All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Tejun Heo <tj@kernel.org>
Cc: tglx@linutronix.de, mingo@elte.hu, avi@redhat.com, efault@gmx.de,
	rusty@rustcorp.com.au, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 4/7] sched: implement force_cpus_allowed()
Date: Fri, 04 Dec 2009 11:40:59 +0100	[thread overview]
Message-ID: <1259923259.3977.1928.camel@laptop> (raw)
In-Reply-To: <1259726212-30259-5-git-send-email-tj@kernel.org>

On Wed, 2009-12-02 at 12:56 +0900, Tejun Heo wrote:
> set_cpus_allowed_ptr() modifies the allowed cpu mask of a task.  The
> function performs the following checks before applying new mask.
> 
> * Check whether PF_THREAD_BOUND is set.  This is set for bound
>   kthreads so that they can't be moved around.
> 
> * Check whether the target cpu is still marked active - cpu_active().
>   Active state is cleared early while downing a cpu.
> 
> This patch adds force_cpus_allowed() which bypasses the above two
> checks.  The caller is responsible for guaranteeing that the
> destination cpu doesn't go down until force_cpus_allowed() finishes.
> 
> The first check is bypassed by factoring out actual migration part
> into __set_cpus_allowed() from set_cpus_allowed_ptr() and calling the
> inner function from force_cpus_allowed().
> 
> The second check is buried deep down in __migrate_task() which is
> executed by migration threads.  @force parameter is added to
> __migrate_task().  As the only way to pass parameters from
> __set_cpus_allowed() is through migration_req, migration_req->force is
> added and the @force parameter is passed down to __migrate_task().
> 
> Please note the naming discrepancy between set_cpus_allowed_ptr() and
> the new functions.  The _ptr suffix is from the days when cpumask api
> wasn't mature and future changes should drop it from
> set_cpus_allowed_ptr() too.
> 
> force_cpus_allowed() will be used for concurrency-managed workqueue.

Would still like to know why all this is needed.


  reply	other threads:[~2009-12-04 10:41 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-12-02  3:56 [PATCHSET tip/sched/core] sched: concurrency managed workqueue related sched patches Tejun Heo
2009-12-02  3:56 ` [PATCH 1/7] sched: revert 498657a478c60be092208422fefa9c7b248729c2 Tejun Heo
2009-12-02 10:42   ` [tip:sched/core] sched: Revert 498657a478c60be092208422fefa9c7b248729c2 tip-bot for Tejun Heo
2009-12-02  3:56 ` [PATCH 2/7] sched: rename preempt_notifiers to sched_notifiers and refactor implementation Tejun Heo
2009-12-02  3:56 ` [PATCH 3/7] sched: refactor try_to_wake_up() Tejun Heo
2009-12-02  9:05   ` Mike Galbraith
2009-12-02  9:51     ` Tejun Heo
2009-12-02 10:10       ` Mike Galbraith
2009-12-02 10:14         ` Tejun Heo
2009-12-02 11:01           ` Peter Zijlstra
2009-12-03  6:11   ` [PATCH UDPATED " Tejun Heo
2009-12-02  3:56 ` [PATCH 4/7] sched: implement force_cpus_allowed() Tejun Heo
2009-12-04 10:40   ` Peter Zijlstra [this message]
2009-12-04 10:43     ` Peter Zijlstra
2009-12-07  4:34       ` Tejun Heo
2009-12-07  8:35         ` Peter Zijlstra
2009-12-07 10:34           ` Tejun Heo
2009-12-07 10:54             ` Peter Zijlstra
2009-12-07 11:07               ` Tejun Heo
2009-12-08  8:41                 ` Tejun Heo
2009-12-08  9:02                   ` Peter Zijlstra
2009-12-08  9:12                     ` Tejun Heo
2009-12-08 10:34                       ` Peter Zijlstra
2009-12-08 10:38                         ` Peter Zijlstra
2009-12-08 11:26                           ` Tejun Heo
2009-12-08 11:24                         ` Tejun Heo
2009-12-08 11:48                           ` Peter Zijlstra
2009-12-08 11:56                             ` Tejun Heo
2009-12-08 12:10                               ` Peter Zijlstra
2009-12-08 12:23                                 ` Tejun Heo
2009-12-08 13:35                                   ` Peter Zijlstra
2009-12-09  5:25                                     ` Tejun Heo
2009-12-09  7:41                                       ` Peter Zijlstra
2009-12-09  8:03                                         ` Tejun Heo
2009-12-02  3:56 ` [PATCH 5/7] sched: make sched_notifiers unconditional Tejun Heo
2009-12-02  3:56 ` [PATCH 6/7] sched: add wakeup/sleep sched_notifiers and allow NULL notifier ops Tejun Heo
2009-12-02  3:56 ` [PATCH 7/7] sched: implement try_to_wake_up_local() Tejun Heo
2009-12-03  6:13   ` [PATCH UPDATED " Tejun Heo
2009-12-04 10:47     ` Peter Zijlstra
2009-12-07  3:31       ` Tejun Heo
2009-12-04 10:44   ` [PATCH " Peter Zijlstra
2009-12-07  3:26     ` Tejun Heo
2009-12-07  8:50       ` Peter Zijlstra
2009-12-07  8:56         ` Peter Zijlstra
2009-12-07 10:27           ` Tejun Heo
2009-12-08  8:53             ` Peter Zijlstra
2009-12-08  9:16               ` Tejun Heo

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=1259923259.3977.1928.camel@laptop \
    --to=peterz@infradead.org \
    --cc=avi@redhat.com \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rusty@rustcorp.com.au \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.