drm/sched: Add new test for DRM_GPU_SCHED_STAT_NO_HANG

Add a test to 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.

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250714-sched-skip-reset-v6-4-5c5ba4f55039@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>

3 files changed, 49 insertions, 0 deletions

diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
index ad96e8db13c4..65acffc3fea8 100644
--- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
+++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
@@ -218,6 +218,11 @@ mock_sched_timedout_job(struct drm_sched_job *sched_job)
 	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;
+	}
+
 	spin_lock_irqsave(&sched->lock, flags);
 	if (!dma_fence_is_signaled_locked(&job->hw_fence)) {
 		list_del(&job->link);
diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h b/drivers/gpu/drm/scheduler/tests/sched_tests.h
index 0eddfb8d89e6..63d4f2ac7074 100644
--- a/drivers/gpu/drm/scheduler/tests/sched_tests.h
+++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h
@@ -97,6 +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;
diff --git a/drivers/gpu/drm/scheduler/tests/tests_basic.c b/drivers/gpu/drm/scheduler/tests/tests_basic.c
index 8153c2e7af77..55eb142bd7c5 100644
--- a/drivers/gpu/drm/scheduler/tests/tests_basic.c
+++ b/drivers/gpu/drm/scheduler/tests/tests_basic.c
@@ -287,8 +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),
 	{}
 };