drm/i915: Always propagate the invocation to i915_schedule

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).

References: https://gitlab.freedesktop.org/drm/intel/issues/1318
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/20200306071614.2846708-2-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index be770f2419b1394d345894f86889dbf0d2ac98c2..52f71e83e088f74774fe545315ce41260edc84a5 100644 (file)
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -227,10 +227,10 @@ unlock:
 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;