linux-kernel - Re: [RFC][PATCH 05/18] sched: Provide p->on

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <AANLkTinmKHSPbrR5Z3_wD52RQRXfZHPSH+b9n2CNPZ8K@mail.gmail.com>
Date:	Wed, 5 Jan 2011 16:13:54 +0800
From:	Yong Zhang <yong.zhang0@...il.com>
To:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc:	Chris Mason <chris.mason@...cle.com>,
	Frank Rowand <frank.rowand@...sony.com>,
	Ingo Molnar <mingo@...e.hu>,
	Thomas Gleixner <tglx@...utronix.de>,
	Mike Galbraith <efault@....de>,
	Oleg Nesterov <oleg@...hat.com>, Paul Turner <pjt@...gle.com>,
	Jens Axboe <axboe@...nel.dk>, linux-kernel@...r.kernel.org
Subject: Re: [RFC][PATCH 05/18] sched: Provide p->on_rq

On Tue, Jan 4, 2011 at 10:59 PM, Peter Zijlstra <a.p.zijlstra@...llo.nl> wrote:
> Provide a generic p->on_rq because the p->se.on_rq semantics are
> unfavourable for lockless wakeups but needed for sched_fair.
>
> In particular, p->on_rq is only cleared when we actually dequeue the
> task in schedule() and not on any random dequeue as done by things
> like __migrate_task() and __sched_setscheduler().
>
> This also allows us to remove p->se usage from !sched_fair code.
>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
> ---
>  include/linux/sched.h   |    1 +
>  kernel/sched.c          |   36 ++++++++++++++++++------------------
>  kernel/sched_debug.c    |    2 +-
>  kernel/sched_rt.c       |   10 +++++-----
>  kernel/sched_stoptask.c |    2 +-
>  5 files changed, 26 insertions(+), 25 deletions(-)
>
> Index: linux-2.6/kernel/sched_rt.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched_rt.c
> +++ linux-2.6/kernel/sched_rt.c
> @@ -1132,7 +1132,7 @@ static void put_prev_task_rt(struct rq *
>         * The previous task needs to be made eligible for pushing
>         * if it is still active
>         */
> -       if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
> +       if (p->on_rq && p->rt.nr_cpus_allowed > 1)

How about on_rt_rq(&p->rt) here?

Quoted from my previous reply:
[Seems we need on_rt_rq(&p->rt) here, otherwise we enqueue the
task to pushable list when called from rt_mutex_setprio()/
__sched_setscheduler() etc. Thus add a little overhead.
Though we call dequeue_pushable_task() in set_curr_task_rt()
unconditionally.]

Thanks,
Yong

>                enqueue_pushable_task(rq, p);
>  }
>
> @@ -1283,7 +1283,7 @@ static struct rq *find_lock_lowest_rq(st
>                                     !cpumask_test_cpu(lowest_rq->cpu,
>                                                       &task->cpus_allowed) ||
>                                     task_running(rq, task) ||
> -                                    !task->se.on_rq)) {
> +                                    !task->on_rq)) {
>
>                                raw_spin_unlock(&lowest_rq->lock);
>                                lowest_rq = NULL;
> @@ -1317,7 +1317,7 @@ static struct task_struct *pick_next_pus
>        BUG_ON(task_current(rq, p));
>        BUG_ON(p->rt.nr_cpus_allowed <= 1);
>
> -       BUG_ON(!p->se.on_rq);
> +       BUG_ON(!p->on_rq);
>        BUG_ON(!rt_task(p));
>
>        return p;
> @@ -1463,7 +1463,7 @@ static int pull_rt_task(struct rq *this_
>                 */
>                if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
>                        WARN_ON(p == src_rq->curr);
> -                       WARN_ON(!p->se.on_rq);
> +                       WARN_ON(!p->on_rq);
>
>                        /*
>                         * There's a chance that p is higher in priority
> @@ -1534,7 +1534,7 @@ static void set_cpus_allowed_rt(struct t
>         * Update the migration status of the RQ if we have an RT task
>         * which is running AND changing its weight value.
>         */
> -       if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
> +       if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
>                struct rq *rq = task_rq(p);
>
>                if (!task_current(rq, p)) {
> Index: linux-2.6/kernel/sched_stoptask.c
> ===================================================================
> --- linux-2.6.orig/kernel/sched_stoptask.c
> +++ linux-2.6/kernel/sched_stoptask.c
> @@ -26,7 +26,7 @@ static struct task_struct *pick_next_tas
>  {
>        struct task_struct *stop = rq->stop;
>
> -       if (stop && stop->se.on_rq)
> +       if (stop && stop->on_rq)
>                return stop;
>
>        return NULL;
>
>
>



-- 
Only stand for myself