perf: Add duration_time to perf stat

index 6d043c78f3c2..3324f23c7efc 100644
@@ -18,11 +18,6 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static void print_running(struct perf_stat_config *config,
 			  u64 run, u64 ena)
 {

@@ -628,9 +623,6 @@ static void print_aggr(struct perf_stat_config *config,
 		ad.id = id = config->aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
 			if (!collect_data(config, counter, aggr_cb, &ad))

@@ -848,8 +840,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 		if (prefix)
 			fputs(prefix, config->output);
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			if (first) {
 				aggr_printout(config, counter, cpu, 0);
 				first = false;

@@ -906,8 +896,6 @@ static void print_metric_headers(struct perf_stat_config *config,
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evlist, counter) {
-		if (is_duration_time(counter))
-			continue;
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;

@@ -1136,15 +1124,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		break;
 	case AGGR_THREAD:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_aggr_thread(config, _target, counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_counter_aggr(config, counter, prefix);
 		}
 		if (metric_only)

@@ -1155,8 +1139,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			print_no_aggr_metric(config, evlist, prefix);
 		else {
 			evlist__for_each_entry(evlist, counter) {
-				if (is_duration_time(counter))
-					continue;
 				print_counter(config, counter, prefix);
 			}
 		}

index 49ee3c2033ec..7f9c4b7f5d69 100644
@@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 					   process_synthesized_event, NULL);
 }
 
+static int read_single_counter(struct perf_evsel *counter, int cpu,
+			       int thread, struct timespec *rs)
+{
+	if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
+		u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
+		struct perf_counts_values *count =
+			perf_counts(counter->counts, cpu, thread);
+		count->ena = count->run = val;
+		count->val = val;
+		return 0;
+	}
+	return perf_evsel__read_counter(counter, cpu, thread);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
  */
-static int read_counter(struct perf_evsel *counter)
+static int read_counter(struct perf_evsel *counter, struct timespec *rs)
 {
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;

@@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter)
 			 * (via perf_evsel__read_counter) and sets threir count->loaded.
 			 */
 			if (!count->loaded &&
-			    perf_evsel__read_counter(counter, cpu, thread)) {
+			    read_single_counter(counter, cpu, thread, rs)) {
 				counter->counts->scaled = -1;
 				perf_counts(counter->counts, cpu, thread)->ena = 0;
 				perf_counts(counter->counts, cpu, thread)->run = 0;

@@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(void)
+static void read_counters(struct timespec *rs)
 {
 	struct perf_evsel *counter;
 	int ret;
 
 	evlist__for_each_entry(evsel_list, counter) {
-		ret = read_counter(counter);
+		ret = read_counter(counter, rs);
 		if (ret)
 			pr_debug("failed to read counter %s\n", counter->name);
 

@@ -323,11 +337,11 @@ static void process_interval(void)
 {
 	struct timespec ts, rs;
 
-	read_counters();
-
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	read_counters(&rs);
+
 	if (STAT_RECORD) {
 		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
 			pr_err("failed to write stat round event\n");

@@ -593,7 +607,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	 * avoid arbitrary skew, we must read all counters before closing any
 	 * group leaders.
 	 */
-	read_counters();
+	read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
 	perf_evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);

index 0f2c6c93d721..6d190cbf1070 100644
@@ -75,6 +75,11 @@ struct perf_stat_evsel;
 
 typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
 
+enum perf_tool_event {
+	PERF_TOOL_NONE		= 0,
+	PERF_TOOL_DURATION_TIME = 1,
+};
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.

@@ -121,6 +126,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	enum perf_tool_event	tool_event;
 	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;

index 5ef4939408f2..98c0fadaedb9 100644
@@ -317,10 +317,12 @@ static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
 	    char *name, struct perf_pmu *pmu,
-	    struct list_head *config_terms, bool auto_merge_stats)
+	    struct list_head *config_terms, bool auto_merge_stats,
+	    const char *cpu_list)
 {
 	struct perf_evsel *evsel;
-	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
+	struct cpu_map *cpus = pmu ? pmu->cpus :
+			       cpu_list ? cpu_map__new(cpu_list) : NULL;
 
 	event_attr_init(attr);
 

@@ -348,7 +350,25 @@ static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, char *name,
 		     struct list_head *config_terms)
 {
-	return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
+	return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM;
+}
+
+static int add_event_tool(struct list_head *list, int *idx,
+			  enum perf_tool_event tool_event)
+{
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+	};
+
+	evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0");
+	if (!evsel)
+		return -ENOMEM;
+	evsel->tool_event = tool_event;
+	if (tool_event == PERF_TOOL_DURATION_TIME)
+		evsel->unit = strdup("ns");
+	return 0;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)

@@ -1233,6 +1253,13 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event)
+{
+	return add_event_tool(list, &parse_state->idx, tool_event);
+}
+
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,

@@ -1267,7 +1294,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
+				    auto_merge_stats, NULL);
 		if (evsel) {
 			evsel->pmu_name = name;
 			evsel->use_uncore_alias = use_uncore_alias;

@@ -1295,7 +1323,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
 			    get_config_name(head_config), pmu,
-			    &config_terms, auto_merge_stats);
+			    &config_terms, auto_merge_stats, NULL);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;

index 5ed035cbcbb7..0c1f5b98f636 100644
@@ -160,6 +160,10 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
+enum perf_tool_event;
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2,
 			   struct parse_events_error *error,

index 7835e05f0c0a..6872394b6f55 100644
@@ -579,6 +579,12 @@ static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
+static int perf_evsel__tool_name(char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "duration_time");
+	return ret;
+}
+
 const char *perf_evsel__name(struct perf_evsel *evsel)
 {
 	char bf[128];

@@ -600,7 +606,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 		break;
 
 	case PERF_TYPE_SOFTWARE:
-		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		if (evsel->tool_event)
+			perf_evsel__tool_name(bf, sizeof(bf));
+		else
+			perf_evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:

index a8394b4f1167..e0312a1c4792 100644
@@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv)
 			print_symbol_events(NULL, PERF_TYPE_HARDWARE,
 					event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 		else if (strcmp(argv[i], "sw") == 0 ||
-			 strcmp(argv[i], "software") == 0)
+			 strcmp(argv[i], "software") == 0) {
 			print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
-		else if (strcmp(argv[i], "cache") == 0 ||
+			print_tool_events(NULL, raw_dump);
+		} else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)

@@ -113,6 +114,7 @@ int cmd_list(int argc, const char **argv)
 					    event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 			print_symbol_events(s, PERF_TYPE_SOFTWARE,
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+			print_tool_events(s, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
 						long_desc_flag,

index 98c0fadaedb9..4432bfe039fd 100644
@@ -2457,6 +2457,25 @@ int print_hwcache_events(const char *event_glob, bool name_only)
 	return evt_num;
 }
 
+static void print_tool_event(const char *name, const char *event_glob,
+			     bool name_only)
+{
+	if (event_glob && !strglobmatch(name, event_glob))
+		return;
+	if (name_only)
+		printf("%s ", name);
+	else
+		printf("  %-50s [%s]\n", name, "Tool event");
+
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+	print_tool_event("duration_time", event_glob, name_only);
+	if (pager_in_use())
+		printf("\n");
+}
+
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only)

@@ -2540,6 +2559,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
 			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+	print_tool_events(event_glob, name_only);
 
 	print_hwcache_events(event_glob, name_only);
 

index 0c1f5b98f636..a052cd6ac63e 100644
@@ -204,6 +204,7 @@ extern struct event_symbol event_symbols_sw[];
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);