From: Petar Penkov <ppenkov@xxxxxxxxxx>
This patch allows generation of a SYN cookie before an SKB has been
allocated, as is the case at XDP.
Signed-off-by: Petar Penkov <ppenkov@xxxxxxxxxx>
---
include/net/tcp.h | 11 +++++++
net/ipv4/tcp_input.c | 76 ++++++++++++++++++++++++++++++++++++++++++++
net/ipv4/tcp_ipv4.c | 8 +++++
net/ipv6/tcp_ipv6.c | 8 +++++
4 files changed, 103 insertions(+)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index cca3c59b98bf..a128e22c0d5d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -414,6 +414,17 @@ void tcp_parse_options(const struct net *net, const struct sk_buff *skb,
int estab, struct tcp_fastopen_cookie *foc);
const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
+/*
+ * BPF SKB-less helpers
+ */
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+ struct tcphdr *tch, u32 *cookie);
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+ struct tcphdr *tch, u32 *cookie);
+u16 tcp_get_syncookie(struct request_sock_ops *rsk_ops,
+ const struct tcp_request_sock_ops *af_ops,
+ struct sock *sk, void *iph, struct tcphdr *tch,
+ u32 *cookie);
/*
* TCP v4 functions exported for the inet6 API
*/
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8892df6de1d4..893b275a6d49 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3782,6 +3782,49 @@ static void smc_parse_options(const struct tcphdr *th,
#endif
}
+/* 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)
+{
+ const unsigned char *ptr = (const unsigned char *)(th + 1);
+ int length = (th->doff * 4) - sizeof(struct tcphdr);
+ u16 mss = 0;
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ switch (opcode) {
+ case TCPOPT_EOL:
+ return mss;
+ case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
+ length--;
+ continue;
+ default:
+ if (length < 2)
+ return mss;
+ opsize = *ptr++;
+ if (opsize < 2) /* "silly options" */
+ return mss;
+ if (opsize > length)
+ return mss; /* fail on partial options */
+ if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) {
+ u16 in_mss = get_unaligned_be16(ptr);
+
+ if (in_mss) {
+ if (user_mss && user_mss < in_mss)
+ in_mss = user_mss;
+ mss = in_mss;
+ }
+ }
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+ }
+ return mss;
+}
+
/* 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
* the fast version below fails.
@@ -6464,6 +6507,39 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
}
}
+u16 tcp_get_syncookie(struct request_sock_ops *rsk_ops,
+ const struct tcp_request_sock_ops *af_ops,
+ struct sock *sk, void *iph, struct tcphdr *th,
+ u32 *cookie)
+{
+ u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+ bool is_v4 = rsk_ops->family == AF_INET;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
+ !inet_csk_reqsk_queue_is_full(sk))
+ return 0;
+
+ if (!tcp_syn_flood_action(sk, rsk_ops->slab_name))
+ return 0;
+
+ if (sk_acceptq_is_full(sk)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
+ return 0;
+ }
+
+ mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss);
+ if (!mss)
+ mss = af_ops->mss_clamp;
+
+ tcp_synq_overflow(sk);
+ *cookie = is_v4 ? __cookie_v4_init_sequence(iph, th, &mss)
+ : __cookie_v6_init_sequence(iph, th, &mss);
+#endif
+ return mss;
+}
+
int tcp_conn_request(struct request_sock_ops *rsk_ops,
const struct tcp_request_sock_ops *af_ops,
struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d57641cb3477..0e06e59784bd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1515,6 +1515,14 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
return sk;
}
+u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph,
+ struct tcphdr *tch, u32 *cookie)
+{
+ return tcp_get_syncookie(&tcp_request_sock_ops,
+ &tcp_request_sock_ipv4_ops, sk, iph, tch,
+ cookie);
+}
+
/* The socket must have it's spinlock held when we get
* here, unless it is a TCP_LISTEN socket.
*
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5da069e91cac..102f68c3152d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1063,6 +1063,14 @@ static struct sock *tcp_v6_cookie_check(struct sock *sk, struct sk_buff *skb)
return sk;
}
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+ struct tcphdr *tch, u32 *cookie)
+{
+ return tcp_get_syncookie(&tcp6_request_sock_ops,
+ &tcp_request_sock_ipv6_ops, sk, iph, tch,
+ cookie);
+}
+
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
--
2.22.0.657.g960e92d24f-goog
