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 +- net/smc/af_smc.c | 6 +- 9 files changed, 66 insertions(+), 66 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`.
- 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)`.]
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 +-
net/smc/af_smc.c | 6 +-
9 files changed, 66 insertions(+), 66 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7a015055fe6d..97e8969b3796 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 be91d81d66ab..dc532cbde05e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -446,7 +446,9 @@ 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 03b0505178f9..5a61f9a364ad 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 1c50867d3e7e..f3ed7d5ff7ef 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -251,7 +251,7 @@ 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 f7693166c516..32b55a6b5e03 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1556,7 +1556,9 @@ 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;
@@ -1612,6 +1614,10 @@ 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 061225d645e6..be4fb0ce2574 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -769,7 +769,7 @@ 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 dea59b123eb7..77069176137d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1234,11 +1234,48 @@ 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;
@@ -1254,61 +1291,10 @@ 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 2ec22660ba7a..33b16ea7ae5b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -670,7 +670,9 @@ 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;
@@ -720,7 +722,7 @@ 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 fe014abcfa4f..1fa44d64958c 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -76,7 +76,9 @@ 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;
@@ -101,7 +103,7 @@ 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);
--
2.34.1Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
New issues:
- [Low] The patch adds a 7th argument (`opt_child_init`) to the `syn_recv_sock` function pointer in `struct inet_connection_sock_af_ops`, but completely fails to update the DCCP subsystem. This breaks the build for DCCP.
Pre-existing issues:
- [Critical] This problem wasn't introduced by this patch, but if route lookup fails when creating an IPv4-mapped IPv6 child socket, the listener's IPv6 resources are erroneously freed.
- [High] This problem wasn't introduced by this patch, but the exact race condition fixed by this patch in TCP is also present in DCCP's IPv6-mapped implementation, which remains unfixed.
--
commit eed5a807840b9b1bb7db87da21b6f743e2ad19f8
Author: Eric Dumazet <edumazet@google.com>
tcp: fix potential race in tcp_v6_syn_recv_sock()
This commit addresses a race condition in tcp_v6_syn_recv_sock() where the
child socket is visible in the TCP ehash table before its ipv6_pinfo is
fully initialized. It moves the initialization code into a new helper
tcp_v6_mapped_child_init() and passes it to tcp_v4_syn_recv_sock() to run
before ehash insertion.
Link: https://lore.kernel.org/netdev/69949275.050a0220.2eeac1.0145.GAE@google.com/
Link: https://patch.msgid.link/20260217161205.2079883-1-edumazet@google.com
> diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
> index 7a015055fe6db..97e8969b37967 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));
[Severity: Low]
Does this change break the build for DCCP? The patch adds the opt_child_init
argument to the syn_recv_sock function pointer, but does not appear to
update the DCCP subsystem. Calling syn_recv_sock with 6 arguments in
net/dccp/minisocks.c:dccp_check_req(), and defining
dccp_v4_request_recv_sock() and dccp_v6_request_recv_sock() without the 7th
argument will likely cause compiler errors.
[Severity: High]
This is a pre-existing issue, but does the same race condition you fixed
here in TCP also affect DCCP?
In net/dccp/ipv6.c:dccp_v6_request_recv_sock(), the IPv6 fields for mapped
sockets are initialized after the socket is already created and inserted
into the ehash by dccp_v4_request_recv_sock():
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst, req_unhash, own_req);
if (newsk == NULL) return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
This appears to leave pinet6 pointing to the listener while the child socket
is already visible to other CPUs, exposing the same race.
[ ... ]
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index f7693166c5161..32b55a6b5e033 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
[ ... ]
> @@ -1612,6 +1614,10 @@ 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
[Severity: Critical]
This is a pre-existing issue, but can this lead to freeing the listener's
IPv6 resources if route lookup fails?
If inet_csk_route_child_sock() fails before opt_child_init() is called
in tcp_v4_syn_recv_sock():
if (!dst) {
dst = inet_csk_route_child_sock(sk, newsk, req);
if (!dst)
goto put_and_exit;
}
It jumps directly to the put_and_exit label where tcp_done(newsk) is called
to destroy the child socket. Since pinet6 has not yet been reassigned by
opt_child_init(), it still points to the listener's ipv6_pinfo. This appears
to incorrectly free the listener's resources, such as pktoptions and rxpmtu,
which could lead to a double-free or use-after-free on the listener.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260903000029.3508006-2-florian.fainelli@broadcom.com?part=1
© 2016 - 2026 Red Hat, Inc.