hmm, random though..

should we define CPU_PREP/CPU_FINI type ioctl's?

At least in the GStreamer case, we could cache the userspace mmap'ing,
and use the extra ioctls so the kernel side would know when cache
clean/invalidate is needed.  That would be a bit more efficient than
forcing userspace to map/unmap all the time, and could hook into
sync-objects of the allocator in cases where you have CPU access after
GPU renders to a buffer..

BR,
-R

<snip>