On Wed, Oct 28, 2015 at 11:22:52AM +0900, David Woodhouse wrote: > On Wed, 2015-10-28 at 11:15 +0900, Joerg Roedel wrote: > > I think a good test for that is to boot a virtio kvm-guest with > > swiotlb=force and see if it still works. > > That's useful but doesn't cover the cases where dma_wmb() is needed, > right? > > We should make sure we're handling descriptors properly as we would for > real hardware, and ensuring that addresses etc. are written to the > descriptor (and a write barrier occurs) *before* the bit is set which > tells the 'hardware' that it owns that descriptor. Hmm, good question. The virtio code has virtio_rmb/wmb and should already call it in the right places. The virtio-barriers default to rmb()/wmb() unless weak_barriers is set, in which case it calls dma_rmb()/wmb(), just a compiler barrier on x86. And weak_barriers is set by the virtio drivers when creating the queue, and the drivers should know what they are doing. Saying this, I think the virtio-drivers should already get this right. Joerg -- 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
