[Intel-gfx] [PATCH] drm/i915: Wrap engine->schedule in RCU locks for set-wedge protection

[Chris Wilson]

Similar to the staging around handling of engine->submit_request, we
need to stop adding to the execlists->queue prior to calling
engine->cancel_requests. cancel_requests will move requests from the
queue onto the timeline, so if we add a request onto the queue after that
point, it will be lost.

Fixes: af7a8ffad9c5 ("drm/i915: Use rcu instead of stop_machine in set_wedged")
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c     | 13 +++++++------
 drivers/gpu/drm/i915/i915_request.c |  2 ++
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a5bd07338b46..8d913d833ab9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -471,10 +471,11 @@ static void __fence_set_priority(struct dma_fence *fence, int prio)
 
 	rq = to_request(fence);
 	engine = rq->engine;
-	if (!engine->schedule)
-		return;
 
-	engine->schedule(rq, prio);
+	rcu_read_lock();
+	if (engine->schedule)
+		engine->schedule(rq, prio);
+	rcu_read_unlock();
 }
 
 static void fence_set_priority(struct dma_fence *fence, int prio)
@@ -3214,8 +3215,11 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 	 */
 	for_each_engine(engine, i915, id) {
 		i915_gem_reset_prepare_engine(engine);
+
 		engine->submit_request = nop_submit_request;
+		engine->schedule = NULL;
 	}
+	i915->caps.scheduler = 0;
 
 	/*
 	 * Make sure no one is running the old callback before we proceed with
@@ -3233,11 +3237,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
 		 * start to complete all requests.
 		 */
 		engine->submit_request = nop_complete_submit_request;
-		engine->schedule = NULL;
 	}
 
-	i915->caps.scheduler = 0;
-
 	/*
 	 * Make sure no request can slip through without getting completed by
 	 * either this call here to intel_engine_init_global_seqno, or the one
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 2265bb8ff4fa..59a87afd83b6 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1081,8 +1081,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	 * decide whether to preempt the entire chain so that it is ready to
 	 * run at the earliest possible convenience.
 	 */
+	rcu_read_lock();
 	if (engine->schedule)
 		engine->schedule(request, request->ctx->priority);
+	rcu_read_unlock();
 
 	local_bh_disable();
 	i915_sw_fence_commit(&request->submit);
-- 
2.16.2