Re: [PATCH 3/3] rcu/exp: Remove needless CPU up quiescent state report

From: Frederic Weisbecker
Date: Fri Feb 21 2025 - 10:34:45 EST


Le Wed, Feb 19, 2025 at 07:55:05AM -0800, Paul E. McKenney a écrit :
> > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > index 86935fe00397..40d6090a33f5 100644
> > > --- a/kernel/rcu/tree.c
> > > +++ b/kernel/rcu/tree.c
> > > @@ -4347,6 +4347,12 @@ void rcutree_report_cpu_dead(void)
> > > * may introduce a new READ-side while it is actually off the QS masks.
> > > */
> > > lockdep_assert_irqs_disabled();
> > > + /*
> > > + * CPUHP_AP_SMPCFD_DYING was the last call for rcu_exp_handler() execution.
> > > + * The requested QS must have been reported on the last context switch
> > > + * from stop machine to idle.
> > > + */
> > > + WARN_ON_ONCE(rdp->cpu_no_qs.b.exp);
> > > // Do any dangling deferred wakeups.
> > > do_nocb_deferred_wakeup(rdp);
> >
> > I fired off a 30-minute run of 100*TREE03 with this change also.
>
> And no failures!

Ok I'm adding that one on my queue.

>
> Thanx, Paul
>
> > > > 3. Your ideas here! ;-)
> > >
> > > :-)
> >
> > Thanx, Paul