Re: [patch 1/2] nohz: only wakeup a single target cpu when kicking a task

[Peter Xu <peterx@redhat.com>]

On Thu, Oct 08, 2020 at 05:28:44PM +0200, Peter Zijlstra wrote:
> 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.

Thanks Peter.  So is that a lighter but trickier version of get_online_cpus()
which is even allowed with spinlock?

I noticed that this method was actually mentioned in the old cpu-hotplug.txt,
but it was removed during the convertion to rst:

  ff58fa7f556c ("Documentation: Update CPU hotplug and move it to core-api")

Not sure whether it's intended, just to raise this up.  If it's still valid,
maybe still worth to document it somewhere.

-- 
Peter Xu