perf report: Display the branch counter histogram

Reusing the existing --total-cycles option to display the branch
counters. Add a new PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER to display
the logged branch counter events. They are shown right after all the
cycle-related annotations.

Extend the 'struct block_info' to store and pass the branch counter
related information.

The annotation_br_cntr_entry() is to print the histogram of each branch
counter event. If the number of logged events is less than 4, the exact
number of the abbr name is printed. Otherwise, using '+' to stands for
more than 3 events.

Assume the number of logged events is less than 4.

The annotation_br_cntr_abbr_list() prints the branch counter's
abbreviation list. Press 'B' to display the list in the TUI mode.

  $ perf record -e "{branch-instructions:ppp,branch-misses}:S" -j any,counter
  $ perf report  --total-cycles --stdio

  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 1M of events 'anon group { branch-instructions:ppp, branch-misses }'
  # Event count (approx.): 1610046
  #
  # Branch counter abbr list:
  # branch-instructions:ppp = A
  # branch-misses = B
  # '-' No event occurs
  # '+' Event occurrences may be lost due to branch counter saturated
  #
  # Sampled Cycles%  Sampled Cycles  Avg Cycles%  Avg Cycles  Branch Counter [Program Block Range]
  # ...............  ..............  ...........  ..........  ..............  ..................
  #
            57.55%            2.5M        0.00%           3     |A   |-   |                 ...
            25.27%            1.1M        0.00%           2     |AA  |-   |                 ...
            15.61%          667.2K        0.00%           1     |A   |-   |                 ...
             0.16%            6.9K        0.81%         575     |A   |-   |                 ...
             0.16%            6.8K        1.38%         977     |AA  |-   |                 ...
             0.16%            6.8K        0.04%          28     |AA  |B   |                 ...
             0.15%            6.6K        1.33%         946     |A   |-   |                 ...
             0.11%            4.5K        0.06%          46     |AAA+|-   |                 ...
             0.10%            4.4K        0.88%         624     |A   |-   |                 ...
             0.09%            3.7K        0.74%         524     |AAA+|B   |                 ...

With -v applied,

  # Sampled Cycles%  Sampled Cycles  Avg Cycles%  Avg Cycles  Branch Counter [Program Block Range]
  # ...............  ..............  ...........  ..........  ..............  ..................
  #
            57.55%            2.5M        0.00%           3       A=1 ,B=-                  ...
            25.27%            1.1M        0.00%           2       A=2 ,B=-                  ...
            15.61%          667.2K        0.00%           1       A=1 ,B=-                  ...
             0.16%            6.9K        0.81%         575       A=1 ,B=-                  ...
             0.16%            6.8K        1.38%         977       A=2 ,B=-                  ...
             0.16%            6.8K        0.04%          28       A=2 ,B=1                  ...
             0.15%            6.6K        1.33%         946       A=1 ,B=-                  ...
             0.11%            4.5K        0.06%          46       A=3+,B=-                  ...
             0.10%            4.4K        0.88%         624       A=1 ,B=-                  ...
             0.09%            3.7K        0.74%         524       A=3+,B=1                  ...

Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240813160208.2493643-7-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-report.txt

@@ -614,6 +614,7 @@ include::itrace.txt[]
 	'Avg Cycles%'     - block average sampled cycles / sum of total block average
 			    sampled cycles
 	'Avg Cycles'      - block average sampled cycles
+	'Branch Counter'  - block branch counter histogram (with -v showing the number)
 
 --skip-empty::
 	Do not print 0 results in the --stat output.

tools/perf/builtin-diff.c

@@ -691,7 +691,7 @@ static void hists__precompute(struct hists *hists)
 		if (compute == COMPUTE_CYCLES) {
 			bh = container_of(he, struct block_hist, he);
 			init_block_hist(bh);
-			block_info__process_sym(he, bh, NULL, 0);
+			block_info__process_sym(he, bh, NULL, 0, 0);
 		}
 
 		data__for_each_file_new(i, d) {
@@ -714,7 +714,7 @@ static void hists__precompute(struct hists *hists)
 				pair_bh = container_of(pair, struct block_hist,
 						       he);
 				init_block_hist(pair_bh);
-				block_info__process_sym(pair, pair_bh, NULL, 0);
+				block_info__process_sym(pair, pair_bh, NULL, 0, 0);
 
 				bh = container_of(he, struct block_hist, he);
 

tools/perf/builtin-report.c

@@ -575,6 +575,13 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 
 		if (rep->total_cycles_mode) {
+			char *buf;
+
+			if (!annotation_br_cntr_abbr_list(&buf, pos, true)) {
+				fprintf(stdout, "%s", buf);
+				fprintf(stdout, "#\n");
+				free(buf);
+			}
 			report__browse_block_hists(&rep->block_reports[i - 1].hist,
 						   rep->min_percent, pos, NULL);
 			continue;
@@ -1119,18 +1126,23 @@ static int __cmd_report(struct report *rep)
 	report__output_resort(rep);
 
 	if (rep->total_cycles_mode) {
-		int block_hpps[6] = {
+		int nr_hpps = 4;
+		int block_hpps[PERF_HPP_REPORT__BLOCK_MAX_INDEX] = {
 			PERF_HPP_REPORT__BLOCK_TOTAL_CYCLES_PCT,
 			PERF_HPP_REPORT__BLOCK_LBR_CYCLES,
 			PERF_HPP_REPORT__BLOCK_CYCLES_PCT,
 			PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
-			PERF_HPP_REPORT__BLOCK_RANGE,
-			PERF_HPP_REPORT__BLOCK_DSO,
 		};
 
+		if (session->evlist->nr_br_cntr > 0)
+			block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER;
+
+		block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_RANGE;
+		block_hpps[nr_hpps++] = PERF_HPP_REPORT__BLOCK_DSO;
+
 		rep->block_reports = block_info__create_report(session->evlist,
 							       rep->total_cycles,
-							       block_hpps, 6,
+							       block_hpps, nr_hpps,
 							       &rep->nr_block_reports);
 		if (!rep->block_reports)
 			return -1;

tools/perf/ui/browsers/hists.c

@@ -3684,8 +3684,10 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 	struct hist_browser *browser;
 	int key = -1;
 	struct popup_action action;
+	char *br_cntr_text = NULL;
 	static const char help[] =
-	" q             Quit \n";
+	" q             Quit \n"
+	" B             Branch counter abbr list (Optional)\n";
 
 	browser = hist_browser__new(hists);
 	if (!browser)
@@ -3703,6 +3705,8 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 
 	memset(&action, 0, sizeof(action));
 
+	annotation_br_cntr_abbr_list(&br_cntr_text, evsel, false);
+
 	while (1) {
 		key = hist_browser__run(browser, "? - help", true, 0);
 
@@ -3723,6 +3727,16 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 			action.ms.sym = browser->selection->sym;
 			do_annotate(browser, &action);
 			continue;
+		case 'B':
+			if (br_cntr_text) {
+				ui__question_window("Branch counter abbr list",
+						    br_cntr_text, "Press any key...", 0);
+			} else {
+				ui__question_window("Branch counter abbr list",
+						    "\n The branch counter is not available.\n",
+						    "Press any key...", 0);
+			}
+			continue;
 		default:
 			break;
 		}
@@ -3730,5 +3744,6 @@ int block_hists_tui_browse(struct block_hist *bh, struct evsel *evsel,
 
 out:
 	hist_browser__delete(browser);
+	free(br_cntr_text);
 	return 0;
 }

tools/perf/util/annotate.c

@@ -41,6 +41,7 @@
 #include "namespaces.h"
 #include "thread.h"
 #include "hashmap.h"
+#include "strbuf.h"
 #include <regex.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
@@ -48,6 +49,7 @@
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
 #include <subcmd/run-command.h>
+#include <math.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -1719,6 +1721,149 @@ static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
 		  ipc, coverage);
 }
 
+int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header)
+{
+	struct evsel *pos;
+	struct strbuf sb;
+
+	if (evsel->evlist->nr_br_cntr <= 0)
+		return -ENOTSUP;
+
+	strbuf_init(&sb, /*hint=*/ 0);
+
+	if (header && strbuf_addf(&sb, "# Branch counter abbr list:\n"))
+		goto err;
+
+	evlist__for_each_entry(evsel->evlist, pos) {
+		if (!(pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			continue;
+		if (header && strbuf_addf(&sb, "#"))
+			goto err;
+
+		if (strbuf_addf(&sb, " %s = %s\n", pos->name, pos->abbr_name))
+			goto err;
+	}
+
+	if (header && strbuf_addf(&sb, "#"))
+		goto err;
+	if (strbuf_addf(&sb, " '-' No event occurs\n"))
+		goto err;
+
+	if (header && strbuf_addf(&sb, "#"))
+		goto err;
+	if (strbuf_addf(&sb, " '+' Event occurrences may be lost due to branch counter saturated\n"))
+		goto err;
+
+	*str = strbuf_detach(&sb, NULL);
+
+	return 0;
+err:
+	strbuf_release(&sb);
+	return -ENOMEM;
+}
+
+/* Assume the branch counter saturated at 3 */
+#define ANNOTATION_BR_CNTR_SATURATION		3
+
+int annotation_br_cntr_entry(char **str, int br_cntr_nr,
+			     u64 *br_cntr, int num_aggr,
+			     struct evsel *evsel)
+{
+	struct evsel *pos = evsel ? evlist__first(evsel->evlist) : NULL;
+	bool saturated = false;
+	int i, j, avg, used;
+	struct strbuf sb;
+
+	strbuf_init(&sb, /*hint=*/ 0);
+	for (i = 0; i < br_cntr_nr; i++) {
+		used = 0;
+		avg = ceil((double)(br_cntr[i] & ~ANNOTATION__BR_CNTR_SATURATED_FLAG) /
+			   (double)num_aggr);
+
+		/*
+		 * A histogram with the abbr name is displayed by default.
+		 * With -v, the exact number of branch counter is displayed.
+		 */
+		if (verbose) {
+			evlist__for_each_entry_from(evsel->evlist, pos) {
+				if ((pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS) &&
+				    (pos->br_cntr_idx == i))
+				break;
+			}
+			if (strbuf_addstr(&sb, pos->abbr_name))
+				goto err;
+
+			if (!br_cntr[i]) {
+				if (strbuf_addstr(&sb, "=-"))
+					goto err;
+			} else {
+				if (strbuf_addf(&sb, "=%d", avg))
+					goto err;
+			}
+			if (br_cntr[i] & ANNOTATION__BR_CNTR_SATURATED_FLAG) {
+				if (strbuf_addch(&sb, '+'))
+					goto err;
+			} else {
+				if (strbuf_addch(&sb, ' '))
+					goto err;
+			}
+
+			if ((i < br_cntr_nr - 1) && strbuf_addch(&sb, ','))
+				goto err;
+			continue;
+		}
+
+		if (strbuf_addch(&sb, '|'))
+			goto err;
+
+		if (!br_cntr[i]) {
+			if (strbuf_addch(&sb, '-'))
+				goto err;
+			used++;
+		} else {
+			evlist__for_each_entry_from(evsel->evlist, pos) {
+				if ((pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS) &&
+				    (pos->br_cntr_idx == i))
+					break;
+			}
+			if (br_cntr[i] & ANNOTATION__BR_CNTR_SATURATED_FLAG)
+				saturated = true;
+
+			for (j = 0; j < avg; j++, used++) {
+				/* Print + if the number of logged events > 3 */
+				if (j >= ANNOTATION_BR_CNTR_SATURATION) {
+					saturated = true;
+					break;
+				}
+				if (strbuf_addstr(&sb, pos->abbr_name))
+					goto err;
+			}
+
+			if (saturated) {
+				if (strbuf_addch(&sb, '+'))
+					goto err;
+				used++;
+			}
+			pos = list_next_entry(pos, core.node);
+		}
+
+		for (j = used; j < ANNOTATION_BR_CNTR_SATURATION + 1; j++) {
+			if (strbuf_addch(&sb, ' '))
+				goto err;
+		}
+	}
+
+	if (!verbose && strbuf_addch(&sb, br_cntr_nr ? '|' : ' '))
+		goto err;
+
+	*str = strbuf_detach(&sb, NULL);
+
+	return 0;
+err:
+	strbuf_release(&sb);
+	return -ENOMEM;
+}
+
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
 				     bool first_line, bool current_entry, bool change_color, int width,
 				     void *obj, unsigned int percent_type,

tools/perf/util/annotate.h

@@ -553,4 +553,7 @@ int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
 
 void debuginfo_cache__delete(void);
 
+int annotation_br_cntr_entry(char **str, int br_cntr_nr, u64 *br_cntr,
+			     int num_aggr, struct evsel *evsel);
+int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header);
 #endif	/* __PERF_ANNOTATE_H */

tools/perf/util/block-info.c

@@ -40,16 +40,32 @@ static struct block_header_column {
 	[PERF_HPP_REPORT__BLOCK_DSO] = {
 		.name = "Shared Object",
 		.width = 20,
+	},
+	[PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER] = {
+		.name = "Branch Counter",
+		.width = 30,
 	}
 };
 
-struct block_info *block_info__new(void)
+static struct block_info *block_info__new(unsigned int br_cntr_nr)
 {
-	return zalloc(sizeof(struct block_info));
+	struct block_info *bi = zalloc(sizeof(struct block_info));
+
+	if (bi && br_cntr_nr) {
+		bi->br_cntr = calloc(br_cntr_nr, sizeof(u64));
+		if (!bi->br_cntr) {
+			free(bi);
+			return NULL;
+		}
+	}
+
+	return bi;
 }
 
 void block_info__delete(struct block_info *bi)
 {
+	if (bi)
+		free(bi->br_cntr);
 	free(bi);
 }
 
@@ -86,7 +102,8 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 
 static void init_block_info(struct block_info *bi, struct symbol *sym,
 			    struct cyc_hist *ch, int offset,
-			    u64 total_cycles)
+			    u64 total_cycles, unsigned int br_cntr_nr,
+			    u64 *br_cntr, struct evsel *evsel)
 {
 	bi->sym = sym;
 	bi->start = ch->start;
@@ -99,10 +116,18 @@ static void init_block_info(struct block_info *bi, struct symbol *sym,
 
 	memcpy(bi->cycles_spark, ch->cycles_spark,
 	       NUM_SPARKS * sizeof(u64));
+
+	if (br_cntr && br_cntr_nr) {
+		bi->br_cntr_nr = br_cntr_nr;
+		memcpy(bi->br_cntr, &br_cntr[offset * br_cntr_nr],
+		       br_cntr_nr * sizeof(u64));
+	}
+	bi->evsel = evsel;
 }
 
 int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
-			    u64 *block_cycles_aggr, u64 total_cycles)
+			    u64 *block_cycles_aggr, u64 total_cycles,
+			    unsigned int br_cntr_nr)
 {
 	struct annotation *notes;
 	struct cyc_hist *ch;
@@ -125,12 +150,14 @@ int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
 			struct block_info *bi;
 			struct hist_entry *he_block;
 
-			bi = block_info__new();
+			bi = block_info__new(br_cntr_nr);
 			if (!bi)
 				return -1;
 
 			init_block_info(bi, he->ms.sym, &ch[i], i,
-					total_cycles);
+					total_cycles, br_cntr_nr,
+					notes->branch->br_cntr,
+					hists_to_evsel(he->hists));
 			cycles += bi->cycles_aggr / bi->num_aggr;
 
 			he_block = hists__add_entry_block(&bh->block_hists,
@@ -327,6 +354,24 @@ static void init_block_header(struct block_fmt *block_fmt)
 	fmt->width = block_column_width;
 }
 
+static int block_branch_counter_entry(struct perf_hpp_fmt *fmt,
+				      struct perf_hpp *hpp,
+				      struct hist_entry *he)
+{
+	struct block_fmt *block_fmt = container_of(fmt, struct block_fmt, fmt);
+	struct block_info *bi = he->block_info;
+	char *buf;
+	int ret;
+
+	if (annotation_br_cntr_entry(&buf, bi->br_cntr_nr, bi->br_cntr,
+				     bi->num_aggr, bi->evsel))
+		return 0;
+
+	ret = scnprintf(hpp->buf, hpp->size, "%*s", block_fmt->width, buf);
+	free(buf);
+	return ret;
+}
+
 static void hpp_register(struct block_fmt *block_fmt, int idx,
 			 struct perf_hpp_list *hpp_list)
 {
@@ -357,6 +402,9 @@ static void hpp_register(struct block_fmt *block_fmt, int idx,
 	case PERF_HPP_REPORT__BLOCK_DSO:
 		fmt->entry = block_dso_entry;
 		break;
+	case PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER:
+		fmt->entry = block_branch_counter_entry;
+		break;
 	default:
 		return;
 	}
@@ -390,7 +438,7 @@ static void init_block_hist(struct block_hist *bh, struct block_fmt *block_fmts,
 static int process_block_report(struct hists *hists,
 				struct block_report *block_report,
 				u64 total_cycles, int *block_hpps,
-				int nr_hpps)
+				int nr_hpps, unsigned int br_cntr_nr)
 {
 	struct rb_node *next = rb_first_cached(&hists->entries);
 	struct block_hist *bh = &block_report->hist;
@@ -405,7 +453,7 @@ static int process_block_report(struct hists *hists,
 	while (next) {
 		he = rb_entry(next, struct hist_entry, rb_node);
 		block_info__process_sym(he, bh, &block_report->cycles,
-					total_cycles);
+					total_cycles, br_cntr_nr);
 		next = rb_next(&he->rb_node);
 	}
 
@@ -435,7 +483,7 @@ struct block_report *block_info__create_report(struct evlist *evlist,
 		struct hists *hists = evsel__hists(pos);
 
 		process_block_report(hists, &block_reports[i], total_cycles,
-				     block_hpps, nr_hpps);
+				     block_hpps, nr_hpps, evlist->nr_br_cntr);
 		i++;
 	}
 

tools/perf/util/block-info.h

@@ -18,6 +18,9 @@ struct block_info {
 	u64			total_cycles;
 	int			num;
 	int			num_aggr;
+	int			br_cntr_nr;
+	u64			*br_cntr;
+	struct evsel		*evsel;
 };
 
 struct block_fmt {
@@ -36,6 +39,7 @@ enum {
 	PERF_HPP_REPORT__BLOCK_AVG_CYCLES,
 	PERF_HPP_REPORT__BLOCK_RANGE,
 	PERF_HPP_REPORT__BLOCK_DSO,
+	PERF_HPP_REPORT__BLOCK_BRANCH_COUNTER,
 	PERF_HPP_REPORT__BLOCK_MAX_INDEX
 };
 
@@ -46,7 +50,6 @@ struct block_report {
 	int			nr_fmts;
 };
 
-struct block_info *block_info__new(void);
 void block_info__delete(struct block_info *bi);
 
 int64_t __block_info__cmp(struct hist_entry *left, struct hist_entry *right);
@@ -55,7 +58,8 @@ int64_t block_info__cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			struct hist_entry *left, struct hist_entry *right);
 
 int block_info__process_sym(struct hist_entry *he, struct block_hist *bh,
-			    u64 *block_cycles_aggr, u64 total_cycles);
+			    u64 *block_cycles_aggr, u64 total_cycles,
+			    unsigned int br_cntr_nr);
 
 struct block_report *block_info__create_report(struct evlist *evlist,
 					       u64 total_cycles,