10 files changed, 228 insertions, 96 deletions

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 2e2d10022355..ba36aac340bc 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -213,17 +213,17 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 		ui_browser__write_nstring(browser, bf, printed);
 		if (change_color)
 			ui_browser__set_color(browser, color);
-		if (dl->ins && dl->ins->ops->scnprintf) {
-			if (ins__is_jump(dl->ins)) {
-				bool fwd = dl->ops.target.offset > (u64)dl->offset;
+		if (dl->ins.ops && dl->ins.ops->scnprintf) {
+			if (ins__is_jump(&dl->ins)) {
+				bool fwd = dl->ops.target.offset > dl->offset;
 
 				ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
 								    SLSMG_UARROW_CHAR);
 				SLsmg_write_char(' ');
-			} else if (ins__is_call(dl->ins)) {
+			} else if (ins__is_call(&dl->ins)) {
 				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
 				SLsmg_write_char(' ');
-			} else if (ins__is_ret(dl->ins)) {
+			} else if (ins__is_ret(&dl->ins)) {
 				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
 				SLsmg_write_char(' ');
 			} else {
@@ -243,9 +243,10 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 
 static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
 {
-	if (!dl || !dl->ins || !ins__is_jump(dl->ins)
+	if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins)
 	    || !disasm_line__has_offset(dl)
-	    || dl->ops.target.offset >= symbol__size(sym))
+	    || dl->ops.target.offset < 0
+	    || dl->ops.target.offset >= (s64)symbol__size(sym))
 		return false;
 
 	return true;
@@ -492,10 +493,10 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	};
 	char title[SYM_TITLE_MAX_SIZE];
 
-	if (!ins__is_call(dl->ins))
+	if (!ins__is_call(&dl->ins))
 		return false;
 
-	if (map_groups__find_ams(&target, NULL) ||
+	if (map_groups__find_ams(&target) ||
 	    map__rip_2objdump(target.map, target.map->map_ip(target.map,
 							     target.addr)) !=
 	    dl->ops.target.addr) {
@@ -543,14 +544,16 @@ struct disasm_line *annotate_browser__find_offset(struct annotate_browser *brows
 static bool annotate_browser__jump(struct annotate_browser *browser)
 {
 	struct disasm_line *dl = browser->selection;
+	u64 offset;
 	s64 idx;
 
-	if (!ins__is_jump(dl->ins))
+	if (!ins__is_jump(&dl->ins))
 		return false;
 
-	dl = annotate_browser__find_offset(browser, dl->ops.target.offset, &idx);
+	offset = dl->ops.target.offset;
+	dl = annotate_browser__find_offset(browser, offset, &idx);
 	if (dl == NULL) {
-		ui_helpline__puts("Invalid jump offset");
+		ui_helpline__printf("Invalid jump offset: %" PRIx64, offset);
 		return true;
 	}
 
@@ -841,9 +844,9 @@ show_help:
 				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
 			else if (browser->selection->offset == -1)
 				ui_helpline__puts("Actions are only available for assembly lines.");
-			else if (!browser->selection->ins)
+			else if (!browser->selection->ins.ops)
 				goto show_sup_ins;
-			else if (ins__is_ret(browser->selection->ins))
+			else if (ins__is_ret(&browser->selection->ins))
 				goto out;
 			else if (!(annotate_browser__jump(browser) ||
 				     annotate_browser__callq(browser, evsel, hbt))) {
@@ -1050,7 +1053,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	err = symbol__disassemble(sym, map, sizeof_bdl);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), sizeof_bdl);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 13d414384739..641b40234a9d 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -30,7 +30,7 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
 {
-	return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
+	return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter || hb->c2c_filter;
 }
 
 static int hist_browser__get_folding(struct hist_browser *browser)
@@ -69,8 +69,11 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 static void hist_browser__update_rows(struct hist_browser *hb)
 {
 	struct ui_browser *browser = &hb->b;
-	u16 header_offset = hb->show_headers ? 1 : 0, index_row;
+	struct hists *hists = hb->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
+	u16 header_offset, index_row;
 
+	header_offset = hb->show_headers ? hpp_list->nr_header_lines : 0;
 	browser->rows = browser->height - header_offset;
 	/*
 	 * Verify if we were at the last line and that line isn't
@@ -99,8 +102,11 @@ static void hist_browser__refresh_dimensions(struct ui_browser *browser)
 
 static void hist_browser__gotorc(struct hist_browser *browser, int row, int column)
 {
-	u16 header_offset = browser->show_headers ? 1 : 0;
+	struct hists *hists = browser->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
+	u16 header_offset;
 
+	header_offset = browser->show_headers ? hpp_list->nr_header_lines : 0;
 	ui_browser__gotorc(&browser->b, row + header_offset, column);
 }
 
@@ -595,7 +601,8 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
 			u64 nr_entries;
 			hbt->timer(hbt->arg);
 
-			if (hist_browser__has_filter(browser))
+			if (hist_browser__has_filter(browser) ||
+			    symbol_conf.report_hierarchy)
 				hist_browser__update_nr_entries(browser);
 
 			nr_entries = hist_browser__nr_entries(browser);
@@ -731,6 +738,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 					     struct callchain_print_arg *arg)
 {
 	char bf[1024], *alloc_str;
+	char buf[64], *alloc_str2;
 	const char *str;
 
 	if (arg->row_offset != 0) {
@@ -739,12 +747,26 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	}
 
 	alloc_str = NULL;
+	alloc_str2 = NULL;
+
 	str = callchain_list__sym_name(chain, bf, sizeof(bf),
 				       browser->show_dso);
 
-	if (need_percent) {
-		char buf[64];
+	if (symbol_conf.show_branchflag_count) {
+		if (need_percent)
+			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_str2, "%s%s", str, buf) < 0)
+			str = "Not enough memory!";
+		else
+			str = alloc_str2;
+	}
+
+	if (need_percent) {
 		callchain_node__scnprintf_value(node, buf, sizeof(buf),
 						total);
 
@@ -757,6 +779,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	print(browser, chain, str, offset, row, arg);
 
 	free(alloc_str);
+	free(alloc_str2);
 	return 1;
 }
 
@@ -1074,7 +1097,7 @@ struct hpp_arg {
 	bool current_entry;
 };
 
-static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
+int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
 	int ret, len;
@@ -1091,7 +1114,6 @@ static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	ui_browser__printf(arg->b, "%s", hpp->buf);
 
-	advance_hpp(hpp, ret);
 	return ret;
 }
 
@@ -1331,8 +1353,8 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		}
 
 		if (first) {
-			ui_browser__printf(&browser->b, "%c", folded_sign);
-			width--;
+			ui_browser__printf(&browser->b, "%c ", folded_sign);
+			width -= 2;
 			first = false;
 		} else {
 			ui_browser__printf(&browser->b, "  ");
@@ -1355,8 +1377,10 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		width -= hpp.buf - s;
 	}
 
-	ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
-	width -= hierarchy_indent;
+	if (!first) {
+		ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+		width -= hierarchy_indent;
+	}
 
 	if (column >= browser->b.horiz_scroll) {
 		char s[2048];
@@ -1375,7 +1399,13 @@ static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
 		}
 
 		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
-			ui_browser__write_nstring(&browser->b, "", 2);
+			if (first) {
+				ui_browser__printf(&browser->b, "%c ", folded_sign);
+				first = false;
+			} else {
+				ui_browser__write_nstring(&browser->b, "", 2);
+			}
+
 			width -= 2;
 
 			/*
@@ -1496,7 +1526,9 @@ static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 	return hpp->size <= 0;
 }
 
-static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf, size_t size)
+static int
+hists_browser__scnprintf_headers(struct hist_browser *browser, char *buf,
+				 size_t size, int line)
 {
 	struct hists *hists = browser->hists;
 	struct perf_hpp dummy_hpp = {
@@ -1506,6 +1538,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	struct perf_hpp_fmt *fmt;
 	size_t ret = 0;
 	int column = 0;
+	int span = 0;
 
 	if (symbol_conf.use_callchain) {
 		ret = scnprintf(buf, size, "  ");
@@ -1517,10 +1550,13 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists);
+		ret = fmt->header(fmt, &dummy_hpp, hists, line, &span);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
+		if (span)
+			continue;
+
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1543,10 +1579,11 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 	int indent = hists->nr_hpp_node - 2;
 	bool first_node, first_col;
 
-	ret = scnprintf(buf, size, " ");
+	ret = scnprintf(buf, size, "  ");
 	if (advance_hpp_check(&dummy_hpp, ret))
 		return ret;
 
+	first_node = true;
 	/* the first hpp_list_node is for overhead columns */
 	fmt_node = list_first_entry(&hists->hpp_formats,
 				    struct perf_hpp_list_node, list);
@@ -1554,19 +1591,23 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 		if (column++ < browser->b.horiz_scroll)
 			continue;
 
-		ret = fmt->header(fmt, &dummy_hpp, hists);
+		ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
 
 		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
+
+		first_node = false;
 	}
 
-	ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
-			indent * HIERARCHY_INDENT, "");
-	if (advance_hpp_check(&dummy_hpp, ret))
-		return ret;
+	if (!first_node) {
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+				indent * HIERARCHY_INDENT, "");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			return ret;
+	}
 
 	first_node = true;
 	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
@@ -1591,7 +1632,7 @@ static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *brows
 			}
 			first_col = false;
 
-			ret = fmt->header(fmt, &dummy_hpp, hists);
+			ret = fmt->header(fmt, &dummy_hpp, hists, 0, NULL);
 			dummy_hpp.buf[ret] = '\0';
 
 			start = trim(dummy_hpp.buf);
@@ -1622,14 +1663,21 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser)
 
 static void hists_browser__headers(struct hist_browser *browser)
 {
-	char headers[1024];
+	struct hists *hists = browser->hists;
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 
-	hists_browser__scnprintf_headers(browser, headers,
-					 sizeof(headers));
+	int line;
 
-	ui_browser__gotorc(&browser->b, 0, 0);
-	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
-	ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+	for (line = 0; line < hpp_list->nr_header_lines; line++) {
+		char headers[1024];
+
+		hists_browser__scnprintf_headers(browser, headers,
+						 sizeof(headers), line);
+
+		ui_browser__gotorc(&browser->b, line, 0);
+		ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+		ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
+	}
 }
 
 static void hist_browser__show_headers(struct hist_browser *browser)
@@ -1656,10 +1704,13 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	u16 header_offset = 0;
 	struct rb_node *nd;
 	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+	struct hists *hists = hb->hists;
 
 	if (hb->show_headers) {
+		struct perf_hpp_list *hpp_list = hists->hpp_list;
+
 		hist_browser__show_headers(hb);
-		header_offset = 1;
+		header_offset = hpp_list->nr_header_lines;
 	}
 
 	ui_browser__hists_init_top(browser);
@@ -2054,10 +2105,23 @@ void hist_browser__init(struct hist_browser *browser,
 	browser->b.use_navkeypressed	= true;
 	browser->show_headers		= symbol_conf.show_hist_headers;
 
-	hists__for_each_format(hists, fmt) {
-		perf_hpp__reset_width(fmt, hists);
+	if (symbol_conf.report_hierarchy) {
+		struct perf_hpp_list_node *fmt_node;
+
+		/* count overhead columns (in the first node) */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+			++browser->b.columns;
+
+		/* add a single column for whole hierarchy sort keys*/
 		++browser->b.columns;
+	} else {
+		hists__for_each_format(hists, fmt)
+			++browser->b.columns;
 	}
+
+	hists__reset_column_width(hists);
 }
 
 struct hist_browser *hist_browser__new(struct hists *hists)
@@ -2418,8 +2482,6 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 		browser->hists->dso_filter = NULL;
 		ui_helpline__pop();
 	} else {
-		if (map == NULL)
-			return 0;
 		ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s DSO\"",
 				   __map__is_kernel(map) ? "the Kernel" : map->dso->short_name);
 		browser->hists->dso_filter = map->dso;
@@ -2787,7 +2849,10 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			do_zoom_dso(browser, actions);
 			continue;
 		case 'V':
-			browser->show_dso = !browser->show_dso;
+			verbose = (verbose + 1) % 4;
+			browser->show_dso = verbose > 0;
+			ui_helpline__fpush("Verbosity level set to %d\n",
+					   verbose);
 			continue;
 		case 't':
 			actions->thread = thread;
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index 39bd0f28f211..23d6acb84800 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -18,6 +18,7 @@ struct hist_browser {
 	u64		     nr_non_filtered_entries;
 	u64		     nr_hierarchy_entries;
 	u64		     nr_callchain_rows;
+	bool		     c2c_filter;
 
 	/* Get title string. */
 	int                  (*title)(struct hist_browser *browser,
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 80912778bb6d..98a34664bb7e 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -52,9 +52,9 @@ static int map_browser__search(struct map_browser *browser)
 
 	if (target[0] == '0' && tolower(target[1]) == 'x') {
 		u64 addr = strtoull(target, NULL, 16);
-		sym = map__find_symbol(browser->map, addr, NULL);
+		sym = map__find_symbol(browser->map, addr);
 	} else
-		sym = map__find_symbol_by_name(browser->map, target, NULL);
+		sym = map__find_symbol_by_name(browser->map, target);
 
 	if (sym != NULL) {
 		u32 *idx = symbol__browser_index(sym);
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 42d319927762..8c9308ac30b7 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -167,7 +167,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__disassemble(sym, map, 0);
+	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel), 0);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index c5f3677f6679..a4f02de7c1b5 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -549,7 +549,7 @@ static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
 				strcat(buf, "+");
 			first_col = false;
 
-			fmt->header(fmt, &hpp, hists);
+			fmt->header(fmt, &hpp, hists, 0, NULL);
 			strcat(buf, ltrim(rtrim(hpp.buf)));
 		}
 	}
diff --git a/tools/perf/ui/helpline.c b/tools/perf/ui/helpline.c
index 5b74a7eba210..379039ab00d8 100644
--- a/tools/perf/ui/helpline.c
+++ b/tools/perf/ui/helpline.c
@@ -72,3 +72,13 @@ int ui_helpline__vshow(const char *fmt, va_list ap)
 {
 	return helpline_fns->show(fmt, ap);
 }
+
+void ui_helpline__printf(const char *fmt, ...)
+{
+	va_list ap;
+
+	ui_helpline__pop();
+	va_start(ap, fmt);
+	ui_helpline__vpush(fmt, ap);
+	va_end(ap);
+}
diff --git a/tools/perf/ui/helpline.h b/tools/perf/ui/helpline.h
index 46181f4fc07e..d52d0a1a881b 100644
--- a/tools/perf/ui/helpline.h
+++ b/tools/perf/ui/helpline.h
@@ -21,6 +21,7 @@ void ui_helpline__push(const char *msg);
 void ui_helpline__vpush(const char *fmt, va_list ap);
 void ui_helpline__fpush(const char *fmt, ...);
 void ui_helpline__puts(const char *msg);
+void ui_helpline__printf(const char *fmt, ...);
 int  ui_helpline__vshow(const char *fmt, va_list ap);
 
 extern char ui_helpline__current[512];
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 4274969ddc89..37388397b5bc 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -230,13 +230,14 @@ static int hpp__width_fn(struct perf_hpp_fmt *fmt,
 }
 
 static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
-			  struct hists *hists)
+			  struct hists *hists, int line __maybe_unused,
+			  int *span __maybe_unused)
 {
 	int len = hpp__width_fn(fmt, hpp, hists);
 	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
-static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
+int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	va_list args;
 	ssize_t ssize = hpp->size;
@@ -441,6 +442,7 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 struct perf_hpp_list perf_hpp_list = {
 	.fields	= LIST_HEAD_INIT(perf_hpp_list.fields),
 	.sorts	= LIST_HEAD_INIT(perf_hpp_list.sorts),
+	.nr_header_lines = 1,
 };
 
 #undef HPP__COLOR_PRINT_FNS
@@ -697,6 +699,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 	}
 }
 
+void hists__reset_column_width(struct hists *hists)
+{
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *node;
+
+	hists__for_each_format(hists, fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	/* hierarchy entries have their own hpp list */
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		perf_hpp_list__for_each_format(&node->hpp, fmt)
+			perf_hpp__reset_width(fmt, hists);
+	}
+}
+
 void perf_hpp__set_user_width(const char *width_list_str)
 {
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index f04a63112079..668f4aecf2e6 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/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;
@@ -373,7 +400,8 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
+			   struct perf_hpp_list *hpp_list)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
@@ -384,7 +412,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	hists__for_each_format(he->hists, fmt) {
+	perf_hpp_list__for_each_format(hpp_list, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
@@ -410,6 +438,11 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 	return hpp->buf - start;
 }
 
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+{
+	return __hist_entry__snprintf(he, hpp, he->hists->hpp_list);
+}
+
 static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
 					 struct perf_hpp *hpp,
 					 struct hists *hists,
@@ -528,8 +561,8 @@ static int print_hierarchy_indent(const char *sep, int indent,
 	return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
 }
 
-static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
-				  const char *sep, FILE *fp)
+static int hists__fprintf_hierarchy_headers(struct hists *hists,
+					    struct perf_hpp *hpp, FILE *fp)
 {
 	bool first_node, first_col;
 	int indent;
@@ -538,6 +571,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	unsigned header_width = 0;
 	struct perf_hpp_fmt *fmt;
 	struct perf_hpp_list_node *fmt_node;
+	const char *sep = symbol_conf.field_sep;
 
 	indent = hists->nr_hpp_node;
 
@@ -549,7 +583,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				    struct perf_hpp_list_node, list);
 
 	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
-		fmt->header(fmt, hpp, hists);
+		fmt->header(fmt, hpp, hists, 0, NULL);
 		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
 	}
 
@@ -569,7 +603,7 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 				header_width += fprintf(fp, "+");
 			first_col = false;
 
-			fmt->header(fmt, hpp, hists);
+			fmt->header(fmt, hpp, hists, 0, NULL);
 
 			header_width += fprintf(fp, "%s", trim(hpp->buf));
 		}
@@ -623,20 +657,28 @@ static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
 	return 2;
 }
 
-static int
-hists__fprintf_hierarchy_headers(struct hists *hists,
-				 struct perf_hpp *hpp,
-				 FILE *fp)
+static void fprintf_line(struct hists *hists, struct perf_hpp *hpp,
+			 int line, FILE *fp)
 {
-	struct perf_hpp_list_node *fmt_node;
 	struct perf_hpp_fmt *fmt;
+	const char *sep = symbol_conf.field_sep;
+	bool first = true;
+	int span = 0;
 
-	list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
-		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
-			perf_hpp__reset_width(fmt, hists);
-	}
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__should_skip(fmt, hists))
+			continue;
+
+		if (!first && !span)
+			fprintf(fp, "%s", sep ?: "  ");
+		else
+			first = false;
+
+		fmt->header(fmt, hpp, hists, line, &span);
 
-	return print_hierarchy_header(hists, hpp, symbol_conf.field_sep, fp);
+		if (!span)
+			fprintf(fp, "%s", hpp->buf);
+	}
 }
 
 static int
@@ -644,28 +686,23 @@ hists__fprintf_standard_headers(struct hists *hists,
 				struct perf_hpp *hpp,
 				FILE *fp)
 {
+	struct perf_hpp_list *hpp_list = hists->hpp_list;
 	struct perf_hpp_fmt *fmt;
 	unsigned int width;
 	const char *sep = symbol_conf.field_sep;
 	bool first = true;
-
-	hists__for_each_format(hists, fmt) {
-		if (perf_hpp__should_skip(fmt, hists))
-			continue;
-
-		if (!first)
-			fprintf(fp, "%s", sep ?: "  ");
-		else
-			first = false;
-
-		fmt->header(fmt, hpp, hists);
-		fprintf(fp, "%s", hpp->buf);
+	int line;
+
+	for (line = 0; line < hpp_list->nr_header_lines; line++) {
+		/* first # is displayed one level up */
+		if (line)
+			fprintf(fp, "# ");
+		fprintf_line(hists, hpp, line, fp);
+		fprintf(fp, "\n");
 	}
 
-	fprintf(fp, "\n");
-
 	if (sep)
-		return 1;
+		return hpp_list->nr_header_lines;
 
 	first = true;
 
@@ -689,12 +726,12 @@ hists__fprintf_standard_headers(struct hists *hists,
 
 	fprintf(fp, "\n");
 	fprintf(fp, "#\n");
-	return 3;
+	return hpp_list->nr_header_lines + 2;
 }
 
-static int hists__fprintf_headers(struct hists *hists, FILE *fp)
+int hists__fprintf_headers(struct hists *hists, FILE *fp)
 {
-	char bf[96];
+	char bf[1024];
 	struct perf_hpp dummy_hpp = {
 		.buf	= bf,
 		.size	= sizeof(bf),
@@ -713,7 +750,6 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
 		      bool use_callchain)
 {
-	struct perf_hpp_fmt *fmt;
 	struct rb_node *nd;
 	size_t ret = 0;
 	const char *sep = symbol_conf.field_sep;
@@ -724,8 +760,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	init_rem_hits();
 
-	hists__for_each_format(hists, fmt)
-		perf_hpp__reset_width(fmt, hists);
+	hists__reset_column_width(hists);
 
 	if (symbol_conf.col_width_list_str)
 		perf_hpp__set_user_width(symbol_conf.col_width_list_str);