From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:49297)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <mst@redhat.com>) id 1ctLCF-0004RT-LW
	for qemu-devel@nongnu.org; Wed, 29 Mar 2017 17:32:04 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <mst@redhat.com>) id 1ctLCA-0006z6-7m
	for qemu-devel@nongnu.org; Wed, 29 Mar 2017 17:32:03 -0400
Received: from mx1.redhat.com ([209.132.183.28]:57894)
	by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32)
	(Exim 4.71) (envelope-from <mst@redhat.com>) id 1ctLCA-0006yv-25
	for qemu-devel@nongnu.org; Wed, 29 Mar 2017 17:31:58 -0400
Date: Thu, 30 Mar 2017 00:31:53 +0300
From: "Michael S. Tsirkin" <mst@redhat.com>
Message-ID: <20170330002953-mutt-send-email-mst@kernel.org>
References: <93cb45b7-feca-9340-5fbe-3cc1e60d9e7e@redhat.com>
	<aa8f8830-9426-7cf5-ec99-363035315aa3@redhat.com>
	<24333171-ada3-cfe8-647a-61dc6839144b@redhat.com>
	<59720527-123d-de99-7066-7c9d392b1a42@redhat.com>
	<2286dd90-c63b-d4ac-4212-f43c4a1ed8f8@redhat.com>
	<4f23135b-ad6d-7e1e-a0fd-cddaa788da7c@redhat.com>
	<bba32cde-6d38-3b49-3bb4-058a5d81d038@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <bba32cde-6d38-3b49-3bb4-058a5d81d038@redhat.com>
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] issues of region cache and iommu reset
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel/>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Jason Wang <jasowang@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>, Peter Xu <peterx@redhat.com>, qemu devel <qemu-devel@nongnu.org>, Cornelia Huck <cornelia.huck@de.ibm.com>

On Wed, Mar 29, 2017 at 05:24:18PM +0800, Jason Wang wrote:
>=20
>=20
> On 2017=E5=B9=B403=E6=9C=8829=E6=97=A5 17:11, Paolo Bonzini wrote:
> >=20
> > On 29/03/2017 11:09, Jason Wang wrote:
> > > > > This looks a good fix but may not solve this issue completely. =
Depends
> > > > > on the iova that guest uses, address_space_cache_init() may suc=
ceed even
> > > > > in this case since vtd does a passthrough translation in this c=
ase.
> > > > Can you explain this more?
> > > Yes.  In this case, virtio-net-pci is not reset, but vtd has been r=
eset.
> > > So virtio-net-pci will still try to use the iova of ring to setup t=
he
> > > cache but now vtd treat iova as gpa since dmar has been disabled du=
ring
> > > reset. (E.g In my test with Linux driver, desc map succeed but used=
 fail.)
> > That would be a Linux bug, the devices below the IOMMU have to be res=
et
> > first.
> >=20
> > Paolo
>=20
> Maybe, but I meet the same issue if I do a "system_reset". I think we s=
hould
> guarantee IOMMU was reset after any pci devices in this case too?
>=20
> Thanks
>=20

system reset would indeed appear to be a big issue.

--=20
MST