diff options
| author | Steven Rostedt <rostedt@goodmis.org> | 2008-07-15 15:53:37 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@elte.hu> | 2008-07-18 18:57:34 +0200 |
| commit | 1e01cb0c6ff7e9ddb6547551794c6aa82785a7cb (patch) | |
| tree | 791ecc834a169f6e3d7322a0c285dd95e9cd0c31 | |
| parent | ftrace: fix 4d3702b6 (post-v2.6.26): WARNING: at kernel/lockdep.c:2731 check_... (diff) | |
| download | linux-1e01cb0c6ff7e9ddb6547551794c6aa82785a7cb.tar.xz linux-1e01cb0c6ff7e9ddb6547551794c6aa82785a7cb.zip | |
ftrace: only trace preempt off with preempt tracer
When PREEMPT_TRACER and IRQSOFF_TRACER are both configured and irqsoff
tracer is running, the preempt_off sections might also be traced.
Thanks to Andrew Morton for pointing out my mistake of spin_lock disabling
interrupts while he was reviewing ftrace.txt. Seems that my example I used
actually hit this bug.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
| -rw-r--r-- | kernel/trace/trace_irqsoff.c | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 421d6fe3650e..b1e4a89b08eb 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -337,12 +337,14 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller); #ifdef CONFIG_PREEMPT_TRACER void trace_preempt_on(unsigned long a0, unsigned long a1) { - stop_critical_timing(a0, a1); + if (preempt_trace()) + stop_critical_timing(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { - start_critical_timing(a0, a1); + if (preempt_trace()) + start_critical_timing(a0, a1); } #endif /* CONFIG_PREEMPT_TRACER */ |