From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: David Gibson <david@gibson.dropbear.id.au>
Cc: mst@redhat.com, qemu-devel@nongnu.org, agraf@suse.de,
eduard.munteanu@linux360.ro, Paolo Bonzini <pbonzini@redhat.com>,
rth@twiddle.net
Subject: Re: [Qemu-devel] [PATCH 13/13] pseries: Implement IOMMU and DMA for PAPR PCI devices
Date: Sun, 11 Mar 2012 13:02:47 +1100 [thread overview]
Message-ID: <1331431367.3105.88.camel@pasglop> (raw)
In-Reply-To: <20120309105847.GA24916@truffala.fritz.box>
On Fri, 2012-03-09 at 21:58 +1100, David Gibson wrote:
> > What about virtio?
>
> virtio doesn't use virtualized PCI DMA, it uses direct hypervisor
> access to guest memory, by guest physical address. It *shouldn't*,
> but it does - that's the way it's specced and that's the way the guest
> kernel expects it to be. It could be fixed with a new feature bit,
> but that's a project for another day.
More precisely, the patch don't break virtio as virtio just bypasses
this all.
Also having virtio go through the iommu might not be such a great idea,
it should definitely remain optional. The ability of virtio to go
straight to guest memory has some significant performance advantages.
Cheers,
Ben.
next prev parent reply other threads:[~2012-03-11 2:03 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-09 5:01 [Qemu-devel] [0/13] Implement support for guest visible IOMMUs David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 01/13] Use DMADirection type for dma_bdrv_io David Gibson
2012-03-09 9:34 ` Kevin Wolf
2012-03-09 10:01 ` Paolo Bonzini
2012-03-13 5:53 ` David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 02/13] Better support for dma_addr_t variables David Gibson
2012-03-09 10:00 ` Paolo Bonzini
2012-03-09 5:01 ` [Qemu-devel] [PATCH 03/13] usb-xhci: Use PCI DMA helper functions David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 04/13] Implement cpu_physical_memory_zero() David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 05/13] iommu: Add universal DMA helper functions David Gibson
2012-03-09 10:06 ` Paolo Bonzini
2012-03-09 11:19 ` David Gibson
2012-03-09 11:55 ` Paolo Bonzini
2012-03-09 5:01 ` [Qemu-devel] [PATCH 06/13] usb-ohci: Use " David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 07/13] iommu: Make sglists and dma_bdrv helpers use new universal DMA helpers David Gibson
2012-03-09 9:43 ` Kevin Wolf
2012-03-13 10:42 ` David Gibson
2012-03-13 11:55 ` Kevin Wolf
2012-03-09 10:11 ` Paolo Bonzini
2012-03-13 6:37 ` David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 08/13] ide/ahci: Use universal DMA helper functions David Gibson
2012-03-09 9:48 ` Kevin Wolf
2012-03-10 5:30 ` David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 09/13] usb: Convert usb_packet_{map, unmap} to universal DMA helpers David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 10/13] iommu: Introduce IOMMU emulation infrastructure David Gibson
2012-03-09 10:23 ` Paolo Bonzini
2012-03-13 5:07 ` David Gibson
2012-03-13 13:56 ` Alexander Graf
2012-03-13 14:04 ` David Gibson
2012-03-13 14:37 ` Alexander Graf
2012-03-14 9:05 ` David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 11/13] pseries: Convert sPAPR TCEs to use generic IOMMU infrastructure David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 12/13] iommu: Allow PCI to use " David Gibson
2012-03-09 5:01 ` [Qemu-devel] [PATCH 13/13] pseries: Implement IOMMU and DMA for PAPR PCI devices David Gibson
2012-03-09 10:23 ` Paolo Bonzini
2012-03-09 10:58 ` David Gibson
2012-03-11 2:02 ` Benjamin Herrenschmidt [this message]
-- strict thread matches above, loose matches on Subject: below --
2012-03-22 2:14 [Qemu-devel] [0/13] RFC: Guest visible IOMMU David Gibson
2012-03-22 2:14 ` [Qemu-devel] [PATCH 13/13] pseries: Implement IOMMU and DMA for PAPR PCI devices David Gibson
2012-03-01 5:35 [Qemu-devel] [0/13] RFC: Support for guest-visible IOMMUs David Gibson
2012-03-01 5:36 ` [Qemu-devel] [PATCH 13/13] pseries: Implement IOMMU and DMA for PAPR PCI devices 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=1331431367.3105.88.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=agraf@suse.de \
--cc=david@gibson.dropbear.id.au \
--cc=eduard.munteanu@linux360.ro \
--cc=mst@redhat.com \
--cc=pbonzini@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).