perf record: Introduce --threads command line option

Provide --threads option in perf record command line interface.
The option creates a data streaming thread for each CPU in the system.
Document --threads option in Documentation/perf-record.txt.
Reviewed-by: Riccardo Mancini <rickyman7@gmail.com>
Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Riccardo Mancini <rickyman7@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Budankov <abudankov@huawei.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/01aeae43b047f428596c4ef9f9342ab94865cedd.1642440724.git.alexey.v.bayduraev@linux.intel.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-record.txt

@@ -713,6 +713,10 @@ measurements:
  wait -n ${perf_pid}
  exit $?
 
+--threads::
+Write collected trace data into several data files using parallel threads.
+The option creates a data streaming thread for each CPU in the system.
+
 include::intel-hybrid.txt[]
 
 --debuginfod[=URLs]::

tools/perf/builtin-record.c

@@ -127,6 +127,11 @@ static const char *thread_msg_tags[THREAD_MSG__MAX] = {
 	"UNDEFINED", "READY"
 };
 
+enum thread_spec {
+	THREAD_SPEC__UNDEFINED = 0,
+	THREAD_SPEC__CPU,
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -2768,6 +2773,16 @@ static void record__thread_mask_free(struct thread_mask *mask)
 	record__mmap_cpu_mask_free(&mask->affinity);
 }
 
+static int record__parse_threads(const struct option *opt, const char *str, int unset)
+{
+	struct record_opts *opts = opt->value;
+
+	if (unset || !str || !strlen(str))
+		opts->threads_spec = THREAD_SPEC__CPU;
+
+	return 0;
+}
+
 static int parse_output_max_size(const struct option *opt,
 				 const char *str, int unset)
 {
@@ -3242,6 +3257,9 @@ static struct option __record_options[] = {
 			  &record.debuginfod.set, "debuginfod urls",
 			  "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
 			  "system"),
+	OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec",
+			    "write collected trace data into several data files using parallel threads",
+			    record__parse_threads),
 	OPT_END()
 };
 
@@ -3292,6 +3310,31 @@ static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr
 	return ret;
 }
 
+static int record__init_thread_cpu_masks(struct record *rec, struct perf_cpu_map *cpus)
+{
+	int t, ret, nr_cpus = perf_cpu_map__nr(cpus);
+
+	ret = record__alloc_thread_masks(rec, nr_cpus, cpu__max_cpu().cpu);
+	if (ret)
+		return ret;
+
+	rec->nr_threads = nr_cpus;
+	pr_debug("nr_threads: %d\n", rec->nr_threads);
+
+	for (t = 0; t < rec->nr_threads; t++) {
+		set_bit(cpus->map[t].cpu, rec->thread_masks[t].maps.bits);
+		set_bit(cpus->map[t].cpu, rec->thread_masks[t].affinity.bits);
+		if (verbose) {
+			pr_debug("thread_masks[%d]: ", t);
+			mmap_cpu_mask__scnprintf(&rec->thread_masks[t].maps, "maps");
+			pr_debug("thread_masks[%d]: ", t);
+			mmap_cpu_mask__scnprintf(&rec->thread_masks[t].affinity, "affinity");
+		}
+	}
+
+	return 0;
+}
+
 static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
 {
 	int ret;
@@ -3311,7 +3354,10 @@ static int record__init_thread_masks(struct record *rec)
 {
 	struct perf_cpu_map *cpus = rec->evlist->core.cpus;
 
-	return record__init_thread_default_masks(rec, cpus);
+	if (!record__threads_enabled(rec))
+		return record__init_thread_default_masks(rec, cpus);
+
+	return record__init_thread_cpu_masks(rec, cpus);
 }
 
 int cmd_record(int argc, const char **argv)