2 files changed, 33 insertions, 1 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index c0277d3f1aaa..a85efd2348bd 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -64,7 +64,6 @@ static void exit_mm(struct task_struct * tsk);
 static void __unhash_process(struct task_struct *p, bool group_dead)
 {
         nr_threads--;
-        detach_pid(p, PIDTYPE_PID);
         if (group_dead) {
                 detach_pid(p, PIDTYPE_PGID);
                 detach_pid(p, PIDTYPE_SID);
@@ -72,7 +71,20 @@ 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(p)->child_reaper == parent) &&
+                            list_empty(&parent->children) &&
+                            (parent->flags & PF_EXITING))
+                                wake_up_process(parent);
+                }
         }
+        detach_pid(p, PIDTYPE_PID);
         list_del_rcu(&p->thread_group);
 }
 
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 16b20e38c4a1..b3c7fd554250 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -184,11 +184,31 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
         }
         read_unlock(&tasklist_lock);
 
+        /* Firstly reap the EXIT_ZOMBIE children we may have. */
         do {
                 clear_thread_flag(TIF_SIGPENDING);
                 rc = sys_wait4(-1, NULL, __WALL, NULL);
         } while (rc != -ECHILD);
 
+        /*
+         * sys_wait4() above can't reap the TASK_DEAD children.
+         * Make sure they all go away, see __unhash_process().
+         */
+        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)
+                        break;
+                schedule();
+        }
+
         if (pid_ns->reboot)
                 current->signal->group_exit_code = pid_ns->reboot;