diff --git a/kernel/exit.c b/kernel/exit.c
index 676149a4ac5f..8cb89045ecf3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -994,6 +994,15 @@ NORET_TYPE void do_exit(long code)
 	exit_fs(tsk);
 	check_stack_usage();
 	exit_thread();
+
+	/*
+	 * Flush inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 *
+	 * because of cgroup mode, must be called before cgroup_exit()
+	 */
+	perf_event_exit_task(tsk);
+
 	cgroup_exit(tsk, 1);
 
 	if (group_dead)
@@ -1007,11 +1016,6 @@ NORET_TYPE void do_exit(long code)
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
 	flush_ptrace_hw_breakpoint(tsk);
-	/*
-	 * Flush inherited counters to the parent - before the parent
-	 * gets woken up by child-exit notifications.
-	 */
-	perf_event_exit_task(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 11847bf1e8cc..2c14e3afdf0d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,6 +38,12 @@
 
 #include <asm/irq_regs.h>
 
+enum event_type_t {
+	EVENT_FLEXIBLE = 0x1,
+	EVENT_PINNED = 0x2,
+	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
+};
+
 atomic_t perf_task_events __read_mostly;
 static atomic_t nr_mmap_events __read_mostly;
 static atomic_t nr_comm_events __read_mostly;
@@ -65,6 +71,12 @@ int sysctl_perf_event_sample_rate __read_mostly = 100000;
 
 static atomic64_t perf_event_id;
 
+static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
+			      enum event_type_t event_type);
+
+static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
+			     enum event_type_t event_type);
+
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -72,6 +84,11 @@ extern __weak const char *perf_pmu_name(void)
 	return "pmu";
 }
 
+static inline u64 perf_clock(void)
+{
+	return local_clock();
+}
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -240,11 +257,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 	put_ctx(ctx);
 }
 
-static inline u64 perf_clock(void)
-{
-	return local_clock();
-}
-
 /*
  * Update the record of the current time in a context.
  */
@@ -1193,12 +1205,6 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
 	return 0;
 }
 
-enum event_type_t {
-	EVENT_FLEXIBLE = 0x1,
-	EVENT_PINNED = 0x2,
-	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
-};
-
 static void ctx_sched_out(struct perf_event_context *ctx,
 			  struct perf_cpu_context *cpuctx,
 			  enum event_type_t event_type)