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 33/42] drm/i915: Teach the i915_dependency to use a double-lock
Date: Sun,  2 Aug 2020 17:44:03 +0100
Message-ID: <20200802164412.2738-34-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200802164412.2738-1-chris@chris-wilson.co.uk>

Currently, we construct and teardown the i915_dependency chains using a
global spinlock. As the lists are entirely local, it should be possible
to use an double-lock with an explicit nesting [signaler -> waiter,
always] and so avoid the costly convenience of a global spinlock.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c         |  6 +--
 drivers/gpu/drm/i915/i915_request.c         |  2 +-
 drivers/gpu/drm/i915/i915_scheduler.c       | 44 +++++++++++++--------
 drivers/gpu/drm/i915/i915_scheduler.h       |  2 +-
 drivers/gpu/drm/i915/i915_scheduler_types.h |  1 +
 5 files changed, 34 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 3999bf6c6aee..cb53f350848f 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1847,7 +1847,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
-			if (p->flags & I915_DEPENDENCY_WEAK)
+			if (!p->waiter || p->flags & I915_DEPENDENCY_WEAK)
 				continue;
 
 			/* Leave semaphores spinning on the other engines */
@@ -2700,7 +2700,7 @@ static void __execlists_hold(struct i915_request *rq)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
-			if (p->flags & I915_DEPENDENCY_WEAK)
+			if (!p->waiter || p->flags & I915_DEPENDENCY_WEAK)
 				continue;
 
 			/* Leave semaphores spinning on the other engines */
@@ -2798,7 +2798,7 @@ static void __execlists_unhold(struct i915_request *rq)
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);
 
-			if (p->flags & I915_DEPENDENCY_WEAK)
+			if (!p->waiter || p->flags & I915_DEPENDENCY_WEAK)
 				continue;
 
 			/* Propagate any change in error status */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8a263556997c..3f9e3e6a34ed 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -329,7 +329,7 @@ bool i915_request_retire(struct i915_request *rq)
 	intel_context_unpin(rq->context);
 
 	free_capture_list(rq);
-	i915_sched_node_fini(&rq->sched);
+	i915_sched_node_retire(&rq->sched);
 	i915_request_put(rq);
 
 	return true;
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 4760d7c9b7cd..247d2e2bb3c8 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -389,6 +389,8 @@ void i915_request_set_priority(struct i915_request *rq, int prio)
 
 void i915_sched_node_init(struct i915_sched_node *node)
 {
+	spin_lock_init(&node->lock);
+
 	INIT_LIST_HEAD(&node->signalers_list);
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
@@ -426,7 +428,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 {
 	bool ret = false;
 
-	spin_lock_irq(&schedule_lock);
+	/* The signal->lock is always the outer lock in this double-lock. */
+	spin_lock_irq(&signal->lock);
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
@@ -435,15 +438,17 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 		dep->flags = flags;
 
 		/* All set, now publish. Beware the lockless walkers. */
+		spin_lock_nested(&node->lock, SINGLE_DEPTH_NESTING);
 		list_add_rcu(&dep->signal_link, &node->signalers_list);
 		list_add_rcu(&dep->wait_link, &signal->waiters_list);
+		spin_unlock(&node->lock);
 
 		/* Propagate the chains */
 		node->flags |= signal->flags;
 		ret = true;
 	}
 
-	spin_unlock_irq(&schedule_lock);
+	spin_unlock_irq(&signal->lock);
 
 	return ret;
 }
@@ -469,39 +474,46 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 	return 0;
 }
 
-void i915_sched_node_fini(struct i915_sched_node *node)
+void i915_sched_node_retire(struct i915_sched_node *node)
 {
 	struct i915_dependency *dep, *tmp;
 
-	spin_lock_irq(&schedule_lock);
+	spin_lock_irq(&node->lock);
 
 	/*
 	 * Everyone we depended upon (the fences we wait to be signaled)
 	 * should retire before us and remove themselves from our list.
 	 * However, retirement is run independently on each timeline and
-	 * so we may be called out-of-order.
+	 * so we may be called out-of-order. As we need to avoid taking
+	 * the signaler's lock, just mark up our completion and be wary
+	 * in traversing the signalers->waiters_list.
 	 */
-	list_for_each_entry_safe(dep, tmp, &node->signalers_list, signal_link) {
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
-
-		list_del_rcu(&dep->wait_link);
-		if (dep->flags & I915_DEPENDENCY_ALLOC)
-			i915_dependency_free(dep);
+	list_for_each_entry(dep, &node->signalers_list, signal_link) {
+		GEM_BUG_ON(dep->waiter != node);
+		WRITE_ONCE(dep->waiter, NULL);
 	}
-	INIT_LIST_HEAD(&node->signalers_list);
+	INIT_LIST_HEAD_RCU(&node->signalers_list);
 
 	/* Remove ourselves from everyone who depends upon us */
 	list_for_each_entry_safe(dep, tmp, &node->waiters_list, wait_link) {
+		struct i915_sched_node *w;
+
 		GEM_BUG_ON(dep->signaler != node);
-		GEM_BUG_ON(!list_empty(&dep->dfs_link));
 
-		list_del_rcu(&dep->signal_link);
+		w = READ_ONCE(dep->waiter);
+		if (w) {
+			spin_lock_nested(&w->lock, SINGLE_DEPTH_NESTING);
+			if (READ_ONCE(dep->waiter))
+				list_del_rcu(&dep->signal_link);
+			spin_unlock(&w->lock);
+		}
+
 		if (dep->flags & I915_DEPENDENCY_ALLOC)
 			i915_dependency_free(dep);
 	}
-	INIT_LIST_HEAD(&node->waiters_list);
+	INIT_LIST_HEAD_RCU(&node->waiters_list);
 
-	spin_unlock_irq(&schedule_lock);
+	spin_unlock_irq(&node->lock);
 }
 
 static void i915_global_scheduler_shrink(void)
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index ccee9acbd101..f9a9d102863b 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -31,7 +31,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node,
 				   struct i915_sched_node *signal,
 				   unsigned long flags);
 
-void i915_sched_node_fini(struct i915_sched_node *node);
+void i915_sched_node_retire(struct i915_sched_node *node);
 
 void i915_request_set_priority(struct i915_request *request, int prio);
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 343ed44d5ed4..3246430eb1c1 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -60,6 +60,7 @@ struct i915_sched_attr {
  * others.
  */
 struct i915_sched_node {
+	spinlock_t lock; /* protect the lists */
 	struct list_head signalers_list; /* those before us, we depend upon */
 	struct list_head waiters_list; /* those after us, they depend upon us */
 	struct list_head link;
-- 
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 ` [Intel-gfx] [PATCH 17/42] drm/i915/gt: Use virtual_engine during execlists_dequeue Chris Wilson
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 ` Chris Wilson [this message]
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=20200802164412.2738-34-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