[PATCH stable 5.10.y] tcp: fix potential race in tcp_v6_syn_recv_sock()
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: 2026-09-03 00:00:42
Also in:
lkml, mptcp, stable
Subsystem:
networking [general], networking [mptcp], networking [tcp], the rest · Maintainers:
"David S. Miller", Eric Dumazet, Jakub Kicinski, Paolo Abeni, Matthieu Baerts, Mat Martineau, Neal Cardwell, Linus Torvalds
From: Eric Dumazet <edumazet@google.com>
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/ (local)
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>
(cherry picked from commit 858d2a4f67ff69e645a43487ef7ea7f28f06deae)
[florian:
- net/ipv6/tcp_ipv6.c:
- Set `newnp->ipv6_fl_list = NULL` instead of `newinet->ipv6_fl_list = NULL`,
as `ipv6_fl_list` is in `struct ipv6_pinfo`.
- Guarded `af_specific` assignment with `#ifdef CONFIG_TCP_MD5SIG` instead
of checking `CONFIG_TCP_AO`.
- Used `if (tcp_inet6_sk(sk)->repflow)` instead of `inet6_test_bit(REPFLOW, sk)`.
- net/smc/af_smc.c:
- Dropped changes to net/smc/af_smc.c because SMC did not implement
`smc_tcp_syn_recv_sock()` in 5.10.y (added in 5.14 via commit e94a869818ab).]
Assisted-by: Cursor:gemini-3.7-flash
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
include/net/inet_connection_sock.h | 4 +-
include/net/tcp.h | 4 +-
net/ipv4/syncookies.c | 2 +-
net/ipv4/tcp_fastopen.c | 2 +-
net/ipv4/tcp_ipv4.c | 8 ++-
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv6/tcp_ipv6.c | 98 +++++++++++++-----------------
net/mptcp/subflow.c | 6 +-
8 files changed, 62 insertions(+), 64 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index cfb66f5a5076..ba99da8eedb7 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h@@ -41,7 +41,9 @@ 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; u16 net_frag_header_len; u16 sockaddr_len;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4c87936a33d6..5488e66ee69a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h@@ -438,7 +438,9 @@ 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 *uaddr, int addr_len); int tcp_connect(struct sock *sk);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index cc860f2dcf65..29fb93cb3228 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c@@ -201,7 +201,7 @@ 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); tcp_sk(child)->tsoffset = tsoff;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 92d63cf3e50b..edaa6dabfc3c 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c@@ -262,7 +262,7 @@ 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 855cca214a02..f1e10db3d625 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c@@ -1535,7 +1535,9 @@ 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;
@@ -1591,6 +1593,10 @@ 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, dst_mtu(dst));
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 866055e1b801..876104fe47bf 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c@@ -770,7 +770,7 @@ 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 523aa2efdc49..12118d5d98a1 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c@@ -1217,11 +1217,48 @@ 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); + + 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; +#ifdef CONFIG_TCP_MD5SIG + tcp_sk(newsk)->af_specific = &tcp_sock_ipv6_mapped_specific; +#endif + + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + newnp->ipv6_fl_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 (tcp_inet6_sk(sk)->repflow) + 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)) { struct inet_request_sock *ireq; struct ipv6_pinfo *newnp;
@@ -1237,61 +1274,10 @@ 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; - - inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); - - newinet = inet_sk(newsk); - 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; -#ifdef CONFIG_TCP_MD5SIG - newtp->af_specific = &tcp_sock_ipv6_mapped_specific; -#endif - - newnp->ipv6_mc_list = NULL; - newnp->ipv6_ac_list = NULL; - newnp->ipv6_fl_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 (np->repflow) - 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 b13cd310882d..c9cf0fdbfbdc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c@@ -532,7 +532,9 @@ 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;
@@ -582,7 +584,7 @@ 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);
--
2.34.1