[PATCH v1 12/15] perf, tools, stat: Support JSON metrics in perf stat

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Add generic support for standalone metrics specified in JSON files
to perf stat. A metric is a formula that uses multiple events
to compute a higher level result (e.g. IPC).

Previously metrics were always tied to an event and automatically
enabled with that event. But now change it that we can have
standalone metrics. They are in the same JSON data structure
as events, but don't have an event name.

We also allow to organize the metrics in metric groups, which
allows a short cut to select several related metrics at once.

Add a new -M / --metrics option to perf stat that adds the metrics
or metric groups specified.

Add the core code to manage and parse the metric groups. They
are collected from the JSON data structures into a separate rblist.
When computing shadow values look for metrics in that list.
Then they are computed using the existing saved values infrastructure
in stat-shadow.c

The actual JSON metrics are in a separate pull request.

% perf stat -M Summary --metric-only -a sleep 1

 Performance counter stats for 'system wide':

Instructions                              CLKS                 CPU_Utilization      GFLOPs               SMT_2T_Utilization   Kernel_Utilization
317614222.0                              1392930775.0             0.0                 0.0                 0.2                 0.1

       1.001497549 seconds time elapsed

% perf stat -M GFLOPs flops

 Performance counter stats for 'flops':

     3,999,541,471      fp_comp_ops_exe.sse_scalar_single #      1.2 GFLOPs                   (66.65%)
                14      fp_comp_ops_exe.sse_scalar_double                                     (66.65%)
                 0      fp_comp_ops_exe.sse_packed_double                                     (66.67%)
                 0      fp_comp_ops_exe.sse_packed_single                                     (66.70%)
                 0      simd_fp_256.packed_double                                     (66.70%)
                 0      simd_fp_256.packed_single                                     (66.67%)
                 0      duration_time

       3.238372845 seconds time elapsed

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 tools/perf/Documentation/perf-stat.txt |   7 +
 tools/perf/builtin-stat.c              |  18 +-
 tools/perf/util/Build                  |   1 +
 tools/perf/util/metricgroup.c          | 334 +++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.c                  |  31 +--
 tools/perf/util/pmu.h                  |   2 +
 tools/perf/util/stat-shadow.c          |  22 ++-
 tools/perf/util/stat.h                 |   4 +-
 8 files changed, 403 insertions(+), 16 deletions(-)
 create mode 100644 tools/perf/util/metricgroup.c

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 698076313606..be8935717678 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -199,6 +199,13 @@ Aggregate counts per processor socket for system-wide mode measurements.
 --per-core::
 Aggregate counts per physical processor for system-wide mode measurements.
 
+-M::
+--metrics::
+Print metrics or metricgroups specified in a comma separated list.
+For a group all metrics from the group are added.
+The events from the metrics are automatically measured.
+See perf list output for the possble metrics and metricgroups.
+
 -A::
 --no-aggr::
 Do not aggregate counts across all monitored CPUs.
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 551ed938e05c..0dccae290b88 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
 #include "util/tool.h"
 #include "util/group.h"
 #include "util/string2.h"
+#include "util/metricgroup.h"
 #include "asm/bug.h"
 
 #include <linux/time64.h>
@@ -133,6 +134,8 @@ static const char *smi_cost_attrs = {
 
 static struct perf_evlist	*evsel_list;
 
+static struct rblist		 metric_events;
+
 static struct target target = {
 	.uid	= UINT_MAX,
 };
@@ -1203,7 +1206,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 
 	perf_stat__print_shadow_stats(counter, uval,
 				first_shadow_cpu(counter, id),
-				&out);
+				&out, &metric_events);
 	if (!csv_output && !metric_only) {
 		print_noise(counter, noise);
 		print_running(run, ena);
@@ -1534,7 +1537,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
-					      &out);
+					      &out,
+					      &metric_events);
 	}
 	fputc('\n', stat_config.output);
 }
@@ -1758,6 +1762,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static int parse_metric_groups(const struct option *opt,
+			       const char *str,
+			       int unset __maybe_unused)
+{
+	return metricgroup__parse_groups(opt, str, &metric_events);
+}
+
 static const struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1823,6 +1834,9 @@ static const struct option stat_options[] = {
 			"measure topdown level 1 statistics"),
 	OPT_BOOLEAN(0, "smi-cost", &smi_cost,
 			"measure SMI cost"),
+	OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
+		     "monitor specified metrics or metric groups (separated by ,)",
+		     parse_metric_groups),
 	OPT_END()
 };
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 94518c1bf8b6..71ab8466714d 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -34,6 +34,7 @@ libperf-y += dso.o
 libperf-y += symbol.o
 libperf-y += symbol_fprintf.o
 libperf-y += color.o
+libperf-y += metricgroup.o
 libperf-y += header.o
 libperf-y += callchain.o
 libperf-y += values.o
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
new file mode 100644
index 000000000000..6c1137125904
--- /dev/null
+++ b/tools/perf/util/metricgroup.c
@@ -0,0 +1,334 @@
+/*
+ * Copyright (c) 2017, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+/* Manage metrics and groups of metrics from JSON files */
+
+#include "metricgroup.h"
+#include "evlist.h"
+#include "strbuf.h"
+#include "pmu.h"
+#include "expr.h"
+#include "rblist.h"
+#include "pmu.h"
+#include <string.h>
+#include <stdbool.h>
+#include <errno.h>
+#include "pmu-events/pmu-events.h"
+#include "strbuf.h"
+#include "strlist.h"
+#include <assert.h>
+#include <ctype.h>
+
+struct metric_event *metricgroup__lookup(struct rblist *metric_events,
+					 struct perf_evsel *evsel,
+					 bool create)
+{
+	struct rb_node *nd;
+	struct metric_event me = {
+		.evsel = evsel
+	};
+	nd = rblist__find(metric_events, &me);
+	if (nd)
+		return container_of(nd, struct metric_event, nd);
+	if (create) {
+		rblist__add_node(metric_events, &me);
+		nd = rblist__find(metric_events, &me);
+		if (nd)
+			return container_of(nd, struct metric_event, nd);
+	}
+	return NULL;
+}
+
+static int metric_event_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct metric_event *a = container_of(rb_node,
+					      struct metric_event,
+					      nd);
+	const struct metric_event *b = entry;
+
+	if (a->evsel == b->evsel)
+		return 0;
+	if ((char *)a->evsel < (char *)b->evsel)
+		return -1;
+	return +1;
+}
+
+static struct rb_node *metric_event_new(struct rblist *rblist __maybe_unused,
+					const void *entry)
+{
+	struct metric_event *me = malloc(sizeof(struct metric_event));
+
+	if (!me)
+		return NULL;
+	memcpy(me, entry, sizeof(struct metric_event));
+	me->evsel = ((struct metric_event *)entry)->evsel;
+	INIT_LIST_HEAD(&me->head);
+	return &me->nd;
+}
+
+static void metricgroup__rblist_init(struct rblist *metric_events)
+{
+	rblist__init(metric_events);
+	metric_events->node_cmp = metric_event_cmp;
+	metric_events->node_new = metric_event_new;
+}
+
+struct egroup {
+	struct list_head nd;
+	int idnum;
+	const char **ids;
+	const char *metric_name;
+	const char *metric_expr;
+};
+
+static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
+				     const char **ids,
+				     int idnum,
+				     struct perf_evsel **metric_events)
+{
+	struct perf_evsel *ev, *start = NULL;
+	int ind = 0;
+
+	evlist__for_each_entry (perf_evlist, ev) {
+		if (!strcmp(ev->name, ids[ind])) {
+			metric_events[ind] = ev;
+			if (ind == 0)
+				start = ev;
+			if (++ind == idnum) {
+				metric_events[ind] = NULL;
+				return start;
+			}
+		} else {
+			ind = 0;
+			start = NULL;
+		}
+	}
+	/*
+	 * This can happen when an alias expands to multiple
+	 * events, like for uncore events.
+	 * We don't support this case for now.
+	 */
+	return NULL;
+}
+
+static int metricgroup__setup_events(struct list_head *groups,
+				     struct perf_evlist *perf_evlist,
+				     struct rblist *metric_events_list)
+{
+	struct metric_event *me;
+	struct metric_expr *expr;
+	int i = 0;
+	int ret = 0;
+	struct egroup *eg;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry (eg, groups, nd) {
+		struct perf_evsel **metric_events;
+
+		metric_events = calloc(sizeof(void *), eg->idnum + 1);
+		if (!metric_events) {
+			ret = -ENOMEM;
+			break;
+		}
+		evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
+				   metric_events);
+		if (!evsel) {
+			pr_debug("Cannot resolve %s: %s\n",
+					eg->metric_name, eg->metric_expr);
+			continue;
+		}
+		for (i = 0; i < eg->idnum; i++)
+			metric_events[i]->collect_stat = true;
+		me = metricgroup__lookup(metric_events_list, evsel, true);
+		if (!me) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr = malloc(sizeof(struct metric_expr));
+		if (!expr) {
+			ret = -ENOMEM;
+			break;
+		}
+		expr->metric_expr = eg->metric_expr;
+		expr->metric_name = eg->metric_name;
+		expr->metric_events = metric_events;
+		list_add(&expr->nd, &me->head);
+	}
+	return ret;
+}
+
+static bool match_metric(const char *n, const char *list)
+{
+	int len;
+	char *m;
+
+	if (!list)
+		return false;
+	if (!strcmp(list, "all"))
+		return true;
+	if (!n)
+		return !strcasecmp(list, "No_group");
+	len = strlen(list);
+	m = strcasestr(n, list);
+	if (!m)
+		return false;
+	if ((m == n || m[-1] == ';' || m[-1] == ' ') &&
+	    (m[len] == 0 || m[len] == ';'))
+		return true;
+	return false;
+}
+
+static struct pmu_events_map *find_map(void)
+{
+	struct pmu_events_map *map;
+	char *cpuid = perf_pmu__getcpuid();
+	int i;
+
+	i = 0;
+	for (;;) {
+		map = &pmu_events_map[i++];
+		if (!map->table) {
+			map = NULL;
+			break;
+		}
+
+		if (!strcmp(map->cpuid, cpuid))
+			break;
+	}
+	free(cpuid);
+	return map;
+}
+
+static int metricgroup__add_metric(const char *metric, struct strbuf *events,
+				   struct list_head *group_list)
+{
+	struct pmu_events_map *map = find_map();
+	struct pmu_event *pe;
+	int ret = -EINVAL;
+	int i, j;
+
+	strbuf_init(events, 100);
+	strbuf_addf(events, "%s", "");
+
+	if (!map)
+		return 0;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_group, metric) ||
+		    match_metric(pe->metric_name, metric)) {
+			const char **ids;
+			int idnum;
+			struct egroup *eg;
+
+			pr_debug("metric expr %s for %s\n", pe->metric_expr, pe->metric_name);
+
+			if (expr__find_other(pe->metric_expr,
+					     NULL, &ids, &idnum) < 0)
+				continue;
+			if (events->len > 0)
+				strbuf_addf(events, ",");
+			for (j = 0; j < idnum; j++) {
+				pr_debug("found event %s\n", ids[j]);
+				strbuf_addf(events, "%s%s",
+					j == 0 ? "{" : ",",
+					ids[j]);
+			}
+			strbuf_addf(events, "}:W");
+
+			eg = malloc(sizeof(struct egroup));
+			if (!eg) {
+				ret = -ENOMEM;
+				break;
+			}
+			eg->ids = ids;
+			eg->idnum = idnum;
+			eg->metric_name = pe->metric_name;
+			eg->metric_expr = pe->metric_expr;
+			list_add_tail(&eg->nd, group_list);
+			ret = 0;
+		}
+	}
+	return ret;
+}
+
+static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
+				        struct list_head *group_list)
+{
+	char *llist, *nlist, *p;
+	int ret = -EINVAL;
+
+	nlist = strdup(list);
+	if (!nlist)
+		return -ENOMEM;
+	llist = nlist;
+	while ((p = strsep(&llist, ",")) != NULL) {
+		ret = metricgroup__add_metric(p, events, group_list);
+		if (ret == -EINVAL) {
+			fprintf(stderr, "Cannot find metric or group `%s'\n",
+					p);
+			break;
+		}
+	}
+	free(nlist);
+	return ret;
+}
+
+static void metricgroup__free_egroups(struct list_head *group_list)
+{
+	struct egroup *eg, *egtmp;
+	int i;
+
+	list_for_each_entry_safe (eg, egtmp, group_list, nd) {
+		for (i = 0; i < eg->idnum; i++)
+			free((char *)eg->ids[i]);
+		free(eg->ids);
+		free(eg);
+	}
+}
+
+int metricgroup__parse_groups(const struct option *opt,
+			   const char *str,
+			   struct rblist *metric_events)
+{
+	struct parse_events_error parse_error;
+	struct perf_evlist *perf_evlist = *(struct perf_evlist **)opt->value;
+	struct strbuf extra_events;
+	LIST_HEAD(group_list);
+	int ret;
+
+	if (metric_events->nr_entries == 0)
+		metricgroup__rblist_init(metric_events);
+	ret = metricgroup__add_metric_list(str, &extra_events, &group_list);
+	if (ret)
+		return ret;
+	pr_debug("adding %s\n", extra_events.buf);
+	memset(&parse_error, 0, sizeof(struct parse_events_error));
+	ret = parse_events(perf_evlist, extra_events.buf, &parse_error);
+	if (ret) {
+		pr_err("Cannot set up events %s\n", extra_events.buf);
+		goto out;
+	}
+	strbuf_release(&extra_events);
+	ret = metricgroup__setup_events(&group_list, perf_evlist,
+					metric_events);
+out:
+	metricgroup__free_egroups(&group_list);
+	return ret;
+}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9db1fb5..4f049285e3ac 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -516,16 +516,8 @@ char * __weak get_cpuid_str(void)
 	return NULL;
 }
 
-/*
- * From the pmu_events_map, find the table of PMU events that corresponds
- * to the current running CPU. Then, add all PMU events from that table
- * as aliases.
- */
-static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+char *perf_pmu__getcpuid(void)
 {
-	int i;
-	struct pmu_events_map *map;
-	struct pmu_event *pe;
 	char *cpuid;
 	static bool printed;
 
@@ -535,12 +527,26 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 	if (!cpuid)
 		cpuid = get_cpuid_str();
 	if (!cpuid)
-		return;
+		return NULL;
 
 	if (!printed) {
 		pr_debug("Using CPUID %s\n", cpuid);
 		printed = true;
 	}
+	return cpuid;
+}
+
+/*
+ * From the pmu_events_map, find the table of PMU events that corresponds
+ * to the current running CPU. Then, add all PMU events from that table
+ * as aliases.
+ */
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
+{
+	int i;
+	struct pmu_events_map *map;
+	struct pmu_event *pe;
+	char *cpuid = perf_pmu__getcpuid();
 
 	i = 0;
 	while (1) {
@@ -560,8 +566,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 		const char *pname;
 
 		pe = &map->table[i++];
-		if (!pe->name)
+		if (!pe->name) {
+			if (pe->metric_group || pe->metric_name)
+				continue;
 			break;
+		}
 
 		pname = pe->pmu ? pe->pmu : "cpu";
 		if (strncmp(pname, name, strlen(pname)))
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e9729331f..b4c807fd4761 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -90,4 +90,6 @@ int perf_pmu__test(void);
 
 struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu);
 
+char *perf_pmu__getcpuid(void);
+
 #endif /* __PMU_H */
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index b6cbb6e67167..1fe6b0db25a6 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -6,6 +6,7 @@
 #include "rblist.h"
 #include "evlist.h"
 #include "expr.h"
+#include "metricgroup.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -669,13 +670,16 @@ static void generic_metric(const char *metric_expr,
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out)
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events)
 {
 	void *ctxp = out->ctx;
 	print_metric_t print_metric = out->print_metric;
 	double total, ratio = 0.0, total2;
 	const char *color = NULL;
 	int ctx = evsel_context(evsel);
+	struct metric_event *me;
+	int num = 1;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
@@ -878,6 +882,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
 		print_smi_cost(cpu, evsel, out);
 	} else {
-		print_metric(ctxp, NULL, NULL, NULL, 0);
+		num = 0;
 	}
+
+	if ((me = metricgroup__lookup(metric_events, evsel, false)) != NULL) {
+		struct metric_expr *mexp;
+
+		list_for_each_entry (mexp, &me->head, nd) {
+			if (num++ > 0)
+				out->new_line(ctxp);
+			generic_metric(mexp->metric_expr, mexp->metric_events,
+					evsel->name, mexp->metric_name,
+					avg, cpu, ctx, out);
+		}
+	}
+	if (num == 0)
+		print_metric(ctxp, NULL, NULL, NULL, 0);
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 7522bf10b03e..f0656c5eca57 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,9 +90,11 @@ struct perf_stat_output_ctx {
 	bool force_header;
 };
 
+struct rblist;
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
-				   struct perf_stat_output_ctx *out);
+				   struct perf_stat_output_ctx *out,
+				   struct rblist *metric_events);
 void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
-- 
2.9.4