From: Joerg Roedel <joro@8bytes.org>
To: Alexander Graf <agraf@suse.de>
Cc: chrisw <chrisw@sous-sol.org>,
Alexey Kardashevskiy <aik@au1.ibm.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Paul Mackerras <pmac@au1.ibm.com>,
"Roedel, Joerg" <joerg.roedel@amd.com>,
qemu-devel <qemu-devel@nongnu.org>, aafabbri <aafabbri@cisco.com>,
iommu <iommu@lists.linux-foundation.org>,
Avi Kivity <avi@redhat.com>,
"linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
"benve@cisco.com" <benve@cisco.com>
Subject: Re: [Qemu-devel] kvm PCI assignment & VFIO ramblings
Date: Fri, 26 Aug 2011 17:24:05 +0200 [thread overview]
Message-ID: <20110826152404.GF8978@8bytes.org> (raw)
In-Reply-To: <571DC890-A1A3-4528-92BE-566F033FD4BF@suse.de>
On Fri, Aug 26, 2011 at 09:07:35AM -0500, Alexander Graf wrote:
> On 26.08.2011, at 04:33, Roedel, Joerg wrote:
> >
> > The reason is that you mean the usability for the programmer and I mean
> > it for the actual user of qemu :)
>
> No, we mean the actual user of qemu. The reason being that making a
> device available for any user space application is an administrative
> task.
>
> Forget the KVM case for a moment and think of a user space device
> driver. I as a user am not root. But I as a user when having access to
> /dev/vfioX want to be able to access the device and manage it - and
> only it. The admin of that box needs to set it up properly for me to
> be able to access it.
Right, and that task is being performed by attaching the device(s) in
question to the vfio driver. The rights-management happens on the
/dev/vfio/$group file.
> So having two steps is really the correct way to go:
>
> * create VFIO group
> * use VFIO group
>
> because the two are done by completely different users. It's similar
> to how tun/tap works in Linux too. Of course nothing keeps you from
> also creating a group on the fly, but it shouldn't be the only
> interface available. The persistent setup is definitely more useful.
I see the use-case. But to make it as easy as possible for the end-user
we can do both.
So the user of (qemu again) does this:
# vfio-ctl attach 00:01.0
vfio-ctl: attached to group 8
# vfio-ctl attach 00:02.0
vfio-ctl: attached to group 16
$ qemu -device vfio-pci,host=00:01.0 -device vfio,host=00:01.0 ...
which should cover the usecase you prefer. Qemu still creates the
meta-group that allow the devices to share the same page-table. But what
should also be possible is:
# qemu -device vfio-pci,host=00:01.0 -device vfio-pci,host=00:02.0
In that case qemu detects that the devices are not yet bound to vfio and
will do so and also unbinds them afterwards (essentially the developer
use-case).
Your interface which requires pre-binding of devices into one group by
the administrator only makes sense if you want to force userspace to
use certain devices (which do not belong to the same hw-group) only
together. But I don't see a usecase for defining such constraints (yet).
Joerg
next prev parent reply other threads:[~2011-08-26 15:24 UTC|newest]
Thread overview: 93+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1311983933.8793.42.camel@pasglop>
2011-07-30 18:20 ` [Qemu-devel] kvm PCI assignment & VFIO ramblings Alex Williamson
2011-07-30 23:54 ` Benjamin Herrenschmidt
2011-08-01 18:59 ` Alex Williamson
2011-08-02 2:00 ` Benjamin Herrenschmidt
2011-07-30 23:55 ` Benjamin Herrenschmidt
2011-08-02 8:28 ` David Gibson
2011-08-02 18:14 ` Alex Williamson
2011-08-02 18:35 ` Alex Williamson
2011-08-03 2:04 ` David Gibson
2011-08-03 3:44 ` Alex Williamson
2011-08-04 0:39 ` David Gibson
2011-08-08 8:28 ` Avi Kivity
2011-08-09 23:24 ` Alex Williamson
2011-08-10 2:48 ` Benjamin Herrenschmidt
2011-08-20 16:51 ` Alex Williamson
2011-08-22 5:55 ` David Gibson
2011-08-22 15:45 ` Alex Williamson
2011-08-22 21:01 ` Benjamin Herrenschmidt
2011-08-23 19:30 ` Alex Williamson
2011-08-23 23:51 ` Benjamin Herrenschmidt
2011-08-24 3:40 ` Alexander Graf
2011-08-24 14:47 ` Alex Williamson
2011-08-24 8:43 ` Joerg Roedel
2011-08-24 14:56 ` Alex Williamson
2011-08-25 11:01 ` Roedel, Joerg
2011-08-23 2:38 ` David Gibson
2011-08-23 16:23 ` Alex Williamson
2011-08-23 23:41 ` Benjamin Herrenschmidt
2011-08-24 3:36 ` Alexander Graf
2011-08-22 6:30 ` Avi Kivity
2011-08-22 10:46 ` Joerg Roedel
2011-08-22 10:51 ` Avi Kivity
2011-08-22 12:36 ` Roedel, Joerg
2011-08-22 12:42 ` Avi Kivity
2011-08-22 12:55 ` Roedel, Joerg
2011-08-22 13:06 ` Avi Kivity
2011-08-22 13:15 ` Roedel, Joerg
2011-08-22 13:17 ` Avi Kivity
2011-08-22 14:37 ` Roedel, Joerg
2011-08-22 20:53 ` Benjamin Herrenschmidt
2011-08-22 17:25 ` Joerg Roedel
2011-08-22 19:17 ` Alex Williamson
2011-08-23 13:14 ` Roedel, Joerg
2011-08-23 17:08 ` Alex Williamson
2011-08-24 8:52 ` Roedel, Joerg
2011-08-24 15:07 ` Alex Williamson
2011-08-25 12:31 ` Roedel, Joerg
2011-08-25 13:25 ` Alexander Graf
2011-08-26 4:24 ` David Gibson
2011-08-26 9:24 ` Roedel, Joerg
2011-08-28 13:14 ` Avi Kivity
2011-08-28 13:56 ` Joerg Roedel
2011-08-28 14:04 ` Avi Kivity
2011-08-30 16:14 ` Joerg Roedel
2011-08-22 21:03 ` Benjamin Herrenschmidt
2011-08-23 13:18 ` Roedel, Joerg
2011-08-23 23:35 ` Benjamin Herrenschmidt
2011-08-24 8:53 ` Roedel, Joerg
2011-08-22 20:29 ` aafabbri
2011-08-22 20:49 ` Benjamin Herrenschmidt
2011-08-22 21:38 ` aafabbri
2011-08-22 21:49 ` Benjamin Herrenschmidt
2011-08-23 0:52 ` aafabbri
2011-08-23 6:54 ` Benjamin Herrenschmidt
2011-08-23 11:09 ` Joerg Roedel
2011-08-23 17:01 ` Alex Williamson
2011-08-23 17:33 ` Aaron Fabbri
2011-08-23 18:01 ` Alex Williamson
2011-08-24 9:10 ` Joerg Roedel
2011-08-24 21:13 ` Alex Williamson
2011-08-25 10:54 ` Roedel, Joerg
2011-08-25 15:38 ` Don Dutile
2011-08-25 16:46 ` Roedel, Joerg
2011-08-25 17:20 ` Alex Williamson
2011-08-25 18:05 ` Joerg Roedel
2011-08-26 18:04 ` Alex Williamson
2011-08-30 16:13 ` Joerg Roedel
2011-08-23 11:04 ` Joerg Roedel
2011-08-23 16:54 ` aafabbri
2011-08-24 9:14 ` Roedel, Joerg
2011-08-24 9:33 ` David Gibson
2011-08-24 11:03 ` Roedel, Joerg
2011-08-26 4:20 ` David Gibson
2011-08-26 9:33 ` Roedel, Joerg
2011-08-26 14:07 ` Alexander Graf
2011-08-26 15:24 ` Joerg Roedel [this message]
2011-08-26 15:29 ` Alexander Graf
2011-08-26 17:52 ` Aaron Fabbri
2011-08-26 19:35 ` Chris Wright
2011-08-26 20:17 ` Aaron Fabbri
2011-08-26 21:06 ` Chris Wright
2011-08-30 1:29 ` David Gibson
2011-08-04 10:35 ` Joerg Roedel
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=20110826152404.GF8978@8bytes.org \
--to=joro@8bytes.org \
--cc=aafabbri@cisco.com \
--cc=agraf@suse.de \
--cc=aik@au1.ibm.com \
--cc=avi@redhat.com \
--cc=benve@cisco.com \
--cc=chrisw@sous-sol.org \
--cc=iommu@lists.linux-foundation.org \
--cc=joerg.roedel@amd.com \
--cc=kvm@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=pmac@au1.ibm.com \
--cc=qemu-devel@nongnu.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).