diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce104e33cd22e393a15cd7b566381393804eeaf4..38117d937332516ff063462fba30dd80a81b3aa3 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -474,7 +474,8 @@ struct cgroup_subsys {
 			struct cgroup *old_cgrp, struct task_struct *tsk,
 			bool threadgroup);
 	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-	void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+	void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+			struct cgroup *old_cgrp, struct task_struct *task);
 	int (*populate)(struct cgroup_subsys *ss,
 			struct cgroup *cgrp);
 	void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b24d7027b83c29b067bdc56f27ae28bf2d16c464..f6495f33a355a85090768f2d8cbe68cff5dcf076 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4230,20 +4230,8 @@ void cgroup_post_fork(struct task_struct *child)
  */
 void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 {
-	int i;
 	struct css_set *cg;
-
-	if (run_callbacks && need_forkexit_callback) {
-		/*
-		 * modular subsystems can't use callbacks, so no need to lock
-		 * the subsys array
-		 */
-		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-			if (ss->exit)
-				ss->exit(ss, tsk);
-		}
-	}
+	int i;
 
 	/*
 	 * Unlink from the css_set task list if necessary.
@@ -4261,7 +4249,24 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	task_lock(tsk);
 	cg = tsk->cgroups;
 	tsk->cgroups = &init_css_set;
+
+	if (run_callbacks && need_forkexit_callback) {
+		/*
+		 * modular subsystems can't use callbacks, so no need to lock
+		 * the subsys array
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss->exit) {
+				struct cgroup *old_cgrp =
+					rcu_dereference_raw(cg->subsys[i])->cgroup;
+				struct cgroup *cgrp = task_cgroup(tsk, i);
+				ss->exit(ss, cgrp, old_cgrp, tsk);
+			}
+		}
+	}
 	task_unlock(tsk);
+
 	if (cg)
 		put_css_set_taskexit(cg);
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index e142e92f38dab77d813f98292f33c7526634be14..79e611cd83dd4e44be1e6bcbf9a850dd787ea99e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -606,9 +606,6 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
-	if (p->flags & PF_EXITING)
-		return &root_task_group;
-
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
@@ -8863,7 +8860,8 @@ cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 }
 
 static void
-cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
+		struct cgroup *old_cgrp, struct task_struct *task)
 {
 	/*
 	 * cgroup_exit() is called in the copy_process() failure path.