Re: [PATCH 07/19] sched/fair: Track LLC-preferred tasks per runqueue

[Tim Chen <tim.c.chen@linux.intel.com>]

On Thu, 2025-10-16 at 09:44 +0200, Peter Zijlstra wrote:
> On Wed, Oct 15, 2025 at 01:03:37PM -0700, Tim Chen wrote:
> > On Wed, 2025-10-15 at 14:05 +0200, Peter Zijlstra wrote:
> > > On Sat, Oct 11, 2025 at 11:24:44AM -0700, Tim Chen wrote:
> > > > @@ -3999,6 +4038,7 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
> > > >  		struct rq *rq = rq_of(cfs_rq);
> > > >  
> > > >  		account_numa_enqueue(rq, task_of(se));
> > > > +		account_llc_enqueue(rq, task_of(se));
> > > >  		list_add(&se->group_node, &rq->cfs_tasks);
> > > 
> > > Here and...
> > > 
> > > >  	}
> > > >  	cfs_rq->nr_queued++;
> > > > @@ -4010,9 +4050,14 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
> > > >  	update_load_sub(&cfs_rq->load, se->load.weight);
> > > >  	if (entity_is_task(se)) {
> > > >  		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
> > > > +		account_llc_dequeue(rq_of(cfs_rq), task_of(se));
> > > 
> > > ... here, could you please check the compiler is doing CSE of task_of()?
> > 
> > Will consolidate those task_of(se). 
> 
> And rq_of(). But really, check code-gen, it *should* DTRT and CSE the
> lot. If it doesn't, then do it manually.

Looking at the assembly dump, it does look like compiler is doing
the right thing and not computing those twice.

Tim