perf test: Add named_threads workload

Add a workload that runs X threads that run a unique function named
"named_threads_thread[x]" which performs a multiplication in a loop for
Y loops. Each thread sets its name to "thread[x]".

This can be used to test that processor trace decoding handles
concurrent threads correctly and the correct symbols and thread names
are assigned to samples.

Signed-off-by: James Clark <james.clark@linaro.org>
Cc: Amir Ayupov <aaupov@meta.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Mike Leach <mike.leach@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paschalis Mpeis <Paschalis.Mpeis@arm.com>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/Documentation/perf-test.txt

@@ -57,7 +57,7 @@ OPTIONS
 --workload=::
 	Run a built-in workload, to list them use '--list-workloads', current
 	ones include: noploop, thloop, leafloop, sqrtloop, brstack, datasym,
-	context_switch_loop, deterministic and landlock.
+	context_switch_loop, deterministic, named_threads and landlock.
 
 	Used with the shell script regression tests.
 
@@ -66,6 +66,9 @@ OPTIONS
 		seconds: leafloop, noploop, sqrtloop, thloop
 		nrloops: brstack, context_switch_loop
 
+	'named_threads' accepts the number of threads and the number of loops to
+	do in each thread.
+
 	The datasym, landlock and deterministic workloads don't accept any.
 
 --list-workloads::

tools/perf/tests/builtin-test.c

@@ -155,6 +155,7 @@ static struct test_suite *generic_tests[] = {
 static struct test_workload *workloads[] = {
 	&workload__noploop,
 	&workload__thloop,
+	&workload__named_threads,
 	&workload__leafloop,
 	&workload__sqrtloop,
 	&workload__brstack,

tools/perf/tests/tests.h

@@ -237,6 +237,7 @@ struct test_workload workload__##work = {	\
 /* The list of test workloads */
 DECLARE_WORKLOAD(noploop);
 DECLARE_WORKLOAD(thloop);
+DECLARE_WORKLOAD(named_threads);
 DECLARE_WORKLOAD(leafloop);
 DECLARE_WORKLOAD(sqrtloop);
 DECLARE_WORKLOAD(brstack);

tools/perf/tests/workloads/Build

@@ -2,6 +2,7 @@
 
 perf-test-y += noploop.o
 perf-test-y += thloop.o
+perf-test-y += named_threads.o
 perf-test-y += leafloop.o
 perf-test-y += sqrtloop.o
 perf-test-y += brstack.o

tools/perf/tests/workloads/named_threads.c

@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <limits.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/compiler.h>
+#include "../tests.h"
+
+#define MAX_THREADS 25
+
+static int iterations = 500;
+int named_threads_work = 1234;
+
+typedef void *(*thread_fn_t)(void *);
+
+#define DEFINE_THREAD(n)						\
+noinline void *named_threads_thread##n(void *arg __maybe_unused)	\
+{									\
+	pthread_setname_np(pthread_self(), "thread" #n);		\
+	for (int i = 0; i < iterations; i++)				\
+		named_threads_work += 3;				\
+									\
+	return NULL;							\
+}
+
+#define THREAD_LIST(macro)	\
+	macro(1)		\
+	macro(2)		\
+	macro(3)		\
+	macro(4)		\
+	macro(5)		\
+	macro(6)		\
+	macro(7)		\
+	macro(8)		\
+	macro(9)		\
+	macro(10)		\
+	macro(11)		\
+	macro(12)		\
+	macro(13)		\
+	macro(14)		\
+	macro(15)		\
+	macro(16)		\
+	macro(17)		\
+	macro(18)		\
+	macro(19)		\
+	macro(20)		\
+	macro(21)		\
+	macro(22)		\
+	macro(23)		\
+	macro(24)		\
+	macro(25)
+
+#define DECLARE_THREAD(n) void *named_threads_thread##n(void *arg);
+
+THREAD_LIST(DECLARE_THREAD)
+THREAD_LIST(DEFINE_THREAD)
+
+#define THREAD_ENTRY(n) named_threads_thread##n,
+
+static thread_fn_t thread_fns[MAX_THREADS] = {
+	THREAD_LIST(THREAD_ENTRY)
+};
+
+/*
+ * Creates argv[0] threads that run a unique function named "thread[x]" which performs
+ * a multiplication in a loop for argv[1] loops.
+ */
+static int named_threads(int argc, const char **argv)
+{
+	pthread_t threads[MAX_THREADS];
+	int nr_threads = 1;
+	int err = 0;
+
+	if (argc > 0)
+		nr_threads = atoi(argv[0]);
+
+	if (nr_threads <= 0 || nr_threads > MAX_THREADS) {
+		fprintf(stderr, "Error: num threads must be 1 - %d\n", MAX_THREADS);
+		return 1;
+	}
+
+	if (argc > 1)
+		iterations = atoi(argv[1]);
+
+	if (iterations < 0) {
+		fprintf(stderr, "Error: iterations must be non-negative\n");
+		return 1;
+	}
+
+	for (int i = 0; i < nr_threads; i++) {
+		int ret;
+
+		ret = pthread_create(&threads[i], NULL, thread_fns[i], NULL);
+		if (ret) {
+			fprintf(stderr, "Error: failed to create thread%d: %s\n",
+				i + 1, strerror(ret));
+			return 1;
+		}
+	}
+
+	for (int i = 0; i < nr_threads; i++)
+		pthread_join(threads[i], NULL);
+
+	return err;
+}
+
+DEFINE_WORKLOAD(named_threads);