Discussion of the implementations of VIRTIO specification
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: Parav Pandit <parav@nvidia.com>
Cc: Max Gurtovoy <mgurtovoy@nvidia.com>,
	Jason Wang <jasowang@redhat.com>,
	"cohuck@redhat.com" <cohuck@redhat.com>,
	"virtio-dev@lists.oasis-open.org"
	<virtio-dev@lists.oasis-open.org>,
	Shahaf Shuler <shahafs@nvidia.com>, Oren Duer <oren@nvidia.com>,
	"stefanha@redhat.com" <stefanha@redhat.com>
Subject: Re: [PATCH 2/5] Introduce VIRTIO_F_ADMIN_VQ_INDIRECT_DESC/VIRTIO_F_ADMIN_VQ_IN_ORDER
Date: Thu, 27 Jan 2022 08:05:49 -0500	[thread overview]
Message-ID: <20220127075537-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <PH0PR12MB548185B0603F0A4C8009EB66DC219@PH0PR12MB5481.namprd12.prod.outlook.com>

On Thu, Jan 27, 2022 at 03:49:58AM +0000, Parav Pandit wrote:
> 
> > From: Michael S. Tsirkin <mst@redhat.com>
> > Sent: Wednesday, January 26, 2022 7:42 PM
> > 
> > On Wed, Jan 26, 2022 at 01:29:27PM +0000, Parav Pandit wrote:
> > >
> > > > From: Michael S. Tsirkin <mst@redhat.com>
> > > > Sent: Tuesday, January 25, 2022 5:39 PM
> > >
> > > > >
> > > > > So you do agree that managing a managed
> > > > > (create/destroy/setup/etc...) will be done using the AQ of the managing
> > device ?
> > > >
> > > > I think Jason asked that the management commands are split from the
> > > > queue itself, such that they can be implemented in more ways down the
> > road.
> > >
> > > Admin commands involved DMA. And also multiple commands can be
> > enqueued to the device.
> > > I don't see any other construct in the spec other than vq that enables driver
> > and device to achieve both.
> > > Hence split the queue from command is very weird for spec to do.
> > 
> >  VIRTIO_PCI_CAP_SHARED_MEMORY_CFG can do this.
> >
> Device needs to always have shared memory region always in available range for driver to read.
> Driver still needs to copy data from shared region to own memory.
> How DMA Can be done in the host driver PA using shared memory region?

It can't but you don't need DMA if device is writing its own memory.

> In future when SIOV occurs, each new SIOV SF/ADI will require new
> window in the shared regions exposed statically during PCI discovery
> time.

Donnu if it's statically. But we are talking about AQ thing, that
is just per group not per SF, so might not be too bad.

> So it doesn't scale.


Maybe. You said that's the only way to queue commands to device in the
spec, I just responded with a way. No need to code that up right now,
but just something to keep in mind, things are not absolute here.

> > 
> > > A recent addition like virtio_fs_req didn’t adopt this suggestion.
> > >
> > > If we just want to split so that admin commands can be transported via non
> > admin queue, we should remove below line from spec:
> > >
> > > "The Admin command set defines the commands that may be issued only to
> > the admin virtqueue"
> > 
> > sure
> > 
> > > And reword it as below,
> > >
> > > The Admin command set defines the commands to manipulate various
> > features/attributes of another device within the same group...
> > > When VIRTIO_F_ADMIN_VQ feature is negotiated, admin commands must
> > be transported through the admin queue.
> > >
> > > Looks ok?
> > 
> > I see no problem with that.
> 
> Since we agree for this, I considered AQ vs no_AQ as closed topic?

It's always hard to answer questions like this when all I have to go on
is a vague idea of what you mean.  Based on the discussion I am guessing
that your v3 will use the VQ in a way that is not controversial if that
is what you are asking about.
-- 
MST


  reply	other threads:[~2022-01-27 13:05 UTC|newest]

Thread overview: 110+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-13 14:50 [PATCH v1 0/5] VIRTIO: Provision maximum MSI-X vectors for a VF Max Gurtovoy
2022-01-13 14:50 ` [PATCH 1/5] Add virtio Admin Virtqueue specification Max Gurtovoy
2022-01-13 17:53   ` Michael S. Tsirkin
2022-01-17  9:56     ` Max Gurtovoy
2022-01-17 21:30       ` Michael S. Tsirkin
2022-01-18  3:22         ` Parav Pandit
2022-01-18  6:17           ` Michael S. Tsirkin
2022-01-18  7:57             ` Parav Pandit
2022-01-18  8:05               ` Michael S. Tsirkin
2022-01-18  8:23                 ` Parav Pandit
2022-01-18 10:26                   ` Michael S. Tsirkin
2022-01-18 10:30                     ` Parav Pandit
2022-01-18 10:41                       ` Michael S. Tsirkin
2022-01-19  3:04         ` Jason Wang
2022-01-19  8:11           ` Michael S. Tsirkin
2022-01-25  3:35             ` Jason Wang
2022-01-17 14:12     ` Parav Pandit
2022-01-17 22:03       ` Michael S. Tsirkin
2022-01-18  3:36         ` Parav Pandit
2022-01-18  7:07           ` Michael S. Tsirkin
2022-01-18  7:14             ` Parav Pandit
2022-01-18  7:20               ` Michael S. Tsirkin
2022-01-19 11:33                 ` Max Gurtovoy
2022-01-19 12:21                   ` Parav Pandit
2022-01-19 14:47                     ` Max Gurtovoy
2022-01-19 15:38                       ` Michael S. Tsirkin
2022-01-19 15:47                         ` Max Gurtovoy
2022-01-13 14:51 ` [PATCH 2/5] Introduce VIRTIO_F_ADMIN_VQ_INDIRECT_DESC/VIRTIO_F_ADMIN_VQ_IN_ORDER Max Gurtovoy
2022-01-13 15:33   ` Michael S. Tsirkin
2022-01-13 17:07     ` Max Gurtovoy
2022-01-13 17:25       ` Michael S. Tsirkin
2022-01-17 13:59         ` Parav Pandit
2022-01-17 22:14           ` Michael S. Tsirkin
2022-01-18  4:44             ` Parav Pandit
2022-01-18  6:23               ` Michael S. Tsirkin
2022-01-18  6:32                 ` Parav Pandit
2022-01-18  6:54                   ` Michael S. Tsirkin
2022-01-18  7:07                     ` Parav Pandit
2022-01-18  7:12                       ` Michael S. Tsirkin
2022-01-18  7:30                         ` Parav Pandit
2022-01-18  7:40                           ` Michael S. Tsirkin
2022-01-19  4:21                             ` Jason Wang
2022-01-19  9:30                               ` Michael S. Tsirkin
2022-01-25  3:39                                 ` Jason Wang
2022-01-18 10:38                           ` Michael S. Tsirkin
2022-01-18 10:50                             ` Parav Pandit
2022-01-18 15:09                               ` Michael S. Tsirkin
2022-01-18 17:17                                 ` Parav Pandit
2022-01-19  7:20                                   ` Michael S. Tsirkin
2022-01-19  8:15                                     ` [virtio-dev] " Parav Pandit
2022-01-19  8:21                                       ` Michael S. Tsirkin
2022-01-19 10:10                                         ` Parav Pandit
2022-01-19 16:40                                           ` Michael S. Tsirkin
2022-01-19 17:07                                             ` Parav Pandit
2022-01-18  7:13                       ` Michael S. Tsirkin
2022-01-18  7:21                         ` Parav Pandit
2022-01-18  7:37                           ` Michael S. Tsirkin
2022-01-19  4:03                       ` Jason Wang
2022-01-19  4:48                         ` Parav Pandit
2022-01-19 20:25                           ` Parav Pandit
2022-01-25  3:45                             ` Jason Wang
2022-01-25  4:07                               ` Parav Pandit
2022-01-25  3:29                           ` Jason Wang
2022-01-25  3:52                             ` Parav Pandit
2022-01-25 10:59                               ` Max Gurtovoy
2022-01-25 12:09                                 ` Michael S. Tsirkin
2022-01-26 13:29                                   ` Parav Pandit
2022-01-26 14:11                                     ` Michael S. Tsirkin
2022-01-27  3:49                                       ` Parav Pandit
2022-01-27 13:05                                         ` Michael S. Tsirkin [this message]
2022-01-27 13:25                                           ` [virtio-dev] " Parav Pandit
2022-01-28  4:35                                     ` Jason Wang
2022-01-26  7:03                                 ` Jason Wang
2022-01-26  9:27                                   ` Max Gurtovoy
2022-01-26  9:34                                     ` Jason Wang
2022-01-26  9:45                                       ` Max Gurtovoy
2022-01-27  3:46                                         ` Jason Wang
2022-01-26  5:04                               ` Jason Wang
2022-01-26  5:26                                 ` Parav Pandit
2022-01-26  5:45                                   ` Jason Wang
2022-01-26  5:58                                     ` Parav Pandit
2022-01-26  6:06                                       ` Jason Wang
2022-01-26  6:24                                         ` Parav Pandit
2022-01-26  6:54                                           ` Jason Wang
2022-01-26  8:09                                             ` Parav Pandit
2022-01-26  9:07                                               ` Jason Wang
2022-01-26  9:47                                                 ` Parav Pandit
2022-01-13 14:51 ` [PATCH 3/5] virtio-blk: add support for VIRTIO_F_ADMIN_VQ Max Gurtovoy
2022-01-13 18:24   ` Michael S. Tsirkin
2022-01-13 14:51 ` [PATCH 4/5] virtio-net: " Max Gurtovoy
2022-01-13 17:56   ` Michael S. Tsirkin
2022-01-16  9:47     ` Max Gurtovoy
2022-01-16 16:45       ` Michael S. Tsirkin
2022-01-17 14:07       ` Parav Pandit
2022-01-17 22:22         ` Michael S. Tsirkin
2022-01-18  2:18           ` Jason Wang
2022-01-18  5:25             ` Michael S. Tsirkin
2022-01-19  4:16               ` Jason Wang
2022-01-19  9:26                 ` Michael S. Tsirkin
2022-01-25  3:53                   ` Jason Wang
2022-01-25  7:19                     ` Michael S. Tsirkin
2022-01-26  5:49                       ` Jason Wang
2022-01-26  7:02                         ` Michael S. Tsirkin
2022-01-26  7:10                           ` Jason Wang
2022-01-13 14:51 ` [PATCH 5/5] Add support for dynamic MSI-X vector mgmt for VFs Max Gurtovoy
2022-01-13 18:20   ` Michael S. Tsirkin
2022-01-18 10:38   ` Michael S. Tsirkin
2022-01-13 18:32 ` [PATCH v1 0/5] VIRTIO: Provision maximum MSI-X vectors for a VF Michael S. Tsirkin
2022-01-17 10:00   ` Shahaf Shuler
2022-01-17 21:41     ` 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=20220127075537-mutt-send-email-mst@kernel.org \
    --to=mst@redhat.com \
    --cc=cohuck@redhat.com \
    --cc=jasowang@redhat.com \
    --cc=mgurtovoy@nvidia.com \
    --cc=oren@nvidia.com \
    --cc=parav@nvidia.com \
    --cc=shahafs@nvidia.com \
    --cc=stefanha@redhat.com \
    --cc=virtio-dev@lists.oasis-open.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