[PATCH 25/33] drm/i915/execlists: Switch to rb_root_cached

Chris Wilson chris at chris-wilson.co.uk
Sat Jun 2 13:12:31 UTC 2018


The kernel recently gained an augmented rbtree with the purpose of
cacheing the leftmost element of the rbtree, a frequent optimisation to
avoid calls to rb_first() which is also employed by the
execlists->queue. Switch from our open-coded cache to the library.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_engine_cs.c      |  7 ++---
 drivers/gpu/drm/i915/intel_guc_submission.c | 12 +++-----
 drivers/gpu/drm/i915/intel_lrc.c            | 32 +++++++--------------
 drivers/gpu/drm/i915/intel_ringbuffer.h     |  7 +----
 4 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index c08587554d0d..7812eaf502d9 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -464,8 +464,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 }
 
 /**
@@ -997,7 +996,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	}
 
 	/* ELSP is empty, but there are ready requests? E.g. after reset */
-	if (READ_ONCE(engine->execlists.first))
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
 		return false;
 
 	/* Ring stopped? */
@@ -1562,7 +1561,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	last = NULL;
 	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	for (rb = execlists->first; rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index c8cfed41fcfd..598c505e2894 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -695,9 +695,6 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->timeline.lock);
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (port_isset(port)) {
 		if (intel_engine_has_preemption(engine)) {
 			struct guc_preempt_work *preempt_work =
@@ -719,7 +716,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 	}
 	GEM_BUG_ON(port_isset(port));
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -744,15 +741,13 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
 done:
 	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
-	execlists->first = rb;
 	if (submit)
 		port_assign(port, last);
 	if (last)
@@ -761,7 +756,8 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	return submit;
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 9976d31e2c69..faa56b484819 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -268,7 +268,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_node;
+	parent = &execlists->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -306,10 +306,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 	p->priority = prio;
 	INIT_LIST_HEAD(&p->requests);
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color(&p->node, &execlists->queue);
-
-	if (first)
-		execlists->first = &p->node;
+	rb_insert_color_cached(&p->node, &execlists->queue, first);
 
 	return p;
 }
@@ -598,9 +595,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (last) {
 		/*
 		 * Don't resubmit or switch until all outstanding
@@ -662,7 +656,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		last->tail = last->wa_tail;
 	}
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -721,8 +715,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -748,14 +741,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	execlists->queue_priority =
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
-	execlists->first = rb;
 	if (submit) {
 		port_assign(port, last);
 		execlists_submit_ports(engine);
 	}
 
 	/* We must always keep the beast fed if we have work piled up */
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	/* Re-evaluate the executing context setup after each preemptive kick */
 	if (last)
@@ -902,8 +895,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	rb = execlists->first;
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
@@ -913,8 +905,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 			__i915_request_submit(rq);
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -923,8 +914,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 	GEM_BUG_ON(port_isset(execlists->port));
 
 	spin_unlock(&engine->timeline.lock);
@@ -1157,7 +1147,7 @@ static void execlists_submit_request(struct i915_request *request)
 
 	queue_request(engine, &request->sched, rq_prio(request));
 
-	GEM_BUG_ON(!engine->execlists.first);
+	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
 	submit_queue(engine, rq_prio(request));
@@ -1990,7 +1980,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
 	/* After a GPU reset, we may have requests to replay */
-	if (execlists->first)
+	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
 		tasklet_schedule(&execlists->tasklet);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f5149bd2b3b7..3448b9a39130 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -292,12 +292,7 @@ struct intel_engine_execlists {
 	/**
 	 * @queue: queue of requests, in priority lists
 	 */
-	struct rb_root queue;
-
-	/**
-	 * @first: leftmost level in priority @queue
-	 */
-	struct rb_node *first;
+	struct rb_root_cached queue;
 
 	/**
 	 * @csb_head: context status buffer head
-- 
2.17.1



More information about the Intel-gfx-trybot mailing list