Re: [patch 1/2] nohz: only wakeup a single target cpu when kicking a task
From: Peter Zijlstra
Date: Thu Oct 08 2020 - 11:28:53 EST
On Thu, Oct 08, 2020 at 10:59:40AM -0400, Peter Xu wrote:
> On Wed, Oct 07, 2020 at 03:01:52PM -0300, Marcelo Tosatti wrote:
> > +static void tick_nohz_kick_task(struct task_struct *tsk)
> > +{
> > + int cpu = task_cpu(tsk);
> > +
> > + /*
> > + * If the task concurrently migrates to another cpu,
> > + * we guarantee it sees the new tick dependency upon
> > + * schedule.
> > + *
> > + *
> > + * set_task_cpu(p, cpu);
> > + * STORE p->cpu = @cpu
> > + * __schedule() (switch to task 'p')
> > + * LOCK rq->lock
> > + * smp_mb__after_spin_lock() STORE p->tick_dep_mask
> > + * tick_nohz_task_switch() smp_mb() (atomic_fetch_or())
> > + * LOAD p->tick_dep_mask LOAD p->cpu
> > + */
> > +
> > + preempt_disable();
>
> Pure question: is preempt_disable() required here? Same question to
> tick_nohz_full_kick_all().
I think it serializes against hotplug.
>
> > + if (cpu_online(cpu))
> > + tick_nohz_full_kick_cpu(cpu);
> > + preempt_enable();
> > +}