perf expr: Migrate expr ids table to a hashmap

Use a hashmap between a char* string and a double* value. While bpf's
hashmap entries are size_t in size, we can't guarantee sizeof(size_t) >=
sizeof(double). Avoid a memory allocation when gathering ids by making
0.0 a special value encoded as NULL.

Original map suggestion by Andi Kleen:

  https://lore.kernel.org/lkml/20200224210308.GQ160988@tassilo.jf.intel.com/

and seconded by Jiri Olsa:

  https://lore.kernel.org/lkml/20200423112915.GH1136647@krava/

Committer notes:

There are fixes that need to land upstream before we can use libbpf's
headers, for now use our copy unconditionally, since the data structures
at this point are exactly the same, no problem.

When the fixes for libbpf's hashmap land upstream, we can fix this up.

Testing it:

Building with LIBBPF=1, i.e. the default:

  $ perf -vv | grep -i bpf
                     bpf: [ on  ]  # HAVE_LIBBPF_SUPPORT
  $ nm ~/bin/perf | grep -i libbpf_ | wc -l
  39
  $ nm ~/bin/perf | grep -i hashmap_ | wc -l
  17
  $

Explicitely building without LIBBPF:

  $ perf -vv | grep -i bpf
                     bpf: [ OFF ]  # HAVE_LIBBPF_SUPPORT
  $
  $ nm ~/bin/perf | grep -i libbpf_ | wc -l
  0
  $ nm ~/bin/perf | grep -i hashmap_ | wc -l
  9
  $

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: bpf@vger.kernel.org
Cc: kp singh <kpsingh@chromium.org>
Cc: netdev@vger.kernel.org
Link: http://lore.kernel.org/lkml/20200515221732.44078-8-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 42 insertions, 50 deletions

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index b071df373f8b..6772d256dfdf 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -85,8 +85,7 @@ static void metricgroup__rblist_init(struct rblist *metric_events)
 
 struct egroup {
 	struct list_head nd;
-	int idnum;
-	const char **ids;
+	struct expr_parse_ctx pctx;
 	const char *metric_name;
 	const char *metric_expr;
 	const char *metric_unit;
@@ -94,19 +93,21 @@ struct egroup {
 };
 
 static struct evsel *find_evsel_group(struct evlist *perf_evlist,
-				      const char **ids,
-				      int idnum,
+				      struct expr_parse_ctx *pctx,
 				      struct evsel **metric_events,
 				      bool *evlist_used)
 {
 	struct evsel *ev;
-	int i = 0, j = 0;
 	bool leader_found;
+	const size_t idnum = hashmap__size(&pctx->ids);
+	size_t i = 0;
+	int j = 0;
+	double *val_ptr;
 
 	evlist__for_each_entry (perf_evlist, ev) {
 		if (evlist_used[j++])
 			continue;
-		if (!strcmp(ev->name, ids[i])) {
+		if (hashmap__find(&pctx->ids, ev->name, (void **)&val_ptr)) {
 			if (!metric_events[i])
 				metric_events[i] = ev;
 			i++;
@@ -117,14 +118,6 @@ static struct evsel *find_evsel_group(struct evlist *perf_evlist,
 			i = 0;
 			memset(metric_events, 0,
 				sizeof(struct evsel *) * idnum);
-
-			if (!strcmp(ev->name, ids[i])) {
-				if (!metric_events[i])
-					metric_events[i] = ev;
-				i++;
-				if (i == idnum)
-					break;
-			}
 		}
 	}
 
@@ -175,19 +168,20 @@ static int metricgroup__setup_events(struct list_head *groups,
 	list_for_each_entry (eg, groups, nd) {
 		struct evsel **metric_events;
 
-		metric_events = calloc(sizeof(void *), eg->idnum + 1);
+		metric_events = calloc(sizeof(void *),
+				hashmap__size(&eg->pctx.ids) + 1);
 		if (!metric_events) {
 			ret = -ENOMEM;
 			break;
 		}
-		evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
-					 metric_events, evlist_used);
+		evsel = find_evsel_group(perf_evlist, &eg->pctx, metric_events,
+					evlist_used);
 		if (!evsel) {
 			pr_debug("Cannot resolve %s: %s\n",
 					eg->metric_name, eg->metric_expr);
 			continue;
 		}
-		for (i = 0; i < eg->idnum; i++)
+		for (i = 0; metric_events[i]; i++)
 			metric_events[i]->collect_stat = true;
 		me = metricgroup__lookup(metric_events_list, evsel, true);
 		if (!me) {
@@ -415,20 +409,20 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 }
 
 static void metricgroup__add_metric_weak_group(struct strbuf *events,
-					       const char **ids,
-					       int idnum)
+					       struct expr_parse_ctx *ctx)
 {
+	struct hashmap_entry *cur;
+	size_t bkt, i = 0;
 	bool no_group = false;
-	int i;
 
-	for (i = 0; i < idnum; i++) {
-		pr_debug("found event %s\n", ids[i]);
+	hashmap__for_each_entry((&ctx->ids), cur, bkt) {
+		pr_debug("found event %s\n", (const char *)cur->key);
 		/*
 		 * Duration time maps to a software event and can make
 		 * groups not count. Always use it outside a
 		 * group.
 		 */
-		if (!strcmp(ids[i], "duration_time")) {
+		if (!strcmp(cur->key, "duration_time")) {
 			if (i > 0)
 				strbuf_addf(events, "}:W,");
 			strbuf_addf(events, "duration_time");
@@ -437,21 +431,22 @@ static void metricgroup__add_metric_weak_group(struct strbuf *events,
 		}
 		strbuf_addf(events, "%s%s",
 			i == 0 || no_group ? "{" : ",",
-			ids[i]);
+			(const char *)cur->key);
 		no_group = false;
+		i++;
 	}
 	if (!no_group)
 		strbuf_addf(events, "}:W");
 }
 
 static void metricgroup__add_metric_non_group(struct strbuf *events,
-					      const char **ids,
-					      int idnum)
+					      struct expr_parse_ctx *ctx)
 {
-	int i;
+	struct hashmap_entry *cur;
+	size_t bkt;
 
-	for (i = 0; i < idnum; i++)
-		strbuf_addf(events, ",%s", ids[i]);
+	hashmap__for_each_entry((&ctx->ids), cur, bkt)
+		strbuf_addf(events, ",%s", (const char *)cur->key);
 }
 
 static void metricgroup___watchdog_constraint_hint(const char *name, bool foot)
@@ -495,32 +490,32 @@ int __weak arch_get_runtimeparam(void)
 static int __metricgroup__add_metric(struct strbuf *events,
 		struct list_head *group_list, struct pmu_event *pe, int runtime)
 {
-
-	const char **ids;
-	int idnum;
 	struct egroup *eg;
 
-	if (expr__find_other(pe->metric_expr, NULL, &ids, &idnum, runtime) < 0)
-		return -EINVAL;
-
-	if (events->len > 0)
-		strbuf_addf(events, ",");
-
-	if (metricgroup__has_constraint(pe))
-		metricgroup__add_metric_non_group(events, ids, idnum);
-	else
-		metricgroup__add_metric_weak_group(events, ids, idnum);
-
 	eg = malloc(sizeof(*eg));
 	if (!eg)
 		return -ENOMEM;
 
-	eg->ids = ids;
-	eg->idnum = idnum;
+	expr__ctx_init(&eg->pctx);
 	eg->metric_name = pe->metric_name;
 	eg->metric_expr = pe->metric_expr;
 	eg->metric_unit = pe->unit;
 	eg->runtime = runtime;
+
+	if (expr__find_other(pe->metric_expr, NULL, &eg->pctx, runtime) < 0) {
+		expr__ctx_clear(&eg->pctx);
+		free(eg);
+		return -EINVAL;
+	}
+
+	if (events->len > 0)
+		strbuf_addf(events, ",");
+
+	if (metricgroup__has_constraint(pe))
+		metricgroup__add_metric_non_group(events, &eg->pctx);
+	else
+		metricgroup__add_metric_weak_group(events, &eg->pctx);
+
 	list_add_tail(&eg->nd, group_list);
 
 	return 0;
@@ -603,12 +598,9 @@ static int metricgroup__add_metric_list(const char *list, struct strbuf *events,
 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++)
-			zfree(&eg->ids[i]);
-		zfree(&eg->ids);
+		expr__ctx_clear(&eg->pctx);
 		list_del_init(&eg->nd);
 		free(eg);
 	}