Hey Gerd, This probably doesn't matter yet, but they virtgpu_vq buffer allocation code you added isn't threadsafe.
I'm not sure what was wrong with the original code I wrote, you never contacted me with reasons for rewriting it, but the Linux kmalloc isn't that slow, but if we want some form of cached allocator you probably should just use kmem_cache_create instead of what you have there. The second any code hits that from two threads its going to explode as the free buffers list isn't protected with a lock of any kind, I know userspace might not be able to hit this at present, but this is a big problem when we add the 3D code. Dave.
