[PATCH v2] drm/sched: Fix dynamic job-flow control race

[Danilo Krummrich]

On Fri, Sep 13, 2024 at 01:23:01PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark at chromium.org>
> 
> Fixes a race condition reported here: https://github.com/AsahiLinux/linux/issues/309#issuecomment-2238968609
> 
> The whole premise of lockless access to a single-producer-single-
> consumer queue is that there is just a single producer and single
> consumer.  That means we can't call drm_sched_can_queue() (which is
> about queueing more work to the hw, not to the spsc queue) from
> anywhere other than the consumer (wq).
> 
> This call in the producer is just an optimization to avoid scheduling
> the consuming worker if it cannot yet queue more work to the hw.  It
> is safe to drop this optimization to avoid the race condition.
> 
> Suggested-by: Asahi Lina <lina at asahilina.net>
> Fixes: a78422e9dff3 ("drm/sched: implement dynamic job-flow control")
> Closes: https://github.com/AsahiLinux/linux/issues/309
> Cc: stable at vger.kernel.org
> Signed-off-by: Rob Clark <robdclark at chromium.org>

Applied to drm-misc-fixes, thanks!

> ---
>  drivers/gpu/drm/scheduler/sched_entity.c | 4 ++--
>  drivers/gpu/drm/scheduler/sched_main.c   | 7 ++-----
>  include/drm/gpu_scheduler.h              | 2 +-
>  3 files changed, 5 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
> index 58c8161289fe..567e5ace6d0c 100644
> --- a/drivers/gpu/drm/scheduler/sched_entity.c
> +++ b/drivers/gpu/drm/scheduler/sched_entity.c
> @@ -380,7 +380,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
>  		container_of(cb, struct drm_sched_entity, cb);
>  
>  	drm_sched_entity_clear_dep(f, cb);
> -	drm_sched_wakeup(entity->rq->sched, entity);
> +	drm_sched_wakeup(entity->rq->sched);
>  }
>  
>  /**
> @@ -612,7 +612,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
>  		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
>  			drm_sched_rq_update_fifo(entity, submit_ts);
>  
> -		drm_sched_wakeup(entity->rq->sched, entity);
> +		drm_sched_wakeup(entity->rq->sched);
>  	}
>  }
>  EXPORT_SYMBOL(drm_sched_entity_push_job);
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index ab53ab486fe6..6f27cab0b76d 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -1013,15 +1013,12 @@ EXPORT_SYMBOL(drm_sched_job_cleanup);
>  /**
>   * drm_sched_wakeup - Wake up the scheduler if it is ready to queue
>   * @sched: scheduler instance
> - * @entity: the scheduler entity
>   *
>   * Wake up the scheduler if we can queue jobs.
>   */
> -void drm_sched_wakeup(struct drm_gpu_scheduler *sched,
> -		      struct drm_sched_entity *entity)
> +void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
>  {
> -	if (drm_sched_can_queue(sched, entity))
> -		drm_sched_run_job_queue(sched);
> +	drm_sched_run_job_queue(sched);
>  }
>  
>  /**
> diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
> index fe8edb917360..9c437a057e5d 100644
> --- a/include/drm/gpu_scheduler.h
> +++ b/include/drm/gpu_scheduler.h
> @@ -574,7 +574,7 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
>  
>  void drm_sched_tdr_queue_imm(struct drm_gpu_scheduler *sched);
>  void drm_sched_job_cleanup(struct drm_sched_job *job);
> -void drm_sched_wakeup(struct drm_gpu_scheduler *sched, struct drm_sched_entity *entity);
> +void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
>  bool drm_sched_wqueue_ready(struct drm_gpu_scheduler *sched);
>  void drm_sched_wqueue_stop(struct drm_gpu_scheduler *sched);
>  void drm_sched_wqueue_start(struct drm_gpu_scheduler *sched);
> -- 
> 2.46.0
>