linux-stable.git/kernel/trace/ftrace.c, branch linux-2.6.30.y

function-graph: allow unregistering twice

2009-04-01T12:47:42+00:00

Impact: fix to permanent disabling of function graph tracer

There should be nothing to prevent a tracer from unregistering a
function graph callback more than once. This can simplify error paths.

But currently, the counter does not account for mulitple unregistering
of the function graph callback. If it happens, the function graph
tracer will be permanently disabled.

Signed-off-by: Steven Rostedt 
Signed-off-by: Ingo Molnar

ftrace: Using FTRACE_WARN_ON() to check "freed record" in ftrace_release()

2009-03-25T21:45:36+00:00

 "Because when we call ftrace_free_rec we change the rec->ip to point to the
  next record in the chain. Something is very wrong if rec->ip >= s &&
  rec->ip < e and the record is already free."

 "Note, use FTRACE_WARN_ON() macro. This way it shuts down ftrace if it is
  hit and helps to avoid further damage later."
                   -- Steven Rostedt 

Signed-off-by: Zhao Lei 
Signed-off-by: Steven Rostedt

tracing: use union for multi-usages field

2009-03-24T15:43:12+00:00

Impact: cleanup

struct dyn_ftrace::ip has different usages in his lifecycle,
we use union for it. And also for struct dyn_ftrace::flags.

Signed-off-by: Lai Jiangshan 
Cc: Steven Rostedt 
Cc: Frederic Weisbecker 
LKML-Reference: <49C871BE.3080405@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

ftrace: show virtual PID

2009-03-24T15:42:49+00:00

Impact: fix PID output under namespaces

When current namespace is not the global namespace,
pid read from set_ftrace_pid is no correct.

 # ~/newpid_namespace_run bash
 # echo $$
 1
 # echo 1 > set_ftrace_pid
 # cat set_ftrace_pid
 3756

Since we write virtual PID to set_ftrace_pid, we need get
virtual PID when we read it.

Signed-off-by: Lai Jiangshan 
Cc: Steven Rostedt 
Cc: Frederic Weisbecker 
LKML-Reference: <49C84D65.9050606@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

function-graph: add option for include sleep times

2009-03-24T15:06:24+00:00

Impact: give user a choice to show times spent while sleeping

The user may want to see the time a function spent sleeping.
This patch adds the trace option "sleep-time" to allow that.
The "sleep-time" option is default on.

 echo sleep-time > /debug/tracing/trace_options

produces:

 ------------------------------------------
 2)  avahi-d-3428  =>    -0
 ------------------------------------------

 2)               |      finish_task_switch() {
 2)   0.621 us    |        _spin_unlock_irq();
 2)   2.202 us    |      }
 2) ! 1002.197 us |    }
 2) ! 1003.521 us |  }

where as,

 echo nosleep-time > /debug/tracing/trace_options

produces:

 0)    -0    =>  yum-upd-3416
 ------------------------------------------

 0)               |              finish_task_switch() {
 0)   0.643 us    |                _spin_unlock_irq();
 0)   2.342 us    |              }
 0) + 41.302 us   |            }
 0) + 42.453 us   |          }

Signed-off-by: Steven Rostedt

function-graph: ignore times across schedule

2009-03-24T13:33:30+00:00

Impact: more accurate timings

The current method of function graph tracing does not take into
account the time spent when a task is not running. This shows functions
that call schedule have increased costs:

 3) + 18.664 us   |      }
 ------------------------------------------
 3)    -0    =>  kblockd-123
 ------------------------------------------

 3)               |      finish_task_switch() {
 3)   1.441 us    |        _spin_unlock_irq();
 3)   3.966 us    |      }
 3) ! 2959.433 us |    }
 3) ! 2961.465 us |  }

This patch uses the tracepoint in the scheduling context switch to
account for time that has elapsed while a task is scheduled out.
Now we see:

 ------------------------------------------
 3)    -0    =>  edac-po-1067
 ------------------------------------------

 3)               |      finish_task_switch() {
 3)   0.685 us    |        _spin_unlock_irq();
 3)   2.331 us    |      }
 3) + 41.439 us   |    }
 3) + 42.663 us   |  }

Signed-off-by: Steven Rostedt

function-graph: prevent more than one tracer registering

2009-03-24T13:32:52+00:00

Impact: prevent crash due to multiple function graph tracers

The function graph tracer can currently only handle a single tracer
being registered. If another tracer registers with the function
graph tracer it can crash the system.

Signed-off-by: Steven Rostedt

tracing/ftrace: fix the check on nopped sites

2009-03-17T02:15:36+00:00

Impact: fix a dynamic tracing failure

Recently, the function and function graph tracers failed to use dynamic
tracing after the following commit:

fa9d13cf135efbd454453a53b6299976bea245a9
(ftrace: don't try to __ftrace_replace_code on !FTRACE_FL_CONVERTED rec)

The patch is right except a mistake on the check for the FTRACE_FL_CONVERTED
flag. The code patching is aborted in case of successfully nopped sites.
What we want is the opposite: ignore the callsites that haven't been nopped.

Signed-off-by: Frederic Weisbecker 
Signed-off-by: Steven Rostedt

ftrace: remove struct list_head from struct dyn_ftrace

2009-03-13T10:36:20+00:00

Impact: save memory

The struct dyn_ftrace table is very large, this patch will save
about 50%.

Signed-off-by: Lai Jiangshan 
Cc: Steven Rostedt 
LKML-Reference: <49BA2C9F.8020009@cn.fujitsu.com>
Signed-off-by: Ingo Molnar

ftrace: use seq_read

2009-03-13T10:35:31+00:00

Impact: cleanup

VFS layer has tested the file mode, we do not need test it.

Signed-off-by: Lai Jiangshan 
Cc: Steven Rostedt 
LKML-Reference: <49BA2BAB.6010608@cn.fujitsu.com>
Signed-off-by: Ingo Molnar