Re: [PATCH] sched/fair: Fix flat hierarchy

[Peter Zijlstra]

On Fri, Aug 14, 2026 at 02:51:20PM +0200, Vincent Guittot wrote:
> On Fri, 14 Aug 2026 at 13:22, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> >
> > On Fri, Aug 14, 2026 at 11:26:13AM +0200, Vincent Guittot wrote:
> >
> > > For the enqueue, the 1st requeue_delayed_entity() which is the main
> > > path for delayed task, requires the update. Then another one before
> > > reweight_eevdf(cfs_rq, se, weight, false); in the !curr case.
> > >
> > > But I'm not sure we want to spread this in different places.
> >
> > Fair enough. I'll test the below and then push to sched/urgent.
> 
> I tested this patch on sched/core.
> 
> That being said, 7.2 wants something like below for requeued_delayed_entity()
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index fd3edf72fb6e..3defda0e2f83 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -7802,6 +7802,8 @@ requeue_delayed_entity(struct sched_entity *se)
>         WARN_ON_ONCE(!se->sched_delayed);
>         WARN_ON_ONCE(!se->on_rq);
> 
> +       update_curr(cfs_rq);
> +
>         if (update_entity_lag(cfs_rq, se)) {
>                 cfs_rq->nr_queued--;
>                 if (se != cfs_rq->curr)
> 
> So I would put the cahnge above in sched/urgent and the patch
> discussed here in sched/core

Right. I've pushed out sched/urgent and sched/core to queue.git. If you
could double check that, I'll push them out to tip later today.

For now, I'm going to go melt someplace outside for a bit.