perf stat: Add scripting support

index b74ee0f..e77880b 100644
@@ -122,6 +122,9 @@ static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
+static bool			append_file;
+static const char		*output_name;
+static int			output_fd;
 
 static volatile int done = 0;
 

@@ -927,6 +930,67 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static const struct option stat_options[] = {
+	OPT_BOOLEAN('T', "transaction", &transaction_run,
+		    "hardware transaction statistics"),
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events_option),
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+		     "event filter", parse_filter),
+	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_STRING('p', "pid", &target.pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target.tid, "tid",
+		   "stat events on existing thread id"),
+	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('g', "group", &group,
+		    "put the counters into a counter group"),
+	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_INTEGER('r', "repeat", &run_count,
+		    "repeat command and print average + stddev (max: 100, forever: 0)"),
+	OPT_BOOLEAN('n', "null", &null_run,
+		    "null run - dont start any counters"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
+			   "print large numbers with thousands\' separators",
+			   stat__set_big_num),
+	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
+		    "list of cpus to monitor in system-wide"),
+	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
+		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+		   "print counts with custom separator"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
+	OPT_STRING(0, "pre", &pre_cmd, "command",
+			"command to run prior to the measured command"),
+	OPT_STRING(0, "post", &post_cmd, "command",
+			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
+		    "print counts at regular interval in ms (>= 10)"),
+	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
+	OPT_UINTEGER('D', "delay", &initial_delay,
+		     "ms to wait before starting measurement after program start"),
+	OPT_END()
+};
+
 static int perf_stat__get_socket(struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);

@@ -1174,69 +1238,6 @@ static int add_default_attributes(void)
 
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	bool append_file = false;
-	int output_fd = 0;
-	const char *output_name	= NULL;
-	const struct option options[] = {
-	OPT_BOOLEAN('T', "transaction", &transaction_run,
-		    "hardware transaction statistics"),
-	OPT_CALLBACK('e', "event", &evsel_list, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
-	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
-		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
-		    "child tasks do not inherit counters"),
-	OPT_STRING('p', "pid", &target.pid, "pid",
-		   "stat events on existing process id"),
-	OPT_STRING('t', "tid", &target.tid, "tid",
-		   "stat events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
-		    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('g', "group", &group,
-		    "put the counters into a counter group"),
-	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
-		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN('n', "null", &null_run,
-		    "null run - dont start any counters"),
-	OPT_INCR('d', "detailed", &detailed_run,
-		    "detailed run - start a lot of events"),
-	OPT_BOOLEAN('S', "sync", &sync_run,
-		    "call sync() before starting a run"),
-	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
-			   "print large numbers with thousands\' separators",
-			   stat__set_big_num),
-	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
-		    "list of cpus to monitor in system-wide"),
-	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
-		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
-		   "print counts with custom separator"),
-	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
-		     "monitor event in cgroup name only", parse_cgroups),
-	OPT_STRING('o', "output", &output_name, "file", "output file name"),
-	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
-	OPT_INTEGER(0, "log-fd", &output_fd,
-		    "log output to fd, instead of stderr"),
-	OPT_STRING(0, "pre", &pre_cmd, "command",
-			"command to run prior to the measured command"),
-	OPT_STRING(0, "post", &post_cmd, "command",
-			"command to run after to the measured command"),
-	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 10)"),
-	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
-		     "aggregate counts per processor socket", AGGR_SOCKET),
-	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
-		     "aggregate counts per physical processor core", AGGR_CORE),
-	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
-		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
-		     "ms to wait before starting measurement after program start"),
-	OPT_END()
-	};
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
 		NULL

@@ -1252,7 +1253,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
-	argc = parse_options(argc, argv, options, stat_usage,
+	argc = parse_options(argc, argv, stat_options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 
 	interval = stat_config.interval;

@@ -1262,14 +1263,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (output_name && output_fd) {
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
-		parse_options_usage(stat_usage, options, "o", 1);
-		parse_options_usage(NULL, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "o", 1);
+		parse_options_usage(NULL, stat_options, "log-fd", 0);
 		goto out;
 	}
 
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
-		parse_options_usage(stat_usage, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
 		goto out;
 	}
 

@@ -1309,8 +1310,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
-			parse_options_usage(stat_usage, options, "B", 1);
-			parse_options_usage(NULL, options, "x", 1);
+			parse_options_usage(stat_usage, stat_options, "B", 1);
+			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
 			big_num = false;

@@ -1318,11 +1319,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		big_num = false;
 
 	if (!argc && target__none(&target))
-		usage_with_options(stat_usage, options);
+		usage_with_options(stat_usage, stat_options);
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
-		parse_options_usage(stat_usage, options, "r", 1);
+		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
 	} else if (run_count == 0) {
 		forever = true;

@@ -1332,8 +1333,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
 		fprintf(stderr, "The --per-thread option is only available "
 			"when monitoring via -p -t options.\n");
-		parse_options_usage(NULL, options, "p", 1);
-		parse_options_usage(NULL, options, "t", 1);
+		parse_options_usage(NULL, stat_options, "p", 1);
+		parse_options_usage(NULL, stat_options, "t", 1);
 		goto out;
 	}
 

@@ -1347,9 +1348,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
-		parse_options_usage(stat_usage, options, "G", 1);
-		parse_options_usage(NULL, options, "A", 1);
-		parse_options_usage(NULL, options, "a", 1);
+		parse_options_usage(stat_usage, stat_options, "G", 1);
+		parse_options_usage(NULL, stat_options, "A", 1);
+		parse_options_usage(NULL, stat_options, "a", 1);
 		goto out;
 	}
 

@@ -1361,12 +1362,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
-			parse_options_usage(stat_usage, options, "p", 1);
-			parse_options_usage(NULL, options, "t", 1);
+			parse_options_usage(stat_usage, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
 		} else if (target__has_cpu(&target)) {
 			perror("failed to parse CPUs map");
-			parse_options_usage(stat_usage, options, "C", 1);
-			parse_options_usage(NULL, options, "a", 1);
+			parse_options_usage(stat_usage, stat_options, "C", 1);
+			parse_options_usage(NULL, stat_options, "a", 1);
 		}
 		goto out;
 	}

@@ -1381,7 +1382,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (interval && interval < 100) {
 		if (interval < 10) {
 			pr_err("print interval must be >= 10ms\n");
-			parse_options_usage(stat_usage, options, "I", 1);
+			parse_options_usage(stat_usage, stat_options, "I", 1);
 			goto out;
 		} else
 			pr_warning("print interval < 100ms. "

index af2a3bf..c9c896a 100644
@@ -1310,6 +1310,19 @@ static const char * const recort_usage[] = {
 	NULL,
 };
 
+static void init_features(struct perf_session *session)
+{
+	int feat;
+
+	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
+		perf_header__set_feat(&session->header, feat);
+
+	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
+	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
+	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+	perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	struct perf_session *session;

@@ -1331,6 +1344,8 @@ static int __cmd_record(int argc, const char **argv)
 	if (perf_stat.file.is_pipe)
 		return -EINVAL;
 
+	init_features(session);
+
 	session->evlist   = evsel_list;
 	perf_stat.session = session;
 	perf_stat.record  = true;

index a90c74b..d5636ba 100644
@@ -37,6 +37,9 @@ static int perf_session__open(struct perf_session *session)
 	if (perf_data_file__is_pipe(file))
 		return 0;
 
+	if (perf_header__has_feat(&session->header, HEADER_STAT))
+		return 0;
+
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
 		pr_err("non matching sample_type\n");
 		return -1;

index c9c896a..45bf4d2 100644
@@ -217,26 +217,20 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 	return 0;
 }
 
-static int perf_stat__write(struct perf_stat *stat, void *bf, size_t size)
+static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine __maybe_unused)
 {
-	if (perf_data_file__write(stat->session->file, bf, size) < 0) {
+	if (perf_data_file__write(&perf_stat.file, event, event->header.size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
 
-	stat->bytes_written += size;
+	perf_stat.bytes_written += event->header.size;
 	return 0;
 }
 
-static int process_synthesized_event(struct perf_tool *tool,
-				     union perf_event *event,
-				     struct perf_sample *sample __maybe_unused,
-				     struct machine *machine __maybe_unused)
-{
-	struct perf_stat *stat = (void *)tool;
-	return perf_stat__write(stat, event, event->header.size);
-}
-
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode

@@ -323,6 +317,35 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
+static int perf_stat_synthesize_config(void)
+{
+	int err;
+
+	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
+						process_synthesized_event,
+						NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_cpu_map(NULL, evsel_list->cpus,
+					     process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize thread map.\n");
+		return err;
+	}
+
+	err = perf_event__synthesize_stat_config(NULL, &stat_config,
+						 process_synthesized_event, NULL);
+	if (err < 0) {
+		pr_err("Couldn't synthesize config.\n");
+		return err;
+	}
+
+	return 0;
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;

@@ -403,6 +426,10 @@ static int __run_perf_stat(int argc, const char **argv)
 						 fd, false);
 		if (err < 0)
 			return err;
+
+		err = perf_stat_synthesize_config();
+		if (err < 0)
+			return err;
 	}
 
 	/*

@@ -1560,7 +1587,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		 * a saner message about no samples being in the perf.data file.
 		 *
 		 * This also serves to suppress a warning about f_header.data.size == 0
-		 * in header.c.  -acme
+		 * in header.c at the moment 'perf stat record' gets introduced, which
+		 * is not really needed once we start adding the stat specific PERF_RECORD_
+		 * records, but the need to suppress the kptr_restrict messages in older
+		 * tools remain  -acme
 		 */
 		int fd = perf_data_file__fd(&perf_stat.file);
 		int err = perf_event__synthesize_kernel_mmap((void *)&perf_stat,

index 45bf4d2..39d0c30f 100644
@@ -346,6 +346,38 @@ static int perf_stat_synthesize_config(void)
 	return 0;
 }
 
+#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
+
+static int __store_counter_ids(struct perf_evsel *counter,
+			       struct cpu_map *cpus,
+			       struct thread_map *threads)
+{
+	int cpu, thread;
+
+	for (cpu = 0; cpu < cpus->nr; cpu++) {
+		for (thread = 0; thread < threads->nr; thread++) {
+			int fd = FD(counter, cpu, thread);
+
+			if (perf_evlist__id_add_fd(evsel_list, counter,
+						   cpu, thread, fd) < 0)
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int store_counter_ids(struct perf_evsel *counter)
+{
+	struct cpu_map *cpus = counter->cpus;
+	struct thread_map *threads = counter->threads;
+
+	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
+		return -ENOMEM;
+
+	return __store_counter_ids(counter, cpus, threads);
+}
+
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;

@@ -410,6 +442,9 @@ static int __run_perf_stat(int argc, const char **argv)
 		l = strlen(counter->unit);
 		if (l > unit_width)
 			unit_width = l;
+
+		if (STAT_RECORD && store_counter_ids(counter))
+			return -1;
 	}
 
 	if (perf_evlist__apply_filters(evsel_list, &counter)) {

index 8c44aad..b9eac0d 100644
@@ -534,9 +534,9 @@ void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 	evsel->id[evsel->ids++] = id;
 }
 
-static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
-				  struct perf_evsel *evsel,
-				  int cpu, int thread, int fd)
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd)
 {
 	u64 read_data[4] = { 0, };
 	int id_idx = 1; /* The first entry is the counter value */

index a459fe7..139a500 100644
@@ -97,6 +97,9 @@ perf_evlist__find_tracepoint_by_name(struct perf_evlist *evlist,
 
 void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
 			 int cpu, int thread, u64 id);
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd);
 
 int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);

index 39d0c30f..8a2f9ce 100644
@@ -317,10 +317,19 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
-static int perf_stat_synthesize_config(void)
+static int perf_stat_synthesize_config(bool is_pipe)
 {
 	int err;
 
+	if (is_pipe) {
+		err = perf_event__synthesize_attrs(NULL, perf_stat.session,
+						   process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize attrs.\n");
+			return err;
+		}
+	}
+
 	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
 						process_synthesized_event,
 						NULL);

@@ -388,6 +397,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	size_t l;
 	int status = 0;
 	const bool forks = (argc > 0);
+	bool is_pipe = STAT_RECORD ? perf_stat.file.is_pipe : false;
 
 	if (interval) {
 		ts.tv_sec  = interval / 1000;

@@ -398,7 +408,7 @@ static int __run_perf_stat(int argc, const char **argv)
 	}
 
 	if (forks) {
-		if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
+		if (perf_evlist__prepare_workload(evsel_list, &target, argv, is_pipe,
 						  workload_exec_failed_signal) < 0) {
 			perror("failed to prepare workload");
 			return -1;

@@ -457,12 +467,17 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (STAT_RECORD) {
 		int err, fd = perf_data_file__fd(&perf_stat.file);
 
-		err = perf_session__write_header(perf_stat.session, evsel_list,
-						 fd, false);
+		if (is_pipe) {
+			err = perf_header__write_pipe(perf_data_file__fd(&perf_stat.file));
+		} else {
+			err = perf_session__write_header(perf_stat.session, evsel_list,
+							 fd, false);
+		}
+
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config();
+		err = perf_stat_synthesize_config(is_pipe);
 		if (err < 0)
 			return err;
 	}

@@ -970,6 +985,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	struct perf_evsel *counter;
 	char buf[64], *prefix = NULL;
 
+	/* Do not print anything if we record to the pipe. */
+	if (STAT_RECORD && perf_stat.file.is_pipe)
+		return;
+
 	if (interval)
 		print_interval(prefix = buf, ts);
 	else

@@ -1402,10 +1421,6 @@ static int __cmd_record(int argc, const char **argv)
 		return -1;
 	}
 
-	/* No pipe support ATM */
-	if (perf_stat.file.is_pipe)
-		return -EINVAL;
-
 	init_features(session);
 
 	session->evlist   = evsel_list;

@@ -1636,8 +1651,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 				   "older tools may produce warnings about this file\n.");
 		}
 
-		perf_stat.session->header.data_size += perf_stat.bytes_written;
-		perf_session__write_header(perf_stat.session, evsel_list, fd, true);
+		if (!perf_stat.file.is_pipe) {
+			perf_stat.session->header.data_size += perf_stat.bytes_written;
+			perf_session__write_header(perf_stat.session, evsel_list, fd, true);
+		}
 
 		perf_session__delete(perf_stat.session);
 	}

index 8a2f9ce..32aa2ea 100644
@@ -231,6 +231,18 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+static int
+perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
+			     struct perf_counts_values *count)
+{
+	struct perf_sample_id *sid = SID(counter, cpu, thread);
+
+	return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
+					   process_synthesized_event, NULL);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode

@@ -254,6 +266,13 @@ static int read_counter(struct perf_evsel *counter)
 			count = perf_counts(counter->counts, cpu, thread);
 			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
+
+			if (STAT_RECORD) {
+				if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+					pr_err("failed to write stat event\n");
+					return -1;
+				}
+			}
 		}
 	}
 

index 32aa2ea..fcece42 100644
@@ -231,6 +231,16 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int write_stat_round_event(u64 time, u64 type)
+{
+	return perf_event__synthesize_stat_round(NULL, time, type,
+						 process_synthesized_event,
+						 NULL);
+}
+
+#define WRITE_STAT_ROUND_EVENT(time, interval) \
+	write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)
+
 #define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
 
 static int

@@ -306,6 +316,11 @@ static void process_interval(void)
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	if (STAT_RECORD) {
+		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSECS_PER_SEC + rs.tv_nsec, INTERVAL))
+			pr_err("failed to write stat round event\n");
+	}
+
 	print_counters(&rs, 0, NULL);
 }
 

@@ -1670,6 +1685,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 				   "older tools may produce warnings about this file\n.");
 		}
 
+		if (!interval) {
+			if (WRITE_STAT_ROUND_EVENT(walltime_nsecs_stats.max, FINAL))
+				pr_err("failed to write stat round event\n");
+		}
+
 		if (!perf_stat.file.is_pipe) {
 			perf_stat.session->header.data_size += perf_stat.bytes_written;
 			perf_session__write_header(perf_stat.session, evsel_list, fd, true);

index fcece42..10f86a6 100644
@@ -1449,6 +1449,11 @@ static int __cmd_record(int argc, const char **argv)
 	if (output_name)
 		file->path = output_name;
 
+	if (run_count != 1 || forever) {
+		pr_err("Cannot use -r option with perf stat record.\n");
+		return -1;
+	}
+
 	session = perf_session__new(file, false, NULL);
 	if (session == NULL) {
 		pr_err("Perf session creation failed.\n");

index 10f86a6..575e253 100644
@@ -351,8 +351,19 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
 	workload_exec_errno = info->si_value.sival_int;
 }
 
+static bool has_unit(struct perf_evsel *counter)
+{
+	return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+	return counter->scale != 1;
+}
+
 static int perf_stat_synthesize_config(bool is_pipe)
 {
+	struct perf_evsel *counter;
 	int err;
 
 	if (is_pipe) {

@@ -364,6 +375,54 @@ static int perf_stat_synthesize_config(bool is_pipe)
 		}
 	}
 
+	/*
+	 * Synthesize other events stuff not carried within
+	 * attr event - unit, scale, name
+	 */
+	evlist__for_each(evsel_list, counter) {
+		if (!counter->supported)
+			continue;
+
+		/*
+		 * Synthesize unit and scale only if it's defined.
+		 */
+		if (has_unit(counter)) {
+			err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel unit.\n");
+				return err;
+			}
+		}
+
+		if (has_scale(counter)) {
+			err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel scale.\n");
+				return err;
+			}
+		}
+
+		if (counter->own_cpus) {
+			err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel scale.\n");
+				return err;
+			}
+		}
+
+		/*
+		 * Name is needed only for pipe output,
+		 * perf.data carries event names.
+		 */
+		if (is_pipe) {
+			err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
+			if (err < 0) {
+				pr_err("Couldn't synthesize evsel name.\n");
+				return err;
+			}
+		}
+	}
+
 	err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
 						process_synthesized_event,
 						NULL);

97 lines not on this page · raw message

index abba49b..0a1cfdd 100644
@@ -135,6 +135,9 @@ struct perf_stat {
 	struct perf_session	*session;
 	u64			 bytes_written;
 	struct perf_tool	 tool;
+	bool			 maps_allocated;
+	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 };
 
 static struct perf_stat		perf_stat;

@@ -234,9 +237,9 @@ static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static int write_stat_round_event(u64 time, u64 type)
+static int write_stat_round_event(u64 tm, u64 type)
 {
-	return perf_event__synthesize_stat_round(NULL, time, type,
+	return perf_event__synthesize_stat_round(NULL, tm, type,
 						 process_synthesized_event,
 						 NULL);
 }

@@ -1530,6 +1533,63 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
+static int set_maps(struct perf_stat *st)
+{
+	if (!st->cpus || !st->threads)
+		return 0;
+
+	if (WARN_ONCE(st->maps_allocated, "stats double allocation\n"))
+		return -EINVAL;
+
+	perf_evlist__set_maps(evsel_list, st->cpus, st->threads);
+
+	if (perf_evlist__alloc_stats(evsel_list, true))
+		return -ENOMEM;
+
+	st->maps_allocated = true;
+	return 0;
+}
+
+static
+int process_thread_map_event(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_session *session __maybe_unused)
+{
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
+	if (st->threads) {
+		pr_warning("Extra thread map event, ignoring.\n");
+		return 0;
+	}
+
+	st->threads = thread_map__new_event(&event->thread_map);
+	if (!st->threads)
+		return -ENOMEM;
+
+	return set_maps(st);
+}
+
+static
+int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
+			  union perf_event *event,
+			  struct perf_session *session __maybe_unused)
+{
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+	struct cpu_map *cpus;
+
+	if (st->cpus) {
+		pr_warning("Extra cpu map event, ignoring.\n");
+		return 0;
+	}
+
+	cpus = cpu_map__new_data(&event->cpu_map.data);
+	if (!cpus)
+		return -ENOMEM;
+
+	st->cpus = cpus;
+	return set_maps(st);
+}
+
 static const char * const report_usage[] = {
 	"perf stat report [<options>]",
 	NULL,

@@ -1538,6 +1598,8 @@ static const char * const report_usage[] = {
 static struct perf_stat perf_stat = {
 	.tool = {
 		.attr		= perf_event__process_attr,
+		.thread_map	= process_thread_map_event,
+		.cpu_map	= process_cpu_map_event,
 	},
 };
 

index 0a1cfdd..1e5db50 100644
@@ -1533,6 +1533,15 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
+static
+int process_stat_config_event(struct perf_tool *tool __maybe_unused,
+			      union perf_event *event,
+			      struct perf_session *session __maybe_unused)
+{
+	perf_event__read_stat_config(&stat_config, &event->stat_config);
+	return 0;
+}
+
 static int set_maps(struct perf_stat *st)
 {
 	if (!st->cpus || !st->threads)

@@ -1600,6 +1609,7 @@ static struct perf_stat perf_stat = {
 		.attr		= perf_event__process_attr,
 		.thread_map	= process_thread_map_event,
 		.cpu_map	= process_cpu_map_event,
+		.stat_config	= process_stat_config_event,
 	},
 };
 

index 1e5db50..c780525 100644
@@ -1326,6 +1326,101 @@ static void perf_stat__exit_aggr_mode(void)
 	cpus_aggr_map = NULL;
 }
 
+static inline int perf_env__get_cpu(struct perf_env *env, struct cpu_map *map, int idx)
+{
+	int cpu;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	if (cpu >= env->nr_cpus_online)
+		return -1;
+
+	return cpu;
+}
+
+static int perf_env__get_socket(struct cpu_map *map, int idx, void *data)
+{
+	struct perf_env *env = data;
+	int cpu = perf_env__get_cpu(env, map, idx);
+
+	return cpu == -1 ? -1 : env->cpu[cpu].socket_id;
+}
+
+static int perf_env__get_core(struct cpu_map *map, int idx, void *data)
+{
+	struct perf_env *env = data;
+	int core = -1, cpu = perf_env__get_cpu(env, map, idx);
+
+	if (cpu != -1) {
+		int socket_id = env->cpu[cpu].socket_id;
+
+		/*
+		 * Encode socket in upper 16 bits
+		 * core_id is relative to socket, and
+		 * we need a global id. So we combine
+		 * socket + core id.
+		 */
+		core = (socket_id << 16) | (env->cpu[cpu].core_id & 0xffff);
+	}
+
+	return core;
+}
+
+static int perf_env__build_socket_map(struct perf_env *env, struct cpu_map *cpus,
+				      struct cpu_map **sockp)
+{
+	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
+}
+
+static int perf_env__build_core_map(struct perf_env *env, struct cpu_map *cpus,
+				    struct cpu_map **corep)
+{
+	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
+}
+
+static int perf_stat__get_socket_file(struct cpu_map *map, int idx)
+{
+	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat__get_core_file(struct cpu_map *map, int idx)
+{
+	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+	struct perf_env *env = &st->session->header.env;
+
+	switch (stat_config.aggr_mode) {
+	case AGGR_SOCKET:
+		if (perf_env__build_socket_map(env, evsel_list->cpus, &aggr_map)) {
+			perror("cannot build socket map");
+			return -1;
+		}
+		aggr_get_id = perf_stat__get_socket_file;
+		break;
+	case AGGR_CORE:
+		if (perf_env__build_core_map(env, evsel_list->cpus, &aggr_map)) {
+			perror("cannot build core map");
+			return -1;
+		}
+		aggr_get_id = perf_stat__get_core_file;
+		break;
+	case AGGR_NONE:
+	case AGGR_GLOBAL:
+	case AGGR_THREAD:
+	case AGGR_UNSET:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:

@@ -1538,7 +1633,15 @@ int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 			      union perf_event *event,
 			      struct perf_session *session __maybe_unused)
 {
+	struct perf_stat *st = container_of(tool, struct perf_stat, tool);
+
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
+
+	if (perf_stat.file.is_pipe)
+		perf_stat_init_aggr_mode();
+	else
+		perf_stat_init_aggr_mode_file(st);
+
 	return 0;
 }
 

index f9d4e09..d27d1b9 100644
@@ -1628,6 +1628,32 @@ static int __cmd_record(int argc, const char **argv)
 	return argc;
 }
 
+static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_session *session)
+{
+	struct stat_round_event *round = &event->stat_round;
+	struct perf_evsel *counter;
+	struct timespec tsh, *ts = NULL;
+	const char **argv = session->header.env.cmdline_argv;
+	int argc = session->header.env.nr_cmdline;
+
+	evlist__for_each(evsel_list, counter)
+		perf_stat_process_counter(&stat_config, counter);
+
+	if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
+		update_stats(&walltime_nsecs_stats, round->time);
+
+	if (stat_config.interval && round->time) {
+		tsh.tv_sec  = round->time / NSECS_PER_SEC;
+		tsh.tv_nsec = round->time % NSECS_PER_SEC;
+		ts = &tsh;
+	}
+
+	print_counters(ts, argc, argv);
+	return 0;
+}
+
 static
 int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 			      union perf_event *event,

@@ -1713,6 +1739,8 @@ static struct perf_stat perf_stat = {
 		.thread_map	= process_thread_map_event,
 		.cpu_map	= process_cpu_map_event,
 		.stat_config	= process_stat_config_event,
+		.stat		= perf_event__process_stat_event,
+		.stat_round	= process_stat_round_event,
 	},
 };
 

index d27d1b9..3ccf5a9 100644
@@ -1736,6 +1736,7 @@ static const char * const report_usage[] = {
 static struct perf_stat perf_stat = {
 	.tool = {
 		.attr		= perf_event__process_attr,
+		.event_update	= perf_event__process_event_update,
 		.thread_map	= process_thread_map_event,
 		.cpu_map	= process_cpu_map_event,
 		.stat_config	= process_stat_config_event,

index c780525..f9d4e09 100644
@@ -1776,6 +1776,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 					(const char **) stat_usage,
 					PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if (csv_sep) {
+		csv_output = true;
+		if (!strcmp(csv_sep, "\\t"))
+			csv_sep = "\t";
+	} else
+		csv_sep = DEFAULT_SEPARATOR;
+
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = __cmd_record(argc, argv);
 		if (argc < 0)

@@ -1826,13 +1833,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	stat_config.output = output;
 
-	if (csv_sep) {
-		csv_output = true;
-		if (!strcmp(csv_sep, "\\t"))
-			csv_sep = "\t";
-	} else
-		csv_sep = DEFAULT_SEPARATOR;
-
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */

index 3ccf5a9..9805e03 100644
@@ -138,6 +138,7 @@ struct perf_stat {
 	bool			 maps_allocated;
 	struct cpu_map		*cpus;
 	struct thread_map	*threads;
+	enum aggr_mode		 aggr_mode;
 };
 
 static struct perf_stat		perf_stat;

@@ -1663,6 +1664,15 @@ int process_stat_config_event(struct perf_tool *tool __maybe_unused,
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
+	if (cpu_map__empty(st->cpus)) {
+		if (st->aggr_mode != AGGR_UNSET)
+			pr_warning("warning: processing task data, aggregation mode not set\n");
+		return 0;
+	}
+
+	if (st->aggr_mode != AGGR_UNSET)
+		stat_config.aggr_mode = st->aggr_mode;
+
 	if (perf_stat.file.is_pipe)
 		perf_stat_init_aggr_mode();
 	else

@@ -1743,6 +1753,7 @@ static struct perf_stat perf_stat = {
 		.stat		= perf_event__process_stat_event,
 		.stat_round	= process_stat_round_event,
 	},
+	.aggr_mode = AGGR_UNSET,
 };
 
 static int __cmd_report(int argc, const char **argv)