[RFC 3/4] drm/sched: Always increment correct scheduler score

[Christian König]

Am 06.09.24 um 20:06 schrieb Tvrtko Ursulin:
> From: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
>
> Entities run queue can change during drm_sched_entity_push_job() so make
> sure to update the score consistently.
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
> Fixes: d41a39dda140 ("drm/scheduler: improve job distribution with multiple queues")

Good catch, that might explain some of the odd behavior we have seen for 
load balancing.

Reviewed-by: Christian König <christian.koenig at amd.com>

> Cc: Nirmoy Das <nirmoy.das at amd.com>
> Cc: Christian König <christian.koenig at amd.com>
> Cc: Luben Tuikov <ltuikov89 at gmail.com>
> Cc: Matthew Brost <matthew.brost at intel.com>
> Cc: David Airlie <airlied at gmail.com>
> Cc: Daniel Vetter <daniel at ffwll.ch>
> Cc: dri-devel at lists.freedesktop.org
> Cc: <stable at vger.kernel.org> # v5.9+
> ---
>   drivers/gpu/drm/scheduler/sched_entity.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 62b07ef7630a..2a910c1df072 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -586,7 +586,6 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
>   	ktime_t submit_ts;
>   
>   	trace_drm_sched_job(sched_job, entity);
> -	atomic_inc(entity->rq->sched->score);
>   	WRITE_ONCE(entity->last_user, current->group_leader);
>   
>   	/*
> @@ -612,6 +611,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
>   
>   		rq = entity->rq;
>   
> +		atomic_inc(rq->sched->score);
>   		drm_sched_rq_add_entity(rq, entity);
>   		spin_unlock(&entity->rq_lock);
>