mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
	Michael Turquette <mturquette@baylibre.com>,
	"rjw@rjwysocki.net" <rjw@rjwysocki.net>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	"linux-pm@vger.kernel.org" <linux-pm@vger.kernel.org>,
	Juri Lelli <Juri.Lelli@arm.com>,
	Steve Muckle <steve.muckle@linaro.org>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Michael Turquette <mturquette+renesas@baylibre.com>
Subject: Re: [PATCH 5/8] sched/cpufreq: pass sched class into cpufreq_update_util
Date: Wed, 16 Mar 2016 14:43:38 +0100	[thread overview]
Message-ID: <20160316134338.GX6344@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <CAJZ5v0hMqZ2+6wKf8f1enmCWjaTQJFdBoyCQOUrnUYJ1zfUX5g@mail.gmail.com>

On Wed, Mar 16, 2016 at 02:23:21PM +0100, Rafael J. Wysocki wrote:
> On Wed, Mar 16, 2016 at 2:10 PM, Peter Zijlstra <peterz@infradead.org> wrote:
> > (this would of course require we allocate struct update_util_data with
> > the proper alignment thingies etc..)

> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index ba49c9efd0b2..d34d75c5cc93 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -3236,8 +3236,10 @@ static inline unsigned long rlimit_max(unsigned int limit)
> >
> >  #ifdef CONFIG_CPU_FREQ
> >  struct update_util_data {
> > -       void (*func)(struct update_util_data *data,
> > -                    u64 time, unsigned long util, unsigned long max);
> > +       unsigned long *cfs_util_avg;
> > +       unsigned long *cfs_util_max;
> > +
> > +       void (*func)(struct update_util_data *data, u64 time);
> >  };

we should add: ____cacheline_aligned here

> How do we ensure proper alignment?

Depends on the allocator; not all of them respect the struct alignment
attribute.

kernel/sched/cpufreq.c:DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);

That one could use:

DEFINE_PER_CPU_ALIGNED() instead

as would this one:

drivers/cpufreq/cpufreq_governor.c:static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);

Because when you cacheline align dbs_info, its update_util_data member
will also get the correct alignment because of the structure attribute.

  reply	other threads:[~2016-03-16 13:44 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-14  5:22 [PATCH 0/8] schedutil enhancements Michael Turquette
2016-03-14  5:22 ` [PATCH 1/8] sched/cpufreq: remove cpufreq_trigger_update() Michael Turquette
2016-03-15 21:14   ` Peter Zijlstra
     [not found]     ` <20160315214545.30639.98727@quark.deferred.io>
2016-03-15 21:49       ` Peter Zijlstra
2016-03-16  8:00   ` Peter Zijlstra
2016-03-14  5:22 ` [PATCH 2/8] sched/fair: add margin to utilization update Michael Turquette
2016-03-15 21:16   ` Peter Zijlstra
     [not found]     ` <20160315212848.30639.38747@quark.deferred.io>
2016-03-15 21:43       ` Peter Zijlstra
2016-03-16  2:52   ` Steve Muckle
2016-03-16 22:12     ` Michael Turquette
2016-03-14  5:22 ` [PATCH 3/8] sched/cpufreq: new cfs capacity margin helpers Michael Turquette
2016-03-15 21:17   ` Peter Zijlstra
2016-03-14  5:22 ` [PATCH 4/8] cpufreq/schedutil: sysfs capacity margin tunable Michael Turquette
2016-03-15 21:20   ` Peter Zijlstra
     [not found]     ` <20160315214043.30639.75507@quark.deferred.io>
2016-03-15 21:48       ` Peter Zijlstra
     [not found]         ` <20160315223701.30639.43127@quark.deferred.io>
2016-03-16  3:36           ` Steve Muckle
2016-03-16  8:05             ` Peter Zijlstra
2016-03-16 10:02               ` Juri Lelli
2016-03-16 17:55                 ` Steve Muckle
2016-03-16 22:05                   ` Michael Turquette
2016-03-17  9:40                   ` Juri Lelli
2016-03-17 13:55                     ` Steve Muckle
2016-03-17 15:53                       ` Patrick Bellasi
2016-03-17 17:54                         ` Juri Lelli
2016-03-17 18:56                           ` Michael Turquette
2016-03-17 22:34                             ` Rafael J. Wysocki
2016-03-16 12:45               ` Rafael J. Wysocki
2016-03-16 22:03             ` Michael Turquette
2016-03-14  5:22 ` [PATCH 5/8] sched/cpufreq: pass sched class into cpufreq_update_util Michael Turquette
2016-03-15 21:25   ` Peter Zijlstra
     [not found]     ` <20160315220609.30639.67271@quark.deferred.io>
2016-03-16  3:55       ` Steve Muckle
2016-03-16  7:41       ` Peter Zijlstra
2016-03-16  8:29         ` Vincent Guittot
2016-03-16  8:53           ` Peter Zijlstra
2016-03-16  9:16             ` Vincent Guittot
2016-03-16 12:39             ` Rafael J. Wysocki
2016-03-16 13:10               ` Peter Zijlstra
2016-03-16 13:23                 ` Rafael J. Wysocki
2016-03-16 13:43                   ` Peter Zijlstra [this message]
2016-03-14  5:22 ` [PATCH 6/8] cpufreq/schedutil: sum per-sched class utilization Michael Turquette
2016-03-15 21:29   ` Peter Zijlstra
     [not found]     ` <20160315220951.30639.12872@quark.deferred.io>
2016-03-16  7:38       ` Peter Zijlstra
2016-03-16 18:20         ` Steve Muckle
2016-03-16 18:36           ` Peter Zijlstra
2016-03-16 19:12             ` Steve Muckle
2016-03-14  5:22 ` [PATCH 7/8] cpufreq: Frequency invariant scheduler load-tracking support Michael Turquette
2016-03-15 19:13   ` Dietmar Eggemann
2016-03-15 20:19     ` Michael Turquette
2016-03-15 21:32       ` Peter Zijlstra
2016-03-16 18:33       ` Dietmar Eggemann
2016-03-15 21:34   ` Peter Zijlstra
2016-03-14  5:22 ` [PATCH 8/8] sched: prefer cpufreq_scale_freq_capacity Michael Turquette
2016-03-15 19:13   ` Dietmar Eggemann
2016-03-15 20:46     ` Michael Turquette
2016-03-16 19:44       ` Dietmar Eggemann
2016-03-16 20:07         ` Peter Zijlstra
2016-03-16 21:32           ` Rafael J. Wysocki
2016-03-15 21:37   ` Peter Zijlstra
     [not found]     ` <20160315222721.30639.28332@quark.deferred.io>
2016-03-16  7:47       ` Peter Zijlstra
2016-03-16 12:41         ` Peter Zijlstra
2016-03-16  0:08 ` [PATCH 0/8] schedutil enhancements Rafael J. Wysocki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160316134338.GX6344@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=Juri.Lelli@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=morten.rasmussen@arm.com \
    --cc=mturquette+renesas@baylibre.com \
    --cc=mturquette@baylibre.com \
    --cc=rafael@kernel.org \
    --cc=rjw@rjwysocki.net \
    --cc=steve.muckle@linaro.org \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome