diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 7315f155803f..8dbe2119686a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -525,6 +525,17 @@ include::itrace.txt[]
 	Configure time quantum for time sort key. Default 100ms.
 	Accepts s, us, ms, ns units.
 
+--total-cycles::
+	When --total-cycles is specified, it supports sorting for all blocks by
+	'Sampled Cycles%'. This is useful to concentrate on the globally hottest
+	blocks. In output, there are some new columns:
+
+	'Sampled Cycles%' - block sampled cycles aggregation / total sampled cycles
+	'Sampled Cycles'  - block sampled cycles aggregation
+	'Avg Cycles%'     - block average sampled cycles / sum of total block average
+			    sampled cycles
+	'Avg Cycles'      - block average sampled cycles
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index bc15b9dcccd6..992b18bdd723 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -51,6 +51,7 @@
 #include "util/util.h" // perf_tip()
 #include "ui/ui.h"
 #include "ui/progress.h"
+#include "util/block-info.h"
 
 #include <dlfcn.h>
 #include <errno.h>
@@ -96,10 +97,13 @@ struct report {
 	float			min_percent;
 	u64			nr_entries;
 	u64			queue_size;
+	u64			total_cycles;
 	int			socket_filter;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 	struct branch_type_stat	brtype_stat;
 	bool			symbol_ipc;
+	bool			total_cycles_mode;
+	struct block_report	*block_reports;
 };
 
 static int report__config(const char *var, const char *value, void *cb)
@@ -290,9 +294,10 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	if (ui__has_annotation() || rep->symbol_ipc) {
+	if (ui__has_annotation() || rep->symbol_ipc || rep->total_cycles_mode) {
 		hist__account_cycles(sample->branch_stack, &al, sample,
-				     rep->nonany_branch_mode, NULL);
+				     rep->nonany_branch_mode,
+				     &rep->total_cycles);
 	}
 
 	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
@@ -485,6 +490,7 @@ static int perf_evlist__tty_browse_hists(struct evlist *evlist,
 					 const char *help)
 {
 	struct evsel *pos;
+	int i = 0;
 
 	if (!quiet) {
 		fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n",
@@ -500,6 +506,13 @@ static int perf_evlist__tty_browse_hists(struct evlist *evlist,
 			continue;
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
+
+		if (rep->total_cycles_mode) {
+			report__browse_block_hists(&rep->block_reports[i++].hist,
+						   0, pos);
+			continue;
+		}
+
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
 			       !(symbol_conf.use_callchain ||
 			         symbol_conf.show_branchflag_count));
@@ -925,6 +938,13 @@ static int __cmd_report(struct report *rep)
 
 	report__output_resort(rep);
 
+	if (rep->total_cycles_mode) {
+		rep->block_reports = block_info__create_report(session->evlist,
+							       rep->total_cycles);
+		if (!rep->block_reports)
+			return -1;
+	}
+
 	return report__browse_hists(rep);
 }
 
@@ -1209,6 +1229,8 @@ int cmd_report(int argc, const char **argv)
 		     "Set time quantum for time sort key (default 100ms)",
 		     parse_time_quantum),
 	OPTS_EVSWITCH(&report.evswitch),
+	OPT_BOOLEAN(0, "total-cycles", &report.total_cycles_mode,
+		    "Sort all blocks by 'Sampled Cycles%'"),
 	OPT_END()
 	};
 	struct perf_data data = {
@@ -1371,6 +1393,17 @@ repeat:
 		goto error;
 	}
 
+	if (report.total_cycles_mode) {
+		if (sort__mode != SORT_MODE__BRANCH)
+			report.total_cycles_mode = false;
+		else if (!report.use_stdio) {
+			pr_err("Error: --total-cycles can be only used together with --stdio\n");
+			goto error;
+		} else {
+			sort_order = "sym";
+		}
+	}
+
 	if (strcmp(input_name, "-") != 0)
 		setup_browser(true);
 	else
@@ -1421,7 +1454,8 @@ repeat:
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
-	if (ui__has_annotation() || report.symbol_ipc) {
+	if (ui__has_annotation() || report.symbol_ipc ||
+	    report.total_cycles_mode) {
 		ret = symbol__annotation_init();
 		if (ret < 0)
 			goto error;
@@ -1482,6 +1516,10 @@ error:
 		itrace_synth_opts__clear_time_range(&itrace_synth_opts);
 		zfree(&report.ptime_range);
 	}
+
+	if (report.block_reports)
+		zfree(&report.block_reports);
+
 	zstd_fini(&(session->zstd_data));
 	perf_session__delete(session);
 	return ret;
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 5365606e9dad..655ef7708cd0 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -558,6 +558,25 @@ static int hist_entry__block_fprintf(struct hist_entry *he,
 	return ret;
 }
 
+static int hist_entry__individual_block_fprintf(struct hist_entry *he,
+						char *bf, size_t size,
+						FILE *fp)
+{
+	int ret = 0;
+
+	struct perf_hpp hpp = {
+		.buf		= bf,
+		.size		= size,
+		.skip		= false,
+	};
+
+	hist_entry__snprintf(he, &hpp);
+	if (!hpp.skip)
+		ret += fprintf(fp, "%s\n", bf);
+
+	return ret;
+}
+
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
 			       bool ignore_callchains)
@@ -580,6 +599,9 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	if (symbol_conf.report_block)
 		return hist_entry__block_fprintf(he, bf, size, fp);
 
+	if (symbol_conf.report_individual_block)
+		return hist_entry__individual_block_fprintf(he, bf, size, fp);
+
 	hist_entry__snprintf(he, &hpp);
 
 	ret = fprintf(fp, "%s\n", bf);
diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 4a7bac95231e..ba891751a6ed 100644
--- a/tools/perf/util/block-info.c
+++ b/tools/perf/util/block-info.c
@@ -437,3 +437,20 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 
 	return block_reports;
 }
+
+int report__browse_block_hists(struct block_hist *bh, float min_percent,
+			       struct evsel *evsel __maybe_unused)
+{
+	switch (use_browser) {
+	case 0:
+		symbol_conf.report_individual_block = true;
+		hists__fprintf(&bh->block_hists, true, 0, 0, min_percent,
+			       stdout, true);
+		hists__delete_entries(&bh->block_hists);
+		return 0;
+	default:
+		return -1;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/block-info.h b/tools/perf/util/block-info.h
index b5266588d476..8309297a6e8f 100644
--- a/tools/perf/util/block-info.h
+++ b/tools/perf/util/block-info.h
@@ -7,6 +7,7 @@
 #include "hist.h"
 #include "symbol.h"
 #include "sort.h"
+#include "ui/ui.h"
 
 struct block_info {
 	struct symbol		*sym;
@@ -69,4 +70,7 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 struct block_report *block_info__create_report(struct evlist *evlist,
 					       u64 total_cycles);
 
+int report__browse_block_hists(struct block_hist *bh, float min_percent,
+			       struct evsel *evsel);
+
 #endif /* __PERF_BLOCK_H */
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index e6880789864c..10f1ec3e0349 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -40,6 +40,7 @@ struct symbol_conf {
 			raw_trace,
 			report_hierarchy,
 			report_block,
+			report_individual_block,
 			inline_name,
 			disable_add2line_warn;
 	const char	*vmlinux_name,