diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 517520ae1520..8766a3dc9440 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -205,12 +205,16 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 {
 	struct perf_data_file *file = &rec->session->data->file;
 
+	if (map && map->file)
+		file = map->file;
+
 	if (perf_data_file__write(file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
 
-	rec->bytes_written += size;
+	if (!(map && map->file))
+		rec->bytes_written += size;
 
 	if (record__output_max_size_exceeded(rec) && !done) {
 		fprintf(stderr, "[ perf record: perf size limit reached (%" PRIu64 " KB),"
@@ -1103,7 +1107,7 @@ static int record__alloc_thread_data(struct record *rec, struct evlist *evlist)
 static int record__mmap_evlist(struct record *rec,
 			       struct evlist *evlist)
 {
-	int ret;
+	int i, ret;
 	struct record_opts *opts = &rec->opts;
 	bool auxtrace_overwrite = opts->auxtrace_snapshot_mode ||
 				  opts->auxtrace_sample_mode;
@@ -1142,6 +1146,18 @@ static int record__mmap_evlist(struct record *rec,
 	if (ret)
 		return ret;
 
+	if (record__threads_enabled(rec)) {
+		ret = perf_data__create_dir(&rec->data, evlist->core.nr_mmaps);
+		if (ret)
+			return ret;
+		for (i = 0; i < evlist->core.nr_mmaps; i++) {
+			if (evlist->mmap)
+				evlist->mmap[i].file = &rec->data.dir.files[i];
+			if (evlist->overwrite_mmap)
+				evlist->overwrite_mmap[i].file = &rec->data.dir.files[i];
+		}
+	}
+
 	return 0;
 }
 
@@ -1448,8 +1464,12 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 	/*
 	 * Mark the round finished in case we wrote
 	 * at least one event.
+	 *
+	 * No need for round events in directory mode,
+	 * because per-cpu maps and files have data
+	 * sorted by kernel.
 	 */
-	if (bytes_written != rec->bytes_written)
+	if (!record__threads_enabled(rec) && bytes_written != rec->bytes_written)
 		rc = record__write(rec, NULL, &finished_round_event, sizeof(finished_round_event));
 
 	if (overwrite)
@@ -1566,7 +1586,9 @@ static void record__init_features(struct record *rec)
 	if (!rec->opts.use_clockid)
 		perf_header__clear_feat(&session->header, HEADER_CLOCK_DATA);
 
-	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
+	if (!record__threads_enabled(rec))
+		perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
+
 	if (!record__comp_enabled(rec))
 		perf_header__clear_feat(&session->header, HEADER_COMPRESSED);
 
@@ -1576,6 +1598,7 @@ static void record__init_features(struct record *rec)
 static void
 record__finish_output(struct record *rec)
 {
+	int i;
 	struct perf_data *data = &rec->data;
 	int fd = perf_data__fd(data);
 
@@ -1584,6 +1607,10 @@ record__finish_output(struct record *rec)
 
 	rec->session->header.data_size += rec->bytes_written;
 	data->file.size = lseek(perf_data__fd(data), 0, SEEK_CUR);
+	if (record__threads_enabled(rec)) {
+		for (i = 0; i < data->dir.nr; i++)
+			data->dir.files[i].size = lseek(data->dir.files[i].fd, 0, SEEK_CUR);
+	}
 
 	if (!rec->no_buildid) {
 		process_buildids(rec);
@@ -3330,7 +3357,7 @@ int cmd_record(int argc, const char **argv)
 		goto out_opts;
 	}
 
-	if (rec->opts.kcore)
+	if (rec->opts.kcore || record__threads_enabled(rec))
 		rec->data.is_dir = true;
 
 	if (rec->opts.comp_level != 0) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 83f6bd4d4082..62f38d7977bb 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -45,6 +45,7 @@ struct mmap {
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
 	int		comp_level;
+	struct perf_data_file *file;
 };
 
 struct mmap_params {