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 43/57] drm/i915/gt: Delay taking irqoff for execlists submission
Date: Mon,  1 Feb 2021 08:57:01 +0000
Message-ID: <20210201085715.27435-43-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210201085715.27435-1-chris@chris-wilson.co.uk>

Before we take the irqsafe spinlock to dequeue requests and submit them
to HW, first do the check whether we need to take any action (i.e.
whether the HW is ready for some work, or if we need to preempt the
currently executing context) without taking the lock. We will then
likely skip taking the spinlock, and so reduce contention.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 88 ++++++++-----------
 1 file changed, 39 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index e8f192984e88..d4ae65af7dc1 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -1014,24 +1014,6 @@ static void virtual_xfer_context(struct virtual_engine *ve,
 	}
 }
 
-static void defer_active(struct intel_engine_cs *engine)
-{
-	struct i915_request *rq;
-
-	rq = __i915_sched_rewind_requests(engine);
-	if (!rq)
-		return;
-
-	/*
-	 * We want to move the interrupted request to the back of
-	 * the round-robin list (i.e. its priority level), but
-	 * in doing so, we must then move all requests that were in
-	 * flight and were waiting for the interrupted request to
-	 * be run after it again.
-	 */
-	__i915_sched_defer_request(engine, rq);
-}
-
 static bool
 timeslice_yield(const struct intel_engine_execlists *el,
 		const struct i915_request *rq)
@@ -1312,8 +1294,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	spin_lock(&se->lock);
-
 	/*
 	 * If the queue is higher priority than the last
 	 * request in the currently active context, submit afresh.
@@ -1336,24 +1316,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				     rq_deadline(last),
 				     rq_prio(last));
 			record_preemption(execlists);
-
-			/*
-			 * Don't let the RING_HEAD advance past the breadcrumb
-			 * as we unwind (and until we resubmit) so that we do
-			 * not accidentally tell it to go backwards.
-			 */
-			ring_set_paused(engine, 1);
-
-			/*
-			 * Note that we have not stopped the GPU at this point,
-			 * so we are unwinding the incomplete requests as they
-			 * remain inflight and so by the time we do complete
-			 * the preemption, some of the unwound requests may
-			 * complete!
-			 */
-			__i915_sched_rewind_requests(engine);
-
-			last = NULL;
+			last = (void *)1;
 		} else if (timeslice_expired(engine, last)) {
 			ENGINE_TRACE(engine,
 				     "expired:%s last=%llx:%llu, deadline=%llu, now=%llu, yield?=%s\n",
@@ -1380,8 +1343,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * same context again, grant it a full timeslice.
 			 */
 			cancel_timer(&execlists->timer);
-			ring_set_paused(engine, 1);
-			defer_active(engine);
 
 			/*
 			 * Unlike for preemption, if we rewind and continue
@@ -1396,7 +1357,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * normal save/restore will preserve state and allow
 			 * us to later continue executing the same request.
 			 */
-			last = NULL;
+			last = (void *)3;
 		} else {
 			/*
 			 * Otherwise if we already have a request pending
@@ -1412,12 +1373,46 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 * Even if ELSP[1] is occupied and not worthy
 				 * of timeslices, our queue might be.
 				 */
-				spin_unlock(&se->lock);
 				return;
 			}
 		}
 	}
 
+	local_irq_disable(); /* irq remains off until after ELSP write */
+	spin_lock(&se->lock);
+
+	if ((unsigned long)last & 1) {
+		bool defer = (unsigned long)last & 2;
+
+		/*
+		 * Don't let the RING_HEAD advance past the breadcrumb
+		 * as we unwind (and until we resubmit) so that we do
+		 * not accidentally tell it to go backwards.
+		 */
+		ring_set_paused(engine, (unsigned long)last);
+
+		/*
+		 * Note that we have not stopped the GPU at this point,
+		 * so we are unwinding the incomplete requests as they
+		 * remain inflight and so by the time we do complete
+		 * the preemption, some of the unwound requests may
+		 * complete!
+		 */
+		last = __i915_sched_rewind_requests(engine);
+
+		/*
+		 * We want to move the interrupted request to the back of
+		 * the round-robin list (i.e. its priority level), but
+		 * in doing so, we must then move all requests that were in
+		 * flight and were waiting for the interrupted request to
+		 * be run after it again.
+		 */
+		if (last && defer)
+			__i915_sched_defer_request(engine, last);
+
+		last = NULL;
+	}
+
 	if (!RB_EMPTY_ROOT(&execlists->virtual.rb_root))
 		virtual_requeue(engine, last);
 
@@ -1533,13 +1528,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			i915_request_put(*port);
 		*execlists->pending = NULL;
 	}
-}
 
-static void execlists_dequeue_irq(struct intel_engine_cs *engine)
-{
-	local_irq_disable(); /* Suspend interrupts across request submission */
-	execlists_dequeue(engine);
-	local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */
+	local_irq_enable();
 }
 
 static void clear_ports(struct i915_request **ports, int count)
@@ -2191,7 +2181,7 @@ static void execlists_submission_tasklet(struct tasklet_struct *t)
 		execlists_reset(engine);
 
 	if (!engine->execlists.pending[0]) {
-		execlists_dequeue_irq(engine);
+		execlists_dequeue(engine);
 		start_timeslice(engine);
 	}
 
-- 
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: 103+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-01  8:56 [Intel-gfx] [PATCH 01/57] drm/i915/gt: Restrict the GT clock override to just Icelake Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 02/57] drm/i915/selftests: Exercise relative mmio paths to non-privileged registers Chris Wilson
2021-02-01 14:34   ` Mika Kuoppala
2021-02-01  8:56 ` [Intel-gfx] [PATCH 03/57] drm/i915/selftests: Exercise cross-process context isolation Chris Wilson
2021-02-01 16:37   ` Mika Kuoppala
2021-02-01  8:56 ` [Intel-gfx] [PATCH 04/57] drm/i915: Protect against request freeing during cancellation on wedging Chris Wilson
2021-02-02  9:55   ` Mika Kuoppala
2021-02-01  8:56 ` [Intel-gfx] [PATCH 05/57] drm/i915: Take rcu_read_lock for querying fence's driver/timeline names Chris Wilson
2021-02-02 18:33   ` Mika Kuoppala
2021-02-01  8:56 ` [Intel-gfx] [PATCH 06/57] drm/i915/gt: Always flush the submission queue on checking for idle Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 07/57] drm/i915/gt: Move engine setup out of set_default_submission Chris Wilson
2021-02-02 11:57   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 08/57] drm/i915/gt: Move submission_method into intel_gt Chris Wilson
2021-02-02 12:03   ` Tvrtko Ursulin
2021-02-02 12:18     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 09/57] drm/i915: Replace engine->schedule() with a known request operation Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 10/57] drm/i915: Restructure priority inheritance Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 11/57] drm/i915/selftests: Measure set-priority duration Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 12/57] drm/i915/selftests: Exercise priority inheritance around an engine loop Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 13/57] drm/i915/selftests: Force a rewind if at first we don't succeed Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 14/57] drm/i915: Improve DFS for priority inheritance Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 15/57] drm/i915: Extract request submission from execlists Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 16/57] drm/i915: Extract request rewinding " Chris Wilson
2021-02-02 13:08   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 17/57] drm/i915: Extract request suspension from the execlists Chris Wilson
2021-02-02 13:15   ` Tvrtko Ursulin
2021-02-02 13:26     ` Chris Wilson
2021-02-02 13:32       ` Tvrtko Ursulin
2021-02-02 13:27     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 18/57] drm/i915: Extract the ability to defer and rerun a request later Chris Wilson
2021-02-02 13:18   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 19/57] drm/i915: Fix the iterative dfs for defering requests Chris Wilson
2021-02-02 14:10   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 20/57] drm/i915: Wrap access to intel_engine.active Chris Wilson
2021-02-04 11:07   ` Tvrtko Ursulin
2021-02-04 11:18     ` Chris Wilson
2021-02-04 11:56       ` Chris Wilson
2021-02-04 12:08         ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 21/57] drm/i915: Move common active lists from engine to i915_scheduler Chris Wilson
2021-02-04 11:12   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 22/57] drm/i915: Move scheduler queue Chris Wilson
2021-02-04 11:19   ` Tvrtko Ursulin
2021-02-04 11:32     ` Chris Wilson
2021-02-04 11:40     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 23/57] drm/i915: Move tasklet from execlists to sched Chris Wilson
2021-02-04 14:06   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 24/57] drm/i915/gt: Only kick the scheduler on timeslice/preemption change Chris Wilson
2021-02-04 14:09   ` Tvrtko Ursulin
2021-02-04 14:43     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 25/57] drm/i915: Move submit_request to i915_sched_engine Chris Wilson
2021-02-04 14:13   ` Tvrtko Ursulin
2021-02-04 14:45     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 26/57] drm/i915: Move finding the current active request to the scheduler Chris Wilson
2021-02-04 14:30   ` Tvrtko Ursulin
2021-02-04 14:59     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 27/57] drm/i915: Show execlists queues when dumping state Chris Wilson
2021-02-04 15:04   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 28/57] drm/i915: Wrap i915_request_use_semaphores() Chris Wilson
2021-02-04 15:05   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 29/57] drm/i915: Move scheduler flags Chris Wilson
2021-02-04 15:14   ` Tvrtko Ursulin
2021-02-04 16:05     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 30/57] drm/i915: Move timeslicing flag to scheduler Chris Wilson
2021-02-04 15:18   ` Tvrtko Ursulin
2021-02-04 16:11     ` Chris Wilson
2021-02-05  9:48       ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 31/57] drm/i915/gt: Declare when we enabled timeslicing Chris Wilson
2021-02-04 15:26   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 32/57] drm/i915: Move needs-breadcrumb flags to scheduler Chris Wilson
2021-02-04 15:28   ` Tvrtko Ursulin
2021-02-04 16:12     ` Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 33/57] drm/i915: Move busywaiting control to the scheduler Chris Wilson
2021-02-04 15:32   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 34/57] drm/i915: Move preempt-reset flag " Chris Wilson
2021-02-04 15:34   ` Tvrtko Ursulin
2021-02-01  8:56 ` [Intel-gfx] [PATCH 35/57] drm/i915: Replace priolist rbtree with a skiplist Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 36/57] drm/i915: Wrap cmpxchg64 with try_cmpxchg64() helper Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 37/57] drm/i915: Fair low-latency scheduling Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 38/57] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 39/57] drm/i915: Extend the priority boosting for the display with a deadline Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 40/57] drm/i915/gt: Support virtual engine queues Chris Wilson
2021-02-01  8:56 ` [Intel-gfx] [PATCH 41/57] drm/i915: Move saturated workload detection back to the context Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 42/57] drm/i915: Bump default timeslicing quantum to 5ms Chris Wilson
2021-02-01  8:57 ` Chris Wilson [this message]
2021-02-01  8:57 ` [Intel-gfx] [PATCH 44/57] drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 45/57] drm/i915/gt: Track timeline GGTT offset separately from subpage offset Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 46/57] drm/i915/gt: Add timeline "mode" Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 47/57] drm/i915/gt: Use indices for writing into relative timelines Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 48/57] drm/i915/selftests: Exercise relative timeline modes Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 49/57] drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 50/57] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq" Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 51/57] drm/i915/gt: Couple tasklet scheduling for all CS interrupts Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 52/57] drm/i915/gt: Support creation of 'internal' rings Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 53/57] drm/i915/gt: Use client timeline address for seqno writes Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 54/57] drm/i915/gt: Infrastructure for ring scheduling Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 55/57] drm/i915/gt: Implement ring scheduler for gen4-7 Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 56/57] drm/i915/gt: Enable ring scheduling for gen5-7 Chris Wilson
2021-02-01  8:57 ` [Intel-gfx] [PATCH 57/57] drm/i915: Support secure dispatch on gen6/gen7 Chris Wilson
2021-02-01 14:13 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/57] drm/i915/gt: Restrict the GT clock override to just Icelake Patchwork
2021-02-01 14:15 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-02-01 14:15 ` [Intel-gfx] [PATCH 01/57] " Mika Kuoppala
2021-02-01 14:41 ` [Intel-gfx] ✓ Fi.CI.BAT: success for series starting with [01/57] " Patchwork
2021-02-01 19:33 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " 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=20210201085715.27435-43-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