[PATCH v2 29/30] perf script: Display metrics for perf stat record data

[Ian Rogers <irogers@google.com>]

perf script displays the counts of each stat round read from a perf stat
record perf.data file. Also display, after each round, the metrics
requested on the perf stat record command line (or all matching metrics
when --all-metrics or stat.all-metrics=true is used), computed from the
counts aggregated across CPUs and threads, for example:

  $ perf stat record -M insn_per_cycle -a sleep 1
  $ perf script
  CPU THREAD         VAL         ENA         RUN        TIME EVENT
  ...
  cpu_atom/cpu-cycles/  metric:      0.7 instructions  insn_per_cycle
  cpu_core/cpu-cycles/  metric:      1.3 instructions  insn_per_cycle

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/Documentation/perf-script.txt |   6 ++
 tools/perf/builtin-script.c              | 107 ++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index f0228e784ced..bfd69d411996 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -468,6 +468,12 @@ include::itrace.txt[]
 	default behavior.  If you want to see separate CALLCHAIN_DEFERRED
 	records for some reason, use --no-merge-callchains explicitly.
 
+--all-metrics::
+	Display all metrics that match the recorded stat events in the perf data
+	file, rather than only the metrics requested on the 'perf stat record'
+	command line. Default setting can be changed with
+	"perf config stat.all-metrics=true".
+
 :GMEXAMPLECMD: script
 :GMEXAMPLESUBCMD:
 include::guest-files.txt[]
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index afed2353ef80..135ec34494bd 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2334,8 +2334,13 @@ static void script_print_metric(struct perf_stat_config *config __maybe_unused,
 
 	if (!fmt)
 		return;
-	perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel,
-				   PERF_RECORD_SAMPLE, mctx->fp);
+	if (mctx->sample) {
+		perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel,
+					   PERF_RECORD_SAMPLE, mctx->fp);
+	} else {
+		/* Metric computed from the counts of a perf stat record round. */
+		fputs(evsel__name(mctx->evsel), mctx->fp);
+	}
 	fputs("\tmetric: ", mctx->fp);
 	if (color)
 		color_fprintf(mctx->fp, color, fmt, val);
@@ -3795,26 +3800,112 @@ static void script__setup_sample_type(struct perf_script *script)
 	}
 }
 
+/*
+ * Set up the computation of metrics whose events were all recorded by perf stat
+ * record. Counts are aggregated globally for the metrics.
+ */
+static bool script_stat_metrics_init(struct evlist *evlist)
+{
+	struct perf_thread_map *threads = evlist__core(evlist)->threads;
+	struct evsel *counter;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (!counter->stats)
+			return false;
+	}
+	/* Metrics may use system_wide, such as for #target_cpu. */
+	stat_config.system_wide = !threads || perf_thread_map__nr(threads) < 1 ||
+				  perf_thread_map__pid(threads, /*idx=*/0) == -1;
+	metricgroup__add_recorded_metrics(evlist, /*metrics=*/NULL,
+					  /*pmu_filter=*/NULL,
+					  /*cputype_filter=*/false,
+					  stat_config.metric_no_group,
+					  stat_config.metric_no_merge,
+					  stat_config.metric_no_threshold,
+					  stat_config.all_metrics,
+					  stat_config.system_wide,
+					  /*default_metricgroup=*/false,
+					  /*metric_only=*/NULL);
+
+	if (rblist__empty(evlist__metric_events(evlist)))
+		return false;
+
+	if (!stat_config.aggr_map) {
+		stat_config.aggr_get_id = script_aggr_cpu_id_get;
+		stat_config.aggr_map =
+			cpu_aggr_map__new(evlist__core(evlist)->user_requested_cpus,
+					  aggr_cpu_id__global, /*data=*/NULL,
+					  /*needs_sort=*/false);
+		if (!stat_config.aggr_map)
+			return false;
+	}
+	/*
+	 * The aggregated stats may already have been allocated, with the
+	 * aggr_map, for metrics computed from samples.
+	 */
+	if (!evlist__first(evlist)->stats->aggr &&
+	    evlist__alloc_aggr_stats(evlist, stat_config.aggr_map->nr))
+		return false;
+
+	if (!stat_config.output)
+		stat_config.output = stdout;
+	stat_config.aggr_mode = AGGR_GLOBAL;
+	return true;
+}
+
+static void script_print_stat_metrics(struct evlist *evlist)
+{
+	struct evsel *counter;
+	int aggr_idx;
+
+	evlist__for_each_entry(evlist, counter) {
+		struct perf_stat_output_ctx ctx = {
+			.print_metric = script_print_metric,
+			.new_line = script_new_line,
+			.ctx = &(struct metric_ctx) {
+				.evsel = counter,
+				.fp = stdout,
+			},
+			.force_header = false,
+		};
+
+		cpu_aggr_map__for_each_idx(aggr_idx, stat_config.aggr_map)
+			perf_stat__print_shadow_stats(&stat_config, counter, aggr_idx, &ctx);
+	}
+}
+
 static int process_stat_round_event(const struct perf_tool *tool __maybe_unused,
 				    struct perf_session *session,
 				    union perf_event *event)
 {
 	struct perf_record_stat_round *round = &event->stat_round;
 	struct evsel *counter;
+	static int show_metrics = -1;
+
+	if (show_metrics < 0)
+		show_metrics = script_stat_metrics_init(session->evlist) ? 1 : 0;
+
+	if (show_metrics)
+		evlist__reset_aggr_stats(session->evlist);
 
 	evlist__for_each_entry(session->evlist, counter) {
 		perf_stat_process_counter(&stat_config, counter);
 		process_stat(counter, round->time);
 	}
 
+	if (show_metrics)
+		script_print_stat_metrics(session->evlist);
+
 	process_stat_interval(round->time);
 	return 0;
 }
 
 static int process_stat_config_event(const struct perf_tool *tool __maybe_unused,
-				     struct perf_session *session __maybe_unused,
+				     struct perf_session *session,
 				     union perf_event *event)
 {
+	struct evsel *counter;
+
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
 	/*
@@ -3823,6 +3914,13 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused
 	 */
 	stat_config.aggr_mode = AGGR_NONE;
 
+	/*
+	 * Mark counters unsupported until a PERF_RECORD_STAT event is
+	 * processed for them by perf_event__process_stat_event().
+	 */
+	evlist__for_each_entry(session->evlist, counter)
+		counter->supported = false;
+
 	return 0;
 }
 
@@ -4206,6 +4304,8 @@ int cmd_script(int argc, const char **argv)
 		    "Enable LBR callgraph stitching approach"),
 	OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains,
 		    "Enable merge deferred user callchains"),
+	OPT_BOOLEAN(0, "all-metrics", &stat_config.all_metrics,
+		    "Display all metrics matching recorded stat events"),
 	OPTS_EVSWITCH(&script.evswitch),
 	OPT_END()
 	};
@@ -4577,6 +4677,7 @@ int cmd_script(int argc, const char **argv)
 
 	zstd_fini(&(session->zstd_data));
 	evlist__free_stats(session->evlist);
+	zfree(&stat_config.aggr_map);
 	perf_session__delete(session);
 	perf_script__exit(&script);
 
-- 
2.56.1.703.gf848ed807c-goog