Linux-libre 4.5-gnu

6 files changed, 521 insertions, 80 deletions

diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index e9703c082..d37202121 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -528,7 +528,7 @@ static struct ui_browser_colorset {
 		.colorset = HE_COLORSET_SELECTED,
 		.name	  = "selected",
 		.fg	  = "black",
-		.bg	  = "lightgray",
+		.bg	  = "yellow",
 	},
 	{
 		.colorset = HE_COLORSET_CODE,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index d4d7cc272..718bd46d4 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -755,11 +755,11 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				nd = browser->curr_hot;
 			break;
 		case K_UNTAB:
-			if (nd != NULL)
+			if (nd != NULL) {
 				nd = rb_next(nd);
 				if (nd == NULL)
 					nd = rb_first(&browser->entries);
-			else
+			} else
 				nd = browser->curr_hot;
 			break;
 		case K_F1:
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 81def6c3f..08c09ad75 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -178,12 +178,51 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 	return n;
 }
 
+static int callchain_node__count_flat_rows(struct callchain_node *node)
+{
+	struct callchain_list *chain;
+	char folded_sign = 0;
+	int n = 0;
+
+	list_for_each_entry(chain, &node->parent_val, list) {
+		if (!folded_sign) {
+			/* only check first chain list entry */
+			folded_sign = callchain_list__folded(chain);
+			if (folded_sign == '+')
+				return 1;
+		}
+		n++;
+	}
+
+	list_for_each_entry(chain, &node->val, list) {
+		if (!folded_sign) {
+			/* node->parent_val list might be empty */
+			folded_sign = callchain_list__folded(chain);
+			if (folded_sign == '+')
+				return 1;
+		}
+		n++;
+	}
+
+	return n;
+}
+
+static int callchain_node__count_folded_rows(struct callchain_node *node __maybe_unused)
+{
+	return 1;
+}
+
 static int callchain_node__count_rows(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 	bool unfolded = false;
 	int n = 0;
 
+	if (callchain_param.mode == CHAIN_FLAT)
+		return callchain_node__count_flat_rows(node);
+	else if (callchain_param.mode == CHAIN_FOLDED)
+		return callchain_node__count_folded_rows(node);
+
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
 		unfolded = chain->unfolded;
@@ -263,7 +302,7 @@ static void callchain_node__init_have_children(struct callchain_node *node,
 	chain = list_entry(node->val.next, struct callchain_list, list);
 	chain->has_children = has_sibling;
 
-	if (!list_empty(&node->val)) {
+	if (node->val.next != node->val.prev) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
 	}
@@ -279,6 +318,9 @@ static void callchain__init_have_children(struct rb_root *root)
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
 		callchain_node__init_have_children(node, has_sibling);
+		if (callchain_param.mode == CHAIN_FLAT ||
+		    callchain_param.mode == CHAIN_FOLDED)
+			callchain_node__make_parent_list(node);
 	}
 }
 
@@ -438,7 +480,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *help)
 
 	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
-	if (ui_browser__show(&browser->b, title, help) < 0)
+	if (ui_browser__show(&browser->b, title, "%s", help) < 0)
 		return -1;
 
 	while (1) {
@@ -577,6 +619,231 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_callchain_list(struct hist_browser *browser,
+					     struct callchain_node *node,
+					     struct callchain_list *chain,
+					     unsigned short row, u64 total,
+					     bool need_percent, int offset,
+					     print_callchain_entry_fn print,
+					     struct callchain_print_arg *arg)
+{
+	char bf[1024], *alloc_str;
+	const char *str;
+
+	if (arg->row_offset != 0) {
+		arg->row_offset--;
+		return 0;
+	}
+
+	alloc_str = NULL;
+	str = callchain_list__sym_name(chain, bf, sizeof(bf),
+				       browser->show_dso);
+
+	if (need_percent) {
+		char buf[64];
+
+		callchain_node__scnprintf_value(node, buf, sizeof(buf),
+						total);
+
+		if (asprintf(&alloc_str, "%s %s", buf, str) < 0)
+			str = "Not enough memory!";
+		else
+			str = alloc_str;
+	}
+
+	print(browser, chain, str, offset, row, arg);
+
+	free(alloc_str);
+	return 1;
+}
+
+static int hist_browser__show_callchain_flat(struct hist_browser *browser,
+					     struct rb_root *root,
+					     unsigned short row, u64 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_OFFSET_STEP;
+	bool need_percent;
+
+	node = rb_first(root);
+	need_percent = node && rb_next(node);
+
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		struct callchain_list *chain;
+		char folded_sign = ' ';
+		int first = true;
+		int extra_offset = 0;
+
+		list_for_each_entry(chain, &child->parent_val, list) {
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else if (need_percent)
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
+
+			if (is_output_full(browser, row))
+				goto out;
+
+			if (folded_sign == '+')
+				goto next;
+		}
+
+		list_for_each_entry(chain, &child->val, list) {
+			bool was_first = first;
+
+			if (first)
+				first = false;
+			else if (need_percent)
+				extra_offset = LEVEL_OFFSET_STEP;
+
+			folded_sign = callchain_list__folded(chain);
+
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
+
+			if (is_output_full(browser, row))
+				goto out;
+
+			if (folded_sign == '+')
+				break;
+		}
+
+next:
+		if (is_output_full(browser, row))
+			break;
+		node = next;
+	}
+out:
+	return row - first_row;
+}
+
+static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
+						struct callchain_list *chain,
+						char *value_str, char *old_str)
+{
+	char bf[1024];
+	const char *str;
+	char *new;
+
+	str = callchain_list__sym_name(chain, bf, sizeof(bf),
+				       browser->show_dso);
+	if (old_str) {
+		if (asprintf(&new, "%s%s%s", old_str,
+			     symbol_conf.field_sep ?: ";", str) < 0)
+			new = NULL;
+	} else {
+		if (value_str) {
+			if (asprintf(&new, "%s %s", value_str, str) < 0)
+				new = NULL;
+		} else {
+			if (asprintf(&new, "%s", str) < 0)
+				new = NULL;
+		}
+	}
+	return new;
+}
+
+static int hist_browser__show_callchain_folded(struct hist_browser *browser,
+					       struct rb_root *root,
+					       unsigned short row, u64 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_OFFSET_STEP;
+	bool need_percent;
+
+	node = rb_first(root);
+	need_percent = node && rb_next(node);
+
+	while (node) {
+		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
+		struct rb_node *next = rb_next(node);
+		struct callchain_list *chain, *first_chain = NULL;
+		int first = true;
+		char *value_str = NULL, *value_str_alloc = NULL;
+		char *chain_str = NULL, *chain_str_alloc = NULL;
+
+		if (arg->row_offset != 0) {
+			arg->row_offset--;
+			goto next;
+		}
+
+		if (need_percent) {
+			char buf[64];
+
+			callchain_node__scnprintf_value(child, buf, sizeof(buf), total);
+			if (asprintf(&value_str, "%s", buf) < 0) {
+				value_str = (char *)"<...>";
+				goto do_print;
+			}
+			value_str_alloc = value_str;
+		}
+
+		list_for_each_entry(chain, &child->parent_val, list) {
+			chain_str = hist_browser__folded_callchain_str(browser,
+						chain, value_str, chain_str);
+			if (first) {
+				first = false;
+				first_chain = chain;
+			}
+
+			if (chain_str == NULL) {
+				chain_str = (char *)"Not enough memory!";
+				goto do_print;
+			}
+
+			chain_str_alloc = chain_str;
+		}
+
+		list_for_each_entry(chain, &child->val, list) {
+			chain_str = hist_browser__folded_callchain_str(browser,
+						chain, value_str, chain_str);
+			if (first) {
+				first = false;
+				first_chain = chain;
+			}
+
+			if (chain_str == NULL) {
+				chain_str = (char *)"Not enough memory!";
+				goto do_print;
+			}
+
+			chain_str_alloc = chain_str;
+		}
+
+do_print:
+		print(browser, first_chain, chain_str, offset, row++, arg);
+		free(value_str_alloc);
+		free(chain_str_alloc);
+
+next:
+		if (is_output_full(browser, row))
+			break;
+		node = next;
+	}
+
+	return row - first_row;
+}
+
 static int hist_browser__show_callchain(struct hist_browser *browser,
 					struct rb_root *root, int level,
 					unsigned short row, u64 total,
@@ -595,15 +862,12 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
-		u64 cumul = callchain_cumul_hits(child);
 		struct callchain_list *chain;
 		char folded_sign = ' ';
 		int first = true;
 		int extra_offset = 0;
 
 		list_for_each_entry(chain, &child->val, list) {
-			char bf[1024], *alloc_str;
-			const char *str;
 			bool was_first = first;
 
 			if (first)
@@ -612,31 +876,16 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
-			if (arg->row_offset != 0) {
-				arg->row_offset--;
-				goto do_next;
-			}
-
-			alloc_str = NULL;
-			str = callchain_list__sym_name(chain, bf, sizeof(bf),
-						       browser->show_dso);
-
-			if (was_first && need_percent) {
-				double percent = cumul * 100.0 / total;
-
-				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-					str = "Not enough memory!";
-				else
-					str = alloc_str;
-			}
 
-			print(browser, chain, str, offset + extra_offset, row, arg);
+			row += hist_browser__show_callchain_list(browser, child,
+							chain, row, total,
+							was_first && need_percent,
+							offset + extra_offset,
+							print, arg);
 
-			free(alloc_str);
-
-			if (is_output_full(browser, ++row))
+			if (is_output_full(browser, row))
 				goto out;
-do_next:
+
 			if (folded_sign == '+')
 				break;
 		}
@@ -792,7 +1041,8 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		hist_browser__gotorc(browser, row, 0);
 
 		perf_hpp__for_each_format(fmt) {
-			if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll)
+			if (perf_hpp__should_skip(fmt, entry->hists) ||
+			    column++ < browser->b.horiz_scroll)
 				continue;
 
 			if (current_entry && browser->b.navkeypressed) {
@@ -847,10 +1097,22 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 				total = entry->stat.period;
 		}
 
-		printed += hist_browser__show_callchain(browser,
+		if (callchain_param.mode == CHAIN_FLAT) {
+			printed += hist_browser__show_callchain_flat(browser,
+					&entry->sorted_chain, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+		} else if (callchain_param.mode == CHAIN_FOLDED) {
+			printed += hist_browser__show_callchain_folded(browser,
+					&entry->sorted_chain, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+		} else {
+			printed += hist_browser__show_callchain(browser,
 					&entry->sorted_chain, 1, row, total,
 					hist_browser__show_callchain_entry, &arg,
 					hist_browser__check_output_full);
+		}
 
 		if (arg.is_current_entry)
 			browser->he_selection = entry;
@@ -883,7 +1145,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
 	}
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt)  || column++ < browser->b.horiz_scroll)
+		if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
 			continue;
 
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
@@ -1153,7 +1415,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 		printed += fprintf(fp, "%c ", folded_sign);
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
 		if (!first) {
@@ -1802,10 +2064,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	SLang_reset_tty();
 	SLang_init_tty(0, 0, 0);
 
-	if (min_pcnt) {
+	if (min_pcnt)
 		browser->min_pcnt = min_pcnt;
-		hist_browser__update_nr_entries(browser);
-	}
+	hist_browser__update_nr_entries(browser);
 
 	browser->pstack = pstack__new(3);
 	if (browser->pstack == NULL)
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 4b3585eed..0f8dcfdfb 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,8 +89,8 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_acc;
 }
 
-static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
-				    GtkTreeIter *parent, int col, u64 total)
+static void perf_gtk__add_callchain_flat(struct rb_root *root, GtkTreeStore *store,
+					 GtkTreeIter *parent, int col, u64 total)
 {
 	struct rb_node *nd;
 	bool has_single_node = (rb_first(root) == rb_last(root));
@@ -100,13 +100,132 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 		struct callchain_list *chain;
 		GtkTreeIter iter, new_parent;
 		bool need_new_parent;
-		double percent;
-		u64 hits, child_total;
 
 		node = rb_entry(nd, struct callchain_node, rb_node);
 
-		hits = callchain_cumul_hits(node);
-		percent = 100.0 * hits / total;
+		new_parent = *parent;
+		need_new_parent = !has_single_node;
+
+		callchain_node__make_parent_list(node);
+
+		list_for_each_entry(chain, &node->parent_val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf), false);
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+
+		list_for_each_entry(chain, &node->val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf), false);
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+	}
+}
+
+static void perf_gtk__add_callchain_folded(struct rb_root *root, GtkTreeStore *store,
+					   GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter;
+		char buf[64];
+		char *str, *str_alloc = NULL;
+		bool first = true;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
+
+		callchain_node__make_parent_list(node);
+
+		list_for_each_entry(chain, &node->parent_val, list) {
+			char name[1024];
+
+			callchain_list__sym_name(chain, name, sizeof(name), false);
+
+			if (asprintf(&str, "%s%s%s",
+				     first ? "" : str_alloc,
+				     first ? "" : symbol_conf.field_sep ?: "; ",
+				     name) < 0)
+				return;
+
+			first = false;
+			free(str_alloc);
+			str_alloc = str;
+		}
+
+		list_for_each_entry(chain, &node->val, list) {
+			char name[1024];
+
+			callchain_list__sym_name(chain, name, sizeof(name), false);
+
+			if (asprintf(&str, "%s%s%s",
+				     first ? "" : str_alloc,
+				     first ? "" : symbol_conf.field_sep ?: "; ",
+				     name) < 0)
+				return;
+
+			first = false;
+			free(str_alloc);
+			str_alloc = str;
+		}
+
+		gtk_tree_store_append(store, &iter, parent);
+
+		callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
+		gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+		gtk_tree_store_set(store, &iter, col, str, -1);
+
+		free(str_alloc);
+	}
+}
+
+static void perf_gtk__add_callchain_graph(struct rb_root *root, GtkTreeStore *store,
+					  GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+	bool has_single_node = (rb_first(root) == rb_last(root));
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter, new_parent;
+		bool need_new_parent;
+		u64 child_total;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
 
 		new_parent = *parent;
 		need_new_parent = !has_single_node && (node->val_nr > 1);
@@ -116,7 +235,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 
 			gtk_tree_store_append(store, &iter, &new_parent);
 
-			scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+			callchain_node__scnprintf_value(node, buf, sizeof(buf), total);
 			gtk_tree_store_set(store, &iter, 0, buf, -1);
 
 			callchain_list__sym_name(chain, buf, sizeof(buf), false);
@@ -138,11 +257,22 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 			child_total = total;
 
 		/* Now 'iter' contains info of the last callchain_list */
-		perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
-					child_total);
+		perf_gtk__add_callchain_graph(&node->rb_root, store, &iter, col,
+					      child_total);
 	}
 }
 
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+				    GtkTreeIter *parent, int col, u64 total)
+{
+	if (callchain_param.mode == CHAIN_FLAT)
+		perf_gtk__add_callchain_flat(root, store, parent, col, total);
+	else if (callchain_param.mode == CHAIN_FOLDED)
+		perf_gtk__add_callchain_folded(root, store, parent, col, total);
+	else
+		perf_gtk__add_callchain_graph(root, store, parent, col, total);
+}
+
 static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
 			     GtkTreeViewColumn *col __maybe_unused,
 			     gpointer user_data __maybe_unused)
@@ -188,7 +318,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	col_idx = 0;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		/*
@@ -238,7 +368,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		col_idx = 0;
 
 		perf_hpp__for_each_format(fmt) {
-			if (perf_hpp__should_skip(fmt))
+			if (perf_hpp__should_skip(fmt, h->hists))
 				continue;
 
 			if (fmt->color)
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 5029ba2b5..bf2a66e25 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -443,7 +443,6 @@ LIST_HEAD(perf_hpp__sort_list);
 
 void perf_hpp__init(void)
 {
-	struct list_head *list;
 	int i;
 
 	for (i = 0; i < PERF_HPP__MAX_INDEX; i++) {
@@ -484,17 +483,6 @@ void perf_hpp__init(void)
 
 	if (symbol_conf.show_total_period)
 		hpp_dimension__add_output(PERF_HPP__PERIOD);
-
-	/* prepend overhead field for backward compatiblity.  */
-	list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list;
-	if (list_empty(list))
-		list_add(list, &perf_hpp__sort_list);
-
-	if (symbol_conf.cumulate_callchain) {
-		list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list;
-		if (list_empty(list))
-			list_add(list, &perf_hpp__sort_list);
-	}
 }
 
 void perf_hpp__column_register(struct perf_hpp_fmt *format)
@@ -619,7 +607,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 	struct perf_hpp dummy_hpp;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (first)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index dfcbc9014..387110d50 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -34,10 +34,10 @@ static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
 	return ret;
 }
 
-static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
+static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
+				     struct callchain_list *chain,
 				     int depth, int depth_mask, int period,
-				     u64 total_samples, u64 hits,
-				     int left_margin)
+				     u64 total_samples, int left_margin)
 {
 	int i;
 	size_t ret = 0;
@@ -50,10 +50,9 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 		else
 			ret += fprintf(fp, " ");
 		if (!period && i == depth - 1) {
-			double percent;
-
-			percent = hits * 100.0 / total_samples;
-			ret += percent_color_fprintf(fp, "--%2.2f%%-- ", percent);
+			ret += fprintf(fp, "--");
+			ret += callchain_node__fprintf_value(node, fp, total_samples);
+			ret += fprintf(fp, "--");
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
@@ -82,13 +81,14 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 					 int depth_mask, int left_margin)
 {
 	struct rb_node *node, *next;
-	struct callchain_node *child;
+	struct callchain_node *child = NULL;
 	struct callchain_list *chain;
 	int new_depth_mask = depth_mask;
 	u64 remaining;
 	size_t ret = 0;
 	int i;
 	uint entries_printed = 0;
+	int cumul_count = 0;
 
 	remaining = total_samples;
 
@@ -100,6 +100,7 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 		child = rb_entry(node, struct callchain_node, rb_node);
 		cumul = callchain_cumul_hits(child);
 		remaining -= cumul;
+		cumul_count += callchain_cumul_counts(child);
 
 		/*
 		 * The depth mask manages the output of pipes that show
@@ -120,10 +121,9 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 						   left_margin);
 		i = 0;
 		list_for_each_entry(chain, &child->val, list) {
-			ret += ipchain__fprintf_graph(fp, chain, depth,
+			ret += ipchain__fprintf_graph(fp, child, chain, depth,
 						      new_depth_mask, i++,
 						      total_samples,
-						      cumul,
 						      left_margin);
 		}
 
@@ -143,14 +143,23 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
 	if (callchain_param.mode == CHAIN_GRAPH_REL &&
 		remaining && remaining != total_samples) {
+		struct callchain_node rem_node = {
+			.hit = remaining,
+		};
 
 		if (!rem_sq_bracket)
 			return ret;
 
+		if (callchain_param.value == CCVAL_COUNT && child && child->parent) {
+			rem_node.count = child->parent->children_count - cumul_count;
+			if (rem_node.count <= 0)
+				return ret;
+		}
+
 		new_depth_mask &= ~(1 << (depth - 1));
-		ret += ipchain__fprintf_graph(fp, &rem_hits, depth,
+		ret += ipchain__fprintf_graph(fp, &rem_node, &rem_hits, depth,
 					      new_depth_mask, 0, total_samples,
-					      remaining, left_margin);
+					      left_margin);
 	}
 
 	return ret;
@@ -243,12 +252,11 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
 	struct rb_node *rb_node = rb_first(tree);
 
 	while (rb_node) {
-		double percent;
-
 		chain = rb_entry(rb_node, struct callchain_node, rb_node);
-		percent = chain->hit * 100.0 / total_samples;
 
-		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
+		ret += fprintf(fp, "           ");
+		ret += callchain_node__fprintf_value(chain, fp, total_samples);
+		ret += fprintf(fp, "\n");
 		ret += __callchain__fprintf_flat(fp, chain, total_samples);
 		ret += fprintf(fp, "\n");
 		if (++entries_printed == callchain_param.print_limit)
@@ -260,6 +268,57 @@ static size_t callchain__fprintf_flat(FILE *fp, struct rb_root *tree,
 	return ret;
 }
 
+static size_t __callchain__fprintf_folded(FILE *fp, struct callchain_node *node)
+{
+	const char *sep = symbol_conf.field_sep ?: ";";
+	struct callchain_list *chain;
+	size_t ret = 0;
+	char bf[1024];
+	bool first;
+
+	if (!node)
+		return 0;
+
+	ret += __callchain__fprintf_folded(fp, node->parent);
+
+	first = (ret == 0);
+	list_for_each_entry(chain, &node->val, list) {
+		if (chain->ip >= PERF_CONTEXT_MAX)
+			continue;
+		ret += fprintf(fp, "%s%s", first ? "" : sep,
+			       callchain_list__sym_name(chain,
+						bf, sizeof(bf), false));
+		first = false;
+	}
+
+	return ret;
+}
+
+static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
+					u64 total_samples)
+{
+	size_t ret = 0;
+	u32 entries_printed = 0;
+	struct callchain_node *chain;
+	struct rb_node *rb_node = rb_first(tree);
+
+	while (rb_node) {
+
+		chain = rb_entry(rb_node, struct callchain_node, rb_node);
+
+		ret += callchain_node__fprintf_value(chain, fp, total_samples);
+		ret += fprintf(fp, " ");
+		ret += __callchain__fprintf_folded(fp, chain);
+		ret += fprintf(fp, "\n");
+		if (++entries_printed == callchain_param.print_limit)
+			break;
+
+		rb_node = rb_next(rb_node);
+	}
+
+	return ret;
+}
+
 static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 					    u64 total_samples, int left_margin,
 					    FILE *fp)
@@ -278,6 +337,9 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
 	case CHAIN_FLAT:
 		return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
 		break;
+	case CHAIN_FOLDED:
+		return callchain__fprintf_folded(fp, &he->sorted_chain, total_samples);
+		break;
 	case CHAIN_NONE:
 		break;
 	default:
@@ -323,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 		return 0;
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, he->hists))
 			continue;
 
 		/*
@@ -402,7 +464,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	fprintf(fp, "# ");
 
 	perf_hpp__for_each_format(fmt) {
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (!first)
@@ -428,7 +490,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 	perf_hpp__for_each_format(fmt) {
 		unsigned int i;
 
-		if (perf_hpp__should_skip(fmt))
+		if (perf_hpp__should_skip(fmt, hists))
 			continue;
 
 		if (!first)