Hi On Wed, Feb 28, 2018 at 6:17 PM, Michael S. Tsirkin <m...@redhat.com> wrote: > On Wed, Feb 28, 2018 at 04:41:51PM +0100, Marc-André Lureau wrote: >> I don't know if it's always safe to enable dma in read_raw(), how >> could we know? Is there a check we could use to choose one or ther >> other (and thus avoiding explicit dma/readfn argument)? > > IMHO the way to go is not to try to do zero copy. > Allocate a buffer and DMA there, then copy.
Sounds fine to me, I'll resend this patch separately if the rest from v16 is applied. thanks
