diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 93040f1..5b1e9a9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2468,8 +2468,8 @@
 			iter->seq.len = len;
 			break;
 		}
-
-		trace_consume(iter);
+		if (ret != TRACE_TYPE_NO_CONSUME)
+			trace_consume(iter);
 
 		if (iter->seq.len >= cnt)
 			break;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1ecfb9d..7b0518a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -63,13 +63,13 @@
 
 /* Function call entry */
 struct ftrace_graph_ent_entry {
-	struct trace_entry			ent;
+	struct trace_entry		ent;
 	struct ftrace_graph_ent		graph_ent;
 };
 
 /* Function return entry */
 struct ftrace_graph_ret_entry {
-	struct trace_entry			ent;
+	struct trace_entry		ent;
 	struct ftrace_graph_ret		ret;
 };
 extern struct tracer boot_tracer;
@@ -309,7 +309,8 @@
 enum print_line_t {
 	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
 	TRACE_TYPE_HANDLED	= 1,
-	TRACE_TYPE_UNHANDLED	= 2	/* Relay to other output functions */
+	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
+	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 88f8d9d..782ec0f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -212,8 +212,8 @@
 	return ret;
 }
 
-static bool
-trace_branch_is_leaf(struct trace_iterator *iter,
+static struct ftrace_graph_ret_entry *
+get_return_for_leaf(struct trace_iterator *iter,
 		struct ftrace_graph_ent_entry *curr)
 {
 	struct ring_buffer_iter *ring_iter;
@@ -222,24 +222,33 @@
 
 	ring_iter = iter->buffer_iter[iter->cpu];
 
-	if (!ring_iter)
-		return false;
-
-	event = ring_buffer_iter_peek(ring_iter, NULL);
+	/* First peek to compare current entry and the next one */
+	if (ring_iter)
+		event = ring_buffer_iter_peek(ring_iter, NULL);
+	else {
+	/* We need to consume the current entry to see the next one */
+		ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+		event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+					NULL);
+	}
 
 	if (!event)
-		return false;
+		return NULL;
 
 	next = ring_buffer_event_data(event);
 
 	if (next->ent.type != TRACE_GRAPH_RET)
-		return false;
+		return NULL;
 
 	if (curr->ent.pid != next->ent.pid ||
 			curr->graph_ent.func != next->ret.func)
-		return false;
+		return NULL;
 
-	return true;
+	/* this is a leaf, now advance the iterator */
+	if (ring_iter)
+		ring_buffer_read(ring_iter, NULL);
+
+	return next;
 }
 
 /* Signal a overhead of time execution to the output */
@@ -376,18 +385,15 @@
 /* Case of a leaf function on its call entry */
 static enum print_line_t
 print_graph_entry_leaf(struct trace_iterator *iter,
-		struct ftrace_graph_ent_entry *entry, struct trace_seq *s)
+		struct ftrace_graph_ent_entry *entry,
+		struct ftrace_graph_ret_entry *ret_entry, struct trace_seq *s)
 {
-	struct ftrace_graph_ret_entry *ret_entry;
 	struct ftrace_graph_ret *graph_ret;
-	struct ring_buffer_event *event;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
 	int ret;
 	int i;
 
-	event = ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
-	ret_entry = ring_buffer_event_data(event);
 	graph_ret = &ret_entry->ret;
 	call = &entry->graph_ent;
 	duration = graph_ret->rettime - graph_ret->calltime;
@@ -457,7 +463,11 @@
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	return TRACE_TYPE_HANDLED;
+	/*
+	 * we already consumed the current entry to check the next one
+	 * and see if this is a leaf.
+	 */
+	return TRACE_TYPE_NO_CONSUME;
 }
 
 static enum print_line_t
@@ -469,6 +479,7 @@
 	pid_t *last_entry = iter->private;
 	struct trace_entry *ent = iter->ent;
 	struct ftrace_graph_ent *call = &field->graph_ent;
+	struct ftrace_graph_ret_entry *leaf_ret;
 
 	/* Pid */
 	if (verif_pid(s, ent->pid, cpu, last_entry) == TRACE_TYPE_PARTIAL_LINE)
@@ -504,8 +515,9 @@
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	if (trace_branch_is_leaf(iter, field))
-		return print_graph_entry_leaf(iter, field, s);
+	leaf_ret = get_return_for_leaf(iter, field);
+	if (leaf_ret)
+		return print_graph_entry_leaf(iter, field, leaf_ret, s);
 	else
 		return print_graph_entry_nested(field, s, iter->ent->pid, cpu);