netdev - Re: [RFC PATCH 5/9] virtio_net: build xdp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACGkMEvBDmGdP7e1c-8s2OQFEYQ2LLbhnDF+qN+yPVwvkxPjCw@mail.gmail.com>
Date:   Tue, 6 Dec 2022 14:14:04 +0800
From:   Jason Wang <jasowang@...hat.com>
To:     Heng Qi <hengqi@...ux.alibaba.com>
Cc:     netdev@...r.kernel.org, bpf@...r.kernel.org,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Paolo Abeni <pabeni@...hat.com>,
        Jakub Kicinski <kuba@...nel.org>,
        John Fastabend <john.fastabend@...il.com>,
        "David S. Miller" <davem@...emloft.net>,
        Daniel Borkmann <daniel@...earbox.net>,
        Alexei Starovoitov <ast@...nel.org>,
        Eric Dumazet <edumazet@...gle.com>
Subject: Re: [RFC PATCH 5/9] virtio_net: build xdp_buff with multi buffers

On Tue, Nov 22, 2022 at 3:44 PM Heng Qi <hengqi@...ux.alibaba.com> wrote:
>
> Support xdp for multi buffer packets.
>
> Putting the first buffer as the linear part for xdp_buff,
> and the rest of the buffers as non-linear fragments to struct
> skb_shared_info in the tailroom belonging to xdp_buff.
>
> Signed-off-by: Heng Qi <hengqi@...ux.alibaba.com>
> Reviewed-by: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
> ---
>  drivers/net/virtio_net.c | 74 ++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 74 insertions(+)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index cd65f85d5075..20784b1d8236 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -911,6 +911,80 @@ static struct sk_buff *receive_big(struct net_device *dev,
>         return NULL;
>  }
>
> +static int virtnet_build_xdp_buff(struct net_device *dev,
> +                                 struct virtnet_info *vi,
> +                                 struct receive_queue *rq,
> +                                 struct xdp_buff *xdp,
> +                                 void *buf,
> +                                 unsigned int len,
> +                                 unsigned int frame_sz,
> +                                 u16 *num_buf,
> +                                 unsigned int *xdp_frags_truesize,
> +                                 struct virtnet_rq_stats *stats)
> +{
> +       unsigned int tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
> +       struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
> +       unsigned int truesize, headroom;
> +       struct skb_shared_info *shinfo;
> +       unsigned int xdp_frags_truesz = 0;
> +       unsigned int cur_frag_size;
> +       struct page *page;
> +       skb_frag_t *frag;
> +       int offset;
> +       void *ctx;
> +
> +       xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq);
> +       xdp_prepare_buff(xdp, buf - VIRTIO_XDP_HEADROOM,
> +                        VIRTIO_XDP_HEADROOM + vi->hdr_len, len - vi->hdr_len, true);
> +       shinfo = xdp_get_shared_info_from_buff(xdp);
> +       shinfo->nr_frags = 0;
> +       shinfo->xdp_frags_size = 0;
> +
> +       if ((*num_buf - 1) > MAX_SKB_FRAGS)
> +               return -EINVAL;
> +
> +       while ((--*num_buf) >= 1) {
> +               buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);

So this works only for a mergeable buffer, I wonder if it's worth it
to make it work for big mode as well. Or at least we can mention it as
a TODO somewhere and rename this function (with mergeable suffix).

Others look good.

Thanks

> +               if (unlikely(!buf)) {
> +                       pr_debug("%s: rx error: %d buffers out of %d missing\n",
> +                                dev->name, *num_buf,
> +                                virtio16_to_cpu(vi->vdev, hdr->num_buffers));
> +                       dev->stats.rx_length_errors++;
> +                       return -EINVAL;
> +               }
> +
> +               if (!xdp_buff_has_frags(xdp))
> +                       xdp_buff_set_frags_flag(xdp);
> +
> +               stats->bytes += len;
> +               page = virt_to_head_page(buf);
> +               offset = buf - page_address(page);
> +               truesize = mergeable_ctx_to_truesize(ctx);
> +               headroom = mergeable_ctx_to_headroom(ctx);
> +
> +               cur_frag_size = truesize + (headroom ? (headroom + tailroom) : 0);
> +               xdp_frags_truesz += cur_frag_size;
> +               if (unlikely(len > truesize || cur_frag_size > PAGE_SIZE)) {
> +                       pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
> +                                dev->name, len, (unsigned long)ctx);
> +                       dev->stats.rx_length_errors++;
> +                       return -EINVAL;
> +               }
> +
> +               frag = &shinfo->frags[shinfo->nr_frags++];
> +               __skb_frag_set_page(frag, page);
> +               skb_frag_off_set(frag, offset);
> +               skb_frag_size_set(frag, len);
> +               if (page_is_pfmemalloc(page))
> +                       xdp_buff_set_frag_pfmemalloc(xdp);
> +
> +               shinfo->xdp_frags_size += len;
> +       }
> +
> +       *xdp_frags_truesize = xdp_frags_truesz;
> +       return 0;
> +}
> +
>  static struct sk_buff *receive_mergeable(struct net_device *dev,
>                                          struct virtnet_info *vi,
>                                          struct receive_queue *rq,
> --
> 2.19.1.6.gb485710b
>