On 10/19/21 7:46 AM, Maxim Mikityanskiy wrote:
> The new helper bpf_tcp_raw_gen_tscookie allows an XDP program to
> generate timestamp cookies (to be used together with SYN cookies) which
> encode different options set by the client in the SYN packet: SACK
> support, ECN support, window scale. These options are encoded in lower
> bits of the timestamp, which will be returned by the client in a
> subsequent ACK packet. The format is the same used by synproxy.
>
> Signed-off-by: Maxim Mikityanskiy <maximmi@xxxxxxxxxx>
> Reviewed-by: Tariq Toukan <tariqt@xxxxxxxxxx>
> ---
> include/net/tcp.h | 1 +
> include/uapi/linux/bpf.h | 27 +++++++++++++++
> net/core/filter.c | 38 +++++++++++++++++++++
> net/ipv4/syncookies.c | 60 ++++++++++++++++++++++++++++++++++
> tools/include/uapi/linux/bpf.h | 27 +++++++++++++++
> 5 files changed, 153 insertions(+)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 1cc96a225848..651820bef6a2 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -564,6 +564,7 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th,
> u16 *mssp);
> __u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss);
> u64 cookie_init_timestamp(struct request_sock *req, u64 now);
> +bool cookie_init_timestamp_raw(struct tcphdr *th, __be32 *tsval, __be32 *tsecr);
> bool cookie_timestamp_decode(const struct net *net,
> struct tcp_options_received *opt);
> bool cookie_ecn_ok(const struct tcp_options_received *opt,
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index e32f72077250..791790b41874 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -5053,6 +5053,32 @@ union bpf_attr {
> *
> * **-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
> * CONFIG_IPV6 is disabled).
> + *
> + * int bpf_tcp_raw_gen_tscookie(struct tcphdr *th, u32 th_len, __be32 *tsopt, u32 tsopt_len)
> + * Description
> + * Try to generate a timestamp cookie which encodes some of the
> + * flags sent by the client in the SYN packet: SACK support, ECN
> + * support, window scale. To be used with SYN cookies.
> + *
> + * *th* points to the start of the TCP header of the client's SYN
> + * packet, while *th_len* contains the length of the TCP header (at
> + * least **sizeof**\ (**struct tcphdr**)).
> + *
> + * *tsopt* points to the output location where to put the resulting
> + * timestamp values: tsval and tsecr, in the format of the TCP
> + * timestamp option.
> + *
> + * Return
> + * On success, 0.
> + *
> + * On failure, the returned value is one of the following:
> + *
> + * **-EINVAL** if the input arguments are invalid.
> + *
> + * **-ENOENT** if the TCP header doesn't have the timestamp option.
> + *
> + * **-EOPNOTSUPP** if the kernel configuration does not enable SYN
> + * cookies (CONFIG_SYN_COOKIES is off).
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -5238,6 +5264,7 @@ union bpf_attr {
> FN(ct_release), \
> FN(tcp_raw_gen_syncookie), \
> FN(tcp_raw_check_syncookie), \
> + FN(tcp_raw_gen_tscookie), \
> /* */
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 5f03d4a282a0..73fe20ef7442 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -7403,6 +7403,42 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_proto = {
> .arg4_type = ARG_CONST_SIZE,
> };
>
> +BPF_CALL_4(bpf_tcp_raw_gen_tscookie, struct tcphdr *, th, u32, th_len,
> + __be32 *, tsopt, u32, tsopt_len)
> +{
> + int err;
> +
> +#ifdef CONFIG_SYN_COOKIES
> + if (tsopt_len != sizeof(u64)) {
> + err = -EINVAL;
> + goto err_out;
> + }
> +
> + if (!cookie_init_timestamp_raw(th, &tsopt[0], &tsopt[1])) {
> + err = -ENOENT;
> + goto err_out;
> + }
> +
> + return 0;
> +err_out:
> +#else
> + err = -EOPNOTSUPP;
> +#endif
> + memset(tsopt, 0, tsopt_len);
> + return err;
> +}
> +
> +static const struct bpf_func_proto bpf_tcp_raw_gen_tscookie_proto = {
> + .func = bpf_tcp_raw_gen_tscookie,
> + .gpl_only = false,
> + .pkt_access = true,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_MEM,
> + .arg2_type = ARG_CONST_SIZE,
> + .arg3_type = ARG_PTR_TO_UNINIT_MEM,
> + .arg4_type = ARG_CONST_SIZE,
> +};
> +
> #endif /* CONFIG_INET */
>
> bool bpf_helper_changes_pkt_data(void *func)
> @@ -7825,6 +7861,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> return &bpf_tcp_raw_gen_syncookie_proto;
> case BPF_FUNC_tcp_raw_check_syncookie:
> return &bpf_tcp_raw_check_syncookie_proto;
> + case BPF_FUNC_tcp_raw_gen_tscookie:
> + return &bpf_tcp_raw_gen_tscookie_proto;
> #endif
> default:
> return bpf_sk_base_func_proto(func_id);
> diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
> index 8696dc343ad2..4dd2c7a096eb 100644
> --- a/net/ipv4/syncookies.c
> +++ b/net/ipv4/syncookies.c
> @@ -85,6 +85,66 @@ u64 cookie_init_timestamp(struct request_sock *req, u64 now)
> return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ);
> }
>
> +bool cookie_init_timestamp_raw(struct tcphdr *th, __be32 *tsval, __be32 *tsecr)
> +{
> + int length = (th->doff * 4) - sizeof(*th);
> + u8 wscale = TS_OPT_WSCALE_MASK;
> + bool option_timestamp = false;
> + bool option_sack = false;
> + u32 cookie;
> + u8 *ptr;
> +
> + ptr = (u8 *)(th + 1);
> +
> + while (length > 0) {
> + u8 opcode = *ptr++;
> + u8 opsize;
> +
> + if (opcode == TCPOPT_EOL)
> + break;
> + if (opcode == TCPOPT_NOP) {
> + length--;
> + continue;
> + }
> +
> + if (length < 2)
> + break;
> + opsize = *ptr++;
> + if (opsize < 2)
> + break;
> + if (opsize > length)
> + break;
> +
> + switch (opcode) {
> + case TCPOPT_WINDOW:
You must check osize.
> + wscale = min_t(u8, *ptr, TCP_MAX_WSCALE);
> + break;
> + case TCPOPT_TIMESTAMP:
You must check opsize.
> + option_timestamp = true;
> + /* Client's tsval becomes our tsecr. */
> + *tsecr = cpu_to_be32(get_unaligned_be32(ptr));
Please avoid useless ntohl/htonl dance (even if compiler probably optimizes this)
No need to obfuscate :)
*tsecr = get_unaligned((__be32 *)ptr);
> + break;
> + case TCPOPT_SACK_PERM:
> + option_sack = true;
> + break;
> + }
> +
> + ptr += opsize - 2;
> + length -= opsize;
> + }
> +
> + if (!option_timestamp)
> + return false;
> +
> + cookie = tcp_time_stamp_raw() & ~TSMASK;
> + cookie |= wscale & TS_OPT_WSCALE_MASK;
> + if (option_sack)
> + cookie |= TS_OPT_SACK;
> + if (th->ece && th->cwr)
> + cookie |= TS_OPT_ECN;
> + *tsval = cpu_to_be32(cookie);
> + return true;
> +}
>
> static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
> __be16 dport, __u32 sseq, __u32 data)
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index e32f72077250..791790b41874 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
> @@ -5053,6 +5053,32 @@ union bpf_attr {
> *
> * **-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
> * CONFIG_IPV6 is disabled).
> + *
> + * int bpf_tcp_raw_gen_tscookie(struct tcphdr *th, u32 th_len, __be32 *tsopt, u32 tsopt_len)
> + * Description
> + * Try to generate a timestamp cookie which encodes some of the
> + * flags sent by the client in the SYN packet: SACK support, ECN
> + * support, window scale. To be used with SYN cookies.
> + *
> + * *th* points to the start of the TCP header of the client's SYN
> + * packet, while *th_len* contains the length of the TCP header (at
> + * least **sizeof**\ (**struct tcphdr**)).
> + *
> + * *tsopt* points to the output location where to put the resulting
> + * timestamp values: tsval and tsecr, in the format of the TCP
> + * timestamp option.
> + *
> + * Return
> + * On success, 0.
> + *
> + * On failure, the returned value is one of the following:
> + *
> + * **-EINVAL** if the input arguments are invalid.
> + *
> + * **-ENOENT** if the TCP header doesn't have the timestamp option.
> + *
> + * **-EOPNOTSUPP** if the kernel configuration does not enable SYN
> + * cookies (CONFIG_SYN_COOKIES is off).
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -5238,6 +5264,7 @@ union bpf_attr {
> FN(ct_release), \
> FN(tcp_raw_gen_syncookie), \
> FN(tcp_raw_check_syncookie), \
> + FN(tcp_raw_gen_tscookie), \
> /* */
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
>
