Re: [PATCH 07/28] drm/sched: Free all finished jobs at once

[Matthew Brost <matthew.brost@intel.com>]

On Wed, Oct 08, 2025 at 09:53:38AM +0100, Tvrtko Ursulin wrote:
> To implement fair scheduling we will need as accurate as possible view
> into per entity GPU time utilisation. Because sched fence execution time
> are only adjusted for accuracy in the free worker we need to process
> completed jobs as soon as possible so the metric is most up to date when
> view from the submission side of things.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
> Cc: Christian König <christian.koenig@amd.com>
> Cc: Danilo Krummrich <dakr@kernel.org>
> Cc: Matthew Brost <matthew.brost@intel.com>

Reviewed-by: Matthew Brost <matthew.brost@intel.com>

> Cc: Philipp Stanner <phasta@kernel.org>
> ---
>  drivers/gpu/drm/scheduler/sched_main.c | 13 ++-----------
>  1 file changed, 2 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 41bfee6b1777..41e076fdcb0d 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -906,7 +906,6 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
>   * drm_sched_get_finished_job - fetch the next finished job to be destroyed
>   *
>   * @sched: scheduler instance
> - * @have_more: are there more finished jobs on the list
>   *
>   * Informs the caller through @have_more whether there are more finished jobs
>   * besides the returned one.
> @@ -915,7 +914,7 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
>   * ready for it to be destroyed.
>   */
>  static struct drm_sched_job *
> -drm_sched_get_finished_job(struct drm_gpu_scheduler *sched, bool *have_more)
> +drm_sched_get_finished_job(struct drm_gpu_scheduler *sched)
>  {
>  	struct drm_sched_job *job, *next;
>  
> @@ -930,7 +929,6 @@ drm_sched_get_finished_job(struct drm_gpu_scheduler *sched, bool *have_more)
>  		/* cancel this job's TO timer */
>  		cancel_delayed_work(&sched->work_tdr);
>  
> -		*have_more = false;
>  		next = list_first_entry_or_null(&sched->pending_list,
>  						typeof(*next), list);
>  		if (next) {
> @@ -940,8 +938,6 @@ drm_sched_get_finished_job(struct drm_gpu_scheduler *sched, bool *have_more)
>  				next->s_fence->scheduled.timestamp =
>  					dma_fence_timestamp(&job->s_fence->finished);
>  
> -			*have_more = dma_fence_is_signaled(&next->s_fence->finished);
> -
>  			/* start TO timer for next job */
>  			drm_sched_start_timeout(sched);
>  		}
> @@ -1000,14 +996,9 @@ static void drm_sched_free_job_work(struct work_struct *w)
>  	struct drm_gpu_scheduler *sched =
>  		container_of(w, struct drm_gpu_scheduler, work_free_job);
>  	struct drm_sched_job *job;
> -	bool have_more;
>  
> -	job = drm_sched_get_finished_job(sched, &have_more);
> -	if (job) {
> +	while ((job = drm_sched_get_finished_job(sched)))
>  		sched->ops->free_job(job);
> -		if (have_more)
> -			drm_sched_run_free_queue(sched);
> -	}
>  
>  	drm_sched_run_job_queue(sched);
>  }
> -- 
> 2.48.0
>