From 8cc3aef0cb198049805ecc061a2cc7b79b0ae43e Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 4 Sep 2026 03:35:28 +0000 Subject: [PATCH 1/2] tcp: Do not allow buggy transitions between ehash and lhash2. 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 Closes: https://lore.kernel.org/netdev/20260731140512.566464-1-david.lee@trailofbits.com/ Reported-by: Michal Luczaj Closes: https://lore.kernel.org/netdev/20260803-sockmap-lookup-tcp-leak-v2-0-306e025bfe66@rbox.co/ Reported-by: Hyunwoo Kim Closes: https://lore.kernel.org/netdev/20260824033331.1084971-1-imv4bel@gmail.com/ Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260904033543.2635540-2-kuniyu@google.com Signed-off-by: Jakub Kicinski --- 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, From 31c5ea8a3296e1486ac34bccea452bfe8c0bb1f9 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 4 Sep 2026 03:35:29 +0000 Subject: [PATCH 2/2] ipv6: Remove IPV6_ADDRFORM. Recently, IPV6_ADDRFORM has received many AI-driven bug reports. Fixing them properly would needlessly churn the fast paths in TCP and UDP. IPV6_ADDRFORM was initially introduced in RFC 2133 in 1997, but only two years later, it was removed from RFC 2553 in 1999. In 2026, modern applications natively support dual-stack sockets; notably, systemd's socket activation does not use IPV6_ADDRFORM. Also, getsockopt(IPV6_ADDRFORM) can be replaced with SO_DOMAIN. Let's remove IPV6_ADDRFORM. Later, we can remove sk->sk_prot_creator and revert commit c26c192c3d48 ("udp: properly deal with xfrm encap and ADDRFORM"). Reported-by: Daehyeon Ko <4ncienth@gmail.com> Closes: https://lore.kernel.org/netdev/20260902010408.1057857-1-4ncienth@gmail.com/ Reported-by: Hyunwoo Kim Closes: https://lore.kernel.org/netdev/20260824033331.1084971-1-imv4bel@gmail.com/ Signed-off-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260904033543.2635540-3-kuniyu@google.com Signed-off-by: Jakub Kicinski --- include/linux/net.h | 2 +- net/core/sock.c | 4 +- net/ipv4/af_inet.c | 3 -- net/ipv6/af_inet6.c | 4 -- net/ipv6/ipv6_sockglue.c | 87 ---------------------------------------- 5 files changed, 2 insertions(+), 98 deletions(-) diff --git a/include/linux/net.h b/include/linux/net.h index 3d82966e2243..470100ae7107 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -166,7 +166,7 @@ struct socket { struct file *file; struct sock *sk; - const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ + const struct proto_ops *ops; /* Might change with MPTCP. */ struct socket_wq wq; }; diff --git a/net/core/sock.c b/net/core/sock.c index fa60b7494c58..1d5927cd49a1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -770,7 +770,7 @@ bool sk_mc_loop(const struct sock *sk) return false; if (!sk) return true; - /* IPV6_ADDRFORM can change sk->sk_family under us. */ + switch (READ_ONCE(sk->sk_family)) { case AF_INET: return inet_test_bit(MC_LOOP, sk); @@ -4010,7 +4010,6 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->getsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_getsockopt); @@ -4032,7 +4031,6 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ return READ_ONCE(sk->sk_prot)->setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(sock_common_setsockopt); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 32d006c1a8ee..d9421ac38d78 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -582,7 +582,6 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr, if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (uaddr->sa_family == AF_UNSPEC) @@ -789,7 +788,6 @@ int inet_accept(struct socket *sock, struct socket *newsock, { struct sock *sk1 = sock->sk, *sk2; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ arg->err = -EINVAL; sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, arg); if (!sk2) @@ -875,7 +873,6 @@ void inet_splice_eof(struct socket *sock) if (unlikely(inet_send_prepare(sk))) return; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (prot->splice_eof) prot->splice_eof(sock); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 282912a11999..f0efdc13baf4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -429,7 +429,6 @@ int inet6_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) const struct proto *prot; int err = 0; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); /* If the socket has its own bind function then use it. */ if (prot->bind) @@ -567,7 +566,6 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCSIFDSTADDR: return addrconf_set_dstaddr(net, argp); default: - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); if (!prot->ioctl) return -ENOIOCTLCMD; @@ -636,7 +634,6 @@ int inet6_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (unlikely(inet_send_prepare(sk))) return -EAGAIN; - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); return INDIRECT_CALL_2(prot->sendmsg, tcp_sendmsg, udpv6_sendmsg, sk, msg, size); @@ -651,7 +648,6 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (likely(!(flags & MSG_ERRQUEUE))) sock_rps_record_flow(sk); - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ prot = READ_ONCE(sk->sk_prot); return INDIRECT_CALL_2(prot->recvmsg, tcp_recvmsg, udpv6_recvmsg, sk, msg, size, flags); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index b4c977434c2e..1f68fb64a43e 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -547,86 +547,7 @@ int do_ipv6_setsockopt(struct sock *sk, int level, int optname, sockopt_lock_sock(sk); - /* Another thread has converted the socket into IPv4 with - * IPV6_ADDRFORM concurrently. - */ - if (unlikely(sk->sk_family != AF_INET6)) - goto unlock; - switch (optname) { - - case IPV6_ADDRFORM: - if (optlen < sizeof(int)) - goto e_inval; - if (val == PF_INET) { - if (sk->sk_type == SOCK_RAW) - break; - - if (sk->sk_protocol == IPPROTO_UDP) { - if (udp_sk(sk)->pending == AF_INET6) { - retv = -EBUSY; - break; - } - } else if (sk->sk_protocol == IPPROTO_TCP) { - if (sk->sk_prot != &tcpv6_prot) { - retv = -EBUSY; - break; - } - } else { - break; - } - - if (sk->sk_state != TCP_ESTABLISHED) { - retv = -ENOTCONN; - break; - } - - if (ipv6_only_sock(sk) || - !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - retv = -EADDRNOTAVAIL; - break; - } - - __ipv6_sock_mc_close(sk); - __ipv6_sock_ac_close(sk); - - if (sk->sk_protocol == IPPROTO_TCP) { - struct inet_connection_sock *icsk = inet_csk(sk); - - sock_prot_inuse_add(net, sk->sk_prot, -1); - sock_prot_inuse_add(net, &tcp_prot, 1); - - /* Paired with READ_ONCE(sk->sk_prot) in inet6_stream_ops */ - WRITE_ONCE(sk->sk_prot, &tcp_prot); - /* Paired with READ_ONCE() in tcp_(get|set)sockopt() */ - WRITE_ONCE(icsk->icsk_af_ops, &ipv4_specific); - WRITE_ONCE(sk->sk_socket->ops, &inet_stream_ops); - WRITE_ONCE(sk->sk_family, PF_INET); - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - } else { - sock_prot_inuse_add(net, sk->sk_prot, -1); - sock_prot_inuse_add(net, &udp_prot, 1); - - /* Paired with READ_ONCE(sk->sk_prot) in inet6_dgram_ops */ - WRITE_ONCE(sk->sk_prot, &udp_prot); - WRITE_ONCE(sk->sk_socket->ops, &inet_dgram_ops); - WRITE_ONCE(sk->sk_family, PF_INET); - } - - /* Disable all options not to allocate memory anymore, - * but there is still a race. See the lockless path - * in udpv6_sendmsg() and ipv6_local_rxpmtu(). - */ - np->rxopt.all = 0; - - inet6_cleanup_sock(sk); - - module_put(THIS_MODULE); - retv = 0; - break; - } - goto e_inval; - case IPV6_V6ONLY: if (optlen < sizeof(int) || inet_sk(sk)->inet_num) @@ -1088,14 +1009,6 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; switch (optname) { - case IPV6_ADDRFORM: - if (sk->sk_protocol != IPPROTO_UDP && - sk->sk_protocol != IPPROTO_TCP) - return -ENOPROTOOPT; - if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTCONN; - val = sk->sk_family; - break; case MCAST_MSFILTER: if (in_compat_syscall()) return compat_ipv6_get_msfilter(sk, optval, optlen, len);