Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230727172354.68243-2-dtatulea@nvidia.com> <CACGkMEt5+O1Q1=SvPpD5kwhEnoLNva73Uew0vaWBVXW3xE-o0Q@mail.gmail.com>
In-Reply-To: <CACGkMEt5+O1Q1=SvPpD5kwhEnoLNva73Uew0vaWBVXW3xE-o0Q@mail.gmail.com>
From:   Lei Yang <leiyang@redhat.com>
Date:   Wed, 2 Aug 2023 08:29:23 +0800
Message-ID: <CAPpAL=yA-H8OXSz0XmVNff7isCS9Zq8UiH9L+zq6B27aOJrrZg@mail.gmail.com>
Subject: Re: [PATCH] vdpa/mlx5: Correct default number of queues when MQ is on
To:     Dragos Tatulea <dtatulea@nvidia.com>
Cc:     "Michael S. Tsirkin" <mst@redhat.com>,
        Xuan Zhuo <xuanzhuo@linux.alibaba.com>,
        =?UTF-8?Q?Eugenio_P=C3=A9rez?= <eperezma@redhat.com>,
        virtualization@lists.linux-foundation.org,
        linux-kernel@vger.kernel.org, Jason Wang <jasowang@redhat.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

QE performed sanity testing on this patch using a real nic's
vhost_vdpa device with multi queues, everything works fine.

Tested-by: Lei Yang <leiyang@redhat.com>


On Fri, Jul 28, 2023 at 9:42=E2=80=AFAM Jason Wang <jasowang@redhat.com> wr=
ote:
>
> On Fri, Jul 28, 2023 at 1:25=E2=80=AFAM Dragos Tatulea <dtatulea@nvidia.c=
om> wrote:
> >
> > The standard specifies that the initial number of queues is the
> > default, which is 1 (1 tx, 1 rx).
> >
> > Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
> > Reviewed-by: Eugenio P=C3=A9rez <eperezma@redhat.com>
>
> Acked-by: Jason Wang <jasowang@redhat.com>
>
> Thanks
>
> > ---
> >  drivers/vdpa/mlx5/net/mlx5_vnet.c | 10 +++++++++-
> >  1 file changed, 9 insertions(+), 1 deletion(-)
> >
> > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/=
mlx5_vnet.c
> > index 9138ef2fb2c8..6b6eb69a8a90 100644
> > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > @@ -2517,7 +2517,15 @@ static int mlx5_vdpa_set_driver_features(struct =
vdpa_device *vdev, u64 features)
> >         else
> >                 ndev->rqt_size =3D 1;
> >
> > -       ndev->cur_num_vqs =3D 2 * ndev->rqt_size;
> > +       /* Device must start with 1 queue pair, as per VIRTIO v1.2 spec=
, section
> > +        * 5.1.6.5.5 "Device operation in multiqueue mode":
> > +        *
> > +        * Multiqueue is disabled by default.
> > +        * The driver enables multiqueue by sending a command using cla=
ss
> > +        * VIRTIO_NET_CTRL_MQ. The command selects the mode of multique=
ue
> > +        * operation, as follows: ...
> > +        */
> > +       ndev->cur_num_vqs =3D 2;
> >
> >         update_cvq_info(mvdev);
> >         return err;
> > --
> > 2.41.0
> >
>