[03/11] drm/i915: Prevent using semaphores to chain up to external fences
diff mbox series

Message ID 20200508081630.13882-3-chris@chris-wilson.co.uk
State New
Headers show
Series
  • [01/11] drm/i915: Ignore submit-fences on the same timeline
Related show

Commit Message

Chris Wilson May 8, 2020, 8:16 a.m. UTC
The downside of using semaphores is that we lose metadata passing
along the signaling chain. This is particularly nasty when we
need to pass along a fatal error such as EFAULT or EDEADLK. For
fatal errors we want to scrub the request before it is executed,
which means that we cannot preload the request onto HW and have
it wait upon a semaphore.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_request.c         | 26 +++++++++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler_types.h |  1 +
 2 files changed, 27 insertions(+)

Patch
diff mbox series

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 94189c7d43cd..f0f9393e2ade 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1002,6 +1002,15 @@  emit_semaphore_wait(struct i915_request *to,
 	if (!rcu_access_pointer(from->hwsp_cacheline))
 		goto await_fence;
 
+	/*
+	 * If this or its dependents are waiting on an external fence
+	 * that may fail catastrophically, then we want to avoid using
+	 * sempahores as they bypass the fence signaling metadata, and we
+	 * lose the fence->error propagation.
+	 */
+	if (from->sched.flags & I915_SCHED_HAS_EXTERNAL_CHAIN)
+		goto await_fence;
+
 	/* Just emit the first semaphore we see as request space is limited. */
 	if (already_busywaiting(to) & mask)
 		goto await_fence;
@@ -1064,12 +1073,29 @@  i915_request_await_request(struct i915_request *to, struct i915_request *from)
 			return ret;
 	}
 
+	if (from->sched.flags & I915_SCHED_HAS_EXTERNAL_CHAIN)
+		to->sched.flags |= I915_SCHED_HAS_EXTERNAL_CHAIN;
+
 	return 0;
 }
 
+static void mark_external(struct i915_request *rq)
+{
+	/*
+	 * The downside of using semaphores is that we lose metadata passing
+	 * along the signaling chain. This is particularly nasty when we
+	 * need to pass along a fatal error such as EFAULT or EDEADLK. For
+	 * fatal errors we want to scrub the request before it is executed,
+	 * which means that we cannot preload the request onto HW and have
+	 * it wait upon a semaphore.
+	 */
+	rq->sched.flags |= I915_SCHED_HAS_EXTERNAL_CHAIN;
+}
+
 static int
 i915_request_await_external(struct i915_request *rq, struct dma_fence *fence)
 {
+	mark_external(rq);
 	return i915_sw_fence_await_dma_fence(&rq->submit, fence,
 					     fence->context ? I915_FENCE_TIMEOUT : 0,
 					     I915_FENCE_GFP);
diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index 7186875088a0..6ab2c5289bed 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -66,6 +66,7 @@  struct i915_sched_node {
 	struct i915_sched_attr attr;
 	unsigned int flags;
 #define I915_SCHED_HAS_SEMAPHORE_CHAIN	BIT(0)
+#define I915_SCHED_HAS_EXTERNAL_CHAIN	BIT(1)
 	intel_engine_mask_t semaphores;
 };