64 files changed, 2450 insertions, 762 deletions

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index a82a113b4a4b..1977fab38656 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -329,8 +329,6 @@ sgi-visws.txt
         - short blurb on the SGI Visual Workstations.
 sh/
         - directory with info on porting Linux to a new architecture.
-smart-config.txt
-        - description of the Smart Config makefile feature.
 sound/
         - directory with info on sound card support.
 sparc/
diff --git a/Documentation/ABI/stable/sysfs-class-ubi b/Documentation/ABI/stable/sysfs-class-ubi
new file mode 100644
index 000000000000..18d471d9faea
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-class-ubi
@@ -0,0 +1,212 @@
+What:           /sys/class/ubi/
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                The ubi/ class sub-directory belongs to the UBI subsystem and
+                provides general UBI information, per-UBI device information
+                and per-UBI volume information.
+
+What:           /sys/class/ubi/version
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                This file contains version of the latest supported UBI on-media
+                format. Currently it is 1, and there is no plan to change this.
+                However, if in the future UBI needs on-flash format changes
+                which cannot be done in a compatible manner, a new format
+                version will be added. So this is a mechanism for possible
+                future backward-compatible (but forward-incompatible)
+                improvements.
+
+What:           /sys/class/ubiX/
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                The /sys/class/ubi0, /sys/class/ubi1, etc directories describe
+                UBI devices (UBI device 0, 1, etc). They contain general UBI
+                device information and per UBI volume information (each UBI
+                device may have many UBI volumes)
+
+What:           /sys/class/ubi/ubiX/avail_eraseblocks
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Amount of available logical eraseblock. For example, one may
+                create a new UBI volume which has this amount of logical
+                eraseblocks.
+
+What:           /sys/class/ubi/ubiX/bad_peb_count
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Count of bad physical eraseblocks on the underlying MTD device.
+
+What:           /sys/class/ubi/ubiX/bgt_enabled
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Contains ASCII "0\n" if the UBI background thread is disabled,
+                and ASCII "1\n" if it is enabled.
+
+What:           /sys/class/ubi/ubiX/dev
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Major and minor numbers of the character device corresponding
+                to this UBI device (in <major>:<minor> format).
+
+What:           /sys/class/ubi/ubiX/eraseblock_size
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Maximum logical eraseblock size this UBI device may provide. UBI
+                volumes may have smaller logical eraseblock size because of their
+                alignment.
+
+What:           /sys/class/ubi/ubiX/max_ec
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Maximum physical eraseblock erase counter value.
+
+What:           /sys/class/ubi/ubiX/max_vol_count
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Maximum number of volumes which this UBI device may have.
+
+What:           /sys/class/ubi/ubiX/min_io_size
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Minimum input/output unit size. All the I/O may only be done
+                in fractions of the contained number.
+
+What:           /sys/class/ubi/ubiX/mtd_num
+Date:           January 2008
+KernelVersion:  2.6.25
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Number of the underlying MTD device.
+
+What:           /sys/class/ubi/ubiX/reserved_for_bad
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Number of physical eraseblocks reserved for bad block handling.
+
+What:           /sys/class/ubi/ubiX/total_eraseblocks
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Total number of good (not marked as bad) physical eraseblocks on
+                the underlying MTD device.
+
+What:           /sys/class/ubi/ubiX/volumes_count
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Count of volumes on this UBI device.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                The /sys/class/ubi/ubiX/ubiX_0/, /sys/class/ubi/ubiX/ubiX_1/,
+                etc directories describe UBI volumes on UBI device X (volumes
+                0, 1, etc).
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/alignment
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Volume alignment - the value the logical eraseblock size of
+                this volume has to be aligned on. For example, 2048 means that
+                logical eraseblock size is multiple of 2048. In other words,
+                volume logical eraseblock size is UBI device logical eraseblock
+                size aligned to the alignment value.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/corrupted
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Contains ASCII "0\n" if the UBI volume is OK, and ASCII "1\n"
+                if it is corrupted (e.g., due to an interrupted volume update).
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/data_bytes
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                The amount of data this volume contains. This value makes sense
+                only for static volumes, and for dynamic volume it equivalent
+                to the total volume size in bytes.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/dev
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Major and minor numbers of the character device corresponding
+                to this UBI volume (in <major>:<minor> format).
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/name
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Volume name.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/reserved_ebs
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Count of physical eraseblock reserved for this volume.
+                Equivalent to the volume size in logical eraseblocks.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/type
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Volume type. Contains ASCII "dynamic\n" for dynamic volumes and
+                "static\n" for static volumes.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/upd_marker
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Contains ASCII "0\n" if the update marker is not set for this
+                volume, and "1\n" if it is set. The update marker is set when
+                volume update starts, and cleaned when it ends. So the presence
+                of the update marker indicates that the volume is being updated
+                at the moment of the update was interrupted. The later may be
+                checked using the "corrupted" sysfs file.
+
+What:           /sys/class/ubi/ubiX/ubiX_Y/usable_eb_size
+Date:           July 2006
+KernelVersion:  2.6.22
+Contact:        Artem Bityutskiy <dedekind@infradead.org>
+Description:
+                Logical eraseblock size of this volume. Equivalent to logical
+                eraseblock size of the device aligned on the volume alignment
+                value.
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index b939ebb62871..80d150458c80 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -145,7 +145,7 @@ Part Ic - DMA addressing limitations
 int
 dma_supported(struct device *dev, u64 mask)
 int
-pci_dma_supported(struct device *dev, u64 mask)
+pci_dma_supported(struct pci_dev *hwdev, u64 mask)
 
 Checks to see if the device can support DMA to the memory described by
 mask.
@@ -189,7 +189,7 @@ 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 device *dev, void *cpu_addr, size_t size,
+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
@@ -395,6 +395,71 @@ Notes:  You must do this:
 
 See also dma_map_single().
 
+dma_addr_t
+dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
+                     enum dma_data_direction dir,
+                     struct dma_attrs *attrs)
+
+void
+dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
+                       size_t size, enum dma_data_direction dir,
+                       struct dma_attrs *attrs)
+
+int
+dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+                 int nents, enum dma_data_direction dir,
+                 struct dma_attrs *attrs)
+
+void
+dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
+                   int nents, enum dma_data_direction dir,
+                   struct dma_attrs *attrs)
+
+The four functions above are just like the counterpart functions
+without the _attrs suffixes, except that they pass an optional
+struct dma_attrs*.
+
+struct dma_attrs encapsulates a set of "dma attributes". For the
+definition of struct dma_attrs see linux/dma-attrs.h.
+
+The interpretation of dma attributes is architecture-specific, and
+each attribute should be documented in Documentation/DMA-attributes.txt.
+
+If struct dma_attrs* is NULL, the semantics of each of these
+functions is identical to those of the corresponding function
+without the _attrs suffix. As a result dma_map_single_attrs()
+can generally replace dma_map_single(), etc.
+
+As an example of the use of the *_attrs functions, here's how
+you could pass an attribute DMA_ATTR_FOO when mapping memory
+for DMA:
+
+#include <linux/dma-attrs.h>
+/* DMA_ATTR_FOO should be defined in linux/dma-attrs.h and
+ * documented in Documentation/DMA-attributes.txt */
+...
+
+        DEFINE_DMA_ATTRS(attrs);
+        dma_set_attr(DMA_ATTR_FOO, &attrs);
+        ....
+        n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, &attr);
+        ....
+
+Architectures that care about DMA_ATTR_FOO would check for its
+presence in their implementations of the mapping and unmapping
+routines, e.g.:
+
+void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
+                             size_t size, enum dma_data_direction dir,
+                             struct dma_attrs *attrs)
+{
+        ....
+        int foo =  dma_get_attr(DMA_ATTR_FOO, attrs);
+        ....
+        if (foo)
+                /* twizzle the frobnozzle */
+        ....
+
 
 Part II - Advanced dma_ usage
 -----------------------------
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
new file mode 100644
index 000000000000..6d772f84b477
--- /dev/null
+++ b/Documentation/DMA-attributes.txt
@@ -0,0 +1,24 @@
+                        DMA attributes
+                        ==============
+
+This document describes the semantics of the DMA attributes that are
+defined in linux/dma-attrs.h.
+
+DMA_ATTR_WRITE_BARRIER
+----------------------
+
+DMA_ATTR_WRITE_BARRIER is a (write) barrier attribute for DMA.  DMA
+to a memory region with the DMA_ATTR_WRITE_BARRIER attribute forces
+all pending DMA writes to complete, and thus provides a mechanism to
+strictly order DMA from a device across all intervening busses and
+bridges.  This barrier is not specific to a particular type of
+interconnect, it applies to the system as a whole, and so its
+implementation must account for the idiosyncracies of the system all
+the way from the DMA device to memory.
+
+As an example of a situation where DMA_ATTR_WRITE_BARRIER would be
+useful, suppose that a device does a DMA write to indicate that data is
+ready and available in memory.  The DMA of the "completion indication"
+could race with data DMA.  Mapping the memory used for completion
+indications with DMA_ATTR_WRITE_BARRIER would prevent the race.
+
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index b2b6366bba51..83966e94cc32 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -187,8 +187,11 @@ quiet_cmd_fig2png = FIG2PNG $@
 
 ###
 # Rule to convert a .c file to inline XML documentation
+       gen_xml = :
+ quiet_gen_xml = echo '  GEN     $@'
+silent_gen_xml = :
 %.xml: %.c
-        @echo '  GEN     $@'
+        @$($(quiet)gen_xml)
         @(                            \
            echo "<programlisting>";   \
            expand --tabs=8 < $< |     \
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 488dd4a4945b..b7b1482f6e04 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -119,7 +119,7 @@ X!Ilib/string.c
 !Elib/string.c
      </sect1>
      <sect1><title>Bit Operations</title>
-!Iinclude/asm-x86/bitops_32.h
+!Iinclude/asm-x86/bitops.h
      </sect1>
   </chapter>
 
@@ -645,4 +645,58 @@ X!Idrivers/video/console/fonts.c
 !Edrivers/i2c/i2c-core.c
   </chapter>
 
+  <chapter id="clk">
+     <title>Clock Framework</title>
+
+     <para>
+        The clock framework defines programming interfaces to support
+        software management of the system clock tree.
+        This framework is widely used with System-On-Chip (SOC) platforms
+        to support power management and various devices which may need
+        custom clock rates.
+        Note that these "clocks" don't relate to timekeeping or real
+        time clocks (RTCs), each of which have separate frameworks.
+        These <structname>struct clk</structname> instances may be used
+        to manage for example a 96 MHz signal that is used to shift bits
+        into and out of peripherals or busses, or otherwise trigger
+        synchronous state machine transitions in system hardware.
+     </para>
+
+     <para>
+        Power management is supported by explicit software clock gating:
+        unused clocks are disabled, so the system doesn't waste power
+        changing the state of transistors that aren't in active use.
+        On some systems this may be backed by hardware clock gating,
+        where clocks are gated without being disabled in software.
+        Sections of chips that are powered but not clocked may be able
+        to retain their last state.
+        This low power state is often called a <emphasis>retention
+        mode</emphasis>.
+        This mode still incurs leakage currents, especially with finer
+        circuit geometries, but for CMOS circuits power is mostly used
+        by clocked state changes.
+     </para>
+
+     <para>
+        Power-aware drivers only enable their clocks when the device
+        they manage is in active use.  Also, system sleep states often
+        differ according to which clock domains are active:  while a
+        "standby" state may allow wakeup from several active domains, a
+        "mem" (suspend-to-RAM) state may require a more wholesale shutdown
+        of clocks derived from higher speed PLLs and oscillators, limiting
+        the number of possible wakeup event sources.  A driver's suspend
+        method may need to be aware of system-specific clock constraints
+        on the target sleep state.
+     </para>
+
+     <para>
+        Some platforms support programmable clock generators.  These
+        can be used by external chips of various kinds, such as other
+        CPUs, multimedia codecs, and devices with strict requirements
+        for interface clocking.
+     </para>
+
+!Iinclude/linux/clk.h
+  </chapter>
+
 </book>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 54835610b3d6..0291ade44c17 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -249,9 +249,11 @@ process is as follows:
     release a new -rc kernel every week.
   - Process continues until the kernel is considered "ready", the
     process should last around 6 weeks.
-  - A list of known regressions present in each -rc release is
-    tracked at the following URI:
-    http://kernelnewbies.org/known_regressions
+  - Known regressions in each release are periodically posted to the 
+    linux-kernel mailing list.  The goal is to reduce the length of 
+    that list to zero before declaring the kernel to be "ready," but, in
+    the real world, a small number of regressions often remain at 
+    release time.
 
 It is worth mentioning what Andrew Morton wrote on the linux-kernel
 mailing list about kernel releases:
@@ -261,7 +263,7 @@ mailing list about kernel releases:
 
 2.6.x.y -stable kernel tree
 ---------------------------
-Kernels with 4 digit versions are -stable kernels. They contain
+Kernels with 4-part versions are -stable kernels. They contain
 relatively small and critical fixes for security problems or significant
 regressions discovered in a given 2.6.x kernel.
 
@@ -273,7 +275,10 @@ If no 2.6.x.y kernel is available, then the highest numbered 2.6.x
 kernel is the current stable kernel.
 
 2.6.x.y are maintained by the "stable" team <stable@kernel.org>, and are
-released almost every other week.
+released as needs dictate.  The normal release period is approximately 
+two weeks, but it can be longer if there are no pressing problems.  A
+security-related problem, instead, can cause a release to happen almost
+instantly.
 
 The file Documentation/stable_kernel_rules.txt in the kernel tree
 documents what kinds of changes are acceptable for the -stable tree, and
@@ -298,7 +303,9 @@ 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.
+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
@@ -354,11 +361,12 @@ Here is a list of some of the different kernel trees available:
     - SCSI, James Bottomley <James.Bottomley@SteelEye.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, PCI, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
+    - USB, Driver Core, and I2C, Greg Kroah-Hartman <gregkh@suse.de>
         kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
-    - x86-64, partly i386, Andi Kleen <ak@suse.de>
-        ftp.firstfloor.org:/pub/ak/x86_64/quilt/
 
   Other kernel trees can be found listed at http://git.kernel.org/ and in
   the MAINTAINERS file.
@@ -392,8 +400,8 @@ If you want to be advised of the future bug reports, you can subscribe to the
 bugme-new mailing list (only new bug reports are mailed here) or to the
 bugme-janitor mailing list (every change in the bugzilla is mailed here)
 
-        http://lists.osdl.org/mailman/listinfo/bugme-new
-        http://lists.osdl.org/mailman/listinfo/bugme-janitors
+        http://lists.linux-foundation.org/mailman/listinfo/bugme-new
+        http://lists.linux-foundation.org/mailman/listinfo/bugme-janitors
 
 
 
diff --git a/Documentation/arm/Samsung-S3C24XX/NAND.txt b/Documentation/arm/Samsung-S3C24XX/NAND.txt
new file mode 100644
index 000000000000..bc478a3409b8
--- /dev/null
+++ b/Documentation/arm/Samsung-S3C24XX/NAND.txt
@@ -0,0 +1,30 @@
+                        S3C24XX NAND Support
+                        ====================
+
+Introduction
+------------
+
+Small Page NAND
+---------------
+
+The driver uses a 512 byte (1 page) ECC code for this setup. The
+ECC code is not directly compatible with the default kernel ECC
+code, so the driver enforces its own OOB layout and ECC parameters
+
+Large Page NAND
+---------------
+
+The driver is capable of handling NAND flash with a 2KiB page
+size, with support for hardware ECC generation and correction.
+
+Unlike the 512byte page mode, the driver generates ECC data for
+each 256 byte block in an 2KiB page. This means that more than
+one error in a page can be rectified. It also means that the
+OOB layout remains the default kernel layout for these flashes.
+
+
+Document Author
+---------------
+
+Ben Dooks, Copyright 2007 Simtec Electronics
+
diff --git a/Documentation/arm/Samsung-S3C24XX/Overview.txt b/Documentation/arm/Samsung-S3C24XX/Overview.txt
index c31b76fa66c4..d04e1e30c47f 100644
--- a/Documentation/arm/Samsung-S3C24XX/Overview.txt
+++ b/Documentation/arm/Samsung-S3C24XX/Overview.txt
@@ -156,6 +156,8 @@ NAND
   controller. If there are any problems the latest linux-mtd
   code can be found from http://www.linux-mtd.infradead.org/
 
+  For more information see Documentation/arm/Samsung-S3C24XX/NAND.txt
+
 
 Serial
 ------
diff --git a/Documentation/cgroups.txt b/Documentation/cgroups.txt
index 31d12e21ff8a..c298a6690e0d 100644
--- a/Documentation/cgroups.txt
+++ b/Documentation/cgroups.txt
@@ -500,8 +500,7 @@ post-attachment activity that requires memory allocations or blocking.
 
 void fork(struct cgroup_subsy *ss, struct task_struct *task)
 
-Called when a task is forked into a cgroup. Also called during
-registration for all existing tasks.
+Called when a task is forked into a cgroup.
 
 void exit(struct cgroup_subsys *ss, struct task_struct *task)
 
diff --git a/Documentation/controllers/devices.txt b/Documentation/controllers/devices.txt
new file mode 100644
index 000000000000..4dcea42432c2
--- /dev/null
+++ b/Documentation/controllers/devices.txt
@@ -0,0 +1,48 @@
+Device Whitelist Controller
+
+1. Description:
+
+Implement a cgroup to track and enforce open and mknod restrictions
+on device files.  A device cgroup associates a device access
+whitelist with each cgroup.  A whitelist entry has 4 fields.
+'type' is a (all), c (char), or b (block).  'all' means it applies
+to all types and all major and minor numbers.  Major and minor are
+either an integer or * for all.  Access is a composition of r
+(read), w (write), and m (mknod).
+
+The root device cgroup starts with rwm to 'all'.  A child device
+cgroup gets a copy of the parent.  Administrators can then remove
+devices from the whitelist or add new entries.  A child cgroup can
+never receive a device access which is denied its parent.  However
+when a device access is removed from a parent it will not also be
+removed from the child(ren).
+
+2. User Interface
+
+An entry is added using devices.allow, and removed using
+devices.deny.  For instance
+
+        echo 'c 1:3 mr' > /cgroups/1/devices.allow
+
+allows cgroup 1 to read and mknod the device usually known as
+/dev/null.  Doing
+
+        echo a > /cgroups/1/devices.deny
+
+will remove the default 'a *:* mrw' entry.
+
+3. Security
+
+Any task can move itself between cgroups.  This clearly won't
+suffice, but we can decide the best way to adequately restrict
+movement as people get some experience with this.  We may just want
+to require CAP_SYS_ADMIN, which at least is a separate bit from
+CAP_MKNOD.  We may want to just refuse moving to a cgroup which
+isn't a descendent of the current one.  Or we may want to use
+CAP_MAC_ADMIN, since we really are trying to lock down root.
+
+CAP_SYS_ADMIN is needed to modify the whitelist or move another
+task to a new cgroup.  (Again we'll probably want to change that).
+
+A cgroup may not be granted more permissions than the cgroup's
+parent has.
diff --git a/Documentation/controllers/resource_counter.txt b/Documentation/controllers/resource_counter.txt
new file mode 100644
index 000000000000..f196ac1d7d25
--- /dev/null
+++ b/Documentation/controllers/resource_counter.txt
@@ -0,0 +1,181 @@
+
+                The Resource Counter
+
+The resource counter, declared at include/linux/res_counter.h,
+is supposed to facilitate the resource management by controllers
+by providing common stuff for accounting.
+
+This "stuff" includes the res_counter structure and routines
+to work with it.
+
+
+
+1. Crucial parts of the res_counter structure
+
+ a. unsigned long long usage
+
+        The usage value shows the amount of a resource that is consumed
+        by a group at a given time. The units of measurement should be
+        determined by the controller that uses this counter. E.g. it can
+        be bytes, items or any other unit the controller operates on.
+
+ b. unsigned long long max_usage
+
+        The maximal value of the usage over time.
+
+        This value is useful when gathering statistical information about
+        the particular group, as it shows the actual resource requirements
+        for a particular group, not just some usage snapshot.
+
+ c. unsigned long long limit
+
+        The maximal allowed amount of resource to consume by the group. In
+        case the group requests for more resources, so that the usage value
+        would exceed the limit, the resource allocation is rejected (see
+        the next section).
+
+ d. unsigned long long failcnt
+
+        The failcnt stands for "failures counter". This is the number of
+        resource allocation attempts that failed.
+
+ c. spinlock_t lock
+
+        Protects changes of the above values.
+
+
+
+2. Basic accounting routines
+
+ a. void res_counter_init(struct res_counter *rc)
+
+        Initializes the resource counter. As usual, should be the first
+        routine called for a new counter.
+
+ b. int res_counter_charge[_locked]
+                        (struct res_counter *rc, unsigned long val)
+
+        When a resource is about to be allocated it has to be accounted
+        with the appropriate resource counter (controller should determine
+        which one to use on its own). This operation is called "charging".
+
+        This is not very important which operation - resource allocation
+        or charging - is performed first, but
+          * if the allocation is performed first, this may create a
+            temporary resource over-usage by the time resource counter is
+            charged;
+          * if the charging is performed first, then it should be uncharged
+            on error path (if the one is called).
+
+ c. void res_counter_uncharge[_locked]
+                        (struct res_counter *rc, unsigned long val)
+
+        When a resource is released (freed) it should be de-accounted
+        from the resource counter it was accounted to.  This is called
+        "uncharging".
+
+    The _locked routines imply that the res_counter->lock is taken.
+
+
+ 2.1 Other accounting routines
+
+    There are more routines that may help you with common needs, like
+    checking whether the limit is reached or resetting the max_usage
+    value. They are all declared in include/linux/res_counter.h.
+
+
+
+3. Analyzing the resource counter registrations
+
+ a. If the failcnt value constantly grows, this means that the counter's
+    limit is too tight. Either the group is misbehaving and consumes too
+    many resources, or the configuration is not suitable for the group
+    and the limit should be increased.
+
+ b. The max_usage value can be used to quickly tune the group. One may
+    set the limits to maximal values and either load the container with
+    a common pattern or leave one for a while. After this the max_usage
+    value shows the amount of memory the container would require during
+    its common activity.
+
+    Setting the limit a bit above this value gives a pretty good
+    configuration that works in most of the cases.
+
+ c. If the max_usage is much less than the limit, but the failcnt value
+    is growing, then the group tries to allocate a big chunk of resource
+    at once.
+
+ d. If the max_usage is much less than the limit, but the failcnt value
+    is 0, then this group is given too high limit, that it does not
+    require. It is better to lower the limit a bit leaving more resource
+    for other groups.
+
+
+
+4. Communication with the control groups subsystem (cgroups)
+
+All the resource controllers that are using cgroups and resource counters
+should provide files (in the cgroup filesystem) to work with the resource
+counter fields. They are recommended to adhere to the following rules:
+
+ a. File names
+
+        Field name      File name
+        ---------------------------------------------------
+        usage           usage_in_<unit_of_measurement>
+        max_usage       max_usage_in_<unit_of_measurement>
+        limit           limit_in_<unit_of_measurement>
+        failcnt         failcnt
+        lock            no file :)
+
+ b. Reading from file should show the corresponding field value in the
+    appropriate format.
+
+ c. Writing to file
+
+        Field           Expected behavior
+        ----------------------------------
+        usage           prohibited
+        max_usage       reset to usage
+        limit           set the limit
+        failcnt         reset to zero
+
+
+
+5. Usage example
+
+ a. Declare a task group (take a look at cgroups subsystem for this) and
+    fold a res_counter into it
+
+        struct my_group {
+                struct res_counter res;
+
+                <other fields>
+        }
+
+ b. Put hooks in resource allocation/release paths
+
+        int alloc_something(...)
+        {
+                if (res_counter_charge(res_counter_ptr, amount) < 0)
+                        return -ENOMEM;
+
+                <allocate the resource and return to the caller>
+        }
+
+        void release_something(...)
+        {
+                res_counter_uncharge(res_counter_ptr, amount);
+
+                <release the resource>
+        }
+
+    In order to keep the usage value self-consistent, both the
+    "res_counter_ptr" and the "amount" in release_something() should be
+    the same as they were in the alloc_something() when the releasing
+    resource was allocated.
+
+ c. Provide the way to read res_counter values and set them (the cgroups
+    still can help with it).
+
+ c. Compile and run :)
diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index af3b925ece08..6c442d8426b5 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -154,6 +154,11 @@ scaling_governor,		and by "echoing" the name of another
                                 that some governors won't load - they only
                                 work on some specific architectures or
                                 processors.
+
+cpuinfo_cur_freq :              Current speed of the CPU, in KHz.
+
+scaling_available_frequencies : List of available frequencies, in KHz.
+
 scaling_min_freq and
 scaling_max_freq                show the current "policy limits" (in
                                 kHz). By echoing new values into these
@@ -162,6 +167,15 @@ scaling_max_freq		show the current "policy limits" (in
                                 first set scaling_max_freq, then
                                 scaling_min_freq.
 
+affected_cpus :                 List of CPUs that require software coordination
+                                of frequency.
+
+related_cpus :                  List of CPUs that need some sort of frequency
+                                coordination, whether software or hardware.
+
+scaling_driver :                Hardware driver for cpufreq.
+
+scaling_cur_freq :              Current frequency of the CPU, in KHz.
 
 If you have selected the "userspace" governor which allows you to
 set the CPU operating frequency to a specific value, you can read out
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index aa854b9b18cd..fb7b361e6eea 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -171,6 +171,7 @@ files describing 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
 
 In addition, the root cpuset only has the following file:
@@ -222,17 +223,18 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
 a direct ancestor or descendent, may share any of the same CPUs or
 Memory Nodes.
 
-A cpuset that is mem_exclusive restricts kernel allocations for
-page, buffer and other data commonly shared by the kernel across
-multiple users.  All cpusets, whether mem_exclusive or not, restrict
-allocations of memory for user space.  This enables configuring a
-system so that several independent jobs can share common kernel data,
-such as file system pages, while isolating each jobs user allocation in
-its own cpuset.  To do this, construct a large mem_exclusive cpuset to
-hold all the jobs, and construct child, non-mem_exclusive cpusets for
-each individual job.  Only a small amount of typical kernel memory,
-such as requests from interrupt handlers, is allowed to be taken
-outside even a mem_exclusive cpuset.
+A cpuset that is mem_exclusive *or* 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
+space.  This enables configuring a system so that several independent
+jobs can share common kernel data, such as file system pages, while
+isolating each job's user allocation in its own cpuset.  To do this,
+construct a large mem_exclusive cpuset to hold all the jobs, and
+construct child, non-mem_exclusive cpusets for each individual job.
+Only a small amount of typical kernel memory, such as requests from
+interrupt handlers, is allowed to be taken outside even a
+mem_exclusive cpuset.
 
 
 1.5 What is memory_pressure ?
@@ -707,7 +709,7 @@ Now you want to do something with this cpuset.
 
 In this directory you can find several files:
 # ls
-cpus  cpu_exclusive  mems  mem_exclusive  tasks
+cpus  cpu_exclusive  mems  mem_exclusive mem_hardwall  tasks
 
 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
diff --git a/Documentation/device-mapper/dm-crypt.txt b/Documentation/device-mapper/dm-crypt.txt
new file mode 100644
index 000000000000..6680cab2c705
--- /dev/null
+++ b/Documentation/device-mapper/dm-crypt.txt
@@ -0,0 +1,52 @@
+dm-crypt
+=========
+
+Device-Mapper's "crypt" target provides transparent encryption of block devices
+using the kernel crypto API.
+
+Parameters: <cipher> <key> <iv_offset> <device path> <offset>
+
+<cipher>
+    Encryption cipher and an optional IV generation mode.
+    (In format cipher-chainmode-ivopts:ivmode).
+    Examples:
+       des
+       aes-cbc-essiv:sha256
+       twofish-ecb
+
+    /proc/crypto contains supported crypto modes
+
+<key>
+    Key used for encryption. It is encoded as a hexadecimal number.
+    You can only use key sizes that are valid for the selected cipher.
+
+<iv_offset>
+    The IV offset is a sector count that is added to the sector number
+    before creating the IV.
+
+<device path>
+    This is the device that is going to be used as backend and contains the
+    encrypted data.  You can specify it as a path like /dev/xxx or a device
+    number <major>:<minor>.
+
+<offset>
+    Starting sector within the device where the encrypted data begins.
+
+Example scripts
+===============
+LUKS (Linux Unified Key Setup) is now the preferred way to set up disk
+encryption with dm-crypt using the 'cryptsetup' utility, see
+http://luks.endorphin.org/
+
+[[
+#!/bin/sh
+# Create a crypt device using dmsetup
+dmsetup create crypt1 --table "0 `blockdev --getsize $1` crypt aes-cbc-essiv:sha256 babebabebabebabebabebabebabebabe 0 $1 0"
+]]
+
+[[
+#!/bin/sh
+# Create a crypt device using cryptsetup and LUKS header with default cipher
+cryptsetup luksFormat $1
+cryptsetup luksOpen $1 crypt1
+]]
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 354aec047c0e..881e6dd03aea 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -141,6 +141,7 @@ mkprep
 mktables
 mktree
 modpost
+modules.order
 modversions.h*
 offset.h
 offsets.h
@@ -171,6 +172,7 @@ sm_tbl*
 split-include
 tags
 tftpboot.img
+timeconst.h
 times.h*
 tkparse
 trix_boot.h
diff --git a/Documentation/fb/gxfb.txt b/Documentation/fb/gxfb.txt
new file mode 100644
index 000000000000..2f640903bbb2
--- /dev/null
+++ b/Documentation/fb/gxfb.txt
@@ -0,0 +1,52 @@
+[This file is cloned from VesaFB/aty128fb]
+
+What is gxfb?
+=================
+
+This is a graphics framebuffer driver for AMD Geode GX2 based processors.
+
+Advantages:
+
+ * No need to use AMD's VSA code (or other VESA emulation layer) in the
+   BIOS.
+ * It provides a nice large console (128 cols + 48 lines with 1024x768)
+   without using tiny, unreadable fonts.
+ * You can run XF68_FBDev on top of /dev/fb0
+ * Most important: boot logo :-)
+
+Disadvantages:
+
+ * graphic mode is slower than text mode...
+
+
+How to use it?
+==============
+
+Switching modes is done using  gxfb.mode_option=<resolution>... boot
+parameter or using `fbset' program.
+
+See Documentation/fb/modedb.txt for more information on modedb
+resolutions.
+
+
+X11
+===
+
+XF68_FBDev should generally work fine, but it is non-accelerated.
+
+
+Configuration
+=============
+
+You can pass kernel command line options to gxfb with gxfb.<option>.
+For example, gxfb.mode_option=800x600@75.
+Accepted options:
+
+mode_option     - specify the video mode.  Of the form
+                  <x>x<y>[-<bpp>][@<refresh>]
+vram            - size of video ram (normally auto-detected)
+vt_switch       - enable vt switching during suspend/resume.  The vt
+                  switch is slow, but harmless.
+
+--
+Andres Salomon <dilinger@debian.org>
diff --git a/Documentation/fb/intelfb.txt b/Documentation/fb/intelfb.txt
index da5ee74219e8..27a3160650a4 100644
--- a/Documentation/fb/intelfb.txt
+++ b/Documentation/fb/intelfb.txt
@@ -14,6 +14,8 @@ graphics devices.  These would include:
         Intel 915GM
         Intel 945G
         Intel 945GM
+        Intel 965G
+        Intel 965GM
 
 B.  List of available options
 
diff --git a/Documentation/fb/lxfb.txt b/Documentation/fb/lxfb.txt
new file mode 100644
index 000000000000..38b3ca6f6ca7
--- /dev/null
+++ b/Documentation/fb/lxfb.txt
@@ -0,0 +1,52 @@
+[This file is cloned from VesaFB/aty128fb]
+
+What is lxfb?
+=================
+
+This is a graphics framebuffer driver for AMD Geode LX based processors.
+
+Advantages:
+
+ * No need to use AMD's VSA code (or other VESA emulation layer) in the
+   BIOS.
+ * It provides a nice large console (128 cols + 48 lines with 1024x768)
+   without using tiny, unreadable fonts.
+ * You can run XF68_FBDev on top of /dev/fb0
+ * Most important: boot logo :-)
+
+Disadvantages:
+
+ * graphic mode is slower than text mode...
+
+
+How to use it?
+==============
+
+Switching modes is done using  lxfb.mode_option=<resolution>... boot
+parameter or using `fbset' program.
+
+See Documentation/fb/modedb.txt for more information on modedb
+resolutions.
+
+
+X11
+===
+
+XF68_FBDev should generally work fine, but it is non-accelerated.
+
+
+Configuration
+=============
+
+You can pass kernel command line options to lxfb with lxfb.<option>.
+For example, lxfb.mode_option=800x600@75.
+Accepted options:
+
+mode_option     - specify the video mode.  Of the form
+                  <x>x<y>[-<bpp>][@<refresh>]
+vram            - size of video ram (normally auto-detected)
+vt_switch       - enable vt switching during suspend/resume.  The vt
+                  switch is slow, but harmless.
+
+--
+Andres Salomon <dilinger@debian.org>
diff --git a/Documentation/fb/metronomefb.txt b/Documentation/fb/metronomefb.txt
index b9a2e7b7e838..237ca412582d 100644
--- a/Documentation/fb/metronomefb.txt
+++ b/Documentation/fb/metronomefb.txt
@@ -1,7 +1,7 @@
                         Metronomefb
                         -----------
 Maintained by Jaya Kumar <jayakumar.lkml.gmail.com>
-Last revised: Nov 20, 2007
+Last revised: Mar 10, 2008
 
 Metronomefb is a driver for the Metronome display controller. The controller
 is from E-Ink Corporation. It is intended to be used to drive the E-Ink
@@ -11,20 +11,18 @@ display media here http://www.e-ink.com/products/matrix/metronome.html .
 Metronome is interfaced to the host CPU through the AMLCD interface. The
 host CPU generates the control information and the image in a framebuffer
 which is then delivered to the AMLCD interface by a host specific method.
-Currently, that's implemented for the PXA's LCDC controller. The display and
-error status are each pulled through individual GPIOs.
+The display and error status are each pulled through individual GPIOs.
 
-Metronomefb was written for the PXA255/gumstix/lyre combination and
-therefore currently has board set specific code in it. If other boards based on
-other architectures are available, then the host specific code can be separated
-and abstracted out.
+Metronomefb is platform independent and depends on a board specific driver
+to do all physical IO work. Currently, an example is implemented for the
+PXA board used in the AM-200 EPD devkit. This example is am200epd.c
 
 Metronomefb requires waveform information which is delivered via the AMLCD
 interface to the metronome controller. The waveform information is expected to
 be delivered from userspace via the firmware class interface. The waveform file
 can be compressed as long as your udev or hotplug script is aware of the need
-to uncompress it before delivering it. metronomefb will ask for waveform.wbf
-which would typically go into /lib/firmware/waveform.wbf depending on your
+to uncompress it before delivering it. metronomefb will ask for metronome.wbf
+which would typically go into /lib/firmware/metronome.wbf depending on your
 udev/hotplug setup. I have only tested with a single waveform file which was
 originally labeled 23P01201_60_WT0107_MTC. I do not know what it stands for.
 Caution should be exercised when manipulating the waveform as there may be
diff --git a/Documentation/fb/modedb.txt b/Documentation/fb/modedb.txt
index 4fcdb4cf4cca..ec4dee75a354 100644
--- a/Documentation/fb/modedb.txt
+++ b/Documentation/fb/modedb.txt
@@ -125,8 +125,12 @@ There may be more modes.
     amifb       - Amiga chipset frame buffer
     aty128fb    - ATI Rage128 / Pro frame buffer
     atyfb       - ATI Mach64 frame buffer
+    pm2fb       - Permedia 2/2V frame buffer
+    pm3fb       - Permedia 3 frame buffer
+    sstfb       - Voodoo 1/2 (SST1) chipset frame buffer
     tdfxfb      - 3D Fx frame buffer
     tridentfb   - Trident (Cyber)blade chipset frame buffer
+    vt8623fb    - VIA 8623 frame buffer
 
 BTW, only a few drivers use this at the moment. Others are to follow
 (feel free to send patches).
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 448729fcaeb1..599fe55bf297 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -128,15 +128,6 @@ Who:	Arjan van de Ven <arjan@linux.intel.com>
 
 ---------------------------
 
-What:   vm_ops.nopage
-When:   Soon, provided in-kernel callers have been converted
-Why:    This interface is replaced by vm_ops.fault, but it has been around
-        forever, is used by a lot of drivers, and doesn't cost much to
-        maintain.
-Who:    Nick Piggin <npiggin@suse.de>
-
----------------------------
-
 What:   PHYSDEVPATH, PHYSDEVBUS, PHYSDEVDRIVER in the uevent environment
 When:   October 2008
 Why:    The stacking of class devices makes these values misleading and
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 42d4b30b1045..c2992bc54f2f 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -511,7 +511,6 @@ prototypes:
         void (*open)(struct vm_area_struct*);
         void (*close)(struct vm_area_struct*);
         int (*fault)(struct vm_area_struct*, struct vm_fault *);
-        struct page *(*nopage)(struct vm_area_struct*, unsigned long, int *);
         int (*page_mkwrite)(struct vm_area_struct *, struct page *);
 
 locking rules:
@@ -519,7 +518,6 @@ locking rules:
 open:           no      yes
 close:          no      yes
 fault:          no      yes
-nopage:         no      yes
 page_mkwrite:   no      yes             no
 
         ->page_mkwrite() is called when a previously read-only page is
@@ -537,4 +535,3 @@ NULL.
 
 ipc/shm.c::shm_delete() - may need BKL.
 ->read() and ->write() in many drivers are (probably) missing BKL.
-drivers/sgi/char/graphics.c::sgi_graphics_nopage() - may need BKL.
diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
new file mode 100644
index 000000000000..d0ec45ae4e7d
--- /dev/null
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -0,0 +1,256 @@
+################################################################################
+#                                                                              #
+#                               NFS/RDMA README                                #
+#                                                                              #
+################################################################################
+
+ Author: NetApp and Open Grid Computing
+ Date: April 15, 2008
+
+Table of Contents
+~~~~~~~~~~~~~~~~~
+ - Overview
+ - Getting Help
+ - Installation
+ - Check RDMA and NFS Setup
+ - NFS/RDMA Setup
+
+Overview
+~~~~~~~~
+
+  This document describes how to install and setup the Linux NFS/RDMA client
+  and server software.
+
+  The NFS/RDMA client was first included in Linux 2.6.24. The NFS/RDMA server
+  was first included in the following release, Linux 2.6.25.
+
+  In our testing, we have obtained excellent performance results (full 10Gbit
+  wire bandwidth at minimal client CPU) under many workloads. The code passes
+  the full Connectathon test suite and operates over both Infiniband and iWARP
+  RDMA adapters.
+
+Getting Help
+~~~~~~~~~~~~
+
+  If you get stuck, you can ask questions on the
+
+                nfs-rdma-devel@lists.sourceforge.net
+
+  mailing list.
+
+Installation
+~~~~~~~~~~~~
+
+  These instructions are a step by step guide to building a machine for
+  use with NFS/RDMA.
+
+  - Install an RDMA device
+
+    Any device supported by the drivers in drivers/infiniband/hw is acceptable.
+
+    Testing has been performed using several Mellanox-based IB cards, the
+    Ammasso AMS1100 iWARP adapter, and the Chelsio cxgb3 iWARP adapter.
+
+  - Install a Linux distribution and tools
+
+    The first kernel release to contain both the NFS/RDMA client and server was
+    Linux 2.6.25  Therefore, a distribution compatible with this and subsequent
+    Linux kernel release should be installed.
+
+    The procedures described in this document have been tested with
+    distributions from Red Hat's Fedora Project (http://fedora.redhat.com/).
+
+  - Install nfs-utils-1.1.1 or greater on the client
+
+    An NFS/RDMA mount point can only be obtained by using the mount.nfs
+    command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs
+    you are using, type:
+
+    > /sbin/mount.nfs -V
+
+    If the version is less than 1.1.1 or the command does not exist,
+    then you will need to install the latest version of nfs-utils.
+
+    Download the latest package from:
+
+    http://www.kernel.org/pub/linux/utils/nfs
+
+    Uncompress the package and follow the installation instructions.
+
+    If you will not be using GSS and NFSv4, the installation process
+    can be simplified by disabling these features when running configure:
+
+    > ./configure --disable-gss --disable-nfsv4
+
+    For more information on this see the package's README and INSTALL files.
+
+    After building the nfs-utils package, there will be a mount.nfs binary in
+    the utils/mount directory. This binary can be used to initiate NFS v2, v3,
+    or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4.
+    The standard technique is to create a symlink called mount.nfs4 to mount.nfs.
+
+    NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed
+    on the NFS client machine. You do not need this specific version of
+    nfs-utils on the server. Furthermore, only the mount.nfs command from
+    nfs-utils-1.1.1 is needed on the client.
+
+  - Install a Linux kernel with NFS/RDMA
+
+    The NFS/RDMA client and server are both included in the mainline Linux
+    kernel version 2.6.25 and later. This and other versions of the 2.6 Linux
+    kernel can be found at:
+
+    ftp://ftp.kernel.org/pub/linux/kernel/v2.6/
+
+    Download the sources and place them in an appropriate location.
+
+  - Configure the RDMA stack
+
+    Make sure your kernel configuration has RDMA support enabled. Under
+    Device Drivers -> InfiniBand support, update the kernel configuration
+    to enable InfiniBand support [NOTE: the option name is misleading. Enabling
+    InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)].
+
+    Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or
+    iWARP adapter support (amso, cxgb3, etc.).
+
+    If you are using InfiniBand, be sure to enable IP-over-InfiniBand support.
+
+  - Configure the NFS client and server
+
+    Your kernel configuration must also have NFS file system support and/or
+    NFS server support enabled. These and other NFS related configuration
+    options can be found under File Systems -> Network File Systems.
+
+  - Build, install, reboot
+
+    The NFS/RDMA code will be enabled automatically if NFS and RDMA
+    are turned on. The NFS/RDMA client and server are configured via the hidden
+    SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
+    value of SUNRPC_XPRT_RDMA will be:
+
+     - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
+       and server will not be built
+     - M if both SUNRPC and INFINIBAND are on (M or Y) and at least one is M,
+       in this case the NFS/RDMA client and server will be built as modules
+     - Y if both SUNRPC and INFINIBAND are Y, in this case the NFS/RDMA client
+       and server will be built into the kernel
+
+    Therefore, if you have followed the steps above and turned no NFS and RDMA,
+    the NFS/RDMA client and server will be built.
+
+    Build a new kernel, install it, boot it.
+
+Check RDMA and NFS Setup
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Before configuring the NFS/RDMA software, it is a good idea to test
+    your new kernel to ensure that the kernel is working correctly.
+    In particular, it is a good idea to verify that the RDMA stack
+    is functioning as expected and standard NFS over TCP/IP and/or UDP/IP
+    is working properly.
+
+  - Check RDMA Setup
+
+    If you built the RDMA components as modules, load them at
+    this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel
+    card:
+
+    > modprobe ib_mthca
+    > modprobe ib_ipoib
+
+    If you are using InfiniBand, make sure there is a Subnet Manager (SM)
+    running on the network. If your IB switch has an embedded SM, you can
+    use it. Otherwise, you will need to run an SM, such as OpenSM, on one
+    of your end nodes.
+
+    If an SM is running on your network, you should see the following:
+
+    > cat /sys/class/infiniband/driverX/ports/1/state
+    4: ACTIVE
+
+    where driverX is mthca0, ipath5, ehca3, etc.
+
+    To further test the InfiniBand software stack, use IPoIB (this
+    assumes you have two IB hosts named host1 and host2):
+
+    host1> ifconfig ib0 a.b.c.x
+    host2> ifconfig ib0 a.b.c.y
+    host1> ping a.b.c.y
+    host2> ping a.b.c.x
+
+    For other device types, follow the appropriate procedures.
+
+  - Check NFS Setup
+
+    For the NFS components enabled above (client and/or server),
+    test their functionality over standard Ethernet using TCP/IP or UDP/IP.
+
+NFS/RDMA Setup
+~~~~~~~~~~~~~~
+
+  We recommend that you use two machines, one to act as the client and
+  one to act as the server.
+
+  One time configuration:
+
+  - On the server system, configure the /etc/exports file and
+    start the NFS/RDMA server.
+
+    Exports entries with the following formats have been tested:
+
+    /vol0   192.168.0.47(fsid=0,rw,async,insecure,no_root_squash)
+    /vol0   192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash)
+
+    The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the
+    cleint's iWARP address(es) for an RNIC.
+
+    NOTE: The "insecure" option must be used because the NFS/RDMA client does not
+    use a reserved port.
+
+ Each time a machine boots:
+
+  - Load and configure the RDMA drivers
+
+    For InfiniBand using a Mellanox adapter:
+
+    > modprobe ib_mthca
+    > modprobe ib_ipoib
+    > ifconfig ib0 a.b.c.d
+
+    NOTE: use unique addresses for the client and server
+
+  - Start the NFS server
+
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    load the RDMA transport module:
+
+    > modprobe svcrdma
+
+    Regardless of how the server was built (module or built-in), start the server:
+
+    > /etc/init.d/nfs start
+
+    or
+
+    > service nfs start
+
+    Instruct the server to listen on the RDMA transport:
+
+    > echo rdma 2050 > /proc/fs/nfsd/portlist
+
+  - On the client system
+
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    load the RDMA client module:
+
+    > modprobe xprtrdma.ko
+
+    Regardless of how the client was built (module or built-in), issue the mount.nfs command:
+
+    > /path/to/your/mount.nfs <IPoIB-server-name-or-address>:/<export> /mnt -i -o rdma,port=2050
+
+    To verify that the mount is using RDMA, run "cat /proc/mounts" and check the
+    "proto" field for the given mount.
+
+  Congratulations! You're using NFS/RDMA!
diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt
index 7fb8e6dc62bf..b843743aa0b5 100644
--- a/Documentation/filesystems/seq_file.txt
+++ b/Documentation/filesystems/seq_file.txt
@@ -122,8 +122,7 @@ stop() is the place to free it.
         }
 
 Finally, the show() function should format the object currently pointed to
-by the iterator for output. It should return zero, or an error code if
-something goes wrong. The example module's show() function is:
+by the iterator for output.  The example module's show() function is:
 
         static int ct_seq_show(struct seq_file *s, void *v)
         {
@@ -132,6 +131,12 @@ something goes wrong. The example module's show() function is:
                 return 0;
         }
 
+If all is well, the show() function should return zero.  A negative error
+code in the usual manner indicates that something went wrong; it will be
+passed back to user space.  This function can also return SEQ_SKIP, which
+causes the current item to be skipped; if the show() function has already
+generated output before returning SEQ_SKIP, that output will be dropped.
+
 We will look at seq_printf() in a moment. But first, the definition of the
 seq_file iterator is finished by creating a seq_operations structure with
 the four functions we have just defined:
@@ -182,12 +187,18 @@ The first two output a single character and a string, just like one would
 expect. seq_escape() is like seq_puts(), except that any character in s
 which is in the string esc will be represented in octal form in the output.
 
-There is also a function for printing filenames:
+There is also a pair of functions for printing filenames:
 
         int seq_path(struct seq_file *m, struct path *path, char *esc);
+        int seq_path_root(struct seq_file *m, struct path *path,
+                          struct path *root, char *esc)
 
 Here, path indicates the file of interest, and esc is a set of characters
-which should be escaped in the output.
+which should be escaped in the output.  A call to seq_path() will output
+the path relative to the current process's filesystem root.  If a different
+root is desired, it can be used with seq_path_root().  Note that, if it
+turns out that path cannot be reached from root, the value of root will be
+changed in seq_file_root() to a root which *does* work.
 
 
 Making it all work
diff --git a/Documentation/filesystems/tmpfs.txt b/Documentation/filesystems/tmpfs.txt
index 145e44086358..222437efd75a 100644
--- a/Documentation/filesystems/tmpfs.txt
+++ b/Documentation/filesystems/tmpfs.txt
@@ -92,6 +92,18 @@ NodeList format is a comma-separated list of decimal numbers and ranges,
 a range being two hyphen-separated decimal numbers, the smallest and
 largest node numbers in the range.  For example, mpol=bind:0-3,5,7,9-15
 
+NUMA memory allocation policies have optional flags that can be used in
+conjunction with their modes.  These optional flags can be specified
+when tmpfs is mounted by appending them to the mode before the NodeList.
+See Documentation/vm/numa_memory_policy.txt for a list of all available
+memory allocation policy mode flags.
+
+        =static         is equivalent to        MPOL_F_STATIC_NODES
+        =relative       is equivalent to        MPOL_F_RELATIVE_NODES
+
+For example, mpol=bind=static:NodeList, is the equivalent of an
+allocation policy of MPOL_BIND | MPOL_F_STATIC_NODES.
+
 Note that trying to mount a tmpfs with an mpol option will fail if the
 running kernel does not support NUMA; and will fail if its nodelist
 specifies a node which is not online.  If your system relies on that
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index fcc123ffa252..2d5e1e582e13 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -17,6 +17,21 @@ dmask=###     -- The permission mask for the directory.
 fmask=###     -- The permission mask for files.
                  The default is the umask of current process.
 
+allow_utime=### -- This option controls the permission check of mtime/atime.
+
+                  20 - If current process is in group of file's group ID,
+                       you can change timestamp.
+                   2 - Other users can change timestamp.
+
+                 The default is set from `dmask' option. (If the directory is
+                 writable, utime(2) is also allowed. I.e. ~dmask & 022)
+
+                 Normally utime(2) checks current process is owner of
+                 the file, or it has CAP_FOWNER capability.  But FAT
+                 filesystem doesn't have uid/gid on disk, so normal
+                 check is too unflexible. With this option you can
+                 relax it.
+
 codepage=###  -- Sets the codepage number for converting to shortname
                  characters on FAT filesystem.
                  By default, FAT_DEFAULT_CODEPAGE setting is used.
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index 54630095aa3c..c35ca9e40d4c 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -107,6 +107,16 @@ type of GPIO controller, and on one particular board 80-95 with an FPGA.
 The numbers need not be contiguous; either of those platforms could also
 use numbers 2000-2063 to identify GPIOs in a bank of I2C GPIO expanders.
 
+If you want to initialize a structure with an invalid GPIO number, use
+some negative number (perhaps "-EINVAL"); that will never be valid.  To
+test if a number could reference a GPIO, you may use this predicate:
+
+        int gpio_is_valid(int number);
+
+A number that's not valid will be rejected by calls which may request
+or free GPIOs (see below).  Other numbers may also be rejected; for
+example, a number might be valid but unused on a given board.
+
 Whether a platform supports multiple GPIO controllers is currently a
 platform-specific implementation issue.
 
diff --git a/Documentation/i386/boot.txt b/Documentation/i386/boot.txt
index 2eb16100bb3f..95ad15c3b01f 100644
--- a/Documentation/i386/boot.txt
+++ b/Documentation/i386/boot.txt
@@ -40,8 +40,18 @@ Protocol 2.05:	(Kernel 2.6.20) Make protected mode kernel relocatable.
                 Introduce relocatable_kernel and kernel_alignment fields.
 
 Protocol 2.06:  (Kernel 2.6.22) Added a field that contains the size of
-                the boot command line
+                the boot command line.
 
+Protocol 2.07:  (Kernel 2.6.24) Added paravirtualised boot protocol.
+                Introduced hardware_subarch and hardware_subarch_data
+                and KEEP_SEGMENTS flag in load_flags.
+
+Protocol 2.08:  (Kernel 2.6.26) Added crc32 checksum and ELF format
+                payload. Introduced payload_offset and payload length
+                fields to aid in locating the payload.
+
+Protocol 2.09:  (Kernel 2.6.26) Added a field of 64-bit physical
+                pointer to single linked list of struct setup_data.
 
 **** MEMORY LAYOUT
 
@@ -172,6 +182,8 @@ Offset	Proto	Name		Meaning
 0240/8  2.07+   hardware_subarch_data Subarchitecture-specific data
 0248/4  2.08+   payload_offset  Offset of kernel payload
 024C/4  2.08+   payload_length  Length of kernel payload
+0250/8  2.09+   setup_data      64-bit physical pointer to linked list
+                                of struct setup_data
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -572,6 +584,28 @@ command line is entered using the following protocol:
         covered by setup_move_size, so you may need to adjust this
         field.
 
+Field name:     setup_data
+Type:           write (obligatory)
+Offset/size:    0x250/8
+Protocol:       2.09+
+
+  The 64-bit physical pointer to NULL terminated single linked list of
+  struct setup_data. This is used to define a more extensible boot
+  parameters passing mechanism. The definition of struct setup_data is
+  as follow:
+
+  struct setup_data {
+          u64 next;
+          u32 type;
+          u32 len;
+          u8  data[0];
+  };
+
+  Where, the next is a 64-bit physical pointer to the next node of
+  linked list, the next field of the last node is 0; the type is used
+  to identify the contents of data; the len is the length of data
+  field; the data holds the real payload.
+
 
 **** MEMORY LAYOUT OF THE REAL-MODE CODE
 
diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt
new file mode 100644
index 000000000000..bec9d815da33
--- /dev/null
+++ b/Documentation/ia64/kvm.txt
@@ -0,0 +1,82 @@
+Currently, kvm module in EXPERIMENTAL stage on IA64. This means that
+interfaces are not stable enough to use. So, plase had better don't run
+critical applications in virtual machine. We will try our best to make it
+strong in future versions!
+                                Guide: How to boot up guests on kvm/ia64
+
+This guide is to describe how to enable kvm support for IA-64 systems.
+
+1. Get the kvm source from git.kernel.org.
+        Userspace source:
+                git clone git://git.kernel.org/pub/scm/virt/kvm/kvm-userspace.git
+        Kernel Source:
+                git clone git://git.kernel.org/pub/scm/linux/kernel/git/xiantao/kvm-ia64.git
+
+2. Compile the source code.
+        2.1 Compile userspace code:
+                (1)cd ./kvm-userspace
+                (2)./configure
+                (3)cd kernel
+                (4)make sync LINUX= $kernel_dir (kernel_dir is the directory of kernel source.)
+                (5)cd ..
+                (6)make qemu
+                (7)cd qemu; make install
+
+        2.2 Compile kernel source code:
+                (1) cd ./$kernel_dir
+                (2) Make menuconfig
+                (3) Enter into virtualization option, and choose kvm.
+                (4) make
+                (5) Once (4) done, make modules_install
+                (6) Make initrd, and use new kernel to reboot up host machine.
+                (7) Once (6) done, cd $kernel_dir/arch/ia64/kvm
+                (8) insmod kvm.ko; insmod kvm-intel.ko
+
+Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qemu, otherwise, may fail.
+
+3. Get Guest Firmware named as Flash.fd, and put it under right place:
+        (1) If you have the guest firmware (binary) released by Intel Corp for Xen, use it directly.
+
+        (2) If you have no firmware at hand, Please download its source from
+                hg clone http://xenbits.xensource.com/ext/efi-vfirmware.hg
+            you can get the firmware's binary in the directory of efi-vfirmware.hg/binaries.
+
+        (3) Rename the firware you owned to Flash.fd, and copy it to /usr/local/share/qemu
+
+4. Boot up Linux or Windows guests:
+        4.1 Create or install a image for guest boot. If you have xen experience, it should be easy.
+
+        4.2 Boot up guests use the following command.
+                /usr/local/bin/qemu-system-ia64 -smp xx -m 512 -hda $your_image
+                (xx is the number of virtual processors for the guest, now the maximum value is 4)
+
+5. Known possibile issue on some platforms with old Firmware.
+
+If meet strange host crashe issues, try to solve it through either of the following ways:
+
+(1): Upgrade your Firmware to the latest one.
+
+(2): Applying the below patch to kernel source.
+diff --git a/arch/ia64/kernel/pal.S b/arch/ia64/kernel/pal.S
+index 0b53344..f02b0f7 100644
+--- a/arch/ia64/kernel/pal.S
++++ b/arch/ia64/kernel/pal.S
+@@ -84,7 +84,8 @@ GLOBAL_ENTRY(ia64_pal_call_static)
+        mov ar.pfs = loc1
+        mov rp = loc0
+        ;;
+-       srlz.d                          // seralize restoration of psr.l
++       srlz.i                  // seralize restoration of psr.l
++       ;;
+        br.ret.sptk.many b0
+ END(ia64_pal_call_static)
+
+6. Bug report:
+        If you found any issues when use kvm/ia64, Please post the bug info to kvm-ia64-devel mailing list.
+        https://lists.sourceforge.net/lists/listinfo/kvm-ia64-devel/
+
+Thanks for your interest! Let's work together, and make kvm/ia64 stronger and stronger!
+
+
+                                                                Xiantao Zhang <xiantao.zhang@intel.com>
+                                                                                        2008.3.10
diff --git a/Documentation/ide/ide-tape.txt b/Documentation/ide/ide-tape.txt
index 658f271a373f..3f348a0b21d8 100644
--- a/Documentation/ide/ide-tape.txt
+++ b/Documentation/ide/ide-tape.txt
@@ -1,146 +1,65 @@
-/*
- * IDE ATAPI streaming tape driver.
- *
- * This driver is a part of the Linux ide driver.
- *
- * The driver, in co-operation with ide.c, basically traverses the
- * request-list for the block device interface. The character device
- * interface, on the other hand, creates new requests, adds them
- * to the request-list of the block device, and waits for their completion.
- *
- * Pipelined operation mode is now supported on both reads and writes.
- *
- * The block device major and minor numbers are determined from the
- * tape's relative position in the ide interfaces, as explained in ide.c.
- *
- * The character device interface consists of the following devices:
- *
- * ht0          major 37, minor 0       first  IDE tape, rewind on close.
- * ht1          major 37, minor 1       second IDE tape, rewind on close.
- * ...
- * nht0         major 37, minor 128     first  IDE tape, no rewind on close.
- * nht1         major 37, minor 129     second IDE tape, no rewind on close.
- * ...
- *
- * The general magnetic tape commands compatible interface, as defined by
- * include/linux/mtio.h, is accessible through the character device.
- *
- * General ide driver configuration options, such as the interrupt-unmask
- * flag, can be configured by issuing an ioctl to the block device interface,
- * as any other ide device.
- *
- * Our own ide-tape ioctl's can be issued to either the block device or
- * the character device interface.
- *
- * Maximal throughput with minimal bus load will usually be achieved in the
- * following scenario:
- *
- *      1.      ide-tape is operating in the pipelined operation mode.
- *      2.      No buffering is performed by the user backup program.
- *
- * Testing was done with a 2 GB CONNER CTMA 4000 IDE ATAPI Streaming Tape Drive.
- *
- * Here are some words from the first releases of hd.c, which are quoted
- * in ide.c and apply here as well:
- *
- * | Special care is recommended.  Have Fun!
- *
- *
- * An overview of the pipelined operation mode.
- *
- * In the pipelined write mode, we will usually just add requests to our
- * pipeline and return immediately, before we even start to service them. The
- * user program will then have enough time to prepare the next request while
- * we are still busy servicing previous requests. In the pipelined read mode,
- * the situation is similar - we add read-ahead requests into the pipeline,
- * before the user even requested them.
- *
- * The pipeline can be viewed as a "safety net" which will be activated when
- * the system load is high and prevents the user backup program from keeping up
- * with the current tape speed. At this point, the pipeline will get
- * shorter and shorter but the tape will still be streaming at the same speed.
- * Assuming we have enough pipeline stages, the system load will hopefully
- * decrease before the pipeline is completely empty, and the backup program
- * will be able to "catch up" and refill the pipeline again.
- *
- * When using the pipelined mode, it would be best to disable any type of
- * buffering done by the user program, as ide-tape already provides all the
- * benefits in the kernel, where it can be done in a more efficient way.
- * As we will usually not block the user program on a request, the most
- * efficient user code will then be a simple read-write-read-... cycle.
- * Any additional logic will usually just slow down the backup process.
- *
- * Using the pipelined mode, I get a constant over 400 KBps throughput,
- * which seems to be the maximum throughput supported by my tape.
- *
- * However, there are some downfalls:
- *
- *      1.      We use memory (for data buffers) in proportional to the number
- *              of pipeline stages (each stage is about 26 KB with my tape).
- *      2.      In the pipelined write mode, we cheat and postpone error codes
- *              to the user task. In read mode, the actual tape position
- *              will be a bit further than the last requested block.
- *
- * Concerning (1):
- *
- *      1.      We allocate stages dynamically only when we need them. When
- *              we don't need them, we don't consume additional memory. In
- *              case we can't allocate stages, we just manage without them
- *              (at the expense of decreased throughput) so when Linux is
- *              tight in memory, we will not pose additional difficulties.
- *
- *      2.      The maximum number of stages (which is, in fact, the maximum
- *              amount of memory) which we allocate is limited by the compile
- *              time parameter IDETAPE_MAX_PIPELINE_STAGES.
- *
- *      3.      The maximum number of stages is a controlled parameter - We
- *              don't start from the user defined maximum number of stages
- *              but from the lower IDETAPE_MIN_PIPELINE_STAGES (again, we
- *              will not even allocate this amount of stages if the user
- *              program can't handle the speed). We then implement a feedback
- *              loop which checks if the pipeline is empty, and if it is, we
- *              increase the maximum number of stages as necessary until we
- *              reach the optimum value which just manages to keep the tape
- *              busy with minimum allocated memory or until we reach
- *              IDETAPE_MAX_PIPELINE_STAGES.
- *
- * Concerning (2):
- *
- *      In pipelined write mode, ide-tape can not return accurate error codes
- *      to the user program since we usually just add the request to the
- *      pipeline without waiting for it to be serviced. In case an error
- *      occurs, I will report it on the next user request.
- *
- *      In the pipelined read mode, subsequent read requests or forward
- *      filemark spacing will perform correctly, as we preserve all blocks
- *      and filemarks which we encountered during our excess read-ahead.
- *
- *      For accurate tape positioning and error reporting, disabling
- *      pipelined mode might be the best option.
- *
- * You can enable/disable/tune the pipelined operation mode by adjusting
- * the compile time parameters below.
- *
- *
- *      Possible improvements.
- *
- *      1.      Support for the ATAPI overlap protocol.
- *
- *              In order to maximize bus throughput, we currently use the DSC
- *              overlap method which enables ide.c to service requests from the
- *              other device while the tape is busy executing a command. The
- *              DSC overlap method involves polling the tape's status register
- *              for the DSC bit, and servicing the other device while the tape
- *              isn't ready.
- *
- *              In the current QIC development standard (December 1995),
- *              it is recommended that new tape drives will *in addition*
- *              implement the ATAPI overlap protocol, which is used for the
- *              same purpose - efficient use of the IDE bus, but is interrupt
- *              driven and thus has much less CPU overhead.
- *
- *              ATAPI overlap is likely to be supported in most new ATAPI
- *              devices, including new ATAPI cdroms, and thus provides us
- *              a method by which we can achieve higher throughput when
- *              sharing a (fast) ATA-2 disk with any (slow) new ATAPI device.
- */
+IDE ATAPI streaming tape driver.
+
+This driver is a part of the Linux ide driver.
+
+The driver, in co-operation with ide.c, basically traverses the
+request-list for the block device interface. The character device
+interface, on the other hand, creates new requests, adds them
+to the request-list of the block device, and waits for their completion.
+
+The block device major and minor numbers are determined from the
+tape's relative position in the ide interfaces, as explained in ide.c.
+
+The character device interface consists of the following devices:
+
+ht0             major 37, minor 0       first  IDE tape, rewind on close.
+ht1             major 37, minor 1       second IDE tape, rewind on close.
+...
+nht0            major 37, minor 128     first  IDE tape, no rewind on close.
+nht1            major 37, minor 129     second IDE tape, no rewind on close.
+...
+
+The general magnetic tape commands compatible interface, as defined by
+include/linux/mtio.h, is accessible through the character device.
+
+General ide driver configuration options, such as the interrupt-unmask
+flag, can be configured by issuing an ioctl to the block device interface,
+as any other ide device.
+
+Our own ide-tape ioctl's can be issued to either the block device or
+the character device interface.
+
+Maximal throughput with minimal bus load will usually be achieved in the
+following scenario:
+
+     1. ide-tape is operating in the pipelined operation mode.
+     2. No buffering is performed by the user backup program.
+
+Testing was done with a 2 GB CONNER CTMA 4000 IDE ATAPI Streaming Tape Drive.
+
+Here are some words from the first releases of hd.c, which are quoted
+in ide.c and apply here as well:
+
+| Special care is recommended.  Have Fun!
+
+Possible improvements:
+
+1. Support for the ATAPI overlap protocol.
+
+In order to maximize bus throughput, we currently use the DSC
+overlap method which enables ide.c to service requests from the
+other device while the tape is busy executing a command. The
+DSC overlap method involves polling the tape's status register
+for the DSC bit, and servicing the other device while the tape
+isn't ready.
+
+In the current QIC development standard (December 1995),
+it is recommended that new tape drives will *in addition*
+implement the ATAPI overlap protocol, which is used for the
+same purpose - efficient use of the IDE bus, but is interrupt
+driven and thus has much less CPU overhead.
+
+ATAPI overlap is likely to be supported in most new ATAPI
+devices, including new ATAPI cdroms, and thus provides us
+a method by which we can achieve higher throughput when
+sharing a (fast) ATA-2 disk with any (slow) new ATAPI device.
diff --git a/Documentation/ide/ide.txt b/Documentation/ide/ide.txt
index 486c699f4aea..0c78f4b1d9d9 100644
--- a/Documentation/ide/ide.txt
+++ b/Documentation/ide/ide.txt
@@ -82,27 +82,26 @@ Drives are normally found by auto-probing and/or examining the CMOS/BIOS data.
 For really weird situations, the apparent (fdisk) geometry can also be specified
 on the kernel "command line" using LILO.  The format of such lines is:
 
-        hdx=cyls,heads,sects
-or      hdx=cdrom
+        ide_core.chs=[interface_number.device_number]:cyls,heads,sects
+or      ide_core.cdrom=[interface_number.device_number]
 
-where hdx can be any of hda through hdh, Three values are required
-(cyls,heads,sects).  For example:
+For example:
 
-        hdc=1050,32,64  hdd=cdrom
+        ide_core.chs=1.0:1050,32,64  ide_core.cdrom=1.1
 
-either {hda,hdb} or {hdc,hdd}.  The results of successful auto-probing may
-override the physical geometry/irq specified, though the "original" geometry
-may be retained as the "logical" geometry for partitioning purposes (fdisk).
+The results of successful auto-probing may override the physical geometry/irq
+specified, though the "original" geometry may be retained as the "logical"
+geometry for partitioning purposes (fdisk).
 
 If the auto-probing during boot time confuses a drive (ie. the drive works
 with hd.c but not with ide.c), then an command line option may be specified
 for each drive for which you'd like the drive to skip the hardware
 probe/identification sequence.  For example:
 
-        hdb=noprobe
+        ide_core.noprobe=0.1
 or
-        hdc=768,16,32
-        hdc=noprobe
+        ide_core.chs=1.0:768,16,32
+        ide_core.noprobe=1.0
 
 Note that when only one IDE device is attached to an interface, it should be
 jumpered as "single" or "master", *not* "slave".  Many folks have had
@@ -118,9 +117,9 @@ If for some reason your cdrom drive is *not* found at boot time, you can force
 the probe to look harder by supplying a kernel command line parameter
 via LILO, such as:
 
-        hdc=cdrom       /* hdc = "master" on second interface */
+        ide_core.cdrom=1.0      /* "master" on second interface (hdc) */
 or
-        hdd=cdrom       /* hdd = "slave" on second interface */
+        ide_core.cdrom=1.1      /* "slave" on second interface (hdd) */
 
 For example, a GW2000 system might have a hard drive on the primary
 interface (/dev/hda) and an IDE cdrom drive on the secondary interface
@@ -174,9 +173,7 @@ to /etc/modprobe.conf.
 
 When ide.c is used as a module, you can pass command line parameters to the
 driver using the "options=" keyword to insmod, while replacing any ',' with
-';'.  For example:
-
-        insmod ide.o options="hda=nodma hdb=nodma"
+';'.
 
 
 ================================================================================
@@ -184,57 +181,6 @@ driver using the "options=" keyword to insmod, while replacing any ',' with
 Summary of ide driver parameters for kernel command line
 --------------------------------------------------------
 
- "hdx="  is recognized for all "x" from "a" to "u", such as "hdc".
-
- "idex=" is recognized for all "x" from "0" to "9", such as "ide1".
-
- "hdx=noprobe"          : drive may be present, but do not probe for it
-
- "hdx=none"             : drive is NOT present, ignore cmos and do not probe
-
- "hdx=nowerr"           : ignore the WRERR_STAT bit on this drive
-
- "hdx=cdrom"            : drive is present, and is a cdrom drive
-
- "hdx=cyl,head,sect"    : disk drive is present, with specified geometry
-
- "hdx=autotune"         : driver will attempt to tune interface speed
-                          to the fastest PIO mode supported,
-                          if possible for this drive only.
-                          Not fully supported by all chipset types,
-                          and quite likely to cause trouble with
-                          older/odd IDE drives.
-
- "hdx=nodma"            : disallow DMA
-
- "idebus=xx"            : inform IDE driver of VESA/PCI bus speed in MHz,
-                          where "xx" is between 20 and 66 inclusive,
-                          used when tuning chipset PIO modes.
-                          For PCI bus, 25 is correct for a P75 system,
-                          30 is correct for P90,P120,P180 systems,
-                          and 33 is used for P100,P133,P166 systems.
-                          If in doubt, use idebus=33 for PCI.
-                          As for VLB, it is safest to not specify it.
-                          Bigger values are safer than smaller ones.
-
- "idex=serialize"       : do not overlap operations on idex. Please note
-                          that you will have to specify this option for
-                          both the respective primary and secondary channel
-                          to take effect.
-
- "idex=reset"           : reset interface after probe
-
- "idex=ata66"           : informs the interface that it has an 80c cable
-                          for chipsets that are ATA-66 capable, but the
-                          ability to bit test for detection is currently
-                          unknown.
-
- "ide=doubler"          : probe/support IDE doublers on Amiga
-
-There may be more options than shown -- use the source, Luke!
-
-Everything else is rejected with a "BAD OPTION" message.
-
 For legacy IDE VLB host drivers (ali14xx/dtc2278/ht6560b/qd65xx/umc8672)
 you need to explicitly enable probing by using "probe" kernel parameter,
 i.e. to enable probing for ALI M14xx chipsets (ali14xx host driver) use:
@@ -251,6 +197,33 @@ are detected automatically).
 You also need to use "probe" kernel parameter for ide-4drives driver
 (support for IDE generic chipset with four drives on one port).
 
+To enable support for IDE doublers on Amiga use "doubler" kernel parameter
+for gayle host driver (i.e. "gayle.doubler" if the driver is built-in).
+
+To force ignoring cable detection (this should be needed only if you're using
+short 40-wires cable which cannot be automatically detected - if this is not
+a case please report it as a bug instead) use "ignore_cable" kernel parameter:
+
+* "ide_core.ignore_cable=[interface_number]" boot option if IDE is built-in
+  (i.e. "ide_core.ignore_cable=1" to force ignoring cable for "ide1")
+
+* "ignore_cable=[interface_number]" module parameter (for ide_core module)
+  if IDE is compiled as module
+
+Other kernel parameters for ide_core are:
+
+* "nodma=[interface_number.device_number]" to disallow DMA for a device
+
+* "noflush=[interface_number.device_number]" to disable flush requests
+
+* "noprobe=[interface_number.device_number]" to skip probing
+
+* "nowerr=[interface_number.device_number]" to ignore the WRERR_STAT bit
+
+* "cdrom=[interface_number.device_number]" to force device as a CD-ROM
+
+* "chs=[interface_number.device_number]" to force device as a disk (using CHS)
+
 ================================================================================
 
 Some Terminology
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index c18363bd8d11..240ce7a56c40 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -183,6 +183,8 @@ Code	Seq#	Include File		Comments
 0xAC    00-1F   linux/raw.h
 0xAD    00      Netfilter device        in development:
                                         <mailto:rusty@rustcorp.com.au>  
+0xAE    all     linux/kvm.h             Kernel-based Virtual Machine
+                                        <mailto:kvm-devel@lists.sourceforge.net>
 0xB0    all     RATIO devices           in development:
                                         <mailto:vgo@ratio.de>
 0xB1    00-1F   PPPoX                   <mailto:mostrows@styx.uwaterloo.ca>
diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index 649cb8799890..00b950d1c193 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -104,14 +104,15 @@ applicable everywhere (see syntax).
   Reverse dependencies can only be used with boolean or tristate
   symbols.
   Note:
-        select is evil.... select will by brute force set a symbol
-        equal to 'y' without visiting the dependencies. So abusing
-        select you are able to select a symbol FOO even if FOO depends
-        on BAR that is not set. In general use select only for
-        non-visible symbols (no prompts anywhere) and for symbols with
-        no dependencies. That will limit the usefulness but on the
-        other hand avoid the illegal configurations all over. kconfig
-        should one day warn about such things.
+        select should be used with care. select will force
+        a symbol to a value without visiting the dependencies.
+        By abusing select you are able to select a symbol FOO even
+        if FOO depends on BAR that is not set.
+        In general use select only for non-visible symbols
+        (no prompts anywhere) and for symbols with no dependencies.
+        That will limit the usefulness but on the other hand avoid
+        the illegal configurations all over.
+        kconfig should one day warn about such things.
 
 - numerical ranges: "range" <symbol> <symbol> ["if" <expr>]
   This allows to limit the range of possible input values for int
diff --git a/Documentation/kbuild/modules.txt b/Documentation/kbuild/modules.txt
index 1d247d59ad56..1821c077b435 100644
--- a/Documentation/kbuild/modules.txt
+++ b/Documentation/kbuild/modules.txt
@@ -486,7 +486,7 @@ Module.symvers contains a list of all exported symbols from a kernel build.
         Sometimes, an external module uses exported symbols from another
         external module. Kbuild needs to have full knowledge on all symbols
         to avoid spitting out warnings about undefined symbols.
-        Two solutions exist to let kbuild know all symbols of more than
+        Three solutions exist to let kbuild know all symbols of more than
         one external module.
         The method with a top-level kbuild file is recommended but may be
         impractical in certain situations.
@@ -523,6 +523,13 @@ Module.symvers contains a list of all exported symbols from a kernel build.
                 containing the sum of all symbols defined and not part of the
                 kernel.
 
+        Use make variable KBUILD_EXTRA_SYMBOLS in the Makefile
+                If it is impractical to copy Module.symvers from another
+                module, you can assign a space separated list of files to
+                KBUILD_EXTRA_SYMBOLS in your Makfile. These files will be
+                loaded by modpost during the initialisation of its symbol
+                tables.
+
 === 8. Tips & Tricks
 
 --- 8.1 Testing for CONFIG_FOO_BAR
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index bf6303ec0bde..3ce193f86565 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -627,8 +627,7 @@ and is between 256 and 4096 characters. It is defined in the file
         eata=           [HW,SCSI]
 
         edd=            [EDD]
-                        Format: {"of[f]" | "sk[ipmbr]"}
-                        See comment in arch/i386/boot/edd.S
+                        Format: {"off" | "on" | "skip[mbr]"}
 
         eisa_irq_edge=  [PARISC,HW]
                         See header of drivers/parisc/eisa.c.
@@ -772,10 +771,6 @@ and is between 256 and 4096 characters. It is defined in the file
                         Format: ide=nodma or ide=doubler
                         See Documentation/ide/ide.txt.
 
-        ide?=           [HW] (E)IDE subsystem
-                        Format: ide?=ata66 or chipset specific parameters.
-                        See Documentation/ide/ide.txt.
-
         idebus=         [HW] (E)IDE subsystem - VLB/PCI bus speed
                         See Documentation/ide/ide.txt.
 
@@ -1393,6 +1388,13 @@ and is between 256 and 4096 characters. It is defined in the file
 
         nr_uarts=       [SERIAL] maximum number of UARTs to be registered.
 
+        olpc_ec_timeout= [OLPC] ms delay when issuing EC commands
+                        Rather than timing out after 20 ms if an EC
+                        command is not properly ACKed, override the length
+                        of the timeout.  We have interrupts disabled while
+                        waiting for the ACK, so if this is set too high
+                        interrupts *may* be lost!
+
         opl3=           [HW,OSS]
                         Format: <io>
 
diff --git a/Documentation/keys-request-key.txt b/Documentation/keys-request-key.txt
index 266955d23ee6..09b55e461740 100644
--- a/Documentation/keys-request-key.txt
+++ b/Documentation/keys-request-key.txt
@@ -11,26 +11,29 @@ request_key*():
 
         struct key *request_key(const struct key_type *type,
                                 const char *description,
-                                const char *callout_string);
+                                const char *callout_info);
 
 or:
 
         struct key *request_key_with_auxdata(const struct key_type *type,
                                              const char *description,
-                                             const char *callout_string,
+                                             const char *callout_info,
+                                             size_t callout_len,
                                              void *aux);
 
 or:
 
         struct key *request_key_async(const struct key_type *type,
                                       const char *description,
-                                      const char *callout_string);
+                                      const char *callout_info,
+                                      size_t callout_len);
 
 or:
 
         struct key *request_key_async_with_auxdata(const struct key_type *type,
                                                    const char *description,
-                                                   const char *callout_string,
+                                                   const char *callout_info,
+                                                   size_t callout_len,
                                                    void *aux);
 
 Or by userspace invoking the request_key system call:
diff --git a/Documentation/keys.txt b/Documentation/keys.txt
index 51652d39e61c..d5c7a57d1700 100644
--- a/Documentation/keys.txt
+++ b/Documentation/keys.txt
@@ -170,7 +170,8 @@ The key service provides a number of features besides keys:
      amount of description and payload space that can be consumed.
 
      The user can view information on this and other statistics through procfs
-     files.
+     files.  The root user may also alter the quota limits through sysctl files
+     (see the section "New procfs files").
 
      Process-specific and thread-specific keyrings are not counted towards a
      user's quota.
@@ -329,6 +330,27 @@ about the status of the key service:
         <bytes>/<max>           Key size quota
 
 
+Four new sysctl files have been added also for the purpose of controlling the
+quota limits on keys:
+
+ (*) /proc/sys/kernel/keys/root_maxkeys
+     /proc/sys/kernel/keys/root_maxbytes
+
+     These files hold the maximum number of keys that root may have and the
+     maximum total number of bytes of data that root may have stored in those
+     keys.
+
+ (*) /proc/sys/kernel/keys/maxkeys
+     /proc/sys/kernel/keys/maxbytes
+
+     These files hold the maximum number of keys that each non-root user may
+     have and the maximum total number of bytes of data that each of those
+     users may have stored in their keys.
+
+Root may alter these by writing each new limit as a decimal number string to
+the appropriate file.
+
+
 ===============================
 USERSPACE SYSTEM CALL INTERFACE
 ===============================
@@ -711,6 +733,27 @@ The keyctl syscall functions are:
      The assumed authoritative key is inherited across fork and exec.
 
 
+ (*) Get the LSM security context attached to a key.
+
+        long keyctl(KEYCTL_GET_SECURITY, key_serial_t key, char *buffer,
+                    size_t buflen)
+
+     This function returns a string that represents the LSM security context
+     attached to a key in the buffer provided.
+
+     Unless there's an error, it always returns the amount of data it could
+     produce, even if that's too big for the buffer, but it won't copy more
+     than requested to userspace. If the buffer pointer is NULL then no copy
+     will take place.
+
+     A NUL character is included at the end of the string if the buffer is
+     sufficiently big.  This is included in the returned count.  If no LSM is
+     in force then an empty string will be returned.
+
+     A process must have view permission on the key for this function to be
+     successful.
+
+
 ===============
 KERNEL SERVICES
 ===============
@@ -771,7 +814,7 @@ payload contents" for more information.
 
         struct key *request_key(const struct key_type *type,
                                 const char *description,
-                                const char *callout_string);
+                                const char *callout_info);
 
     This is used to request a key or keyring with a description that matches
     the description specified according to the key type's match function. This
@@ -793,24 +836,28 @@ payload contents" for more information.
 
         struct key *request_key_with_auxdata(const struct key_type *type,
                                              const char *description,
-                                             const char *callout_string,
+                                             const void *callout_info,
+                                             size_t callout_len,
                                              void *aux);
 
     This is identical to request_key(), except that the auxiliary data is
-    passed to the key_type->request_key() op if it exists.
+    passed to the key_type->request_key() op if it exists, and the callout_info
+    is a blob of length callout_len, if given (the length may be 0).
 
 
 (*) A key can be requested asynchronously by calling one of:
 
         struct key *request_key_async(const struct key_type *type,
                                       const char *description,
-                                      const char *callout_string);
+                                      const void *callout_info,
+                                      size_t callout_len);
 
     or:
 
         struct key *request_key_async_with_auxdata(const struct key_type *type,
                                                    const char *description,
-                                                   const char *callout_string,
+                                                   const char *callout_info,
+                                                   size_t callout_len,
                                                    void *aux);
 
     which are asynchronous equivalents of request_key() and
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index be89f393274f..6877e7187113 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -37,6 +37,11 @@ registration function such as register_kprobe() specifies where
 the probe is to be inserted and what handler is to be called when
 the probe is hit.
 
+There are also register_/unregister_*probes() functions for batch
+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
@@ -190,10 +195,11 @@ code mapping.
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
-function for each type of probe.  Here are terse, mini-man-page
-specifications for these functions and the associated probe handlers
-that you'll write.  See the files in the samples/kprobes/ sub-directory
-for examples.
+function for each type of probe. The API also includes "register_*probes"
+and "unregister_*probes" functions for (un)registering arrays of probes.
+Here are terse, mini-man-page specifications for these functions and
+the associated probe handlers that you'll write. See the files in the
+samples/kprobes/ sub-directory for examples.
 
 4.1 register_kprobe
 
@@ -319,6 +325,43 @@ void unregister_kretprobe(struct kretprobe *rp);
 Removes the specified probe.  The unregister function can be called
 at any time after the probe has been registered.
 
+NOTE:
+If the functions find an incorrect probe (ex. an unregistered probe),
+they clear the addr field of the probe.
+
+4.5 register_*probes
+
+#include <linux/kprobes.h>
+int register_kprobes(struct kprobe **kps, int num);
+int register_kretprobes(struct kretprobe **rps, int num);
+int register_jprobes(struct jprobe **jps, int num);
+
+Registers each of the num probes in the specified array.  If any
+error occurs during registration, all probes in the array, up to
+the bad probe, are safely unregistered before the register_*probes
+function returns.
+- kps/rps/jps: an array of pointers to *probe data structures
+- num: the number of the array entries.
+
+NOTE:
+You have to allocate(or define) an array of pointers and set all
+of the array entries before using these functions.
+
+4.6 unregister_*probes
+
+#include <linux/kprobes.h>
+void unregister_kprobes(struct kprobe **kps, int num);
+void unregister_kretprobes(struct kretprobe **rps, int num);
+void unregister_jprobes(struct jprobe **jps, int num);
+
+Removes each of the num probes in the specified array at once.
+
+NOTE:
+If the functions find some incorrect probes (ex. unregistered
+probes) in the specified array, they clear the addr field of those
+incorrect probes. However, other probes in the array are
+unregistered correctly.
+
 5. Kprobes Features and Limitations
 
 Kprobes allows multiple probes at the same address.  Currently,
diff --git a/Documentation/leds-class.txt b/Documentation/leds-class.txt
index 56757c751d6f..18860ad9935a 100644
--- a/Documentation/leds-class.txt
+++ b/Documentation/leds-class.txt
@@ -19,6 +19,12 @@ optimises away.
 
 Complex triggers whilst available to all LEDs have LED specific
 parameters and work on a per LED basis. The timer trigger is an example.
+The timer trigger will periodically change the LED brightness between
+LED_OFF and the current brightness setting. The "on" and "off" time can
+be specified via /sys/class/leds/<device>/delay_{on,off} in milliseconds.
+You can change the brightness value of a LED independently of the timer
+trigger. However, if you set the brightness value to LED_OFF it will
+also disable the timer trigger.
 
 You can change triggers in a similar manner to the way an IO scheduler
 is chosen (via /sys/class/leds/<device>/trigger). Trigger specific
@@ -63,9 +69,9 @@ value if it is called with *delay_on==0 && *delay_off==0 parameters. In
 this case the driver should give back the chosen value through delay_on
 and delay_off parameters to the leds subsystem.
 
-Any call to the brightness_set() callback function should cancel the
-previously programmed hardware blinking function so setting the brightness
-to 0 can also cancel the blinking of the LED.
+Setting the brightness to zero with brightness_set() callback function
+should completely turn off the LED and cancel the previously programmed
+hardware blinking function, if any.
 
 
 Known Issues
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 396cdd982c26..a8b430627473 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -450,3 +450,9 @@ These currently include
       there are upper and lower limits (32768, 16).  Default is 128.
   strip_cache_active (currently raid5 only)
       number of active entries in the stripe cache
+  preread_bypass_threshold (currently raid5 only)
+      number of times a stripe requiring preread will be bypassed by
+      a stripe that does not require preread.  For fairness defaults
+      to 1.  Setting this to 0 disables bypass accounting and
+      requires preread stripes to wait until all full-width stripe-
+      writes are complete.  Valid values are 0 to stripe_cache_size.
diff --git a/Documentation/mips/AU1xxx_IDE.README b/Documentation/mips/AU1xxx_IDE.README
index 5c8334123f4f..25a6ed1aaa5b 100644
--- a/Documentation/mips/AU1xxx_IDE.README
+++ b/Documentation/mips/AU1xxx_IDE.README
@@ -46,8 +46,6 @@ Two files are introduced:
 
   a) 'include/asm-mips/mach-au1x00/au1xxx_ide.h'
      containes : struct _auide_hwif
-                 struct drive_list_entry dma_white_list
-                 struct drive_list_entry dma_black_list
                  timing parameters for PIO mode 0/1/2/3/4
                  timing parameters for MWDMA 0/1/2
 
@@ -63,12 +61,6 @@ Four configs variables are introduced:
   CONFIG_BLK_DEV_IDE_AU1XXX_SEQTS_PER_RQ - maximum transfer size
                                            per descriptor
 
-If MWDMA is enabled and the connected hard disc is not on the white list, the
-kernel switches to a "safe mwdma mode" at boot time. In this mode the IDE
-performance is substantial slower then in full speed mwdma. In this case
-please add your hard disc to the white list (follow instruction from 'ADD NEW
-HARD DISC TO WHITE OR BLACK LIST' section).
-
 
 SUPPORTED IDE MODES
 -------------------
@@ -120,44 +112,6 @@ CONFIG_IDEDMA_AUTO=y
 Also undefine 'IDE_AU1XXX_BURSTMODE' in 'drivers/ide/mips/au1xxx-ide.c' to
 disable the burst support on DBDMA controller.
 
-ADD NEW HARD DISC TO WHITE OR BLACK LIST
-----------------------------------------
-
-Step 1 : detect the model name of your hard disc
-
-  a) connect your hard disc to the AU1XXX
-
-  b) boot your kernel and get the hard disc model.
-
-     Example boot log:
-
-     --snipped--
-     Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
-     ide: Assuming 50MHz system bus speed for PIO modes; override with idebus=xx
-     Au1xxx IDE(builtin) configured for MWDMA2
-     Probing IDE interface ide0...
-     hda: Maxtor 6E040L0, ATA DISK drive
-     ide0 at 0xac800000-0xac800007,0xac8001c0 on irq 64
-     hda: max request size: 64KiB
-     hda: 80293248 sectors (41110 MB) w/2048KiB Cache, CHS=65535/16/63, (U)DMA
-     --snipped--
-
-     In this example 'Maxtor 6E040L0'.
-
-Step  2 : edit 'include/asm-mips/mach-au1x00/au1xxx_ide.h'
-
-  Add your hard disc to the dma_white_list or dma_black_list structur.
-
-Step 3 : Recompile the kernel
-
-  Enable MWDMA support in the kernel configuration. Recompile the kernel and
-  reboot.
-
-Step 4 : Tests
-
-  If you have add a hard disc to the white list, please run some stress tests
-  for verification.
-
 
 ACKNOWLEDGMENTS
 ---------------
diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt
index 0bc95eab1512..8df6a7b0e66c 100644
--- a/Documentation/networking/phy.txt
+++ b/Documentation/networking/phy.txt
@@ -1,7 +1,7 @@
 
 -------
 PHY Abstraction Layer
-(Updated 2006-11-30)
+(Updated 2008-04-08)
 
 Purpose
 
@@ -291,3 +291,39 @@ Writing a PHY driver
  Feel free to look at the Marvell, Cicada, and Davicom drivers in
  drivers/net/phy/ for examples (the lxt and qsemi drivers have
  not been tested as of this writing)
+
+Board Fixups
+
+ Sometimes the specific interaction between the platform and the PHY requires
+ special handling.  For instance, to change where the PHY's clock input is,
+ or to add a delay to account for latency issues in the data path.  In order
+ to support such contingencies, the PHY Layer allows platform code to register
+ fixups to be run when the PHY is brought up (or subsequently reset).
+
+ When the PHY Layer brings up a PHY it checks to see if there are any fixups
+ registered for it, matching based on UID (contained in the PHY device's phy_id
+ field) and the bus identifier (contained in phydev->dev.bus_id).  Both must
+ match, however two constants, PHY_ANY_ID and PHY_ANY_UID, are provided as
+ wildcards for the bus ID and UID, respectively.
+
+ When a match is found, the PHY layer will invoke the run function associated
+ with the fixup.  This function is passed a pointer to the phy_device of
+ interest.  It should therefore only operate on that PHY.
+
+ The platform code can either register the fixup using phy_register_fixup():
+
+        int phy_register_fixup(const char *phy_id,
+                u32 phy_uid, u32 phy_uid_mask,
+                int (*run)(struct phy_device *));
+
+ Or using one of the two stubs, phy_register_fixup_for_uid() and
+ phy_register_fixup_for_id():
+
+ int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask,
+                int (*run)(struct phy_device *));
+ int phy_register_fixup_for_id(const char *phy_id,
+                int (*run)(struct phy_device *));
+
+ The stubs set one of the two matching criteria, and set the other one to
+ match anything.
+
diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt
index 7f60dfe642ca..b152e81da592 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -253,6 +253,10 @@ characters, each representing a particular tainted value.
 
   8: 'D' if the kernel has died recently, i.e. there was an OOPS or BUG.
 
+  9: 'A' if the ACPI table has been overridden.
+
+ 10: 'W' if a warning has previously been issued by the kernel.
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index 4cc780024e6c..1d2a772506cf 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -2601,6 +2601,17 @@ platforms are moved over to use the flattened-device-tree model.
                       differ between different families.  May be
                       'virtex2p', 'virtex4', or 'virtex5'.
 
+      vi) Xilinx Uart 16550
+
+      Xilinx UART 16550 devices are very similar to the NS16550 but with
+      different register spacing and an offset from the base address.
+
+      Requred properties:
+       - clock-frequency : Frequency of the clock input
+       - reg-offset : A value of 3 is required
+       - reg-shift : A value of 2 is required
+
+
     p) Freescale Synchronous Serial Interface
 
        The SSI is a serial device that communicates with audio codecs.  It can
@@ -2825,6 +2836,39 @@ platforms are moved over to use the flattened-device-tree model.
                    big-endian;
            };
 
+    r) Freescale Display Interface Unit
+
+    The Freescale DIU is a LCD controller, with proper hardware, it can also
+    drive DVI monitors.
+
+    Required properties:
+    - compatible : should be "fsl-diu".
+    - reg : should contain at least address and length of the DIU register
+      set.
+    - Interrupts : one DIU interrupt should be describe here.
+
+    Example (MPC8610HPCD)
+        display@2c000 {
+                compatible = "fsl,diu";
+                reg = <0x2c000 100>;
+                interrupts = <72 2>;
+                interrupt-parent = <&mpic>;
+        };
+
+    s) Freescale on board FPGA
+
+    This is the memory-mapped registers for on board FPGA.
+
+    Required properities:
+    - compatible : should be "fsl,fpga-pixis".
+    - reg : should contain the address and the lenght of the FPPGA register
+      set.
+
+    Example (MPC8610HPCD)
+        board-control@e8000000 {
+                compatible = "fsl,fpga-pixis";
+                reg = <0xe8000000 32>;
+        };
 
 VII - Marvell Discovery mv64[345]6x System Controller chips
 ===========================================================
diff --git a/Documentation/powerpc/kvm_440.txt b/Documentation/powerpc/kvm_440.txt
new file mode 100644
index 000000000000..c02a003fa03a
--- /dev/null
+++ b/Documentation/powerpc/kvm_440.txt
@@ -0,0 +1,41 @@
+Hollis Blanchard <hollisb@us.ibm.com>
+15 Apr 2008
+
+Various notes on the implementation of KVM for PowerPC 440:
+
+To enforce isolation, host userspace, guest kernel, and guest userspace all
+run at user privilege level. Only the host kernel runs in supervisor mode.
+Executing privileged instructions in the guest traps into KVM (in the host
+kernel), where we decode and emulate them. Through this technique, unmodified
+440 Linux kernels can be run (slowly) as guests. Future performance work will
+focus on reducing the overhead and frequency of these traps.
+
+The usual code flow is started from userspace invoking an "run" ioctl, which
+causes KVM to switch into guest context. We use IVPR to hijack the host
+interrupt vectors while running the guest, which allows us to direct all
+interrupts to kvmppc_handle_interrupt(). At this point, we could either
+- handle the interrupt completely (e.g. emulate "mtspr SPRG0"), or
+- let the host interrupt handler run (e.g. when the decrementer fires), or
+- return to host userspace (e.g. when the guest performs device MMIO)
+
+Address spaces: We take advantage of the fact that Linux doesn't use the AS=1
+address space (in host or guest), which gives us virtual address space to use
+for guest mappings. While the guest is running, the host kernel remains mapped
+in AS=0, but the guest can only use AS=1 mappings.
+
+TLB entries: The TLB entries covering the host linear mapping remain
+present while running the guest. This reduces the overhead of lightweight
+exits, which are handled by KVM running in the host kernel. We keep three
+copies of the TLB:
+ - guest TLB: contents of the TLB as the guest sees it
+ - shadow TLB: the TLB that is actually in hardware while guest is running
+ - host TLB: to restore TLB state when context switching guest -> host
+When a TLB miss occurs because a mapping was not present in the shadow TLB,
+but was present in the guest TLB, KVM handles the fault without invoking the
+guest. Large guest pages are backed by multiple 4KB shadow pages through this
+mechanism.
+
+IO: MMIO and DCR accesses are emulated by userspace. We use virtio for network
+and block IO, so those drivers must be enabled in the guest. It's possible
+that some qemu device emulation (e.g. e1000 or rtl8139) may also work with
+little effort.
diff --git a/Documentation/s390/kvm.txt b/Documentation/s390/kvm.txt
new file mode 100644
index 000000000000..6f5ceb0f09fc
--- /dev/null
+++ b/Documentation/s390/kvm.txt
@@ -0,0 +1,125 @@
+*** BIG FAT WARNING ***
+The kvm module is currently in EXPERIMENTAL state for s390. This means that
+the interface to the module is not yet considered to remain stable. Thus, be
+prepared that we keep breaking your userspace application and guest
+compatibility over and over again until we feel happy with the result. Make sure
+your guest kernel, your host kernel, and your userspace launcher are in a
+consistent state.
+
+This Documentation describes the unique ioctl calls to /dev/kvm, the resulting
+kvm-vm file descriptors, and the kvm-vcpu file descriptors that differ from x86.
+
+1. ioctl calls to /dev/kvm
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_GET_API_VERSION
+KVM_CREATE_VM           (*) see note
+KVM_CHECK_EXTENSION
+KVM_GET_VCPU_MMAP_SIZE
+
+Notes:
+* KVM_CREATE_VM may fail on s390, if the calling process has multiple
+threads and has not called KVM_S390_ENABLE_SIE before.
+
+In addition, on s390 the following architecture specific ioctls are supported:
+ioctl:          KVM_S390_ENABLE_SIE
+args:           none
+see also:       include/linux/kvm.h
+This call causes the kernel to switch on PGSTE in the user page table. This
+operation is needed in order to run a virtual machine, and it requires the
+calling process to be single-threaded. Note that the first call to KVM_CREATE_VM
+will implicitly try to switch on PGSTE if the user process has not called
+KVM_S390_ENABLE_SIE before. User processes that want to launch multiple threads
+before creating a virtual machine have to call KVM_S390_ENABLE_SIE, or will
+observe an error calling KVM_CREATE_VM. Switching on PGSTE is a one-time
+operation, is not reversible, and will persist over the entire lifetime of
+the calling process. It does not have any user-visible effect other than a small
+performance penalty.
+
+2. ioctl calls to the kvm-vm file descriptor
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_CREATE_VCPU
+KVM_SET_USER_MEMORY_REGION      (*) see note
+KVM_GET_DIRTY_LOG               (**) see note
+
+Notes:
+*  kvm does only allow exactly one memory slot on s390, which has to start
+   at guest absolute address zero and at a user address that is aligned on any
+   page boundary. This hardware "limitation" allows us to have a few unique
+   optimizations. The memory slot doesn't have to be filled
+   with memory actually, it may contain sparse holes. That said, with different
+   user memory layout this does still allow a large flexibility when
+   doing the guest memory setup.
+** KVM_GET_DIRTY_LOG doesn't work properly yet. The user will receive an empty
+log. This ioctl call is only needed for guest migration, and we intend to
+implement this one in the future.
+
+In addition, on s390 the following architecture specific ioctls for the kvm-vm
+file descriptor are supported:
+ioctl:          KVM_S390_INTERRUPT
+args:           struct kvm_s390_interrupt *
+see also:       include/linux/kvm.h
+This ioctl is used to submit a floating interrupt for a virtual machine.
+Floating interrupts may be delivered to any virtual cpu in the configuration.
+Only some interrupt types defined in include/linux/kvm.h make sense when
+submitted as floating interrupts. The following interrupts are not considered
+to be useful as floating interrupts, and a call to inject them will result in
+-EINVAL error code: program interrupts and interprocessor signals. Valid
+floating interrupts are:
+KVM_S390_INT_VIRTIO
+KVM_S390_INT_SERVICE
+
+3. ioctl calls to the kvm-vcpu file descriptor
+KVM does support the following ioctls on s390 that are common with other
+architectures and do behave the same:
+KVM_RUN
+KVM_GET_REGS
+KVM_SET_REGS
+KVM_GET_SREGS
+KVM_SET_SREGS
+KVM_GET_FPU
+KVM_SET_FPU
+
+In addition, on s390 the following architecture specific ioctls for the
+kvm-vcpu file descriptor are supported:
+ioctl:          KVM_S390_INTERRUPT
+args:           struct kvm_s390_interrupt *
+see also:       include/linux/kvm.h
+This ioctl is used to submit an interrupt for a specific virtual cpu.
+Only some interrupt types defined in include/linux/kvm.h make sense when
+submitted for a specific cpu. The following interrupts are not considered
+to be useful, and a call to inject them will result in -EINVAL error code:
+service processor calls and virtio interrupts. Valid interrupt types are:
+KVM_S390_PROGRAM_INT
+KVM_S390_SIGP_STOP
+KVM_S390_RESTART
+KVM_S390_SIGP_SET_PREFIX
+KVM_S390_INT_EMERGENCY
+
+ioctl:          KVM_S390_STORE_STATUS
+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:
+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
+its prefix page just like the dump tool that comes with zipl. This is useful
+to create a system dump for use with lkcdutils or crash.
+
+ioctl:          KVM_S390_SET_INITIAL_PSW
+args:           struct kvm_s390_psw *
+see also:       include/linux/kvm.h
+This ioctl can be used to set the processor status word (psw) of a stopped cpu
+prior to running it with KVM_RUN. Note that this call is not required to modify
+the psw during sie intercepts that fall back to userspace because struct kvm_run
+does contain the psw, and this value is evaluated during reentry of KVM_RUN
+after the intercept exit was recognized.
+
+ioctl:          KVM_S390_INITIAL_RESET
+args:           none
+see also:       include/linux/kvm.h
+This ioctl can be used to perform an initial cpu reset as defined by the
+principles of operation. The target cpu has to be in stopped state.
diff --git a/Documentation/smart-config.txt b/Documentation/smart-config.txt
deleted file mode 100644
index 8467447b5a87..000000000000
--- a/Documentation/smart-config.txt
+++ /dev/null
@@ -1,98 +0,0 @@
-Smart CONFIG_* Dependencies
-1 August 1999
-
-Michael Chastain   <mec@shout.net>
-Werner Almesberger <almesber@lrc.di.epfl.ch>
-Martin von Loewis  <martin@mira.isdn.cs.tu-berlin.de>
-
-Here is the problem:
-
-    Suppose that drivers/net/foo.c has the following lines:
-
-        #include <linux/config.h>
-
-        ...
-
-        #ifdef CONFIG_FOO_AUTOFROB
-            /* Code for auto-frobbing */
-        #else
-            /* Manual frobbing only */
-        #endif
-
-        ...
-
-        #ifdef CONFIG_FOO_MODEL_TWO
-            /* Code for model two */
-        #endif
-
-    Now suppose the user (the person building kernels) reconfigures the
-    kernel to change some unrelated setting.  This will regenerate the
-    file include/linux/autoconf.h, which will cause include/linux/config.h
-    to be out of date, which will cause drivers/net/foo.c to be recompiled.
-
-    Most kernel sources, perhaps 80% of them, have at least one CONFIG_*
-    dependency somewhere.  So changing _any_ CONFIG_* setting requires
-    almost _all_ of the kernel to be recompiled.
-
-Here is the solution:
-
-    We've made the dependency generator, mkdep.c, smarter.  Instead of
-    generating this dependency:
-
-        drivers/net/foo.c: include/linux/config.h
-
-    It now generates these dependencies:
-
-        drivers/net/foo.c: \
-            include/config/foo/autofrob.h \
-            include/config/foo/model/two.h
-
-    So drivers/net/foo.c depends only on the CONFIG_* lines that
-    it actually uses.
-
-    A new program, split-include.c, runs at the beginning of
-    compilation (make bzImage or make zImage).  split-include reads
-    include/linux/autoconf.h and updates the include/config/ tree,
-    writing one file per option.  It updates only the files for options
-    that have changed.
-
-Flag Dependencies
-
-    Martin Von Loewis contributed another feature to this patch:
-    'flag dependencies'.  The idea is that a .o file depends on
-    the compilation flags used to build it.  The file foo.o has
-    its flags stored in .flags.foo.o.
-
-    Suppose the user changes the foo driver from resident to modular.
-    'make' will notice that the current foo.o was not compiled with
-    -DMODULE and will recompile foo.c.
-
-    All .o files made from C source have flag dependencies.  So do .o
-    files made with ld, and .a files made with ar.  However, .o files
-    made from assembly source do not have flag dependencies (nobody
-    needs this yet, but it would be good to fix).
-
-Per-source-file Flags
-
-    Flag dependencies also work with per-source-file flags.
-    You can specify compilation flags for individual source files
-    like this:
-
-        CFLAGS_foo.o = -DSPECIAL_FOO_DEFINE
-
-    This helps clean up drivers/net/Makefile, drivers/scsi/Makefile,
-    and several other Makefiles.
-
-Credit
-
-    Werner Almesberger had the original idea and wrote the first
-    version of this patch.
-    
-    Michael Chastain picked it up and continued development.  He is
-    now the principal author and maintainer.  Please report any bugs
-    to him.
-
-    Martin von Loewis wrote flag dependencies, with some modifications
-    by Michael Chastain.
-
-    Thanks to all of the beta testers.
diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index e985cf5e0410..0bbee38acd26 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -284,6 +284,13 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
            control correctly. If you have problems regarding this, try
            another ALSA compliant mixer (alsamixer works).
 
+  Module snd-aw2
+  --------------
+
+    Module for Audiowerk2 sound card
+
+    This module supports multiple cards.
+
   Module snd-azt2320
   ------------------
 
@@ -788,6 +795,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           lg-lw         LG LW20/LW25 laptop
           tcl           TCL S700
           clevo         Clevo laptops (m520G, m665n)
+          medion        Medion Rim 2150
           test          for testing/debugging purpose, almost all controls can be
                         adjusted.  Appearing only when compiled with
                         $CONFIG_SND_DEBUG=y
@@ -818,19 +826,25 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           hippo_1       Hippo (Benq) with jack detection
           sony-assamd   Sony ASSAMD
           ultra         Samsung Q1 Ultra Vista model
+          lenovo-3000   Lenovo 3000 y410
           basic         fixed pin assignment w/o SPDIF
           auto          auto-config reading BIOS (default)
 
-        ALC268
+        ALC267/268
+          quanta-il1    Quanta IL1 mini-notebook
           3stack        3-stack model
           toshiba       Toshiba A205
           acer          Acer laptops
           dell          Dell OEM laptops (Vostro 1200)
+          zepto         Zepto laptops
           test          for testing/debugging purpose, almost all controls can
                         adjusted.  Appearing only when compiled with
                         $CONFIG_SND_DEBUG=y
           auto          auto-config reading BIOS (default)
 
+        ALC269
+          basic         Basic preset
+
         ALC662
           3stack-dig    3-stack (2-channel) with SPDIF
           3stack-6ch     3-stack (6-channel)
@@ -871,10 +885,11 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           lenovo-nb0763 Lenovo NB0763
           lenovo-ms7195-dig Lenovo MS7195
           haier-w66     Haier W66
-          6stack-hp     HP machines with 6stack (Nettle boards)
           3stack-hp     HP machines with 3stack (Lucknow, Samba boards)
           6stack-dell   Dell machines with 6stack (Inspiron 530)
           mitac         Mitac 8252D
+          clevo-m720    Clevo M720 laptop series
+          fujitsu-pi2515 Fujitsu AMILO Pi2515
           auto          auto-config reading BIOS (default)
 
         ALC861/660
@@ -911,6 +926,12 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           3stack        3-stack mode (default)
           6stack        6-stack mode
 
+        AD1884A / AD1883 / AD1984A / AD1984B
+          desktop       3-stack desktop (default)
+          laptop        laptop with HP jack sensing
+          mobile        mobile devices with HP jack sensing
+          thinkpad      Lenovo Thinkpad X300
+
         AD1884
           N/A
 
@@ -936,7 +957,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           laptop-automute 2-channel with EAPD and HP-automute (Lenovo N100)
           ultra         2-channel with EAPD (Samsung Ultra tablet PC)
 
-        AD1988
+        AD1988/AD1988B/AD1989A/AD1989B
           6stack        6-jack
           6stack-dig    ditto with SPDIF
           3stack        3-jack
@@ -979,6 +1000,7 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           dell-m26      Dell Inspiron 1501
           dell-m27      Dell Inspiron E1705/9400
           gateway       Gateway laptops with EAPD control
+          panasonic     Panasonic CF-74
 
         STAC9205/9254
           ref           Reference board
@@ -1017,6 +1039,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
           3stack        D965 3stack
           5stack        D965 5stack + SPDIF
           dell-3stack   Dell Dimension E520
+          dell-bios     Fixes with Dell BIOS setup
+
+        STAC92HD71B*
+          ref           Reference board
+          dell-m4-1     Dell desktops
+          dell-m4-2     Dell desktops
+
+        STAC92HD73*
+          ref           Reference board
+          dell-m6       Dell desktops
 
         STAC9872
           vaio          Setup for VAIO FE550G/SZ110
@@ -1590,6 +1622,16 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
 
     Power management is _not_ supported.
 
+  Module snd-pcsp
+  -----------------
+
+    Module for internal PC-Speaker.
+
+    nforce_wa   - enable NForce chipset workaround. Expect bad sound.
+
+    This module supports system beeps, some kind of PCM playback and
+    even a few mixer controls.
+
   Module snd-pcxhr
   ----------------
 
diff --git a/Documentation/spi/spidev b/Documentation/spi/spidev
index 5c8e1b988a08..ed2da5e5b28a 100644
--- a/Documentation/spi/spidev
+++ b/Documentation/spi/spidev
@@ -126,8 +126,8 @@ NOTES:
 FULL DUPLEX CHARACTER DEVICE API
 ================================
 
-See the sample program below for one example showing the use of the full
-duplex programming interface.  (Although it doesn't perform a full duplex
+See the spidev_fdx.c sample program for one example showing the use of the
+full duplex programming interface.  (Although it doesn't perform a full duplex
 transfer.)  The model is the same as that used in the kernel spi_sync()
 request; the individual transfers offer the same capabilities as are
 available to kernel drivers (except that it's not asynchronous).
@@ -141,167 +141,3 @@ and bitrate for each transfer segment.)
 
 To make a full duplex request, provide both rx_buf and tx_buf for the
 same transfer.  It's even OK if those are the same buffer.
-
-
-SAMPLE PROGRAM
-==============
-
---------------------------------        CUT HERE
-#include <stdio.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <fcntl.h>
-#include <string.h>
-
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/types.h>
-#include <linux/spi/spidev.h>
-
-
-static int verbose;
-
-static void do_read(int fd, int len)
-{
-        unsigned char   buf[32], *bp;
-        int             status;
-
-        /* read at least 2 bytes, no more than 32 */
-        if (len < 2)
-                len = 2;
-        else if (len > sizeof(buf))
-                len = sizeof(buf);
-        memset(buf, 0, sizeof buf);
-
-        status = read(fd, buf, len);
-        if (status < 0) {
-                perror("read");
-                return;
-        }
-        if (status != len) {
-                fprintf(stderr, "short read\n");
-                return;
-        }
-
-        printf("read(%2d, %2d): %02x %02x,", len, status,
-                buf[0], buf[1]);
-        status -= 2;
-        bp = buf + 2;
-        while (status-- > 0)
-                printf(" %02x", *bp++);
-        printf("\n");
-}
-
-static void do_msg(int fd, int len)
-{
-        struct spi_ioc_transfer xfer[2];
-        unsigned char           buf[32], *bp;
-        int                     status;
-
-        memset(xfer, 0, sizeof xfer);
-        memset(buf, 0, sizeof buf);
-
-        if (len > sizeof buf)
-                len = sizeof buf;
-
-        buf[0] = 0xaa;
-        xfer[0].tx_buf = (__u64) buf;
-        xfer[0].len = 1;
-
-        xfer[1].rx_buf = (__u64) buf;
-        xfer[1].len = len;
-
-        status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
-        if (status < 0) {
-                perror("SPI_IOC_MESSAGE");
-                return;
-        }
-
-        printf("response(%2d, %2d): ", len, status);
-        for (bp = buf; len; len--)
-                printf(" %02x", *bp++);
-        printf("\n");
-}
-
-static void dumpstat(const char *name, int fd)
-{
-        __u8    mode, lsb, bits;
-        __u32   speed;
-
-        if (ioctl(fd, SPI_IOC_RD_MODE, &mode) < 0) {
-                perror("SPI rd_mode");
-                return;
-        }
-        if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
-                perror("SPI rd_lsb_fist");
-                return;
-        }
-        if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
-                perror("SPI bits_per_word");
-                return;
-        }
-        if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
-                perror("SPI max_speed_hz");
-                return;
-        }
-
-        printf("%s: spi mode %d, %d bits %sper word, %d Hz max\n",
-                name, mode, bits, lsb ? "(lsb first) " : "", speed);
-}
-
-int main(int argc, char **argv)
-{
-        int             c;
-        int             readcount = 0;
-        int             msglen = 0;
-        int             fd;
-        const char      *name;
-
-        while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
-                switch (c) {
-                case 'm':
-                        msglen = atoi(optarg);
-                        if (msglen < 0)
-                                goto usage;
-                        continue;
-                case 'r':
-                        readcount = atoi(optarg);
-                        if (readcount < 0)
-                                goto usage;
-                        continue;
-                case 'v':
-                        verbose++;
-                        continue;
-                case 'h':
-                case '?':
-usage:
-                        fprintf(stderr,
-                                "usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
-                                argv[0]);
-                        return 1;
-                }
-        }
-
-        if ((optind + 1) != argc)
-                goto usage;
-        name = argv[optind];
-
-        fd = open(name, O_RDWR);
-        if (fd < 0) {
-                perror("open");
-                return 1;
-        }
-
-        dumpstat(name, fd);
-
-        if (msglen)
-                do_msg(fd, msglen);
-
-        if (readcount)
-                do_read(fd, readcount);
-
-        close(fd);
-        return 0;
-}
diff --git a/Documentation/spi/spidev_fdx.c b/Documentation/spi/spidev_fdx.c
new file mode 100644
index 000000000000..fc354f760384
--- /dev/null
+++ b/Documentation/spi/spidev_fdx.c
@@ -0,0 +1,158 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <string.h>
+
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <linux/types.h>
+#include <linux/spi/spidev.h>
+
+
+static int verbose;
+
+static void do_read(int fd, int len)
+{
+        unsigned char   buf[32], *bp;
+        int             status;
+
+        /* read at least 2 bytes, no more than 32 */
+        if (len < 2)
+                len = 2;
+        else if (len > sizeof(buf))
+                len = sizeof(buf);
+        memset(buf, 0, sizeof buf);
+
+        status = read(fd, buf, len);
+        if (status < 0) {
+                perror("read");
+                return;
+        }
+        if (status != len) {
+                fprintf(stderr, "short read\n");
+                return;
+        }
+
+        printf("read(%2d, %2d): %02x %02x,", len, status,
+                buf[0], buf[1]);
+        status -= 2;
+        bp = buf + 2;
+        while (status-- > 0)
+                printf(" %02x", *bp++);
+        printf("\n");
+}
+
+static void do_msg(int fd, int len)
+{
+        struct spi_ioc_transfer xfer[2];
+        unsigned char           buf[32], *bp;
+        int                     status;
+
+        memset(xfer, 0, sizeof xfer);
+        memset(buf, 0, sizeof buf);
+
+        if (len > sizeof buf)
+                len = sizeof buf;
+
+        buf[0] = 0xaa;
+        xfer[0].tx_buf = (__u64) buf;
+        xfer[0].len = 1;
+
+        xfer[1].rx_buf = (__u64) buf;
+        xfer[1].len = len;
+
+        status = ioctl(fd, SPI_IOC_MESSAGE(2), xfer);
+        if (status < 0) {
+                perror("SPI_IOC_MESSAGE");
+                return;
+        }
+
+        printf("response(%2d, %2d): ", len, status);
+        for (bp = buf; len; len--)
+                printf(" %02x", *bp++);
+        printf("\n");
+}
+
+static void dumpstat(const char *name, int fd)
+{
+        __u8    mode, lsb, bits;
+        __u32   speed;
+
+        if (ioctl(fd, SPI_IOC_RD_MODE, &mode) < 0) {
+                perror("SPI rd_mode");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_LSB_FIRST, &lsb) < 0) {
+                perror("SPI rd_lsb_fist");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_BITS_PER_WORD, &bits) < 0) {
+                perror("SPI bits_per_word");
+                return;
+        }
+        if (ioctl(fd, SPI_IOC_RD_MAX_SPEED_HZ, &speed) < 0) {
+                perror("SPI max_speed_hz");
+                return;
+        }
+
+        printf("%s: spi mode %d, %d bits %sper word, %d Hz max\n",
+                name, mode, bits, lsb ? "(lsb first) " : "", speed);
+}
+
+int main(int argc, char **argv)
+{
+        int             c;
+        int             readcount = 0;
+        int             msglen = 0;
+        int             fd;
+        const char      *name;
+
+        while ((c = getopt(argc, argv, "hm:r:v")) != EOF) {
+                switch (c) {
+                case 'm':
+                        msglen = atoi(optarg);
+                        if (msglen < 0)
+                                goto usage;
+                        continue;
+                case 'r':
+                        readcount = atoi(optarg);
+                        if (readcount < 0)
+                                goto usage;
+                        continue;
+                case 'v':
+                        verbose++;
+                        continue;
+                case 'h':
+                case '?':
+usage:
+                        fprintf(stderr,
+                                "usage: %s [-h] [-m N] [-r N] /dev/spidevB.D\n",
+                                argv[0]);
+                        return 1;
+                }
+        }
+
+        if ((optind + 1) != argc)
+                goto usage;
+        name = argv[optind];
+
+        fd = open(name, O_RDWR);
+        if (fd < 0) {
+                perror("open");
+                return 1;
+        }
+
+        dumpstat(name, fd);
+
+        if (msglen)
+                do_msg(fd, msglen);
+
+        if (readcount)
+                do_read(fd, readcount);
+
+        close(fd);
+        return 0;
+}
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 10c8f6922ef4..5ce0952aa065 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -85,6 +85,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 'k'     - Secure Access Key (SAK) Kills all programs on the current virtual
           console. NOTE: See important comments below in SAK section.
 
+'l'     - Shows a stack backtrace for all active CPUs.
+
 'm'     - Will dump current memory info to your console.
 
 'n'     - Used to make RT tasks nice-able
diff --git a/Documentation/usb/anchors.txt b/Documentation/usb/anchors.txt
new file mode 100644
index 000000000000..7304bcf5a306
--- /dev/null
+++ b/Documentation/usb/anchors.txt
@@ -0,0 +1,50 @@
+What is anchor?
+===============
+
+A USB driver needs to support some callbacks requiring
+a driver to cease all IO to an interface. To do so, a
+driver has to keep track of the URBs it has submitted
+to know they've all completed or to call usb_kill_urb
+for them. The anchor is a data structure takes care of
+keeping track of URBs and provides methods to deal with
+multiple URBs.
+
+Allocation and Initialisation
+=============================
+
+There's no API to allocate an anchor. It is simply declared
+as struct usb_anchor. init_usb_anchor() must be called to
+initialise the data structure.
+
+Deallocation
+============
+
+Once it has no more URBs associated with it, the anchor can be
+freed with normal memory management operations.
+
+Association and disassociation of URBs with anchors
+===================================================
+
+An association of URBs to an anchor is made by an explicit
+call to usb_anchor_urb(). The association is maintained until
+an URB is finished by (successfull) completion. Thus disassociation
+is automatic. A function is provided to forcibly finish (kill)
+all URBs associated with an anchor.
+Furthermore, disassociation can be made with usb_unanchor_urb()
+
+Operations on multitudes of URBs
+================================
+
+usb_kill_anchored_urbs()
+------------------------
+
+This function kills all URBs associated with an anchor. The URBs
+are called in the reverse temporal order they were submitted.
+This way no data can be reordered.
+
+usb_wait_anchor_empty_timeout()
+-------------------------------
+
+This function waits for all URBs associated with an anchor to finish
+or a timeout, whichever comes first. Its return value will tell you
+whether the timeout was reached.
diff --git a/Documentation/usb/callbacks.txt b/Documentation/usb/callbacks.txt
new file mode 100644
index 000000000000..7c812411945b
--- /dev/null
+++ b/Documentation/usb/callbacks.txt
@@ -0,0 +1,132 @@
+What callbacks will usbcore do?
+===============================
+
+Usbcore will call into a driver through callbacks defined in the driver
+structure and through the completion handler of URBs a driver submits.
+Only the former are in the scope of this document. These two kinds of
+callbacks are completely independent of each other. Information on the
+completion callback can be found in Documentation/usb/URB.txt.
+
+The callbacks defined in the driver structure are:
+
+1. Hotplugging callbacks:
+
+ * @probe: Called to see if the driver is willing to manage a particular
+ *      interface on a device.
+ * @disconnect: Called when the interface is no longer accessible, usually
+ *      because its device has been (or is being) disconnected or the
+ *      driver module is being unloaded.
+
+2. Odd backdoor through usbfs:
+
+ * @ioctl: Used for drivers that want to talk to userspace through
+ *      the "usbfs" filesystem.  This lets devices provide ways to
+ *      expose information to user space regardless of where they
+ *      do (or don't) show up otherwise in the filesystem.
+
+3. Power management (PM) callbacks:
+
+ * @suspend: Called when the device is going to be suspended.
+ * @resume: Called when the device is being resumed.
+ * @reset_resume: Called when the suspended device has been reset instead
+ *      of being resumed.
+
+4. Device level operations:
+
+ * @pre_reset: Called when the device is about to be reset.
+ * @post_reset: Called after the device has been reset
+
+The ioctl interface (2) should be used only if you have a very good
+reason. Sysfs is preferred these days. The PM callbacks are covered
+separately in Documentation/usb/power-management.txt.
+
+Calling conventions
+===================
+
+All callbacks are mutually exclusive. There's no need for locking
+against other USB callbacks. All callbacks are called from a task
+context. You may sleep. However, it is important that all sleeps have a
+small fixed upper limit in time. In particular you must not call out to
+user space and await results.
+
+Hotplugging callbacks
+=====================
+
+These callbacks are intended to associate and disassociate a driver with
+an interface. A driver's bond to an interface is exclusive.
+
+The probe() callback
+--------------------
+
+int (*probe) (struct usb_interface *intf,
+                const struct usb_device_id *id);
+
+Accept or decline an interface. If you accept the device return 0,
+otherwise -ENODEV or -ENXIO. Other error codes should be used only if a
+genuine error occurred during initialisation which prevented a driver
+from accepting a device that would else have been accepted.
+You are strongly encouraged to use usbcore'sfacility,
+usb_set_intfdata(), to associate a data structure with an interface, so
+that you know which internal state and identity you associate with a
+particular interface. The device will not be suspended and you may do IO
+to the interface you are called for and endpoint 0 of the device. Device
+initialisation that doesn't take too long is a good idea here.
+
+The disconnect() callback
+-------------------------
+
+void (*disconnect) (struct usb_interface *intf);
+
+This callback is a signal to break any connection with an interface.
+You are not allowed any IO to a device after returning from this
+callback. You also may not do any other operation that may interfere
+with another driver bound the interface, eg. a power management
+operation.
+If you are called due to a physical disconnection, all your URBs will be
+killed by usbcore. Note that in this case disconnect will be called some
+time after the physical disconnection. Thus your driver must be prepared
+to deal with failing IO even prior to the callback.
+
+Device level callbacks
+======================
+
+pre_reset
+---------
+
+int (*pre_reset)(struct usb_interface *intf);
+
+Another driver or user space is triggering a reset on the device which
+contains the interface passed as an argument. Cease IO and save any
+device state you need to restore.
+
+If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if you
+are in atomic context.
+
+post_reset
+----------
+
+int (*post_reset)(struct usb_interface *intf);
+
+The reset has completed.  Restore any saved device state and begin
+using the device again.
+
+If you need to allocate memory here, use GFP_NOIO or GFP_ATOMIC, if you
+are in atomic context.
+
+Call sequences
+==============
+
+No callbacks other than probe will be invoked for an interface
+that isn't bound to your driver.
+
+Probe will never be called for an interface bound to a driver.
+Hence following a successful probe, disconnect will be called
+before there is another probe for the same interface.
+
+Once your driver is bound to an interface, disconnect can be
+called at any time except in between pre_reset and post_reset.
+pre_reset is always followed by post_reset, even if the reset
+failed or the device has been unplugged.
+
+suspend is always followed by one of: resume, reset_resume, or
+disconnect.
diff --git a/Documentation/usb/persist.txt b/Documentation/usb/persist.txt
index df54d645cbb5..d56cb1a11550 100644
--- a/Documentation/usb/persist.txt
+++ b/Documentation/usb/persist.txt
@@ -2,7 +2,7 @@
 
                    Alan Stern <stern@rowland.harvard.edu>
 
-                 September 2, 2006 (Updated May 29, 2007)
+                September 2, 2006 (Updated February 25, 2008)
 
 
         What is the problem?
@@ -65,9 +65,10 @@ much better.)
 
         What is the solution?
 
-Setting CONFIG_USB_PERSIST will cause the kernel to work around these
-issues.  It enables a mode in which the core USB device data
-structures are allowed to persist across a power-session disruption.
+The kernel includes a feature called USB-persist.  It tries to work
+around these issues by allowing the core USB device data structures to
+persist across a power-session disruption.
+
 It works like this.  If the kernel sees that a USB host controller is
 not in the expected state during resume (i.e., if the controller was
 reset or otherwise had lost power) then it applies a persistence check
@@ -80,28 +81,30 @@ re-enumeration shows that the device now attached to that port has the
 same descriptors as before, including the Vendor and Product IDs, then
 the kernel continues to use the same device structure.  In effect, the
 kernel treats the device as though it had merely been reset instead of
-unplugged.
+unplugged.  The same thing happens if the host controller is in the
+expected state but a USB device was unplugged and then replugged.
 
 If no device is now attached to the port, or if the descriptors are
 different from what the kernel remembers, then the treatment is what
 you would expect.  The kernel destroys the old device structure and
 behaves as though the old device had been unplugged and a new device
-plugged in, just as it would without the CONFIG_USB_PERSIST option.
+plugged in.
 
 The end result is that the USB device remains available and usable.
 Filesystem mounts and memory mappings are unaffected, and the world is
 now a good and happy place.
 
-Note that even when CONFIG_USB_PERSIST is set, the "persist" feature
-will be applied only to those devices for which it is enabled.  You
-can enable the feature by doing (as root):
+Note that the "USB-persist" feature will be applied only to those
+devices for which it is enabled.  You can enable the feature by doing
+(as root):
 
         echo 1 >/sys/bus/usb/devices/.../power/persist
 
 where the "..." should be filled in the with the device's ID.  Disable
 the feature by writing 0 instead of 1.  For hubs the feature is
-automatically and permanently enabled, so you only have to worry about
-setting it for devices where it really matters.
+automatically and permanently enabled and the power/persist file
+doesn't even exist, so you only have to worry about setting it for
+devices where it really matters.
 
 
         Is this the best solution?
@@ -112,19 +115,19 @@ centralized Logical Volume Manager.  Such a solution would allow you
 to plug in a USB flash device, create a persistent volume associated
 with it, unplug the flash device, plug it back in later, and still
 have the same persistent volume associated with the device.  As such
-it would be more far-reaching than CONFIG_USB_PERSIST.
+it would be more far-reaching than USB-persist.
 
 On the other hand, writing a persistent volume manager would be a big
 job and using it would require significant input from the user.  This
 solution is much quicker and easier -- and it exists now, a giant
 point in its favor!
 
-Furthermore, the USB_PERSIST option applies to _all_ USB devices, not
+Furthermore, the USB-persist feature applies to _all_ USB devices, not
 just mass-storage devices.  It might turn out to be equally useful for
 other device types, such as network interfaces.
 
 
-        WARNING: Using CONFIG_USB_PERSIST can be dangerous!!
+        WARNING: USB-persist can be dangerous!!
 
 When recovering an interrupted power session the kernel does its best
 to make sure the USB device hasn't been changed; that is, the same
@@ -133,10 +136,10 @@ aren't guaranteed to be 100% accurate.
 
 If you replace one USB device with another of the same type (same
 manufacturer, same IDs, and so on) there's an excellent chance the
-kernel won't detect the change.  Serial numbers and other strings are
-not compared.  In many cases it wouldn't help if they were, because
-manufacturers frequently omit serial numbers entirely in their
-devices.
+kernel won't detect the change.  The serial number string and other
+descriptors are compared with the kernel's stored values, but this
+might not help since manufacturers frequently omit serial numbers
+entirely in their devices.
 
 Furthermore it's quite possible to leave a USB device exactly the same
 while changing its media.  If you replace the flash memory card in a
@@ -152,5 +155,5 @@ but yourself.
 YOU HAVE BEEN WARNED!  USE AT YOUR OWN RISK!
 
 That having been said, most of the time there shouldn't be any trouble
-at all.  The "persist" feature can be extremely useful.  Make the most
-of it.
+at all.  The USB-persist feature can be extremely useful.  Make the
+most of it.
diff --git a/Documentation/usb/usb-serial.txt b/Documentation/usb/usb-serial.txt
index 8b077e43eee7..ff2c1ff57ba2 100644
--- a/Documentation/usb/usb-serial.txt
+++ b/Documentation/usb/usb-serial.txt
@@ -192,12 +192,9 @@ Keyspan USA-series Serial Adapters
 
 FTDI Single Port Serial Driver
 
-  This is a single port DB-25 serial adapter. More information about this
-  device and the Linux driver can be found at:
-        http://reality.sgi.com/bryder_wellington/ftdi_sio/
+  This is a single port DB-25 serial adapter.
 
-  For any questions or problems with this driver, please contact Bill Ryder
-  at bryder@sgi.com
+  For any questions or problems with this driver, please contact Bill Ryder.
 
 
 ZyXEL omni.net lcd plus ISDN TA
diff --git a/Documentation/video4linux/CARDLIST.au0828 b/Documentation/video4linux/CARDLIST.au0828
new file mode 100644
index 000000000000..aaae360312e4
--- /dev/null
+++ b/Documentation/video4linux/CARDLIST.au0828
@@ -0,0 +1,4 @@
+  0 -> Unknown board                            (au0828)
+  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200]
+  2 -> Hauppauge HVR850                         (au0828)        [2040:7240]
+  3 -> DViCO FusionHDTV USB                     (au0828)        [0fe9:d620]
diff --git a/Documentation/video4linux/CARDLIST.bttv b/Documentation/video4linux/CARDLIST.bttv
index d97cf7cc6088..f32efb6fb12c 100644
--- a/Documentation/video4linux/CARDLIST.bttv
+++ b/Documentation/video4linux/CARDLIST.bttv
@@ -148,3 +148,5 @@
 147 -> VoodooTV 200 (USA)                                  [121a:3000]
 148 -> DViCO FusionHDTV 2                                  [dbc0:d200]
 149 -> Typhoon TV-Tuner PCI (50684)
+150 -> Geovision GV-600                                    [008a:763c]
+151 -> Kozumi KTV-01C
diff --git a/Documentation/video4linux/CARDLIST.cx23885 b/Documentation/video4linux/CARDLIST.cx23885
index 0924e6e142c4..929b90c8387f 100644
--- a/Documentation/video4linux/CARDLIST.cx23885
+++ b/Documentation/video4linux/CARDLIST.cx23885
@@ -5,3 +5,6 @@
   4 -> DViCO FusionHDTV5 Express                           [18ac:d500]
   5 -> Hauppauge WinTV-HVR1500Q                            [0070:7790,0070:7797]
   6 -> Hauppauge WinTV-HVR1500                             [0070:7710,0070:7717]
+  7 -> Hauppauge WinTV-HVR1200                             [0070:71d1]
+  8 -> Hauppauge WinTV-HVR1700                             [0070:8101]
+  9 -> Hauppauge WinTV-HVR1400                             [0070:8010]
diff --git a/Documentation/video4linux/CARDLIST.cx88 b/Documentation/video4linux/CARDLIST.cx88
index bc5593bd9704..543957346469 100644
--- a/Documentation/video4linux/CARDLIST.cx88
+++ b/Documentation/video4linux/CARDLIST.cx88
@@ -57,3 +57,12 @@
  56 -> Hauppauge WinTV-HVR1300 DVB-T/Hybrid MPEG Encoder   [0070:9600,0070:9601,0070:9602]
  57 -> ADS Tech Instant Video PCI                          [1421:0390]
  58 -> Pinnacle PCTV HD 800i                               [11bd:0051]
+ 59 -> DViCO FusionHDTV 5 PCI nano                         [18ac:d530]
+ 60 -> Pinnacle Hybrid PCTV                                [12ab:1788]
+ 61 -> Winfast TV2000 XP Global                            [107d:6f18]
+ 62 -> PowerColor Real Angel 330                           [14f1:ea3d]
+ 63 -> Geniatech X8000-MT DVBT                             [14f1:8852]
+ 64 -> DViCO FusionHDTV DVB-T PRO                          [18ac:db30]
+ 65 -> DViCO FusionHDTV 7 Gold                             [18ac:d610]
+ 66 -> Prolink Pixelview MPEG 8000GT                       [1554:4935]
+ 67 -> Kworld PlusTV HD PCI 120 (ATSC 120)                 [17de:08c1]
diff --git a/Documentation/video4linux/CARDLIST.saa7134 b/Documentation/video4linux/CARDLIST.saa7134
index 0424901ebc78..44d84dd15ad6 100644
--- a/Documentation/video4linux/CARDLIST.saa7134
+++ b/Documentation/video4linux/CARDLIST.saa7134
@@ -25,8 +25,8 @@
  24 -> KNC One TV-Station DVR                   [1894:a006]
  25 -> ASUS TV-FM 7133                          [1043:4843]
  26 -> Pinnacle PCTV Stereo (saa7134)           [11bd:002b]
- 27 -> Manli MuchTV M-TV002/Behold TV 403 FM
- 28 -> Manli MuchTV M-TV001/Behold TV 401
+ 27 -> Manli MuchTV M-TV002
+ 28 -> Manli MuchTV M-TV001
  29 -> Nagase Sangyo TransGear 3000TV           [1461:050c]
  30 -> Elitegroup ECS TVP3XP FM1216 Tuner Card(PAL-BG,FM)  [1019:4cb4]
  31 -> Elitegroup ECS TVP3XP FM1236 Tuner Card (NTSC,FM) [1019:4cb5]
@@ -131,3 +131,12 @@
 130 -> Beholder BeholdTV M6 / BeholdTV M6 Extra [5ace:6190,5ace:6193]
 131 -> Twinhan Hybrid DTV-DVB 3056 PCI          [1822:0022]
 132 -> Genius TVGO AM11MCE
+133 -> NXP Snake DVB-S reference design
+134 -> Medion/Creatix CTX953 Hybrid             [16be:0010]
+135 -> MSI TV@nywhere A/D v1.1                  [1462:8625]
+136 -> AVerMedia Cardbus TV/Radio (E506R)       [1461:f436]
+137 -> AVerMedia Hybrid TV/Radio (A16D)         [1461:f936]
+138 -> Avermedia M115                           [1461:a836]
+139 -> Compro VideoMate T750                    [185b:c900]
+140 -> Avermedia DVB-S Pro A700                 [1461:a7a1]
+141 -> Avermedia DVB-S Hybrid+FM A700           [1461:a7a2]
diff --git a/Documentation/video4linux/extract_xc3028.pl b/Documentation/video4linux/extract_xc3028.pl
index cced8ac5c543..2cb816047fc1 100644
--- a/Documentation/video4linux/extract_xc3028.pl
+++ b/Documentation/video4linux/extract_xc3028.pl
@@ -686,11 +686,11 @@ sub main_firmware($$$$)
         write_hunk(812664, 192);
 
         #
-        # Firmware 58, type: SCODE FW  HAS IF (0x60000000), IF = 4.50 MHz id: NTSC/M Jp (0000000000002000), size: 192
+        # Firmware 58, type: SCODE FW  MTS LCD NOGD MONO IF HAS IF (0x6002b004), IF = 4.50 MHz id: NTSC PAL/M PAL/N (000000000000b700), size: 192
         #
 
-        write_le32(0x60000000);                 # Type
-        write_le64(0x00000000, 0x00002000);     # ID
+        write_le32(0x6002b004);                 # Type
+        write_le64(0x00000000, 0x0000b700);     # ID
         write_le16(4500);                       # IF
         write_le32(192);                        # Size
         write_hunk(807672, 192);
@@ -706,10 +706,10 @@ sub main_firmware($$$$)
         write_hunk(807864, 192);
 
         #
-        # Firmware 60, type: SCODE FW  DTV78 ZARLINK456 HAS IF (0x62000100), IF = 4.76 MHz id: (0000000000000000), size: 192
+        # Firmware 60, type: SCODE FW  DTV6 QAM DTV7 DTV78 DTV8 ZARLINK456 HAS IF (0x620003e0), IF = 4.76 MHz id: (0000000000000000), size: 192
         #
 
-        write_le32(0x62000100);                 # Type
+        write_le32(0x620003e0);                 # Type
         write_le64(0x00000000, 0x00000000);     # ID
         write_le16(4760);                       # IF
         write_le32(192);                        # Size
@@ -726,30 +726,30 @@ sub main_firmware($$$$)
         write_hunk(811512, 192);
 
         #
-        # Firmware 62, type: SCODE FW  DTV7 ZARLINK456 HAS IF (0x62000080), IF = 5.26 MHz id: (0000000000000000), size: 192
+        # Firmware 62, type: SCODE FW  HAS IF (0x60000000), IF = 5.26 MHz id: (0000000000000000), size: 192
         #
 
-        write_le32(0x62000080);                 # Type
+        write_le32(0x60000000);                 # Type
         write_le64(0x00000000, 0x00000000);     # ID
         write_le16(5260);                       # IF
         write_le32(192);                        # Size
         write_hunk(810552, 192);
 
         #
-        # Firmware 63, type: SCODE FW  MONO HAS IF (0x60008000), IF = 5.32 MHz id: PAL/BG NICAM/B (0000000800000007), size: 192
+        # Firmware 63, type: SCODE FW  MONO HAS IF (0x60008000), IF = 5.32 MHz id: PAL/BG A2 NICAM (0000000f00000007), size: 192
         #
 
         write_le32(0x60008000);                 # Type
-        write_le64(0x00000008, 0x00000007);     # ID
+        write_le64(0x0000000f, 0x00000007);     # ID
         write_le16(5320);                       # IF
         write_le32(192);                        # Size
         write_hunk(810744, 192);
 
         #
-        # Firmware 64, type: SCODE FW  DTV8 CHINA HAS IF (0x64000200), IF = 5.40 MHz id: (0000000000000000), size: 192
+        # Firmware 64, type: SCODE FW  DTV7 DTV78 DTV8 DIBCOM52 CHINA HAS IF (0x65000380), IF = 5.40 MHz id: (0000000000000000), size: 192
         #
 
-        write_le32(0x64000200);                 # Type
+        write_le32(0x65000380);                 # Type
         write_le64(0x00000000, 0x00000000);     # ID
         write_le16(5400);                       # IF
         write_le32(192);                        # Size
@@ -766,50 +766,50 @@ sub main_firmware($$$$)
         write_hunk(809592, 192);
 
         #
-        # Firmware 66, type: SCODE FW  HAS IF (0x60000000), IF = 5.64 MHz id: PAL/BG A2/B (0000000200000007), size: 192
+        # Firmware 66, type: SCODE FW  HAS IF (0x60000000), IF = 5.64 MHz id: PAL/BG A2 (0000000300000007), size: 192
         #
 
         write_le32(0x60000000);                 # Type
-        write_le64(0x00000002, 0x00000007);     # ID
+        write_le64(0x00000003, 0x00000007);     # ID
         write_le16(5640);                       # IF
         write_le32(192);                        # Size
         write_hunk(808440, 192);
 
         #
-        # Firmware 67, type: SCODE FW  HAS IF (0x60000000), IF = 5.74 MHz id: PAL/BG NICAM/B (0000000800000007), size: 192
+        # Firmware 67, type: SCODE FW  HAS IF (0x60000000), IF = 5.74 MHz id: PAL/BG NICAM (0000000c00000007), size: 192
         #
 
         write_le32(0x60000000);                 # Type
-        write_le64(0x00000008, 0x00000007);     # ID
+        write_le64(0x0000000c, 0x00000007);     # ID
         write_le16(5740);                       # IF
         write_le32(192);                        # Size
         write_hunk(808632, 192);
 
         #
-        # Firmware 68, type: SCODE FW  DTV7 DIBCOM52 HAS IF (0x61000080), IF = 5.90 MHz id: (0000000000000000), size: 192
+        # Firmware 68, type: SCODE FW  HAS IF (0x60000000), IF = 5.90 MHz id: (0000000000000000), size: 192
         #
 
-        write_le32(0x61000080);                 # Type
+        write_le32(0x60000000);                 # Type
         write_le64(0x00000000, 0x00000000);     # ID
         write_le16(5900);                       # IF
         write_le32(192);                        # Size
         write_hunk(810360, 192);
 
         #
-        # Firmware 69, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.00 MHz id: PAL/I (0000000000000010), size: 192
+        # Firmware 69, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.00 MHz id: PAL/DK PAL/I SECAM/K3 SECAM/L SECAM/Lc NICAM (0000000c04c000f0), size: 192
         #
 
         write_le32(0x60008000);                 # Type
-        write_le64(0x00000000, 0x00000010);     # ID
+        write_le64(0x0000000c, 0x04c000f0);     # ID
         write_le16(6000);                       # IF
         write_le32(192);                        # Size
         write_hunk(808824, 192);
 
         #
-        # Firmware 70, type: SCODE FW  DTV6 QAM F6MHZ HAS IF (0x68000060), IF = 6.20 MHz id: (0000000000000000), size: 192
+        # Firmware 70, type: SCODE FW  DTV6 QAM ATSC LG60 F6MHZ HAS IF (0x68050060), IF = 6.20 MHz id: (0000000000000000), size: 192
         #
 
-        write_le32(0x68000060);                 # Type
+        write_le32(0x68050060);                 # Type
         write_le64(0x00000000, 0x00000000);     # ID
         write_le16(6200);                       # IF
         write_le32(192);                        # Size
@@ -846,11 +846,11 @@ sub main_firmware($$$$)
         write_hunk(809208, 192);
 
         #
-        # Firmware 74, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.50 MHz id: SECAM/K3 (0000000004000000), size: 192
+        # Firmware 74, type: SCODE FW  MONO HAS IF (0x60008000), IF = 6.50 MHz id: PAL/DK SECAM/K3 SECAM/L NICAM (0000000c044000e0), size: 192
         #
 
         write_le32(0x60008000);                 # Type
-        write_le64(0x00000000, 0x04000000);     # ID
+        write_le64(0x0000000c, 0x044000e0);     # ID
         write_le16(6500);                       # IF
         write_le32(192);                        # Size
         write_hunk(811128, 192);
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index dd4986497996..bad16d3f6a47 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -135,77 +135,58 @@ most general to most specific:
 
 Components of Memory Policies
 
-    A Linux memory policy is a tuple consisting of a "mode" and an optional set
-    of nodes.  The mode determine the behavior of the policy, while the
-    optional set of nodes can be viewed as the arguments to the behavior.
+    A Linux memory policy consists of a "mode", optional mode flags, and an
+    optional set of nodes.  The mode determines the behavior of the policy,
+    the optional mode flags determine the behavior of the mode, and the
+    optional set of nodes can be viewed as the arguments to the policy
+    behavior.
 
    Internally, memory policies are implemented by a reference counted
    structure, struct mempolicy.  Details of this structure will be discussed
    in context, below, as required to explain the behavior.
 
-        Note:  in some functions AND in the struct mempolicy itself, the mode
-        is called "policy".  However, to avoid confusion with the policy tuple,
-        this document will continue to use the term "mode".
-
    Linux memory policy supports the following 4 behavioral modes:
 
-        Default Mode--MPOL_DEFAULT:  The behavior specified by this mode is
-        context or scope dependent.
-
-            As mentioned in the Policy Scope section above, during normal
-            system operation, the System Default Policy is hard coded to
-            contain the Default mode.
-
-            In this context, default mode means "local" allocation--that is
-            attempt to allocate the page from the node associated with the cpu
-            where the fault occurs.  If the "local" node has no memory, or the
-            node's memory can be exhausted [no free pages available], local
-            allocation will "fallback to"--attempt to allocate pages from--
-            "nearby" nodes, in order of increasing "distance".
+        Default Mode--MPOL_DEFAULT:  This mode is only used in the memory
+        policy APIs.  Internally, MPOL_DEFAULT is converted to the NULL
+        memory policy in all policy scopes.  Any existing non-default policy
+        will simply be removed when MPOL_DEFAULT is specified.  As a result,
+        MPOL_DEFAULT means "fall back to the next most specific policy scope."
 
-                Implementation detail -- subject to change:  "Fallback" uses
-                a per node list of sibling nodes--called zonelists--built at
-                boot time, or when nodes or memory are added or removed from
-                the system [memory hotplug].  These per node zonelist are
-                constructed with nodes in order of increasing distance based
-                on information provided by the platform firmware.
+            For example, a NULL or default task policy will fall back to the
+            system default policy.  A NULL or default vma policy will fall
+            back to the task policy.
 
-            When a task/process policy or a shared policy contains the Default
-            mode, this also means "local allocation", as described above.
+            When specified in one of the memory policy APIs, the Default mode
+            does not use the optional set of nodes.
 
-            In the context of a VMA, Default mode means "fall back to task
-            policy"--which may or may not specify Default mode.  Thus, Default
-            mode can not be counted on to mean local allocation when used
-            on a non-shared region of the address space.  However, see
-            MPOL_PREFERRED below.
-
-            The Default mode does not use the optional set of nodes.
+            It is an error for the set of nodes specified for this policy to
+            be non-empty.
 
         MPOL_BIND:  This mode specifies that memory must come from the
-        set of nodes specified by the policy.
-
-            The memory policy APIs do not specify an order in which the nodes
-            will be searched.  However, unlike "local allocation", the Bind
-            policy does not consider the distance between the nodes.  Rather,
-            allocations will fallback to the nodes specified by the policy in
-            order of numeric node id.  Like everything in Linux, this is subject
-            to change.
+        set of nodes specified by the policy.  Memory will be allocated from
+        the node in the set with sufficient free memory that is closest to
+        the node where the allocation takes place.
 
         MPOL_PREFERRED:  This mode specifies that the allocation should be
         attempted from the single node specified in the policy.  If that
-        allocation fails, the kernel will search other nodes, exactly as
-        it would for a local allocation that started at the preferred node
-        in increasing distance from the preferred node.  "Local" allocation
-        policy can be viewed as a Preferred policy that starts at the node
+        allocation fails, the kernel will search other nodes, in order of
+        increasing distance from the preferred node based on information
+        provided by the platform firmware.
         containing the cpu where the allocation takes place.
 
             Internally, the Preferred policy uses a single node--the
-            preferred_node member of struct mempolicy.  A "distinguished
-            value of this preferred_node, currently '-1', is interpreted
-            as "the node containing the cpu where the allocation takes
-            place"--local allocation.  This is the way to specify
-            local allocation for a specific range of addresses--i.e. for
-            VMA policies.
+            preferred_node member of struct mempolicy.  When the internal
+            mode flag MPOL_F_LOCAL is set, the preferred_node is ignored and
+            the policy is interpreted as local allocation.  "Local" allocation
+            policy can be viewed as a Preferred policy that starts at the node
+            containing the cpu where the allocation takes place.
+
+            It is possible for the user to specify that local allocation is
+            always preferred by passing an empty nodemask with this mode.
+            If an empty nodemask is passed, the policy cannot use the
+            MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags described
+            below.
 
         MPOL_INTERLEAVED:  This mode specifies that page allocations be
         interleaved, on a page granularity, across the nodes specified in
@@ -231,6 +212,154 @@ Components of Memory Policies
             the temporary interleaved system default policy works in this
             mode.
 
+   Linux memory policy supports the following optional mode flags:
+
+        MPOL_F_STATIC_NODES:  This flag specifies that the nodemask passed by
+        the user should not be remapped if the task or VMA's set of allowed
+        nodes changes after the memory policy has been defined.
+
+            Without this flag, anytime a mempolicy is rebound because of a
+            change in the set of allowed nodes, the node (Preferred) or
+            nodemask (Bind, Interleave) is remapped to the new set of
+            allowed nodes.  This may result in nodes being used that were
+            previously undesired.
+
+            With this flag, if the user-specified nodes overlap with the
+            nodes allowed by the task's cpuset, then the memory policy is
+            applied to their intersection.  If the two sets of nodes do not
+            overlap, the Default policy is used.
+
+            For example, consider a task that is attached to a cpuset with
+            mems 1-3 that sets an Interleave policy over the same set.  If
+            the cpuset's mems change to 3-5, the Interleave will now occur
+            over nodes 3, 4, and 5.  With this flag, however, since only node
+            3 is allowed from the user's nodemask, the "interleave" only
+            occurs over that node.  If no nodes from the user's nodemask are
+            now allowed, the Default behavior is used.
+
+            MPOL_F_STATIC_NODES cannot be combined with the
+            MPOL_F_RELATIVE_NODES flag.  It also cannot be used for
+            MPOL_PREFERRED policies that were created with an empty nodemask
+            (local allocation).
+
+        MPOL_F_RELATIVE_NODES:  This flag specifies that the nodemask passed
+        by the user will be mapped relative to the set of the task or VMA's
+        set of allowed nodes.  The kernel stores the user-passed nodemask,
+        and if the allowed nodes changes, then that original nodemask will
+        be remapped relative to the new set of allowed nodes.
+
+            Without this flag (and without MPOL_F_STATIC_NODES), anytime a
+            mempolicy is rebound because of a change in the set of allowed
+            nodes, the node (Preferred) or nodemask (Bind, Interleave) is
+            remapped to the new set of allowed nodes.  That remap may not
+            preserve the relative nature of the user's passed nodemask to its
+            set of allowed nodes upon successive rebinds: a nodemask of
+            1,3,5 may be remapped to 7-9 and then to 1-3 if the set of
+            allowed nodes is restored to its original state.
+
+            With this flag, the remap is done so that the node numbers from
+            the user's passed nodemask are relative to the set of allowed
+            nodes.  In other words, if nodes 0, 2, and 4 are set in the user's
+            nodemask, the policy will be effected over the first (and in the
+            Bind or Interleave case, the third and fifth) nodes in the set of
+            allowed nodes.  The nodemask passed by the user represents nodes
+            relative to task or VMA's set of allowed nodes.
+
+            If the user's nodemask includes nodes that are outside the range
+            of the new set of allowed nodes (for example, node 5 is set in
+            the user's nodemask when the set of allowed nodes is only 0-3),
+            then the remap wraps around to the beginning of the nodemask and,
+            if not already set, sets the node in the mempolicy nodemask.
+
+            For example, consider a task that is attached to a cpuset with
+            mems 2-5 that sets an Interleave policy over the same set with
+            MPOL_F_RELATIVE_NODES.  If the cpuset's mems change to 3-7, the
+            interleave now occurs over nodes 3,5-6.  If the cpuset's mems
+            then change to 0,2-3,5, then the interleave occurs over nodes
+            0,3,5.
+
+            Thanks to the consistent remapping, applications preparing
+            nodemasks to specify memory policies using this flag should
+            disregard their current, actual cpuset imposed memory placement
+            and prepare the nodemask as if they were always located on
+            memory nodes 0 to N-1, where N is the number of memory nodes the
+            policy is intended to manage.  Let the kernel then remap to the
+            set of memory nodes allowed by the task's cpuset, as that may
+            change over time.
+
+            MPOL_F_RELATIVE_NODES cannot be combined with the
+            MPOL_F_STATIC_NODES flag.  It also cannot be used for
+            MPOL_PREFERRED policies that were created with an empty nodemask
+            (local allocation).
+
+MEMORY POLICY REFERENCE COUNTING
+
+To resolve use/free races, struct mempolicy contains an atomic reference
+count field.  Internal interfaces, mpol_get()/mpol_put() increment and
+decrement this reference count, respectively.  mpol_put() will only free
+the structure back to the mempolicy kmem cache when the reference count
+goes to zero.
+
+When a new memory policy is allocated, it's reference count is initialized
+to '1', representing the reference held by the task that is installing the
+new policy.  When a pointer to a memory policy structure is stored in another
+structure, another reference is added, as the task's reference will be dropped
+on completion of the policy installation.
+
+During run-time "usage" of the policy, we attempt to minimize atomic operations
+on the reference count, as this can lead to cache lines bouncing between cpus
+and NUMA nodes.  "Usage" here means one of the following:
+
+1) querying of the policy, either by the task itself [using the get_mempolicy()
+   API discussed below] or by another task using the /proc/<pid>/numa_maps
+   interface.
+
+2) examination of the policy to determine the policy mode and associated node
+   or node lists, if any, for page allocation.  This is considered a "hot
+   path".  Note that for MPOL_BIND, the "usage" extends across the entire
+   allocation process, which may sleep during page reclaimation, because the
+   BIND policy nodemask is used, by reference, to filter ineligible nodes.
+
+We can avoid taking an extra reference during the usages listed above as
+follows:
+
+1) we never need to get/free the system default policy as this is never
+   changed nor freed, once the system is up and running.
+
+2) for querying the policy, we do not need to take an extra reference on the
+   target task's task policy nor vma policies because we always acquire the
+   task's mm's mmap_sem for read during the query.  The set_mempolicy() and
+   mbind() APIs [see below] always acquire the mmap_sem for write when
+   installing or replacing task or vma policies.  Thus, there is no possibility
+   of a task or thread freeing a policy while another task or thread is
+   querying it.
+
+3) Page allocation usage of task or vma policy occurs in the fault path where
+   we hold them mmap_sem for read.  Again, because replacing the task or vma
+   policy requires that the mmap_sem be held for write, the policy can't be
+   freed out from under us while we're using it for page allocation.
+
+4) Shared policies require special consideration.  One task can replace a
+   shared memory policy while another task, with a distinct mmap_sem, is
+   querying or allocating a page based on the policy.  To resolve this
+   potential race, the shared policy infrastructure adds an extra reference
+   to the shared policy during lookup while holding a spin lock on the shared
+   policy management structure.  This requires that we drop this extra
+   reference when we're finished "using" the policy.  We must drop the
+   extra reference on shared policies in the same query/allocation paths
+   used for non-shared policies.  For this reason, shared policies are marked
+   as such, and the extra reference is dropped "conditionally"--i.e., only
+   for shared policies.
+
+   Because of this extra reference counting, and because we must lookup
+   shared policies in a tree structure under spinlock, shared policies are
+   more expensive to use in the page allocation path.  This is expecially
+   true for shared policies on shared memory regions shared by tasks running
+   on different NUMA nodes.  This extra overhead can be avoided by always
+   falling back to task or system default policy for shared memory regions,
+   or by prefaulting the entire shared memory region into memory and locking
+   it down.  However, this might not be appropriate for all applications.
+
 MEMORY POLICY APIs
 
 Linux supports 3 system calls for controlling memory policy.  These APIS
@@ -251,7 +380,9 @@ Set [Task] Memory Policy:
         Set's the calling task's "task/process memory policy" to mode
         specified by the 'mode' argument and the set of nodes defined
         by 'nmask'.  'nmask' points to a bit mask of node ids containing
-        at least 'maxnode' ids.
+        at least 'maxnode' ids.  Optional mode flags may be passed by
+        combining the 'mode' argument with the flag (for example:
+        MPOL_INTERLEAVE | MPOL_F_STATIC_NODES).
 
         See the set_mempolicy(2) man page for more details
 
@@ -303,29 +434,19 @@ MEMORY POLICIES AND CPUSETS
 Memory policies work within cpusets as described above.  For memory policies
 that require a node or set of nodes, the nodes are restricted to the set of
 nodes whose memories are allowed by the cpuset constraints.  If the nodemask
-specified for the policy contains nodes that are not allowed by the cpuset, or
-the intersection of the set of nodes specified for the policy and the set of
-nodes with memory is the empty set, the policy is considered invalid
-and cannot be installed.
-
-The interaction of memory policies and cpusets can be problematic for a
-couple of reasons:
-
-1) the memory policy APIs take physical node id's as arguments.  As mentioned
-   above, it is illegal to specify nodes that are not allowed in the cpuset.
-   The application must query the allowed nodes using the get_mempolicy()
-   API with the MPOL_F_MEMS_ALLOWED flag to determine the allowed nodes and
-   restrict itself to those nodes.  However, the resources available to a
-   cpuset can be changed by the system administrator, or a workload manager
-   application, at any time.  So, a task may still get errors attempting to
-   specify policy nodes, and must query the allowed memories again.
-
-2) when tasks in two cpusets share access to a memory region, such as shared
-   memory segments created by shmget() of mmap() with the MAP_ANONYMOUS and
-   MAP_SHARED flags, and any of the tasks install shared policy on the region,
-   only nodes whose memories are allowed in both cpusets may be used in the
-   policies.  Obtaining this information requires "stepping outside" the
-   memory policy APIs to use the cpuset information and requires that one
-   know in what cpusets other task might be attaching to the shared region.
-   Furthermore, if the cpusets' allowed memory sets are disjoint, "local"
-   allocation is the only valid policy.
+specified for the policy contains nodes that are not allowed by the cpuset and
+MPOL_F_RELATIVE_NODES is not used, the intersection of the set of nodes
+specified for the policy and the set of nodes with memory is used.  If the
+result is the empty set, the policy is considered invalid and cannot be
+installed.  If MPOL_F_RELATIVE_NODES is used, the policy's nodes are mapped
+onto and folded into the task's set of allowed nodes as previously described.
+
+The interaction of memory policies and cpusets can be problematic when tasks
+in two cpusets share access to a memory region, such as shared memory segments
+created by shmget() of mmap() with the MAP_ANONYMOUS and MAP_SHARED flags, and
+any of the tasks install shared policy on the region, only nodes whose
+memories are allowed in both cpusets may be used in the policies.  Obtaining
+this information requires "stepping outside" the memory policy APIs to use the
+cpuset information and requires that one know in what cpusets other task might
+be attaching to the shared region.  Furthermore, if the cpusets' allowed
+memory sets are disjoint, "local" allocation is the only valid policy.
diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c
index 22d7e3e4d60c..d3ce295bffac 100644
--- a/Documentation/vm/slabinfo.c
+++ b/Documentation/vm/slabinfo.c
@@ -31,7 +31,7 @@ struct slabinfo {
         int hwcache_align, object_size, objs_per_slab;
         int sanity_checks, slab_size, store_user, trace;
         int order, poison, reclaim_account, red_zone;
-        unsigned long partial, objects, slabs;
+        unsigned long partial, objects, slabs, objects_partial, objects_total;
         unsigned long alloc_fastpath, alloc_slowpath;
         unsigned long free_fastpath, free_slowpath;
         unsigned long free_frozen, free_add_partial, free_remove_partial;
@@ -540,7 +540,8 @@ void slabcache(struct slabinfo *s)
                 return;
 
         store_size(size_str, slab_size(s));
-        snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs, s->partial, s->cpu_slabs);
+        snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
+                                                s->partial, s->cpu_slabs);
 
         if (!line++)
                 first_line();
@@ -776,7 +777,6 @@ void totals(void)
                 unsigned long used;
                 unsigned long long wasted;
                 unsigned long long objwaste;
-                long long objects_in_partial_slabs;
                 unsigned long percentage_partial_slabs;
                 unsigned long percentage_partial_objs;
 
@@ -790,18 +790,11 @@ void totals(void)
                 wasted = size - used;
                 objwaste = s->slab_size - s->object_size;
 
-                objects_in_partial_slabs = s->objects -
-                        (s->slabs - s->partial - s ->cpu_slabs) *
-                        s->objs_per_slab;
-
-                if (objects_in_partial_slabs < 0)
-                        objects_in_partial_slabs = 0;
-
                 percentage_partial_slabs = s->partial * 100 / s->slabs;
                 if (percentage_partial_slabs > 100)
                         percentage_partial_slabs = 100;
 
-                percentage_partial_objs = objects_in_partial_slabs * 100
+                percentage_partial_objs = s->objects_partial * 100
                                                         / s->objects;
 
                 if (percentage_partial_objs > 100)
@@ -823,8 +816,8 @@ void totals(void)
                         min_objects = s->objects;
                 if (used < min_used)
                         min_used = used;
-                if (objects_in_partial_slabs < min_partobj)
-                        min_partobj = objects_in_partial_slabs;
+                if (s->objects_partial < min_partobj)
+                        min_partobj = s->objects_partial;
                 if (percentage_partial_slabs < min_ppart)
                         min_ppart = percentage_partial_slabs;
                 if (percentage_partial_objs < min_ppartobj)
@@ -848,8 +841,8 @@ void totals(void)
                         max_objects = s->objects;
                 if (used > max_used)
                         max_used = used;
-                if (objects_in_partial_slabs > max_partobj)
-                        max_partobj = objects_in_partial_slabs;
+                if (s->objects_partial > max_partobj)
+                        max_partobj = s->objects_partial;
                 if (percentage_partial_slabs > max_ppart)
                         max_ppart = percentage_partial_slabs;
                 if (percentage_partial_objs > max_ppartobj)
@@ -864,7 +857,7 @@ void totals(void)
 
                 total_objects += s->objects;
                 total_used += used;
-                total_partobj += objects_in_partial_slabs;
+                total_partobj += s->objects_partial;
                 total_ppart += percentage_partial_slabs;
                 total_ppartobj += percentage_partial_objs;
 
@@ -1160,6 +1153,8 @@ void read_slab_dir(void)
                         slab->hwcache_align = get_obj("hwcache_align");
                         slab->object_size = get_obj("object_size");
                         slab->objects = get_obj("objects");
+                        slab->objects_partial = get_obj("objects_partial");
+                        slab->objects_total = get_obj("objects_total");
                         slab->objs_per_slab = get_obj("objs_per_slab");
                         slab->order = get_obj("order");
                         slab->partial = get_obj("partial");