Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH bpf-next v4] virtio_net: add XDP meta data support
To:     Yuya Kusakabe <yuya.kusakabe@gmail.com>
Cc:     ast@kernel.org, daniel@iogearbox.net, davem@davemloft.net,
        hawk@kernel.org, john.fastabend@gmail.com, kafai@fb.com,
        mst@redhat.com, songliubraving@fb.com, yhs@fb.com, kuba@kernel.org,
        andriin@fb.com, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, bpf@vger.kernel.org
References: <8da1b560-3128-b885-b453-13de5c7431fb@redhat.com>
 <20200204071655.94474-1-yuya.kusakabe@gmail.com>
 <9a0a1469-c8a7-8223-a4d5-dad656a142fc@redhat.com>
 <1100837f-075f-dc97-cd14-758c96f2ac1d@gmail.com>
From:   Jason Wang <jasowang@redhat.com>
Message-ID: <0c5eaba2-dd5a-fc3f-0e8f-154f7ad52881@redhat.com>
Date:   Thu, 6 Feb 2020 11:20:24 +0800
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.8.0
MIME-Version: 1.0
In-Reply-To: <1100837f-075f-dc97-cd14-758c96f2ac1d@gmail.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


On 2020/2/5 =E4=B8=8B=E5=8D=885:18, Yuya Kusakabe wrote:
>>>  =C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0 case XDP_TX:
>>>  =C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=
=A0=C2=A0 stats->xdp_tx++;
>>> +=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0=C2=A0 x=
dp.data_meta =3D xdp.data;
>> Any reason for doing this?
> XDP_TX can not support metadata for now, because if metasize > 0, __vir=
tnet_xdp_xmit_one() returns EOPNOTSUPP.
>
> static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
> 				   struct send_queue *sq,
> 				   struct xdp_frame *xdpf)
> {
> 	struct virtio_net_hdr_mrg_rxbuf *hdr;
> 	int err;
>
> 	/* virtqueue want to use data area in-front of packet */
> 	if (unlikely(xdpf->metasize > 0))
> 		return -EOPNOTSUPP;
>
>

I see.

Then I think it's better to fix __virtnet_xdp_xmit_one() instead.

Thanks