diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f0e52383a001..1516a8ff8f92 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -41,6 +41,7 @@ extern struct fs_struct init_fs;
 
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\
@@ -222,6 +223,7 @@ extern struct task_group root_task_group;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),	\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffccdad050b5..485234d2fd42 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -549,6 +549,7 @@ struct signal_struct {
 	atomic_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 
@@ -1271,6 +1272,7 @@ struct task_struct {
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
+	struct list_head thread_node;
 
 	struct completion *vfork_done;		/* for vfork() */
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
@@ -2341,6 +2343,16 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
 static inline int get_nr_threads(struct task_struct *tsk)
 {
 	return tsk->signal->nr_threads;
diff --git a/kernel/exit.c b/kernel/exit.c
index a949819055d5..1e77fc645317 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -74,6 +74,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
 		__this_cpu_dec(process_counts);
 	}
 	list_del_rcu(&p->thread_group);
+	list_del_rcu(&p->thread_node);
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 294189fc7ac8..2f11bbe376b0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1035,6 +1035,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->nr_threads = 1;
 	atomic_set(&sig->live, 1);
 	atomic_set(&sig->sigcnt, 1);
+
+	/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
+	sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
+	tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
+
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
@@ -1474,6 +1479,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			atomic_inc(&current->signal->sigcnt);
 			list_add_tail_rcu(&p->thread_group,
 					  &p->group_leader->thread_group);
+			list_add_tail_rcu(&p->thread_node,
+					  &p->signal->thread_head);
 		}
 		attach_pid(p, PIDTYPE_PID);
 		nr_threads++;