drm/i915: Don't set queue-priority hint when supressing the reschedule (0fad590f) · Commits · 戴 / test

We recorded the execlists->queue_priority_hint update for the inflight request without kicking the tasklet. The next submitted request then failed to be scheduled as it had a lower priority than the hint, leaving the HW running with only the inflight request. Fixes: ("drm/i915: Tweak scheduler's kick_submission()") 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/20200519063123.20673-1-chris@chris-wilson.co.uk (cherry picked from commit ) Signed-off-by:

Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

drivers/gpu/drm/i915/i915_scheduler.c

+8 −8

Original line number	Diff line number	Diff line
		@@ -209,14 +209,6 @@ static void kick_submission(struct intel_engine_cs *engine,
		if (!inflight)
		goto unlock;

		ENGINE_TRACE(engine,
		"bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
		prio,
		rq->fence.context, rq->fence.seqno,
		inflight->fence.context, inflight->fence.seqno,
		inflight->sched.attr.priority);
		engine->execlists.queue_priority_hint = prio;

		/*
		* If we are already the currently executing context, don't
		* bother evaluating if we should preempt ourselves.
		@@ -224,6 +216,14 @@ static void kick_submission(struct intel_engine_cs *engine,
		if (inflight->context == rq->context)
		goto unlock;

		ENGINE_TRACE(engine,
		"bumping queue-priority-hint:%d for rq:%llx:%lld, inflight:%llx:%lld prio %d\n",
		prio,
		rq->fence.context, rq->fence.seqno,
		inflight->fence.context, inflight->fence.seqno,
		inflight->sched.attr.priority);

		engine->execlists.queue_priority_hint = prio;
		if (need_preempt(prio, rq_prio(inflight)))
		tasklet_hi_schedule(&engine->execlists.tasklet);

Admin message