diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f9a320694b8555eee9d32abd8e891a81c71671cf..a7f93f5a1ac81968fd4d2cc4eef37c0806b9493b 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
-	printf("%s: nr:%" PRIu64 "\n",
-		!callstack ? "... branch stack" : "... branch callstack",
-		sample->branch_stack->nr);
+	if (!callstack) {
+		printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+	} else {
+		/* the reason of adding 1 to nr is because after expanding
+		 * branch stack it generates nr + 1 callstack records. e.g.,
+		 *         B()->C()
+		 *         A()->B()
+		 * the final callstack should be:
+		 *         C()
+		 *         B()
+		 *         A()
+		 */
+		printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+	}
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 				(unsigned)e->flags.reserved,
 				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
-			printf("..... %2"PRIu64": %016" PRIx64 "\n",
-				i, i > 0 ? e->from : e->to);
+			if (i == 0) {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n"
+				       "..... %2"PRIu64": %016" PRIx64 "\n",
+						i, e->to, i+1, e->from);
+			} else {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+			}
 		}
 	}
 }