> Similar to native xdp, do not always linearize the skb in
> netif_receive_generic_xdp routine but create a non-linear xdp_buff to be
> processed by the eBPF program. This allow to add multi-buffer support
> for xdp running in generic mode.
>
> Signed-off-by: Lorenzo Bianconi <lorenzo@xxxxxxxxxx>
> ---
> net/core/dev.c | 28 +++++++++++++++++++++++-----
> 1 file changed, 23 insertions(+), 5 deletions(-)
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 3950ced396b5..5a58f3e28657 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -4853,6 +4853,12 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
> xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq);
> xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len,
> skb_headlen(skb) + mac_len, true);
> + if (skb_is_nonlinear(skb)) {
> + skb_shinfo(skb)->xdp_frags_size = skb->data_len;
> + xdp_buff_set_frags_flag(xdp);
> + } else {
> + xdp_buff_clear_frags_flag(xdp);
> + }
>
> orig_data_end = xdp->data_end;
> orig_data = xdp->data;
> @@ -4882,6 +4888,14 @@ u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
> skb->len += off; /* positive on grow, negative on shrink */
> }
>
> + /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
> + * (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
> + */
> + if (xdp_buff_has_frags(xdp))
> + skb->data_len = skb_shinfo(skb)->xdp_frags_size;
> + else
> + skb->data_len = 0;
> +
> /* check if XDP changed eth hdr such SKB needs update */
> eth = (struct ethhdr *)xdp->data;
> if ((orig_eth_type != eth->h_proto) ||
> @@ -4927,9 +4941,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
> if (skb_is_redirected(skb))
> return XDP_PASS;
>
> - /* XDP packets must be linear and must have sufficient headroom
> - * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
> - * native XDP provides, thus we need to do it here as well.
> + /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM
> + * bytes. This is the guarantee that also native XDP provides,
> + * thus we need to do it here as well.
> */
> if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
> skb_headroom(skb) < XDP_PACKET_HEADROOM) {
> @@ -4943,8 +4957,12 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
> hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
> troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
> goto do_drop;
> - if (skb_linearize(skb))
> - goto do_drop;
> +
> + /* XDP does not support fraglist */
> + if (skb_has_frag_list(skb) || !xdp_prog->aux->xdp_has_frags) {
> + if (skb_linearize(skb))
> + goto do_drop;
@Jakub: iirc we were discussing something similar for veth [0].
Here pskb_expand_head() reallocates skb paged data (skb_shinfo()->frags[])
just if the skb is cloned and if it is zero-copied [1] while in skb_cow_data()
we always reallocate the paged area if skb_shinfo()->nr_frags is set [2].
Since the eBPF program can theoretically modify paged data, I would say we
should do the same we did for veth even here, right?
Regards,
Lorenzo
[0] https://lore.kernel.org/netdev/20220312131806.1c2919ba@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
[1] https://elixir.bootlin.com/linux/v6.6.2/source/net/core/skbuff.c#L2113
[2] https://elixir.bootlin.com/linux/v6.6.2/source/net/core/skbuff.c#L5016
> + }
> }
>
> act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
> --
> 2.43.0
>
Attachment:
signature.asc
Description: PGP signature
