seccomp: interrupt SECCOMP_IOCTL_NOTIF_RECV when all users have exited

SECCOMP_IOCTL_NOTIF_RECV promptly returns when a seccomp filter becomes
unused, as a filter without users can't trigger any events.

Previously, event listeners had to rely on epoll to detect when all
processes had exited.

The change is based on the 'commit 99cdb8b ("seccomp: notify about
unused filter")' which implemented (E)POLLHUP notifications.

Reviewed-by: Christian Brauner <[email protected]>
Signed-off-by: Andrei Vagin <[email protected]>
Reviewed-by: Oleg Nesterov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Reviewed-by: Tycho Andersen <[email protected]>
Signed-off-by: Kees Cook <[email protected]>

Author: avagin

kernel/seccomp.c

@@ -1466,7 +1466,7 @@ static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int s
 				  void *key)
 {
 	/* Avoid a wakeup if event not interesting for us. */
-	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR | EPOLLHUP)))
 		return 0;
 	return autoremove_wake_function(wait, mode, sync, key);
 }
@@ -1476,6 +1476,9 @@ static int recv_wait_event(struct seccomp_filter *filter)
 	DEFINE_WAIT_FUNC(wait, recv_wake_function);
 	int ret;
 
+	if (refcount_read(&filter->users) == 0)
+		return 0;
+
 	if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
 		return 0;
 
@@ -1484,6 +1487,8 @@ static int recv_wait_event(struct seccomp_filter *filter)
 
 		if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
 			break;
+		if (refcount_read(&filter->users) == 0)
+			break;
 
 		if (ret)
 			return ret;