From: "Michael S. Tsirkin" <mst@redhat.com>
To: Eli Cohen <elic@nvidia.com>
Cc: eperezma@redhat.com, parav@mellanox.com,
virtualization@lists.linux-foundation.org
Subject: Re: [PATCH v3 2/2] vdpa/mlx5: Make VIRTIO_NET_F_MRG_RXBUF off by default
Date: Tue, 21 Mar 2023 05:29:41 -0400 [thread overview]
Message-ID: <20230321052812-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <ff359e29-8249-8a6f-7cd3-77c5c43ff96c@nvidia.com>
On Tue, Mar 21, 2023 at 11:24:34AM +0200, Eli Cohen wrote:
>
> On 20/03/2023 22:02, Michael S. Tsirkin wrote:
> > On Mon, Mar 20, 2023 at 01:49:30PM +0200, Eli Cohen wrote:
> > > One can still enable it when creating the vdpa device using vdpa tool by
> > > providing features that include it.
> > >
> > > For example:
> > > $ vdpa dev add name vdpa0 mgmtdev pci/0000:86:00.2 device_features 0x300cb982b
> > >
> > > Please be aware that this feature was not supported before the previous
> > > patch in this list was introduced so we don't change user experience.
> > so I would say the patches have to be reordered to avoid a regression?
> Yes, I can do that.
> >
> > > Current firmware versions show degradation in packet rate when using
> > > MRG_RXBUF. Users who favor memory saving over packet rate could enable
> > > this feature but we want to keep it off by default.
> > >
> > > Signed-off-by: Eli Cohen <elic@nvidia.com>
> > OK and when future firmware will (maybe) fix this up how
> > will you know it's ok to enable by default?
> > Some version check I guess?
> > It would be better if firmware specified flags to enable
> > by default ...
> Currently there are no flags for that so let's just keep the default off.
Right but I mean, why are mrg buffers slow? It's a firmware bug right?
> >
> > > ---
> > > drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 ++
> > > 1 file changed, 2 insertions(+)
> > >
> > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > index 5285dd76c793..24397a71d6f3 100644
> > > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > @@ -3146,6 +3146,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
> > > return -EINVAL;
> > > }
> > > device_features &= add_config->device_features;
> > > + } else {
> > > + device_features &= ~BIT_ULL(VIRTIO_NET_F_MRG_RXBUF);
> > > }
> > > if (!(device_features & BIT_ULL(VIRTIO_F_VERSION_1) &&
> > > device_features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) {
> > > --
> > > 2.38.1
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2023-03-21 9:29 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20230320114930.8457-1-elic@nvidia.com>
[not found] ` <20230320114930.8457-3-elic@nvidia.com>
2023-03-20 20:02 ` [PATCH v3 2/2] vdpa/mlx5: Make VIRTIO_NET_F_MRG_RXBUF off by default Michael S. Tsirkin
[not found] ` <ff359e29-8249-8a6f-7cd3-77c5c43ff96c@nvidia.com>
2023-03-21 9:29 ` Michael S. Tsirkin [this message]
[not found] ` <20230320114930.8457-2-elic@nvidia.com>
2023-03-21 4:49 ` [PATCH v3 1/2] vdpa/mlx5: Extend driver support for new features Si-Wei Liu
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=20230321052812-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=elic@nvidia.com \
--cc=eperezma@redhat.com \
--cc=parav@mellanox.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).