tcp: add skb-less helpers to retrieve SYN cookie

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@google.com>
Reviewed-by: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e5cf514..fb7e153 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -414,6 +414,16 @@ 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 *th, u32 *cookie);
+u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph,
+                        struct tcphdr *th, u32 *cookie);
+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);
 /*
  *     TCP v4 functions exported for the inet6 API
  */

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8892df6..706cbb3 100644 (file)
--- 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 +6507,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
        }
 }
 
+/* If a SYN cookie is required and supported, returns a clamped MSS value to be
+ * used for SYN cookie generation.
+ */
+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)
+{
+       struct tcp_sock *tp = tcp_sk(sk);
+       u16 mss;
+
+       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;
+
+       return mss;
+}
+EXPORT_SYMBOL_GPL(tcp_get_syncookie_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 d57641c..1021739 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1515,6 +1515,21 @@ 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 *th, u32 *cookie)
+{
+       u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+       mss = tcp_get_syncookie_mss(&tcp_request_sock_ops,
+                                   &tcp_request_sock_ipv4_ops, sk, th);
+       if (mss) {
+               *cookie = __cookie_v4_init_sequence(iph, th, &mss);
+               tcp_synq_overflow(sk);
+       }
+#endif
+       return mss;
+}
+
 /* 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 5da069e..87f44d3 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1063,6 +1063,21 @@ 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 *th, u32 *cookie)
+{
+       u16 mss = 0;
+#ifdef CONFIG_SYN_COOKIES
+       mss = tcp_get_syncookie_mss(&tcp6_request_sock_ops,
+                                   &tcp_request_sock_ipv6_ops, sk, th);
+       if (mss) {
+               *cookie = __cookie_v6_init_sequence(iph, th, &mss);
+               tcp_synq_overflow(sk);
+       }
+#endif
+       return mss;
+}
+
 static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
        if (skb->protocol == htons(ETH_P_IP))