[PATCH v2 3/5] drm/scheduler: Add a simple timeout test

[Philipp Stanner]

On Fri, 2025-02-21 at 12:09 +0000, Tvrtko Ursulin wrote:
> Add a very simple timeout test which submits a single job and
> verifies
> that the timeout handling will run if the backend failed to complete
> the
> job in time.
> 
> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at igalia.com>
> Cc: Christian König <christian.koenig at amd.com>
> Cc: Danilo Krummrich <dakr at kernel.org>
> Cc: Matthew Brost <matthew.brost at intel.com>
> Cc: Philipp Stanner <phasta at kernel.org>
> ---
>  .../gpu/drm/scheduler/tests/mock_scheduler.c  | 13 +++-
>  drivers/gpu/drm/scheduler/tests/sched_tests.h |  6 +-
>  drivers/gpu/drm/scheduler/tests/tests_basic.c | 64
> ++++++++++++++++++-
>  3 files changed, 77 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> index d73a9f0337da..427ce29354d0 100644
> --- a/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> +++ b/drivers/gpu/drm/scheduler/tests/mock_scheduler.c
> @@ -193,7 +193,11 @@ static struct dma_fence
> *mock_sched_run_job(struct drm_sched_job *sched_job)
>  static enum drm_gpu_sched_stat
>  mock_sched_timedout_job(struct drm_sched_job *sched_job)
>  {
> -	return DRM_GPU_SCHED_STAT_ENODEV;
> +	struct drm_mock_sched_job *job =
> drm_sched_job_to_mock_job(sched_job);
> +
> +	job->flags |= DRM_MOCK_SCHED_JOB_TIMEDOUT;
> +
> +	return DRM_GPU_SCHED_STAT_NOMINAL;
>  }
>  
>  static void mock_sched_free_job(struct drm_sched_job *sched_job)
> @@ -211,17 +215,20 @@ static const struct drm_sched_backend_ops
> drm_mock_scheduler_ops = {
>   * drm_mock_new_scheduler - Create a new mock scheduler
>   *
>   * @test: KUnit test owning the job
> + * @timeout: Job timeout to set
>   *
>   * Returns: New mock scheduler with allocation managed by the test
>   */
> -struct drm_mock_scheduler *drm_mock_new_scheduler(struct kunit

-> …_scheduler_new()

As said in the previous thread, I think that if you want to introduce
the new prefix drm_mock_, then it should always be followed by the DRM
subcomponent, so that it can be congruent across DRM.


> *test)
> +struct drm_mock_scheduler *
> +drm_mock_new_scheduler(struct kunit *test,
> +		       long timeout)

fits on one line

>  {
>  	struct drm_sched_init_args args = {
>  		.ops		= &drm_mock_scheduler_ops,
>  		.num_rqs	= DRM_SCHED_PRIORITY_COUNT,
>  		.credit_limit	= U32_MAX,
>  		.hang_limit	= UINT_MAX,
> -		.timeout	= MAX_SCHEDULE_TIMEOUT,
> +		.timeout	= timeout,
>  		.name		= "drm-mock-scheduler",
>  	};
>  	struct drm_mock_scheduler *sched;
> diff --git a/drivers/gpu/drm/scheduler/tests/sched_tests.h
> b/drivers/gpu/drm/scheduler/tests/sched_tests.h
> index 0614bc901dd1..258fec748ca7 100644
> --- a/drivers/gpu/drm/scheduler/tests/sched_tests.h
> +++ b/drivers/gpu/drm/scheduler/tests/sched_tests.h
> @@ -88,6 +88,9 @@ struct drm_mock_sched_entity {
>  struct drm_mock_sched_job {
>  	struct drm_sched_job	base;
>  
> +#define DRM_MOCK_SCHED_JOB_TIMEDOUT 0x1

Why's that defined here within the struct's body? Better move it above


P.


> +	unsigned long		flags;
> +
>  	struct list_head	link;
>  	struct hrtimer		timer;
>  
> @@ -118,7 +121,8 @@ drm_sched_job_to_mock_job(struct drm_sched_job
> *sched_job)
>  	return container_of(sched_job, struct drm_mock_sched_job,
> base);
>  };
>  
> -struct drm_mock_scheduler *drm_mock_new_scheduler(struct kunit
> *test);
> +struct drm_mock_scheduler *drm_mock_new_scheduler(struct kunit
> *test,
> +						  long timeout);
>  void drm_mock_scheduler_fini(struct drm_mock_scheduler *sched);
>  unsigned int drm_mock_sched_advance(struct drm_mock_scheduler
> *sched,
>  				    unsigned int num);
> diff --git a/drivers/gpu/drm/scheduler/tests/tests_basic.c
> b/drivers/gpu/drm/scheduler/tests/tests_basic.c
> index c12368a22a39..023143b80d78 100644
> --- a/drivers/gpu/drm/scheduler/tests/tests_basic.c
> +++ b/drivers/gpu/drm/scheduler/tests/tests_basic.c
> @@ -11,7 +11,7 @@
>  
>  static int drm_sched_basic_init(struct kunit *test)
>  {
> -	test->priv = drm_mock_new_scheduler(test);
> +	test->priv = drm_mock_new_scheduler(test,
> MAX_SCHEDULE_TIMEOUT);
>  
>  	return 0;
>  }
> @@ -23,6 +23,13 @@ static void drm_sched_basic_exit(struct kunit
> *test)
>  	drm_mock_scheduler_fini(sched);
>  }
>  
> +static int drm_sched_timeout_init(struct kunit *test)
> +{
> +	test->priv = drm_mock_new_scheduler(test, HZ);
> +
> +	return 0;
> +}
> +
>  static void drm_sched_basic_submit(struct kunit *test)
>  {
>  	struct drm_mock_scheduler *sched = test->priv;
> @@ -194,4 +201,57 @@ static struct kunit_suite drm_sched_basic = {
>  	.test_cases = drm_sched_basic_tests,
>  };
>  
> -kunit_test_suite(drm_sched_basic);
> +static void drm_sched_basic_timeout(struct kunit *test)
> +{
> +	struct drm_mock_scheduler *sched = test->priv;
> +	struct drm_mock_sched_entity *entity;
> +	struct drm_mock_sched_job *job;
> +	bool done;
> +
> +	/*
> +	 * Submit a single job against a scheduler with the timeout
> configured
> +	 * and verify that the timeout handling will run if the
> backend fails
> +	 * to complete it in time.
> +	 */
> +
> +	entity = drm_mock_new_sched_entity(test,
> +					  
> DRM_SCHED_PRIORITY_NORMAL,
> +					   sched);
> +	job = drm_mock_new_sched_job(test, entity);
> +
> +	drm_mock_sched_job_submit(job);
> +
> +	done = drm_mock_sched_job_wait_scheduled(job, HZ);
> +	KUNIT_ASSERT_EQ(test, done, true);
> +
> +	done = drm_mock_sched_job_wait_finished(job, HZ / 2);
> +	KUNIT_ASSERT_EQ(test, done, false);
> +
> +	KUNIT_ASSERT_EQ(test,
> +			job->flags & DRM_MOCK_SCHED_JOB_TIMEDOUT,
> +			0);
> +
> +	done = drm_mock_sched_job_wait_finished(job, HZ);
> +	KUNIT_ASSERT_EQ(test, done, false);
> +
> +	KUNIT_ASSERT_EQ(test,
> +			job->flags & DRM_MOCK_SCHED_JOB_TIMEDOUT,
> +			DRM_MOCK_SCHED_JOB_TIMEDOUT);
> +
> +	drm_mock_sched_entity_free(entity);
> +}
> +
> +static struct kunit_case drm_sched_timeout_tests[] = {
> +	KUNIT_CASE(drm_sched_basic_timeout),
> +	{}
> +};
> +
> +static struct kunit_suite drm_sched_timeout = {
> +	.name = "drm_sched_basic_timeout_tests",
> +	.init = drm_sched_timeout_init,
> +	.exit = drm_sched_basic_exit,
> +	.test_cases = drm_sched_timeout_tests,
> +};
> +
> +kunit_test_suites(&drm_sched_basic,
> +		  &drm_sched_timeout);