11 files changed, 969 insertions, 184 deletions

diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index aada3ac5e891..d4a5a21c2a7e 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -32,8 +32,17 @@ unsigned char sane_ctype[256] = {
 
 const char *graph_line =
 	"_____________________________________________________________________"
+	"_____________________________________________________________________"
 	"_____________________________________________________________________";
 const char *graph_dotted_line =
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------"
 	"---------------------------------------------------------------------";
+const char *spaces =
+	"                                                                     "
+	"                                                                     "
+	"                                                                     ";
+const char *dots =
+	"....................................................................."
+	"....................................................................."
+	".....................................................................";
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index ff7e86ad1b06..8c4212abd19b 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -106,40 +106,61 @@ int dump_printf(const char *fmt, ...)
 	return ret;
 }
 
+static void trace_event_printer(enum binary_printer_ops op,
+				unsigned int val, void *extra)
+{
+	const char *color = PERF_COLOR_BLUE;
+	union perf_event *event = (union perf_event *)extra;
+	unsigned char ch = (unsigned char)val;
+
+	switch (op) {
+	case BINARY_PRINT_DATA_BEGIN:
+		printf(".");
+		color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+				event->header.size);
+		break;
+	case BINARY_PRINT_LINE_BEGIN:
+		printf(".");
+		break;
+	case BINARY_PRINT_ADDR:
+		color_fprintf(stdout, color, "  %04x: ", val);
+		break;
+	case BINARY_PRINT_NUM_DATA:
+		color_fprintf(stdout, color, " %02x", val);
+		break;
+	case BINARY_PRINT_NUM_PAD:
+		color_fprintf(stdout, color, "   ");
+		break;
+	case BINARY_PRINT_SEP:
+		color_fprintf(stdout, color, "  ");
+		break;
+	case BINARY_PRINT_CHAR_DATA:
+		color_fprintf(stdout, color, "%c",
+			      isprint(ch) ? ch : '.');
+		break;
+	case BINARY_PRINT_CHAR_PAD:
+		color_fprintf(stdout, color, " ");
+		break;
+	case BINARY_PRINT_LINE_END:
+		color_fprintf(stdout, color, "\n");
+		break;
+	case BINARY_PRINT_DATA_END:
+		printf("\n");
+		break;
+	default:
+		break;
+	}
+}
+
 void trace_event(union perf_event *event)
 {
 	unsigned char *raw_event = (void *)event;
-	const char *color = PERF_COLOR_BLUE;
-	int i, j;
 
 	if (!dump_trace)
 		return;
 
-	printf(".");
-	color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-		      event->header.size);
-
-	for (i = 0; i < event->header.size; i++) {
-		if ((i & 15) == 0) {
-			printf(".");
-			color_fprintf(stdout, color, "  %04x: ", i);
-		}
-
-		color_fprintf(stdout, color, " %02x", raw_event[i]);
-
-		if (((i & 15) == 15) || i == event->header.size-1) {
-			color_fprintf(stdout, color, "  ");
-			for (j = 0; j < 15-(i & 15); j++)
-				color_fprintf(stdout, color, "   ");
-			for (j = i & ~15; j <= i; j++) {
-				color_fprintf(stdout, color, "%c",
-					      isprint(raw_event[j]) ?
-					      raw_event[j] : '.');
-			}
-			color_fprintf(stdout, color, "\n");
-		}
-	}
-	printf(".\n");
+	print_binary(raw_event, event->header.size, 16,
+		     trace_event_printer, event);
 }
 
 static struct debug_variable {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 017eb5c42c37..1c530428e087 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -248,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat)
 	/* XXX need decay for weight too? */
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
+
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
 	u64 prev_period = he->stat.period;
@@ -263,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
 	diff = prev_period - he->stat.period;
 
-	hists->stats.total_period -= diff;
-	if (!he->filtered)
-		hists->stats.total_non_filtered_period -= diff;
+	if (!he->depth) {
+		hists->stats.total_period -= diff;
+		if (!he->filtered)
+			hists->stats.total_non_filtered_period -= diff;
+	}
+
+	if (!he->leaf) {
+		struct hist_entry *child;
+		struct rb_node *node = rb_first(&he->hroot_out);
+		while (node) {
+			child = rb_entry(node, struct hist_entry, rb_node);
+			node = rb_next(node);
+
+			if (hists__decay_entry(hists, child))
+				hists__delete_entry(hists, child);
+		}
+	}
 
 	return he->stat.period == 0;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-	rb_erase(&he->rb_node, &hists->entries);
+	struct rb_root *root_in;
+	struct rb_root *root_out;
 
-	if (sort__need_collapse)
-		rb_erase(&he->rb_node_in, &hists->entries_collapsed);
-	else
-		rb_erase(&he->rb_node_in, hists->entries_in);
+	if (he->parent_he) {
+		root_in  = &he->parent_he->hroot_in;
+		root_out = &he->parent_he->hroot_out;
+	} else {
+		if (sort__need_collapse)
+			root_in = &hists->entries_collapsed;
+		else
+			root_in = hists->entries_in;
+		root_out = &hists->entries;
+	}
+
+	rb_erase(&he->rb_node_in, root_in);
+	rb_erase(&he->rb_node, root_out);
 
 	--hists->nr_entries;
 	if (!he->filtered)
@@ -396,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 		}
 		INIT_LIST_HEAD(&he->pairs.node);
 		thread__get(he->thread);
+
+		if (!symbol_conf.report_hierarchy)
+			he->leaf = true;
 	}
 
 	return he;
@@ -1049,6 +1078,114 @@ int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
  * collapse the histogram
  */
 
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+
+static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
+						 struct rb_root *root,
+						 struct hist_entry *he,
+						 struct perf_hpp_fmt *fmt)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter, *new;
+	int64_t cmp;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node_in);
+
+		cmp = fmt->collapse(fmt, iter, he);
+		if (!cmp) {
+			he_stat__add_stat(&iter->stat, &he->stat);
+			return iter;
+		}
+
+		if (cmp < 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	new = hist_entry__new(he, true);
+	if (new == NULL)
+		return NULL;
+
+	hists__apply_filters(hists, new);
+	hists->nr_entries++;
+
+	/* save related format for output */
+	new->fmt = fmt;
+
+	/* some fields are now passed to 'new' */
+	if (perf_hpp__is_trace_entry(fmt))
+		he->trace_output = NULL;
+	else
+		new->trace_output = NULL;
+
+	if (perf_hpp__is_srcline_entry(fmt))
+		he->srcline = NULL;
+	else
+		new->srcline = NULL;
+
+	if (perf_hpp__is_srcfile_entry(fmt))
+		he->srcfile = NULL;
+	else
+		new->srcfile = NULL;
+
+	rb_link_node(&new->rb_node_in, parent, p);
+	rb_insert_color(&new->rb_node_in, root);
+	return new;
+}
+
+static int hists__hierarchy_insert_entry(struct hists *hists,
+					 struct rb_root *root,
+					 struct hist_entry *he)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hist_entry *new_he = NULL;
+	struct hist_entry *parent = NULL;
+	int depth = 0;
+	int ret = 0;
+
+	hists__for_each_sort_list(hists, fmt) {
+		if (!perf_hpp__is_sort_entry(fmt) &&
+		    !perf_hpp__is_dynamic_entry(fmt))
+			continue;
+		if (perf_hpp__should_skip(fmt, hists))
+			continue;
+
+		/* insert copy of 'he' for each fmt into the hierarchy */
+		new_he = hierarchy_insert_entry(hists, root, he, fmt);
+		if (new_he == NULL) {
+			ret = -1;
+			break;
+		}
+
+		root = &new_he->hroot_in;
+		new_he->parent_he = parent;
+		new_he->depth = depth++;
+		parent = new_he;
+	}
+
+	if (new_he) {
+		new_he->leaf = true;
+
+		if (symbol_conf.use_callchain) {
+			callchain_cursor_reset(&callchain_cursor);
+			if (callchain_merge(&callchain_cursor,
+					    new_he->callchain,
+					    he->callchain) < 0)
+				ret = -1;
+		}
+	}
+
+	/* 'he' is no longer used */
+	hist_entry__delete(he);
+
+	/* return 0 (or -1) since it already applied filters */
+	return ret;
+}
+
 int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
 				 struct hist_entry *he)
 {
@@ -1057,6 +1194,9 @@ int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
 	struct hist_entry *iter;
 	int64_t cmp;
 
+	if (symbol_conf.report_hierarchy)
+		return hists__hierarchy_insert_entry(hists, root, he);
+
 	while (*p != NULL) {
 		parent = *p;
 		iter = rb_entry(parent, struct hist_entry, rb_node_in);
@@ -1204,6 +1344,86 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
 	hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_insert_output_entry(struct rb_root *root,
+					  struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &parent->rb_left;
+		else
+			p = &parent->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+}
+
+static void hists__hierarchy_output_resort(struct hists *hists,
+					   struct ui_progress *prog,
+					   struct rb_root *root_in,
+					   struct rb_root *root_out,
+					   u64 min_callchain_hits,
+					   bool use_callchain)
+{
+	struct rb_node *node;
+	struct hist_entry *he;
+
+	*root_out = RB_ROOT;
+	node = rb_first(root_in);
+
+	while (node) {
+		he = rb_entry(node, struct hist_entry, rb_node_in);
+		node = rb_next(node);
+
+		hierarchy_insert_output_entry(root_out, he);
+
+		if (prog)
+			ui_progress__update(prog, 1);
+
+		if (!he->leaf) {
+			hists__hierarchy_output_resort(hists, prog,
+						       &he->hroot_in,
+						       &he->hroot_out,
+						       min_callchain_hits,
+						       use_callchain);
+			hists->nr_entries++;
+			if (!he->filtered) {
+				hists->nr_non_filtered_entries++;
+				hists__calc_col_len(hists, he);
+			}
+
+			continue;
+		}
+
+		/* only update stat for leaf entries to avoid duplication */
+		hists__inc_stats(hists, he);
+		if (!he->filtered)
+			hists__calc_col_len(hists, he);
+
+		if (!use_callchain)
+			continue;
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			u64 total = he->stat.period;
+
+			if (symbol_conf.cumulate_callchain)
+				total = he->stat_acc->period;
+
+			min_callchain_hits = total * (callchain_param.min_percent / 100);
+		}
+
+		callchain_param.sort(&he->sorted_chain, he->callchain,
+				     min_callchain_hits, &callchain_param);
+	}
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
 					 struct hist_entry *he,
 					 u64 min_callchain_hits,
@@ -1255,6 +1475,17 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 
 	min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
 
+	hists__reset_stats(hists);
+	hists__reset_col_len(hists);
+
+	if (symbol_conf.report_hierarchy) {
+		return hists__hierarchy_output_resort(hists, prog,
+						      &hists->entries_collapsed,
+						      &hists->entries,
+						      min_callchain_hits,
+						      use_callchain);
+	}
+
 	if (sort__need_collapse)
 		root = &hists->entries_collapsed;
 	else
@@ -1263,9 +1494,6 @@ static void output_resort(struct hists *hists, struct ui_progress *prog,
 	next = rb_first(root);
 	hists->entries = RB_ROOT;
 
-	hists__reset_stats(hists);
-	hists__reset_col_len(hists);
-
 	while (next) {
 		n = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&n->rb_node_in);
@@ -1298,10 +1526,87 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 	output_resort(hists, prog, symbol_conf.use_callchain);
 }
 
+static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
+{
+	if (he->leaf || hmd == HMD_FORCE_SIBLING)
+		return false;
+
+	if (he->unfolded || hmd == HMD_FORCE_CHILD)
+		return true;
+
+	return false;
+}
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	while (can_goto_child(he, HMD_NORMAL)) {
+		node = rb_last(&he->hroot_out);
+		he = rb_entry(node, struct hist_entry, rb_node);
+	}
+	return node;
+}
+
+struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	if (can_goto_child(he, hmd))
+		node = rb_first(&he->hroot_out);
+	else
+		node = rb_next(node);
+
+	while (node == NULL) {
+		he = he->parent_he;
+		if (he == NULL)
+			break;
+
+		node = rb_next(&he->rb_node);
+	}
+	return node;
+}
+
+struct rb_node *rb_hierarchy_prev(struct rb_node *node)
+{
+	struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+	node = rb_prev(node);
+	if (node)
+		return rb_hierarchy_last(node);
+
+	he = he->parent_he;
+	if (he == NULL)
+		return NULL;
+
+	return &he->rb_node;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
 				       enum hist_filter filter)
 {
 	h->filtered &= ~(1 << filter);
+
+	if (symbol_conf.report_hierarchy) {
+		struct hist_entry *parent = h->parent_he;
+
+		while (parent) {
+			he_stat__add_stat(&parent->stat, &h->stat);
+
+			parent->filtered &= ~(1 << filter);
+
+			if (parent->filtered)
+				goto next;
+
+			/* force fold unfiltered entry for simplicity */
+			parent->unfolded = false;
+			parent->row_offset = 0;
+			parent->nr_rows = 0;
+next:
+			parent = parent->parent_he;
+		}
+	}
+
 	if (h->filtered)
 		return;
 
@@ -1387,28 +1692,146 @@ static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t fil
 	}
 }
 
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct hist_entry *iter;
+	struct rb_root new_root = RB_ROOT;
+	struct rb_node *nd;
+
+	while (*p != NULL) {
+		parent = *p;
+		iter = rb_entry(parent, struct hist_entry, rb_node);
+
+		if (hist_entry__sort(he, iter) > 0)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&he->rb_node, parent, p);
+	rb_insert_color(&he->rb_node, root);
+
+	if (he->leaf || he->filtered)
+		return;
+
+	nd = rb_first(&he->hroot_out);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &he->hroot_out);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	he->hroot_out = new_root;
+}
+
+static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
+{
+	struct rb_node *nd;
+	struct rb_root new_root = RB_ROOT;
+
+	hists->stats.nr_non_filtered_samples = 0;
+
+	hists__reset_filter_stats(hists);
+	hists__reset_col_len(hists);
+
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+		int ret;
+
+		ret = hist_entry__filter(h, type, arg);
+
+		/*
+		 * case 1. non-matching type
+		 * zero out the period, set filter marker and move to child
+		 */
+		if (ret < 0) {
+			memset(&h->stat, 0, sizeof(h->stat));
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD);
+		}
+		/*
+		 * case 2. matched type (filter out)
+		 * set filter marker and move to next
+		 */
+		else if (ret == 1) {
+			h->filtered |= (1 << type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+		/*
+		 * case 3. ok (not filtered)
+		 * add period to hists and parents, erase the filter marker
+		 * and move to next sibling
+		 */
+		else {
+			hists__remove_entry_filter(hists, h, type);
+
+			nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+		}
+	}
+
+	/*
+	 * resort output after applying a new filter since filter in a lower
+	 * hierarchy can change periods in a upper hierarchy.
+	 */
+	nd = rb_first(&hists->entries);
+	while (nd) {
+		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+		nd = rb_next(nd);
+		rb_erase(&h->rb_node, &hists->entries);
+
+		resort_filtered_entry(&new_root, h);
+	}
+
+	hists->entries = new_root;
+}
+
 void hists__filter_by_thread(struct hists *hists)
 {
-	hists__filter_by_type(hists, HIST_FILTER__THREAD,
-			      hists__filter_entry_by_thread);
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__THREAD,
+					hists->thread_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__THREAD,
+				      hists__filter_entry_by_thread);
 }
 
 void hists__filter_by_dso(struct hists *hists)
 {
-	hists__filter_by_type(hists, HIST_FILTER__DSO,
-			      hists__filter_entry_by_dso);
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__DSO,
+					hists->dso_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__DSO,
+				      hists__filter_entry_by_dso);
 }
 
 void hists__filter_by_symbol(struct hists *hists)
 {
-	hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
-			      hists__filter_entry_by_symbol);
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL,
+					hists->symbol_filter_str);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+				      hists__filter_entry_by_symbol);
 }
 
 void hists__filter_by_socket(struct hists *hists)
 {
-	hists__filter_by_type(hists, HIST_FILTER__SOCKET,
-			      hists__filter_entry_by_socket);
+	if (symbol_conf.report_hierarchy)
+		hists__filter_hierarchy(hists, HIST_FILTER__SOCKET,
+					&hists->socket_filter);
+	else
+		hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+				      hists__filter_entry_by_socket);
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 97baa1d6ae5f..722aa447f705 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -237,6 +237,7 @@ struct perf_hpp_fmt {
 struct perf_hpp_list {
 	struct list_head fields;
 	struct list_head sorts;
+	int nr_sort_keys;
 };
 
 extern struct perf_hpp_list perf_hpp_list;
@@ -301,6 +302,11 @@ void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
 bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
 					 struct hists *hists)
@@ -415,4 +421,22 @@ int perf_hist_config(const char *var, const char *value);
 
 void perf_hpp_list__init(struct perf_hpp_list *list);
 
+enum hierarchy_move_dir {
+	HMD_NORMAL,
+	HMD_FORCE_SIBLING,
+	HMD_FORCE_CHILD,
+};
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node);
+struct rb_node *__rb_hierarchy_next(struct rb_node *node,
+				    enum hierarchy_move_dir hmd);
+struct rb_node *rb_hierarchy_prev(struct rb_node *node);
+
+static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
+{
+	return __rb_hierarchy_next(node, HMD_NORMAL);
+}
+
+#define HIERARCHY_INDENT  3
+
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index b1507c04b257..75465f89a413 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -2,18 +2,29 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
 #include "mem-events.h"
 #include "debug.h"
+#include "symbol.h"
 
-#define E(t, n) { .tag = t, .name = n }
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
 struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P"),
-	E("ldlat-stores",	"cpu/mem-stores/P"),
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=30/P",	"mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
 };
+#undef E
 
 #undef E
 
+char *perf_mem_events__name(int i)
+{
+	return (char *)perf_mem_events[i].name;
+}
+
 int perf_mem_events__parse(const char *str)
 {
 	char *tok, *saveptr = NULL;
@@ -49,3 +60,196 @@ int perf_mem_events__parse(const char *str)
 	pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
 	return -1;
 }
+
+int perf_mem_events__init(void)
+{
+	const char *mnt = sysfs__mount();
+	bool found = false;
+	int j;
+
+	if (!mnt)
+		return -ENOENT;
+
+	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+		char path[PATH_MAX];
+		struct perf_mem_event *e = &perf_mem_events[j];
+		struct stat st;
+
+		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+			  mnt, e->sysfs_name);
+
+		if (!stat(path, &st))
+			e->supported = found = true;
+	}
+
+	return found ? 0 : -ENOENT;
+}
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, tlb_access[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (mem_info)
+		m  = mem_info->data_src.mem_lvl;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, mem_lvl[i]);
+	}
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+	if (hit)
+		l += scnprintf(out + l, sz - l, " hit");
+	if (miss)
+		l += scnprintf(out + l, sz - l, " miss");
+
+	return l;
+}
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	sz -= 1; /* -1 for null termination */
+	out[0] = '\0';
+
+	if (mem_info)
+		m = mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		l += scnprintf(out, sz - l, "N/A");
+
+	return l;
+}
+
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	u64 mask = PERF_MEM_LOCK_NA;
+	int l;
+
+	if (mem_info)
+		mask = mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		l = scnprintf(out, sz, "N/A");
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		l = scnprintf(out, sz, "Yes");
+	else
+		l = scnprintf(out, sz, "No");
+
+	return l;
+}
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+	int i = 0;
+
+	i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+	i += scnprintf(out + i, sz - i, "|SNP ");
+	i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|TLB ");
+	i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+	i += scnprintf(out + i, sz - i, "|LCK ");
+	i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+	return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 2995bae6ac33..5d6d93066a6e 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -5,8 +5,10 @@
 
 struct perf_mem_event {
 	bool		record;
+	bool		supported;
 	const char	*tag;
 	const char	*name;
+	const char	*sysfs_name;
 };
 
 enum {
@@ -18,5 +20,16 @@ enum {
 extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 
 int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
+
+char *perf_mem_events__name(int i);
+
+struct mem_info;
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
 
 #endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5388f7940474..6bee8bdfb91b 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t		parent_regex;
 const char	default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -89,10 +90,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 			       width, width, comm ?: "");
 }
 
+static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct thread *th = arg;
+
+	if (type != HIST_FILTER__THREAD)
+		return -1;
+
+	return th && he->thread != th;
+}
+
 struct sort_entry sort_thread = {
 	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_THREAD,
 };
 
@@ -130,6 +142,7 @@ struct sort_entry sort_comm = {
 	.se_collapse	= sort__comm_collapse,
 	.se_sort	= sort__comm_sort,
 	.se_snprintf	= hist_entry__comm_snprintf,
+	.se_filter	= hist_entry__thread_filter,
 	.se_width_idx	= HISTC_COMM,
 };
 
@@ -179,10 +192,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
 	return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
 }
 
+static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->ms.map || he->ms.map->dso != dso);
+}
+
 struct sort_entry sort_dso = {
 	.se_header	= "Shared Object",
 	.se_cmp		= sort__dso_cmp,
 	.se_snprintf	= hist_entry__dso_snprintf,
+	.se_filter	= hist_entry__dso_filter,
 	.se_width_idx	= HISTC_DSO,
 };
 
@@ -276,11 +300,22 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
 					 he->level, bf, size, width);
 }
 
+static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym));
+}
+
 struct sort_entry sort_sym = {
 	.se_header	= "Symbol",
 	.se_cmp		= sort__sym_cmp,
 	.se_sort	= sort__sym_sort,
 	.se_snprintf	= hist_entry__sym_snprintf,
+	.se_filter	= hist_entry__sym_filter,
 	.se_width_idx	= HISTC_SYMBOL,
 };
 
@@ -439,10 +474,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
 }
 
+static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg)
+{
+	int sk = *(const int *)arg;
+
+	if (type != HIST_FILTER__SOCKET)
+		return -1;
+
+	return sk >= 0 && he->socket != sk;
+}
+
 struct sort_entry sort_socket = {
 	.se_header      = "Socket",
 	.se_cmp	        = sort__socket_cmp,
 	.se_snprintf    = hist_entry__socket_snprintf,
+	.se_filter      = hist_entry__socket_filter,
 	.se_width_idx	= HISTC_SOCKET,
 };
 
@@ -529,6 +575,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->from.map ||
+		       he->branch_info->from.map->dso != dso);
+}
+
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -549,6 +607,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
 		return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
+				     const void *arg)
+{
+	const struct dso *dso = arg;
+
+	if (type != HIST_FILTER__DSO)
+		return -1;
+
+	return dso && (!he->branch_info || !he->branch_info->to.map ||
+		       he->branch_info->to.map->dso != dso);
+}
+
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -610,10 +680,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__sym_from_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->from.sym &&
+			strstr(he->branch_info->from.sym->name, sym));
+}
+
+static int hist_entry__sym_to_filter(struct hist_entry *he, int type,
+				       const void *arg)
+{
+	const char *sym = arg;
+
+	if (type != HIST_FILTER__SYMBOL)
+		return -1;
+
+	return sym && !(he->branch_info && he->branch_info->to.sym &&
+		        strstr(he->branch_info->to.sym->name, sym));
+}
+
 struct sort_entry sort_dso_from = {
 	.se_header	= "Source Shared Object",
 	.se_cmp		= sort__dso_from_cmp,
 	.se_snprintf	= hist_entry__dso_from_snprintf,
+	.se_filter	= hist_entry__dso_from_filter,
 	.se_width_idx	= HISTC_DSO_FROM,
 };
 
@@ -621,6 +716,7 @@ struct sort_entry sort_dso_to = {
 	.se_header	= "Target Shared Object",
 	.se_cmp		= sort__dso_to_cmp,
 	.se_snprintf	= hist_entry__dso_to_snprintf,
+	.se_filter	= hist_entry__dso_to_filter,
 	.se_width_idx	= HISTC_DSO_TO,
 };
 
@@ -628,6 +724,7 @@ struct sort_entry sort_sym_from = {
 	.se_header	= "Source Symbol",
 	.se_cmp		= sort__sym_from_cmp,
 	.se_snprintf	= hist_entry__sym_from_snprintf,
+	.se_filter	= hist_entry__sym_from_filter,
 	.se_width_idx	= HISTC_SYMBOL_FROM,
 };
 
@@ -635,6 +732,7 @@ struct sort_entry sort_sym_to = {
 	.se_header	= "Target Symbol",
 	.se_cmp		= sort__sym_to_cmp,
 	.se_snprintf	= hist_entry__sym_to_snprintf,
+	.se_filter	= hist_entry__sym_to_filter,
 	.se_width_idx	= HISTC_SYMBOL_TO,
 };
 
@@ -794,19 +892,9 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	const char *out;
-	u64 mask = PERF_MEM_LOCK_NA;
-
-	if (he->mem_info)
-		mask = he->mem_info->data_src.mem_lock;
-
-	if (mask & PERF_MEM_LOCK_NA)
-		out = "N/A";
-	else if (mask & PERF_MEM_LOCK_LOCKED)
-		out = "Yes";
-	else
-		out = "No";
+	char out[10];
 
+	perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
@@ -829,53 +917,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"L2",
-	"Walker",
-	"Fault",
-};
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t l = 0, i;
-	u64 m = PERF_MEM_TLB_NA;
-	u64 hit, miss;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_dtlb;
-
-	hit = m & PERF_MEM_TLB_HIT;
-	miss = m & PERF_MEM_TLB_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-	for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, tlb_access[i], sz - l);
-		l += strlen(tlb_access[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -898,60 +945,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-	"N/A",
-	"HIT",
-	"MISS",
-	"L1",
-	"LFB",
-	"L2",
-	"L3",
-	"Local RAM",
-	"Remote RAM (1 hop)",
-	"Remote RAM (2 hops)",
-	"Remote Cache (1 hop)",
-	"Remote Cache (2 hops)",
-	"I/O",
-	"Uncached",
-};
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m =  PERF_MEM_LVL_NA;
-	u64 hit, miss;
-
-	if (he->mem_info)
-		m  = he->mem_info->data_src.mem_lvl;
-
-	out[0] = '\0';
-
-	hit = m & PERF_MEM_LVL_HIT;
-	miss = m & PERF_MEM_LVL_MISS;
-
-	/* already taken care of */
-	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, mem_lvl[i], sz - l);
-		l += strlen(mem_lvl[i]);
-	}
-	if (*out == '\0')
-		strcpy(out, "N/A");
-	if (hit)
-		strncat(out, " hit", sz - l);
-	if (miss)
-		strncat(out, " miss", sz - l);
 
+	perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -974,41 +973,12 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
 	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-	"N/A",
-	"None",
-	"Miss",
-	"Hit",
-	"HitM",
-};
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
 	char out[64];
-	size_t sz = sizeof(out) - 1; /* -1 for null termination */
-	size_t i, l = 0;
-	u64 m = PERF_MEM_SNOOP_NA;
-
-	out[0] = '\0';
-
-	if (he->mem_info)
-		m = he->mem_info->data_src.mem_snoop;
-
-	for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (l) {
-			strcat(out, " or ");
-			l += 4;
-		}
-		strncat(out, snoop_access[i], sz - l);
-		l += strlen(snoop_access[i]);
-	}
-
-	if (*out == '\0')
-		strcpy(out, "N/A");
 
+	perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -1518,6 +1488,39 @@ bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
 	return format->header == __sort__hpp_header;
 }
 
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	if (!perf_hpp__is_sort_entry(fmt))
+		return false;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	return hse->se == &sort_trace;
+}
+
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	if (!perf_hpp__is_sort_entry(fmt))
+		return false;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	return hse->se == &sort_srcline;
+}
+
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt)
+{
+	struct hpp_sort_entry *hse;
+
+	if (!perf_hpp__is_sort_entry(fmt))
+		return false;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	return hse->se == &sort_srcfile;
+}
+
 static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 {
 	struct hpp_sort_entry *hse_a;
@@ -1592,6 +1595,22 @@ static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd)
 	return fmt;
 }
 
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
+{
+	struct perf_hpp_fmt *fmt;
+	struct hpp_sort_entry *hse;
+
+	fmt = he->fmt;
+	if (fmt == NULL || !perf_hpp__is_sort_entry(fmt))
+		return -1;
+
+	hse = container_of(fmt, struct hpp_sort_entry, hpp);
+	if (hse->se->se_filter == NULL)
+		return -1;
+
+	return hse->se->se_filter(he, type, arg);
+}
+
 static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
 {
 	struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5b9c6246de6d..a8d53ffe0916 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -96,9 +96,11 @@ struct hist_entry {
 	s32			socket;
 	s32			cpu;
 	u8			cpumode;
+	u8			depth;
 
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
+	bool			leaf;
 
 	char			level;
 	u8			filtered;
@@ -120,13 +122,22 @@ struct hist_entry {
 	char			*srcline;
 	char			*srcfile;
 	struct symbol		*parent;
-	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
 	struct mem_info		*mem_info;
 	void			*raw_data;
 	u32			raw_size;
 	void			*trace_output;
+	struct perf_hpp_fmt	*fmt;
+	struct hist_entry	*parent_he;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root	hroot_in;
+			struct rb_root  hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
 	struct callchain_root	callchain[0]; /* must be last member */
 };
 
@@ -234,6 +245,7 @@ struct sort_entry {
 	int64_t	(*se_sort)(struct hist_entry *, struct hist_entry *);
 	int	(*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
 			       unsigned int width);
+	int	(*se_filter)(struct hist_entry *he, int type, const void *arg);
 	u8	se_width_idx;
 };
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ccd1caa40e11..a937053a0ae0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,7 +110,8 @@ struct symbol_conf {
 			has_filter,
 			show_ref_callgraph,
 			hide_unresolved,
-			raw_trace;
+			raw_trace,
+			report_hierarchy;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 35b20dd454de..b7766c577b01 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
@@ -670,3 +671,39 @@ int fetch_current_timestamp(char *buf, size_t sz)
 
 	return 0;
 }
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra)
+{
+	size_t i, j, mask;
+
+	if (!printer)
+		return;
+
+	bytes_per_line = roundup_pow_of_two(bytes_per_line);
+	mask = bytes_per_line - 1;
+
+	printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+	for (i = 0; i < len; i++) {
+		if ((i & mask) == 0) {
+			printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+			printer(BINARY_PRINT_ADDR, i, extra);
+		}
+
+		printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+		if (((i & mask) == mask) || i == len - 1) {
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+			printer(BINARY_PRINT_SEP, i, extra);
+			for (j = i & ~mask; j <= i; j++)
+				printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+			for (j = 0; j < mask-(i & mask); j++)
+				printer(BINARY_PRINT_CHAR_PAD, i, extra);
+			printer(BINARY_PRINT_LINE_END, -1, extra);
+		}
+	}
+	printer(BINARY_PRINT_DATA_END, -1, extra);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 3dd04089e8be..d0d50cef8b2a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -82,6 +82,8 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
 extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
@@ -345,4 +347,24 @@ const char *perf_tip(const char *dirpath);
 bool is_regular_file(const char *file);
 int fetch_current_timestamp(char *buf, size_t sz);
 
+enum binary_printer_ops {
+	BINARY_PRINT_DATA_BEGIN,
+	BINARY_PRINT_LINE_BEGIN,
+	BINARY_PRINT_ADDR,
+	BINARY_PRINT_NUM_DATA,
+	BINARY_PRINT_NUM_PAD,
+	BINARY_PRINT_SEP,
+	BINARY_PRINT_CHAR_DATA,
+	BINARY_PRINT_CHAR_PAD,
+	BINARY_PRINT_LINE_END,
+	BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops,
+			       unsigned int val,
+			       void *extra);
+
+void print_binary(unsigned char *data, size_t len,
+		  size_t bytes_per_line, print_binary_t printer,
+		  void *extra);
 #endif /* GIT_COMPAT_UTIL_H */