perf stat: Delay metric parsing

Having metric parsing as part of argument processing causes issues as
flags like metric-no-group may be specified later. It also denies the
opportunity to optimize the events on SMT systems where fewer events
may be possible if we know the target is system-wide. Move metric
parsing to after command line option parsing. Because of how stat runs
this moves the parsing after record/report which fail to work with
metrics currently anyway.

Signed-off-by: Ian Rogers <[e-mail]>
Cc: Ahmad Yasin <[e-mail]>
Cc: Alexander Shishkin <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: Caleb Biggers <[e-mail]>
Cc: Florian Fischer <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: John Garry <[e-mail]>
Cc: Kan Liang <[e-mail]>
Cc: Kshipra Bopardikar <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Miaoqian Lin <[e-mail]>
Cc: Namhyung Kim <[e-mail]>
Cc: Perry Taylor <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Cc: Thomas Richter <[e-mail]>
Cc: Xing Zhengjun <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/builtin-stat.c

···
 static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
+static char			*metrics;
 
 struct perf_stat {
 	bool			 record;
···
 	return 0;
 }
 
-static int parse_metric_groups(const struct option *opt,
+static int append_metric_groups(const struct option *opt __maybe_unused,
 			       const char *str,
 			       int unset __maybe_unused)
 {
-	return metricgroup__parse_groups(opt, str,
-					 stat_config.metric_no_group,
-					 stat_config.metric_no_merge,
-					 &stat_config.metric_events);
+	if (metrics) {
+		char *tmp;
+
+		if (asprintf(&tmp, "%s,%s", metrics, str) < 0)
+			return -ENOMEM;
+		free(metrics);
+		metrics = tmp;
+	} else {
+		metrics = strdup(str);
+		if (!metrics)
+			return -ENOMEM;
+	}
+	return 0;
 }
 
 static int parse_control_option(const struct option *opt,
···
 			"measure SMI cost"),
 	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
 		     "monitor specified metrics or metric groups (separated by ,)",
-		     parse_metric_groups),
+		     append_metric_groups),
 	OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel,
 			 "Configure all used events to run in kernel space.",
 			 PARSE_OPT_EXCLUSIVE),
···
 		 * on an architecture test for such a metric name.
 		 */
 		if (metricgroup__has_metric("transaction")) {
-			struct option opt = { .value = &evsel_list };
-
-			return metricgroup__parse_groups(&opt, "transaction",
+			return metricgroup__parse_groups(evsel_list, "transaction",
 							 stat_config.metric_no_group,
-							stat_config.metric_no_merge,
+							 stat_config.metric_no_merge,
 							 &stat_config.metric_events);
 		}
 
···
 			input_name = "perf.data";
 	}
 
+	perf_stat__init_shadow_stats();
+
 	perf_stat.data.path = input_name;
 	perf_stat.data.mode = PERF_DATA_MODE_READ;
 
···
 	argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
-	perf_stat__collect_metric_expr(evsel_list);
-	perf_stat__init_shadow_stats();
 
 	if (stat_config.csv_sep) {
 		stat_config.csv_output = true;
···
 			target.system_wide = true;
 	}
 
+	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+		target.per_thread = true;
+
+	/*
+	 * Metric parsing needs to be delayed as metrics may optimize events
+	 * knowing the target is system-wide.
+	 */
+	if (metrics) {
+		metricgroup__parse_groups(evsel_list, metrics,
+					stat_config.metric_no_group,
+					stat_config.metric_no_merge,
+					&stat_config.metric_events);
+		zfree(&metrics);
+	}
+	perf_stat__collect_metric_expr(evsel_list);
+	perf_stat__init_shadow_stats();
+
 	if (add_default_attributes())
 		goto out;
 
···
 			goto out;
 		}
 	}
-
-	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
-		target.per_thread = true;
 
 	if (evlist__fix_hybrid_cpus(evsel_list, target.cpu_list)) {
 		pr_err("failed to use cpu list %s\n", target.cpu_list);

tools/perf/util/metricgroup.c

···
 	return ret;
 }
 
-int metricgroup__parse_groups(const struct option *opt,
+int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,
 			      struct rblist *metric_events)
 {
-	struct evlist *perf_evlist = *(struct evlist **)opt->value;
 	const struct pmu_events_table *table = pmu_events_table__find();
 
 	if (!table)

tools/perf/util/metricgroup.h

···
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
 					 struct evsel *evsel,
 					 bool create);
-int metricgroup__parse_groups(const struct option *opt,
+int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,