On 11/22/14 11:18, Christoffer Dall wrote: > On Fri, Nov 21, 2014 at 05:50:43PM -0800, Mario Smarduch wrote: >> But virtio writes to guest memory directly and that appears to >> work just fine. I read that code sometime back, and will need to revisit. >> > In any case, that's a QEMU implementation issue and nothing the kernel > needs to be concerned with. (Let's call it "qemu implementation detail" -- there's no "issue". The reason virtio works is not by incident, it has a known cause. As confirmed by Peter, there's no problem with the virtio buffers because the guest doesn't mark them as uncacheable, so *all* accesses go through the dcache.) Thanks Laszlo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
