On Wed, Jun 25, 2014 at 07:05:08PM +0200, Paolo Bonzini wrote: > Il 25/06/2014 18:56, Nikolay Nikolaev ha scritto: > >>> I understand now what you mean. Yeah, the format should be changed > >>> to include the offset (why does vhost-user need the ua at all? > >The vring addresses are QEMU UA addresses. Of course vhost-user can > >translate them to guest physical before sending the message. > > Yeah, that looks like a good idea. > > Paolo
Is this is must? Seems too close to hard freeze to change the protocol ... Does vhost-user actually work if you use a UA outside guest memory? If not, ok, but maybe add some capability so this can be discovered during init. -- MST
