drm/i915/gt: Another tweak for flushing the tasklets

tasklet_kill() ensures that we _yield_ the processor until a remote
tasklet is completed. However, this leads to a starvation condition as
being at the bottom of the scheduler's runqueue means that anything else
is able to run, including all hogs keeping the tasklet occupied.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201220134858.10510-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -232,7 +232,12 @@ static inline void __intel_engine_reset(struct intel_engine_cs *engine,
 
 bool intel_engines_are_idle(struct intel_gt *gt);
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
-void intel_engine_flush_submission(struct intel_engine_cs *engine);
+
+void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync);
+static inline void intel_engine_flush_submission(struct intel_engine_cs *engine)
+{
+	__intel_engine_flush_submission(engine, true);
+}
 
 void intel_engines_reset_default_submission(struct intel_gt *gt);
 

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -1190,17 +1190,13 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	return idle;
 }
 
-void intel_engine_flush_submission(struct intel_engine_cs *engine)
+void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync)
 {
 	struct tasklet_struct *t = &engine->execlists.tasklet;
 
 	if (!t->func)
 		return;
 
-	/* Synchronise and wait for the tasklet on another CPU */
-	tasklet_kill(t);
-
-	/* Having cancelled the tasklet, ensure that is run */
 	local_bh_disable();
 	if (tasklet_trylock(t)) {
 		/* Must wait for any GPU reset in progress. */
@@ -1209,6 +1205,10 @@ void intel_engine_flush_submission(struct intel_engine_cs *engine)
 		tasklet_unlock(t);
 	}
 	local_bh_enable();
+
+	/* Synchronise and wait for the tasklet on another CPU */
+	if (sync)
+		tasklet_unlock_wait(t);
 }
 
 /**

drivers/gpu/drm/i915/i915_request.c

@@ -1825,7 +1825,7 @@ long i915_request_wait(struct i915_request *rq,
 	 * for unhappy HW.
 	 */
 	if (i915_request_is_ready(rq))
-		intel_engine_flush_submission(rq->engine);
+		__intel_engine_flush_submission(rq->engine, false);
 
 	for (;;) {
 		set_current_state(state);