diff --git a/kernel/fork.c b/kernel/fork.c
index 5449efbc6427..bb762b4dd217 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -981,6 +981,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (!p)
 		goto fork_out;
 
+	ftrace_graph_init_task(p);
+
 	rt_mutex_init_task(p);
 
 #ifdef CONFIG_PROVE_LOCKING
@@ -1130,8 +1132,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		}
 	}
 
-	ftrace_graph_init_task(p);
-
 	p->pid = pid_nr(pid);
 	p->tgid = p->pid;
 	if (clone_flags & CLONE_THREAD)
@@ -1140,7 +1140,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (current->nsproxy != p->nsproxy) {
 		retval = ns_cgroup_clone(p, pid);
 		if (retval)
-			goto bad_fork_free_graph;
+			goto bad_fork_free_pid;
 	}
 
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
@@ -1232,7 +1232,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_free_graph;
+		goto bad_fork_free_pid;
 	}
 
 	if (clone_flags & CLONE_THREAD) {
@@ -1267,8 +1267,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	cgroup_post_fork(p);
 	return p;
 
-bad_fork_free_graph:
-	ftrace_graph_exit_task(p);
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d6973dfadb36..bb60732ade0c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3218,12 +3218,12 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 
 		if (t->ret_stack == NULL) {
-			t->curr_ret_stack = -1;
-			/* Make sure IRQs see the -1 first: */
-			barrier();
-			t->ret_stack = ret_stack_list[start++];
 			atomic_set(&t->tracing_graph_pause, 0);
 			atomic_set(&t->trace_overrun, 0);
+			t->curr_ret_stack = -1;
+			/* Make sure the tasks see the -1 first: */
+			smp_wmb();
+			t->ret_stack = ret_stack_list[start++];
 		}
 	} while_each_thread(g, t);
 
@@ -3281,8 +3281,10 @@ static int start_graph_tracing(void)
 		return -ENOMEM;
 
 	/* The cpu_boot init_task->ret_stack will never be freed */
-	for_each_online_cpu(cpu)
-		ftrace_graph_init_task(idle_task(cpu));
+	for_each_online_cpu(cpu) {
+		if (!idle_task(cpu)->ret_stack)
+			ftrace_graph_init_task(idle_task(cpu));
+	}
 
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
@@ -3374,18 +3376,25 @@ void unregister_ftrace_graph(void)
 /* Allocate a return stack for newly created task */
 void ftrace_graph_init_task(struct task_struct *t)
 {
+	/* Make sure we do not use the parent ret_stack */
+	t->ret_stack = NULL;
+
 	if (ftrace_graph_active) {
-		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+		struct ftrace_ret_stack *ret_stack;
+
+		ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
 				* sizeof(struct ftrace_ret_stack),
 				GFP_KERNEL);
-		if (!t->ret_stack)
+		if (!ret_stack)
 			return;
 		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
 		t->ftrace_timestamp = 0;
-	} else
-		t->ret_stack = NULL;
+		/* make curr_ret_stack visable before we add the ret_stack */
+		smp_wmb();
+		t->ret_stack = ret_stack;
+	}
 }
 
 void ftrace_graph_exit_task(struct task_struct *t)
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 10f6ad7d85f6..8b592418d8b2 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -65,6 +65,12 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth)
 	if (!current->ret_stack)
 		return -EBUSY;
 
+	/*
+	 * We must make sure the ret_stack is tested before we read
+	 * anything else.
+	 */
+	smp_rmb();
+
 	/* The return trace stack is full */
 	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
 		atomic_inc(&current->trace_overrun);