[PATCH bpf-next 08/10] bpf: Add helpers to issue and check SYN cookies in XDP

[Maxim Mikityanskiy <maximmi@nvidia.com>]

The new helpers bpf_tcp_raw_{gen,check}_syncookie allow an XDP program
to generate SYN cookies in response to TCP SYN packets and to check
those cookies upon receiving the first ACK packet (the final packet of
the TCP handshake).

Unlike bpf_tcp_{gen,check}_syncookie these new helpers don't need a
listening socket on the local machine, which allows to use them together
with synproxy to accelerate SYN cookie generation.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
---
 include/net/tcp.h              |   1 +
 include/uapi/linux/bpf.h       |  57 +++++++++++++++
 net/core/filter.c              | 122 +++++++++++++++++++++++++++++++++
 net/ipv4/tcp_input.c           |   3 +-
 tools/include/uapi/linux/bpf.h |  57 +++++++++++++++
 5 files changed, 239 insertions(+), 1 deletion(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4c2898ac6569..1cc96a225848 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -431,6 +431,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
 			 struct tcphdr *th, u32 *cookie);
 u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
 			 struct tcphdr *th, u32 *cookie);
+u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss);
 u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
 			  const struct tcp_request_sock_ops *af_ops,
 			  struct sock *sk, struct tcphdr *th);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 883de3f1bb8b..e32f72077250 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4998,6 +4998,61 @@ union bpf_attr {
  *		pointer that was returned from **bpf_ct_lookup_xxx**\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie(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*, without depending on a listening
+ *		socket.
+ *
+ *		*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 (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	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** if the packet or input arguments are invalid.
+ *
+ *		**-EOPNOTSUPP** if the kernel configuration does not enable SYN
+ *		cookies (CONFIG_SYN_COOKIES is off).
+ *
+ *		**-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
+ *		CONFIG_IPV6 is disabled).
+ *
+ * int bpf_tcp_raw_check_syncookie(void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Check whether *iph* and *th* contain a valid SYN cookie ACK
+ *		without depending on a listening socket.
+ *
+ *		*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 (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	Return
+ *		0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EACCES** if the SYN cookie is not valid.
+ *
+ *		**-EINVAL** if the packet or input arguments are invalid.
+ *
+ *		**-EOPNOTSUPP** if the kernel configuration does not enable SYN
+ *		cookies (CONFIG_SYN_COOKIES is off).
+ *
+ *		**-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
+ *		CONFIG_IPV6 is disabled).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5181,6 +5236,8 @@ union bpf_attr {
 	FN(ct_lookup_tcp),		\
 	FN(ct_lookup_udp),		\
 	FN(ct_release),			\
+	FN(tcp_raw_gen_syncookie),	\
+	FN(tcp_raw_check_syncookie),	\
 	/* */
 
 /* 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 f913851c97f7..5f03d4a282a0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7285,6 +7285,124 @@ static const struct bpf_func_proto bpf_ct_release_proto = {
 };
 #endif
 
+BPF_CALL_4(bpf_tcp_raw_gen_syncookie, 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 (!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:
+		mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT;
+		cookie = __cookie_v4_init_sequence(iph, th, &mss);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case 6: {
+		const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
+
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		mss = tcp_parse_mss_option(th, 0) ?: mss_clamp;
+		cookie = __cookie_v6_init_sequence(iph, th, &mss);
+		break;
+		}
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+
+	return cookie | ((u64)mss << 32);
+#else
+	return -EOPNOTSUPP;
+#endif /* CONFIG_SYN_COOKIES */
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_proto = {
+	.func		= bpf_tcp_raw_gen_syncookie,
+	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_4(bpf_tcp_raw_check_syncookie, void *, iph, u32, iph_len,
+	   struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+	u32 cookie;
+	int ret;
+
+	if (unlikely(th_len < sizeof(*th)))
+		return -EINVAL;
+
+	if (!th->ack || th->rst || th->syn)
+		return -EINVAL;
+
+	if (unlikely(iph_len < sizeof(struct iphdr)))
+		return -EINVAL;
+
+	cookie = ntohl(th->ack_seq) - 1;
+
+	/* 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:
+		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case 6:
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+		break;
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+
+	if (ret > 0)
+		return 0;
+
+	return -EACCES;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_proto = {
+	.func		= bpf_tcp_raw_check_syncookie,
+	.gpl_only	= true, /* __cookie_v*_check is GPL */
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -7703,6 +7821,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ct_release:
 		return &bpf_ct_release_proto;
 #endif
+	case BPF_FUNC_tcp_raw_gen_syncookie:
+		return &bpf_tcp_raw_gen_syncookie_proto;
+	case BPF_FUNC_tcp_raw_check_syncookie:
+		return &bpf_tcp_raw_check_syncookie_proto;
 #endif
 	default:
 		return bpf_sk_base_func_proto(func_id);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 246ab7b5e857..659af6cc7d8c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3961,7 +3961,7 @@ static bool smc_parse_options(const struct tcphdr *th,
 /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
  * value on success.
  */
-static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
+u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
 {
 	const unsigned char *ptr = (const unsigned char *)(th + 1);
 	int length = (th->doff * 4) - sizeof(struct tcphdr);
@@ -4000,6 +4000,7 @@ static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
 	}
 	return mss;
 }
+EXPORT_SYMBOL_GPL(tcp_parse_mss_option);
 
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 883de3f1bb8b..e32f72077250 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4998,6 +4998,61 @@ union bpf_attr {
  *		pointer that was returned from **bpf_ct_lookup_xxx**\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * s64 bpf_tcp_raw_gen_syncookie(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*, without depending on a listening
+ *		socket.
+ *
+ *		*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 (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	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** if the packet or input arguments are invalid.
+ *
+ *		**-EOPNOTSUPP** if the kernel configuration does not enable SYN
+ *		cookies (CONFIG_SYN_COOKIES is off).
+ *
+ *		**-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
+ *		CONFIG_IPV6 is disabled).
+ *
+ * int bpf_tcp_raw_check_syncookie(void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ *	Description
+ *		Check whether *iph* and *th* contain a valid SYN cookie ACK
+ *		without depending on a listening socket.
+ *
+ *		*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 (at least
+ *		**sizeof**\ (**struct tcphdr**)).
+ *	Return
+ *		0 if *iph* and *th* are a valid SYN cookie ACK.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EACCES** if the SYN cookie is not valid.
+ *
+ *		**-EINVAL** if the packet or input arguments are invalid.
+ *
+ *		**-EOPNOTSUPP** if the kernel configuration does not enable SYN
+ *		cookies (CONFIG_SYN_COOKIES is off).
+ *
+ *		**-EPROTONOSUPPORT** if the IP version is not 4 or 6 (or 6, but
+ *		CONFIG_IPV6 is disabled).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5181,6 +5236,8 @@ union bpf_attr {
 	FN(ct_lookup_tcp),		\
 	FN(ct_lookup_udp),		\
 	FN(ct_release),			\
+	FN(tcp_raw_gen_syncookie),	\
+	FN(tcp_raw_check_syncookie),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.30.2