Merge branch 'linus' into core/rcu

Conflicts:

	include/linux/rculist.h
	kernel/rcupreempt.c

Signed-off-by: Ingo Molnar <mingo@elte.hu>

16 files changed, 1421 insertions, 30 deletions

diff --git a/Documentation/accounting/taskstats-struct.txt b/Documentation/accounting/taskstats-struct.txt
index 8aa7529f825..cd784f46bf8 100644
--- a/Documentation/accounting/taskstats-struct.txt
+++ b/Documentation/accounting/taskstats-struct.txt
@@ -24,6 +24,8 @@ There are three different groups of fields in the struct taskstats:
 
 4) Per-task and per-thread context switch count statistics
 
+5) Time accounting for SMT machines
+
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
 
@@ -164,4 +166,8 @@ struct taskstats {
 	__u64	nvcsw;			/* Context voluntary switch counter */
 	__u64	nivcsw;			/* Context involuntary switch counter */
 
+5) Time accounting for SMT machines
+	__u64	ac_utimescaled;		/* utime scaled on frequency etc */
+	__u64	ac_stimescaled;		/* stime scaled on frequency etc */
+	__u64	cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
 }
diff --git a/Documentation/auxdisplay/cfag12864b b/Documentation/auxdisplay/cfag12864b
index b714183d412..eb7be393a51 100644
--- a/Documentation/auxdisplay/cfag12864b
+++ b/Documentation/auxdisplay/cfag12864b
@@ -3,7 +3,7 @@
 	===================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -22,7 +22,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support one cfag12864b display at time.
+This driver supports a cfag12864b LCD.
 
 
 ---------------------
diff --git a/Documentation/auxdisplay/cfag12864b-example.c b/Documentation/auxdisplay/cfag12864b-example.c
index 7bfac354d4c..2caeea5e499 100644
--- a/Documentation/auxdisplay/cfag12864b-example.c
+++ b/Documentation/auxdisplay/cfag12864b-example.c
@@ -4,7 +4,7 @@
  * Description: cfag12864b LCD userspace example program
  *     License: GPLv2
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify
diff --git a/Documentation/auxdisplay/ks0108 b/Documentation/auxdisplay/ks0108
index 92b03b60c61..8ddda0c8cee 100644
--- a/Documentation/auxdisplay/ks0108
+++ b/Documentation/auxdisplay/ks0108
@@ -3,7 +3,7 @@
 	==========================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -21,7 +21,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support the ks0108 LCD controller.
+This driver supports the ks0108 LCD controller.
 
 
 ---------------------
diff --git a/Documentation/cgroups.txt b/Documentation/cgroups.txt
index 824fc027447..d9014aa0eb6 100644
--- a/Documentation/cgroups.txt
+++ b/Documentation/cgroups.txt
@@ -390,6 +390,10 @@ If you have several tasks to attach, you have to do it one after another:
 	...
 # /bin/echo PIDn > tasks
 
+You can attach the current shell task by echoing 0:
+
+# echo 0 > tasks
+
 3. Kernel API
 =============
 
diff --git a/Documentation/controllers/devices.txt b/Documentation/controllers/devices.txt
index 4dcea42432c..7cc6e6a6067 100644
--- a/Documentation/controllers/devices.txt
+++ b/Documentation/controllers/devices.txt
@@ -13,7 +13,7 @@ either an integer or * for all.  Access is a composition of r
 The root device cgroup starts with rwm to 'all'.  A child device
 cgroup gets a copy of the parent.  Administrators can then remove
 devices from the whitelist or add new entries.  A child cgroup can
-never receive a device access which is denied its parent.  However
+never receive a device access which is denied by its parent.  However
 when a device access is removed from a parent it will not also be
 removed from the child(ren).
 
@@ -29,7 +29,11 @@ allows cgroup 1 to read and mknod the device usually known as
 
 	echo a > /cgroups/1/devices.deny
 
-will remove the default 'a *:* mrw' entry.
+will remove the default 'a *:* rwm' entry. Doing
+
+	echo a > /cgroups/1/devices.allow
+
+will add the 'a *:* rwm' entry to the whitelist.
 
 3. Security
 
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index 353504de308..1f5a924d1e5 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -154,13 +154,15 @@ browsing and modifying the cpusets presently known to the kernel.  No
 new system calls are added for cpusets - all support for querying and
 modifying cpusets is via this cpuset file system.
 
-The /proc/<pid>/status file for each task has two added lines,
+The /proc/<pid>/status file for each task has four added lines,
 displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
 and mems_allowed (on which Memory Nodes it may obtain memory),
-in the format seen in the following example:
+in the two formats seen in the following example:
 
   Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
+  Cpus_allowed_list:      0-127
   Mems_allowed:   ffffffff,ffffffff
+  Mems_allowed_list:      0-63
 
 Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
@@ -544,6 +546,9 @@ otherwise initial value -1 that indicates the cpuset has no request.
  ( 4  : search nodes in a chunk of node [on NUMA system] )
  ( 5  : search system wide [on NUMA system] )
 
+The system default is architecture dependent.  The system default
+can be changed using the relax_domain_level= boot parameter.
+
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
 is disabled, then 'sched_relax_domain_level' have no effect since
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 5b3f31faed5..46ece3fba6f 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -312,3 +312,12 @@ When:	2.6.26
 Why:	Implementation became generic; users should now include
 	linux/semaphore.h instead.
 Who:	Matthew Wilcox <willy@linux.intel.com>
+
+---------------------------
+
+What:	CONFIG_THERMAL_HWMON
+When:	January 2009
+Why:	This option was introduced just to allow older lm-sensors userspace
+	to keep working over the upgrade to 2.6.26. At the scheduled time of
+	removal fixed lm-sensors (2.x or 3.x) should be readily available.
+Who:	Rene Herman <rene.herman@gmail.com>
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
new file mode 100644
index 00000000000..13e4bf054c3
--- /dev/null
+++ b/Documentation/ftrace.txt
@@ -0,0 +1,1353 @@
+		ftrace - Function Tracer
+		========================
+
+Copyright 2008 Red Hat Inc.
+Author: Steven Rostedt <srostedt@redhat.com>
+
+
+Introduction
+------------
+
+Ftrace is an internal tracer designed to help out developers and
+designers of systems to find what is going on inside the kernel.
+It can be used for debugging or analyzing latencies and performance
+issues that take place outside of user-space.
+
+Although ftrace is the function tracer, it also includes an
+infrastructure that allows for other types of tracing. Some of the
+tracers that are currently in ftrace is a tracer to trace
+context switches, the time it takes for a high priority task to
+run after it was woken up, the time interrupts are disabled, and
+more.
+
+
+The File System
+---------------
+
+Ftrace uses the debugfs file system to hold the control files as well
+as the files to display output.
+
+To mount the debugfs system:
+
+  # mkdir /debug
+  # mount -t debugfs nodev /debug
+
+
+That's it! (assuming that you have ftrace configured into your kernel)
+
+After mounting the debugfs, you can see a directory called
+"tracing".  This directory contains the control and output files
+of ftrace. Here is a list of some of the key files:
+
+
+ Note: all time values are in microseconds.
+
+  current_tracer : This is used to set or display the current tracer
+		that is configured.
+
+  available_tracers : This holds the different types of tracers that
+		has been compiled into the kernel. The tracers
+		listed here can be configured by echoing in their
+		name into current_tracer.
+
+  tracing_enabled : This sets or displays whether the current_tracer
+		is activated and tracing or not. Echo 0 into this
+		file to disable the tracer or 1 (or non-zero) to
+		enable it.
+
+  trace : This file holds the output of the trace in a human readable
+		format.
+
+  latency_trace : This file shows the same trace but the information
+		is organized more to display possible latencies
+		in the system.
+
+  trace_pipe : The output is the same as the "trace" file but this
+		file is meant to be streamed with live tracing.
+		Reads from this file will block until new data
+		is retrieved. Unlike the "trace" and "latency_trace"
+		files, this file is a consumer. This means reading
+		from this file causes sequential reads to display
+		more current data. Once data is read from this
+		file, it is consumed, and will not be read
+		again with a sequential read. The "trace" and
+		"latency_trace" files are static, and if the
+		tracer isn't adding more data, they will display
+		the same information every time they are read.
+
+  iter_ctrl : This file lets the user control the amount of data
+		that is displayed in one of the above output
+		files.
+
+  trace_max_latency : Some of the tracers record the max latency.
+		For example, the time interrupts are disabled.
+		This time is saved in this file. The max trace
+		will also be stored, and displayed by either
+		"trace" or "latency_trace".  A new max trace will
+		only be recorded if the latency is greater than
+		the value in this file. (in microseconds)
+
+  trace_entries : This sets or displays the number of trace
+		entries each CPU buffer can hold. The tracer buffers
+		are the same size for each CPU, so care must be
+		taken when modifying the trace_entries. The number
+		of actually entries will be the number given
+		times the number of possible CPUS. The buffers
+		are saved as individual pages, and the actual entries
+		will always be rounded up to entries per page.
+
+		This can only be updated when the current_tracer
+		is set to "none".
+
+		NOTE: It is planned on changing the allocated buffers
+		      from being the number of possible CPUS to
+		      the number of online CPUS.
+
+  tracing_cpumask : This is a mask that lets the user only trace
+		on specified CPUS. The format is a hex string
+		representing the CPUS.
+
+  set_ftrace_filter : When dynamic ftrace is configured in, the
+		code is dynamically modified to disable calling
+		of the function profiler (mcount). This lets
+		tracing be configured in with practically no overhead
+		in performance.  This also has a side effect of
+		enabling or disabling specific functions to be
+		traced.  Echoing in names of functions into this
+		file will limit the trace to only those files.
+
+  set_ftrace_notrace: This has the opposite effect that
+		set_ftrace_filter has. Any function that is added
+		here will not be traced. If a function exists
+		in both set_ftrace_filter and set_ftrace_notrace
+		the function will _not_ bet traced.
+
+  available_filter_functions : When a function is encountered the first
+		time by the dynamic tracer, it is recorded and
+		later the call is converted into a nop. This file
+		lists the functions that have been recorded
+		by the dynamic tracer and these functions can
+		be used to set the ftrace filter by the above
+		"set_ftrace_filter" file.
+
+
+The Tracers
+-----------
+
+Here are the list of current tracers that can be configured.
+
+  ftrace - function tracer that uses mcount to trace all functions.
+		It is possible to filter out which functions that are
+		traced when dynamic ftrace is configured in.
+
+  sched_switch - traces the context switches between tasks.
+
+  irqsoff - traces the areas that disable interrupts and saves off
+  		the trace with the longest max latency.
+		See tracing_max_latency.  When a new max is recorded,
+		it replaces the old trace. It is best to view this
+		trace with the latency_trace file.
+
+  preemptoff - Similar to irqsoff but traces and records the time
+		preemption is disabled.
+
+  preemptirqsoff - Similar to irqsoff and preemptoff, but traces and
+		 records the largest time irqs and/or preemption is
+		 disabled.
+
+  wakeup - Traces and records the max latency that it takes for
+		the highest priority task to get scheduled after
+		it has been woken up.
+
+  none - This is not a tracer. To remove all tracers from tracing
+		simply echo "none" into current_tracer.
+
+
+Examples of using the tracer
+----------------------------
+
+Here are typical examples of using the tracers with only controlling
+them with the debugfs interface (without using any user-land utilities).
+
+Output format:
+--------------
+
+Here's an example of the output format of the file "trace"
+
+                             --------
+# tracer: ftrace
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-4251  [01] 10152.583854: path_put <-path_walk
+            bash-4251  [01] 10152.583855: dput <-path_put
+            bash-4251  [01] 10152.583855: _atomic_dec_and_lock <-dput
+                             --------
+
+A header is printed with the trace that is represented. In this case
+the tracer is "ftrace". Then a header showing the format. Task name
+"bash", the task PID "4251", the CPU that it was running on
+"01", the timestamp in <secs>.<usecs> format, the function name that was
+traced "path_put" and the parent function that called this function
+"path_walk".
+
+The sched_switch tracer also includes tracing of task wake ups and
+context switches.
+
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +  2916:115:S
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R   +    10:115:S
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:R ==>    10:115:R
+        events/1-10    [01]  1453.070013:     10:115:S ==>  2916:115:R
+     kondemand/1-2916  [01]  1453.070013:   2916:115:S ==>     7:115:R
+     ksoftirqd/1-7     [01]  1453.070013:      7:115:S ==>     0:140:R
+
+Wake ups are represented by a "+" and the context switches show
+"==>".  The format is:
+
+ Context switches:
+
+       Previous task              Next Task
+
+  <pid>:<prio>:<state>  ==>  <pid>:<prio>:<state>
+
+ Wake ups:
+
+       Current task               Task waking up
+
+  <pid>:<prio>:<state>    +  <pid>:<prio>:<state>
+
+The prio is the internal kernel priority, which is inverse to the
+priority that is usually displayed by user-space tools. Zero represents
+the highest priority (99). Prio 100 starts the "nice" priorities with
+100 being equal to nice -20 and 139 being nice 19. The prio "140" is
+reserved for the idle task which is the lowest priority thread (pid 0).
+
+
+Latency trace format
+--------------------
+
+For traces that display latency times, the latency_trace file gives
+a bit more information to see why a latency happened. Here's a typical
+trace.
+
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 97 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: swapper-0 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: apic_timer_interrupt
+ => ended at:   do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+  <idle>-0     0d..1    0us+: trace_hardirqs_off_thunk (apic_timer_interrupt)
+  <idle>-0     0d.s.   97us : __do_softirq (do_softirq)
+  <idle>-0     0d.s1   98us : trace_hardirqs_on (do_softirq)
+
+
+vim:ft=help
+
+
+This shows that the current tracer is "irqsoff" tracing the time
+interrupts are disabled. It gives the trace version and the kernel
+this was executed on (2.6.26-rc8). Then it displays the max latency
+in microsecs (97 us). The number of trace entries displayed
+by the total number recorded (both are three: #3/3). The type of
+preemption that was used (PREEMPT). VP, KP, SP, and HP are always zero
+and reserved for later use. #P is the number of online CPUS (#P:2).
+
+The task is the process that was running when the latency happened.
+(swapper pid: 0).
+
+The start and stop that caused the latencies:
+
+  apic_timer_interrupt is where the interrupts were disabled.
+  do_softirq is where they were enabled again.
+
+The next lines after the header are the trace itself. The header
+explains which is which.
+
+  cmd: The name of the process in the trace.
+
+  pid: The PID of that process.
+
+  CPU#: The CPU that the process was running on.
+
+  irqs-off: 'd' interrupts are disabled. '.' otherwise.
+
+  need-resched: 'N' task need_resched is set, '.' otherwise.
+
+  hardirq/softirq:
+	'H' - hard irq happened inside a softirq.
+	'h' - hard irq is running
+	's' - soft irq is running
+	'.' - normal context.
+
+  preempt-depth: The level of preempt_disabled
+
+The above is mostly meaningful for kernel developers.
+
+  time: This differs from the trace output where as the trace output
+	contained a absolute timestamp. This timestamp is relative
+	to the start of the first entry in the the trace.
+
+  delay: This is just to help catch your eye a bit better. And
+	needs to be fixed to be only relative to the same CPU.
+	The marks is determined by the difference between this
+	current trace and the next trace.
+	 '!' - greater than preempt_mark_thresh (default 100)
+	 '+' - greater than 1 microsecond
+	 ' ' - less than or equal to 1 microsecond.
+
+  The rest is the same as the 'trace' file.
+
+
+iter_ctrl
+---------
+
+The iter_ctrl file is used to control what gets printed in the trace
+output. To see what is available, simply cat the file:
+
+  cat /debug/tracing/iter_ctrl
+  print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
+ noblock nostacktrace nosched-tree
+
+To disable one of the options, echo in the option appended with "no".
+
+  echo noprint-parent > /debug/tracing/iter_ctrl
+
+To enable an option, leave off the "no".
+
+  echo sym-offest > /debug/tracing/iter_ctrl
+
+Here are the available options:
+
+  print-parent - On function traces, display the calling function
+		as well as the function being traced.
+
+  print-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul <-strict_strtoul
+
+  noprint-parent:
+   bash-4000  [01]  1477.606694: simple_strtoul
+
+
+  sym-offset - Display not only the function name, but also the offset
+		in the function. For example, instead of seeing just
+		"ktime_get" you will see "ktime_get+0xb/0x20"
+
+  sym-offset:
+   bash-4000  [01]  1477.606694: simple_strtoul+0x6/0xa0
+
+  sym-addr - this will also display the function address as well as
+		the function name.
+
+  sym-addr:
+   bash-4000  [01]  1477.606694: simple_strtoul <c0339346>
+
+  verbose - This deals with the latency_trace file.
+
+    bash  4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
+    (+0.000ms): simple_strtoul (strict_strtoul)
+
+  raw - This will display raw numbers. This option is best for use with
+	user applications that can translate the raw numbers better than
+	having it done in the kernel.
+
+  hex - similar to raw, but the numbers will be in a hexadecimal format.
+
+  bin - This will print out the formats in raw binary.
+
+  block - TBD (needs update)
+
+  stacktrace - This is one of the options that changes the trace itself.
+		When a trace is recorded, so is the stack of functions.
+		This allows for back traces of trace sites.
+
+  sched-tree - TBD (any users??)
+
+
+sched_switch
+------------
+
+This tracer simply records schedule switches. Here's an example
+on how to implement it.
+
+ # echo sched_switch > /debug/tracing/current_tracer
+ # echo 1 > /debug/tracing/tracing_enabled
+ # sleep 1
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/trace
+
+# tracer: sched_switch
+#
+#           TASK-PID   CPU#    TIMESTAMP  FUNCTION
+#              | |      |          |         |
+            bash-3997  [01]   240.132281:   3997:120:R   +  4055:120:R
+            bash-3997  [01]   240.132284:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132371:   4055:120:S ==>  3997:120:R
+            bash-3997  [01]   240.132454:   3997:120:R   +  4055:120:S
+            bash-3997  [01]   240.132457:   3997:120:R ==>  4055:120:R
+           sleep-4055  [01]   240.132460:   4055:120:D ==>  3997:120:R
+            bash-3997  [01]   240.132463:   3997:120:R   +  4055:120:D
+            bash-3997  [01]   240.132465:   3997:120:R ==>  4055:120:R
+          <idle>-0     [00]   240.132589:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132591:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132595:      4:115:S ==>     0:140:R
+          <idle>-0     [00]   240.132598:      0:140:R   +     4:115:S
+          <idle>-0     [00]   240.132599:      0:140:R ==>     4:115:R
+     ksoftirqd/0-4     [00]   240.132603:      4:115:S ==>     0:140:R
+           sleep-4055  [01]   240.133058:   4055:120:S ==>  3997:120:R
+ [...]
+
+
+As we have discussed previously about this format, the header shows
+the name of the trace and points to the options. The "FUNCTION"
+is a misnomer since here it represents the wake ups and context
+switches.
+
+The sched_switch only lists the wake ups (represented with '+')
+and context switches ('==>') with the previous task or current
+first followed by the next task or task waking up. The format for both
+of these is PID:KERNEL-PRIO:TASK-STATE. Remember that the KERNEL-PRIO
+is the inverse of the actual priority with zero (0) being the highest
+priority and the nice values starting at 100 (nice -20). Below is
+a quick chart to map the kernel priority to user land priorities.
+
+  Kernel priority: 0 to 99    ==> user RT priority 99 to 0
+  Kernel priority: 100 to 139 ==> user nice -20 to 19
+  Kernel priority: 140        ==> idle task priority
+
+The task states are:
+
+ R - running : wants to run, may not actually be running
+ S - sleep   : process is waiting to be woken up (handles signals)
+ D - deep sleep : process must be woken up (ignores signals)
+ T - stopped : process suspended
+ t - traced  : process is being traced (with something like gdb)
+ Z - zombie  : process waiting to be cleaned up
+ X - unknown
+
+
+ftrace_enabled
+--------------
+
+The following tracers give different output depending on whether
+or not the sysctl ftrace_enabled is set. To set ftrace_enabled,
+one can either use the sysctl function or set it via the proc
+file system interface.
+
+  sysctl kernel.ftrace_enabled=1
+
+ or
+
+  echo 1 > /proc/sys/kernel/ftrace_enabled
+
+To disable ftrace_enabled simply replace the '1' with '0' in
+the above commands.
+
+When ftrace_enabled is set the tracers will also record the functions
+that are within the trace. The descriptions of the tracers
+will also show an example with ftrace enabled.
+
+
+irqsoff
+-------
+
+When interrupts are disabled, the CPU can not react to any other
+external event (besides NMIs and SMIs). This prevents the timer
+interrupt from triggering or the mouse interrupt from letting the
+kernel know of a new mouse event. The result is a latency with the
+reaction time.
+
+The irqsoff tracer tracks the time interrupts are disabled and when
+they are re-enabled. When a new maximum latency is hit, it saves off
+the trace so that it may be retrieved at a later time. Every time a
+new maximum in reached, the old saved trace is discarded and the new
+trace is saved.
+
+To reset the maximum, echo 0 into tracing_max_latency. Here's an
+example:
+
+ # echo irqsoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 6 us, #3/3, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: bash-4269 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: copy_page_range
+ => ended at:   copy_page_range
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    bash-4269  1...1    0us+: _spin_lock (copy_page_range)
+    bash-4269  1...1    7us : _spin_unlock (copy_page_range)
+    bash-4269  1...2    7us : trace_preempt_on (copy_page_range)
+
+
+vim:ft=help
+
+Here we see that that we had a latency of 6 microsecs (which is
+very good). The spin_lock in copy_page_range disabled interrupts.
+The difference between the 6 and the displayed timestamp 7us is
+because the clock must have incremented between the time of recording
+the max latency and recording the function that had that latency.
+
+Note the above had ftrace_enabled not set. If we set the ftrace_enabled
+we get a much larger output:
+
+# tracer: irqsoff
+#
+irqsoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 50 us, #101/101, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: ls-4339 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: __alloc_pages_internal
+ => ended at:   __alloc_pages_internal
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+      ls-4339  0...1    0us+: get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..1    3us : rmqueue_bulk (get_page_from_freelist)
+      ls-4339  0d..1    3us : _spin_lock (rmqueue_bulk)
+      ls-4339  0d..1    4us : add_preempt_count (_spin_lock)
+      ls-4339  0d..2    4us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    5us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    5us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    6us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    6us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2    7us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2    7us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2    8us : __rmqueue_smallest (__rmqueue)
+[...]
+      ls-4339  0d..2   46us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   47us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   47us : __rmqueue (rmqueue_bulk)
+      ls-4339  0d..2   48us : __rmqueue_smallest (__rmqueue)
+      ls-4339  0d..2   48us : __mod_zone_page_state (__rmqueue_smallest)
+      ls-4339  0d..2   49us : _spin_unlock (rmqueue_bulk)
+      ls-4339  0d..2   49us : sub_preempt_count (_spin_unlock)
+      ls-4339  0d..1   50us : get_page_from_freelist (__alloc_pages_internal)
+      ls-4339  0d..2   51us : trace_hardirqs_on (__alloc_pages_internal)
+
+
+vim:ft=help
+
+
+Here we traced a 50 microsecond latency. But we also see all the
+functions that were called during that time. Note that enabling
+function tracing we endure an added overhead. This overhead may
+extend the latency times. But never the less, this trace has provided
+some very helpful debugging.
+
+
+preemptoff
+----------
+
+When preemption is disabled we may be able to receive interrupts but
+the task can not be preempted and a higher priority task must wait
+for preemption to be enabled again before it can preempt a lower
+priority task.
+
+The preemptoff tracer traces the places that disables preemption.
+Like the irqsoff, it records the maximum latency that preemption
+was disabled. The control of preemptoff is much like the irqsoff.
+
+ # echo preemptoff > /debug/tracing/current_tracer
+ # echo 0 > /debug/tracing/tracing_max_latency
+ # echo 1 > /debug/tracing/tracing_enabled
+ # ls -ltr
+ [...]
+ # echo 0 > /debug/tracing/tracing_enabled
+ # cat /debug/tracing/latency_trace
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 29 us, #3/3, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: do_IRQ
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d.h.    0us+: irq_enter (do_IRQ)
+    sshd-4261  0d.s.   29us : _local_bh_enable (__do_softirq)
+    sshd-4261  0d.s1   30us : trace_preempt_on (__do_softirq)
+
+
+vim:ft=help
+
+This has some more changes. Preemption was disabled when an interrupt
+came in (notice the 'h'), and was enabled while doing a softirq.
+(notice the 's'). But we also see that interrupts have been disabled
+when entering the preempt off section and leaving it (the 'd').
+We do not know if interrupts were enabled in the mean time.
+
+# tracer: preemptoff
+#
+preemptoff latency trace v1.1.5 on 2.6.26-rc8
+--------------------------------------------------------------------
+ latency: 63 us, #87/87, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
+    -----------------
+    | task: sshd-4261 (uid:0 nice:0 policy:0 rt_prio:0)
+    -----------------
+ => started at: remove_wait_queue
+ => ended at:   __do_softirq
+
+#                _------=> CPU#
+#               / _-----=> irqs-off
+#              | / _----=> need-resched
+#              || / _---=> hardirq/softirq
+#              ||| / _--=> preempt-depth
+#              |||| /
+#              |||||     delay
+#  cmd     pid ||||| time  |   caller
+#     \   /    |||||   \   |   /
+    sshd-4261  0d..1    0us : _spin_lock_irqsave (remove_wait_queue)
+    sshd-4261  0d..1    1us : _spin_unlock_irqrestore (remove_wait_queue)
+    sshd-4261  0d..1    2us : do_IRQ (common_interrupt)
+    sshd-4261  0d..1    2us : irq_enter (do_IRQ)
+    sshd-4261  0d..1    2us : idle_cpu (irq_enter)
+    sshd-4261  0d..1    3us : add_preempt_count (irq_enter)
+    sshd-4261  0d.h1    3us : idle_cpu (irq_enter)
+    sshd-4261  0d.h.    4us : handle_fasteoi_irq (do_IRQ)
+[...]
+    sshd-4261  0d.h.   12us : add_preempt_count (_spin_lock)
+    sshd-4261  0d.h1   12us : ack_ioapic_quirk_irq (handle_fasteoi_irq)
+    sshd-4261  0d.h1   13us : move_native_irq (ack_ioapic_quirk_irq)
+    sshd-4261  0d.h1   13us : _spin_unlock (handle_fasteoi_irq)
+    sshd-4261  0d.h1   14us : sub_preempt_count (_spin_unlock)
+    sshd-4261  0d.h1   14us : irq_exit (do_IRQ)
+    sshd-4261  0d.h1   15us : sub_preempt_count (irq_exit)
+    sshd-4261  0d..2   15us : do_softirq (irq_exit)
+    sshd-4261