Impact: cleanup

This patch factors out common code from multiple tracers into a
tracing_reset_online_cpus() function and converts the tracers to use it.
Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: display ftrace_printk messages "as is"

By default, ftrace_printk() messages find their output with some other
informations like pid, caller, ...
Sometimes a developer just want to have the ftrace_printk left "as is", without
other information.

This is done by providing a default-off option called printk-msg-only.
To enable it, just do `echo printk-msg-only > /debugfs/tracing/trace_options`

Before the patch:

           <...>-2739  [000]   145.692153: __might_sleep: I'm an ftrace_printk msg in __might_sleep
           <...>-2739  [000]   145.692155: __might_sleep: I'm another ftrace_printk msg in __might_sleep

After the patch and the printk-msg-only option enabled:

I'm an ftrace_printk msg in __might_sleep
I'm another ftrace_printk msg in __might_sleep
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: restructure code, cleanup

Remove BTS bits from the hw-branch-tracer (renamed from bts-tracer) and
use the ds interface.
Signed-off-by: NMarkus Metzger <markut.t.metzger@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix default empty traces on function-graph-tracer

The actual ftrace_trace_task() checks if ftrace_pid_trace is allocated
and return 1 if it is true.
If it is NULL, it will check the bit of pid tracing flag for the current
task (which are not set by default).
So by default, a task is not traced.
Actually all tasks should be traced by default and filter_by_pid when
ftrace_pid_trace is allocated.

The appropriate condition should be to return 1 if filter_by_pid is
set.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acke-dby: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Handle the TRACE_PRINT entries from the function grapg tracer
and output them as a C comment just below the function that called
it, as if it was a comment inside this function.

Example with an ftrace_printk inside might_sleep() function:

void __might_sleep(char *file, int line)
{
	static unsigned long prev_jiffy;	/* ratelimiting */

	ftrace_printk("Hi I'm a comment in might_sleep() :-)");

A chunk of a resulting trace:

 0)               |        _reiserfs_free_block() {
 0)               |          reiserfs_read_bitmap_block() {
 0)               |            __bread() {
 0)               |              __getblk() {
 0)               |                __find_get_block() {
 0)   0.698 us    |                  mark_page_accessed();
 0)   2.267 us    |                }
 0)               |                __might_sleep() {
 0)               |                  /* Hi I'm a comment in might_sleep() :-) */
 0)   1.321 us    |                }
 0)   5.872 us    |              }
 0)   7.313 us    |            }
 0)   8.718 us    |          }

And this patch brings two minor fixes:

- The newline after a switch-out task has disappeared
- The "|" sign just before the cpu number on task-switch has been deleted.

 0)   0.616 us    |                pick_next_task_rt();
 0)   1.457 us    |                _spin_trylock();
 0)   0.653 us    |                _spin_unlock();
 0)   0.728 us    |                _spin_trylock();
 0)   0.631 us    |                _spin_unlock();
 0)   0.729 us    |                native_load_sp0();
 0)   0.593 us    |                native_load_tls();
 ------------------------------------------
 0)    cat-2834    =>   migrati-3
 ------------------------------------------

 0)               |    finish_task_switch() {
 0)   0.841 us    |      _spin_unlock_irq();
 0)   0.616 us    |      post_schedule_rt();
 0)   3.882 us    |    }
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix build bugs
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: clean up, extend PID filtering to PID namespaces

Eric Biederman suggested using the struct pid for filtering on
pids in the kernel. This patch is based off of a demonstration
of an implementation that Eric sent me in an email.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: New feature

This patch makes the changes to set_ftrace_pid apply to the function
graph tracer.

  # echo $$ > /debugfs/tracing/set_ftrace_pid
  # echo function_graph > /debugfs/tracing/current_tracer

Will cause only the current task to be traced. Note, the trace flags are
also inherited by child processes, so the children of the shell
will also be traced.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This patch adds the file:

   /debugfs/tracing/set_graph_function

which can be used along with the function graph tracer.

When this file is empty, the function graph tracer will act as
usual. When the file has a function in it, the function graph
tracer will only trace that function.

For example:

 # echo blk_unplug > /debugfs/tracing/set_graph_function
 # cat /debugfs/tracing/trace
 [...]
 ------------------------------------------
 | 2)  make-19003  =>  kjournald-2219
 ------------------------------------------

 2)               |  blk_unplug() {
 2)               |    dm_unplug_all() {
 2)               |      dm_get_table() {
 2)      1.381 us |        _read_lock();
 2)      0.911 us |        dm_table_get();
 2)      1. 76 us |        _read_unlock();
 2) +   12.912 us |      }
 2)               |      dm_table_unplug_all() {
 2)               |        blk_unplug() {
 2)      0.778 us |          generic_unplug_device();
 2)      2.409 us |        }
 2)      5.992 us |      }
 2)      0.813 us |      dm_table_put();
 2) +   29. 90 us |    }
 2) +   34.532 us |  }

You can add up to 32 functions into this file. Currently we limit it
to 32, but this may change with later improvements.

To add another function, use the append '>>':

  # echo sys_read >> /debugfs/tracing/set_graph_function
  # cat /debugfs/tracing/set_graph_function
  blk_unplug
  sys_read

Using the '>' will clear out the function and write anew:

  # echo sys_write > /debug/tracing/set_graph_function
  # cat /debug/tracing/set_graph_function
  sys_write

Note, if you have function graph running while doing this, the small
time between clearing it and updating it will cause the graph to
record all functions. This should not be an issue because after
it sets the filter, only those functions will be recorded from then on.
If you need to only record a particular function then set this
file first before starting the function graph tracer. In the future
this side effect may be corrected.

The set_graph_function file is similar to the set_ftrace_filter but
it does not take wild cards nor does it allow for more than one
function to be set with a single write. There is no technical reason why
this is the case, I just do not have the time yet to implement that.

Note, dynamic ftrace must be enabled for this to appear because it
uses the dynamic ftrace records to match the name to the mcount
call sites.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: feature, let entry function decide to trace or not

This patch lets the graph tracer entry function decide if the tracing
should be done at the end as well. This requires all function graph
entry functions return 1 if it should trace, or 0 if the return should
not be traced.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: new "power-tracer" ftrace plugin

This patch adds a C/P-state ftrace plugin that will generate
detailed statistics about the C/P-states that are being used,
so that we can look at detailed decisions that the C/P-state
code is making, rather than the too high level "average"
that we have today.

An example way of using this is:

 mount -t debugfs none /sys/kernel/debug
 echo cstate > /sys/kernel/debug/tracing/current_tracer
 echo 1 > /sys/kernel/debug/tracing/tracing_enabled
 sleep 1
 echo 0 > /sys/kernel/debug/tracing/tracing_enabled
 cat /sys/kernel/debug/tracing/trace | perl scripts/trace/cstate.pl > out.svg
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: enhancement to function graph tracer

Export the trace_find_cmdline so the function graph tracer can
use it to print the comms of the threads.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: feature

This patch sets a C-like output for the function graph tracing.
For this aim, we now call two handler for each function: one on the entry
and one other on return. This way we can draw a well-ordered call stack.

The pid of the previous trace is loosely stored to be compared against
the one of the current trace to see if there were a context switch.

Without this little feature, the call tree would seem broken at
some locations.
We could use the sched_tracer to capture these sched_events but this
way of processing is much more simpler.

2 spaces have been chosen for indentation to fit the screen while deep
calls. The time of execution in nanosecs is printed just after closed
braces, it seems more easy this way to find the corresponding function.
If the time was printed as a first column, it would be not so easy to
find the corresponding function if it is called on a deep depth.

I plan to output the return value but on 32 bits CPU, the return value
can be 32 or 64, and its difficult to guess on which case we are.
I don't know what would be the better solution on X86-32: only print
eax (low-part) or even edx (high-part).

Actually it's thee same problem when a function return a 8 bits value, the
high part of eax could contain junk values...

Here is an example of trace:

sys_read() {
  fget_light() {
  } 526
  vfs_read() {
    rw_verify_area() {
      security_file_permission() {
        cap_file_permission() {
        } 519
      } 1564
    } 2640
    do_sync_read() {
      pipe_read() {
        __might_sleep() {
        } 511
        pipe_wait() {
          prepare_to_wait() {
          } 760
          deactivate_task() {
            dequeue_task() {
              dequeue_task_fair() {
                dequeue_entity() {
                  update_curr() {
                    update_min_vruntime() {
                    } 504
                  } 1587
                  clear_buddies() {
                  } 512
                  add_cfs_task_weight() {
                  } 519
                  update_min_vruntime() {
                  } 511
                } 5602
                dequeue_entity() {
                  update_curr() {
                    update_min_vruntime() {
                    } 496
                  } 1631
                  clear_buddies() {
                  } 496
                  update_min_vruntime() {
                  } 527
                } 4580
                hrtick_update() {
                  hrtick_start_fair() {
                  } 488
                } 1489
              } 13700
            } 14949
          } 16016
          msecs_to_jiffies() {
          } 496
          put_prev_task_fair() {
          } 504
          pick_next_task_fair() {
          } 489
          pick_next_task_rt() {
          } 496
          pick_next_task_fair() {
          } 489
          pick_next_task_idle() {
          } 489

------------8<---------- thread 4 ------------8<----------

finish_task_switch() {
} 1203
do_softirq() {
  __do_softirq() {
    __local_bh_disable() {
    } 669
    rcu_process_callbacks() {
      __rcu_process_callbacks() {
        cpu_quiet() {
          rcu_start_batch() {
          } 503
        } 1647
      } 3128
      __rcu_process_callbacks() {
      } 542
    } 5362
    _local_bh_enable() {
    } 587
  } 8880
} 9986
kthread_should_stop() {
} 669
deactivate_task() {
  dequeue_task() {
    dequeue_task_fair() {
      dequeue_entity() {
        update_curr() {
          calc_delta_mine() {
          } 511
          update_min_vruntime() {
          } 511
        } 2813
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: cleanup

This patch changes the name of the "return function tracer" into
function-graph-tracer which is a more suitable name for a tracing
which makes one able to retrieve the ordered call stack during
the code flow.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add new ftrace plugin

A prototype for a BTS ftrace plug-in.

The tracer collects branch trace in a cyclic buffer for each cpu.

The tracer is not configurable and the trace for each snapshot is
appended when doing cat /debug/tracing/trace.

This is a proof of concept that will be extended with future patches
to become a (hopefully) useful tool.
Signed-off-by: NMarkus Metzger <markus.t.metzger@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Add a callback to allow an ftrace plug-in to write its own header.

Move the call to trace->open() up a few lines.

The changes are required by the BTS ftrace plug-in.
Signed-off-by: NMarkus Metzger <markus.t.metzger@intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: modify+improve the userstacktrace tracing visualization feature

Store thread group leader id, and use it to lookup the address in the
process's map. We could have looked up the address on thread's map,
but the thread might not exist by the time we are called. The process
might not exist either, but if you are reading trace_pipe, that is
unlikely.

Example usage:

 mount -t debugfs nodev /sys/kernel/debug
 cd /sys/kernel/debug/tracing
 echo userstacktrace >iter_ctrl
 echo sym-userobj >iter_ctrl
 echo sched_switch >current_tracer
 echo 1 >tracing_enabled
 cat trace_pipe >/tmp/trace&
 .... run application ...
 echo 0 >tracing_enabled
 cat /tmp/trace

You'll see stack entries like:

   /lib/libpthread-2.7.so[+0xd370]

You can convert them to function/line using:

   addr2line -fie /lib/libpthread-2.7.so 0xd370

Or:

   addr2line -fie /usr/lib/debug/libpthread-2.7.so 0xd370

For non-PIC/PIE executables this won't work:

   a.out[+0x73b]

You need to run the following: addr2line -fie a.out 0x40073b
(where 0x400000 is the default load address of a.out)
Signed-off-by: NTörök Edwin <edwintorok@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add new (default-off) tracing visualization feature

Usage example:

 mount -t debugfs nodev /sys/kernel/debug
 cd /sys/kernel/debug/tracing
 echo userstacktrace >iter_ctrl
 echo sched_switch >current_tracer
 echo 1 >tracing_enabled
 .... run application ...
 echo 0 >tracing_enabled

Then read one of 'trace','latency_trace','trace_pipe'.

To get the best output you can compile your userspace programs with
frame pointers (at least glibc + the app you are tracing).
Signed-off-by: NTörök Edwin <edwintorok@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: help to find the better depth of trace

We decided to arbitrary define the depth of function return trace as
"20". Perhaps this is not enough. To help finding an optimal depth, we
measure now the overrun: the number of functions that have been missed
for the current thread. By default this is not displayed, we have to
do set a particular flag on the return tracer: echo overrun >
/debug/tracing/trace_options And the overrun will be printed on the
right.

As the trace shows below, the current 20 depth is not enough.

update_wall_time+0x37f/0x8c0 -> update_xtime_cache (345 ns) (Overruns: 2838)
update_wall_time+0x384/0x8c0 -> clocksource_get_next (1141 ns) (Overruns: 2838)
do_timer+0x23/0x100 -> update_wall_time (3882 ns) (Overruns: 2838)
tick_do_update_jiffies64+0xbf/0x160 -> do_timer (5339 ns) (Overruns: 2838)
tick_sched_timer+0x6a/0xf0 -> tick_do_update_jiffies64 (7209 ns) (Overruns: 2838)
vgacon_set_cursor_size+0x98/0x120 -> native_io_delay (2613 ns) (Overruns: 274)
vgacon_cursor+0x16e/0x1d0 -> vgacon_set_cursor_size (33151 ns) (Overruns: 274)
set_cursor+0x5f/0x80 -> vgacon_cursor (36432 ns) (Overruns: 274)
con_flush_chars+0x34/0x40 -> set_cursor (38790 ns) (Overruns: 274)
release_console_sem+0x1ec/0x230 -> up (721 ns) (Overruns: 274)
release_console_sem+0x225/0x230 -> wake_up_klogd (316 ns) (Overruns: 274)
con_flush_chars+0x39/0x40 -> release_console_sem (2996 ns) (Overruns: 274)
con_write+0x22/0x30 -> con_flush_chars (46067 ns) (Overruns: 274)
n_tty_write+0x1cc/0x360 -> con_write (292670 ns) (Overruns: 274)
smp_apic_timer_interrupt+0x2a/0x90 -> native_apic_mem_write (330 ns) (Overruns: 274)
irq_enter+0x17/0x70 -> idle_cpu (413 ns) (Overruns: 274)
smp_apic_timer_interrupt+0x2f/0x90 -> irq_enter (1525 ns) (Overruns: 274)
ktime_get_ts+0x40/0x70 -> getnstimeofday (465 ns) (Overruns: 274)
ktime_get_ts+0x60/0x70 -> set_normalized_timespec (436 ns) (Overruns: 274)
ktime_get+0x16/0x30 -> ktime_get_ts (2501 ns) (Overruns: 274)
hrtimer_interrupt+0x77/0x1a0 -> ktime_get (3439 ns) (Overruns: 274)
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: give a way to send specific messages to tracers

The current implementation of tracing uses some flags to control the
output of general tracers. But we have no way to implement custom
flags handling for a specific tracer. This patch proposes a new
callback for the struct tracer which called set_flag and a structure
that represents a 32 bits variable flag.

A tracer can implement a struct tracer_flags on which it puts the
initial value of the flag integer. Than it can place a range of flags
with their name and their flag mask on the flag integer. The structure
that implement a single flag is called struct tracer_opt.

These custom flags will be available through the trace_options file
like the general tracing flags. Changing their value is done like the
other general flags. For example if you have a flag that calls "foo",
you can activate it by writing "foo" or "nofoo" on trace_options.

Note that the set_flag callback is optional and is only needed if you
want the flags changing to be signaled to your tracer and let it to
accept or refuse their assignment.

V2: Some arrangements in coding style....
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix trace_options behavior

writing to trace/trace_options use the index of the array
to find the value of the flag. With branch tracer flag
defined conditionally, this breaks writing to trace_options
with branch tracer disabled.
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: extend the ->init() method with the ability to fail

This bring a way to know if the initialization of a tracer successed.
A tracer must return 0 on success and a traditional error (ie:
-ENOMEM) if it fails.

If a tracer fails to init, it is free to print a detailed warn. The
tracing api will not and switch to a new tracer will just return the
error from the init callback.

Note: this will be used for the return tracer.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: better handling of CPU buffer start annotation

Because of the confusion with the per CPU buffers wrapping where
one CPU might be more active at the end of the trace than the other
CPUs causing that one CPU to have a shorter history. Kernel
developers were confused by the "missing" data of that one CPU
at the beginning of the trace output. An annotation was added to
the trace output to show that the buffer had started:

 # tracer: function
 #
 #           TASK-PID    CPU#    TIMESTAMP  FUNCTION
 #              | |       |          |         |
 ##### CPU 3 buffer started ####
          <idle>-0     [003]   158.192959: smp_apic_timer_interrupt
 [...]
           <idle>-0     [003]   161.556520: default_idle
 ##### CPU 1 buffer started ####
           <idle>-0     [001]   161.592494: hrtimer_force_reprogram
 [etc]

But this annotation gets a bit messy when tracers do not fill the
buffers. This patch does a couple of things:

 One) it adds a flag to trace_options to disable these annotations

 Two) it does not annotate if the tracer did not overflow its buffer.

This makes the output much cleaner.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: added new branch tracer

Currently the tracing of branch profiling (unlikelys and likelys hit)
is only activated by the iter_ctrl. This patch adds a tracer called
"branch" that will just trace the branch profiling. The advantage
of adding this tracer is that it can be added to the ftrace selftests
on startup.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: rename of iter_ctrl unlikely to branch

The unlikely name is ugly. This patch converts the iter_ctrl command
"unlikely" and "nounlikely" to "branch" and "nobranch" respectively.

It also renames a lot of internal functions to use "branch" instead
of "unlikely".
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: name change of unlikely tracer and profiler

Ingo Molnar suggested changing the config from UNLIKELY_PROFILE
to BRANCH_PROFILING. I never did like the "unlikely" name so I
went one step farther, and renamed all the unlikely configurations
to a "BRANCH" variant.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: new likely/unlikely branch tracer

This patch adds a way to record the instances of the likely() and unlikely()
branch condition annotations.

When "unlikely" is set in /debugfs/tracing/iter_ctrl the unlikely conditions
will be added to any of the ftrace tracers. The change takes effect when
a new tracer is passed into the current_tracer file.

For example:

 bash-3471  [003]   357.014755: [INCORRECT] sched_info_dequeued:sched_stats.h:177
 bash-3471  [003]   357.014756: [correct] update_curr:sched_fair.c:489
 bash-3471  [003]   357.014758: [correct] calc_delta_fair:sched_fair.c:411
 bash-3471  [003]   357.014759: [correct] account_group_exec_runtime:sched_stats.h:356
 bash-3471  [003]   357.014761: [correct] update_curr:sched_fair.c:489
 bash-3471  [003]   357.014763: [INCORRECT] calc_delta_fair:sched_fair.c:411
 bash-3471  [003]   357.014765: [correct] calc_delta_mine:sched.c:1279

Which shows the normal tracer heading, as well as whether the condition was
correct "[correct]" or was mistaken "[INCORRECT]", followed by the function,
file name and line number.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: Split the boot tracer entries in two parts: call and return

Now that we are using the sched tracer from the boot tracer, we want
to use the same timestamp than the ring-buffer to have consistent time
captures between sched events and initcall events.

So we get rid of the old time capture by the boot tracer and split the
initcall events in two parts: call and return. This way we have the
ring buffer timestamp of both.

An example trace:

[   27.904149584] calling  net_ns_init+0x0/0x1c0 @ 1
[   27.904429624] initcall net_ns_init+0x0/0x1c0 returned 0 after 0 msecs
[   27.904575926] calling  reboot_init+0x0/0x20 @ 1
[   27.904655399] initcall reboot_init+0x0/0x20 returned 0 after 0 msecs
[   27.904800228] calling  sysctl_init+0x0/0x30 @ 1
[   27.905142914] initcall sysctl_init+0x0/0x30 returned 0 after 0 msecs
[   27.905287211] calling  ksysfs_init+0x0/0xb0 @ 1
 ##### CPU 0 buffer started ####
            init-1     [000]    27.905395:      1:120:R   + [001]    11:115:S
 ##### CPU 1 buffer started ####
          <idle>-0     [001]    27.905425:      0:140:R ==> [001]    11:115:R
            init-1     [000]    27.905426:      1:120:D ==> [000]     0:140:R
          <idle>-0     [000]    27.905431:      0:140:R   + [000]     4:115:S
          <idle>-0     [000]    27.905451:      0:140:R ==> [000]     4:115:R
     ksoftirqd/0-4     [000]    27.905456:      4:115:S ==> [000]     0:140:R
           udevd-11    [001]    27.905458:     11:115:R   + [001]    14:115:R
          <idle>-0     [000]    27.905459:      0:140:R   + [000]     4:115:S
          <idle>-0     [000]    27.905462:      0:140:R ==> [000]     4:115:R
           udevd-11    [001]    27.905462:     11:115:R ==> [001]    14:115:R
     ksoftirqd/0-4     [000]    27.905467:      4:115:S ==> [000]     0:140:R
          <idle>-0     [000]    27.905470:      0:140:R   + [000]     4:115:S
          <idle>-0     [000]    27.905473:      0:140:R ==> [000]     4:115:R
     ksoftirqd/0-4     [000]    27.905476:      4:115:S ==> [000]     0:140:R
          <idle>-0     [000]    27.905479:      0:140:R   + [000]     4:115:S
          <idle>-0     [000]    27.905482:      0:140:R ==> [000]     4:115:R
     ksoftirqd/0-4     [000]    27.905486:      4:115:S ==> [000]     0:140:R
           udevd-14    [001]    27.905499:     14:120:X ==> [001]    11:115:R
           udevd-11    [001]    27.905506:     11:115:R   + [000]     1:120:D
          <idle>-0     [000]    27.905515:      0:140:R ==> [000]     1:120:R
           udevd-11    [001]    27.905517:     11:115:S ==> [001]     0:140:R
[   27.905557107] initcall ksysfs_init+0x0/0xb0 returned 0 after 3906 msecs
[   27.905705736] calling  init_jiffies_clocksource+0x0/0x10 @ 1
[   27.905779239] initcall init_jiffies_clocksource+0x0/0x10 returned 0 after 0 msecs
[   27.906769814] calling  pm_init+0x0/0x30 @ 1
[   27.906853627] initcall pm_init+0x0/0x30 returned 0 after 0 msecs
[   27.906997803] calling  pm_disk_init+0x0/0x20 @ 1
[   27.907076946] initcall pm_disk_init+0x0/0x20 returned 0 after 0 msecs
[   27.907222556] calling  swsusp_header_init+0x0/0x30 @ 1
[   27.907294325] initcall swsusp_header_init+0x0/0x30 returned 0 after 0 msecs
[   27.907439620] calling  stop_machine_init+0x0/0x50 @ 1
            init-1     [000]    27.907485:      1:120:R   + [000]     2:115:S
            init-1     [000]    27.907490:      1:120:D ==> [000]     2:115:R
        kthreadd-2     [000]    27.907507:      2:115:R   + [001]    15:115:R
          <idle>-0     [001]    27.907517:      0:140:R ==> [001]    15:115:R
        kthreadd-2     [000]    27.907517:      2:115:D ==> [000]     0:140:R
          <idle>-0     [000]    27.907521:      0:140:R   + [000]     4:115:S
          <idle>-0     [000]    27.907524:      0:140:R ==> [000]     4:115:R
           udevd-15    [001]    27.907527:     15:115:D   + [000]     2:115:D
     ksoftirqd/0-4     [000]    27.907537:      4:115:S ==> [000]     2:115:R
           udevd-15    [001]    27.907537:     15:115:D ==> [001]     0:140:R
        kthreadd-2     [000]    27.907546:      2:115:R   + [000]     1:120:D
        kthreadd-2     [000]    27.907550:      2:115:S ==> [000]     1:120:R
            init-1     [000]    27.907584:      1:120:R   + [000]    15:  0:D
            init-1     [000]    27.907589:      1:120:R   + [000]     2:115:S
            init-1     [000]    27.907593:      1:120:D ==> [000]    15:  0:R
           udevd-15    [000]    27.907601:     15:  0:S ==> [000]     2:115:R
 ##### CPU 0 buffer started ####
        kthreadd-2     [000]    27.907616:      2:115:R   + [001]    16:115:R
 ##### CPU 1 buffer started ####
          <idle>-0     [001]    27.907620:      0:140:R ==> [001]    16:115:R
        kthreadd-2     [000]    27.907621:      2:115:D ==> [000]     0:140:R
           udevd-16    [001]    27.907625:     16:115:D   + [000]     2:115:D
          <idle>-0     [000]    27.907628:      0:140:R   + [000]     4:115:S
           udevd-16    [001]    27.907629:     16:115:D ==> [001]     0:140:R
          <idle>-0     [000]    27.907631:      0:140:R ==> [000]     4:115:R
     ksoftirqd/0-4     [000]    27.907636:      4:115:S ==> [000]     2:115:R
        kthreadd-2     [000]    27.907644:      2:115:R   + [000]     1:120:D
        kthreadd-2     [000]    27.907647:      2:115:S ==> [000]     1:120:R
            init-1     [000]    27.907657:      1:120:R   + [001]    16:  0:D
          <idle>-0     [001]    27.907666:      0:140:R ==> [001]    16:  0:R
[   27.907703862] initcall stop_machine_init+0x0/0x50 returned 0 after 0 msecs
[   27.907850704] calling  filelock_init+0x0/0x30 @ 1
[   27.907926573] initcall filelock_init+0x0/0x30 returned 0 after 0 msecs
[   27.908071327] calling  init_script_binfmt+0x0/0x10 @ 1
[   27.908165195] initcall init_script_binfmt+0x0/0x10 returned 0 after 0 msecs
[   27.908309461] calling  init_elf_binfmt+0x0/0x10 @ 1
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: Cleanups on the boot tracer and ftrace

This patch bring some cleanups about the boot tracer headers. The
functions and structures of this tracer have nothing related to ftrace
and should have so their own header file.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add new tracing plugin which can trace full (entry+exit) function calls

This tracer uses the low level function return ftrace plugin to
measure the execution time of the kernel functions.

The first field is the caller of the function, the second is the
measured function, and the last one is the execution time in
nanoseconds.

- v3:

- HAVE_FUNCTION_RET_TRACER have been added. Each arch that support ftrace return
  should enable it.
- ftrace_return_stub becomes ftrace_stub.
- CONFIG_FUNCTION_RET_TRACER depends now on CONFIG_FUNCTION_TRACER
- Return traces printing can be used for other tracers on trace.c
- Adapt to the new tracing API (no more ctrl_update callback)
- Correct the check of "disabled" during insertion.
- Minor changes...
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: change in trace output

Because the trace buffers are per cpu ring buffers, the start of
the trace can be confusing. If one CPU is very active at the
end of the trace, its history will not go as far back as the
other CPU traces.  This means that output for a particular CPU
may not appear for the first part of a trace.

To help annotate what is happening, and to prevent any more
confusion, this patch adds a line that annotates the start of
a CPU buffer output.

For example:

       automount-3495  [001]   184.596443: dnotify_parent <-vfs_write
[...]
       automount-3495  [001]   184.596449: dput <-path_put
       automount-3496  [002]   184.596450: down_read_trylock <-do_page_fault
[...]
           sshd-3497  [001]   184.597069: up_read <-do_page_fault
          <idle>-0     [000]   184.597074: __exit_idle <-exit_idle
[...]
       automount-3496  [002]   184.597257: filemap_fault <-__do_fault
          <idle>-0     [003]   184.597261: exit_idle <-smp_apic_timer_interrupt

Note, parsers of a trace output should always ignore any lines that
start with a '#'.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: remove obsolete variable in trace_array structure

With the new start / stop method of ftrace, the ctrl variable
in the trace_array structure is now obsolete. Remove it.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: Remove the ctrl_update tracer method

With the new quick start/stop method of tracing, the ctrl_update
method is out of date.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: fix for sched_switch that broke dynamic ftrace startup

The commit: tracing/fastboot: use sched switch tracer from boot tracer
broke the API of the sched_switch trace. The use of the
tracing_start/stop_cmdline record is for only recording the cmdline,
NOT recording the schedule switches themselves.

Seeing that the boot tracer broke the API to do something that it
wanted, this patch adds a new interface for the API while
puting back the original interface of the old API.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: boot tracer startup modified

The boot tracer calls into some of the schedule tracing private functions
that should not be exported. This patch cleans it up, and makes
way for further changes in the ftrace infrastructure.

This patch adds a api to assign a tracer array to the schedule
context switch tracer.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Acked-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: change where tracing is started up and stopped

Currently, when a new tracer is selected via echo'ing a tracer name into
the current_tracer file, the startup is only done if tracing_enabled is
set to one. If tracing_enabled is changed to zero (by echo'ing 0 into
the tracing_enabled file) a full shutdown is performed.

The full startup and shutdown of a tracer can be expensive and the
user can lose out traces when echo'ing in 0 to the tracing_enabled file,
because the process takes too long. There can also be places that
the user would like to start and stop the tracer several times and
doing the full startup and shutdown of a tracer might be too expensive.

This patch performs the full startup and shutdown when a tracer is
selected. It also adds a way to do a quick start or stop of a tracer.
The quick version is just a flag that prevents the tracing from
taking place, but the overhead of the code is still there.

For example, the startup of a tracer may enable tracepoints, or enable
the function tracer.  The stop and start will just set a flag to
have the tracer ignore the calls when the tracepoint or function trace
is called.  The overhead of the tracer may still be present when
the tracer is stopped, but no tracing will occur. Setting the tracer
to the 'nop' tracer (or any other tracer) will perform the shutdown
of the tracer which will disable the tracepoint or disable the
function tracer.

The tracing_enabled file will simply start or stop tracing.

This change is all internal. The end result for the user should be the same
as before. If tracing_enabled is not set, no trace will happen.
If tracing_enabled is set, then the trace will happen. The tracing_enabled
variable is static between tracers. Enabling  tracing_enabled and
going to another tracer will keep tracing_enabled enabled. Same
is true with disabling tracing_enabled.

This patch will now provide a fast start/stop method to the users
for enabling or disabling tracing.

Note: There were two methods to the struct tracer that were never
 used: The methods start and stop. These were to be used as a hook
 to the reading of the trace output, but ended up not being
 necessary. These two methods are now used to enable the start
 and stop of each tracer, in case the tracer needs to do more than
 just not write into the buffer. For example, the irqsoff tracer
 must stop recording max latencies when tracing is stopped.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: enhance boot trace output with scheduling events

Use the sched_switch tracer from the boot tracer.

We also can trace schedule events inside the initcalls.
Sched tracing is disabled after the initcall has finished and
then reenabled before the next one is started.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: disable interrupts during trace entry creation (as opposed to preempt)

To help with performance, I set the ftracer to not disable interrupts,
and only to disable preemption. If an interrupt occurred, it would not
be traced, because the function tracer protects itself from recursion.
This may be faster, but the trace output might miss some traces.

This patch makes the fuction trace disable interrupts, but it also
adds a runtime feature to disable preemption instead. It does this by
having two different tracer functions. When the function tracer is
enabled, it will check to see which version is requested (irqs disabled
or preemption disabled). Then it will use the corresponding function
as the tracer.

Irq disabling is the default behaviour, but if the user wants better
performance, with the chance of missing traces, then they can choose
the preempt disabled version.

Running hackbench 3 times with the irqs disabled and 3 times with
the preempt disabled function tracer yielded:

tracing type       times            entries recorded
------------      --------          ----------------
irq disabled      43.393            166433066
                  43.282            166172618
                  43.298            166256704

preempt disabled  38.969            159871710
                  38.943            159972935
                  39.325            161056510

Average:

   irqs disabled:  43.324           166287462
preempt disabled:  39.079           160300385

 preempt is 10.8 percent faster than irqs disabled.

I wrote a patch to count function trace recursion and reran hackbench.

With irq disabled: 1,150 times the function tracer did not trace due to
  recursion.
with preempt disabled: 5,117,718 times.

The thousand times with irq disabled could be due to NMIs, or simply a case
where it called a function that was not protected by notrace.

But we also see that a large amount of the trace is lost with the
preempt version.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: add new ftrace-plugin internal APIs

Parts of the tracer needs to be careful about schedule recursion.
If the NEED_RESCHED flag is set, a preempt_enable will call schedule.
Inside the schedule function, the NEED_RESCHED flag is cleared.

The problem arises when a trace happens in the schedule function but before
NEED_RESCHED is cleared. The race is as follows:

schedule()
  >> tracer called

    trace_function()
       preempt_disable()
       [ record trace ]
       preempt_enable()  <<- here's the issue.

         [check NEED_RESCHED]
          schedule()
          [ Repeat the above, over and over again ]

The naive approach is simply to use preempt_enable_no_schedule instead.
The problem with that approach is that, although we solve the schedule
recursion issue, we now might lose a preemption check when not in the
schedule function.

  trace_function()
    preempt_disable()
    [ record trace ]
    [Interrupt comes in and sets NEED_RESCHED]
    preempt_enable_no_resched()
    [continue without scheduling]

The way ftrace handles this problem is with the following approach:

	int resched;

	resched = need_resched();
	preempt_disable_notrace();
	[record trace]
	if (resched)
		preempt_enable_no_sched_notrace();
	else
		preempt_enable_notrace();

This may seem like the opposite of what we want. If resched is set
then we call the "no_sched" version??  The reason we do this is because
if NEED_RESCHED is set before we disable preemption, there's two reasons
for that:

  1) we are in an atomic code path
  2) we are already on our way to the schedule function, and maybe even
     in the schedule function, but have yet to clear the flag.

Both the above cases we do not want to schedule.

This solution has already been implemented within the ftrace infrastructure.
But the problem is that it has been implemented several times. This patch
encapsulates this code to two nice functions.

  resched = ftrace_preempt_disable();
  [ record trace]
  ftrace_preempt_enable(resched);

This way the tracers do not need to worry about getting it right.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Impact: build fix on non-lockdep architectures

Some architectures do not support a way to read the irq flags that
is set from "local_irq_save(flags)" to determine if interrupts were
disabled or enabled. Ftrace uses this information to display to the user
if the trace occurred with interrupts enabled or disabled.

Besides the fact that those archs that do not support this will fail to
compile, unless they fix it, we do not want to have the trace simply
say interrupts were not disabled or they were enabled, without knowing
the real answer.

This patch adds a 'X' in the output to let the user know that the
architecture they are running on does not support a way for the tracer
to determine if interrupts were enabled or disabled. It also lets those
same archs compile with tracing enabled.
Signed-off-by: NSteven Rostedt <srostedt@redhat.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>