提交 4e93ad60 编写于 作者: J Jiri Olsa 提交者: Ingo Molnar

perf: Do not send exit event twice

In case we monitor events system wide, we get EXIT event
(when configured) twice for each task that exited.

Note doubled lines with same pid/tid in following example:

  $ sudo ./perf record -a
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.480 MB perf.data (2518 samples) ]
  $ sudo ./perf report -D | grep EXIT

  0 60290687567581 0x59910 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250)
  0 60290687568354 0x59948 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250)
  0 60290687988744 0x59ad8 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250)
  0 60290687989198 0x59b10 [0x38]: PERF_RECORD_EXIT(1250:1250):(1250:1250)
  1 60290692567895 0x62af0 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253)
  1 60290692568322 0x62b28 [0x38]: PERF_RECORD_EXIT(1253:1253):(1253:1253)
  2 60290692739276 0x69a18 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252)
  2 60290692739910 0x69a50 [0x38]: PERF_RECORD_EXIT(1252:1252):(1252:1252)

The reason is that the cpu contexts are processes each time
we call perf_event_task. I'm changing the perf_event_aux logic
to serve task_ctx and cpu contexts separately, which ensure we
don't get EXIT event generated twice on same cpu context.

This does not affect other auxiliary events, as they don't
use task_ctx at all.
Signed-off-by: NJiri Olsa <jolsa@kernel.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/1446649205-5822-1-git-send-email-jolsa@kernel.orgSigned-off-by: NIngo Molnar <mingo@kernel.org>
上级 169b932a
......@@ -5682,6 +5682,17 @@ perf_event_aux_ctx(struct perf_event_context *ctx,
}
}
static void
perf_event_aux_task_ctx(perf_event_aux_output_cb output, void *data,
struct perf_event_context *task_ctx)
{
rcu_read_lock();
preempt_disable();
perf_event_aux_ctx(task_ctx, output, data);
preempt_enable();
rcu_read_unlock();
}
static void
perf_event_aux(perf_event_aux_output_cb output, void *data,
struct perf_event_context *task_ctx)
......@@ -5691,14 +5702,23 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
struct pmu *pmu;
int ctxn;
/*
* If we have task_ctx != NULL we only notify
* the task context itself. The task_ctx is set
* only for EXIT events before releasing task
* context.
*/
if (task_ctx) {
perf_event_aux_task_ctx(output, data, task_ctx);
return;
}
rcu_read_lock();
list_for_each_entry_rcu(pmu, &pmus, entry) {
cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
if (cpuctx->unique_pmu != pmu)
goto next;
perf_event_aux_ctx(&cpuctx->ctx, output, data);
if (task_ctx)
goto next;
ctxn = pmu->task_ctx_nr;
if (ctxn < 0)
goto next;
......@@ -5708,12 +5728,6 @@ perf_event_aux(perf_event_aux_output_cb output, void *data,
next:
put_cpu_ptr(pmu->pmu_cpu_context);
}
if (task_ctx) {
preempt_disable();
perf_event_aux_ctx(task_ctx, output, data);
preempt_enable();
}
rcu_read_unlock();
}
......@@ -8803,10 +8817,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
struct perf_event_context *child_ctx, *clone_ctx = NULL;
unsigned long flags;
if (likely(!child->perf_event_ctxp[ctxn])) {
perf_event_task(child, NULL, 0);
if (likely(!child->perf_event_ctxp[ctxn]))
return;
}
local_irq_save(flags);
/*
......@@ -8890,6 +8902,14 @@ void perf_event_exit_task(struct task_struct *child)
for_each_task_context_nr(ctxn)
perf_event_exit_task_context(child, ctxn);
/*
* The perf_event_exit_task_context calls perf_event_task
* with child's task_ctx, which generates EXIT events for
* child contexts and sets child->perf_event_ctxp[] to NULL.
* At this point we need to send EXIT events to cpu contexts.
*/
perf_event_task(child, NULL, 0);
}
static void perf_free_event(struct perf_event *event,
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册