3 files changed, 39 insertions, 5 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 16b07bfac22..456329fd4ea 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -687,11 +687,11 @@ static void exit_mm(struct task_struct * tsk)
 }
 
 /*
- * When we die, we re-parent all our children.
- * Try to give them to another thread in our thread
- * group, and if no such member exists, give it to
- * the child reaper process (ie "init") in our pid
- * space.
+ * When we die, we re-parent all our children, and try to:
+ * 1. give them to another thread in our thread group, if such a member exists
+ * 2. give it to the first ancestor process which prctl'd itself as a
+ *    child_subreaper for its children (like a service manager)
+ * 3. give it to the init process (PID 1) in our pid namespace
  */
 static struct task_struct *find_new_reaper(struct task_struct *father)
 	__releases(&tasklist_lock)
@@ -722,6 +722,29 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 		 * forget_original_parent() must move them somewhere.
 		 */
 		pid_ns->child_reaper = init_pid_ns.child_reaper;
+	} else if (father->signal->has_child_subreaper) {
+		struct task_struct *reaper;
+
+		/*
+		 * Find the first ancestor marked as child_subreaper.
+		 * Note that the code below checks same_thread_group(reaper,
+		 * pid_ns->child_reaper).  This is what we need to DTRT in a
+		 * PID namespace. However we still need the check above, see
+		 * http://marc.info/?l=linux-kernel&m=131385460420380
+		 */
+		for (reaper = father->real_parent;
+		     reaper != &init_task;
+		     reaper = reaper->real_parent) {
+			if (same_thread_group(reaper, pid_ns->child_reaper))
+				break;
+			if (!reaper->signal->is_child_subreaper)
+				continue;
+			thread = reaper;
+			do {
+				if (!(thread->flags & PF_EXITING))
+					return reaper;
+			} while_each_thread(reaper, thread);
+		}
 	}
 
 	return pid_ns->child_reaper;
diff --git a/kernel/fork.c b/kernel/fork.c
index 37674ec55cd..b9372a0bff1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1051,6 +1051,9 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
+	sig->has_child_subreaper = current->signal->has_child_subreaper ||
+				   current->signal->is_child_subreaper;
+
 	mutex_init(&sig->cred_guard_mutex);
 
 	return 0;
diff --git a/kernel/sys.c b/kernel/sys.c
index 888d227fd19..9eb7fcab8df 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1962,6 +1962,14 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		case PR_SET_MM:
 			error = prctl_set_mm(arg2, arg3, arg4, arg5);
 			break;
+		case PR_SET_CHILD_SUBREAPER:
+			me->signal->is_child_subreaper = !!arg2;
+			error = 0;
+			break;
+		case PR_GET_CHILD_SUBREAPER:
+			error = put_user(me->signal->is_child_subreaper,
+					 (int __user *) arg2);
+			break;
 		default:
 			error = -EINVAL;
 			break;