3 files changed, 151 insertions, 54 deletions

diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
index f999c8859cf7..65acffc3fea8 100644
--- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
+++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
@@ -63,8 +63,8 @@ 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);
-	dma_fence_signal(&job->hw_fence);
+	list_del(&job->link);
+	dma_fence_signal_locked(&job->hw_fence);
 	complete(&job->done);
 }
 
@@ -117,13 +117,13 @@ drm_mock_sched_job_new(struct kunit *test,
 	ret = drm_sched_job_init(&job->base,
 				 &entity->base,
 				 1,
-				 NULL);
+				 NULL,
+				 1);
 	KUNIT_ASSERT_EQ(test, ret, 0);
 
 	job->test = test;
 
 	init_completion(&job->done);
-	spin_lock_init(&job->lock);
 	INIT_LIST_HEAD(&job->link);
 	hrtimer_setup(&job->timer, drm_mock_sched_job_signal_timer,
 		      CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
@@ -169,7 +169,7 @@ static struct dma_fence *mock_sched_run_job(struct drm_sched_job *sched_job)
 
 	dma_fence_init(&job->hw_fence,
 		       &drm_mock_sched_hw_fence_ops,
-		       &job->lock,
+		       &sched->lock,
 		       sched->hw_timeline.context,
 		       atomic_inc_return(&sched->hw_timeline.next_seqno));
 
@@ -200,38 +200,82 @@ static struct dma_fence *mock_sched_run_job(struct drm_sched_job *sched_job)
 	return &job->hw_fence;
 }
 
+/*
+ * Normally, drivers would take appropriate measures in this callback, such as
+ * killing the entity the faulty job is associated with, resetting the hardware
+ * and / or resubmitting non-faulty jobs.
+ *
+ * For the mock scheduler, there are no hardware rings to be resetted nor jobs
+ * to be resubmitted. Thus, this function merely ensures that
+ *   a) timedout fences get signaled properly and removed from the pending list
+ *   b) the mock scheduler framework gets informed about the timeout via a flag
+ *   c) The drm_sched_job, not longer needed, gets freed
+ */
 static enum drm_gpu_sched_stat
 mock_sched_timedout_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;
+
+	if (job->flags & DRM_MOCK_SCHED_JOB_DONT_RESET) {
+		job->flags &= ~DRM_MOCK_SCHED_JOB_DONT_RESET;
+		return DRM_GPU_SCHED_STAT_NO_HANG;
+	}
 
-	job->flags |= DRM_MOCK_SCHED_JOB_TIMEDOUT;
+	spin_lock_irqsave(&sched->lock, flags);
+	if (!dma_fence_is_signaled_locked(&job->hw_fence)) {
+		list_del(&job->link);
+		job->flags |= DRM_MOCK_SCHED_JOB_TIMEDOUT;
+		dma_fence_set_error(&job->hw_fence, -ETIMEDOUT);
+		dma_fence_signal_locked(&job->hw_fence);
+	}
+	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. */
 
-	return DRM_GPU_SCHED_STAT_NOMINAL;
+	return DRM_GPU_SCHED_STAT_RESET;
 }
 
 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,
 };
 
 /**
@@ -265,7 +309,6 @@ 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;
@@ -280,38 +323,6 @@ 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 27caf8285fb7..63d4f2ac7074 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;
@@ -98,6 +97,7 @@ struct drm_mock_sched_job {
 
 #define DRM_MOCK_SCHED_JOB_DONE		0x1
 #define DRM_MOCK_SCHED_JOB_TIMEDOUT	0x2
+#define DRM_MOCK_SCHED_JOB_DONT_RESET	0x4
 	unsigned long		flags;
 
 	struct list_head	link;
@@ -106,7 +106,6 @@ struct drm_mock_sched_job {
 	unsigned int		duration_us;
 	ktime_t			finish_at;
 
-	spinlock_t		lock;
 	struct dma_fence	hw_fence;
 
 	struct kunit		*test;
diff --git a/drivers/gpu/drm/scheduler/tests/tests_basic.c b/drivers/gpu/drm/scheduler/tests/tests_basic.c
index 7230057e0594..55eb142bd7c5 100644
--- a/drivers/gpu/drm/scheduler/tests/tests_basic.c
+++ b/drivers/gpu/drm/scheduler/tests/tests_basic.c
@@ -5,6 +5,8 @@
 
 #include "sched_tests.h"
 
+#define MOCK_TIMEOUT (HZ / 5)
+
 /*
  * DRM scheduler basic tests should check the basic functional correctness of
  * the scheduler, including some very light smoke testing. More targeted tests,
@@ -28,7 +30,7 @@ static void drm_sched_basic_exit(struct kunit *test)
 
 static int drm_sched_timeout_init(struct kunit *test)
 {
-	test->priv = drm_mock_sched_new(test, HZ);
+	test->priv = drm_mock_sched_new(test, MOCK_TIMEOUT);
 
 	return 0;
 }
@@ -204,6 +206,47 @@ static struct kunit_suite drm_sched_basic = {
 	.test_cases = drm_sched_basic_tests,
 };
 
+static void drm_sched_basic_cancel(struct kunit *test)
+{
+	struct drm_mock_sched_entity *entity;
+	struct drm_mock_scheduler *sched;
+	struct drm_mock_sched_job *job;
+	bool done;
+
+	/*
+	 * Check that drm_sched_fini() uses the cancel_job() callback to cancel
+	 * jobs that are still pending.
+	 */
+
+	sched = drm_mock_sched_new(test, MAX_SCHEDULE_TIMEOUT);
+	entity = drm_mock_sched_entity_new(test, DRM_SCHED_PRIORITY_NORMAL,
+					   sched);
+
+	job = drm_mock_sched_job_new(test, entity);
+
+	drm_mock_sched_job_submit(job);
+
+	done = drm_mock_sched_job_wait_scheduled(job, HZ);
+	KUNIT_ASSERT_TRUE(test, done);
+
+	drm_mock_sched_entity_free(entity);
+	drm_mock_sched_fini(sched);
+
+	KUNIT_ASSERT_EQ(test, job->hw_fence.error, -ECANCELED);
+}
+
+static struct kunit_case drm_sched_cancel_tests[] = {
+	KUNIT_CASE(drm_sched_basic_cancel),
+	{}
+};
+
+static struct kunit_suite drm_sched_cancel = {
+	.name = "drm_sched_basic_cancel_tests",
+	.init = drm_sched_basic_init,
+	.exit = drm_sched_basic_exit,
+	.test_cases = drm_sched_cancel_tests,
+};
+
 static void drm_sched_basic_timeout(struct kunit *test)
 {
 	struct drm_mock_scheduler *sched = test->priv;
@@ -227,14 +270,14 @@ static void drm_sched_basic_timeout(struct kunit *test)
 	done = drm_mock_sched_job_wait_scheduled(job, HZ);
 	KUNIT_ASSERT_TRUE(test, done);
 
-	done = drm_mock_sched_job_wait_finished(job, HZ / 2);
+	done = drm_mock_sched_job_wait_finished(job, MOCK_TIMEOUT / 2);
 	KUNIT_ASSERT_FALSE(test, done);
 
 	KUNIT_ASSERT_EQ(test,
 			job->flags & DRM_MOCK_SCHED_JOB_TIMEDOUT,
 			0);
 
-	done = drm_mock_sched_job_wait_finished(job, HZ);
+	done = drm_mock_sched_job_wait_finished(job, MOCK_TIMEOUT);
 	KUNIT_ASSERT_FALSE(test, done);
 
 	KUNIT_ASSERT_EQ(test,
@@ -244,8 +287,51 @@ static void drm_sched_basic_timeout(struct kunit *test)
 	drm_mock_sched_entity_free(entity);
 }
 
+static void drm_sched_skip_reset(struct kunit *test)
+{
+	struct drm_mock_scheduler *sched = test->priv;
+	struct drm_mock_sched_entity *entity;
+	struct drm_mock_sched_job *job;
+	unsigned int i;
+	bool done;
+
+	/*
+	 * Submit a single job against a scheduler with the timeout configured
+	 * and verify that if the job is still running, the timeout handler
+	 * will skip the reset and allow the job to complete.
+	 */
+
+	entity = drm_mock_sched_entity_new(test,
+					   DRM_SCHED_PRIORITY_NORMAL,
+					   sched);
+	job = drm_mock_sched_job_new(test, entity);
+
+	job->flags = DRM_MOCK_SCHED_JOB_DONT_RESET;
+
+	drm_mock_sched_job_submit(job);
+
+	done = drm_mock_sched_job_wait_scheduled(job, HZ);
+	KUNIT_ASSERT_TRUE(test, done);
+
+	done = drm_mock_sched_job_wait_finished(job, 2 * MOCK_TIMEOUT);
+	KUNIT_ASSERT_FALSE(test, done);
+
+	KUNIT_ASSERT_EQ(test,
+			job->flags & DRM_MOCK_SCHED_JOB_DONT_RESET,
+			0);
+
+	i = drm_mock_sched_advance(sched, 1);
+	KUNIT_ASSERT_EQ(test, i, 1);
+
+	done = drm_mock_sched_job_wait_finished(job, HZ);
+	KUNIT_ASSERT_TRUE(test, done);
+
+	drm_mock_sched_entity_free(entity);
+}
+
 static struct kunit_case drm_sched_timeout_tests[] = {
 	KUNIT_CASE(drm_sched_basic_timeout),
+	KUNIT_CASE(drm_sched_skip_reset),
 	{}
 };
 
@@ -471,6 +557,7 @@ static struct kunit_suite drm_sched_credits = {
 
 kunit_test_suites(&drm_sched_basic,
 		  &drm_sched_timeout,
+		  &drm_sched_cancel,
 		  &drm_sched_priority,
 		  &drm_sched_modify_sched,
 		  &drm_sched_credits);