seccomp: don't use semaphore and wait_queue together

The main reason is to use new wake_up helpers that will be added in the
following patches. But here are a few other reasons:

* if we use two different ways, we always need to call them both. This
  patch fixes seccomp_notify_recv where we forgot to call wake_up_poll
  in the error path.

* If we use one primitive, we can control how many waiters are woken up
  for each request. Our goal is to wake up just one that will handle a
  request. Right now, wake_up_poll can wake up one waiter and
  up(&match->notif->request) can wake up one more.
Signed-off-by: Andrei Vagin <avagin@google.com>
Acked-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230308073201.3102738-2-avagin@google.comSigned-off-by: Kees Cook <keescook@chromium.org>

kernel/seccomp.c

@@ -145,7 +145,7 @@ struct seccomp_kaddfd {
  * @notifications: A list of struct seccomp_knotif elements.
  */
 struct notification {
-	struct semaphore request;
+	atomic_t requests;
 	u64 next_id;
 	struct list_head notifications;
 };
@@ -1116,7 +1116,7 @@ static int seccomp_do_user_notification(int this_syscall,
 	list_add_tail(&n.list, &match->notif->notifications);
 	INIT_LIST_HEAD(&n.addfd);
 
-	up(&match->notif->request);
+	atomic_inc(&match->notif->requests);
 	wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
 
 	/*
@@ -1450,6 +1450,37 @@ find_notification(struct seccomp_filter *filter, u64 id)
 	return NULL;
 }
 
+static int recv_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
+				  void *key)
+{
+	/* Avoid a wakeup if event not interesting for us. */
+	if (key && !(key_to_poll(key) & (EPOLLIN | EPOLLERR)))
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+static int recv_wait_event(struct seccomp_filter *filter)
+{
+	DEFINE_WAIT_FUNC(wait, recv_wake_function);
+	int ret;
+
+	if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+		return 0;
+
+	for (;;) {
+		ret = prepare_to_wait_event(&filter->wqh, &wait, TASK_INTERRUPTIBLE);
+
+		if (atomic_dec_if_positive(&filter->notif->requests) >= 0)
+			break;
+
+		if (ret)
+			return ret;
+
+		schedule();
+	}
+	finish_wait(&filter->wqh, &wait);
+	return 0;
+}
 
 static long seccomp_notify_recv(struct seccomp_filter *filter,
 				void __user *buf)
@@ -1467,7 +1498,7 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 
 	memset(&unotif, 0, sizeof(unotif));
 
-	ret = down_interruptible(&filter->notif->request);
+	ret = recv_wait_event(filter);
 	if (ret < 0)
 		return ret;
 
@@ -1515,7 +1546,8 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
 			if (should_sleep_killable(filter, knotif))
 				complete(&knotif->ready);
 			knotif->state = SECCOMP_NOTIFY_INIT;
-			up(&filter->notif->request);
+			atomic_inc(&filter->notif->requests);
+			wake_up_poll(&filter->wqh, EPOLLIN | EPOLLRDNORM);
 		}
 		mutex_unlock(&filter->notify_lock);
 	}
@@ -1777,7 +1809,6 @@ static struct file *init_listener(struct seccomp_filter *filter)
 	if (!filter->notif)
 		goto out;
 
-	sema_init(&filter->notif->request, 0);
 	filter->notif->next_id = get_random_u64();
 	INIT_LIST_HEAD(&filter->notif->notifications);