On 18 September 2013 20:26, Paolo Bonzini <pbonz...@redhat.com> wrote: > But does guest code actually care? In many cases, I suspect that > sticking a smp_rmb() in the read side of "unlocked" register accesses, > and a smp_wmb() in the write side, will do just fine. And add a > compatibility property to place a device back under the BQL for guests > that have problems.
Yuck. This sounds like a recipe for spending the next five years debugging subtle race conditions. We need to continue to support the semantics that the architecture and hardware specs define for memory access orderings to emulated devices. -- PMM