Fix subtle bug in "finish_wait()", which can cause kernel stack

corruption on SMP because of another CPU still accessing a waitqueue
even after it was de-allocated.

Use a careful version of the list emptiness check to make sure we
don't de-allocate the stack frame before the waitqueue is all done.

include/linux/list.h

@@ -208,6 +208,18 @@ static inline int list_empty(const struct list_head *head)
 	return head->next == head;
 }
 
+/**
+ * list_empty_careful - tests whether a list is
+ * empty _and_ checks that no other CPU might be
+ * in the process of still modifying either member
+ * @head: the list to test.
+ */
+static inline int list_empty_careful(const struct list_head *head)
+{
+	struct list_head *next = head->next;
+	return (next == head) && (next == head->prev);
+}
+
 static inline void __list_splice(struct list_head *list,
 				 struct list_head *head)
 {

kernel/fork.c

@@ -159,7 +159,20 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 	unsigned long flags;
 
 	__set_current_state(TASK_RUNNING);
-	if (!list_empty(&wait->task_list)) {
+	/*
+	 * We can check for list emptiness outside the lock
+	 * IFF:
+	 *  - we use the "careful" check that verifies both
+	 *    the next and prev pointers, so that there cannot
+	 *    be any half-pending updates in progress on other
+	 *    CPU's that we haven't seen yet (and that might
+	 *    still change the stack area.
+	 * and
+	 *  - all other users take the lock (ie we can only
+	 *    have _one_ other CPU that looks at or modifies
+	 *    the list).
+	 */
+	if (!list_empty_careful(&wait->task_list)) {
 		spin_lock_irqsave(&q->lock, flags);
 		list_del_init(&wait->task_list);
 		spin_unlock_irqrestore(&q->lock, flags);