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 04/57] drm/i915: Protect against request freeing during cancellation on wedging
Date: Mon,  1 Feb 2021 08:56:22 +0000
Message-ID: <20210201085715.27435-4-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210201085715.27435-1-chris@chris-wilson.co.uk>

As soon as we mark a request as completed, it may be retired. So when
cancelling a request and marking it complete, make sure we first keep a
reference to the request.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 .../drm/i915/gt/intel_execlists_submission.c  | 19 +++++++++++--------
 drivers/gpu/drm/i915/gt/intel_reset.c         | 15 ++++++---------
 .../gpu/drm/i915/gt/intel_ring_submission.c   |  2 +-
 drivers/gpu/drm/i915/gt/mock_engine.c         |  8 +++++---
 drivers/gpu/drm/i915/i915_request.c           |  9 +++++++--
 drivers/gpu/drm/i915/i915_request.h           |  2 +-
 6 files changed, 31 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index e7593df6777d..45a8ac152b88 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2976,7 +2976,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->active.requests, sched.link)
-		i915_request_mark_eio(rq);
+		i915_request_put(i915_request_mark_eio(rq));
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
@@ -2984,8 +2984,10 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 		struct i915_priolist *p = to_priolist(rb);
 
 		priolist_for_each_request_consume(rq, rn, p) {
-			i915_request_mark_eio(rq);
-			__i915_request_submit(rq);
+			if (i915_request_mark_eio(rq)) {
+				__i915_request_submit(rq);
+				i915_request_put(rq);
+			}
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2994,7 +2996,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 
 	/* On-hold requests will be flushed to timeline upon their release */
 	list_for_each_entry(rq, &engine->active.hold, sched.link)
-		i915_request_mark_eio(rq);
+		i915_request_put(i915_request_mark_eio(rq));
 
 	/* Cancel all attached virtual engines */
 	while ((rb = rb_first_cached(&execlists->virtual))) {
@@ -3007,10 +3009,11 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine)
 		spin_lock(&ve->base.active.lock);
 		rq = fetch_and_zero(&ve->request);
 		if (rq) {
-			i915_request_mark_eio(rq);
-
-			rq->engine = engine;
-			__i915_request_submit(rq);
+			if (i915_request_mark_eio(rq)) {
+				rq->engine = engine;
+				__i915_request_submit(rq);
+				i915_request_put(rq);
+			}
 			i915_request_put(rq);
 
 			ve->base.execlists.queue_priority_hint = INT_MIN;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 107430e1e864..a82c4d7b23bc 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -786,18 +786,15 @@ static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
 
 static void nop_submit_request(struct i915_request *request)
 {
-	struct intel_engine_cs *engine = request->engine;
-	unsigned long flags;
-
 	RQ_TRACE(request, "-EIO\n");
-	i915_request_set_error_once(request, -EIO);
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	__i915_request_submit(request);
-	i915_request_mark_complete(request);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	request = i915_request_mark_eio(request);
+	if (request) {
+		i915_request_submit(request);
+		intel_engine_signal_breadcrumbs(request->engine);
 
-	intel_engine_signal_breadcrumbs(engine);
+		i915_request_put(request);
+	}
 }
 
 static void __intel_gt_set_wedged(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index 8b7cc637c432..9c2c605d7a92 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -400,7 +400,7 @@ static void reset_cancel(struct intel_engine_cs *engine)
 
 	/* Mark all submitted requests as skipped. */
 	list_for_each_entry(request, &engine->active.requests, sched.link)
-		i915_request_mark_eio(request);
+		i915_request_put(i915_request_mark_eio(request));
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Remaining _unready_ requests will be nop'ed when submitted */
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index df7c1b1acc32..cf1269e74998 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -239,13 +239,15 @@ static void mock_reset_cancel(struct intel_engine_cs *engine)
 
 	/* Mark all submitted requests as skipped. */
 	list_for_each_entry(rq, &engine->active.requests, sched.link)
-		i915_request_mark_eio(rq);
+		i915_request_put(i915_request_mark_eio(rq));
 	intel_engine_signal_breadcrumbs(engine);
 
 	/* Cancel and submit all pending requests. */
 	list_for_each_entry(rq, &mock->hw_queue, mock.link) {
-		i915_request_mark_eio(rq);
-		__i915_request_submit(rq);
+		if (i915_request_mark_eio(rq)) {
+			__i915_request_submit(rq);
+			i915_request_put(rq);
+		}
 	}
 	INIT_LIST_HEAD(&mock->hw_queue);
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d66981b083cd..a336d6c40d8b 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -514,15 +514,20 @@ void i915_request_set_error_once(struct i915_request *rq, int error)
 	} while (!try_cmpxchg(&rq->fence.error, &old, error));
 }
 
-void i915_request_mark_eio(struct i915_request *rq)
+struct i915_request *i915_request_mark_eio(struct i915_request *rq)
 {
 	if (__i915_request_is_complete(rq))
-		return;
+		return NULL;
 
 	GEM_BUG_ON(i915_request_signaled(rq));
 
+	/* As soon as the request is completed, it may be retired */
+	rq = i915_request_get(rq);
+
 	i915_request_set_error_once(rq, -EIO);
 	i915_request_mark_complete(rq);
+
+	return rq;
 }
 
 bool __i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 1bfe214a47e9..c0bd4cb8786a 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -311,7 +311,7 @@ i915_request_create(struct intel_context *ce);
 
 void __i915_request_skip(struct i915_request *rq);
 void i915_request_set_error_once(struct i915_request *rq, int error);
-void i915_request_mark_eio(struct i915_request *rq);
+struct i915_request *i915_request_mark_eio(struct i915_request *rq);
 
 struct i915_request *__i915_request_commit(struct i915_request *request);
 void __i915_request_queue(struct i915_request *rq,
-- 
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 ` Chris Wilson [this message]
2021-02-02  9:55   ` [Intel-gfx] [PATCH 04/57] drm/i915: Protect against request freeing during cancellation on wedging 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 ` [Intel-gfx] [PATCH 43/57] drm/i915/gt: Delay taking irqoff for execlists submission Chris Wilson
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=20210201085715.27435-4-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