Re: [PATCH v2 1/1] psi: stop relying on timer_pending for poll_work rescheduling

From: Peter Zijlstra <peterz@infradead.org>
To: Suren Baghdasaryan <surenb@google.com>
Cc: "Johannes Weiner" <hannes@cmpxchg.org>,
	"Ingo Molnar" <mingo@redhat.com>,
	"Juri Lelli" <juri.lelli@redhat.com>,
	"Vincent Guittot" <vincent.guittot@linaro.org>,
	"Dietmar Eggemann" <dietmar.eggemann@arm.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Benjamin Segall" <bsegall@google.com>,
	"Mel Gorman" <mgorman@suse.de>,
	"Daniel Bristot de Oliveira" <bristot@redhat.com>,
	matthias.bgg@gmail.com, "Minchan Kim" <minchan@google.com>,
	"Tim Murray" <timmurray@google.com>,
	"YT Chang" <yt.chang@mediatek.com>,
	"Wenju Xu (许文举)" <wenju.xu@mediatek.com>,
	"Jonathan JMChen (陳家明)" <jonathan.jmchen@mediatek.com>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	linux-mediatek@lists.infradead.org,
	kernel-team <kernel-team@android.com>,
	"SH Chen" <show-hong.chen@mediatek.com>
Subject: Re: [PATCH v2 1/1] psi: stop relying on timer_pending for poll_work rescheduling
Date: Fri, 2 Jul 2021 11:28:05 +0200	[thread overview]
Message-ID: <YN7cJZOZzjYJFClR@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <CAJuCfpFKDhcgjU=MGsz+JuetrWvYCe0EL3FMp91zopH+8T=mMQ@mail.gmail.com>

On Thu, Jul 01, 2021 at 09:28:04AM -0700, Suren Baghdasaryan wrote:
> On Thu, Jul 1, 2021 at 9:12 AM Peter Zijlstra <peterz@infradead.org> wrote:
> >
> > On Thu, Jul 01, 2021 at 09:09:25AM -0700, Suren Baghdasaryan wrote:
> > > On Thu, Jul 1, 2021 at 1:59 AM Peter Zijlstra <peterz@infradead.org> wrote:
> > > >
> > > > On Wed, Jun 30, 2021 at 01:51:51PM -0700, Suren Baghdasaryan wrote:
> > > > > +     /* cmpxchg should be called even when !force to set poll_scheduled */
> > > > > +     if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) && !force)
> > > > >               return;
> > > >
> > > > Why is that a cmpxchg() ?
> > >
> > > We want to set poll_scheduled and proceed with rescheduling the timer
> > > unless it's already scheduled, so cmpxchg helps us to make that
> > > decision atomically. Or did I misunderstand your question?
> >
> > What's wrong with: atomic_xchg(&group->poll_scheduled, 1) ?
> 
> Yes, since poll_scheduled can be only 0 or 1 atomic_xchg should work
> fine here. Functionally equivalent but I assume atomic_xchg() is more
> efficient due to no comparison.

Mostly conceptually simpler; the cmpxchg-on-0 makes that you have to
check if there's ever any state outside of {0,1}. The xchg() thing is
the classical test-and-set pattern.

On top of all that, the cmpxchg() can fail, which brings ordering
issues.

Typically, I think, you want to ensure that everything that happens
before psi_schedule_poll_work() is visible to the work when it runs
(also see Johannes' email). In case poll_scheduled is already 1, the
cmpxchg will fail and *NOT* provide that ordering. Meaning the work
might not observe the latest changes. xchg() doesn't have this subtlety.

_______________________________________________
Linux-mediatek mailing list
Linux-mediatek@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-mediatek