.)
           Therefore, lack of this feature may cause future clients to
           fail.
         - Incomplete backchannel support: incomplete backchannel gss
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 839efd8a8a8c..cf6d0d85ca82 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -74,6 +74,9 @@ norecovery		Disable recovery of the filesystem on mount.
                         This disables every write access on the device for
                         read-only mounts or snapshots.  This option will fail
                         for r/w mounts on an unclean volume.
+discard                 Issue discard/TRIM commands to the underlying block
+                        device when blocks are freed.  This is useful for SSD
+                        devices and sparse/thinly-provisioned LUNs.
 
 NILFS2 usage
 ============
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 0d07513a67a6..1e359b62c40a 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -164,6 +164,7 @@ read the file /proc/PID/status:
   VmExe:        68 kB
   VmLib:      1412 kB
   VmPTE:        20 kb
+  VmSwap:        0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -188,7 +189,13 @@ memory usage. Its seven fields are explained in Table 1-3.  The stat file
 contains details information about the process itself.  Its fields are
 explained in Table 1-4.
 
-Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
+(for SMP CONFIG users)
+For making accounting scalable, RSS related information are handled in
+asynchronous manner and the vaule may not be very precise. To see a precise
+snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
+It's slow but very precise.
+
+Table 1-2: Contents of the status files (as of 2.6.30-rc7)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
@@ -213,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
@@ -308,7 +316,7 @@ address           perms offset  dev   inode      pathname
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -344,7 +352,6 @@ is not associated with a file:
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
- [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 
@@ -430,6 +437,7 @@ Table 1-5: Kernel info in /proc
  modules     List of loaded modules                            
  mounts      Mounted filesystems                               
  net         Networking info (see text)                        
+ pagetypeinfo Additional page allocator information (see text)  (2.5)
  partitions  Table of partitions known to the system           
  pci         Deprecated info of PCI bus (new way -> /proc/bus/pci/,
              decoupled by lspci                                 (2.4)
@@ -584,7 +592,7 @@ Node 0, zone      DMA      0      4      5      4      4      3 ...
 Node 0, zone   Normal      1      0      0      1    101      8 ...
 Node 0, zone  HighMem      2      0      0      1      1      0 ...
 
-Memory fragmentation is a problem under some workloads, and buddyinfo is a 
+External fragmentation is a problem under some workloads, and buddyinfo is a
 useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 clue as to how big an area you can safely allocate, or why a previous
 allocation failed.
@@ -594,6 +602,48 @@ available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in
 ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 available in ZONE_NORMAL, etc... 
 
+More information relevant to external fragmentation can be found in
+pagetypeinfo.
+
+> cat /proc/pagetypeinfo
+Page block order: 9
+Pages per block:  512
+
+Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
+Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
+Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
+Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
+Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
+Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
+Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
+Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
+Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
+
+Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
+Node 0, zone      DMA            2            0            5            1            0
+Node 0, zone    DMA32           41            6          967            2            0
+
+Fragmentation avoidance in the kernel works by grouping pages of different
+migrate types into the same contiguous regions of memory called page blocks.
+A page block is typically the size of the default hugepage size e.g. 2MB on
+X86-64. By keeping pages grouped based on their ability to move, the kernel
+can reclaim pages within a page block to satisfy a high-order allocation.
+
+The pagetypinfo begins with information on the size of a page block. It
+then gives the same type of information as buddyinfo except broken down
+by migrate-type and finishes with details on how many page blocks of each
+type exist.
+
+If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
+from libhugetlbfs http://sourceforge.net/projects/libhugetlbfs/), one can
+make an estimate of the likely number of huge pages that can be allocated
+at a given point in time. All the "Movable" blocks should be allocatable
+unless memory has been mlock()'d. Some of the Reclaimable blocks should
+also be allocatable although a lot of filesystem metadata may have to be
+reclaimed to achieve this.
+
 ..............................................................................
 
 meminfo:
diff --git a/Documentation/filesystems/sharedsubtree.txt b/Documentation/filesystems/sharedsubtree.txt
index 23a181074f94..fc0e39af43c3 100644
--- a/Documentation/filesystems/sharedsubtree.txt
+++ b/Documentation/filesystems/sharedsubtree.txt
@@ -837,6 +837,9 @@ replicas continue to be exactly same.
          individual lists does not affect propagation or the way propagation
          tree is modified by operations.
 
+        All vfsmounts in a peer group have the same ->mnt_master.  If it is
+        non-NULL, they form a contiguous (ordered) segment of slave list.
+
         A example propagation tree looks as shown in the figure below.
         [ NOTE: Though it looks like a forest, if we consider all the shared
         mounts as a conceptual entity called 'pnode', it becomes a tree]
@@ -874,8 +877,19 @@ replicas continue to be exactly same.
 
         NOTE: The propagation tree is orthogonal to the mount tree.
 
+8B Locking:
+
+        ->mnt_share, ->mnt_slave, ->mnt_slave_list, ->mnt_master are protected
+        by namespace_sem (exclusive for modifications, shared for reading).
+
+        Normally we have ->mnt_flags modifications serialized by vfsmount_lock.
+        There are two exceptions: do_add_mount() and clone_mnt().
+        The former modifies a vfsmount that has not been visible in any shared
+        data structures yet.
+        The latter holds namespace_sem and the only references to vfsmount
+        are in lists that can't be traversed without namespace_sem.
 
-8B Algorithm:
+8C Algorithm:
 
         The crux of the implementation resides in rbind/move operation.
 
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 3015da0c6b2a..fe09a2cb1858 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -82,11 +82,13 @@ tmpfs has a mount option to set the NUMA memory allocation policy for
 all files in that instance (if CONFIG_NUMA is enabled) - which can be
 adjusted on the fly via 'mount -o remount ...'
 
-mpol=default             prefers to allocate memory from the local node
+mpol=default             use the process allocation policy
+                         (see set_mempolicy(2))
 mpol=prefer:Node         prefers to allocate memory from the given Node
 mpol=bind:NodeList       allocates memory only from nodes in NodeList
 mpol=interleave          prefers to allocate from each node in turn
 mpol=interleave:NodeList allocates from each node of NodeList in turn
+mpol=local               prefers to allocate memory from the local node
 
 NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
@@ -134,3 +136,5 @@ Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
 Updated:
    Hugh Dickins, 4 June 2007
+Updated:
+   KOSAKI Motohiro, 16 Mar 2010
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 1866c27eec69..c2c6e9b39bbe 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -253,6 +253,70 @@ pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
 Also note that it's your responsibility to have stopped using a GPIO
 before you free it.
 
+Considering in most cases GPIOs are actually configured right after they
+are claimed, three additional calls are defined:
+
+        /* request a single GPIO, with initial configuration specified by
+         * 'flags', identical to gpio_request() wrt other arguments and
+         * return value
+         */
+        int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
+
+        /* request multiple GPIOs in a single call
+         */
+        int gpio_request_array(struct gpio *array, size_t num);
+
+        /* release multiple GPIOs in a single call
+         */
+        void gpio_free_array(struct gpio *array, size_t num);
+
+where 'flags' is currently defined to specify the following properties:
+
+        * GPIOF_DIR_IN          - to configure direction as input
+        * GPIOF_DIR_OUT         - to configure direction as output
+
+        * GPIOF_INIT_LOW        - as output, set initial level to LOW
+        * GPIOF_INIT_HIGH       - as output, set initial level to HIGH
+
+since GPIOF_INIT_* are only valid when configured as output, so group valid
+combinations as:
+
+        * GPIOF_IN              - configure as input
+        * GPIOF_OUT_INIT_LOW    - configured as output, initial level LOW
+        * GPIOF_OUT_INIT_HIGH   - configured as output, initial level HIGH
+
+In the future, these flags can be extended to support more properties such
+as open-drain status.
+
+Further more, to ease the claim/release of multiple GPIOs, 'struct gpio' is
+introduced to encapsulate all three fields as:
+
+        struct gpio {
+                unsigned        gpio;
+                unsigned long   flags;
+                const char      *label;
+        };
+
+A typical example of usage:
+
+        static struct gpio leds_gpios[] = {
+                { 32, GPIOF_OUT_INIT_HIGH, "Power LED" }, /* default to ON */
+                { 33, GPIOF_OUT_INIT_LOW,  "Green LED" }, /* default to OFF */
+                { 34, GPIOF_OUT_INIT_LOW,  "Red LED"   }, /* default to OFF */
+                { 35, GPIOF_OUT_INIT_LOW,  "Blue LED"  }, /* default to OFF */
+                { ... },
+        };
+
+        err = gpio_request_one(31, GPIOF_IN, "Reset Button");
+        if (err)
+                ...
+
+        err = gpio_request_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+        if (err)
+                ...
+
+        gpio_free_array(leds_gpios, ARRAY_SIZE(leds_gpios));
+
 
 GPIOs mapped to IRQs
 --------------------
diff --git a/Documentation/hwmon/abituguru b/Documentation/hwmon/abituguru
index 87ffa0f5ec70..5eb3b9d5f0d5 100644
--- a/Documentation/hwmon/abituguru
+++ b/Documentation/hwmon/abituguru
@@ -30,7 +30,7 @@ Supported chips:
            bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
            You may also need to specify the fan_sensors option for these boards
            fan_sensors=5
-        2) There is a seperate abituguru3 driver for these motherboards,
+        2) There is a separate abituguru3 driver for these motherboards,
            the abituguru (without the 3 !) driver will not work on these
            motherboards (and visa versa)!
 
diff --git a/Documentation/hwmon/adt7411 b/Documentation/hwmon/adt7411
new file mode 100644
index 000000000000..1632960f9745
--- /dev/null
+++ b/Documentation/hwmon/adt7411
@@ -0,0 +1,42 @@
+Kernel driver adt7411
+=====================
+
+Supported chips:
+  * Analog Devices ADT7411
+    Prefix: 'adt7411'
+    Addresses scanned: 0x48, 0x4a, 0x4b
+    Datasheet: Publicly available at the Analog Devices website
+
+Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
+
+Description
+-----------
+
+This driver implements support for the Analog Devices ADT7411 chip. There may
+be other chips that implement this interface.
+
+The ADT7411 can use an I2C/SMBus compatible 2-wire interface or an
+SPI-compatible 4-wire interface. It provides a 10-bit analog to digital
+converter which measures 1 temperature, vdd and 8 input voltages. It has an
+internal temperature sensor, but an external one can also be connected (one
+loses 2 inputs then). There are high- and low-limit registers for all inputs.
+
+Check the datasheet for details.
+
+sysfs-Interface
+---------------
+
+in0_input       - vdd voltage input
+in[1-8]_input   - analog 1-8 input
+temp1_input     - temperature input
+
+Besides standard interfaces, this driver adds (0 = off, 1 = on):
+
+  adc_ref_vdd   - Use vdd as reference instead of 2.25 V
+  fast_sampling - Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average    - Turn off averaging over 16 samples
+
+Notes
+-----
+
+SPI, external temperature sensor and limit registers are not supported yet.
diff --git a/Documentation/hwmon/adt7473 b/Documentation/hwmon/adt7473
deleted file mode 100644
index 446612bd1fb9..000000000000
--- a/Documentation/hwmon/adt7473
+++ /dev/null
@@ -1,74 +0,0 @@
-Kernel driver adt7473
-======================
-
-Supported chips:
-  * Analog Devices ADT7473
-    Prefix: 'adt7473'
-    Addresses scanned: I2C 0x2C, 0x2D, 0x2E
-    Datasheet: Publicly available at the Analog Devices website
-
-Author: Darrick J. Wong
-
-This driver is depreacted, please use the adt7475 driver instead.
-
-Description
------------
-
-This driver implements support for the Analog Devices ADT7473 chip family.
-
-The ADT7473 uses the 2-wire interface compatible with the SMBUS 2.0
-specification. Using an analog to digital converter it measures three (3)
-temperatures and two (2) voltages. It has four (4) 16-bit counters for
-measuring fan speed. There are three (3) PWM outputs that can be used
-to control fan speed.
-
-A sophisticated control system for the PWM outputs is designed into the
-ADT7473 that allows fan speed to be adjusted automatically based on any of the
-three temperature sensors. Each PWM output is individually adjustable and
-programmable. Once configured, the ADT7473 will adjust the PWM outputs in
-response to the measured temperatures without further host intervention.
-This feature can also be disabled for manual control of the PWM's.
-
-Each of the measured inputs (voltage, temperature, fan speed) has
-corresponding high/low limit values. The ADT7473 will signal an ALARM if
-any measured value exceeds either limit.
-
-The ADT7473 samples all inputs continuously. The driver will not read
-the registers more often than once every other second. Further,
-configuration data is only read once per minute.
-
-Special Features
-----------------
-
-The ADT7473 have a 10-bit ADC and can therefore measure temperatures
-with 0.25 degC resolution. Temperature readings can be configured either
-for twos complement format or "Offset 64" format, wherein 63 is subtracted
-from the raw value to get the temperature value.
-
-The Analog Devices datasheet is very detailed and describes a procedure for
-determining an optimal configuration for the automatic PWM control.
-
-Configuration Notes
--------------------
-
-Besides standard interfaces driver adds the following:
-
-* PWM Control
-
-* pwm#_auto_point1_pwm and temp#_auto_point1_temp and
-* pwm#_auto_point2_pwm and temp#_auto_point2_temp -
-
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
-
-The ADT7473 will scale the pwm between the lower and higher pwm speed when
-the temperature is between the two temperature boundaries.  PWM values range
-from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
-temperature sensor associated with the PWM control exceeds temp#_max.
-
-Notes
------
-
-The NVIDIA binary driver presents an ADT7473 chip via an on-card i2c bus.
-Unfortunately, they fail to set the i2c adapter class, so this driver may
-fail to find the chip until the nvidia driver is patched.
diff --git a/Documentation/hwmon/asc7621 b/Documentation/hwmon/asc7621
new file mode 100644
index 000000000000..7287be7e1f21
--- /dev/null
+++ b/Documentation/hwmon/asc7621
@@ -0,0 +1,296 @@
+Kernel driver asc7621
+==================
+
+Supported chips:
+    Andigilog aSC7621 and aSC7621a
+    Prefix: 'asc7621'
+    Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+    Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
+
+Author:
+                George Joseph
+
+Description provided by Dave Pivin @ Andigilog:
+
+Andigilog has both the PECI and pre-PECI versions of the Heceta-6, as
+Intel calls them. Heceta-6e has high frequency PWM and Heceta-6p has
+added PECI and a 4th thermal zone. The Andigilog aSC7611 is the
+Heceta-6e part and aSC7621 is the Heceta-6p part. They are both in
+volume production, shipping to Intel and their subs.
+
+We have enhanced both parts relative to the governing Intel
+specification. First enhancement is temperature reading resolution. We
+have used registers below 20h for vendor-specific functions in addition
+to those in the Intel-specified vendor range.
+
+Our conversion process produces a result that is reported as two bytes.
+The fan speed control uses this finer value to produce a "step-less" fan
+PWM output. These two bytes are "read-locked" to guarantee that once a
+high or low byte is read, the other byte is locked-in until after the
+next read of any register. So to get an atomic reading, read high or low
+byte, then the very next read should be the opposite byte. Our data
+sheet says 10-bits of resolution, although you may find the lower bits
+are active, they are not necessarily reliable or useful externally. We
+chose not to mask them.
+
+We employ significant filtering that is user tunable as described in the
+data sheet. Our temperature reports and fan PWM outputs are very smooth
+when compared to the competition, in addition to the higher resolution
+temperature reports. The smoother PWM output does not require user
+intervention.
+
+We offer GPIO features on the former VID pins. These are open-drain
+outputs or inputs and may be used as general purpose I/O or as alarm
+outputs that are based on temperature limits. These are in 19h and 1Ah.
+
+We offer flexible mapping of temperature readings to thermal zones. Any
+temperature may be mapped to any zone, which has a default assignment
+that follows Intel's specs.
+
+Since there is a fan to zone assignment that allows for the "hotter" of
+a set of zones to control the PWM of an individual fan, but there is no
+indication to the user, we have added an indicator that shows which zone
+is currently controlling the PWM for a given fan. This is in register
+00h.
+
+Both remote diode temperature readings may be given an offset value such
+that the reported reading as well as the temperature used to determine
+PWM may be offset for system calibration purposes.
+
+PECI Extended configuration allows for having more than two domains per
+PECI address and also provides an enabling function for each PECI
+address. One could use our flexible zone assignment to have a zone
+assigned to up to 4 PECI addresses. This is not possible in the default
+Intel configuration. This would be useful in multi-CPU systems with
+individual fans on each that would benefit from individual fan control.
+This is in register 0Eh.
+
+The tachometer measurement system is flexible and able to adapt to many
+fan types. We can also support pulse-stretched PWM so that 3-wire fans
+may be used. These characteristics are in registers 04h to 07h.
+
+Finally, we have added a tach disable function that turns off the tach
+measurement system for individual tachs in order to save power. That is
+in register 75h.
+
+--
+aSC7621 Product Description
+
+The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
+Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
+connected transistors as well as its own die. Support for Platform
+Environmental Control Interface (PECI) is included.
+
+Using temperature information from these four zones, an automatic fan speed
+control algorithm is employed to minimize acoustic impact while achieving
+recommended CPU temperature under varying operational loads.
+
+To set fan speed, the aSC7621 has three independent pulse width modulation
+(PWM) outputs that are controlled by one, or a combination of three,
+temperature zones. Both high- and low-frequency PWM ranges are supported.
+
+The aSC7621 also includes a digital filter that can be invoked to smooth
+temperature readings for better control of fan speed and minimum acoustic
+impact.
+
+The aSC7621 has tachometer inputs to measure fan speed on up to four fans.
+Limit and status registers for all measured values are included to alert
+the system host that any measurements are outside of programmed limits
+via status registers.
+
+System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
+monitored efficiently with internal scaling resistors.
+
+Features
+- Supports PECI interface and monitors internal and remote thermal diodes
+- 2-wire, SMBus 2.0 compliant, serial interface
+- 10-bit ADC
+- Monitors VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard/processor supplies
+- Programmable autonomous fan control based on temperature readings
+- Noise filtering of temperature reading for fan speed control
+- 0.25C digital temperature sensor resolution
+- 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
+        tachometer inputs
+- Enhanced measured temperature to Temperature Zone assignment.
+- Provides high and low PWM frequency ranges
+- 3 GPIO pins for custom use
+- 24-Lead QSOP package
+
+Configuration Notes
+===================
+
+Except where noted below, the sysfs entries created by this driver follow
+the standards defined in "sysfs-interface".
+
+temp1_source
+        0       (default) peci_legacy = 0, Remote 1 Temperature
+                        peci_legacy = 1, PECI Processor Temperature 0
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7  PECI Processor Temperature 3
+
+temp2_source
+        0       (default) Internal Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+
+temp3_source
+        0       (default) Remote 2 Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+
+temp4_source
+        0       (default) peci_legacy = 0, PECI Processor Temperature 0
+                        peci_legacy = 1, Remote 1 Temperature
+        1       Remote 1 Temperature
+        2       Remote 2 Temperature
+        3       Internal Temperature
+        4       PECI Processor Temperature 0
+        5       PECI Processor Temperature 1
+        6       PECI Processor Temperature 2
+        7       PECI Processor Temperature 3
+
+temp[1-4]_smoothing_enable
+temp[1-4]_smoothing_time
+        Smooths spikes in temp readings caused by noise.
+        Valid values in milliseconds are:
+        35000
+        17600
+        11800
+         7000
+         4400
+         3000
+         1600
+          800
+
+temp[1-4]_crit
+        When the corresponding zone temperature reaches this value,
+        ALL pwm outputs will got to 100%.
+
+temp[5-8]_input
+temp[5-8]_enable
+        The aSC7621 can also read temperatures provided by the processor
+        via the PECI bus.  Usually these are "core" temps and are relative
+        to the point where the automatic thermal control circuit starts
+        throttling.  This means that these are usually negative numbers.
+
+pwm[1-3]_enable
+        0               Fan off.
+        1               Fan on manual control.
+        2               Fan on automatic control and will run at the minimum pwm
+                                if the temperature for the zone is below the minimum.
+        3               Fan on automatic control but will be off if the temperature
+                                for the zone is below the minimum.
+        4-254   Ignored.
+        255             Fan on full.
+
+pwm[1-3]_auto_channels
+        Bitmap as described in sysctl-interface with the following
+        exceptions...
+        Only the following combination of zones (and their corresponding masks)
+        are valid:
+        1
+        2
+        3
+        2,3
+        1,2,3
+        4
+        1,2,3,4
+
+        Special values:
+        0                       Disabled.
+        16              Fan on manual control.
+        31              Fan on full.
+
+
+pwm[1-3]_invert
+        When set, inverts the meaning of pwm[1-3].
+        i.e.  when pwm = 0, the fan will be on full and
+        when pwm = 255 the fan will be off.
+
+pwm[1-3]_freq
+        PWM frequency in Hz
+        Valid values in Hz are:
+
+        10
+        15
+        23
+        30  (default)
+        38
+        47
+        62
+        94
+        23000
+        24000
+        25000
+        26000
+        27000
+        28000
+        29000
+        30000
+
+        Setting any other value will be ignored.
+
+peci_enable
+        Enables or disables PECI
+
+peci_avg
+        Input filter average time.
+
+        0       0 Sec. (no Smoothing) (default)
+        1       0.25 Sec.
+        2       0.5 Sec.
+        3       1.0 Sec.
+        4       2.0 Sec.
+        5       4.0 Sec.
+        6       8.0 Sec.
+        7       0.0 Sec.
+
+peci_legacy
+
+        0       Standard Mode (default)
+                Remote Diode 1 reading is associated with
+                Temperature Zone 1, PECI is associated with
+                Zone 4
+
+        1       Legacy Mode
+                PECI is associated with Temperature Zone 1,
+                Remote Diode 1 is associated with Zone 4
+
+peci_diode
+        Diode filter
+
+        0       0.25 Sec.
+        1       1.1 Sec.
+        2       2.4 Sec.  (default)
+        3       3.4 Sec.
+        4       5.0 Sec.
+        5       6.8 Sec.
+        6       10.2 Sec.
+        7       16.4 Sec.
+
+peci_4domain
+        Four domain enable
+
+        0       1 or 2 Domains for enabled processors (default)
+        1       3 or 4 Domains for enabled processors
+
+peci_domain
+        Domain
+
+        0       Processor contains a single domain (0)   (default)
+        1       Processor contains two domains (0,1)
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index f9ba96c0ac4a..8d08bf0d38ed 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -5,31 +5,23 @@ Supported chips:
   * IT8705F
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8705F_V.0.4.1.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8712F
     Prefix: 'it8712'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/Errata%20V0.1%20for%20IT8712F%20V0.9.1.pdf
-               http://www.ite.com.tw/product_info/file/pc/IT8712F_V0.9.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8716F/IT8726F
     Prefix: 'it8716'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8716F_V0.3.ZIP
-               http://www.ite.com.tw/product_info/file/pc/IT8726F_V0.3.pdf
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8718F
     Prefix: 'it8718'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Publicly available at the ITE website
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
-               http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
+    Datasheet: Once publicly available at the ITE website, but no longer
   * IT8720F
     Prefix: 'it8720'
     Addresses scanned: from Super I/O config space (8 I/O ports)
-    Datasheet: Not yet publicly available.
+    Datasheet: Not publicly available
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -136,6 +128,10 @@ registers are read whenever any data is read (unless it is less than 1.5
 seconds since the last update). This means that you can easily miss
 once-only alarms.
 
+Out-of-limit readings can also result in beeping, if the chip is properly
+wired and configured. Beeping can be enabled or disabled per sensor type
+(temperatures, voltages and fans.)
+
 The IT87xx only updates its values each 1.5 seconds; reading it more often
 will do no harm, but will return 'old' values.
 
@@ -150,11 +146,38 @@ Fan speed control
 -----------------
 
 The fan speed control features are limited to manual PWM mode. Automatic
-"Smart Guardian" mode control handling is not implemented. However
-if you want to go for "manual mode" just write 1 to pwmN_enable.
+"Smart Guardian" mode control handling is only implemented for older chips
+(see below.) However if you want to go for "manual mode" just write 1 to
+pwmN_enable.
 
 If you are only able to control the fan speed with very small PWM values,
 try lowering the PWM base frequency (pwm1_freq). Depending on the fan,
 it may give you a somewhat greater control range. The same frequency is
 used to drive all fan outputs, which is why pwm2_freq and pwm3_freq are
 read-only.
+
+
+Automatic fan speed control (old interface)
+-------------------------------------------
+
+The driver supports the old interface to automatic fan speed control
+which is implemented by IT8705F chips up to revision F and IT8712F
+chips up to revision G.
+
+This interface implements 4 temperature vs. PWM output trip points.
+The PWM output of trip point 4 is always the maximum value (fan running
+at full speed) while the PWM output of the other 3 trip points can be
+freely chosen. The temperature of all 4 trip points can be freely chosen.
+Additionally, trip point 1 has an hysteresis temperature attached, to
+prevent fast switching between fan on and off.
+
+The chip automatically computes the PWM output value based on the input
+temperature, based on this simple rule: if the temperature value is
+between trip point N and trip point N+1 then the PWM output value is
+the one of trip point N. The automatic control mode is less flexible
+than the manual control mode, but it reacts faster, is more robust and
+doesn't use CPU cycles.
+
+Trip points must be set properly before switching to automatic fan speed
+control mode. The driver will perform basic integrity checks before
+actually switching to automatic control mode.
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90
index 93d8e3d55150..6a03dd4bcc94 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90
@@ -84,6 +84,10 @@ Supported chips:
     Addresses scanned: I2C 0x4c
     Datasheet: Publicly available at the Maxim website
                http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+  * Winbond/Nuvoton W83L771AWG/ASG
+    Prefix: 'w83l771'
+    Addresses scanned: I2C 0x4c
+    Datasheet: Not publicly available, can be requested from Nuvoton
 
 
 Author: Jean Delvare <khali@linux-fr.org>
@@ -147,6 +151,12 @@ MAX6680 and MAX6681:
   * Selectable address
   * Remote sensor type selection
 
+W83L771AWG/ASG
+  * The AWG and ASG variants only differ in package format.
+  * Filter and alert configuration register at 0xBF
+  * Diode ideality factor configuration (remote sensor) at 0xE3
+  * Moving average (depending on conversion rate)
+
 All temperature values are given in degrees Celsius. Resolution
 is 1.0 degree for the local temperature, 0.125 degree for the remote
 temperature, except for the MAX6657, MAX6658 and MAX6659 which have a
@@ -163,6 +173,18 @@ The lm90 driver will not update its values more frequently than every
 other second; reading them more often will do no harm, but will return
 'old' values.
 
+SMBus Alert Support
+-------------------
+
+This driver has basic support for SMBus alert. When an alert is received,
+the status register is read and the faulty temperature channel is logged.
+
+The Analog Devices chips (ADM1032 and ADT7461) do not implement the SMBus
+alert protocol properly so additional care is needed: the ALERT output is
+disabled when an alert is received, and is re-enabled only when the alarm
+is gone. Otherwise the chip would block alerts from other chips in the bus
+as long as the alarm is active.
+
 PEC Support
 -----------
 
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 81c0c59a60ea..e1bb5b261693 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -15,7 +15,8 @@ Supported adapters:
   * Intel 82801I (ICH9)
   * Intel EP80579 (Tolapai)
   * Intel 82801JI (ICH10)
-  * Intel PCH
+  * Intel 3400/5 Series (PCH)
+  * Intel Cougar Point (PCH)
    Datasheets: Publicly available at the Intel website
 
 Authors: 
diff --git a/Documentation/i2c/busses/i2c-parport b/Documentation/i2c/busses/i2c-parport
index dceaba1ad930..2461c7b53b2c 100644
--- a/Documentation/i2c/busses/i2c-parport
+++ b/Documentation/i2c/busses/i2c-parport
@@ -29,6 +29,9 @@ can be easily added when needed.
 Earlier kernels defaulted to type=0 (Philips).  But now, if the type
 parameter is missing, the driver will simply fail to initialize.
 
+SMBus alert support is available on adapters which have this line properly
+connected to the parallel port's interrupt pin.
+
 
 Building your own adapter
 -------------------------
diff --git a/Documentation/i2c/busses/i2c-parport-light b/Documentation/i2c/busses/i2c-parport-light
index 287436478520..bdc9cbb2e0f2 100644
--- a/Documentation/i2c/busses/i2c-parport-light
+++ b/Documentation/i2c/busses/i2c-parport-light
@@ -9,3 +9,14 @@ parport handling is not an option. The drawback is a reduced portability
 and the impossibility to daisy-chain other parallel port devices.                 
   
 Please see i2c-parport for documentation.
+
+Module parameters:
+
+* type: type of adapter (see i2c-parport or modinfo)
+
+* base: base I/O address
+  Default is 0x378 which is fairly common for parallel ports, at least on PC.
+
+* irq: optional IRQ
+  This must be passed if you want SMBus alert support, assuming your adapter
+  actually supports this.
diff --git a/Documentation/i2c/smbus-protocol b/Documentation/i2c/smbus-protocol
index 9df47441f0e7..7c19d1a2bea0 100644
--- a/Documentation/i2c/smbus-protocol
+++ b/Documentation/i2c/smbus-protocol
@@ -185,6 +185,22 @@ the protocol. All ARP communications use slave address 0x61 and
 require PEC checksums.
 
 
+SMBus Alert
+===========
+
+SMBus Alert was introduced in Revision 1.0 of the specification.
+
+The SMBus alert protocol allows several SMBus slave devices to share a
+single interrupt pin on the SMBus master, while still allowing the master
+to know which slave triggered the interrupt.
+
+This is implemented the following way in the Linux kernel:
+* I2C bus drivers which support SMBus alert should call
+  i2c_setup_smbus_alert() to setup SMBus alert support.
+* I2C drivers for devices which can trigger SMBus alerts should implement
+  the optional alert() callback.
+
+
 I2C Block Transactions
 ======================
 
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 0a74603eb671..5ebf5af1d716 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -74,6 +74,11 @@ structure at all.  You should use this to keep device-specific data.
         /* retrieve the value */
         void *i2c_get_clientdata(const struct i2c_client *client);
 
+Note that starting with kernel 2.6.34, you don't have to set the `data' field
+to NULL in remove() or if probe() failed anymore. The i2c-core does this
+automatically on these occasions. Those are also the only times the core will
+touch this field.
+
 
 Accessing the client
 ====================
@@ -318,8 +323,9 @@ Plain I2C communication
 These routines read and write some bytes from/to a client. The client
 contains the i2c address, so you do not have to include it. The second
 parameter contains the bytes to read/write, the third the number of bytes
-to read/write (must be less than the length of the buffer.) Returned is
-the actual number of bytes read/written.
+to read/write (must be less than the length of the buffer, also should be
+less than 64k since msg.len is u16.) Returned is the actual number of bytes
+read/written.
 
         int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msg,
                          int num);
diff --git a/Documentation/init.txt b/Documentation/init.txt
new file mode 100644
index 000000000000..535ad5e82b98
--- /dev/null
+++ b/Documentation/init.txt
@@ -0,0 +1,49 @@
+Explaining the dreaded "No init found." boot hang message
+=========================================================
+
+OK, so you've got this pretty unintuitive message (currently located
+in init/main.c) and are wondering what the H*** went wrong.
+Some high-level reasons for failure (listed roughly in order of execution)
+to load the init binary are:
+A) Unable to mount root FS
+B) init binary doesn't exist on rootfs
+C) broken console device
+D) binary exists but dependencies not available
+E) binary cannot be loaded
+
+Detailed explanations:
+0) Set "debug" kernel parameter (in bootloader config file or CONFIG_CMDLINE)
+   to get more detailed kernel messages.
+A) make sure you have the correct root FS type
+   (and root= kernel parameter points to the correct partition),
+   required drivers such as storage hardware (such as SCSI or USB!)
+   and filesystem (ext3, jffs2 etc.) are builtin (alternatively as modules,
+   to be pre-loaded by an initrd)
+C) Possibly a conflict in console= setup --> initial console unavailable.
+   E.g. some serial consoles are unreliable due to serial IRQ issues (e.g.
+   missing interrupt-based configuration).
+   Try using a different console= device or e.g. netconsole= .
+D) e.g. required library dependencies of the init binary such as
+   /lib/ld-linux.so.2 missing or broken. Use readelf -d <INIT>|grep NEEDED
+   to find out which libraries are required.
+E) make sure the binary's architecture matches your hardware.
+   E.g. i386 vs. x86_64 mismatch, or trying to load x86 on ARM hardware.
+   In case you tried loading a non-binary file here (shell script?),
+   you should make sure that the script specifies an interpreter in its shebang
+   header line (#!/...) that is fully working (including its library
+   dependencies). And before tackling scripts, better first test a simple
+   non-script binary such as /bin/sh and confirm its successful execution.
+   To find out more, add code to init/main.c to display kernel_execve()s
+   return values.
+
+Please extend this explanation whenever you find new failure causes
+(after all loading the init binary is a CRITICAL and hard transition step
+which needs to be made as painless as possible), then submit patch to LKML.
+Further TODOs:
+- Implement the various run_init_process() invocations via a struct array
+  which can then store the kernel_execve() result value and on failure
+  log it all by iterating over _all_ results (very important usability fix).
+- try to make the implementation itself more helpful in general,
+  e.g. by providing additional error messages at affected places.
+
+Andreas Mohr <andi at lisas period de>
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index a10c3b6ba7c4..56941ae1f5db 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -333,14 +333,14 @@ byte 0:
 byte 1:
 
    bit   7   6   5   4   3   2   1   0
-        x15 x14 x13 x12 x11 x10 x9  x8
+         .   .   .   .   .  x10 x9  x8
 
 byte 2:
 
    bit   7   6   5   4   3   2   1   0
         x7  x6  x5  x4  x4  x2  x1  x0
 
-         x15..x0 = absolute x value (horizontal)
+         x10..x0 = absolute x value (horizontal)
 
 byte 3:
 
@@ -350,14 +350,14 @@ byte 3:
 byte 4:
 
    bit   7   6   5   4   3   2   1   0
-        y15 y14 y13 y12 y11 y10 y8  y8
+         .   .   .   .   .   .  y9  y8
 
 byte 5:
 
    bit   7   6   5   4   3   2   1   0
         y7  y6  y5  y4  y3  y2  y1  y0
 
-         y15..y0 = absolute y value (vertical)
+         y9..y0 = absolute y value (vertical)
 
 
 4.2.2 Two finger touch
diff --git a/Documentation/input/multi-touch-protocol.txt b/Documentation/input/multi-touch-protocol.txt
index 8490480ce432..c0fc1c75fd88 100644
--- a/Documentation/input/multi-touch-protocol.txt
+++ b/Documentation/input/multi-touch-protocol.txt
@@ -68,6 +68,22 @@ like:
    SYN_MT_REPORT
    SYN_REPORT
 
+Here is the sequence after lifting one of the fingers:
+
+   ABS_MT_POSITION_X
+   ABS_MT_POSITION_Y
+   SYN_MT_REPORT
+   SYN_REPORT
+
+And here is the sequence after lifting the remaining finger:
+
+   SYN_MT_REPORT
+   SYN_REPORT
+
+If the driver reports one of BTN_TOUCH or ABS_PRESSURE in addition to the
+ABS_MT events, the last SYN_MT_REPORT event may be omitted. Otherwise, the
+last SYN_REPORT will be dropped by the input core, resulting in no
+zero-finger event reaching userland.
 
 Event Semantics
 ---------------
@@ -217,11 +233,6 @@ where examples can be found.
 difference between the contact position and the approaching tool position
 could be used to derive tilt.
 [2] The list can of course be extended.
-[3] The multi-touch X driver is currently in the prototyping stage. At the
-time of writing (April 2009), the MT protocol is not yet merged, and the
-prototype implements finger matching, basic mouse support and two-finger
-scrolling. The project aims at improving the quality of current multi-touch
-functionality available in the Synaptics X driver, and in addition
-implement more advanced gestures.
+[3] Multitouch X driver project: http://bitmath.org/code/multitouch/.
 [4] See the section on event computation.
 [5] See the section on finger tracking.
diff --git a/Documentation/input/rotary-encoder.txt b/Documentation/input/rotary-encoder.txt
index 3a6aec40c0b0..8b4129de1d2d 100644
--- a/Documentation/input/rotary-encoder.txt
+++ b/Documentation/input/rotary-encoder.txt
@@ -75,7 +75,7 @@ and the number of steps or will clamp at the maximum and zero depending on
 the configuration.
 
 Because GPIO to IRQ mapping is platform specific, this information must
-be given in seperately to the driver. See the example below.
+be given in separately to the driver. See the example below.
 
 ---------<snip>---------
 
diff --git a/Documentation/input/sentelic.txt b/Documentation/input/sentelic.txt
index f7160a2fb6a2..b35affd5c649 100644
--- a/Documentation/input/sentelic.txt
+++ b/Documentation/input/sentelic.txt
@@ -1,5 +1,5 @@
-Copyright (C) 2002-2008 Sentelic Corporation.
-Last update: Oct-31-2008
+Copyright (C) 2002-2010 Sentelic Corporation.
+Last update: Jan-13-2010
 
 ==============================================================================
 * Finger Sensing Pad Intellimouse Mode(scrolling wheel, 4th and 5th buttons)
@@ -44,7 +44,7 @@ B) MSID 6: Horizontal and Vertical scrolling.
 Packet 1
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
-  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|l|r|u|d|
+  1   |Y|X|y|x|1|M|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 | | |B|F|r|l|u|d|
       |---------------|     |---------------|    |---------------|    |---------------|
 
 Byte 1: Bit7 => Y overflow
@@ -59,15 +59,15 @@ Byte 2: X Movement(9-bit 2's complement integers)
 Byte 3: Y Movement(9-bit 2's complement integers)
 Byte 4: Bit0 => the Vertical scrolling movement downward.
         Bit1 => the Vertical scrolling movement upward.
-        Bit2 => the Vertical scrolling movement rightward.
-        Bit3 => the Vertical scrolling movement leftward.
+        Bit2 => the Horizontal scrolling movement leftward.
+        Bit3 => the Horizontal scrolling movement rightward.
         Bit4 => 1 = 4th mouse button is pressed, Forward one page.
                 0 = 4th mouse button is not pressed.
         Bit5 => 1 = 5th mouse button is pressed, Backward one page.
                 0 = 5th mouse button is not pressed.
 
 C) MSID 7:
-# FSP uses 2 packets(8 Bytes) data to represent Absolute Position
+# FSP uses 2 packets (8 Bytes) to represent Absolute Position.
   so we have PACKET NUMBER to identify packets.
   If PACKET NUMBER is 0, the packet is Packet 1.
   If PACKET NUMBER is 1, the packet is Packet 2.
@@ -129,7 +129,7 @@ Byte 3: Message Type => 0x00 (Disabled)
 Byte 4: Bit7~Bit0 => Don't Care
 
 ==============================================================================
-* Absolute position for STL3888-A0.
+* Absolute position for STL3888-Ax.
 ==============================================================================
 Packet 1 (ABSOLUTE POSITION)
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
@@ -179,14 +179,14 @@ Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
         Bit5~Bit4 => y2_g
         Bit7~Bit6 => x2_g
 
-Notify Packet for STL3888-A0
+Notify Packet for STL3888-Ax
    Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
 BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
   1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|d|u|0|0|0|0|
       |---------------|     |---------------|    |---------------|    |---------------|
 
 Byte 1: Bit7~Bit6 => 00, Normal data packet
-                  => 01, Absolute coordination packet
+                  => 01, Absolute coordinates packet
                   => 10, Notify packet
         Bit5 => 1
         Bit4 => when in absolute coordinates mode (valid when EN_PKT_GO is 1):
@@ -205,15 +205,106 @@ Byte 4: Bit7 => scroll right button
         Bit6 => scroll left button
         Bit5 => scroll down button
         Bit4 => scroll up button
-            * Note that if gesture and additional button (Bit4~Bit7)
-              happen at the same time, the button information will not
-              be sent.
+            * Note that if gesture and additional buttoni (Bit4~Bit7)
+              happen at the same time, the button information will not
+              be sent.
+        Bit3~Bit0 => Reserved
+
+Sample sequence of Multi-finger, Multi-coordinate mode:
+
+        notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
+        abs pkt 2, ..., notify packet (valid bit == 0)
+
+==============================================================================
+* Absolute position for STL3888-B0.
+==============================================================================
+Packet 1(ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|0|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordinates packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+
+Packet 2 (ABSOLUTE POSITION)
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |0|1|V|F|1|1|R|L|  2  |X|X|X|X|X|X|X|X|  3 |Y|Y|Y|Y|Y|Y|Y|Y|  4 |r|l|u|d|X|X|Y|Y|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => Valid bit, 0 means that the coordinate is invalid or finger up.
+                When both fingers are up, the last two reports have zero valid
+                bit.
+        Bit4 => finger up/down information. 1: finger down, 0: finger up.
+        Bit3 => 1
+        Bit2 => finger index, 0 is the first finger, 1 is the second finger.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: X coordinate (xpos[9:2])
+Byte 3: Y coordinate (ypos[9:2])
+Byte 4: Bit1~Bit0 => Y coordinate (xpos[1:0])
+        Bit3~Bit2 => X coordinate (ypos[1:0])
+        Bit4 => scroll down button
+        Bit5 => scroll up button
+        Bit6 => scroll left button
+        Bit7 => scroll right button
+
+Notify Packet for STL3888-B0
+   Bit 7 6 5 4 3 2 1 0       7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0      7 6 5 4 3 2 1 0
+BYTE  |---------------|BYTE |---------------|BYTE|---------------|BYTE|---------------|
+  1   |1|0|1|P|1|M|R|L|  2  |C|C|C|C|C|C|C|C|  3 |0|0|F|F|0|0|0|i|  4 |r|l|u|d|0|0|0|0|
+      |---------------|     |---------------|    |---------------|    |---------------|
+
+Byte 1: Bit7~Bit6 => 00, Normal data packet
+                  => 01, Absolute coordination packet
+                  => 10, Notify packet
+        Bit5 => 1
+        Bit4 => when in absolute coordinate mode (valid when EN_PKT_GO is 1):
+                0: left button is generated by the on-pad command
+                1: left button is generated by the external button
+        Bit3 => 1
+        Bit2 => Middle Button, 1 is pressed, 0 is not pressed.
+        Bit1 => Right Button, 1 is pressed, 0 is not pressed.
+        Bit0 => Left Button, 1 is pressed, 0 is not pressed.
+Byte 2: Message Type => 0xB7 (Multi Finger, Multi Coordinate mode)
+Byte 3: Bit7~Bit6 => Don't care
+        Bit5~Bit4 => Number of fingers
+        Bit3~Bit1 => Reserved
+        Bit0 => 1: enter gesture mode; 0: leaving gesture mode
+Byte 4: Bit7 => scroll right button
+        Bit6 => scroll left button
+        Bit5 => scroll up button
+        Bit4 => scroll down button
+            * Note that if gesture and additional button(Bit4~Bit7)
+              happen at the same time, the button information will not
+              be sent.
         Bit3~Bit0 => Reserved
 
 Sample sequence of Multi-finger, Multi-coordinate mode:
 
         notify packet (valid bit == 1), abs pkt 1, abs pkt 2, abs pkt 1,
-        abs pkt 2, ..., notify packet(valid bit == 0)
+        abs pkt 2, ..., notify packet (valid bit == 0)
 
 ==============================================================================
 * FSP Enable/Disable packet
@@ -409,7 +500,8 @@ offset	width		default	r/w	name
                                         0: read only, 1: read/write enable
         (Note that following registers does not require clock gating being
         enabled prior to write: 05 06 07 08 09 0c 0f 10 11 12 16 17 18 23 2e
-        40 41 42 43.)
+        40 41 42 43.  In addition to that, this bit must be 1 when gesture
+        mode is enabled)
 
 0x31                            RW      on-pad command detection
         bit7            0       RW      on-pad command left button down tag
@@ -463,6 +555,10 @@ offset	width		default	r/w	name
         absolute coordinates; otherwise, host only receives packets with
         relative coordinate.)
 
+        bit7            0       RW      EN_PS2_F2: PS/2 gesture mode 2nd
+                                        finger packet enable
+                                        0: disable, 1: enable
+
 0x43                            RW      on-pad control
         bit0            0       RW      on-pad control enable
                                         0: disable, 1: enable
diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt
index f40a1f030019..87c8990dbbd9 100644
--- a/Documentation/intel_txt.txt
+++ b/Documentation/intel_txt.txt
@@ -161,13 +161,15 @@ o  In order to put a system into any of the sleep states after a TXT
       has been restored, it will restore the TPM PCRs and then
       transfer control back to the kernel's S3 resume vector.
       In order to preserve system integrity across S3, the kernel
-      provides tboot with a set of memory ranges (kernel
-      code/data/bss, S3 resume code, and AP trampoline) that tboot
-      will calculate a MAC (message authentication code) over and then
-      seal with the TPM.  On resume and once the measured environment
-      has been re-established, tboot will re-calculate the MAC and
-      verify it against the sealed value.  Tboot's policy determines
-      what happens if the verification fails.
+      provides tboot with a set of memory ranges (RAM and RESERVED_KERN
+      in the e820 table, but not any memory that BIOS might alter over
+      the S3 transition) that tboot will calculate a MAC (message
+      authentication code) over and then seal with the TPM. On resume
+      and once the measured environment has been re-established, tboot
+      will re-calculate the MAC and verify it against the sealed value.
+      Tboot's policy determines what happens if the verification fails.
+      Note that the c/s 194 of tboot which has the new MAC code supports
+      this.
 
 That's pretty much it for TXT support.
 
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 35cf64d4436d..dd5806f4fcc4 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -139,7 +139,6 @@ Code  Seq#(hex)	Include File		Comments
 'K'     all     linux/kd.h
 'L'     00-1F   linux/loop.h            conflict!
 'L'     10-1F   drivers/scsi/mpt2sas/mpt2sas_ctl.h      conflict!
-'L'     20-2F   linux/usb/vstusb.h
 'L'     E0-FF   linux/ppdd.h            encrypted disk device driver
                                         <http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'     all     linux/soundcard.h       conflict!
@@ -292,6 +291,7 @@ Code  Seq#(hex)	Include File		Comments
 0x92    00-0F   drivers/usb/mon/mon_bin.c
 0x93    60-7F   linux/auto_fs.h
 0x94    all     fs/btrfs/ioctl.h
+0x97    00-7F   fs/ceph/ioctl.h         Ceph file system
 0x99    00-0F                           537-Addinboard driver
                                         <mailto:buk@buks.ipn.de>
 0xA0    all     linux/sdp/sdp.h         Industrial Device Project
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 5fe8de5cc727..f172091fb7cd 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -149,10 +149,11 @@ char *(*procinfo)(struct capi_ctr *ctrlr)
         pointer to a callback function returning the entry for the device in
         the CAPI controller info table, /proc/capi/controller
 
-read_proc_t *ctr_read_proc
-        pointer to the read_proc callback function for the device's proc file
-        system entry, /proc/capi/controllers/<n>; will be called with a
-        pointer to the device's capi_ctr structure as the last (data) argument
+const struct file_operations *proc_fops
+        pointers to callback functions for the device's proc file
+        system entry, /proc/capi/controllers/<n>; pointer to the device's
+        capi_ctr structure is available from struct proc_dir_entry::data
+        which is available from struct inode.
 
 Note: Callback functions except send_message() are never called in interrupt
 context.
diff --git a/Documentation/isdn/README.gigaset b/Documentation/isdn/README.gigaset
index 794941fc9493..e472df842323 100644
--- a/Documentation/isdn/README.gigaset
+++ b/Documentation/isdn/README.gigaset
@@ -292,10 +292,10 @@ GigaSet 307x Device Driver
         to /etc/modprobe.d/gigaset, /etc/modprobe.conf.local or a similar file.
 
      Problem:
-        Your isdn script aborts with a message about isdnlog.
+        The isdnlog program emits error messages or just doesn't work.
      Solution:
-        Try deactivating (or commenting out) isdnlog. This driver does not
-        support it.
+        Isdnlog supports only the HiSax driver. Do not attempt to use it with
+        other drivers such as Gigaset.
 
      Problem:
         You have two or more DECT data adapters (M101/M105) and only the
@@ -321,8 +321,8 @@ GigaSet 307x Device Driver
      writing an appropriate value to /sys/module/gigaset/parameters/debug, e.g.
         echo 0 > /sys/module/gigaset/parameters/debug
      switches off debugging output completely,
-        echo 0x10a020 > /sys/module/gigaset/parameters/debug
-     enables the standard set of debugging output messages. These values are
+        echo 0x302020 > /sys/module/gigaset/parameters/debug
+     enables a reasonable set of debugging output messages. These values are
      bit patterns where every bit controls a certain type of debugging output.
      See the constants DEBUG_* in the source file gigaset.h for details.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e7848a0d99eb..567b7a8eb878 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -54,6 +54,7 @@ parameter is applicable:
         IMA     Integrity measurement architecture is enabled.
         IOSCHED More than one I/O scheduler is enabled.
         IP_PNP  IP DHCP, BOOTP, or RARP is enabled.
+        IPV6    IPv6 support is enabled.
         ISAPNP  ISA PnP code is enabled.
         ISDN    Appropriate ISDN support is enabled.
         JOY     Appropriate joystick support is enabled.
@@ -199,10 +200,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         acpi_display_output=video
                         See above.
 
-        acpi_early_pdc_eval     [HW,ACPI] Evaluate processor _PDC methods
-                                early. Needed on some platforms to properly
-                                initialize the EC.
-
         acpi_irq_balance [HW,ACPI]
                         ACPI will balance active IRQs
                         default in APIC mode
@@ -323,15 +320,12 @@ and is between 256 and 4096 characters. It is defined in the file
         amd_iommu=      [HW,X86-84]
                         Pass parameters to the AMD IOMMU driver in the system.
                         Possible values are:
-                        isolate - enable device isolation (each device, as far
-                                  as possible, will get its own protection
-                                  domain) [default]
-                        share - put every device behind one IOMMU into the
-                                same protection domain
                         fullflush - enable flushing of IO/TLB entries when
                                     they are unmapped. Otherwise they are
                                     flushed before they will be reused, which
                                     is a lot of faster
+                        off       - do not initialize any AMD IOMMU found in
+                                    the system
 
         amijoy.map=     [HW,JOY] Amiga joystick support
                         Map of devices attached to JOY0DAT and JOY1DAT
@@ -356,6 +350,9 @@ and is between 256 and 4096 characters. It is defined in the file
                         Change the amount of debugging information output
                         when initialising the APIC and IO-APIC components.
 
+        autoconf=       [IPV6]
+                        See Documentation/networking/ipv6.txt.
+
         show_lapic=     [APIC,X86] Advanced Programmable Interrupt Controller
                         Limit apic dumping. The parameter defines the maximal
                         number of local apics being dumped. Also it is possible
@@ -638,6 +635,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         See drivers/char/README.epca and
                         Documentation/serial/digiepca.txt.
 
+        disable=        [IPV6]
+                        See Documentation/networking/ipv6.txt.
+
+        disable_ipv6=   [IPV6]
+                        See Documentation/networking/ipv6.txt.
+
         disable_mtrr_cleanup [X86]
                         The kernel tries to adjust MTRR layout from continuous
                         to discrete, to make X server driver able to add WB
@@ -783,8 +786,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         as early as possible in order to facilitate early
                         boot debugging.
 
-        ftrace_dump_on_oops
+        ftrace_dump_on_oops[=orig_cpu]
                         [FTRACE] will dump the trace buffers on oops.
+                        If no parameter is passed, ftrace will dump
+                        buffers of all CPUs, but if you pass orig_cpu, it will
+                        dump only the buffer of the CPU that triggered the
+                        oops.
 
         ftrace_filter=[function-list]
                         [FTRACE] Limit the functions traced by the function
@@ -1193,7 +1200,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
         libata.force=   [LIBATA] Force configurations.  The format is comma
                         separated list of "[ID:]VAL" where ID is
-                        PORT[:DEVICE].  PORT and DEVICE are decimal numbers
+                        PORT[.DEVICE].  PORT and DEVICE are decimal numbers
                         matching port, link or device.  Basically, it matches
                         the ATA ID string printed on console by libata.  If
                         the whole ID part is omitted, the last PORT and DEVICE
@@ -1738,6 +1745,9 @@ and is between 256 and 4096 characters. It is defined in the file
         nomfgpt         [X86-32] Disable Multi-Function General Purpose
                         Timer usage (for AMD Geode machines).
 
+        nopat           [X86] Disable PAT (page attribute table extension of
+                        pagetables) support.
+
         norandmaps      Don't use address space randomization.  Equivalent to
                         echo 0 > /proc/sys/kernel/randomize_va_space
 
@@ -1781,6 +1791,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         purges which is reported from either PAL_VM_SUMMARY or
                         SAL PALO.
 
+        nr_cpus=        [SMP] Maximum number of processors that an SMP kernel
+                        could support.  nr_cpus=n : n >= 1 limits the kernel to
+                        supporting 'n' processors. Later in runtime you can not
+                        use hotplug cpu feature to put more cpu back to online.
+                        just like you compile the kernel NR_CPUS=n
+
         nr_uarts=       [SERIAL] maximum number of UARTs to be registered.
 
         numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA.
@@ -1948,8 +1964,12 @@ and is between 256 and 4096 characters. It is defined in the file
                                 IRQ routing is enabled.
                 noacpi          [X86] Do not use ACPI for IRQ routing
                                 or for PCI scanning.
-                use_crs         [X86] Use _CRS for PCI resource
-                                allocation.
+                use_crs         [X86] Use PCI host bridge window information
+                                from ACPI.  On BIOSes from 2008 or later, this
+                                is enabled by default.  If you need to use this,
+                                please report a bug.
+                nocrs           [X86] Ignore PCI host bridge windows from ACPI.
+                                If you need to use this, please report a bug.
                 routeirq        Do IRQ routing for all PCI devices.
                                 This is normally done in pci_enable_device(),
                                 so this option is a temporary workaround
@@ -1998,6 +2018,14 @@ and is between 256 and 4096 characters. It is defined in the file
                 force   Enable ASPM even on devices that claim not to support it.
                         WARNING: Forcing ASPM on may cause system lockups.
 
+        pcie_pme=       [PCIE,PM] Native PCIe PME signaling options:
+                off     Do not use native PCIe PME signaling.
+                force   Use native PCIe PME signaling even if the BIOS refuses
+                        to allow the kernel to control the relevant PCIe config
+                        registers.
+                nomsi   Do not use MSI for native PCIe PME signaling (this makes
+                        all PCIe root ports use INTx for everything).
+
         pcmv=           [HW,PCMCIA] BadgePAD 4
 
         pd.             [PARIDE]
@@ -2703,6 +2731,13 @@ and is between 256 and 4096 characters. It is defined in the file
                                         medium is write-protected).
                         Example: quirks=0419:aaf5:rl,0421:0433:rc
 
+        userpte=
+                        [X86] Flags controlling user PTE allocations.
+
+                                nohigh = do not allocate PTE pages in
+                                        HIGHMEM regardless of setting
+                                        of CONFIG_HIGHPTE.
+
         vdso=           [X86,SH]
                         vdso=2: enable compat VDSO (default with COMPAT_VDSO)
                         vdso=1: enable VDSO (default)
@@ -2796,6 +2831,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         default x2apic cluster mode on platforms
                         supporting x2apic.
 
+        x86_mrst_timer= [X86-32,APBT]
+                        Choose timer option for x86 Moorestown MID platform.
+                        Two valid options are apbt timer only and lapic timer
+                        plus one apbt timer for broadcast timer.
+                        x86_mrst_timer=apbt_only | lapic_and_apbt
+
         xd=             [HW,XT] Original XT pre-IDE (RLL encoded) disks.
         xd_geo=         See header of drivers/block/xd.c.
 
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index c79ab996dada..3ab2472509cb 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -59,37 +59,56 @@ nice to have in other objects.  The C language does not allow for the
 direct expression of inheritance, so other techniques - such as structure
 embedding - must be used.
 
-So, for example, the UIO code has a structure that defines the memory
-region associated with a uio device:
+(As an aside, for those familiar with the kernel linked list implementation,
+this is analogous as to how "list_head" structs are rarely useful on
+their own, but are invariably found embedded in the larger objects of
+interest.)
 
-struct uio_mem {
+So, for example, the UIO code in drivers/uio/uio.c has a structure that
+defines the memory region associated with a uio device:
+
+    struct uio_map {
         struct kobject kobj;
-        unsigned long addr;
-        unsigned long size;
-        int memtype;
-        void __iomem *internal_addr;
-};
+        struct uio_mem *mem;
+    };
 
-If you have a struct uio_mem structure, finding its embedded kobject is
+If you have a struct uio_map structure, finding its embedded kobject is
 just a matter of using the kobj member.  Code that works with kobjects will
 often have the opposite problem, however: given a struct kobject pointer,
 what is the pointer to the containing structure?  You must avoid tricks
 (such as assuming that the kobject is at the beginning of the structure)
 and, instead, use the container_of() macro, found in <linux/kernel.h>:
 
-        container_of(pointer, type, member)
+    container_of(pointer, type, member)
+
+where:
+
+  * "pointer" is the pointer to the embedded kobject,
+  * "type" is the type of the containing structure, and
+  * "member" is the name of the structure field to which "pointer" points.
+
+The return value from container_of() is a pointer to the corresponding
+container type. So, for example, a pointer "kp" to a struct kobject
+embedded *within* a struct uio_map could be converted to a pointer to the
+*containing* uio_map structure with:
+
+    struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
+
+For convenience, programmers often define a simple macro for "back-casting"
+kobject pointers to the containing type.  Exactly this happens in the
+earlier drivers/uio/uio.c, as you can see here:
+
+    struct uio_map {
+        struct kobject kobj;
+        struct uio_mem *mem;
+    };
 
-where pointer is the pointer to the embedded kobject, type is the type of
-the containing structure, and member is the name of the structure field to
-which pointer points.  The return value from container_of() is a pointer to
-the given type. So, for example, a pointer "kp" to a struct kobject
-embedded within a struct uio_mem could be converted to a pointer to the
-containing uio_mem structure with:
+    #define to_map(map) container_of(map, struct uio_map, kobj)
 
-    struct uio_mem *u_mem = container_of(kp, struct uio_mem, kobj);
+where the macro argument "map" is a pointer to the struct kobject in
+question.  That macro is subsequently invoked with:
 
-Programmers often define a simple macro for "back-casting" kobject pointers
-to the containing type.
+    struct uio_map *map = to_map(kobj);
 
 
 Initialization of kobjects
@@ -266,7 +285,7 @@ kobj_type:
 
     struct kobj_type {
             void (*release)(struct kobject *);
-            struct sysfs_ops    *sysfs_ops;
+            const struct sysfs_ops *sysfs_ops;
             struct attribute    **default_attrs;
     };
 
@@ -387,4 +406,5 @@ called, and the objects in the former circle release each other.
 Example code to copy from
 
 For a more complete example of using ksets and kobjects properly, see the
-sample/kobject/kset-example.c code.
+example programs samples/kobject/{kobject-example.c,kset-example.c},
+which will be built as loadable modules if you select CONFIG_SAMPLE_KOBJECT.
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 053037a1fe6d..61c291cddf18 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -1,6 +1,7 @@
 Title   : Kernel Probes (Kprobes)
 Authors : Jim Keniston <jkenisto@us.ibm.com>
-        : Prasanna S Panchamukhi <prasanna@in.ibm.com>
+        : Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+        : Masami Hiramatsu <mhiramat@redhat.com>
 
 CONTENTS
 
@@ -15,6 +16,7 @@ CONTENTS
 9. Jprobes Example
 10. Kretprobes Example
 Appendix A: The kprobes debugfs interface
+Appendix B: The kprobes sysctl interface
 
 1. Concepts: Kprobes, Jprobes, Return Probes
 
@@ -42,13 +44,13 @@ registration/unregistration of a group of *probes. These functions
 can speed up unregistration process when you have to unregister
 a lot of probes at once.
 
-The next three subsections explain how the different types of
-probes work.  They explain certain things that you'll need to
-know in order to make the best use of Kprobes -- e.g., the
-difference between a pre_handler and a post_handler, and how
-to use the maxactive and nmissed fields of a kretprobe.  But
-if you're in a hurry to start using Kprobes, you can skip ahead
-to section 2.
+The next four subsections explain how the different types of
+probes work and how jump optimization works.  They explain certain
+things that you'll need to know in order to make the best use of
+Kprobes -- e.g., the difference between a pre_handler and
+a post_handler, and how to use the maxactive and nmissed fields of
+a kretprobe.  But if you're in a hurry to start using Kprobes, you
+can skip ahead to section 2.
 
 1.1 How Does a Kprobe Work?
 
@@ -161,13 +163,123 @@ In case probed function is entered but there is no kretprobe_instance
 object available, then in addition to incrementing the nmissed count,
 the user entry_handler invocation is also skipped.
 
+1.4 How Does Jump Optimization Work?
+
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
+the "debug.kprobes_optimization" kernel parameter is set to 1 (see
+sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
+instruction instead of a breakpoint instruction at each probepoint.
+
+1.4.1 Init a Kprobe
+
+When a probe is registered, before attempting this optimization,
+Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
+address. So, even if it's not possible to optimize this particular
+probepoint, there'll be a probe there.
+
+1.4.2 Safety Check
+
+Before optimizing a probe, Kprobes performs the following safety checks:
+
+- Kprobes verifies that the region that will be replaced by the jump
+instruction (the "optimized region") lies entirely within one function.
+(A jump instruction is multiple bytes, and so may overlay multiple
+instructions.)
+
+- Kprobes analyzes the entire function and verifies that there is no
+jump into the optimized region.  Specifically:
+  - the function contains no indirect jump;
+  - the function contains no instruction that causes an exception (since
+  the fixup code triggered by the exception could jump back into the
+  optimized region -- Kprobes checks the exception tables to verify this);
+  and
+  - there is no near jump to the optimized region (other than to the first
+  byte).
+
+- For each instruction in the optimized region, Kprobes verifies that
+the instruction can be executed out of line.
+
+1.4.3 Preparing Detour Buffer
+
+Next, Kprobes prepares a "detour" buffer, which contains the following
+instruction sequence:
+- code to push the CPU's registers (emulating a breakpoint trap)
+- a call to the trampoline code which calls user's probe handlers.
+- code to restore registers
+- the instructions from the optimized region
+- a jump back to the original execution path.
+
+1.4.4 Pre-optimization
+
+After preparing the detour buffer, Kprobes verifies that none of the
+following situations exist:
+- The probe has either a break_handler (i.e., it's a jprobe) or a
+post_handler.
+- Other instructions in the optimized region are probed.
+- The probe is disabled.
+In any of the above cases, Kprobes won't start optimizing the probe.
+Since these are temporary situations, Kprobes tries to start
+optimizing it again if the situation is changed.
+
+If the kprobe can be optimized, Kprobes enqueues the kprobe to an
+optimizing list, and kicks the kprobe-optimizer workqueue to optimize
+it.  If the to-be-optimized probepoint is hit before being optimized,
+Kprobes returns control to the original instruction path by setting
+the CPU's instruction pointer to the copied code in the detour buffer
+-- thus at least avoiding the single-step.
+
+1.4.5 Optimization
+
+The Kprobe-optimizer doesn't insert the jump instruction immediately;
+rather, it calls synchronize_sched() for safety first, because it's
+possible for a CPU to be interrupted in the middle of executing the
+optimized region(*).  As you know, synchronize_sched() can ensure
+that all interruptions that were active when synchronize_sched()
+was called are done, but only if CONFIG_PREEMPT=n.  So, this version
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
+
+After that, the Kprobe-optimizer calls stop_machine() to replace
+the optimized region with a jump instruction to the detour buffer,
+using text_poke_smp().
+
+1.4.6 Unoptimization
+
+When an optimized kprobe is unregistered, disabled, or blocked by
+another kprobe, it will be unoptimized.  If this happens before
+the optimization is complete, the kprobe is just dequeued from the
+optimized list.  If the optimization has been done, the jump is
+replaced with the original code (except for an int3 breakpoint in
+the first byte) by using text_poke_smp().
+
+(*)Please imagine that the 2nd instruction is interrupted and then
+the optimizer replaces the 2nd instruction with the jump *address*
+while the interrupt handler is running. When the interrupt
+returns to original address, there is no valid instruction,
+and it causes an unexpected result.
+
+(**)This optimization-safety checking may be replaced with the
+stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+kernel.
+
+NOTE for geeks:
+The jump optimization changes the kprobe's pre_handler behavior.
+Without optimization, the pre_handler can change the kernel's execution
+path by changing regs->ip and returning 1.  However, when the probe
+is optimized, that modification is ignored.  Thus, if you want to
+tweak the kernel's execution path, you need to suppress optimization,
+using one of the following techniques:
+- Specify an empty function for the kprobe's post_handler or break_handler.
+ or
+- Execute 'sysctl -w debug.kprobes_optimization=n'
+
 2. Architectures Supported
 
 Kprobes, jprobes, and return probes are implemented on the following
 architectures:
 
-- i386
-- x86_64 (AMD-64, EM64T)
+- i386 (Supports jump optimization)
+- x86_64 (AMD-64, EM64T) (Supports jump optimization)
 - ppc64
 - ia64 (Does not support probes on instruction slot1.)
 - sparc64 (Return probes not yet implemented.)
@@ -389,7 +501,10 @@ the probe which has been registered.
 
 Kprobes allows multiple probes at the same address.  Currently,
 however, there cannot be multiple jprobes on the same function at
-the same time.
+the same time.  Also, a probepoint for which there is a jprobe or
+a post_handler cannot be optimized.  So if you install a jprobe,
+or a kprobe with a post_handler, at an optimized probepoint, the
+probepoint will be unoptimized automatically.
 
 In general, you can install a probe anywhere in the kernel.
 In particular, you can probe interrupt handlers.  Known exceptions
@@ -453,6 +568,38 @@ reason, Kprobes doesn't support return probes (or kprobes or jprobes)
 on the x86_64 version of __switch_to(); the registration functions
 return -EINVAL.
 
+On x86/x86-64, since the Jump Optimization of Kprobes modifies
+instructions widely, there are some limitations to optimization. To
+explain it, we introduce some terminology. Imagine a 3-instruction
+sequence consisting of a two 2-byte instructions and one 3-byte
+instruction.
+
+        IA
+         |
+[-2][-1][0][1][2][3][4][5][6][7]
+        [ins1][ins2][  ins3 ]
+        [<-     DCR       ->]
+           [<- JTPR ->]
+
+ins1: 1st Instruction
+ins2: 2nd Instruction
+ins3: 3rd Instruction
+IA:  Insertion Address
+JTPR: Jump Target Prohibition Region
+DCR: Detoured Code Region
+
+The instructions in DCR are copied to the out-of-line buffer
+of the kprobe, because the bytes in DCR are replaced by
+a 5-byte jump instruction. So there are several limitations.
+
+a) The instructions in DCR must be relocatable.
+b) The instructions in DCR must not include a call instruction.
+c) JTPR must not be targeted by any jump or call instruction.
+d) DCR must not straddle the border betweeen functions.
+
+Anyway, these limitations are checked by the in-kernel instruction
+decoder, so you don't need to worry about that.
+
 6. Probe Overhead
 
 On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
@@ -476,6 +623,19 @@ k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
 ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
 k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
 
+6.1 Optimized Probe Overhead
+
+Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
+process. Here are sample overhead figures (in usec) for x86 architectures.
+k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+
+i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+
+x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+
 7. TODO
 
 a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
@@ -523,7 +683,8 @@ is also specified. Following columns show probe status. If the probe is on
 a virtual address that is no longer valid (module init sections, module
 virtual addresses that correspond to modules that've been unloaded),
 such probes are marked with [GONE]. If the probe is temporarily disabled,
-such probes are marked with [DISABLED].
+such probes are marked with [DISABLED]. If the probe is optimized, it is
+marked with [OPTIMIZED].
 
 /sys/kernel/debug/kprobes/enabled: Turn kprobes ON/OFF forcibly.
 
@@ -533,3 +694,19 @@ registered probes will be disarmed, till such time a "1" is echoed to this
 file. Note that this knob just disarms and arms all kprobes and doesn't
 change each probe's disabling state. This means that disabled kprobes (marked
 [DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
+
+
+Appendix B: The kprobes sysctl interface
+
+/proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
+
+When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
+a knob to globally and forcibly turn jump optimization (see section
+1.4) ON or OFF. By default, jump optimization is allowed (ON).
+If you echo "0" to this file or set "debug.kprobes_optimization" to
+0 via sysctl, all optimized probes will be unoptimized, and any new
+probes registered after that will not be optimized.  Note that this
+knob *changes* the optimized state. This means that optimized probes
+(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+removed). If the knob is turned on, they will be optimized again.
+
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 2811e452f756..c6416a398163 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -23,12 +23,12 @@ of a virtual machine.  The ioctls belong to three classes
    Only run vcpu ioctls from the same thread that was used to create the
    vcpu.
 
-2. File descritpors
+2. File descriptors
 
 The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
-handle will create a VM file descripror which can be used to issue VM
+handle will create a VM file descriptor which can be used to issue VM
 ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
 and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
 fd can be used to control the vcpu, including the important task of
@@ -643,7 +643,7 @@ Type: vm ioctl
 Parameters: struct kvm_clock_data (in)
 Returns: 0 on success, -1 on error
 
-Sets the current timestamp of kvmclock to the valued specific in its parameter.
+Sets the current timestamp of kvmclock to the value specified in its parameter.
 In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
 such as migration.
 
@@ -795,11 +795,11 @@ Unused.
                         __u64 data_offset; /* relative to kvm_run start */
                 } io;
 
-If exit_reason is KVM_EXIT_IO_IN or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_IO, then the vcpu has
 executed a port I/O instruction which could not be satisfied by kvm.
 data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
 where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a patcked array.
+KVM_RUN invocation (KVM_EXIT_IO_IN).  Data format is a packed array.
 
                 struct {
                         struct kvm_debug_exit_arch arch;
@@ -815,7 +815,7 @@ Unused.
                         __u8  is_write;
                 } mmio;
 
-If exit_reason is KVM_EXIT_MMIO or KVM_EXIT_IO_OUT, then the vcpu has
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
 executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX
index ee5692b26dd4..fa688538e757 100644
--- a/Documentation/laptops/00-INDEX
+++ b/Documentation/laptops/00-INDEX
@@ -2,6 +2,12 @@
         - This file
 acer-wmi.txt
         - information on the Acer Laptop WMI Extras driver.
+asus-laptop.txt
+        - information on the Asus Laptop Extras driver.
+disk-shock-protection.txt
+        - information on hard disk shock protection.
+dslm.c
+        - Simple Disk Sleep Monitor program
 laptop-mode.txt
         - how to conserve battery power using laptop-mode.
 sony-laptop.txt
diff --git a/Documentation/laptops/Makefile b/Documentation/laptops/Makefile
new file mode 100644
index 000000000000..5cb144af3c09
--- /dev/null
+++ b/Documentation/laptops/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := dslm
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/laptops/dslm.c b/Documentation/laptops/dslm.c
new file mode 100644
index 000000000000..72ff290c5fc6
--- /dev/null
+++ b/Documentation/laptops/dslm.c
@@ -0,0 +1,166 @@
+/*
+ * dslm.c
+ * Simple Disk Sleep Monitor
+ *  by Bartek Kania
+ * Licenced under the GPL
+ */
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <time.h>
+#include <string.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/hdreg.h>
+
+#ifdef DEBUG
+#define D(x) x
+#else
+#define D(x)
+#endif
+
+int endit = 0;
+
+/* Check if the disk is in powersave-mode
+ * Most of the code is stolen from hdparm.
+ * 1 = active, 0 = standby/sleep, -1 = unknown */
+static int check_powermode(int fd)
+{
+    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
+    int state;
+
+    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
+        && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
+        && ioctl(fd, HDIO_DRIVE_CMD, &args)) {
+        if (errno != EIO || args[0] != 0 || args[1] != 0) {
+            state = -1; /* "unknown"; */
+        } else
+            state = 0; /* "sleeping"; */
+    } else {
+        state = (args[2] == 255) ? 1 : 0;
+    }
+    D(printf(" drive state is:  %d\n", state));
+
+    return state;
+}
+
+static char *state_name(int i)
+{
+    if (i == -1) return "unknown";
+    if (i == 0) return "sleeping";
+    if (i == 1) return "active";
+
+    return "internal error";
+}
+
+static char *myctime(time_t time)
+{
+    char *ts = ctime(&time);
+    ts[strlen(ts) - 1] = 0;
+
+    return ts;
+}
+
+static void measure(int fd)
+{
+    time_t start_time;
+    int last_state;
+    time_t last_time;
+    int curr_state;
+    time_t curr_time = 0;
+    time_t time_diff;
+    time_t active_time = 0;
+    time_t sleep_time = 0;
+    time_t unknown_time = 0;
+    time_t total_time = 0;
+    int changes = 0;
+    float tmp;
+
+    printf("Starting measurements\n");
+
+    last_state = check_powermode(fd);
+    start_time = last_time = time(0);
+    printf("  System is in state %s\n\n", state_name(last_state));
+
+    while(!endit) {
+        sleep(1);
+        curr_state = check_powermode(fd);
+
+        if (curr_state != last_state || endit) {
+            changes++;
+            curr_time = time(0);
+            time_diff = curr_time - last_time;
+
+            if (last_state == 1) active_time += time_diff;
+            else if (last_state == 0) sleep_time += time_diff;
+            else unknown_time += time_diff;
+
+            last_state = curr_state;
+            last_time = curr_time;
+
+            printf("%s: State-change to %s\n", myctime(curr_time),
+                   state_name(curr_state));
+        }
+    }
+    changes--; /* Compensate for SIGINT */
+
+    total_time = time(0) - start_time;
+    printf("\nTotal running time:  %lus\n", curr_time - start_time);
+    printf(" State changed %d times\n", changes);
+
+    tmp = (float)sleep_time / (float)total_time * 100;
+    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
+    tmp = (float)active_time / (float)total_time * 100;
+    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
+    tmp = (float)unknown_time / (float)total_time * 100;
+    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
+}
+
+static void ender(int s)
+{
+    endit = 1;
+}
+
+static void usage(void)
+{
+    puts("usage: dslm [-w <time>] <disk>");
+    exit(0);
+}
+
+int main(int argc, char **argv)
+{
+    int fd;
+    char *disk = 0;
+    int settle_time = 60;
+
+    /* Parse the simple command-line */
+    if (argc == 2)
+        disk = argv[1];
+    else if (argc == 4) {
+        settle_time = atoi(argv[2]);
+        disk = argv[3];
+    } else
+        usage();
+
+    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
+        printf("Can't open %s, because: %s\n", disk, strerror(errno));
+        exit(-1);
+    }
+
+    if (settle_time) {
+        printf("Waiting %d seconds for the system to settle down to "
+               "'normal'\n", settle_time);
+        sleep(settle_time);
+    } else
+        puts("Not waiting for system to settle down");
+
+    signal(SIGINT, ender);
+
+    measure(fd);
+
+    close(fd);
+
+    return 0;
+}
diff --git a/Documentation/laptops/laptop-mode.txt b/Documentation/laptops/laptop-mode.txt
index eeedee11c8c2..2c3c35093023 100644
--- a/Documentation/laptops/laptop-mode.txt
+++ b/Documentation/laptops/laptop-mode.txt
@@ -779,172 +779,4 @@ Monitoring tool
 ---------------
 
 Bartek Kania submitted this, it can be used to measure how much time your disk
-spends spun up/down.
-
----------------------------dslm.c BEGIN-----------------------------------------
-/*
- * Simple Disk Sleep Monitor
- *  by Bartek Kania
- * Licenced under the GPL
- */
-#include <unistd.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <time.h>
-#include <string.h>
-#include <signal.h>
-#include <sys/ioctl.h>
-#include <linux/hdreg.h>
-
-#ifdef DEBUG
-#define D(x) x
-#else
-#define D(x)
-#endif
-
-int endit = 0;
-
-/* Check if the disk is in powersave-mode
- * Most of the code is stolen from hdparm.
- * 1 = active, 0 = standby/sleep, -1 = unknown */
-int check_powermode(int fd)
-{
-    unsigned char args[4] = {WIN_CHECKPOWERMODE1,0,0,0};
-    int state;
-
-    if (ioctl(fd, HDIO_DRIVE_CMD, &args)
-        && (args[0] = WIN_CHECKPOWERMODE2) /* try again with 0x98 */
-        && ioctl(fd, HDIO_DRIVE_CMD, &args)) {
-        if (errno != EIO || args[0] != 0 || args[1] != 0) {
-            state = -1; /* "unknown"; */
-        } else
-            state = 0; /* "sleeping"; */
-    } else {
-        state = (args[2] == 255) ? 1 : 0;
-    }
-    D(printf(" drive state is:  %d\n", state));
-
-    return state;
-}
-
-char *state_name(int i)
-{
-    if (i == -1) return "unknown";
-    if (i == 0) return "sleeping";
-    if (i == 1) return "active";
-
-    return "internal error";
-}
-
-char *myctime(time_t time)
-{
-    char *ts = ctime(&time);
-    ts[strlen(ts) - 1] = 0;
-
-    return ts;
-}
-
-void measure(int fd)
-{
-    time_t start_time;
-    int last_state;
-    time_t last_time;
-    int curr_state;
-    time_t curr_time = 0;
-    time_t time_diff;
-    time_t active_time = 0;
-    time_t sleep_time = 0;
-    time_t unknown_time = 0;
-    time_t total_time = 0;
-    int changes = 0;
-    float tmp;
-
-    printf("Starting measurements\n");
-
-    last_state = check_powermode(fd);
-    start_time = last_time = time(0);
-    printf("  System is in state %s\n\n", state_name(last_state));
-
-    while(!endit) {
-        sleep(1);
-        curr_state = check_powermode(fd);
-
-        if (curr_state != last_state || endit) {
-            changes++;
-            curr_time = time(0);
-            time_diff = curr_time - last_time;
-
-            if (last_state == 1) active_time += time_diff;
-            else if (last_state == 0) sleep_time += time_diff;
-            else unknown_time += time_diff;
-
-            last_state = curr_state;
-            last_time = curr_time;
-
-            printf("%s: State-change to %s\n", myctime(curr_time),
-                   state_name(curr_state));
-        }
-    }
-    changes--; /* Compensate for SIGINT */
-
-    total_time = time(0) - start_time;
-    printf("\nTotal running time:  %lus\n", curr_time - start_time);
-    printf(" State changed %d times\n", changes);
-
-    tmp = (float)sleep_time / (float)total_time * 100;
-    printf(" Time in sleep state:   %lus (%.2f%%)\n", sleep_time, tmp);
-    tmp = (float)active_time / (float)total_time * 100;
-    printf(" Time in active state:  %lus (%.2f%%)\n", active_time, tmp);
-    tmp = (float)unknown_time / (float)total_time * 100;
-    printf(" Time in unknown state: %lus (%.2f%%)\n", unknown_time, tmp);
-}
-
-void ender(int s)
-{
-    endit = 1;
-}
-
-void usage()
-{
-    puts("usage: dslm [-w <time>] <disk>");
-    exit(0);
-}
-
-int main(int argc, char **argv)
-{
-    int fd;
-    char *disk = 0;
-    int settle_time = 60;
-
-    /* Parse the simple command-line */
-    if (argc == 2)
-        disk = argv[1];
-    else if (argc == 4) {
-        settle_time = atoi(argv[2]);
-        disk = argv[3];
-    } else
-        usage();
-
-    if (!(fd = open(disk, O_RDONLY|O_NONBLOCK))) {
-        printf("Can't open %s, because: %s\n", disk, strerror(errno));
-        exit(-1);
-    }
-
-    if (settle_time) {
-        printf("Waiting %d seconds for the system to settle down to "
-               "'normal'\n", settle_time);
-        sleep(settle_time);
-    } else
-        puts("Not waiting for system to settle down");
-
-    signal(SIGINT, ender);
-
-    measure(fd);
-
-    close(fd);
-
-    return 0;
-}
----------------------------dslm.c END-------------------------------------------
+spends spun up/down.  See Documentation/laptops/dslm.c
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 75afa1229fd7..39c0a09d0105 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -650,6 +650,10 @@ LCD, CRT or DVI (if available). The following commands are available:
         echo expand_toggle > /proc/acpi/ibm/video
         echo video_switch > /proc/acpi/ibm/video
 
+NOTE: Access to this feature is restricted to processes owning the
+CAP_SYS_ADMIN capability for safety reasons, as it can interact badly
+enough with some versions of X.org to crash it.
+
 Each video output device can be enabled or disabled individually.
 Reading /proc/acpi/ibm/video shows the status of each device.
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 7f5809eddee6..631ad2f1b229 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -3,6 +3,7 @@
                          ============================
 
 By: David Howells <dhowells@redhat.com>
+    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 Contents:
 
@@ -60,6 +61,10 @@ Contents:
 
      - And then there's the Alpha.
 
+ (*) Example uses.
+
+     - Circular buffers.
+
  (*) References.
 
 
@@ -2226,6 +2231,21 @@ The Alpha defines the Linux kernel's memory barrier model.
 See the subsection on "Cache Coherency" above.
 
 
+============
+EXAMPLE USES
+============
+
+CIRCULAR BUFFERS
+----------------
+
+Memory barriers can be used to implement circular buffering without the need
+of a lock to serialise the producer with the consumer.  See:
+
+        Documentation/circular-buffers.txt
+
+for details.
+
+
 ==========
 REFERENCES
 ==========
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 50189bf07d53..fe5c099b8fc8 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -32,6 +32,8 @@ cs89x0.txt
         - the Crystal LAN (CS8900/20-based) Ethernet ISA adapter driver
 cxacru.txt
         - Conexant AccessRunner USB ADSL Modem
+cxacru-cf.py
+        - Conexant AccessRunner USB ADSL Modem configuration file parser
 de4x5.txt
         - the Digital EtherWORKS DE4?? and DE5?? PCI Ethernet driver
 decnet.txt
diff --git a/Documentation/networking/Makefile b/Documentation/networking/Makefile
index 6d8af1ac56c4..5aba7a33aeeb 100644
--- a/Documentation/networking/Makefile
+++ b/Documentation/networking/Makefile
@@ -6,3 +6,5 @@ hostprogs-y := ifenslave
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
+
+obj-m := timestamping/
diff --git a/Documentation/networking/cxacru-cf.py b/Documentation/networking/cxacru-cf.py
new file mode 100644
index 000000000000..b41d298398c8
--- /dev/null
+++ b/Documentation/networking/cxacru-cf.py
@@ -0,0 +1,48 @@
+#!/usr/bin/env python
+# Copyright 2009 Simon Arlott
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License as published by the Free
+# Software Foundation; either version 2 of the License, or (at your option)
+# any later version.
+#
+# This program is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+# more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# this program; if not, write to the Free Software Foundation, Inc., 59
+# Temple Place - Suite 330, Boston, MA  02111-1307, USA.
+#
+# Usage: cxacru-cf.py < cxacru-cf.bin
+# Output: values string suitable for the sysfs adsl_config attribute
+#
+# Warning: cxacru-cf.bin with MD5 hash cdbac2689969d5ed5d4850f117702110
+# contains mis-aligned values which will stop the modem from being able
+# to make a connection. If the first and last two bytes are removed then
+# the values become valid, but the modulation will be forced to ANSI
+# T1.413 only which may not be appropriate.
+#
+# The original binary format is a packed list of le32 values.
+
+import sys
+import struct
+
+i = 0
+while True:
+        buf = sys.stdin.read(4)
+
+        if len(buf) == 0:
+                break
+        elif len(buf) != 4:
+                sys.stdout.write("\n")
+                sys.stderr.write("Error: read {0} not 4 bytes\n".format(len(buf)))
+                sys.exit(1)
+
+        if i > 0:
+                sys.stdout.write(" ")
+        sys.stdout.write("{0:x}={1}".format(i, struct.unpack("<I", buf)[0]))
+        i += 1
+
+sys.stdout.write("\n")
diff --git a/Documentation/networking/cxacru.txt b/Documentation/networking/cxacru.txt
index b074681a963e..2cce04457b4d 100644
--- a/Documentation/networking/cxacru.txt
+++ b/Documentation/networking/cxacru.txt
@@ -4,6 +4,12 @@ While it is capable of managing/maintaining the ADSL connection without the
 module loaded, the device will sometimes stop responding after unloading the
 driver and it is necessary to unplug/remove power to the device to fix this.
 
+Note: support for cxacru-cf.bin has been removed. It was not loaded correctly
+so it had no effect on the device configuration. Fixing it could have stopped
+existing devices working when an invalid configuration is supplied.
+
+There is a script cxacru-cf.py to convert an existing file to the sysfs form.
+
 Detected devices will appear as ATM devices named "cxacru". In /sys/class/atm/
 these are directories named cxacruN where N is the device number. A symlink
 named device points to the USB interface device's directory which contains
@@ -15,6 +21,15 @@ several sysfs attribute files for retrieving device statistics:
 * adsl_headend_environment
         Information about the remote headend.
 
+* adsl_config
+        Configuration writing interface.
+        Write parameters in hexadecimal format <index>=<value>,
+        separated by whitespace, e.g.:
+                "1=0 a=5"
+        Up to 7 parameters at a time will be sent and the modem will restart
+        the ADSL connection when any value is set. These are logged for future
+        reference.
+
 * downstream_attenuation (dB)
 * downstream_bits_per_frame
 * downstream_rate (kbps)
@@ -61,6 +76,7 @@ several sysfs attribute files for retrieving device statistics:
 * mac_address
 
 * modulation
+        "" (when not connected)
         "ANSI T1.413"
         "ITU-T G.992.1 (G.DMT)"
         "ITU-T G.992.2 (G.LITE)"
diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt
index b132e4a3cf0f..a62fdf7a6bff 100644
--- a/Documentation/networking/dccp.txt
+++ b/Documentation/networking/dccp.txt
@@ -58,8 +58,10 @@ DCCP_SOCKOPT_GET_CUR_MPS is read-only and retrieves the current maximum packet
 size (application payload size) in bytes, see RFC 4340, section 14.
 
 DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs
-supported by the endpoint (see include/linux/dccp.h for symbolic constants).
-The caller needs to provide a sufficiently large (> 2) array of type uint8_t.
+supported by the endpoint. The option value is an array of type uint8_t whose
+size is passed as option length. The minimum array size is 4 elements, the
+value returned in the optlen argument always reflects the true number of
+built-in CCIDs.
 
 DCCP_SOCKOPT_CCID is write-only and sets both the TX and RX CCIDs at the same
 time, combining the operation of the next two socket options. This option is
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e87f3cdc8a6a..8b72c88ba213 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -487,6 +487,30 @@ tcp_dma_copybreak - INTEGER
         and CONFIG_NET_DMA is enabled.
         Default: 4096
 
+tcp_thin_linear_timeouts - BOOLEAN
+        Enable dynamic triggering of linear timeouts for thin streams.
+        If set, a check is performed upon retransmission by timeout to
+        determine if the stream is thin (less than 4 packets in flight).
+        As long as the stream is found to be thin, up to 6 linear
+        timeouts may be performed before exponential backoff mode is
+        initiated. This improves retransmission latency for
+        non-aggressive thin streams, often found to be time-dependent.
+        For more information on thin streams, see
+        Documentation/networking/tcp-thin.txt
+        Default: 0
+
+tcp_thin_dupack - BOOLEAN
+        Enable dynamic triggering of retransmissions after one dupACK
+        for thin streams. If set, a check is performed upon reception
+        of a dupACK to determine if the stream is thin (less than 4
+        packets in flight). As long as the stream is found to be thin,
+        data is retransmitted on the first received dupACK. This
+        improves retransmission latency for non-aggressive thin
+        streams, often found to be time-dependent.
+        For more information on thin streams, see
+        Documentation/networking/tcp-thin.txt
+        Default: 0
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
@@ -692,6 +716,25 @@ proxy_arp - BOOLEAN
         conf/{all,interface}/proxy_arp is set to TRUE,
         it will be disabled otherwise
 
+proxy_arp_pvlan - BOOLEAN
+        Private VLAN proxy arp.
+        Basically allow proxy arp replies back to the same interface
+        (from which the ARP request/solicitation was received).
+
+        This is done to support (ethernet) switch features, like RFC
+        3069, where the individual ports are NOT allowed to
+        communicate with each other, but they are allowed to talk to
+        the upstream router.  As described in RFC 3069, it is possible
+        to allow these hosts to communicate through the upstream
+        router by proxy_arp'ing. Don't need to be used together with
+        proxy_arp.
+
+        This technology is known by different names:
+          In RFC 3069 it is called VLAN Aggregation.
+          Cisco and Allied Telesyn call it Private VLAN.
+          Hewlett-Packard call it Source-Port filtering or port-isolation.
+          Ericsson call it MAC-Forced Forwarding (RFC Draft).
+
 shared_media - BOOLEAN
         Send(router) or accept(host) RFC1620 shared media redirects.
         Overrides ip_secure_redirects.
@@ -833,9 +876,18 @@ arp_notify - BOOLEAN
             or hardware address changes.
 
 arp_accept - BOOLEAN
-        Define behavior when gratuitous arp replies are received:
-        0 - drop gratuitous arp frames
-        1 - accept gratuitous arp frames
+        Define behavior for gratuitous ARP frames who's IP is not
+        already present in the ARP table:
+        0 - don't create new entries in the ARP table
+        1 - create new entries in the ARP table
+
+        Both replies and requests type gratuitous arp will trigger the
+        ARP table to be updated, if this setting is on.
+
+        If the ARP table already contains the IP address of the
+        gratuitous arp frame, the arp table will be updated regardless
+        if this setting is on or off.
+
 
 app_solicit - INTEGER
         The maximum number of probes to send to the user space ARP daemon
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
new file mode 100755
index 000000000000..19015de6725f
--- /dev/null
+++ b/Documentation/networking/ixgbevf.txt
@@ -0,0 +1,90 @@
+Linux* Base Driver for Intel(R) Network Connection
+==================================================
+
+November 24, 2009
+
+Contents
+========
+
+- In This Release
+- Identifying Your Adapter
+- Known Issues/Troubleshooting
+- Support
+
+In This Release
+===============
+
+This file describes the ixgbevf Linux* Base Driver for Intel Network
+Connection.
+
+The ixgbevf driver supports 82599-based virtual function devices that can only
+be activated on kernels with CONFIG_PCI_IOV enabled.
+
+The ixgbevf driver supports virtual functions generated by the ixgbe driver
+with a max_vfs value of 1 or greater.
+
+The guest OS loading the ixgbevf driver must support MSI-X interrupts.
+
+VLANs: There is a limit of a total of 32 shared VLANs to 1 or more VFs.
+
+Identifying Your Adapter
+========================
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/network/sb/CS-008441.htm
+
+Known Issues/Troubleshooting
+============================
+
+  Unloading Physical Function (PF) Driver Causes System Reboots When VM is
+  Running and VF is Loaded on the VM
+  ------------------------------------------------------------------------
+  Do not unload the PF driver (ixgbe) while VFs are assigned to guests.
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    http://support.intel.com
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
+
+License
+=======
+
+Intel 10 Gigabit Linux driver.
+Copyright(c) 1999 - 2009 Intel Corporation.
+
+This program is free software; you can redistribute it and/or modify it
+under the terms and conditions of the GNU General Public License,
+version 2, as published by the Free Software Foundation.
+
+This program is distributed in the hope it will be useful, but WITHOUT
+ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+more details.
+
+You should have received a copy of the GNU General Public License along with
+this program; if not, write to the Free Software Foundation, Inc.,
+51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+
+The full GNU General Public License is included in this distribution in
+the file called "COPYING".
+
+Trademarks
+==========
+
+Intel, Itanium, and Pentium are trademarks or registered trademarks of
+Intel Corporation or its subsidiaries in the United States and other
+countries.
+
+* Other names and brands may be claimed as the property of others.
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index a22fd85e3796..09ab0d290326 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -2,7 +2,7 @@
 + ABSTRACT
 --------------------------------------------------------------------------------
 
-This file documents the CONFIG_PACKET_MMAP option available with the PACKET
+This file documents the mmap() facility available with the PACKET
 socket interface on 2.4 and 2.6 kernels. This type of sockets is used for 
 capture network traffic with utilities like tcpdump or any other that needs
 raw access to network interface.
@@ -44,7 +44,7 @@ enabled. For transmission, check the MTU (Maximum Transmission Unit) used and
 supported by devices of your network.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP to improve capture process
++ How to use mmap() to improve capture process
 --------------------------------------------------------------------------------
 
 From the user standpoint, you should use the higher level libpcap library, which
@@ -64,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP
 support.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve capture process
++ How to use mmap() directly to improve capture process
 --------------------------------------------------------------------------------
 
 From the system calls stand point, the use of PACKET_MMAP involves
@@ -105,7 +105,7 @@ also the mapping of the circular buffer in the user process and
 the use of this buffer.
 
 --------------------------------------------------------------------------------
-+ How to use CONFIG_PACKET_MMAP directly to improve transmission process
++ How to use mmap() directly to improve transmission process
 --------------------------------------------------------------------------------
 Transmission process is similar to capture as shown below.
 
diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt
index ee31369e9e5b..9551622d0a7b 100644
--- a/Documentation/networking/regulatory.txt
+++ b/Documentation/networking/regulatory.txt
@@ -188,3 +188,27 @@ Then in some part of your code after your wiphy has been registered:
                        &mydriver_jp_regdom.reg_rules[i],
                        sizeof(struct ieee80211_reg_rule));
         regulatory_struct_hint(rd);
+
+Statically compiled regulatory database
+---------------------------------------
+
+In most situations the userland solution using CRDA as described
+above is the preferred solution.  However in some cases a set of
+rules built into the kernel itself may be desirable.  To account
+for this situation, a configuration option has been provided
+(i.e. CONFIG_CFG80211_INTERNAL_REGDB).  With this option enabled,
+the wireless database information contained in net/wireless/db.txt is
+used to generate a data structure encoded in net/wireless/regdb.c.
+That option also enables code in net/wireless/reg.c which queries
+the data in regdb.c as an alternative to using CRDA.
+
+The file net/wireless/db.txt should be kept up-to-date with the db.txt
+file available in the git repository here:
+
+    git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-regdb.git
+
+Again, most users in most situations should be using the CRDA package
+provided with their distribution, and in most other situations users
+should be building and using CRDA on their own rather than using
+this option.  If you are not absolutely sure that you should be using
+CONFIG_CFG80211_INTERNAL_REGDB then _DO_NOT_USE_IT_.
diff --git a/Documentation/networking/skfp.txt b/Documentation/networking/skfp.txt
index abfddf81e34a..203ec66c9fb4 100644
--- a/Documentation/networking/skfp.txt
+++ b/Documentation/networking/skfp.txt
@@ -68,7 +68,7 @@ Compaq adapters (not tested):
 =======================
 
 From v2.01 on, the driver is integrated in the linux kernel sources.
-Therefor, the installation is the same as for any other adapter
+Therefore, the installation is the same as for any other adapter
 supported by the kernel.
 Refer to the manual of your distribution about the installation
 of network adapters.
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
new file mode 100644
index 000000000000..7ee770b5ef5f
--- /dev/null
+++ b/Documentation/networking/stmmac.txt
@@ -0,0 +1,143 @@
+       STMicroelectronics 10/100/1000 Synopsys Ethernet driver
+
+Copyright (C) 2007-2010  STMicroelectronics Ltd
+Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+
+This is the driver for the MAC 10/100/1000 on-chip Ethernet controllers
+(Synopsys IP blocks); it has been fully tested on STLinux platforms.
+
+Currently this network device driver is for all STM embedded MAC/GMAC
+(7xxx SoCs).
+
+DWC Ether MAC 10/100/1000 Universal version 3.41a and DWC Ether MAC 10/100
+Universal version 4.0 have been used for developing the first code
+implementation.
+
+Please, for more information also visit: www.stlinux.com
+
+1) Kernel Configuration
+The kernel configuration option is STMMAC_ETH:
+ Device Drivers ---> Network device support ---> Ethernet (1000 Mbit) --->
+ STMicroelectronics 10/100/1000 Ethernet driver (STMMAC_ETH)
+
+2) Driver parameters list:
+        debug: message level (0: no output, 16: all);
+        phyaddr: to manually provide the physical address to the PHY device;
+        dma_rxsize: DMA rx ring size;
+        dma_txsize: DMA tx ring size;
+        buf_sz: DMA buffer size;
+        tc: control the HW FIFO threshold;
+        tx_coe: Enable/Disable Tx Checksum Offload engine;
+        watchdog: transmit timeout (in milliseconds);
+        flow_ctrl: Flow control ability [on/off];
+        pause: Flow Control Pause Time;
+        tmrate: timer period (only if timer optimisation is configured).
+
+3) Command line options
+Driver parameters can be also passed in command line by using:
+        stmmaceth=dma_rxsize:128,dma_txsize:512
+
+4) Driver information and notes
+
+4.1) Transmit process
+The xmit method is invoked when the kernel needs to transmit a packet; it sets
+the descriptors in the ring and informs the DMA engine that there is a packet
+ready to be transmitted.
+Once the controller has finished transmitting the packet, an interrupt is
+triggered; So the driver will be able to release the socket buffers.
+By default, the driver sets the NETIF_F_SG bit in the features field of the
+net_device structure enabling the scatter/gather feature.
+
+4.2) Receive process
+When one or more packets are received, an interrupt happens. The interrupts
+are not queued so the driver has to scan all the descriptors in the ring during
+the receive process.
+This is based on NAPI so the interrupt handler signals only if there is work to be
+done, and it exits.
+Then the poll method will be scheduled at some future point.
+The incoming packets are stored, by the DMA, in a list of pre-allocated socket
+buffers in order to avoid the memcpy (Zero-copy).
+
+4.3) Timer-Driver Interrupt
+Instead of having the device that asynchronously notifies the frame receptions, the
+driver configures a timer to generate an interrupt at regular intervals.
+Based on the granularity of the timer, the frames that are received by the device
+will experience different levels of latency. Some NICs have dedicated timer
+device to perform this task. STMMAC can use either the RTC device or the TMU
+channel 2  on STLinux platforms.
+The timers frequency can be passed to the driver as parameter; when change it,
+take care of both hardware capability and network stability/performance impact.
+Several performance tests on STM platforms showed this optimisation allows to spare
+the CPU while having the maximum throughput.
+
+4.4) WOL
+Wake up on Lan feature through Magic Frame is only supported for the GMAC
+core.
+
+4.5) DMA descriptors
+Driver handles both normal and enhanced descriptors. The latter has been only
+tested on DWC Ether MAC 10/100/1000 Universal version 3.41a.
+
+4.6) Ethtool support
+Ethtool is supported. Driver statistics and internal errors can be taken using:
+ethtool -S ethX command. It is possible to dump registers etc.
+
+4.7) Jumbo and Segmentation Offloading
+Jumbo frames are supported and tested for the GMAC.
+The GSO has been also added but it's performed in software.
+LRO is not supported.
+
+4.8) Physical
+The driver is compatible with PAL to work with PHY and GPHY devices.
+
+4.9) Platform information
+Several information came from the platform; please refer to the
+driver's Header file in include/linux directory.
+
+struct plat_stmmacenet_data {
+        int bus_id;
+        int pbl;
+        int has_gmac;
+        void (*fix_mac_speed)(void *priv, unsigned int speed);
+        void (*bus_setup)(unsigned long ioaddr);
+#ifdef CONFIG_STM_DRIVERS
+        struct stm_pad_config *pad_config;
+#endif
+        void *bsp_priv;
+};
+
+Where:
+- pbl (Programmable Burst Length) is maximum number of
+  beats to be transferred in one DMA transaction.
+  GMAC also enables the 4xPBL by default.
+- fix_mac_speed and bus_setup are used to configure internal target
+  registers (on STM platforms);
+- has_gmac: GMAC core is on board (get it at run-time in the next step);
+- bus_id: bus identifier.
+
+struct plat_stmmacphy_data {
+        int bus_id;
+        int phy_addr;
+        unsigned int phy_mask;
+        int interface;
+        int (*phy_reset)(void *priv);
+        void *priv;
+};
+
+Where:
+- bus_id: bus identifier;
+- phy_addr: physical address used for the attached phy device;
+            set it to -1 to get it at run-time;
+- interface: physical MII interface mode;
+- phy_reset: hook to reset HW function.
+
+TODO:
+- Continue to make the driver more generic and suitable for other Synopsys
+  Ethernet controllers used on other architectures (i.e. ARM).
+- 10G controllers are not supported.
+- MAC uses Normal descriptors and GMAC uses enhanced ones.
+  This is a limit that should be reviewed. MAC could want to
+  use the enhanced structure.
+- Checksumming: Rx/Tx csum is done in HW in case of GMAC only.
+- Review the timer optimisation code to use an embedded device that seems to be
+  available in new chip generations.
diff --git a/Documentation/networking/tcp-thin.txt b/Documentation/networking/tcp-thin.txt
new file mode 100644
index 000000000000..151e229980f1
--- /dev/null
+++ b/Documentation/networking/tcp-thin.txt
@@ -0,0 +1,47 @@
+Thin-streams and TCP
+====================
+A wide range of Internet-based services that use reliable transport
+protocols display what we call thin-stream properties. This means
+that the application sends data with such a low rate that the
+retransmission mechanisms of the transport protocol are not fully
+effective. In time-dependent scenarios (like online games, control
+systems, stock trading etc.) where the user experience depends
+on the data delivery latency, packet loss can be devastating for
+the service quality. Extreme latencies are caused by TCP's
+dependency on the arrival of new data from the application to trigger
+retransmissions effectively through fast retransmit instead of
+waiting for long timeouts.
+
+After analysing a large number of time-dependent interactive
+applications, we have seen that they often produce thin streams
+and also stay with this traffic pattern throughout its entire
+lifespan. The combination of time-dependency and the fact that the
+streams provoke high latencies when using TCP is unfortunate.
+
+In order to reduce application-layer latency when packets are lost,
+a set of mechanisms has been made, which address these latency issues
+for thin streams. In short, if the kernel detects a thin stream,
+the retransmission mechanisms are modified in the following manner:
+
+1) If the stream is thin, fast retransmit on the first dupACK.
+2) If the stream is thin, do not apply exponential backoff.
+
+These enhancements are applied only if the stream is detected as
+thin. This is accomplished by defining a threshold for the number
+of packets in flight. If there are less than 4 packets in flight,
+fast retransmissions can not be triggered, and the stream is prone
+to experience high retransmission latencies.
+
+Since these mechanisms are targeted at time-dependent applications,
+they must be specifically activated by the application using the
+TCP_THIN_LINEAR_TIMEOUTS and TCP_THIN_DUPACK IOCTLS or the
+tcp_thin_linear_timeouts and tcp_thin_dupack sysctls. Both
+modifications are turned off by default.
+
+References
+==========
+More information on the modifications, as well as a wide range of
+experimental data can be found here:
+"Improving latency for interactive, thin-stream applications over
+reliable transport"
+http://simula.no/research/nd/publications/Simula.nd.477/simula_pdf_file
diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt
index 0e58b4539176..e8c8f4f06c67 100644
--- a/Documentation/networking/timestamping.txt
+++ b/Documentation/networking/timestamping.txt
@@ -41,11 +41,12 @@ SOF_TIMESTAMPING_SOFTWARE:     return system time stamp generated in
 SOF_TIMESTAMPING_TX/RX determine how time stamps are generated.
 SOF_TIMESTAMPING_RAW/SYS determine how they are reported in the
 following control message:
-    struct scm_timestamping {
-           struct timespec systime;
-           struct timespec hwtimetrans;
-           struct timespec hwtimeraw;
-    };
+
+struct scm_timestamping {
+        struct timespec systime;
+        struct timespec hwtimetrans;
+        struct timespec hwtimeraw;
+};
 
 recvmsg() can be used to get this control message for regular incoming
 packets. For send time stamps the outgoing packet is looped back to
@@ -87,12 +88,13 @@ by the network device and will be empty without that support.
 SIOCSHWTSTAMP:
 
 Hardware time stamping must also be initialized for each device driver
-that is expected to do hardware time stamping. The parameter is:
+that is expected to do hardware time stamping. The parameter is defined in
+/include/linux/net_tstamp.h as:
 
 struct hwtstamp_config {
-    int flags;           /* no flags defined right now, must be zero */
-    int tx_type;         /* HWTSTAMP_TX_* */
-    int rx_filter;       /* HWTSTAMP_FILTER_* */
+        int flags;      /* no flags defined right now, must be zero */
+        int tx_type;    /* HWTSTAMP_TX_* */
+        int rx_filter;  /* HWTSTAMP_FILTER_* */
 };
 
 Desired behavior is passed into the kernel and to a specific device by
@@ -139,42 +141,56 @@ enum {
         /* time stamp any incoming packet */
         HWTSTAMP_FILTER_ALL,
 
-        /* return value: time stamp all packets requested plus some others */
-        HWTSTAMP_FILTER_SOME,
+        /* return value: time stamp all packets requested plus some others */
+        HWTSTAMP_FILTER_SOME,
 
         /* PTP v1, UDP, any kind of event packet */
         HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
 
-        ...
+        /* for the complete list of values, please check
+         * the include file /include/linux/net_tstamp.h
+         */
 };
 
 
 DEVICE IMPLEMENTATION
 
 A driver which supports hardware time stamping must support the
-SIOCSHWTSTAMP ioctl. Time stamps for received packets must be stored
-in the skb with skb_hwtstamp_set().
+SIOCSHWTSTAMP ioctl and update the supplied struct hwtstamp_config with
+the actual values as described in the section on SIOCSHWTSTAMP.
+
+Time stamps for received packets must be stored in the skb. To get a pointer
+to the shared time stamp structure of the skb call skb_hwtstamps(). Then
+set the time stamps in the structure:
+
+struct skb_shared_hwtstamps {
+        /* hardware time stamp transformed into duration
+         * since arbitrary point in time
+         */
+        ktime_t hwtstamp;
+        ktime_t syststamp; /* hwtstamp transformed to system time base */
+};
 
 Time stamps for outgoing packets are to be generated as follows:
-- In hard_start_xmit(), check if skb_hwtstamp_check_tx_hardware()
-  returns non-zero. If yes, then the driver is expected
-  to do hardware time stamping.
+- In hard_start_xmit(), check if skb_tx(skb)->hardware is set no-zero.
+  If yes, then the driver is expected to do hardware time stamping.
 - If this is possible for the skb and requested, then declare
-  that the driver is doing the time stamping by calling
-  skb_hwtstamp_tx_in_progress(). A driver not supporting
-  hardware time stamping doesn't do that. A driver must never
-  touch sk_buff::tstamp! It is used to store how time stamping
-  for an outgoing packets is to be done.
+  that the driver is doing the time stamping by setting the field
+  skb_tx(skb)->in_progress non-zero. You might want to keep a pointer
+  to the associated skb for the next step and not free the skb. A driver
+  not supporting hardware time stamping doesn't do that. A driver must
+  never touch sk_buff::tstamp! It is used to store software generated
+  time stamps by the network subsystem.
 - As soon as the driver has sent the packet and/or obtained a
   hardware time stamp for it, it passes the time stamp back by
   calling skb_hwtstamp_tx() with the original skb, the raw
-  hardware time stamp and a handle to the device (necessary
-  to convert the hardware time stamp to system time). If obtaining
-  the hardware time stamp somehow fails, then the driver should
-  not fall back to software time stamping. The rationale is that
-  this would occur at a later time in the processing pipeline
-  than other software time stamping and therefore could lead
-  to unexpected deltas between time stamps.
-- If the driver did not call skb_hwtstamp_tx_in_progress(), then
+  hardware time stamp. skb_hwtstamp_tx() clones the original skb and
+  adds the timestamps, therefore the original skb has to be freed now.
+  If obtaining the hardware time stamp somehow fails, then the driver
+  should not fall back to software time stamping. The rationale is that
+  this would occur at a later time in the processing pipeline than other
+  software time stamping and therefore could lead to unexpected deltas
+  between time stamps.
+- If the driver did not call set skb_tx(skb)->in_progress, then
   dev_hard_start_xmit() checks whether software time stamping
   is wanted as fallback and potentially generates the time stamp.
diff --git a/Documentation/networking/timestamping/Makefile b/Documentation/networking/timestamping/Makefile
index 2a1489fdc036..e79973443e9f 100644
--- a/Documentation/networking/timestamping/Makefile
+++ b/Documentation/networking/timestamping/Makefile
@@ -1,6 +1,13 @@
-CPPFLAGS = -I../../../include
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
 
-timestamping: timestamping.c
+# List of programs to build
+hostprogs-y := timestamping
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_timestamping.o += -I$(objtree)/usr/include
 
 clean:
         rm -f timestamping
diff --git a/Documentation/networking/timestamping/timestamping.c b/Documentation/networking/timestamping/timestamping.c
index a7936fe8444a..8ba82bfe6a33 100644
--- a/Documentation/networking/timestamping/timestamping.c
+++ b/Documentation/networking/timestamping/timestamping.c
@@ -41,9 +41,9 @@
 #include <arpa/inet.h>
 #include <net/if.h>
 
-#include "asm/types.h"
-#include "linux/net_tstamp.h"
-#include "linux/errqueue.h"
+#include <asm/types.h>
+#include <linux/net_tstamp.h>
+#include <linux/errqueue.h>
 
 #ifndef SO_TIMESTAMPING
 # define SO_TIMESTAMPING         37
@@ -164,7 +164,7 @@ static void printpacket(struct msghdr *msg, int res,
 
         gettimeofday(&now, 0);
 
-        printf("%ld.%06ld: received %s data, %d bytes from %s, %d bytes control messages\n",
+        printf("%ld.%06ld: received %s data, %d bytes from %s, %zu bytes control messages\n",
                (long)now.tv_sec, (long)now.tv_usec,
                (recvmsg_flags & MSG_ERRQUEUE) ? "error" : "regular",
                res,
@@ -173,7 +173,7 @@ static void printpacket(struct msghdr *msg, int res,
         for (cmsg = CMSG_FIRSTHDR(msg);
              cmsg;
              cmsg = CMSG_NXTHDR(msg, cmsg)) {
-                printf("   cmsg len %d: ", cmsg->cmsg_len);
+                printf("   cmsg len %zu: ", cmsg->cmsg_len);
                 switch (cmsg->cmsg_level) {
                 case SOL_SOCKET:
                         printf("SOL_SOCKET ");
@@ -370,7 +370,7 @@ int main(int argc, char **argv)
         }
 
         sock = socket(PF_INET, SOCK_DGRAM, IPPROTO_UDP);
-        if (socket < 0)
+        if (sock < 0)
                 bail("socket");
 
         memset(&device, 0, sizeof(device));
diff --git a/Documentation/pcmcia/locking.txt b/Documentation/pcmcia/locking.txt
new file mode 100644
index 000000000000..68f622bc4064
--- /dev/null
+++ b/Documentation/pcmcia/locking.txt
@@ -0,0 +1,118 @@
+This file explains the locking and exclusion scheme used in the PCCARD
+and PCMCIA subsystems.
+
+
+A) Overview, Locking Hierarchy:
+===============================
+
+pcmcia_socket_list_rwsem        - protects only the list of sockets
+- skt_mutex                     - serializes card insert / ejection
+  - ops_mutex                   - serializes socket operation
+
+
+B) Exclusion
+============
+
+The following functions and callbacks to struct pcmcia_socket must
+be called with "skt_mutex" held:
+
+        socket_detect_change()
+        send_event()
+        socket_reset()
+        socket_shutdown()
+        socket_setup()
+        socket_remove()
+        socket_insert()
+        socket_early_resume()
+        socket_late_resume()
+        socket_resume()
+        socket_suspend()
+
+        struct pcmcia_callback  *callback
+
+The following functions and callbacks to struct pcmcia_socket must
+be called with "ops_mutex" held:
+
+        socket_reset()
+        socket_setup()
+
+        struct pccard_operations        *ops
+        struct pccard_resource_ops      *resource_ops;
+
+Note that send_event() and struct pcmcia_callback *callback must not be
+called with "ops_mutex" held.
+
+
+C) Protection
+=============
+
+1. Global Data:
+---------------
+struct list_head        pcmcia_socket_list;
+
+protected by pcmcia_socket_list_rwsem;
+
+
+2. Per-Socket Data:
+-------------------
+The resource_ops and their data are protected by ops_mutex.
+
+The "main" struct pcmcia_socket is protected as follows (read-only fields
+or single-use fields not mentioned):
+
+- by pcmcia_socket_list_rwsem:
+        struct list_head        socket_list;
+
+- by thread_lock:
+        unsigned int            thread_events;
+
+- by skt_mutex:
+        u_int                   suspended_state;
+        void                    (*tune_bridge);
+        struct pcmcia_callback  *callback;
+        int                     resume_status;
+
+- by ops_mutex:
+        socket_state_t          socket;
+        u_int                   state;
+        u_short                 lock_count;
+        pccard_mem_map          cis_mem;
+        void __iomem            *cis_virt;
+        struct { }              irq;
+        io_window_t             io[];
+        pccard_mem_map          win[];
+        struct list_head        cis_cache;
+        size_t                  fake_cis_len;
+        u8                      *fake_cis;
+        u_int                   irq_mask;
+        void                    (*zoom_video);
+        int                     (*power_hook);
+        u8                      resource...;
+        struct list_head        devices_list;
+        u8                      device_count;
+        struct                  pcmcia_state;
+
+
+3. Per PCMCIA-device Data:
+--------------------------
+
+The "main" struct pcmcia_devie is protected as follows (read-only fields
+or single-use fields not mentioned):
+
+
+- by pcmcia_socket->ops_mutex:
+        struct list_head        socket_device_list;
+        struct config_t         *function_config;
+        u16                     _irq:1;
+        u16                     _io:1;
+        u16                     _win:4;
+        u16                     _locked:1;
+        u16                     allow_func_id_match:1;
+        u16                     suspended:1;
+        u16                     _removed:1;
+
+- by the PCMCIA driver:
+        io_req_t                io;
+        irq_req_t               irq;
+        config_req_t            conf;
+        window_handle_t         win;
diff --git a/Documentation/pnp.txt b/Documentation/pnp.txt
index a327db67782a..763e4659bf18 100644
--- a/Documentation/pnp.txt
+++ b/Documentation/pnp.txt
@@ -57,7 +57,7 @@ PC standard floppy disk controller
 # cat resources
 DISABLED
 
-- Notice the string "DISABLED".  THis means the device is not active.
+- Notice the string "DISABLED".  This means the device is not active.
 
 3.) check the device's possible configurations (optional)
 # cat options
@@ -139,7 +139,7 @@ Plug and Play but it is planned to be in the near future.
 
 Requirements for a Linux PnP protocol:
 1.) the protocol must use EISA IDs
-2.) the protocol must inform the PnP Layer of a devices current configuration
+2.) the protocol must inform the PnP Layer of a device's current configuration
 - the ability to set resources is optional but preferred.
 
 The following are PnP protocol related functions:
@@ -158,7 +158,7 @@ pnp_remove_device
 - automatically will free mem used by the device and related structures
 
 pnp_add_id
-- adds a EISA ID to the list of supported IDs for the specified device
+- adds an EISA ID to the list of supported IDs for the specified device
 
 For more information consult the source of a protocol such as
 /drivers/pnp/pnpbios/core.c.
@@ -167,7 +167,7 @@ For more information consult the source of a protocol such as
 
 Linux Plug and Play Drivers
 ---------------------------
-        This section contains information for linux PnP driver developers.
+        This section contains information for Linux PnP driver developers.
 
 The New Way
 ...........
@@ -235,11 +235,10 @@ static int __init serial8250_pnp_init(void)
 The Old Way
 ...........
 
-a series of compatibility functions have been created to make it easy to convert 
-
+A series of compatibility functions have been created to make it easy to convert
 ISAPNP drivers.  They should serve as a temporary solution only.
 
-they are as follows:
+They are as follows:
 
 struct pnp_card *pnp_find_card(unsigned short vendor,
                                  unsigned short device,
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 356fd86f4ea8..55b859b3bc72 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -224,6 +224,12 @@ defined in include/linux/pm.h:
       RPM_SUSPENDED, which means that each device is initially regarded by the
       PM core as 'suspended', regardless of its real hardware status
 
+  unsigned int runtime_auto;
+    - if set, indicates that the user space has allowed the device driver to
+      power manage the device at run time via the /sys/devices/.../power/control
+      interface; it may only be modified with the help of the pm_runtime_allow()
+      and pm_runtime_forbid() helper functions
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -250,7 +256,7 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       to suspend the device again in future
 
   int pm_runtime_resume(struct device *dev);
-    - execute the subsystem-leve resume callback for the device; returns 0 on
+    - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
       error code on failure, where -EAGAIN means it may be safe to attempt to
       resume the device again in future, but 'power.runtime_error' should be
@@ -329,6 +335,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       'power.runtime_error' is set or 'power.disable_depth' is greater than
       zero)
 
+  bool pm_runtime_suspended(struct device *dev);
+    - return true if the device's runtime PM status is 'suspended', or false
+      otherwise
+
+  void pm_runtime_allow(struct device *dev);
+    - set the power.runtime_auto flag for the device and decrease its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively allow the device to be power managed at run time)
+
+  void pm_runtime_forbid(struct device *dev);
+    - unset the power.runtime_auto flag for the device and increase its usage
+      counter (used by the /sys/devices/.../power/control interface to
+      effectively prevent the device from being power managed at run time)
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
@@ -382,6 +402,18 @@ may be desirable to suspend the device as soon as ->probe() or ->remove() has
 finished, so the PM core uses pm_runtime_idle_sync() to invoke the
 subsystem-level idle callback for the device at that time.
 
+The user space can effectively disallow the driver of the device to power manage
+it at run time by changing the value of its /sys/devices/.../power/control
+attribute to "on", which causes pm_runtime_forbid() to be called.  In principle,
+this mechanism may also be used by the driver to effectively turn off the
+run-time power management of the device until the user space turns it on.
+Namely, during the initialization the driver can make sure that the run-time PM
+status of the device is 'active' and call pm_runtime_forbid().  It should be
+noted, however, that if the user space has already intentionally changed the
+value of /sys/devices/.../power/control to "auto" to allow the driver to power
+manage the device at run time, the driver may confuse it by using
+pm_runtime_forbid() this way.
+
 6. Run-time PM and System Sleep
 
 Run-time PM and system sleep (i.e., system suspend and hibernation, also known
@@ -431,3 +463,64 @@ The PM core always increments the run-time usage counter before calling the
 ->prepare() callback and decrements it after calling the ->complete() callback.
 Hence disabling run-time PM temporarily like this will not cause any run-time
 suspend callbacks to be lost.
+
+7. Generic subsystem callbacks
+
+Subsystems may wish to conserve code space by using the set of generic power
+management callbacks provided by the PM core, defined in
+driver/base/power/generic_ops.c:
+
+  int pm_generic_runtime_idle(struct device *dev);
+    - invoke the ->runtime_idle() callback provided by the driver of this
+      device, if defined, and call pm_runtime_suspend() for this device if the
+      return value is 0 or the callback is not defined
+
+  int pm_generic_runtime_suspend(struct device *dev);
+    - invoke the ->runtime_suspend() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_runtime_resume(struct device *dev);
+    - invoke the ->runtime_resume() callback provided by the driver of this
+      device and return its result, or return -EINVAL if not defined
+
+  int pm_generic_suspend(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->suspend()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_resume(struct device *dev);
+    - invoke the ->resume() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+  int pm_generic_freeze(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->freeze()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_thaw(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->thaw()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_poweroff(struct device *dev);
+    - if the device has not been suspended at run time, invoke the ->poweroff()
+      callback provided by its driver and return its result, or return 0 if not
+      defined
+
+  int pm_generic_restore(struct device *dev);
+    - invoke the ->restore() callback provided by the driver of this device and,
+      if successful, change the device's runtime PM status to 'active'
+
+These functions can be assigned to the ->runtime_idle(), ->runtime_suspend(),
+->runtime_resume(), ->suspend(), ->resume(), ->freeze(), ->thaw(), ->poweroff(),
+or ->restore() callback pointers in the subsystem-level dev_pm_ops structures.
+
+If a subsystem wishes to use all of them at the same time, it can simply assign
+the GENERIC_SUBSYS_PM_OPS macro, defined in include/linux/pm.h, to its
+dev_pm_ops structure pointer.
+
+Device drivers that wish to use the same function as a system suspend, freeze,
+poweroff and run-time suspend callback, and similarly for system resume, thaw,
+restore, and run-time resume, can achieve this with the help of the
+UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
+last argument to NULL).
diff --git a/Documentation/powerpc/dts-bindings/fsl/can.txt b/Documentation/powerpc/dts-bindings/fsl/can.txt
new file mode 100644
index 000000000000..2fa4fcd38fd6
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/can.txt
@@ -0,0 +1,53 @@
+CAN Device Tree Bindings
+------------------------
+
+(c) 2006-2009 Secret Lab Technologies Ltd
+Grant Likely <grant.likely@secretlab.ca>
+
+fsl,mpc5200-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+                           are: "ip" for ip bus clock
+                                 "ref" for reference clock (XTAL)
+                           "ref" is default in case this property is not
+                           present.
+
+fsl,mpc5121-mscan nodes
+-----------------------
+In addition to the required compatible-, reg- and interrupt-properties, you can
+also specify which clock source and divider shall be used for the controller:
+
+- fsl,mscan-clock-source : a string describing the clock source. Valid values
+                           are: "ip" for ip bus clock
+                                "ref" for reference clock
+                                "sys" for system clock
+                           If this property is not present, an optimal CAN
+                           clock source and frequency based on the system
+                           clock will be selected. If this is not possible,
+                           the reference clock will be used.
+
+- fsl,mscan-clock-divider: for the reference and system clock, an additional
+                           clock divider can be specified. By default, a
+                           value of 1 is used.
+
+Note that the MPC5121 Rev. 1 processor is not supported.
+
+Examples:
+        can@1300 {
+                compatible = "fsl,mpc5121-mscan";
+                interrupts = <12 0x8>;
+                interrupt-parent = <&ipic>;
+                reg = <0x1300 0x80>;
+        };
+
+        can@1380 {
+                compatible = "fsl,mpc5121-mscan";
+                interrupts = <13 0x8>;
+                interrupt-parent = <&ipic>;
+                reg = <0x1380 0x80>;
+                fsl,mscan-clock-source = "ref";
+                fsl,mscan-clock-divider = <3>;
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
index 6e37be1eeb2d..4f8930263dd9 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe.txt
@@ -21,6 +21,15 @@ Required properties:
 - fsl,qe-num-snums: define how many serial number(SNUM) the QE can use for the
   threads.
 
+Optional properties:
+- fsl,firmware-phandle:
+    Usage: required only if there is no fsl,qe-firmware child node
+    Value type: <phandle>
+    Definition: Points to a firmware node (see "QE Firmware Node" below)
+        that contains the firmware that should be uploaded for this QE.
+        The compatible property for the firmware node should say,
+        "fsl,qe-firmware".
+
 Recommended properties
 - brg-frequency : the internal clock source frequency for baud-rate
   generators in Hz.
@@ -59,3 +68,48 @@ Example:
                 reg = <0 c000>;
         };
      };
+
+* QE Firmware Node
+
+This node defines a firmware binary that is embedded in the device tree, for
+the purpose of passing the firmware from bootloader to the kernel, or from
+the hypervisor to the guest.
+
+The firmware node itself contains the firmware binary contents, a compatible
+property, and any firmware-specific properties.  The node should be placed
+inside a QE node that needs it.  Doing so eliminates the need for a
+fsl,firmware-phandle property.  Other QE nodes that need the same firmware
+should define an fsl,firmware-phandle property that points to the firmware node
+in the first QE node.
+
+The fsl,firmware property can be specified in the DTS (possibly using incbin)
+or can be inserted by the boot loader at boot time.
+
+Required properties:
+  - compatible
+      Usage: required
+      Value type: <string>
+      Definition: A standard property.  Specify a string that indicates what
+          kind of firmware it is.  For QE, this should be "fsl,qe-firmware".
+
+   - fsl,firmware
+      Usage: required
+      Value type: <prop-encoded-array>, encoded as an array of bytes
+      Definition: A standard property.  This property contains the firmware
+          binary "blob".
+
+Example:
+        qe1@e0080000 {
+                compatible = "fsl,qe";
+                qe_firmware:qe-firmware {
+                        compatible = "fsl,qe-firmware";
+                        fsl,firmware = [0x70 0xcd 0x00 0x00 0x01 0x46 0x45 ...];
+                };
+                ...
+        };
+
+        qe2@e0090000 {
+                compatible = "fsl,qe";
+                fsl,firmware-phandle = <&qe_firmware>;
+                ...
+        };
diff --git a/Documentation/powerpc/dts-bindings/fsl/dma.txt b/Documentation/powerpc/dts-bindings/fsl/dma.txt
index 0732cdd05ba1..2a4b4bce6110 100644
--- a/Documentation/powerpc/dts-bindings/fsl/dma.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/dma.txt
@@ -44,21 +44,29 @@ Example:
                         compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                         cell-index = <0>;
                         reg = <0 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                 };
                 dma-channel@80 {
                         compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                         cell-index = <1>;
                         reg = <0x80 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                 };
                 dma-channel@100 {
                         compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                         cell-index = <2>;
                         reg = <0x100 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                 };
                 dma-channel@180 {
                         compatible = "fsl,mpc8349-dma-channel", "fsl,elo-dma-channel";
                         cell-index = <3>;
                         reg = <0x180 0x80>;
+                        interrupt-parent = <&ipic>;
+                        interrupts = <71 8>;
                 };
         };
 
diff --git a/Documentation/powerpc/dts-bindings/fsl/i2c.txt b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
index b6d2e21474f9..50da20310585 100644
--- a/Documentation/powerpc/dts-bindings/fsl/i2c.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/i2c.txt
@@ -2,15 +2,14 @@
 
 Required properties :
 
- - device_type : Should be "i2c"
  - reg : Offset and length of the register set for the device
+ - compatible : should be "fsl,CHIP-i2c" where CHIP is the name of a
+   compatible processor, e.g. mpc8313, mpc8543, mpc8544, mpc5121,
+   mpc5200 or mpc5200b. For the mpc5121, an additional node
+   "fsl,mpc5121-i2c-ctrl" is required as shown in the example below.
 
 Recommended properties :
 
- - compatible : compatibility list with 2 entries, the first should
-   be "fsl,CHIP-i2c" where CHIP is the name of a compatible processor,
-   e.g. mpc8313, mpc8543, mpc8544, mpc5200 or mpc5200b. The second one
-   should be "fsl-i2c".
  - interrupts : <a b> where a is the interrupt number and b is a
    field that represents an encoding of the sense and level
    information for the interrupt.  This should be encoded based on
@@ -24,25 +23,40 @@ Recommended properties :
 
 Examples :
 
+        /* MPC5121 based board */
+        i2c@1740 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "fsl,mpc5121-i2c", "fsl-i2c";
+                reg = <0x1740 0x20>;
+                interrupts = <11 0x8>;
+                interrupt-parent = <&ipic>;
+                clock-frequency = <100000>;
+        };
+
+        i2ccontrol@1760 {
+                compatible = "fsl,mpc5121-i2c-ctrl";
+                reg = <0x1760 0x8>;
+        };
+
+        /* MPC5200B based board */
         i2c@3d00 {
                 #address-cells = <1>;
                 #size-cells = <0>;
                 compatible = "fsl,mpc5200b-i2c","fsl,mpc5200-i2c","fsl-i2c";
-                cell-index = <0>;
                 reg = <0x3d00 0x40>;
                 interrupts = <2 15 0>;
                 interrupt-parent = <&mpc5200_pic>;
                 fsl,preserve-clocking;
         };
 
+        /* MPC8544 base board */
         i2c@3100 {
                 #address-cells = <1>;
                 #size-cells = <0>;
-                cell-index = <1>;
                 compatible = "fsl,mpc8544-i2c", "fsl-i2c";
                 reg = <0x3100 0x100>;
                 interrupts = <43 2>;
                 interrupt-parent = <&mpic>;
                 clock-frequency = <400000>;
         };
-
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
new file mode 100644
index 000000000000..8832e8798912
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5121-psc.txt
@@ -0,0 +1,70 @@
+MPC5121 PSC Device Tree Bindings
+
+PSC in UART mode
+----------------
+
+For PSC in UART mode the needed PSC serial devices
+are specified by fsl,mpc5121-psc-uart nodes in the
+fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
+Controller node fsl,mpc5121-psc-fifo is requered there:
+
+fsl,mpc5121-psc-uart nodes
+--------------------------
+
+Required properties :
+ - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
+ - cell-index : Index of the PSC in hardware
+ - reg : Offset and length of the register set for the PSC device
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+
+Recommended properties :
+ - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
+ - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
+
+
+fsl,mpc5121-psc-fifo node
+-------------------------
+
+Required properties :
+ - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - reg : Offset and length of the register set for the PSC
+         FIFO Controller
+ - interrupts : <a b> where a is the interrupt number of the
+   PSC FIFO Controller and b is a field that represents an
+   encoding of the sense and level information for the interrupt.
+ - interrupt-parent : the phandle for the interrupt controller that
+   services interrupts for this device.
+
+
+Example for a board using PSC0 and PSC1 devices in serial mode:
+
+serial@11000 {
+        compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+        cell-index = <0>;
+        reg = <0x11000 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+        fsl,rx-fifo-size = <16>;
+        fsl,tx-fifo-size = <16>;
+};
+
+serial@11100 {
+        compatible = "fsl,mpc5121-psc-uart", "fsl,mpc5121-psc";
+        cell-index = <1>;
+        reg = <0x11100 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+        fsl,rx-fifo-size = <16>;
+        fsl,tx-fifo-size = <16>;
+};
+
+pscfifo@11f00 {
+        compatible = "fsl,mpc5121-psc-fifo";
+        reg = <0x11f00 0x100>;
+        interrupts = <40 0x8>;
+        interrupt-parent = < &ipic >;
+};
diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
index 5c6602dbfdc2..4ccb2cd5df94 100644
--- a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
@@ -195,11 +195,4 @@ External interrupts:
 
 fsl,mpc5200-mscan nodes
 -----------------------
-In addition to the required compatible-, reg- and interrupt-properites, you can
-also specify which clock source shall be used for the controller:
-
-- fsl,mscan-clock-source- a string describing the clock source. Valid values
-                          are:  "ip" for ip bus clock
-                                "ref" for reference clock (XTAL)
-                          "ref" is default in case this property is not
-                          present.
+See file can.txt in this directory.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index e7d9a344c4f4..80510c018eea 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -13,6 +13,11 @@ Required properties:
 - interrupt-parent : the phandle for the interrupt controller that
   services interrupts for this device.
 
+Optional properties:
+- gpios : specifies the gpio pins to be used for chipselects.
+  The gpios will be referred to as reg = <index> in the SPI child nodes.
+  If unspecified, a single SPI device without a chip select can be used.
+
 Example:
         spi@4c0 {
                 cell-index = <0>;
@@ -21,4 +26,6 @@ Example:
                 interrupts = <82 0>;
                 interrupt-parent = <700>;
                 mode = "cpu";
+                gpios = <&gpio 18 1     // device reg=<0>
+                         &gpio 19 1>;   // device reg=<1>
         };
diff --git a/Documentation/powerpc/ptrace.txt b/Documentation/powerpc/ptrace.txt
new file mode 100644
index 000000000000..f4a5499b7bc6
--- /dev/null
+++ b/Documentation/powerpc/ptrace.txt
@@ -0,0 +1,134 @@
+GDB intends to support the following hardware debug features of BookE
+processors:
+
+4 hardware breakpoints (IAC)
+2 hardware watchpoints (read, write and read-write) (DAC)
+2 value conditions for the hardware watchpoints (DVC)
+
+For that, we need to extend ptrace so that GDB can query and set these
+resources. Since we're extending, we're trying to create an interface
+that's extendable and that covers both BookE and server processors, so
+that GDB doesn't need to special-case each of them. We added the
+following 3 new ptrace requests.
+
+1. PTRACE_PPC_GETHWDEBUGINFO
+
+Query for GDB to discover the hardware debug features. The main info to
+be returned here is the minimum alignment for the hardware watchpoints.
+BookE processors don't have restrictions here, but server processors have
+an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
+adding special cases to GDB based on what it sees in AUXV.
+
+Since we're at it, we added other useful info that the kernel can return to
+GDB: this query will return the number of hardware breakpoints, hardware
+watchpoints and whether it supports a range of addresses and a condition.
+The query will fill the following structure provided by the requesting process:
+
+struct ppc_debug_info {
+       unit32_t version;
+       unit32_t num_instruction_bps;
+       unit32_t num_data_bps;
+       unit32_t num_condition_regs;
+       unit32_t data_bp_alignment;
+       unit32_t sizeof_condition; /* size of the DVC register */
+       uint64_t features; /* bitmask of the individual flags */
+};
+
+features will have bits indicating whether there is support for:
+
+#define PPC_DEBUG_FEATURE_INSN_BP_RANGE         0x1
+#define PPC_DEBUG_FEATURE_INSN_BP_MASK          0x2
+#define PPC_DEBUG_FEATURE_DATA_BP_RANGE         0x4
+#define PPC_DEBUG_FEATURE_DATA_BP_MASK          0x8
+
+2. PTRACE_SETHWDEBUG
+
+Sets a hardware breakpoint or watchpoint, according to the provided structure:
+
+struct ppc_hw_breakpoint {
+        uint32_t version;
+#define PPC_BREAKPOINT_TRIGGER_EXECUTE  0x1
+#define PPC_BREAKPOINT_TRIGGER_READ     0x2
+#define PPC_BREAKPOINT_TRIGGER_WRITE    0x4
+        uint32_t trigger_type;       /* only some combinations allowed */
+#define PPC_BREAKPOINT_MODE_EXACT               0x0
+#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE     0x1
+#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE     0x2
+#define PPC_BREAKPOINT_MODE_MASK                0x3
+        uint32_t addr_mode;          /* address match mode */
+
+#define PPC_BREAKPOINT_CONDITION_MODE   0x3
+#define PPC_BREAKPOINT_CONDITION_NONE   0x0
+#define PPC_BREAKPOINT_CONDITION_AND    0x1
+#define PPC_BREAKPOINT_CONDITION_EXACT  0x1     /* different name for the same thing as above */
+#define PPC_BREAKPOINT_CONDITION_OR     0x2
+#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
+#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000      /* byte enable bits */
+#define PPC_BREAKPOINT_CONDITION_BE(n)  (1<<((n)+16))
+        uint32_t condition_mode;     /* break/watchpoint condition flags */
+
+        uint64_t addr;
+        uint64_t addr2;
+        uint64_t condition_value;
+};
+
+A request specifies one event, not necessarily just one register to be set.
+For instance, if the request is for a watchpoint with a condition, both the
+DAC and DVC registers will be set in the same request.
+
+With this GDB can ask for all kinds of hardware breakpoints and watchpoints
+that the BookE supports. COMEFROM breakpoints available in server processors
+are not contemplated, but that is out of the scope of this work.
+
+ptrace will return an integer (handle) uniquely identifying the breakpoint or
+watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
+request to ask for its removal. Return -ENOSPC if the requested breakpoint
+can't be allocated on the registers.
+
+Some examples of using the structure to:
+
+- set a breakpoint in the first breakpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers on reads in the second watchpoint register
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = 0;
+
+- set a watchpoint which triggers only with a specific value
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_READ;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_EXACT;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
+  p.addr            = (uint64_t) address;
+  p.addr2           = 0;
+  p.condition_value = (uint64_t) condition;
+
+- set a ranged hardware breakpoint
+
+  p.version         = PPC_DEBUG_CURRENT_VERSION;
+  p.trigger_type    = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+  p.addr_mode       = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+  p.condition_mode  = PPC_BREAKPOINT_CONDITION_NONE;
+  p.addr            = (uint64_t) begin_range;
+  p.addr2           = (uint64_t) end_range;
+  p.condition_value = 0;
+
+3. PTRACE_DELHWDEBUG
+
+Takes an integer which identifies an existing breakpoint or watchpoint
+(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
+corresponding breakpoint or watchpoint..
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index aae8355d3166..221f38be98f4 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -190,3 +190,61 @@ Example:
   for (node = rb_first(&mytree); node; node = rb_next(node))
         printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
 
+Support for Augmented rbtrees
+-----------------------------
+
+Augmented rbtree is an rbtree with "some" additional data stored in each node.
+This data can be used to augment some new functionality to rbtree.
+Augmented rbtree is an optional feature built on top of basic rbtree
+infrastructure. rbtree user who wants this feature will have an augment
+callback function in rb_root initialized.
+
+This callback function will be called from rbtree core routines whenever
+a node has a change in one or both of its children. It is the responsibility
+of the callback function to recalculate the additional data that is in the
+rb node using new children information. Note that if this new additional
+data affects the parent node's additional data, then callback function has
+to handle it and do the recursive updates.
+
+
+Interval tree is an example of augmented rb tree. Reference -
+"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
+More details about interval trees:
+
+Classical rbtree has a single key and it cannot be directly used to store
+interval ranges like [lo:hi] and do a quick lookup for any overlap with a new
+lo:hi or to find whether there is an exact match for a new lo:hi.
+
+However, rbtree can be augmented to store such interval ranges in a structured
+way making it possible to do efficient lookup and exact match.
+
+This "extra information" stored in each node is the maximum hi
+(max_hi) value among all the nodes that are its descendents. This
+information can be maintained at each node just be looking at the node
+and its immediate children. And this will be used in O(log n) lookup
+for lowest match (lowest start address among all possible matches)
+with something like:
+
+find_lowest_match(lo, hi, node)
+{
+        lowest_match = NULL;
+        while (node) {
+                if (max_hi(node->left) > lo) {
+                        // Lowest overlap if any must be on left side
+                        node = node->left;
+                } else if (overlap(lo, hi, node)) {
+                        lowest_match = node;
+                        break;
+                } else if (lo > node->lo) {
+                        // Lowest overlap if any must be on right side
+                        node = node->right;
+                } else {
+                        break;
+                }
+        }
+        return lowest_match;
+}
+
+Finding exact match will be to first find lowest match and then to follow
+successor nodes looking for exact match, until the start of a node is beyond
+the hi value we are looking for.
diff --git a/Documentation/s390/CommonIO b/Documentation/s390/CommonIO
index 339207d11d95..d378cba66456 100644
--- a/Documentation/s390/CommonIO
+++ b/Documentation/s390/CommonIO
@@ -87,6 +87,12 @@ Command line parameters
   compatibility, by the device number in hexadecimal (0xabcd or abcd). Device
   numbers given as 0xabcd will be interpreted as 0.0.abcd.
 
+* /proc/cio_settle
+
+  A write request to this file is blocked until all queued cio actions are
+  handled. This will allow userspace to wait for pending work affecting
+  device availability after changing cio_ignore or the hardware configuration.
+
 * For some of the information present in the /proc filesystem in 2.4 (namely,
   /proc/subchannels and /proc/chpids), see driver-model.txt.
   Information formerly in /proc/irq_count is now in /proc/interrupts.
diff --git a/Documentation/s390/driver-model.txt b/Documentation/s390/driver-model.txt
index bde473df748d..ed265cf54cde 100644
--- a/Documentation/s390/driver-model.txt
+++ b/Documentation/s390/driver-model.txt
@@ -223,8 +223,8 @@ touched by the driver - it should use the ccwgroup device's driver_data for its
 private data.
 
 To implement a ccwgroup driver, please refer to include/asm/ccwgroup.h. Keep in
-mind that most drivers will need to implement both a ccwgroup and a ccw driver
-(unless you have a meta ccw driver, like cu3088 for lcs and ctc).
+mind that most drivers will need to implement both a ccwgroup and a ccw
+driver.
 
 
 2. Channel paths
diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt
index 6f5ceb0f09fc..85f3280d7ef6 100644
--- a/Documentation/s390/kvm.txt
+++ b/Documentation/s390/kvm.txt
@@ -102,7 +102,7 @@ args:		unsigned long
 see also:       include/linux/kvm.h
 This ioctl stores the state of the cpu at the guest real address given as
 argument, unless one of the following values defined in include/linux/kvm.h
-is given as arguement:
+is given as argument:
 KVM_S390_STORE_STATUS_NOADDR - the CPU stores its status to the save area in
 absolute lowcore as defined by the principles of operation
 KVM_S390_STORE_STATUS_PREFIXED - the CPU stores its status to the save area in
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 6f33593e59e2..8239ebbcddce 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -211,7 +211,7 @@ provide fair CPU time to each such task group.  For example, it may be
 desirable to first provide fair CPU time to each user on the system and then to
 each task belonging to a user.
 
-CONFIG_GROUP_SCHED strives to achieve exactly that.  It lets tasks to be
+CONFIG_CGROUP_SCHED strives to achieve exactly that.  It lets tasks to be
 grouped and divides CPU time fairly among such groups.
 
 CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
@@ -220,38 +220,11 @@ SCHED_RR) tasks.
 CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
 SCHED_BATCH) tasks.
 
-At present, there are two (mutually exclusive) mechanisms to group tasks for
-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
+   These options need CONFIG_CGROUPS to be defined, and let the administrator
    create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
    Documentation/cgroups/cgroups.txt for more information about this filesystem.
 
-Only one of these options to group tasks can be chosen and not both.
-
-When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
-user and a "cpu_share" file is added in that directory.
-
-        # cd /sys/kernel/uids
-        # cat 512/cpu_share             # Display user 512's CPU share
-        1024
-        # echo 2048 > 512/cpu_share     # Modify user 512's CPU share
-        # cat 512/cpu_share             # Display user 512's CPU share
-        2048
-        #
-
-CPU bandwidth between two users is divided in the ratio of their CPU shares.
-For example: if you would like user "root" to get twice the bandwidth of user
-"guest," then set the cpu_share for both the users such that "root"'s cpu_share
-is twice "guest"'s cpu_share.
-
-When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
+When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
@@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
         # #Launch gmplayer (or your favourite movie player)
         # echo <movie_player_pid> > multimedia/tasks
-
-8. Implementation note: user namespaces
-
-User namespaces are intended to be hierarchical.  But they are currently
-only partially implemented.  Each of those has ramifications for CFS.
-
-First, since user namespaces are hierarchical, the /sys/kernel/uids
-presentation is inadequate.  Eventually we will likely want to use sysfs
-tagging to provide private views of /sys/kernel/uids within each user
-namespace.
-
-Second, the hierarchical nature is intended to support completely
-unprivileged use of user namespaces.  So if using user groups, then
-we want the users in a user namespace to be children of the user
-who created it.
-
-That is currently unimplemented.  So instead, every user in a new
-user namespace will receive 1024 shares just like any user in the
-initial user namespace.  Note that at the moment creation of a new
-user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and
-CAP_SETGID.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 86eabe6c3419..605b0d40329d 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -126,23 +126,12 @@ priority!
 2.3 Basis for grouping tasks
 ----------------------------
 
-There are two compile-time settings for allocating CPU bandwidth. These are
-configured using the "Basis for grouping tasks" multiple choice menu under
-General setup > Group CPU Scheduler:
-
-a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" =  "user id")
-
-This lets you use the virtual files under
-"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for
-each user .
-
-The other option is:
-
-.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
+Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
+CPU bandwidth to task groups.
 
 This uses the /cgroup virtual file system and
 "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group instead.
+control group.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 
 There is work in progress to make the scheduling period for each group
-("/sys/kernel/uids/<uid>/cpu_rt_period_us" or
-"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well.
+("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
 
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/Documentation/scsi/ChangeLog.lpfc b/Documentation/scsi/ChangeLog.lpfc
index ff19a52fe004..2ffc1148eb95 100644
--- a/Documentation/scsi/ChangeLog.lpfc
+++ b/Documentation/scsi/ChangeLog.lpfc
@@ -989,8 +989,8 @@ Changes from 20040709 to 20040716
         * Remove redundant port_cmp != 2 check in if
           (!port_cmp) { .... if (port_cmp != 2).... }
         * Clock changes: removed struct clk_data and timerList.
-        * Clock changes: seperate nodev_tmo and els_retry_delay into 2
-          seperate timers and convert to 1 argument changed
+        * Clock changes: separate nodev_tmo and els_retry_delay into 2
+          separate timers and convert to 1 argument changed
           LPFC_NODE_FARP_PEND_t to struct lpfc_node_farp_pend convert
           ipfarp_tmo to 1 argument convert target struct tmofunc and
           rtplunfunc to 1 argument * cr_count, cr_delay and
@@ -1514,7 +1514,7 @@ Changes from 20040402 to 20040409
         * Remove unused elxclock declaration in elx_sli.h.
         * Since everywhere IOCB_ENTRY is used, the return value is cast,
           move the cast into the macro.
-        * Split ioctls out into seperate files
+        * Split ioctls out into separate files
 
 Changes from 20040326 to 20040402
 
@@ -1534,7 +1534,7 @@ Changes from 20040326 to 20040402
         * Unused variable cleanup
         * Use Linux list macros for DMABUF_t
         * Break up ioctls into 3 sections, dfc, util, hbaapi
-          rearranged code so this could be easily seperated into a
+          rearranged code so this could be easily separated into a
           differnet module later All 3 are currently turned on by
           defines in lpfc_ioctl.c LPFC_DFC_IOCTL, LPFC_UTIL_IOCTL,
           LPFC_HBAAPI_IOCTL
@@ -1551,7 +1551,7 @@ Changes from 20040326 to 20040402
           started by lpfc_online().  lpfc_offline() only stopped
           els_timeout routine.  It now stops all timeout routines
           associated with that hba.
-        * Replace seperate next and prev pointers in struct
+        * Replace separate next and prev pointers in struct
           lpfc_bindlist with list_head type.  In elxHBA_t, replace
           fc_nlpbind_start and _end with fc_nlpbind_list and use
           list_head macros to access it.
diff --git a/Documentation/scsi/ChangeLog.megaraid_sas b/Documentation/scsi/ChangeLog.megaraid_sas
index 17ffa0607712..30023568805e 100644
--- a/Documentation/scsi/ChangeLog.megaraid_sas
+++ b/Documentation/scsi/ChangeLog.megaraid_sas
@@ -1,3 +1,19 @@
+1 Release Date    : Thur.  Oct 29, 2009 09:12:45 PST 2009 -
+                        (emaild-id:megaraidlinux@lsi.com)
+                        Bo Yang
+
+2 Current Version : 00.00.04.17.1-rc1
+3 Older Version   : 00.00.04.12
+
+1.      Add the pad_0 in mfi frame structure to 0 to fix the
+        context value larger than 32bit value issue.
+
+2.      Add the logic drive list to the driver.  Driver will
+        keep the logic drive list internal after driver load.
+
+3.      driver fixed the device update issue after get the AEN
+        PD delete/ADD, LD add/delete from FW.
+
 1 Release Date    : Tues.  July 28, 2009 10:12:45 PST 2009 -
                         (emaild-id:megaraidlinux@lsi.com)
                         Bo Yang
diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt
index 5e5349a4fcd2..7c900507279f 100644
--- a/Documentation/serial/tty.txt
+++ b/Documentation/serial/tty.txt
@@ -105,6 +105,10 @@ write_wakeup()	-	May be called at any point between open and close.
                         is permitted to call the driver write method from
                         this function. In such a situation defer it.
 
+dcd_change()    -       Report to the tty line the current DCD pin status
+                        changes and the relative timestamp. The timestamp
+                        can be NULL.
+
 
 Driver Access
 
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 8923597bd2bd..bfcbbf88c44d 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -482,6 +482,9 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     reference_rate      - reference sample rate, 44100 or 48000 (default)
     multiple            - multiple to ref. sample rate, 1 or 2 (default)
+    subsystem           - override the PCI SSID for probing; the value
+                          consists of SSVID << 16 | SSDID.  The default is
+                          zero, which means no override.
 
     This module supports multiple cards.
 
@@ -1123,6 +1126,21 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     This module supports multiple cards, autoprobe and ISA PnP.
 
+  Module snd-jazz16
+  -------------------
+
+    Module for Media Vision Jazz16 chipset. The chipset consists of 3 chips:
+    MVD1216 + MVA416 + MVA514.
+
+    port        - port # for SB DSP chip (0x210,0x220,0x230,0x240,0x250,0x260)
+    irq         - IRQ # for SB DSP chip (3,5,7,9,10,15)
+    dma8        - DMA # for SB DSP chip (1,3)
+    dma16       - DMA # for SB DSP chip (5,7)
+    mpu_port    - MPU-401 port # (0x300,0x310,0x320,0x330)
+    mpu_irq     - MPU-401 irq # (2,3,5,7)
+
+    This module supports multiple cards.
+
   Module snd-korg1212
   -------------------
 
@@ -1791,6 +1809,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     The power-management is supported.
 
+  Module snd-ua101
+  ----------------
+
+    Module for the Edirol UA-101/UA-1000 audio/MIDI interfaces.
+
+    This module supports multiple devices, autoprobe and hotplugging.
+
   Module snd-usb-audio
   --------------------
 
@@ -1923,7 +1948,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, HDAV1.3 (Deluxe), Essence ST
+    i.e., Xonar D1, DX, D2, D2X, DS, HDAV1.3 (Deluxe), Essence ST
     (Deluxe) and Essence STX.
 
     This module supports autoprobe and multiple cards.
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index e72cee9e2a71..1d38b0dfba95 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -124,6 +124,8 @@ ALC882/883/885/888/889
   asus-a7m      ASUS A7M
   macpro        MacPro support
   mb5           Macbook 5,1
+  macmini3      Macmini 3,1
+  mba21         Macbook Air 2,1
   mbp3          Macbook Pro rev3
   imac24        iMac 24'' with jack detection
   imac91        iMac 9,1
@@ -279,13 +281,16 @@ Conexant 5051
   laptop        Basic Laptop config (default)
   hp            HP Spartan laptop
   hp-dv6736     HP dv6736
+  hp-f700       HP Compaq Presario F700
   lenovo-x200   Lenovo X200 laptop
+  toshiba       Toshiba Satellite M300
 
 Conexant 5066
 =============
   laptop        Basic Laptop config (default)
   dell-laptop   Dell laptops
   olpc-xo-1_5   OLPC XO 1.5
+  ideapad       Lenovo IdeaPad U150
 
 STAC9200
 ========
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index 6325bec06a72..98d14cb8a85d 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -119,10 +119,18 @@ the codec slots 0 and 1 no matter what the hardware reports.
 
 Interrupt Handling
 ~~~~~~~~~~~~~~~~~~
-In rare but some cases, the interrupt isn't properly handled as
-default.  You would notice this by the DMA transfer error reported by
-ALSA PCM core, for example.  Using MSI might help in such a case.
-Pass `enable_msi=1` option for enabling MSI.
+HD-audio driver uses MSI as default (if available) since 2.6.33
+kernel as MSI works better on some machines, and in general, it's
+better for performance.  However, Nvidia controllers showed bad
+regressions with MSI (especially in a combination with AMD chipset),
+thus we disabled MSI for them.
+
+There seem also still other devices that don't work with MSI.  If you
+see a regression wrt the sound quality (stuttering, etc) or a lock-up
+in the recent kernel, try to pass `enable_msi=0` option to disable
+MSI.  If it works, you can add the known bad device to the blacklist
+defined in hda_intel.c.  In such a case, please report and give the
+patch back to the upstream developer. 
 
 
 HD-AUDIO CODEC
@@ -452,6 +460,33 @@ Similarly, the lines after `[verb]` are parsed as `init_verbs`
 sysfs entries, and the lines after `[hint]` are parsed as `hints`
 sysfs entries, respectively.
 
+Another example to override the codec vendor id from 0x12345678 to
+0xdeadbeef is like below:
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+
+  [vendor_id]
+  0xdeadbeef
+------------------------------------------------------------------------
+
+In the similar way, you can override the codec subsystem_id via
+`[subsystem_id]`, the revision id via `[revision_id]` line.
+Also, the codec chip name can be rewritten via `[chip_name]` line.
+------------------------------------------------------------------------
+  [codec]
+  0x12345678 0xabcd1234 2
+
+  [subsystem_id]
+  0xffff1111
+
+  [revision_id]
+  0x10
+
+  [chip_name]
+  My-own NEWS-0002
+------------------------------------------------------------------------
+
 The hd-audio driver reads the file via request_firmware().  Thus,
 a patch file has to be located on the appropriate firmware path,
 typically, /lib/firmware.  For example, when you pass the option
diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index 10abd3773e49..16feda901469 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -58,7 +58,7 @@ static void transfer(int fd)
         };
 
         ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-        if (ret == 1)
+        if (ret < 1)
                 pabort("can't send spi message");
 
         for (ret = 0; ret < ARRAY_SIZE(tx); ret++) {
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index 5effa5bd993b..e213f45cf9d7 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the
  - It cannot contain any "trivial" fixes in it (spelling changes,
    whitespace cleanups, etc).
  - It must follow the Documentation/SubmittingPatches rules.
- - It or an equivalent fix must already exist in Linus' tree.  Quote the
-   respective commit ID in Linus' tree in your patch submission to -stable.
+ - It or an equivalent fix must already exist in Linus' tree (upstream).
 
 
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.
- - To have the patch automatically included in the stable tree, add the
-   the tag
+   stable@kernel.org.  You must note the upstream commit ID in the changelog
+   of your submission.
+ - To have the patch automatically included in the stable tree, add the tag
      Cc: stable@kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index fc5790d36cd9..6c7d18c53f84 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -573,11 +573,14 @@ Because other nodes' memory may be free. This means system total status
 may be not fatal yet.
 
 If this is set to 2, the kernel panics compulsorily even on the
-above-mentioned.
+above-mentioned. Even oom happens under memory cgroup, the whole
+system panics.
 
 The default value is 0.
 1 and 2 are for failover of clustering. Please select either
 according to your policy of failover.
+panic_on_oom=2+kdump gives you very strong tool to investigate
+why oom happens. You can get snapshot.
 
 =============================================================
 
diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX
index 397dc35e1323..a9248da5cdbc 100644
--- a/Documentation/timers/00-INDEX
+++ b/Documentation/timers/00-INDEX
@@ -4,6 +4,8 @@ highres.txt
         - High resolution timers and dynamic ticks design notes
 hpet.txt
         - High Precision Event Timer Driver for Linux
+hpet_example.c
+        - sample hpet timer test program
 hrtimers.txt
         - subsystem for high-resolution kernel timers
 timer_stats.txt
diff --git a/Documentation/timers/Makefile b/Documentation/timers/Makefile
new file mode 100644
index 000000000000..c85625f4ab25
--- /dev/null
+++ b/Documentation/timers/Makefile
@@ -0,0 +1,8 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := hpet_example
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 16d25e6b5a00..767392ffd31e 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -26,274 +26,5 @@ initialization.  An example of this initialization can be found in
 arch/x86/kernel/hpet.c.
 
 The driver provides a userspace API which resembles the API found in the
-RTC driver framework.  An example user space program is provided below.
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <string.h>
-#include <memory.h>
-#include <malloc.h>
-#include <time.h>
-#include <ctype.h>
-#include <sys/types.h>
-#include <sys/wait.h>
-#include <signal.h>
-#include <fcntl.h>
-#include <errno.h>
-#include <sys/time.h>
-#include <linux/hpet.h>
-
-
-extern void hpet_open_close(int, const char **);
-extern void hpet_info(int, const char **);
-extern void hpet_poll(int, const char **);
-extern void hpet_fasync(int, const char **);
-extern void hpet_read(int, const char **);
-
-#include <sys/poll.h>
-#include <sys/ioctl.h>
-#include <signal.h>
-
-struct hpet_command {
-        char            *command;
-        void            (*func)(int argc, const char ** argv);
-} hpet_command[] = {
-        {
-                "open-close",
-                hpet_open_close
-        },
-        {
-                "info",
-                hpet_info
-        },
-        {
-                "poll",
-                hpet_poll
-        },
-        {
-                "fasync",
-                hpet_fasync
-        },
-};
-
-int
-main(int argc, const char ** argv)
-{
-        int     i;
-
-        argc--;
-        argv++;
-
-        if (!argc) {
-                fprintf(stderr, "-hpet: requires command\n");
-                return -1;
-        }
-
-
-        for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
-                if (!strcmp(argv[0], hpet_command[i].command)) {
-                        argc--;
-                        argv++;
-                        fprintf(stderr, "-hpet: executing %s\n",
-                                hpet_command[i].command);
-                        hpet_command[i].func(argc, argv);
-                        return 0;
-                }
-
-        fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
-
-        return -1;
-}
-
-void
-hpet_open_close(int argc, const char **argv)
-{
-        int     fd;
-
-        if (argc != 1) {
-                fprintf(stderr, "hpet_open_close: device-name\n");
-                return;
-        }
-
-        fd = open(argv[0], O_RDONLY);
-        if (fd < 0)
-                fprintf(stderr, "hpet_open_close: open failed\n");
-        else
-                close(fd);
-
-        return;
-}
-
-void
-hpet_info(int argc, const char **argv)
-{
-}
-
-void
-hpet_poll(int argc, const char **argv)
-{
-        unsigned long           freq;
-        int                     iterations, i, fd;
-        struct pollfd           pfd;
-        struct hpet_info        info;
-        struct timeval          stv, etv;
-        struct timezone         tz;
-        long                    usec;
-
-        if (argc != 3) {
-                fprintf(stderr, "hpet_poll: device-name freq iterations\n");
-                return;
-        }
-
-        freq = atoi(argv[1]);
-        iterations = atoi(argv[2]);
-
-        fd = open(argv[0], O_RDONLY);
-
-        if (fd < 0) {
-                fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
-                return;
-        }
-
-        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-                fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
-                goto out;
-        }
-
-        if (ioctl(fd, HPET_INFO, &info) < 0) {
-                fprintf(stderr, "hpet_poll: failed to get info\n");
-                goto out;
-        }
-
-        fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
-
-        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-                fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
-                goto out;
-        }
-
-        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-                fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
-                goto out;
-        }
-
-        pfd.fd = fd;
-        pfd.events = POLLIN;
-
-        for (i = 0; i < iterations; i++) {
-                pfd.revents = 0;
-                gettimeofday(&stv, &tz);
-                if (poll(&pfd, 1, -1) < 0)
-                        fprintf(stderr, "hpet_poll: poll failed\n");
-                else {
-                        long    data;
-
-                        gettimeofday(&etv, &tz);
-                        usec = stv.tv_sec * 1000000 + stv.tv_usec;
-                        usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
-
-                        fprintf(stderr,
-                                "hpet_poll: expired time = 0x%lx\n", usec);
-
-                        fprintf(stderr, "hpet_poll: revents = 0x%x\n",
-                                pfd.revents);
-
-                        if (read(fd, &data, sizeof(data)) != sizeof(data)) {
-                                fprintf(stderr, "hpet_poll: read failed\n");
-                        }
-                        else
-                                fprintf(stderr, "hpet_poll: data 0x%lx\n",
-                                        data);
-                }
-        }
-
-out:
-        close(fd);
-        return;
-}
-
-static int hpet_sigio_count;
-
-static void
-hpet_sigio(int val)
-{
-        fprintf(stderr, "hpet_sigio: called\n");
-        hpet_sigio_count++;
-}
-
-void
-hpet_fasync(int argc, const char **argv)
-{
-        unsigned long           freq;
-        int                     iterations, i, fd, value;
-        sig_t                   oldsig;
-        struct hpet_info        info;
-
-        hpet_sigio_count = 0;
-        fd = -1;
-
-        if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
-                fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
-                return;
-        }
-
-        if (argc != 3) {
-                fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
-                goto out;
-        }
-
-        fd = open(argv[0], O_RDONLY);
-
-        if (fd < 0) {
-                fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
-                return;
-        }
-
-
-        if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
-                ((value = fcntl(fd, F_GETFL)) == 1) ||
-                (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
-                fprintf(stderr, "hpet_fasync: fcntl failed\n");
-                goto out;
-        }
-
-        freq = atoi(argv[1]);
-        iterations = atoi(argv[2]);
-
-        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
-                fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
-                goto out;
-        }
-
-        if (ioctl(fd, HPET_INFO, &info) < 0) {
-                fprintf(stderr, "hpet_fasync: failed to get info\n");
-                goto out;
-        }
-
-        fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
-
-        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
-                fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
-                goto out;
-        }
-
-        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
-                fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
-                goto out;
-        }
-
-        for (i = 0; i < iterations; i++) {
-                (void) pause();
-                fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
-        }
-
-out:
-        signal(SIGIO, oldsig);
-
-        if (fd >= 0)
-                close(fd);
-
-        return;
-}
+RTC driver framework.  An example user space program is provided in
+file:Documentation/timers/hpet_example.c
diff --git a/Documentation/timers/hpet_example.c b/Documentation/timers/hpet_example.c
new file mode 100644
index 000000000000..f9ce2d9fdfd5
--- /dev/null
+++ b/Documentation/timers/hpet_example.c
@@ -0,0 +1,269 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <string.h>
+#include <memory.h>
+#include <malloc.h>
+#include <time.h>
+#include <ctype.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <signal.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <sys/time.h>
+#include <linux/hpet.h>
+
+
+extern void hpet_open_close(int, const char **);
+extern void hpet_info(int, const char **);
+extern void hpet_poll(int, const char **);
+extern void hpet_fasync(int, const char **);
+extern void hpet_read(int, const char **);
+
+#include <sys/poll.h>
+#include <sys/ioctl.h>
+#include <signal.h>
+
+struct hpet_command {
+        char            *command;
+        void            (*func)(int argc, const char ** argv);
+} hpet_command[] = {
+        {
+                "open-close",
+                hpet_open_close
+        },
+        {
+                "info",
+                hpet_info
+        },
+        {
+                "poll",
+                hpet_poll
+        },
+        {
+                "fasync",
+                hpet_fasync
+        },
+};
+
+int
+main(int argc, const char ** argv)
+{
+        int     i;
+
+        argc--;
+        argv++;
+
+        if (!argc) {
+                fprintf(stderr, "-hpet: requires command\n");
+                return -1;
+        }
+
+
+        for (i = 0; i < (sizeof (hpet_command) / sizeof (hpet_command[0])); i++)
+                if (!strcmp(argv[0], hpet_command[i].command)) {
+                        argc--;
+                        argv++;
+                        fprintf(stderr, "-hpet: executing %s\n",
+                                hpet_command[i].command);
+                        hpet_command[i].func(argc, argv);
+                        return 0;
+                }
+
+        fprintf(stderr, "do_hpet: command %s not implemented\n", argv[0]);
+
+        return -1;
+}
+
+void
+hpet_open_close(int argc, const char **argv)
+{
+        int     fd;
+
+        if (argc != 1) {
+                fprintf(stderr, "hpet_open_close: device-name\n");
+                return;
+        }
+
+        fd = open(argv[0], O_RDONLY);
+        if (fd < 0)
+                fprintf(stderr, "hpet_open_close: open failed\n");
+        else
+                close(fd);
+
+        return;
+}
+
+void
+hpet_info(int argc, const char **argv)
+{
+}
+
+void
+hpet_poll(int argc, const char **argv)
+{
+        unsigned long           freq;
+        int                     iterations, i, fd;
+        struct pollfd           pfd;
+        struct hpet_info        info;
+        struct timeval          stv, etv;
+        struct timezone         tz;
+        long                    usec;
+
+        if (argc != 3) {
+                fprintf(stderr, "hpet_poll: device-name freq iterations\n");
+                return;
+        }
+
+        freq = atoi(argv[1]);
+        iterations = atoi(argv[2]);
+
+        fd = open(argv[0], O_RDONLY);
+
+        if (fd < 0) {
+                fprintf(stderr, "hpet_poll: open of %s failed\n", argv[0]);
+                return;
+        }
+
+        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+                fprintf(stderr, "hpet_poll: HPET_IRQFREQ failed\n");
+                goto out;
+        }
+
+        if (ioctl(fd, HPET_INFO, &info) < 0) {
+                fprintf(stderr, "hpet_poll: failed to get info\n");
+                goto out;
+        }
+
+        fprintf(stderr, "hpet_poll: info.hi_flags 0x%lx\n", info.hi_flags);
+
+        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+                fprintf(stderr, "hpet_poll: HPET_EPI failed\n");
+                goto out;
+        }
+
+        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+                fprintf(stderr, "hpet_poll, HPET_IE_ON failed\n");
+                goto out;
+        }
+
+        pfd.fd = fd;
+        pfd.events = POLLIN;
+
+        for (i = 0; i < iterations; i++) {
+                pfd.revents = 0;
+                gettimeofday(&stv, &tz);
+                if (poll(&pfd, 1, -1) < 0)
+                        fprintf(stderr, "hpet_poll: poll failed\n");
+                else {
+                        long    data;
+
+                        gettimeofday(&etv, &tz);
+                        usec = stv.tv_sec * 1000000 + stv.tv_usec;
+                        usec = (etv.tv_sec * 1000000 + etv.tv_usec) - usec;
+
+                        fprintf(stderr,
+                                "hpet_poll: expired time = 0x%lx\n", usec);
+
+                        fprintf(stderr, "hpet_poll: revents = 0x%x\n",
+                                pfd.revents);
+
+                        if (read(fd, &data, sizeof(data)) != sizeof(data)) {
+                                fprintf(stderr, "hpet_poll: read failed\n");
+                        }
+                        else
+                                fprintf(stderr, "hpet_poll: data 0x%lx\n",
+                                        data);
+                }
+        }
+
+out:
+        close(fd);
+        return;
+}
+
+static int hpet_sigio_count;
+
+static void
+hpet_sigio(int val)
+{
+        fprintf(stderr, "hpet_sigio: called\n");
+        hpet_sigio_count++;
+}
+
+void
+hpet_fasync(int argc, const char **argv)
+{
+        unsigned long           freq;
+        int                     iterations, i, fd, value;
+        sig_t                   oldsig;
+        struct hpet_info        info;
+
+        hpet_sigio_count = 0;
+        fd = -1;
+
+        if ((oldsig = signal(SIGIO, hpet_sigio)) == SIG_ERR) {
+                fprintf(stderr, "hpet_fasync: failed to set signal handler\n");
+                return;
+        }
+
+        if (argc != 3) {
+                fprintf(stderr, "hpet_fasync: device-name freq iterations\n");
+                goto out;
+        }
+
+        fd = open(argv[0], O_RDONLY);
+
+        if (fd < 0) {
+                fprintf(stderr, "hpet_fasync: failed to open %s\n", argv[0]);
+                return;
+        }
+
+
+        if ((fcntl(fd, F_SETOWN, getpid()) == 1) ||
+                ((value = fcntl(fd, F_GETFL)) == 1) ||
+                (fcntl(fd, F_SETFL, value | O_ASYNC) == 1)) {
+                fprintf(stderr, "hpet_fasync: fcntl failed\n");
+                goto out;
+        }
+
+        freq = atoi(argv[1]);
+        iterations = atoi(argv[2]);
+
+        if (ioctl(fd, HPET_IRQFREQ, freq) < 0) {
+                fprintf(stderr, "hpet_fasync: HPET_IRQFREQ failed\n");
+                goto out;
+        }
+
+        if (ioctl(fd, HPET_INFO, &info) < 0) {
+                fprintf(stderr, "hpet_fasync: failed to get info\n");
+                goto out;
+        }
+
+        fprintf(stderr, "hpet_fasync: info.hi_flags 0x%lx\n", info.hi_flags);
+
+        if (info.hi_flags && (ioctl(fd, HPET_EPI, 0) < 0)) {
+                fprintf(stderr, "hpet_fasync: HPET_EPI failed\n");
+                goto out;
+        }
+
+        if (ioctl(fd, HPET_IE_ON, 0) < 0) {
+                fprintf(stderr, "hpet_fasync, HPET_IE_ON failed\n");
+                goto out;
+        }
+
+        for (i = 0; i < iterations; i++) {
+                (void) pause();
+                fprintf(stderr, "hpet_fasync: count = %d\n", hpet_sigio_count);
+        }
+
+out:
+        signal(SIGIO, oldsig);
+
+        if (fd >= 0)
+                close(fd);
+
+        return;
+}
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index 02ac6ed38b2d..778ddf38b82c 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option:
 
         trace_event=[event-list]
 
-The format of this boot option is the same as described in section 2.1.
+event-list is a comma separated list of events. See section 2.1 for event
+format.
 
 3. Defining an event-enabled tracepoint
 =======================================
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 6a5a579126b0..f1f81afee8a0 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -238,11 +238,10 @@ HAVE_SYSCALL_TRACEPOINTS
 
 You need very few things to get the syscalls tracing in an arch.
 
+- Support HAVE_ARCH_TRACEHOOK (see arch/Kconfig).
 - Have a NR_syscalls variable in <asm/unistd.h> that provides the number
   of syscalls supported by the arch.
-- Implement arch_syscall_addr() that resolves a syscall address from a
-  syscall number.
-- Support the TIF_SYSCALL_TRACEPOINT thread flags
+- Support the TIF_SYSCALL_TRACEPOINT thread flags.
 - Put the trace_sys_enter() and trace_sys_exit() tracepoints calls from ptrace
   in the ptrace syscalls tracing path.
 - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index bab3040da548..557c1edeccaf 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files:
         to be traced. Echoing names of functions into this file
         will limit the trace to only those functions.
 
+        This interface also allows for commands to be used. See the
+        "Filter commands" section for more details.
+
   set_ftrace_notrace:
 
         This has an effect opposite to that of
@@ -1337,12 +1340,14 @@ ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one
 can either use the sysctl function or set it via the proc system
 interface.
 
-  sysctl kernel.ftrace_dump_on_oops=1
+  sysctl kernel.ftrace_dump_on_oops=n
 
 or
 
-  echo 1 > /proc/sys/kernel/ftrace_dump_on_oops
+  echo n > /proc/sys/kernel/ftrace_dump_on_oops
 
+If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will
+only dump the buffer of the CPU that triggered the oops.
 
 Here's an example of such a dump after a null pointer
 dereference in a kernel module:
@@ -1588,7 +1593,7 @@ module author does not need to worry about it.
 
 When tracing is enabled, kstop_machine is called to prevent
 races with the CPUS executing code being modified (which can
-cause the CPU to do undesireable things), and the nops are
+cause the CPU to do undesirable things), and the nops are
 patched back to calls. But this time, they do not call mcount
 (which is just a function stub). They now call into the ftrace
 infrastructure.
@@ -1822,6 +1827,47 @@ this special filter via:
  echo > set_graph_function
 
 
+Filter commands
+---------------
+
+A few commands are supported by the set_ftrace_filter interface.
+Trace commands have the following format:
+
+<function>:<command>:<parameter>
+
+The following commands are supported:
+
+- mod
+  This command enables function filtering per module. The
+  parameter defines the module. For example, if only the write*
+  functions in the ext3 module are desired, run:
+
+   echo 'write*:mod:ext3' > set_ftrace_filter
+
+  This command interacts with the filter in the same way as
+  filtering based on function names. Thus, adding more functions
+  in a different module is accomplished by appending (>>) to the
+  filter file. Remove specific module functions by prepending
+  '!':
+
+   echo '!writeback*:mod:ext3' >> set_ftrace_filter
+
+- traceon/traceoff
+  These commands turn tracing on and off when the specified
+  functions are hit. The parameter determines how many times the
+  tracing system is turned on and off. If unspecified, there is
+  no limit. For example, to disable tracing when a schedule bug
+  is hit the first 5 times, run:
+
+   echo '__schedule_bug:traceoff:5' > set_ftrace_filter
+
+  These commands are cumulative whether or not they are appended
+  to set_ftrace_filter. To remove a command, prepend it by '!'
+  and drop the parameter:
+
+   echo '!__schedule_bug:traceoff' > set_ftrace_filter
+
+
 trace_pipe
 ----------
 
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 47aabeebbdf6..ec94748ae65b 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -24,6 +24,7 @@ Synopsis of kprobe_events
 -------------------------
   p[:[GRP/]EVENT] SYMBOL[+offs]|MEMADDR [FETCHARGS]     : Set a probe
   r[:[GRP/]EVENT] SYMBOL[+0] [FETCHARGS]                : Set a return probe
+  -:[GRP/]EVENT                                         : Clear a probe
 
  GRP            : Group name. If omitted, use "kprobes" for it.
  EVENT          : Event name. If omitted, the event name is generated
@@ -37,15 +38,14 @@ Synopsis of kprobe_events
   @SYM[+|-offs] : Fetch memory at SYM +|- offs (SYM should be a data symbol)
   $stackN       : Fetch Nth entry of stack (N >= 0)
   $stack        : Fetch stack address.
-  $argN         : Fetch function argument. (N >= 0)(*)
-  $retval       : Fetch return value.(**)
-  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(***)
-  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+  $retval       : Fetch return value.(*)
+  +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
+  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
+  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
+                  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
 
-  (*) aN may not correct on asmlinkaged functions and at the middle of
-      function body.
-  (**) only for return probe.
-  (***) this is useful for fetching a field of data structures.
+  (*) only for return probe.
+  (**) this is useful for fetching a field of data structures.
 
 
 Per-Probe Event Filtering
@@ -82,13 +82,16 @@ Usage examples
 To add a probe as a new event, write a new definition to kprobe_events
 as below.
 
-  echo p:myprobe do_sys_open dfd=$arg0 filename=$arg1 flags=$arg2 mode=$arg3 > /sys/kernel/debug/tracing/kprobe_events
+  echo 'p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack)' > /sys/kernel/debug/tracing/kprobe_events
 
  This sets a kprobe on the top of do_sys_open() function with recording
-1st to 4th arguments as "myprobe" event. As this example shows, users can
-choose more familiar names for each arguments.
+1st to 4th arguments as "myprobe" event. Note, which register/stack entry is
+assigned to each function argument depends on arch-specific ABI. If you unsure
+the ABI, please try to use probe subcommand of perf-tools (you can find it
+under tools/perf/).
+As this example shows, users can choose more familiar names for each arguments.
 
-  echo r:myretprobe do_sys_open $retval >> /sys/kernel/debug/tracing/kprobe_events
+  echo 'r:myretprobe do_sys_open $retval' >> /sys/kernel/debug/tracing/kprobe_events
 
  This sets a kretprobe on the return point of do_sys_open() function with
 recording return value as "myretprobe" event.
@@ -97,23 +100,24 @@ recording return value as "myretprobe" event.
 
   cat /sys/kernel/debug/tracing/events/kprobes/myprobe/format
 name: myprobe
-ID: 75
+ID: 780
 format:
-        field:unsigned short common_type;       offset:0;       size:2;
-        field:unsigned char common_flags;       offset:2;       size:1;
-        field:unsigned char common_preempt_count;       offset:3;       size:1;
-        field:int common_pid;   offset:4;       size:4;
-        field:int common_tgid;  offset:8;       size:4;
+        field:unsigned short common_type;       offset:0;       size:2; signed:0;
+        field:unsigned char common_flags;       offset:2;       size:1; signed:0;
+        field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
+        field:int common_pid;   offset:4;       size:4; signed:1;
+        field:int common_lock_depth;    offset:8;       size:4; signed:1;
 
-        field: unsigned long ip;        offset:16;tsize:8;
-        field: int nargs;       offset:24;tsize:4;
-        field: unsigned long dfd;       offset:32;tsize:8;
-        field: unsigned long filename;  offset:40;tsize:8;
-        field: unsigned long flags;     offset:48;tsize:8;
-        field: unsigned long mode;      offset:56;tsize:8;
+        field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
+        field:int __probe_nargs;        offset:16;      size:4; signed:1;
+        field:unsigned long dfd;        offset:20;      size:4; signed:0;
+        field:unsigned long filename;   offset:24;      size:4; signed:0;
+        field:unsigned long flags;      offset:28;      size:4; signed:0;
+        field:unsigned long mode;       offset:32;      size:4; signed:0;
 
-print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, REC->filename, REC->flags, REC->mode
 
+print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->__probe_ip,
+REC->dfd, REC->filename, REC->flags, REC->mode
 
  You can see that the event has 4 arguments as in the expressions you specified.
 
@@ -121,6 +125,12 @@ print fmt: "(%lx) dfd=%lx filename=%lx flags=%lx mode=%lx", REC->ip, REC->dfd, R
 
  This clears all probe points.
 
+ Or,
+
+  echo -:myprobe >> kprobe_events
+
+ This clears probe points selectively.
+
  Right after definition, each event is disabled by default. For tracing these
 events, you need to enable it.
 
@@ -146,4 +156,3 @@ events, you need to enable it.
 returns from SYMBOL(e.g. "sys_open+0x1b/0x1d <- do_sys_open" means kernel
 returns from do_sys_open to sys_open+0x1b).
 
-
diff --git a/Documentation/usb/error-codes.txt b/Documentation/usb/error-codes.txt
index 9cf83e8c27b8..d83703ea74b2 100644
--- a/Documentation/usb/error-codes.txt
+++ b/Documentation/usb/error-codes.txt
@@ -41,8 +41,8 @@ USB-specific:
 
 -EFBIG          Host controller driver can't schedule that many ISO frames.
 
--EPIPE          Specified endpoint is stalled.  For non-control endpoints,
-                reset this status with usb_clear_halt().
+-EPIPE          The pipe type specified in the URB doesn't match the
+                endpoint's actual type.
 
 -EMSGSIZE       (a) endpoint maxpacket size is zero; it is not usable
                     in the current interface altsetting.
@@ -60,6 +60,8 @@ USB-specific:
 
 -EHOSTUNREACH   URB was rejected because the device is suspended.
 
+-ENOEXEC        A control URB doesn't contain a Setup packet.
+
 
 **************************************************************************
 *                   Error codes returned by in urb->status               *
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index 3bf6818c8cf5..2790ad48cfc2 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -2,7 +2,7 @@
 
                  Alan Stern <stern@rowland.harvard.edu>
 
-                            November 10, 2009
+                            December 11, 2009
 
 
 
@@ -29,9 +29,9 @@ covered to some extent (see Documentation/power/*.txt for more
 information about system PM).
 
 Note: Dynamic PM support for USB is present only if the kernel was
-built with CONFIG_USB_SUSPEND enabled.  System PM support is present
-only if the kernel was built with CONFIG_SUSPEND or CONFIG_HIBERNATION
-enabled.
+built with CONFIG_USB_SUSPEND enabled (which depends on
+CONFIG_PM_RUNTIME).  System PM support is present only if the kernel
+was built with CONFIG_SUSPEND or CONFIG_HIBERNATION enabled.
 
 
         What is Remote Wakeup?
@@ -229,6 +229,11 @@ necessary operations by hand or add them to a udev script.  You can
 also change the idle-delay time; 2 seconds is not the best choice for
 every device.
 
+If a driver knows that its device has proper suspend/resume support,
+it can enable autosuspend all by itself.  For example, the video
+driver for a laptop's webcam might do this, since these devices are
+rarely used and so should normally be autosuspended.
+
 Sometimes it turns out that even when a device does work okay with
 autosuspend there are still problems.  For example, there are
 experimental patches adding autosuspend support to the usbhid driver,
@@ -321,69 +326,81 @@ driver does so by calling these six functions:
         void usb_autopm_get_interface_no_resume(struct usb_interface *intf);
         void usb_autopm_put_interface_no_suspend(struct usb_interface *intf);
 
-The functions work by maintaining a counter in the usb_interface
-structure.  When intf->pm_usage_count is > 0 then the interface is
-deemed to be busy, and the kernel will not autosuspend the interface's
-device.  When intf->pm_usage_count is <= 0 then the interface is
-considered to be idle, and the kernel may autosuspend the device.
+The functions work by maintaining a usage counter in the
+usb_interface's embedded device structure.  When the counter is > 0
+then the interface is deemed to be busy, and the kernel will not
+autosuspend the interface's device.  When the usage counter is = 0
+then the interface is considered to be idle, and the kernel may
+autosuspend the device.
 
-(There is a similar pm_usage_count field in struct usb_device,
+(There is a similar usage counter field in struct usb_device,
 associated with the device itself rather than any of its interfaces.
-This field is used only by the USB core.)
-
-Drivers must not modify intf->pm_usage_count directly; its value
-should be changed only be using the functions listed above.  Drivers
-are responsible for insuring that the overall change to pm_usage_count
-during their lifetime balances out to 0 (it may be necessary for the
-disconnect method to call usb_autopm_put_interface() one or more times
-to fulfill this requirement).  The first two routines use the PM mutex
-in struct usb_device for mutual exclusion; drivers using the async
-routines are responsible for their own synchronization and mutual
-exclusion.
-
-        usb_autopm_get_interface() increments pm_usage_count and
-        attempts an autoresume if the new value is > 0 and the
-        device is suspended.
-
-        usb_autopm_put_interface() decrements pm_usage_count and
-        attempts an autosuspend if the new value is <= 0 and the
-        device isn't suspended.
+This counter is used only by the USB core.)
+
+Drivers need not be concerned about balancing changes to the usage
+counter; the USB core will undo any remaining "get"s when a driver
+is unbound from its interface.  As a corollary, drivers must not call
+any of the usb_autopm_* functions after their diconnect() routine has
+returned.
+
+Drivers using the async routines are responsible for their own
+synchronization and mutual exclusion.
+
+        usb_autopm_get_interface() increments the usage counter and
+        does an autoresume if the device is suspended.  If the
+        autoresume fails, the counter is decremented back.
+
+        usb_autopm_put_interface() decrements the usage counter and
+        attempts an autosuspend if the new value is = 0.
 
         usb_autopm_get_interface_async() and
         usb_autopm_put_interface_async() do almost the same things as
-        their non-async counterparts.  The differences are: they do
-        not acquire the PM mutex, and they use a workqueue to do their
+        their non-async counterparts.  The big difference is that they
+        use a workqueue to do the resume or suspend part of their
         jobs.  As a result they can be called in an atomic context,
         such as an URB's completion handler, but when they return the
-        device will not generally not yet be in the desired state.
+        device will generally not yet be in the desired state.
 
         usb_autopm_get_interface_no_resume() and
         usb_autopm_put_interface_no_suspend() merely increment or
-        decrement the pm_usage_count value; they do not attempt to
-        carry out an autoresume or an autosuspend.  Hence they can be
-        called in an atomic context.
+        decrement the usage counter; they do not attempt to carry out
+        an autoresume or an autosuspend.  Hence they can be called in
+        an atomic context.
 
-The conventional usage pattern is that a driver calls
+The simplest usage pattern is that a driver calls
 usb_autopm_get_interface() in its open routine and
-usb_autopm_put_interface() in its close or release routine.  But
-other patterns are possible.
+usb_autopm_put_interface() in its close or release routine.  But other
+patterns are possible.
 
 The autosuspend attempts mentioned above will often fail for one
 reason or another.  For example, the power/level attribute might be
 set to "on", or another interface in the same device might not be
 idle.  This is perfectly normal.  If the reason for failure was that
-the device hasn't been idle for long enough, a delayed workqueue
-routine is automatically set up to carry out the operation when the
-autosuspend idle-delay has expired.
+the device hasn't been idle for long enough, a timer is scheduled to
+carry out the operation automatically when the autosuspend idle-delay
+has expired.
 
 Autoresume attempts also can fail, although failure would mean that
 the device is no longer present or operating properly.  Unlike
-autosuspend, there's no delay for an autoresume.
+autosuspend, there's no idle-delay for an autoresume.
 
 
         Other parts of the driver interface
         -----------------------------------
 
+Drivers can enable autosuspend for their devices by calling
+
+        usb_enable_autosuspend(struct usb_device *udev);
+
+in their probe() routine, if they know that the device is capable of
+suspending and resuming correctly.  This is exactly equivalent to
+writing "auto" to the device's power/level attribute.  Likewise,
+drivers can disable autosuspend by calling
+
+        usb_disable_autosuspend(struct usb_device *udev);
+
+This is exactly the same as writing "on" to the power/level attribute.
+
 Sometimes a driver needs to make sure that remote wakeup is enabled
 during autosuspend.  For example, there's not much point
 autosuspending a keyboard if the user can't cause the keyboard to do a
@@ -395,26 +412,27 @@ though, setting this flag won't cause the kernel to autoresume it.
 Normally a driver would set this flag in its probe method, at which
 time the device is guaranteed not to be autosuspended.)
 
-The synchronous usb_autopm_* routines have to run in a sleepable
-process context; they must not be called from an interrupt handler or
-while holding a spinlock.  In fact, the entire autosuspend mechanism
-is not well geared toward interrupt-driven operation.  However there
-is one thing a driver can do in an interrupt handler:
+If a driver does its I/O asynchronously in interrupt context, it
+should call usb_autopm_get_interface_async() before starting output and
+usb_autopm_put_interface_async() when the output queue drains.  When
+it receives an input event, it should call
 
         usb_mark_last_busy(struct usb_device *udev);
 
-This sets udev->last_busy to the current time.  udev->last_busy is the
-field used for idle-delay calculations; updating it will cause any
-pending autosuspend to be moved back.  The usb_autopm_* routines will
-also set the last_busy field to the current time.
-
-Calling urb_mark_last_busy() from within an URB completion handler is
-subject to races: The kernel may have just finished deciding the
-device has been idle for long enough but not yet gotten around to
-calling the driver's suspend method.  The driver would have to be
-responsible for synchronizing its suspend method with its URB
-completion handler and causing the autosuspend to fail with -EBUSY if
-an URB had completed too recently.
+in the event handler.  This sets udev->last_busy to the current time.
+udev->last_busy is the field used for idle-delay calculations;
+updating it will cause any pending autosuspend to be moved back.  Most
+of the usb_autopm_* routines will also set the last_busy field to the
+current time.
+
+Asynchronous operation is always subject to races.  For example, a
+driver may call one of the usb_autopm_*_interface_async() routines at
+a time when the core has just finished deciding the device has been
+idle for long enough but not yet gotten around to calling the driver's
+suspend method.  The suspend method must be responsible for
+synchronizing with the output request routine and the URB completion
+handler; it should cause autosuspends to fail with -EBUSY if the
+driver needs to use the device.
 
 External suspend calls should never be allowed to fail in this way,
 only autosuspend calls.  The driver can tell them apart by checking
@@ -422,75 +440,23 @@ the PM_EVENT_AUTO bit in the message.event argument to the suspend
 method; this bit will be set for internal PM events (autosuspend) and
 clear for external PM events.
 
-Many of the ingredients in the autosuspend framework are oriented
-towards interfaces: The usb_interface structure contains the
-pm_usage_cnt field, and the usb_autopm_* routines take an interface
-pointer as their argument.  But somewhat confusingly, a few of the
-pieces (i.e., usb_mark_last_busy()) use the usb_device structure
-instead.  Drivers need to keep this straight; they can call
-interface_to_usbdev() to find the device structure for a given
-interface.
-
 
-        Locking requirements
-        --------------------
+        Mutual exclusion
+        ----------------
 
-All three suspend/resume methods are always called while holding the
-usb_device's PM mutex.  For external events -- but not necessarily for
-autosuspend or autoresume -- the device semaphore (udev->dev.sem) will
-also be held.  This implies that external suspend/resume events are
-mutually exclusive with calls to probe, disconnect, pre_reset, and
-post_reset; the USB core guarantees that this is true of internal
-suspend/resume events as well.
+For external events -- but not necessarily for autosuspend or
+autoresume -- the device semaphore (udev->dev.sem) will be held when a
+suspend or resume method is called.  This implies that external
+suspend/resume events are mutually exclusive with calls to probe,
+disconnect, pre_reset, and post_reset; the USB core guarantees that
+this is true of autosuspend/autoresume events as well.
 
 If a driver wants to block all suspend/resume calls during some
-critical section, it can simply acquire udev->pm_mutex. Note that
-calls to resume may be triggered indirectly. Block IO due to memory
-allocations can make the vm subsystem resume a device. Thus while
-holding this lock you must not allocate memory with GFP_KERNEL or
-GFP_NOFS.
-
-Alternatively, if the critical section might call some of the
-usb_autopm_* routines, the driver can avoid deadlock by doing:
-
-        down(&udev->dev.sem);
-        rc = usb_autopm_get_interface(intf);
-
-and at the end of the critical section:
-
-        if (!rc)
-                usb_autopm_put_interface(intf);
-        up(&udev->dev.sem);
-
-Holding the device semaphore will block all external PM calls, and the
-usb_autopm_get_interface() will prevent any internal PM calls, even if
-it fails.  (Exercise: Why?)
-
-The rules for locking order are:
-
-        Never acquire any device semaphore while holding any PM mutex.
-
-        Never acquire udev->pm_mutex while holding the PM mutex for
-        a device that isn't a descendant of udev.
-
-In other words, PM mutexes should only be acquired going up the device
-tree, and they should be acquired only after locking all the device
-semaphores you need to hold.  These rules don't matter to drivers very
-much; they usually affect just the USB core.
-
-Still, drivers do need to be careful.  For example, many drivers use a
-private mutex to synchronize their normal I/O activities with their
-disconnect method.  Now if the driver supports autosuspend then it
-must call usb_autopm_put_interface() from somewhere -- maybe from its
-close method.  It should make the call while holding the private mutex,
-since a driver shouldn't call any of the usb_autopm_* functions for an
-interface from which it has been unbound.
-
-But the usb_autpm_* routines always acquire the device's PM mutex, and
-consequently the locking order has to be: private mutex first, PM
-mutex second.  Since the suspend method is always called with the PM
-mutex held, it mustn't try to acquire the private mutex.  It has to
-synchronize with the driver's I/O activities in some other way.
+critical section, the best way is to lock the device and call
+usb_autopm_get_interface() (and do the reverse at the end of the
+critical section).  Holding the device semaphore will block all
+external PM calls, and the usb_autopm_get_interface() will prevent any
+internal PM calls, even if it fails.  (Exercise: Why?)
 
 
         Interaction between dynamic PM and system PM
@@ -499,22 +465,11 @@ synchronize with the driver's I/O activities in some other way.
 Dynamic power management and system power management can interact in
 a couple of ways.
 
-Firstly, a device may already be manually suspended or autosuspended
-when a system suspend occurs.  Since system suspends are supposed to
-be as transparent as possible, the device should remain suspended
-following the system resume.  The 2.6.23 kernel obeys this principle
-for manually suspended devices but not for autosuspended devices; they
-do get resumed when the system wakes up.  (Presumably they will be
-autosuspended again after their idle-delay time expires.)  In later
-kernels this behavior will be fixed.
-
-(There is an exception.  If a device would undergo a reset-resume
-instead of a normal resume, and the device is enabled for remote
-wakeup, then the reset-resume takes place even if the device was
-already suspended when the system suspend began.  The justification is
-that a reset-resume is a kind of remote-wakeup event.  Or to put it
-another way, a device which needs a reset won't be able to generate
-normal remote-wakeup signals, so it ought to be resumed immediately.)
+Firstly, a device may already be autosuspended when a system suspend
+occurs.  Since system suspends are supposed to be as transparent as
+possible, the device should remain suspended following the system
+resume.  But this theory may not work out well in practice; over time
+the kernel's behavior in this regard has changed.
 
 Secondly, a dynamic power-management event may occur as a system
 suspend is underway.  The window for this is short, since system
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 7539e8fa1ffd..16ca030e1185 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -26,3 +26,4 @@
  25 -> Compro VideoMate E800                               [1858:e800]
  26 -> Hauppauge WinTV-HVR1290                             [0070:8551]
  27 -> Mygica X8558 PRO DMB-TH                             [14f1:8578]
+ 28 -> LEADTEK WinFast PxTV1200                            [107d:6f22]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index fce1e7eb0474..b4a767060ed7 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -174,3 +174,4 @@
 173 -> Zolid Hybrid TV Tuner PCI                [1131:2004]
 174 -> Asus Europa Hybrid OEM                   [1043:4847]
 175 -> Leadtek Winfast DTV1000S                 [107d:6655]
+176 -> Beholder BeholdTV 505 RDS                [0000:5051]
diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index e0d298fe8830..9b2e0dd6017e 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -81,3 +81,4 @@ tuner=80 - Philips FQ1216LME MK3 PAL/SECAM w/active loopthrough
 tuner=81 - Partsnic (Daewoo) PTI-5NF05
 tuner=82 - Philips CU1216L
 tuner=83 - NXP TDA18271
+tuner=84 - Sony BTF-Pxn01Z
diff --git a/Documentation/video4linux/README.tlg2300 b/Documentation/video4linux/README.tlg2300
new file mode 100644
index 000000000000..416ccb93d8c9
--- /dev/null
+++ b/Documentation/video4linux/README.tlg2300
@@ -0,0 +1,47 @@
+tlg2300 release notes
+====================
+
+This is a v4l2/dvb device driver for the tlg2300 chip.
+
+
+current status
+==============
+
+video
+        - support mmap and read().(no overlay)
+
+audio
+        - The driver will register a ALSA card for the audio input.
+
+vbi
+        - Works for almost TV norms.
+
+dvb-t
+        - works for DVB-T
+
+FM
+        - Works for radio.
+
+---------------------------------------------------------------------------
+TESTED APPLICATIONS:
+
+-VLC1.0.4 test the video and dvb. The GUI is friendly to use.
+
+-Mplayer test the video.
+
+-Mplayer test the FM. The mplayer should be compiled with --enable-radio and
+         --enable-radio-capture.
+        The command runs as this(The alsa audio registers to card 1):
+        #mplayer radio://103.7/capture/ -radio adevice=hw=1,0:arate=48000 \
+                -rawaudio rate=48000:channels=2
+
+---------------------------------------------------------------------------
+KNOWN PROBLEMS:
+about preemphasis:
+        You can set the preemphasis for radio by the following command:
+        #v4l2-ctl -d /dev/radio0 --set-ctrl=pre_emphasis_settings=1
+
+        "pre_emphasis_settings=1" means that you select the 50us. If you want
+        to select the 75us, please use "pre_emphasis_settings=2"
+
+
diff --git a/Documentation/video4linux/gspca.txt b/Documentation/video4linux/gspca.txt
index 1800a62cf135..181b9e6fd984 100644
--- a/Documentation/video4linux/gspca.txt
+++ b/Documentation/video4linux/gspca.txt
@@ -42,6 +42,7 @@ ov519		041e:4064	Creative Live! VISTA VF0420
 ov519           041e:4067       Creative Live! Cam Video IM (VF0350)
 ov519           041e:4068       Creative Live! VISTA VF0470
 spca561         0458:7004       Genius VideoCAM Express V2
+sn9c2028        0458:7005       Genius Smart 300, version 2
 sunplus         0458:7006       Genius Dsc 1.3 Smart
 zc3xx           0458:7007       Genius VideoCam V2
 zc3xx           0458:700c       Genius VideoCam V3
@@ -109,6 +110,7 @@ sunplus		04a5:3003	Benq DC 1300
 sunplus         04a5:3008       Benq DC 1500
 sunplus         04a5:300a       Benq DC 3410
 spca500         04a5:300c       Benq DC 1016
+benq            04a5:3035       Benq DC E300
 finepix         04cb:0104       Fujifilm FinePix 4800
 finepix         04cb:0109       Fujifilm FinePix A202
 finepix         04cb:010b       Fujifilm FinePix A203
@@ -142,6 +144,7 @@ sunplus		04fc:5360	Sunplus Generic
 spca500         04fc:7333       PalmPixDC85
 sunplus         04fc:ffff       Pure DigitalDakota
 spca501         0506:00df       3Com HomeConnect Lite
+sunplus         052b:1507       Megapixel 5 Pretec DC-1007
 sunplus         052b:1513       Megapix V4
 sunplus         052b:1803       MegaImage VI
 tv8532          0545:808b       Veo Stingray
@@ -151,6 +154,7 @@ sunplus		0546:3191	Polaroid Ion 80
 sunplus         0546:3273       Polaroid PDC2030
 ov519           054c:0154       Sonny toy4
 ov519           054c:0155       Sonny toy5
+cpia1           0553:0002       CPIA CPiA (version1) based cameras
 zc3xx           055f:c005       Mustek Wcam300A
 spca500         055f:c200       Mustek Gsmart 300
 sunplus         055f:c211       Kowa Bs888e Microcamera
@@ -188,8 +192,7 @@ spca500		06bd:0404	Agfa CL20
 spca500         06be:0800       Optimedia
 sunplus         06d6:0031       Trust 610 LCD PowerC@m Zoom
 spca506         06e1:a190       ADS Instant VCD
-ov534           06f8:3002       Hercules Blog Webcam
-ov534           06f8:3003       Hercules Dualpix HD Weblog
+ov534_9         06f8:3003       Hercules Dualpix HD Weblog
 sonixj          06f8:3004       Hercules Classic Silver
 sonixj          06f8:3008       Hercules Deluxe Optical Glass
 pac7302         06f8:3009       Hercules Classic Link
@@ -204,6 +207,7 @@ sunplus		0733:2221	Mercury Digital Pro 3.1p
 sunplus         0733:3261       Concord 3045 spca536a
 sunplus         0733:3281       Cyberpix S550V
 spca506         0734:043b       3DeMon USB Capture aka
+cpia1           0813:0001       QX3 camera
 ov519           0813:0002       Dual Mode USB Camera Plus
 spca500         084d:0003       D-Link DSC-350
 spca500         08ca:0103       Aiptek PocketDV
@@ -225,7 +229,8 @@ sunplus		08ca:2050	Medion MD 41437
 sunplus         08ca:2060       Aiptek PocketDV5300
 tv8532          0923:010f       ICM532 cams
 mars            093a:050f       Mars-Semi Pc-Camera
-mr97310a        093a:010f       Sakar Digital no. 77379
+mr97310a        093a:010e       All known CIF cams with this ID
+mr97310a        093a:010f       All known VGA cams with this ID
 pac207          093a:2460       Qtec Webcam 100
 pac207          093a:2461       HP Webcam
 pac207          093a:2463       Philips SPC 220 NC
@@ -302,6 +307,7 @@ sonixj		0c45:613b	Surfer SN-206
 sonixj          0c45:613c       Sonix Pccam168
 sonixj          0c45:6143       Sonix Pccam168
 sonixj          0c45:6148       Digitus DA-70811/ZSMC USB PC Camera ZS211/Microdia
+sonixj          0c45:614a       Frontech E-Ccam (JIL-2225)
 sn9c20x         0c45:6240       PC Camera (SN9C201 + MT9M001)
 sn9c20x         0c45:6242       PC Camera (SN9C201 + MT9M111)
 sn9c20x         0c45:6248       PC Camera (SN9C201 + OV9655)
@@ -324,6 +330,10 @@ sn9c20x		0c45:62b0	PC Camera (SN9C202 + MT9V011/MT9V111/MT9V112)
 sn9c20x         0c45:62b3       PC Camera (SN9C202 + OV9655)
 sn9c20x         0c45:62bb       PC Camera (SN9C202 + OV7660)
 sn9c20x         0c45:62bc       PC Camera (SN9C202 + HV7131R)
+sn9c2028        0c45:8001       Wild Planet Digital Spy Camera
+sn9c2028        0c45:8003       Sakar #11199, #6637x, #67480 keychain cams
+sn9c2028        0c45:8008       Mini-Shotz ms-350
+sn9c2028        0c45:800a       Vivitar Vivicam 3350B
 sunplus         0d64:0303       Sunplus FashionCam DXG
 ov519           0e96:c001       TRUST 380 USB2 SPACEC@M
 etoms           102c:6151       Qcam Sangha CIF
@@ -341,10 +351,11 @@ spca501		1776:501c	Arowana 300K CMOS Camera
 t613            17a1:0128       TASCORP JPEG Webcam, NGS Cyclops
 vc032x          17ef:4802       Lenovo Vc0323+MI1310_SOC
 pac207          2001:f115       D-Link DSB-C120
-sq905c          2770:9050       sq905c
-sq905c          2770:905c       DualCamera
-sq905           2770:9120       Argus Digital Camera DC1512
-sq905c          2770:913d       sq905c
+sq905c          2770:9050       Disney pix micro (CIF)
+sq905c          2770:9052       Disney pix micro 2 (VGA)
+sq905c          2770:905c       All 11 known cameras with this ID
+sq905           2770:9120       All 24 known cameras with this ID
+sq905c          2770:913d       All 4 known cameras with this ID
 spca500         2899:012c       Toptro Industrial
 ov519           8020:ef04       ov519
 spca508         8086:0110       Intel Easy PC Camera
diff --git a/Documentation/video4linux/v4l2-framework.txt b/Documentation/video4linux/v4l2-framework.txt
index 74d677c8b036..5155700c206b 100644
--- a/Documentation/video4linux/v4l2-framework.txt
+++ b/Documentation/video4linux/v4l2-framework.txt
@@ -599,99 +599,13 @@ video_device::minor fields.
 video buffer helper functions
 -----------------------------
 
-The v4l2 core API provides a standard method for dealing with video
-buffers. Those methods allow a driver to implement read(), mmap() and
-overlay() on a consistent way.
-
-There are currently methods for using video buffers on devices that
-supports DMA with scatter/gather method (videobuf-dma-sg), DMA with
-linear access (videobuf-dma-contig), and vmalloced buffers, mostly
-used on USB drivers (videobuf-vmalloc).
-
-Any driver using videobuf should provide operations (callbacks) for
-four handlers:
-
-ops->buf_setup   - calculates the size of the video buffers and avoid they
-                   to waste more than some maximum limit of RAM;
-ops->buf_prepare - fills the video buffer structs and calls
-                   videobuf_iolock() to alloc and prepare mmaped memory;
-ops->buf_queue   - advices the driver that another buffer were
-                   requested (by read() or by QBUF);
-ops->buf_release - frees any buffer that were allocated.
-
-In order to use it, the driver need to have a code (generally called at
-interrupt context) that will properly handle the buffer request lists,
-announcing that a new buffer were filled.
-
-The irq handling code should handle the videobuf task lists, in order
-to advice videobuf that a new frame were filled, in order to honor to a
-request. The code is generally like this one:
-        if (list_empty(&dma_q->active))
-                return;
-
-        buf = list_entry(dma_q->active.next, struct vbuffer, vb.queue);
-
-        if (!waitqueue_active(&buf->vb.done))
-                return;
-
-        /* Some logic to handle the buf may be needed here */
-
-        list_del(&buf->vb.queue);
-        do_gettimeofday(&buf->vb.ts);
-        wake_up(&buf->vb.done);
-
-Those are the videobuffer functions used on drivers, implemented on
-videobuf-core:
-
-- Videobuf init functions
-  videobuf_queue_sg_init()
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on drivers that uses DMA
-      Scatter/Gather buffers.
-
-  videobuf_queue_dma_contig_init
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on drivers that need DMA
-      contiguous buffers.
-
-  videobuf_queue_vmalloc_init()
-      Initializes the videobuf infrastructure. This function should be
-      called before any other videobuf function on USB (and other drivers)
-      that need a vmalloced type of videobuf.
-
-- videobuf_iolock()
-  Prepares the videobuf memory for the proper method (read, mmap, overlay).
-
-- videobuf_queue_is_busy()
-  Checks if a videobuf is streaming.
-
-- videobuf_queue_cancel()
-  Stops video handling.
-
-- videobuf_mmap_free()
-  frees mmap buffers.
-
-- videobuf_stop()
-  Stops video handling, ends mmap and frees mmap and other buffers.
-
-- V4L2 api functions. Those functions correspond to VIDIOC_foo ioctls:
-   videobuf_reqbufs(), videobuf_querybuf(), videobuf_qbuf(),
-   videobuf_dqbuf(), videobuf_streamon(), videobuf_streamoff().
-
-- V4L1 api function (corresponds to VIDIOCMBUF ioctl):
-   videobuf_cgmbuf()
-      This function is used to provide backward compatibility with V4L1
-      API.
-
-- Some help functions for read()/poll() operations:
-   videobuf_read_stream()
-      For continuous stream read()
-   videobuf_read_one()
-      For snapshot read()
-   videobuf_poll_stream()
-      polling help function
-
-The better way to understand it is to take a look at vivi driver. One
-of the main reasons for vivi is to be a videobuf usage example. the
-vivi_thread_tick() does the task that the IRQ callback would do on PCI
-drivers (or the irq callback on USB).
+The v4l2 core API provides a set of standard methods (called "videobuf")
+for dealing with video buffers. Those methods allow a driver to implement
+read(), mmap() and overlay() in a consistent way.  There are currently
+methods for using video buffers on devices that supports DMA with
+scatter/gather method (videobuf-dma-sg), DMA with linear access
+(videobuf-dma-contig), and vmalloced buffers, mostly used on USB drivers
+(videobuf-vmalloc).
+
+Please see Documentation/video4linux/videobuf for more information on how
+to use the videobuf layer.
diff --git a/Documentation/video4linux/videobuf b/Documentation/video4linux/videobuf
new file mode 100644
index 000000000000..17a1f9abf260
--- /dev/null
+++ b/Documentation/video4linux/videobuf
@@ -0,0 +1,360 @@
+An introduction to the videobuf layer
+Jonathan Corbet <corbet@lwn.net>
+Current as of 2.6.33
+
+The videobuf layer functions as a sort of glue layer between a V4L2 driver
+and user space.  It handles the allocation and management of buffers for
+the storage of video frames.  There is a set of functions which can be used
+to implement many of the standard POSIX I/O system calls, including read(),
+poll(), and, happily, mmap().  Another set of functions can be used to
+implement the bulk of the V4L2 ioctl() calls related to streaming I/O,
+including buffer allocation, queueing and dequeueing, and streaming
+control.  Using videobuf imposes a few design decisions on the driver
+author, but the payback comes in the form of reduced code in the driver and
+a consistent implementation of the V4L2 user-space API.
+
+Buffer types
+
+Not all video devices use the same kind of buffers.  In fact, there are (at
+least) three common variations:
+
+ - Buffers which are scattered in both the physical and (kernel) virtual
+   address spaces.  (Almost) all user-space buffers are like this, but it
+   makes great sense to allocate kernel-space buffers this way as well when
+   it is possible.  Unfortunately, it is not always possible; working with
+   this kind of buffer normally requires hardware which can do
+   scatter/gather DMA operations.
+
+ - Buffers which are physically scattered, but which are virtually
+   contiguous; buffers allocated with vmalloc(), in other words.  These
+   buffers are just as hard to use for DMA operations, but they can be
+   useful in situations where DMA is not available but virtually-contiguous
+   buffers are convenient.
+
+ - Buffers which are physically contiguous.  Allocation of this kind of
+   buffer can be unreliable on fragmented systems, but simpler DMA
+   controllers cannot deal with anything else.
+
+Videobuf can work with all three types of buffers, but the driver author
+must pick one at the outset and design the driver around that decision.
+
+[It's worth noting that there's a fourth kind of buffer: "overlay" buffers
+which are located within the system's video memory.  The overlay
+functionality is considered to be deprecated for most use, but it still
+shows up occasionally in system-on-chip drivers where the performance
+benefits merit the use of this technique.  Overlay buffers can be handled
+as a form of scattered buffer, but there are very few implementations in
+the kernel and a description of this technique is currently beyond the
+scope of this document.]
+
+Data structures, callbacks, and initialization
+
+Depending on which type of buffers are being used, the driver should
+include one of the following files:
+
+    <media/videobuf-dma-sg.h>           /* Physically scattered */
+    <media/videobuf-vmalloc.h>          /* vmalloc() buffers    */
+    <media/videobuf-dma-contig.h>       /* Physically contiguous */
+
+The driver's data structure describing a V4L2 device should include a
+struct videobuf_queue instance for the management of the buffer queue,
+along with a list_head for the queue of available buffers.  There will also
+need to be an interrupt-safe spinlock which is used to protect (at least)
+the queue.
+
+The next step is to write four simple callbacks to help videobuf deal with
+the management of buffers:
+
+    struct videobuf_queue_ops {
+        int (*buf_setup)(struct videobuf_queue *q,
+                         unsigned int *count, unsigned int *size);
+        int (*buf_prepare)(struct videobuf_queue *q,
+                           struct videobuf_buffer *vb,
+                           enum v4l2_field field);
+        void (*buf_queue)(struct videobuf_queue *q,
+                          struct videobuf_buffer *vb);
+        void (*buf_release)(struct videobuf_queue *q,
+                            struct videobuf_buffer *vb);
+    };
+
+buf_setup() is called early in the I/O process, when streaming is being
+initiated; its purpose is to tell videobuf about the I/O stream.  The count
+parameter will be a suggested number of buffers to use; the driver should
+check it for rationality and adjust it if need be.  As a practical rule, a
+minimum of two buffers are needed for proper streaming, and there is
+usually a maximum (which cannot exceed 32) which makes sense for each
+device.  The size parameter should be set to the expected (maximum) size
+for each frame of data.
+
+Each buffer (in the form of a struct videobuf_buffer pointer) will be
+passed to buf_prepare(), which should set the buffer's size, width, height,
+and field fields properly.  If the buffer's state field is
+VIDEOBUF_NEEDS_INIT, the driver should pass it to:
+
+    int videobuf_iolock(struct videobuf_queue* q, struct videobuf_buffer *vb,
+                        struct v4l2_framebuffer *fbuf);
+
+Among other things, this call will usually allocate memory for the buffer.
+Finally, the buf_prepare() function should set the buffer's state to
+VIDEOBUF_PREPARED.
+
+When a buffer is queued for I/O, it is passed to buf_queue(), which should
+put it onto the driver's list of available buffers and set its state to
+VIDEOBUF_QUEUED.  Note that this function is called with the queue spinlock
+held; if it tries to acquire it as well things will come to a screeching
+halt.  Yes, this is the voice of experience.  Note also that videobuf may
+wait on the first buffer in the queue; placing other buffers in front of it
+could again gum up the works.  So use list_add_tail() to enqueue buffers.
+
+Finally, buf_release() is called when a buffer is no longer intended to be
+used.  The driver should ensure that there is no I/O active on the buffer,
+then pass it to the appropriate free routine(s):
+
+    /* Scatter/gather drivers */
+    int videobuf_dma_unmap(struct videobuf_queue *q,
+                           struct videobuf_dmabuf *dma);
+    int videobuf_dma_free(struct videobuf_dmabuf *dma);
+
+    /* vmalloc drivers */
+    void videobuf_vmalloc_free (struct videobuf_buffer *buf);
+
+    /* Contiguous drivers */
+    void videobuf_dma_contig_free(struct videobuf_queue *q,
+                                  struct videobuf_buffer *buf);
+
+One way to ensure that a buffer is no longer under I/O is to pass it to:
+
+    int videobuf_waiton(struct videobuf_buffer *vb, int non_blocking, int intr);
+
+Here, vb is the buffer, non_blocking indicates whether non-blocking I/O
+should be used (it should be zero in the buf_release() case), and intr
+controls whether an interruptible wait is used.
+
+File operations
+
+At this point, much of the work is done; much of the rest is slipping
+videobuf calls into the implementation of the other driver callbacks.  The
+first step is in the open() function, which must initialize the
+videobuf queue.  The function to use depends on the type of buffer used:
+
+    void videobuf_queue_sg_init(struct videobuf_queue *q,
+                                struct videobuf_queue_ops *ops,
+                                struct device *dev,
+                                spinlock_t *irqlock,
+                                enum v4l2_buf_type type,
+                                enum v4l2_field field,
+                                unsigned int msize,
+                                void *priv);
+
+    void videobuf_queue_vmalloc_init(struct videobuf_queue *q,
+                                struct videobuf_queue_ops *ops,
+                                struct device *dev,
+                                spinlock_t *irqlock,
+                                enum v4l2_buf_type type,
+                                enum v4l2_field field,
+                                unsigned int msize,
+                                void *priv);
+
+    void videobuf_queue_dma_contig_init(struct videobuf_queue *q,
+                                       struct videobuf_queue_ops *ops,
+                                       struct device *dev,
+                                       spinlock_t *irqlock,
+                                       enum v4l2_buf_type type,
+                                       enum v4l2_field field,
+                                       unsigned int msize,
+                                       void *priv);
+
+In each case, the parameters are the same: q is the queue structure for the
+device, ops is the set of callbacks as described above, dev is the device
+structure for this video device, irqlock is an interrupt-safe spinlock to
+protect access to the data structures, type is the buffer type used by the
+device (cameras will use V4L2_BUF_TYPE_VIDEO_CAPTURE, for example), field
+describes which field is being captured (often V4L2_FIELD_NONE for
+progressive devices), msize is the size of any containing structure used
+around struct videobuf_buffer, and priv is a private data pointer which
+shows up in the priv_data field of struct videobuf_queue.  Note that these
+are void functions which, evidently, are immune to failure.
+
+V4L2 capture drivers can be written to support either of two APIs: the
+read() system call and the rather more complicated streaming mechanism.  As
+a general rule, it is necessary to support both to ensure that all
+applications have a chance of working with the device.  Videobuf makes it
+easy to do that with the same code.  To implement read(), the driver need
+only make a call to one of:
+
+    ssize_t videobuf_read_one(struct videobuf_queue *q,
+                              char __user *data, size_t count,
+                              loff_t *ppos, int nonblocking);
+
+    ssize_t videobuf_read_stream(struct videobuf_queue *q,
+                                 char __user *data, size_t count,
+                                 loff_t *ppos, int vbihack, int nonblocking);
+
+Either one of these functions will read frame data into data, returning the
+amount actually read; the difference is that videobuf_read_one() will only
+read a single frame, while videobuf_read_stream() will read multiple frames
+if they are needed to satisfy the count requested by the application.  A
+typical driver read() implementation will start the capture engine, call
+one of the above functions, then stop the engine before returning (though a
+smarter implementation might leave the engine running for a little while in
+anticipation of another read() call happening in the near future).
+
+The poll() function can usually be implemented with a direct call to:
+
+    unsigned int videobuf_poll_stream(struct file *file,
+                                      struct videobuf_queue *q,
+                                      poll_table *wait);
+
+Note that the actual wait queue eventually used will be the one associated
+with the first available buffer.
+
+When streaming I/O is done to kernel-space buffers, the driver must support
+the mmap() system call to enable user space to access the data.  In many
+V4L2 drivers, the often-complex mmap() implementation simplifies to a
+single call to:
+
+    int videobuf_mmap_mapper(struct videobuf_queue *q,
+                             struct vm_area_struct *vma);
+
+Everything else is handled by the videobuf code.
+
+The release() function requires two separate videobuf calls:
+
+    void videobuf_stop(struct videobuf_queue *q);
+    int videobuf_mmap_free(struct videobuf_queue *q);
+
+The call to videobuf_stop() terminates any I/O in progress - though it is
+still up to the driver to stop the capture engine.  The call to
+videobuf_mmap_free() will ensure that all buffers have been unmapped; if
+so, they will all be passed to the buf_release() callback.  If buffers
+remain mapped, videobuf_mmap_free() returns an error code instead.  The
+purpose is clearly to cause the closing of the file descriptor to fail if
+buffers are still mapped, but every driver in the 2.6.32 kernel cheerfully
+ignores its return value.
+
+ioctl() operations
+
+The V4L2 API includes a very long list of driver callbacks to respond to
+the many ioctl() commands made available to user space.  A number of these
+- those associated with streaming I/O - turn almost directly into videobuf
+calls.  The relevant helper functions are:
+
+    int videobuf_reqbufs(struct videobuf_queue *q,
+                         struct v4l2_requestbuffers *req);
+    int videobuf_querybuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b);
+    int videobuf_dqbuf(struct videobuf_queue *q, struct v4l2_buffer *b,
+                       int nonblocking);
+    int videobuf_streamon(struct videobuf_queue *q);
+    int videobuf_streamoff(struct videobuf_queue *q);
+    int videobuf_cgmbuf(struct videobuf_queue *q, struct video_mbuf *mbuf,
+                        int count);
+
+So, for example, a VIDIOC_REQBUFS call turns into a call to the driver's
+vidioc_reqbufs() callback which, in turn, usually only needs to locate the
+proper struct videobuf_queue pointer and pass it to videobuf_reqbufs().
+These support functions can replace a great deal of buffer management
+boilerplate in a lot of V4L2 drivers.
+
+The vidioc_streamon() and vidioc_streamoff() functions will be a bit more
+complex, of course, since they will also need to deal with starting and
+stopping the capture engine.  videobuf_cgmbuf(), called from the driver's
+vidiocgmbuf() function, only exists if the V4L1 compatibility module has
+been selected with CONFIG_VIDEO_V4L1_COMPAT, so its use must be surrounded
+with #ifdef directives.
+
+Buffer allocation
+
+Thus far, we have talked about buffers, but have not looked at how they are
+allocated.  The scatter/gather case is the most complex on this front.  For
+allocation, the driver can leave buffer allocation entirely up to the
+videobuf layer; in this case, buffers will be allocated as anonymous
+user-space pages and will be very scattered indeed.  If the application is
+using user-space buffers, no allocation is needed; the videobuf layer will
+take care of calling get_user_pages() and filling in the scatterlist array.
+
+If the driver needs to do its own memory allocation, it should be done in
+the vidioc_reqbufs() function, *after* calling videobuf_reqbufs().  The
+first step is a call to:
+
+    struct videobuf_dmabuf *videobuf_to_dma(struct videobuf_buffer *buf);
+
+The returned videobuf_dmabuf structure (defined in
+<media/videobuf-dma-sg.h>) includes a couple of relevant fields:
+
+    struct scatterlist  *sglist;
+    int                 sglen;
+
+The driver must allocate an appropriately-sized scatterlist array and
+populate it with pointers to the pieces of the allocated buffer; sglen
+should be set to the length of the array.
+
+Drivers using the vmalloc() method need not (and cannot) concern themselves
+with buffer allocation at all; videobuf will handle those details.  The
+same is normally true of contiguous-DMA drivers as well; videobuf will
+allocate the buffers (with dma_alloc_coherent()) when it sees fit.  That
+means that these drivers may be trying to do high-order allocations at any
+time, an operation which is not always guaranteed to work.  Some drivers
+play tricks by allocating DMA space at system boot time; videobuf does not
+currently play well with those drivers.
+
+As of 2.6.31, contiguous-DMA drivers can work with a user-supplied buffer,
+as long as that buffer is physically contiguous.  Normal user-space
+allocations will not meet that criterion, but buffers obtained from other
+kernel drivers, or those contained within huge pages, will work with these
+drivers.
+
+Filling the buffers
+
+The final part of a videobuf implementation has no direct callback - it's
+the portion of the code which actually puts frame data into the buffers,
+usually in response to interrupts from the device.  For all types of
+drivers, this process works approximately as follows:
+
+ - Obtain the next available buffer and make sure that somebody is actually
+   waiting for it.
+
+ - Get a pointer to the memory and put video data there.
+
+ - Mark the buffer as done and wake up the process waiting for it.
+
+Step (1) above is done by looking at the driver-managed list_head structure
+- the one which is filled in the buf_queue() callback.  Because starting
+the engine and enqueueing buffers are done in separate steps, it's possible
+for the engine to be running without any buffers available - in the
+vmalloc() case especially.  So the driver should be prepared for the list
+to be empty.  It is equally possible that nobody is yet interested in the
+buffer; the driver should not remove it from the list or fill it until a
+process is waiting on it.  That test can be done by examining the buffer's
+done field (a wait_queue_head_t structure) with waitqueue_active().
+
+A buffer's state should be set to VIDEOBUF_ACTIVE before being mapped for
+DMA; that ensures that the videobuf layer will not try to do anything with
+it while the device is transferring data.
+
+For scatter/gather drivers, the needed memory pointers will be found in the
+scatterlist structure described above.  Drivers using the vmalloc() method
+can get a memory pointer with:
+
+    void *videobuf_to_vmalloc(struct videobuf_buffer *buf);
+
+For contiguous DMA drivers, the function to use is:
+
+    dma_addr_t videobuf_to_dma_contig(struct videobuf_buffer *buf);
+
+The contiguous DMA API goes out of its way to hide the kernel-space address
+of the DMA buffer from drivers.
+
+The final step is to set the size field of the relevant videobuf_buffer
+structure to the actual size of the captured image, set state to
+VIDEOBUF_DONE, then call wake_up() on the done queue.  At this point, the
+buffer is owned by the videobuf layer and the driver should not touch it
+again.
+
+Developers who are interested in more information can go into the relevant
+header files; there are a few low-level functions declared there which have
+not been talked about here.  Also worthwhile is the vivi driver
+(drivers/media/video/vivi.c), which is maintained as an example of how V4L2
+drivers should be written.  Vivi only uses the vmalloc() API, but it's good
+enough to get started with.  Note also that all of these calls are exported
+GPL-only, so they will not be available to non-GPL kernel modules.
diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX
index e57d6a9dd32b..dca82d7c83d8 100644
--- a/Documentation/vm/00-INDEX
+++ b/Documentation/vm/00-INDEX
@@ -4,23 +4,35 @@ active_mm.txt
         - An explanation from Linus about tsk->active_mm vs tsk->mm.
 balance
         - various information on memory balancing.
+hugepage-mmap.c
+        - Example app using huge page memory with the mmap system call.
+hugepage-shm.c
+        - Example app using huge page memory with Sys V shared memory system calls.
 hugetlbpage.txt
         - a brief summary of hugetlbpage support in the Linux kernel.
+hwpoison.txt
+        - explains what hwpoison is
 ksm.txt
         - how to use the Kernel Samepage Merging feature.
 locking
         - info on how locking and synchronization is done in the Linux vm code.
+map_hugetlb.c
+        - an example program that uses the MAP_HUGETLB mmap flag.
 numa
         - information about NUMA specific code in the Linux vm.
 numa_memory_policy.txt
         - documentation of concepts and APIs of the 2.6 memory policy support.
 overcommit-accounting
         - description of the Linux kernels overcommit handling modes.
+page-types.c
+        - Tool for querying page flags
 page_migration
         - description of page migration in NUMA systems.
+pagemap.txt
+        - pagemap, from the userspace perspective
 slabinfo.c
         - source code for a tool to get reports about slabs.
 slub.txt
         - a short users guide for SLUB.
-map_hugetlb.c
-        - an example program that uses the MAP_HUGETLB mmap flag.
+unevictable-lru.txt
+        - Unevictable LRU infrastructure
diff --git a/Documentation/vm/Makefile b/Documentation/vm/Makefile
index 5bd269b3731a..9dcff328b964 100644
--- a/Documentation/vm/Makefile
+++ b/Documentation/vm/Makefile
@@ -2,7 +2,7 @@
 obj- := dummy.o
 
 # List of programs to build
-hostprogs-y := slabinfo page-types
+hostprogs-y := slabinfo page-types hugepage-mmap hugepage-shm map_hugetlb
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
diff --git a/Documentation/vm/hugepage-mmap.c b/Documentation/vm/hugepage-mmap.c
new file mode 100644
index 000000000000..db0dd9a33d54
--- /dev/null
+++ b/Documentation/vm/hugepage-mmap.c
@@ -0,0 +1,91 @@
+/*
+ * hugepage-mmap:
+ *
+ * Example of using huge page memory in a user application using the mmap
+ * system call.  Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 256MB that is backed by
+ * huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define FILE_NAME "/mnt/hugepagefile"
+#define LENGTH (256UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define FLAGS (MAP_SHARED | MAP_FIXED)
+#else
+#define ADDR (void *)(0x0UL)
+#define FLAGS (MAP_SHARED)
+#endif
+
+static void check_bytes(char *addr)
+{
+        printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+        unsigned long i;
+
+        for (i = 0; i < LENGTH; i++)
+                *(addr + i) = (char)i;
+}
+
+static void read_bytes(char *addr)
+{
+        unsigned long i;
+
+        check_bytes(addr);
+        for (i = 0; i < LENGTH; i++)
+                if (*(addr + i) != (char)i) {
+                        printf("Mismatch at %lu\n", i);
+                        break;
+                }
+}
+
+int main(void)
+{
+        void *addr;
+        int fd;
+
+        fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
+        if (fd < 0) {
+                perror("Open failed");
+                exit(1);
+        }
+
+        addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
+        if (addr == MAP_FAILED) {
+                perror("mmap");
+                unlink(FILE_NAME);
+                exit(1);
+        }
+
+        printf("Returned address is %p\n", addr);
+        check_bytes(addr);
+        write_bytes(addr);
+        read_bytes(addr);
+
+        munmap(addr, LENGTH);
+        close(fd);
+        unlink(FILE_NAME);
+
+        return 0;
+}
diff --git a/Documentation/vm/hugepage-shm.c b/Documentation/vm/hugepage-shm.c
new file mode 100644
index 000000000000..07956d8592c9
--- /dev/null
+++ b/Documentation/vm/hugepage-shm.c
@@ -0,0 +1,98 @@
+/*
+ * hugepage-shm:
+ *
+ * Example of using huge page memory in a user application using Sys V shared
+ * memory system calls.  In this example the app is requesting 256MB of
+ * memory that is backed by huge pages.  The application uses the flag
+ * SHM_HUGETLB in the shmget system call to inform the kernel that it is
+ * requesting huge pages.
+ *
+ * For the ia64 architecture, the Linux kernel reserves Region number 4 for
+ * huge pages.  That means that if one requires a fixed address, a huge page
+ * aligned address starting with 0x800000... will be required.  If a fixed
+ * address is not required, the kernel will select an address in the proper
+ * range.
+ * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ *
+ * Note: The default shared memory limit is quite low on many kernels,
+ * you may need to increase it via:
+ *
+ * echo 268435456 > /proc/sys/kernel/shmmax
+ *
+ * This will increase the maximum size per shared memory segment to 256MB.
+ * The other limit that you will hit eventually is shmall which is the
+ * total amount of shared memory in pages. To set it to 16GB on a system
+ * with a 4kB pagesize do:
+ *
+ * echo 4194304 > /proc/sys/kernel/shmall
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+#include <sys/mman.h>
+
+#ifndef SHM_HUGETLB
+#define SHM_HUGETLB 04000
+#endif
+
+#define LENGTH (256UL*1024*1024)
+
+#define dprintf(x)  printf(x)
+
+/* Only ia64 requires this */
+#ifdef __ia64__
+#define ADDR (void *)(0x8000000000000000UL)
+#define SHMAT_FLAGS (SHM_RND)
+#else
+#define ADDR (void *)(0x0UL)
+#define SHMAT_FLAGS (0)
+#endif
+
+int main(void)
+{
+        int shmid;
+        unsigned long i;
+        char *shmaddr;
+
+        if ((shmid = shmget(2, LENGTH,
+                            SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
+                perror("shmget");
+                exit(1);
+        }
+        printf("shmid: 0x%x\n", shmid);
+
+        shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
+        if (shmaddr == (char *)-1) {
+                perror("Shared memory attach failure");
+                shmctl(shmid, IPC_RMID, NULL);
+                exit(2);
+        }
+        printf("shmaddr: %p\n", shmaddr);
+
+        dprintf("Starting the writes:\n");
+        for (i = 0; i < LENGTH; i++) {
+                shmaddr[i] = (char)(i);
+                if (!(i % (1024 * 1024)))
+                        dprintf(".");
+        }
+        dprintf("\n");
+
+        dprintf("Starting the Check...");
+        for (i = 0; i < LENGTH; i++)
+                if (shmaddr[i] != (char)i)
+                        printf("\nIndex %lu mismatched\n", i);
+        dprintf("Done.\n");
+
+        if (shmdt((const void *)shmaddr) != 0) {
+                perror("Detach failure");
+                shmctl(shmid, IPC_RMID, NULL);
+                exit(3);
+        }
+
+        shmctl(shmid, IPC_RMID, NULL);
+
+        return 0;
+}
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index bc31636973e3..457634c1e03e 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,176 +299,11 @@ map_hugetlb.c.
 *******************************************************************
 
 /*
- * Example of using huge page memory in a user application using Sys V shared
- * memory system calls.  In this example the app is requesting 256MB of
- * memory that is backed by huge pages.  The application uses the flag
- * SHM_HUGETLB in the shmget system call to inform the kernel that it is
- * requesting huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
- *
- * Note: The default shared memory limit is quite low on many kernels,
- * you may need to increase it via:
- *
- * echo 268435456 > /proc/sys/kernel/shmmax
- *
- * This will increase the maximum size per shared memory segment to 256MB.
- * The other limit that you will hit eventually is shmall which is the
- * total amount of shared memory in pages. To set it to 16GB on a system
- * with a 4kB pagesize do:
- *
- * echo 4194304 > /proc/sys/kernel/shmall
+ * hugepage-shm:  see Documentation/vm/hugepage-shm.c
  */
-#include <stdlib.h>
-#include <stdio.h>
-#include <sys/types.h>
-#include <sys/ipc.h>
-#include <sys/shm.h>
-#include <sys/mman.h>
-
-#ifndef SHM_HUGETLB
-#define SHM_HUGETLB 04000
-#endif
-
-#define LENGTH (256UL*1024*1024)
-
-#define dprintf(x)  printf(x)
-
-#define ADDR (void *)(0x0UL)    /* let kernel choose address */
-#define SHMAT_FLAGS (0)
-
-int main(void)
-{
-        int shmid;
-        unsigned long i;
-        char *shmaddr;
-
-        if ((shmid = shmget(2, LENGTH,
-                            SHM_HUGETLB | IPC_CREAT | SHM_R | SHM_W)) < 0) {
-                perror("shmget");
-                exit(1);
-        }
-        printf("shmid: 0x%x\n", shmid);
-
-        shmaddr = shmat(shmid, ADDR, SHMAT_FLAGS);
-        if (shmaddr == (char *)-1) {
-                perror("Shared memory attach failure");
-                shmctl(shmid, IPC_RMID, NULL);
-                exit(2);
-        }
-        printf("shmaddr: %p\n", shmaddr);
-
-        dprintf("Starting the writes:\n");
-        for (i = 0; i < LENGTH; i++) {
-                shmaddr[i] = (char)(i);
-                if (!(i % (1024 * 1024)))
-                        dprintf(".");
-        }
-        dprintf("\n");
-
-        dprintf("Starting the Check...");
-        for (i = 0; i < LENGTH; i++)
-                if (shmaddr[i] != (char)i)
-                        printf("\nIndex %lu mismatched\n", i);
-        dprintf("Done.\n");
-
-        if (shmdt((const void *)shmaddr) != 0) {
-                perror("Detach failure");
-                shmctl(shmid, IPC_RMID, NULL);
-                exit(3);
-        }
-
-        shmctl(shmid, IPC_RMID, NULL);
-
-        return 0;
-}
 
 *******************************************************************
 
 /*
- * Example of using huge page memory in a user application using the mmap
- * system call.  Before running this application, make sure that the
- * administrator has mounted the hugetlbfs filesystem (on some directory
- * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
- * example, the app is requesting memory of size 256MB that is backed by
- * huge pages.
- *
- * For the ia64 architecture, the Linux kernel reserves Region number 4 for
- * huge pages.  That means that if one requires a fixed address, a huge page
- * aligned address starting with 0x800000... will be required.  If a fixed
- * address is not required, the kernel will select an address in the proper
- * range.
- * Other architectures, such as ppc64, i386 or x86_64 are not so constrained.
+ * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
  */
-#include <stdlib.h>
-#include <stdio.h>
-#include <unistd.h>
-#include <sys/mman.h>
-#include <fcntl.h>
-
-#define FILE_NAME "/mnt/hugepagefile"
-#define LENGTH (256UL*1024*1024)
-#define PROTECTION (PROT_READ | PROT_WRITE)
-
-#define ADDR (void *)(0x0UL)    /* let kernel choose address */
-#define FLAGS (MAP_SHARED)
-
-void check_bytes(char *addr)
-{
-        printf("First hex is %x\n", *((unsigned int *)addr));
-}
-
-void write_bytes(char *addr)
-{
-        unsigned long i;
-
-        for (i = 0; i < LENGTH; i++)
-                *(addr + i) = (char)i;
-}
-
-void read_bytes(char *addr)
-{
-        unsigned long i;
-
-        check_bytes(addr);
-        for (i = 0; i < LENGTH; i++)
-                if (*(addr + i) != (char)i) {
-                        printf("Mismatch at %lu\n", i);
-                        break;
-                }
-}
-
-int main(void)
-{
-        void *addr;
-        int fd;
-
-        fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755);
-        if (fd < 0) {
-                perror("Open failed");
-                exit(1);
-        }
-
-        addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, fd, 0);
-        if (addr == MAP_FAILED) {
-                perror("mmap");
-                unlink(FILE_NAME);
-                exit(1);
-        }
-
-        printf("Returned address is %p\n", addr);
-        check_bytes(addr);
-        write_bytes(addr);
-        read_bytes(addr);
-
-        munmap(addr, LENGTH);
-        close(fd);
-        unlink(FILE_NAME);
-
-        return 0;
-}
diff --git a/Documentation/vm/map_hugetlb.c b/Documentation/vm/map_hugetlb.c
index e2bdae37f499..9969c7d9f985 100644
--- a/Documentation/vm/map_hugetlb.c
+++ b/Documentation/vm/map_hugetlb.c
@@ -31,12 +31,12 @@
 #define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
 #endif
 
-void check_bytes(char *addr)
+static void check_bytes(char *addr)
 {
         printf("First hex is %x\n", *((unsigned int *)addr));
 }
 
-void write_bytes(char *addr)
+static void write_bytes(char *addr)
 {
         unsigned long i;
 
@@ -44,7 +44,7 @@ void write_bytes(char *addr)
                 *(addr + i) = (char)i;
 }
 
-void read_bytes(char *addr)
+static void read_bytes(char *addr)
 {
         unsigned long i;
 
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index b37300edf27c..07375e73981a 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -41,6 +41,7 @@ Possible debug options are
         P               Poisoning (object and padding)
         U               User tracking (free and alloc)
         T               Trace (please only use on single slabs)
+        A               Toggle failslab filter mark for the cache
         O               Switch debugging off for caches that would have
                         caused higher minimum slab orders
         -               Switch all debugging off (useful if the kernel is
diff --git a/Documentation/volatile-considered-harmful.txt b/Documentation/volatile-considered-harmful.txt
index 991c26a6ef64..db0cb228d64a 100644
--- a/Documentation/volatile-considered-harmful.txt
+++ b/Documentation/volatile-considered-harmful.txt
@@ -63,9 +63,9 @@ way to perform a busy wait is:
         cpu_relax();
 
 The cpu_relax() call can lower CPU power consumption or yield to a
-hyperthreaded twin processor; it also happens to serve as a memory barrier,
-so, once again, volatile is unnecessary.  Of course, busy-waiting is
-generally an anti-social act to begin with.
+hyperthreaded twin processor; it also happens to serve as a compiler
+barrier, so, once again, volatile is unnecessary.  Of course, busy-
+waiting is generally an anti-social act to begin with.
 
 There are still a few rare situations where volatile makes sense in the
 kernel:
diff --git a/Documentation/voyager.txt b/Documentation/voyager.txt
deleted file mode 100644
index 2749af552cdf..000000000000
--- a/Documentation/voyager.txt
+++ /dev/null
@@ -1,95 +0,0 @@
-Running Linux on the Voyager Architecture
-=========================================
-
-For full details and current project status, see
-
-http://www.hansenpartnership.com/voyager
-
-The voyager architecture was designed by NCR in the mid 80s to be a
-fully SMP capable RAS computing architecture built around intel's 486
-chip set.  The voyager came in three levels of architectural
-sophistication: 3,4 and 5 --- 1 and 2 never made it out of prototype.
-The linux patches support only the Level 5 voyager architecture (any
-machine class 3435 and above).
-
-The Voyager Architecture
-------------------------
-
-Voyager machines consist of a Baseboard with a 386 diagnostic
-processor, a Power Supply Interface (PSI) a Primary and possibly
-Secondary Microchannel bus and between 2 and 20 voyager slots.  The
-voyager slots can be populated with memory and cpu cards (up to 4GB
-memory and from 1 486 to 32 Pentium Pro processors).  Internally, the
-voyager has a dual arbitrated system bus and a configuration and test
-bus (CAT).  The voyager bus speed is 40MHz.  Therefore (since all
-voyager cards are dual ported for each system bus) the maximum
-transfer rate is 320Mb/s but only if you have your slot configuration
-tuned (only memory cards can communicate with both busses at once, CPU
-cards utilise them one at a time).
-
-Voyager SMP
------------
-
-Since voyager was the first intel based SMP system, it is slightly
-more primitive than the Intel IO-APIC approach to SMP.  Voyager allows
-arbitrary interrupt routing (including processor affinity routing) of
-all 16 PC type interrupts.  However it does this by using a modified
-5259 master/slave chip set instead of an APIC bus.  Additionally,
-voyager supports Cross Processor Interrupts (CPI) equivalent to the
-APIC IPIs.  There are two routed voyager interrupt lines provided to
-each slot.
-
-Processor Cards
----------------
-
-These come in single, dyadic and quad configurations (the quads are
-problematic--see later).  The maximum configuration is 8 quad cards
-for 32 way SMP.
-
-Quad Processors
----------------
-
-Because voyager only supplies two interrupt lines to each Processor
-card, the Quad processors have to be configured (and Bootstrapped) in
-as a pair of Master/Slave processors.
-
-In fact, most Quad cards only accept one VIC interrupt line, so they
-have one interrupt handling processor (called the VIC extended
-processor) and three non-interrupt handling processors.
-
-Current Status
---------------
-
-The System will boot on Mono, Dyad and Quad cards.  There was
-originally a Quad boot problem which has been fixed by proper gdt
-alignment in the initial boot loader.  If you still cannot get your
-voyager system to boot, email me at:
-
-<J.E.J.Bottomley@HansenPartnership.com>
-
-
-The Quad cards now support using the separate Quad CPI vectors instead
-of going through the VIC mailbox system.
-
-The Level 4 architecture (3430 and 3360 Machines) should also work
-fine.
-
-Dump Switch
------------
-
-The voyager dump switch sends out a broadcast NMI which the voyager
-code intercepts and does a task dump.
-
-Power Switch
-------------
-
-The front panel power switch is intercepted by the kernel and should
-cause a system shutdown and power off.
-
-A Note About Mixed CPU Systems
-------------------------------
-
-Linux isn't designed to handle mixed CPU systems very well.  In order
-to get everything going you *must* make sure that your lowest
-capability CPU is used for booting.  Also, mixing CPU classes
-(e.g. 486 and 586) is really not going to work very well at all.
diff --git a/Documentation/watchdog/src/watchdog-simple.c b/Documentation/watchdog/src/watchdog-simple.c
index 4cf72f3fa8e9..ba45803a2216 100644
--- a/Documentation/watchdog/src/watchdog-simple.c
+++ b/Documentation/watchdog/src/watchdog-simple.c
@@ -17,9 +17,6 @@ int main(void)
                         ret = -1;
                         break;
                 }
-                ret = fsync(fd);
-                if (ret)
-                        break;
                 sleep(10);
         }
         close(fd);
diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c
index a750532ffcf8..63fdc34ceb98 100644
--- a/Documentation/watchdog/src/watchdog-test.c
+++ b/Documentation/watchdog/src/watchdog-test.c
@@ -31,6 +31,8 @@ static void keep_alive(void)
  */
 int main(int argc, char *argv[])
 {
+    int flags;
+
     fd = open("/dev/watchdog", O_WRONLY);
 
     if (fd == -1) {
@@ -41,12 +43,14 @@ int main(int argc, char *argv[])
 
     if (argc > 1) {
         if (!strncasecmp(argv[1], "-d", 2)) {
-            ioctl(fd, WDIOC_SETOPTIONS, WDIOS_DISABLECARD);
+            flags = WDIOS_DISABLECARD;
+            ioctl(fd, WDIOC_SETOPTIONS, &flags);
             fprintf(stderr, "Watchdog card disabled.\n");
             fflush(stderr);
             exit(0);
         } else if (!strncasecmp(argv[1], "-e", 2)) {
-            ioctl(fd, WDIOC_SETOPTIONS, WDIOS_ENABLECARD);
+            flags = WDIOS_ENABLECARD;
+            ioctl(fd, WDIOC_SETOPTIONS, &flags);
             fprintf(stderr, "Watchdog card enabled.\n");
             fflush(stderr);
             exit(0);
diff --git a/Documentation/watchdog/watchdog-api.txt b/Documentation/watchdog/watchdog-api.txt
index 4cc4ba9d7150..eb7132ed8bbc 100644
--- a/Documentation/watchdog/watchdog-api.txt
+++ b/Documentation/watchdog/watchdog-api.txt
@@ -222,11 +222,10 @@ returned value is the temperature in degrees fahrenheit.
     ioctl(fd, WDIOC_GETTEMP, &temperature);
 
 Finally the SETOPTIONS ioctl can be used to control some aspects of
-the cards operation; right now the pcwd driver is the only one
-supporting this ioctl.
+the cards operation.
 
     int options = 0;
-    ioctl(fd, WDIOC_SETOPTIONS, options);
+    ioctl(fd, WDIOC_SETOPTIONS, &options);
 
 The following options are available:
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 29a6ff8bc7d3..7fbbaf85f5b7 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -166,19 +166,13 @@ NUMA
 
   numa=noacpi   Don't parse the SRAT table for NUMA setup
 
-  numa=fake=CMDLINE
-                If a number, fakes CMDLINE nodes and ignores NUMA setup of the
-                actual machine.  Otherwise, system memory is configured
-                depending on the sizes and coefficients listed.  For example:
-                        numa=fake=2*512,1024,4*256,*128
-                gives two 512M nodes, a 1024M node, four 256M nodes, and the
-                rest split into 128M chunks.  If the last character of CMDLINE
-                is a *, the remaining memory is divided up equally among its
-                coefficient:
-                        numa=fake=2*512,2*
-                gives two 512M nodes and the rest split into two nodes.
-                Otherwise, the remaining system RAM is allocated to an
-                additional node.
+  numa=fake=<size>[MG]
+                If given as a memory unit, fills all system RAM with nodes of
+                size interleaved over physical nodes.
+
+  numa=fake=<N>
+                If given as an integer, fills all system RAM with N fake nodes
+                interleaved over physical nodes.
 
 ACPI