[Intel-gfx] [PATCH 06/59] drm/i915: i915_add_request must not fail

John.C.Harrison at Intel.com John.C.Harrison at Intel.com
Thu Mar 19 05:30:11 PDT 2015


From: John Harrison <John.C.Harrison at Intel.com>

The i915_add_request() function is called to keep track of work that has been
written to the ring buffer. It adds epilogue commands to track progress (seqno
updates and such), moves the request structure onto the right list and other
such house keeping tasks. However, the work itself has already been written to
the ring and will get executed whether or not the add request call succeeds. So
no matter what goes wrong, there isn't a whole lot of point in failing the call.

At the moment, this is fine(ish). If the add request does bail early on and not
do the housekeeping, the request will still float around in the
ring->outstanding_lazy_request field and be picked up next time. It means
multiple pieces of work will be tagged as the same request and driver can't
actually wait for the first piece of work until something else has been
submitted. But it all sort of hangs together.

This patch series is all about removing the OLR and guaranteeing that each piece
of work gets its own personal request. That means that there is no more
'hoovering up of forgotten requests'. If the request does not get tracked then
it will be leaked. Thus the add request call _must_ not fail. The previous patch
should have already ensured that it _will_ not fail by removing the potential
for running out of ring space. This patch enforces the rule by actually removing
the early exit paths and the return code.

Note that if something does manage to fail and the epilogue commands don't get
written to the ring, the driver will still hang together. The request will be
added to the tracking lists. And as in the old case, any subsequent work will
generate a new seqno which will suffice for marking the old one as complete.

For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison at Intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h              |    6 ++--
 drivers/gpu/drm/i915/i915_gem.c              |   44 +++++++++++---------------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c   |    2 +-
 drivers/gpu/drm/i915/i915_gem_render_state.c |    2 +-
 drivers/gpu/drm/i915/intel_lrc.c             |    2 +-
 drivers/gpu/drm/i915/intel_overlay.c         |   10 +++---
 drivers/gpu/drm/i915/intel_ringbuffer.c      |    8 ++---
 7 files changed, 32 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fe6446d..7b36d4a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2748,9 +2748,9 @@ void i915_gem_init_swizzling(struct drm_device *dev);
 void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int __must_check i915_gpu_idle(struct drm_device *dev);
 int __must_check i915_gem_suspend(struct drm_device *dev);
-int __i915_add_request(struct intel_engine_cs *ring,
-		       struct drm_file *file,
-		       struct drm_i915_gem_object *batch_obj);
+void __i915_add_request(struct intel_engine_cs *ring,
+			struct drm_file *file,
+			struct drm_i915_gem_object *batch_obj);
 #define i915_add_request(ring) \
 	__i915_add_request(ring, NULL, NULL)
 int __i915_wait_request(struct drm_i915_gem_request *req,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fc383fc..cdf1c9d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1159,15 +1159,12 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
 int
 i915_gem_check_olr(struct drm_i915_gem_request *req)
 {
-	int ret;
-
 	WARN_ON(!mutex_is_locked(&req->ring->dev->struct_mutex));
 
-	ret = 0;
 	if (req == req->ring->outstanding_lazy_request)
-		ret = i915_add_request(req->ring);
+		i915_add_request(req->ring);
 
-	return ret;
+	return 0;
 }
 
 static void fake_irq(unsigned long data)
@@ -2325,9 +2322,14 @@ i915_gem_get_seqno(struct drm_device *dev, u32 *seqno)
 	return 0;
 }
 
-int __i915_add_request(struct intel_engine_cs *ring,
-		       struct drm_file *file,
-		       struct drm_i915_gem_object *obj)
+/*
+ * NB: This function is not allowed to fail. Doing so would mean the the
+ * request is not being tracked for completion but the work itself is
+ * going to happen on the hardware. This would be a Bad Thing(tm).
+ */
+void __i915_add_request(struct intel_engine_cs *ring,
+			struct drm_file *file,
+			struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *request;
@@ -2337,7 +2339,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 
 	request = ring->outstanding_lazy_request;
 	if (WARN_ON(request == NULL))
-		return -ENOMEM;
+		return;
 
 	if (i915.enable_execlists) {
 		ringbuf = request->ctx->engine[ring->id].ringbuf;
@@ -2359,15 +2361,12 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 * is that the flush _must_ happen before the next request, no matter
 	 * what.
 	 */
-	if (i915.enable_execlists) {
+	if (i915.enable_execlists)
 		ret = logical_ring_flush_all_caches(ringbuf, request->ctx);
-		if (ret)
-			return ret;
-	} else {
+	else
 		ret = intel_ring_flush_all_caches(ring);
-		if (ret)
-			return ret;
-	}
+	/* Not allowed to fail! */
+	WARN_ON(ret);
 
 	/* Record the position of the start of the request so that
 	 * should we detect the updated seqno part-way through the
@@ -2376,15 +2375,12 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	 */
 	request->postfix = intel_ring_get_tail(ringbuf);
 
-	if (i915.enable_execlists) {
+	if (i915.enable_execlists)
 		ret = ring->emit_request(ringbuf, request);
-		if (ret)
-			return ret;
-	} else {
+	else
 		ret = ring->add_request(ring);
-		if (ret)
-			return ret;
-	}
+	/* Not allowed to fail! */
+	WARN_ON(ret);
 
 	request->head = request_start;
 	request->tail = intel_ring_get_tail(ringbuf);
@@ -2435,8 +2431,6 @@ int __i915_add_request(struct intel_engine_cs *ring,
 
 	/* Sanity check that the reserved size was large enough. */
 	intel_ring_reserved_space_end(ringbuf);
-
-	return 0;
 }
 
 static inline void
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 38e2178..1bb237c 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1063,7 +1063,7 @@ i915_gem_execbuffer_retire_commands(struct drm_device *dev,
 	ring->gpu_caches_dirty = true;
 
 	/* Add a breadcrumb for the completion of the batch buffer */
-	(void)__i915_add_request(ring, file, obj);
+	__i915_add_request(ring, file, obj);
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 521548a..ce4788f 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -173,7 +173,7 @@ int i915_gem_render_state_init(struct intel_engine_cs *ring)
 
 	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
 
-	ret = __i915_add_request(ring, NULL, so.obj);
+	__i915_add_request(ring, NULL, so.obj);
 	/* __i915_add_request moves object to inactive if it fails */
 out:
 	i915_gem_render_state_fini(&so);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index bdbdcae..8d48761 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1352,7 +1352,7 @@ static int intel_lr_context_render_state_init(struct intel_engine_cs *ring,
 
 	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
 
-	ret = __i915_add_request(ring, file, so.obj);
+	__i915_add_request(ring, file, so.obj);
 	/* intel_logical_ring_add_request moves object to inactive if it
 	 * fails */
 out:
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 823d1d9..6af2581 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -219,17 +219,15 @@ static int intel_overlay_do_wait_request(struct intel_overlay *overlay,
 	BUG_ON(overlay->last_flip_req);
 	i915_gem_request_assign(&overlay->last_flip_req,
 					     ring->outstanding_lazy_request);
-	ret = i915_add_request(ring);
-	if (ret)
-		return ret;
+	i915_add_request(ring);
 
 	overlay->flip_tail = tail;
 	ret = i915_wait_request(overlay->last_flip_req);
 	if (ret)
 		return ret;
 	i915_gem_retire_requests(dev);
-
 	i915_gem_request_assign(&overlay->last_flip_req, NULL);
+
 	return 0;
 }
 
@@ -291,7 +289,9 @@ static int intel_overlay_continue(struct intel_overlay *overlay,
 	WARN_ON(overlay->last_flip_req);
 	i915_gem_request_assign(&overlay->last_flip_req,
 					     ring->outstanding_lazy_request);
-	return i915_add_request(ring);
+	i915_add_request(ring);
+
+	return 0;
 }
 
 static void intel_overlay_release_old_vid_tail(struct intel_overlay *overlay)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 9075008..1a7ed8b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2172,14 +2172,10 @@ static int intel_wrap_ring_buffer(struct intel_engine_cs *ring)
 int intel_ring_idle(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_request *req;
-	int ret;
 
 	/* We need to add any requests required to flush the objects and ring */
-	if (ring->outstanding_lazy_request) {
-		ret = i915_add_request(ring);
-		if (ret)
-			return ret;
-	}
+	if (ring->outstanding_lazy_request)
+		i915_add_request(ring);
 
 	/* Wait upon the last request to be completed */
 	if (list_empty(&ring->request_list))
-- 
1.7.9.5



More information about the Intel-gfx mailing list