The GPU Scheduler now supports a new callback, cancel_job(), which lets
the scheduler cancel all jobs which might not yet be freed when
drm_sched_fini() runs. Using this callback allows for significantly
simplifying the mock scheduler teardown code.

Implement the cancel_job() callback and adjust the code where necessary.

Signed-off-by: Philipp Stanner <phasta@kernel.org>
---
 .../gpu/drm/scheduler/tests/mock_scheduler.c  | 68 +++++++------------
 drivers/gpu/drm/scheduler/tests/sched_tests.h |  1 -
 2 files changed, 25 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
index 49d067fecd67..0d1d57213e05 100644
--- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
+++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
@@ -63,7 +63,7 @@ static void drm_mock_sched_job_complete(struct drm_mock_sched_job *job)
 	lockdep_assert_held(&sched->lock);
 
 	job->flags |= DRM_MOCK_SCHED_JOB_DONE;
-	list_move_tail(&job->link, &sched->done_list);
+	list_del(&job->link);
 	dma_fence_signal_locked(&job->hw_fence);
 	complete(&job->done);
 }
@@ -236,26 +236,41 @@ mock_sched_timedout_job(struct drm_sched_job *sched_job)
 
 static void mock_sched_free_job(struct drm_sched_job *sched_job)
 {
-	struct drm_mock_scheduler *sched =
-			drm_sched_to_mock_sched(sched_job->sched);
 	struct drm_mock_sched_job *job = drm_sched_job_to_mock_job(sched_job);
-	unsigned long flags;
 
-	/* Remove from the scheduler done list. */
-	spin_lock_irqsave(&sched->lock, flags);
-	list_del(&job->link);
-	spin_unlock_irqrestore(&sched->lock, flags);
 	dma_fence_put(&job->hw_fence);
-
 	drm_sched_job_cleanup(sched_job);
 
 	/* Mock job itself is freed by the kunit framework. */
 }
 
+static void mock_sched_cancel_job(struct drm_sched_job *sched_job)
+{
+	struct drm_mock_scheduler *sched = drm_sched_to_mock_sched(sched_job->sched);
+	struct drm_mock_sched_job *job = drm_sched_job_to_mock_job(sched_job);
+	unsigned long flags;
+
+	hrtimer_cancel(&job->timer);
+
+	spin_lock_irqsave(&sched->lock, flags);
+	if (!dma_fence_is_signaled_locked(&job->hw_fence)) {
+		list_del(&job->link);
+		dma_fence_set_error(&job->hw_fence, -ECANCELED);
+		dma_fence_signal_locked(&job->hw_fence);
+	}
+	spin_unlock_irqrestore(&sched->lock, flags);
+
+	/*
+	 * The GPU Scheduler will call drm_sched_backend_ops.free_job(), still.
+	 * Mock job itself is freed by the kunit framework.
+	 */
+}
+
 static const struct drm_sched_backend_ops drm_mock_scheduler_ops = {
 	.run_job = mock_sched_run_job,
 	.timedout_job = mock_sched_timedout_job,
-	.free_job = mock_sched_free_job
+	.free_job = mock_sched_free_job,
+	.cancel_job = mock_sched_cancel_job,
 };
 
 /**
@@ -289,7 +304,6 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout)
 	sched->hw_timeline.context = dma_fence_context_alloc(1);
 	atomic_set(&sched->hw_timeline.next_seqno, 0);
 	INIT_LIST_HEAD(&sched->job_list);
-	INIT_LIST_HEAD(&sched->done_list);
 	spin_lock_init(&sched->lock);
 
 	return sched;
@@ -304,38 +318,6 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout)
  */
 void drm_mock_sched_fini(struct drm_mock_scheduler *sched)
 {
-	struct drm_mock_sched_job *job, *next;
-	unsigned long flags;
-	LIST_HEAD(list);
-
-	drm_sched_wqueue_stop(&sched->base);
-
-	/* Force complete all unfinished jobs. */
-	spin_lock_irqsave(&sched->lock, flags);
-	list_for_each_entry_safe(job, next, &sched->job_list, link)
-		list_move_tail(&job->link, &list);
-	spin_unlock_irqrestore(&sched->lock, flags);
-
-	list_for_each_entry(job, &list, link)
-		hrtimer_cancel(&job->timer);
-
-	spin_lock_irqsave(&sched->lock, flags);
-	list_for_each_entry_safe(job, next, &list, link)
-		drm_mock_sched_job_complete(job);
-	spin_unlock_irqrestore(&sched->lock, flags);
-
-	/*
-	 * Free completed jobs and jobs not yet processed by the DRM scheduler
-	 * free worker.
-	 */
-	spin_lock_irqsave(&sched->lock, flags);
-	list_for_each_entry_safe(job, next, &sched->done_list, link)
-		list_move_tail(&job->link, &list);
-	spin_unlock_irqrestore(&sched->lock, flags);
-
-	list_for_each_entry_safe(job, next, &list, link)
-		mock_sched_free_job(&job->base);
-
 	drm_sched_fini(&sched->base);
 }
 
diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h b/drivers/gpu/drm/scheduler/tests/sched_tests.h
index fbba38137f0c..0eddfb8d89e6 100644
--- a/drivers/gpu/drm/scheduler/tests/sched_tests.h
+++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h
@@ -49,7 +49,6 @@ struct drm_mock_scheduler {
 
 	spinlock_t		lock;
 	struct list_head	job_list;
-	struct list_head	done_list;
 
 	struct {
 		u64		context;
-- 
2.49.0

On 09/07/2025 12:52, Philipp Stanner wrote:
> The GPU Scheduler now supports a new callback, cancel_job(), which lets
> the scheduler cancel all jobs which might not yet be freed when
> drm_sched_fini() runs. Using this callback allows for significantly
> simplifying the mock scheduler teardown code.
> 
> Implement the cancel_job() callback and adjust the code where necessary.
> 
> Signed-off-by: Philipp Stanner <phasta@kernel.org>
> ---
>   .../gpu/drm/scheduler/tests/mock_scheduler.c  | 68 +++++++------------
>   drivers/gpu/drm/scheduler/tests/sched_tests.h |  1 -
>   2 files changed, 25 insertions(+), 44 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> index 49d067fecd67..0d1d57213e05 100644
> --- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> +++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> @@ -63,7 +63,7 @@ static void drm_mock_sched_job_complete(struct drm_mock_sched_job *job)
>   	lockdep_assert_held(&sched->lock);
>   
>   	job->flags |= DRM_MOCK_SCHED_JOB_DONE;
> -	list_move_tail(&job->link, &sched->done_list);
> +	list_del(&job->link);
>   	dma_fence_signal_locked(&job->hw_fence);
>   	complete(&job->done);
>   }
> @@ -236,26 +236,41 @@ mock_sched_timedout_job(struct drm_sched_job *sched_job)
>   
>   static void mock_sched_free_job(struct drm_sched_job *sched_job)
>   {
> -	struct drm_mock_scheduler *sched =
> -			drm_sched_to_mock_sched(sched_job->sched);
>   	struct drm_mock_sched_job *job = drm_sched_job_to_mock_job(sched_job);
> -	unsigned long flags;
>   
> -	/* Remove from the scheduler done list. */
> -	spin_lock_irqsave(&sched->lock, flags);
> -	list_del(&job->link);
> -	spin_unlock_irqrestore(&sched->lock, flags);
>   	dma_fence_put(&job->hw_fence);
> -
>   	drm_sched_job_cleanup(sched_job);
>   
>   	/* Mock job itself is freed by the kunit framework. */
>   }
>   
> +static void mock_sched_cancel_job(struct drm_sched_job *sched_job)
> +{
> +	struct drm_mock_scheduler *sched = drm_sched_to_mock_sched(sched_job->sched);
> +	struct drm_mock_sched_job *job = drm_sched_job_to_mock_job(sched_job);
> +	unsigned long flags;
> +
> +	hrtimer_cancel(&job->timer);
> +
> +	spin_lock_irqsave(&sched->lock, flags);
> +	if (!dma_fence_is_signaled_locked(&job->hw_fence)) {
> +		list_del(&job->link);
> +		dma_fence_set_error(&job->hw_fence, -ECANCELED);
> +		dma_fence_signal_locked(&job->hw_fence);
> +	}
> +	spin_unlock_irqrestore(&sched->lock, flags);
> +
> +	/*
> +	 * The GPU Scheduler will call drm_sched_backend_ops.free_job(), still.
> +	 * Mock job itself is freed by the kunit framework.
> +	 */
> +}
> +
>   static const struct drm_sched_backend_ops drm_mock_scheduler_ops = {
>   	.run_job = mock_sched_run_job,
>   	.timedout_job = mock_sched_timedout_job,
> -	.free_job = mock_sched_free_job
> +	.free_job = mock_sched_free_job,
> +	.cancel_job = mock_sched_cancel_job,
>   };
>   
>   /**
> @@ -289,7 +304,6 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout)
>   	sched->hw_timeline.context = dma_fence_context_alloc(1);
>   	atomic_set(&sched->hw_timeline.next_seqno, 0);
>   	INIT_LIST_HEAD(&sched->job_list);
> -	INIT_LIST_HEAD(&sched->done_list);
>   	spin_lock_init(&sched->lock);
>   
>   	return sched;
> @@ -304,38 +318,6 @@ struct drm_mock_scheduler *drm_mock_sched_new(struct kunit *test, long timeout)
>    */
>   void drm_mock_sched_fini(struct drm_mock_scheduler *sched)
>   {
> -	struct drm_mock_sched_job *job, *next;
> -	unsigned long flags;
> -	LIST_HEAD(list);
> -
> -	drm_sched_wqueue_stop(&sched->base);
> -
> -	/* Force complete all unfinished jobs. */
> -	spin_lock_irqsave(&sched->lock, flags);
> -	list_for_each_entry_safe(job, next, &sched->job_list, link)
> -		list_move_tail(&job->link, &list);
> -	spin_unlock_irqrestore(&sched->lock, flags);
> -
> -	list_for_each_entry(job, &list, link)
> -		hrtimer_cancel(&job->timer);
> -
> -	spin_lock_irqsave(&sched->lock, flags);
> -	list_for_each_entry_safe(job, next, &list, link)
> -		drm_mock_sched_job_complete(job);
> -	spin_unlock_irqrestore(&sched->lock, flags);
> -
> -	/*
> -	 * Free completed jobs and jobs not yet processed by the DRM scheduler
> -	 * free worker.
> -	 */
> -	spin_lock_irqsave(&sched->lock, flags);
> -	list_for_each_entry_safe(job, next, &sched->done_list, link)
> -		list_move_tail(&job->link, &list);
> -	spin_unlock_irqrestore(&sched->lock, flags);
> -
> -	list_for_each_entry_safe(job, next, &list, link)
> -		mock_sched_free_job(&job->base);
> -
>   	drm_sched_fini(&sched->base);
>   }
>   
> diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h b/drivers/gpu/drm/scheduler/tests/sched_tests.h
> index fbba38137f0c..0eddfb8d89e6 100644
> --- a/drivers/gpu/drm/scheduler/tests/sched_tests.h
> +++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h
> @@ -49,7 +49,6 @@ struct drm_mock_scheduler {
>   
>   	spinlock_t		lock;
>   	struct list_head	job_list;
> -	struct list_head	done_list;
>   
>   	struct {
>   		u64		context;

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>

Regards,

Tvrtko