Linux-libre 4.6.2-gnu

7 files changed, 1380 insertions, 227 deletions

diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index d37202121..af68a9d48 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -531,8 +531,8 @@ static struct ui_browser_colorset {
 		.bg	  = "yellow",
 	},
 	{
-		.colorset = HE_COLORSET_CODE,
-		.name	  = "code",
+		.colorset = HE_COLORSET_JUMP_ARROWS,
+		.name	  = "jump_arrows",
 		.fg	  = "blue",
 		.bg	  = "default",
 	},
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 01781de59..be3b70eb5 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -7,7 +7,7 @@
 #define HE_COLORSET_MEDIUM	51
 #define HE_COLORSET_NORMAL	52
 #define HE_COLORSET_SELECTED	53
-#define HE_COLORSET_CODE	54
+#define HE_COLORSET_JUMP_ARROWS	54
 #define HE_COLORSET_ADDR	55
 #define HE_COLORSET_ROOT	56
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 718bd46d4..4fc208e82 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
-	ui_browser__set_color(browser, HE_COLORSET_CODE);
+	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7bb47424b..2a8341415 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -32,6 +32,7 @@ struct hist_browser {
 	bool		     show_headers;
 	float		     min_pcnt;
 	u64		     nr_non_filtered_entries;
+	u64		     nr_hierarchy_entries;
 	u64		     nr_callchain_rows;
 };
 
@@ -58,11 +59,11 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 
 	for (nd = rb_first(&hists->entries);
 	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
+	     nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *he =
 			rb_entry(nd, struct hist_entry, rb_node);
 
-		if (he->unfolded)
+		if (he->leaf && he->unfolded)
 			unfolded_rows += he->nr_rows;
 	}
 	return unfolded_rows;
@@ -72,7 +73,9 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 {
 	u32 nr_entries;
 
-	if (hist_browser__has_filter(hb))
+	if (symbol_conf.report_hierarchy)
+		nr_entries = hb->nr_hierarchy_entries;
+	else if (hist_browser__has_filter(hb))
 		nr_entries = hb->nr_non_filtered_entries;
 	else
 		nr_entries = hb->hists->nr_entries;
@@ -247,6 +250,38 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
+static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he,
+				bool include_children)
+{
+	int count = 0;
+	struct rb_node *node;
+	struct hist_entry *child;
+
+	if (he->leaf)
+		return callchain__count_rows(&he->sorted_chain);
+
+	if (he->has_no_entry)
+		return 1;
+
+	node = rb_first(&he->hroot_out);
+	while (node) {
+		float percent;
+
+		child = rb_entry(node, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+
+		if (!child->filtered && percent >= hb->min_pcnt) {
+			count++;
+
+			if (include_children && child->unfolded)
+				count += hierarchy_count_rows(hb, child, true);
+		}
+
+		node = rb_next(node);
+	}
+	return count;
+}
+
 static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
 	if (!he)
@@ -326,11 +361,17 @@ static void callchain__init_have_children(struct rb_root *root)
 
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
-	if (!he->init_have_children) {
+	if (he->init_have_children)
+		return;
+
+	if (he->leaf) {
 		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
-		he->init_have_children = true;
+	} else {
+		he->has_children = !RB_EMPTY_ROOT(&he->hroot_out);
 	}
+
+	he->init_have_children = true;
 }
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
@@ -349,17 +390,49 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 		has_children = callchain_list__toggle_fold(cl);
 
 	if (has_children) {
+		int child_rows = 0;
+
 		hist_entry__init_have_children(he);
 		browser->b.nr_entries -= he->nr_rows;
-		browser->nr_callchain_rows -= he->nr_rows;
 
-		if (he->unfolded)
-			he->nr_rows = callchain__count_rows(&he->sorted_chain);
+		if (he->leaf)
+			browser->nr_callchain_rows -= he->nr_rows;
 		else
+			browser->nr_hierarchy_entries -= he->nr_rows;
+
+		if (symbol_conf.report_hierarchy)
+			child_rows = hierarchy_count_rows(browser, he, true);
+
+		if (he->unfolded) {
+			if (he->leaf)
+				he->nr_rows = callchain__count_rows(&he->sorted_chain);
+			else
+				he->nr_rows = hierarchy_count_rows(browser, he, false);
+
+			/* account grand children */
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries += child_rows - he->nr_rows;
+
+			if (!he->leaf && he->nr_rows == 0) {
+				he->has_no_entry = true;
+				he->nr_rows = 1;
+			}
+		} else {
+			if (symbol_conf.report_hierarchy)
+				browser->b.nr_entries -= child_rows - he->nr_rows;
+
+			if (he->has_no_entry)
+				he->has_no_entry = false;
+
 			he->nr_rows = 0;
+		}
 
 		browser->b.nr_entries += he->nr_rows;
-		browser->nr_callchain_rows += he->nr_rows;
+
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else
+			browser->nr_hierarchy_entries += he->nr_rows;
 
 		return true;
 	}
@@ -422,13 +495,38 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
+static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
+				 bool unfold __maybe_unused)
+{
+	float percent;
+	struct rb_node *nd;
+	struct hist_entry *child;
+	int n = 0;
+
+	for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) {
+		child = rb_entry(nd, struct hist_entry, rb_node);
+		percent = hist_entry__get_percent_limit(child);
+		if (!child->filtered && percent >= hb->min_pcnt)
+			n++;
+	}
+
+	return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
 
 	if (he->has_children) {
-		int n = callchain__set_folding(&he->sorted_chain, unfold);
+		int n;
+
+		if (he->leaf)
+			n = callchain__set_folding(&he->sorted_chain, unfold);
+		else
+			n = hierarchy_set_folding(hb, he, unfold);
+
 		he->nr_rows = unfold ? n : 0;
 	} else
 		he->nr_rows = 0;
@@ -438,19 +536,38 @@ static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
-	struct hists *hists = browser->hists;
+	struct hist_entry *he;
+	double percent;
 
-	for (nd = rb_first(&hists->entries);
-	     (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-	     nd = rb_next(nd)) {
-		struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-		hist_entry__set_folding(he, unfold);
-		browser->nr_callchain_rows += he->nr_rows;
+	nd = rb_first(&browser->hists->entries);
+	while (nd) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		/* set folding state even if it's currently folded */
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		hist_entry__set_folding(he, browser, unfold);
+
+		percent = hist_entry__get_percent_limit(he);
+		if (he->filtered || percent < browser->min_pcnt)
+			continue;
+
+		if (!he->depth || unfold)
+			browser->nr_hierarchy_entries++;
+		if (he->leaf)
+			browser->nr_callchain_rows += he->nr_rows;
+		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+			browser->nr_hierarchy_entries++;
+			he->has_no_entry = true;
+			he->nr_rows = 1;
+		} else
+			he->has_no_entry = false;
 	}
 }
 
 static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
+	browser->nr_hierarchy_entries = 0;
 	browser->nr_callchain_rows = 0;
 	__hist_browser__set_folding(browser, unfold);
 
@@ -657,9 +774,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
 	return 1;
 }
 
+static bool check_percent_display(struct rb_node *node, u64 parent_total)
+{
+	struct callchain_node *child;
+
+	if (node == NULL)
+		return false;
+
+	if (rb_next(node))
+		return true;
+
+	child = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(child) != parent_total;
+}
+
 static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 					     struct rb_root *root,
 					     unsigned short row, u64 total,
+					     u64 parent_total,
 					     print_callchain_entry_fn print,
 					     struct callchain_print_arg *arg,
 					     check_output_full_fn is_output_full)
@@ -669,7 +801,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -763,6 +895,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
 static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 					       struct rb_root *root,
 					       unsigned short row, u64 total,
+					       u64 parent_total,
 					       print_callchain_entry_fn print,
 					       struct callchain_print_arg *arg,
 					       check_output_full_fn is_output_full)
@@ -772,7 +905,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
 	bool need_percent;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -847,17 +980,21 @@ next:
 static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
+					u64 parent_total,
 					print_callchain_entry_fn print,
 					struct callchain_print_arg *arg,
 					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total;
 	bool need_percent;
+	u64 percent_total = total;
+
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		percent_total = parent_total;
 
 	node = rb_first(root);
-	need_percent = node && rb_next(node);
+	need_percent = check_percent_display(node, parent_total);
 
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -878,7 +1015,7 @@ static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 			folded_sign = callchain_list__folded(chain);
 
 			row += hist_browser__show_callchain_list(browser, child,
-							chain, row, total,
+							chain, row, percent_total,
 							was_first && need_percent,
 							offset + extra_offset,
 							print, arg);
@@ -893,13 +1030,9 @@ static int hist_browser__show_callchain_graph(struct hist_browser *browser,
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
 
-			if (callchain_param.mode == CHAIN_GRAPH_REL)
-				new_total = child->children_hit;
-			else
-				new_total = total;
-
 			row += hist_browser__show_callchain_graph(browser, &child->rb_root,
-							    new_level, row, new_total,
+							    new_level, row, total,
+							    child->children_hit,
 							    print, arg, is_output_full);
 		}
 		if (is_output_full(browser, row))
@@ -918,27 +1051,29 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 					check_output_full_fn is_output_full)
 {
 	u64 total = hists__total_period(entry->hists);
+	u64 parent_total;
 	int printed;
 
-	if (callchain_param.mode == CHAIN_GRAPH_REL) {
-		if (symbol_conf.cumulate_callchain)
-			total = entry->stat_acc->period;
-		else
-			total = entry->stat.period;
-	}
+	if (symbol_conf.cumulate_callchain)
+		parent_total = entry->stat_acc->period;
+	else
+		parent_total = entry->stat.period;
 
 	if (callchain_param.mode == CHAIN_FLAT) {
 		printed = hist_browser__show_callchain_flat(browser,
-						&entry->sorted_chain, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	} else if (callchain_param.mode == CHAIN_FOLDED) {
 		printed = hist_browser__show_callchain_folded(browser,
-						&entry->sorted_chain, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	} else {
 		printed = hist_browser__show_callchain_graph(browser,
-						&entry->sorted_chain, level, row, total,
-						print, arg, is_output_full);
+						&entry->sorted_chain, level, row,
+						total, parent_total, print, arg,
+						is_output_full);
 	}
 
 	if (arg->is_current_entry)
@@ -1043,7 +1178,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				    struct hist_entry *entry,
 				    unsigned short row)
 {
-	char s[256];
 	int printed = 0;
 	int width = browser->b.width;
 	char folded_sign = ' ';
@@ -1068,16 +1202,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.folded_sign	= folded_sign,
 			.current_entry	= current_entry,
 		};
-		struct perf_hpp hpp = {
-			.buf		= s,
-			.size		= sizeof(s),
-			.ptr		= &arg,
-		};
 		int column = 0;
 
 		hist_browser__gotorc(browser, row, 0);
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(browser->hists, fmt) {
+			char s[2048];
+			struct perf_hpp hpp = {
+				.buf	= s,
+				.size	= sizeof(s),
+				.ptr	= &arg,
+			};
+
 			if (perf_hpp__should_skip(fmt, entry->hists) ||
 			    column++ < browser->b.horiz_scroll)
 				continue;
@@ -1102,11 +1238,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			}
 
 			if (fmt->color) {
-				width -= fmt->color(fmt, &hpp, entry);
+				int ret = fmt->color(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+				/*
+				 * fmt->color() already used ui_browser to
+				 * print the non alignment bits, skip it (+ret):
+				 */
+				ui_browser__printf(&browser->b, "%s", s + ret);
 			} else {
-				width -= fmt->entry(fmt, &hpp, entry);
+				hist_entry__snprintf_alignment(entry, &hpp, fmt, fmt->entry(fmt, &hpp, entry));
 				ui_browser__printf(&browser->b, "%s", s);
 			}
+			width -= hpp.buf - s;
 		}
 
 		/* The scroll bar isn't being used */
@@ -1134,6 +1277,233 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	return printed;
 }
 
+static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
+					      struct hist_entry *entry,
+					      unsigned short row,
+					      int level)
+{
+	int printed = 0;
+	int width = browser->b.width;
+	char folded_sign = ' ';
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	off_t row_offset = entry->row_offset;
+	bool first = true;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	struct hpp_arg arg = {
+		.b		= &browser->b,
+		.current_entry	= current_entry,
+	};
+	int column = 0;
+	int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	if (current_entry) {
+		browser->he_selection = entry;
+		browser->selection = &entry->ms;
+	}
+
+	hist_entry__init_have_children(entry);
+	folded_sign = hist_entry__folded(entry);
+	arg.folded_sign = folded_sign;
+
+	if (entry->leaf && row_offset) {
+		row_offset--;
+		goto show_callchain;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&entry->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (perf_hpp__should_skip(fmt, entry->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
+		} else {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
+		}
+
+		if (first) {
+			ui_browser__printf(&browser->b, "%c", folded_sign);
+			width--;
+			first = false;
+		} else {
+			ui_browser__printf(&browser->b, "  ");
+			width -= 2;
+		}
+
+		if (fmt->color) {
+			int ret = fmt->color(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			/*
+			 * fmt->color() already used ui_browser to
+			 * print the non alignment bits, skip it (+ret):
+			 */
+			ui_browser__printf(&browser->b, "%s", s + ret);
+		} else {
+			int ret = fmt->entry(fmt, &hpp, entry);
+			hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+			ui_browser__printf(&browser->b, "%s", s);
+		}
+		width -= hpp.buf - s;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+	width -= hierarchy_indent;
+
+	if (column >= browser->b.horiz_scroll) {
+		char s[2048];
+		struct perf_hpp hpp = {
+			.buf		= s,
+			.size		= sizeof(s),
+			.ptr		= &arg,
+		};
+
+		if (current_entry && browser->b.navkeypressed) {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_SELECTED);
+		} else {
+			ui_browser__set_color(&browser->b,
+					      HE_COLORSET_NORMAL);
+		}
+
+		perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
+			ui_browser__write_nstring(&browser->b, "", 2);
+			width -= 2;
+
+			/*
+			 * No need to call hist_entry__snprintf_alignment()
+			 * since this fmt is always the last column in the
+			 * hierarchy mode.
+			 */
+			if (fmt->color) {
+				width -= fmt->color(fmt, &hpp, entry);
+			} else {
+				int i = 0;
+
+				width -= fmt->entry(fmt, &hpp, entry);
+				ui_browser__printf(&browser->b, "%s", ltrim(s));
+
+				while (isspace(s[i++]))
+					width++;
+			}
+		}
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+
+	++row;
+	++printed;
+
+show_callchain:
+	if (entry->leaf && folded_sign == '-' && row != browser->b.rows) {
+		struct callchain_print_arg carg = {
+			.row_offset = row_offset,
+		};
+
+		printed += hist_browser__show_callchain(browser, entry,
+					level + 1, row,
+					hist_browser__show_callchain_entry, &carg,
+					hist_browser__check_output_full);
+	}
+
+	return printed;
+}
+
+static int hist_browser__show_no_entry(struct hist_browser *browser,
+				       unsigned short row, int level)
+{
+	int width = browser->b.width;
+	bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+	bool first = true;
+	int column = 0;
+	int ret;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	int indent = browser->hists->nr_hpp_node - 2;
+
+	if (current_entry) {
+		browser->he_selection = NULL;
+		browser->selection = NULL;
+	}
+
+	hist_browser__gotorc(browser, row, 0);
+
+	if (current_entry && browser->b.navkeypressed)
+		ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+	else
+		ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+	ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+	width -= level * HIERARCHY_INDENT;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&browser->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (perf_hpp__should_skip(fmt, browser->hists) ||
+		    column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+
+		if (first) {
+			/* for folded sign */
+			first = false;
+			ret++;
+		} else {
+			/* space between columns */
+			ret += 2;
+		}
+
+		ui_browser__write_nstring(&browser->b, "", ret);
+		width -= ret;
+	}
+
+	ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT);
+	width -= indent * HIERARCHY_INDENT;
+
+	if (column >= browser->b.horiz_scroll) {
+		char buf[32];
+
+		ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt);
+		ui_browser__printf(&browser->b, "  %s", buf);
+		width -= ret + 2;
+	}
+
+	/* The scroll bar isn't being used */
+	if (!browser->b.navkeypressed)
+		width += 1;
+
+	ui_browser__write_nstring(&browser->b, "", width);
+	return 1;
+}
+
 static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 {
 	advance_hpp(hpp, inc);
@@ -1157,7 +1527,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 			return ret;
 	}
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
@@ -1173,11 +1543,96 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	return ret;
 }
 
+static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size)
+{
+	struct hists *hists = browser->hists;
+	struct perf_hpp dummy_hpp = {
+		.buf    = buf,
+		.size   = size,
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	size_t ret = 0;
+	int column = 0;
+	int indent = hists->nr_hpp_node - 2;
+	bool first_node, first_col;
+
+	ret = scnprintf(buf, size, " ");
+	if (advance_hpp_check(&dummy_hpp, ret))
+		return ret;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (column++ < browser->b.horiz_scroll)
+			continue;
+
+		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+	}
+
+	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) {
+		if (!first_node) {
+			ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / ");
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			char *start;
+
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col) {
+				ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+");
+				if (advance_hpp_check(&dummy_hpp, ret))
+					break;
+			}
+			first_col = false;
+
+			ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+			dummy_hpp.buf[ret] = '\0';
+			rtrim(dummy_hpp.buf);
+
+			start = ltrim(dummy_hpp.buf);
+			ret = strlen(start);
+
+			if (start != dummy_hpp.buf)
+				memmove(dummy_hpp.buf, start, ret + 1);
+
+			if (advance_hpp_check(&dummy_hpp, ret))
+				break;
+		}
+	}
+
+	return ret;
+}
+
 static void hist_browser__show_headers(struct hist_browser *browser)
 {
 	char headers[1024];
 
-	hists_browser__scnprintf_headers(browser, headers, sizeof(headers));
+	if (symbol_conf.report_hierarchy)
+		hists_browser__scnprintf_hierarchy_headers(browser, headers,
+							   sizeof(headers));
+	else
+		hists_browser__scnprintf_headers(browser, headers,
+						 sizeof(headers));
 	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);
@@ -1209,18 +1664,34 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 	hb->he_selection = NULL;
 	hb->selection = NULL;
 
-	for (nd = browser->top; nd; nd = rb_next(nd)) {
+	for (nd = browser->top; nd; nd = rb_hierarchy_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
-		if (h->filtered)
+		if (h->filtered) {
+			/* let it move to sibling */
+			h->unfolded = false;
 			continue;
+		}
 
 		percent = hist_entry__get_percent_limit(h);
 		if (percent < hb->min_pcnt)
 			continue;
 
-		row += hist_browser__show_entry(hb, h, row);
+		if (symbol_conf.report_hierarchy) {
+			row += hist_browser__show_hierarchy_entry(hb, h, row,
+								  h->depth);
+			if (row == browser->rows)
+				break;
+
+			if (h->has_no_entry) {
+				hist_browser__show_no_entry(hb, row, h->depth + 1);
+				row++;
+			}
+		} else {
+			row += hist_browser__show_entry(hb, h, row);
+		}
+
 		if (row == browser->rows)
 			break;
 	}
@@ -1238,7 +1709,14 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_next(nd);
+		/*
+		 * If it's filtered, its all children also were filtered.
+		 * So move to sibling node.
+		 */
+		if (rb_next(nd))
+			nd = rb_next(nd);
+		else
+			nd = rb_hierarchy_next(nd);
 	}
 
 	return NULL;
@@ -1254,7 +1732,7 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
 		if (!h->filtered && percent >= min_pcnt)
 			return nd;
 
-		nd = rb_prev(nd);
+		nd = rb_hierarchy_prev(nd);
 	}
 
 	return NULL;
@@ -1284,8 +1762,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
 		nd = browser->top;
 		goto do_offset;
 	case SEEK_END:
-		nd = hists__filter_prev_entries(rb_last(browser->entries),
-						hb->min_pcnt);
+		nd = rb_hierarchy_last(rb_last(browser->entries));
+		nd = hists__filter_prev_entries(nd, hb->min_pcnt);
 		first = false;
 		break;
 	default:
@@ -1319,7 +1797,7 @@ do_offset:
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				u16 remaining = h->nr_rows - h->row_offset;
 				if (offset > remaining) {
 					offset -= remaining;
@@ -1331,7 +1809,8 @@ do_offset:
 					break;
 				}
 			}
-			nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
+			nd = hists__filter_entries(rb_hierarchy_next(nd),
+						   hb->min_pcnt);
 			if (nd == NULL)
 				break;
 			--offset;
@@ -1340,7 +1819,7 @@ do_offset:
 	} else if (offset < 0) {
 		while (1) {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->unfolded) {
+			if (h->unfolded && h->leaf) {
 				if (first) {
 					if (-offset > h->row_offset) {
 						offset += h->row_offset;
@@ -1364,7 +1843,7 @@ do_offset:
 				}
 			}
 
-			nd = hists__filter_prev_entries(rb_prev(nd),
+			nd = hists__filter_prev_entries(rb_hierarchy_prev(nd),
 							hb->min_pcnt);
 			if (nd == NULL)
 				break;
@@ -1377,7 +1856,7 @@ do_offset:
 				 * row_offset at its last entry.
 				 */
 				h = rb_entry(nd, struct hist_entry, rb_node);
-				if (h->unfolded)
+				if (h->unfolded && h->leaf)
 					h->row_offset = h->nr_rows;
 				break;
 			}
@@ -1391,13 +1870,14 @@ do_offset:
 }
 
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-					   struct hist_entry *he, FILE *fp)
+					   struct hist_entry *he, FILE *fp,
+					   int level)
 {
 	struct callchain_print_arg arg  = {
 		.fp = fp,
 	};
 
-	hist_browser__show_callchain(browser, he, 1, 0,
+	hist_browser__show_callchain(browser, he, level, 0,
 				     hist_browser__fprintf_callchain_entry, &arg,
 				     hist_browser__check_dump_full);
 	return arg.printed;
@@ -1423,7 +1903,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 	if (symbol_conf.use_callchain)
 		printed += fprintf(fp, "%c ", folded_sign);
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
@@ -1434,12 +1914,71 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 			first = false;
 
 		ret = fmt->entry(fmt, &hpp, he);
+		ret = hist_entry__snprintf_alignment(he, &hpp, fmt, ret);
 		advance_hpp(&hpp, ret);
 	}
-	printed += fprintf(fp, "%s\n", rtrim(s));
+	printed += fprintf(fp, "%s\n", s);
 
 	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain(browser, he, fp);
+		printed += hist_browser__fprintf_callchain(browser, he, fp, 1);
+
+	return printed;
+}
+
+
+static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
+						 struct hist_entry *he,
+						 FILE *fp, int level)
+{
+	char s[8192];
+	int printed = 0;
+	char folded_sign = ' ';
+	struct perf_hpp hpp = {
+		.buf = s,
+		.size = sizeof(s),
+	};
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	bool first = true;
+	int ret;
+	int hierarchy_indent = (he->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+	printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, "");
+
+	folded_sign = hist_entry__folded(he);
+	printed += fprintf(fp, "%c", folded_sign);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&he->hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first) {
+			ret = scnprintf(hpp.buf, hpp.size, "  ");
+			advance_hpp(&hpp, ret);
+		} else
+			first = false;
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, "");
+	advance_hpp(&hpp, ret);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		ret = scnprintf(hpp.buf, hpp.size, "  ");
+		advance_hpp(&hpp, ret);
+
+		ret = fmt->entry(fmt, &hpp, he);
+		advance_hpp(&hpp, ret);
+	}
+
+	printed += fprintf(fp, "%s\n", rtrim(s));
+
+	if (he->leaf && folded_sign == '-') {
+		printed += hist_browser__fprintf_callchain(browser, he, fp,
+							   he->depth + 1);
+	}
 
 	return printed;
 }
@@ -1453,8 +1992,16 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
 	while (nd) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		printed += hist_browser__fprintf_entry(browser, h, fp);
-		nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
+		if (symbol_conf.report_hierarchy) {
+			printed += hist_browser__fprintf_hierarchy_entry(browser,
+									 h, fp,
+									 h->depth);
+		} else {
+			printed += hist_browser__fprintf_entry(browser, h, fp);
+		}
+
+		nd = hists__filter_entries(rb_hierarchy_next(nd),
+					   browser->min_pcnt);
 	}
 
 	return printed;
@@ -1589,11 +2136,18 @@ static int hists__browser_title(struct hists *hists,
 	if (hists->uid_filter_str)
 		printed += snprintf(bf + printed, size - printed,
 				    ", UID: %s", hists->uid_filter_str);
-	if (thread)
-		printed += scnprintf(bf + printed, size - printed,
+	if (thread) {
+		if (sort__has_thread) {
+			printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				     (thread->comm_set ? thread__comm_str(thread) : ""),
 				    thread->tid);
+		} else {
+			printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s",
+				     (thread->comm_set ? thread__comm_str(thread) : ""));
+		}
+	}
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1768,15 +2322,24 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
 	struct thread *thread = act->thread;
 
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+		return 0;
+
 	if (browser->hists->thread_filter) {
 		pstack__remove(browser->pstack, &browser->hists->thread_filter);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		thread__zput(browser->hists->thread_filter);
 		ui_helpline__pop();
 	} else {
-		ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
-				   thread->comm_set ? thread__comm_str(thread) : "",
-				   thread->tid);
+		if (sort__has_thread) {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "",
+					   thread->tid);
+		} else {
+			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s thread\"",
+					   thread->comm_set ? thread__comm_str(thread) : "");
+		}
+
 		browser->hists->thread_filter = thread__get(thread);
 		perf_hpp__set_elide(HISTC_THREAD, false);
 		pstack__push(browser->pstack, &browser->hists->thread_filter);
@@ -1791,13 +2354,22 @@ static int
 add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, struct thread *thread)
 {
-	if (thread == NULL)
+	int ret;
+
+	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
 		return 0;
 
-	if (asprintf(optstr, "Zoom %s %s(%d) thread",
-		     browser->hists->thread_filter ? "out of" : "into",
-		     thread->comm_set ? thread__comm_str(thread) : "",
-		     thread->tid) < 0)
+	if (sort__has_thread) {
+		ret = asprintf(optstr, "Zoom %s %s(%d) thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "",
+			       thread->tid);
+	} else {
+		ret = asprintf(optstr, "Zoom %s %s thread",
+			       browser->hists->thread_filter ? "out of" : "into",
+			       thread->comm_set ? thread__comm_str(thread) : "");
+	}
+	if (ret < 0)
 		return 0;
 
 	act->thread = thread;
@@ -1810,6 +2382,9 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 {
 	struct map *map = act->ms.map;
 
+	if (!sort__has_dso || map == NULL)
+		return 0;
+
 	if (browser->hists->dso_filter) {
 		pstack__remove(browser->pstack, &browser->hists->dso_filter);
 		perf_hpp__set_elide(HISTC_DSO, false);
@@ -1834,7 +2409,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s DSO",
@@ -1859,7 +2434,7 @@ static int
 add_map_opt(struct hist_browser *browser __maybe_unused,
 	    struct popup_action *act, char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Browse map details") < 0)
@@ -1961,6 +2536,9 @@ add_exit_opt(struct hist_browser *browser __maybe_unused,
 static int
 do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
 {
+	if (!sort__has_socket || act->socket < 0)
+		return 0;
+
 	if (browser->hists->socket_filter > -1) {
 		pstack__remove(browser->pstack, &browser->hists->socket_filter);
 		browser->hists->socket_filter = -1;
@@ -1980,7 +2558,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, int socket_id)
 {
-	if (socket_id < 0)
+	if (!sort__has_socket || socket_id < 0)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -1998,17 +2576,60 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 	u64 nr_entries = 0;
 	struct rb_node *nd = rb_first(&hb->hists->entries);
 
-	if (hb->min_pcnt == 0) {
+	if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) {
 		hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
 		return;
 	}
 
 	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
 		nr_entries++;
-		nd = rb_next(nd);
+		nd = rb_hierarchy_next(nd);
 	}
 
 	hb->nr_non_filtered_entries = nr_entries;
+	hb->nr_hierarchy_entries = nr_entries;
+}
+
+static void hist_browser__update_percent_limit(struct hist_browser *hb,
+					       double percent)
+{
+	struct hist_entry *he;
+	struct rb_node *nd = rb_first(&hb->hists->entries);
+	u64 total = hists__total_period(hb->hists);
+	u64 min_callchain_hits = total * (percent / 100);
+
+	hb->min_pcnt = callchain_param.min_percent = percent;
+
+	while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
+		he = rb_entry(nd, struct hist_entry, rb_node);
+
+		if (he->has_no_entry) {
+			he->has_no_entry = false;
+			he->nr_rows = 0;
+		}
+
+		if (!he->leaf || !symbol_conf.use_callchain)
+			goto next;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+
+next:
+		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+		/* force to re-evaluate folding state of callchains */
+		he->init_have_children = false;
+		hist_entry__set_folding(he, hb, false);
+	}
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -2046,6 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
 	"H             Display column headers\n"			\
+	"L             Change percent limit\n"				\
 	"m             Display context menu\n"				\
 	"S             Zoom into current Processor Socket\n"		\
 
@@ -2086,7 +2708,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	memset(options, 0, sizeof(options));
 	memset(actions, 0, sizeof(actions));
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(browser->hists, fmt) {
 		perf_hpp__reset_width(fmt, hists);
 		/*
 		 * This is done just once, and activates the horizontal scrolling
@@ -2201,6 +2823,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				top->zero = !top->zero;
 			}
 			continue;
+		case 'L':
+			if (ui_browser__input_window("Percent Limit",
+					"Please enter the value you want to hide entries under that percent.",
+					buf, "ENTER: OK, ESC: Cancel",
+					delay_secs * 2) == K_ENTER) {
+				char *end;
+				double new_percent = strtod(buf, &end);
+
+				if (new_percent < 0 || new_percent > 100) {
+					ui_browser__warning(&browser->b, delay_secs * 2,
+						"Invalid percent: %.2f", new_percent);
+					continue;
+				}
+
+				hist_browser__update_percent_limit(browser, new_percent);
+				hist_browser__reset(browser);
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
@@ -2272,10 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!sort__has_sym)
-			goto add_exit_option;
-
-		if (browser->selection == NULL)
+		if (!sort__has_sym || browser->selection == NULL)
 			goto skip_annotation;
 
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -2315,11 +2952,16 @@ skip_annotation:
 					     &options[nr_options],
 					     socked_id);
 		/* perf script support */
+		if (!is_report_browser(hbt))
+			goto skip_scripting;
+
 		if (browser->he_selection) {
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     thread, NULL);
+			if (sort__has_thread && thread) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     thread, NULL);
+			}
 			/*
 			 * Note that browser->selection != NULL
 			 * when browser->he_selection is not NULL,
@@ -2340,7 +2982,7 @@ skip_annotation:
 					     &options[nr_options], NULL, NULL);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
-add_exit_option:
+skip_scripting:
 		nr_options += add_exit_opt(browser, &actions[nr_options],
 					   &options[nr_options]);
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 0f8dcfdfb..2aa45b606 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -55,7 +55,7 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
 	return he->stat_acc->_field;						\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
@@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	nr_cols = 0;
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		col_types[nr_cols++] = G_TYPE_STRING;
 
 	store = gtk_tree_store_newv(nr_cols, col_types);
@@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 	col_idx = 0;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
 		col_idx = 0;
 
-		perf_hpp__for_each_format(fmt) {
+		hists__for_each_format(hists, fmt) {
 			if (perf_hpp__should_skip(fmt, h->hists))
 				continue;
 
@@ -396,6 +396,194 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 
+static void perf_gtk__add_hierarchy_entries(struct hists *hists,
+					    struct rb_root *root,
+					    GtkTreeStore *store,
+					    GtkTreeIter *parent,
+					    struct perf_hpp *hpp,
+					    float min_pcnt)
+{
+	int col_idx = 0;
+	struct rb_node *node;
+	struct hist_entry *he;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	u64 total = hists__total_period(hists);
+	int size;
+
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		GtkTreeIter iter;
+		float percent;
+		char *bf;
+
+		he = rb_entry(node, struct hist_entry, rb_node);
+		if (he->filtered)
+			continue;
+
+		percent = hist_entry__get_percent_limit(he);
+		if (percent < min_pcnt)
+			continue;
+
+		gtk_tree_store_append(store, &iter, parent);
+
+		col_idx = 0;
+
+		/* the first hpp_list_node is for overhead columns */
+		fmt_node = list_first_entry(&hists->hpp_formats,
+					    struct perf_hpp_list_node, list);
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (fmt->color)
+				fmt->color(fmt, hpp, he);
+			else
+				fmt->entry(fmt, hpp, he);
+
+			gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1);
+		}
+
+		bf = hpp->buf;
+		size = hpp->size;
+		perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+			int ret;
+
+			if (fmt->color)
+				ret = fmt->color(fmt, hpp, he);
+			else
+				ret = fmt->entry(fmt, hpp, he);
+
+			snprintf(hpp->buf + ret, hpp->size - ret, "  ");
+			advance_hpp(hpp, ret + 2);
+		}
+
+		gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
+
+		if (!he->leaf) {
+			hpp->buf = bf;
+			hpp->size = size;
+
+			perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
+							store, &iter, hpp,
+							min_pcnt);
+
+			if (!hist_entry__has_hierarchy_children(he, min_pcnt)) {
+				char buf[32];
+				GtkTreeIter child;
+
+				snprintf(buf, sizeof(buf), "no entry >= %.2f%%",
+					 min_pcnt);
+
+				gtk_tree_store_append(store, &child, &iter);
+				gtk_tree_store_set(store, &child, col_idx, buf, -1);
+			}
+		}
+
+		if (symbol_conf.use_callchain && he->leaf) {
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				total = symbol_conf.cumulate_callchain ?
+					he->stat_acc->period : he->stat.period;
+
+			perf_gtk__add_callchain(&he->sorted_chain, store, &iter,
+						col_idx, total);
+		}
+	}
+
+}
+
+static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
+				     float min_pcnt)
+{
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+	GType col_types[MAX_COLUMNS];
+	GtkCellRenderer *renderer;
+	GtkTreeStore *store;
+	GtkWidget *view;
+	int col_idx;
+	int nr_cols = 0;
+	char s[512];
+	char buf[512];
+	bool first_node, first_col;
+	struct perf_hpp hpp = {
+		.buf		= s,
+		.size		= sizeof(s),
+	};
+
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) ||
+		    perf_hpp__is_dynamic_entry(fmt))
+			break;
+
+		col_types[nr_cols++] = G_TYPE_STRING;
+	}
+	col_types[nr_cols++] = G_TYPE_STRING;
+
+	store = gtk_tree_store_newv(nr_cols, col_types);
+	view = gtk_tree_view_new();
+	renderer = gtk_cell_renderer_text_new();
+
+	col_idx = 0;
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+							    -1, fmt->name,
+							    renderer, "markup",
+							    col_idx++, NULL);
+	}
+
+	/* construct merged column header since sort keys share single column */
+	buf[0] = '\0';
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			strcat(buf, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				strcat(buf, "+");
+			first_col = false;
+
+			fmt->header(fmt, &hpp, hists_to_evsel(hists));
+			strcat(buf, ltrim(rtrim(hpp.buf)));
+		}
+	}
+
+	gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+						    -1, buf,
+						    renderer, "markup",
+						    col_idx++, NULL);
+
+	for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+		GtkTreeViewColumn *column;
+
+		column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+		gtk_tree_view_column_set_resizable(column, TRUE);
+
+		if (col_idx == 0) {
+			gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+							  column);
+		}
+	}
+
+	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+	g_object_unref(GTK_TREE_MODEL(store));
+
+	perf_gtk__add_hierarchy_entries(hists, &hists->entries, store,
+					NULL, &hpp, min_pcnt);
+
+	gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+	g_signal_connect(view, "row-activated",
+			 G_CALLBACK(on_row_activated), NULL);
+	gtk_container_add(GTK_CONTAINER(window), view);
+}
+
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 				  const char *help,
 				  struct hist_browser_timer *hbt __maybe_unused,
@@ -463,7 +651,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
 							GTK_POLICY_AUTOMATIC,
 							GTK_POLICY_AUTOMATIC);
 
-		perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
+		if (symbol_conf.report_hierarchy)
+			perf_gtk__show_hierarchy(scrolled_window, hists, min_pcnt);
+		else
+			perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
 
 		tab_label = gtk_label_new(evname);
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index bf2a66e25..3baeaa6e7 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -5,6 +5,7 @@
 #include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
+#include "../util/evlist.h"
 
 /* hist period print (hpp) functions */
 
@@ -371,7 +372,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
+static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a)
+{
+	return a->header == hpp__header_fn;
+}
+
+static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b))
+		return false;
+
+	return a->idx == b->idx;
+}
+
+#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -381,9 +395,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx)	\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -393,9 +409,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
-#define HPP__PRINT_FNS(_name, _fn)			\
+#define HPP__PRINT_FNS(_name, _fn, _idx)		\
 	{						\
 		.name   = _name,			\
 		.header	= hpp__header_fn,		\
@@ -404,22 +422,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
 		.sort	= hpp__sort_ ## _fn,		\
+		.idx	= PERF_HPP__ ## _idx,		\
+		.equal	= hpp__equal,			\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS("Overhead", overhead),
-	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
-	HPP__COLOR_PRINT_FNS("usr", overhead_us),
-	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
-	HPP__PRINT_FNS("Samples", samples),
-	HPP__PRINT_FNS("Period", period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
+	HPP__PRINT_FNS("Samples", samples, SAMPLES),
+	HPP__PRINT_FNS("Period", period, PERIOD)
 };
 
-LIST_HEAD(perf_hpp__list);
-LIST_HEAD(perf_hpp__sort_list);
-
+struct perf_hpp_list perf_hpp_list = {
+	.fields	= LIST_HEAD_INIT(perf_hpp_list.fields),
+	.sorts	= LIST_HEAD_INIT(perf_hpp_list.sorts),
+};
 
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__COLOR_ACC_PRINT_FNS
@@ -485,63 +506,60 @@ void perf_hpp__init(void)
 		hpp_dimension__add_output(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_register(struct perf_hpp_fmt *format)
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+				    struct perf_hpp_fmt *format)
 {
-	list_add_tail(&format->list, &perf_hpp__list);
+	list_add_tail(&format->list, &list->fields);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+					struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_add_tail(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
-{
-	list_add_tail(&format->sort_list, &perf_hpp__sort_list);
-}
-
-void perf_hpp__column_enable(unsigned col)
-{
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_register(&perf_hpp__format[col]);
-}
-
-void perf_hpp__column_disable(unsigned col)
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	BUG_ON(col >= PERF_HPP__MAX_INDEX);
-	perf_hpp__column_unregister(&perf_hpp__format[col]);
+	list_del(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
 {
+	struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp;
+
 	if (is_strict_order(field_order))
 		return;
 
-	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
+	ovh = &perf_hpp__format[PERF_HPP__OVERHEAD];
+	acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC];
+
+	perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
+		if (acc->equal(acc, fmt)) {
+			perf_hpp__column_unregister(fmt);
+			continue;
+		}
+
+		if (ovh->equal(ovh, fmt))
+			fmt->name = "Overhead";
+	}
 }
 
-void perf_hpp__setup_output_field(void)
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+	return a->equal && a->equal(a, b);
+}
+
+void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append sort keys to output field */
-	perf_hpp__for_each_sort_list(fmt) {
-		if (!list_empty(&fmt->list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_sort_list(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_format(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_format(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__column_register(fmt);
@@ -550,27 +568,17 @@ next:
 	}
 }
 
-void perf_hpp__append_sort_keys(void)
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt;
 
 	/* append output fields to sort keys */
-	perf_hpp__for_each_format(fmt) {
-		if (!list_empty(&fmt->sort_list))
-			continue;
-
-		/*
-		 * sort entry fields are dynamically created,
-		 * so they can share a same sort key even though
-		 * the list is empty.
-		 */
-		if (perf_hpp__is_sort_entry(fmt)) {
-			struct perf_hpp_fmt *pos;
+	perf_hpp_list__for_each_format(list, fmt) {
+		struct perf_hpp_fmt *pos;
 
-			perf_hpp__for_each_sort_list(pos) {
-				if (perf_hpp__same_sort_entry(pos, fmt))
-					goto next;
-			}
+		perf_hpp_list__for_each_sort_list(list, pos) {
+			if (fmt_equal(fmt, pos))
+				goto next;
 		}
 
 		perf_hpp__register_sort_field(fmt);
@@ -579,20 +587,29 @@ next:
 	}
 }
 
-void perf_hpp__reset_output_field(void)
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+	if (fmt->free)
+		fmt->free(fmt);
+}
+
+void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
 	struct perf_hpp_fmt *fmt, *tmp;
 
 	/* reset output fields */
-	perf_hpp__for_each_format_safe(fmt, tmp) {
+	perf_hpp_list__for_each_format_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 
 	/* reset sort keys */
-	perf_hpp__for_each_sort_list_safe(fmt, tmp) {
+	perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) {
 		list_del_init(&fmt->list);
 		list_del_init(&fmt->sort_list);
+		fmt_free(fmt);
 	}
 }
 
@@ -606,7 +623,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	bool first = true;
 	struct perf_hpp dummy_hpp;
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -624,22 +641,39 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	return ret;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+unsigned int hists__overhead_width(struct hists *hists)
 {
-	int idx;
-
-	if (perf_hpp__is_sort_entry(fmt))
-		return perf_hpp__reset_sort_width(fmt, hists);
+	struct perf_hpp_fmt *fmt;
+	int ret = 0;
+	bool first = true;
+	struct perf_hpp dummy_hpp;
 
-	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-		if (fmt == &perf_hpp__format[idx])
+	hists__for_each_format(hists, fmt) {
+		if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
 			break;
+
+		if (first)
+			first = false;
+		else
+			ret += 2;
+
+		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 	}
 
-	if (idx == PERF_HPP__MAX_INDEX)
+	return ret;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	if (perf_hpp__is_dynamic_entry(fmt))
 		return;
 
-	switch (idx) {
+	BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX);
+
+	switch (fmt->idx) {
 	case PERF_HPP__OVERHEAD:
 	case PERF_HPP__OVERHEAD_SYS:
 	case PERF_HPP__OVERHEAD_US:
@@ -667,7 +701,7 @@ void perf_hpp__set_user_width(const char *width_list_str)
 	struct perf_hpp_fmt *fmt;
 	const char *ptr = width_list_str;
 
-	perf_hpp__for_each_format(fmt) {
+	perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
 		char *p;
 
 		int len = strtol(ptr, &p, 10);
@@ -679,3 +713,71 @@ void perf_hpp__set_user_width(const char *width_list_str)
 			break;
 	}
 }
+
+static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt)
+{
+	struct perf_hpp_list_node *node = NULL;
+	struct perf_hpp_fmt *fmt_copy;
+	bool found = false;
+	bool skip = perf_hpp__should_skip(fmt, hists);
+
+	list_for_each_entry(node, &hists->hpp_formats, list) {
+		if (node->level == fmt->level) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		node = malloc(sizeof(*node));
+		if (node == NULL)
+			return -1;
+
+		node->skip = skip;
+		node->level = fmt->level;
+		perf_hpp_list__init(&node->hpp);
+
+		hists->nr_hpp_node++;
+		list_add_tail(&node->list, &hists->hpp_formats);
+	}
+
+	fmt_copy = perf_hpp_fmt__dup(fmt);
+	if (fmt_copy == NULL)
+		return -1;
+
+	if (!skip)
+		node->skip = false;
+
+	list_add_tail(&fmt_copy->list, &node->hpp.fields);
+	list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts);
+
+	return 0;
+}
+
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+				  struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	struct perf_hpp_fmt *fmt;
+	struct hists *hists;
+	int ret;
+
+	if (!symbol_conf.report_hierarchy)
+		return 0;
+
+	evlist__for_each(evlist, evsel) {
+		hists = evsel__hists(evsel);
+
+		perf_hpp_list__for_each_sort_list(list, fmt) {
+			if (perf_hpp__is_dynamic_entry(fmt) &&
+			    !perf_hpp__defined_dynamic_entry(fmt, hists))
+				continue;
+
+			ret = add_hierarchy_fmt(hists, fmt);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 387110d50..7aff5acf3 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	return ret;
 }
 
+/*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ *
+ * However when percent-limit applied, it's possible that single callchain
+ * node have different (non-100% in fractal mode) percentage.
+ */
+static bool need_percent_display(struct rb_node *node, u64 parent_samples)
+{
+	struct callchain_node *cnode;
+
+	if (rb_next(node))
+		return true;
+
+	cnode = rb_entry(node, struct callchain_node, rb_node);
+	return callchain_cumul_hits(cnode) != parent_samples;
+}
+
 static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
-				       u64 total_samples, int left_margin)
+				       u64 total_samples, u64 parent_samples,
+				       int left_margin)
 {
 	struct callchain_node *cnode;
 	struct callchain_list *chain;
@@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	int ret = 0;
 	char bf[1024];
 
-	/*
-	 * If have one single callchain root, don't bother printing
-	 * its percentage (100 % in fractal mode and the same percentage
-	 * than the hist in graph mode). This also avoid one level of column.
-	 */
 	node = rb_first(root);
-	if (node && !rb_next(node)) {
+	if (node && !need_percent_display(node, parent_samples)) {
 		cnode = rb_entry(node, struct callchain_node, rb_node);
 		list_for_each_entry(chain, &cnode->val, list) {
 			/*
@@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		root = &cnode->rb_root;
 	}
 
+	if (callchain_param.mode == CHAIN_GRAPH_REL)
+		total_samples = parent_samples;
+
 	ret += __callchain__fprintf_graph(fp, root, total_samples,
 					  1, 1, left_margin);
-	ret += fprintf(fp, "\n");
+	if (ret) {
+		/* do not add a blank line if it printed nothing */
+		ret += fprintf(fp, "\n");
+	}
 
 	return ret;
 }
@@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 					    u64 total_samples, int left_margin,
 					    FILE *fp)
 {
+	u64 parent_samples = he->stat.period;
+
+	if (symbol_conf.cumulate_callchain)
+		parent_samples = he->stat_acc->period;
+
 	switch (callchain_param.mode) {
 	case CHAIN_GRAPH_REL:
-		return callchain__fprintf_graph(fp, &he->sorted_chain,
-						symbol_conf.cumulate_callchain ?
-						he->stat_acc->period : he->stat.period,
-						left_margin);
+		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+						parent_samples, left_margin);
 		break;
 	case CHAIN_GRAPH_ABS:
 		return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
-						left_margin);
+						parent_samples, left_margin);
 		break;
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
@@ -349,45 +373,66 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	return 0;
 }
 
-static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
-					    struct hists *hists,
-					    FILE *fp)
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 {
-	int left_margin = 0;
-	u64 total_period = hists->stats.total_period;
+	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
+	char *start = hpp->buf;
+	int ret;
+	bool first = true;
 
-	if (field_order == NULL && (sort_order == NULL ||
-				    !prefixcmp(sort_order, "comm"))) {
-		struct perf_hpp_fmt *fmt;
+	if (symbol_conf.exclude_other && !he->parent)
+		return 0;
 
-		perf_hpp__for_each_format(fmt) {
-			if (!perf_hpp__is_sort_entry(fmt))
-				continue;
+	hists__for_each_format(he->hists, fmt) {
+		if (perf_hpp__should_skip(fmt, he->hists))
+			continue;
 
-			/* must be 'comm' sort entry */
-			left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
-			left_margin -= thread__comm_len(he->thread);
-			break;
-		}
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
+		if (!sep || !first) {
+			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+			advance_hpp(hpp, ret);
+		} else
+			first = false;
+
+		if (perf_hpp__use_color() && fmt->color)
+			ret = fmt->color(fmt, hpp, he);
+		else
+			ret = fmt->entry(fmt, hpp, he);
+
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
+		advance_hpp(hpp, ret);
 	}
-	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+
+	return hpp->buf - start;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
+					 struct perf_hpp *hpp,
+					 struct hists *hists,
+					 FILE *fp)
 {
 	const char *sep = symbol_conf.field_sep;
 	struct perf_hpp_fmt *fmt;
-	char *start = hpp->buf;
-	int ret;
+	struct perf_hpp_list_node *fmt_node;
+	char *buf = hpp->buf;
+	size_t size = hpp->size;
+	int ret, printed = 0;
 	bool first = true;
 
 	if (symbol_conf.exclude_other && !he->parent)
 		return 0;
 
-	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt, he->hists))
-			continue;
+	ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
 
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
 		/*
 		 * If there's no field_sep, we still need
 		 * to display initial '  '.
@@ -403,10 +448,47 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 		else
 			ret = fmt->entry(fmt, hpp, he);
 
+		ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
 		advance_hpp(hpp, ret);
 	}
 
-	return hpp->buf - start;
+	if (!sep)
+		ret = scnprintf(hpp->buf, hpp->size, "%*s",
+				(hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
+	advance_hpp(hpp, ret);
+
+	printed += fprintf(fp, "%s", buf);
+
+	perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+		hpp->buf  = buf;
+		hpp->size = size;
+
+		/*
+		 * No need to call hist_entry__snprintf_alignment() since this
+		 * fmt is always the last column in the hierarchy mode.
+		 */
+		if (perf_hpp__use_color() && fmt->color)
+			fmt->color(fmt, hpp, he);
+		else
+			fmt->entry(fmt, hpp, he);
+
+		/*
+		 * dynamic entries are right-aligned but we want left-aligned
+		 * in the hierarchy mode
+		 */
+		printed += fprintf(fp, "%s%s", sep ?: "  ", ltrim(buf));
+	}
+	printed += putc('\n', fp);
+
+	if (symbol_conf.use_callchain && he->leaf) {
+		u64 total = hists__total_period(hists);
+
+		printed += hist_entry_callchain__fprintf(he, total, 0, fp);
+		goto out;
+	}
+
+out:
+	return printed;
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
@@ -418,24 +500,134 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 		.buf		= bf,
 		.size		= size,
 	};
+	u64 total_period = hists->stats.total_period;
 
 	if (size == 0 || size > bfsz)
 		size = hpp.size = bfsz;
 
+	if (symbol_conf.report_hierarchy)
+		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
+
 	hist_entry__snprintf(he, &hpp);
 
 	ret = fprintf(fp, "%s\n", bf);
 
 	if (symbol_conf.use_callchain)
-		ret += hist_entry__callchain_fprintf(he, hists, fp);
+		ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
 	return ret;
 }
 
+static int print_hierarchy_indent(const char *sep, int indent,
+				  const char *line, FILE *fp)
+{
+	if (sep != NULL || indent < 2)
+		return 0;
+
+	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)
+{
+	bool first_node, first_col;
+	int indent;
+	int depth;
+	unsigned width = 0;
+	unsigned header_width = 0;
+	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
+
+	indent = hists->nr_hpp_node;
+
+	/* preserve max indent depth for column headers */
+	print_hierarchy_indent(sep, indent, spaces, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		fmt->header(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
+	}
+
+	/* combine sort headers with ' / ' */
+	first_node = true;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		if (!first_node)
+			header_width += fprintf(fp, " / ");
+		first_node = false;
+
+		first_col = true;
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				header_width += fprintf(fp, "+");
+			first_col = false;
+
+			fmt->header(fmt, hpp, hists_to_evsel(hists));
+			rtrim(hpp->buf);
+
+			header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+		}
+	}
+
+	fprintf(fp, "\n# ");
+
+	/* preserve max indent depth for initial dots */
+	print_hierarchy_indent(sep, indent, dots, fp);
+
+	/* the first hpp_list_node is for overhead columns */
+	fmt_node = list_first_entry(&hists->hpp_formats,
+				    struct perf_hpp_list_node, list);
+
+	first_col = true;
+	perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+		if (!first_col)
+			fprintf(fp, "%s", sep ?: "..");
+		first_col = false;
+
+		width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+		fprintf(fp, "%.*s", width, dots);
+	}
+
+	depth = 0;
+	list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+		first_col = true;
+		width = depth * HIERARCHY_INDENT;
+
+		perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+			if (perf_hpp__should_skip(fmt, hists))
+				continue;
+
+			if (!first_col)
+				width++;  /* for '+' sign between column header */
+			first_col = false;
+
+			width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+		}
+
+		if (width > header_width)
+			header_width = width;
+
+		depth++;
+	}
+
+	fprintf(fp, "%s%-.*s", sep ?: "  ", header_width, dots);
+
+	fprintf(fp, "\n#\n");
+
+	return 2;
+}
+
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp)
 {
 	struct perf_hpp_fmt *fmt;
+	struct perf_hpp_list_node *fmt_node;
 	struct rb_node *nd;
 	size_t ret = 0;
 	unsigned int width;
@@ -449,10 +641,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	bool first = true;
 	size_t linesz;
 	char *line = NULL;
+	unsigned indent;
 
 	init_rem_hits();
 
-	perf_hpp__for_each_format(fmt)
+	hists__for_each_format(hists, fmt)
 		perf_hpp__reset_width(fmt, hists);
 
 	if (symbol_conf.col_width_list_str)
@@ -463,7 +656,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	if (symbol_conf.report_hierarchy) {
+		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);
+		}
+		nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
+		goto print_entries;
+	}
+
+	hists__for_each_format(hists, fmt) {
 		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
@@ -487,7 +689,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	fprintf(fp, "# ");
 
-	perf_hpp__for_each_format(fmt) {
+	hists__for_each_format(hists, fmt) {
 		unsigned int i;
 
 		if (perf_hpp__should_skip(fmt, hists))
@@ -520,7 +722,9 @@ print_entries:
 		goto out;
 	}
 
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+	indent = hists__overhead_width(hists) + 4;
+
+	for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 		float percent;
 
@@ -536,6 +740,20 @@ print_entries:
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
 
+		/*
+		 * If all children are filtered out or percent-limited,
+		 * display "no entry >= x.xx%" message.
+		 */
+		if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
+			int depth = hists->nr_hpp_node + h->depth + 1;
+
+			print_hierarchy_indent(sep, depth, spaces, fp);
+			fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
+
+			if (max_rows && ++nr_rows >= max_rows)
+				break;
+		}
+
 		if (h->ms.map == NULL && verbose > 1) {
 			__map_groups__fprintf_maps(h->thread->mg,
 						   MAP__FUNCTION, fp);