[Intel-gfx] [PATCH 49/50] drm/i915/bdw: Help out the ctx switch interrupt handler

[oscar.mateo at intel.com]

From: Oscar Mateo <oscar.mateo at intel.com>

If we receive a storm of requests for the same context (see gem_storedw_loop_*)
we might end up iterating over too many elements in interrupt time, looking for
contexts to squash together. Instead, share the burden by giving more
intelligence to the queue function. At most, the interrupt will iterate over
three elements.

Signed-off-by: Oscar Mateo <oscar.mateo at intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d9edd10..0aad721 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -410,9 +410,11 @@ int gen8_switch_context_queue(struct intel_engine *ring,
 			      struct i915_hw_context *to,
 			      u32 tail)
 {
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_request *req = NULL;
 	unsigned long flags;
-	bool was_empty;
+	struct drm_i915_gem_request *cursor;
+	int num_elements = 0;
 
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
 	if (req == NULL)
@@ -425,9 +427,24 @@ int gen8_switch_context_queue(struct intel_engine *ring,
 
 	spin_lock_irqsave(&ring->execlist_lock, flags);
 
-	was_empty = list_empty(&ring->execlist_queue);
+	list_for_each_entry(cursor, &ring->execlist_queue, execlist_link)
+		if (++num_elements > 2)
+			break;
+
+	if (num_elements > 2) {
+		struct drm_i915_gem_request *tail_req =
+				list_last_entry(&ring->execlist_queue,
+					struct drm_i915_gem_request, execlist_link);
+		if (to == tail_req->ctx) {
+			WARN(tail_req->elsp_submitted != 0,
+					"More than 2 already-submitted reqs queued\n");
+			list_del(&tail_req->execlist_link);
+			queue_work(dev_priv->wq, &tail_req->work);
+		}
+	}
+
 	list_add_tail(&req->execlist_link, &ring->execlist_queue);
-	if (was_empty)
+	if (num_elements == 0)
 		gen8_switch_context_unqueue(ring);
 
 	spin_unlock_irqrestore(&ring->execlist_lock, flags);
-- 
1.9.0