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>

1 files changed, 57 insertions, 9 deletions

diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c
index 04068d48683f..649392bee7ed 100644
--- a/tools/perf/util/block-info.c
+++ b/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++;
 	}