22 files changed, 1639 insertions, 228 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator
index 3731f6f29bcb..873ef1fc1569 100644
--- a/Documentation/ABI/testing/sysfs-class-regulator
+++ b/Documentation/ABI/testing/sysfs-class-regulator
@@ -3,8 +3,9 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
-                state. This holds the regulator output state.
+                Some regulator directories will contain a field called
+                state. This reports the regulator enable status, for
+                regulators which can report that value.
 
                 This will be one of the following strings:
 
@@ -18,7 +19,8 @@ Description:
                 'disabled' means the regulator output is OFF and is not
                 supplying power to the system..
 
-                'unknown' means software cannot determine the state.
+                'unknown' means software cannot determine the state, or
+                the reported state is invalid.
 
                 NOTE: this field can be used in conjunction with microvolts
                 and microamps to determine regulator output levels.
@@ -53,9 +55,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 microvolts. This holds the regulator output voltage setting
-                measured in microvolts (i.e. E-6 Volts).
+                measured in microvolts (i.e. E-6 Volts), for regulators
+                which can report that voltage.
 
                 NOTE: This value should not be used to determine the regulator
                 output voltage level as this value is the same regardless of
@@ -67,9 +70,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 microamps. This holds the regulator output current limit
-                setting measured in microamps (i.e. E-6 Amps).
+                setting measured in microamps (i.e. E-6 Amps), for regulators
+                which can report that current.
 
                 NOTE: This value should not be used to determine the regulator
                 output current level as this value is the same regardless of
@@ -81,8 +85,9 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
-                opmode. This holds the regulator operating mode setting.
+                Some regulator directories will contain a field called
+                opmode. This holds the current regulator operating mode,
+                for regulators which can report it.
 
                 The opmode value can be one of the following strings:
 
@@ -92,7 +97,7 @@ Description:
                 'standby'
                 'unknown'
 
-                The modes are described in include/linux/regulator/regulator.h
+                The modes are described in include/linux/regulator/consumer.h
 
                 NOTE: This value should not be used to determine the regulator
                 output operating mode as this value is the same regardless of
@@ -104,9 +109,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 min_microvolts. This holds the minimum safe working regulator
-                output voltage setting for this domain measured in microvolts.
+                output voltage setting for this domain measured in microvolts,
+                for regulators which support voltage constraints.
 
                 NOTE: this will return the string 'constraint not defined' if
                 the power domain has no min microvolts constraint defined by
@@ -118,9 +124,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 max_microvolts. This holds the maximum safe working regulator
-                output voltage setting for this domain measured in microvolts.
+                output voltage setting for this domain measured in microvolts,
+                for regulators which support voltage constraints.
 
                 NOTE: this will return the string 'constraint not defined' if
                 the power domain has no max microvolts constraint defined by
@@ -132,10 +139,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 min_microamps. This holds the minimum safe working regulator
                 output current limit setting for this domain measured in
-                microamps.
+                microamps, for regulators which support current constraints.
 
                 NOTE: this will return the string 'constraint not defined' if
                 the power domain has no min microamps constraint defined by
@@ -147,10 +154,10 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 max_microamps. This holds the maximum safe working regulator
                 output current limit setting for this domain measured in
-                microamps.
+                microamps, for regulators which support current constraints.
 
                 NOTE: this will return the string 'constraint not defined' if
                 the power domain has no max microamps constraint defined by
@@ -185,7 +192,7 @@ Date:		April 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 requested_microamps. This holds the total requested load
                 current in microamps for this regulator from all its consumer
                 devices.
@@ -204,125 +211,102 @@ Date:		May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_mem_microvolts. This holds the regulator output
                 voltage setting for this domain measured in microvolts when
-                the system is suspended to memory.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to memory voltage defined by
-                platform code.
+                the system is suspended to memory, for voltage regulators
+                implementing suspend voltage configuration constraints.
 
 What:           /sys/class/regulator/.../suspend_disk_microvolts
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_disk_microvolts. This holds the regulator output
                 voltage setting for this domain measured in microvolts when
-                the system is suspended to disk.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to disk voltage defined by
-                platform code.
+                the system is suspended to disk, for voltage regulators
+                implementing suspend voltage configuration constraints.
 
 What:           /sys/class/regulator/.../suspend_standby_microvolts
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_standby_microvolts. This holds the regulator output
                 voltage setting for this domain measured in microvolts when
-                the system is suspended to standby.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to standby voltage defined by
-                platform code.
+                the system is suspended to standby, for voltage regulators
+                implementing suspend voltage configuration constraints.
 
 What:           /sys/class/regulator/.../suspend_mem_mode
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_mem_mode. This holds the regulator operating mode
                 setting for this domain when the system is suspended to
-                memory.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to memory mode defined by
-                platform code.
+                memory, for regulators implementing suspend mode
+                configuration constraints.
 
 What:           /sys/class/regulator/.../suspend_disk_mode
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_disk_mode. This holds the regulator operating mode
-                setting for this domain when the system is suspended to disk.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to disk mode defined by
-                platform code.
+                setting for this domain when the system is suspended to disk,
+                for regulators implementing suspend mode configuration
+                constraints.
 
 What:           /sys/class/regulator/.../suspend_standby_mode
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_standby_mode. This holds the regulator operating mode
                 setting for this domain when the system is suspended to
-                standby.
-
-                NOTE: this will return the string 'not defined' if
-                the power domain has no suspend to standby mode defined by
-                platform code.
+                standby, for regulators implementing suspend mode
+                configuration constraints.
 
 What:           /sys/class/regulator/.../suspend_mem_state
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_mem_state. This holds the regulator operating state
-                when suspended to memory.
-
-                This will be one of the following strings:
+                when suspended to memory, for regulators implementing suspend
+                configuration constraints.
 
-                'enabled'
-                'disabled'
-                'not defined'
+                This will be one of the same strings reported by
+                the "state" attribute.
 
 What:           /sys/class/regulator/.../suspend_disk_state
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_disk_state. This holds the regulator operating state
-                when suspended to disk.
-
-                This will be one of the following strings:
+                when suspended to disk, for regulators implementing
+                suspend configuration constraints.
 
-                'enabled'
-                'disabled'
-                'not defined'
+                This will be one of the same strings reported by
+                the "state" attribute.
 
 What:           /sys/class/regulator/.../suspend_standby_state
 Date:           May 2008
 KernelVersion:  2.6.26
 Contact:        Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
-                Each regulator directory will contain a field called
+                Some regulator directories will contain a field called
                 suspend_standby_state. This holds the regulator operating
-                state when suspended to standby.
-
-                This will be one of the following strings:
+                state when suspended to standby, for regulators implementing
+                suspend configuration constraints.
 
-                'enabled'
-                'disabled'
-                'not defined'
+                This will be one of the same strings reported by
+                the "state" attribute.
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index 0a08126d3094..dc3154e49279 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -12,7 +12,7 @@ DOCBOOKS := z8530book.xml mcabook.xml \
             kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
             gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
             genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
-            mac80211.xml debugobjects.xml sh.xml
+            mac80211.xml debugobjects.xml sh.xml regulator.xml
 
 ###
 # The build process is as follows (targets):
diff --git a/Documentation/DocBook/regulator.tmpl b/Documentation/DocBook/regulator.tmpl
new file mode 100644
index 000000000000..53f4f8d3b810
--- /dev/null
+++ b/Documentation/DocBook/regulator.tmpl
@@ -0,0 +1,304 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+        "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="regulator-api">
+ <bookinfo>
+  <title>Voltage and current regulator API</title>
+
+  <authorgroup>
+   <author>
+    <firstname>Liam</firstname>
+    <surname>Girdwood</surname>
+    <affiliation>
+     <address>
+      <email>lrg@slimlogic.co.uk</email>
+     </address>
+    </affiliation>
+   </author>
+   <author>
+    <firstname>Mark</firstname>
+    <surname>Brown</surname>
+    <affiliation>
+     <orgname>Wolfson Microelectronics</orgname>
+     <address>
+      <email>broonie@opensource.wolfsonmicro.com</email>
+     </address>
+    </affiliation>
+   </author>
+  </authorgroup>
+
+  <copyright>
+   <year>2007-2008</year>
+   <holder>Wolfson Microelectronics</holder>
+  </copyright>
+  <copyright>
+   <year>2008</year>
+   <holder>Liam Girdwood</holder>
+  </copyright>
+
+  <legalnotice>
+   <para>
+     This documentation is free software; you can redistribute
+     it and/or modify it under the terms of the GNU General Public
+     License version 2 as published by the Free Software Foundation.
+   </para>
+
+   <para>
+     This program is distributed in the hope that it will be
+     useful, but WITHOUT ANY WARRANTY; without even the implied
+     warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+     See the GNU General Public License for more details.
+   </para>
+
+   <para>
+     You should have received a copy of the GNU General Public
+     License along with this program; if not, write to the Free
+     Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+     MA 02111-1307 USA
+   </para>
+
+   <para>
+     For more details see the file COPYING in the source
+     distribution of Linux.
+   </para>
+  </legalnotice>
+ </bookinfo>
+
+<toc></toc>
+
+  <chapter id="intro">
+    <title>Introduction</title>
+    <para>
+        This framework is designed to provide a standard kernel
+        interface to control voltage and current regulators.
+    </para>
+    <para>
+        The intention is to allow systems to dynamically control
+        regulator power output in order to save power and prolong
+        battery life.  This applies to both voltage regulators (where
+        voltage output is controllable) and current sinks (where current
+        limit is controllable).
+    </para>
+    <para>
+        Note that additional (and currently more complete) documentation
+        is available in the Linux kernel source under
+        <filename>Documentation/power/regulator</filename>.
+    </para>
+
+    <sect1 id="glossary">
+       <title>Glossary</title>
+       <para>
+        The regulator API uses a number of terms which may not be
+        familiar:
+       </para>
+       <glossary>
+
+         <glossentry>
+           <glossterm>Regulator</glossterm>
+           <glossdef>
+             <para>
+        Electronic device that supplies power to other devices.  Most
+        regulators can enable and disable their output and some can also
+        control their output voltage or current.
+             </para>
+           </glossdef>
+         </glossentry>
+
+         <glossentry>
+           <glossterm>Consumer</glossterm>
+           <glossdef>
+             <para>
+        Electronic device which consumes power provided by a regulator.
+        These may either be static, requiring only a fixed supply, or
+        dynamic, requiring active management of the regulator at
+        runtime.
+             </para>
+           </glossdef>
+         </glossentry>
+
+         <glossentry>
+           <glossterm>Power Domain</glossterm>
+           <glossdef>
+             <para>
+        The electronic circuit supplied by a given regulator, including
+        the regulator and all consumer devices.  The configuration of
+        the regulator is shared between all the components in the
+        circuit.
+             </para>
+           </glossdef>
+         </glossentry>
+
+         <glossentry>
+           <glossterm>Power Management Integrated Circuit</glossterm>
+           <acronym>PMIC</acronym>
+           <glossdef>
+             <para>
+        An IC which contains numerous regulators and often also other
+        subsystems.  In an embedded system the primary PMIC is often
+        equivalent to a combination of the PSU and southbridge in a
+        desktop system.
+             </para>
+           </glossdef>
+         </glossentry>
+        </glossary>
+     </sect1>
+  </chapter>
+
+  <chapter id="consumer">
+     <title>Consumer driver interface</title>
+     <para>
+       This offers a similar API to the kernel clock framework.
+       Consumer drivers use <link
+       linkend='API-regulator-get'>get</link> and <link
+       linkend='API-regulator-put'>put</link> operations to acquire and
+       release regulators.  Functions are
+       provided to <link linkend='API-regulator-enable'>enable</link>
+       and <link linkend='API-regulator-disable'>disable</link> the
+       reguator and to get and set the runtime parameters of the
+       regulator.
+     </para>
+     <para>
+       When requesting regulators consumers use symbolic names for their
+       supplies, such as "Vcc", which are mapped into actual regulator
+       devices by the machine interface.
+     </para>
+     <para>
+        A stub version of this API is provided when the regulator
+        framework is not in use in order to minimise the need to use
+        ifdefs.
+     </para>
+
+     <sect1 id="consumer-enable">
+       <title>Enabling and disabling</title>
+       <para>
+         The regulator API provides reference counted enabling and
+         disabling of regulators. Consumer devices use the <function><link
+         linkend='API-regulator-enable'>regulator_enable</link></function>
+         and <function><link
+         linkend='API-regulator-disable'>regulator_disable</link>
+         </function> functions to enable and disable regulators.  Calls
+         to the two functions must be balanced.
+       </para>
+       <para>
+         Note that since multiple consumers may be using a regulator and
+         machine constraints may not allow the regulator to be disabled
+         there is no guarantee that calling
+         <function>regulator_disable</function> will actually cause the
+         supply provided by the regulator to be disabled. Consumer
+         drivers should assume that the regulator may be enabled at all
+         times.
+       </para>
+     </sect1>
+
+     <sect1 id="consumer-config">
+       <title>Configuration</title>
+       <para>
+         Some consumer devices may need to be able to dynamically
+         configure their supplies.  For example, MMC drivers may need to
+         select the correct operating voltage for their cards.  This may
+         be done while the regulator is enabled or disabled.
+       </para>
+       <para>
+         The <function><link
+         linkend='API-regulator-set-voltage'>regulator_set_voltage</link>
+         </function> and <function><link
+         linkend='API-regulator-set-current-limit'
+         >regulator_set_current_limit</link>
+         </function> functions provide the primary interface for this.
+         Both take ranges of voltages and currents, supporting drivers
+         that do not require a specific value (eg, CPU frequency scaling
+         normally permits the CPU to use a wider range of supply
+         voltages at lower frequencies but does not require that the
+         supply voltage be lowered).  Where an exact value is required
+         both minimum and maximum values should be identical.
+       </para>
+     </sect1>
+
+     <sect1 id="consumer-callback">
+       <title>Callbacks</title>
+       <para>
+          Callbacks may also be <link
+          linkend='API-regulator-register-notifier'>registered</link>
+          for events such as regulation failures.
+       </para>
+     </sect1>
+   </chapter>
+
+   <chapter id="driver">
+     <title>Regulator driver interface</title>
+     <para>
+       Drivers for regulator chips <link
+       linkend='API-regulator-register'>register</link> the regulators
+       with the regulator core, providing operations structures to the
+       core.  A <link
+       linkend='API-regulator-notifier-call-chain'>notifier</link> interface
+       allows error conditions to be reported to the core.
+     </para>
+     <para>
+       Registration should be triggered by explicit setup done by the
+       platform, supplying a <link
+       linkend='API-struct-regulator-init-data'>struct
+       regulator_init_data</link> for the regulator containing
+       <link linkend='machine-constraint'>constraint</link> and
+       <link linkend='machine-supply'>supply</link> information.
+     </para>
+   </chapter>
+
+   <chapter id="machine">
+     <title>Machine interface</title>
+     <para>
+       This interface provides a way to define how regulators are
+       connected to consumers on a given system and what the valid
+       operating parameters are for the system.
+     </para>
+
+     <sect1 id="machine-supply">
+       <title>Supplies</title>
+       <para>
+         Regulator supplies are specified using <link
+         linkend='API-struct-regulator-consumer-supply'>struct
+         regulator_consumer_supply</link>.  This is done at
+         <link linkend='driver'>driver registration
+         time</link> as part of the machine constraints.
+       </para>
+     </sect1>
+
+     <sect1 id="machine-constraint">
+       <title>Constraints</title>
+       <para>
+         As well as definining the connections the machine interface
+         also provides constraints definining the operations that
+         clients are allowed to perform and the parameters that may be
+         set.  This is required since generally regulator devices will
+         offer more flexibility than it is safe to use on a given
+         system, for example supporting higher supply voltages than the
+         consumers are rated for.
+       </para>
+       <para>
+         This is done at <link linkend='driver'>driver
+         registration time</link> by providing a <link
+         linkend='API-struct-regulation-constraints'>struct
+         regulation_constraints</link>.
+       </para>
+       <para>
+         The constraints may also specify an initial configuration for the
+         regulator in the constraints, which is particularly useful for
+         use with static consumers.
+       </para>
+     </sect1>
+  </chapter>
+
+  <chapter id="api">
+    <title>API reference</title>
+    <para>
+      Due to limitations of the kernel documentation framework and the
+      existing layout of the source code the entire regulator API is
+      documented here.
+    </para>
+!Iinclude/linux/regulator/consumer.h
+!Iinclude/linux/regulator/machine.h
+!Iinclude/linux/regulator/driver.h
+!Edrivers/regulator/core.c
+  </chapter>
+</book>
diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX
index 7dc0695a8f90..9bb62f7b89c3 100644
--- a/Documentation/RCU/00-INDEX
+++ b/Documentation/RCU/00-INDEX
@@ -12,6 +12,8 @@ rcuref.txt
         - Reference-count design for elements of lists/arrays protected by RCU
 rcu.txt
         - RCU Concepts
+rcubarrier.txt
+        - Unloading modules that use RCU callbacks
 RTFP.txt
         - List of RCU papers (bibliography) going back to 1980.
 torture.txt
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
new file mode 100644
index 000000000000..909602d409bb
--- /dev/null
+++ b/Documentation/RCU/rcubarrier.txt
@@ -0,0 +1,304 @@
+RCU and Unloadable Modules
+
+[Originally published in LWN Jan. 14, 2007: http://lwn.net/Articles/217484/]
+
+RCU (read-copy update) is a synchronization mechanism that can be thought
+of as a replacement for read-writer locking (among other things), but with
+very low-overhead readers that are immune to deadlock, priority inversion,
+and unbounded latency. RCU read-side critical sections are delimited
+by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT
+kernels, generate no code whatsoever.
+
+This means that RCU writers are unaware of the presence of concurrent
+readers, so that RCU updates to shared data must be undertaken quite
+carefully, leaving an old version of the data structure in place until all
+pre-existing readers have finished. These old versions are needed because
+such readers might hold a reference to them. RCU updates can therefore be
+rather expensive, and RCU is thus best suited for read-mostly situations.
+
+How can an RCU writer possibly determine when all readers are finished,
+given that readers might well leave absolutely no trace of their
+presence? There is a synchronize_rcu() primitive that blocks until all
+pre-existing readers have completed. An updater wishing to delete an
+element p from a linked list might do the following, while holding an
+appropriate lock, of course:
+
+        list_del_rcu(p);
+        synchronize_rcu();
+        kfree(p);
+
+But the above code cannot be used in IRQ context -- the call_rcu()
+primitive must be used instead. This primitive takes a pointer to an
+rcu_head struct placed within the RCU-protected data structure and
+another pointer to a function that may be invoked later to free that
+structure. Code to delete an element p from the linked list from IRQ
+context might then be as follows:
+
+        list_del_rcu(p);
+        call_rcu(&p->rcu, p_callback);
+
+Since call_rcu() never blocks, this code can safely be used from within
+IRQ context. The function p_callback() might be defined as follows:
+
+        static void p_callback(struct rcu_head *rp)
+        {
+                struct pstruct *p = container_of(rp, struct pstruct, rcu);
+
+                kfree(p);
+        }
+
+
+Unloading Modules That Use call_rcu()
+
+But what if p_callback is defined in an unloadable module?
+
+If we unload the module while some RCU callbacks are pending,
+the CPUs executing these callbacks are going to be severely
+disappointed when they are later invoked, as fancifully depicted at
+http://lwn.net/images/ns/kernel/rcu-drop.jpg.
+
+We could try placing a synchronize_rcu() in the module-exit code path,
+but this is not sufficient. Although synchronize_rcu() does wait for a
+grace period to elapse, it does not wait for the callbacks to complete.
+
+One might be tempted to try several back-to-back synchronize_rcu()
+calls, but this is still not guaranteed to work. If there is a very
+heavy RCU-callback load, then some of the callbacks might be deferred
+in order to allow other processing to proceed. Such deferral is required
+in realtime kernels in order to avoid excessive scheduling latencies.
+
+
+rcu_barrier()
+
+We instead need the rcu_barrier() primitive. This primitive is similar
+to synchronize_rcu(), but instead of waiting solely for a grace
+period to elapse, it also waits for all outstanding RCU callbacks to
+complete. Pseudo-code using rcu_barrier() is as follows:
+
+   1. Prevent any new RCU callbacks from being posted.
+   2. Execute rcu_barrier().
+   3. Allow the module to be unloaded.
+
+Quick Quiz #1: Why is there no srcu_barrier()?
+
+The rcutorture module makes use of rcu_barrier in its exit function
+as follows:
+
+ 1 static void
+ 2 rcu_torture_cleanup(void)
+ 3 {
+ 4   int i;
+ 5
+ 6   fullstop = 1;
+ 7   if (shuffler_task != NULL) {
+ 8     VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task");
+ 9     kthread_stop(shuffler_task);
+10   }
+11   shuffler_task = NULL;
+12
+13   if (writer_task != NULL) {
+14     VERBOSE_PRINTK_STRING("Stopping rcu_torture_writer task");
+15     kthread_stop(writer_task);
+16   }
+17   writer_task = NULL;
+18
+19   if (reader_tasks != NULL) {
+20     for (i = 0; i < nrealreaders; i++) {
+21       if (reader_tasks[i] != NULL) {
+22         VERBOSE_PRINTK_STRING(
+23           "Stopping rcu_torture_reader task");
+24         kthread_stop(reader_tasks[i]);
+25       }
+26       reader_tasks[i] = NULL;
+27     }
+28     kfree(reader_tasks);
+29     reader_tasks = NULL;
+30   }
+31   rcu_torture_current = NULL;
+32
+33   if (fakewriter_tasks != NULL) {
+34     for (i = 0; i < nfakewriters; i++) {
+35       if (fakewriter_tasks[i] != NULL) {
+36         VERBOSE_PRINTK_STRING(
+37           "Stopping rcu_torture_fakewriter task");
+38         kthread_stop(fakewriter_tasks[i]);
+39       }
+40       fakewriter_tasks[i] = NULL;
+41     }
+42     kfree(fakewriter_tasks);
+43     fakewriter_tasks = NULL;
+44   }
+45
+46   if (stats_task != NULL) {
+47     VERBOSE_PRINTK_STRING("Stopping rcu_torture_stats task");
+48     kthread_stop(stats_task);
+49   }
+50   stats_task = NULL;
+51
+52   /* Wait for all RCU callbacks to fire. */
+53   rcu_barrier();
+54
+55   rcu_torture_stats_print(); /* -After- the stats thread is stopped! */
+56
+57   if (cur_ops->cleanup != NULL)
+58     cur_ops->cleanup();
+59   if (atomic_read(&n_rcu_torture_error))
+60     rcu_torture_print_module_parms("End of test: FAILURE");
+61   else
+62     rcu_torture_print_module_parms("End of test: SUCCESS");
+63 }
+
+Line 6 sets a global variable that prevents any RCU callbacks from
+re-posting themselves. This will not be necessary in most cases, since
+RCU callbacks rarely include calls to call_rcu(). However, the rcutorture
+module is an exception to this rule, and therefore needs to set this
+global variable.
+
+Lines 7-50 stop all the kernel tasks associated with the rcutorture
+module. Therefore, once execution reaches line 53, no more rcutorture
+RCU callbacks will be posted. The rcu_barrier() call on line 53 waits
+for any pre-existing callbacks to complete.
+
+Then lines 55-62 print status and do operation-specific cleanup, and
+then return, permitting the module-unload operation to be completed.
+
+Quick Quiz #2: Is there any other situation where rcu_barrier() might
+        be required?
+
+Your module might have additional complications. For example, if your
+module invokes call_rcu() from timers, you will need to first cancel all
+the timers, and only then invoke rcu_barrier() to wait for any remaining
+RCU callbacks to complete.
+
+
+Implementing rcu_barrier()
+
+Dipankar Sarma's implementation of rcu_barrier() makes use of the fact
+that RCU callbacks are never reordered once queued on one of the per-CPU
+queues. His implementation queues an RCU callback on each of the per-CPU
+callback queues, and then waits until they have all started executing, at
+which point, all earlier RCU callbacks are guaranteed to have completed.
+
+The original code for rcu_barrier() was as follows:
+
+ 1 void rcu_barrier(void)
+ 2 {
+ 3   BUG_ON(in_interrupt());
+ 4   /* Take cpucontrol mutex to protect against CPU hotplug */
+ 5   mutex_lock(&rcu_barrier_mutex);
+ 6   init_completion(&rcu_barrier_completion);
+ 7   atomic_set(&rcu_barrier_cpu_count, 0);
+ 8   on_each_cpu(rcu_barrier_func, NULL, 0, 1);
+ 9   wait_for_completion(&rcu_barrier_completion);
+10   mutex_unlock(&rcu_barrier_mutex);
+11 }
+
+Line 3 verifies that the caller is in process context, and lines 5 and 10
+use rcu_barrier_mutex to ensure that only one rcu_barrier() is using the
+global completion and counters at a time, which are initialized on lines
+6 and 7. Line 8 causes each CPU to invoke rcu_barrier_func(), which is
+shown below. Note that the final "1" in on_each_cpu()'s argument list
+ensures that all the calls to rcu_barrier_func() will have completed
+before on_each_cpu() returns. Line 9 then waits for the completion.
+
+This code was rewritten in 2008 to support rcu_barrier_bh() and
+rcu_barrier_sched() in addition to the original rcu_barrier().
+
+The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
+to post an RCU callback, as follows:
+
+ 1 static void rcu_barrier_func(void *notused)
+ 2 {
+ 3 int cpu = smp_processor_id();
+ 4 struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+ 5 struct rcu_head *head;
+ 6
+ 7 head = &rdp->barrier;
+ 8 atomic_inc(&rcu_barrier_cpu_count);
+ 9 call_rcu(head, rcu_barrier_callback);
+10 }
+
+Lines 3 and 4 locate RCU's internal per-CPU rcu_data structure,
+which contains the struct rcu_head that needed for the later call to
+call_rcu(). Line 7 picks up a pointer to this struct rcu_head, and line
+8 increments a global counter. This counter will later be decremented
+by the callback. Line 9 then registers the rcu_barrier_callback() on
+the current CPU's queue.
+
+The rcu_barrier_callback() function simply atomically decrements the
+rcu_barrier_cpu_count variable and finalizes the completion when it
+reaches zero, as follows:
+
+ 1 static void rcu_barrier_callback(struct rcu_head *notused)
+ 2 {
+ 3 if (atomic_dec_and_test(&rcu_barrier_cpu_count))
+ 4 complete(&rcu_barrier_completion);
+ 5 }
+
+Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+        immediately (thus incrementing rcu_barrier_cpu_count to the
+        value one), but the other CPU's rcu_barrier_func() invocations
+        are delayed for a full grace period? Couldn't this result in
+        rcu_barrier() returning prematurely?
+
+
+rcu_barrier() Summary
+
+The rcu_barrier() primitive has seen relatively little use, since most
+code using RCU is in the core kernel rather than in modules. However, if
+you are using RCU from an unloadable module, you need to use rcu_barrier()
+so that your module may be safely unloaded.
+
+
+Answers to Quick Quizzes
+
+Quick Quiz #1: Why is there no srcu_barrier()?
+
+Answer: Since there is no call_srcu(), there can be no outstanding SRCU
+        callbacks. Therefore, there is no need to wait for them.
+
+Quick Quiz #2: Is there any other situation where rcu_barrier() might
+        be required?
+
+Answer: Interestingly enough, rcu_barrier() was not originally
+        implemented for module unloading. Nikita Danilov was using
+        RCU in a filesystem, which resulted in a similar situation at
+        filesystem-unmount time. Dipankar Sarma coded up rcu_barrier()
+        in response, so that Nikita could invoke it during the
+        filesystem-unmount process.
+
+        Much later, yours truly hit the RCU module-unload problem when
+        implementing rcutorture, and found that rcu_barrier() solves
+        this problem as well.
+
+Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes
+        immediately (thus incrementing rcu_barrier_cpu_count to the
+        value one), but the other CPU's rcu_barrier_func() invocations
+        are delayed for a full grace period? Couldn't this result in
+        rcu_barrier() returning prematurely?
+
+Answer: This cannot happen. The reason is that on_each_cpu() has its last
+        argument, the wait flag, set to "1". This flag is passed through
+        to smp_call_function() and further to smp_call_function_on_cpu(),
+        causing this latter to spin until the cross-CPU invocation of
+        rcu_barrier_func() has completed. This by itself would prevent
+        a grace period from completing on non-CONFIG_PREEMPT kernels,
+        since each CPU must undergo a context switch (or other quiescent
+        state) before the grace period can complete. However, this is
+        of no use in CONFIG_PREEMPT kernels.
+
+        Therefore, on_each_cpu() disables preemption across its call
+        to smp_call_function() and also across the local call to
+        rcu_barrier_func(). This prevents the local CPU from context
+        switching, again preventing grace periods from completing. This
+        means that all CPUs have executed rcu_barrier_func() before
+        the first rcu_barrier_callback() can possibly execute, in turn
+        preventing rcu_barrier_cpu_count from prematurely reaching zero.
+
+        Currently, -rt implementations of RCU keep but a single global
+        queue for RCU callbacks, and thus do not suffer from this
+        problem. However, when the -rt RCU eventually does have per-CPU
+        callback queues, things will have to change. One simple change
+        is to add an rcu_read_lock() before line 8 of rcu_barrier()
+        and an rcu_read_unlock() after line 8 of this same function. If
+        you can think of a better change, please let me know!
diff --git a/Documentation/bad_memory.txt b/Documentation/bad_memory.txt
new file mode 100644
index 000000000000..df8416213202
--- /dev/null
+++ b/Documentation/bad_memory.txt
@@ -0,0 +1,45 @@
+March 2008
+Jan-Simon Moeller, dl9pf@gmx.de
+
+
+How to deal with bad memory e.g. reported by memtest86+ ?
+#########################################################
+
+There are three possibilities I know of:
+
+1) Reinsert/swap the memory modules
+
+2) Buy new modules (best!) or try to exchange the memory
+   if you have spare-parts
+
+3) Use BadRAM or memmap
+
+This Howto is about number 3) .
+
+
+BadRAM
+######
+BadRAM is the actively developed and available as kernel-patch
+here:  http://rick.vanrein.org/linux/badram/
+
+For more details see the BadRAM documentation.
+
+memmap
+######
+
+memmap is already in the kernel and usable as kernel-parameter at
+boot-time.  Its syntax is slightly strange and you may need to
+calculate the values by yourself!
+
+Syntax to exclude a memory area (see kernel-parameters.txt for details):
+memmap=<size>$<address>
+
+Example: memtest86+ reported here errors at address 0x18691458, 0x18698424 and
+         some others. All had 0x1869xxxx in common, so I chose a pattern of
+         0x18690000,0xffff0000.
+
+With the numbers of the example above:
+memmap=64K$0x18690000
+ or
+memmap=0x10000$0x18690000
+
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index d9014aa0eb68..e33ee74eee77 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -227,7 +227,6 @@ Each cgroup is represented by a directory in the cgroup file system
 containing the following files describing that cgroup:
 
  - tasks: list of tasks (by pid) attached to that cgroup
- - releasable flag: cgroup currently removeable?
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -360,7 +359,7 @@ Now you want to do something with this cgroup.
 
 In this directory you can find several files:
 # ls
-notify_on_release releasable tasks
+notify_on_release tasks
 (plus whatever files added by the attached subsystems)
 
 Now attach your shell to this cgroup:
@@ -479,7 +478,6 @@ newly-created cgroup if an error occurs after this subsystem's
 create() method has been called for the new cgroup).
 
 void pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
-(cgroup_mutex held by caller)
 
 Called before checking the reference count on each subsystem. This may
 be useful for subsystems which have some extra references even if
@@ -498,6 +496,7 @@ remain valid while the caller holds cgroup_mutex.
 
 void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
             struct cgroup *old_cgrp, struct task_struct *task)
+(cgroup_mutex held by caller)
 
 Called after the task has been attached to the cgroup, to allow any
 post-attachment activity that requires memory allocations or blocking.
@@ -511,6 +510,7 @@ void exit(struct cgroup_subsys *ss, struct task_struct *task)
 Called during task exit.
 
 int populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+(cgroup_mutex held by caller)
 
 Called after creation of a cgroup to allow a subsystem to populate
 the cgroup directory with file entries.  The subsystem should make
@@ -520,6 +520,7 @@ method can return an error code, the error code is currently not
 always handled well.
 
 void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp)
+(cgroup_mutex held by caller)
 
 Called at the end of cgroup_clone() to do any paramater
 initialization which might be required before a task could attach.  For
@@ -527,7 +528,7 @@ example in cpusets, no task may attach before 'cpus' and 'mems' are set
 up.
 
 void bind(struct cgroup_subsys *ss, struct cgroup *root)
-(cgroup_mutex held by caller)
+(cgroup_mutex and ss->hierarchy_mutex held by caller)
 
 Called when a cgroup subsystem is rebound to a different hierarchy
 and root cgroup. Currently this will only involve movement between
diff --git a/Documentation/controllers/memcg_test.txt b/Documentation/controllers/memcg_test.txt
new file mode 100644
index 000000000000..08d4d3ea0d79
--- /dev/null
+++ b/Documentation/controllers/memcg_test.txt
@@ -0,0 +1,342 @@
+Memory Resource Controller(Memcg)  Implementation Memo.
+Last Updated: 2008/12/15
+Base Kernel Version: based on 2.6.28-rc8-mm.
+
+Because VM is getting complex (one of reasons is memcg...), memcg's behavior
+is complex. This is a document for memcg's internal behavior.
+Please note that implementation details can be changed.
+
+(*) Topics on API should be in Documentation/controllers/memory.txt)
+
+0. How to record usage ?
+   2 objects are used.
+
+   page_cgroup ....an object per page.
+        Allocated at boot or memory hotplug. Freed at memory hot removal.
+
+   swap_cgroup ... an entry per swp_entry.
+        Allocated at swapon(). Freed at swapoff().
+
+   The page_cgroup has USED bit and double count against a page_cgroup never
+   occurs. swap_cgroup is used only when a charged page is swapped-out.
+
+1. Charge
+
+   a page/swp_entry may be charged (usage += PAGE_SIZE) at
+
+        mem_cgroup_newpage_charge()
+          Called at new page fault and Copy-On-Write.
+
+        mem_cgroup_try_charge_swapin()
+          Called at do_swap_page() (page fault on swap entry) and swapoff.
+          Followed by charge-commit-cancel protocol. (With swap accounting)
+          At commit, a charge recorded in swap_cgroup is removed.
+
+        mem_cgroup_cache_charge()
+          Called at add_to_page_cache()
+
+        mem_cgroup_cache_charge_swapin()
+          Called at shmem's swapin.
+
+        mem_cgroup_prepare_migration()
+          Called before migration. "extra" charge is done and followed by
+          charge-commit-cancel protocol.
+          At commit, charge against oldpage or newpage will be committed.
+
+2. Uncharge
+  a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
+
+        mem_cgroup_uncharge_page()
+          Called when an anonymous page is fully unmapped. I.e., mapcount goes
+          to 0. If the page is SwapCache, uncharge is delayed until
+          mem_cgroup_uncharge_swapcache().
+
+        mem_cgroup_uncharge_cache_page()
+          Called when a page-cache is deleted from radix-tree. If the page is
+          SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
+
+        mem_cgroup_uncharge_swapcache()
+          Called when SwapCache is removed from radix-tree. The charge itself
+          is moved to swap_cgroup. (If mem+swap controller is disabled, no
+          charge to swap occurs.)
+
+        mem_cgroup_uncharge_swap()
+          Called when swp_entry's refcnt goes down to 0. A charge against swap
+          disappears.
+
+        mem_cgroup_end_migration(old, new)
+        At success of migration old is uncharged (if necessary), a charge
+        to new page is committed. At failure, charge to old page is committed.
+
+3. charge-commit-cancel
+        In some case, we can't know this "charge" is valid or not at charging
+        (because of races).
+        To handle such case, there are charge-commit-cancel functions.
+                mem_cgroup_try_charge_XXX
+                mem_cgroup_commit_charge_XXX
+                mem_cgroup_cancel_charge_XXX
+        these are used in swap-in and migration.
+
+        At try_charge(), there are no flags to say "this page is charged".
+        at this point, usage += PAGE_SIZE.
+
+        At commit(), the function checks the page should be charged or not
+        and set flags or avoid charging.(usage -= PAGE_SIZE)
+
+        At cancel(), simply usage -= PAGE_SIZE.
+
+Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
+
+4. Anonymous
+        Anonymous page is newly allocated at
+                  - page fault into MAP_ANONYMOUS mapping.
+                  - Copy-On-Write.
+        It is charged right after it's allocated before doing any page table
+        related operations. Of course, it's uncharged when another page is used
+        for the fault address.
+
+        At freeing anonymous page (by exit() or munmap()), zap_pte() is called
+        and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
+        are done at page_remove_rmap() when page_mapcount() goes down to 0.
+
+        Another page freeing is by page-reclaim (vmscan.c) and anonymous
+        pages are swapped out. In this case, the page is marked as
+        PageSwapCache(). uncharge() routine doesn't uncharge the page marked
+        as SwapCache(). It's delayed until __delete_from_swap_cache().
+
+        4.1 Swap-in.
+        At swap-in, the page is taken from swap-cache. There are 2 cases.
+
+        (a) If the SwapCache is newly allocated and read, it has no charges.
+        (b) If the SwapCache has been mapped by processes, it has been
+            charged already.
+
+        This swap-in is one of the most complicated work. In do_swap_page(),
+        following events occur when pte is unchanged.
+
+        (1) the page (SwapCache) is looked up.
+        (2) lock_page()
+        (3) try_charge_swapin()
+        (4) reuse_swap_page() (may call delete_swap_cache())
+        (5) commit_charge_swapin()
+        (6) swap_free().
+
+        Considering following situation for example.
+
+        (A) The page has not been charged before (2) and reuse_swap_page()
+            doesn't call delete_from_swap_cache().
+        (B) The page has not been charged before (2) and reuse_swap_page()
+            calls delete_from_swap_cache().
+        (C) The page has been charged before (2) and reuse_swap_page() doesn't
+            call delete_from_swap_cache().
+        (D) The page has been charged before (2) and reuse_swap_page() calls
+            delete_from_swap_cache().
+
+            memory.usage/memsw.usage changes to this page/swp_entry will be
+         Case          (A)      (B)       (C)     (D)
+         Event
+       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
+          ===========================================
+          (3)        +1/+1    +1/+1     +1/+1   +1/+1
+          (4)          -       0/ 0       -     -1/ 0
+          (5)         0/-1     0/ 0     -1/-1    0/ 0
+          (6)          -       0/-1       -      0/-1
+          ===========================================
+       Result         1/ 1     1/ 1      1/ 1    1/ 1
+
+       In any cases, charges to this page should be 1/ 1.
+
+        4.2 Swap-out.
+        At swap-out, typical state transition is below.
+
+        (a) add to swap cache. (marked as SwapCache)
+            swp_entry's refcnt += 1.
+        (b) fully unmapped.
+            swp_entry's refcnt += # of ptes.
+        (c) write back to swap.
+        (d) delete from swap cache. (remove from SwapCache)
+            swp_entry's refcnt -= 1.
+
+
+        At (b), the page is marked as SwapCache and not uncharged.
+        At (d), the page is removed from SwapCache and a charge in page_cgroup
+        is moved to swap_cgroup.
+
+        Finally, at task exit,
+        (e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
+        Here, a charge in swap_cgroup disappears.
+
+5. Page Cache
+        Page Cache is charged at
+        - add_to_page_cache_locked().
+
+        uncharged at
+        - __remove_from_page_cache().
+
+        The logic is very clear. (About migration, see below)
+        Note: __remove_from_page_cache() is called by remove_from_page_cache()
+        and __remove_mapping().
+
+6. Shmem(tmpfs) Page Cache
+        Memcg's charge/uncharge have special handlers of shmem. The best way
+        to understand shmem's page state transition is to read mm/shmem.c.
+        But brief explanation of the behavior of memcg around shmem will be
+        helpful to understand the logic.
+
+        Shmem's page (just leaf page, not direct/indirect block) can be on
+                - radix-tree of shmem's inode.
+                - SwapCache.
+                - Both on radix-tree and SwapCache. This happens at swap-in
+                  and swap-out,
+
+        It's charged when...
+        - A new page is added to shmem's radix-tree.
+        - A swp page is read. (move a charge from swap_cgroup to page_cgroup)
+        It's uncharged when
+        - A page is removed from radix-tree and not SwapCache.
+        - When SwapCache is removed, a charge is moved to swap_cgroup.
+        - When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
+          disappears.
+
+7. Page Migration
+        One of the most complicated functions is page-migration-handler.
+        Memcg has 2 routines. Assume that we are migrating a page's contents
+        from OLDPAGE to NEWPAGE.
+
+        Usual migration logic is..
+        (a) remove the page from LRU.
+        (b) allocate NEWPAGE (migration target)
+        (c) lock by lock_page().
+        (d) unmap all mappings.
+        (e-1) If necessary, replace entry in radix-tree.
+        (e-2) move contents of a page.
+        (f) map all mappings again.
+        (g) pushback the page to LRU.
+        (-) OLDPAGE will be freed.
+
+        Before (g), memcg should complete all necessary charge/uncharge to
+        NEWPAGE/OLDPAGE.
+
+        The point is....
+        - If OLDPAGE is anonymous, all charges will be dropped at (d) because
+          try_to_unmap() drops all mapcount and the page will not be
+          SwapCache.
+
+        - If OLDPAGE is SwapCache, charges will be kept at (g) because
+          __delete_from_swap_cache() isn't called at (e-1)
+
+        - If OLDPAGE is page-cache, charges will be kept at (g) because
+          remove_from_swap_cache() isn't called at (e-1)
+
+        memcg provides following hooks.
+
+        - mem_cgroup_prepare_migration(OLDPAGE)
+          Called after (b) to account a charge (usage += PAGE_SIZE) against
+          memcg which OLDPAGE belongs to.
+
+        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
+          Called after (f) before (g).
+          If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
+          charged, a charge by prepare_migration() is automatically canceled.
+          If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
+
+          But zap_pte() (by exit or munmap) can be called while migration,
+          we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
+
+8. LRU
+        Each memcg has its own private LRU. Now, it's handling is under global
+        VM's control (means that it's handled under global zone->lru_lock).
+        Almost all routines around memcg's LRU is called by global LRU's
+        list management functions under zone->lru_lock().
+
+        A special function is mem_cgroup_isolate_pages(). This scans
+        memcg's private LRU and call __isolate_lru_page() to extract a page
+        from LRU.
+        (By __isolate_lru_page(), the page is removed from both of global and
+         private LRU.)
+
+
+9. Typical Tests.
+
+ Tests for racy cases.
+
+ 9.1 Small limit to memcg.
+        When you do test to do racy case, it's good test to set memcg's limit
+        to be very small rather than GB. Many races found in the test under
+        xKB or xxMB limits.
+        (Memory behavior under GB and Memory behavior under MB shows very
+         different situation.)
+
+ 9.2 Shmem
+        Historically, memcg's shmem handling was poor and we saw some amount
+        of troubles here. This is because shmem is page-cache but can be
+        SwapCache. Test with shmem/tmpfs is always good test.
+
+ 9.3 Migration
+        For NUMA, migration is an another special case. To do easy test, cpuset
+        is useful. Following is a sample script to do migration.
+
+        mount -t cgroup -o cpuset none /opt/cpuset
+
+        mkdir /opt/cpuset/01
+        echo 1 > /opt/cpuset/01/cpuset.cpus
+        echo 0 > /opt/cpuset/01/cpuset.mems
+        echo 1 > /opt/cpuset/01/cpuset.memory_migrate
+        mkdir /opt/cpuset/02
+        echo 1 > /opt/cpuset/02/cpuset.cpus
+        echo 1 > /opt/cpuset/02/cpuset.mems
+        echo 1 > /opt/cpuset/02/cpuset.memory_migrate
+
+        In above set, when you moves a task from 01 to 02, page migration to
+        node 0 to node 1 will occur. Following is a script to migrate all
+        under cpuset.
+        --
+        move_task()
+        {
+        for pid in $1
+        do
+                /bin/echo $pid >$2/tasks 2>/dev/null
+                echo -n $pid
+                echo -n " "
+        done
+        echo END
+        }
+
+        G1_TASK=`cat ${G1}/tasks`
+        G2_TASK=`cat ${G2}/tasks`
+        move_task "${G1_TASK}" ${G2} &
+        --
+ 9.4 Memory hotplug.
+        memory hotplug test is one of good test.
+        to offline memory, do following.
+        # echo offline > /sys/devices/system/memory/memoryXXX/state
+        (XXX is the place of memory)
+        This is an easy way to test page migration, too.
+
+ 9.5 mkdir/rmdir
+        When using hierarchy, mkdir/rmdir test should be done.
+        Use tests like the following.
+
+        echo 1 >/opt/cgroup/01/memory/use_hierarchy
+        mkdir /opt/cgroup/01/child_a
+        mkdir /opt/cgroup/01/child_b
+
+        set limit to 01.
+        add limit to 01/child_b
+        run jobs under child_a and child_b
+
+        create/delete following groups at random while jobs are running.
+        /opt/cgroup/01/child_a/child_aa
+        /opt/cgroup/01/child_b/child_bb
+        /opt/cgroup/01/child_c
+
+        running new jobs in new group is also good.
+
+ 9.6 Mount with other subsystems.
+        Mounting with other subsystems is a good test because there is a
+        race and lock dependency with other cgroup subsystems.
+
+        example)
+        # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices
+
+        and do task move, mkdir, rmdir etc...under this.
diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
index 1c07547d3f81..e1501964df1e 100644
--- a/Documentation/controllers/memory.txt
+++ b/Documentation/controllers/memory.txt
@@ -137,7 +137,32 @@ behind this approach is that a cgroup that aggressively uses a shared
 page will eventually get charged for it (once it is uncharged from
 the cgroup that brought it in -- this will happen on memory pressure).
 
-2.4 Reclaim
+Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used..
+When you do swapoff and make swapped-out pages of shmem(tmpfs) to
+be backed into memory in force, charges for pages are accounted against the
+caller of swapoff rather than the users of shmem.
+
+
+2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
+Swap Extension allows you to record charge for swap. A swapped-in page is
+charged back to original page allocator if possible.
+
+When swap is accounted, following files are added.
+ - memory.memsw.usage_in_bytes.
+ - memory.memsw.limit_in_bytes.
+
+usage of mem+swap is limited by memsw.limit_in_bytes.
+
+Note: why 'mem+swap' rather than swap.
+The global LRU(kswapd) can swap out arbitrary pages. Swap-out means
+to move account from memory to swap...there is no change in usage of
+mem+swap.
+
+In other words, when we want to limit the usage of swap without affecting
+global LRU, mem+swap limit is better than just limiting swap from OS point
+of view.
+
+2.5 Reclaim
 
 Each cgroup maintains a per cgroup LRU that consists of an active
 and inactive list. When a cgroup goes over its limit, we first try
@@ -207,12 +232,6 @@ exceeded.
 The memory.stat file gives accounting information. Now, the number of
 caches, RSS and Active pages/Inactive pages are shown.
 
-The memory.force_empty gives an interface to drop *all* charges by force.
-
-# echo 1 > memory.force_empty
-
-will drop all charges in cgroup. Currently, this is maintained for test.
-
 4. Testing
 
 Balbir posted lmbench, AIM9, LTP and vmmstress results [10] and [11].
@@ -242,10 +261,106 @@ reclaimed.
 
 A cgroup can be removed by rmdir, but as discussed in sections 4.1 and 4.2, a
 cgroup might have some charge associated with it, even though all
-tasks have migrated away from it. Such charges are automatically dropped at
-rmdir() if there are no tasks.
+tasks have migrated away from it.
+Such charges are freed(at default) or moved to its parent. When moved,
+both of RSS and CACHES are moved to parent.
+If both of them are busy, rmdir() returns -EBUSY. See 5.1 Also.
+
+Charges recorded in swap information is not updated at removal of cgroup.
+Recorded information is discarded and a cgroup which uses swap (swapcache)
+will be charged as a new owner of it.
+
+
+5. Misc. interfaces.
+
+5.1 force_empty
+  memory.force_empty interface is provided to make cgroup's memory usage empty.
+  You can use this interface only when the cgroup has no tasks.
+  When writing anything to this
+
+  # echo 0 > memory.force_empty
+
+  Almost all pages tracked by this memcg will be unmapped and freed. Some of
+  pages cannot be freed because it's locked or in-use. Such pages are moved
+  to parent and this cgroup will be empty. But this may return -EBUSY in
+  some too busy case.
+
+  Typical use case of this interface is that calling this before rmdir().
+  Because rmdir() moves all pages to parent, some out-of-use page caches can be
+  moved to the parent. If you want to avoid that, force_empty will be useful.
+
+5.2 stat file
+  memory.stat file includes following statistics (now)
+        cache                   - # of pages from page-cache and shmem.
+        rss                     - # of pages from anonymous memory.
+        pgpgin                  - # of event of charging
+        pgpgout                 - # of event of uncharging
+        active_anon             - # of pages on active lru of anon, shmem.
+        inactive_anon           - # of pages on active lru of anon, shmem
+        active_file             - # of pages on active lru of file-cache
+        inactive_file           - # of pages on inactive lru of file cache
+        unevictable             - # of pages cannot be reclaimed.(mlocked etc)
+
+        Below is depend on CONFIG_DEBUG_VM.
+        inactive_ratio          - VM inernal parameter. (see mm/page_alloc.c)
+        recent_rotated_anon     - VM internal parameter. (see mm/vmscan.c)
+        recent_rotated_file     - VM internal parameter. (see mm/vmscan.c)
+        recent_scanned_anon     - VM internal parameter. (see mm/vmscan.c)
+        recent_scanned_file     - VM internal parameter. (see mm/vmscan.c)
+
+  Memo:
+        recent_rotated means recent frequency of lru rotation.
+        recent_scanned means recent # of scans to lru.
+        showing for better debug please see the code for meanings.
+
+
+5.3 swappiness
+  Similar to /proc/sys/vm/swappiness, but affecting a hierarchy of groups only.
+
+  Following cgroup's swapiness can't be changed.
+  - root cgroup (uses /proc/sys/vm/swappiness).
+  - a cgroup which uses hierarchy and it has child cgroup.
+  - a cgroup which uses hierarchy and not the root of hierarchy.
+
+
+6. Hierarchy support
+
+The memory controller supports a deep hierarchy and hierarchical accounting.
+The hierarchy is created by creating the appropriate cgroups in the
+cgroup filesystem. Consider for example, the following cgroup filesystem
+hierarchy
+
+                root
+             /  |   \
+           /    |    \
+          a     b       c
+                        | \
+                        |  \
+                        d   e
+
+In the diagram above, with hierarchical accounting enabled, all memory
+usage of e, is accounted to its ancestors up until the root (i.e, c and root),
+that has memory.use_hierarchy enabled.  If one of the ancestors goes over its
+limit, the reclaim algorithm reclaims from the tasks in the ancestor and the
+children of the ancestor.
+
+6.1 Enabling hierarchical accounting and reclaim
+
+The memory controller by default disables the hierarchy feature. Support
+can be enabled by writing 1 to memory.use_hierarchy file of the root cgroup
+
+# echo 1 > memory.use_hierarchy
+
+The feature can be disabled by
+
+# echo 0 > memory.use_hierarchy
+
+NOTE1: Enabling/disabling will fail if the cgroup already has other
+cgroups created below it.
+
+NOTE2: This feature can be enabled/disabled per subtree.
 
-5. TODO
+7. TODO
 
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
diff --git a/Documentation/crypto/async-tx-api.txt b/Documentation/crypto/async-tx-api.txt
index c1e9545c59bd..9f59fcbf5d82 100644
--- a/Documentation/crypto/async-tx-api.txt
+++ b/Documentation/crypto/async-tx-api.txt
@@ -13,9 +13,9 @@
 3.6 Constraints
 3.7 Example
 
-4 DRIVER DEVELOPER NOTES
+4 DMAENGINE DRIVER DEVELOPER NOTES
 4.1 Conformance points
-4.2 "My application needs finer control of hardware channels"
+4.2 "My application needs exclusive control of hardware channels"
 
 5 SOURCE
 
@@ -150,6 +150,7 @@ ops_run_* and ops_complete_* routines in drivers/md/raid5.c for more
 implementation examples.
 
 4 DRIVER DEVELOPMENT NOTES
+
 4.1 Conformance points:
 There are a few conformance points required in dmaengine drivers to
 accommodate assumptions made by applications using the async_tx API:
@@ -158,58 +159,49 @@ accommodate assumptions made by applications using the async_tx API:
 3/ Use async_tx_run_dependencies() in the descriptor clean up path to
    handle submission of dependent operations
 
-4.2 "My application needs finer control of hardware channels"
-This requirement seems to arise from cases where a DMA engine driver is
-trying to support device-to-memory DMA.  The dmaengine and async_tx
-implementations were designed for offloading memory-to-memory
-operations; however, there are some capabilities of the dmaengine layer
-that can be used for platform-specific channel management.
-Platform-specific constraints can be handled by registering the
-application as a 'dma_client' and implementing a 'dma_event_callback' to
-apply a filter to the available channels in the system.  Before showing
-how to implement a custom dma_event callback some background of
-dmaengine's client support is required.
-
-The following routines in dmaengine support multiple clients requesting
-use of a channel:
-- dma_async_client_register(struct dma_client *client)
-- dma_async_client_chan_request(struct dma_client *client)
-
-dma_async_client_register takes a pointer to an initialized dma_client
-structure.  It expects that the 'event_callback' and 'cap_mask' fields
-are already initialized.
-
-dma_async_client_chan_request triggers dmaengine to notify the client of
-all channels that satisfy the capability mask.  It is up to the client's
-event_callback routine to track how many channels the client needs and
-how many it is currently using.  The dma_event_callback routine returns a
-dma_state_client code to let dmaengine know the status of the
-allocation.
-
-Below is the example of how to extend this functionality for
-platform-specific filtering of the available channels beyond the
-standard capability mask:
-
-static enum dma_state_client
-my_dma_client_callback(struct dma_client *client,
-                        struct dma_chan *chan, enum dma_state state)
-{
-        struct dma_device *dma_dev;
-        struct my_platform_specific_dma *plat_dma_dev;
-        
-        dma_dev = chan->device;
-        plat_dma_dev = container_of(dma_dev,
-                                    struct my_platform_specific_dma,
-                                    dma_dev);
-
-        if (!plat_dma_dev->platform_specific_capability)
-                return DMA_DUP;
-
-        . . .
-}
+4.2 "My application needs exclusive control of hardware channels"
+Primarily this requirement arises from cases where a DMA engine driver
+is being used to support device-to-memory operations.  A channel that is
+performing these operations cannot, for many platform specific reasons,
+be shared.  For these cases the dma_request_channel() interface is
+provided.
+
+The interface is:
+struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+                                     dma_filter_fn filter_fn,
+                                     void *filter_param);
+
+Where dma_filter_fn is defined as:
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+When the optional 'filter_fn' parameter is set to NULL
+dma_request_channel simply returns the first channel that satisfies the
+capability mask.  Otherwise, when the mask parameter is insufficient for
+specifying the necessary channel, the filter_fn routine can be used to
+disposition the available channels in the system. The filter_fn routine
+is called once for each free channel in the system.  Upon seeing a
+suitable channel filter_fn returns DMA_ACK which flags that channel to
+be the return value from dma_request_channel.  A channel allocated via
+this interface is exclusive to the caller, until dma_release_channel()
+is called.
+
+The DMA_PRIVATE capability flag is used to tag dma devices that should
+not be used by the general-purpose allocator.  It can be set at
+initialization time if it is known that a channel will always be
+private.  Alternatively, it is set when dma_request_channel() finds an
+unused "public" channel.
+
+A couple caveats to note when implementing a driver and consumer:
+1/ Once a channel has been privately allocated it will no longer be
+   considered by the general-purpose allocator even after a call to
+   dma_release_channel().
+2/ Since capabilities are specified at the device level a dma_device
+   with multiple channels will either have all channels public, or all
+   channels private.
 
 5 SOURCE
-include/linux/dmaengine.h: core header file for DMA drivers and clients
+
+include/linux/dmaengine.h: core header file for DMA drivers and api users
 drivers/dma/dmaengine.c: offload engine channel management routines
 drivers/dma/: location for offload engine drivers
 include/linux/async_tx.h: core header file for the async_tx api
diff --git a/Documentation/development-process/4.Coding b/Documentation/development-process/4.Coding
index 014aca8f14e2..a5a3450faaa0 100644
--- a/Documentation/development-process/4.Coding
+++ b/Documentation/development-process/4.Coding
@@ -375,10 +375,10 @@ say, this can be a large job, so it is best to be sure that the
 justification is solid.
 
 When making an incompatible API change, one should, whenever possible,
-ensure that code which has not been updated is caught by the compiler.  
+ensure that code which has not been updated is caught by the compiler.
 This will help you to be sure that you have found all in-tree uses of that
 interface.  It will also alert developers of out-of-tree code that there is
 a change that they need to respond to.  Supporting out-of-tree code is not
 something that kernel developers need to be worried about, but we also do
-not have to make life harder for out-of-tree developers than it it needs to
-be. 
+not have to make life harder for out-of-tree developers than it needs to
+be.
diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt
new file mode 100644
index 000000000000..0c1c2f63c0a9
--- /dev/null
+++ b/Documentation/dmaengine.txt
@@ -0,0 +1 @@
+See Documentation/crypto/async-tx-api.txt
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt
new file mode 100644
index 000000000000..64087c34327f
--- /dev/null
+++ b/Documentation/filesystems/btrfs.txt
@@ -0,0 +1,91 @@
+
+        BTRFS
+        =====
+
+Btrfs is a new copy on write filesystem for Linux aimed at
+implementing advanced features while focusing on fault tolerance,
+repair and easy administration. Initially developed by Oracle, Btrfs
+is licensed under the GPL and open for contribution from anyone.
+
+Linux has a wealth of filesystems to choose from, but we are facing a
+number of challenges with scaling to the large storage subsystems that
+are becoming common in today's data centers. Filesystems need to scale
+in their ability to address and manage large storage, and also in
+their ability to detect, repair and tolerate errors in the data stored
+on disk.  Btrfs is under heavy development, and is not suitable for
+any uses other than benchmarking and review. The Btrfs disk format is
+not yet finalized.
+
+The main Btrfs features include:
+
+    * Extent based file storage (2^64 max file size)
+    * Space efficient packing of small files
+    * Space efficient indexed directories
+    * Dynamic inode allocation
+    * Writable snapshots
+    * Subvolumes (separate internal filesystem roots)
+    * Object level mirroring and striping
+    * Checksums on data and metadata (multiple algorithms available)
+    * Compression
+    * Integrated multiple device support, with several raid algorithms
+    * Online filesystem check (not yet implemented)
+    * Very fast offline filesystem check
+    * Efficient incremental backup and FS mirroring (not yet implemented)
+    * Online filesystem defragmentation
+
+
+
+        MAILING LIST
+        ============
+
+There is a Btrfs mailing list hosted on vger.kernel.org. You can
+find details on how to subscribe here:
+
+http://vger.kernel.org/vger-lists.html#linux-btrfs
+
+Mailing list archives are available from gmane:
+
+http://dir.gmane.org/gmane.comp.file-systems.btrfs
+
+
+
+        IRC
+        ===
+
+Discussion of Btrfs also occurs on the #btrfs channel of the Freenode
+IRC network.
+
+
+
+        UTILITIES
+        =========
+
+Userspace tools for creating and manipulating Btrfs file systems are
+available from the git repository at the following location:
+
+ http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git
+
+These include the following tools:
+
+mkfs.btrfs: create a filesystem
+
+btrfsctl: control program to create snapshots and subvolumes:
+
+        mount /dev/sda2 /mnt
+        btrfsctl -s new_subvol_name /mnt
+        btrfsctl -s snapshot_of_default /mnt/default
+        btrfsctl -s snapshot_of_new_subvol /mnt/new_subvol_name
+        btrfsctl -s snapshot_of_a_snapshot /mnt/snapshot_of_new_subvol
+        ls /mnt
+        default snapshot_of_a_snapshot snapshot_of_new_subvol
+        new_subvol_name snapshot_of_default
+
+        Snapshots and subvolumes cannot be deleted right now, but you can
+        rm -rf all the files and directories inside them.
+
+btrfsck: do a limited check of the FS extent trees.
+
+btrfs-debug-tree: print all of the FS metadata in text form.  Example:
+
+        btrfs-debug-tree /dev/sda2 >& big_output_file
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index 174eaff7ded9..cec829bc7291 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -58,13 +58,22 @@ Note: More extensive information for getting started with ext4 can be
 
         # mount -t ext4 /dev/hda1 /wherever
 
-  - When comparing performance with other filesystems, remember that
-    ext3/4 by default offers higher data integrity guarantees than most.
-    So when comparing with a metadata-only journalling filesystem, such
-    as ext3, use `mount -o data=writeback'.  And you might as well use
-    `mount -o nobh' too along with it.  Making the journal larger than
-    the mke2fs default often helps performance with metadata-intensive
-    workloads.
+  - When comparing performance with other filesystems, it's always
+    important to try multiple workloads; very often a subtle change in a
+    workload parameter can completely change the ranking of which
+    filesystems do well compared to others.  When comparing versus ext3,
+    note that ext4 enables write barriers by default, while ext3 does
+    not enable write barriers by default.  So it is useful to use
+    explicitly specify whether barriers are enabled or not when via the
+    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+    for a fair comparison.  When tuning ext3 for best benchmark numbers,
+    it is often worthwhile to try changing the data journaling mode; '-o
+    data=writeback,nobh' can be faster for some workloads.  (Note
+    however that running mounted with data=writeback can potentially
+    leave stale data exposed in recently written files in case of an
+    unclean shutdown, which could be a security exposure in some
+    situations.)  Configuring the filesystem with a large journal can
+    also be helpful for metadata-intensive workloads.
 
 2. Features
 ===========
@@ -74,7 +83,7 @@ Note: More extensive information for getting started with ext4 can be
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
 * extent format more robust in face of on-disk corruption due to magics,
-* internal redunancy in tree
+* internal redundancy in tree
 * improved file allocation (multi-block alloc)
 * fix 32000 subdirectory limit
 * nsec timestamps for mtime, atime, ctime, create time
@@ -116,10 +125,11 @@ grouping of bitmaps and inode tables.  Some test results available here:
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
-extents         (*)     ext4 will use extents to address file data.  The
-                        file system will no longer be mountable by ext3.
-
-noextents               ext4 will not use extents for newly created files
+ro                      Mount filesystem read only. Note that ext4 will
+                        replay the journal (and thus write to the
+                        partition) even when mounted "read only". The
+                        mount options "ro,noload" can be used to prevent
+                        writes to the filesystem.
 
 journal_checksum        Enable checksumming of the journal transactions.
                         This will allow the recovery code in e2fsck and the
@@ -134,17 +144,17 @@ journal_async_commit	Commit block can be written to disk without waiting
 journal=update          Update the ext4 file system's journal to the current
                         format.
 
-journal=inum            When a journal already exists, this option is ignored.
-                        Otherwise, it specifies the number of the inode which
-                        will represent the ext4 file system's journal file.
-
 journal_dev=devnum      When the external journal device's major/minor numbers
                         have changed, this option allows the user to specify
                         the new journal location.  The journal device is
                         identified through its new major/minor numbers encoded
                         in devnum.
 
-noload                  Don't load the journal on mounting.
+noload                  Don't load the journal on mounting.  Note that
+                        if the filesystem was not unmounted cleanly,
+                        skipping the journal replay will lead to the
+                        filesystem containing inconsistencies that can
+                        lead to any number of problems.
 
 data=journal            All data are committed into the journal prior to being
                         written into the main file system.
@@ -219,9 +229,12 @@ minixdf			Make 'df' act like Minix.
 
 debug                   Extra debugging information is sent to syslog.
 
-errors=remount-ro(*)    Remount the filesystem read-only on an error.
+errors=remount-ro       Remount the filesystem read-only on an error.
 errors=continue         Keep going on a filesystem error.
 errors=panic            Panic and halt the machine if an error occurs.
+                        (These mount options override the errors behavior
+                        specified in the superblock, which can be configured
+                        using tune2fs)
 
 data_err=ignore(*)      Just print an error message if an error occurs
                         in a file data buffer in ordered mode.
@@ -261,6 +274,42 @@ delalloc	(*)	Deferring block allocation until write-out time.
 nodelalloc              Disable delayed allocation. Blocks are allocation
                         when data is copied from user to page cache.
 
+max_batch_time=usec     Maximum amount of time ext4 should wait for
+                        additional filesystem operations to be batch
+                        together with a synchronous write operation.
+                        Since a synchronous write operation is going to
+                        force a commit and then a wait for the I/O
+                        complete, it doesn't cost much, and can be a
+                        huge throughput win, we wait for a small amount
+                        of time to see if any other transactions can
+                        piggyback on the synchronous write.   The
+                        algorithm used is designed to automatically tune
+                        for the speed of the disk, by measuring the
+                        amount of time (on average) that it takes to
+                        finish committing a transaction.  Call this time
+                        the "commit time".  If the time that the
+                        transactoin has been running is less than the
+                        commit time, ext4 will try sleeping for the
+                        commit time to see if other operations will join
+                        the transaction.   The commit time is capped by
+                        the max_batch_time, which defaults to 15000us
+                        (15ms).   This optimization can be turned off
+                        entirely by setting max_batch_time to 0.
+
+min_batch_time=usec     This parameter sets the commit time (as
+                        described above) to be at least min_batch_time.
+                        It defaults to zero microseconds.  Increasing
+                        this parameter may improve the throughput of
+                        multi-threaded, synchronous workloads on very
+                        fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio     The I/O priority (from 0 to 7, where 0 is the
+                        highest priorty) which should be used for I/O
+                        operations submitted by kjournald2 during a
+                        commit operation.  This defaults to 3, which is
+                        a slightly higher priority than the default I/O
+                        priority.
+
 Data Mode
 =========
 There are 3 different data modes:
diff --git a/Documentation/hwmon/abituguru-datasheet b/Documentation/hwmon/abituguru-datasheet
index 4d184f2db0ea..d9251efdcec7 100644
--- a/Documentation/hwmon/abituguru-datasheet
+++ b/Documentation/hwmon/abituguru-datasheet
@@ -121,7 +121,7 @@ Once all bytes have been read data will hold 0x09, but there is no reason to
 test for this. Notice that the number of bytes is bank address dependent see
 above and below.
 
-After completing a successfull read it is advised to put the uGuru back in
+After completing a successful read it is advised to put the uGuru back in
 ready mode, so that it is ready for the next read / write cycle. This way
 if your program / driver is unloaded and later loaded again the detection
 algorithm described above will still work.
@@ -141,7 +141,7 @@ don't ask why this is the way it is.
 
 Once DATA holds 0x01 read CMD it should hold 0xAC now.
 
-After completing a successfull write it is advised to put the uGuru back in
+After completing a successful write it is advised to put the uGuru back in
 ready mode, so that it is ready for the next read / write cycle. This way
 if your program / driver is unloaded and later loaded again the detection
 algorithm described above will still work.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 532eacbbed62..8511d3532c27 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -141,6 +141,7 @@ and is between 256 and 4096 characters. It is defined in the file
                         ht -- run only enough ACPI to enable Hyper Threading
                         strict -- Be less tolerant of platforms that are not
                                 strictly ACPI specification compliant.
+                        rsdt -- prefer RSDT over (default) XSDT
 
                         See also Documentation/power/pm.txt, pci=noacpi
 
@@ -151,16 +152,20 @@ and is between 256 and 4096 characters. It is defined in the file
                         default: 0
 
         acpi_sleep=     [HW,ACPI] Sleep options
-                        Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering }
-                        See Documentation/power/video.txt for s3_bios and s3_mode.
+                        Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
+                                  old_ordering, s4_nonvs }
+                        See Documentation/power/video.txt for information on
+                        s3_bios and s3_mode.
                         s3_beep is for debugging; it makes the PC's speaker beep
                         as soon as the kernel's real-mode entry point is called.
                         s4_nohwsig prevents ACPI hardware signature from being
                         used during resume from hibernation.
                         old_ordering causes the ACPI 1.0 ordering of the _PTS
-                        control method, wrt putting devices into low power
-                        states, to be enforced (the ACPI 2.0 ordering of _PTS is
-                        used by default).
+                        control method, with respect to putting devices into
+                        low power states, to be enforced (the ACPI 2.0 ordering
+                        of _PTS is used by default).
+                        s4_nonvs prevents the kernel from saving/restoring the
+                        ACPI NVS memory during hibernation.
 
         acpi_sci=       [HW,ACPI] ACPI System Control Interrupt trigger mode
                         Format: { level | edge | high | low }
@@ -195,7 +200,7 @@ and is between 256 and 4096 characters. It is defined in the file
         acpi_skip_timer_override [HW,ACPI]
                         Recognize and ignore IRQ0/pin2 Interrupt Override.
                         For broken nForce2 BIOS resulting in XT-PIC timer.
-        acpi_use_timer_override [HW,ACPI}
+        acpi_use_timer_override [HW,ACPI]
                         Use timer override. For some broken Nvidia NF5 boards
                         that require a timer override, but don't have
                         HPET
@@ -829,8 +834,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         hlt             [BUGS=ARM,SH]
 
-        hvc_iucv=       [S390] Number of z/VM IUCV Hypervisor console (HVC)
-                               back-ends. Valid parameters: 0..8
+        hvc_iucv=       [S390] Number of z/VM IUCV hypervisor console (HVC)
+                               terminal devices. Valid values: 0..8
 
         i8042.debug     [HW] Toggle i8042 debug mode
         i8042.direct    [HW] Put keyboard port into non-translated mode
@@ -878,17 +883,19 @@ and is between 256 and 4096 characters. It is defined in the file
                         See Documentation/ide/ide.txt.
 
         idle=           [X86]
-                        Format: idle=poll or idle=mwait, idle=halt, idle=nomwait
-                        Poll forces a polling idle loop that can slightly improves the performance
-                        of waking up a idle CPU, but will use a lot of power and make the system
-                        run hot. Not recommended.
-                        idle=mwait. On systems which support MONITOR/MWAIT but the kernel chose
-                        to not use it because it doesn't save as much power as a normal idle
-                        loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same
-                        as idle=poll.
-                        idle=halt. Halt is forced to be used for CPU idle.
+                        Format: idle=poll, idle=mwait, idle=halt, idle=nomwait
+                        Poll forces a polling idle loop that can slightly
+                        improve the performance of waking up a idle CPU, but
+                        will use a lot of power and make the system run hot.
+                        Not recommended.
+                        idle=mwait: On systems which support MONITOR/MWAIT but
+                        the kernel chose to not use it because it doesn't save
+                        as much power as a normal idle loop, use the
+                        MONITOR/MWAIT idle loop anyways. Performance should be
+                        the same as idle=poll.
+                        idle=halt: Halt is forced to be used for CPU idle.
                         In such case C2/C3 won't be used again.
-                        idle=nomwait. Disable mwait for CPU C-states
+                        idle=nomwait: Disable mwait for CPU C-states
 
         ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
                         Claim all unknown PCI IDE storage controllers.
@@ -1074,8 +1081,8 @@ and is between 256 and 4096 characters. It is defined in the file
         lapic           [X86-32,APIC] Enable the local APIC even if BIOS
                         disabled it.
 
-        lapic_timer_c2_ok       [X86-32,x86-64,APIC] trust the local apic timer in
-                        C2 power state.
+        lapic_timer_c2_ok       [X86-32,x86-64,APIC] trust the local apic timer
+                        in C2 power state.
 
         libata.dma=     [LIBATA] DMA control
                         libata.dma=0      Disable all PATA and SATA DMA
@@ -1562,6 +1569,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
         nosoftlockup    [KNL] Disable the soft-lockup detector.
 
+        noswapaccount   [KNL] Disable accounting of swap in memory resource
+                        controller. (See Documentation/controllers/memory.txt)
+
         nosync          [HW,M68K] Disables sync negotiation for all devices.
 
         notsc           [BUGS=X86-32] Disable Time Stamp Counter
@@ -2300,7 +2310,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
         thermal.psv=    [HW,ACPI]
                         -1: disable all passive trip points
-                        <degrees C>: override all passive trip points to this value
+                        <degrees C>: override all passive trip points to this
+                        value
 
         thermal.tzp=    [HW,ACPI]
                         Specify global default ACPI thermal zone polling rate
diff --git a/Documentation/powerpc/dts-bindings/4xx/ndfc.txt b/Documentation/powerpc/dts-bindings/4xx/ndfc.txt
new file mode 100644
index 000000000000..869f0b5f16e8
--- /dev/null
+++ b/Documentation/powerpc/dts-bindings/4xx/ndfc.txt
@@ -0,0 +1,39 @@
+AMCC NDFC (NanD Flash Controller)
+
+Required properties:
+- compatible : "ibm,ndfc".
+- reg : should specify chip select and size used for the chip (0x2000).
+
+Optional properties:
+- ccr : NDFC config and control register value (default 0).
+- bank-settings : NDFC bank configuration register value (default 0).
+
+Notes:
+- partition(s) - follows the OF MTD standard for partitions
+
+Example:
+
+ndfc@1,0 {
+        compatible = "ibm,ndfc";
+        reg = <0x00000001 0x00000000 0x00002000>;
+        ccr = <0x00001000>;
+        bank-settings = <0x80002222>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        nand {
+                #address-cells = <1>;
+                #size-cells = <1>;
+
+                partition@0 {
+                        label = "kernel";
+                        reg = <0x00000000 0x00200000>;
+                };
+                partition@200000 {
+                        label = "root";
+                        reg = <0x00200000 0x03E00000>;
+                };
+        };
+};
+
+
diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt
index 81a917ef96e9..6c974d28eeb4 100644
--- a/Documentation/powerpc/dts-bindings/fsl/board.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/board.txt
@@ -18,7 +18,7 @@ This is the memory-mapped registers for on board FPGA.
 
 Required properities:
 - compatible : should be "fsl,fpga-pixis".
-- reg : should contain the address and the lenght of the FPPGA register
+- reg : should contain the address and the length of the FPPGA register
   set.
 
 Example (MPC8610HPCD):
@@ -27,3 +27,33 @@ Example (MPC8610HPCD):
                 compatible = "fsl,fpga-pixis";
                 reg = <0xe8000000 32>;
         };
+
+* Freescale BCSR GPIO banks
+
+Some BCSR registers act as simple GPIO controllers, each such
+register can be represented by the gpio-controller node.
+
+Required properities:
+- compatible : Should be "fsl,<board>-bcsr-gpio".
+- reg : Should contain the address and the length of the GPIO bank
+  register.
+- #gpio-cells : Should be two. The first cell is the pin number and the
+  second cell is used to specify optional paramters (currently unused).
+- gpio-controller : Marks the port as GPIO controller.
+
+Example:
+
+        bcsr@1,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc8360mds-bcsr";
+                reg = <1 0 0x8000>;
+                ranges = <0 1 0 0x8000>;
+
+                bcsr13: gpio-controller@d {
+                        #gpio-cells = <2>;
+                        compatible = "fsl,mpc8360mds-bcsr-gpio";
+                        reg = <0xd 1>;
+                        gpio-controller;
+                };
+        };
diff --git a/Documentation/scsi/scsi_fc_transport.txt b/Documentation/scsi/scsi_fc_transport.txt
index 38d324d62b25..e5b071d46619 100644
--- a/Documentation/scsi/scsi_fc_transport.txt
+++ b/Documentation/scsi/scsi_fc_transport.txt
@@ -191,7 +191,7 @@ Vport States:
       This is equivalent to a driver "attach" on an adapter, which is
       independent of the adapter's link state.
     - Instantiation of the vport on the FC link via ELS traffic, etc.
-      This is equivalent to a "link up" and successfull link initialization.
+      This is equivalent to a "link up" and successful link initialization.
   Further information can be found in the interfaces section below for
   Vport Creation.
 
@@ -320,7 +320,7 @@ Vport Creation:
       This is equivalent to a driver "attach" on an adapter, which is
       independent of the adapter's link state.
     - Instantiation of the vport on the FC link via ELS traffic, etc.
-      This is equivalent to a "link up" and successfull link initialization.
+      This is equivalent to a "link up" and successful link initialization.
 
   The LLDD's vport_create() function will not synchronously wait for both
   parts to be fully completed before returning. It must validate that the
diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX
index 7b0ceaaad7af..d63fa024ac05 100644
--- a/Documentation/w1/masters/00-INDEX
+++ b/Documentation/w1/masters/00-INDEX
@@ -4,5 +4,7 @@ ds2482
         - The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses.
 ds2490
         - The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges.
+mxc_w1
+        - W1 master controller driver found on Freescale MX2/MX3 SoCs
 w1-gpio
         - GPIO 1-wire bus master driver.
diff --git a/Documentation/w1/masters/mxc-w1 b/Documentation/w1/masters/mxc-w1
new file mode 100644
index 000000000000..97f6199a7f39
--- /dev/null
+++ b/Documentation/w1/masters/mxc-w1
@@ -0,0 +1,11 @@
+Kernel driver mxc_w1
+====================
+
+Supported chips:
+  * Freescale MX27, MX31 and probably other i.MX SoCs
+    Datasheets:
+        http://www.freescale.com/files/32bit/doc/data_sheet/MCIMX31.pdf?fpsp=1
+        http://www.freescale.com/files/dsp/MCIMX27.pdf?fpsp=1
+
+Author: Originally based on Freescale code, prepared for mainline by
+        Sascha Hauer <s.hauer@pengutronix.de>
diff --git a/Documentation/w1/w1.netlink b/Documentation/w1/w1.netlink
index 3640c7c87d45..804445f745ed 100644
--- a/Documentation/w1/w1.netlink
+++ b/Documentation/w1/w1.netlink
@@ -5,69 +5,157 @@ Message types.
 =============
 
 There are three types of messages between w1 core and userspace:
-1. Events. They are generated each time new master or slave device found
-        either due to automatic or requested search.
-2. Userspace commands. Includes read/write and search/alarm search comamnds.
+1. Events. They are generated each time new master or slave device
+        found either due to automatic or requested search.
+2. Userspace commands.
 3. Replies to userspace commands.
 
 
 Protocol.
 ========
 
-[struct cn_msg] - connector header. It's length field is equal to size of the attached data.
+[struct cn_msg] - connector header.
+        Its length field is equal to size of the attached data
 [struct w1_netlink_msg] - w1 netlink header.
         __u8 type       - message type.
-                        W1_SLAVE_ADD/W1_SLAVE_REMOVE - slave add/remove events.
-                        W1_MASTER_ADD/W1_MASTER_REMOVE - master add/remove events.
-                        W1_MASTER_CMD - userspace command for bus master device (search/alarm search).
-                        W1_SLAVE_CMD - userspace command for slave device (read/write/ search/alarm search
-                                        for bus master device where given slave device found).
+                        W1_LIST_MASTERS
+                                list current bus masters
+                        W1_SLAVE_ADD/W1_SLAVE_REMOVE
+                                slave add/remove events
+                        W1_MASTER_ADD/W1_MASTER_REMOVE
+                                master add/remove events
+                        W1_MASTER_CMD
+                                userspace command for bus master
+                                device (search/alarm search)
+                        W1_SLAVE_CMD
+                                userspace command for slave device
+                                (read/write/touch)
         __u8 res        - reserved
-        __u16 len       - size of attached to this header data.
+        __u16 len       - size of data attached to this header data
         union {
-                __u8 id;                         - slave unique device id
+                __u8 id[8];                      - slave unique device id
                 struct w1_mst {
-                        __u32           id;      - master's id.
+                        __u32           id;      - master's id
                         __u32           res;     - reserved
                 } mst;
         } id;
 
-[strucrt w1_netlink_cmd] - command for gived master or slave device.
+[struct w1_netlink_cmd] - command for given master or slave device.
         __u8 cmd        - command opcode.
-                        W1_CMD_READ     - read command.
-                        W1_CMD_WRITE    - write command.
-                        W1_CMD_SEARCH   - search command.
-                        W1_CMD_ALARM_SEARCH - alarm search command.
+                        W1_CMD_READ     - read command
+                        W1_CMD_WRITE    - write command
+                        W1_CMD_TOUCH    - touch command
+                                (write and sample data back to userspace)
+                        W1_CMD_SEARCH   - search command
+                        W1_CMD_ALARM_SEARCH - alarm search command
         __u8 res        - reserved
-        __u16 len       - length of data for this command.
-                        For read command data must be allocated like for write command.
-        __u8 data[0]    - data for this command.
+        __u16 len       - length of data for this command
+                For read command data must be allocated like for write command
+        __u8 data[0]    - data for this command
 
 
-Each connector message can include one or more w1_netlink_msg with zero of more attached w1_netlink_cmd messages.
+Each connector message can include one or more w1_netlink_msg with
+zero or more attached w1_netlink_cmd messages.
 
-For event messages there are no w1_netlink_cmd embedded structures, only connector header
-and w1_netlink_msg strucutre with "len" field being zero and filled type (one of event types)
-and id - either 8 bytes of slave unique id in host order, or master's id, which is assigned
-to bus master device when it is added to w1 core.
+For event messages there are no w1_netlink_cmd embedded structures,
+only connector header and w1_netlink_msg strucutre with "len" field
+being zero and filled type (one of event types) and id:
+either 8 bytes of slave unique id in host order,
+or master's id, which is assigned to bus master device
+when it is added to w1 core.
+
+Currently replies to userspace commands are only generated for read
+command request. One reply is generated exactly for one w1_netlink_cmd
+read request. Replies are not combined when sent - i.e. typical reply
+messages looks like the following:
 
-Currently replies to userspace commands are only generated for read command request.
-One reply is generated exactly for one w1_netlink_cmd read request.
-Replies are not combined when sent - i.e. typical reply messages looks like the following:
 [cn_msg][w1_netlink_msg][w1_netlink_cmd]
-cn_msg.len = sizeof(struct w1_netlink_msg) + sizeof(struct w1_netlink_cmd) + cmd->len;
+cn_msg.len = sizeof(struct w1_netlink_msg) +
+             sizeof(struct w1_netlink_cmd) +
+             cmd->len;
 w1_netlink_msg.len = sizeof(struct w1_netlink_cmd) + cmd->len;
 w1_netlink_cmd.len = cmd->len;
 
+Replies to W1_LIST_MASTERS should send a message back to the userspace
+which will contain list of all registered master ids in the following
+format:
+
+        cn_msg (CN_W1_IDX.CN_W1_VAL as id, len is equal to sizeof(struct
+        w1_netlink_msg) plus number of masters multipled by 4)
+        w1_netlink_msg (type: W1_LIST_MASTERS, len is equal to
+                number of masters multiplied by 4 (u32 size))
+        id0 ... idN
+
+        Each message is at most 4k in size, so if number of master devices
+        exceeds this, it will be split into several messages,
+        cn.seq will be increased for each one.
+
+W1 search and alarm search commands.
+request:
+[cn_msg]
+  [w1_netlink_msg type = W1_MASTER_CMD
+        id is equal to the bus master id to use for searching]
+  [w1_netlink_cmd cmd = W1_CMD_SEARCH or W1_CMD_ALARM_SEARCH]
+
+reply:
+  [cn_msg, ack = 1 and increasing, 0 means the last message,
+        seq is equal to the request seq]
+  [w1_netlink_msg type = W1_MASTER_CMD]
+  [w1_netlink_cmd cmd = W1_CMD_SEARCH or W1_CMD_ALARM_SEARCH
+        len is equal to number of IDs multiplied by 8]
+  [64bit-id0 ... 64bit-idN]
+Length in each header corresponds to the size of the data behind it, so
+w1_netlink_cmd->len = N * 8; where N is number of IDs in this message.
+        Can be zero.
+w1_netlink_msg->len = sizeof(struct w1_netlink_cmd) + N * 8;
+cn_msg->len = sizeof(struct w1_netlink_msg) +
+              sizeof(struct w1_netlink_cmd) +
+              N*8;
+
+W1 reset command.
+[cn_msg]
+  [w1_netlink_msg type = W1_MASTER_CMD
+        id is equal to the bus master id to use for searching]
+  [w1_netlink_cmd cmd = W1_CMD_RESET]
+
+
+Command status replies.
+======================
+
+Each command (either root, master or slave with or without w1_netlink_cmd
+structure) will be 'acked' by the w1 core. Format of the reply is the same
+as request message except that length parameters do not account for data
+requested by the user, i.e. read/write/touch IO requests will not contain
+data, so w1_netlink_cmd.len will be 0, w1_netlink_msg.len will be size
+of the w1_netlink_cmd structure and cn_msg.len will be equal to the sum
+of the sizeof(struct w1_netlink_msg) and sizeof(struct w1_netlink_cmd).
+If reply is generated for master or root command (which do not have
+w1_netlink_cmd attached), reply will contain only cn_msg and w1_netlink_msg
+structires.
+
+w1_netlink_msg.status field will carry positive error value
+(EINVAL for example) or zero in case of success.
+
+All other fields in every structure will mirror the same parameters in the
+request message (except lengths as described above).
+
+Status reply is generated for every w1_netlink_cmd embedded in the
+w1_netlink_msg, if there are no w1_netlink_cmd structures,
+reply will be generated for the w1_netlink_msg.
+
+All w1_netlink_cmd command structures are handled in every w1_netlink_msg,
+even if there were errors, only length mismatch interrupts message processing.
+
 
 Operation steps in w1 core when new command is received.
 =======================================================
 
-When new message (w1_netlink_msg) is received w1 core detects if it is master of slave request,
-according to w1_netlink_msg.type field.
+When new message (w1_netlink_msg) is received w1 core detects if it is
+master or slave request, according to w1_netlink_msg.type field.
 Then master or slave device is searched for.
-When found, master device (requested or those one on where slave device is found) is locked.
-If slave command is requested, then reset/select procedure is started to select given device.
+When found, master device (requested or those one on where slave device
+is found) is locked. If slave command is requested, then reset/select
+procedure is started to select given device.
 
 Then all requested in w1_netlink_msg operations are performed one by one.
 If command requires reply (like read command) it is sent on command completion.
@@ -82,8 +170,8 @@ Connector [1] specific documentation.
 Each connector message includes two u32 fields as "address".
 w1 uses CN_W1_IDX and CN_W1_VAL defined in include/linux/connector.h header.
 Each message also includes sequence and acknowledge numbers.
-Sequence number for event messages is appropriate bus master sequence number increased with
-each event message sent "through" this master.
+Sequence number for event messages is appropriate bus master sequence number
+increased with each event message sent "through" this master.
 Sequence number for userspace requests is set by userspace application.
 Sequence number for reply is the same as was in request, and
 acknowledge number is set to seq+1.
@@ -93,6 +181,6 @@ Additional documantion, source code examples.
 ============================================
 
 1. Documentation/connector
-2. http://tservice.net.ru/~s0mbre/archive/w1
-This archive includes userspace application w1d.c which
-uses read/write/search commands for all master/slave devices found on the bus.
+2. http://www.ioremap.net/archive/w1
+This archive includes userspace application w1d.c which uses
+read/write/search commands for all master/slave devices found on the bus.