On 04/16/10 12:18, Paolo Bonzini wrote:
I'd just use __sync_fetch_and_or here.Good idea. I think we can zap the memory barrier and fix a small race while being at it, see the incremental fix below.Not sure about the memory barrier semantics of __sync_* (rth?), but besides that the patch seems like a good idea.
I think a memory barrier isn't needed there. We don't touch anything shared beside int_pending which is only accessed using the sync op (after applying the patch).
cheers, Gerd
