Petar Penkov <ppenkov.ker...@gmail.com> writes:
> From: Petar Penkov <ppen...@google.com>
>
> This helper function allows BPF programs to try to generate SYN
> cookies, given a reference to a listener socket. The function works
> from XDP and with an skb context since bpf_skc_lookup_tcp can lookup a
> socket in both cases.
>
> Signed-off-by: Petar Penkov <ppen...@google.com>
> Suggested-by: Eric Dumazet <eduma...@google.com>
> ---
> include/uapi/linux/bpf.h | 30 ++++++++++++++++-
> net/core/filter.c | 73 ++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 102 insertions(+), 1 deletion(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index 6f68438aa4ed..20baee7b2219 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2713,6 +2713,33 @@ union bpf_attr {
> * **-EPERM** if no permission to send the *sig*.
> *
> * **-EAGAIN** if bpf program can try again.
> + *
> + * s64 bpf_tcp_gen_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len,
> struct tcphdr *th, u32 th_len)
> + * Description
> + * Try to issue a SYN cookie for the packet with corresponding
> + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*.
> + *
> + * *iph* points to the start of the IPv4 or IPv6 header, while
> + * *iph_len* contains **sizeof**\ (**struct iphdr**) or
> + * **sizeof**\ (**struct ip6hdr**).
> + *
> + * *th* points to the start of the TCP header, while *th_len*
> + * contains the length of the TCP header.
> + *
> + * Return
> + * On success, lower 32 bits hold the generated SYN cookie in
> + * followed by 16 bits which hold the MSS value for that cookie,
> + * and the top 16 bits are unused.
> + *
> + * On failure, the returned value is one of the following:
> + *
> + * **-EINVAL** SYN cookie cannot be issued due to error
> + *
> + * **-ENOENT** SYN cookie should not be issued (no SYN flood)
> + *
> + * **-ENOTSUPP** kernel configuration does not enable SYN
> cookies
nit: This should be EOPNOTSUPP - the other one is for NFS...
> + *
> + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -2824,7 +2851,8 @@ union bpf_attr {
> FN(strtoul), \
> FN(sk_storage_get), \
> FN(sk_storage_delete), \
> - FN(send_signal),
> + FN(send_signal), \
> + FN(tcp_gen_syncookie),
>
> /* 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 47f6386fb17a..92114271eff6 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5850,6 +5850,75 @@ static const struct bpf_func_proto
> bpf_tcp_check_syncookie_proto = {
> .arg5_type = ARG_CONST_SIZE,
> };
>
> +BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32,
> iph_len,
> + struct tcphdr *, th, u32, th_len)
> +{
> +#ifdef CONFIG_SYN_COOKIES
> + u32 cookie;
> + u16 mss;
> +
> + if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
> + return -EINVAL;
> +
> + if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
> + return -EINVAL;
> +
> + if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
> + return -ENOENT;
> +
> + if (!th->syn || th->ack || th->fin || th->rst)
> + return -EINVAL;
> +
> + if (unlikely(iph_len < sizeof(struct iphdr)))
> + return -EINVAL;
> +
> + /* Both struct iphdr and struct ipv6hdr have the version field at the
> + * same offset so we can cast to the shorter header (struct iphdr).
> + */
> + switch (((struct iphdr *)iph)->version) {
> + case 4:
> + if (sk->sk_family == AF_INET6 && sk->sk_ipv6only)
> + return -EINVAL;
> +
> + mss = tcp_v4_get_syncookie(sk, iph, th, &cookie);
> + break;
> +
> +#if IS_BUILTIN(CONFIG_IPV6)
> + case 6:
> + if (unlikely(iph_len < sizeof(struct ipv6hdr)))
> + return -EINVAL;
> +
> + if (sk->sk_family != AF_INET6)
> + return -EINVAL;
> +
> + mss = tcp_v6_get_syncookie(sk, iph, th, &cookie);
> + break;
> +#endif /* CONFIG_IPV6 */
> +
> + default:
> + return -EPROTONOSUPPORT;
> + }
> + if (mss <= 0)
> + return -ENOENT;
> +
> + return cookie | ((u64)mss << 32);
> +#else
> + return -ENOTSUPP;
See above
> +#endif /* CONFIG_SYN_COOKIES */
> +}
> +
> +static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
> + .func = bpf_tcp_gen_syncookie,
> + .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */
> + .pkt_access = true,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_SOCK_COMMON,
> + .arg2_type = ARG_PTR_TO_MEM,
> + .arg3_type = ARG_CONST_SIZE,
> + .arg4_type = ARG_PTR_TO_MEM,
> + .arg5_type = ARG_CONST_SIZE,
> +};
> +
> #endif /* CONFIG_INET */
>
> bool bpf_helper_changes_pkt_data(void *func)
> @@ -6135,6 +6204,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const
> struct bpf_prog *prog)
> return &bpf_tcp_check_syncookie_proto;
> case BPF_FUNC_skb_ecn_set_ce:
> return &bpf_skb_ecn_set_ce_proto;
> + case BPF_FUNC_tcp_gen_syncookie:
> + return &bpf_tcp_gen_syncookie_proto;
> #endif
> default:
> return bpf_base_func_proto(func_id);
> @@ -6174,6 +6245,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct
> bpf_prog *prog)
> return &bpf_xdp_skc_lookup_tcp_proto;
> case BPF_FUNC_tcp_check_syncookie:
> return &bpf_tcp_check_syncookie_proto;
> + case BPF_FUNC_tcp_gen_syncookie:
> + return &bpf_tcp_gen_syncookie_proto;
> #endif
> default:
> return bpf_base_func_proto(func_id);
> --
> 2.22.0.657.g960e92d24f-goog
