Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 7 Jun 2021 08:51:59 +0300
From:   Leon Romanovsky <leon@kernel.org>
To:     Jason Wang <jasowang@redhat.com>
Cc:     Eli Cohen <elic@nvidia.com>, mst@redhat.com,
        virtualization@lists.linux-foundation.org,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH] vdp/mlx5: Fix setting the correct dma_device
Message-ID: <YL2z/4RT/nwHscYE@unreal>
References: <20210603112215.69259-1-elic@nvidia.com>
 <864e8d21-22d4-7735-817b-f88ec0126f87@redhat.com>
 <YLpNc5WsBWQ5f4cl@unreal>
 <c083f4b2-aa0a-ad3c-7a16-fe1c7dbda92d@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <c083f4b2-aa0a-ad3c-7a16-fe1c7dbda92d@redhat.com>
Precedence: bulk

On Mon, Jun 07, 2021 at 10:30:42AM +0800, Jason Wang wrote:
> 
> 在 2021/6/4 下午11:57, Leon Romanovsky 写道:
> > On Fri, Jun 04, 2021 at 10:35:59AM +0800, Jason Wang wrote:
> > > 在 2021/6/3 下午7:22, Eli Cohen 写道:
> > > > Before SF support was introduced, the DMA device was equal to
> > > > mdev->device which was in essence equal to pdev->dev;
> > > > With SF introduction this is no longer true. It has already been
> > > > handled for vhost_vdpa since the reference to the dma device can from
> > > > within mlx5_vdpa. With virtio_vdpa this broke. To fix this we set the
> > > > real dma device when initializing the device.
> > > > 
> > > > Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
> > > 
> > > Note sure this is correct, according to the commit log it should be the
> > > patch that introduces the SF or aux bus support for vDPA.
> > Where did you see that?
> > 
> > git log -p drivers/vdpa/mlx5/net/mlx5_vnet.c
> > 
> > ...
> > +       mvdev->vdev.dma_dev = mdev->device;
> > +       err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
> > ...
> >   comes from commit 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
> 
> 
> If I read the commit log and code correctly:
> 
> "
> 
> With SF introduction this is no longer true.
> 
> "
> 
> It works before SF is introduced.

Yes, you are right, sorry for the noise.

> 
> Thanks
> 
> 
> > 
> > Thanks
> > 
> > > 
> > > > Signed-off-by: Eli Cohen <elic@nvidia.com>
> > > 
> > > Patch looks correct.
> > > 
> > > Thanks
> > > 
> > > 
> > > > ---
> > > >    drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +-
> > > >    1 file changed, 1 insertion(+), 1 deletion(-)
> > > > 
> > > > diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > > index bc33f2c523d3..a4ff158181e0 100644
> > > > --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > > +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
> > > > @@ -2046,7 +2046,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
> > > >    	if (err)
> > > >    		goto err_mtu;
> > > > -	mvdev->vdev.dma_dev = mdev->device;
> > > > +	mvdev->vdev.dma_dev = &mdev->pdev->dev;
> > > >    	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
> > > >    	if (err)
> > > >    		goto err_mtu;
> > > _______________________________________________
> > > Virtualization mailing list
> > > Virtualization@lists.linux-foundation.org
> > > https://lists.linuxfoundation.org/mailman/listinfo/virtualization
>