From mboxrd@z Thu Jan  1 00:00:00 1970
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Subject: Re: [virtio-dev] Re: VIRTIO - compatibility with
 different virtualization solutions
Date: Tue, 25 Feb 2014 16:12:47 -0500
Message-ID: <20140225211247.GC5827@phenom.dumpdata.com>
References: <20140217132331.GA3441@olila.local.net-space.pl>
	<87vbwcaqxe.fsf@rustcorp.com.au>
	<1392804568.23084.112.camel@kazak.uk.xensource.com>
	<8761oab4y7.fsf@rustcorp.com.au>
	<20140220203704.GG3441@olila.local.net-space.pl>
	<8761o99tft.fsf@rustcorp.com.au>
	<CA+aC4kt1HcH8dryqDTxcv0rNWBx8Ed4F7VNVjuHCkAFSWC+Ktw@mail.gmail.com>
	<87vbw458jr.fsf@rustcorp.com.au>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
Received: from mail6.bemta5.messagelabs.com ([195.245.231.135])
	by lists.xen.org with esmtp (Exim 4.72)
	(envelope-from <konrad.wilk@oracle.com>) id 1WJN6q-0004GR-Fb
	for xen-devel@lists.xenproject.org; Fri, 28 Feb 2014 13:04:12 +0000
Content-Disposition: inline
In-Reply-To: <87vbw458jr.fsf@rustcorp.com.au>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: Rusty Russell <rusty@au1.ibm.com>
Cc: virtio-dev@lists.oasis-open.org, Wei Liu <wei.liu2@citrix.com>, Ian Campbell <Ian.Campbell@citrix.com>, Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Daniel Kiper <daniel.kiper@oracle.com>, ian@bromium.com, Anthony Liguori <anthony@codemonkey.ws>, sasha.levin@oracle.com, xen-devel@lists.xenproject.org
List-Id: xen-devel@lists.xenproject.org

On Tue, Feb 25, 2014 at 11:10:24AM +1030, Rusty Russell wrote:
> Anthony Liguori <anthony@codemonkey.ws> writes:
> > On Thu, Feb 20, 2014 at 4:54 PM, Rusty Russell <rusty@au1.ibm.com> wrote:
> >> On the other hand, if we wanted a more Xen-like setup, it would looke
> >> like this:
> >>
> >> 1) Abstract away the "physical addresses" to "handles" in the standard,
> >>    and allow some platform-specific mapping setup and teardown.
> >
> > At the risk of beating a dead horse, passing handles (grant
> > references) is going to be slow.
> ...
> > I really think the best paths forward for virtio on Xen are either (1)
> > reject the memory isolation thing and leave things as is or (2) assume
> > bounce buffering at the transport layer (by using the PCI DMA API).
> 
> Xen can get memory isolation back by doing the copy in the hypervisor.
> I've always liked that approach because it doesn't alter the guest
> semantics, but it's very different from what Xen does now.

It could. But why do it - the backend can choose it as well to do it
and perhaps even do some translation of the payload as it sees fit.

Or it can map it - and if using DPDK for example - one has
memory pages shared between the domains all the time - where you
just need to map once.

> 
> Cheers,
> Rusty.
>