drm/i915/selftest: Fix hangcheck self test for GuC submission

When GuC submission is enabled, the GuC controls engine resets. Rather
than explicitly triggering a reset, the driver must submit a hanging
context to GuC and wait for the reset to occur.

Conversely, one of the tests specifically sends hanging batches to the
engines but wants them to sit around until a manual reset of the full
GT (including GuC itself). That means disabling GuC based engine
resets to prevent those from killing the hanging batch too soon. So,
add support to the scheduling policy helper for disabling resets as
well as making them quicker!

In GuC submission mode, the 'is engine idle' test basically turns into
'is engine PM wakelock held'. Independently, there is a heartbeat
disable helper function that the tests use. For unexplained reasons,
this acquires the engine wakelock before disabling the heartbeat and
only releases it when re-enabling the heartbeat. As one of the tests
tries to do a wait for idle in the middle of a heartbeat disabled
section, it is therefore guaranteed to always fail. Added a 'no_pm'
variant of the heartbeat helper that allows the engine to be asleep
while also having heartbeats disabled.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-31-matthew.brost@intel.com

2 files changed, 33 insertions, 14 deletions

diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
index 5cdee1378e98..dac275e835c4 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c
@@ -15,7 +15,8 @@
 #define WAIT_FOR_RESET_TIME	1000
 
 int intel_selftest_modify_policy(struct intel_engine_cs *engine,
-				 struct intel_selftest_saved_policy *saved)
+				 struct intel_selftest_saved_policy *saved,
+				 u32 modify_type)
 
 {
 	int err;
@@ -25,18 +26,30 @@ int intel_selftest_modify_policy(struct intel_engine_cs *engine,
 	saved->timeslice = engine->props.timeslice_duration_ms;
 	saved->preempt_timeout = engine->props.preempt_timeout_ms;
 
-	/*
-	 * Enable force pre-emption on time slice expiration
-	 * together with engine reset on pre-emption timeout.
-	 * This is required to make the GuC notice and reset
-	 * the single hanging context.
-	 * Also, reduce the preemption timeout to something
-	 * small to speed the test up.
-	 */
-	engine->i915->params.reset = 2;
-	engine->flags |= I915_ENGINE_WANT_FORCED_PREEMPTION;
-	engine->props.timeslice_duration_ms = REDUCED_TIMESLICE;
-	engine->props.preempt_timeout_ms = REDUCED_PREEMPT;
+	switch (modify_type) {
+	case SELFTEST_SCHEDULER_MODIFY_FAST_RESET:
+		/*
+		 * Enable force pre-emption on time slice expiration
+		 * together with engine reset on pre-emption timeout.
+		 * This is required to make the GuC notice and reset
+		 * the single hanging context.
+		 * Also, reduce the preemption timeout to something
+		 * small to speed the test up.
+		 */
+		engine->i915->params.reset = 2;
+		engine->flags |= I915_ENGINE_WANT_FORCED_PREEMPTION;
+		engine->props.timeslice_duration_ms = REDUCED_TIMESLICE;
+		engine->props.preempt_timeout_ms = REDUCED_PREEMPT;
+		break;
+
+	case SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK:
+		engine->props.preempt_timeout_ms = 0;
+		break;
+
+	default:
+		pr_err("Invalid scheduler policy modification type: %d!\n", modify_type);
+		return -EINVAL;
+	}
 
 	if (!intel_engine_uses_guc(engine))
 		return 0;
diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
index 79605b14bc33..35c098601ac0 100644
--- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
+++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.h
@@ -18,8 +18,14 @@ struct intel_selftest_saved_policy {
 	u64 preempt_timeout;
 };
 
+enum selftest_scheduler_modify {
+	SELFTEST_SCHEDULER_MODIFY_NO_HANGCHECK = 0,
+	SELFTEST_SCHEDULER_MODIFY_FAST_RESET,
+};
+
 int intel_selftest_modify_policy(struct intel_engine_cs *engine,
-				 struct intel_selftest_saved_policy *saved);
+				 struct intel_selftest_saved_policy *saved,
+				 enum selftest_scheduler_modify modify_type);
 int intel_selftest_restore_policy(struct intel_engine_cs *engine,
 				  struct intel_selftest_saved_policy *saved);
 int intel_selftest_wait_for_rq(struct i915_request *rq);