perf metrics: Wire up core_wide

Pass state necessary for core_wide into the expression parser. Add
system_wide and user_requested_cpu_list to perf_stat_config to make it
available at display time. evlist isn't used as the
evlist__create_maps, that computes user_requested_cpus, needs the list
of events which is generated by the metric.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Ahmad Yasin <ahmad.yasin@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: Florian Fischer <florian.fischer@muhq.space>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Miaoqian Lin <linmq006@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20220831174926.579643-7-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -1805,6 +1805,8 @@ static int add_default_attributes(void)
 			return metricgroup__parse_groups(evsel_list, "transaction",
 							 stat_config.metric_no_group,
 							 stat_config.metric_no_merge,
+							 stat_config.user_requested_cpu_list,
+							 stat_config.system_wide,
 							 &stat_config.metric_events);
 		}
 
@@ -2441,6 +2443,15 @@ int cmd_stat(int argc, const char **argv)
 	if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
 		target.per_thread = true;
 
+	stat_config.system_wide = target.system_wide;
+	if (target.cpu_list) {
+		stat_config.user_requested_cpu_list = strdup(target.cpu_list);
+		if (!stat_config.user_requested_cpu_list) {
+			status = -ENOMEM;
+			goto out;
+		}
+	}
+
 	/*
 	 * Metric parsing needs to be delayed as metrics may optimize events
 	 * knowing the target is system-wide.
@@ -2449,6 +2460,8 @@ int cmd_stat(int argc, const char **argv)
 		metricgroup__parse_groups(evsel_list, metrics,
 					stat_config.metric_no_group,
 					stat_config.metric_no_merge,
+					stat_config.user_requested_cpu_list,
+					stat_config.system_wide,
 					&stat_config.metric_events);
 		zfree(&metrics);
 	}
@@ -2639,6 +2652,7 @@ out:
 		iostat_release(evsel_list);
 
 	zfree(&stat_config.walltime_run);
+	zfree(&stat_config.user_requested_cpu_list);
 
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);

tools/perf/util/expr.c

@@ -310,7 +310,9 @@ struct expr_parse_ctx *expr__ctx_new(void)
 		free(ctx);
 		return NULL;
 	}
+	ctx->sctx.user_requested_cpu_list = NULL;
 	ctx->sctx.runtime = 0;
+	ctx->sctx.system_wide = false;
 
 	return ctx;
 }
@@ -332,6 +334,10 @@ void expr__ctx_free(struct expr_parse_ctx *ctx)
 	struct hashmap_entry *cur;
 	size_t bkt;
 
+	if (!ctx)
+		return;
+
+	free(ctx->sctx.user_requested_cpu_list);
 	hashmap__for_each_entry(ctx->ids, cur, bkt) {
 		free((char *)cur->key);
 		free(cur->value);
@@ -407,7 +413,7 @@ double arch_get_tsc_freq(void)
 }
 #endif
 
-double expr__get_literal(const char *literal)
+double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx)
 {
 	static struct cpu_topology *topology;
 	double result = NAN;
@@ -439,6 +445,11 @@ double expr__get_literal(const char *literal)
 		result = smt_on(topology) ? 1.0 : 0.0;
 		goto out;
 	}
+	if (!strcmp("#core_wide", literal)) {
+		result = core_wide(ctx->system_wide, ctx->user_requested_cpu_list, topology)
+			? 1.0 : 0.0;
+		goto out;
+	}
 	if (!strcmp("#num_packages", literal)) {
 		result = topology->package_cpus_lists;
 		goto out;

tools/perf/util/expr.h

@@ -11,7 +11,9 @@
 struct metric_ref;
 
 struct expr_scanner_ctx {
+	char *user_requested_cpu_list;
 	int runtime;
+	bool system_wide;
 };
 
 struct expr_parse_ctx {
@@ -55,6 +57,6 @@ int expr__find_ids(const char *expr, const char *one,
 
 double expr_id_data__value(const struct expr_id_data *data);
 double expr_id_data__source_count(const struct expr_id_data *data);
-double expr__get_literal(const char *literal);
+double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
 
 #endif

tools/perf/util/expr.l

@@ -79,11 +79,11 @@ static int str(yyscan_t scanner, int token, int runtime)
 	return token;
 }
 
-static int literal(yyscan_t scanner)
+static int literal(yyscan_t scanner, const struct expr_scanner_ctx *sctx)
 {
 	YYSTYPE *yylval = expr_get_lval(scanner);
 
-	yylval->num = expr__get_literal(expr_get_text(scanner));
+	yylval->num = expr__get_literal(expr_get_text(scanner), sctx);
 	if (isnan(yylval->num))
 		return EXPR_ERROR;
 
@@ -108,7 +108,7 @@ min		{ return MIN; }
 if		{ return IF; }
 else		{ return ELSE; }
 source_count	{ return SOURCE_COUNT; }
-{literal}	{ return literal(yyscanner); }
+{literal}	{ return literal(yyscanner, sctx); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }
 "|"		{ return '|'; }

tools/perf/util/metricgroup.c

@@ -22,6 +22,7 @@
 #include <linux/list_sort.h>
 #include <linux/string.h>
 #include <linux/zalloc.h>
+#include <perf/cpumap.h>
 #include <subcmd/parse-options.h>
 #include <api/fs/fs.h>
 #include "util.h"
@@ -189,10 +190,24 @@ static bool metricgroup__has_constraint(const struct pmu_event *pe)
 	return false;
 }
 
+static void metric__free(struct metric *m)
+{
+	if (!m)
+		return;
+
+	free(m->metric_refs);
+	expr__ctx_free(m->pctx);
+	free((char *)m->modifier);
+	evlist__delete(m->evlist);
+	free(m);
+}
+
 static struct metric *metric__new(const struct pmu_event *pe,
 				  const char *modifier,
 				  bool metric_no_group,
-				  int runtime)
+				  int runtime,
+				  const char *user_requested_cpu_list,
+				  bool system_wide)
 {
 	struct metric *m;
 
@@ -201,35 +216,34 @@ static struct metric *metric__new(const struct pmu_event *pe,
 		return NULL;
 
 	m->pctx = expr__ctx_new();
-	if (!m->pctx) {
+	if (!m->pctx)
-		free(m);
+		goto out_err;
-		return NULL;
-	}
 
 	m->metric_name = pe->metric_name;
-	m->modifier = modifier ? strdup(modifier) : NULL;
+	m->modifier = NULL;
-	if (modifier && !m->modifier) {
+	if (modifier) {
-		expr__ctx_free(m->pctx);
+		m->modifier = strdup(modifier);
-		free(m);
+		if (!m->modifier)
-		return NULL;
+			goto out_err;
 	}
 	m->metric_expr = pe->metric_expr;
 	m->metric_unit = pe->unit;
+	m->pctx->sctx.user_requested_cpu_list = NULL;
+	if (user_requested_cpu_list) {
+		m->pctx->sctx.user_requested_cpu_list = strdup(user_requested_cpu_list);
+		if (!m->pctx->sctx.user_requested_cpu_list)
+			goto out_err;
+	}
 	m->pctx->sctx.runtime = runtime;
+	m->pctx->sctx.system_wide = system_wide;
 	m->has_constraint = metric_no_group || metricgroup__has_constraint(pe);
 	m->metric_refs = NULL;
 	m->evlist = NULL;
 
 	return m;
-}
+out_err:
-
+	metric__free(m);
-static void metric__free(struct metric *m)
+	return NULL;
-{
-	free(m->metric_refs);
-	expr__ctx_free(m->pctx);
-	free((char *)m->modifier);
-	evlist__delete(m->evlist);
-	free(m);
 }
 
 static bool contains_metric_id(struct evsel **metric_events, int num_events,
@@ -874,6 +888,8 @@ struct metricgroup_add_iter_data {
 	int *ret;
 	bool *has_match;
 	bool metric_no_group;
+	const char *user_requested_cpu_list;
+	bool system_wide;
 	struct metric *root_metric;
 	const struct visited_metric *visited;
 	const struct pmu_events_table *table;
@@ -887,6 +903,8 @@ static int add_metric(struct list_head *metric_list,
 		      const struct pmu_event *pe,
 		      const char *modifier,
 		      bool metric_no_group,
+		      const char *user_requested_cpu_list,
+		      bool system_wide,
 		      struct metric *root_metric,
 		      const struct visited_metric *visited,
 		      const struct pmu_events_table *table);
@@ -899,6 +917,8 @@ static int add_metric(struct list_head *metric_list,
  * @metric_no_group: Should events written to events be grouped "{}" or
  *                   global. Grouping is the default but due to multiplexing the
  *                   user may override.
+ * @user_requested_cpu_list: Command line specified CPUs to record on.
+ * @system_wide: Are events for all processes recorded.
  * @root_metric: Metrics may reference other metrics to form a tree. In this
  *               case the root_metric holds all the IDs and a list of referenced
  *               metrics. When adding a root this argument is NULL.
@@ -910,6 +930,8 @@ static int add_metric(struct list_head *metric_list,
 static int resolve_metric(struct list_head *metric_list,
 			  const char *modifier,
 			  bool metric_no_group,
+			  const char *user_requested_cpu_list,
+			  bool system_wide,
 			  struct metric *root_metric,
 			  const struct visited_metric *visited,
 			  const struct pmu_events_table *table)
@@ -956,7 +978,8 @@ static int resolve_metric(struct list_head *metric_list,
 	 */
 	for (i = 0; i < pending_cnt; i++) {
 		ret = add_metric(metric_list, &pending[i].pe, modifier, metric_no_group,
-				root_metric, visited, table);
+				 user_requested_cpu_list, system_wide, root_metric, visited,
+				 table);
 		if (ret)
 			break;
 	}
@@ -974,6 +997,8 @@ static int resolve_metric(struct list_head *metric_list,
  *                   global. Grouping is the default but due to multiplexing the
  *                   user may override.
  * @runtime: A special argument for the parser only known at runtime.
+ * @user_requested_cpu_list: Command line specified CPUs to record on.
+ * @system_wide: Are events for all processes recorded.
  * @root_metric: Metrics may reference other metrics to form a tree. In this
  *               case the root_metric holds all the IDs and a list of referenced
  *               metrics. When adding a root this argument is NULL.
@@ -987,6 +1012,8 @@ static int __add_metric(struct list_head *metric_list,
 			const char *modifier,
 			bool metric_no_group,
 			int runtime,
+			const char *user_requested_cpu_list,
+			bool system_wide,
 			struct metric *root_metric,
 			const struct visited_metric *visited,
 			const struct pmu_events_table *table)
@@ -1011,7 +1038,8 @@ static int __add_metric(struct list_head *metric_list,
 		 * This metric is the root of a tree and may reference other
 		 * metrics that are added recursively.
 		 */
-		root_metric = metric__new(pe, modifier, metric_no_group, runtime);
+		root_metric = metric__new(pe, modifier, metric_no_group, runtime,
+					  user_requested_cpu_list, system_wide);
 		if (!root_metric)
 			return -ENOMEM;
 
@@ -1060,8 +1088,9 @@ static int __add_metric(struct list_head *metric_list,
 		ret = -EINVAL;
 	} else {
 		/* Resolve referenced metrics. */
-		ret = resolve_metric(metric_list, modifier, metric_no_group, root_metric,
+		ret = resolve_metric(metric_list, modifier, metric_no_group,
-				     &visited_node, table);
+				     user_requested_cpu_list, system_wide,
+				     root_metric, &visited_node, table);
 	}
 
 	if (ret) {
@@ -1109,6 +1138,8 @@ static int add_metric(struct list_head *metric_list,
 		      const struct pmu_event *pe,
 		      const char *modifier,
 		      bool metric_no_group,
+		      const char *user_requested_cpu_list,
+		      bool system_wide,
 		      struct metric *root_metric,
 		      const struct visited_metric *visited,
 		      const struct pmu_events_table *table)
@@ -1119,7 +1150,8 @@ static int add_metric(struct list_head *metric_list,
 
 	if (!strstr(pe->metric_expr, "?")) {
 		ret = __add_metric(metric_list, pe, modifier, metric_no_group, 0,
-				   root_metric, visited, table);
+				   user_requested_cpu_list, system_wide, root_metric,
+				   visited, table);
 	} else {
 		int j, count;
 
@@ -1132,7 +1164,8 @@ static int add_metric(struct list_head *metric_list,
 
 		for (j = 0; j < count && !ret; j++)
 			ret = __add_metric(metric_list, pe, modifier, metric_no_group, j,
-					root_metric, visited, table);
+					   user_requested_cpu_list, system_wide,
+					   root_metric, visited, table);
 	}
 
 	return ret;
@@ -1149,6 +1182,7 @@ static int metricgroup__add_metric_sys_event_iter(const struct pmu_event *pe,
 		return 0;
 
 	ret = add_metric(d->metric_list, pe, d->modifier, d->metric_no_group,
+			 d->user_requested_cpu_list, d->system_wide,
 			 d->root_metric, d->visited, d->table);
 	if (ret)
 		goto out;
@@ -1191,7 +1225,9 @@ struct metricgroup__add_metric_data {
 	struct list_head *list;
 	const char *metric_name;
 	const char *modifier;
+	const char *user_requested_cpu_list;
 	bool metric_no_group;
+	bool system_wide;
 	bool has_match;
 };
 
@@ -1208,8 +1244,8 @@ static int metricgroup__add_metric_callback(const struct pmu_event *pe,
 
 		data->has_match = true;
 		ret = add_metric(data->list, pe, data->modifier, data->metric_no_group,
-				 /*root_metric=*/NULL,
+				 data->user_requested_cpu_list, data->system_wide,
-				 /*visited_metrics=*/NULL, table);
+				 /*root_metric=*/NULL, /*visited_metrics=*/NULL, table);
 	}
 	return ret;
 }
@@ -1223,12 +1259,16 @@ static int metricgroup__add_metric_callback(const struct pmu_event *pe,
  * @metric_no_group: Should events written to events be grouped "{}" or
  *                   global. Grouping is the default but due to multiplexing the
  *                   user may override.
+ * @user_requested_cpu_list: Command line specified CPUs to record on.
+ * @system_wide: Are events for all processes recorded.
  * @metric_list: The list that the metric or metric group are added to.
  * @table: The table that is searched for metrics, most commonly the table for the
  *       architecture perf is running upon.
  */
 static int metricgroup__add_metric(const char *metric_name, const char *modifier,
 				   bool metric_no_group,
+				   const char *user_requested_cpu_list,
+				   bool system_wide,
 				   struct list_head *metric_list,
 				   const struct pmu_events_table *table)
 {
@@ -1242,6 +1282,8 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier
 			.metric_name = metric_name,
 			.modifier = modifier,
 			.metric_no_group = metric_no_group,
+			.user_requested_cpu_list = user_requested_cpu_list,
+			.system_wide = system_wide,
 			.has_match = false,
 		};
 		/*
@@ -1263,6 +1305,8 @@ static int metricgroup__add_metric(const char *metric_name, const char *modifier
 				.metric_name = metric_name,
 				.modifier = modifier,
 				.metric_no_group = metric_no_group,
+				.user_requested_cpu_list = user_requested_cpu_list,
+				.system_wide = system_wide,
 				.has_match = &has_match,
 				.ret = &ret,
 				.table = table,
@@ -1293,12 +1337,15 @@ out:
  * @metric_no_group: Should events written to events be grouped "{}" or
  *                   global. Grouping is the default but due to multiplexing the
  *                   user may override.
+ * @user_requested_cpu_list: Command line specified CPUs to record on.
+ * @system_wide: Are events for all processes recorded.
  * @metric_list: The list that metrics are added to.
  * @table: The table that is searched for metrics, most commonly the table for the
  *       architecture perf is running upon.
  */
 static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
-					struct list_head *metric_list,
+					const char *user_requested_cpu_list,
+					bool system_wide, struct list_head *metric_list,
 					const struct pmu_events_table *table)
 {
 	char *list_itr, *list_copy, *metric_name, *modifier;
@@ -1315,8 +1362,8 @@ static int metricgroup__add_metric_list(const char *list, bool metric_no_group,
 			*modifier++ = '\0';
 
 		ret = metricgroup__add_metric(metric_name, modifier,
-					      metric_no_group, metric_list,
+					      metric_no_group, user_requested_cpu_list,
-					      table);
+					      system_wide, metric_list, table);
 		if (ret == -EINVAL)
 			pr_err("Cannot find metric or group `%s'\n", metric_name);
 
@@ -1505,6 +1552,8 @@ err_out:
 static int parse_groups(struct evlist *perf_evlist, const char *str,
 			bool metric_no_group,
 			bool metric_no_merge,
+			const char *user_requested_cpu_list,
+			bool system_wide,
 			struct perf_pmu *fake_pmu,
 			struct rblist *metric_events_list,
 			const struct pmu_events_table *table)
@@ -1518,7 +1567,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 	if (metric_events_list->nr_entries == 0)
 		metricgroup__rblist_init(metric_events_list);
 	ret = metricgroup__add_metric_list(str, metric_no_group,
-					   &metric_list, table);
+					   user_requested_cpu_list,
+					   system_wide, &metric_list, table);
 	if (ret)
 		goto out;
 
@@ -1650,6 +1700,8 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,
+			      const char *user_requested_cpu_list,
+			      bool system_wide,
 			      struct rblist *metric_events)
 {
 	const struct pmu_events_table *table = pmu_events_table__find();
@@ -1657,8 +1709,9 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 	if (!table)
 		return -EINVAL;
 
-	return parse_groups(perf_evlist, str, metric_no_group,
+	return parse_groups(perf_evlist, str, metric_no_group, metric_no_merge,
-			    metric_no_merge, NULL, metric_events, table);
+			    user_requested_cpu_list, system_wide,
+			    /*fake_pmu=*/NULL, metric_events, table);
 }
 
 int metricgroup__parse_groups_test(struct evlist *evlist,
@@ -1668,8 +1721,10 @@ int metricgroup__parse_groups_test(struct evlist *evlist,
 				   bool metric_no_merge,
 				   struct rblist *metric_events)
 {
-	return parse_groups(evlist, str, metric_no_group,
+	return parse_groups(evlist, str, metric_no_group, metric_no_merge,
-			    metric_no_merge, &perf_pmu__fake, metric_events, table);
+			    /*user_requested_cpu_list=*/NULL,
+			    /*system_wide=*/false,
+			    &perf_pmu__fake, metric_events, table);
 }
 
 static int metricgroup__has_metric_callback(const struct pmu_event *pe,

tools/perf/util/metricgroup.h

@@ -68,6 +68,8 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      const char *str,
 			      bool metric_no_group,
 			      bool metric_no_merge,
+			      const char *user_requested_cpu_list,
+			      bool system_wide,
 			      struct rblist *metric_events);
 int metricgroup__parse_groups_test(struct evlist *evlist,
 				   const struct pmu_events_table *table,

tools/perf/util/stat-shadow.c

@@ -911,7 +911,10 @@ static void generic_metric(struct perf_stat_config *config,
 	if (!pctx)
 		return;
 
+	if (config->user_requested_cpu_list)
+		pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list);
 	pctx->sctx.runtime = runtime;
+	pctx->sctx.system_wide = config->system_wide;
 	i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st);
 	if (i < 0) {
 		expr__ctx_free(pctx);
@@ -1304,7 +1307,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
-				evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st);
+			       evsel->name, evsel->metric_name, NULL, 1,
+			       cpu_map_idx, out, st);
 	} else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) {
 		char unit = ' ';
 		char unit_buf[10] = "/sec";
@@ -1329,8 +1333,9 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			if (num++ > 0)
 				out->new_line(config, ctxp);
 			generic_metric(config, mexp->metric_expr, mexp->metric_events,
-					mexp->metric_refs, evsel->name, mexp->metric_name,
+				       mexp->metric_refs, evsel->name, mexp->metric_name,
-					mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st);
+				       mexp->metric_unit, mexp->runtime,
+				       cpu_map_idx, out, st);
 		}
 	}
 	if (num == 0)

tools/perf/util/stat.h

@@ -141,6 +141,8 @@ struct perf_stat_config {
 	bool			 stop_read_counter;
 	bool			 quiet;
 	bool			 iostat_run;
+	char			 *user_requested_cpu_list;
+	bool			 system_wide;
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;