From: Avi Kivity <avi@redhat.com>
To: Anthony Liguori <aliguori@us.ibm.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
qemu-devel@nongnu.org, joerg.roedel@amd.com, rth@twiddle.net,
agraf@suse.de, eduard.munteanu@linux360.ro, kraxel@redhat.com
Subject: Re: [Qemu-devel] [PATCH 1/9] Add stub functions for PCI device models to do PCI DMA
Date: Sun, 16 Oct 2011 15:15:53 +0200 [thread overview]
Message-ID: <4E9AD909.1000509@redhat.com> (raw)
In-Reply-To: <20111014021407.GB4580@truffala.fritz.box>
On 10/14/2011 04:14 AM, David Gibson wrote:
> > Virtio is a very, very special case. virtio requires coherent RAM access.
>
> Right. Virtio's access to memory is *not* emulated PCI DMA, it's
> god-like hypervisor access to guest system memory. It should
> correctly bypass any IOMMU, and so should remain as
> cpu_physical_memory_rw() or the atomic accessors, rather than being
> converted to this new API.
virtio should definitely not bypass an iommu. A guest may assign a
virtio device to nested guests, and would wish it confined by the
emulated iommu.
More generally, a guest sees a virtio device as just another pci device,
and has no way to tell that it bypasses the iommu.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2011-10-16 13:16 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-05 4:34 [Qemu-devel] [0/9] Preliminary work for IOMMU emulation support; the easy bits (v2) David Gibson
2011-09-05 4:34 ` [Qemu-devel] [PATCH 1/9] Add stub functions for PCI device models to do PCI DMA David Gibson
2011-10-02 10:25 ` Michael S. Tsirkin
2011-10-02 10:29 ` Avi Kivity
2011-10-02 10:52 ` Michael S. Tsirkin
2011-10-02 10:58 ` Avi Kivity
2011-10-02 11:17 ` Michael S. Tsirkin
2011-10-02 11:28 ` Alexander Graf
2011-10-02 11:43 ` Michael S. Tsirkin
2011-10-02 12:01 ` Avi Kivity
2011-10-02 12:14 ` Michael S. Tsirkin
2011-10-02 12:26 ` Avi Kivity
2011-10-03 13:17 ` Anthony Liguori
2011-10-12 3:09 ` David Gibson
2011-10-12 9:12 ` Michael S. Tsirkin
2011-10-14 2:14 ` David Gibson
2011-10-16 12:50 ` Michael S. Tsirkin
2011-10-16 13:15 ` Avi Kivity [this message]
2011-10-18 1:46 ` David Gibson
2011-10-19 0:31 ` Rusty Russell
2011-10-19 1:22 ` Michael S. Tsirkin
2011-10-19 9:10 ` Avi Kivity
2011-10-20 2:58 ` David Gibson
2011-10-12 3:07 ` David Gibson
2011-10-12 7:22 ` Michael S. Tsirkin
2011-10-12 15:43 ` David Gibson
2011-10-12 15:45 ` David Gibson
2011-10-12 3:11 ` David Gibson
2011-10-12 8:44 ` Michael S. Tsirkin
2011-10-12 9:08 ` Gerd Hoffmann
2011-10-03 13:10 ` Anthony Liguori
2011-09-05 4:34 ` [Qemu-devel] [PATCH 2/9] rtl8139: Use PCI DMA stub functions David Gibson
2011-09-05 4:34 ` [Qemu-devel] [PATCH 3/9] eepro100: " David Gibson
2011-10-02 11:45 ` Michael S. Tsirkin
2011-10-14 2:15 ` David Gibson
2011-09-05 4:34 ` [Qemu-devel] [PATCH 4/9] ac97: " David Gibson
2011-09-05 4:35 ` [Qemu-devel] [PATCH 5/9] es1370: " David Gibson
2011-09-05 4:35 ` [Qemu-devel] [PATCH 6/9] e1000: " David Gibson
2011-09-05 4:35 ` [Qemu-devel] [PATCH 7/9] lsi53c895a: " David Gibson
2011-09-05 4:35 ` [Qemu-devel] [PATCH 8/9] pcnet-pci: " David Gibson
2011-09-05 4:35 ` [Qemu-devel] [PATCH 9/9] intel-hda: " David Gibson
2011-09-16 6:58 ` [Qemu-devel] [0/9] Preliminary work for IOMMU emulation support; the easy bits (v2) David Gibson
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4E9AD909.1000509@redhat.com \
--to=avi@redhat.com \
--cc=agraf@suse.de \
--cc=aliguori@us.ibm.com \
--cc=eduard.munteanu@linux360.ro \
--cc=joerg.roedel@amd.com \
--cc=kraxel@redhat.com \
--cc=mst@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.