If we have multiple waiters, we may find that many complete on the same
wake up. If we first inspect the seqno from the CPU cache, we may reduce
the number of heavyweight coherent seqno reads we require.
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_drv.h | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4a71f4e9a97a..4ddb9ff319cb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3918,6 +3918,12 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
{
struct intel_engine_cs *engine = req->engine;
+ /* Before we do the heavier coherent read of the seqno,
+ * check the value (hopefully) in the CPU cacheline.
+ */
+ if (i915_gem_request_completed(req))
+ return true;
+
/* Ensure our read of the seqno is coherent so that we
* do not "miss an interrupt" (i.e. if this is the last
* request and the seqno write from the GPU is not visible
@@ -3929,11 +3935,11 @@ static inline bool __i915_request_irq_complete(struct drm_i915_gem_request *req)
* but it is easier and safer to do it every time the waiter
* is woken.
*/
- if (engine->irq_seqno_barrier)
+ if (engine->irq_seqno_barrier) {
engine->irq_seqno_barrier(engine);
-
- if (i915_gem_request_completed(req))
- return true;
+ if (i915_gem_request_completed(req))
+ return true;
+ }
/* We need to check whether any gpu reset happened in between
* the request being submitted and now. If a reset has occurred,
--
2.8.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
