bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop

When a sockmap is free'd and a socket in the map is enabled with tls
we tear down the bpf context on the socket, the psock struct and state,
and then call tcp_update_ulp(). The tcp_update_ulp() call is to inform
the tls stack it needs to update its saved sock ops so that when the tls
socket is later destroyed it doesn't try to call the now destroyed psock
hooks.

This is about keeping stacked ULPs in good shape so they always have
the right set of stacked ops.

However, recently unhash() hook was removed from TLS side. But, the
sockmap/bpf side is not doing any extra work to update the unhash op
when is torn down instead expecting TLS side to manage it. So both
TLS and sockmap believe the other side is managing the op and instead
no one updates the hook so it continues to point at tcp_bpf_unhash().
When unhash hook is called we call tcp_bpf_unhash() which detects the
psock has already been destroyed and calls sk->sk_prot_unhash() which
calls tcp_bpf_unhash() yet again and so on looping and hanging the core.

To fix have sockmap tear down logic fixup the stale pointer.

Fixes: 5d92e63 ("net/tls: partially revert fix transition through disconnect with close")
Reported-by: [email protected]
Signed-off-by: John Fastabend <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Reviewed-by: Jakub Sitnicki <[email protected]>
Acked-by: Song Liu <[email protected]>
Cc: [email protected]
Link: https://lore.kernel.org/bpf/[email protected]

Author: jrfastab

include/linux/skmsg.h

@@ -358,6 +358,7 @@ static inline void sk_psock_update_proto(struct sock *sk,
 static inline void sk_psock_restore_proto(struct sock *sk,
 					  struct sk_psock *psock)
 {
+	sk->sk_prot->unhash = psock->saved_unhash;
 	sk->sk_write_space = psock->saved_write_space;
 
 	if (psock->sk_proto) {