drm/i915/bdw: Help out the ctx switch interrupt handler
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@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0f1b6b2..6f6c5a9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -392,10 +392,10 @@
struct intel_context *to,
u32 tail)
{
- struct intel_ctx_submit_request *req = NULL;
+ struct intel_ctx_submit_request *req = NULL, *cursor;
struct drm_i915_private *dev_priv = ring->dev->dev_private;
unsigned long flags;
- bool was_empty;
+ int num_elements = 0;
req = kzalloc(sizeof(*req), GFP_KERNEL);
if (req == NULL)
@@ -410,9 +410,27 @@
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 intel_ctx_submit_request *tail_req;
+
+ tail_req = list_last_entry(&ring->execlist_queue,
+ struct intel_ctx_submit_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)
execlists_context_unqueue(ring);
spin_unlock_irqrestore(&ring->execlist_lock, flags);