Re: [PATCH 1/4] rcu/nocb: Pass a cpumask instead of a single CPU to offload/deoffload

[Paul E. McKenney]

On Thu, May 26, 2022 at 12:19:17AM +0200, Frederic Weisbecker wrote:
> On Thu, May 26, 2022 at 12:10:52AM +0200, Frederic Weisbecker wrote:
> > @@ -1117,12 +1111,6 @@ static long rcu_nocb_rdp_offload(void *arg)
> >  	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
> >  
> >  	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
> > -	/*
> > -	 * For now we only support re-offload, ie: the rdp must have been
> > -	 * offloaded on boot first.
> > -	 */
> > -	if (!rdp->nocb_gp_rdp)
> > -		return -EINVAL;
> >  
> >  	if (WARN_ON_ONCE(!rdp_gp->nocb_gp_kthread))
> >  		return -EINVAL;
> 
> And why did I remove this critical check? I have no answer...

Me, I was going to ask if rcutorture should (de)offload multiple
CPUs in one go...  ;-)

							Thanx, Paul