[PATCH 11/11] perf, tools, stat: Output JSON MetricExpr metric

[Andi Kleen <andi@firstfloor.org>]

From: Andi Kleen <ak@linux.intel.com>

Add generic infrastructure to perf stat to output ratios for "MetricExpr"
entries in the event lists. Many events are more useful as ratios
than in raw form, typically some count in relation to total ticks.

Transfer the MetricExpr information from the alias to the evsel.

We mark the events that need to be collected for MetricExpr, and also
link the events using them with a pointer. The code is careful
to always prefer the right event in the same group to minimize
multiplexing errors. At the moment only a single relation is supported.

Then add a rblist to the stat shadow code that remembers stats based
on the cpu and context.

Then finally update and retrieve and print these values similarly to the
existing hardcoded perf metrics. We use the simple expression parser
added earlier to evaluate the expression.

Normally we just output the result without further commentary,
but for --metric-only this would lead to empty columns. So for this
case use the original event as description.

So far there is no attempt to automatically add the MetricExpr event,
if it is missing, however we suggest it to the user.

$ perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}'
     1.000228813        800,139,950      unc_p_clockticks
     1.000228813        789,833,783      unc_p_freq_max_os_cycles  #     98.7
     2.000654229        800,308,990      unc_p_clockticks
     2.000654229        396,214,238      unc_p_freq_max_os_cycles  #     49.5

$ perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only
     1.000206740     48.0
     2.000451543     48.1

v2: Change from DivideBy to MetricExpr
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/builtin-stat.c      |   3 +
 tools/perf/util/evsel.c        |   3 +
 tools/perf/util/evsel.h        |   3 +
 tools/perf/util/parse-events.c |   1 +
 tools/perf/util/pmu.c          |   8 ++-
 tools/perf/util/pmu.h          |   3 +-
 tools/perf/util/stat-shadow.c  | 152 +++++++++++++++++++++++++++++++++++++++++
 tools/perf/util/stat.h         |   2 +
 8 files changed, 171 insertions(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 501d58a4925a..3480711bb727 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1141,6 +1141,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 	out.print_metric = pm;
 	out.new_line = nl;
 	out.ctx = &os;
+	out.force_header = false;
 
 	if (csv_output && !metric_only) {
 		print_noise(counter, noise);
@@ -1465,6 +1466,7 @@ static void print_metric_headers(const char *prefix, bool no_indent)
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
 		out.new_line = new_line_metric;
+		out.force_header = true;
 		os.evsel = counter;
 		perf_stat__print_shadow_stats(counter, 0,
 					      0,
@@ -2447,6 +2449,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	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 (csv_sep) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b2365a63db45..fcf05535b343 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -236,6 +236,9 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
 	perf_evsel__calc_id_pos(evsel);
 	evsel->cmdline_group_boundary = false;
+	evsel->metric_expr   = NULL;
+	evsel->metric_event   = NULL;
+	evsel->collect_stat = false;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 77273f312698..6d62d046d968 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,9 @@ struct perf_evsel {
 	struct list_head	config_terms;
 	int			bpf_fd;
 	bool			merged_stat;
+	const char *		metric_expr;
+	struct perf_evsel	*metric_event;
+	bool			collect_stat;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index fba53ba22431..6adc284ff434 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1252,6 +1252,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
 		evsel->scale = info.scale;
 		evsel->per_pkg = info.per_pkg;
 		evsel->snapshot = info.snapshot;
+		evsel->metric_expr = info.metric_expr;
 	}
 
 	return evsel ? 0 : -ENOMEM;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index fd752da2dc04..de9559a2c486 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -232,7 +232,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 				 char *desc __maybe_unused, char *val,
 				 char *long_desc, char *topic,
 				 char *unit, char *perpkg,
-				 char *dividedby)
+				 char *metric_expr)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
@@ -266,7 +266,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 		perf_pmu__parse_snapshot(alias, dir, name);
 	}
 
-	alias->dividedby = dividedby ? strdup(dividedby) : NULL;
+	alias->metric_expr = metric_expr ? strdup(metric_expr) : NULL;
 	alias->desc = desc ? strdup(desc) : NULL;
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
@@ -564,7 +564,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 				(char *)pe->desc, (char *)pe->event,
 				(char *)pe->long_desc, (char *)pe->topic,
 				(char *)pe->unit, (char *)pe->perpkg,
-				(char *)pe->dividedby);
+				(char *)pe->metric_expr);
 	}
 
 out:
@@ -979,6 +979,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	info->unit     = NULL;
 	info->scale    = 0.0;
 	info->snapshot = false;
+	info->metric_expr = NULL;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -994,6 +995,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 
 		if (alias->per_pkg)
 			info->per_pkg = true;
+		info->metric_expr = alias->metric_expr;
 
 		list_del(&term->list);
 		free(term);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index faf8a7f97d03..27f078ccc594 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -31,6 +31,7 @@ struct perf_pmu {
 
 struct perf_pmu_info {
 	const char *unit;
+	const char *metric_expr;
 	double scale;
 	bool per_pkg;
 	bool snapshot;
@@ -50,7 +51,7 @@ struct perf_pmu_alias {
 	double scale;
 	bool per_pkg;
 	bool snapshot;
-	char *dividedby;
+	char *metric_expr;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 8a2bbd2a4d82..f22178ddc0ef 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -3,6 +3,9 @@
 #include "stat.h"
 #include "color.h"
 #include "pmu.h"
+#include "rblist.h"
+#include "evlist.h"
+#include "expr.h"
 
 enum {
 	CTX_BIT_USER	= 1 << 0,
@@ -41,13 +44,73 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct rblist runtime_saved_values;
 static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+struct saved_value {
+	struct rb_node rb_node;
+	struct perf_evsel *evsel;
+	int cpu;
+	int ctx;
+	struct stats stats;
+};
+
+static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
+{
+	struct saved_value *a = container_of(rb_node,
+					     struct saved_value,
+					     rb_node);
+	const struct saved_value *b = entry;
+
+	if (a->ctx != b->ctx)
+		return a->ctx - b->ctx;
+	if (a->cpu != b->cpu)
+		return a->cpu - b->cpu;
+	return a->evsel - b->evsel;
+}
+
+static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused,
+				     const void *entry)
+{
+	struct saved_value *nd = malloc(sizeof(struct saved_value));
+
+	if (!nd)
+		return NULL;
+	memcpy(nd, entry, sizeof(struct saved_value));
+	return &nd->rb_node;
+}
+
+static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
+					      int cpu, int ctx,
+					      bool create)
+{
+	struct rb_node *nd;
+	struct saved_value dm = {
+		.cpu = cpu,
+		.ctx = ctx,
+		.evsel = evsel,
+	};
+	nd = rblist__find(&runtime_saved_values, &dm);
+	if (nd)
+		return container_of(nd, struct saved_value, rb_node);
+	if (create) {
+		rblist__add_node(&runtime_saved_values, &dm);
+		nd = rblist__find(&runtime_saved_values, &dm);
+		if (nd)
+			return container_of(nd, struct saved_value, rb_node);
+	}
+	return NULL;
+}
+
 void perf_stat__init_shadow_stats(void)
 {
 	have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+	rblist__init(&runtime_saved_values);
+	runtime_saved_values.node_cmp = saved_value_cmp;
+	runtime_saved_values.node_new = saved_value_new;
+	/* No delete for now */
 }
 
 static int evsel_context(struct perf_evsel *evsel)
@@ -70,6 +133,8 @@ static int evsel_context(struct perf_evsel *evsel)
 
 void perf_stat__reset_shadow_stats(void)
 {
+	struct rb_node *pos, *next;
+
 	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
 	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
 	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
@@ -92,6 +157,15 @@ void perf_stat__reset_shadow_stats(void)
 	memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
 	memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
 	memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+
+	next = rb_first(&runtime_saved_values.entries);
+	while (next) {
+		pos = next;
+		next = rb_next(pos);
+		memset(&container_of(pos, struct saved_value, rb_node)->stats,
+		       0,
+		       sizeof(struct stats));
+	}
 }
 
 /*
@@ -143,6 +217,12 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
 	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
 		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+
+	if (counter->collect_stat) {
+		struct saved_value *v = saved_value_lookup(counter, cpu, ctx,
+							   true);
+		update_stats(&v->stats, count[0]);
+	}
 }
 
 /* used for get_ratio_color() */
@@ -172,6 +252,60 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
 	return color;
 }
 
+static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
+						const char *name)
+{
+	struct perf_evsel *c2;
+
+	evlist__for_each_entry (evsel_list, c2) {
+		if (!strcasecmp(c2->name, name))
+			return c2;
+	}
+	return NULL;
+}
+
+/* Mark DividedBy target events and link events using them to them. */
+void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
+{
+	struct perf_evsel *counter, *leader, *c2;
+	bool found;
+	const char *metric_event;
+
+	evlist__for_each_entry(evsel_list, counter) {
+		leader = counter->leader;
+		if (!counter->metric_expr)
+			continue;
+		if (expr_find_other(counter->metric_expr, counter->name,
+					&metric_event) < 0)
+			continue;
+
+		found = false;
+		if (leader) {
+			/* Search in group */
+			for_each_group_member (c2, leader) {
+				if (!strcasecmp(c2->name, metric_event)) {
+					found = true;
+					break;
+				}
+			}
+		}
+		if (!found) {
+			/* Search ignoring groups */
+			c2 = perf_stat__find_event(evsel_list, metric_event);
+		}
+		if (!c2) {
+			/* Could try to automatically add the event here. */
+			fprintf(stderr, "Add %s to groups to get metric event for %s\n",
+						metric_event,
+						counter->name);
+			counter->metric_expr = NULL;
+			continue;
+		}
+		counter->metric_event = c2;
+		c2->collect_stat = true;
+	}
+}
+
 static void print_stalled_cycles_frontend(int cpu,
 					  struct perf_evsel *evsel, double avg,
 					  struct perf_stat_output_ctx *out)
@@ -614,6 +748,24 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 					be_bound * 100.);
 		else
 			print_metric(ctxp, NULL, NULL, name, 0);
+	} else if (evsel->metric_expr) {
+		struct saved_value *v = saved_value_lookup(evsel->metric_event, cpu, ctx,
+							   false);
+		if (v) {
+			struct parse_ctx pctx;
+			const char *p;
+
+			expr_ctx_init(&pctx);
+			expr_add_id(&pctx, evsel->name, avg);
+			expr_add_id(&pctx, evsel->metric_event->name, avg_stats(&v->stats));
+			p = evsel->metric_expr;
+			if (expr_parse(&ratio, &pctx, &p) == 0)
+				print_metric(ctxp, NULL, "%8.1f",
+					out->force_header ? evsel->name : "",
+					ratio);
+			else
+				print_metric(ctxp, NULL, NULL, "", 0);
+		}
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 		char unit_buf[10];
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c29bb94c48a4..0a65ae23f495 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -85,11 +85,13 @@ struct perf_stat_output_ctx {
 	void *ctx;
 	print_metric_t print_metric;
 	new_line_t new_line;
+	bool force_header;
 };
 
 void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 				   double avg, int cpu,
 				   struct perf_stat_output_ctx *out);
+void perf_stat__collect_metric_expr(struct perf_evlist *);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
-- 
2.9.3