[PATCH v2] drm: Don't free jobs in wait_event_interruptible()

[PATCH v2] drm: Don't free jobs in wait_event_interruptible()

[Steven Price]

drm_sched_cleanup_jobs() attempts to free finished jobs, however because
it is called as the condition of wait_event_interruptible() it must not
sleep. Unfortuantly some free callbacks (notibly for Panfrost) do sleep.

Instead let's rename drm_sched_cleanup_jobs() to
drm_sched_get_cleanup_job() and simply return a job for processing if
there is one. The caller can then call the free_job() callback outside
the wait_event_interruptible() where sleeping is possible before
re-checking and returning to sleep if necessary.

Signed-off-by: Steven Price <steven.price@arm.com>
---

Changes from v1:
 * Move list_first_entry_or_null() within the lock

 drivers/gpu/drm/scheduler/sched_main.c | 44 ++++++++++++++------------
 1 file changed, 24 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74d82dc..0ed4aaa4e6d1 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -622,43 +622,41 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 }
 
 /**
- * drm_sched_cleanup_jobs - destroy finished jobs
+ * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
  *
- * Remove all finished jobs from the mirror list and destroy them.
+ * Returns the next finished job from the mirror list (if there is one)
+ * ready for it to be destroyed.
  */
-static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
+static struct drm_sched_job *
+drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 {
+	struct drm_sched_job *job = NULL;
 	unsigned long flags;
 
 	/* Don't destroy jobs while the timeout worker is running */
 	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
 	    !cancel_delayed_work(&sched->work_tdr))
-		return;
-
-
-	while (!list_empty(&sched->ring_mirror_list)) {
-		struct drm_sched_job *job;
+		return NULL;
 
-		job = list_first_entry(&sched->ring_mirror_list,
+	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
-		if (!dma_fence_is_signaled(&job->s_fence->finished))
-			break;
 
-		spin_lock_irqsave(&sched->job_list_lock, flags);
+	spin_lock_irqsave(&sched->job_list_lock, flags);
+
+	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from ring_mirror_list */
 		list_del_init(&job->node);
-		spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-		sched->ops->free_job(job);
+	} else {
+		job = NULL;
+		/* queue timeout for next job */
+		drm_sched_start_timeout(sched);
 	}
 
-	/* queue timeout for next job */
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	drm_sched_start_timeout(sched);
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 
+	return job;
 }
 
 /**
@@ -698,12 +696,18 @@ static int drm_sched_main(void *param)
 		struct drm_sched_fence *s_fence;
 		struct drm_sched_job *sched_job;
 		struct dma_fence *fence;
+		struct drm_sched_job *cleanup_job = NULL;
 
 		wait_event_interruptible(sched->wake_up_worker,
-					 (drm_sched_cleanup_jobs(sched),
+					 (cleanup_job = drm_sched_get_cleanup_job(sched)) ||
 					 (!drm_sched_blocked(sched) &&
 					  (entity = drm_sched_select_entity(sched))) ||
-					 kthread_should_stop()));
+					 kthread_should_stop());
+
+		while (cleanup_job) {
+			sched->ops->free_job(cleanup_job);
+			cleanup_job = drm_sched_get_cleanup_job(sched);
+		}
 
 		if (!entity)
 			continue;
-- 
2.20.1

Re: [PATCH v2] drm: Don't free jobs in wait_event_interruptible()

[Steven Price]

On 26/09/2019 10:54, Steven Price wrote:
> drm_sched_cleanup_jobs() attempts to free finished jobs, however because
> it is called as the condition of wait_event_interruptible() it must not
> sleep. Unfortuantly some free callbacks (notibly for Panfrost) do sleep.
> 
> Instead let's rename drm_sched_cleanup_jobs() to
> drm_sched_get_cleanup_job() and simply return a job for processing if
> there is one. The caller can then call the free_job() callback outside
> the wait_event_interruptible() where sleeping is possible before
> re-checking and returning to sleep if necessary.
> 
> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
> 
> Changes from v1:
>  * Move list_first_entry_or_null() within the lock

Or rather that was my intention - but apparently I fat fingered and
didn't actually include this change. Sorry - v3 on it's way!

Steve

> 
>  drivers/gpu/drm/scheduler/sched_main.c | 44 ++++++++++++++------------
>  1 file changed, 24 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index 9a0ee74d82dc..0ed4aaa4e6d1 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -622,43 +622,41 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
>  }
>  
>  /**
> - * drm_sched_cleanup_jobs - destroy finished jobs
> + * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed
>   *
>   * @sched: scheduler instance
>   *
> - * Remove all finished jobs from the mirror list and destroy them.
> + * Returns the next finished job from the mirror list (if there is one)
> + * ready for it to be destroyed.
>   */
> -static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
> +static struct drm_sched_job *
> +drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
>  {
> +	struct drm_sched_job *job = NULL;
>  	unsigned long flags;
>  
>  	/* Don't destroy jobs while the timeout worker is running */
>  	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
>  	    !cancel_delayed_work(&sched->work_tdr))
> -		return;
> -
> -
> -	while (!list_empty(&sched->ring_mirror_list)) {
> -		struct drm_sched_job *job;
> +		return NULL;
>  
> -		job = list_first_entry(&sched->ring_mirror_list,
> +	job = list_first_entry_or_null(&sched->ring_mirror_list,
>  				       struct drm_sched_job, node);
> -		if (!dma_fence_is_signaled(&job->s_fence->finished))
> -			break;
>  
> -		spin_lock_irqsave(&sched->job_list_lock, flags);
> +	spin_lock_irqsave(&sched->job_list_lock, flags);
> +
> +	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
>  		/* remove job from ring_mirror_list */
>  		list_del_init(&job->node);
> -		spin_unlock_irqrestore(&sched->job_list_lock, flags);
> -
> -		sched->ops->free_job(job);
> +	} else {
> +		job = NULL;
> +		/* queue timeout for next job */
> +		drm_sched_start_timeout(sched);
>  	}
>  
> -	/* queue timeout for next job */
> -	spin_lock_irqsave(&sched->job_list_lock, flags);
> -	drm_sched_start_timeout(sched);
>  	spin_unlock_irqrestore(&sched->job_list_lock, flags);
>  
> +	return job;
>  }
>  
>  /**
> @@ -698,12 +696,18 @@ static int drm_sched_main(void *param)
>  		struct drm_sched_fence *s_fence;
>  		struct drm_sched_job *sched_job;
>  		struct dma_fence *fence;
> +		struct drm_sched_job *cleanup_job = NULL;
>  
>  		wait_event_interruptible(sched->wake_up_worker,
> -					 (drm_sched_cleanup_jobs(sched),
> +					 (cleanup_job = drm_sched_get_cleanup_job(sched)) ||
>  					 (!drm_sched_blocked(sched) &&
>  					  (entity = drm_sched_select_entity(sched))) ||
> -					 kthread_should_stop()));
> +					 kthread_should_stop());
> +
> +		while (cleanup_job) {
> +			sched->ops->free_job(cleanup_job);
> +			cleanup_job = drm_sched_get_cleanup_job(sched);
> +		}
>  
>  		if (!entity)
>  			continue;
>