From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Andy Lutomirski <luto@amacapital.net>
Cc: "linux-s390@vger.kernel.org" <linux-s390@vger.kernel.org>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
Linux Virtualization <virtualization@lists.linux-foundation.org>,
Christian Borntraeger <borntraeger@de.ibm.com>,
Paolo Bonzini <pbonzini@redhat.com>,
"linux390@de.ibm.com" <linux390@de.ibm.com>
Subject: Re: [PATCH v4 0/4] virtio: Clean up scatterlists and use the DMA API
Date: Wed, 03 Sep 2014 06:53:33 +1000 [thread overview]
Message-ID: <1409691213.30640.37.camel@pasglop> (raw)
In-Reply-To: <CALCETrVHSjaCe5TN6+Gr9W9uT8XEZC97ne_dZUazMDyLr0Wetw@mail.gmail.com>
On Mon, 2014-09-01 at 22:55 -0700, Andy Lutomirski wrote:
>
> On x86, at least, I doubt that we'll ever see a physically addressed
> PCI virtio device for which ACPI advertises an IOMMU, since any sane
> hypervisor will just not advertise an IOMMU for the virtio device.
> But are there arm64 or PPC guests that use virtio_pci, that have
> IOMMUs, and that will malfunction if the virtio_pci driver ends up
> using the IOMMU? I certainly hope not, since these systems might be
> very hard-pressed to work right if someone plugged in a physical
> virtio-speaking PCI device.
It will definitely not work on ppc64. We always have IOMMUs on pseries,
all PCI busses do, and because it's a paravirtualized environment,
napping/unmapping pages means hypercalls -> expensive.
But our virtio implementation bypasses it in qemu, so if virtio-pci
starts using the DMA mapping API without changing the DMA ops under the
hood, it will break for us.
Cheers,
Ben.
next prev parent reply other threads:[~2014-09-02 20:53 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-01 17:39 [PATCH v4 0/4] virtio: Clean up scatterlists and use the DMA API Andy Lutomirski
2014-09-01 17:39 ` [PATCH v4 1/4] virtio_ring: Support DMA APIs if requested Andy Lutomirski
2014-09-01 17:39 ` [PATCH v4 2/4] virtio_pci: Use the DMA API for virtqueues Andy Lutomirski
2014-09-01 17:39 ` [PATCH v4 3/4] virtio_net: Don't set the end flag on reusable sg entries Andy Lutomirski
2014-09-01 17:39 ` [PATCH v4 4/4] virtio_net: Stop doing DMA from the stack Andy Lutomirski
2014-09-01 22:16 ` [PATCH v4 0/4] virtio: Clean up scatterlists and use the DMA API Benjamin Herrenschmidt
2014-09-02 5:55 ` Andy Lutomirski
2014-09-02 20:53 ` Benjamin Herrenschmidt [this message]
2014-09-02 20:56 ` Konrad Rzeszutek Wilk
2014-09-02 21:08 ` Benjamin Herrenschmidt
2014-09-02 21:37 ` Andy Lutomirski
2014-09-02 22:10 ` Benjamin Herrenschmidt
2014-09-02 23:11 ` Andy Lutomirski
2014-09-02 23:20 ` Benjamin Herrenschmidt
2014-09-02 23:42 ` Andy Lutomirski
2014-09-03 0:25 ` Benjamin Herrenschmidt
2014-09-03 0:32 ` Andy Lutomirski
2014-09-03 0:43 ` Benjamin Herrenschmidt
2014-09-04 2:03 ` Andy Lutomirski
2014-09-03 7:47 ` Paolo Bonzini
2014-09-03 7:52 ` Andy Lutomirski
2014-09-03 8:01 ` Paolo Bonzini
2014-09-03 8:05 ` Benjamin Herrenschmidt
2014-09-03 12:11 ` Paolo Bonzini
2014-09-03 15:07 ` Andy Lutomirski
2014-09-03 15:11 ` Paolo Bonzini
2014-09-03 16:39 ` Michael S. Tsirkin
2014-09-03 20:38 ` Andy Lutomirski
2014-09-03 7:43 ` Paolo Bonzini
2014-09-03 6:42 ` Rusty Russell
2014-09-03 7:50 ` Andy Lutomirski
2014-09-05 2:31 ` Rusty Russell
2014-09-05 2:57 ` Andy Lutomirski
2014-09-05 5:20 ` Benjamin Herrenschmidt
2014-09-05 7:33 ` Christian Borntraeger
2014-09-10 15:36 ` Christopher Covington
2014-09-10 16:15 ` Andy Lutomirski
2014-09-05 5:16 ` Benjamin Herrenschmidt
2014-09-14 8:58 ` Michael S. Tsirkin
2014-09-03 12:51 ` Michael S. Tsirkin
2014-09-05 2:32 ` Rusty Russell
2014-09-05 3:06 ` Andy Lutomirski
2014-09-02 21:10 ` Michael S. Tsirkin
2014-09-02 21:49 ` Andy Lutomirski
-- strict thread matches above, loose matches on Subject: below --
2015-07-28 1:08 Andy Lutomirski
2015-07-28 7:05 ` Christian Borntraeger
2015-07-28 8:16 ` Paolo Bonzini
2015-07-28 10:12 ` Benjamin Herrenschmidt
2015-07-28 12:46 ` Paolo Bonzini
2015-07-28 13:06 ` Michael S. Tsirkin
2015-07-28 13:11 ` Jan Kiszka
2015-07-28 16:11 ` Andy Lutomirski
2015-07-28 16:44 ` Jan Kiszka
2015-07-28 17:10 ` Andy Lutomirski
2015-07-28 17:17 ` Jan Kiszka
2015-07-28 18:22 ` Andy Lutomirski
2015-07-28 19:06 ` Jan Kiszka
2015-07-28 19:24 ` Andy Lutomirski
2015-07-28 19:33 ` Jan Kiszka
2015-07-28 21:16 ` Andy Lutomirski
2015-07-28 22:43 ` Andy Lutomirski
2015-07-28 23:21 ` Benjamin Herrenschmidt
2015-07-28 23:33 ` Andy Lutomirski
2015-07-29 0:36 ` Benjamin Herrenschmidt
2015-07-29 0:47 ` Andy Lutomirski
2015-07-29 0:54 ` Benjamin Herrenschmidt
2015-07-29 8:17 ` Paolo Bonzini
2015-07-29 8:20 ` Jan Kiszka
2015-07-29 9:21 ` Benjamin Herrenschmidt
2015-07-29 8:07 ` Jan Kiszka
2015-07-28 16:36 ` Paolo Bonzini
2015-07-28 16:42 ` Jan Kiszka
2015-07-28 17:15 ` Paolo Bonzini
2015-07-28 17:19 ` Jan Kiszka
2015-07-28 17:31 ` Paolo Bonzini
2015-07-28 13:08 ` Michael S. Tsirkin
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=1409691213.30640.37.camel@pasglop \
--to=benh@kernel.crashing.org \
--cc=borntraeger@de.ibm.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-s390@vger.kernel.org \
--cc=linux390@de.ibm.com \
--cc=luto@amacapital.net \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=virtualization@lists.linux-foundation.org \
/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).