Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

  - Validate syscall list passed via -e argument to 'perf trace'. (Arnaldo Carvalho de Melo)

  - Introduce 'perf stat --per-thread'. (Jiri Olsa)

  - Check access permission for --kallsyms and --vmlinux. (Li Zhang)

Infrastructure changes:

  - Move stuff out of 'perf stat' and into the lib for further use. (Jiri Olsa)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 570 insertions, 255 deletions

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04e150d..47469ab 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 32626ea..348bed4 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -742,6 +742,17 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 
+	if (symbol_conf.vmlinux_name &&
+	    access(symbol_conf.vmlinux_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
+		return -EINVAL;
+	}
+	if (symbol_conf.kallsyms_name &&
+	    access(symbol_conf.kallsyms_name, R_OK)) {
+		pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
+		return -EINVAL;
+	}
+
 	if (report.use_stdio)
 		use_browser = 0;
 	else if (report.use_tui)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e1636c..37e301a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -67,10 +67,7 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static void print_stat(int argc, const char **argv);
-static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
-static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr(char *prefix);
+static void print_counters(struct timespec *ts, int argc, const char **argv);
 
 /* Default events used for perf stat -T */
 static const char *transaction_attrs = {
@@ -141,86 +138,9 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_stat__reset_stats(void)
 {
-	int i;
-	struct perf_stat *ps = evsel->priv;
-
-	for (i = 0; i < 3; i++)
-		init_stats(&ps->res_stats[i]);
-
-	perf_stat_evsel_id_init(evsel);
-}
-
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
-{
-	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel->priv == NULL)
-		return -ENOMEM;
-	perf_evsel__reset_stat_priv(evsel);
-	return 0;
-}
-
-static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
-{
-	zfree(&evsel->priv);
-}
-
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
-{
-	struct perf_counts *counts;
-
-	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
-	if (counts)
-		evsel->prev_raw_counts = counts;
-
-	return counts ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
-{
-	perf_counts__delete(evsel->prev_raw_counts);
-	evsel->prev_raw_counts = NULL;
-}
-
-static void perf_evlist__free_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__free_stat_priv(evsel);
-		perf_evsel__free_counts(evsel);
-		perf_evsel__free_prev_raw_counts(evsel);
-	}
-}
-
-static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
-		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
-		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
-			goto out_free;
-	}
-
-	return 0;
-
-out_free:
-	perf_evlist__free_stats(evlist);
-	return -1;
-}
-
-static void perf_stat__reset_stats(struct perf_evlist *evlist)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		perf_evsel__reset_stat_priv(evsel);
-		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
-	}
-
+	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
 }
 
@@ -294,8 +214,9 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
 	return 0;
 }
 
-static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
-		   struct perf_counts_values *count)
+static int
+process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
+		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	static struct perf_counts_values zero;
@@ -310,13 +231,13 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_THREAD:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			perf_evsel__compute_deltas(evsel, cpu, count);
+			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, scale, NULL);
-		evsel->counts->cpu[cpu] = *count;
 		if (aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
@@ -333,26 +254,48 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 	return 0;
 }
 
-static int read_counter(struct perf_evsel *counter);
+static int process_counter_maps(struct perf_evsel *counter)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-/*
- * Read out the results of a single counter:
- * aggregate counts across CPUs in system-wide mode
- */
-static int read_counter_aggr(struct perf_evsel *counter)
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (process_counter_values(counter, cpu, thread,
+						   perf_counts(counter->counts, cpu, thread)))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int process_counter(struct perf_evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
-	int i;
+	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
+	init_stats(ps->res_stats);
 
-	if (read_counter(counter))
-		return -1;
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
+
+	ret = process_counter_maps(counter);
+	if (ret)
+		return ret;
+
+	if (aggr_mode != AGGR_GLOBAL)
+		return 0;
 
 	if (!counter->snapshot)
-		perf_evsel__compute_deltas(counter, -1, aggr);
+		perf_evsel__compute_deltas(counter, -1, -1, aggr);
 	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)
@@ -387,12 +330,12 @@ static int read_counter(struct perf_evsel *counter)
 	if (counter->system_wide)
 		nthreads = 1;
 
-	if (counter->per_pkg)
-		zero_per_pkg(counter);
-
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
-			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+			struct perf_counts_values *count;
+
+			count = perf_counts(counter->counts, cpu, thread);
+			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
 		}
 	}
@@ -400,68 +343,34 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void print_interval(void)
+static void read_counters(bool close)
 {
-	static int num_print_interval;
 	struct perf_evsel *counter;
-	struct perf_stat *ps;
-	struct timespec ts, rs;
-	char prefix[64];
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter_aggr(counter);
-		}
-	} else	{
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter(counter);
-		}
-	}
+	evlist__for_each(evsel_list, counter) {
+		if (read_counter(counter))
+			pr_warning("failed to read counter %s\n", counter->name);
 
-	clock_gettime(CLOCK_MONOTONIC, &ts);
-	diff_timespec(&rs, &ts, &ref_time);
-	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+		if (process_counter(counter))
+			pr_warning("failed to process counter %s\n", counter->name);
 
-	if (num_print_interval == 0 && !csv_output) {
-		switch (aggr_mode) {
-		case AGGR_SOCKET:
-			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_CORE:
-			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_NONE:
-			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
-			break;
-		case AGGR_GLOBAL:
-		default:
-			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+		if (close) {
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
+					     thread_map__nr(evsel_list->threads));
 		}
 	}
+}
 
-	if (++num_print_interval == 25)
-		num_print_interval = 0;
+static void process_interval(void)
+{
+	struct timespec ts, rs;
 
-	switch (aggr_mode) {
-	case AGGR_CORE:
-	case AGGR_SOCKET:
-		print_aggr(prefix);
-		break;
-	case AGGR_NONE:
-		evlist__for_each(evsel_list, counter)
-			print_counter(counter, prefix);
-		break;
-	case AGGR_GLOBAL:
-	default:
-		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, prefix);
-	}
+	read_counters(false);
 
-	fflush(output);
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+
+	print_counters(&rs, 0, NULL);
 }
 
 static void handle_initial_delay(void)
@@ -576,7 +485,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
-				print_interval();
+				process_interval();
 			}
 		}
 		wait(&status);
@@ -594,7 +503,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		while (!done) {
 			nanosleep(&ts, NULL);
 			if (interval)
-				print_interval();
+				process_interval();
 		}
 	}
 
@@ -602,18 +511,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     thread_map__nr(evsel_list->threads));
-		}
-	} else {
-		evlist__for_each(evsel_list, counter) {
-			read_counter(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-		}
-	}
+	read_counters(true);
 
 	return WEXITSTATUS(status);
 }
@@ -705,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_THREAD:
+		fprintf(output, "%*s-%*d%s",
+			csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -805,9 +711,9 @@ static void print_aggr(char *prefix)
 				s2 = aggr_get_id(evsel_list->cpus, cpu2);
 				if (s2 != id)
 					continue;
-				val += counter->counts->cpu[cpu].val;
-				ena += counter->counts->cpu[cpu].ena;
-				run += counter->counts->cpu[cpu].run;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+				ena += perf_counts(counter->counts, cpu, 0)->ena;
+				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
 			if (prefix)
@@ -853,6 +759,40 @@ static void print_aggr(char *prefix)
 	}
 }
 
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -915,9 +855,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = counter->counts->cpu[cpu].val;
-		ena = counter->counts->cpu[cpu].ena;
-		run = counter->counts->cpu[cpu].run;
+		val = perf_counts(counter->counts, cpu, 0)->val;
+		ena = perf_counts(counter->counts, cpu, 0)->ena;
+		run = perf_counts(counter->counts, cpu, 0)->run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
@@ -962,9 +902,38 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	}
 }
 
-static void print_stat(int argc, const char **argv)
+static void print_interval(char *prefix, struct timespec *ts)
+{
+	static int num_print_interval;
+
+	sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		switch (aggr_mode) {
+		case AGGR_SOCKET:
+			fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_NONE:
+			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			break;
+		case AGGR_GLOBAL:
+		default:
+			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
+		}
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+}
+
+static void print_header(int argc, const char **argv)
 {
-	struct perf_evsel *counter;
 	int i;
 
 	fflush(stdout);
@@ -990,36 +959,57 @@ static void print_stat(int argc, const char **argv)
 			fprintf(output, " (%d runs)", run_count);
 		fprintf(output, ":\n\n");
 	}
+}
+
+static void print_footer(void)
+{
+	if (!null_run)
+		fprintf(output, "\n");
+	fprintf(output, " %17.9f seconds time elapsed",
+			avg_stats(&walltime_nsecs_stats)/1e9);
+	if (run_count > 1) {
+		fprintf(output, "                                        ");
+		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
+				avg_stats(&walltime_nsecs_stats));
+	}
+	fprintf(output, "\n\n");
+}
+
+static void print_counters(struct timespec *ts, int argc, const char **argv)
+{
+	struct perf_evsel *counter;
+	char buf[64], *prefix = NULL;
+
+	if (interval)
+		print_interval(prefix = buf, ts);
+	else
+		print_header(argc, argv);
 
 	switch (aggr_mode) {
 	case AGGR_CORE:
 	case AGGR_SOCKET:
-		print_aggr(NULL);
+		print_aggr(prefix);
+		break;
+	case AGGR_THREAD:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_thread(counter, prefix);
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
-			print_counter_aggr(counter, NULL);
+			print_counter_aggr(counter, prefix);
 		break;
 	case AGGR_NONE:
 		evlist__for_each(evsel_list, counter)
-			print_counter(counter, NULL);
+			print_counter(counter, prefix);
 		break;
 	default:
 		break;
 	}
 
-	if (!csv_output) {
-		if (!null_run)
-			fprintf(output, "\n");
-		fprintf(output, " %17.9f seconds time elapsed",
-				avg_stats(&walltime_nsecs_stats)/1e9);
-		if (run_count > 1) {
-			fprintf(output, "                                        ");
-			print_noise_pct(stddev_stats(&walltime_nsecs_stats),
-					avg_stats(&walltime_nsecs_stats));
-		}
-		fprintf(output, "\n\n");
-	}
+	if (!interval && !csv_output)
+		print_footer();
+
+	fflush(output);
 }
 
 static volatile int signr = -1;
@@ -1091,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void)
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_THREAD:
 	default:
 		break;
 	}
@@ -1315,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &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()
@@ -1406,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	if ((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);
+		goto out;
+	}
+
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
@@ -1435,6 +1439,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		goto out;
 	}
+
+	/*
+	 * Initialize thread_map with comm names,
+	 * so we could print it out on output.
+	 */
+	if (aggr_mode == AGGR_THREAD)
+		thread_map__read_comms(evsel_list->threads);
+
 	if (interval && interval < 100) {
 		pr_err("print interval must be >= 100ms\n");
 		parse_options_usage(stat_usage, options, "I", 1);
@@ -1468,13 +1480,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 		status = run_perf_stat(argc, argv);
 		if (forever && status != -1) {
-			print_stat(argc, argv);
-			perf_stat__reset_stats(evsel_list);
+			print_counters(NULL, argc, argv);
+			perf_stat__reset_stats();
 		}
 	}
 
 	if (!forever && status != -1 && !interval)
-		print_stat(argc, argv);
+		print_counters(NULL, argc, argv);
 
 	perf_evlist__free_stats(evsel_list);
 out:
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 2bf2ca7..39ad4d0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1617,6 +1617,34 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	return syscall__set_arg_fmts(sc);
 }
 
+static int trace__validate_ev_qualifier(struct trace *trace)
+{
+	int err = 0;
+	struct str_node *pos;
+
+	strlist__for_each(pos, trace->ev_qualifier) {
+		const char *sc = pos->s;
+
+		if (audit_name_to_syscall(sc, trace->audit.machine) < 0) {
+			if (err == 0) {
+				fputs("Error:\tInvalid syscall ", trace->output);
+				err = -EINVAL;
+			} else {
+				fputs(", ", trace->output);
+			}
+
+			fputs(sc, trace->output);
+		}
+	}
+
+	if (err < 0) {
+		fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
+		      "\nHint:\tand: 'man syscalls'\n", trace->output);
+	}
+
+	return err;
+}
+
 /*
  * args is to be interpreted as a series of longs but we need to handle
  * 8-byte unaligned accesses. args points to raw_data within the event
@@ -2862,6 +2890,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			err = -ENOMEM;
 			goto out_close;
 		}
+
+		err = trace__validate_ev_qualifier(&trace);
+		if (err)
+			goto out_close;
 	}
 
 	err = target__validate(&trace.opts.target);
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index ee41e70..d20d6e6 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,6 +31,7 @@ perf-y += code-reading.o
 perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
+perf-y += thread-map.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 87b9961..c1dde73 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -171,6 +171,10 @@ static struct test {
 		.func = test__kmod_path__parse,
 	},
 	{
+		.desc = "Test thread map",
+		.func = test__thread_map,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index b8d552b..a572f87 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -78,7 +78,7 @@ int test__openat_syscall_event_on_all_cpus(void)
 	 * we use the auto allocation it will allocate just for 1 cpu,
 	 * as we start by cpu 0.
 	 */
-	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+	if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
 		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
 		goto out_close_fd;
 	}
@@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void)
 		}
 
 		expected = nr_openat_calls + cpu;
-		if (evsel->counts->cpu[cpu].val != expected) {
+		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
-				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
+				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
 			err = -1;
 		}
 	}
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index bdfa1f4..c9a37bc 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -44,9 +44,9 @@ int test__openat_syscall_event(void)
 		goto out_close_fd;
 	}
 
-	if (evsel->counts->cpu[0].val != nr_openat_calls) {
+	if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_openat_calls, evsel->counts->cpu[0].val);
+			 nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val);
 		goto out_close_fd;
 	}
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8e5038b..ebb47d9 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -61,6 +61,7 @@ int test__switch_tracking(void);
 int test__fdarray__filter(void);
 int test__fdarray__add(void);
 int test__kmod_path__parse(void);
+int test__thread_map(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
new file mode 100644
index 0000000..5acf000
--- /dev/null
+++ b/tools/perf/tests/thread-map.c
@@ -0,0 +1,38 @@
+#include <sys/types.h>
+#include <unistd.h>
+#include "tests.h"
+#include "thread_map.h"
+#include "debug.h"
+
+int test__thread_map(void)
+{
+	struct thread_map *map;
+
+	/* test map on current pid */
+	map = thread_map__new_by_pid(getpid());
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid",
+			thread_map__pid(map, 0) == getpid());
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "perf"));
+	thread_map__put(map);
+
+	/* test dummy pid */
+	map = thread_map__new_dummy();
+	TEST_ASSERT_VAL("failed to alloc map", map);
+
+	thread_map__read_comms(map);
+
+	TEST_ASSERT_VAL("wrong nr", map->nr == 1);
+	TEST_ASSERT_VAL("wrong pid", thread_map__pid(map, 0) == -1);
+	TEST_ASSERT_VAL("wrong comm",
+			thread_map__comm(map, 0) &&
+			!strcmp(thread_map__comm(map, 0), "dummy"));
+	thread_map__put(map);
+	return 0;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index a8489b9..037633c 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -289,5 +289,4 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
-
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1b2f480..2936b30 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -898,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -910,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = evsel->prev_raw_counts->cpu[cpu];
-		evsel->prev_raw_counts->cpu[cpu] = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -939,20 +939,18 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb)
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count)
 {
-	struct perf_counts_values count;
-
-	memset(&count, 0, sizeof(count));
+	memset(count, 0, sizeof(*count));
 
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
 		return -errno;
 
-	return cb(evsel, cpu, thread, &count);
+	return 0;
 }
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
@@ -964,15 +962,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	evsel->counts->cpu[cpu] = count;
+	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 4dbf32d..4a7ed56 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -9,23 +9,7 @@
 #include "xyarray.h"
 #include "symbol.h"
 #include "cpumap.h"
-
-struct perf_counts_values {
-	union {
-		struct {
-			u64 val;
-			u64 ena;
-			u64 run;
-		};
-		u64 values[3];
-	};
-};
-
-struct perf_counts {
-	s8		   	  scaled;
-	struct perf_counts_values aggr;
-	struct perf_counts_values cpu[];
-};
+#include "stat.h"
 
 struct perf_evsel;
 
@@ -128,7 +112,7 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
@@ -245,12 +229,8 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
-typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
-				    int cpu, int thread,
-				    struct perf_counts_values *count);
-
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb);
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count);
 
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5925fec..e23ded4 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -20,3 +20,4 @@ util/stat.c
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
+util/string.c
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4014b70..f2a0d15 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,8 @@
 #include <math.h>
 #include "stat.h"
+#include "evlist.h"
 #include "evsel.h"
+#include "thread_map.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -95,33 +97,46 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-struct perf_counts *perf_counts__new(int ncpus)
+struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
-	int size = sizeof(struct perf_counts) +
-		   ncpus * sizeof(struct perf_counts_values);
+	struct perf_counts *counts = zalloc(sizeof(*counts));
 
-	return zalloc(size);
+	if (counts) {
+		struct xyarray *values;
+
+		values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
+		if (!values) {
+			free(counts);
+			return NULL;
+		}
+
+		counts->values = values;
+	}
+
+	return counts;
 }
 
 void perf_counts__delete(struct perf_counts *counts)
 {
-	free(counts);
+	if (counts) {
+		xyarray__delete(counts->values);
+		free(counts);
+	}
 }
 
-static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+static void perf_counts__reset(struct perf_counts *counts)
 {
-	memset(counts, 0, (sizeof(*counts) +
-	       (ncpus * sizeof(struct perf_counts_values))));
+	xyarray__reset(counts->values);
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+void perf_evsel__reset_counts(struct perf_evsel *evsel)
 {
-	perf_counts__reset(evsel->counts, ncpus);
+	perf_counts__reset(evsel->counts);
 }
 
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
-	evsel->counts = perf_counts__new(ncpus);
+	evsel->counts = perf_counts__new(ncpus, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
@@ -130,3 +145,96 @@ void perf_evsel__free_counts(struct perf_evsel *evsel)
 	perf_counts__delete(evsel->counts);
 	evsel->counts = NULL;
 }
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
+}
+
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel->priv == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
+}
+
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads)
+{
+	struct perf_counts *counts;
+
+	counts = perf_counts__new(ncpus, nthreads);
+	if (counts)
+		evsel->prev_raw_counts = counts;
+
+	return counts ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
+}
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+{
+	int ncpus = perf_evsel__nr_cpus(evsel);
+	int nthreads = thread_map__nr(evsel->threads);
+
+	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+	    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		return -ENOMEM;
+
+	return 0;
+}
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (perf_evsel__alloc_stats(evsel, alloc_raw))
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	perf_evlist__free_stats(evlist);
+	return -1;
+}
+
+void perf_evlist__free_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__free_stat_priv(evsel);
+		perf_evsel__free_counts(evsel);
+		perf_evsel__free_prev_raw_counts(evsel);
+	}
+}
+
+void perf_evlist__reset_stats(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		perf_evsel__reset_stat_priv(evsel);
+		perf_evsel__reset_counts(evsel);
+	}
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 093dc3c..1cfbe0a 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <stdio.h>
+#include "xyarray.h"
 
 struct stats
 {
@@ -29,8 +30,32 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_THREAD,
 };
 
+struct perf_counts_values {
+	union {
+		struct {
+			u64 val;
+			u64 ena;
+			u64 run;
+		};
+		u64 values[3];
+	};
+};
+
+struct perf_counts {
+	s8			  scaled;
+	struct perf_counts_values aggr;
+	struct xyarray		  *values;
+};
+
+static inline struct perf_counts_values*
+perf_counts(struct perf_counts *counts, int cpu, int thread)
+{
+	return xyarray__entry(counts->values, cpu, thread);
+}
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -46,6 +71,8 @@ static inline void init_stats(struct stats *stats)
 }
 
 struct perf_evsel;
+struct perf_evlist;
+
 bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 			   enum perf_stat_evsel_id id);
 
@@ -62,10 +89,24 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				   double avg, int cpu, enum aggr_mode aggr);
 
-struct perf_counts *perf_counts__new(int ncpus);
+struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__reset_counts(struct perf_evsel *evsel);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads);
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+
+int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
+void perf_evlist__free_stats(struct perf_evlist *evlist);
+void perf_evlist__reset_stats(struct perf_evlist *evlist);
 #endif
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 504f2d7..48b588c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1132,8 +1132,11 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
-	if (fd < 0)
+	if (fd < 0) {
+		pr_err("%s requires CAP_SYS_RAWIO capability to access.\n",
+			kcore_filename);
 		return -EINVAL;
+	}
 
 	/* Read new maps into temporary lists */
 	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 368cc58..da7646d 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,9 +8,11 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
 #include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -21,11 +23,26 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static void thread_map__reset(struct thread_map *map, int start, int nr)
+{
+	size_t size = (nr - start) * sizeof(map->map[0]);
+
+	memset(&map->map[start], 0, size);
+}
+
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 {
 	size_t size = sizeof(*map) + sizeof(map->map[0]) * nr;
+	int start = map ? map->nr : 0;
 
-	return realloc(map, size);
+	map = realloc(map, size);
+	/*
+	 * We only realloc to add more items, let's reset new items.
+	 */
+	if (map)
+		thread_map__reset(map, start, nr);
+
+	return map;
 }
 
 #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
@@ -304,8 +321,12 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 static void thread_map__delete(struct thread_map *threads)
 {
 	if (threads) {
+		int i;
+
 		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
 			  "thread map refcnt unbalanced\n");
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
 		free(threads);
 	}
 }
@@ -333,3 +354,56 @@ size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
 
 	return printed + fprintf(fp, "\n");
 }
+
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		map->map[i].comm = strdup("dummy");
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	map->map[i].comm = comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads)
+{
+	int i;
+
+	for (i = 0; i < threads->nr; ++i)
+		comm_init(threads, i);
+}
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 6b0cd2d..af679d8 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -7,6 +7,7 @@
 
 struct thread_map_data {
 	pid_t    pid;
+	char	*comm;
 };
 
 struct thread_map {
@@ -44,4 +45,11 @@ thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
 {
 	map->map[thread].pid = pid;
 }
+
+static inline char *thread_map__comm(struct thread_map *map, int thread)
+{
+	return map->map[thread].comm;
+}
+
+void thread_map__read_comms(struct thread_map *threads);
 #endif	/* __PERF_THREAD_MAP_H */