[Intel-gfx] [RFC 1/3] execlist queue items to hold ptr/ref to gem_request

[Nick Hoath]

Add a reference and pointer from the execlist queue item to the associated
gem request. For execlist requests that don't have a request, create one
as a placeholder.

This patchset requires John Harrison's "Replace seqno values with request structures"
patchset.

Issue: VIZ-4274
Signed-off-by: Nick Hoath <nicholas.hoath at intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c | 31 +++++++++++++++++++++++++------
 drivers/gpu/drm/i915/intel_lrc.h |  5 ++++-
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 09d548d..8f301ac 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -521,6 +521,7 @@ static void execlists_free_request_task(struct work_struct *work)
 
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_unreference(req->ctx);
+	i915_gem_request_unreference(req->request);
 	mutex_unlock(&dev->struct_mutex);
 
 	kfree(req);
@@ -528,7 +529,8 @@ static void execlists_free_request_task(struct work_struct *work)
 
 static int execlists_context_queue(struct intel_engine_cs *ring,
 				   struct intel_context *to,
-				   u32 tail)
+				   u32 tail,
+				   struct drm_i915_gem_request *request)
 {
 	struct intel_ctx_submit_request *req = NULL, *cursor;
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
@@ -544,6 +546,22 @@ static int execlists_context_queue(struct intel_engine_cs *ring,
 	req->tail = tail;
 	INIT_WORK(&req->work, execlists_free_request_task);
 
+	if(!request)
+	{
+		/*
+		 * If there isn't a request associated with this submission,
+		 * create one as a temporary holder.
+		 */
+		WARN(1, "execlist context submission without request");
+		request = kzalloc(sizeof(*request), GFP_KERNEL);
+		if (request == NULL)
+			return -ENOMEM;
+		request->ctx = to;
+		request->ring = ring;
+	}
+	req->request = request;
+	i915_gem_request_reference(request);
+
 	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irqsave(&ring->execlist_lock, flags);
@@ -778,7 +796,8 @@ int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf)
  * on a queue waiting for the ELSP to be ready to accept a new context submission. At that
  * point, the tail *inside* the context is updated and the ELSP written to.
  */
-void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf)
+void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+					   struct drm_i915_gem_request *request)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	struct intel_context *ctx = ringbuf->FIXME_lrc_ctx;
@@ -788,7 +807,7 @@ void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf)
 	if (intel_ring_stopped(ring))
 		return;
 
-	execlists_context_queue(ring, ctx, ringbuf->tail);
+	execlists_context_queue(ring, ctx, ringbuf->tail, request);
 }
 
 static int logical_ring_alloc_request(struct intel_engine_cs *ring,
@@ -876,7 +895,7 @@ static int logical_ring_wait_for_space(struct intel_ringbuffer *ringbuf,
 		return ret;
 
 	/* Force the context submission in case we have been skipping it */
-	intel_logical_ring_advance_and_submit(ringbuf);
+	intel_logical_ring_advance_and_submit(ringbuf, NULL);
 
 	/* With GEM the hangcheck timer should kick us out of the loop,
 	 * leaving it early runs the risk of corrupting GEM state (due
@@ -1183,7 +1202,7 @@ static void gen8_set_seqno(struct intel_engine_cs *ring, u32 seqno)
 	intel_write_status_page(ring, I915_GEM_HWS_INDEX, seqno);
 }
 
-static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
+static int gen8_emit_request(struct intel_ringbuffer *ringbuf, struct drm_i915_gem_request *request)
 {
 	struct intel_engine_cs *ring = ringbuf->ring;
 	u32 cmd;
@@ -1205,7 +1224,7 @@ static int gen8_emit_request(struct intel_ringbuffer *ringbuf)
 		i915_gem_request_get_seqno(ring->outstanding_lazy_request));
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
 	intel_logical_ring_emit(ringbuf, MI_NOOP);
-	intel_logical_ring_advance_and_submit(ringbuf);
+	intel_logical_ring_advance_and_submit(ringbuf, request);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 33c3b4b..6f81669 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -37,7 +37,8 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *ring);
 int intel_logical_rings_init(struct drm_device *dev);
 
 int logical_ring_flush_all_caches(struct intel_ringbuffer *ringbuf);
-void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf);
+void intel_logical_ring_advance_and_submit(struct intel_ringbuffer *ringbuf,
+					   struct drm_i915_gem_request *request);
 /**
  * intel_logical_ring_advance() - advance the ringbuffer tail
  * @ringbuf: Ringbuffer to advance.
@@ -107,6 +108,8 @@ struct intel_ctx_submit_request {
 	struct work_struct work;
 
 	int elsp_submitted;
+
+	struct drm_i915_gem_request *request;
 };
 
 void intel_execlists_handle_ctx_events(struct intel_engine_cs *ring);
-- 
2.1.1