Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1623081

Re: [PATCH v2] sched: Have do_idle() call __schedule() without enabling preemption

From Peter Zijlstra <peterz@infradead.org>
Newsgroups linux.kernel
Subject Re: [PATCH v2] sched: Have do_idle() call __schedule() without enabling preemption
Date 2017-04-13 16:40 +0200
Message-ID <tvO4F-4ff-1@gated-at.bofh.it> (permalink)
References <tvvbH-7UV-13@gated-at.bofh.it> <tvIBX-oq-7@gated-at.bofh.it> <tvNij-3GT-41@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

On Thu, Apr 13, 2017 at 09:48:40AM -0400, Steven Rostedt wrote:
> On Thu, 13 Apr 2017 10:44:53 +0200
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Wed, Apr 12, 2017 at 02:27:44PM -0400, Steven Rostedt wrote:
> > > + * schedule_idle() is similar to schedule_preempt_disable() except
> > > + * that it never enables preemption.  
> > 
> > That's not right. The primary distinction is that it doesn't call
> > sched_submit_work().
> 
> That has nothing to do with fixing synchronize_rcu_tasks(), which is
> the entire point of my patch, thus it is *not* the primary distinction.

It is. The only reason you _can_ avoid that preemption window is by not
doing sched_submit_work().

The moment you need to call that, the preemption window comes back.

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v2] sched: Have do_idle() call __schedule() without   enabling preemption Steven Rostedt <rostedt@goodmis.org> - 2017-04-12 20:30 +0200
  Re: [PATCH v2] sched: Have do_idle() call __schedule() without   enabling preemption Steven Rostedt <rostedt@goodmis.org> - 2017-04-12 20:40 +0200
  Re: [PATCH v2] sched: Have do_idle() call __schedule() without   enabling preemption "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-13 01:50 +0200
    Re: [PATCH v2] sched: Have do_idle() call __schedule() without   enabling preemption Steven Rostedt <rostedt@goodmis.org> - 2017-04-13 02:50 +0200
      Re: [PATCH v2] sched: Have do_idle() call __schedule() without  enabling preemption "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2017-04-13 03:00 +0200
  Re: [PATCH v2] sched: Have do_idle() call __schedule() without  enabling preemption Peter Zijlstra <peterz@infradead.org> - 2017-04-13 10:50 +0200
    Re: [PATCH v2] sched: Have do_idle() call __schedule() without  enabling preemption Steven Rostedt <rostedt@goodmis.org> - 2017-04-13 15:50 +0200
      Re: [PATCH v2] sched: Have do_idle() call __schedule() without  enabling preemption Peter Zijlstra <peterz@infradead.org> - 2017-04-13 16:40 +0200
        Re: [PATCH v2] sched: Have do_idle() call __schedule() without  enabling preemption Steven Rostedt <rostedt@goodmis.org> - 2017-04-13 17:00 +0200

csiph-web