[Intel-gfx] [PATCH v2] drm/i915/execlists: Suppress redundant preemption

[Chris Wilson]

On unwinding the active request we give it a small (limited to internal
priority levels) boost to prevent it from being gazumped a second time.
However, this means that it can be promoted to above the request that
triggered the preemption request, causing a preempt-to-idle cycle for no
change. We can avoid this if we take the boost into account when
checking if the preemption request is valid.

v2: After preemption the active request will be after the preemptee if
they end up with equal priority.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_lrc.c | 39 ++++++++++++++++++++++++++++----
 1 file changed, 35 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d9d744f6ab2c..65997ed055b2 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -163,6 +163,8 @@
 #define WA_TAIL_DWORDS 2
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
+#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT)
+
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 					    struct intel_engine_cs *engine,
 					    struct intel_context *ce);
@@ -181,13 +183,41 @@ static inline int rq_prio(const struct i915_request *rq)
 	return rq->sched.attr.priority;
 }
 
+static inline int active_prio(const struct i915_request *rq)
+{
+	int prio = rq_prio(rq);
+
+	/*
+	 * On unwinding the active request, we give it a priority bump
+	 * equivalent to a freshly submitted request. This protects it from
+	 * being gazumped again, but it would be preferable if we didn't
+	 * let it be gazumped in the first place!
+	 *
+	 * See __unwind_incomplete_requests()
+	 */
+	if ((prio & ACTIVE_PRIORITY) != ACTIVE_PRIORITY &&
+	    i915_request_started(rq)) {
+		/*
+		 * After preemption, we insert the active request at the
+		 * end of the new priority level. This means that we will be
+		 * _lower_ priority than the preemptee all things equal (and
+		 * so the preemption is valid), so adjust our comparison
+		 * accordingly.
+		 */
+		prio |= ACTIVE_PRIORITY;
+		prio--;
+	}
+
+	return prio;
+}
+
 static inline bool need_preempt(const struct intel_engine_cs *engine,
 				const struct i915_request *rq,
 				int q_prio)
 {
 	const struct intel_context *ctx = rq->hw_context;
-	const int last_prio = rq_prio(rq);
 	struct rb_node *rb;
+	int last_prio;
 	int idx;
 
 	if (!intel_engine_has_preemption(engine))
@@ -196,6 +226,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	if (i915_request_completed(rq))
 		return false;
 
+	last_prio = active_prio(rq);
 	if (!__execlists_need_preempt(q_prio, last_prio))
 		return false;
 
@@ -320,7 +351,7 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq, *rn, *active = NULL;
 	struct list_head *uninitialized_var(pl);
-	int prio = I915_PRIORITY_INVALID | I915_PRIORITY_NEWCLIENT;
+	int prio = I915_PRIORITY_INVALID | ACTIVE_PRIORITY;
 
 	lockdep_assert_held(&engine->timeline.lock);
 
@@ -352,8 +383,8 @@ static void __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	 * stream, so give it the equivalent small priority bump to prevent
 	 * it being gazumped a second time by another peer.
 	 */
-	if (!(prio & I915_PRIORITY_NEWCLIENT)) {
-		prio |= I915_PRIORITY_NEWCLIENT;
+	if ((prio & ACTIVE_PRIORITY) != ACTIVE_PRIORITY) {
+		prio |= ACTIVE_PRIORITY;
 		active->sched.attr.priority = prio;
 		list_move_tail(&active->sched.link,
 			       i915_sched_lookup_priolist(engine, prio));
-- 
2.20.1