linux_old1/kernel/trace
Steven Rostedt 8f0a056fcb ftrace: introduce ftrace_preempt_disable()/enable()
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: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-04 10:09:48 +01:00
..
Kconfig tracing, alpha: undefined reference to `save_stack_trace' 2008-11-03 10:12:13 +01:00
Makefile ftrace: rename FTRACE to FUNCTION_TRACER 2008-10-20 18:27:03 +02:00
ftrace.c ftrace: perform an initialization for ftrace to enable it 2008-10-28 19:15:58 +01:00
ring_buffer.c trace: fix printk warning for u64 2008-10-27 11:31:58 +01:00
trace.c Merge branches 'tracing/ftrace', 'tracing/markers', 'tracing/mmiotrace', 'tracing/nmisafe', 'tracing/tracepoints' and 'tracing/urgent' into tracing/core 2008-11-03 10:34:23 +01:00
trace.h ftrace: introduce ftrace_preempt_disable()/enable() 2008-11-04 10:09:48 +01:00
trace_boot.c tracing/fastboot: fix printk format typo in boot tracer 2008-10-14 10:39:23 +02:00
trace_functions.c ftrace: rename the ftrace tracer to function 2008-10-20 18:27:04 +02:00
trace_irqsoff.c ftrace: rename FTRACE to FUNCTION_TRACER 2008-10-20 18:27:03 +02:00
trace_mmiotrace.c ftrace: preempt disable over interrupt disable 2008-10-14 10:39:09 +02:00
trace_nop.c ftrace: make work with new ring buffer 2008-10-14 10:38:57 +02:00
trace_sched_switch.c ftrace: make some tracers reentrant 2008-10-14 10:39:20 +02:00
trace_sched_wakeup.c ftrace: rename FTRACE to FUNCTION_TRACER 2008-10-20 18:27:03 +02:00
trace_selftest.c ftrace: remove daemon 2008-10-23 16:00:22 +02:00
trace_selftest_dynamic.c ftrace: fix dynamic ftrace selftest 2008-05-23 21:13:23 +02:00
trace_stack.c ftrace: stack tracer only record when on stack 2008-10-20 18:31:37 +02:00
trace_sysprof.c ftrace: make work with new ring buffer 2008-10-14 10:38:57 +02:00