1 files changed, 126 insertions, 82 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 34bb31f08bb5..ff7e1d6cfcd2 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -270,7 +270,7 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 static int record__aio_enabled(struct record *rec);
 static int record__comp_enabled(struct record *rec);
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
@@ -405,9 +405,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 */
 
 	if (record__comp_enabled(aio->rec)) {
-		size = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
-				     buf, size);
+		ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
+						   mmap__mmap_len(map) - aio->size,
+						   buf, size);
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -633,7 +637,13 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map, map->data, mmap__mmap_len(map), bf, size);
+		ssize_t compressed = zstd_compress(rec->session, map, map->data,
+						   mmap__mmap_len(map), bf, size);
+
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 		bf   = map->data;
 	}
 
@@ -906,6 +916,65 @@ static int record__config_off_cpu(struct record *rec)
 	return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
 }
 
+static bool record__tracking_system_wide(struct record *rec)
+{
+	struct evlist *evlist = rec->evlist;
+	struct evsel *evsel;
+
+	/*
+	 * If non-dummy evsel exists, system_wide sideband is need to
+	 * help parse sample information.
+	 * For example, PERF_EVENT_MMAP event to help parse symbol,
+	 * and PERF_EVENT_COMM event to help parse task executable name.
+	 */
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel__is_dummy_event(evsel))
+			return true;
+	}
+
+	return false;
+}
+
+static int record__config_tracking_events(struct record *rec)
+{
+	struct record_opts *opts = &rec->opts;
+	struct evlist *evlist = rec->evlist;
+	bool system_wide = false;
+	struct evsel *evsel;
+
+	/*
+	 * For initial_delay, system wide or a hybrid system, we need to add
+	 * tracking event so that we can track PERF_RECORD_MMAP to cover the
+	 * delay of waiting or event synthesis.
+	 */
+	if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
+	    perf_pmus__num_core_pmus() > 1) {
+
+		/*
+		 * User space tasks can migrate between CPUs, so when tracing
+		 * selected CPUs, sideband for all CPUs is still needed.
+		 */
+		if (!!opts->target.cpu_list && record__tracking_system_wide(rec))
+			system_wide = true;
+
+		evsel = evlist__findnew_tracking_event(evlist, system_wide);
+		if (!evsel)
+			return -ENOMEM;
+
+		/*
+		 * Enable the tracking event when the process is forked for
+		 * initial_delay, immediately for system wide.
+		 */
+		if (opts->target.initial_delay && !evsel->immediate &&
+		    !target__has_cpu(&opts->target))
+			evsel->core.attr.enable_on_exec = 1;
+		else
+			evsel->immediate = 1;
+	}
+
+	return 0;
+}
+
 static bool record__kcore_readable(struct machine *machine)
 {
 	char kcore[PATH_MAX];
@@ -1286,39 +1355,12 @@ static int record__open(struct record *rec)
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	/*
-	 * For initial_delay, system wide or a hybrid system, we need to add a
-	 * dummy event so that we can track PERF_RECORD_MMAP to cover the delay
-	 * of waiting or event synthesis.
-	 */
-	if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
-	    perf_pmus__num_core_pmus() > 1) {
-		pos = evlist__get_tracking_event(evlist);
-		if (!evsel__is_dummy_event(pos)) {
-			/* Set up dummy event. */
-			if (evlist__add_dummy(evlist))
-				return -ENOMEM;
-			pos = evlist__last(evlist);
-			evlist__set_tracking_event(evlist, pos);
-		}
-
-		/*
-		 * Enable the dummy event when the process is forked for
-		 * initial_delay, immediately for system wide.
-		 */
-		if (opts->target.initial_delay && !pos->immediate &&
-		    !target__has_cpu(&opts->target))
-			pos->core.attr.enable_on_exec = 1;
-		else
-			pos->immediate = 1;
-	}
-
 	evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
-			if (evsel__fallback(pos, errno, msg, sizeof(msg))) {
+			if (evsel__fallback(pos, &opts->target, errno, msg, sizeof(msg))) {
 				if (verbose > 0)
 					ui__warning("%s\n", msg);
 				goto try_again;
@@ -1495,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
-	size_t compressed;
+	ssize_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
@@ -1507,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map,
 
 	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
+	if (compressed < 0)
+		return compressed;
 
 	if (map && map->file) {
 		thread->bytes_transferred += src_size;
@@ -1729,8 +1773,11 @@ record__finish_output(struct record *rec)
 	struct perf_data *data = &rec->data;
 	int fd = perf_data__fd(data);
 
-	if (data->is_pipe)
+	if (data->is_pipe) {
+		/* Just to display approx. size */
+		data->file.size = rec->bytes_written;
 		return;
+	}
 
 	rec->session->header.data_size += rec->bytes_written;
 	data->file.size = lseek(perf_data__fd(data), 0, SEEK_CUR);
@@ -1786,8 +1833,8 @@ static int
 record__switch_output(struct record *rec, bool at_exit)
 {
 	struct perf_data *data = &rec->data;
+	char *new_filename = NULL;
 	int fd, err;
-	char *new_filename;
 
 	/* Same Size:      "2015122520103046"*/
 	char timestamp[] = "InvalidTimestamp";
@@ -1809,16 +1856,17 @@ record__switch_output(struct record *rec, bool at_exit)
 	}
 
 	fd = perf_data__switch(data, timestamp,
-				    rec->session->header.data_offset,
-				    at_exit, &new_filename);
+			       rec->session->header.data_offset,
+			       at_exit, &new_filename);
 	if (fd >= 0 && !at_exit) {
 		rec->bytes_written = 0;
 		rec->session->header.data_size = 0;
 	}
 
-	if (!quiet)
+	if (!quiet) {
 		fprintf(stderr, "[ perf record: Dump %s.%s ]\n",
 			data->path, timestamp);
+	}
 
 	if (rec->switch_output.num_files) {
 		int n = rec->switch_output.cur_file + 1;
@@ -1880,21 +1928,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
 static void record__read_lost_samples(struct record *rec)
 {
 	struct perf_session *session = rec->session;
-	struct perf_record_lost_samples *lost;
+	struct perf_record_lost_samples *lost = NULL;
 	struct evsel *evsel;
 
 	/* there was an error during record__open */
 	if (session->evlist == NULL)
 		return;
 
-	lost = zalloc(PERF_SAMPLE_MAX_SIZE);
-	if (lost == NULL) {
-		pr_debug("Memory allocation failed\n");
-		return;
-	}
-
-	lost->header.type = PERF_RECORD_LOST_SAMPLES;
-
 	evlist__for_each_entry(session->evlist, evsel) {
 		struct xyarray *xy = evsel->core.sample_id;
 		u64 lost_count;
@@ -1917,6 +1957,15 @@ static void record__read_lost_samples(struct record *rec)
 				}
 
 				if (count.lost) {
+					if (!lost) {
+						lost = zalloc(sizeof(*lost) +
+							      session->machines.host.id_hdr_size);
+						if (!lost) {
+							pr_debug("Memory allocation failed\n");
+							return;
+						}
+						lost->header.type = PERF_RECORD_LOST_SAMPLES;
+					}
 					__record__save_lost_samples(rec, evsel, lost,
 								    x, y, count.lost, 0);
 				}
@@ -1924,9 +1973,19 @@ static void record__read_lost_samples(struct record *rec)
 		}
 
 		lost_count = perf_bpf_filter__lost_count(evsel);
-		if (lost_count)
+		if (lost_count) {
+			if (!lost) {
+				lost = zalloc(sizeof(*lost) +
+					      session->machines.host.id_hdr_size);
+				if (!lost) {
+					pr_debug("Memory allocation failed\n");
+					return;
+				}
+				lost->header.type = PERF_RECORD_LOST_SAMPLES;
+			}
 			__record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
 						    PERF_RECORD_MISC_LOST_SAMPLES_BPF);
+		}
 	}
 out:
 	free(lost);
@@ -2184,32 +2243,6 @@ static void hit_auxtrace_snapshot_trigger(struct record *rec)
 	}
 }
 
-static void record__uniquify_name(struct record *rec)
-{
-	struct evsel *pos;
-	struct evlist *evlist = rec->evlist;
-	char *new_name;
-	int ret;
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return;
-
-	evlist__for_each_entry(evlist, pos) {
-		if (!evsel__is_hybrid(pos))
-			continue;
-
-		if (strchr(pos->name, '/'))
-			continue;
-
-		ret = asprintf(&new_name, "%s/%s/",
-			       pos->pmu_name, pos->name);
-		if (ret) {
-			free(pos->name);
-			pos->name = new_name;
-		}
-	}
-}
-
 static int record__terminate_thread(struct record_thread *thread_data)
 {
 	int err;
@@ -2443,7 +2476,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	if (data->is_pipe && rec->evlist->core.nr_entries == 1)
 		rec->opts.sample_id = true;
 
-	record__uniquify_name(rec);
+	if (rec->timestamp_filename && perf_data__is_pipe(data)) {
+		rec->timestamp_filename = false;
+		pr_warning("WARNING: --timestamp-filename option is not available in pipe mode.\n");
+	}
+
+	evlist__uniquify_name(rec->evlist);
 
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
@@ -3548,9 +3586,7 @@ static int record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cp
 	if (cpu_map__is_dummy(cpus))
 		return 0;
 
-	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
-		if (cpu.cpu == -1)
-			continue;
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpus) {
 		/* Return ENODEV is input cpu is greater than max cpu */
 		if ((unsigned long)cpu.cpu > mask->nbits)
 			return -ENODEV;
@@ -3957,6 +3993,8 @@ int cmd_record(int argc, const char **argv)
 # undef set_nobuild
 #endif
 
+	/* Disable eager loading of kernel symbols that adds overhead to perf record. */
+	symbol_conf.lazy_load_kernel_maps = true;
 	rec->opts.affinity = PERF_AFFINITY_SYS;
 
 	rec->evlist = evlist__new();
@@ -4051,8 +4089,8 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	if (rec->switch_output.num_files) {
-		rec->switch_output.filenames = calloc(sizeof(char *),
-						      rec->switch_output.num_files);
+		rec->switch_output.filenames = calloc(rec->switch_output.num_files,
+						      sizeof(char *));
 		if (!rec->switch_output.filenames) {
 			err = -EINVAL;
 			goto out_opts;
@@ -4195,6 +4233,12 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
+	err = record__config_tracking_events(rec);
+	if (err) {
+		pr_err("record__config_tracking_events failed, error %d\n", err);
+		goto out;
+	}
+
 	err = record__init_thread_masks(rec);
 	if (err) {
 		pr_err("Failed to initialize parallel data streaming masks\n");