Intel-GFX Archive on lore.kernel.org
 help / color / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 17/42] drm/i915/gt: Use virtual_engine during execlists_dequeue
Date: Sun,  2 Aug 2020 17:43:47 +0100
Message-ID: <20200802164412.2738-18-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200802164412.2738-1-chris@chris-wilson.co.uk>

Rather than going back and forth between the rb_node entry and the
virtual_engine type, store the ve local and reuse it. As the
container_of conversion from rb_node to virtual_engine requires a
variable offset, performing that conversion just once shaves off a bit
of code.

v2: Keep a single virtual engine lookup, for typical use.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 239 ++++++++++++----------------
 1 file changed, 105 insertions(+), 134 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index dcbd47e8a513..c1ba1eee4b29 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -454,9 +454,15 @@ static int queue_prio(const struct intel_engine_execlists *execlists)
 	return ((p->priority + 1) << I915_USER_PRIORITY_SHIFT) - ffs(p->used);
 }
 
+static int virtual_prio(const struct intel_engine_execlists *el)
+{
+	struct rb_node *rb = rb_first_cached(&el->virtual);
+
+	return rb ? rb_entry(rb, struct ve_node, rb)->prio : INT_MIN;
+}
+
 static inline bool need_preempt(const struct intel_engine_cs *engine,
-				const struct i915_request *rq,
-				struct rb_node *rb)
+				const struct i915_request *rq)
 {
 	int last_prio;
 
@@ -493,25 +499,6 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	    rq_prio(list_next_entry(rq, sched.link)) > last_prio)
 		return true;
 
-	if (rb) {
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		bool preempt = false;
-
-		if (engine == ve->siblings[0]) { /* only preempt one sibling */
-			struct i915_request *next;
-
-			rcu_read_lock();
-			next = READ_ONCE(ve->request);
-			if (next)
-				preempt = rq_prio(next) > last_prio;
-			rcu_read_unlock();
-		}
-
-		if (preempt)
-			return preempt;
-	}
-
 	/*
 	 * If the inflight context did not trigger the preemption, then maybe
 	 * it was the set of queued requests? Pick the highest priority in
@@ -522,7 +509,8 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	 * ELSP[0] or ELSP[1] as, thanks again to PI, if it was the same
 	 * context, it's priority would not exceed ELSP[0] aka last_prio.
 	 */
-	return queue_prio(&engine->execlists) > last_prio;
+	return max(virtual_prio(&engine->execlists),
+		   queue_prio(&engine->execlists)) > last_prio;
 }
 
 __maybe_unused static inline bool
@@ -1807,6 +1795,35 @@ static bool virtual_matches(const struct virtual_engine *ve,
 	return true;
 }
 
+static struct virtual_engine *
+first_virtual_engine(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *el = &engine->execlists;
+	struct rb_node *rb = rb_first_cached(&el->virtual);
+
+	while (rb) {
+		struct virtual_engine *ve =
+			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+		struct i915_request *rq = READ_ONCE(ve->request);
+
+		/* lazily cleanup after another engine handled rq */
+		if (!rq) {
+			rb_erase_cached(rb, &el->virtual);
+			RB_CLEAR_NODE(rb);
+			rb = rb_first_cached(&el->virtual);
+			continue;
+		}
+
+		if (!virtual_matches(ve, rq, engine)) {
+			rb = rb_next(rb);
+			continue;
+		}
+		return ve;
+	}
+
+	return NULL;
+}
+
 static void virtual_xfer_context(struct virtual_engine *ve,
 				 struct intel_engine_cs *engine)
 {
@@ -1905,32 +1922,15 @@ static void defer_active(struct intel_engine_cs *engine)
 
 static bool
 need_timeslice(const struct intel_engine_cs *engine,
-	       const struct i915_request *rq,
-	       const struct rb_node *rb)
+	       const struct i915_request *rq)
 {
 	int hint;
 
 	if (!intel_engine_has_timeslices(engine))
 		return false;
 
-	hint = engine->execlists.queue_priority_hint;
-
-	if (rb) {
-		const struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		const struct intel_engine_cs *inflight =
-			intel_context_inflight(&ve->context);
-
-		if (!inflight || inflight == engine) {
-			struct i915_request *next;
-
-			rcu_read_lock();
-			next = READ_ONCE(ve->request);
-			if (next)
-				hint = max(hint, rq_prio(next));
-			rcu_read_unlock();
-		}
-	}
+	hint = max(engine->execlists.queue_priority_hint,
+		   virtual_prio(&engine->execlists));
 
 	if (!list_is_last(&rq->sched.link, &engine->active.requests))
 		hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
@@ -2077,6 +2077,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	struct i915_request **port = execlists->pending;
 	struct i915_request ** const last_port = port + execlists->port_mask;
 	struct i915_request *last = *execlists->active;
+	struct virtual_engine *ve;
 	struct rb_node *rb;
 	bool submit = false;
 
@@ -2103,26 +2104,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 */
 	spin_lock_irq(&engine->active.lock);
 
-	for (rb = rb_first_cached(&execlists->virtual); rb; ) {
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
-		struct i915_request *rq = READ_ONCE(ve->request);
-
-		if (!rq) { /* lazily cleanup after another engine handled rq */
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
-			rb = rb_first_cached(&execlists->virtual);
-			continue;
-		}
-
-		if (!virtual_matches(ve, rq, engine)) {
-			rb = rb_next(rb);
-			continue;
-		}
-
-		break;
-	}
-
 	/*
 	 * If the queue is higher priority than the last
 	 * request in the currently active context, submit afresh.
@@ -2145,7 +2126,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	if (last) {
 		if (i915_request_completed(last)) {
 			goto check_secondary;
-		} else if (need_preempt(engine, last, rb)) {
+		} else if (need_preempt(engine, last)) {
 			ENGINE_TRACE(engine,
 				     "preempting last=%llx:%lld, prio=%d, hint=%d\n",
 				     last->fence.context,
@@ -2171,7 +2152,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			__unwind_incomplete_requests(engine);
 
 			last = NULL;
-		} else if (need_timeslice(engine, last, rb) &&
+		} else if (need_timeslice(engine, last) &&
 			   timeslice_expired(execlists, last)) {
 			ENGINE_TRACE(engine,
 				     "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n",
@@ -2222,96 +2203,86 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		}
 	}
 
-	while (rb) { /* XXX virtual is always taking precedence */
-		struct virtual_engine *ve =
-			rb_entry(rb, typeof(*ve), nodes[engine->id].rb);
+	/* XXX virtual is always taking precedence */
+	while ((ve = first_virtual_engine(engine))) {
 		struct i915_request *rq;
 
 		spin_lock(&ve->base.active.lock);
 
 		rq = ve->request;
-		if (unlikely(!rq)) { /* lost the race to a sibling */
-			spin_unlock(&ve->base.active.lock);
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
-			rb = rb_first_cached(&execlists->virtual);
-			continue;
-		}
+		if (unlikely(!rq)) /* lost the race to a sibling */
+			goto unlock;
 
-		GEM_BUG_ON(rq != ve->request);
 		GEM_BUG_ON(rq->engine != &ve->base);
 		GEM_BUG_ON(rq->context != &ve->context);
 
-		if (rq_prio(rq) >= queue_prio(execlists)) {
-			if (!virtual_matches(ve, rq, engine)) {
-				spin_unlock(&ve->base.active.lock);
-				rb = rb_next(rb);
-				continue;
-			}
+		if (unlikely(rq_prio(rq) < queue_prio(execlists))) {
+			spin_unlock(&ve->base.active.lock);
+			break;
+		}
 
-			if (last && !can_merge_rq(last, rq)) {
-				spin_unlock(&ve->base.active.lock);
-				spin_unlock_irq(&engine->active.lock);
-				start_timeslice(engine, rq_prio(rq));
-				return; /* leave this for another sibling */
-			}
+		GEM_BUG_ON(!virtual_matches(ve, rq, engine));
 
-			ENGINE_TRACE(engine,
-				     "virtual rq=%llx:%lld%s, new engine? %s\n",
-				     rq->fence.context,
-				     rq->fence.seqno,
-				     i915_request_completed(rq) ? "!" :
-				     i915_request_started(rq) ? "*" :
-				     "",
-				     yesno(engine != ve->siblings[0]));
-
-			WRITE_ONCE(ve->request, NULL);
-			WRITE_ONCE(ve->base.execlists.queue_priority_hint,
-				   INT_MIN);
-			rb_erase_cached(rb, &execlists->virtual);
-			RB_CLEAR_NODE(rb);
+		if (last && !can_merge_rq(last, rq)) {
+			spin_unlock(&ve->base.active.lock);
+			spin_unlock_irq(&engine->active.lock);
+			start_timeslice(engine, rq_prio(rq));
+			return; /* leave this for another sibling */
+		}
 
-			GEM_BUG_ON(!(rq->execution_mask & engine->mask));
-			WRITE_ONCE(rq->engine, engine);
+		ENGINE_TRACE(engine,
+			     "virtual rq=%llx:%lld%s, new engine? %s\n",
+			     rq->fence.context,
+			     rq->fence.seqno,
+			     i915_request_completed(rq) ? "!" :
+			     i915_request_started(rq) ? "*" :
+			     "",
+			     yesno(engine != ve->siblings[0]));
 
-			if (__i915_request_submit(rq)) {
-				/*
-				 * Only after we confirm that we will submit
-				 * this request (i.e. it has not already
-				 * completed), do we want to update the context.
-				 *
-				 * This serves two purposes. It avoids
-				 * unnecessary work if we are resubmitting an
-				 * already completed request after timeslicing.
-				 * But more importantly, it prevents us altering
-				 * ve->siblings[] on an idle context, where
-				 * we may be using ve->siblings[] in
-				 * virtual_context_enter / virtual_context_exit.
-				 */
-				virtual_xfer_context(ve, engine);
-				GEM_BUG_ON(ve->siblings[0] != engine);
+		WRITE_ONCE(ve->request, NULL);
+		WRITE_ONCE(ve->base.execlists.queue_priority_hint, INT_MIN);
 
-				submit = true;
-				last = rq;
-			}
-			i915_request_put(rq);
+		rb = &ve->nodes[engine->id].rb;
+		rb_erase_cached(rb, &execlists->virtual);
+		RB_CLEAR_NODE(rb);
+
+		GEM_BUG_ON(!(rq->execution_mask & engine->mask));
+		WRITE_ONCE(rq->engine, engine);
 
+		if (__i915_request_submit(rq)) {
 			/*
-			 * Hmm, we have a bunch of virtual engine requests,
-			 * but the first one was already completed (thanks
-			 * preempt-to-busy!). Keep looking at the veng queue
-			 * until we have no more relevant requests (i.e.
-			 * the normal submit queue has higher priority).
+			 * Only after we confirm that we will submit
+			 * this request (i.e. it has not already
+			 * completed), do we want to update the context.
+			 *
+			 * This serves two purposes. It avoids
+			 * unnecessary work if we are resubmitting an
+			 * already completed request after timeslicing.
+			 * But more importantly, it prevents us altering
+			 * ve->siblings[] on an idle context, where
+			 * we may be using ve->siblings[] in
+			 * virtual_context_enter / virtual_context_exit.
 			 */
-			if (!submit) {
-				spin_unlock(&ve->base.active.lock);
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
+			virtual_xfer_context(ve, engine);
+			GEM_BUG_ON(ve->siblings[0] != engine);
+
+			submit = true;
+			last = rq;
 		}
 
+		i915_request_put(rq);
+unlock:
 		spin_unlock(&ve->base.active.lock);
-		break;
+
+		/*
+		 * Hmm, we have a bunch of virtual engine requests,
+		 * but the first one was already completed (thanks
+		 * preempt-to-busy!). Keep looking at the veng queue
+		 * until we have no more relevant requests (i.e.
+		 * the normal submit queue has higher priority).
+		 */
+		if (submit)
+			break;
 	}
 
 	while ((rb = rb_first_cached(&execlists->queue))) {
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply index

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-02 16:43 [Intel-gfx] Time, where did it go? Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 01/42] drm/i915: Fix wrong return value Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 02/42] drm/i915/gem: Don't drop the timeline lock during execbuf Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 03/42] drm/i915/gem: Reduce context termination list iteration guard to RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 04/42] drm/i915/gt: Protect context lifetime with RCU Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 05/42] drm/i915/gt: Free stale request on destroying the virtual engine Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 06/42] drm/i915/gt: Track signaled breadcrumbs outside of the breadcrumb spinlock Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 07/42] drm/i915/gt: Split the breadcrumb spinlock between global and contexts Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 08/42] drm/i915: Drop i915_request.lock serialisation around await_start Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 09/42] drm/i915: Drop i915_request.lock requirement for intel_rps_boost() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 10/42] drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 11/42] drm/i915/gem: Reduce ctx->engines_mutex for get_engines() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 12/42] drm/i915: Reduce test_and_set_bit to set_bit in i915_request_submit() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 13/42] drm/i915/gt: Decouple completed requests on unwind Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 14/42] drm/i915/gt: Check for a completed last request once Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 15/42] drm/i915/gt: Refactor heartbeat request construction and submission Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 16/42] drm/i915/gt: Replace direct submit with direct call to tasklet Chris Wilson
2020-08-02 16:43 ` Chris Wilson [this message]
2020-08-02 16:43 ` [Intel-gfx] [PATCH 18/42] drm/i915/gt: Decouple inflight virtual engines Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 19/42] drm/i915/gt: Defer schedule_out until after the next dequeue Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 20/42] drm/i915/gt: Resubmit the virtual engine on schedule-out Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 21/42] drm/i915/gt: Simplify virtual engine handling for execlists_hold() Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 22/42] drm/i915/gt: ce->inflight updates are now serialised Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 23/42] drm/i915/gt: Drop atomic for engine->fw_active tracking Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 24/42] drm/i915/gt: Extract busy-stats for ring-scheduler Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 25/42] drm/i915/gt: Convert stats.active to plain unsigned int Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 26/42] drm/i915: Lift waiter/signaler iterators Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 27/42] drm/i915: Strip out internal priorities Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 28/42] drm/i915: Remove I915_USER_PRIORITY_SHIFT Chris Wilson
2020-08-02 16:43 ` [Intel-gfx] [PATCH 29/42] drm/i915/gt: Defer the kmem_cache_free() until after the HW submit Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 30/42] drm/i915: Prune empty priolists Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 31/42] drm/i915: Replace engine->schedule() with a known request operation Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 32/42] drm/i915/gt: Do not suspend bonded requests if one hangs Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 33/42] drm/i915: Teach the i915_dependency to use a double-lock Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 34/42] drm/i915: Restructure priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 35/42] drm/i915/selftests: Measure set-priority duration Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 36/42] drm/i915: Improve DFS for priority inheritance Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 37/42] drm/i915/gt: Remove timeslice suppression Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 38/42] drm/i915: Fair low-latency scheduling Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 39/42] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 40/42] drm/i915: Replace the priority boosting for the display with a deadline Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 41/42] drm/i915: Move saturated workload detection back to the context Chris Wilson
2020-08-02 16:44 ` [Intel-gfx] [PATCH 42/42] drm/i915/gt: Another tweak for flushing the tasklets Chris Wilson
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/42] drm/i915: Fix wrong return value Patchwork
2020-08-02 17:14 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-08-02 17:34 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-08-02 17:56 ` [Intel-gfx] Time, where did it go? Dave Airlie
2020-08-02 19:36   ` Chris Wilson
2020-08-04 21:45     ` Dave Airlie
2020-08-07  7:12       ` Chris Wilson
2020-08-09 20:01         ` Dave Airlie
2020-08-02 21:03 ` [Intel-gfx] ✗ Fi.CI.IGT: failure for series starting with [01/42] drm/i915: Fix wrong return value Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200802164412.2738-18-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Intel-GFX Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/intel-gfx/0 intel-gfx/git/0.git
	git clone --mirror https://lore.kernel.org/intel-gfx/1 intel-gfx/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 intel-gfx intel-gfx/ https://lore.kernel.org/intel-gfx \
		intel-gfx@lists.freedesktop.org
	public-inbox-index intel-gfx

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.freedesktop.lists.intel-gfx


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git