On 02/23/2019 02:06 AM, brakmo wrote:
> This patch adds a new bpf helper BPF_FUNC_skb_ecn_set_ce
> "int bpf_skb_ecn_set_ce(struct sk_buff *skb)". It is added to
> BPF_PROG_TYPE_CGROUP_SKB typed bpf_prog which currently can
> be attached to the ingress and egress path. The helper is needed
> because his type of bpf_prog cannot modify the skb directly.
>
> This helper is used to set the ECN field of ECN capable IP packets to ce
> (congestion encountered) in the IPv6 or IPv4 header of the skb. It can be
> used by a bpf_prog to manage egress or ingress network bandwdith limit
> per cgroupv2 by inducing an ECN response in the TCP sender.
> This works best when using DCTCP.
>
> Signed-off-by: Lawrence Brakmo <bra...@fb.com>
> ---
> include/uapi/linux/bpf.h | 10 +++++++++-
> net/core/filter.c | 14 ++++++++++++++
> 2 files changed, 23 insertions(+), 1 deletion(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 95b5058fa945..fc646f3eaf9b 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2365,6 +2365,13 @@ union bpf_attr {
> * Make a tcp_sock enter CWR state.
> * Return
> * 0 on success, or a negative error in case of failure.
> + *
> + * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
> + * Description
> + * Sets ECN of IP header to ce (congestion encountered) if
> + * current value is ect (ECN capable). Works with IPv6 and IPv4.
> + * Return
> + * 1 if set, 0 if not set.
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -2464,7 +2471,8 @@ union bpf_attr {
> FN(spin_unlock), \
> FN(sk_fullsock), \
> FN(tcp_sock), \
> - FN(tcp_enter_cwr),
> + FN(tcp_enter_cwr), \
> + FN(skb_ecn_set_ce),
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> * function eBPF program intends to call
> diff --git a/net/core/filter.c b/net/core/filter.c
> index ca57ef25279c..955369c6ed30 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5444,6 +5444,18 @@ static const struct bpf_func_proto
> bpf_tcp_enter_cwr_proto = {
> .ret_type = RET_INTEGER,
> .arg1_type = ARG_PTR_TO_TCP_SOCK,
> };
> +
> +BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
> +{
> + return INET_ECN_set_ce(skb);
Hm, but as mentioned last time, don't we have to ensure here that skb
is writable (aka skb->data private to us before writing into it)?
> +}
> +
> +static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
> + .func = bpf_skb_ecn_set_ce,
> + .gpl_only = false,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_CTX,
> +};
> #endif /* CONFIG_INET */
>
> bool bpf_helper_changes_pkt_data(void *func)
> @@ -5610,6 +5622,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, struct
> bpf_prog *prog)
> } else {
> return NULL;
> }
> + case BPF_FUNC_skb_ecn_set_ce:
> + return &bpf_skb_ecn_set_ce_proto;
> #endif
> default:
> return sk_filter_func_proto(func_id, prog);
>
Thanks,
Daniel
