Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 28 Apr 2021 09:13:44 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Josh Don <joshdon@google.com>
Cc:     Joel Fernandes <joel@joelfernandes.org>,
        "Hyser,Chris" <chris.hyser@oracle.com>,
        Ingo Molnar <mingo@kernel.org>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Valentin Schneider <valentin.schneider@arm.com>,
        Mel Gorman <mgorman@suse.de>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 04/19] sched: Prepare for Core-wide rq->lock
Message-ID: <YIkLKNdr8Zld+0u4@hirez.programming.kicks-ass.net>
References: <20210422120459.447350175@infradead.org>
 <20210422123308.196692074@infradead.org>
 <CABk29Ntop2nX+z1bV7giG8ToR_w3f_+GYGAw+hFQ6g9rCZunmw@mail.gmail.com>
 <YIZ6ZpkrMGQ9A9x2@hirez.programming.kicks-ass.net>
 <CABk29NvicqM_c2ssYnDrEy_FPsfD5GH38rB_XHooErALOabe5g@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CABk29NvicqM_c2ssYnDrEy_FPsfD5GH38rB_XHooErALOabe5g@mail.gmail.com>
Precedence: bulk

On Mon, Apr 26, 2021 at 03:21:36PM -0700, Josh Don wrote:
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index f732642e3e09..1a81e9cc9e5d 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -290,6 +290,10 @@ static void sched_core_assert_empty(void)
> >  static void __sched_core_enable(void)
> >  {
> >         static_branch_enable(&__sched_core_enabled);
> > +       /*
> > +        * Ensure raw_spin_rq_*lock*() have completed before flipping.
> > +        */
> > +       synchronize_sched();
> 
> synchronize_rcu()

Moo, I actually like synchronize_sched() because it indicates it matches
a preempt disabled region.

> >         __sched_core_flip(true);
> >         sched_core_assert_empty();
> >  }
> > @@ -449,16 +453,22 @@ void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
> >  {
> >         raw_spinlock_t *lock;
> >
> > +       preempt_disable();
> >         if (sched_core_disabled()) {
> >                 raw_spin_lock_nested(&rq->__lock, subclass);
> > +               /* preempt *MUST* still be disabled here */
> > +               preempt_enable_no_resched();
> >                 return;
> >         }
> 
> This approach looks good to me. I'm guessing you went this route
> instead of doing the re-check after locking in order to optimize the
> disabled case?

Exactly.

> Recommend a comment that the preempt_disable() here pairs with the
> synchronize_rcu() in __sched_core_enable().

Fair enough.