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:
   <IRQ>
   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
   </IRQ>

The child is freed before it is ever established, so it should run no
sock_ops callback. Clear its cb flags before the forced close.

Fixes: d44874910a26 ("bpf: Add BPF_SOCK_OPS_STATE_CB")
Signed-off-by: Sechang Lim <rhkrqnwk98@gmail.com>
---
 include/net/tcp.h   | 7 +++++++
 net/ipv4/tcp_ipv4.c | 1 +
 net/ipv6/tcp_ipv6.c | 1 +
 3 files changed, 9 insertions(+)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 98848db62894..97eac5fa341c 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 +2964,8 @@ 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/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fdc81150ff6c..7748668dba82 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1783,6 +1783,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	return NULL;
 put_and_exit:
 	newinet->inet_opt = NULL;
+	tcp_clear_sock_ops_cb_flags(newsk);
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 36d75fb50a70..493477b786db 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1531,6 +1531,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	tcp_listendrop(sk);
 	return NULL;
 put_and_exit:
+	tcp_clear_sock_ops_cb_flags(newsk);
 	inet_csk_prepare_forced_close(newsk);
 	tcp_done(newsk);
 	goto exit;
-- 
2.43.0

On 6/5/26 5:49 PM, Sechang Lim wrote:
> 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:
>     <IRQ>
>     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
>     </IRQ>
>
> The child is freed before it is ever established, so it should run no
> sock_ops callback. Clear its cb flags before the forced close.
>
> Fixes: d44874910a26 ("bpf: Add BPF_SOCK_OPS_STATE_CB")
> Signed-off-by: Sechang Lim <rhkrqnwk98@gmail.com>
> ---
>   include/net/tcp.h   | 7 +++++++
>   net/ipv4/tcp_ipv4.c | 1 +
>   net/ipv6/tcp_ipv6.c | 1 +
>   3 files changed, 9 insertions(+)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 98848db62894..97eac5fa341c 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 +2964,8 @@ 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/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index fdc81150ff6c..7748668dba82 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1783,6 +1783,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
>   	return NULL;
>   put_and_exit:
>   	newinet->inet_opt = NULL;
> +	tcp_clear_sock_ops_cb_flags(newsk);
>   	inet_csk_prepare_forced_close(newsk);


I prefer clearing the bit in inet_csk_prepare_forced_close(), since it 
looks like inet_csk_prepare_forced_close()
is already a TCP-specific function.

Let's wait for the TCP maintainer's.


>   	tcp_done(newsk);
>   	goto exit;
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index 36d75fb50a70..493477b786db 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1531,6 +1531,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
>   	tcp_listendrop(sk);
>   	return NULL;
>   put_and_exit:
> +	tcp_clear_sock_ops_cb_flags(newsk);
>   	inet_csk_prepare_forced_close(newsk);
>   	tcp_done(newsk);
>   	goto exit;