[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <1433255230.1495.2.camel@twins>
Date: Tue, 02 Jun 2015 16:27:10 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Kirill Tkhai <tkhai@...dex.ru>
Cc: "umgwanakikbuti@...il.com" <umgwanakikbuti@...il.com>,
"mingo@...e.hu" <mingo@...e.hu>,
"ktkhai@...allels.com" <ktkhai@...allels.com>,
"rostedt@...dmis.org" <rostedt@...dmis.org>,
"juri.lelli@...il.com" <juri.lelli@...il.com>,
"pang.xunlei@...aro.org" <pang.xunlei@...aro.org>,
"oleg@...hat.com" <oleg@...hat.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC][PATCH 3/7] sched: Allow balance callbacks for
check_class_changed()
On Tue, 2015-06-02 at 16:58 +0300, Kirill Tkhai wrote:
> 01.06.2015, 17:13, "Peter Zijlstra" <peterz@...radead.org>:
> > @@ -1010,7 +1014,7 @@ static inline void check_class_changed(s
> > if (prev_class != p->sched_class) {
> > if (prev_class->switched_from)
> > prev_class->switched_from(rq, p);
> > - /* Possble rq->lock 'hole'. */
> > +
>
> But switched_from_dl()->cancel_dl_timer() still unlocks rq->lock.
>
> It seems we should drop it (cancel_dl_timer) and move hrtimer_cancel()
> from switched_from_dl() to finish_task_switch(). It will be executed
> for all classes and completely take the functionality we implement
> cancel_dl_timer() for.
*groan* yes.. I don't like moving it into generic code though.
more thinking required.
> > p->sched_class->switched_to(rq, p);
> > } else if (oldprio != p->prio || dl_task(p))
> > p->sched_class->prio_changed(rq, p, oldprio);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists