[PATCH 4/8] drm/sched: Optimise drm_sched_entity_push_job

[Christian König]

Am 13.09.24 um 18:05 schrieb Tvrtko Ursulin:
> From: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
>
> In FIFO mode We can avoid dropping the lock only to immediately re-acquire
> by adding a new drm_sched_rq_update_fifo_locked() helper.
>
> v2:
>   * Remove drm_sched_rq_update_fifo() altogether. (Christian)
>
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
> Cc: Christian König <christian.koenig at amd.com>
> Cc: Alex Deucher <alexander.deucher at amd.com>
> Cc: Luben Tuikov <ltuikov89 at gmail.com>
> Cc: Matthew Brost <matthew.brost at intel.com>
> Cc: Philipp Stanner <pstanner at redhat.com>

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

> ---
>   drivers/gpu/drm/scheduler/sched_entity.c | 13 +++++++++----
>   drivers/gpu/drm/scheduler/sched_main.c   |  6 +++---
>   include/drm/gpu_scheduler.h              |  2 +-
>   3 files changed, 13 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 6645a8524699..aff79055643f 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -514,8 +514,12 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
>   		struct drm_sched_job *next;
>   
>   		next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
> -		if (next)
> -			drm_sched_rq_update_fifo(entity, next->submit_ts);
> +		if (next) {
> +			spin_lock(&entity->rq_lock);
> +			drm_sched_rq_update_fifo_locked(entity,
> +							next->submit_ts);
> +			spin_unlock(&entity->rq_lock);
> +		}
>   	}
>   
>   	/* Jobs and entities might have different lifecycles. Since we're
> @@ -615,10 +619,11 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
>   
>   		atomic_inc(sched->score);
>   		drm_sched_rq_add_entity(rq, entity);
> -		spin_unlock(&entity->rq_lock);
>   
>   		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
> -			drm_sched_rq_update_fifo(entity, submit_ts);
> +			drm_sched_rq_update_fifo_locked(entity, submit_ts);
> +
> +		spin_unlock(&entity->rq_lock);
>   
>   		drm_sched_wakeup(sched, entity);
>   	}
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index f093616fe53c..d0ee0ba75a86 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -163,14 +163,15 @@ static inline void drm_sched_rq_remove_fifo_locked(struct drm_sched_entity *enti
>   	}
>   }
>   
> -void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
> +void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, ktime_t ts)
>   {
>   	/*
>   	 * Both locks need to be grabbed, one to protect from entity->rq change
>   	 * for entity from within concurrent drm_sched_entity_select_rq and the
>   	 * other to update the rb tree structure.
>   	 */
> -	spin_lock(&entity->rq_lock);
> +	lockdep_assert_held(&entity->rq_lock);
> +
>   	spin_lock(&entity->rq->lock);
>   
>   	drm_sched_rq_remove_fifo_locked(entity);
> @@ -181,7 +182,6 @@ void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts)
>   		      drm_sched_entity_compare_before);
>   
>   	spin_unlock(&entity->rq->lock);
> -	spin_unlock(&entity->rq_lock);
>   }
>   
>   /**
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index a8d19b10f9b8..38465b78c7d5 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -593,7 +593,7 @@ void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
>   void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
>   				struct drm_sched_entity *entity);
>   
> -void drm_sched_rq_update_fifo(struct drm_sched_entity *entity, ktime_t ts);
> +void drm_sched_rq_update_fifo_locked(struct drm_sched_entity *entity, ktime_t ts);
>   
>   int drm_sched_entity_init(struct drm_sched_entity *entity,
>   			  enum drm_sched_priority priority,