bpf: tcp: Handle BPF SYN Cookie in cookie_v[46]_check().

We will support arbitrary SYN Cookie with BPF in the following
patch.

If BPF prog validates ACK and kfunc allocates a reqsk, it will
be carried to cookie_[46]_check() as skb->sk.  If skb->sk is not
NULL, we call cookie_bpf_check().

Then, we clear skb->sk and skb->destructor, which are needed not
to hold refcnt for reqsk and the listener.  See the following patch
for details.

After that, we finish initialisation for the remaining fields with
cookie_tcp_reqsk_init().

Note that the server side WScale is set only for non-BPF SYN Cookie.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240115205514.68364-5-kuniyu@amazon.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 56 insertions, 8 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 114000e71a46..dfe99a084a71 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -599,6 +599,26 @@ static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *
 		dst_feature(dst, RTAX_FEATURE_ECN);
 }
 
+#if IS_ENABLED(CONFIG_BPF)
+static inline bool cookie_bpf_ok(struct sk_buff *skb)
+{
+	return skb->sk;
+}
+
+struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb);
+#else
+static inline bool cookie_bpf_ok(struct sk_buff *skb)
+{
+	return false;
+}
+
+static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk,
+						    struct sk_buff *skb)
+{
+	return NULL;
+}
+#endif
+
 /* From net/ipv6/syncookies.c */
 int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 981944c22820..be88bf586ff9 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -295,6 +295,24 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_BPF)
+struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb)
+{
+	struct request_sock *req = inet_reqsk(skb->sk);
+
+	skb->sk = NULL;
+	skb->destructor = NULL;
+
+	if (cookie_tcp_reqsk_init(sk, skb, req)) {
+		reqsk_free(req);
+		req = NULL;
+	}
+
+	return req;
+}
+EXPORT_SYMBOL_GPL(cookie_bpf_check);
+#endif
+
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk, struct sk_buff *skb,
 					    struct tcp_options_received *tcp_opt,
@@ -395,9 +413,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	    !th->ack || th->rst)
 		goto out;
 
-	req = cookie_tcp_check(net, sk, skb);
-	if (IS_ERR(req))
-		goto out;
+	if (cookie_bpf_ok(skb)) {
+		req = cookie_bpf_check(sk, skb);
+	} else {
+		req = cookie_tcp_check(net, sk, skb);
+		if (IS_ERR(req))
+			goto out;
+	}
 	if (!req)
 		goto out_drop;
 
@@ -445,7 +467,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
-	ireq->rcv_wscale  = rcv_wscale;
+	if (!req->syncookie)
+		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c8d2ca27220c..6b9c69278819 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -182,9 +182,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	    !th->ack || th->rst)
 		goto out;
 
-	req = cookie_tcp_check(net, sk, skb);
-	if (IS_ERR(req))
-		goto out;
+	if (cookie_bpf_ok(skb)) {
+		req = cookie_bpf_check(sk, skb);
+	} else {
+		req = cookie_tcp_check(net, sk, skb);
+		if (IS_ERR(req))
+			goto out;
+	}
 	if (!req)
 		goto out_drop;
 
@@ -247,7 +251,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
 
-	ireq->rcv_wscale = rcv_wscale;
+	if (!req->syncookie)
+		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, dst);