intel: Fix drm_intel_gem_bo_wait_rendering to wait for read-only usage too.

Both the consumers of this API (sync objects and client throttling)
were expecting this behavior.  The kernel used to actually behave the
desired (but incorrect) way for us anyway, but that got fixed a while
back.

diff --git a/intel/intel_bufmgr_gem.c b/intel/intel_bufmgr_gem.c
index 2b7bd47..aea7bdb 100644 (file)
--- a/intel/intel_bufmgr_gem.c
+++ b/intel/intel_bufmgr_gem.c
@@ -1204,11 +1204,11 @@ drm_intel_gem_bo_get_subdata(drm_intel_bo *bo, unsigned long offset,
        return ret;
 }
 
-/** Waits for all GPU rendering to the object to have completed. */
+/** Waits for all GPU rendering with the object to have completed. */
 static void
 drm_intel_gem_bo_wait_rendering(drm_intel_bo *bo)
 {
-       drm_intel_gem_bo_start_gtt_access(bo, 0);
+       drm_intel_gem_bo_start_gtt_access(bo, 1);
 }
 
 /**