diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 39db2ee..c37a786 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -6,6 +6,7 @@
  * DSOs and symbol information, sort them and produce a diff.
  */
 #include "builtin.h"
+#include "perf.h"
 
 #include "util/debug.h"
 #include "util/event.h"
@@ -15,16 +16,32 @@
 #include "util/session.h"
 #include "util/tool.h"
 #include "util/sort.h"
+#include "util/srcline.h"
 #include "util/symbol.h"
-#include "util/util.h"
 #include "util/data.h"
 #include "util/config.h"
+#include "util/time-utils.h"
+#include "util/annotate.h"
+#include "util/map.h"
+#include <linux/err.h>
+#include <linux/zalloc.h>
+#include <subcmd/pager.h>
+#include <subcmd/parse-options.h>
 
 #include <errno.h>
 #include <inttypes.h>
 #include <stdlib.h>
 #include <math.h>
 
+struct perf_diff {
+	struct perf_tool		 tool;
+	const char			*time_str;
+	struct perf_time_interval	*ptime_range;
+	int				 range_size;
+	int				 range_num;
+	bool				 has_br_stack;
+};
+
 /* Diff command specific HPP columns. */
 enum {
 	PERF_HPP_DIFF__BASELINE,
@@ -35,6 +52,7 @@
 	PERF_HPP_DIFF__WEIGHTED_DIFF,
 	PERF_HPP_DIFF__FORMULA,
 	PERF_HPP_DIFF__DELTA_ABS,
+	PERF_HPP_DIFF__CYCLES,
 
 	PERF_HPP_DIFF__MAX_INDEX
 };
@@ -74,11 +92,17 @@
 static s64 compute_wdiff_w1;
 static s64 compute_wdiff_w2;
 
+static const char		*cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
+static struct addr_location dummy_al;
+
 enum {
 	COMPUTE_DELTA,
 	COMPUTE_RATIO,
 	COMPUTE_WEIGHTED_DIFF,
 	COMPUTE_DELTA_ABS,
+	COMPUTE_CYCLES,
 	COMPUTE_MAX,
 };
 
@@ -87,6 +111,7 @@
 	[COMPUTE_DELTA_ABS] = "delta-abs",
 	[COMPUTE_RATIO] = "ratio",
 	[COMPUTE_WEIGHTED_DIFF] = "wdiff",
+	[COMPUTE_CYCLES] = "cycles",
 };
 
 static int compute = COMPUTE_DELTA_ABS;
@@ -96,6 +121,7 @@
 	[COMPUTE_DELTA_ABS]	= PERF_HPP_DIFF__DELTA_ABS,
 	[COMPUTE_RATIO]		= PERF_HPP_DIFF__RATIO,
 	[COMPUTE_WEIGHTED_DIFF]	= PERF_HPP_DIFF__WEIGHTED_DIFF,
+	[COMPUTE_CYCLES]	= PERF_HPP_DIFF__CYCLES,
 };
 
 #define MAX_COL_WIDTH 70
@@ -134,6 +160,10 @@
 	[PERF_HPP_DIFF__FORMULA] = {
 		.name  = "Formula",
 		.width = MAX_COL_WIDTH,
+	},
+	[PERF_HPP_DIFF__CYCLES] = {
+		.name  = "[Program Block Range] Cycles Diff",
+		.width = 70,
 	}
 };
 
@@ -323,27 +353,76 @@
 	return -1;
 }
 
-static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
+static void *block_hist_zalloc(size_t size)
+{
+	struct block_hist *bh;
+
+	bh = zalloc(size + sizeof(*bh));
+	if (!bh)
+		return NULL;
+
+	return &bh->he;
+}
+
+static void block_hist_free(void *he)
+{
+	struct block_hist *bh;
+
+	bh = container_of(he, struct block_hist, he);
+	hists__delete_entries(&bh->block_hists);
+	free(bh);
+}
+
+struct hist_entry_ops block_hist_ops = {
+	.new    = block_hist_zalloc,
+	.free   = block_hist_free,
+};
+
+static int diff__process_sample_event(struct perf_tool *tool,
 				      union perf_event *event,
 				      struct perf_sample *sample,
-				      struct perf_evsel *evsel,
+				      struct evsel *evsel,
 				      struct machine *machine)
 {
+	struct perf_diff *pdiff = container_of(tool, struct perf_diff, tool);
 	struct addr_location al;
 	struct hists *hists = evsel__hists(evsel);
 	int ret = -1;
 
+	if (perf_time__ranges_skip_sample(pdiff->ptime_range, pdiff->range_num,
+					  sample->time)) {
+		return 0;
+	}
+
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
 			   event->header.type);
 		return -1;
 	}
 
-	if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample, true)) {
-		pr_warning("problem incrementing symbol period, skipping event\n");
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap)) {
+		ret = 0;
 		goto out_put;
 	}
 
+	if (compute != COMPUTE_CYCLES) {
+		if (!hists__add_entry(hists, &al, NULL, NULL, NULL, sample,
+				      true)) {
+			pr_warning("problem incrementing symbol period, "
+				   "skipping event\n");
+			goto out_put;
+		}
+	} else {
+		if (!hists__add_entry_ops(hists, &block_hist_ops, &al, NULL,
+					  NULL, NULL, sample, true)) {
+			pr_warning("problem incrementing symbol period, "
+				   "skipping event\n");
+			goto out_put;
+		}
+
+		hist__account_cycles(sample->branch_stack, &al, sample, false);
+	}
+
 	/*
 	 * The total_period is updated here before going to the output
 	 * tree since normally only the baseline hists will call
@@ -359,23 +438,25 @@
 	return ret;
 }
 
-static struct perf_tool tool = {
-	.sample	= diff__process_sample_event,
-	.mmap	= perf_event__process_mmap,
-	.mmap2	= perf_event__process_mmap2,
-	.comm	= perf_event__process_comm,
-	.exit	= perf_event__process_exit,
-	.fork	= perf_event__process_fork,
-	.lost	= perf_event__process_lost,
-	.namespaces = perf_event__process_namespaces,
-	.ordered_events = true,
-	.ordering_requires_timestamps = true,
+static struct perf_diff pdiff = {
+	.tool = {
+		.sample	= diff__process_sample_event,
+		.mmap	= perf_event__process_mmap,
+		.mmap2	= perf_event__process_mmap2,
+		.comm	= perf_event__process_comm,
+		.exit	= perf_event__process_exit,
+		.fork	= perf_event__process_fork,
+		.lost	= perf_event__process_lost,
+		.namespaces = perf_event__process_namespaces,
+		.ordered_events = true,
+		.ordering_requires_timestamps = true,
+	},
 };
 
-static struct perf_evsel *evsel_match(struct perf_evsel *evsel,
-				      struct perf_evlist *evlist)
+static struct evsel *evsel_match(struct evsel *evsel,
+				      struct evlist *evlist)
 {
-	struct perf_evsel *e;
+	struct evsel *e;
 
 	evlist__for_each_entry(evlist, e) {
 		if (perf_evsel__match2(evsel, e))
@@ -385,9 +466,9 @@
 	return NULL;
 }
 
-static void perf_evlist__collapse_resort(struct perf_evlist *evlist)
+static void perf_evlist__collapse_resort(struct evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct evsel *evsel;
 
 	evlist__for_each_entry(evlist, evsel) {
 		struct hists *hists = evsel__hists(evsel);
@@ -429,7 +510,7 @@
 
 static void hists__baseline_only(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 
 	if (hists__has(hists, need_collapse))
@@ -437,21 +518,218 @@
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 	while (next != NULL) {
 		struct hist_entry *he = rb_entry(next, struct hist_entry, rb_node_in);
 
 		next = rb_next(&he->rb_node_in);
 		if (!hist_entry__next_pair(he)) {
-			rb_erase(&he->rb_node_in, root);
+			rb_erase_cached(&he->rb_node_in, root);
 			hist_entry__delete(he);
 		}
 	}
 }
 
+static int64_t block_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
+			 struct hist_entry *left, struct hist_entry *right)
+{
+	struct block_info *bi_l = left->block_info;
+	struct block_info *bi_r = right->block_info;
+	int cmp;
+
+	if (!bi_l->sym || !bi_r->sym) {
+		if (!bi_l->sym && !bi_r->sym)
+			return 0;
+		else if (!bi_l->sym)
+			return -1;
+		else
+			return 1;
+	}
+
+	if (bi_l->sym == bi_r->sym) {
+		if (bi_l->start == bi_r->start) {
+			if (bi_l->end == bi_r->end)
+				return 0;
+			else
+				return (int64_t)(bi_r->end - bi_l->end);
+		} else
+			return (int64_t)(bi_r->start - bi_l->start);
+	} else {
+		cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
+		return cmp;
+	}
+
+	if (bi_l->sym->start != bi_r->sym->start)
+		return (int64_t)(bi_r->sym->start - bi_l->sym->start);
+
+	return (int64_t)(bi_r->sym->end - bi_l->sym->end);
+}
+
+static int64_t block_cycles_diff_cmp(struct hist_entry *left,
+				     struct hist_entry *right)
+{
+	bool pairs_left  = hist_entry__has_pairs(left);
+	bool pairs_right = hist_entry__has_pairs(right);
+	s64 l, r;
+
+	if (!pairs_left && !pairs_right)
+		return 0;
+
+	l = labs(left->diff.cycles);
+	r = labs(right->diff.cycles);
+	return r - l;
+}
+
+static int64_t block_sort(struct perf_hpp_fmt *fmt __maybe_unused,
+			  struct hist_entry *left, struct hist_entry *right)
+{
+	return block_cycles_diff_cmp(right, left);
+}
+
+static void init_block_hist(struct block_hist *bh)
+{
+	__hists__init(&bh->block_hists, &bh->block_list);
+	perf_hpp_list__init(&bh->block_list);
+
+	INIT_LIST_HEAD(&bh->block_fmt.list);
+	INIT_LIST_HEAD(&bh->block_fmt.sort_list);
+	bh->block_fmt.cmp = block_cmp;
+	bh->block_fmt.sort = block_sort;
+	perf_hpp_list__register_sort_field(&bh->block_list,
+					   &bh->block_fmt);
+	bh->valid = true;
+}
+
+static void init_block_info(struct block_info *bi, struct symbol *sym,
+			    struct cyc_hist *ch, int offset)
+{
+	bi->sym = sym;
+	bi->start = ch->start;
+	bi->end = offset;
+	bi->cycles = ch->cycles;
+	bi->cycles_aggr = ch->cycles_aggr;
+	bi->num = ch->num;
+	bi->num_aggr = ch->num_aggr;
+}
+
+static int process_block_per_sym(struct hist_entry *he)
+{
+	struct annotation *notes;
+	struct cyc_hist *ch;
+	struct block_hist *bh;
+
+	if (!he->ms.map || !he->ms.sym)
+		return 0;
+
+	notes = symbol__annotation(he->ms.sym);
+	if (!notes || !notes->src || !notes->src->cycles_hist)
+		return 0;
+
+	bh = container_of(he, struct block_hist, he);
+	init_block_hist(bh);
+
+	ch = notes->src->cycles_hist;
+	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
+		if (ch[i].num_aggr) {
+			struct block_info *bi;
+			struct hist_entry *he_block;
+
+			bi = block_info__new();
+			if (!bi)
+				return -1;
+
+			init_block_info(bi, he->ms.sym, &ch[i], i);
+			he_block = hists__add_entry_block(&bh->block_hists,
+							  &dummy_al, bi);
+			if (!he_block) {
+				block_info__put(bi);
+				return -1;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
+{
+	struct block_info *bi_a = a->block_info;
+	struct block_info *bi_b = b->block_info;
+	int cmp;
+
+	if (!bi_a->sym || !bi_b->sym)
+		return -1;
+
+	cmp = strcmp(bi_a->sym->name, bi_b->sym->name);
+
+	if ((!cmp) && (bi_a->start == bi_b->start) && (bi_a->end == bi_b->end))
+		return 0;
+
+	return -1;
+}
+
+static struct hist_entry *get_block_pair(struct hist_entry *he,
+					 struct hists *hists_pair)
+{
+	struct rb_root_cached *root = hists_pair->entries_in;
+	struct rb_node *next = rb_first_cached(root);
+	int cmp;
+
+	while (next != NULL) {
+		struct hist_entry *he_pair = rb_entry(next, struct hist_entry,
+						      rb_node_in);
+
+		next = rb_next(&he_pair->rb_node_in);
+
+		cmp = block_pair_cmp(he_pair, he);
+		if (!cmp)
+			return he_pair;
+	}
+
+	return NULL;
+}
+
+static void compute_cycles_diff(struct hist_entry *he,
+				struct hist_entry *pair)
+{
+	pair->diff.computed = true;
+	if (pair->block_info->num && he->block_info->num) {
+		pair->diff.cycles =
+			pair->block_info->cycles_aggr / pair->block_info->num_aggr -
+			he->block_info->cycles_aggr / he->block_info->num_aggr;
+	}
+}
+
+static void block_hists_match(struct hists *hists_base,
+			      struct hists *hists_pair)
+{
+	struct rb_root_cached *root = hists_base->entries_in;
+	struct rb_node *next = rb_first_cached(root);
+
+	while (next != NULL) {
+		struct hist_entry *he = rb_entry(next, struct hist_entry,
+						 rb_node_in);
+		struct hist_entry *pair = get_block_pair(he, hists_pair);
+
+		next = rb_next(&he->rb_node_in);
+
+		if (pair) {
+			hist_entry__add_pair(pair, he);
+			compute_cycles_diff(he, pair);
+		}
+	}
+}
+
+static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
+{
+	/* Skip the calculation of column length in output_resort */
+	he->filtered = true;
+	return 0;
+}
+
 static void hists__precompute(struct hists *hists)
 {
-	struct rb_root *root;
+	struct rb_root_cached *root;
 	struct rb_node *next;
 
 	if (hists__has(hists, need_collapse))
@@ -459,8 +737,9 @@
 	else
 		root = hists->entries_in;
 
-	next = rb_first(root);
+	next = rb_first_cached(root);
 	while (next != NULL) {
+		struct block_hist *bh, *pair_bh;
 		struct hist_entry *he, *pair;
 		struct data__file *d;
 		int i;
@@ -468,6 +747,9 @@
 		he   = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&he->rb_node_in);
 
+		if (compute == COMPUTE_CYCLES)
+			process_block_per_sym(he);
+
 		data__for_each_file_new(i, d) {
 			pair = get_pair_data(he, d);
 			if (!pair)
@@ -484,6 +766,19 @@
 			case COMPUTE_WEIGHTED_DIFF:
 				compute_wdiff(he, pair);
 				break;
+			case COMPUTE_CYCLES:
+				process_block_per_sym(pair);
+				bh = container_of(he, struct block_hist, he);
+				pair_bh = container_of(pair, struct block_hist,
+						       he);
+
+				if (bh->valid && pair_bh->valid) {
+					block_hists_match(&bh->block_hists,
+							  &pair_bh->block_hists);
+					hists__output_resort_cb(&pair_bh->block_hists,
+								NULL, filter_cb);
+				}
+				break;
 			default:
 				BUG_ON(1);
 			}
@@ -695,6 +990,9 @@
 	hists__precompute(hists);
 	hists__output_resort(hists, NULL);
 
+	if (compute == COMPUTE_CYCLES)
+		symbol_conf.report_block = true;
+
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
 		       !symbol_conf.use_callchain);
 }
@@ -708,7 +1006,7 @@
 
 	data__for_each_file(i, d)
 		fprintf(stdout, "#  [%d] %s %s\n",
-			d->idx, d->data.file.path,
+			d->idx, d->data.path,
 			!d->idx ? "(Baseline)" : "");
 
 	fprintf(stdout, "#\n");
@@ -716,8 +1014,8 @@
 
 static void data_process(void)
 {
-	struct perf_evlist *evlist_base = data__files[0].session->evlist;
-	struct perf_evsel *evsel_base;
+	struct evlist *evlist_base = data__files[0].session->evlist;
+	struct evsel *evsel_base;
 	bool first = true;
 
 	evlist__for_each_entry(evlist_base, evsel_base) {
@@ -726,8 +1024,8 @@
 		int i;
 
 		data__for_each_file_new(i, d) {
-			struct perf_evlist *evlist = d->session->evlist;
-			struct perf_evsel *evsel;
+			struct evlist *evlist = d->session->evlist;
+			struct evsel *evsel;
 			struct hists *hists;
 
 			evsel = evsel_match(evsel_base, evlist);
@@ -771,26 +1069,152 @@
 	}
 }
 
+static int abstime_str_dup(char **pstr)
+{
+	char *str = NULL;
+
+	if (pdiff.time_str && strchr(pdiff.time_str, ':')) {
+		str = strdup(pdiff.time_str);
+		if (!str)
+			return -ENOMEM;
+	}
+
+	*pstr = str;
+	return 0;
+}
+
+static int parse_absolute_time(struct data__file *d, char **pstr)
+{
+	char *p = *pstr;
+	int ret;
+
+	/*
+	 * Absolute timestamp for one file has the format: a.b,c.d
+	 * For multiple files, the format is: a.b,c.d:a.b,c.d
+	 */
+	p = strchr(*pstr, ':');
+	if (p) {
+		if (p == *pstr) {
+			pr_err("Invalid time string\n");
+			return -EINVAL;
+		}
+
+		*p = 0;
+		p++;
+		if (*p == 0) {
+			pr_err("Invalid time string\n");
+			return -EINVAL;
+		}
+	}
+
+	ret = perf_time__parse_for_ranges(*pstr, d->session,
+					  &pdiff.ptime_range,
+					  &pdiff.range_size,
+					  &pdiff.range_num);
+	if (ret < 0)
+		return ret;
+
+	if (!p || *p == 0)
+		*pstr = NULL;
+	else
+		*pstr = p;
+
+	return ret;
+}
+
+static int parse_percent_time(struct data__file *d)
+{
+	int ret;
+
+	ret = perf_time__parse_for_ranges(pdiff.time_str, d->session,
+					  &pdiff.ptime_range,
+					  &pdiff.range_size,
+					  &pdiff.range_num);
+	return ret;
+}
+
+static int parse_time_str(struct data__file *d, char *abstime_ostr,
+			   char **pabstime_tmp)
+{
+	int ret = 0;
+
+	if (abstime_ostr)
+		ret = parse_absolute_time(d, pabstime_tmp);
+	else if (pdiff.time_str)
+		ret = parse_percent_time(d);
+
+	return ret;
+}
+
+static int check_file_brstack(void)
+{
+	struct data__file *d;
+	bool has_br_stack;
+	int i;
+
+	data__for_each_file(i, d) {
+		d->session = perf_session__new(&d->data, false, &pdiff.tool);
+		if (IS_ERR(d->session)) {
+			pr_err("Failed to open %s\n", d->data.path);
+			return PTR_ERR(d->session);
+		}
+
+		has_br_stack = perf_header__has_feat(&d->session->header,
+						     HEADER_BRANCH_STACK);
+		perf_session__delete(d->session);
+		if (!has_br_stack)
+			return 0;
+	}
+
+	/* Set only all files having branch stacks */
+	pdiff.has_br_stack = true;
+	return 0;
+}
+
 static int __cmd_diff(void)
 {
 	struct data__file *d;
-	int ret = -EINVAL, i;
+	int ret, i;
+	char *abstime_ostr, *abstime_tmp;
+
+	ret = abstime_str_dup(&abstime_ostr);
+	if (ret)
+		return ret;
+
+	abstime_tmp = abstime_ostr;
+	ret = -EINVAL;
 
 	data__for_each_file(i, d) {
-		d->session = perf_session__new(&d->data, false, &tool);
-		if (!d->session) {
-			pr_err("Failed to open %s\n", d->data.file.path);
-			ret = -1;
+		d->session = perf_session__new(&d->data, false, &pdiff.tool);
+		if (IS_ERR(d->session)) {
+			ret = PTR_ERR(d->session);
+			pr_err("Failed to open %s\n", d->data.path);
 			goto out_delete;
 		}
 
+		if (pdiff.time_str) {
+			ret = parse_time_str(d, abstime_ostr, &abstime_tmp);
+			if (ret < 0)
+				goto out_delete;
+		}
+
+		if (cpu_list) {
+			ret = perf_session__cpu_bitmap(d->session, cpu_list,
+						       cpu_bitmap);
+			if (ret < 0)
+				goto out_delete;
+		}
+
 		ret = perf_session__process_events(d->session);
 		if (ret) {
-			pr_err("Failed to process %s\n", d->data.file.path);
+			pr_err("Failed to process %s\n", d->data.path);
 			goto out_delete;
 		}
 
 		perf_evlist__collapse_resort(d->session->evlist);
+
+		if (pdiff.ptime_range)
+			zfree(&pdiff.ptime_range);
 	}
 
 	data_process();
@@ -802,6 +1226,13 @@
 	}
 
 	free(data__files);
+
+	if (pdiff.ptime_range)
+		zfree(&pdiff.ptime_range);
+
+	if (abstime_ostr)
+		free(abstime_ostr);
+
 	return ret;
 }
 
@@ -817,7 +1248,7 @@
 	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
 		    "Show only items with match in baseline"),
 	OPT_CALLBACK('c', "compute", &compute,
-		     "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
+		     "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs),cycles",
 		     "Entries differential computation selection",
 		     setup_compute),
 	OPT_BOOLEAN('p', "period", &show_period,
@@ -849,6 +1280,13 @@
 	OPT_UINTEGER('o', "order", &sort_compute, "Specify compute sorting."),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),
+	OPT_STRING(0, "time", &pdiff.time_str, "str",
+		   "Time span (time percent or absolute timestamp)"),
+	OPT_STRING(0, "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING(0, "pid", &symbol_conf.pid_list_str, "pid[,pid...]",
+		   "only consider symbols in these pids"),
+	OPT_STRING(0, "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
+		   "only consider symbols in these tids"),
 	OPT_END()
 };
 
@@ -888,6 +1326,49 @@
 	return ret;
 }
 
+static int cycles_printf(struct hist_entry *he, struct hist_entry *pair,
+			 struct perf_hpp *hpp, int width)
+{
+	struct block_hist *bh = container_of(he, struct block_hist, he);
+	struct block_hist *bh_pair = container_of(pair, struct block_hist, he);
+	struct hist_entry *block_he;
+	struct block_info *bi;
+	char buf[128];
+	char *start_line, *end_line;
+
+	block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
+	if (!block_he) {
+		hpp->skip = true;
+		return 0;
+	}
+
+	/*
+	 * Avoid printing the warning "addr2line_init failed for ..."
+	 */
+	symbol_conf.disable_add2line_warn = true;
+
+	bi = block_he->block_info;
+
+	start_line = map__srcline(he->ms.map, bi->sym->start + bi->start,
+				  he->ms.sym);
+
+	end_line = map__srcline(he->ms.map, bi->sym->start + bi->end,
+				he->ms.sym);
+
+	if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) {
+		scnprintf(buf, sizeof(buf), "[%s -> %s] %4ld",
+			  start_line, end_line, block_he->diff.cycles);
+	} else {
+		scnprintf(buf, sizeof(buf), "[%7lx -> %7lx] %4ld",
+			  bi->start, bi->end, block_he->diff.cycles);
+	}
+
+	free_srcline(start_line);
+	free_srcline(end_line);
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, buf);
+}
+
 static int __hpp__color_compare(struct perf_hpp_fmt *fmt,
 				struct perf_hpp *hpp, struct hist_entry *he,
 				int comparison_method)
@@ -899,8 +1380,17 @@
 	s64 wdiff;
 	char pfmt[20] = " ";
 
-	if (!pair)
+	if (!pair) {
+		if (comparison_method == COMPUTE_CYCLES) {
+			struct block_hist *bh;
+
+			bh = container_of(he, struct block_hist, he);
+			if (bh->block_idx)
+				hpp->skip = true;
+		}
+
 		goto no_print;
+	}
 
 	switch (comparison_method) {
 	case COMPUTE_DELTA:
@@ -935,6 +1425,8 @@
 		return color_snprintf(hpp->buf, hpp->size,
 				get_percent_color(wdiff),
 				pfmt, wdiff);
+	case COMPUTE_CYCLES:
+		return cycles_printf(he, pair, hpp, dfmt->header_width);
 	default:
 		BUG_ON(1);
 	}
@@ -964,6 +1456,12 @@
 	return __hpp__color_compare(fmt, hpp, he, COMPUTE_WEIGHTED_DIFF);
 }
 
+static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
+			     struct perf_hpp *hpp, struct hist_entry *he)
+{
+	return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -1165,6 +1663,10 @@
 		fmt->color = hpp__color_delta;
 		fmt->sort  = hist_entry__cmp_delta_abs;
 		break;
+	case PERF_HPP_DIFF__CYCLES:
+		fmt->color = hpp__color_cycles;
+		fmt->sort  = hist_entry__cmp_nop;
+		break;
 	default:
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
@@ -1245,6 +1747,13 @@
 	case COMPUTE_DELTA_ABS:
 		fmt->sort = hist_entry__cmp_delta_abs_idx;
 		break;
+	case COMPUTE_CYCLES:
+		/*
+		 * Should set since 'fmt->sort' is called without
+		 * checking valid during sorting
+		 */
+		fmt->sort = hist_entry__cmp_nop;
+		break;
 	default:
 		BUG_ON(1);
 	}
@@ -1289,9 +1798,9 @@
 	data__for_each_file(i, d) {
 		struct perf_data *data = &d->data;
 
-		data->file.path = use_default ? defaults[i] : argv[i];
-		data->mode      = PERF_DATA_MODE_READ,
-		data->force     = force,
+		data->path  = use_default ? defaults[i] : argv[i];
+		data->mode  = PERF_DATA_MODE_READ,
+		data->force = force,
 
 		d->idx  = i;
 	}
@@ -1341,12 +1850,20 @@
 	if (quiet)
 		perf_quiet_option();
 
+	symbol__annotation_init();
+
 	if (symbol__init(NULL) < 0)
 		return -1;
 
 	if (data_init(argc, argv) < 0)
 		return -1;
 
+	if (check_file_brstack() < 0)
+		return -1;
+
+	if (compute == COMPUTE_CYCLES && !pdiff.has_br_stack)
+		return -1;
+
 	if (ui_init() < 0)
 		return -1;