[PATCH bpf 08/11] bpf, sockmap: Fix socket lock taken on a child before accept()

From: Jiayuan Chen

Date: Sat Nov 21 2026 - 05:36:19 EST


A sockops prog can add a child that is not accepted yet to a sockmap at
BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB. An sk_msg redirect to this child,
ingress or egress, takes lock_sock() on it. If the listener is closed at
that time, inet_csk_listen_stop() hits:

WARN_ON(sock_owned_by_user(child));

WARNING: net/ipv4/inet_connection_sock.c:1492 at inet_csk_listen_stop+0x7ba/0xc40
Call Trace:
<TASK>
__tcp_close+0xb64/0xee0
tcp_close+0x24/0xf0
inet_release+0x10a/0x240
__sock_release+0xaf/0x270
sock_close+0x18/0x30
__fput+0x360/0xa90
fput_close_sync+0xe6/0x1d0
__x64_sys_close+0x80/0xe0
x64_sys_call+0x2680/0x27e0
do_syscall_64+0xe5/0x610
entry_SYSCALL_64_after_hwframe+0x76/0x7e
</TASK>

Commit 4aeaad1c536e ("bpf, sockmap: Check the target of an egress
redirect before each send") already refuses an egress redirect to such a
child, but only after lock_sock(). Refuse the ingress redirect too, and
do it before taking the lock: a child has no sk_socket until accept()
has taken it off the queue.

sock_map_free() and sock_hash_free() also lock the sockets in the map.
They can't refuse, so unlink such a child without the lock, as a delete
from the map already does.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Fixes: 7e81a3530206 ("bpf: Sockmap, ensure sock lock held during tear down")
Signed-off-by: Jiayuan Chen <jiayuan.chen@xxxxxxxxx>
---
net/core/sock_map.c | 27 +++++++++++++++++++++++----
net/ipv4/tcp_bpf.c | 10 +++++++++-
2 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 6fc1d29ac6ed5..4a053846bd60e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -386,6 +386,19 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk)
return ret;
}

+/*
+ * The listener frees a child that nobody has accepted yet without waiting
+ * for the owner of its socket lock. Unlink such a child without the lock,
+ * as a delete does.
+ */
+static bool sock_map_free_lock_sk(struct sock *sk)
+{
+ if (!READ_ONCE(sk->sk_socket))
+ return false;
+ lock_sock(sk);
+ return true;
+}
+
static void sock_map_free(struct bpf_map *map)
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
@@ -402,12 +415,15 @@ static void sock_map_free(struct bpf_map *map)

sk = xchg(psk, NULL);
if (sk) {
+ bool locked;
+
sock_hold(sk);
- lock_sock(sk);
+ locked = sock_map_free_lock_sk(sk);
rcu_read_lock();
sock_map_unref(sk, psk);
rcu_read_unlock();
- release_sock(sk);
+ if (locked)
+ release_sock(sk);
sock_put(sk);
}
}
@@ -1228,12 +1244,15 @@ static void sock_hash_free(struct bpf_map *map)
* link to sockhash.
*/
hlist_for_each_entry_safe(elem, node, &unlink_list, node) {
+ bool locked;
+
hlist_del(&elem->node);
- lock_sock(elem->sk);
+ locked = sock_map_free_lock_sk(elem->sk);
rcu_read_lock();
sock_map_unref(elem->sk, elem);
rcu_read_unlock();
- release_sock(elem->sk);
+ if (locked)
+ release_sock(elem->sk);
sock_put(elem->sk);
sock_hash_free_elem(htab, elem);
}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 9715716518c49..da9caccfede79 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -188,9 +188,17 @@ static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg,
int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress,
struct sk_msg *msg, u32 bytes, int flags)
{
- struct sk_psock *psock = sk_psock_get(sk);
+ struct sk_psock *psock;
int ret;

+ /*
+ * The listener frees a child that nobody has accepted yet without
+ * waiting for the owner of its socket lock.
+ */
+ if (!READ_ONCE(sk->sk_socket))
+ return sock_flag(sk, SOCK_DEAD) ? -EPIPE : -EINVAL;
+
+ psock = sk_psock_get(sk);
if (unlikely(!psock))
return -EPIPE;

--
2.43.0