perf stat: Introduce config stat.bpf-counter-events

Currently, to use BPF to aggregate perf event counters, the user uses
--bpf-counters option. Enable "use bpf by default" events with a config
option, stat.bpf-counter-events. Events with name in the option will use
BPF.

This also enables mixed BPF event and regular event in the same sesssion.
For example:

   perf config stat.bpf-counter-events=instructions
   perf stat -e instructions,cs

The second command will use BPF for "instructions" but not "cs".

Signed-off-by: Song Liu <song@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/r/20210425214333.1090950-4-song@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: liu-song-6

tools/perf/Documentation/perf-stat.txt

@@ -97,6 +97,8 @@ report::
 	Use BPF programs to aggregate readings from perf_events.  This
 	allows multiple perf-stat sessions that are counting the same metric (cycles,
 	instructions, etc.) to share hardware counters.
+	To use BPF programs on common events by default, use
+	"perf config stat.bpf-counter-events=<list_of_events>".
 
 --bpf-attr-map::
 	With option "--bpf-counters", different perf-stat sessions share

tools/perf/builtin-stat.c

@@ -161,6 +161,7 @@ static const char *smi_cost_attrs = {
 };
 
 static struct evlist	*evsel_list;
+static bool all_counters_use_bpf = true;
 
 static struct target target = {
 	.uid	= UINT_MAX,
@@ -401,6 +402,9 @@ static int read_affinity_counters(struct timespec *rs)
 	struct affinity affinity;
 	int i, ncpus, cpu;
 
+	if (all_counters_use_bpf)
+		return 0;
+
 	if (affinity__setup(&affinity) < 0)
 		return -1;
 
@@ -415,6 +419,8 @@ static int read_affinity_counters(struct timespec *rs)
 		evlist__for_each_entry(evsel_list, counter) {
 			if (evsel__cpu_iter_skip(counter, cpu))
 				continue;
+			if (evsel__is_bpf(counter))
+				continue;
 			if (!counter->err) {
 				counter->err = read_counter_cpu(counter, rs,
 								counter->cpu_iter - 1);
@@ -431,6 +437,9 @@ static int read_bpf_map_counters(void)
 	int err;
 
 	evlist__for_each_entry(evsel_list, counter) {
+		if (!evsel__is_bpf(counter))
+			continue;
+
 		err = bpf_counter__read(counter);
 		if (err)
 			return err;
@@ -441,14 +450,10 @@ static int read_bpf_map_counters(void)
 static void read_counters(struct timespec *rs)
 {
 	struct evsel *counter;
-	int err;
 
 	if (!stat_config.stop_read_counter) {
-		if (target__has_bpf(&target))
-			err = read_bpf_map_counters();
-		else
-			err = read_affinity_counters(rs);
-		if (err < 0)
+		if (read_bpf_map_counters() ||
+		    read_affinity_counters(rs))
 			return;
 	}
 
@@ -537,12 +542,13 @@ static int enable_counters(void)
 	struct evsel *evsel;
 	int err;
 
-	if (target__has_bpf(&target)) {
-		evlist__for_each_entry(evsel_list, evsel) {
-			err = bpf_counter__enable(evsel);
-			if (err)
-				return err;
-		}
+	evlist__for_each_entry(evsel_list, evsel) {
+		if (!evsel__is_bpf(evsel))
+			continue;
+
+		err = bpf_counter__enable(evsel);
+		if (err)
+			return err;
 	}
 
 	if (stat_config.initial_delay < 0) {
@@ -786,11 +792,11 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	if (affinity__setup(&affinity) < 0)
 		return -1;
 
-	if (target__has_bpf(&target)) {
-		evlist__for_each_entry(evsel_list, counter) {
-			if (bpf_counter__load(counter, &target))
-				return -1;
-		}
+	evlist__for_each_entry(evsel_list, counter) {
+		if (bpf_counter__load(counter, &target))
+			return -1;
+		if (!evsel__is_bpf(counter))
+			all_counters_use_bpf = false;
 	}
 
 	evlist__for_each_cpu (evsel_list, i, cpu) {
@@ -807,6 +813,8 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 				continue;
 			if (counter->reset_group || counter->errored)
 				continue;
+			if (evsel__is_bpf(counter))
+				continue;
 try_again:
 			if (create_perf_stat_counter(counter, &stat_config, &target,
 						     counter->cpu_iter - 1) < 0) {

tools/perf/util/bpf_counter.c

@@ -790,7 +790,8 @@ int bpf_counter__load(struct evsel *evsel, struct target *target)
 {
 	if (target->bpf_str)
 		evsel->bpf_counter_ops = &bpf_program_profiler_ops;
-	else if (target->use_bpf)
+	else if (target->use_bpf ||
+		 evsel__match_bpf_counter_events(evsel->name))
 		evsel->bpf_counter_ops = &bperf_ops;
 
 	if (evsel->bpf_counter_ops)

tools/perf/util/config.c

@@ -18,6 +18,7 @@
 #include "util/hist.h"  /* perf_hist_config */
 #include "util/llvm-utils.h"   /* perf_llvm_config */
 #include "util/stat.h"  /* perf_stat__set_big_num */
+#include "util/evsel.h"  /* evsel__hw_names, evsel__use_bpf_counters */
 #include "build-id.h"
 #include "debug.h"
 #include "config.h"
@@ -460,6 +461,9 @@ static int perf_stat_config(const char *var, const char *value)
 	if (!strcmp(var, "stat.no-csv-summary"))
 		perf_stat__set_no_csv_summary(perf_config_bool(var, value));
 
+	if (!strcmp(var, "stat.bpf-counter-events"))
+		evsel__bpf_counter_events = strdup(value);
+
 	/* Add other config variables here. */
 	return 0;
 }

tools/perf/util/evsel.c

@@ -492,6 +492,28 @@ const char *evsel__hw_names[PERF_COUNT_HW_MAX] = {
 	"ref-cycles",
 };
 
+char *evsel__bpf_counter_events;
+
+bool evsel__match_bpf_counter_events(const char *name)
+{
+	int name_len;
+	bool match;
+	char *ptr;
+
+	if (!evsel__bpf_counter_events)
+		return false;
+
+	ptr = strstr(evsel__bpf_counter_events, name);
+	name_len = strlen(name);
+
+	/* check name matches a full token in evsel__bpf_counter_events */
+	match = (ptr != NULL) &&
+		((ptr == evsel__bpf_counter_events) || (*(ptr - 1) == ',')) &&
+		((*(ptr + name_len) == ',') || (*(ptr + name_len) == '\0'));
+
+	return match;
+}
+
 static const char *__evsel__hw_name(u64 config)
 {
 	if (config < PERF_COUNT_HW_MAX && evsel__hw_names[config])

tools/perf/util/evsel.h

@@ -239,13 +239,21 @@ void evsel__calc_id_pos(struct evsel *evsel);
 
 bool evsel__is_cache_op_valid(u8 type, u8 op);
 
+static inline bool evsel__is_bpf(struct evsel *evsel)
+{
+	return evsel->bpf_counter_ops != NULL;
+}
+
 #define EVSEL__MAX_ALIASES 8
 
 extern const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES];
 extern const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES];
 extern const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES];
 extern const char *evsel__hw_names[PERF_COUNT_HW_MAX];
 extern const char *evsel__sw_names[PERF_COUNT_SW_MAX];
+extern char *evsel__bpf_counter_events;
+bool evsel__match_bpf_counter_events(const char *name);
+
 int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size);
 const char *evsel__name(struct evsel *evsel);
 

tools/perf/util/target.h

@@ -66,11 +66,6 @@ static inline bool target__has_cpu(struct target *target)
 	return target->system_wide || target->cpu_list;
 }
 
-static inline bool target__has_bpf(struct target *target)
-{
-	return target->bpf_str || target->use_bpf;
-}
-
 static inline bool target__none(struct target *target)
 {
 	return !target__has_task(target) && !target__has_cpu(target);