pidns: Wait in zap_pid_ns_processes until pid_ns->nr_hashed == 1

Looking at pid_ns->nr_hashed is a bit simpler and it works for
disjoint process trees that an unshare or a join of a pid_namespace
may create.

Acked-by: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

kernel/exit.c

@@ -72,18 +72,6 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		list_del_rcu(&p->tasks);
 		list_del_init(&p->sibling);
 		__this_cpu_dec(process_counts);
-		/*
-		 * If we are the last child process in a pid namespace to be
-		 * reaped, notify the reaper sleeping zap_pid_ns_processes().
-		 */
-		if (IS_ENABLED(CONFIG_PID_NS)) {
-			struct task_struct *parent = p->real_parent;
-
-			if ((task_active_pid_ns(parent)->child_reaper == parent) &&
-			    list_empty(&parent->children) &&
-			    (parent->flags & PF_EXITING))
-				wake_up_process(parent);
-		}
 	}
 	list_del_rcu(&p->thread_group);
 }

kernel/pid.c

@@ -273,10 +273,20 @@ void free_pid(struct pid *pid)
 	spin_lock_irqsave(&pidmap_lock, flags);
 	for (i = 0; i <= pid->level; i++) {
 		struct upid *upid = pid->numbers + i;
+		struct pid_namespace *ns = upid->ns;
 		hlist_del_rcu(&upid->pid_chain);
-		if (--upid->ns->nr_hashed == 0) {
-			upid->ns->nr_hashed = -1;
-			schedule_work(&upid->ns->proc_work);
+		switch(--ns->nr_hashed) {
+		case 1:
+			/* When all that is left in the pid namespace
+			 * is the reaper wake up the reaper.  The reaper
+			 * may be sleeping in zap_pid_ns_processes().
+			 */
+			wake_up_process(ns->child_reaper);
+			break;
+		case 0:
+			ns->nr_hashed = -1;
+			schedule_work(&ns->proc_work);
+			break;
 		}
 	}
 	spin_unlock_irqrestore(&pidmap_lock, flags);

kernel/pid_namespace.c

@@ -217,22 +217,15 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 
 	/*
 	 * sys_wait4() above can't reap the TASK_DEAD children.
-	 * Make sure they all go away, see __unhash_process().
+	 * Make sure they all go away, see free_pid().
 	 */
 	for (;;) {
-		bool need_wait = false;
-
-		read_lock(&tasklist_lock);
-		if (!list_empty(&current->children)) {
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			need_wait = true;
-		}
-		read_unlock(&tasklist_lock);
-
-		if (!need_wait)
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (pid_ns->nr_hashed == 1)
 			break;
 		schedule();
 	}
+	__set_current_state(TASK_RUNNING);
 
 	if (pid_ns->reboot)
 		current->signal->group_exit_code = pid_ns->reboot;