From: "Michael S. Tsirkin" <mst@redhat.com>
To: Parav Pandit <parav@nvidia.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Maor Gottlieb <maorg@nvidia.com>,
"virtualization@lists.linux-foundation.org"
<virtualization@lists.linux-foundation.org>,
Christoph Hellwig <hch@infradead.org>,
Jason Gunthorpe <jgg@nvidia.com>, Jiri Pirko <jiri@nvidia.com>,
Leon Romanovsky <leonro@nvidia.com>
Subject: Re: [PATCH vfio 10/11] vfio/virtio: Expose admin commands over virtio device
Date: Wed, 11 Oct 2023 04:10:58 -0400 [thread overview]
Message-ID: <20231011040331-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <PH0PR12MB5481336B395F38E875ED11D8DCCCA@PH0PR12MB5481.namprd12.prod.outlook.com>
On Wed, Oct 11, 2023 at 08:00:57AM +0000, Parav Pandit wrote:
> Hi Christoph,
>
> > From: Christoph Hellwig <hch@infradead.org>
> > Sent: Wednesday, October 11, 2023 12:29 PM
> >
> > On Wed, Oct 11, 2023 at 02:43:37AM -0400, Michael S. Tsirkin wrote:
> > > > Btw, what is that intel thing everyone is talking about? And why
> > > > would the virtio core support vendor specific behavior like that?
> > >
> > > It's not a thing it's Zhu Lingshan :) intel is just one of the vendors
> > > that implemented vdpa support and so Zhu Lingshan from intel is
> > > working on vdpa and has also proposed virtio spec extensions for migration.
> > > intel's driver is called ifcvf. vdpa composes all this stuff that is
> > > added to vfio in userspace, so it's a different approach.
> >
> > Well, so let's call it virtio live migration instead of intel.
> >
> > And please work all together in the virtio committee that you have one way of
> > communication between controlling and controlled functions.
> > If one extension does it one way and the other a different way that's just
> > creating a giant mess.
>
> We in virtio committee are working on VF device migration where:
> VF = controlled function
> PF = controlling function
>
> The second proposal is what Michael mentioned from Intel that somehow combine controlled and controlling function as single entity on VF.
>
> The main reasons I find it weird are:
> 1. it must always need to do mediation to do fake the device reset, and flr flows
> 2. dma cannot work as you explained for complex device state
> 3. it needs constant knowledge of each tiny things for each virtio device type
>
> Such single entity appears a bit very weird to me but maybe it is just me.
Yea it appears to include everyone from nvidia. Others are used to it -
this is exactly what happens with virtio generally. E.g. vhost
processes fast path in the kernel and control path is in userspace.
vdpa has been largely modeled after that, for better or worse.
--
MST
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2023-10-11 8:11 UTC|newest]
Thread overview: 140+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-21 12:40 [PATCH vfio 00/11] Introduce a vfio driver over virtio devices Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 01/11] virtio-pci: Use virtio pci device layer vq info instead of generic one Yishai Hadas via Virtualization
2023-09-21 13:46 ` Michael S. Tsirkin
2023-09-26 19:13 ` Feng Liu via Virtualization
2023-09-27 18:09 ` Feng Liu via Virtualization
2023-09-27 21:24 ` Michael S. Tsirkin
2023-09-21 12:40 ` [PATCH vfio 02/11] virtio: Define feature bit for administration virtqueue Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 03/11] virtio-pci: Introduce admin virtqueue Yishai Hadas via Virtualization
2023-09-21 13:57 ` Michael S. Tsirkin
2023-09-26 19:23 ` Feng Liu via Virtualization
2023-09-27 18:12 ` Feng Liu via Virtualization
2023-09-27 21:27 ` Michael S. Tsirkin
2023-10-02 18:07 ` Feng Liu via Virtualization
2023-09-21 12:40 ` [PATCH vfio 04/11] virtio: Expose the synchronous command helper function Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 05/11] virtio-pci: Introduce admin command sending function Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 06/11] virtio-pci: Introduce API to get PF virtio device from VF PCI device Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 07/11] virtio-pci: Introduce admin commands Yishai Hadas via Virtualization
2023-09-24 5:18 ` kernel test robot
2023-09-25 3:18 ` kernel test robot
2023-09-21 12:40 ` [PATCH vfio 08/11] vfio/pci: Expose vfio_pci_core_setup_barmap() Yishai Hadas via Virtualization
2023-09-21 16:35 ` Alex Williamson
2023-09-26 9:45 ` Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 09/11] vfio/pci: Expose vfio_pci_iowrite/read##size() Yishai Hadas via Virtualization
2023-09-21 12:40 ` [PATCH vfio 10/11] vfio/virtio: Expose admin commands over virtio device Yishai Hadas via Virtualization
2023-09-21 13:08 ` Michael S. Tsirkin
2023-09-21 20:34 ` Michael S. Tsirkin
2023-09-26 10:51 ` Yishai Hadas via Virtualization
2023-09-26 11:25 ` Michael S. Tsirkin
2023-09-22 9:54 ` Michael S. Tsirkin
2023-09-26 11:14 ` Yishai Hadas via Virtualization
2023-09-26 11:41 ` Michael S. Tsirkin
[not found] ` <20230927131817.GA338226@nvidia.com>
2023-09-27 21:30 ` Michael S. Tsirkin
[not found] ` <20230927231600.GD339126@nvidia.com>
2023-09-28 5:26 ` Michael S. Tsirkin
2023-10-02 6:28 ` Christoph Hellwig
[not found] ` <20231002151320.GA650762@nvidia.com>
2023-10-05 8:49 ` Christoph Hellwig
[not found] ` <20231005111004.GK682044@nvidia.com>
2023-10-06 13:09 ` Christoph Hellwig
[not found] ` <20231010131031.GJ3952@nvidia.com>
2023-10-10 13:56 ` Michael S. Tsirkin
[not found] ` <20231010140849.GL3952@nvidia.com>
2023-10-10 14:54 ` Michael S. Tsirkin
2023-10-10 15:09 ` Yishai Hadas via Virtualization
2023-10-10 15:14 ` Michael S. Tsirkin
2023-10-10 15:43 ` Yishai Hadas via Virtualization
2023-10-10 15:58 ` Parav Pandit via Virtualization
2023-10-10 15:58 ` Michael S. Tsirkin
2023-10-10 16:09 ` Yishai Hadas via Virtualization
2023-10-10 20:42 ` Michael S. Tsirkin
2023-10-11 7:44 ` Yishai Hadas via Virtualization
2023-10-11 8:02 ` Michael S. Tsirkin
2023-10-11 8:58 ` Yishai Hadas via Virtualization
2023-10-11 9:03 ` Michael S. Tsirkin
2023-10-11 11:25 ` Yishai Hadas via Virtualization
2023-10-11 6:12 ` Christoph Hellwig
[not found] ` <20231010155937.GN3952@nvidia.com>
2023-10-10 16:03 ` Michael S. Tsirkin
[not found] ` <20231010160712.GO3952@nvidia.com>
2023-10-10 16:21 ` Parav Pandit via Virtualization
2023-10-10 20:38 ` Michael S. Tsirkin
2023-10-11 6:13 ` Christoph Hellwig
2023-10-11 6:43 ` Michael S. Tsirkin
2023-10-11 6:59 ` Christoph Hellwig
2023-10-11 8:00 ` Parav Pandit via Virtualization
2023-10-11 8:10 ` Michael S. Tsirkin [this message]
[not found] ` <20231011121849.GV3952@nvidia.com>
2023-10-11 17:03 ` Michael S. Tsirkin
2023-10-11 17:05 ` Michael S. Tsirkin
2023-10-12 10:29 ` Zhu, Lingshan
[not found] ` <20231012132749.GK3952@nvidia.com>
2023-10-13 10:28 ` Zhu, Lingshan
2023-10-13 13:50 ` Michael S. Tsirkin
2023-10-16 8:33 ` Zhu, Lingshan
2023-10-16 8:52 ` Michael S. Tsirkin
2023-10-16 9:53 ` Zhu, Lingshan
2023-10-11 8:12 ` Michael S. Tsirkin
2023-10-12 10:30 ` Zhu, Lingshan
2023-10-11 6:26 ` Christoph Hellwig
[not found] ` <20231011135709.GW3952@nvidia.com>
2023-10-11 14:17 ` Christoph Hellwig
[not found] ` <20231011145810.GZ3952@nvidia.com>
2023-10-11 16:59 ` Michael S. Tsirkin
[not found] ` <20231011171944.GA3952@nvidia.com>
2023-10-11 20:20 ` Michael S. Tsirkin
2023-09-21 12:40 ` [PATCH vfio 11/11] vfio/virtio: Introduce a vfio driver over virtio devices Yishai Hadas via Virtualization
2023-09-21 13:16 ` Michael S. Tsirkin
[not found] ` <20230921141125.GM13733@nvidia.com>
2023-09-21 14:16 ` Michael S. Tsirkin
[not found] ` <20230921164139.GP13733@nvidia.com>
2023-09-21 16:53 ` Michael S. Tsirkin
[not found] ` <20230921183926.GV13733@nvidia.com>
2023-09-21 19:13 ` Michael S. Tsirkin
[not found] ` <20230921194946.GX13733@nvidia.com>
2023-09-21 20:45 ` Michael S. Tsirkin
[not found] ` <20230921225526.GE13733@nvidia.com>
2023-09-22 3:02 ` Jason Wang
2023-09-22 11:23 ` Michael S. Tsirkin
2023-09-22 3:01 ` Jason Wang
[not found] ` <20230922121132.GK13733@nvidia.com>
2023-09-25 2:34 ` Jason Wang
[not found] ` <20230925122607.GW13733@nvidia.com>
2023-09-25 19:44 ` Michael S. Tsirkin
[not found] ` <20230926004059.GM13733@nvidia.com>
2023-09-26 5:34 ` Michael S. Tsirkin
2023-09-26 5:42 ` Michael S. Tsirkin
[not found] ` <20230926135057.GO13733@nvidia.com>
2023-09-27 21:38 ` Michael S. Tsirkin
[not found] ` <20230927232005.GE339126@nvidia.com>
2023-09-28 5:31 ` Michael S. Tsirkin
2023-09-26 4:37 ` Jason Wang
2023-09-26 5:33 ` Parav Pandit via Virtualization
2023-09-21 19:17 ` Michael S. Tsirkin
[not found] ` <20230921195115.GY13733@nvidia.com>
2023-09-21 20:55 ` Michael S. Tsirkin
2023-09-25 4:44 ` Zhu, Lingshan
2023-09-22 3:45 ` Zhu, Lingshan
2023-09-21 13:33 ` Michael S. Tsirkin
2023-09-21 16:43 ` Alex Williamson
[not found] ` <20230921165224.GR13733@nvidia.com>
2023-09-21 17:01 ` Michael S. Tsirkin
2023-09-21 17:09 ` Parav Pandit via Virtualization
2023-09-21 17:24 ` Michael S. Tsirkin
[not found] ` <20230921170709.GS13733@nvidia.com>
2023-09-21 17:21 ` Michael S. Tsirkin
[not found] ` <20230921174450.GT13733@nvidia.com>
2023-09-21 17:55 ` Michael S. Tsirkin
[not found] ` <20230921181637.GU13733@nvidia.com>
2023-09-21 19:34 ` Michael S. Tsirkin
[not found] ` <20230921195345.GZ13733@nvidia.com>
2023-09-21 20:16 ` Michael S. Tsirkin
2023-09-22 3:02 ` Jason Wang
[not found] ` <20230922122246.GN13733@nvidia.com>
2023-09-22 12:25 ` Parav Pandit via Virtualization
2023-09-22 15:13 ` Michael S. Tsirkin
[not found] ` <20230922151534.GR13733@nvidia.com>
2023-09-22 15:40 ` Michael S. Tsirkin
[not found] ` <20230922162233.GT13733@nvidia.com>
2023-09-25 17:36 ` Michael S. Tsirkin
2023-09-25 2:30 ` Jason Wang
2023-09-25 8:26 ` Parav Pandit via Virtualization
2023-09-25 18:36 ` Michael S. Tsirkin
2023-09-26 2:34 ` Zhu, Lingshan
2023-09-26 3:45 ` Parav Pandit via Virtualization
2023-09-26 4:37 ` Jason Wang
2023-10-12 10:52 ` Michael S. Tsirkin
2023-10-12 11:11 ` Parav Pandit via Virtualization
2023-10-12 11:30 ` Michael S. Tsirkin
2023-10-12 11:40 ` Parav Pandit via Virtualization
2023-09-26 2:32 ` Jason Wang
2023-09-26 4:01 ` Parav Pandit via Virtualization
2023-09-26 4:37 ` Jason Wang
2023-09-26 5:27 ` Parav Pandit via Virtualization
2023-09-26 11:49 ` Michael S. Tsirkin
2023-10-08 4:28 ` Jason Wang
[not found] ` <20230921224836.GD13733@nvidia.com>
2023-09-22 9:47 ` Michael S. Tsirkin
[not found] ` <20230922122328.GO13733@nvidia.com>
2023-09-22 15:45 ` Michael S. Tsirkin
2023-09-22 3:02 ` Jason Wang
[not found] ` <20230922122501.GP13733@nvidia.com>
2023-09-22 15:39 ` Michael S. Tsirkin
[not found] ` <20230922161928.GS13733@nvidia.com>
2023-09-25 18:16 ` Michael S. Tsirkin
[not found] ` <20230925185318.GK13733@nvidia.com>
2023-09-25 19:52 ` Michael S. Tsirkin
2023-09-21 19:58 ` Alex Williamson
[not found] ` <20230921200121.GA13733@nvidia.com>
2023-09-21 20:20 ` Michael S. Tsirkin
2023-09-21 20:59 ` Alex Williamson
[not found] ` <20230922123708.GA130749@nvidia.com>
2023-09-22 12:59 ` Parav Pandit via Virtualization
2023-09-26 15:20 ` Yishai Hadas via Virtualization
2023-09-26 17:00 ` Michael S. Tsirkin
2023-10-02 4:38 ` Parav Pandit via Virtualization
2023-09-22 10:10 ` Michael S. Tsirkin
2023-09-22 15:53 ` Michael S. Tsirkin
2023-10-02 11:23 ` Parav Pandit via Virtualization
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=20231011040331-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=hch@infradead.org \
--cc=jgg@nvidia.com \
--cc=jiri@nvidia.com \
--cc=kvm@vger.kernel.org \
--cc=leonro@nvidia.com \
--cc=maorg@nvidia.com \
--cc=parav@nvidia.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).