@@ -10224,6 +10224,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
enum pipe pipe = intel_crtc->pipe;
struct intel_unpin_work *work;
struct intel_engine_cs *ring;
+ bool mmio_flip;
int ret;
/*
@@ -10321,15 +10322,23 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
ring = &dev_priv->ring[RCS];
}
+ mmio_flip = use_mmio_flip(ring, obj);
+
+ /* When using CS flips, we want to emit semaphores between rings.
+ * However, when using mmio flips we will create a task to do the
+ * synchronisation, so all we want here is to pin the framebuffer
+ * into the display plane and skip any waits.
+ */
ret = intel_pin_and_fence_fb_obj(crtc->primary, fb,
- crtc->primary->state, ring);
+ crtc->primary->state,
+ mmio_flip ? i915_gem_request_get_ring(obj->last_read_req) : ring);
if (ret)
goto cleanup_pending;
work->gtt_offset = intel_plane_obj_offset(to_intel_plane(primary), obj)
+ intel_crtc->dspaddr_offset;
- if (use_mmio_flip(ring, obj)) {
+ if (mmio_flip) {
ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
page_flip_flags);
if (ret)
Currently we emit semaphore synchronisation as if we were going to flip using the target CS engine, but we then change our minds and do the flip using the CPU. Consequently we write instructions to the ring but never use them - even to the point of filling that ring up entirely and never submitting a request. The wrinkle in the ointment is that we have to tell a white lie to pin-to-display for it to skip the synchronisation for mmioflips as we will create a task specifically for that slow synchronisation. An oddity of note is the discrepancy in requests that we tell to pin-display to serialise to and that we then eventually wait upon. This is due to a limitation in the i915_gem_object_sync() routine that will be lifted later. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> --- drivers/gpu/drm/i915/intel_display.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)