A child socket inherits the listener's bpf_sock_ops_cb_flags via
sk_clone_lock(). If its setup fails in tcp_v4_syn_recv_sock() /
tcp_v6_syn_recv_sock(), the child is freed through put_and_exit, where
inet_csk_prepare_forced_close() drops the socket lock and tcp_done() runs
without it.
If BPF_SOCK_OPS_STATE_CB_FLAG was inherited, tcp_done() -> tcp_set_state()
calls tcp_call_bpf(), which expects the lock and trips sock_owned_by_me():
WARNING: include/net/sock.h:1799 at tcp_set_state+0x433/0x550
RIP: 0010:tcp_set_state+0x433/0x550 include/net/sock.h:1799
Call Trace:
tcp_done+0xba/0x250 net/ipv4/tcp.c:5095
tcp_v4_syn_recv_sock+0x850/0xa50 net/ipv4/tcp_ipv4.c:1787
tcp_check_req+0xf30/0x1360 net/ipv4/tcp_minisocks.c:926
tcp_v4_rcv+0x1047/0x1b50 net/ipv4/tcp_ipv4.c:2164
The child is freed before it is ever established, so it should run no
sock_ops callback. Clear its cb flags in inet_csk_prepare_for_destroy_sock(),
the common point for the IPv4, IPv6 and chtls forced-close paths and for the
MPTCP ->syn_recv_sock() failure path (dispose_child), which reaches tcp_done()
on a child that was never established too.
Suggested-by: Jiayuan Chen
Fixes: d44874910a26 ("bpf: Add BPF_SOCK_OPS_STATE_CB")
Signed-off-by: Sechang Lim
---
v3:
- move the clearing into inet_csk_prepare_for_destroy_sock() (Kuniyuki Iwashima)
v2:
- move the clearing into inet_csk_prepare_forced_close (Jiayuan Chen,
Simon Horman)
- https://lore.kernel.org/all/20260610155946.894878-1-rhkrqnwk98@gmail.com/
v1:
- https://lore.kernel.org/all/20260605094954.1374489-1-rhkrqnwk98@gmail.com/
include/net/tcp.h | 9 +++++++++
net/ipv4/inet_connection_sock.c | 1 +
2 files changed, 10 insertions(+)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 98848db62894..607298501e12 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2942,6 +2942,11 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
return tcp_call_bpf(sk, op, 3, args);
}
+static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk)
+{
+ tcp_sk(sk)->bpf_sock_ops_cb_flags = 0;
+}
+
#else
static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
{
@@ -2959,6 +2964,10 @@ static inline int tcp_call_bpf_3arg(struct sock *sk, int op, u32 arg1, u32 arg2,
return -EPERM;
}
+static inline void tcp_clear_sock_ops_cb_flags(struct sock *sk)
+{
+}
+
#endif
static inline u32 tcp_timeout_init(struct sock *sk)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dbcd37dfdc15..6305da871e78 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1279,6 +1279,7 @@ EXPORT_SYMBOL(inet_csk_destroy_sock);
void inet_csk_prepare_for_destroy_sock(struct sock *sk)
{
/* The below has to be done to allow calling inet_csk_destroy_sock */
+ tcp_clear_sock_ops_cb_flags(sk);
sock_set_flag(sk, SOCK_DEAD);
tcp_orphan_count_inc();
}
--
2.43.0