perf test: Add 'brstack' test workload

The brstack is to run different kinds of branches repeatedly.  This is
necessary for brstack test case to verify if it has correct branch info.

  $ perf test -w brstack

I renamed the internal functions to have brstack_ prefix as it's too
generic name.

Add a -U_FORTIFY_SOURCE to the brstack CFLAGS, as the main perf flags
set it and it requires building with optimization, and this new test has
a -O0.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221116233854.1596378-10-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/tests/builtin-test.c

@@ -123,6 +123,7 @@ static struct test_workload *workloads[] = {
 	&workload__thloop,
 	&workload__leafloop,
 	&workload__sqrtloop,
+	&workload__brstack,
 };
 
 static int num_subtests(const struct test_suite *t)

tools/perf/tests/tests.h

@@ -204,5 +204,6 @@ DECLARE_WORKLOAD(noploop);
 DECLARE_WORKLOAD(thloop);
 DECLARE_WORKLOAD(leafloop);
 DECLARE_WORKLOAD(sqrtloop);
+DECLARE_WORKLOAD(brstack);
 
 #endif /* TESTS_H */

tools/perf/tests/workloads/Build

@@ -4,6 +4,8 @@ perf-y += noploop.o
 perf-y += thloop.o
 perf-y += leafloop.o
 perf-y += sqrtloop.o
+perf-y += brstack.o
 
 CFLAGS_sqrtloop.o         = -g -O0 -fno-inline -U_FORTIFY_SOURCE
 CFLAGS_leafloop.o         = -g -O0 -fno-inline -fno-omit-frame-pointer -U_FORTIFY_SOURCE
+CFLAGS_brstack.o          = -g -O0 -fno-inline -U_FORTIFY_SOURCE

tools/perf/tests/workloads/brstack.c

@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include "../tests.h"
+
+#define BENCH_RUNS 999999
+
+static volatile int cnt;
+
+static void brstack_bar(void) {
+}				/* return */
+
+static void brstack_foo(void) {
+	brstack_bar();		/* call */
+}				/* return */
+
+static void brstack_bench(void) {
+	void (*brstack_foo_ind)(void) = brstack_foo;
+
+	if ((cnt++) % 3)	/* branch (cond) */
+		brstack_foo();	/* call */
+	brstack_bar();		/* call */
+	brstack_foo_ind();	/* call (ind) */
+}
+
+static int brstack(int argc, const char **argv)
+{
+	int num_loops = BENCH_RUNS;
+
+	if (argc > 0)
+		num_loops = atoi(argv[0]);
+
+	while (1) {
+		if ((cnt++) > num_loops)
+			break;
+		brstack_bench();/* call */
+	}			/* branch (uncond) */
+	return 0;
+}
+
+DEFINE_WORKLOAD(brstack);