tcp: fix potential race in tcp_v6_syn_recv_sock()

Code in tcp_v6_syn_recv_sock() after the call to tcp_v4_syn_recv_sock()
is done too late.

After tcp_v4_syn_recv_sock(), the child socket is already visible
from TCP ehash table and other cpus might use it.

Since newinet->pinet6 is still pointing to the listener ipv6_pinfo
bad things can happen as syzbot found.

Move the problematic code in tcp_v6_mapped_child_init()
and call this new helper from tcp_v4_syn_recv_sock() before
the ehash insertion.

This allows the removal of one tcp_sync_mss(), since
tcp_v4_syn_recv_sock() will call it with the correct
context.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+937b5bbb6a815b3e5d0b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/69949275.050a0220.2eeac1.0145.GAE@google.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260217161205.2079883-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

9 files changed, 66 insertions, 66 deletions

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index ecb362025c4e..5cb3056d6ddc 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -42,7 +42,9 @@ struct inet_connection_sock_af_ops {
 				      struct request_sock *req,
 				      struct dst_entry *dst,
 				      struct request_sock *req_unhash,
-				      bool *own_req);
+				      bool *own_req,
+				      void (*opt_child_init)(struct sock *newsk,
+							     const struct sock *sk));
 	u16	    net_header_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  sockptr_t optval, unsigned int optlen);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 40e72b9cb85f..eb8bf63fdafc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -544,7 +544,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req);
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk));
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
 int tcp_connect(struct sock *sk);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 569befcf021b..061751aabc8e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -203,7 +203,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 	bool own_req;
 
 	child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						 NULL, &own_req);
+						 NULL, &own_req, NULL);
 	if (child) {
 		refcount_set(&req->rsk_refcnt, 1);
 		sock_rps_save_rxhash(child, skb);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index b30090cff3cf..df803f088f45 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -333,7 +333,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	bool own_req;
 
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 NULL, &own_req);
+							 NULL, &own_req, NULL);
 	if (!child)
 		return NULL;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6264fc0b2be5..2980c175d326 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1705,7 +1705,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  struct request_sock *req,
 				  struct dst_entry *dst,
 				  struct request_sock *req_unhash,
-				  bool *own_req)
+				  bool *own_req,
+				  void (*opt_child_init)(struct sock *newsk,
+							 const struct sock *sk))
 {
 	struct inet_request_sock *ireq;
 	bool found_dup_sk = false;
@@ -1757,6 +1759,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	}
 	sk_setup_caps(newsk, dst);
 
+#if IS_ENABLED(CONFIG_IPV6)
+	if (opt_child_init)
+		opt_child_init(newsk, sk);
+#endif
 	tcp_ca_openreq_child(newsk, dst);
 
 	tcp_sync_mss(newsk, dst4_mtu(dst));
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ec128865f5c0..d9c5a43bd281 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -925,7 +925,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * socket is created, wait for troubles.
 	 */
 	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
-							 req, &own_req);
+							 req, &own_req, NULL);
 	if (!child)
 		goto listen_overflow;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d10487b4e5bf..e46a0efae012 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1312,11 +1312,48 @@ static void tcp_v6_restore_cb(struct sk_buff *skb)
 		sizeof(struct inet6_skb_parm));
 }
 
+/* Called from tcp_v4_syn_recv_sock() for v6_mapped children. */
+static void tcp_v6_mapped_child_init(struct sock *newsk, const struct sock *sk)
+{
+	struct inet_sock *newinet = inet_sk(newsk);
+	struct ipv6_pinfo *newnp;
+
+	newinet->pinet6 = newnp = tcp_inet6_sk(newsk);
+	newinet->ipv6_fl_list = NULL;
+
+	memcpy(newnp, tcp_inet6_sk(sk), sizeof(struct ipv6_pinfo));
+
+	newnp->saddr = newsk->sk_v6_rcv_saddr;
+
+	inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
+	if (sk_is_mptcp(newsk))
+		mptcpv6_handle_mapped(newsk, true);
+	newsk->sk_backlog_rcv = tcp_v4_do_rcv;
+#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
+	tcp_sk(newsk)->af_specific = &tcp_sock_ipv6_mapped_specific;
+#endif
+
+	newnp->ipv6_mc_list = NULL;
+	newnp->ipv6_ac_list = NULL;
+	newnp->pktoptions  = NULL;
+	newnp->opt	   = NULL;
+
+	/* tcp_v4_syn_recv_sock() has initialized newinet->mc_{index,ttl} */
+	newnp->mcast_oif   = newinet->mc_index;
+	newnp->mcast_hops  = newinet->mc_ttl;
+
+	newnp->rcv_flowinfo = 0;
+	if (inet6_test_bit(REPFLOW, sk))
+		newnp->flow_label = 0;
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
 					 struct request_sock *req_unhash,
-					 bool *own_req)
+					 bool *own_req,
+					 void (*opt_child_init)(struct sock *newsk,
+								const struct sock *sk))
 {
 	const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct inet_request_sock *ireq;
@@ -1332,61 +1369,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 #endif
 	struct flowi6 fl6;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		/*
-		 *	v6 mapped
-		 */
-
-		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst,
-					     req_unhash, own_req);
-
-		if (!newsk)
-			return NULL;
-
-		newinet = inet_sk(newsk);
-		newinet->pinet6 = tcp_inet6_sk(newsk);
-		newinet->ipv6_fl_list = NULL;
-
-		newnp = tcp_inet6_sk(newsk);
-		newtp = tcp_sk(newsk);
-
-		memcpy(newnp, np, sizeof(struct ipv6_pinfo));
-
-		newnp->saddr = newsk->sk_v6_rcv_saddr;
-
-		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
-		if (sk_is_mptcp(newsk))
-			mptcpv6_handle_mapped(newsk, true);
-		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
-#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
-		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
-#endif
-
-		newnp->ipv6_mc_list = NULL;
-		newnp->ipv6_ac_list = NULL;
-		newnp->pktoptions  = NULL;
-		newnp->opt	   = NULL;
-		newnp->mcast_oif   = inet_iif(skb);
-		newnp->mcast_hops  = ip_hdr(skb)->ttl;
-		newnp->rcv_flowinfo = 0;
-		if (inet6_test_bit(REPFLOW, sk))
-			newnp->flow_label = 0;
-
-		/*
-		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
-		 * here, tcp_create_openreq_child now does this for us, see the comment in
-		 * that function for the gory details. -acme
-		 */
-
-		/* It is tricky place. Until this moment IPv4 tcp
-		   worked with IPv6 icsk.icsk_af_ops.
-		   Sync it now.
-		 */
-		tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
-
-		return newsk;
-	}
-
+	if (skb->protocol == htons(ETH_P_IP))
+		return tcp_v4_syn_recv_sock(sk, skb, req, dst,
+					    req_unhash, own_req,
+					    tcp_v6_mapped_child_init);
 	ireq = inet_rsk(req);
 
 	if (sk_acceptq_is_full(sk))
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index f66129f1e649..8b25dd86ffeb 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -808,7 +808,9 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
@@ -855,7 +857,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 create_child:
 	child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
-						     req_unhash, own_req);
+						     req_unhash, own_req, opt_child_init);
 
 	if (child && *own_req) {
 		struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index d8201eb3ac5f..18c56b0d7ad5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -124,7 +124,9 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 					  struct request_sock *req,
 					  struct dst_entry *dst,
 					  struct request_sock *req_unhash,
-					  bool *own_req)
+					  bool *own_req,
+					  void (*opt_child_init)(struct sock *newsk,
+								 const struct sock *sk))
 {
 	struct smc_sock *smc;
 	struct sock *child;
@@ -142,7 +144,7 @@ static struct sock *smc_tcp_syn_recv_sock(const struct sock *sk,
 
 	/* passthrough to original syn recv sock fct */
 	child = smc->ori_af_ops->syn_recv_sock(sk, skb, req, dst, req_unhash,
-					       own_req);
+					       own_req, opt_child_init);
 	/* child must not inherit smc or its ops */
 	if (child) {
 		rcu_assign_sk_user_data(child, NULL);