diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ce03fd5b3f5b59abc9f13982f2c6bae5222916ca..fd6362ea865c0e389e6123f0f896dce4f867d8a0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -808,6 +808,9 @@ void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
 int i915_gem_do_init(struct drm_device *dev, unsigned long start,
 		     unsigned long end);
 int i915_gem_idle(struct drm_device *dev);
+uint32_t i915_add_request(struct drm_device *dev, struct drm_file *file_priv,
+			  uint32_t flush_domains);
+int i915_do_wait_request(struct drm_device *dev, uint32_t seqno, int interruptible);
 int i915_lp_ring_sync(struct drm_device *dev);
 int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
 int i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 7d1e9adf0f4c32fc79b87bfab0e0f85cb6bb74f5..5e579a41b6ad23514b84707c87b1564390aa2158 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1583,7 +1583,7 @@ i915_gem_object_move_to_inactive(struct drm_gem_object *obj)
  *
  * Returned sequence numbers are nonzero on success.
  */
-static uint32_t
+uint32_t
 i915_add_request(struct drm_device *dev, struct drm_file *file_priv,
 		 uint32_t flush_domains)
 {
@@ -1820,7 +1820,7 @@ i915_gem_retire_work_handler(struct work_struct *work)
 	mutex_unlock(&dev->struct_mutex);
 }
 
-static int
+int
 i915_do_wait_request(struct drm_device *dev, uint32_t seqno, int interruptible)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c9b1b97ab792328bde00af99c9b6a1a2e4dcc351..5b503cb793ba24b05efe8842c3620a8cdec80007 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -126,7 +126,9 @@ struct intel_overlay {
 	u32 flip_addr;
 	struct drm_i915_gem_object *reg_bo;
 	void *virt_addr;
+	/* flip handling */
 	int hw_wedged;
+	uint32_t last_flip_req;
 };
 
 struct intel_crtc {
diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c
index 4e88abb423b084111ff46020f73af555266ca222..85e07e4459ceed9931497a7280f4b64238d7d62d 100644
--- a/drivers/gpu/drm/i915/intel_overlay.c
+++ b/drivers/gpu/drm/i915/intel_overlay.c
@@ -251,7 +251,6 @@ static void intel_overlay_continue(struct intel_overlay *overlay,
         drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 flip_addr = overlay->flip_addr;
 	u32 tmp;
-	int ret;
 	RING_LOCALS;
 
 	BUG_ON(!overlay->active);
@@ -264,11 +263,40 @@ static void intel_overlay_continue(struct intel_overlay *overlay,
 	if (tmp & (1 << 17))
 		DRM_DEBUG("overlay underrun, DOVSTA: %x\n", tmp);
 
-	BEGIN_LP_RING(6);
+	BEGIN_LP_RING(4);
 	OUT_RING(MI_FLUSH);
 	OUT_RING(MI_NOOP);
 	OUT_RING(MI_OVERLAY_FLIP | MI_OVERLAY_CONTINUE);
 	OUT_RING(flip_addr);
+        ADVANCE_LP_RING();
+
+	overlay->last_flip_req = i915_add_request(dev, NULL, 0);
+}
+
+static int intel_overlay_wait_flip(struct intel_overlay *overlay)
+{
+	struct drm_device *dev = overlay->dev;
+        drm_i915_private_t *dev_priv = dev->dev_private;
+	int ret;
+	u32 tmp;
+	RING_LOCALS;
+
+	if (overlay->last_flip_req != 0) {
+		ret = i915_do_wait_request(dev, overlay->last_flip_req, 0);
+
+		if (ret != 0)
+			return ret;
+
+		overlay->last_flip_req = 0;
+
+		tmp = I915_READ(ISR);
+
+		if (!(tmp & I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT))
+			return 0;
+	}
+
+	/* synchronous slowpath */
+	BEGIN_LP_RING(2);
         OUT_RING(MI_WAIT_FOR_EVENT | MI_WAIT_FOR_OVERLAY_FLIP);
         OUT_RING(MI_NOOP);
         ADVANCE_LP_RING();
@@ -279,13 +307,8 @@ static void intel_overlay_continue(struct intel_overlay *overlay,
 		DRM_ERROR("intel overlay: ring sync failed, hw likely wedged\n");
 		overlay->hw_wedged = 1;
 	}
-}
 
-static int intel_overlay_wait_flip(struct intel_overlay *overlay)
-{
-	/* don't overcomplicate things for now with asynchronous operations
-	 * see comment above */
-	return 0;
+	return ret;
 }
 
 /* overlay needs to be disabled in OCMD reg */
@@ -344,7 +367,9 @@ static int intel_overlay_off(struct intel_overlay *overlay)
 	return ret;
 }
 
-/* wait for pending overlay flip and release old frame */
+/* Wait for pending overlay flip and release old frame.
+ * Needs to be called before the overlay register are changed
+ * via intel_overlay_(un)map_regs_atomic */
 static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 {
 	int ret;