Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 23 Oct 2019 11:37:57 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Stephane Eranian <eranian@google.com>
Cc:     LKML <linux-kernel@vger.kernel.org>, mingo@elte.hu,
        Arnaldo Carvalho de Melo <acme@redhat.com>,
        Jiri Olsa <jolsa@redhat.com>,
        "Liang, Kan" <kan.liang@intel.com>,
        Song Liu <songliubraving@fb.com>,
        Ian Rogers <irogers@google.com>
Subject: Re: [PATCH] perf/core: fix multiplexing event scheduling issue
Message-ID: <20191023093757.GR1817@hirez.programming.kicks-ass.net>
References: <20191018002746.149200-1-eranian@google.com>
 <20191021100558.GC1800@hirez.programming.kicks-ass.net>
 <CABPqkBRgBegcdNHtXUqkdfJUASjuUYnSkh_cNeqfoO4wF7tnFQ@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CABPqkBRgBegcdNHtXUqkdfJUASjuUYnSkh_cNeqfoO4wF7tnFQ@mail.gmail.com>
User-Agent: Mutt/1.10.1 (2018-07-13)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Oct 23, 2019 at 12:06:43AM -0700, Stephane Eranian wrote:
> On Mon, Oct 21, 2019 at 3:06 AM Peter Zijlstra <peterz@infradead.org> wrote:
> > On Thu, Oct 17, 2019 at 05:27:46PM -0700, Stephane Eranian wrote:

> > > +      * others removed. There is a way to get removed and not be disabled first.
> > > +      */
> > > +     if (ctx->rotate_necessary && ctx->nr_events) {
> > > +             int type = get_event_type(event);
> > > +             /*
> > > +              * In case we removed a pinned event, then we need to
> > > +              * resched for both pinned and flexible events. The
> > > +              * opposite is not true. A pinned event can never be
> > > +              * inactive due to multiplexing.
> > > +              */
> > > +             if (type & EVENT_PINNED)
> > > +                     type |= EVENT_FLEXIBLE;
> > > +             ctx_resched(cpuctx, cpuctx->task_ctx, type);
> > > +     }
> >
> > What you're relying on is that ->rotate_necessary implies ->is_active
> > and there's pending events. And if we tighten ->rotate_necessary you can
> > remove the && ->nr_events.
> >
> Imagine I have 6 events and 4 counters and I do delete them all before
> the timer expires.  Then, I can be in a situation where
> rotate_necessary is still true and yet have no more events in the
> context. That is because only ctx_sched_out() clears rotate_necessary,
> IIRC. So that is why there is the && nr_events. Now, calling
> ctx_resched() with no events wouldn't probably cause any harm, just
> wasted work.

> So if by tightening, I am guessing you mean clearing rotate_necessary
> earlier. But that would be tricky because the only reliable way of
> clearing it is when you know you are about the reschedule everything.
> Removing an event by itself may not be enough to eliminate
> multiplexing.

I think you're over-thinking things. The thing you test 'ctx->nr_events'
has a clear place where it drops to 0.

If we add

	ctx->nr_events--;
+	if (!ctx->nr_events && ctx->rotate_necessary)
+		ctx->rotate_necessary = 0;

to list_del_event(), we can get rid of that.

Further, since we set it on reschedule, I propose you change the above
like:

	if (ctx->rotate_necessary) {
		int type = get_event_type(event);
		/*
		 * comment..
		 */
		if (type & EVENT_PINNED)
			type |= EVENT_FLEXIBLE;
+		/*
+		 * Will be reset by ctx_resched()'s flexible_sched_in().
+		 */
+		ctx->rotate_necessary = 0;
		ctx_resched(cpuctx, cpuctx->task_ctx, type);
	}

Then rotate_necessary will be tight.