perf report: Show branch info in callchain entry for stdio mode

If the branch is 100% predicted then the "predicted" is hidden.
Similarly, if there is no branch tsx abort, the "abort" is hidden.
There is only cycles shown (cycle is supported on skylake platform,
older platform would be 0).

If no iterations, the "iterations" is hidden.

For example:

|--29.93%--main div.c:39 (predicted:50.6%, cycles:1, iterations:18)
|          main div.c:44 (predicted:50.6%, cycles:1)
|          |
|           --22.69%--main div.c:42 (cycles:2, iterations:17)
|                     compute_flag div.c:28 (cycles:2)
|                     |
|                      --10.52%--compute_flag div.c:27 (cycles:1)
|                                rand rand.c:28 (cycles:1)
|                                rand rand.c:28 (cycles:1)
|                                __random random.c:298 (cycles:1)
|                                __random random.c:297 (cycles:1)
|                                __random random.c:295 (cycles:1)
|                                __random random.c:295 (cycles:1)
|                                __random random.c:295 (cycles:1)
|                                __random random.c:295 (cycles:6)

Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/1477876794-30749-5-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/ui/stdio/hist.c

@@ -41,7 +41,9 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
 {
 	int i;
 	size_t ret = 0;
-	char bf[1024];
+	char bf[1024], *alloc_str = NULL;
+	char buf[64];
+	const char *str;
 
 	ret += callchain__fprintf_left_margin(fp, left_margin);
 	for (i = 0; i < depth; i++) {
@@ -56,8 +58,26 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
-	fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp);
+
+	str = callchain_list__sym_name(chain, bf, sizeof(bf), false);
+
+	if (symbol_conf.show_branchflag_count) {
+		if (!period)
+			callchain_list_counts__printf_value(node, chain, NULL,
+							    buf, sizeof(buf));
+		else
+			callchain_list_counts__printf_value(NULL, chain, NULL,
+							    buf, sizeof(buf));
+
+		if (asprintf(&alloc_str, "%s%s", str, buf) < 0)
+			str = "Not enough memory!";
+		else
+			str = alloc_str;
+	}
+
+	fputs(str, fp);
 	fputc('\n', fp);
+	free(alloc_str);
 	return ret;
 }
 
@@ -219,8 +239,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 			} else
 				ret += callchain__fprintf_left_margin(fp, left_margin);
 
-			ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf),
-							false));
+			ret += fprintf(fp, "%s",
+				       callchain_list__sym_name(chain, bf,
+								sizeof(bf),
+								false));
+
+			if (symbol_conf.show_branchflag_count)
+				ret += callchain_list_counts__printf_value(
+						NULL, chain, fp, NULL, 0);
+			ret += fprintf(fp, "\n");
 
 			if (++entries_printed == callchain_param.print_limit)
 				break;