On Fri, Apr 15, 2011 at 07:04:13AM +0100, Chris Wilson wrote: > We need to perform a few operations in order to move the object into the > display plane (where it can be accessed coherently by the display > engine) that are important for future safety to forbid whilst pinned. As a > result, we want to need to perform some of operations before pinning, > but some are required once we have been bound into the GTT. So combine > the pinning performed by all the callers with set_to_display_plane(), so > this complication is contained within the single function.
The latest version from -next-proposed with the fail_unpin: hunk reinstated does indeed get rid of the cacheline dirt I've seen on my ilk. But in that version you're calling set_to_gtt_domain which calls flush_gpu_write_domain and then waits synchronously when obj->pending_gpu_write is set. Which is almost guaranteed to happen for pageflips. -Daniel -- Daniel Vetter Mail: dan...@ffwll.ch Mobile: +41 (0)79 365 57 48 _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
