include/net/inet_connection_sock.h | 4 +- include/net/tcp.h | 4 +- net/dccp/dccp.h | 4 +- net/dccp/ipv4.c | 4 +- net/dccp/ipv6.c | 7 ++- net/dccp/minisocks.c | 2 +- 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 | 97 +++++++++++++----------------- net/mptcp/subflow.c | 6 +- net/smc/af_smc.c | 6 +- 13 files changed, 78 insertions(+), 70 deletions(-)
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/
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`.
- net/dccp/:
- Updated `syn_recv_sock` implementations and call sites for DCCP, which was
removed in upstream kernels prior to this commit.]
Assisted-by: Cursor:gemini-3.7-flash
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
Changes in v2:
- Updated the DCCP subsystem (net/dccp/) to handle the additional
opt_child_init argument in syn_recv_sock callback, fixing build
failures when CONFIG_IP_DCCP is enabled.
include/net/inet_connection_sock.h | 4 +-
include/net/tcp.h | 4 +-
net/dccp/dccp.h | 4 +-
net/dccp/ipv4.c | 4 +-
net/dccp/ipv6.c | 7 ++-
net/dccp/minisocks.c | 2 +-
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 | 97 +++++++++++++-----------------
net/mptcp/subflow.c | 6 +-
net/smc/af_smc.c | 6 +-
13 files changed, 78 insertions(+), 70 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index bcc138ff087b..fe4f8261c443 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;
u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1cc25e0b3bde..64c300659a8e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -464,7 +464,9 @@ 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/dccp/dccp.h b/net/dccp/dccp.h
index 1f748ed1279d..e4e055493203 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -267,7 +267,9 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *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 sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 5926159a6f20..b8f5e20368ec 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -410,7 +410,9 @@ struct sock *dccp_v4_request_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 inet_request_sock *ireq;
struct inet_sock *newinet;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d6649246188d..c1db85366747 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -419,7 +419,9 @@ static struct sock *dccp_v6_request_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 inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *newnp;
@@ -434,7 +436,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
- req_unhash, own_req);
+ req_unhash, own_req,
+ opt_child_init);
if (newsk == NULL)
return NULL;
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index fecc8190064f..49939eba8703 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -187,7 +187,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
goto drop;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
- req, &own_req);
+ req, &own_req, NULL);
if (child) {
child = inet_csk_complete_hashdance(sk, child, req, own_req);
goto out;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index facf0fa7d659..66d5272c5abb 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -202,7 +202,7 @@ 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 947109f01db6..5378ef3b6ab5 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -247,7 +247,7 @@ 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 40b73e97d5fb..2b7c580e3728 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1742,7 +1742,9 @@ 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;
@@ -1798,6 +1800,10 @@ 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 7149ddb09840..f6657c571fb7 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -859,7 +859,7 @@ 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 085fc97c5a5b..84efaf846f07 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1341,11 +1341,48 @@ 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;
+#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->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 (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))
{
struct inet_request_sock *ireq;
struct ipv6_pinfo *newnp;
@@ -1361,60 +1398,10 @@ 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);
-
- 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->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 (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 26ea58691f79..4fc9a5a78876 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -812,7 +812,9 @@ 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;
@@ -859,7 +861,7 @@ 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 8e95839161aa..98b4449131d7 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -125,7 +125,9 @@ 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;
@@ -150,7 +152,7 @@ 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);
--
2.34.1© 2016 - 2026 Red Hat, Inc.