45 files changed, 2330 insertions, 723 deletions

diff --git a/Documentation/ABI/testing/sysfs-ata b/Documentation/ABI/testing/sysfs-ata
new file mode 100644
index 00000000000..0a932155cbb
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-ata
@@ -0,0 +1,99 @@
+What:           /sys/class/ata_...
+Date:           August 2008
+Contact:        Gwendal Grignou<gwendal@google.com>
+Description:
+
+Provide a place in sysfs for storing the ATA topology of the system.  This allows
+retrieving various information about ATA objects.
+
+Files under /sys/class/ata_port
+-------------------------------
+
+        For each port, a directory ataX is created where X is the ata_port_id of
+        the port. The device parent is the ata host device.
+
+idle_irq (read)
+
+        Number of IRQ received by the port while idle [some ata HBA only].
+
+nr_pmp_links (read)
+
+        If a SATA Port Multiplier (PM) is connected, number of link behind it.
+
+Files under /sys/class/ata_link
+-------------------------------
+
+        Behind each port, there is a ata_link. If there is a SATA PM in the
+        topology, 15 ata_link objects are created.
+
+        If a link is behind a port, the directory name is linkX, where X is
+        ata_port_id of the port.
+        If a link is behind a PM, its name is linkX.Y where X is ata_port_id
+        of the parent port and Y the PM port.
+
+hw_sata_spd_limit
+
+        Maximum speed supported by the connected SATA device.
+
+sata_spd_limit
+
+        Maximum speed imposed by libata.
+
+sata_spd
+
+        Current speed of the link [1.5, 3Gps,...].
+
+Files under /sys/class/ata_device
+---------------------------------
+
+        Behind each link, up to two ata device are created.
+        The name of the directory is devX[.Y].Z where:
+        - X is ata_port_id of the port where the device is connected,
+        - Y the port of the PM if any, and
+        - Z the device id: for PATA, there is usually 2 devices [0,1],
+        only 1 for SATA.
+
+class
+        Device class. Can be "ata" for disk, "atapi" for packet device,
+        "pmp" for PM, or "none" if no device was found behind the link.
+
+dma_mode
+
+        Transfer modes supported by the device when in DMA mode.
+        Mostly used by PATA device.
+
+pio_mode
+
+        Transfer modes supported by the device when in PIO mode.
+        Mostly used by PATA device.
+
+xfer_mode
+
+        Current transfer mode.
+
+id
+
+        Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17.
+        Only valid if the device is not a PM.
+
+gscr
+
+        Cached result of the dump of PM GSCR register.
+        Valid registers are:
+        0:      SATA_PMP_GSCR_PROD_ID,
+        1:      SATA_PMP_GSCR_REV,
+        2:      SATA_PMP_GSCR_PORT_INFO,
+        32:     SATA_PMP_GSCR_ERROR,
+        33:     SATA_PMP_GSCR_ERROR_EN,
+        64:     SATA_PMP_GSCR_FEAT,
+        96:     SATA_PMP_GSCR_FEAT_EN,
+        130:    SATA_PMP_GSCR_SII_GPIO
+        Only valid if the device is a PM.
+
+spdn_cnt
+
+        Number of time libata decided to lower the speed of link due to errors.
+
+ering
+
+        Formatted output of the error ring of the device.
diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 6123c523bfd..7628cd1bc36 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -77,3 +77,91 @@ Description:
                 devices this attribute is set to "enabled" by bus type code or
                 device drivers and in that cases it should be safe to leave the
                 default value.
+
+What:           /sys/devices/.../power/wakeup_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_count attribute contains the number
+                of signaled wakeup events associated with the device.  This
+                attribute is read-only.  If the device is not enabled to wake up
+                the system from sleep states, this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_active_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_active_count attribute contains the
+                number of times the processing of wakeup events associated with
+                the device was completed (at the kernel level).  This attribute
+                is read-only.  If the device is not enabled to wake up the
+                system from sleep states, this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_hit_count
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_hit_count attribute contains the
+                number of times the processing of a wakeup event associated with
+                the device might prevent the system from entering a sleep state.
+                This attribute is read-only.  If the device is not enabled to
+                wake up the system from sleep states, this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_active
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_active attribute contains either 1,
+                or 0, depending on whether or not a wakeup event associated with
+                the device is being processed (1).  This attribute is read-only.
+                If the device is not enabled to wake up the system from sleep
+                states, this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_total_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_total_time_ms attribute contains
+                the total time of processing wakeup events associated with the
+                device, in milliseconds.  This attribute is read-only.  If the
+                device is not enabled to wake up the system from sleep states,
+                this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_max_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_max_time_ms attribute contains
+                the maximum time of processing a single wakeup event associated
+                with the device, in milliseconds.  This attribute is read-only.
+                If the device is not enabled to wake up the system from sleep
+                states, this attribute is empty.
+
+What:           /sys/devices/.../power/wakeup_last_time_ms
+Date:           September 2010
+Contact:        Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+                The /sys/devices/.../wakeup_last_time_ms attribute contains
+                the value of the monotonic clock corresponding to the time of
+                signaling the last wakeup event associated with the device, in
+                milliseconds.  This attribute is read-only.  If the device is
+                not enabled to wake up the system from sleep states, this
+                attribute is empty.
+
+What:           /sys/devices/.../power/autosuspend_delay_ms
+Date:           September 2010
+Contact:        Alan Stern <stern@rowland.harvard.edu>
+Description:
+                The /sys/devices/.../power/autosuspend_delay_ms attribute
+                contains the autosuspend delay value (in milliseconds).  Some
+                drivers do not want their device to suspend as soon as it
+                becomes idle at run time; they want the device to remain
+                inactive for a certain minimum period of time first.  That
+                period is called the autosuspend delay.  Negative values will
+                prevent the device from being suspended at run time (similar
+                to writing "on" to the power/control attribute).  Values >=
+                1000 will cause the autosuspend timer expiration to be rounded
+                up to the nearest second.
+
+                Not all drivers support this attribute.  If it isn't supported,
+                attempts to read or write it will yield I/O errors.
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 2875f1f74a0..194ca446ac2 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -99,9 +99,38 @@ Description:
 
                 dmesg -s 1000000 | grep 'hash matches'
 
+                If you do not get any matches (or they appear to be false
+                positives), it is possible that the last PM event point
+                referred to a device created by a loadable kernel module.  In
+                this case cat /sys/power/pm_trace_dev_match (see below) after
+                your system is started up and the kernel modules are loaded.
+
                 CAUTION: Using it will cause your machine's real-time (CMOS)
                 clock to be set to a random invalid time after a resume.
 
+What;           /sys/power/pm_trace_dev_match
+Date:           October 2010
+Contact:        James Hogan <james@albanarts.com>
+Description:
+                The /sys/power/pm_trace_dev_match file contains the name of the
+                device associated with the last PM event point saved in the RTC
+                across reboots when pm_trace has been used.  More precisely it
+                contains the list of current devices (including those
+                registered by loadable kernel modules since boot) which match
+                the device hash in the RTC at boot, with a newline after each
+                one.
+
+                The advantage of this file over the hash matches printed to the
+                kernel log (see /sys/power/pm_trace), is that it includes
+                devices created after boot by loadable kernel modules.
+
+                Due to the small hash size necessary to fit in the RTC, it is
+                possible that more than one device matches the hash, in which
+                case further investigation is required to determine which
+                device is causing the problem.  Note that genuine RTC clock
+                values (such as when pm_trace has not been used), can still
+                match a device and output it's name here.
+
 What:           /sys/power/pm_async
 Date:           January 2009
 Contact:        Rafael J. Wysocki <rjw@sisk.pl>
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
index ecd35e9d441..feca0758391 100644
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -46,7 +46,6 @@
 
      <sect1><title>Atomic and pointer manipulation</title>
 !Iarch/x86/include/asm/atomic.h
-!Iarch/x86/include/asm/unaligned.h
      </sect1>
 
      <sect1><title>Delaying, scheduling, and timer routines</title>
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 910c923a9b8..2861055afd7 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -136,6 +136,7 @@
 #ifdef CONFIG_COMPAT
                 .compat_ioctl = i915_compat_ioctl,
 #endif
+                .llseek = noop_llseek,
                 },
         .pci_driver = {
                 .name = DRIVER_NAME,
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index 1448b33fd22..fb10fd08c05 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -28,7 +28,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
    <holder>Thomas Gleixner</holder>
   </copyright>
   <copyright>
@@ -100,6 +100,10 @@
           <listitem><para>Edge type</para></listitem>
           <listitem><para>Simple type</para></listitem>
         </itemizedlist>
+        During the implementation we identified another type:
+        <itemizedlist>
+          <listitem><para>Fast EOI type</para></listitem>
+        </itemizedlist>
         In the SMP world of the __do_IRQ() super-handler another type
         was identified:
         <itemizedlist>
@@ -153,6 +157,7 @@
         is still available. This leads to a kind of duality for the time
         being. Over time the new model should be used in more and more
         architectures, as it enables smaller and cleaner IRQ subsystems.
+        It's deprecated for three years now and about to be removed.
         </para>
   </chapter>
   <chapter id="bugs">
@@ -217,6 +222,7 @@
           <itemizedlist>
           <listitem><para>handle_level_irq</para></listitem>
           <listitem><para>handle_edge_irq</para></listitem>
+          <listitem><para>handle_fasteoi_irq</para></listitem>
           <listitem><para>handle_simple_irq</para></listitem>
           <listitem><para>handle_percpu_irq</para></listitem>
           </itemizedlist>
@@ -233,33 +239,33 @@
                 are used by the default flow implementations.
                 The following helper functions are implemented (simplified excerpt):
                 <programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-        desc->chip->unmask(irq);
+        desc->chip->irq_unmask(data);
 }
 
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-        if (!delay_disable(irq))
-                desc->chip->mask(irq);
+        if (!delay_disable(data))
+                desc->chip->irq_mask(data);
 }
 
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-        chip->ack(irq);
+        chip->irq_ack(data);
 }
 
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-        if (chip->mask_ack) {
-                chip->mask_ack(irq);
+        if (chip->irq_mask_ack) {
+                chip->irq_mask_ack(data);
         } else {
-                chip->mask(irq);
-                chip->ack(irq);
+                chip->irq_mask(data);
+                chip->irq_ack(data);
         }
 }
 
-noop(irq)
+noop(struct irq_data *data))
 {
 }
 
@@ -278,12 +284,27 @@ noop(irq)
                 <para>
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
                 </programlisting>
                 </para>
-            </sect3>
+            </sect3>
+            <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+                <title>Default Fast EOI IRQ flow handler</title>
+                <para>
+                handle_fasteoi_irq provides a generic implementation
+                for interrupts, which only need an EOI at the end of
+                the handler
+                </para>
+                <para>
+                The following control flow is implemented (simplified excerpt):
+                <programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+                </programlisting>
+                </para>
+            </sect3>
             <sect3 id="Default_Edge_IRQ_flow_handler">
                 <title>Default Edge IRQ flow handler</title>
                 <para>
@@ -294,20 +315,19 @@ desc->chip->end();
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
 if (desc->status &amp; running) {
-        desc->chip->hold();
+        desc->chip->irq_mask();
         desc->status |= pending | masked;
         return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
         if (desc->status &amp; masked)
-                desc->chip->enable();
+                desc->chip->irq_unmask();
         desc->status &amp;= ~pending;
         handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
                 </programlisting>
                 </para>
             </sect3>
@@ -342,9 +362,9 @@ handle_IRQ_event(desc->action);
                 <para>
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
                 </programlisting>
                 </para>
             </sect3>
@@ -375,8 +395,7 @@ desc->chip->end();
         mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
         you want to use the delayed interrupt disable feature and your
         hardware is not capable of retriggering an interrupt.)
-        The delayed interrupt disable can be runtime enabled, per interrupt,
-        by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
+        The delayed interrupt disable is not configurable.
         </para>
         </sect2>
     </sect1>
@@ -387,13 +406,13 @@ desc->chip->end();
         contains all the direct chip relevant functions, which
         can be utilized by the irq flow implementations.
           <itemizedlist>
-          <listitem><para>ack()</para></listitem>
-          <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
-          <listitem><para>mask()</para></listitem>
-          <listitem><para>unmask()</para></listitem>
-          <listitem><para>retrigger() - Optional</para></listitem>
-          <listitem><para>set_type() - Optional</para></listitem>
-          <listitem><para>set_wake() - Optional</para></listitem>
+          <listitem><para>irq_ack()</para></listitem>
+          <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
+          <listitem><para>irq_mask()</para></listitem>
+          <listitem><para>irq_unmask()</para></listitem>
+          <listitem><para>irq_retrigger() - Optional</para></listitem>
+          <listitem><para>irq_set_type() - Optional</para></listitem>
+          <listitem><para>irq_set_wake() - Optional</para></listitem>
           </itemizedlist>
         These primitives are strictly intended to mean what they say: ack means
         ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@ desc->chip->end();
      <para>
      This chapter contains the autogenerated documentation of the internal functions.
      </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
   </chapter>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index a20c6f6fffc..6b4e07f28b6 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -57,7 +57,6 @@
      </para>
 
      <sect1><title>String Conversions</title>
-!Ilib/vsprintf.c
 !Elib/vsprintf.c
      </sect1>
      <sect1><title>String Manipulation</title>
@@ -258,7 +257,8 @@ X!Earch/x86/kernel/mca_32.c
 !Iblock/blk-sysfs.c
 !Eblock/blk-settings.c
 !Eblock/blk-exec.c
-!Eblock/blk-barrier.c
+!Eblock/blk-flush.c
+!Eblock/blk-lib.c
 !Eblock/blk-tag.c
 !Iblock/blk-tag.c
 !Eblock/blk-integrity.c
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index 0b1a3f97f28..f66f4df1869 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1645,7 +1645,9 @@ the amount of locking which needs to be done.
       all the readers who were traversing the list when we deleted the
       element are finished.  We use <function>call_rcu()</function> to
       register a callback which will actually destroy the object once
-      the readers are finished.
+      all pre-existing readers are finished.  Alternatively,
+      <function>synchronize_rcu()</function> may be used to block until
+      all pre-existing are finished.
     </para>
     <para>
       But how does Read Copy Update know when the readers are
@@ -1714,7 +1716,7 @@ the amount of locking which needs to be done.
 -        object_put(obj);
 +        list_del_rcu(&amp;obj-&gt;list);
          cache_num--;
-+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu, obj);
++        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu);
  }
 
  /* Must be holding cache_lock */
@@ -1725,14 +1727,6 @@ the amount of locking which needs to be done.
          if (++cache_num > MAX_CACHE_SIZE) {
                  struct object *i, *outcast = NULL;
                  list_for_each_entry(i, &amp;cache, list) {
-@@ -85,6 +94,7 @@
-         obj-&gt;popularity = 0;
-         atomic_set(&amp;obj-&gt;refcnt, 1); /* The cache holds a reference */
-         spin_lock_init(&amp;obj-&gt;lock);
-+        INIT_RCU_HEAD(&amp;obj-&gt;rcu);
-
-         spin_lock_irqsave(&amp;cache_lock, flags);
-         __cache_add(obj);
 @@ -104,12 +114,11 @@
  struct object *cache_find(int id)
  {
@@ -1961,6 +1955,12 @@ machines due to caching.
    </sect1>
   </chapter>
 
+  <chapter id="apiref">
+   <title>Mutex API reference</title>
+!Iinclude/linux/mutex.h
+!Ekernel/mutex.c
+  </chapter>
+
   <chapter id="references">
    <title>Further reading</title>
 
diff --git a/Documentation/DocBook/tracepoint.tmpl b/Documentation/DocBook/tracepoint.tmpl
index e8473eae2a2..b57a9ede322 100644
--- a/Documentation/DocBook/tracepoint.tmpl
+++ b/Documentation/DocBook/tracepoint.tmpl
@@ -104,4 +104,9 @@
    <title>Block IO</title>
 !Iinclude/trace/events/block.h
   </chapter>
+
+  <chapter id="workqueue">
+   <title>Workqueue</title>
+!Iinclude/trace/events/workqueue.h
+  </chapter>
 </book>
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 790d1a81237..0c134f8afc6 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -218,13 +218,22 @@ over a rather long period of time, but improvements are always welcome!
         include:
 
         a.      Keeping a count of the number of data-structure elements
-                used by the RCU-protected data structure, including those
-                waiting for a grace period to elapse.  Enforce a limit
-                on this number, stalling updates as needed to allow
-                previously deferred frees to complete.
-
-                Alternatively, limit only the number awaiting deferred
-                free rather than the total number of elements.
+                used by the RCU-protected data structure, including
+                those waiting for a grace period to elapse.  Enforce a
+                limit on this number, stalling updates as needed to allow
+                previously deferred frees to complete.  Alternatively,
+                limit only the number awaiting deferred free rather than
+                the total number of elements.
+
+                One way to stall the updates is to acquire the update-side
+                mutex.  (Don't try this with a spinlock -- other CPUs
+                spinning on the lock could prevent the grace period
+                from ever ending.)  Another way to stall the updates
+                is for the updates to use a wrapper function around
+                the memory allocator, so that this wrapper function
+                simulates OOM when there is too much memory awaiting an
+                RCU grace period.  There are of course many other
+                variations on this theme.
 
         b.      Limiting update rate.  For example, if updates occur only
                 once per hour, then no explicit rate limiting is required,
@@ -365,3 +374,26 @@ over a rather long period of time, but improvements are always welcome!
         and the compiler to freely reorder code into and out of RCU
         read-side critical sections.  It is the responsibility of the
         RCU update-side primitives to deal with this.
+
+17.     Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and
+        the __rcu sparse checks to validate your RCU code.  These
+        can help find problems as follows:
+
+        CONFIG_PROVE_RCU: check that accesses to RCU-protected data
+                structures are carried out under the proper RCU
+                read-side critical section, while holding the right
+                combination of locks, or whatever other conditions
+                are appropriate.
+
+        CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the
+                same object to call_rcu() (or friends) before an RCU
+                grace period has elapsed since the last time that you
+                passed that same object to call_rcu() (or friends).
+
+        __rcu sparse checks: tag the pointer to the RCU-protected data
+                structure with __rcu, and sparse will warn you if you
+                access that pointer without the services of one of the
+                variants of rcu_dereference().
+
+        These debugging aids can help you find problems that are
+        otherwise extremely difficult to spot.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 44c6dcc93d6..862c08ef1fd 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -80,6 +80,24 @@ o	A CPU looping with bottom halves disabled.  This condition can
 o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
         without invoking schedule().
 
+o       A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+        happen to preempt a low-priority task in the middle of an RCU
+        read-side critical section.   This is especially damaging if
+        that low-priority task is not permitted to run on any other CPU,
+        in which case the next RCU grace period can never complete, which
+        will eventually cause the system to run out of memory and hang.
+        While the system is in the process of running itself out of
+        memory, you might see stall-warning messages.
+
+o       A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+        is running at a higher priority than the RCU softirq threads.
+        This will prevent RCU callbacks from ever being invoked,
+        and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+        RCU grace periods from ever completing.  Either way, the
+        system will eventually run out of memory and hang.  In the
+        CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+        messages.
+
 o       A bug in the RCU implementation.
 
 o       A hardware failure.  This is quite unlikely, but has occurred
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index efd8cc95c06..a851118775d 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -125,6 +125,17 @@ o	"b" is the batch limit for this CPU.  If more than this number
         of RCU callbacks is ready to invoke, then the remainder will
         be deferred.
 
+o       "ci" is the number of RCU callbacks that have been invoked for
+        this CPU.  Note that ci+ql is the number of callbacks that have
+        been registered in absence of CPU-hotplug activity.
+
+o       "co" is the number of RCU callbacks that have been orphaned due to
+        this CPU going offline.
+
+o       "ca" is the number of RCU callbacks that have been adopted due to
+        other CPUs going offline.  Note that ci+co-ca+ql is the number of
+        RCU callbacks registered on this CPU.
+
 There is also an rcu/rcudata.csv file with the same information in
 comma-separated-variable spreadsheet format.
 
@@ -180,7 +191,7 @@ o	"s" is the "signaled" state that drives force_quiescent_state()'s
 
 o       "jfq" is the number of jiffies remaining for this grace period
         before force_quiescent_state() is invoked to help push things
-        along.  Note that CPUs in dyntick-idle mode thoughout the grace
+        along.  Note that CPUs in dyntick-idle mode throughout the grace
         period will not report on their own, but rather must be check by
         some other CPU via force_quiescent_state().
 
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 7f5fc3ba9c9..ecf7d04bca2 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -6,6 +6,8 @@ Interrupts
         - ARM Interrupt subsystem documentation
 IXP2000
         - Release Notes for Linux on Intel's IXP2000 Network Processor
+msm
+        - MSM specific documentation
 Netwinder
         - Netwinder specific documentation
 Porting
diff --git a/Documentation/arm/msm/gpiomux.txt b/Documentation/arm/msm/gpiomux.txt
new file mode 100644
index 00000000000..67a81620adf
--- /dev/null
+++ b/Documentation/arm/msm/gpiomux.txt
@@ -0,0 +1,176 @@
+This document provides an overview of the msm_gpiomux interface, which
+is used to provide gpio pin multiplexing and configuration on mach-msm
+targets.
+
+History
+=======
+
+The first-generation API for gpio configuration & multiplexing on msm
+is the function gpio_tlmm_config().  This function has a few notable
+shortcomings, which led to its deprecation and replacement by gpiomux:
+
+The 'disable' parameter:  Setting the second parameter to
+gpio_tlmm_config to GPIO_CFG_DISABLE tells the peripheral
+processor in charge of the subsystem to perform a look-up into a
+low-power table and apply the low-power/sleep setting for the pin.
+As the msm family evolved this became problematic. Not all pins
+have sleep settings, not all peripheral processors will accept requests
+to apply said sleep settings, and not all msm targets have their gpio
+subsystems managed by a peripheral processor. In order to get consistent
+behavior on all targets, drivers are forced to ignore this parameter,
+rendering it useless.
+
+The 'direction' flag: for all mux-settings other than raw-gpio (0),
+the output-enable bit of a gpio is hard-wired to a known
+input (usually VDD or ground).  For those settings, the direction flag
+is meaningless at best, and deceptive at worst.  In addition, using the
+direction flag to change output-enable (OE) directly can cause trouble in
+gpiolib, which has no visibility into gpio direction changes made
+in this way.  Direction control in gpio mode should be made through gpiolib.
+
+Key Features of gpiomux
+=======================
+
+- A consistent interface across all generations of msm.  Drivers can expect
+the same results on every target.
+- gpiomux plays nicely with gpiolib.  Functions that should belong to gpiolib
+are left to gpiolib and not duplicated here.  gpiomux is written with the
+intent that gpio_chips will call gpiomux reference-counting methods
+from their request() and free() hooks, providing full integration.
+- Tabular configuration.  Instead of having to call gpio_tlmm_config
+hundreds of times, gpio configuration is placed in a single table.
+- Per-gpio sleep.  Each gpio is individually reference counted, allowing only
+those lines which are in use to be put in high-power states.
+- 0 means 'do nothing': all flags are designed so that the default memset-zero
+equates to a sensible default of 'no configuration', preventing users
+from having to provide hundreds of 'no-op' configs for unused or
+unwanted lines.
+
+Usage
+=====
+
+To use gpiomux, provide configuration information for relevant gpio lines
+in the msm_gpiomux_configs table.  Since a 0 equates to "unconfigured",
+only those lines to be managed by gpiomux need to be specified.  Here
+is a completely fictional example:
+
+struct msm_gpiomux_config msm_gpiomux_configs[GPIOMUX_NGPIOS] = {
+        [12] = {
+                .active = GPIOMUX_VALID | GPIOMUX_DRV_8MA | GPIOMUX_FUNC_1,
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+        [34] = {
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+};
+
+To indicate that a gpio is in use, call msm_gpiomux_get() to increase
+its reference count.  To decrease the reference count, call msm_gpiomux_put().
+
+The effect of this configuration is as follows:
+
+When the system boots, gpios 12 and 34 will be initialized with their
+'suspended' configurations.  All other gpios, which were left unconfigured,
+will not be touched.
+
+When msm_gpiomux_get() is called on gpio 12 to raise its reference count
+above 0, its active configuration will be applied.  Since no other gpio
+line has a valid active configuration, msm_gpiomux_get() will have no
+effect on any other line.
+
+When msm_gpiomux_put() is called on gpio 12 or 34 to drop their reference
+count to 0, their suspended configurations will be applied.
+Since no other gpio line has a valid suspended configuration, no other
+gpio line will be effected by msm_gpiomux_put().  Since gpio 34 has no valid
+active configuration, this is effectively a no-op for gpio 34 as well,
+with one small caveat, see the section "About Output-Enable Settings".
+
+All of the GPIOMUX_VALID flags may seem like unnecessary overhead, but
+they address some important issues.  As unused entries (all those
+except 12 and 34) are zero-filled, gpiomux needs a way to distinguish
+the used fields from the unused.  In addition, the all-zero pattern
+is a valid configuration!  Therefore, gpiomux defines an additional bit
+which is used to indicate when a field is used.  This has the pleasant
+side-effect of allowing calls to msm_gpiomux_write to use '0' to indicate
+that a value should not be changed:
+
+  msm_gpiomux_write(0, GPIOMUX_VALID, 0);
+
+replaces the active configuration of gpio 0 with an all-zero configuration,
+but leaves the suspended configuration as it was.
+
+Static Configurations
+=====================
+
+To install a static configuration, which is applied at boot and does
+not change after that, install a configuration with a suspended component
+but no active component, as in the previous example:
+
+        [34] = {
+                .suspended = GPIOMUX_VALID | GPIOMUX_PULL_DOWN,
+        },
+
+The suspended setting is applied during boot, and the lack of any valid
+active setting prevents any other setting from being applied at runtime.
+If other subsystems attempting to access the line is a concern, one could
+*really* anchor the configuration down by calling msm_gpiomux_get on the
+line at initialization to move the line into active mode.  With the line
+held, it will never be re-suspended, and with no valid active configuration,
+no new configurations will be applied.
+
+But then, if having other subsystems grabbing for the line is truly a concern,
+it should be reserved with gpio_request instead, which carries an implicit
+msm_gpiomux_get.
+
+gpiomux and gpiolib
+===================
+
+It is expected that msm gpio_chips will call msm_gpiomux_get() and
+msm_gpiomux_put() from their request and free hooks, like this fictional
+example:
+
+static int request(struct gpio_chip *chip, unsigned offset)
+{
+        return msm_gpiomux_get(chip->base + offset);
+}
+
+static void free(struct gpio_chip *chip, unsigned offset)
+{
+        msm_gpiomux_put(chip->base + offset);
+}
+
+        ...somewhere in a gpio_chip declaration...
+        .request = request,
+        .free    = free,
+
+This provides important functionality:
+- It guarantees that a gpio line will have its 'active' config applied
+  when the line is requested, and will not be suspended while the line
+  remains requested; and
+- It guarantees that gpio-direction settings from gpiolib behave sensibly.
+  See "About Output-Enable Settings."
+
+This mechanism allows for "auto-request" of gpiomux lines via gpiolib
+when it is suitable.  Drivers wishing more exact control are, of course,
+free to also use msm_gpiomux_set and msm_gpiomux_get.
+
+About Output-Enable Settings
+============================
+
+Some msm targets do not have the ability to query the current gpio
+configuration setting.  This means that changes made to the output-enable
+(OE) bit by gpiolib cannot be consistently detected and preserved by gpiomux.
+Therefore, when gpiomux applies a configuration setting, any direction
+settings which may have been applied by gpiolib are lost and the default
+input settings are re-applied.
+
+For this reason, drivers should not assume that gpio direction settings
+continue to hold if they free and then re-request a gpio.  This seems like
+common sense - after all, anybody could have obtained the line in the
+meantime - but it needs saying.
+
+This also means that calls to msm_gpiomux_write will reset the OE bit,
+which means that if the gpio line is held by a client of gpiolib and
+msm_gpiomux_write is called, the direction setting has been lost and
+gpiolib's internal state has been broken.
+Release gpio lines before reconfiguring them.
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index a406286f6f3..d111e3b23db 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,7 +1,5 @@
 00-INDEX
         - This file
-barrier.txt
-        - I/O Barriers
 biodoc.txt
         - Notes on the Generic Block Layer Rewrite in Linux 2.5
 capability.txt
@@ -16,3 +14,5 @@ stat.txt
         - Block layer statistics in /sys/block/<dev>/stat
 switching-sched.txt
         - Switching I/O schedulers at runtime
+writeback_cache_control.txt
+        - Control of volatile write back caches
diff --git a/Documentation/block/barrier.txt b/Documentation/block/barrier.txt
deleted file mode 100644
index 2c2f24f634e..00000000000
--- a/Documentation/block/barrier.txt
+++ /dev/null
@@ -1,261 +0,0 @@
-I/O Barriers
-============
-Tejun Heo <htejun@gmail.com>, July 22 2005
-
-I/O barrier requests are used to guarantee ordering around the barrier
-requests.  Unless you're crazy enough to use disk drives for
-implementing synchronization constructs (wow, sounds interesting...),
-the ordering is meaningful only for write requests for things like
-journal checkpoints.  All requests queued before a barrier request
-must be finished (made it to the physical medium) before the barrier
-request is started, and all requests queued after the barrier request
-must be started only after the barrier request is finished (again,
-made it to the physical medium).
-
-In other words, I/O barrier requests have the following two properties.
-
-1. Request ordering
-
-Requests cannot pass the barrier request.  Preceding requests are
-processed before the barrier and following requests after.
-
-Depending on what features a drive supports, this can be done in one
-of the following three ways.
-
-i. For devices which have queue depth greater than 1 (TCQ devices) and
-support ordered tags, block layer can just issue the barrier as an
-ordered request and the lower level driver, controller and drive
-itself are responsible for making sure that the ordering constraint is
-met.  Most modern SCSI controllers/drives should support this.
-
-NOTE: SCSI ordered tag isn't currently used due to limitation in the
-      SCSI midlayer, see the following random notes section.
-
-ii. For devices which have queue depth greater than 1 but don't
-support ordered tags, block layer ensures that the requests preceding
-a barrier request finishes before issuing the barrier request.  Also,
-it defers requests following the barrier until the barrier request is
-finished.  Older SCSI controllers/drives and SATA drives fall in this
-category.
-
-iii. Devices which have queue depth of 1.  This is a degenerate case
-of ii.  Just keeping issue order suffices.  Ancient SCSI
-controllers/drives and IDE drives are in this category.
-
-2. Forced flushing to physical medium
-
-Again, if you're not gonna do synchronization with disk drives (dang,
-it sounds even more appealing now!), the reason you use I/O barriers
-is mainly to protect filesystem integrity when power failure or some
-other events abruptly stop the drive from operating and possibly make
-the drive lose data in its cache.  So, I/O barriers need to guarantee
-that requests actually get written to non-volatile medium in order.
-
-There are four cases,
-
-i. No write-back cache.  Keeping requests ordered is enough.
-
-ii. Write-back cache but no flush operation.  There's no way to
-guarantee physical-medium commit order.  This kind of devices can't to
-I/O barriers.
-
-iii. Write-back cache and flush operation but no FUA (forced unit
-access).  We need two cache flushes - before and after the barrier
-request.
-
-iv. Write-back cache, flush operation and FUA.  We still need one
-flush to make sure requests preceding a barrier are written to medium,
-but post-barrier flush can be avoided by using FUA write on the
-barrier itself.
-
-
-How to support barrier requests in drivers
-------------------------------------------
-
-All barrier handling is done inside block layer proper.  All low level
-drivers have to are implementing its prepare_flush_fn and using one
-the following two functions to indicate what barrier type it supports
-and how to prepare flush requests.  Note that the term 'ordered' is
-used to indicate the whole sequence of performing barrier requests
-including draining and flushing.
-
-typedef void (prepare_flush_fn)(struct request_queue *q, struct request *rq);
-
-int blk_queue_ordered(struct request_queue *q, unsigned ordered,
-                      prepare_flush_fn *prepare_flush_fn);
-
-@q                      : the queue in question
-@ordered                : the ordered mode the driver/device supports
-@prepare_flush_fn       : this function should prepare @rq such that it
-                          flushes cache to physical medium when executed
-
-For example, SCSI disk driver's prepare_flush_fn looks like the
-following.
-
-static void sd_prepare_flush(struct request_queue *q, struct request *rq)
-{
-        memset(rq->cmd, 0, sizeof(rq->cmd));
-        rq->cmd_type = REQ_TYPE_BLOCK_PC;
-        rq->timeout = SD_TIMEOUT;
-        rq->cmd[0] = SYNCHRONIZE_CACHE;
-        rq->cmd_len = 10;
-}
-
-The following seven ordered modes are supported.  The following table
-shows which mode should be used depending on what features a
-device/driver supports.  In the leftmost column of table,
-QUEUE_ORDERED_ prefix is omitted from the mode names to save space.
-
-The table is followed by description of each mode.  Note that in the
-descriptions of QUEUE_ORDERED_DRAIN*, '=>' is used whereas '->' is
-used for QUEUE_ORDERED_TAG* descriptions.  '=>' indicates that the
-preceding step must be complete before proceeding to the next step.
-'->' indicates that the next step can start as soon as the previous
-step is issued.
-
-            write-back cache    ordered tag     flush           FUA
------------------------------------------------------------------------
-NONE            yes/no          N/A             no              N/A
-DRAIN           no              no              N/A             N/A
-DRAIN_FLUSH     yes             no              yes             no
-DRAIN_FUA       yes             no              yes             yes
-TAG             no              yes             N/A             N/A
-TAG_FLUSH       yes             yes             yes             no
-TAG_FUA         yes             yes             yes             yes
-
-
-QUEUE_ORDERED_NONE
-        I/O barriers are not needed and/or supported.
-
-        Sequence: N/A
-
-QUEUE_ORDERED_DRAIN
-        Requests are ordered by draining the request queue and cache
-        flushing isn't needed.
-
-        Sequence: drain => barrier
-
-QUEUE_ORDERED_DRAIN_FLUSH
-        Requests are ordered by draining the request queue and both
-        pre-barrier and post-barrier cache flushings are needed.
-
-        Sequence: drain => preflush => barrier => postflush
-
-QUEUE_ORDERED_DRAIN_FUA
-        Requests are ordered by draining the request queue and
-        pre-barrier cache flushing is needed.  By using FUA on barrier
-        request, post-barrier flushing can be skipped.
-
-        Sequence: drain => preflush => barrier
-
-QUEUE_ORDERED_TAG
-        Requests are ordered by ordered tag and cache flushing isn't
-        needed.
-
-        Sequence: barrier
-
-QUEUE_ORDERED_TAG_FLUSH
-        Requests are ordered by ordered tag and both pre-barrier and
-        post-barrier cache flushings are needed.
-
-        Sequence: preflush -> barrier -> postflush
-
-QUEUE_ORDERED_TAG_FUA
-        Requests are ordered by ordered tag and pre-barrier cache
-        flushing is needed.  By using FUA on barrier request,
-        post-barrier flushing can be skipped.
-
-        Sequence: preflush -> barrier
-
-
-Random notes/caveats
---------------------
-
-* SCSI layer currently can't use TAG ordering even if the drive,
-controller and driver support it.  The problem is that SCSI midlayer
-request dispatch function is not atomic.  It releases queue lock and
-switch to SCSI host lock during issue and it's possible and likely to
-happen in time that requests change their relative positions.  Once
-this problem is solved, TAG ordering can be enabled.
-
-* Currently, no matter which ordered mode is used, there can be only
-one barrier request in progress.  All I/O barriers are held off by
-block layer until the previous I/O barrier is complete.  This doesn't
-make any difference for DRAIN ordered devices, but, for TAG ordered
-devices with very high command latency, passing multiple I/O barriers
-to low level *might* be helpful if they are very frequent.  Well, this
-certainly is a non-issue.  I'm writing this just to make clear that no
-two I/O barrier is ever passed to low-level driver.
-
-* Completion order.  Requests in ordered sequence are issued in order
-but not required to finish in order.  Barrier implementation can
-handle out-of-order completion of ordered sequence.  IOW, the requests
-MUST be processed in order but the hardware/software completion paths
-are allowed to reorder completion notifications - eg. current SCSI
-midlayer doesn't preserve completion order during error handling.
-
-* Requeueing order.  Low-level drivers are free to requeue any request
-after they removed it from the request queue with
-blkdev_dequeue_request().  As barrier sequence should be kept in order
-when requeued, generic elevator code takes care of putting requests in
-order around barrier.  See blk_ordered_req_seq() and
-ELEVATOR_INSERT_REQUEUE handling in __elv_add_request() for details.
-
-Note that block drivers must not requeue preceding requests while
-completing latter requests in an ordered sequence.  Currently, no
-error checking is done against this.
-
-* Error handling.  Currently, block layer will report error to upper
-layer if any of requests in an ordered sequence fails.  Unfortunately,
-this doesn't seem to be enough.  Look at the following request flow.
-QUEUE_ORDERED_TAG_FLUSH is in use.
-
- [0] [1] [2] [3] [pre] [barrier] [post] < [4] [5] [6] ... >
-                                          still in elevator
-
-Let's say request [2], [3] are write requests to update file system
-metadata (journal or whatever) and [barrier] is used to mark that
-those updates are valid.  Consider the following sequence.
-
- i.     Requests [0] ~ [post] leaves the request queue and enters
-        low-level driver.
- ii.    After a while, unfortunately, something goes wrong and the
-        drive fails [2].  Note that any of [0], [1] and [3] could have
-        completed by this time, but [pre] couldn't have been finished
-        as the drive must process it in order and it failed before
-        processing that command.
- iii.   Error handling kicks in and determines that the error is
-        unrecoverable and fails [2], and resumes operation.
- iv.    [pre] [barrier] [post] gets processed.
- v.     *BOOM* power fails
-
-The problem here is that the barrier request is *supposed* to indicate
-that filesystem update requests [2] and [3] made it safely to the
-physical medium and, if the machine crashes after the barrier is
-written, filesystem recovery code can depend on that.  Sadly, that
-isn't true in this case anymore.  IOW, the success of a I/O barrier
-should also be dependent on success of some of the preceding requests,
-where only upper layer (filesystem) knows what 'some' is.
-
-This can be solved by implementing a way to tell the block layer which
-requests affect the success of the following barrier request and
-making lower lever drivers to resume operation on error only after
-block layer tells it to do so.
-
-As the probability of this happening is very low and the drive should
-be faulty, implementing the fix is probably an overkill.  But, still,
-it's there.
-
-* In previous drafts of barrier implementation, there was fallback
-mechanism such that, if FUA or ordered TAG fails, less fancy ordered
-mode can be selected and the failed barrier request is retried
-automatically.  The rationale for this feature was that as FUA is
-pretty new in ATA world and ordered tag was never used widely, there
-could be devices which report to support those features but choke when
-actually given such requests.
-
- This was removed for two reasons 1. it's an overkill 2. it's
-impossible to implement properly when TAG ordering is used as low
-level drivers resume after an error automatically.  If it's ever
-needed adding it back and modifying low level drivers accordingly
-shouldn't be difficult.
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt
new file mode 100644
index 00000000000..e578feed6d8
--- /dev/null
+++ b/Documentation/block/cfq-iosched.txt
@@ -0,0 +1,45 @@
+CFQ ioscheduler tunables
+========================
+
+slice_idle
+----------
+This specifies how long CFQ should idle for next request on certain cfq queues
+(for sequential workloads) and service trees (for random workloads) before
+queue is expired and CFQ selects next queue to dispatch from.
+
+By default slice_idle is a non-zero value. That means by default we idle on
+queues/service trees. This can be very helpful on highly seeky media like
+single spindle SATA/SAS disks where we can cut down on overall number of
+seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues/service tree
+level and one should see an overall improved throughput on faster storage
+devices like multiple SATA/SAS disks in hardware RAID configuration. The down
+side is that isolation provided from WRITES also goes down and notion of
+IO priority becomes weaker.
+
+So depending on storage and workload, it might be useful to set slice_idle=0.
+In general I think for SATA/SAS disks and software RAID of SATA/SAS disks
+keeping slice_idle enabled should be useful. For any configurations where
+there are multiple spindles behind single LUN (Host based hardware RAID
+controller or for storage arrays), setting slice_idle=0 might end up in better
+throughput and acceptable latencies.
+
+CFQ IOPS Mode for group scheduling
+===================================
+Basic CFQ design is to provide priority based time slices. Higher priority
+process gets bigger time slice and lower priority process gets smaller time
+slice. Measuring time becomes harder if storage is fast and supports NCQ and
+it would be better to dispatch multiple requests from multiple cfq queues in
+request queue at a time. In such scenario, it is not possible to measure time
+consumed by single queue accurately.
+
+What is possible though is to measure number of requests dispatched from a
+single queue and also allow dispatch from multiple cfq queue at the same time.
+This effectively becomes the fairness in terms of IOPS (IO operations per
+second).
+
+If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
+to IOPS mode and starts providing fairness in terms of number of requests
+dispatched. Note that this mode switching takes effect only for group
+scheduling. For non-cgroup users nothing should change.
diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt
new file mode 100644
index 00000000000..83407d36630
--- /dev/null
+++ b/Documentation/block/writeback_cache_control.txt
@@ -0,0 +1,86 @@
+
+Explicit volatile write back cache control
+=====================================
+
+Introduction
+------------
+
+Many storage devices, especially in the consumer market, come with volatile
+write back caches.  That means the devices signal I/O completion to the
+operating system before data actually has hit the non-volatile storage.  This
+behavior obviously speeds up various workloads, but it means the operating
+system needs to force data out to the non-volatile storage when it performs
+a data integrity operation like fsync, sync or an unmount.
+
+The Linux block layer provides two simple mechanisms that let filesystems
+control the caching behavior of the storage device.  These mechanisms are
+a forced cache flush, and the Force Unit Access (FUA) flag for requests.
+
+
+Explicit cache flushes
+----------------------
+
+The REQ_FLUSH flag can be OR ed into the r/w flags of a bio submitted from
+the filesystem and will make sure the volatile cache of the storage device
+has been flushed before the actual I/O operation is started.  This explicitly
+guarantees that previously completed write requests are on non-volatile
+storage before the flagged bio starts. In addition the REQ_FLUSH flag can be
+set on an otherwise empty bio structure, which causes only an explicit cache
+flush without any dependent I/O.  It is recommend to use
+the blkdev_issue_flush() helper for a pure cache flush.
+
+
+Forced Unit Access
+-----------------
+
+The REQ_FUA flag can be OR ed into the r/w flags of a bio submitted from the
+filesystem and will make sure that I/O completion for this request is only
+signaled after the data has been committed to non-volatile storage.
+
+
+Implementation details for filesystems
+--------------------------------------
+
+Filesystems can simply set the REQ_FLUSH and REQ_FUA bits and do not have to
+worry if the underlying devices need any explicit cache flushing and how
+the Forced Unit Access is implemented.  The REQ_FLUSH and REQ_FUA flags
+may both be set on a single bio.
+
+
+Implementation details for make_request_fn based block drivers
+--------------------------------------------------------------
+
+These drivers will always see the REQ_FLUSH and REQ_FUA bits as they sit
+directly below the submit_bio interface.  For remapping drivers the REQ_FUA
+bits need to be propagated to underlying devices, and a global flush needs
+to be implemented for bios with the REQ_FLUSH bit set.  For real device
+drivers that do not have a volatile cache the REQ_FLUSH and REQ_FUA bits
+on non-empty bios can simply be ignored, and REQ_FLUSH requests without
+data can be completed successfully without doing any work.  Drivers for
+devices with volatile caches need to implement the support for these
+flags themselves without any help from the block layer.
+
+
+Implementation details for request_fn based block drivers
+--------------------------------------------------------------
+
+For devices that do not support volatile write caches there is no driver
+support required, the block layer completes empty REQ_FLUSH requests before
+entering the driver and strips off the REQ_FLUSH and REQ_FUA bits from
+requests that have a payload.  For devices with volatile write caches the
+driver needs to tell the block layer that it supports flushing caches by
+doing:
+
+        blk_queue_flush(sdkp->disk->queue, REQ_FLUSH);
+
+and handle empty REQ_FLUSH requests in its prep_fn/request_fn.  Note that
+REQ_FLUSH requests with a payload are automatically turned into a sequence
+of an empty REQ_FLUSH request followed by the actual write by the block
+layer.  For devices that also support the FUA bit the block layer needs
+to be told to pass through the REQ_FUA bit using:
+
+        blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA);
+
+and the driver must handle write requests that have the REQ_FUA bit set
+in prep_fn/request_fn.  If the FUA bit is not natively supported the block
+layer turns it into an empty REQ_FLUSH request after the actual write.
diff --git a/Documentation/cgroups/blkio-controller.txt b/Documentation/cgroups/blkio-controller.txt
index 48e0b21b005..d6da611f8f6 100644
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@@ -8,12 +8,17 @@ both at leaf nodes as well as at intermediate nodes in a storage hierarchy.
 Plan is to use the same cgroup based management interface for blkio controller
 and based on user options switch IO policies in the background.
 
-In the first phase, this patchset implements proportional weight time based
-division of disk policy. It is implemented in CFQ. Hence this policy takes
-effect only on leaf nodes when CFQ is being used.
+Currently two IO control policies are implemented. First one is proportional
+weight time based division of disk policy. It is implemented in CFQ. Hence
+this policy takes effect only on leaf nodes when CFQ is being used. The second
+one is throttling policy which can be used to specify upper IO rate limits
+on devices. This policy is implemented in generic block layer and can be
+used on leaf nodes as well as higher level logical devices like device mapper.
 
 HOWTO
 =====
+Proportional Weight division of bandwidth
+-----------------------------------------
 You can do a very simple testing of running two dd threads in two different
 cgroups. Here is what you can do.
 
@@ -55,6 +60,35 @@ cgroups. Here is what you can do.
   group dispatched to the disk. We provide fairness in terms of disk time, so
   ideally io.disk_time of cgroups should be in proportion to the weight.
 
+Throttling/Upper Limit policy
+-----------------------------
+- Enable Block IO controller
+        CONFIG_BLK_CGROUP=y
+
+- Enable throttling in block layer
+        CONFIG_BLK_DEV_THROTTLING=y
+
+- Mount blkio controller
+        mount -t cgroup -o blkio none /cgroup/blkio
+
+- Specify a bandwidth rate on particular device for root group. The format
+  for policy is "<major>:<minor>  <byes_per_second>".
+
+        echo "8:16  1048576" > /cgroup/blkio/blkio.read_bps_device
+
+  Above will put a limit of 1MB/second on reads happening for root group
+  on device having major/minor number 8:16.
+
+- Run dd to read a file and see if rate is throttled to 1MB/s or not.
+
+                # dd if=/mnt/common/zerofile of=/dev/null bs=4K count=1024
+                # iflag=direct
+        1024+0 records in
+        1024+0 records out
+        4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s
+
+ Limits for writes can be put using blkio.write_bps_device file.
+
 Various user visible config options
 ===================================
 CONFIG_BLK_CGROUP
@@ -68,8 +102,13 @@ CONFIG_CFQ_GROUP_IOSCHED
         - Enables group scheduling in CFQ. Currently only 1 level of group
           creation is allowed.
 
+CONFIG_BLK_DEV_THROTTLING
+        - Enable block device throttling support in block layer.
+
 Details of cgroup files
 =======================
+Proportional weight policy files
+--------------------------------
 - blkio.weight
         - Specifies per cgroup weight. This is default weight of the group
           on all the devices until and unless overridden by per device rule.
@@ -210,6 +249,67 @@ Details of cgroup files
           and minor number of the device and third field specifies the number
           of times a group was dequeued from a particular device.
 
+Throttling/Upper limit policy files
+-----------------------------------
+- blkio.throttle.read_bps_device
+        - Specifies upper limit on READ rate from the device. IO rate is
+          specified in bytes per second. Rules are per deivce. Following is
+          the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.read_bps_device
+
+- blkio.throttle.write_bps_device
+        - Specifies upper limit on WRITE rate to the device. IO rate is
+          specified in bytes per second. Rules are per deivce. Following is
+          the format.
+
+  echo "<major>:<minor>  <rate_bytes_per_second>" > /cgrp/blkio.write_bps_device
+
+- blkio.throttle.read_iops_device
+        - Specifies upper limit on READ rate from the device. IO rate is
+          specified in IO per second. Rules are per deivce. Following is
+          the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.read_iops_device
+
+- blkio.throttle.write_iops_device
+        - Specifies upper limit on WRITE rate to the device. IO rate is
+          specified in io per second. Rules are per deivce. Following is
+          the format.
+
+  echo "<major>:<minor>  <rate_io_per_second>" > /cgrp/blkio.write_iops_device
+
+Note: If both BW and IOPS rules are specified for a device, then IO is
+      subjectd to both the constraints.
+
+- blkio.throttle.io_serviced
+        - Number of IOs (bio) completed to/from the disk by the group (as
+          seen by throttling policy). These are further divided by the type
+          of operation - read or write, sync or async. First two fields specify
+          the major and minor number of the device, third field specifies the
+          operation type and the fourth field specifies the number of IOs.
+
+          blkio.io_serviced does accounting as seen by CFQ and counts are in
+          number of requests (struct request). On the other hand,
+          blkio.throttle.io_serviced counts number of IO in terms of number
+          of bios as seen by throttling policy.  These bios can later be
+          merged by elevator and total number of requests completed can be
+          lesser.
+
+- blkio.throttle.io_service_bytes
+        - Number of bytes transferred to/from the disk by the group. These
+          are further divided by the type of operation - read or write, sync
+          or async. First two fields specify the major and minor number of the
+          device, third field specifies the operation type and the fourth field
+          specifies the number of bytes.
+
+          These numbers should roughly be same as blkio.io_service_bytes as
+          updated by CFQ. The difference between two is that
+          blkio.io_service_bytes will not be updated if CFQ is not operating
+          on request queue.
+
+Common files among various policies
+-----------------------------------
 - blkio.reset_stats
         - Writing an int to this file will result in resetting all the stats
           for that cgroup.
@@ -217,6 +317,7 @@ Details of cgroup files
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation
+-----------------------------------------------
 
 If group_isolation=1, it provides stronger isolation between groups at the
 expense of throughput. By default group_isolation is 0. In general that
@@ -243,6 +344,33 @@ By default one should run with group_isolation=0. If that is not sufficient
 and one wants stronger isolation between groups, then set group_isolation=1
 but this will come at cost of reduced throughput.
 
+/sys/block/<disk>/queue/iosched/slice_idle
+------------------------------------------
+On a faster hardware CFQ can be slow, especially with sequential workload.
+This happens because CFQ idles on a single queue and single queue might not
+drive deeper request queue depths to keep the storage busy. In such scenarios
+one can try setting slice_idle=0 and that would switch CFQ to IOPS
+(IO operations per second) mode on NCQ supporting hardware.
+
+That means CFQ will not idle between cfq queues of a cfq group and hence be
+able to driver higher queue depth and achieve better throughput. That also
+means that cfq provides fairness among groups in terms of IOPS and not in
+terms of disk time.
+
+/sys/block/<disk>/queue/iosched/group_idle
+------------------------------------------
+If one disables idling on individual cfq queues and cfq service trees by
+setting slice_idle=0, group_idle kicks in. That means CFQ will still idle
+on the group in an attempt to provide fairness among groups.
+
+By default group_idle is same as slice_idle and does not do anything if
+slice_idle is enabled.
+
+One can experience an overall throughput drop if you have created multiple
+groups and put applications in that group which are not driving enough
+IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
+on individual groups and throughput should improve.
+
 What works
 ==========
 - Currently only sync IO queues are support. All the buffered writes are
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4bccd3..902d3151f52 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
         identifier (rather than the kernel's).  The actual value is
         architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+        the book ID of cpuX. Typically it is the hardware platform's
+        identifier (rather than the kernel's).  The actual value is
+        architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
         internel kernel map of cpuX's hardware threads within the same
         core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
         internal kernel map of cpuX's hardware threads within the same
         physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+        internal kernel map of cpuX's hardware threads within the same
+        book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 842aa9de84a..5e2bc4ab897 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -386,34 +386,6 @@ Who:	Tejun Heo <tj@kernel.org>
 
 ----------------------------
 
-What:   Support for VMware's guest paravirtuliazation technique [VMI] will be
-        dropped.
-When:   2.6.37 or earlier.
-Why:    With the recent innovations in CPU hardware acceleration technologies
-        from Intel and AMD, VMware ran a few experiments to compare these
-        techniques to guest paravirtualization technique on VMware's platform.
-        These hardware assisted virtualization techniques have outperformed the
-        performance benefits provided by VMI in most of the workloads. VMware
-        expects that these hardware features will be ubiquitous in a couple of
-        years, as a result, VMware has started a phased retirement of this
-        feature from the hypervisor. We will be removing this feature from the
-        Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-        technical reasons (read opportunity to remove major chunk of pvops)
-        arise.
-
-        Please note that VMI has always been an optimization and non-VMI kernels
-        still work fine on VMware's platform.
-        Latest versions of VMware's product which support VMI are,
-        Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-        releases for these products will continue supporting VMI.
-
-        For more details about VMI retirement take a look at this,
-        http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who:    Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
 What:   Support for lcd_switch and display_get in asus-laptop driver
 When:   March 2010
 Why:    These two features use non-standard interfaces. There are the
diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt
index 1f7ae144f6d..5393e661169 100644
--- a/Documentation/filesystems/ocfs2.txt
+++ b/Documentation/filesystems/ocfs2.txt
@@ -87,3 +87,10 @@ dir_resv_level=	(*)	By default, directory reservations will scale with file
                         reservations - users should rarely need to change this
                         value. If allocation reservations are turned off, this
                         option will have no effect.
+coherency=full  (*)     Disallow concurrent O_DIRECT writes, cluster inode
+                        lock will be taken to force other nodes drop cache,
+                        therefore full cluster coherency is guaranteed even
+                        for O_DIRECT writes.
+coherency=buffered      Allow concurrent O_DIRECT writes without EX lock among
+                        nodes, which gains high performance at risk of getting
+                        stale data on other nodes.
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index d96a6dba574..9633da01ff4 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -109,17 +109,19 @@ 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:
+test if such number from such a structure 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.
+example, a number might be valid but temporarily unused on a given board.
 
+Whether a platform supports multiple GPIO controllers is a platform-specific
+implementation issue, as are whether that support can leave "holes" in the space
+of GPIO numbers, and whether new controllers can be added at runtime.  Such issues
+can affect things including whether adjacent GPIO numbers are both valid.
 
 Using GPIOs
 -----------
@@ -480,12 +482,16 @@ To support this framework, a platform's Kconfig will "select" either
 ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
-They may also want to provide a custom value for ARCH_NR_GPIOS.
 
-ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+It may also provide a custom value for ARCH_NR_GPIOS, so that it better
+reflects the number of GPIOs in actual use on that platform, without
+wasting static table space.  (It should count both built-in/SoC GPIOs and
+also ones on GPIO expanders.
+
+ARCH_REQUIRE_GPIOLIB means that the gpiolib code will always get compiled
 into the kernel on that architecture.
 
-ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpiolib code defaults to off and the user
 can enable it and build it into the kernel optionally.
 
 If neither of these options are selected, the platform does not support
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index ff45d1f837c..48ceabedf55 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -91,12 +91,11 @@ name		The chip name.
                 I2C devices get this attribute created automatically.
                 RO
 
-update_rate     The rate at which the chip will update readings.
+update_interval The interval at which the chip will update readings.
                 Unit: millisecond
                 RW
-                Some devices have a variable update rate. This attribute
-                can be used to change the update rate to the desired
-                frequency.
+                Some devices have a variable update rate or interval.
+                This attribute can be used to change it to the desired value.
 
 
 ************
diff --git a/Documentation/kernel-doc-nano-HOWTO.txt b/Documentation/kernel-doc-nano-HOWTO.txt
index 27a52b35d55..3d8a97747f7 100644
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@@ -345,5 +345,10 @@ documentation, in <filename>, for the functions listed.
 section titled <section title> from <filename>.
 Spaces are allowed in <section title>; do not quote the <section title>.
 
+!C<filename> is replaced by nothing, but makes the tools check that
+all DOC: sections and documented functions, symbols, etc. are used.
+This makes sense to use when you use !F/!P only and want to verify
+that all documentation is included.
+
 Tim.
 */ <twaugh@redhat.com>
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f084af0cb8e..02f21d9220c 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -455,7 +455,7 @@ and is between 256 and 4096 characters. It is defined in the file
                         [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
                                 pxa_timer,timer3,32k_counter,timer0_1
                         [AVR32] avr32
-                        [X86-32] pit,hpet,tsc,vmi-timer;
+                        [X86-32] pit,hpet,tsc;
                                 scx200_hrt on Geode; cyclone on IBM x440
                         [MIPS] MIPS
                         [PARISC] cr16
@@ -1974,15 +1974,18 @@ and is between 256 and 4096 characters. It is defined in the file
                 force   Enable ASPM even on devices that claim not to support it.
                         WARNING: Forcing ASPM on may cause system lockups.
 
+        pcie_ports=     [PCIE] PCIe ports handling:
+                auto    Ask the BIOS whether or not to use native PCIe services
+                        associated with PCIe ports (PME, hot-plug, AER).  Use
+                        them only if that is allowed by the BIOS.
+                native  Use native PCIe services associated with PCIe ports
+                        unconditionally.
+                compat  Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
+                        ports driver.
+
         pcie_pme=       [PCIE,PM] Native PCIe PME signaling options:
-                        Format: {auto|force}[,nomsi]
-                auto    Use native PCIe PME signaling if the BIOS allows the
-                        kernel to control PCIe config registers of root ports.
-                force   Use native PCIe PME signaling even if the BIOS refuses
-                        to allow the kernel to control the relevant PCIe config
-                        registers.
                 nomsi   Do not use MSI for native PCIe PME signaling (this makes
-                        all PCIe root ports use INTx for everything).
+                        all PCIe root ports use INTx for all services).
 
         pcmv=           [HW,PCMCIA] BadgePAD 4
 
@@ -2150,6 +2153,11 @@ and is between 256 and 4096 characters. It is defined in the file
                         Reserves a hole at the top of the kernel virtual
                         address space.
 
+        reservelow=     [X86]
+                        Format: nn[K]
+                        Set the amount of memory to reserve for BIOS at
+                        the bottom of the address space.
+
         reset_devices   [KNL] Force drivers to reset the underlying device
                         during initialization.
 
@@ -2162,6 +2170,11 @@ and is between 256 and 4096 characters. It is defined in the file
                         in <PAGE_SIZE> units (needed only for swap files).
                         See  Documentation/power/swsusp-and-swap-files.txt
 
+        hibernate=      [HIBERNATION]
+                noresume        Don't check if there's a hibernation image
+                                present during boot.
+                nocompress      Don't compress/decompress hibernation images.
+
         retain_initrd   [RAM] Keep initrd memory after extraction
 
         rhash_entries=  [KNL,NET]
@@ -2432,6 +2445,10 @@ and is between 256 and 4096 characters. It is defined in the file
                         disables clocksource verification at runtime.
                         Used to enable high-resolution timer mode on older
                         hardware, and in virtualized environment.
+                        [x86] noirqtime: Do not use TSC to do irq accounting.
+                        Used to run time disable IRQ_TIME_ACCOUNTING on any
+                        platforms where RDTSC is slow and this accounting
+                        can add overhead.
 
         turbografx.map[2|3]=    [HW,JOY]
                         TurboGraFX parallel port interface
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 1762b81fcdf..741fe66d6ec 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -542,9 +542,11 @@ Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
 Probe handlers are run with preemption disabled.  Depending on the
-architecture, handlers may also run with interrupts disabled.  In any
-case, your handler should not yield the CPU (e.g., by attempting to
-acquire a semaphore).
+architecture and optimization state, handlers may also run with
+interrupts disabled (e.g., kretprobe handlers and optimized kprobe
+handlers run without interrupt disabled on x86/x86-64).  In any case,
+your handler should not yield the CPU (e.g., by attempting to acquire
+a semaphore).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/Documentation/lguest/lguest.c b/Documentation/lguest/lguest.c
index 8a6a8c6d498..dc73bc54cc4 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/lguest/lguest.c
@@ -1640,15 +1640,6 @@ static void blk_request(struct virtqueue *vq)
         off = out->sector * 512;
 
         /*
-         * The block device implements "barriers", where the Guest indicates
-         * that it wants all previous writes to occur before this write.  We
-         * don't have a way of asking our kernel to do a barrier, so we just
-         * synchronize all the data in the file.  Pretty poor, no?
-         */
-        if (out->type & VIRTIO_BLK_T_BARRIER)
-                fdatasync(vblk->fd);
-
-        /*
          * In general the virtio block driver is allowed to try SCSI commands.
          * It'd be nice if we supported eject, for example, but we don't.
          */
@@ -1680,6 +1671,13 @@ static void blk_request(struct virtqueue *vq)
                         /* Die, bad Guest, die. */
                         errx(1, "Write past end %llu+%u", off, ret);
                 }
+
+                wlen = sizeof(*in);
+                *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+        } else if (out->type & VIRTIO_BLK_T_FLUSH) {
+                /* Flush */
+                ret = fdatasync(vblk->fd);
+                verbose("FLUSH fdatasync: %i\n", ret);
                 wlen = sizeof(*in);
                 *in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
         } else {
@@ -1703,15 +1701,6 @@ static void blk_request(struct virtqueue *vq)
                 }
         }
 
-        /*
-         * OK, so we noted that it was pretty poor to use an fdatasync as a
-         * barrier.  But Christoph Hellwig points out that we need a sync
-         * *afterwards* as well: "Barriers specify no reordering to the front
-         * or the back."  And Jens Axboe confirmed it, so here we are:
-         */
-        if (out->type & VIRTIO_BLK_T_BARRIER)
-                fdatasync(vblk->fd);
-
         /* Finished that request. */
         add_used(vq, head, wlen);
 }
@@ -1736,8 +1725,8 @@ static void setup_block_file(const char *filename)
         vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
         vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-        /* We support barriers. */
-        add_feature(dev, VIRTIO_BLK_F_BARRIER);
+        /* We support FLUSH. */
+        add_feature(dev, VIRTIO_BLK_F_FLUSH);
 
         /* Tell Guest how many sectors this device has. */
         conf.capacity = cpu_to_le64(vblk->len / 512);
diff --git a/Documentation/mutex-design.txt b/Documentation/mutex-design.txt
index c91ccc0720f..38c10fd7f41 100644
--- a/Documentation/mutex-design.txt
+++ b/Documentation/mutex-design.txt
@@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler
 mutex semantics are sufficient for your code, then there are a couple
 of advantages of mutexes:
 
- - 'struct mutex' is smaller on most architectures: .e.g on x86,
+ - 'struct mutex' is smaller on most architectures: E.g. on x86,
    'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
    A smaller structure size means less RAM footprint, and better
    CPU-cache utilization.
@@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined:
  void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
  int  mutex_lock_interruptible_nested(struct mutex *lock,
                                       unsigned int subclass);
+ int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
diff --git a/Documentation/networking/e1000.txt b/Documentation/networking/e1000.txt
index 2df71861e57..d9271e74e48 100644
--- a/Documentation/networking/e1000.txt
+++ b/Documentation/networking/e1000.txt
@@ -1,82 +1,35 @@
 Linux* Base Driver for the Intel(R) PRO/1000 Family of Adapters
 ===============================================================
 
-September 26, 2006
-
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
-- Building and Installation
 - Command Line Parameters
 - Speed and Duplex Configuration
 - Additional Configurations
-- Known Issues
 - Support
 
-
-In This Release
-===============
-
-This file describes the Linux* Base Driver for the Intel(R) PRO/1000 Family
-of Adapters.  This driver includes support for Itanium(R)2-based systems.
-
-For questions related to hardware requirements, refer to the documentation
-supplied with your Intel PRO/1000 adapter. All hardware requirements listed
-apply to use with Linux.
-
-The following features are now available in supported kernels:
- - Native VLANs
- - Channel Bonding (teaming)
- - SNMP
-
-Channel Bonding documentation can be found in the Linux kernel source:
-/Documentation/networking/bonding.txt
-
-The driver information previously displayed in the /proc filesystem is not
-supported in this release.  Alternatively, you can use ethtool (version 1.6
-or later), lspci, and ifconfig to obtain the same information.
-
-Instructions on updating ethtool can be found in the section "Additional
-Configurations" later in this document.
-
-NOTE: The Intel(R) 82562v 10/100 Network Connection only provides 10/100
-support.
-
-
 Identifying Your Adapter
 ========================
 
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/adapter/pro100/21397.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 For the latest Intel network drivers for Linux, refer to the following
 website.  In the search field, enter your adapter name or type, or use the
 networking link on the left to search for your adapter:
 
-    http://downloadfinder.intel.com/scripts-df/support_intel.asp
-
+    http://support.intel.com/support/go/network/adapter/home.htm
 
 Command Line Parameters
 =======================
 
-If the driver is built as a module, the  following optional parameters
-are used by entering them on the command line with the modprobe command
-using this syntax:
-
-     modprobe e1000 [<option>=<VAL1>,<VAL2>,...]
-
-For example, with two PRO/1000 PCI adapters, entering:
-
-     modprobe e1000 TxDescriptors=80,128
-
-loads the e1000 driver with 80 TX descriptors for the first adapter and
-128 TX descriptors for the second adapter.
-
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
@@ -89,10 +42,6 @@ NOTES:  For more information about the AutoNeg, Duplex, and Speed
         parameters, see the application note at:
         http://www.intel.com/design/network/applnots/ap450.htm
 
-        A descriptor describes a data buffer and attributes related to
-        the data buffer.  This information is accessed by the hardware.
-
-
 AutoNeg
 -------
 (Supported only on adapters with copper connections)
@@ -106,7 +55,6 @@ Duplex parameters must not be specified.
 NOTE:  Refer to the Speed and Duplex section of this readme for more
        information on the AutoNeg parameter.
 
-
 Duplex
 ------
 (Supported only on adapters with copper connections)
@@ -119,7 +67,6 @@ set to auto-negotiate, the board auto-detects the correct duplex.  If the
 link partner is forced (either full or half), Duplex defaults to half-
 duplex.
 
-
 FlowControl
 -----------
 Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
@@ -128,16 +75,16 @@ Default Value: Reads flow control settings from the EEPROM
 This parameter controls the automatic generation(Tx) and response(Rx)
 to Ethernet PAUSE frames.
 
-
 InterruptThrottleRate
 ---------------------
 (not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range:   0,1,3,100-100000 (0=off, 1=dynamic, 3=dynamic conservative)
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
 Default Value: 3
 
 The driver can limit the amount of interrupts per second that the adapter
-will generate for incoming packets. It does this by writing a value to the 
-adapter that is based on the maximum amount of interrupts that the adapter 
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
 will generate per second.
 
 Setting InterruptThrottleRate to a value greater or equal to 100
@@ -146,37 +93,43 @@ per second, even if more packets have come in. This reduces interrupt
 load on the system and can lower CPU utilization under heavy load,
 but will increase latency as packets are not processed as quickly.
 
-The default behaviour of the driver previously assumed a static 
-InterruptThrottleRate value of 8000, providing a good fallback value for 
-all traffic types,but lacking in small packet performance and latency. 
-The hardware can handle many more small packets per second however, and 
+The default behaviour of the driver previously assumed a static
+InterruptThrottleRate value of 8000, providing a good fallback value for
+all traffic types,but lacking in small packet performance and latency.
+The hardware can handle many more small packets per second however, and
 for this reason an adaptive interrupt moderation algorithm was implemented.
 
 Since 7.3.x, the driver has two adaptive modes (setting 1 or 3) in which
-it dynamically adjusts the InterruptThrottleRate value based on the traffic 
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
 that it receives. After determining the type of incoming traffic in the last
-timeframe, it will adjust the InterruptThrottleRate to an appropriate value 
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
 for that traffic.
 
 The algorithm classifies the incoming traffic every interval into
-classes.  Once the class is determined, the InterruptThrottleRate value is 
-adjusted to suit that traffic type the best. There are three classes defined: 
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
 "Bulk traffic", for large amounts of packets of normal size; "Low latency",
 for small amounts of traffic and/or a significant percentage of small
-packets; and "Lowest latency", for almost completely small packets or 
+packets; and "Lowest latency", for almost completely small packets or
 minimal traffic.
 
-In dynamic conservative mode, the InterruptThrottleRate value is set to 4000 
-for traffic that falls in class "Bulk traffic". If traffic falls in the "Low 
-latency" or "Lowest latency" class, the InterruptThrottleRate is increased 
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
 stepwise to 20000. This default mode is suitable for most applications.
 
 For situations where low latency is vital such as cluster or
 grid computing, the algorithm can reduce latency even more when
 InterruptThrottleRate is set to mode 1. In this mode, which operates
-the same as mode 3, the InterruptThrottleRate will be increased stepwise to 
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
 70000 for traffic in class "Lowest latency".
 
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal, the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
 Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 and may improve small packet latency, but is generally not suitable
 for bulk throughput traffic.
@@ -212,8 +165,6 @@ NOTE:  When e1000 is loaded with default settings and multiple adapters
        be platform-specific.  If CPU utilization is not a concern, use
        RX_POLLING (NAPI) and default driver settings.
 
-
-
 RxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -225,15 +176,14 @@ by the driver.  Increasing this value allows the driver to buffer more
 incoming packets, at the expense of increased system memory utilization.
 
 Each descriptor is 16 bytes.  A receive buffer is also allocated for each
-descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending 
+descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
 on the MTU setting. The maximum MTU size is 16110.
 
-NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo 
-       Frames.  Depending on the available system resources, the request 
-       for a higher number of receive descriptors may be denied.  In this 
+NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo
+       Frames.  Depending on the available system resources, the request
+       for a higher number of receive descriptors may be denied.  In this
        case, use a lower number.
 
-
 RxIntDelay
 ----------
 Valid Range:   0-65535 (0=off)
@@ -254,7 +204,6 @@ CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
           restoring the network connection.  To eliminate the potential
           for the hang ensure that RxIntDelay is set to 0.
 
-
 RxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -268,7 +217,6 @@ packet is received within the set amount of time.  Proper tuning,
 along with RxIntDelay, may improve traffic throughput in specific network
 conditions.
 
-
 Speed
 -----
 (This parameter is supported only on adapters with copper connections.)
@@ -280,7 +228,6 @@ Speed forces the line speed to the specified value in megabits per second
 partner is set to auto-negotiate, the board will auto-detect the correct
 speed.  Duplex should also be set when Speed is set to either 10 or 100.
 
-
 TxDescriptors
 -------------
 Valid Range:   80-256 for 82542 and 82543-based adapters
@@ -295,6 +242,36 @@ NOTE:  Depending on the available system resources, the request for a
        higher number of transmit descriptors may be denied.  In this case,
        use a lower number.
 
+TxDescriptorStep
+----------------
+Valid Range:    1 (use every Tx Descriptor)
+                4 (use every 4th Tx Descriptor)
+
+Default Value:  1 (use every Tx Descriptor)
+
+On certain non-Intel architectures, it has been observed that intense TX
+traffic bursts of short packets may result in an improper descriptor
+writeback. If this occurs, the driver will report a "TX Timeout" and reset
+the adapter, after which the transmit flow will restart, though data may
+have stalled for as much as 10 seconds before it resumes.
+
+The improper writeback does not occur on the first descriptor in a system
+memory cache-line, which is typically 32 bytes, or 4 descriptors long.
+
+Setting TxDescriptorStep to a value of 4 will ensure that all TX descriptors
+are aligned to the start of a system memory cache line, and so this problem
+will not occur.
+
+NOTES: Setting TxDescriptorStep to 4 effectively reduces the number of
+       TxDescriptors available for transmits to 1/4 of the normal allocation.
+       This has a possible negative performance impact, which may be
+       compensated for by allocating more descriptors using the TxDescriptors
+       module parameter.
+
+       There are other conditions which may result in "TX Timeout", which will
+       not be resolved by the use of the TxDescriptorStep parameter. As the
+       issue addressed by this parameter has never been observed on Intel
+       Architecture platforms, it should not be used on Intel platforms.
 
 TxIntDelay
 ----------
@@ -307,7 +284,6 @@ efficiency if properly tuned for specific network traffic.  If the
 system is reporting dropped transmits, this value may be set too high
 causing the driver to run out of available transmit descriptors.
 
-
 TxAbsIntDelay
 -------------
 (This parameter is supported only on 82540, 82545 and later adapters.)
@@ -330,6 +306,35 @@ Default Value: 1
 A value of '1' indicates that the driver should enable IP checksum
 offload for received packets (both UDP and TCP) to the adapter hardware.
 
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+Usage: insmod e1000.ko copybreak=128
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can turn off
+this parameter in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
 
 Speed and Duplex Configuration
 ==============================
@@ -385,40 +390,9 @@ If the link partner is forced to a specific speed and duplex, then this
 parameter should not be used.  Instead, use the Speed and Duplex parameters
 previously mentioned to force the adapter to the same speed and duplex.
 
-
 Additional Configurations
 =========================
 
-  Configuring the Driver on Different Distributions
-  -------------------------------------------------
-  Configuring a network driver to load properly when the system is started
-  is distribution dependent.  Typically, the configuration process involves
-  adding an alias line to /etc/modules.conf or /etc/modprobe.conf as well
-  as editing other system startup scripts and/or configuration files.  Many
-  popular Linux distributions ship with tools to make these changes for you.
-  To learn the proper way to configure a network device for your system,
-  refer to your distribution documentation.  If during this process you are
-  asked for the driver or module name, the name for the Linux Base Driver
-  for the Intel(R) PRO/1000 Family of Adapters is e1000.
-
-  As an example, if you install the e1000 driver for two PRO/1000 adapters
-  (eth0 and eth1) and set the speed and duplex to 10full and 100half, add
-  the following to modules.conf or or modprobe.conf:
-
-       alias eth0 e1000
-       alias eth1 e1000
-       options e1000 Speed=10,100 Duplex=2,1
-
-  Viewing Link Messages
-  ---------------------
-  Link messages will not be displayed to the console if the distribution is
-  restricting system messages.  In order to see network driver link messages
-  on your console, set dmesg to eight by entering the following:
-
-       dmesg -n 8
-
-  NOTE: This setting is not saved across reboots.
-
   Jumbo Frames
   ------------
   Jumbo Frames support is enabled by changing the MTU to a value larger than
@@ -437,9 +411,11 @@ Additional Configurations
    setting in a different location.
 
   Notes:
-
-  - To enable Jumbo Frames, increase the MTU size on the interface beyond
-    1500.
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments. If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
 
   - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
     with the maximum Jumbo Frames size of 16128.
@@ -447,40 +423,11 @@ Additional Configurations
   - Using Jumbo Frames at 10 or 100 Mbps may result in poor performance or
     loss of link.
 
-  - Some Intel gigabit adapters that support Jumbo Frames have a frame size
-    limit of 9238 bytes, with a corresponding MTU size limit of 9216 bytes.
-    The adapters with this limitation are based on the Intel(R) 82571EB,
-    82572EI, 82573L and 80003ES2LAN controller.  These correspond to the
-    following product names:
-     Intel(R) PRO/1000 PT Server Adapter
-     Intel(R) PRO/1000 PT Desktop Adapter
-     Intel(R) PRO/1000 PT Network Connection
-     Intel(R) PRO/1000 PT Dual Port Server Adapter
-     Intel(R) PRO/1000 PT Dual Port Network Connection
-     Intel(R) PRO/1000 PF Server Adapter
-     Intel(R) PRO/1000 PF Network Connection
-     Intel(R) PRO/1000 PF Dual Port Server Adapter
-     Intel(R) PRO/1000 PB Server Connection
-     Intel(R) PRO/1000 PL Network Connection
-     Intel(R) PRO/1000 EB Network Connection with I/O Acceleration
-     Intel(R) PRO/1000 EB Backplane Connection with I/O Acceleration
-     Intel(R) PRO/1000 PT Quad Port Server Adapter
-
   - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
     support Jumbo Frames. These correspond to the following product names:
      Intel(R) PRO/1000 Gigabit Server Adapter
      Intel(R) PRO/1000 PM Network Connection
 
-  - The following adapters do not support Jumbo Frames:
-     Intel(R) 82562V 10/100 Network Connection
-     Intel(R) 82566DM Gigabit Network Connection
-     Intel(R) 82566DC Gigabit Network Connection
-     Intel(R) 82566MM Gigabit Network Connection
-     Intel(R) 82566MC Gigabit Network Connection
-     Intel(R) 82562GT 10/100 Network Connection
-     Intel(R) 82562G 10/100 Network Connection
-
-
   Ethtool
   -------
   The driver utilizes the ethtool interface for driver configuration and
@@ -490,142 +437,14 @@ Additional Configurations
   The latest release of ethtool can be found from
   http://sourceforge.net/projects/gkernel.
 
-  NOTE: Ethtool 1.6 only supports a limited set of ethtool options.  Support
-  for a more complete ethtool feature set can be enabled by upgrading
-  ethtool to ethtool-1.8.1.
-
   Enabling Wake on LAN* (WoL)
   ---------------------------
-  WoL is configured through the Ethtool* utility.  Ethtool is included with
-  all versions of Red Hat after Red Hat 7.2.  For other Linux distributions,
-  download and install Ethtool from the following website:
-  http://sourceforge.net/projects/gkernel.
-
-  For instructions on enabling WoL with Ethtool, refer to the website listed
-  above.
+  WoL is configured through the Ethtool* utility.
 
   WoL will be enabled on the system during the next shut down or reboot.
   For this driver version, in order to enable WoL, the e1000 driver must be
   loaded when shutting down or rebooting the system.
 
-  Wake On LAN is only supported on port A for the following devices:
-  Intel(R) PRO/1000 PT Dual Port Network Connection
-  Intel(R) PRO/1000 PT Dual Port Server Connection
-  Intel(R) PRO/1000 PT Dual Port Server Adapter
-  Intel(R) PRO/1000 PF Dual Port Server Adapter
-  Intel(R) PRO/1000 PT Quad Port Server Adapter
-
-  NAPI
-  ----
-  NAPI (Rx polling mode) is enabled in the e1000 driver.
-
-  See www.cyberus.ca/~hadi/usenix-paper.tgz for more information on NAPI.
-
-
-Known Issues
-============
-
-Dropped Receive Packets on Half-duplex 10/100 Networks
-------------------------------------------------------
-If you have an Intel PCI Express adapter running at 10mbps or 100mbps, half-
-duplex, you may observe occasional dropped receive packets.  There are no
-workarounds for this problem in this network configuration.  The network must
-be updated to operate in full-duplex, and/or 1000mbps only.
-
-Jumbo Frames System Requirement
--------------------------------
-Memory allocation failures have been observed on Linux systems with 64 MB
-of RAM or less that are running Jumbo Frames.  If you are using Jumbo
-Frames, your system may require more than the advertised minimum
-requirement of 64 MB of system memory.
-
-Performance Degradation with Jumbo Frames
------------------------------------------
-Degradation in throughput performance may be observed in some Jumbo frames
-environments.  If this is observed, increasing the application's socket
-buffer size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values
-may help.  See the specific application manual and
-/usr/src/linux*/Documentation/
-networking/ip-sysctl.txt for more details.
-
-Jumbo Frames on Foundry BigIron 8000 switch
--------------------------------------------
-There is a known issue using Jumbo frames when connected to a Foundry
-BigIron 8000 switch.  This is a 3rd party limitation.  If you experience
-loss of packets, lower the MTU size.
-
-Allocating Rx Buffers when Using Jumbo Frames 
----------------------------------------------
-Allocating Rx buffers when using Jumbo Frames on 2.6.x kernels may fail if 
-the available memory is heavily fragmented. This issue may be seen with PCI-X 
-adapters or with packet split disabled. This can be reduced or eliminated 
-by changing the amount of available memory for receive buffer allocation, by
-increasing /proc/sys/vm/min_free_kbytes. 
-
-Multiple Interfaces on Same Ethernet Broadcast Network
-------------------------------------------------------
-Due to the default ARP behavior on Linux, it is not possible to have
-one system on two IP networks in the same Ethernet broadcast domain
-(non-partitioned switch) behave as expected.  All Ethernet interfaces
-will respond to IP traffic for any IP address assigned to the system.
-This results in unbalanced receive traffic.
-
-If you have multiple interfaces in a server, either turn on ARP
-filtering by entering:
-
-    echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
-(this only works if your kernel's version is higher than 2.4.5),
-
-NOTE: This setting is not saved across reboots.  The configuration
-change can be made permanent by adding the line:
-    net.ipv4.conf.all.arp_filter = 1
-to the file /etc/sysctl.conf
-
-      or,
-
-install the interfaces in separate broadcast domains (either in
-different switches or in a switch partitioned to VLANs).
-
-82541/82547 can't link or are slow to link with some link partners
------------------------------------------------------------------
-There is a known compatibility issue with 82541/82547 and some
-low-end switches where the link will not be established, or will
-be slow to establish.  In particular, these switches are known to
-be incompatible with 82541/82547:
-
-    Planex FXG-08TE
-    I-O Data ETG-SH8
-
-To workaround this issue, the driver can be compiled with an override
-of the PHY's master/slave setting.  Forcing master or forcing slave
-mode will improve time-to-link.
-
-    # make CFLAGS_EXTRA=-DE1000_MASTER_SLAVE=<n>
-
-Where <n> is:
-
-    0 = Hardware default
-    1 = Master mode
-    2 = Slave mode
-    3 = Auto master/slave
-
-Disable rx flow control with ethtool
-------------------------------------
-In order to disable receive flow control using ethtool, you must turn
-off auto-negotiation on the same command line.
-
-For example:
-
-   ethtool -A eth? autoneg off rx off
-
-Unplugging network cable while ethtool -p is running
-----------------------------------------------------
-In kernel versions 2.5.50 and later (including 2.6 kernel), unplugging
-the network cable while ethtool -p is running will cause the system to
-become unresponsive to keyboard commands, except for control-alt-delete.
-Restarting the system appears to be the only remedy.
-
-
 Support
 =======
 
diff --git a/Documentation/networking/e1000e.txt b/Documentation/networking/e1000e.txt
new file mode 100644
index 00000000000..6aa048badf3
--- /dev/null
+++ b/Documentation/networking/e1000e.txt
@@ -0,0 +1,302 @@
+Linux* Driver for Intel(R) Network Connection
+===============================================================
+
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
+
+Contents
+========
+
+- Identifying Your Adapter
+- Command Line Parameters
+- Additional Configurations
+- Support
+
+Identifying Your Adapter
+========================
+
+The e1000e driver supports all PCI Express Intel(R) Gigabit Network
+Connections, except those that are 82575, 82576 and 82580-based*.
+
+* NOTE: The Intel(R) PRO/1000 P Dual Port Server Adapter is supported by
+  the e1000 driver, not the e1000e driver due to the 82546 part being used
+  behind a PCI Express bridge.
+
+For more information on how to identify your adapter, go to the Adapter &
+Driver ID Guide at:
+
+    http://support.intel.com/support/go/network/adapter/idguide.htm
+
+For the latest Intel network drivers for Linux, refer to the following
+website.  In the search field, enter your adapter name or type, or use the
+networking link on the left to search for your adapter:
+
+    http://support.intel.com/support/go/network/adapter/home.htm
+
+Command Line Parameters
+=======================
+
+The default value for each parameter is generally the recommended setting,
+unless otherwise noted.
+
+NOTES:  For more information about the InterruptThrottleRate,
+        RxIntDelay, TxIntDelay, RxAbsIntDelay, and TxAbsIntDelay
+        parameters, see the application note at:
+        http://www.intel.com/design/network/applnots/ap450.htm
+
+InterruptThrottleRate
+---------------------
+Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+                                   4=simplified balancing)
+Default Value: 3
+
+The driver can limit the amount of interrupts per second that the adapter
+will generate for incoming packets. It does this by writing a value to the
+adapter that is based on the maximum amount of interrupts that the adapter
+will generate per second.
+
+Setting InterruptThrottleRate to a value greater or equal to 100
+will program the adapter to send out a maximum of that many interrupts
+per second, even if more packets have come in. This reduces interrupt
+load on the system and can lower CPU utilization under heavy load,
+but will increase latency as packets are not processed as quickly.
+
+The driver has two adaptive modes (setting 1 or 3) in which
+it dynamically adjusts the InterruptThrottleRate value based on the traffic
+that it receives. After determining the type of incoming traffic in the last
+timeframe, it will adjust the InterruptThrottleRate to an appropriate value
+for that traffic.
+
+The algorithm classifies the incoming traffic every interval into
+classes.  Once the class is determined, the InterruptThrottleRate value is
+adjusted to suit that traffic type the best. There are three classes defined:
+"Bulk traffic", for large amounts of packets of normal size; "Low latency",
+for small amounts of traffic and/or a significant percentage of small
+packets; and "Lowest latency", for almost completely small packets or
+minimal traffic.
+
+In dynamic conservative mode, the InterruptThrottleRate value is set to 4000
+for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
+latency" or "Lowest latency" class, the InterruptThrottleRate is increased
+stepwise to 20000. This default mode is suitable for most applications.
+
+For situations where low latency is vital such as cluster or
+grid computing, the algorithm can reduce latency even more when
+InterruptThrottleRate is set to mode 1. In this mode, which operates
+the same as mode 3, the InterruptThrottleRate will be increased stepwise to
+70000 for traffic in class "Lowest latency".
+
+In simplified mode the interrupt rate is based on the ratio of Tx and
+Rx traffic.  If the bytes per second rate is approximately equal the
+interrupt rate will drop as low as 2000 interrupts per second.  If the
+traffic is mostly transmit or mostly receive, the interrupt rate could
+be as high as 8000.
+
+Setting InterruptThrottleRate to 0 turns off any interrupt moderation
+and may improve small packet latency, but is generally not suitable
+for bulk throughput traffic.
+
+NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+       RxAbsIntDelay parameters.  In other words, minimizing the receive
+       and/or transmit absolute delays does not force the controller to
+       generate more interrupts than what the Interrupt Throttle Rate
+       allows.
+
+NOTE:  When e1000e is loaded with default settings and multiple adapters
+       are in use simultaneously, the CPU utilization may increase non-
+       linearly.  In order to limit the CPU utilization without impacting
+       the overall throughput, we recommend that you load the driver as
+       follows:
+
+           modprobe e1000e InterruptThrottleRate=3000,3000,3000
+
+       This sets the InterruptThrottleRate to 3000 interrupts/sec for
+       the first, second, and third instances of the driver.  The range
+       of 2000 to 3000 interrupts per second works on a majority of
+       systems and is a good starting point, but the optimal value will
+       be platform-specific.  If CPU utilization is not a concern, use
+       RX_POLLING (NAPI) and default driver settings.
+
+RxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 0
+
+This value delays the generation of receive interrupts in units of 1.024
+microseconds.  Receive interrupt reduction can improve CPU efficiency if
+properly tuned for specific network traffic.  Increasing this value adds
+extra latency to frame reception and can end up decreasing the throughput
+of TCP traffic.  If the system is reporting dropped receives, this value
+may be set too high, causing the driver to run out of available receive
+descriptors.
+
+CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
+          hang (stop transmitting) under certain network conditions.  If
+          this occurs a NETDEV WATCHDOG message is logged in the system
+          event log.  In addition, the controller is automatically reset,
+          restoring the network connection.  To eliminate the potential
+          for the hang ensure that RxIntDelay is set to 0.
+
+RxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is received within the set amount of time.  Proper tuning,
+along with RxIntDelay, may improve traffic throughput in specific network
+conditions.
+
+TxIntDelay
+----------
+Valid Range:   0-65535 (0=off)
+Default Value: 8
+
+This value delays the generation of transmit interrupts in units of
+1.024 microseconds.  Transmit interrupt reduction can improve CPU
+efficiency if properly tuned for specific network traffic.  If the
+system is reporting dropped transmits, this value may be set too high
+causing the driver to run out of available transmit descriptors.
+
+TxAbsIntDelay
+-------------
+Valid Range:   0-65535 (0=off)
+Default Value: 32
+
+This value, in units of 1.024 microseconds, limits the delay in which a
+transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
+this value ensures that an interrupt is generated after the initial
+packet is sent on the wire within the set amount of time.  Proper tuning,
+along with TxIntDelay, may improve traffic throughput in specific
+network conditions.
+
+Copybreak
+---------
+Valid Range:   0-xxxxxxx (0=off)
+Default Value: 256
+
+Driver copies all packets below or equaling this size to a fresh Rx
+buffer before handing it up the stack.
+
+This parameter is different than other parameters, in that it is a
+single (not 1,1,1 etc.) parameter applied to all driver instances and
+it is also available during runtime at
+/sys/module/e1000e/parameters/copybreak
+
+SmartPowerDownEnable
+--------------------
+Valid Range: 0-1
+Default Value:  0 (disabled)
+
+Allows PHY to turn off in lower power states. The user can set this parameter
+in supported chipsets.
+
+KumeranLockLoss
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+This workaround skips resetting the PHY at shutdown for the initial
+silicon releases of ICH8 systems.
+
+IntMode
+-------
+Valid Range: 0-2 (0=legacy, 1=MSI, 2=MSI-X)
+Default Value: 2
+
+Allows changing the interrupt mode at module load time, without requiring a
+recompile. If the driver load fails to enable a specific interrupt mode, the
+driver will try other interrupt modes, from least to most compatible.  The
+interrupt order is MSI-X, MSI, Legacy.  If specifying MSI (IntMode=1)
+interrupts, only MSI and Legacy will be attempted.
+
+CrcStripping
+------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Strip the CRC from received packets before sending up the network stack.  If
+you have a machine with a BMC enabled but cannot receive IPMI traffic after
+loading or enabling the driver, try disabling this feature.
+
+WriteProtectNVM
+---------------
+Valid Range: 0-1
+Default Value: 1 (enabled)
+
+Set the hardware to ignore all write/erase cycles to the GbE region in the
+ICHx NVM (non-volatile memory).  This feature can be disabled by the
+WriteProtectNVM module parameter (enabled by default) only after a hardware
+reset, but the machine must be power cycled before trying to enable writes.
+
+Note: the kernel boot option iomem=relaxed may need to be set if the kernel
+config option CONFIG_STRICT_DEVMEM=y, if the root user wants to write the
+NVM from user space via ethtool.
+
+Additional Configurations
+=========================
+
+  Jumbo Frames
+  ------------
+  Jumbo Frames support is enabled by changing the MTU to a value larger than
+  the default of 1500.  Use the ifconfig command to increase the MTU size.
+  For example:
+
+       ifconfig eth<x> mtu 9000 up
+
+  This setting is not saved across reboots.
+
+  Notes:
+
+  - The maximum MTU setting for Jumbo Frames is 9216.  This value coincides
+    with the maximum Jumbo Frames size of 9234 bytes.
+
+  - Using Jumbo Frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
+
+  - Some adapters limit Jumbo Frames sized packets to a maximum of
+    4096 bytes and some adapters do not support Jumbo Frames.
+
+
+  Ethtool
+  -------
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  We
+  strongly recommend downloading the latest version of Ethtool at:
+
+  http://sourceforge.net/projects/gkernel.
+
+  Speed and Duplex
+  ----------------
+  Speed and Duplex are configured through the Ethtool* utility. For
+  instructions,  refer to the Ethtool man page.
+
+  Enabling Wake on LAN* (WoL)
+  ---------------------------
+  WoL is configured through the Ethtool* utility. For instructions on
+  enabling WoL with Ethtool, refer to the Ethtool man page.
+
+  WoL will be enabled on the system during the next shut down or reboot.
+  For this driver version, in order to enable WoL, the e1000e driver must be
+  loaded when shutting down or rebooting the system.
+
+  In most cases Wake On LAN is only supported on port A for multiple port
+  adapters. To verify if a port supports Wake on LAN run ethtool eth<X>.
+
+
+Support
+=======
+
+For general information, go to the Intel support website at:
+
+    www.intel.com/support/
+
+or the Intel Wired Networking project hosted by Sourceforge at:
+
+    http://sourceforge.net/projects/e1000
+
+If an issue is identified with the released source code on the supported
+kernel with a supported adapter, email the specific information related
+to the issue to e1000-devel@lists.sf.net
diff --git a/Documentation/networking/ixgbevf.txt b/Documentation/networking/ixgbevf.txt
index 19015de6725..21dd5d15b6b 100755..100644
--- a/Documentation/networking/ixgbevf.txt
+++ b/Documentation/networking/ixgbevf.txt
@@ -1,19 +1,16 @@
 Linux* Base Driver for Intel(R) Network Connection
 ==================================================
 
-November 24, 2009
+Intel Gigabit Linux driver.
+Copyright(c) 1999 - 2010 Intel Corporation.
 
 Contents
 ========
 
-- In This Release
 - Identifying Your Adapter
 - Known Issues/Troubleshooting
 - Support
 
-In This Release
-===============
-
 This file describes the ixgbevf Linux* Base Driver for Intel Network
 Connection.
 
@@ -33,7 +30,7 @@ Identifying Your Adapter
 For more information on how to identify your adapter, go to the Adapter &
 Driver ID Guide at:
 
-    http://support.intel.com/support/network/sb/CS-008441.htm
+    http://support.intel.com/support/go/network/adapter/idguide.htm
 
 Known Issues/Troubleshooting
 ============================
@@ -57,34 +54,3 @@ or the Intel Wired Networking project hosted by Sourceforge at:
 If an issue is identified with the released source code on the supported
 kernel with a supported adapter, email the specific information related
 to the issue to e1000-devel@lists.sf.net
-
-License
-=======
-
-Intel 10 Gigabit Linux driver.
-Copyright(c) 1999 - 2009 Intel Corporation.
-
-This program is free software; you can redistribute it and/or modify it
-under the terms and conditions of the GNU General Public License,
-version 2, as published by the Free Software Foundation.
-
-This program is distributed in the hope it will be useful, but WITHOUT
-ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
-FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
-more details.
-
-You should have received a copy of the GNU General Public License along with
-this program; if not, write to the Free Software Foundation, Inc.,
-51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
-
-The full GNU General Public License is included in this distribution in
-the file called "COPYING".
-
-Trademarks
-==========
-
-Intel, Itanium, and Pentium are trademarks or registered trademarks of
-Intel Corporation or its subsidiaries in the United States and other
-countries.
-
-* Other names and brands may be claimed as the property of others.
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 26c0f9c0054..dd04361dd36 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,4 +1,29 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* pcmcia_loop_config() and autoconfiguration (as of 2.6.36)
+   If struct pcmcia_device *p_dev->config_flags is set accordingly,
+   pcmcia_loop_config() now sets up certain configuration values
+   automatically, though the driver may still override the settings
+   in the callback function. The following autoconfiguration options
+   are provided at the moment:
+        CONF_AUTO_CHECK_VCC : check for matching Vcc
+        CONF_AUTO_SET_VPP   : set Vpp
+        CONF_AUTO_AUDIO     : auto-enable audio line, if required
+        CONF_AUTO_SET_IO    : set ioport resources (->resource[0,1])
+        CONF_AUTO_SET_IOMEM : set first iomem resource (->resource[2])
+
+* pcmcia_request_configuration -> pcmcia_enable_device (as of 2.6.36)
+   pcmcia_request_configuration() got renamed to pcmcia_enable_device(),
+   as it mirrors pcmcia_disable_device(). Configuration settings are now
+   stored in struct pcmcia_device, e.g. in the fields config_flags,
+   config_index, config_base, vpp.
+
+* pcmcia_request_window changes (as of 2.6.36)
+   Instead of win_req_t, drivers are now requested to fill out
+   struct pcmcia_device *p_dev->resource[2,3,4,5] for up to four ioport
+   ranges. After a call to pcmcia_request_window(), the regions found there
+   are reserved and may be used immediately -- until pcmcia_release_window()
+   is called.
+
 * pcmcia_request_io changes (as of 2.6.36)
    Instead of io_req_t, drivers are now requested to fill out
    struct pcmcia_device *p_dev->resource[0,1] for up to two ioport
diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX
index fb742c213c9..45e9d4a9128 100644
--- a/Documentation/power/00-INDEX
+++ b/Documentation/power/00-INDEX
@@ -14,6 +14,8 @@ interface.txt
         - Power management user interface in /sys/power
 notifiers.txt
         - Registering suspend notifiers in device drivers
+opp.txt
+        - Operating Performance Point library
 pci.txt
         - How the PCI Subsystem Does Power Management
 pm_qos_interface.txt
diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt
index e67211fe0ee..c537834af00 100644
--- a/Documentation/power/interface.txt
+++ b/Documentation/power/interface.txt
@@ -57,7 +57,7 @@ smallest image possible.  In particular, if "0" is written to this file, the
 suspend image will be as small as possible.
 
 Reading from this file will display the current image size limit, which
-is set to 500 MB by default.
+is set to 2/5 of available RAM by default.
 
 /sys/power/pm_trace controls the code which saves the last PM event point in
 the RTC across reboots, so that you can debug a machine that just hangs
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
new file mode 100644
index 00000000000..44d87ad3cea
--- /dev/null
+++ b/Documentation/power/opp.txt
@@ -0,0 +1,375 @@
+*=============*
+* OPP Library *
+*=============*
+
+(C) 2009-2010 Nishanth Menon <nm@ti.com>, Texas Instruments Incorporated
+
+Contents
+--------
+1. Introduction
+2. Initial OPP List Registration
+3. OPP Search Functions
+4. OPP Availability Control Functions
+5. OPP Data Retrieval Functions
+6. Cpufreq Table Generation
+7. Data Structures
+
+1. Introduction
+===============
+Complex SoCs of today consists of a multiple sub-modules working in conjunction.
+In an operational system executing varied use cases, not all modules in the SoC
+need to function at their highest performing frequency all the time. To
+facilitate this, sub-modules in a SoC are grouped into domains, allowing some
+domains to run at lower voltage and frequency while other domains are loaded
+more. The set of discrete tuples consisting of frequency and voltage pairs that
+the device will support per domain are called Operating Performance Points or
+OPPs.
+
+OPP library provides a set of helper functions to organize and query the OPP
+information. The library is located in drivers/base/power/opp.c and the header
+is located in include/linux/opp.h. OPP library can be enabled by enabling
+CONFIG_PM_OPP from power management menuconfig menu. OPP library depends on
+CONFIG_PM as certain SoCs such as Texas Instrument's OMAP framework allows to
+optionally boot at a certain OPP without needing cpufreq.
+
+Typical usage of the OPP library is as follows:
+(users)         -> registers a set of default OPPs              -> (library)
+SoC framework   -> modifies on required cases certain OPPs      -> OPP layer
+                -> queries to search/retrieve information       ->
+
+OPP layer expects each domain to be represented by a unique device pointer. SoC
+framework registers a set of initial OPPs per device with the OPP layer. This
+list is expected to be an optimally small number typically around 5 per device.
+This initial list contains a set of OPPs that the framework expects to be safely
+enabled by default in the system.
+
+Note on OPP Availability:
+------------------------
+As the system proceeds to operate, SoC framework may choose to make certain
+OPPs available or not available on each device based on various external
+factors. Example usage: Thermal management or other exceptional situations where
+SoC framework might choose to disable a higher frequency OPP to safely continue
+operations until that OPP could be re-enabled if possible.
+
+OPP library facilitates this concept in it's implementation. The following
+operational functions operate only on available opps:
+opp_find_freq_{ceil, floor}, opp_get_voltage, opp_get_freq, opp_get_opp_count
+and opp_init_cpufreq_table
+
+opp_find_freq_exact is meant to be used to find the opp pointer which can then
+be used for opp_enable/disable functions to make an opp available as required.
+
+WARNING: Users of OPP library should refresh their availability count using
+get_opp_count if opp_enable/disable functions are invoked for a device, the
+exact mechanism to trigger these or the notification mechanism to other
+dependent subsystems such as cpufreq are left to the discretion of the SoC
+specific framework which uses the OPP library. Similar care needs to be taken
+care to refresh the cpufreq table in cases of these operations.
+
+WARNING on OPP List locking mechanism:
+-------------------------------------------------
+OPP library uses RCU for exclusivity. RCU allows the query functions to operate
+in multiple contexts and this synchronization mechanism is optimal for a read
+intensive operations on data structure as the OPP library caters to.
+
+To ensure that the data retrieved are sane, the users such as SoC framework
+should ensure that the section of code operating on OPP queries are locked
+using RCU read locks. The opp_find_freq_{exact,ceil,floor},
+opp_get_{voltage, freq, opp_count} fall into this category.
+
+opp_{add,enable,disable} are updaters which use mutex and implement it's own
+RCU locking mechanisms. opp_init_cpufreq_table acts as an updater and uses
+mutex to implment RCU updater strategy. These functions should *NOT* be called
+under RCU locks and other contexts that prevent blocking functions in RCU or
+mutex operations from working.
+
+2. Initial OPP List Registration
+================================
+The SoC implementation calls opp_add function iteratively to add OPPs per
+device. It is expected that the SoC framework will register the OPP entries
+optimally- typical numbers range to be less than 5. The list generated by
+registering the OPPs is maintained by OPP library throughout the device
+operation. The SoC framework can subsequently control the availability of the
+OPPs dynamically using the opp_enable / disable functions.
+
+opp_add - Add a new OPP for a specific domain represented by the device pointer.
+        The OPP is defined using the frequency and voltage. Once added, the OPP
+        is assumed to be available and control of it's availability can be done
+        with the opp_enable/disable functions. OPP library internally stores
+        and manages this information in the opp struct. This function may be
+        used by SoC framework to define a optimal list as per the demands of
+        SoC usage environment.
+
+        WARNING: Do not use this function in interrupt context.
+
+        Example:
+         soc_pm_init()
+         {
+                /* Do things */
+                r = opp_add(mpu_dev, 1000000, 900000);
+                if (!r) {
+                        pr_err("%s: unable to register mpu opp(%d)\n", r);
+                        goto no_cpufreq;
+                }
+                /* Do cpufreq things */
+         no_cpufreq:
+                /* Do remaining things */
+         }
+
+3. OPP Search Functions
+=======================
+High level framework such as cpufreq operates on frequencies. To map the
+frequency back to the corresponding OPP, OPP library provides handy functions
+to search the OPP list that OPP library internally manages. These search
+functions return the matching pointer representing the opp if a match is
+found, else returns error. These errors are expected to be handled by standard
+error checks such as IS_ERR() and appropriate actions taken by the caller.
+
+opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
+        availability. This function is especially useful to enable an OPP which
+        is not available by default.
+        Example: In a case when SoC framework detects a situation where a
+        higher frequency could be made available, it can use this function to
+        find the OPP prior to call the opp_enable to actually make it available.
+         rcu_read_lock();
+         opp = opp_find_freq_exact(dev, 1000000000, false);
+         rcu_read_unlock();
+         /* dont operate on the pointer.. just do a sanity check.. */
+         if (IS_ERR(opp)) {
+                pr_err("frequency not disabled!\n");
+                /* trigger appropriate actions.. */
+         } else {
+                opp_enable(dev,1000000000);
+         }
+
+        NOTE: This is the only search function that operates on OPPs which are
+        not available.
+
+opp_find_freq_floor - Search for an available OPP which is *at most* the
+        provided frequency. This function is useful while searching for a lesser
+        match OR operating on OPP information in the order of decreasing
+        frequency.
+        Example: To find the highest opp for a device:
+         freq = ULONG_MAX;
+         rcu_read_lock();
+         opp_find_freq_floor(dev, &freq);
+         rcu_read_unlock();
+
+opp_find_freq_ceil - Search for an available OPP which is *at least* the
+        provided frequency. This function is useful while searching for a
+        higher match OR operating on OPP information in the order of increasing
+        frequency.
+        Example 1: To find the lowest opp for a device:
+         freq = 0;
+         rcu_read_lock();
+         opp_find_freq_ceil(dev, &freq);
+         rcu_read_unlock();
+        Example 2: A simplified implementation of a SoC cpufreq_driver->target:
+         soc_cpufreq_target(..)
+         {
+                /* Do stuff like policy checks etc. */
+                /* Find the best frequency match for the req */
+                rcu_read_lock();
+                opp = opp_find_freq_ceil(dev, &freq);
+                rcu_read_unlock();
+                if (!IS_ERR(opp))
+                        soc_switch_to_freq_voltage(freq);
+                else
+                        /* do something when we cant satisfy the req */
+                /* do other stuff */
+         }
+
+4. OPP Availability Control Functions
+=====================================
+A default OPP list registered with the OPP library may not cater to all possible
+situation. The OPP library provides a set of functions to modify the
+availability of a OPP within the OPP list. This allows SoC frameworks to have
+fine grained dynamic control of which sets of OPPs are operationally available.
+These functions are intended to *temporarily* remove an OPP in conditions such
+as thermal considerations (e.g. don't use OPPx until the temperature drops).
+
+WARNING: Do not use these functions in interrupt context.
+
+opp_enable - Make a OPP available for operation.
+        Example: Lets say that 1GHz OPP is to be made available only if the
+        SoC temperature is lower than a certain threshold. The SoC framework
+        implementation might choose to do something as follows:
+         if (cur_temp < temp_low_thresh) {
+                /* Enable 1GHz if it was disabled */
+                rcu_read_lock();
+                opp = opp_find_freq_exact(dev, 1000000000, false);
+                rcu_read_unlock();
+                /* just error check */
+                if (!IS_ERR(opp))
+                        ret = opp_enable(dev, 1000000000);
+                else
+                        goto try_something_else;
+         }
+
+opp_disable - Make an OPP to be not available for operation
+        Example: Lets say that 1GHz OPP is to be disabled if the temperature
+        exceeds a threshold value. The SoC framework implementation might
+        choose to do something as follows:
+         if (cur_temp > temp_high_thresh) {
+                /* Disable 1GHz if it was enabled */
+                rcu_read_lock();
+                opp = opp_find_freq_exact(dev, 1000000000, true);
+                rcu_read_unlock();
+                /* just error check */
+                if (!IS_ERR(opp))
+                        ret = opp_disable(dev, 1000000000);
+                else
+                        goto try_something_else;
+         }
+
+5. OPP Data Retrieval Functions
+===============================
+Since OPP library abstracts away the OPP information, a set of functions to pull
+information from the OPP structure is necessary. Once an OPP pointer is
+retrieved using the search functions, the following functions can be used by SoC
+framework to retrieve the information represented inside the OPP layer.
+
+opp_get_voltage - Retrieve the voltage represented by the opp pointer.
+        Example: At a cpufreq transition to a different frequency, SoC
+        framework requires to set the voltage represented by the OPP using
+        the regulator framework to the Power Management chip providing the
+        voltage.
+         soc_switch_to_freq_voltage(freq)
+         {
+                /* do things */
+                rcu_read_lock();
+                opp = opp_find_freq_ceil(dev, &freq);
+                v = opp_get_voltage(opp);
+                rcu_read_unlock();
+                if (v)
+                        regulator_set_voltage(.., v);
+                /* do other things */
+         }
+
+opp_get_freq - Retrieve the freq represented by the opp pointer.
+        Example: Lets say the SoC framework uses a couple of helper functions
+        we could pass opp pointers instead of doing additional parameters to
+        handle quiet a bit of data parameters.
+         soc_cpufreq_target(..)
+         {
+                /* do things.. */
+                 max_freq = ULONG_MAX;
+                 rcu_read_lock();
+                 max_opp = opp_find_freq_floor(dev,&max_freq);
+                 requested_opp = opp_find_freq_ceil(dev,&freq);
+                 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
+                        r = soc_test_validity(max_opp, requested_opp);
+                 rcu_read_unlock();
+                /* do other things */
+         }
+         soc_test_validity(..)
+         {
+                 if(opp_get_voltage(max_opp) < opp_get_voltage(requested_opp))
+                         return -EINVAL;
+                 if(opp_get_freq(max_opp) < opp_get_freq(requested_opp))
+                         return -EINVAL;
+                /* do things.. */
+         }
+
+opp_get_opp_count - Retrieve the number of available opps for a device
+        Example: Lets say a co-processor in the SoC needs to know the available
+        frequencies in a table, the main processor can notify as following:
+         soc_notify_coproc_available_frequencies()
+         {
+                /* Do things */
+                rcu_read_lock();
+                num_available = opp_get_opp_count(dev);
+                speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
+                /* populate the table in increasing order */
+                freq = 0;
+                while (!IS_ERR(opp = opp_find_freq_ceil(dev, &freq))) {
+                        speeds[i] = freq;
+                        freq++;
+                        i++;
+                }
+                rcu_read_unlock();
+
+                soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
+                /* Do other things */
+         }
+
+6. Cpufreq Table Generation
+===========================
+opp_init_cpufreq_table - cpufreq framework typically is initialized with
+        cpufreq_frequency_table_cpuinfo which is provided with the list of
+        frequencies that are available for operation. This function provides
+        a ready to use conversion routine to translate the OPP layer's internal
+        information about the available frequencies into a format readily
+        providable to cpufreq.
+
+        WARNING: Do not use this function in interrupt context.
+
+        Example:
+         soc_pm_init()
+         {
+                /* Do things */
+                r = opp_init_cpufreq_table(dev, &freq_table);
+                if (!r)
+                        cpufreq_frequency_table_cpuinfo(policy, freq_table);
+                /* Do other things */
+         }
+
+        NOTE: This function is available only if CONFIG_CPU_FREQ is enabled in
+        addition to CONFIG_PM as power management feature is required to
+        dynamically scale voltage and frequency in a system.
+
+7. Data Structures
+==================
+Typically an SoC contains multiple voltage domains which are variable. Each
+domain is represented by a device pointer. The relationship to OPP can be
+represented as follows:
+SoC
+ |- device 1
+ |      |- opp 1 (availability, freq, voltage)
+ |      |- opp 2 ..
+ ...    ...
+ |      `- opp n ..
+ |- device 2
+ ...
+ `- device m
+
+OPP library maintains a internal list that the SoC framework populates and
+accessed by various functions as described above. However, the structures
+representing the actual OPPs and domains are internal to the OPP library itself
+to allow for suitable abstraction reusable across systems.
+
+struct opp - The internal data structure of OPP library which is used to
+        represent an OPP. In addition to the freq, voltage, availability
+        information, it also contains internal book keeping information required
+        for the OPP library to operate on.  Pointer to this structure is
+        provided back to the users such as SoC framework to be used as a
+        identifier for OPP in the interactions with OPP layer.
+
+        WARNING: The struct opp pointer should not be parsed or modified by the
+        users. The defaults of for an instance is populated by opp_add, but the
+        availability of the OPP can be modified by opp_enable/disable functions.
+
+struct device - This is used to identify a domain to the OPP layer. The
+        nature of the device and it's implementation is left to the user of
+        OPP library such as the SoC framework.
+
+Overall, in a simplistic view, the data structure operations is represented as
+following:
+
+Initialization / modification:
+            +-----+        /- opp_enable
+opp_add --> | opp | <-------
+  |         +-----+        \- opp_disable
+  \-------> domain_info(device)
+
+Search functions:
+             /-- opp_find_freq_ceil  ---\   +-----+
+domain_info<---- opp_find_freq_exact -----> | opp |
+             \-- opp_find_freq_floor ---/   +-----+
+
+Retrieval functions:
++-----+     /- opp_get_voltage
+| opp | <---
++-----+     \- opp_get_freq
+
+domain_info <- opp_get_opp_count
diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt
index 9363e056188..8ed17587a74 100644
--- a/Documentation/power/regulator/overview.txt
+++ b/Documentation/power/regulator/overview.txt
@@ -13,7 +13,7 @@ regulators (where voltage output is controllable) and current sinks (where
 current limit is controllable).
 
 (C) 2008  Wolfson Microelectronics PLC.
-Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+Author: Liam Girdwood <lrg@slimlogic.co.uk>
 
 
 Nomenclature
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 55b859b3bc7..489e9bacd16 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -1,6 +1,7 @@
 Run-time Power Management Framework for I/O Devices
 
 (C) 2009 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+(C) 2010 Alan Stern <stern@rowland.harvard.edu>
 
 1. Introduction
 
@@ -157,7 +158,8 @@ rules:
     to execute it, the other callbacks will not be executed for the same device.
 
   * A request to execute ->runtime_resume() will cancel any pending or
-    scheduled requests to execute the other callbacks for the same device.
+    scheduled requests to execute the other callbacks for the same device,
+    except for scheduled autosuspends.
 
 3. Run-time PM Device Fields
 
@@ -165,7 +167,7 @@ The following device run-time PM fields are present in 'struct dev_pm_info', as
 defined in include/linux/pm.h:
 
   struct timer_list suspend_timer;
-    - timer used for scheduling (delayed) suspend request
+    - timer used for scheduling (delayed) suspend and autosuspend requests
 
   unsigned long timer_expires;
     - timer expiration time, in jiffies (if this is different from zero, the
@@ -230,6 +232,28 @@ defined in include/linux/pm.h:
       interface; it may only be modified with the help of the pm_runtime_allow()
       and pm_runtime_forbid() helper functions
 
+  unsigned int no_callbacks;
+    - indicates that the device does not use the run-time PM callbacks (see
+      Section 8); it may be modified only by the pm_runtime_no_callbacks()
+      helper function
+
+  unsigned int use_autosuspend;
+    - indicates that the device's driver supports delayed autosuspend (see
+      Section 9); it may be modified only by the
+      pm_runtime{_dont}_use_autosuspend() helper functions
+
+  unsigned int timer_autosuspends;
+    - indicates that the PM core should attempt to carry out an autosuspend
+      when the timer expires rather than a normal suspend
+
+  int autosuspend_delay;
+    - the delay time (in milliseconds) to be used for autosuspend
+
+  unsigned long last_busy;
+    - the time (in jiffies) when the pm_runtime_mark_last_busy() helper
+      function was last called for this device; used in calculating inactivity
+      periods for autosuspend
+
 All of the above fields are members of the 'power' member of 'struct device'.
 
 4. Run-time PM Device Helper Functions
@@ -255,6 +279,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       error code on failure, where -EAGAIN or -EBUSY means it is safe to attempt
       to suspend the device again in future
 
+  int pm_runtime_autosuspend(struct device *dev);
+    - same as pm_runtime_suspend() except that the autosuspend delay is taken
+      into account; if pm_runtime_autosuspend_expiration() says the delay has
+      not yet expired then an autosuspend is scheduled for the appropriate time
+      and 0 is returned
+
   int pm_runtime_resume(struct device *dev);
     - execute the subsystem-level resume callback for the device; returns 0 on
       success, 1 if the device's run-time PM status was already 'active' or
@@ -267,6 +297,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       device (the request is represented by a work item in pm_wq); returns 0 on
       success or error code if the request has not been queued up
 
+  int pm_request_autosuspend(struct device *dev);
+    - schedule the execution of the subsystem-level suspend callback for the
+      device when the autosuspend delay has expired; if the delay has already
+      expired then the work item is queued up immediately
+
   int pm_schedule_suspend(struct device *dev, unsigned int delay);
     - schedule the execution of the subsystem-level suspend callback for the
       device in future, where 'delay' is the time to wait before queuing up a
@@ -298,12 +333,20 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
     - decrement the device's usage counter
 
   int pm_runtime_put(struct device *dev);
-    - decrement the device's usage counter, run pm_request_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_idle(dev) and return its result
+
+  int pm_runtime_put_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
 
   int pm_runtime_put_sync(struct device *dev);
-    - decrement the device's usage counter, run pm_runtime_idle(dev) and return
-      its result
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_idle(dev) and return its result
+
+  int pm_runtime_put_sync_autosuspend(struct device *dev);
+    - decrement the device's usage counter; if the result is 0 then run
+      pm_runtime_autosuspend(dev) and return its result
 
   void pm_runtime_enable(struct device *dev);
     - enable the run-time PM helper functions to run the device bus type's
@@ -349,19 +392,51 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       counter (used by the /sys/devices/.../power/control interface to
       effectively prevent the device from being power managed at run time)
 
+  void pm_runtime_no_callbacks(struct device *dev);
+    - set the power.no_callbacks flag for the device and remove the run-time
+      PM attributes from /sys/devices/.../power (or prevent them from being
+      added when the device is registered)
+
+  void pm_runtime_mark_last_busy(struct device *dev);
+    - set the power.last_busy field to the current time
+
+  void pm_runtime_use_autosuspend(struct device *dev);
+    - set the power.use_autosuspend flag, enabling autosuspend delays
+
+  void pm_runtime_dont_use_autosuspend(struct device *dev);
+    - clear the power.use_autosuspend flag, disabling autosuspend delays
+
+  void pm_runtime_set_autosuspend_delay(struct device *dev, int delay);
+    - set the power.autosuspend_delay value to 'delay' (expressed in
+      milliseconds); if 'delay' is negative then run-time suspends are
+      prevented
+
+  unsigned long pm_runtime_autosuspend_expiration(struct device *dev);
+    - calculate the time when the current autosuspend delay period will expire,
+      based on power.last_busy and power.autosuspend_delay; if the delay time
+      is 1000 ms or larger then the expiration time is rounded up to the
+      nearest second; returns 0 if the delay period has already expired or
+      power.use_autosuspend isn't set, otherwise returns the expiration time
+      in jiffies
+
 It is safe to execute the following helper functions from interrupt context:
 
 pm_request_idle()
+pm_request_autosuspend()
 pm_schedule_suspend()
 pm_request_resume()
 pm_runtime_get_noresume()
 pm_runtime_get()
 pm_runtime_put_noidle()
 pm_runtime_put()
+pm_runtime_put_autosuspend()
+pm_runtime_enable()
 pm_suspend_ignore_children()
 pm_runtime_set_active()
 pm_runtime_set_suspended()
-pm_runtime_enable()
+pm_runtime_suspended()
+pm_runtime_mark_last_busy()
+pm_runtime_autosuspend_expiration()
 
 5. Run-time PM Initialization, Device Probing and Removal
 
@@ -524,3 +599,141 @@ poweroff and run-time suspend callback, and similarly for system resume, thaw,
 restore, and run-time resume, can achieve this with the help of the
 UNIVERSAL_DEV_PM_OPS macro defined in include/linux/pm.h (possibly setting its
 last argument to NULL).
+
+8. "No-Callback" Devices
+
+Some "devices" are only logical sub-devices of their parent and cannot be
+power-managed on their own.  (The prototype example is a USB interface.  Entire
+USB devices can go into low-power mode or send wake-up requests, but neither is
+possible for individual interfaces.)  The drivers for these devices have no
+need of run-time PM callbacks; if the callbacks did exist, ->runtime_suspend()
+and ->runtime_resume() would always return 0 without doing anything else and
+->runtime_idle() would always call pm_runtime_suspend().
+
+Subsystems can tell the PM core about these devices by calling
+pm_runtime_no_callbacks().  This should be done after the device structure is
+initialized and before it is registered (although after device registration is
+also okay).  The routine will set the device's power.no_callbacks flag and
+prevent the non-debugging run-time PM sysfs attributes from being created.
+
+When power.no_callbacks is set, the PM core will not invoke the
+->runtime_idle(), ->runtime_suspend(), or ->runtime_resume() callbacks.
+Instead it will assume that suspends and resumes always succeed and that idle
+devices should be suspended.
+
+As a consequence, the PM core will never directly inform the device's subsystem
+or driver about run-time power changes.  Instead, the driver for the device's
+parent must take responsibility for telling the device's driver when the
+parent's power state changes.
+
+9. Autosuspend, or automatically-delayed suspends
+
+Changing a device's power state isn't free; it requires both time and energy.
+A device should be put in a low-power state only when there's some reason to
+think it will remain in that state for a substantial time.  A common heuristic
+says that a device which hasn't been used for a while is liable to remain
+unused; following this advice, drivers should not allow devices to be suspended
+at run-time until they have been inactive for some minimum period.  Even when
+the heuristic ends up being non-optimal, it will still prevent devices from
+"bouncing" too rapidly between low-power and full-power states.
+
+The term "autosuspend" is an historical remnant.  It doesn't mean that the
+device is automatically suspended (the subsystem or driver still has to call
+the appropriate PM routines); rather it means that run-time suspends will
+automatically be delayed until the desired period of inactivity has elapsed.
+
+Inactivity is determined based on the power.last_busy field.  Drivers should
+call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
+typically just before calling pm_runtime_put_autosuspend().  The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
+registration the length should be controlled by user space, using the
+/sys/devices/.../power/autosuspend_delay_ms attribute.
+
+In order to use autosuspend, subsystems or drivers must call
+pm_runtime_use_autosuspend() (preferably before registering the device), and
+thereafter they should use the various *_autosuspend() helper functions instead
+of the non-autosuspend counterparts:
+
+        Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
+        Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
+        Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
+        Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
+
+Drivers may also continue to use the non-autosuspend helper functions; they
+will behave normally, not taking the autosuspend delay into account.
+Similarly, if the power.use_autosuspend field isn't set then the autosuspend
+helper functions will behave just like the non-autosuspend counterparts.
+
+The implementation is well suited for asynchronous use in interrupt contexts.
+However such use inevitably involves races, because the PM core can't
+synchronize ->runtime_suspend() callbacks with the arrival of I/O requests.
+This synchronization must be handled by the driver, using its private lock.
+Here is a schematic pseudo-code example:
+
+        foo_read_or_write(struct foo_priv *foo, void *data)
+        {
+                lock(&foo->private_lock);
+                add_request_to_io_queue(foo, data);
+                if (foo->num_pending_requests++ == 0)
+                        pm_runtime_get(&foo->dev);
+                if (!foo->is_suspended)
+                        foo_process_next_request(foo);
+                unlock(&foo->private_lock);
+        }
+
+        foo_io_completion(struct foo_priv *foo, void *req)
+        {
+                lock(&foo->private_lock);
+                if (--foo->num_pending_requests == 0) {
+                        pm_runtime_mark_last_busy(&foo->dev);
+                        pm_runtime_put_autosuspend(&foo->dev);
+                } else {
+                        foo_process_next_request(foo);
+                }
+                unlock(&foo->private_lock);
+                /* Send req result back to the user ... */
+        }
+
+        int foo_runtime_suspend(struct device *dev)
+        {
+                struct foo_priv foo = container_of(dev, ...);
+                int ret = 0;
+
+                lock(&foo->private_lock);
+                if (foo->num_pending_requests > 0) {
+                        ret = -EBUSY;
+                } else {
+                        /* ... suspend the device ... */
+                        foo->is_suspended = 1;
+                }
+                unlock(&foo->private_lock);
+                return ret;
+        }
+
+        int foo_runtime_resume(struct device *dev)
+        {
+                struct foo_priv foo = container_of(dev, ...);
+
+                lock(&foo->private_lock);
+                /* ... resume the device ... */
+                foo->is_suspended = 0;
+                pm_runtime_mark_last_busy(&foo->dev);
+                if (foo->num_pending_requests > 0)
+                        foo_process_requests(foo);
+                unlock(&foo->private_lock);
+                return 0;
+        }
+
+The important point is that after foo_io_completion() asks for an autosuspend,
+the foo_runtime_suspend() callback may race with foo_read_or_write().
+Therefore foo_runtime_suspend() has to check whether there are any pending I/O
+requests (while holding the private lock) before allowing the suspend to
+proceed.
+
+In addition, the power.autosuspend_delay field can be changed by user space at
+any time.  If a driver cares about this, it can call
+pm_runtime_autosuspend_expiration() from within the ->runtime_suspend()
+callback while holding its private lock.  If the function returns a nonzero
+value then the delay has not yet expired and the callback should return
+-EAGAIN.
diff --git a/Documentation/power/s2ram.txt b/Documentation/power/s2ram.txt
index 514b94fc931..1bdfa044377 100644
--- a/Documentation/power/s2ram.txt
+++ b/Documentation/power/s2ram.txt
@@ -49,6 +49,13 @@ machine that doesn't boot) is:
    device (lspci and /sys/devices/pci* is your friend), and see if you can
    fix it, disable it, or trace into its resume function.
 
+   If no device matches the hash (or any matches appear to be false positives),
+   the culprit may be a device from a loadable kernel module that is not loaded
+   until after the hash is checked. You can check the hash against the current
+   devices again after more modules are loaded using sysfs:
+
+        cat /sys/power/pm_trace_dev_match
+
 For example, the above happens to be the VGA device on my EVO, which I
 used to run with "radeonfb" (it's an ATI Radeon mobility). It turns out
 that "radeonfb" simply cannot resume that device - it tries to set the
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 9d60ab717a7..ea718891a66 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -66,7 +66,8 @@ swsusp saves the state of the machine into active swaps and then reboots or
 powerdowns.  You must explicitly specify the swap partition to resume from with
 ``resume='' kernel option. If signature is found it loads and restores saved
 state. If the option ``noresume'' is specified as a boot parameter, it skips
-the resuming.
+the resuming.  If the option ``hibernate=nocompress'' is specified as a boot
+parameter, it saves hibernation image without compression.
 
 In the meantime while the system is suspended you should not add/remove any
 of the hardware, write to the filesystems, etc.
diff --git a/Documentation/powerpc/dts-bindings/fsl/spi.txt b/Documentation/powerpc/dts-bindings/fsl/spi.txt
index 80510c018ee..777abd7399d 100644
--- a/Documentation/powerpc/dts-bindings/fsl/spi.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/spi.txt
@@ -1,7 +1,9 @@
 * SPI (Serial Peripheral Interface)
 
 Required properties:
-- cell-index : SPI controller index.
+- cell-index : QE SPI subblock index.
+                0: QE subblock SPI1
+                1: QE subblock SPI2
 - compatible : should be "fsl,spi".
 - mode : the SPI operation mode, it can be "cpu" or "cpu-qe".
 - reg : Offset and length of the register set for the device
@@ -29,3 +31,23 @@ Example:
                 gpios = <&gpio 18 1     // device reg=<0>
                          &gpio 19 1>;   // device reg=<1>
         };
+
+
+* eSPI (Enhanced Serial Peripheral Interface)
+
+Required properties:
+- compatible : should be "fsl,mpc8536-espi".
+- reg : Offset and length of the register set for the device.
+- interrupts : should contain eSPI interrupt, the device has one interrupt.
+- fsl,espi-num-chipselects : the number of the chipselect signals.
+
+Example:
+        spi@110000 {
+                #address-cells = <1>;
+                #size-cells = <0>;
+                compatible = "fsl,mpc8536-espi";
+                reg = <0x110000 0x1000>;
+                interrupts = <53 0x2>;
+                interrupt-parent = <&mpic>;
+                fsl,espi-num-chipselects = <4>;
+        };
diff --git a/Documentation/sound/alsa/HD-Audio-Models.txt b/Documentation/sound/alsa/HD-Audio-Models.txt
index ce46fa1e643..37c6aad5e59 100644
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@@ -296,6 +296,7 @@ Conexant 5051
 Conexant 5066
 =============
   laptop        Basic Laptop config (default)
+  hp-laptop     HP laptops, e g G60
   dell-laptop   Dell laptops
   dell-vostro   Dell Vostro
   olpc-xo-1_5   OLPC XO 1.5
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index ccd951fa94e..cc96ee2666f 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -478,7 +478,7 @@ static void prepare_hwpoison_fd(void)
         }
 
         if (opt_unpoison && !hwpoison_forget_fd) {
-                sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs);
+                sprintf(buf, "%s/unpoison-pfn", hwpoison_debug_fs);
                 hwpoison_forget_fd = checked_open(buf, O_WRONLY);
         }
 }
diff --git a/Documentation/workqueue.txt b/Documentation/workqueue.txt
new file mode 100644
index 00000000000..996a27d9b8d
--- /dev/null
+++ b/Documentation/workqueue.txt
@@ -0,0 +1,381 @@
+
+Concurrency Managed Workqueue (cmwq)
+
+September, 2010         Tejun Heo <tj@kernel.org>
+                        Florian Mickler <florian@mickler.org>
+
+CONTENTS
+
+1. Introduction
+2. Why cmwq?
+3. The Design
+4. Application Programming Interface (API)
+5. Example Execution Scenarios
+6. Guidelines
+
+
+1. Introduction
+
+There are many cases where an asynchronous process execution context
+is needed and the workqueue (wq) API is the most commonly used
+mechanism for such cases.
+
+When such an asynchronous execution context is needed, a work item
+describing which function to execute is put on a queue.  An
+independent thread serves as the asynchronous execution context.  The
+queue is called workqueue and the thread is called worker.
+
+While there are work items on the workqueue the worker executes the
+functions associated with the work items one after the other.  When
+there is no work item left on the workqueue the worker becomes idle.
+When a new work item gets queued, the worker begins executing again.
+
+
+2. Why cmwq?
+
+In the original wq implementation, a multi threaded (MT) wq had one
+worker thread per CPU and a single threaded (ST) wq had one worker
+thread system-wide.  A single MT wq needed to keep around the same
+number of workers as the number of CPUs.  The kernel grew a lot of MT
+wq users over the years and with the number of CPU cores continuously
+rising, some systems saturated the default 32k PID space just booting
+up.
+
+Although MT wq wasted a lot of resource, the level of concurrency
+provided was unsatisfactory.  The limitation was common to both ST and
+MT wq albeit less severe on MT.  Each wq maintained its own separate
+worker pool.  A MT wq could provide only one execution context per CPU
+while a ST wq one for the whole system.  Work items had to compete for
+those very limited execution contexts leading to various problems
+including proneness to deadlocks around the single execution context.
+
+The tension between the provided level of concurrency and resource
+usage also forced its users to make unnecessary tradeoffs like libata
+choosing to use ST wq for polling PIOs and accepting an unnecessary
+limitation that no two polling PIOs can progress at the same time.  As
+MT wq don't provide much better concurrency, users which require
+higher level of concurrency, like async or fscache, had to implement
+their own thread pool.
+
+Concurrency Managed Workqueue (cmwq) is a reimplementation of wq with
+focus on the following goals.
+
+* Maintain compatibility with the original workqueue API.
+
+* Use per-CPU unified worker pools shared by all wq to provide
+  flexible level of concurrency on demand without wasting a lot of
+  resource.
+
+* Automatically regulate worker pool and level of concurrency so that
+  the API users don't need to worry about such details.
+
+
+3. The Design
+
+In order to ease the asynchronous execution of functions a new
+abstraction, the work item, is introduced.
+
+A work item is a simple struct that holds a pointer to the function
+that is to be executed asynchronously.  Whenever a driver or subsystem
+wants a function to be executed asynchronously it has to set up a work
+item pointing to that function and queue that work item on a
+workqueue.
+
+Special purpose threads, called worker threads, execute the functions
+off of the queue, one after the other.  If no work is queued, the
+worker threads become idle.  These worker threads are managed in so
+called thread-pools.
+
+The cmwq design differentiates between the user-facing workqueues that
+subsystems and drivers queue work items on and the backend mechanism
+which manages thread-pool and processes the queued work items.
+
+The backend is called gcwq.  There is one gcwq for each possible CPU
+and one gcwq to serve work items queued on unbound workqueues.
+
+Subsystems and drivers can create and queue work items through special
+workqueue API functions as they see fit. They can influence some
+aspects of the way the work items are executed by setting flags on the
+workqueue they are putting the work item on. These flags include
+things like CPU locality, reentrancy, concurrency limits and more. To
+get a detailed overview refer to the API description of
+alloc_workqueue() below.
+
+When a work item is queued to a workqueue, the target gcwq is
+determined according to the queue parameters and workqueue attributes
+and appended on the shared worklist of the gcwq.  For example, unless
+specifically overridden, a work item of a bound workqueue will be
+queued on the worklist of exactly that gcwq that is associated to the
+CPU the issuer is running on.
+
+For any worker pool implementation, managing the concurrency level
+(how many execution contexts are active) is an important issue.  cmwq
+tries to keep the concurrency at a minimal but sufficient level.
+Minimal to save resources and sufficient in that the system is used at
+its full capacity.
+
+Each gcwq bound to an actual CPU implements concurrency management by
+hooking into the scheduler.  The gcwq is notified whenever an active
+worker wakes up or sleeps and keeps track of the number of the
+currently runnable workers.  Generally, work items are not expected to
+hog a CPU and consume many cycles.  That means maintaining just enough
+concurrency to prevent work processing from stalling should be
+optimal.  As long as there are one or more runnable workers on the
+CPU, the gcwq doesn't start execution of a new work, but, when the
+last running worker goes to sleep, it immediately schedules a new
+worker so that the CPU doesn't sit idle while there are pending work
+items.  This allows using a minimal number of workers without losing
+execution bandwidth.
+
+Keeping idle workers around doesn't cost other than the memory space
+for kthreads, so cmwq holds onto idle ones for a while before killing
+them.
+
+For an unbound wq, the above concurrency management doesn't apply and
+the gcwq for the pseudo unbound CPU tries to start executing all work
+items as soon as possible.  The responsibility of regulating
+concurrency level is on the users.  There is also a flag to mark a
+bound wq to ignore the concurrency management.  Please refer to the
+API section for details.
+
+Forward progress guarantee relies on that workers can be created when
+more execution contexts are necessary, which in turn is guaranteed
+through the use of rescue workers.  All work items which might be used
+on code paths that handle memory reclaim are required to be queued on
+wq's that have a rescue-worker reserved for execution under memory
+pressure.  Else it is possible that the thread-pool deadlocks waiting
+for execution contexts to free up.
+
+
+4. Application Programming Interface (API)
+
+alloc_workqueue() allocates a wq.  The original create_*workqueue()
+functions are deprecated and scheduled for removal.  alloc_workqueue()
+takes three arguments - @name, @flags and @max_active.  @name is the
+name of the wq and also used as the name of the rescuer thread if
+there is one.
+
+A wq no longer manages execution resources but serves as a domain for
+forward progress guarantee, flush and work item attributes.  @flags
+and @max_active control how work items are assigned execution
+resources, scheduled and executed.
+
+@flags:
+
+  WQ_NON_REENTRANT
+
+        By default, a wq guarantees non-reentrance only on the same
+        CPU.  A work item may not be executed concurrently on the same
+        CPU by multiple workers but is allowed to be executed
+        concurrently on multiple CPUs.  This flag makes sure
+        non-reentrance is enforced across all CPUs.  Work items queued
+        to a non-reentrant wq are guaranteed to be executed by at most
+        one worker system-wide at any given time.
+
+  WQ_UNBOUND
+
+        Work items queued to an unbound wq are served by a special
+        gcwq which hosts workers which are not bound to any specific
+        CPU.  This makes the wq behave as a simple execution context
+        provider without concurrency management.  The unbound gcwq
+        tries to start execution of work items as soon as possible.
+        Unbound wq sacrifices locality but is useful for the following
+        cases.
+
+        * Wide fluctuation in the concurrency level requirement is
+          expected and using bound wq may end up creating large number
+          of mostly unused workers across different CPUs as the issuer
+          hops through different CPUs.
+
+        * Long running CPU intensive workloads which can be better
+          managed by the system scheduler.
+
+  WQ_FREEZEABLE
+
+        A freezeable wq participates in the freeze phase of the system
+        suspend operations.  Work items on the wq are drained and no
+        new work item starts execution until thawed.
+
+  WQ_MEM_RECLAIM
+
+        All wq which might be used in the memory reclaim paths _MUST_
+        have this flag set.  The wq is guaranteed to have at least one
+        execution context regardless of memory pressure.
+
+  WQ_HIGHPRI
+
+        Work items of a highpri wq are queued at the head of the
+        worklist of the target gcwq and start execution regardless of
+        the current concurrency level.  In other words, highpri work
+        items will always start execution as soon as execution
+        resource is available.
+
+        Ordering among highpri work items is preserved - a highpri
+        work item queued after another highpri work item will start
+        execution after the earlier highpri work item starts.
+
+        Although highpri work items are not held back by other
+        runnable work items, they still contribute to the concurrency
+        level.  Highpri work items in runnable state will prevent
+        non-highpri work items from starting execution.
+
+        This flag is meaningless for unbound wq.
+
+  WQ_CPU_INTENSIVE
+
+        Work items of a CPU intensive wq do not contribute to the
+        concurrency level.  In other words, runnable CPU intensive
+        work items will not prevent other work items from starting
+        execution.  This is useful for bound work items which are
+        expected to hog CPU cycles so that their execution is
+        regulated by the system scheduler.
+
+        Although CPU intensive work items don't contribute to the
+        concurrency level, start of their executions is still
+        regulated by the concurrency management and runnable
+        non-CPU-intensive work items can delay execution of CPU
+        intensive work items.
+
+        This flag is meaningless for unbound wq.
+
+  WQ_HIGHPRI | WQ_CPU_INTENSIVE
+
+        This combination makes the wq avoid interaction with
+        concurrency management completely and behave as a simple
+        per-CPU execution context provider.  Work items queued on a
+        highpri CPU-intensive wq start execution as soon as resources
+        are available and don't affect execution of other work items.
+
+@max_active:
+
+@max_active determines the maximum number of execution contexts per
+CPU which can be assigned to the work items of a wq.  For example,
+with @max_active of 16, at most 16 work items of the wq can be
+executing at the same time per CPU.
+
+Currently, for a bound wq, the maximum limit for @max_active is 512
+and the default value used when 0 is specified is 256.  For an unbound
+wq, the limit is higher of 512 and 4 * num_possible_cpus().  These
+values are chosen sufficiently high such that they are not the
+limiting factor while providing protection in runaway cases.
+
+The number of active work items of a wq is usually regulated by the
+users of the wq, more specifically, by how many work items the users
+may queue at the same time.  Unless there is a specific need for
+throttling the number of active work items, specifying '0' is
+recommended.
+
+Some users depend on the strict execution ordering of ST wq.  The
+combination of @max_active of 1 and WQ_UNBOUND is used to achieve this
+behavior.  Work items on such wq are always queued to the unbound gcwq
+and only one work item can be active at any given time thus achieving
+the same ordering property as ST wq.
+
+
+5. Example Execution Scenarios
+
+The following example execution scenarios try to illustrate how cmwq
+behave under different configurations.
+
+ Work items w0, w1, w2 are queued to a bound wq q0 on the same CPU.
+ w0 burns CPU for 5ms then sleeps for 10ms then burns CPU for 5ms
+ again before finishing.  w1 and w2 burn CPU for 5ms then sleep for
+ 10ms.
+
+Ignoring all other tasks, works and processing overhead, and assuming
+simple FIFO scheduling, the following is one highly simplified version
+of possible sequences of events with the original wq.
+
+ TIME IN MSECS  EVENT
+ 0              w0 starts and burns CPU
+ 5              w0 sleeps
+ 15             w0 wakes up and burns CPU
+ 20             w0 finishes
+ 20             w1 starts and burns CPU
+ 25             w1 sleeps
+ 35             w1 wakes up and finishes
+ 35             w2 starts and burns CPU
+ 40             w2 sleeps
+ 50             w2 wakes up and finishes
+
+And with cmwq with @max_active >= 3,
+
+ TIME IN MSECS  EVENT
+ 0              w0 starts and burns CPU
+ 5              w0 sleeps
+ 5              w1 starts and burns CPU
+ 10             w1 sleeps
+ 10             w2 starts and burns CPU
+ 15             w2 sleeps
+ 15             w0 wakes up and burns CPU
+ 20             w0 finishes
+ 20             w1 wakes up and finishes
+ 25             w2 wakes up and finishes
+
+If @max_active == 2,
+
+ TIME IN MSECS  EVENT
+ 0              w0 starts and burns CPU
+ 5              w0 sleeps
+ 5              w1 starts and burns CPU
+ 10             w1 sleeps
+ 15             w0 wakes up and burns CPU
+ 20             w0 finishes
+ 20             w1 wakes up and finishes
+ 20             w2 starts and burns CPU
+ 25             w2 sleeps
+ 35             w2 wakes up and finishes
+
+Now, let's assume w1 and w2 are queued to a different wq q1 which has
+WQ_HIGHPRI set,
+
+ TIME IN MSECS  EVENT
+ 0              w1 and w2 start and burn CPU
+ 5              w1 sleeps
+ 10             w2 sleeps
+ 10             w0 starts and burns CPU
+ 15             w0 sleeps
+ 15             w1 wakes up and finishes
+ 20             w2 wakes up and finishes
+ 25             w0 wakes up and burns CPU
+ 30             w0 finishes
+
+If q1 has WQ_CPU_INTENSIVE set,
+
+ TIME IN MSECS  EVENT
+ 0              w0 starts and burns CPU
+ 5              w0 sleeps
+ 5              w1 and w2 start and burn CPU
+ 10             w1 sleeps
+ 15             w2 sleeps
+ 15             w0 wakes up and burns CPU
+ 20             w0 finishes
+ 20             w1 wakes up and finishes
+ 25             w2 wakes up and finishes
+
+
+6. Guidelines
+
+* Do not forget to use WQ_MEM_RECLAIM if a wq may process work items
+  which are used during memory reclaim.  Each wq with WQ_MEM_RECLAIM
+  set has an execution context reserved for it.  If there is
+  dependency among multiple work items used during memory reclaim,
+  they should be queued to separate wq each with WQ_MEM_RECLAIM.
+
+* Unless strict ordering is required, there is no need to use ST wq.
+
+* Unless there is a specific need, using 0 for @max_active is
+  recommended.  In most use cases, concurrency level usually stays
+  well under the default limit.
+
+* A wq serves as a domain for forward progress guarantee
+  (WQ_MEM_RECLAIM, flush and work item attributes.  Work items which
+  are not involved in memory reclaim and don't need to be flushed as a
+  part of a group of work items, and don't require any special
+  attribute, can use one of the system wq.  There is no difference in
+  execution characteristics between using a dedicated wq and a system
+  wq.
+
+* Unless work items are expected to consume a huge amount of CPU
+  cycles, using a bound wq is usually beneficial due to the increased
+  level of locality in wq operations and work item execution.
diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d51fb9..a01eec5d1d0 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
@@ -18,9 +18,9 @@ specialized stacks contain no useful data.  The main CPU stacks are:
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
   kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
-  this gives more room for kernel interrupt processing without having
-  to increase the size of every per thread stack.
+  the split thread and interrupt stacks on i386, this gives more room
+  for kernel interrupt processing without having to increase the size
+  of every per thread stack.
 
   The interrupt stack is also used when processing a softirq.