Merge tag 'perf-core-for-mingo' of...

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>

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

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)

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);

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
 

tools/perf/tests/builtin-test.c

@@ -170,6 +170,10 @@ static struct test {
 		.desc = "Test kmod_path__parse function",
 		.func = test__kmod_path__parse,
 	},
+	{
+		.desc = "Test thread map",
+		.func = test__thread_map,
+	},
 	{
 		.func = NULL,
 	},

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;
 		}
 	}

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;
 	}
 

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

tools/perf/tests/thread-map.c

+#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;
+}

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 */

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;
 }
 

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);

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

tools/perf/util/stat.c

 #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);
+	}
+}

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

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,

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);
+}

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 */