[PATCH 2/4] drm/i915: Always propagate the invocation to i915_schedule

[Chris Wilson]

We only call i915_schedule() when we know we have changed the priority
on a request and so require to propagate any change in priority to its
signalers (for PI). By unconditionally checking all of our signalers, we
avoid skipping changes made prior to construction of the request (as the
request may be waited upon before submission when used in parallel).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_scheduler.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index be770f2419b1..52f71e83e088 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -227,10 +227,10 @@ static void kick_submission(struct intel_engine_cs *engine,
 static void __i915_schedule(struct i915_sched_node *node,
 			    const struct i915_sched_attr *attr)
 {
+	const int prio = max(attr->priority, node->attr.priority);
 	struct intel_engine_cs *engine;
 	struct i915_dependency *dep, *p;
 	struct i915_dependency stack;
-	const int prio = attr->priority;
 	struct sched_cache cache;
 	LIST_HEAD(dfs);
 
@@ -238,9 +238,6 @@ static void __i915_schedule(struct i915_sched_node *node,
 	lockdep_assert_held(&schedule_lock);
 	GEM_BUG_ON(prio == I915_PRIORITY_INVALID);
 
-	if (prio <= READ_ONCE(node->attr.priority))
-		return;
-
 	if (node_signaled(node))
 		return;
 
-- 
2.25.1