30 files changed, 917 insertions, 608 deletions

diff --git a/Documentation/DocBook/libata.tmpl b/Documentation/DocBook/libata.tmpl
index 261b57bc6f08..265c08c96fcd 100644
--- a/Documentation/DocBook/libata.tmpl
+++ b/Documentation/DocBook/libata.tmpl
@@ -107,10 +107,6 @@ void (*dev_config) (struct ata_port *, struct ata_device *);
         issue of SET FEATURES - XFER MODE, and prior to operation.
         </para>
         <para>
-        Called by ata_device_add() after ata_dev_identify() determines
-        a device is present.
-        </para>
-        <para>
         This entry may be specified as NULL in ata_port_operations.
         </para>
 
@@ -154,8 +150,8 @@ unsigned int (*mode_filter) (struct ata_port *, struct ata_device *, unsigned in
 
         <sect2><title>Taskfile read/write</title>
         <programlisting>
-void (*tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
-void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_load) (struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
         </programlisting>
 
         <para>
@@ -164,36 +160,35 @@ void (*tf_read) (struct ata_port *ap, struct ata_taskfile *tf);
         hardware registers / DMA buffers, to obtain the current set of
         taskfile register values.
         Most drivers for taskfile-based hardware (PIO or MMIO) use
-        ata_tf_load() and ata_tf_read() for these hooks.
+        ata_sff_tf_load() and ata_sff_tf_read() for these hooks.
         </para>
 
         </sect2>
 
         <sect2><title>PIO data read/write</title>
         <programlisting>
-void (*data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
+void (*sff_data_xfer) (struct ata_device *, unsigned char *, unsigned int, int);
         </programlisting>
 
         <para>
 All bmdma-style drivers must implement this hook.  This is the low-level
 operation that actually copies the data bytes during a PIO data
 transfer.
-Typically the driver
-will choose one of ata_pio_data_xfer_noirq(), ata_pio_data_xfer(), or
-ata_mmio_data_xfer().
+Typically the driver will choose one of ata_sff_data_xfer_noirq(),
+ata_sff_data_xfer(), or ata_sff_data_xfer32().
         </para>
 
         </sect2>
 
         <sect2><title>ATA command execute</title>
         <programlisting>
-void (*exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
+void (*sff_exec_command)(struct ata_port *ap, struct ata_taskfile *tf);
         </programlisting>
 
         <para>
         causes an ATA command, previously loaded with
         ->tf_load(), to be initiated in hardware.
-        Most drivers for taskfile-based hardware use ata_exec_command()
+        Most drivers for taskfile-based hardware use ata_sff_exec_command()
         for this hook.
         </para>
 
@@ -218,8 +213,8 @@ command.
 
         <sect2><title>Read specific ATA shadow registers</title>
         <programlisting>
-u8   (*check_status)(struct ata_port *ap);
-u8   (*check_altstatus)(struct ata_port *ap);
+u8   (*sff_check_status)(struct ata_port *ap);
+u8   (*sff_check_altstatus)(struct ata_port *ap);
         </programlisting>
 
         <para>
@@ -227,20 +222,14 @@ u8   (*check_altstatus)(struct ata_port *ap);
         hardware.  On some hardware, reading the Status register has
         the side effect of clearing the interrupt condition.
         Most drivers for taskfile-based hardware use
-        ata_check_status() for this hook.
-        </para>
-        <para>
-        Note that because this is called from ata_device_add(), at
-        least a dummy function that clears device interrupts must be
-        provided for all drivers, even if the controller doesn't
-        actually have a taskfile status register.
+        ata_sff_check_status() for this hook.
         </para>
 
         </sect2>
 
         <sect2><title>Select ATA device on bus</title>
         <programlisting>
-void (*dev_select)(struct ata_port *ap, unsigned int device);
+void (*sff_dev_select)(struct ata_port *ap, unsigned int device);
         </programlisting>
 
         <para>
@@ -251,9 +240,7 @@ void (*dev_select)(struct ata_port *ap, unsigned int device);
         </para>
         <para>
         Most drivers for taskfile-based hardware use
-        ata_std_dev_select() for this hook.  Controllers which do not
-        support second drives on a port (such as SATA contollers) will
-        use ata_noop_dev_select().
+        ata_sff_dev_select() for this hook.
         </para>
 
         </sect2>
@@ -441,13 +428,13 @@ void (*irq_clear) (struct ata_port *);
         to struct ata_host_set.
         </para>
         <para>
-        Most legacy IDE drivers use ata_interrupt() for the
+        Most legacy IDE drivers use ata_sff_interrupt() for the
         irq_handler hook, which scans all ports in the host_set,
         determines which queued command was active (if any), and calls
-        ata_host_intr(ap,qc).
+        ata_sff_host_intr(ap,qc).
         </para>
         <para>
-        Most legacy IDE drivers use ata_bmdma_irq_clear() for the
+        Most legacy IDE drivers use ata_sff_irq_clear() for the
         irq_clear() hook, which simply clears the interrupt and error
         flags in the DMA status register.
         </para>
@@ -496,10 +483,6 @@ void (*host_stop) (struct ata_host_set *host_set);
         data from port at this time.
         </para>
         <para>
-        Many drivers use ata_port_stop() as this hook, which frees the
-        PRD table.
-        </para>
-        <para>
         ->host_stop() is called after all ->port_stop() calls
 have completed.  The hook must finalize hardware shutdown, release DMA
 and other resources, etc.
diff --git a/Documentation/DocBook/sh.tmpl b/Documentation/DocBook/sh.tmpl
index 0c3dc4c69dd1..d858d92cf6d9 100644
--- a/Documentation/DocBook/sh.tmpl
+++ b/Documentation/DocBook/sh.tmpl
@@ -19,13 +19,17 @@
   </authorgroup>
 
   <copyright>
-   <year>2008</year>
+   <year>2008-2010</year>
    <holder>Paul Mundt</holder>
   </copyright>
   <copyright>
-   <year>2008</year>
+   <year>2008-2010</year>
    <holder>Renesas Technology Corp.</holder>
   </copyright>
+  <copyright>
+   <year>2010</year>
+   <holder>Renesas Electronics Corp.</holder>
+  </copyright>
 
   <legalnotice>
    <para>
@@ -77,7 +81,7 @@
   </chapter>
   <chapter id="clk">
     <title>Clock Framework Extensions</title>
-!Iarch/sh/include/asm/clock.h
+!Iinclude/linux/sh_clk.h
   </chapter>
   <chapter id="mach">
     <title>Machine Specific Interfaces</title>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index f5395af88a41..40ada93b820a 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -234,7 +234,7 @@ process is as follows:
     Linus, usually the patches that have already been included in the
     -next kernel for a few weeks.  The preferred way to submit big changes
     is using git (the kernel's source management tool, more information
-    can be found at http://git.or.cz/) but plain patches are also just
+    can be found at http://git-scm.com/) but plain patches are also just
     fine.
   - After two weeks a -rc1 kernel is released it is now possible to push
     only patches that do not include new features that could affect the
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 1423d2570d78..44c6dcc93d6d 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -3,35 +3,79 @@ Using RCU's CPU Stall Detector
 The CONFIG_RCU_CPU_STALL_DETECTOR kernel config parameter enables
 RCU's CPU stall detector, which detects conditions that unduly delay
 RCU grace periods.  The stall detector's idea of what constitutes
-"unduly delayed" is controlled by a pair of C preprocessor macros:
+"unduly delayed" is controlled by a set of C preprocessor macros:
 
 RCU_SECONDS_TILL_STALL_CHECK
 
         This macro defines the period of time that RCU will wait from
         the beginning of a grace period until it issues an RCU CPU
-        stall warning.  It is normally ten seconds.
+        stall warning.  This time period is normally ten seconds.
 
 RCU_SECONDS_TILL_STALL_RECHECK
 
         This macro defines the period of time that RCU will wait after
-        issuing a stall warning until it issues another stall warning.
-        It is normally set to thirty seconds.
+        issuing a stall warning until it issues another stall warning
+        for the same stall.  This time period is normally set to thirty
+        seconds.
 
 RCU_STALL_RAT_DELAY
 
-        The CPU stall detector tries to make the offending CPU rat on itself,
-        as this often gives better-quality stack traces.  However, if
-        the offending CPU does not detect its own stall in the number
-        of jiffies specified by RCU_STALL_RAT_DELAY, then other CPUs will
-        complain.  This is normally set to two jiffies.
+        The CPU stall detector tries to make the offending CPU print its
+        own warnings, as this often gives better-quality stack traces.
+        However, if the offending CPU does not detect its own stall in
+        the number of jiffies specified by RCU_STALL_RAT_DELAY, then
+        some other CPU will complain.  This delay is normally set to
+        two jiffies.
 
-The following problems can result in an RCU CPU stall warning:
+When a CPU detects that it is stalling, it will print a message similar
+to the following:
+
+INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
+
+This message indicates that CPU 5 detected that it was causing a stall,
+and that the stall was affecting RCU-sched.  This message will normally be
+followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
+RCU and RCU-sched are implemented by the same underlying mechanism,
+while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
+by rcu_preempt_state.
+
+On the other hand, if the offending CPU fails to print out a stall-warning
+message quickly enough, some other CPU will print a message similar to
+the following:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
+
+This message indicates that CPU 2 detected that CPUs 3 and 5 were both
+causing stalls, and that the stall was affecting RCU-bh.  This message
+will normally be followed by stack dumps for each CPU.  Please note that
+TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
+and that the tasks will be indicated by PID, for example, "P3421".
+It is even possible for a rcu_preempt_state stall to be caused by both
+CPUs -and- tasks, in which case the offending CPUs and tasks will all
+be called out in the list.
+
+Finally, if the grace period ends just as the stall warning starts
+printing, there will be a spurious stall-warning message:
+
+INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
+
+This is rare, but does happen from time to time in real life.
+
+So your kernel printed an RCU CPU stall warning.  The next question is
+"What caused it?"  The following problems can result in RCU CPU stall
+warnings:
 
 o       A CPU looping in an RCU read-side critical section.
         
-o       A CPU looping with interrupts disabled.
+o       A CPU looping with interrupts disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
 
-o       A CPU looping with preemption disabled.
+o       A CPU looping with preemption disabled.  This condition can
+        result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+        stalls.
+
+o       A CPU looping with bottom halves disabled.  This condition can
+        result in RCU-sched and RCU-bh stalls.
 
 o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
         without invoking schedule().
@@ -39,20 +83,24 @@ o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 o       A bug in the RCU implementation.
 
 o       A hardware failure.  This is quite unlikely, but has occurred
-        at least once in a former life.  A CPU failed in a running system,
+        at least once in real life.  A CPU failed in a running system,
         becoming unresponsive, but not causing an immediate crash.
         This resulted in a series of RCU CPU stall warnings, eventually
         leading the realization that the CPU had failed.
 
-The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
-SRCU does not do so directly, but its calls to synchronize_sched() will
-result in RCU-sched detecting any CPU stalls that might be occurring.
-
-To diagnose the cause of the stall, inspect the stack traces.  The offending
-function will usually be near the top of the stack.  If you have a series
-of stall warnings from a single extended stall, comparing the stack traces
-can often help determine where the stall is occurring, which will usually
-be in the function nearest the top of the stack that stays the same from
-trace to trace.
+The RCU, RCU-sched, and RCU-bh implementations have CPU stall
+warning.  SRCU does not have its own CPU stall warnings, but its
+calls to synchronize_sched() will result in RCU-sched detecting
+RCU-sched-related CPU stalls.  Please note that RCU only detects
+CPU stalls when there is a grace period in progress.  No grace period,
+no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
 
 RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.
diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt
index 0e50bc2aa1e2..5d9016795fd8 100644
--- a/Documentation/RCU/torture.txt
+++ b/Documentation/RCU/torture.txt
@@ -182,16 +182,6 @@ Similarly, sched_expedited RCU provides the following:
         sched_expedited-torture: Reader Pipe:  12660320201 95875 0 0 0 0 0 0 0 0 0
         sched_expedited-torture: Reader Batch:  12660424885 0 0 0 0 0 0 0 0 0 0
         sched_expedited-torture: Free-Block Circulation:  1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0
-        state: -1 / 0:0 3:0 4:0
-
-As before, the first four lines are similar to those for RCU.
-The last line shows the task-migration state.  The first number is
--1 if synchronize_sched_expedited() is idle, -2 if in the process of
-posting wakeups to the migration kthreads, and N when waiting on CPU N.
-Each of the colon-separated fields following the "/" is a CPU:state pair.
-Valid states are "0" for idle, "1" for waiting for quiescent state,
-"2" for passed through quiescent state, and "3" when a race with a
-CPU-hotplug event forces use of the synchronize_sched() primitive.
 
 
 USAGE
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 8608fd85e921..efd8cc95c06b 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -256,23 +256,23 @@ o	Each element of the form "1/1 0:127 ^0" represents one struct
 The output of "cat rcu/rcu_pending" looks as follows:
 
 rcu_sched:
-  0 np=255892 qsp=53936 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
-  1 np=261224 qsp=54638 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
-  2 np=237496 qsp=49664 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
-  3 np=236249 qsp=48766 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
-  4 np=221310 qsp=46850 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
-  5 np=237332 qsp=48449 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
-  6 np=219995 qsp=46718 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
-  7 np=249893 qsp=49390 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
+  0 np=255892 qsp=53936 rpq=85 cbr=0 cng=14417 gpc=10033 gps=24320 nf=6445 nn=146741
+  1 np=261224 qsp=54638 rpq=33 cbr=0 cng=25723 gpc=16310 gps=2849 nf=5912 nn=155792
+  2 np=237496 qsp=49664 rpq=23 cbr=0 cng=2762 gpc=45478 gps=1762 nf=1201 nn=136629
+  3 np=236249 qsp=48766 rpq=98 cbr=0 cng=286 gpc=48049 gps=1218 nf=207 nn=137723
+  4 np=221310 qsp=46850 rpq=7 cbr=0 cng=26 gpc=43161 gps=4634 nf=3529 nn=123110
+  5 np=237332 qsp=48449 rpq=9 cbr=0 cng=54 gpc=47920 gps=3252 nf=201 nn=137456
+  6 np=219995 qsp=46718 rpq=12 cbr=0 cng=50 gpc=42098 gps=6093 nf=4202 nn=120834
+  7 np=249893 qsp=49390 rpq=42 cbr=0 cng=72 gpc=38400 gps=17102 nf=41 nn=144888
 rcu_bh:
-  0 np=146741 qsp=1419 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
-  1 np=155792 qsp=12597 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
-  2 np=136629 qsp=18680 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
-  3 np=137723 qsp=2843 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
-  4 np=123110 qsp=12433 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
-  5 np=137456 qsp=4210 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
-  6 np=120834 qsp=9902 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
-  7 np=144888 qsp=26336 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
+  0 np=146741 qsp=1419 rpq=6 cbr=0 cng=6 gpc=0 gps=0 nf=2 nn=145314
+  1 np=155792 qsp=12597 rpq=3 cbr=0 cng=0 gpc=4 gps=8 nf=3 nn=143180
+  2 np=136629 qsp=18680 rpq=1 cbr=0 cng=0 gpc=7 gps=6 nf=0 nn=117936
+  3 np=137723 qsp=2843 rpq=0 cbr=0 cng=0 gpc=10 gps=7 nf=0 nn=134863
+  4 np=123110 qsp=12433 rpq=0 cbr=0 cng=0 gpc=4 gps=2 nf=0 nn=110671
+  5 np=137456 qsp=4210 rpq=1 cbr=0 cng=0 gpc=6 gps=5 nf=0 nn=133235
+  6 np=120834 qsp=9902 rpq=2 cbr=0 cng=0 gpc=6 gps=3 nf=2 nn=110921
+  7 np=144888 qsp=26336 rpq=0 cbr=0 cng=0 gpc=8 gps=2 nf=0 nn=118542
 
 As always, this is once again split into "rcu_sched" and "rcu_bh"
 portions, with CONFIG_TREE_PREEMPT_RCU kernels having an additional
@@ -284,6 +284,9 @@ o	"np" is the number of times that __rcu_pending() has been invoked
 o       "qsp" is the number of times that the RCU was waiting for a
         quiescent state from this CPU.
 
+o       "rpq" is the number of times that the CPU had passed through
+        a quiescent state, but not yet reported it to RCU.
+
 o       "cbr" is the number of times that this CPU had RCU callbacks
         that had passed through a grace period, and were thus ready
         to be invoked.
diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 82e418d648d0..7f5fc3ba9c91 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -20,6 +20,8 @@ Samsung-S3C24XX
         - S3C24XX ARM Linux Overview
 Sharp-LH
         - Linux on Sharp LH79524 and LH7A40X System On a Chip (SOC)
+SPEAr
+        - ST SPEAr platform Linux Overview
 VFP/
         - Release notes for Linux Kernel Vector Floating Point support code
 empeg/
diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt
new file mode 100644
index 000000000000..253a35c6f782
--- /dev/null
+++ b/Documentation/arm/SPEAr/overview.txt
@@ -0,0 +1,60 @@
+                        SPEAr ARM Linux Overview
+                        ==========================
+
+Introduction
+------------
+
+  SPEAr (Structured Processor Enhanced Architecture).
+  weblink : http://www.st.com/spear
+
+  The ST Microelectronics SPEAr range of ARM9/CortexA9 System-on-Chip CPUs are
+  supported by the 'spear' platform of ARM Linux. Currently SPEAr300,
+  SPEAr310, SPEAr320 and SPEAr600 SOCs are supported. Support for the SPEAr13XX
+  series is in progress.
+
+  Hierarchy in SPEAr is as follows:
+
+  SPEAr (Platform)
+        - SPEAr3XX (3XX SOC series, based on ARM9)
+                - SPEAr300 (SOC)
+                        - SPEAr300_EVB (Evaluation Board)
+                - SPEAr310 (SOC)
+                        - SPEAr310_EVB (Evaluation Board)
+                - SPEAr320 (SOC)
+                        - SPEAr320_EVB (Evaluation Board)
+        - SPEAr6XX (6XX SOC series, based on ARM9)
+                - SPEAr600 (SOC)
+                        - SPEAr600_EVB (Evaluation Board)
+        - SPEAr13XX (13XX SOC series, based on ARM CORTEXA9)
+                - SPEAr1300 (SOC)
+
+  Configuration
+  -------------
+
+  A generic configuration is provided for each machine, and can be used as the
+  default by
+        make spear600_defconfig
+        make spear300_defconfig
+        make spear310_defconfig
+        make spear320_defconfig
+
+  Layout
+  ------
+
+  The common files for multiple machine families (SPEAr3XX, SPEAr6XX and
+  SPEAr13XX) are located in the platform code contained in arch/arm/plat-spear
+  with headers in plat/.
+
+  Each machine series have a directory with name arch/arm/mach-spear followed by
+  series name. Like mach-spear3xx, mach-spear6xx and mach-spear13xx.
+
+  Common file for machines of spear3xx family is mach-spear3xx/spear3xx.c and for
+  spear6xx is mach-spear6xx/spear6xx.c. mach-spear* also contain soc/machine
+  specific files, like spear300.c, spear310.c, spear320.c and spear600.c.
+  mach-spear* also contains board specific files for each machine type.
+
+
+  Document Author
+  ---------------
+
+  Viresh Kumar, (c) 2010 ST Microelectronics
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 5eb279a48fa4..57444c2609fc 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -235,8 +235,7 @@ containing the following files describing that cgroup:
  - cgroup.procs: list of tgids in the cgroup.  This list is not
    guaranteed to be sorted or free of duplicate tgids, and userspace
    should sort/uniquify the list if this property is required.
-   Writing a tgid into this file moves all threads with that tgid into
-   this cgroup.
+   This is a read-only file, for now.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
diff --git a/Documentation/credentials.txt b/Documentation/credentials.txt
index df03169782ea..a2db35287003 100644
--- a/Documentation/credentials.txt
+++ b/Documentation/credentials.txt
@@ -408,9 +408,6 @@ This should be used inside the RCU read lock, as in the following example:
                 ...
         }
 
-A function need not get RCU read lock to use __task_cred() if it is holding a
-spinlock at the time as this implicitly holds the RCU read lock.
-
 Should it be necessary to hold another task's credentials for a long period of
 time, and possibly to sleep whilst doing so, then the caller should get a
 reference on them using:
@@ -426,17 +423,16 @@ credentials, hiding the RCU magic from the caller:
         uid_t task_uid(task)            Task's real UID
         uid_t task_euid(task)           Task's effective UID
 
-If the caller is holding a spinlock or the RCU read lock at the time anyway,
-then:
+If the caller is holding the RCU read lock at the time anyway, then:
 
         __task_cred(task)->uid
         __task_cred(task)->euid
 
 should be used instead.  Similarly, if multiple aspects of a task's credentials
-need to be accessed, RCU read lock or a spinlock should be used, __task_cred()
-called, the result stored in a temporary pointer and then the credential
-aspects called from that before dropping the lock.  This prevents the
-potentially expensive RCU magic from being invoked multiple times.
+need to be accessed, RCU read lock should be used, __task_cred() called, the
+result stored in a temporary pointer and then the credential aspects called
+from that before dropping the lock.  This prevents the potentially expensive
+RCU magic from being invoked multiple times.
 
 Should some other single aspect of another task's credentials need to be
 accessed, then this can be used:
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index ed511af0f79a..e7965f4a385a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -520,29 +520,6 @@ Who:	Hans de Goede <hdegoede@redhat.com>
 
 ----------------------------
 
-What:   corgikbd, spitzkbd, tosakbd driver
-When:   2.6.35
-Files:  drivers/input/keyboard/{corgi,spitz,tosa}kbd.c
-Why:    We now have a generic GPIO based matrix keyboard driver that
-        are fully capable of handling all the keys on these devices.
-        The original drivers manipulate the GPIO registers directly
-        and so are difficult to maintain.
-Who:    Eric Miao <eric.y.miao@gmail.com>
-
-----------------------------
-
-What:   corgi_ssp and corgi_ts driver
-When:   2.6.35
-Files:  arch/arm/mach-pxa/corgi_ssp.c, drivers/input/touchscreen/corgi_ts.c
-Why:    The corgi touchscreen is now deprecated in favour of the generic
-        ads7846.c driver. The noise reduction technique used in corgi_ts.c,
-        that's to wait till vsync before ADC sampling, is also integrated into
-        ads7846 driver now. Provided that the original driver is not generic
-        and is difficult to maintain, it will be removed later.
-Who:    Eric Miao <eric.y.miao@gmail.com>
-
-----------------------------
-
 What:   capifs
 When:   February 2011
 Files:  drivers/isdn/capi/capifs.*
@@ -564,6 +541,16 @@ Who:	Avi Kivity <avi@redhat.com>
 
 ----------------------------
 
+What:   xtime, wall_to_monotonic
+When:   2.6.36+
+Files:  kernel/time/timekeeping.c include/linux/time.h
+Why:    Cleaning up timekeeping internal values. Please use
+        existing timekeeping accessor functions to access
+        the equivalent functionality.
+Who:    John Stultz <johnstul@us.ibm.com>
+
+----------------------------
+
 What:   KVM kernel-allocated memory slots
 When:   July 2010
 Why:    Since 2.6.25, kvm supports user-allocated memory slots, which are
@@ -589,3 +576,36 @@ Why:	Useful in 2003, implementation is a hack.
         Generally invoked by accident today.
         Seen as doing more harm than good.
 Who:    Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:   video4linux /dev/vtx teletext API support
+When:   2.6.35
+Files:  drivers/media/video/saa5246a.c drivers/media/video/saa5249.c
+        include/linux/videotext.h
+Why:    The vtx device nodes have been superseded by vbi device nodes
+        for many years. No applications exist that use the vtx support.
+        Of the two i2c drivers that actually support this API the saa5249
+        has been impossible to use for a year now and no known hardware
+        that supports this device exists. The saa5246a is theoretically
+        supported by the old mxb boards, but it never actually worked.
+
+        In summary: there is no hardware that can use this API and there
+        are no applications actually implementing this API.
+
+        The vtx support still reserves minors 192-223 and we would really
+        like to reuse those for upcoming new functionality. In the unlikely
+        event that new hardware appears that wants to use the functionality
+        provided by the vtx API, then that functionality should be build
+        around the sliced VBI API instead.
+Who:    Hans Verkuil <hverkuil@xs4all.nl>
+
+----------------------------
+
+What:   IRQF_DISABLED
+When:   2.6.36
+Why:    The flag is a NOOP as we run interrupt handlers with interrupts disabled
+Who:    Thomas Gleixner <tglx@linutronix.de>
+
+----------------------------
+
diff --git a/Documentation/filesystems/nfs/nfs41-server.txt b/Documentation/filesystems/nfs/nfs41-server.txt
index 6a53a84afc72..04884914a1c8 100644
--- a/Documentation/filesystems/nfs/nfs41-server.txt
+++ b/Documentation/filesystems/nfs/nfs41-server.txt
@@ -137,7 +137,7 @@ NS*| OPENATTR             | OPT        |              | Section 18.17  |
    | READ                 | REQ        |              | Section 18.22  |
    | READDIR              | REQ        |              | Section 18.23  |
    | READLINK             | OPT        |              | Section 18.24  |
-NS | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
+   | RECLAIM_COMPLETE     | REQ        |              | Section 18.51  |
    | RELEASE_LOCKOWNER    | MNI        |              | N/A            |
    | REMOVE               | REQ        |              | Section 18.25  |
    | RENAME               | REQ        |              | Section 18.26  |
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index f6b1b5fca1df..9fb6cbe70bde 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -316,7 +316,7 @@ address           perms offset  dev   inode      pathname
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 0804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
-a7cb2000-a7eb2000 rw-p 00000000 00:00 0          [threadstack:001ff4b4]
+a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
 a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
@@ -352,7 +352,6 @@ is not associated with a file:
  [stack]                  = the stack of the main process
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
- [threadstack:xxxxxxxx]   = the stack of the thread, xxxxxxxx is the stack size
 
  or if empty, the mapping is anonymous.
 
@@ -566,6 +565,10 @@ The default_smp_affinity mask applies to all non-active IRQs, which are the
 IRQs which have not yet been allocated/activated, and hence which lack a
 /proc/irq/[0-9]* directory.
 
+The node file on an SMP system shows the node to which the device using the IRQ
+reports itself as being attached. This hardware locality information does not
+include information about any possible driver locality preference.
+
 prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 profiler. Default value is ffffffff (all cpus).
 
diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index 3219ee0dbfef..5ebf5af1d716 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -74,6 +74,11 @@ structure at all.  You should use this to keep device-specific data.
         /* retrieve the value */
         void *i2c_get_clientdata(const struct i2c_client *client);
 
+Note that starting with kernel 2.6.34, you don't have to set the `data' field
+to NULL in remove() or if probe() failed anymore. The i2c-core does this
+automatically on these occasions. Those are also the only times the core will
+touch this field.
+
 
 Accessing the client
 ====================
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index a10c3b6ba7c4..56941ae1f5db 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -333,14 +333,14 @@ byte 0:
 byte 1:
 
    bit   7   6   5   4   3   2   1   0
-        x15 x14 x13 x12 x11 x10 x9  x8
+         .   .   .   .   .  x10 x9  x8
 
 byte 2:
 
    bit   7   6   5   4   3   2   1   0
         x7  x6  x5  x4  x4  x2  x1  x0
 
-         x15..x0 = absolute x value (horizontal)
+         x10..x0 = absolute x value (horizontal)
 
 byte 3:
 
@@ -350,14 +350,14 @@ byte 3:
 byte 4:
 
    bit   7   6   5   4   3   2   1   0
-        y15 y14 y13 y12 y11 y10 y8  y8
+         .   .   .   .   .   .  y9  y8
 
 byte 5:
 
    bit   7   6   5   4   3   2   1   0
         y7  y6  y5  y4  y3  y2  y1  y0
 
-         y15..y0 = absolute y value (vertical)
+         y9..y0 = absolute y value (vertical)
 
 
 4.2.2 Two finger touch
diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt
index 1423bcc7c507..5dc59b04a71f 100644
--- a/Documentation/intel_txt.txt
+++ b/Documentation/intel_txt.txt
@@ -161,13 +161,15 @@ o  In order to put a system into any of the sleep states after a TXT
       has been restored, it will restore the TPM PCRs and then
       transfer control back to the kernel's S3 resume vector.
       In order to preserve system integrity across S3, the kernel
-      provides tboot with a set of memory ranges (kernel
-      code/data/bss, S3 resume code, and AP trampoline) that tboot
-      will calculate a MAC (message authentication code) over and then
-      seal with the TPM.  On resume and once the measured environment
-      has been re-established, tboot will re-calculate the MAC and
-      verify it against the sealed value.  Tboot's policy determines
-      what happens if the verification fails.
+      provides tboot with a set of memory ranges (RAM and RESERVED_KERN
+      in the e820 table, but not any memory that BIOS might alter over
+      the S3 transition) that tboot will calculate a MAC (message
+      authentication code) over and then seal with the TPM. On resume
+      and once the measured environment has been re-established, tboot
+      will re-calculate the MAC and verify it against the sealed value.
+      Tboot's policy determines what happens if the verification fails.
+      Note that the c/s 194 of tboot which has the new MAC code supports
+      this.
 
 That's pretty much it for TXT support.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e2202e93b148..b9b0d7989f4e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -99,6 +99,7 @@ parameter is applicable:
         SWSUSP  Software suspend (hibernation) is enabled.
         SUSPEND System suspend states are enabled.
         FTRACE  Function tracing enabled.
+        TPM     TPM drivers are enabled.
         TS      Appropriate touchscreen support is enabled.
         UMS     USB Mass Storage support is enabled.
         USB     USB support is enabled.
@@ -324,6 +325,8 @@ and is between 256 and 4096 characters. It is defined in the file
                                     they are unmapped. Otherwise they are
                                     flushed before they will be reused, which
                                     is a lot of faster
+                        off       - do not initialize any AMD IOMMU found in
+                                    the system
 
         amijoy.map=     [HW,JOY] Amiga joystick support
                         Map of devices attached to JOY0DAT and JOY1DAT
@@ -784,8 +787,12 @@ and is between 256 and 4096 characters. It is defined in the file
                         as early as possible in order to facilitate early
                         boot debugging.
 
-        ftrace_dump_on_oops
+        ftrace_dump_on_oops[=orig_cpu]
                         [FTRACE] will dump the trace buffers on oops.
+                        If no parameter is passed, ftrace will dump
+                        buffers of all CPUs, but if you pass orig_cpu, it will
+                        dump only the buffer of the CPU that triggered the
+                        oops.
 
         ftrace_filter=[function-list]
                         [FTRACE] Limit the functions traced by the function
@@ -1194,7 +1201,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
         libata.force=   [LIBATA] Force configurations.  The format is comma
                         separated list of "[ID:]VAL" where ID is
-                        PORT[:DEVICE].  PORT and DEVICE are decimal numbers
+                        PORT[.DEVICE].  PORT and DEVICE are decimal numbers
                         matching port, link or device.  Basically, it matches
                         the ATA ID string printed on console by libata.  If
                         the whole ID part is omitted, the last PORT and DEVICE
@@ -2610,6 +2617,15 @@ and is between 256 and 4096 characters. It is defined in the file
 
         tp720=          [HW,PS2]
 
+        tpm_suspend_pcr=[HW,TPM]
+                        Format: integer pcr id
+                        Specify that at suspend time, the tpm driver
+                        should extend the specified pcr with zeros,
+                        as a workaround for some chips which fail to
+                        flush the last written pcr on TPM_SaveState.
+                        This will guarantee that all the other pcrs
+                        are saved.
+
         trace_buf_size=nn[KMG]
                         [FTRACE] will set tracing buffer size.
 
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 51ec634ac04b..6653017680dd 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -165,8 +165,8 @@ the user entry_handler invocation is also skipped.
 
 1.4 How Does Jump Optimization Work?
 
-If you configured your kernel with CONFIG_OPTPROBES=y (currently
-this option is supported on x86/x86-64, non-preemptive kernel) and
+If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
+is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
 the "debug.kprobes_optimization" kernel parameter is set to 1 (see
 sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
 instruction instead of a breakpoint instruction at each probepoint.
@@ -271,8 +271,6 @@ tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 - Specify an empty function for the kprobe's post_handler or break_handler.
  or
-- Config CONFIG_OPTPROBES=n.
- or
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
 2. Architectures Supported
@@ -307,10 +305,6 @@ it useful to "Compile the kernel with debug info" (CONFIG_DEBUG_INFO),
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
-If you want to reduce probing overhead, set "Kprobes jump optimization
-support" (CONFIG_OPTPROBES) to "y". You can find this option under the
-"Kprobes" line.
-
 4. API Reference
 
 The Kprobes API includes a "register" function and an "unregister"
diff --git a/Documentation/pcmcia/driver-changes.txt b/Documentation/pcmcia/driver-changes.txt
index 446f43b309df..61bc4e943116 100644
--- a/Documentation/pcmcia/driver-changes.txt
+++ b/Documentation/pcmcia/driver-changes.txt
@@ -1,4 +1,17 @@
 This file details changes in 2.6 which affect PCMCIA card driver authors:
+* No dev_node_t (as of 2.6.35)
+   There is no more need to fill out a "dev_node_t" structure.
+
+* New IRQ request rules (as of 2.6.35)
+   Instead of the old pcmcia_request_irq() interface, drivers may now
+   choose between:
+   - calling request_irq/free_irq directly. Use the IRQ from *p_dev->irq.
+   - use pcmcia_request_irq(p_dev, handler_t); the PCMCIA core will
+     clean up automatically on calls to pcmcia_disable_device() or
+     device ejection.
+   - drivers still not capable of IRQF_SHARED (or not telling us so) may
+     use the deprecated pcmcia_request_exclusive_irq() for the time
+     being; they might receive a shared IRQ nonetheless.
 
 * no cs_error / CS_CHECK / CONFIG_PCMCIA_DEBUG (as of 2.6.33)
    Instead of the cs_error() callback or the CS_CHECK() macro, please use
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index c9abbd86bc18..57080cd74575 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -1,7 +1,13 @@
+Device Power Management
+
+Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu>
+
+
 Most of the code in Linux is device drivers, so most of the Linux power
-management code is also driver-specific.  Most drivers will do very little;
-others, especially for platforms with small batteries (like cell phones),
-will do a lot.
+management (PM) code is also driver-specific.  Most drivers will do very
+little; others, especially for platforms with small batteries (like cell
+phones), will do a lot.
 
 This writeup gives an overview of how drivers interact with system-wide
 power management goals, emphasizing the models and interfaces that are
@@ -15,9 +21,10 @@ Drivers will use one or both of these models to put devices into low-power
 states:
 
     System Sleep model:
-        Drivers can enter low power states as part of entering system-wide
-        low-power states like "suspend-to-ram", or (mostly for systems with
-        disks) "hibernate" (suspend-to-disk).
+        Drivers can enter low-power states as part of entering system-wide
+        low-power states like "suspend" (also known as "suspend-to-RAM"), or
+        (mostly for systems with disks) "hibernation" (also known as
+        "suspend-to-disk").
 
         This is something that device, bus, and class drivers collaborate on
         by implementing various role-specific suspend and resume methods to
@@ -25,33 +32,41 @@ states:
         them without loss of data.
 
         Some drivers can manage hardware wakeup events, which make the system
-        leave that low-power state.  This feature may be disabled using the
-        relevant /sys/devices/.../power/wakeup file; enabling it may cost some
-        power usage, but let the whole system enter low power states more often.
+        leave the low-power state.  This feature may be enabled or disabled
+        using the relevant /sys/devices/.../power/wakeup file (for Ethernet
+        drivers the ioctl interface used by ethtool may also be used for this
+        purpose); enabling it may cost some power usage, but let the whole
+        system enter low-power states more often.
 
     Runtime Power Management model:
-        Drivers may also enter low power states while the system is running,
-        independently of other power management activity.  Upstream drivers
-        will normally not know (or care) if the device is in some low power
-        state when issuing requests; the driver will auto-resume anything
-        that's needed when it gets a request.
-
-        This doesn't have, or need much infrastructure; it's just something you
-        should do when writing your drivers.  For example, clk_disable() unused
-        clocks as part of minimizing power drain for currently-unused hardware.
-        Of course, sometimes clusters of drivers will collaborate with each
-        other, which could involve task-specific power management.
-
-There's not a lot to be said about those low power states except that they
-are very system-specific, and often device-specific.  Also, that if enough
-drivers put themselves into low power states (at "runtime"), the effect may be
-the same as entering some system-wide low-power state (system sleep) ... and
-that synergies exist, so that several drivers using runtime pm might put the
-system into a state where even deeper power saving options are available.
-
-Most suspended devices will have quiesced all I/O:  no more DMA or irqs, no
-more data read or written, and requests from upstream drivers are no longer
-accepted.  A given bus or platform may have different requirements though.
+        Devices may also be put into low-power states while the system is
+        running, independently of other power management activity in principle.
+        However, devices are not generally independent of each other (for
+        example, a parent device cannot be suspended unless all of its child
+        devices have been suspended).  Moreover, depending on the bus type the
+        device is on, it may be necessary to carry out some bus-specific
+        operations on the device for this purpose.  Devices put into low power
+        states at run time may require special handling during system-wide power
+        transitions (suspend or hibernation).
+
+        For these reasons not only the device driver itself, but also the
+        appropriate subsystem (bus type, device type or device class) driver and
+        the PM core are involved in runtime power management.  As in the system
+        sleep power management case, they need to collaborate by implementing
+        various role-specific suspend and resume methods, so that the hardware
+        is cleanly powered down and reactivated without data or service loss.
+
+There's not a lot to be said about those low-power states except that they are
+very system-specific, and often device-specific.  Also, that if enough devices
+have been put into low-power states (at runtime), the effect may be very similar
+to entering some system-wide low-power state (system sleep) ... and that
+synergies exist, so that several drivers using runtime PM might put the system
+into a state where even deeper power saving options are available.
+
+Most suspended devices will have quiesced all I/O: no more DMA or IRQs (except
+for wakeup events), no more data read or written, and requests from upstream
+drivers are no longer accepted.  A given bus or platform may have different
+requirements though.
 
 Examples of hardware wakeup events include an alarm from a real time clock,
 network wake-on-LAN packets, keyboard or mouse activity, and media insertion
@@ -60,129 +75,152 @@ or removal (for PCMCIA, MMC/SD, USB, and so on).
 
 Interfaces for Entering System Sleep States
 ===========================================
-Most of the programming interfaces a device driver needs to know about
-relate to that first model:  entering a system-wide low power state,
-rather than just minimizing power consumption by one device.
-
-
-Bus Driver Methods
-------------------
-The core methods to suspend and resume devices reside in struct bus_type.
-These are mostly of interest to people writing infrastructure for busses
-like PCI or USB, or because they define the primitives that device drivers
-may need to apply in domain-specific ways to their devices:
-
-struct bus_type {
-        ...
-        int  (*suspend)(struct device *dev, pm_message_t state);
-        int  (*resume)(struct device *dev);
+There are programming interfaces provided for subsystems (bus type, device type,
+device class) and device drivers to allow them to participate in the power
+management of devices they are concerned with.  These interfaces cover both
+system sleep and runtime power management.
+
+
+Device Power Management Operations
+----------------------------------
+Device power management operations, at the subsystem level as well as at the
+device driver level, are implemented by defining and populating objects of type
+struct dev_pm_ops:
+
+struct dev_pm_ops {
+        int (*prepare)(struct device *dev);
+        void (*complete)(struct device *dev);
+        int (*suspend)(struct device *dev);
+        int (*resume)(struct device *dev);
+        int (*freeze)(struct device *dev);
+        int (*thaw)(struct device *dev);
+        int (*poweroff)(struct device *dev);
+        int (*restore)(struct device *dev);
+        int (*suspend_noirq)(struct device *dev);
+        int (*resume_noirq)(struct device *dev);
+        int (*freeze_noirq)(struct device *dev);
+        int (*thaw_noirq)(struct device *dev);
+        int (*poweroff_noirq)(struct device *dev);
+        int (*restore_noirq)(struct device *dev);
+        int (*runtime_suspend)(struct device *dev);
+        int (*runtime_resume)(struct device *dev);
+        int (*runtime_idle)(struct device *dev);
 };
 
-Bus drivers implement those methods as appropriate for the hardware and
-the drivers using it; PCI works differently from USB, and so on.  Not many
-people write bus drivers; most driver code is a "device driver" that
-builds on top of bus-specific framework code.
+This structure is defined in include/linux/pm.h and the methods included in it
+are also described in that file.  Their roles will be explained in what follows.
+For now, it should be sufficient to remember that the last three methods are
+specific to runtime power management while the remaining ones are used during
+system-wide power transitions.
 
-For more information on these driver calls, see the description later;
-they are called in phases for every device, respecting the parent-child
-sequencing in the driver model tree.  Note that as this is being written,
-only the suspend() and resume() are widely available; not many bus drivers
-leverage all of those phases, or pass them down to lower driver levels.
+There also is a deprecated "old" or "legacy" interface for power management
+operations available at least for some subsystems.  This approach does not use
+struct dev_pm_ops objects and it is suitable only for implementing system sleep
+power management methods.  Therefore it is not described in this document, so
+please refer directly to the source code for more information about it.
 
 
-/sys/devices/.../power/wakeup files
------------------------------------
-All devices in the driver model have two flags to control handling of
-wakeup events, which are hardware signals that can force the device and/or
-system out of a low power state.  These are initialized by bus or device
-driver code using device_init_wakeup(dev,can_wakeup).
+Subsystem-Level Methods
+-----------------------
+The core methods to suspend and resume devices reside in struct dev_pm_ops
+pointed to by the pm member of struct bus_type, struct device_type and
+struct class.  They are mostly of interest to the people writing infrastructure
+for buses, like PCI or USB, or device type and device class drivers.
 
-The "can_wakeup" flag just records whether the device (and its driver) can
-physically support wakeup events.  When that flag is clear, the sysfs
-"wakeup" file is empty, and device_may_wakeup() returns false.
+Bus drivers implement these methods as appropriate for the hardware and the
+drivers using it; PCI works differently from USB, and so on.  Not many people
+write subsystem-level drivers; most driver code is a "device driver" that builds
+on top of bus-specific framework code.
 
-For devices that can issue wakeup events, a separate flag controls whether
-that device should try to use its wakeup mechanism.  The initial value of
-device_may_wakeup() will be true, so that the device's "wakeup" file holds
-the value "enabled".  Userspace can change that to "disabled" so that
-device_may_wakeup() returns false; or change it back to "enabled" (so that
-it returns true again).
+For more information on these driver calls, see the description later;
+they are called in phases for every device, respecting the parent-child
+sequencing in the driver model tree.
 
 
-EXAMPLE:  PCI Device Driver Methods
+/sys/devices/.../power/wakeup files
 -----------------------------------
-PCI framework software calls these methods when the PCI device driver bound
-to a device device has provided them:
-
-struct pci_driver {
-        ...
-        int  (*suspend)(struct pci_device *pdev, pm_message_t state);
-        int  (*suspend_late)(struct pci_device *pdev, pm_message_t state);
+All devices in the driver model have two flags to control handling of wakeup
+events (hardware signals that can force the device and/or system out of a low
+power state).  These flags are initialized by bus or device driver code using
+device_set_wakeup_capable() and device_set_wakeup_enable(), defined in
+include/linux/pm_wakeup.h.
 
-        int  (*resume_early)(struct pci_device *pdev);
-        int  (*resume)(struct pci_device *pdev);
-};
-
-Drivers will implement those methods, and call PCI-specific procedures
-like pci_set_power_state(), pci_enable_wake(), pci_save_state(), and
-pci_restore_state() to manage PCI-specific mechanisms.  (PCI config space
-could be saved during driver probe, if it weren't for the fact that some
-systems rely on userspace tweaking using setpci.)  Devices are suspended
-before their bridges enter low power states, and likewise bridges resume
-before their devices.
-
-
-Upper Layers of Driver Stacks
------------------------------
-Device drivers generally have at least two interfaces, and the methods
-sketched above are the ones which apply to the lower level (nearer PCI, USB,
-or other bus hardware).  The network and block layers are examples of upper
-level interfaces, as is a character device talking to userspace.
-
-Power management requests normally need to flow through those upper levels,
-which often use domain-oriented requests like "blank that screen".  In
-some cases those upper levels will have power management intelligence that
-relates to end-user activity, or other devices that work in cooperation.
-
-When those interfaces are structured using class interfaces, there is a
-standard way to have the upper layer stop issuing requests to a given
-class device (and restart later):
-
-struct class {
-        ...
-        int  (*suspend)(struct device *dev, pm_message_t state);
-        int  (*resume)(struct device *dev);
-};
-
-Those calls are issued in specific phases of the process by which the
-system enters a low power "suspend" state, or resumes from it.
-
-
-Calling Drivers to Enter System Sleep States
-============================================
-When the system enters a low power state, each device's driver is asked
-to suspend the device by putting it into state compatible with the target
+The "can_wakeup" flag just records whether the device (and its driver) can
+physically support wakeup events.  The device_set_wakeup_capable() routine
+affects this flag.  The "should_wakeup" flag controls whether the device should
+try to use its wakeup mechanism.  device_set_wakeup_enable() affects this flag;
+for the most part drivers should not change its value.  The initial value of
+should_wakeup is supposed to be false for the majority of devices; the major
+exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
+(wake-on-LAN) feature has been set up with ethtool.
+
+Whether or not a device is capable of issuing wakeup events is a hardware
+matter, and the kernel is responsible for keeping track of it.  By contrast,
+whether or not a wakeup-capable device should issue wakeup events is a policy
+decision, and it is managed by user space through a sysfs attribute: the
+power/wakeup file.  User space can write the strings "enabled" or "disabled" to
+set or clear the should_wakeup flag, respectively.  Reads from the file will
+return the corresponding string if can_wakeup is true, but if can_wakeup is
+false then reads will return an empty string, to indicate that the device
+doesn't support wakeup events.  (But even though the file appears empty, writes
+will still affect the should_wakeup flag.)
+
+The device_may_wakeup() routine returns true only if both flags are set.
+Drivers should check this routine when putting devices in a low-power state
+during a system sleep transition, to see whether or not to enable the devices'
+wakeup mechanisms.  However for runtime power management, wakeup events should
+be enabled whenever the device and driver both support them, regardless of the
+should_wakeup flag.
+
+
+/sys/devices/.../power/control files
+------------------------------------
+Each device in the driver model has a flag to control whether it is subject to
+runtime power management.  This flag, called runtime_auto, is initialized by the
+bus type (or generally subsystem) code using pm_runtime_allow() or
+pm_runtime_forbid(); the default is to allow runtime power management.
+
+The setting can be adjusted by user space by writing either "on" or "auto" to
+the device's power/control sysfs file.  Writing "auto" calls pm_runtime_allow(),
+setting the flag and allowing the device to be runtime power-managed by its
+driver.  Writing "on" calls pm_runtime_forbid(), clearing the flag, returning
+the device to full power if it was in a low-power state, and preventing the
+device from being runtime power-managed.  User space can check the current value
+of the runtime_auto flag by reading the file.
+
+The device's runtime_auto flag has no effect on the handling of system-wide
+power transitions.  In particular, the device can (and in the majority of cases
+should and will) be put into a low-power state during a system-wide transition
+to a sleep state even though its runtime_auto flag is clear.
+
+For more information about the runtime power management framework, refer to
+Documentation/power/runtime_pm.txt.
+
+
+Calling Drivers to Enter and Leave System Sleep States
+======================================================
+When the system goes into a sleep state, each device's driver is asked to
+suspend the device by putting it into a state compatible with the target
 system state.  That's usually some version of "off", but the details are
 system-specific.  Also, wakeup-enabled devices will usually stay partly
 functional in order to wake the system.
 
-When the system leaves that low power state, the device's driver is asked
-to resume it.  The suspend and resume operations always go together, and
-both are multi-phase operations.
+When the system leaves that low-power state, the device's driver is asked to
+resume it by returning it to full power.  The suspend and resume operations
+always go together, and both are multi-phase operations.
 
-For simple drivers, suspend might quiesce the device using the class code
-and then turn its hardware as "off" as possible with late_suspend.  The
+For simple drivers, suspend might quiesce the device using class code
+and then turn its hardware as "off" as possible during suspend_noirq.  The
 matching resume calls would then completely reinitialize the hardware
 before reactivating its class I/O queues.
 
-More power-aware drivers drivers will use more than one device low power
-state, either at runtime or during system sleep states, and might trigger
-system wakeup events.
+More power-aware drivers might prepare the devices for triggering system wakeup
+events.
 
 
 Call Sequence Guarantees
 ------------------------
-To ensure that bridges and similar links needed to talk to a device are
+To ensure that bridges and similar links needing to talk to a device are
 available when the device is suspended or resumed, the device tree is
 walked in a bottom-up order to suspend devices.  A top-down order is
 used to resume those devices.
@@ -194,67 +232,310 @@ its parent; and can't be removed or suspended after that parent.
 The policy is that the device tree should match hardware bus topology.
 (Or at least the control bus, for devices which use multiple busses.)
 In particular, this means that a device registration may fail if the parent of
-the device is suspending (ie. has been chosen by the PM core as the next
+the device is suspending (i.e. has been chosen by the PM core as the next
 device to suspend) or has already suspended, as well as after all of the other
 devices have been suspended.  Device drivers must be prepared to cope with such
 situations.
 
 
-Suspending Devices
-------------------
-Suspending a given device is done in several phases.  Suspending the
-system always includes every phase, executing calls for every device
-before the next phase begins.  Not all busses or classes support all
-these callbacks; and not all drivers use all the callbacks.
+System Power Management Phases
+------------------------------
+Suspending or resuming the system is done in several phases.  Different phases
+are used for standby or memory sleep states ("suspend-to-RAM") and the
+hibernation state ("suspend-to-disk").  Each phase involves executing callbacks
+for every device before the next phase begins.  Not all busses or classes
+support all these callbacks and not all drivers use all the callbacks.  The
+various phases always run after tasks have been frozen and before they are
+unfrozen.  Furthermore, the *_noirq phases run at a time when IRQ handlers have
+been disabled (except for those marked with the IRQ_WAKEUP flag).
 
-The phases are seen by driver notifications issued in this order:
+Most phases use bus, type, and class callbacks (that is, methods defined in
+dev->bus->pm, dev->type->pm, and dev->class->pm).  The prepare and complete
+phases are exceptions; they use only bus callbacks.  When multiple callbacks
+are used in a phase, they are invoked in the order: <class, type, bus> during
+power-down transitions and in the opposite order during power-up transitions.
+For example, during the suspend phase the PM core invokes
 
-   1    class.suspend(dev, message) is called after tasks are frozen, for
-        devices associated with a class that has such a method.  This
-        method may sleep.
+        dev->class->pm.suspend(dev);
+        dev->type->pm.suspend(dev);
+        dev->bus->pm.suspend(dev);
 
-        Since I/O activity usually comes from such higher layers, this is
-        a good place to quiesce all drivers of a given type (and keep such
-        code out of those drivers).
+before moving on to the next device, whereas during the resume phase the core
+invokes
 
-   2    bus.suspend(dev, message) is called next.  This method may sleep,
-        and is often morphed into a device driver call with bus-specific
-        parameters and/or rules.
+        dev->bus->pm.resume(dev);
+        dev->type->pm.resume(dev);
+        dev->class->pm.resume(dev);
 
-        This call should handle parts of device suspend logic that require
-        sleeping.  It probably does work to quiesce the device which hasn't
-        been abstracted into class.suspend().
+These callbacks may in turn invoke device- or driver-specific methods stored in
+dev->driver->pm, but they don't have to.
 
-The pm_message_t parameter is currently used to refine those semantics
-(described later).
 
-At the end of those phases, drivers should normally have stopped all I/O
-transactions (DMA, IRQs), saved enough state that they can re-initialize
-or restore previous state (as needed by the hardware), and placed the
-device into a low-power state.  On many platforms they will also use
-clk_disable() to gate off one or more clock sources; sometimes they will
-also switch off power supplies, or reduce voltages.  Drivers which have
-runtime PM support may already have performed some or all of the steps
-needed to prepare for the upcoming system sleep state.
+Entering System Suspend
+-----------------------
+When the system goes into the standby or memory sleep state, the phases are:
+
+                prepare, suspend, suspend_noirq.
+
+    1.  The prepare phase is meant to prevent races by preventing new devices
+        from being registered; the PM core would never know that all the
+        children of a device had been suspended if new children could be
+        registered at will.  (By contrast, devices may be unregistered at any
+        time.)  Unlike the other suspend-related phases, during the prepare
+        phase the device tree is traversed top-down.
+
+        The prepare phase uses only a bus callback.  After the callback method
+        returns, no new children may be registered below the device.  The method
+        may also prepare the device or driver in some way for the upcoming
+        system power transition, but it should not put the device into a
+        low-power state.
+
+    2.  The suspend methods should quiesce the device to stop it from performing
+        I/O.  They also may save the device registers and put it into the
+        appropriate low-power state, depending on the bus type the device is on,
+        and they may enable wakeup events.
+
+    3.  The suspend_noirq phase occurs after IRQ handlers have been disabled,
+        which means that the driver's interrupt handler will not be called while
+        the callback method is running.  The methods should save the values of
+        the device's registers that weren't saved previously and finally put the
+        device into the appropriate low-power state.
+
+        The majority of subsystems and device drivers need not implement this
+        callback.  However, bus types allowing devices to share interrupt
+        vectors, like PCI, generally need it; otherwise a driver might encounter
+        an error during the suspend phase by fielding a shared interrupt
+        generated by some other device after its own device had been set to low
+        power.
+
+At the end of these phases, drivers should have stopped all I/O transactions
+(DMA, IRQs), saved enough state that they can re-initialize or restore previous
+state (as needed by the hardware), and placed the device into a low-power state.
+On many platforms they will gate off one or more clock sources; sometimes they
+will also switch off power supplies or reduce voltages.  (Drivers supporting
+runtime PM may already have performed some or all of these steps.)
+
+If device_may_wakeup(dev) returns true, the device should be prepared for
+generating hardware wakeup signals to trigger a system wakeup event when the
+system is in the sleep state.  For example, enable_irq_wake() might identify
+GPIO signals hooked up to a switch or other external hardware, and
+pci_enable_wake() does something similar for the PCI PME signal.
+
+If any of these callbacks returns an error, the system won't enter the desired
+low-power state.  Instead the PM core will unwind its actions by resuming all
+the devices that were suspended.
+
+
+Leaving System Suspend
+----------------------
+When resuming from standby or memory sleep, the phases are:
+
+                resume_noirq, resume, complete.
+
+    1.  The resume_noirq callback methods should perform any actions needed
+        before the driver's interrupt handlers are invoked.  This generally
+        means undoing the actions of the suspend_noirq phase.  If the bus type
+        permits devices to share interrupt vectors, like PCI, the method should
+        bring the device and its driver into a state in which the driver can
+        recognize if the device is the source of incoming interrupts, if any,
+        and handle them correctly.
+
+        For example, the PCI bus type's ->pm.resume_noirq() puts the device into
+        the full-power state (D0 in the PCI terminology) and restores the
+        standard configuration registers of the device.  Then it calls the
+        device driver's ->pm.resume_noirq() method to perform device-specific
+        actions.
+
+    2.  The resume methods should bring the the device back to its operating
+        state, so that it can perform normal I/O.  This generally involves
+        undoing the actions of the suspend phase.
+
+    3.  The complete phase uses only a bus callback.  The method should undo the
+        actions of the prepare phase.  Note, however, that new children may be
+        registered below the device as soon as the resume callbacks occur; it's
+        not necessary to wait until the complete phase.
+
+At the end of these phases, drivers should be as functional as they were before
+suspending: I/O can be performed using DMA and IRQs, and the relevant clocks are
+gated on.  Even if the device was in a low-power state before the system sleep
+because of runtime power management, afterwards it should be back in its
+full-power state.  There are multiple reasons why it's best to do this; they are
+discussed in more detail in Documentation/power/runtime_pm.txt.
 
-When any driver sees that its device_can_wakeup(dev), it should make sure
-to use the relevant hardware signals to trigger a system wakeup event.
-For example, enable_irq_wake() might identify GPIO signals hooked up to
-a switch or other external hardware, and pci_enable_wake() does something
-similar for PCI's PME# signal.
+However, the details here may again be platform-specific.  For example,
+some systems support multiple "run" states, and the mode in effect at
+the end of resume might not be the one which preceded suspension.
+That means availability of certain clocks or power supplies changed,
+which could easily affect how a driver works.
+
+Drivers need to be able to handle hardware which has been reset since the
+suspend methods were called, for example by complete reinitialization.
+This may be the hardest part, and the one most protected by NDA'd documents
+and chip errata.  It's simplest if the hardware state hasn't changed since
+the suspend was carried out, but that can't be guaranteed (in fact, it ususally
+is not the case).
+
+Drivers must also be prepared to notice that the device has been removed
+while the system was powered down, whenever that's physically possible.
+PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses
+where common Linux platforms will see such removal.  Details of how drivers
+will notice and handle such removals are currently bus-specific, and often
+involve a separate thread.
+
+These callbacks may return an error value, but the PM core will ignore such
+errors since there's nothing it can do about them other than printing them in
+the system log.
+
+
+Entering Hibernation
+--------------------
+Hibernating the system is more complicated than putting it into the standby or
+memory sleep state, because it involves creating and saving a system image.
+Therefore there are more phases for hibernation, with a different set of
+callbacks.  These phases always run after tasks have been frozen and memory has
+been freed.
+
+The general procedure for hibernation is to quiesce all devices (freeze), create
+an image of the system memory while everything is stable, reactivate all
+devices (thaw), write the image to permanent storage, and finally shut down the
+system (poweroff).  The phases used to accomplish this are:
+
+        prepare, freeze, freeze_noirq, thaw_noirq, thaw, complete,
+        prepare, poweroff, poweroff_noirq
+
+    1.  The prepare phase is discussed in the "Entering System Suspend" section
+        above.
+
+    2.  The freeze methods should quiesce the device so that it doesn't generate
+        IRQs or DMA, and they may need to save the values of device registers.
+        However the device does not have to be put in a low-power state, and to
+        save time it's best not to do so.  Also, the device should not be
+        prepared to generate wakeup events.
+
+    3.  The freeze_noirq phase is analogous to the suspend_noirq phase discussed
+        above, except again that the device should not be put in a low-power
+        state and should not be allowed to generate wakeup events.
+
+At this point the system image is created.  All devices should be inactive and
+the contents of memory should remain undisturbed while this happens, so that the
+image forms an atomic snapshot of the system state.
+
+    4.  The thaw_noirq phase is analogous to the resume_noirq phase discussed
+        above.  The main difference is that its methods can assume the device is
+        in the same state as at the end of the freeze_noirq phase.
+
+    5.  The thaw phase is analogous to the resume phase discussed above.  Its
+        methods should bring the device back to an operating state, so that it
+        can be used for saving the image if necessary.
+
+    6.  The complete phase is discussed in the "Leaving System Suspend" section
+        above.
+
+At this point the system image is saved, and the devices then need to be
+prepared for the upcoming system shutdown.  This is much like suspending them
+before putting the system into the standby or memory sleep state, and the phases
+are similar.
+
+    7.  The prepare phase is discussed above.
+
+    8.  The poweroff phase is analogous to the suspend phase.
+
+    9.  The poweroff_noirq phase is analogous to the suspend_noirq phase.
+
+The poweroff and poweroff_noirq callbacks should do essentially the same things
+as the suspend and suspend_noirq callbacks.  The only notable difference is that
+they need not store the device register values, because the registers should
+already have been stored during the freeze or freeze_noirq phases.
+
+
+Leaving Hibernation
+-------------------
+Resuming from hibernation is, again, more complicated than resuming from a sleep
+state in which the contents of main memory are preserved, because it requires
+a system image to be loaded into memory and the pre-hibernation memory contents
+to be restored before control can be passed back to the image kernel.
+
+Although in principle, the image might be loaded into memory and the
+pre-hibernation memory contents restored by the boot loader, in practice this
+can't be done because boot loaders aren't smart enough and there is no
+established protocol for passing the necessary information.  So instead, the
+boot loader loads a fresh instance of the kernel, called the boot kernel, into
+memory and passes control to it in the usual way.  Then the boot kernel reads
+the system image, restores the pre-hibernation memory contents, and passes
+control to the image kernel.  Thus two different kernels are involved in
+resuming from hibernation.  In fact, the boot kernel may be completely different
+from the image kernel: a different configuration and even a different version.
+This has important consequences for device drivers and their subsystems.
+
+To be able to load the system image into memory, the boot kernel needs to
+include at least a subset of device drivers allowing it to access the storage
+medium containing the image, although it doesn't need to include all of the
+drivers present in the image kernel.  After the image has been loaded, the
+devices managed by the boot kernel need to be prepared for passing control back
+to the image kernel.  This is very similar to the initial steps involved in
+creating a system image, and it is accomplished in the same way, using prepare,
+freeze, and freeze_noirq phases.  However the devices affected by these phases
+are only those having drivers in the boot kernel; other devices will still be in
+whatever state the boot loader left them.
+
+Should the restoration of the pre-hibernation memory contents fail, the boot
+kernel would go through the "thawing" procedure described above, using the
+thaw_noirq, thaw, and complete phases, and then continue running normally.  This
+happens only rarely.  Most often the pre-hibernation memory contents are
+restored successfully and control is passed to the image kernel, which then
+becomes responsible for bringing the system back to the working state.
+
+To achieve this, the image kernel must restore the devices' pre-hibernation
+functionality.  The operation is much like waking up from the memory sleep
+state, although it involves different phases:
+
+        restore_noirq, restore, complete
+
+    1.  The restore_noirq phase is analogous to the resume_noirq phase.
+
+    2.  The restore phase is analogous to the resume phase.
+
+    3.  The complete phase is discussed above.
+
+The main difference from resume[_noirq] is that restore[_noirq] must assume the
+device has been accessed and reconfigured by the boot loader or the boot kernel.
+Consequently the state of the device may be different from the state remembered
+from the freeze and freeze_noirq phases.  The device may even need to be reset
+and completely re-initialized.  In many cases this difference doesn't matter, so
+the resume[_noirq] and restore[_norq] method pointers can be set to the same
+routines.  Nevertheless, different callback pointers are used in case there is a
+situation where it actually matters.
 
-If a driver (or bus, or class) fails it suspend method, the system won't
-enter the desired low power state; it will resume all the devices it's
-suspended so far.
 
-Note that drivers may need to perform different actions based on the target
-system lowpower/sleep state.  At this writing, there are only platform
-specific APIs through which drivers could determine those target states.
+System Devices
+--------------
+System devices (sysdevs) follow a slightly different API, which can be found in
+
+        include/linux/sysdev.h
+        drivers/base/sys.c
+
+System devices will be suspended with interrupts disabled, and after all other
+devices have been suspended.  On resume, they will be resumed before any other
+devices, and also with interrupts disabled.  These things occur in special
+"sysdev_driver" phases, which affect only system devices.
+
+Thus, after the suspend_noirq (or freeze_noirq or poweroff_noirq) phase, when
+the non-boot CPUs are all offline and IRQs are disabled on the remaining online
+CPU, then a sysdev_driver.suspend phase is carried out, and the system enters a
+sleep state (or a system image is created).  During resume (or after the image
+has been created or loaded) a sysdev_driver.resume phase is carried out, IRQs
+are enabled on the only online CPU, the non-boot CPUs are enabled, and the
+resume_noirq (or thaw_noirq or restore_noirq) phase begins.
+
+Code to actually enter and exit the system-wide low power state sometimes
+involves hardware details that are only known to the boot firmware, and
+may leave a CPU running software (from SRAM or flash memory) that monitors
+the system and manages its wakeup sequence.
 
 
 Device Low Power (suspend) States
 ---------------------------------
-Device low-power states aren't very standard.  One device might only handle
+Device low-power states aren't standard.  One device might only handle
 "on" and "off, while another might support a dozen different versions of
 "on" (how many engines are active?), plus a state that gets back to "on"
 faster than from a full "off".
@@ -265,7 +546,7 @@ PCI device may not perform DMA or issue IRQs, and any wakeup events it
 issues would be issued through the PME# bus signal.  Plus, there are
 several PCI-standard device states, some of which are optional.
 
-In contrast, integrated system-on-chip processors often use irqs as the
+In contrast, integrated system-on-chip processors often use IRQs as the
 wakeup event sources (so drivers would call enable_irq_wake) and might
 be able to treat DMA completion as a wakeup event (sometimes DMA can stay
 active too, it'd only be the CPU and some peripherals that sleep).
@@ -284,120 +565,17 @@ ways; the aforementioned LCD might be active in one product's "standby",
 but a different product using the same SOC might work differently.
 
 
-Meaning of pm_message_t.event
------------------------------
-Parameters to suspend calls include the device affected and a message of
-type pm_message_t, which has one field:  the event.  If driver does not
-recognize the event code, suspend calls may abort the request and return
-a negative errno.  However, most drivers will be fine if they implement
-PM_EVENT_SUSPEND semantics for all messages.
+Power Management Notifiers
+--------------------------
+There are some operations that cannot be carried out by the power management
+callbacks discussed above, because the callbacks occur too late or too early.
+To handle these cases, subsystems and device drivers may register power
+management notifiers that are called before tasks are frozen and after they have
+been thawed.  Generally speaking, the PM notifiers are suitable for performing
+actions that either require user space to be available, or at least won't
+interfere with user space.
 
-The event codes are used to refine the goal of suspending the device, and
-mostly matter when creating or resuming system memory image snapshots, as
-used with suspend-to-disk:
-
-    PM_EVENT_SUSPEND -- quiesce the driver and put hardware into a low-power
-        state.  When used with system sleep states like "suspend-to-RAM" or
-        "standby", the upcoming resume() call will often be able to rely on
-        state kept in hardware, or issue system wakeup events.
-
-    PM_EVENT_HIBERNATE -- Put hardware into a low-power state and enable wakeup
-        events as appropriate.  It is only used with hibernation
-        (suspend-to-disk) and few devices are able to wake up the system from
-        this state; most are completely powered off.
-
-    PM_EVENT_FREEZE -- quiesce the driver, but don't necessarily change into
-        any low power mode.  A system snapshot is about to be taken, often
-        followed by a call to the driver's resume() method.  Neither wakeup
-        events nor DMA are allowed.
-
-    PM_EVENT_PRETHAW -- quiesce the driver, knowing that the upcoming resume()
-        will restore a suspend-to-disk snapshot from a different kernel image.
-        Drivers that are smart enough to look at their hardware state during
-        resume() processing need that state to be correct ... a PRETHAW could
-        be used to invalidate that state (by resetting the device), like a
-        shutdown() invocation would before a kexec() or system halt.  Other
-        drivers might handle this the same way as PM_EVENT_FREEZE.  Neither
-        wakeup events nor DMA are allowed.
-
-To enter "standby" (ACPI S1) or "Suspend to RAM" (STR, ACPI S3) states, or
-the similarly named APM states, only PM_EVENT_SUSPEND is used; the other event
-codes are used for hibernation ("Suspend to Disk", STD, ACPI S4).
-
-There's also PM_EVENT_ON, a value which never appears as a suspend event
-but is sometimes used to record the "not suspended" device state.
-
-
-Resuming Devices
-----------------
-Resuming is done in multiple phases, much like suspending, with all
-devices processing each phase's calls before the next phase begins.
-
-The phases are seen by driver notifications issued in this order:
-
-   1    bus.resume(dev) reverses the effects of bus.suspend().  This may
-        be morphed into a device driver call with bus-specific parameters;
-        implementations may sleep.
-
-   2    class.resume(dev) is called for devices associated with a class
-        that has such a method.  Implementations may sleep.
-
-        This reverses the effects of class.suspend(), and would usually
-        reactivate the device's I/O queue.
-
-At the end of those phases, drivers should normally be as functional as
-they were before suspending:  I/O can be performed using DMA and IRQs, and
-the relevant clocks are gated on.  The device need not be "fully on"; it
-might be in a runtime lowpower/suspend state that acts as if it were.
-
-However, the details here may again be platform-specific.  For example,
-some systems support multiple "run" states, and the mode in effect at
-the end of resume() might not be the one which preceded suspension.
-That means availability of certain clocks or power supplies changed,
-which could easily affect how a driver works.
-
-
-Drivers need to be able to handle hardware which has been reset since the
-suspend methods were called, for example by complete reinitialization.
-This may be the hardest part, and the one most protected by NDA'd documents
-and chip errata.  It's simplest if the hardware state hasn't changed since
-the suspend() was called, but that can't always be guaranteed.
-
-Drivers must also be prepared to notice that the device has been removed
-while the system was powered off, whenever that's physically possible.
-PCMCIA, MMC, USB, Firewire, SCSI, and even IDE are common examples of busses
-where common Linux platforms will see such removal.  Details of how drivers
-will notice and handle such removals are currently bus-specific, and often
-involve a separate thread.
-
-
-Note that the bus-specific runtime PM wakeup mechanism can exist, and might
-be defined to share some of the same driver code as for system wakeup.  For
-example, a bus-specific device driver's resume() method might be used there,
-so it wouldn't only be called from bus.resume() during system-wide wakeup.
-See bus-specific information about how runtime wakeup events are handled.
-
-
-System Devices
---------------
-System devices follow a slightly different API, which can be found in
-
-        include/linux/sysdev.h
-        drivers/base/sys.c
-
-System devices will only be suspended with interrupts disabled, and after
-all other devices have been suspended.  On resume, they will be resumed
-before any other devices, and also with interrupts disabled.
-
-That is, IRQs are disabled, the suspend_late() phase begins, then the
-sysdev_driver.suspend() phase, and the system enters a sleep state.  Then
-the sysdev_driver.resume() phase begins, followed by the resume_early()
-phase, after which IRQs are enabled.
-
-Code to actually enter and exit the system-wide low power state sometimes
-involves hardware details that are only known to the boot firmware, and
-may leave a CPU running software (from SRAM or flash memory) that monitors
-the system and manages its wakeup sequence.
+For details refer to Documentation/power/notifiers.txt.
 
 
 Runtime Power Management
@@ -407,82 +585,23 @@ running. This feature is useful for devices that are not being used, and
 can offer significant power savings on a running system.  These devices
 often support a range of runtime power states, which might use names such
 as "off", "sleep", "idle", "active", and so on.  Those states will in some
-cases (like PCI) be partially constrained by a bus the device uses, and will
+cases (like PCI) be partially constrained by the bus the device uses, and will
 usually include hardware states that are also used in system sleep states.
 
-However, note that if a driver puts a device into a runtime low power state
-and the system then goes into a system-wide sleep state, it normally ought
-to resume into that runtime low power state rather than "full on".  Such
-distinctions would be part of the driver-internal state machine for that
-hardware; the whole point of runtime power management is to be sure that
-drivers are decoupled in that way from the state machine governing phases
-of the system-wide power/sleep state transitions.
-
-
-Power Saving Techniques
------------------------
-Normally runtime power management is handled by the drivers without specific
-userspace or kernel intervention, by device-aware use of techniques like:
-
-    Using information provided by other system layers
-        - stay deeply "off" except between open() and close()
-        - if transceiver/PHY indicates "nobody connected", stay "off"
-        - application protocols may include power commands or hints
-
-    Using fewer CPU cycles
-        - using DMA instead of PIO
-        - removing timers, or making them lower frequency
-        - shortening "hot" code paths
-        - eliminating cache misses
-        - (sometimes) offloading work to device firmware
-
-    Reducing other resource costs
-        - gating off unused clocks in software (or hardware)
-        - switching off unused power supplies
-        - eliminating (or delaying/merging) IRQs
-        - tuning DMA to use word and/or burst modes
-
-    Using device-specific low power states
-        - using lower voltages
-        - avoiding needless DMA transfers
-
-Read your hardware documentation carefully to see the opportunities that
-may be available.  If you can, measure the actual power usage and check
-it against the budget established for your project.
-
-
-Examples:  USB hosts, system timer, system CPU
-----------------------------------------------
-USB host controllers make interesting, if complex, examples.  In many cases
-these have no work to do:  no USB devices are connected, or all of them are
-in the USB "suspend" state.  Linux host controller drivers can then disable
-periodic DMA transfers that would otherwise be a constant power drain on the
-memory subsystem, and enter a suspend state.  In power-aware controllers,
-entering that suspend state may disable the clock used with USB signaling,
-saving a certain amount of power.
-
-The controller will be woken from that state (with an IRQ) by changes to the
-signal state on the data lines of a given port, for example by an existing
-peripheral requesting "remote wakeup" or by plugging a new peripheral.  The
-same wakeup mechanism usually works from "standby" sleep states, and on some
-systems also from "suspend to RAM" (or even "suspend to disk") states.
-(Except that ACPI may be involved instead of normal IRQs, on some hardware.)
-
-System devices like timers and CPUs may have special roles in the platform
-power management scheme.  For example, system timers using a "dynamic tick"
-approach don't just save CPU cycles (by eliminating needless timer IRQs),
-but they may also open the door to using lower power CPU "idle" states that
-cost more than a jiffie to enter and exit.  On x86 systems these are states
-like "C3"; note that periodic DMA transfers from a USB host controller will
-also prevent entry to a C3 state, much like a periodic timer IRQ.
-
-That kind of runtime mechanism interaction is common.  "System On Chip" (SOC)
-processors often have low power idle modes that can't be entered unless
-certain medium-speed clocks (often 12 or 48 MHz) are gated off.  When the
-drivers gate those clocks effectively, then the system idle task may be able
-to use the lower power idle modes and thereby increase battery life.
-
-If the CPU can have a "cpufreq" driver, there also may be opportunities
-to shift to lower voltage settings and reduce the power cost of executing
-a given number of instructions.  (Without voltage adjustment, it's rare
-for cpufreq to save much power; the cost-per-instruction must go down.)
+A system-wide power transition can be started while some devices are in low
+power states due to runtime power management.  The system sleep PM callbacks
+should recognize such situations and react to them appropriately, but the
+necessary actions are subsystem-specific.
+
+In some cases the decision may be made at the subsystem level while in other
+cases the device driver may be left to decide.  In some cases it may be
+desirable to leave a suspended device in that state during a system-wide power
+transition, but in other cases the device must be put back into the full-power
+state temporarily, for example so that its system wakeup capability can be
+disabled.  This all depends on the hardware and the design of the subsystem and
+device driver in question.
+
+During system-wide resume from a sleep state it's best to put devices into the
+full-power state, as explained in Documentation/power/runtime_pm.txt.  Refer to
+that document for more information regarding this particular issue as well as
+for information on the device runtime power management framework in general.
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index c40866e8b957..bfed898a03fc 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -18,44 +18,46 @@ and pm_qos_params.h.  This is done because having the available parameters
 being runtime configurable or changeable from a driver was seen as too easy to
 abuse.
 
-For each parameter a list of performance requirements is maintained along with
+For each parameter a list of performance requests is maintained along with
 an aggregated target value.  The aggregated target value is updated with
-changes to the requirement list or elements of the list.  Typically the
-aggregated target value is simply the max or min of the requirement values held
+changes to the request list or elements of the list.  Typically the
+aggregated target value is simply the max or min of the request values held
 in the parameter list elements.
 
 From kernel mode the use of this interface is simple:
-pm_qos_add_requirement(param_id, name, target_value):
-Will insert a named element in the list for that identified PM_QOS parameter
-with the target value.  Upon change to this list the new target is recomputed
-and any registered notifiers are called only if the target value is now
-different.
 
-pm_qos_update_requirement(param_id, name, new_target_value):
-Will search the list identified by the param_id for the named list element and
-then update its target value, calling the notification tree if the aggregated
-target is changed.  with that name is already registered.
+handle = pm_qos_add_request(param_class, target_value):
+Will insert an element into the list for that identified PM_QOS class with the
+target value.  Upon change to this list the new target is recomputed and any
+registered notifiers are called only if the target value is now different.
+Clients of pm_qos need to save the returned handle.
 
-pm_qos_remove_requirement(param_id, name):
-Will search the identified list for the named element and remove it, after
-removal it will update the aggregate target and call the notification tree if
-the target was changed as a result of removing the named requirement.
+void pm_qos_update_request(handle, new_target_value):
+Will update the list element pointed to by the handle with the new target value
+and recompute the new aggregated target, calling the notification tree if the
+target is changed.
+
+void pm_qos_remove_request(handle):
+Will remove the element.  After removal it will update the aggregate target and
+call the notification tree if the target was changed as a result of removing
+the request.
 
 
 From user mode:
-Only processes can register a pm_qos requirement.  To provide for automatic
-cleanup for process the interface requires the process to register its
-parameter requirements in the following way:
+Only processes can register a pm_qos request.  To provide for automatic
+cleanup of a process, the interface requires the process to register its
+parameter requests in the following way:
 
 To register the default pm_qos target for the specific parameter, the process
 must open one of /dev/[cpu_dma_latency, network_latency, network_throughput]
 
 As long as the device node is held open that process has a registered
-requirement on the parameter.  The name of the requirement is "process_<PID>"
-derived from the current->pid from within the open system call.
+request on the parameter.
 
-To change the requested target value the process needs to write a s32 value to
-the open device node.  This translates to a pm_qos_update_requirement call.
+To change the requested target value the process needs to write an s32 value to
+the open device node.  Alternatively the user mode program could write a hex
+string for the value using 10 char long format e.g. "0x12345678".  This
+translates to a pm_qos_update_request call.
 
 To remove the user mode request for a target value simply close the device
 node.
diff --git a/Documentation/power/userland-swsusp.txt b/Documentation/power/userland-swsusp.txt
index b967cd9137d6..81680f9f5909 100644
--- a/Documentation/power/userland-swsusp.txt
+++ b/Documentation/power/userland-swsusp.txt
@@ -24,6 +24,10 @@ assumed to be in the resume mode.  The device cannot be open for simultaneous
 reading and writing.  It is also impossible to have the device open more than
 once at a time.
 
+Even opening the device has side effects. Data structures are
+allocated, and PM_HIBERNATION_PREPARE / PM_RESTORE_PREPARE chains are
+called.
+
 The ioctl() commands recognized by the device are:
 
 SNAPSHOT_FREEZE - freeze user space processes (the current process is
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index aae8355d3166..221f38be98f4 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -190,3 +190,61 @@ Example:
   for (node = rb_first(&mytree); node; node = rb_next(node))
         printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
 
+Support for Augmented rbtrees
+-----------------------------
+
+Augmented rbtree is an rbtree with "some" additional data stored in each node.
+This data can be used to augment some new functionality to rbtree.
+Augmented rbtree is an optional feature built on top of basic rbtree
+infrastructure. rbtree user who wants this feature will have an augment
+callback function in rb_root initialized.
+
+This callback function will be called from rbtree core routines whenever
+a node has a change in one or both of its children. It is the responsibility
+of the callback function to recalculate the additional data that is in the
+rb node using new children information. Note that if this new additional
+data affects the parent node's additional data, then callback function has
+to handle it and do the recursive updates.
+
+
+Interval tree is an example of augmented rb tree. Reference -
+"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
+More details about interval trees:
+
+Classical rbtree has a single key and it cannot be directly used to store
+interval ranges like [lo:hi] and do a quick lookup for any overlap with a new
+lo:hi or to find whether there is an exact match for a new lo:hi.
+
+However, rbtree can be augmented to store such interval ranges in a structured
+way making it possible to do efficient lookup and exact match.
+
+This "extra information" stored in each node is the maximum hi
+(max_hi) value among all the nodes that are its descendents. This
+information can be maintained at each node just be looking at the node
+and its immediate children. And this will be used in O(log n) lookup
+for lowest match (lowest start address among all possible matches)
+with something like:
+
+find_lowest_match(lo, hi, node)
+{
+        lowest_match = NULL;
+        while (node) {
+                if (max_hi(node->left) > lo) {
+                        // Lowest overlap if any must be on left side
+                        node = node->left;
+                } else if (overlap(lo, hi, node)) {
+                        lowest_match = node;
+                        break;
+                } else if (lo > node->lo) {
+                        // Lowest overlap if any must be on right side
+                        node = node->right;
+                } else {
+                        break;
+                }
+        }
+        return lowest_match;
+}
+
+Finding exact match will be to first find lowest match and then to follow
+successor nodes looking for exact match, until the start of a node is beyond
+the hi value we are looking for.
diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index 6f33593e59e2..8239ebbcddce 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -211,7 +211,7 @@ provide fair CPU time to each such task group.  For example, it may be
 desirable to first provide fair CPU time to each user on the system and then to
 each task belonging to a user.
 
-CONFIG_GROUP_SCHED strives to achieve exactly that.  It lets tasks to be
+CONFIG_CGROUP_SCHED strives to achieve exactly that.  It lets tasks to be
 grouped and divides CPU time fairly among such groups.
 
 CONFIG_RT_GROUP_SCHED permits to group real-time (i.e., SCHED_FIFO and
@@ -220,38 +220,11 @@ SCHED_RR) tasks.
 CONFIG_FAIR_GROUP_SCHED permits to group CFS (i.e., SCHED_NORMAL and
 SCHED_BATCH) tasks.
 
-At present, there are two (mutually exclusive) mechanisms to group tasks for
-CPU bandwidth control purposes:
-
- - Based on user id (CONFIG_USER_SCHED)
-
-   With this option, tasks are grouped according to their user id.
-
- - Based on "cgroup" pseudo filesystem (CONFIG_CGROUP_SCHED)
-
-   This options needs CONFIG_CGROUPS to be defined, and lets the administrator
+   These options need CONFIG_CGROUPS to be defined, and let the administrator
    create arbitrary groups of tasks, using the "cgroup" pseudo filesystem.  See
    Documentation/cgroups/cgroups.txt for more information about this filesystem.
 
-Only one of these options to group tasks can be chosen and not both.
-
-When CONFIG_USER_SCHED is defined, a directory is created in sysfs for each new
-user and a "cpu_share" file is added in that directory.
-
-        # cd /sys/kernel/uids
-        # cat 512/cpu_share             # Display user 512's CPU share
-        1024
-        # echo 2048 > 512/cpu_share     # Modify user 512's CPU share
-        # cat 512/cpu_share             # Display user 512's CPU share
-        2048
-        #
-
-CPU bandwidth between two users is divided in the ratio of their CPU shares.
-For example: if you would like user "root" to get twice the bandwidth of user
-"guest," then set the cpu_share for both the users such that "root"'s cpu_share
-is twice "guest"'s cpu_share.
-
-When CONFIG_CGROUP_SCHED is defined, a "cpu.shares" file is created for each
+When CONFIG_FAIR_GROUP_SCHED is defined, a "cpu.shares" file is created for each
 group created using the pseudo filesystem.  See example steps below to create
 task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
@@ -273,24 +246,3 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem.
 
         # #Launch gmplayer (or your favourite movie player)
         # echo <movie_player_pid> > multimedia/tasks
-
-8. Implementation note: user namespaces
-
-User namespaces are intended to be hierarchical.  But they are currently
-only partially implemented.  Each of those has ramifications for CFS.
-
-First, since user namespaces are hierarchical, the /sys/kernel/uids
-presentation is inadequate.  Eventually we will likely want to use sysfs
-tagging to provide private views of /sys/kernel/uids within each user
-namespace.
-
-Second, the hierarchical nature is intended to support completely
-unprivileged use of user namespaces.  So if using user groups, then
-we want the users in a user namespace to be children of the user
-who created it.
-
-That is currently unimplemented.  So instead, every user in a new
-user namespace will receive 1024 shares just like any user in the
-initial user namespace.  Note that at the moment creation of a new
-user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and
-CAP_SETGID.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 86eabe6c3419..605b0d40329d 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -126,23 +126,12 @@ priority!
 2.3 Basis for grouping tasks
 ----------------------------
 
-There are two compile-time settings for allocating CPU bandwidth. These are
-configured using the "Basis for grouping tasks" multiple choice menu under
-General setup > Group CPU Scheduler:
-
-a. CONFIG_USER_SCHED (aka "Basis for grouping tasks" =  "user id")
-
-This lets you use the virtual files under
-"/sys/kernel/uids/<uid>/cpu_rt_runtime_us" to control he CPU time reserved for
-each user .
-
-The other option is:
-
-.o CONFIG_CGROUP_SCHED (aka "Basis for grouping tasks" = "Control groups")
+Enabling CONFIG_RT_GROUP_SCHED lets you explicitly allocate real
+CPU bandwidth to task groups.
 
 This uses the /cgroup virtual file system and
 "/cgroup/<cgroup>/cpu.rt_runtime_us" to control the CPU time reserved for each
-control group instead.
+control group.
 
 For more information on working with control groups, you should read
 Documentation/cgroups/cgroups.txt as well.
@@ -161,8 +150,7 @@ For now, this can be simplified to just the following (but see Future plans):
 ===============
 
 There is work in progress to make the scheduling period for each group
-("/sys/kernel/uids/<uid>/cpu_rt_period_us" or
-"/cgroup/<cgroup>/cpu.rt_period_us" respectively) configurable as well.
+("/cgroup/<cgroup>/cpu.rt_period_us") configurable as well.
 
 The constraint on the period is that a subgroup must have a smaller or
 equal period to its parent. But realistically its not very useful _yet_
diff --git a/Documentation/spi/spidev_test.c b/Documentation/spi/spidev_test.c
index 10abd3773e49..16feda901469 100644
--- a/Documentation/spi/spidev_test.c
+++ b/Documentation/spi/spidev_test.c
@@ -58,7 +58,7 @@ static void transfer(int fd)
         };
 
         ret = ioctl(fd, SPI_IOC_MESSAGE(1), &tr);
-        if (ret == 1)
+        if (ret < 1)
                 pabort("can't send spi message");
 
         for (ret = 0; ret < ARRAY_SIZE(tx); ret++) {
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index 5effa5bd993b..e213f45cf9d7 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -18,16 +18,15 @@ Rules on what kind of patches are accepted, and which ones are not, into the
  - It cannot contain any "trivial" fixes in it (spelling changes,
    whitespace cleanups, etc).
  - It must follow the Documentation/SubmittingPatches rules.
- - It or an equivalent fix must already exist in Linus' tree.  Quote the
-   respective commit ID in Linus' tree in your patch submission to -stable.
+ - It or an equivalent fix must already exist in Linus' tree (upstream).
 
 
 Procedure for submitting patches to the -stable tree:
 
  - Send the patch, after verifying that it follows the above rules, to
-   stable@kernel.org.
- - To have the patch automatically included in the stable tree, add the
-   the tag
+   stable@kernel.org.  You must note the upstream commit ID in the changelog
+   of your submission.
+ - To have the patch automatically included in the stable tree, add the tag
      Cc: stable@kernel.org
    in the sign-off area. Once the patch is merged it will be applied to
    the stable tree without anything else needing to be done by the author
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index b22000dbc57d..09bd8e902989 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -90,7 +90,8 @@ In order to facilitate early boot debugging, use boot option:
 
         trace_event=[event-list]
 
-The format of this boot option is the same as described in section 2.1.
+event-list is a comma separated list of events. See section 2.1 for event
+format.
 
 3. Defining an event-enabled tracepoint
 =======================================
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index 03485bfbd797..557c1edeccaf 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -155,6 +155,9 @@ of ftrace. Here is a list of some of the key files:
         to be traced. Echoing names of functions into this file
         will limit the trace to only those functions.
 
+        This interface also allows for commands to be used. See the
+        "Filter commands" section for more details.
+
   set_ftrace_notrace:
 
         This has an effect opposite to that of
@@ -1337,12 +1340,14 @@ ftrace_dump_on_oops must be set. To set ftrace_dump_on_oops, one
 can either use the sysctl function or set it via the proc system
 interface.
 
-  sysctl kernel.ftrace_dump_on_oops=1
+  sysctl kernel.ftrace_dump_on_oops=n
 
 or
 
-  echo 1 > /proc/sys/kernel/ftrace_dump_on_oops
+  echo n > /proc/sys/kernel/ftrace_dump_on_oops
 
+If n = 1, ftrace will dump buffers of all CPUs, if n = 2 ftrace will
+only dump the buffer of the CPU that triggered the oops.
 
 Here's an example of such a dump after a null pointer
 dereference in a kernel module:
@@ -1822,6 +1827,47 @@ this special filter via:
  echo > set_graph_function
 
 
+Filter commands
+---------------
+
+A few commands are supported by the set_ftrace_filter interface.
+Trace commands have the following format:
+
+<function>:<command>:<parameter>
+
+The following commands are supported:
+
+- mod
+  This command enables function filtering per module. The
+  parameter defines the module. For example, if only the write*
+  functions in the ext3 module are desired, run:
+
+   echo 'write*:mod:ext3' > set_ftrace_filter
+
+  This command interacts with the filter in the same way as
+  filtering based on function names. Thus, adding more functions
+  in a different module is accomplished by appending (>>) to the
+  filter file. Remove specific module functions by prepending
+  '!':
+
+   echo '!writeback*:mod:ext3' >> set_ftrace_filter
+
+- traceon/traceoff
+  These commands turn tracing on and off when the specified
+  functions are hit. The parameter determines how many times the
+  tracing system is turned on and off. If unspecified, there is
+  no limit. For example, to disable tracing when a schedule bug
+  is hit the first 5 times, run:
+
+   echo '__schedule_bug:traceoff:5' > set_ftrace_filter
+
+  These commands are cumulative whether or not they are appended
+  to set_ftrace_filter. To remove a command, prepend it by '!'
+  and drop the parameter:
+
+   echo '!__schedule_bug:traceoff' > set_ftrace_filter
+
+
 trace_pipe
 ----------
 
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index a9100b28eb84..ec94748ae65b 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -40,7 +40,9 @@ Synopsis of kprobe_events
   $stack        : Fetch stack address.
   $retval       : Fetch return value.(*)
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
-  NAME=FETCHARG: Set NAME as the argument name of FETCHARG.
+  NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
+  FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
+                  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.