lkml.org 
[lkml]   [2011]   [Jan]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    SubjectRe: perf_events: question about __perf_event_read()
    From
    On Fri, Jan 21, 2011 at 7:18 PM, Peter Zijlstra <peterz@infradead.org> wrote:
    > On Fri, 2011-01-21 at 19:06 +0100, Stephane Eranian wrote:
    >> Hi,
    >>
    >> I think the code below still has a problem in case of a per-cpu event.
    >>
    >> If you issue a read() on a different CPU, then you IPI to the event's cpu.
    >> By the time you get there, the event may be de-scheduled in which
    >> case you don't want to issue event->pmu_read() nor update context
    >> timings. The function has a test but it seems to be checking the per-cpu
    >> case only.
    >>
    >> I have seen panics on P4 with this code because it goes all the way
    >> down to rdmsrl() with a bogus counter index (like -1).
    >>
    >> Am I missing something here?
    >>
    >> static void __perf_event_read(void *info)
    >> {
    >>         struct perf_event *event = info;
    >>         struct perf_event_context *ctx = event->ctx;
    >>         struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
    >>
    >>         /*
    >>          * If this is a task context, we need to check whether it is
    >>          * the current task context of this cpu.  If not it has been
    >>          * scheduled out before the smp call arrived.  In that case
    >>          * event->count would have been updated to a recent sample
    >>          * when the event was scheduled out.
    >>          */
    >>         if (ctx->task && cpuctx->task_ctx != ctx)
    >>                 return;
    >>
    >>         raw_spin_lock(&ctx->lock);
    >
    > Shouldn't we re-check event->state once we hold this lock?
    >
    I remember checking this about a month ago and tip-x86 had
    some checks in this routine, but now the're gone.

    I think you need something like:

    + if (ctx->is_active)
    + update_context_time(ctx);

    + if (event->state == PERF_EVENT_STATE_ACTIVE)
    + event->pmu->read(event);

    >>         update_context_time(ctx);
    >>         update_event_times(event);
    >>         raw_spin_unlock(&ctx->lock);
    >>
    >>         event->pmu->read(event);
    >> }
    >
    >
    >
    --
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

    \
     
     \ /
      Last update: 2011-01-21 19:29    [W:0.024 / U:30.272 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site