[PATCH v1 net-next 1/2] tcp: Do not allow buggy transitions between ehash and lhash2.

[Kuniyuki Iwashima <kuniyu@google.com>]

The following state transitions have long been a playground for
syzbot, and recently AI joined in, reporting a lot more bugs.

  * listen() + shutdown() + connect()
  * connect() + connect(AF_UNSPEC) + listen()

All the fix attempts would add more code to the fast path, which
is not worth it.

Instead of playing whack-a-mole with these edge-case bugs,
let's disallow these transitions.

Note that unhashed_state is placed in the 4-byte hole after
icsk_pmtu_cookie.

  $ pahole -C inet_connection_sock vmlinux
  struct inet_connection_sock {
  ...
	__u32                      icsk_pmtu_cookie;     /*  1208     4 */
	unsigned char              unhashed_state;       /*  1212     1 */

	/* XXX 3 bytes hole, try to pack */

Reported-by: Kyle Zeng <kylebot@openai.com>
Closes: https://lore.kernel.org/netdev/20260731140512.566464-1-david.lee@trailofbits.com/
Reported-by: Michal Luczaj <mhal@rbox.co>
Closes: https://lore.kernel.org/netdev/20260803-sockmap-lookup-tcp-leak-v2-0-306e025bfe66@rbox.co/
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Closes: https://lore.kernel.org/netdev/20260824033331.1084971-1-imv4bel@gmail.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 include/net/inet_connection_sock.h |  1 +
 net/ipv4/inet_connection_sock.c    |  1 +
 net/ipv4/inet_hashtables.c         | 11 +++++++++++
 3 files changed, 13 insertions(+)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 433c2df23076..903499581db7 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -94,6 +94,7 @@ struct inet_connection_sock {
 	u32			  icsk_rto_max;
 	__u32                     icsk_delack_max;
 	__u32			  icsk_pmtu_cookie;
+	unsigned char		  unhashed_state;
 	const struct tcp_congestion_ops *icsk_ca_ops;
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	const struct tcp_ulp_ops  *icsk_ulp_ops;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 6257459bcee2..560ca861b6d0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1253,6 +1253,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	memset(&newicsk->icsk_accept_queue, 0,
 	       sizeof(newicsk->icsk_accept_queue));
 
+	newicsk->unhashed_state = 0;
 	inet_sk_set_state(newsk, TCP_SYN_RECV);
 
 	inet_clone_ulp(req, newsk, priority);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ba0faa9ae2bb..5abcb0debb27 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -803,6 +803,11 @@ int inet_hash(struct sock *sk)
 	inet_init_ehash_secret();
 
 	WARN_ON(!sk_unhashed(sk));
+
+	if (unlikely(inet_csk(sk)->unhashed_state &&
+		     inet_csk(sk)->unhashed_state != TCP_LISTEN))
+		return -EINVAL;
+
 	ilb2 = inet_lhash2_bucket_sk(hashinfo, sk);
 
 	spin_lock(&ilb2->lock);
@@ -832,6 +837,9 @@ void inet_unhash(struct sock *sk)
 		return;
 
 	sock_rps_delete_flow(sk);
+
+	inet_csk(sk)->unhashed_state = sk->sk_state;
+
 	if (sk->sk_state == TCP_LISTEN) {
 		struct inet_listen_hashbucket *ilb2;
 
@@ -1058,6 +1066,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	int ret, i, low, high;
 	bool local_ports;
 
+	if (unlikely(inet_csk(sk)->unhashed_state == TCP_LISTEN))
+		return -EINVAL;
+
 	if (port) {
 		local_bh_disable();
 		ret = check_established(death_row, sk, port, NULL, false,
-- 
2.55.0.1003.g10538fe699-goog