[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAM9d7ciSJXFC4Wdioy2PxZNCd+6-+kcA6+qqJs-BvQ3yAgQmAg@mail.gmail.com>
Date: Tue, 6 Aug 2024 12:29:01 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: "Liang, Kan" <kan.liang@...ux.intel.com>, Ingo Molnar <mingo@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, LKML <linux-kernel@...r.kernel.org>,
Ravi Bangoria <ravi.bangoria@....com>, Stephane Eranian <eranian@...gle.com>,
Ian Rogers <irogers@...gle.com>, Mingwei Zhang <mizhang@...gle.com>
Subject: Re: [PATCH v2] perf/core: Optimize event reschedule for a PMU
On Tue, Aug 6, 2024 at 1:08 AM Peter Zijlstra <peterz@...radead.org> wrote:
>
> On Tue, Aug 06, 2024 at 09:56:30AM +0200, Peter Zijlstra wrote:
>
> > Does this help? What would be an easy reproducer?
Yep, it helps! I guess you can reproduce it easily with:
$ sudo perf stat -a sleep 1
> >
> > ---
> > diff --git a/kernel/events/core.c b/kernel/events/core.c
> > index c67fc43fe877..4a04611333d9 100644
> > --- a/kernel/events/core.c
> > +++ b/kernel/events/core.c
> > @@ -179,23 +179,27 @@ static void perf_ctx_lock(struct perf_cpu_context *cpuctx,
> > }
> > }
> >
> > +static inline void __perf_ctx_unlock(struct perf_event_context *ctx)
> > +{
> > + /*
> > + * If ctx_sched_in() didn't again set any ALL flags, clean up
> > + * after ctx_sched_out() by clearing is_active.
> > + */
> > + if (ctx->is_active & EVENT_FROZEN) {
> > + if (!(ctx->is_active & EVENT_ALL))
> > + ctx->is_active = 0;
> > + else
> > + ctx->is_active &= ~EVENT_FROZEN;
> > + }
> > + raw_spin_unlock(&ctx->lock);
> > +}
> > +
> > static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
> > struct perf_event_context *ctx)
> > {
> > - if (ctx) {
> > - /*
> > - * If ctx_sched_in() didn't again set any ALL flags, clean up
> > - * after ctx_sched_out() by clearing is_active.
> > - */
> > - if (ctx->is_active & EVENT_FROZEN) {
> > - if (!(ctx->is_active & EVENT_ALL))
> > - ctx->is_active = 0;
> > - else
> > - ctx->is_active &= ~EVENT_FROZEN;
> > - }
> > - raw_spin_unlock(&ctx->lock);
> > - }
> > - raw_spin_unlock(&cpuctx->ctx.lock);
> > + if (ctx)
> > + __perf_ctx_unlock(ctx);
> > + __perf_ctx_unlock(&cpuctx->ctx.lock);
>
> Obviously that wants to be just: &cpuctx->ctx :-)
Sure. And I think we need this for perf_ctx_lock() too.
Thanks,
Namhyung
>
> > }
> >
> > #define TASK_TOMBSTONE ((void *)-1L)
Powered by blists - more mailing lists