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(-)
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)`.
- 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);
--
2.34.1Thank 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` callback but fails to update the DCCP subsystem, leading to compilation errors.
Pre-existing issues:
- [Critical] This problem wasn't introduced by this patch, but the error path in tcp_v4_syn_recv_sock() frees the listening socket's IPv6 options via a stale pinet6 pointer.
- [High] This problem wasn't introduced by this patch, but the exact data race condition fixed for TCP IPv6-mapped sockets was left unfixed for DCCP IPv6-mapped sockets.
--
commit 9fb42b0dda20f2c1f24b669590d7c23a325895a3
Author: Eric Dumazet <edumazet@google.com>
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. 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.
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 cfb66f5a50766..ba99da8eedb75 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;
[Severity: Low]
Does the DCCP subsystem need to be updated for this new 7th argument?
The syn_recv_sock callback signature now requires 7 arguments, but it looks
like dccp_v4_request_recv_sock() and dccp_v6_request_recv_sock() might
still be using 6 arguments, and dccp_check_req() in net/dccp/minisocks.c
might be missing the 7th argument in its call. Could this cause a build
failure when CONFIG_IP_DCCP is enabled due to an arity mismatch?
[Severity: High]
This is a pre-existing issue, but does DCCP have the same race condition for
IPv6-mapped sockets that this patch fixes for TCP?
Looking at dccp_v6_request_recv_sock() in net/dccp/ipv6.c:
dccp_v6_request_recv_sock() {
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst, ...);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
...
}
It appears that dccp_v4_request_recv_sock() publishes the child socket to
the ehash table before dccp_v6_request_recv_sock() initializes its pinet6
pointer. Can a concurrent thread looking up the ehash table access the
partially initialized DCCP socket?
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 855cca214a021..f1e10db3d6253 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
[ ... ]
> @@ -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));
[Severity: Critical]
This isn't a bug introduced by this patch, but does placing the
opt_child_init() callback here leave a window for a use-after-free on the
listener's IPv6 options in the error path?
When an IPv4 SYN packet is received on an IPv6-mapped TCP listener,
tcp_create_openreq_child() bitwise-copies the listener's memory into the
new socket, meaning newinet->pinet6 points to the listener's ipv6_pinfo.
If routing fails before reaching this new callback, such as when processing
an unroutable spoofed source IP:
tcp_v4_syn_recv_sock() {
newsk = tcp_create_openreq_child(sk, req, skb);
...
if (!dst) {
dst = inet_csk_route_child_sock(sk, newsk, req);
if (!dst)
goto put_and_exit;
}
...
if (opt_child_init)
opt_child_init(newsk, sk);
...
put_and_exit:
newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
...
}
The error path put_and_exit will call tcp_done(newsk) and destroy the
child socket. Since opt_child_init() hasn't reassigned pinet6 yet, won't
the child socket's destructor free the listener's IPv6 options (pktoptions,
rxpmtu, opt) while the listener is still actively using them?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260903000029.3508006-1-florian.fainelli@broadcom.com?part=1
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
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 | 97 +++++++++++++-----------------
net/mptcp/subflow.c | 6 +-
net/smc/af_smc.c | 6 +-
9 files changed, 66 insertions(+), 65 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3eb715f66cbf..b7935e293757 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 net_frag_header_len;
u16 sockaddr_len;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 23d830a7a6c8..7392f51a3479 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -461,7 +461,9 @@ 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 e14356207795..9deeb3f8215e 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -199,7 +199,7 @@ 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 408985eb74ee..51bd11588d6d 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 3f9e1cfde008..163c8726a17d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1566,7 +1566,9 @@ 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;
@@ -1622,6 +1624,10 @@ 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 86f0feb2497f..d6d64697ce89 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -817,7 +817,7 @@ 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 689c0b383ebf..f13fdd1214aa 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1180,11 +1180,48 @@ 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;
@@ -1200,60 +1237,10 @@ 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;
-#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 d3b5c2d48b53..db2e3a1ebb6e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -788,7 +788,9 @@ 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;
@@ -834,7 +836,7 @@ 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 087102ff3c64..dba856528890 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -119,7 +119,9 @@ 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;
@@ -144,7 +146,7 @@ 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 4 potential issue(s) to consider:
New issues:
- [Low] The DCCP subsystem was not updated to handle the new `syn_recv_sock` function pointer signature, resulting in a build failure and Control Flow Integrity (CFI) violations.
Pre-existing issues:
- [Critical] Use-After-Free and Double-Free of listener's `ipv6_pinfo` on the `tcp_v4_syn_recv_sock` error path.
- [High] The patch leaves the identical ehash race condition completely unfixed in the DCCP subsystem.
- [High] The `opt_child_init` callback is non-composable and ignored by IPv6, leaving wrapper ULPs (SMC, MPTCP) vulnerable to the same ehash race condition.
--
commit 1232c8e7afdc63a365473845ad392043814df4fb
Author: Eric Dumazet <edumazet@google.com>
tcp: fix potential race in tcp_v6_syn_recv_sock()
This commit fixes a race condition where a child socket is inserted into the
TCP ehash table while its newinet->pinet6 still points to the listener's
IPv6 info. It introduces a new opt_child_init callback parameter to
syn_recv_sock to perform the initialization before ehash insertion.
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
> --- 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));
[Severity: Low]
Does this break the DCCP subsystem?
The DCCP implementations of syn_recv_sock (dccp_v4_request_recv_sock and
dccp_v6_request_recv_sock) were not updated to accept this new 7th parameter.
Since dccp_check_req() still passes 6 arguments, this appears to cause a
direct compilation error (too few arguments). If compiled with loose
warnings and kCFI enabled, it could also cause pointer mismatch panics at
runtime.
[Severity: High]
This is a pre-existing issue, but does this leave the identical ehash race
condition unfixed in DCCP?
dccp_v6_request_recv_sock() calls dccp_v4_request_recv_sock(), which inserts
the socket into the ehash via inet_ehash_nolisten(). Only after it returns
does dccp_v6_request_recv_sock() initialize newinet->pinet6. A lockless
reader (like sock_diag or BPF) can access the socket from the ehash in this
window and observe the listener's pinet6 pointer, which is exactly the race
condition this patch fixes for TCP.
[ ... ]
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1622,6 +1624,10 @@ 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 is there a use-after-free of the listener's
ipv6_pinfo if routing fails earlier in this function?
If inet_csk_route_child_sock() fails before sk_setup_caps() and this new
opt_child_init() call:
if (!dst) {
dst = inet_csk_route_child_sock(sk, newsk, req);
if (!dst)
goto put_and_exit;
}
The code jumps to put_and_exit, which destroys the child socket:
put_and_exit:
newinet->inet_opt = NULL;
inet_csk_prepare_forced_close(newsk);
tcp_done(newsk);
goto exit;
Since put_and_exit calls tcp_done() before opt_child_init() has repointed
pinet6 to the child's own memory, pinet6 still points to the listener. The
destruction path will free the listener's pktoptions, rxpmtu, and opt while
the listener is still active, causing a double-free memory corruption.
[ ... ]
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1200,60 +1237,10 @@ 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)) {
[ ... ]
> + 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);
[Severity: High]
This is a pre-existing issue, but by overriding opt_child_init with a
hardcoded tcp_v6_mapped_child_init callback here, does this leave wrapper
ULPs like SMC and MPTCP vulnerable to the same ehash race condition?
Because tcp_v6_syn_recv_sock() ignores the passed opt_child_init callback for
IPv6 (and hardcodes it for v4-mapped), wrapper ULPs cannot use it to
initialize their state before ehash insertion.
[ ... ]
> diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
> --- a/net/mptcp/subflow.c
> +++ b/net/mptcp/subflow.c
> @@ -834,7 +836,7 @@ 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);
[Severity: High]
This is a pre-existing issue, but since MPTCP mutates ctx->conn via
mptcp_sk_clone_init() after syn_recv_sock() returns, does this create a race
window where lockless readers can access the listener's state on the newly
hashed child?
This seems especially problematic for IPv6 because the passed opt_child_init
callback is completely ignored by tcp_v6_syn_recv_sock().
[ ... ]
> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
> --- a/net/smc/af_smc.c
> +++ b/net/smc/af_smc.c
> @@ -144,7 +146,7 @@ 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);
[Severity: High]
This is a pre-existing issue, but does clearing the inherited user data via
rcu_assign_sk_user_data(child, NULL) here occur too late?
Because this happens after syn_recv_sock() has already hashed the child
socket globally, there is a window where lockless readers can access the
listener's SMC state on the child socket. Again, this is exacerbated for IPv6
where the opt_child_init callback is ignored.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260903000029.3508006-4-florian.fainelli@broadcom.com?part=1
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 | 97 +++++++++++++-----------------
net/mptcp/subflow.c | 6 +-
net/smc/af_smc.c | 6 +-
9 files changed, 66 insertions(+), 65 deletions(-)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 7649d4901f0c..3d19420dce51 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 net_frag_header_len;
u16 sockaddr_len;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9632ac801e01..b54fd01c5bed 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -468,7 +468,9 @@ 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 f9514cf87649..d7202f86566a 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -199,7 +199,7 @@ 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 cbce1306bb08..c99f10786c1f 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 753a881ce3cd..ec3b0aa0a626 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1509,7 +1509,9 @@ 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;
@@ -1565,6 +1567,10 @@ 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 22b5748a6ee2..67735100f9ac 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -780,7 +780,7 @@ 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 3d909982d818..d3952b058453 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1191,11 +1191,48 @@ 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;
@@ -1211,60 +1248,10 @@ 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;
-#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 bdf7f439cf2c..d9734bfb7283 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -699,7 +699,9 @@ 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;
@@ -745,7 +747,7 @@ 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 d069e5b156e5..6713296fffd9 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -118,7 +118,9 @@ 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;
@@ -143,7 +145,7 @@ 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 new argument to the `syn_recv_sock` function pointer in `struct inet_connection_sock_af_ops` but fails to update the DCCP subsystem, breaking the build when `CONFIG_IP_DCCP` is enabled.
Pre-existing issues:
- [Critical] Use-After-Free and double-free of the listener's IPv6 options on routing failure during IPv4-mapped socket creation.
- [High] The DCCP subsystem contains the identical race condition for IPv4-mapped IPv6 sockets that this patch intended to fix for TCP.
--
commit 0524a546fd92e10009336d36766fbc7fa6b854ac
Author: Eric Dumazet <edumazet@google.com>
tcp: fix potential race in tcp_v6_syn_recv_sock()
This commit fixes a race condition where a child socket is inserted into
the TCP ehash table before its IPv6-specific fields are fully initialized.
It introduces an opt_child_init callback in the syn_recv_sock af_ops to
allow IPv6 mapped sockets to be initialized before hash 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 7649d4901f0c4..3d19420dce511 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));
[Severity: Low]
Does this change break the build for the DCCP subsystem?
It looks like dccp_v4_request_recv_sock(), dccp_v6_request_recv_sock(),
and their caller dccp_check_req() in net/dccp/minisocks.c were not updated
to handle this new 7th argument. This would result in compilation errors
when CONFIG_IP_DCCP is enabled.
[Severity: High]
This isn't a bug introduced by this patch, but does the DCCP subsystem
suffer from the same race condition this commit fixes for TCP?
In net/dccp/ipv6.c:dccp_v6_request_recv_sock(), the child socket is created
and inserted into the ehash table by dccp_v4_request_recv_sock() before
its IPv6-specific fields are initialized:
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;
Could concurrent threads access uninitialized IPv6 fields via a lookup,
similar to the syzbot crash found in TCP?
[ ... ]
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 753a881ce3cdf..ec3b0aa0a6260 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1565,6 +1567,10 @@ 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);
[Severity: Critical]
This is a pre-existing issue, but does this routing failure path in
tcp_v4_syn_recv_sock() cause a use-after-free of the listener's IPv6
options?
Just above this block in tcp_v4_syn_recv_sock():
if (!dst) {
dst = inet_csk_route_child_sock(sk, newsk, req);
if (!dst)
goto put_and_exit;
}
If inet_csk_route_child_sock() fails, the code jumps to put_and_exit and
destroys the child socket. Because opt_child_init() hasn't run yet,
newinet->pinet6 still points to the listener's ipv6_pinfo. The child's
destructor (inet6_destroy_sock) will then free the listener's options,
corrupting the active listener socket.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260903000029.3508006-3-florian.fainelli@broadcom.com?part=1
© 2016 - 2026 Red Hat, Inc.