[PATCH v3 18/18] vfio: selftests: Add vfio_pci_device_init_perf_test

[David Matlack <dmatlack@google.com>]

Add a new VFIO selftest for measuring the time it takes to run
vfio_pci_device_init() in parallel for one or more devices.

This test serves as manual regression test for the performance
improvement of commit e908f58b6beb ("vfio/pci: Separate SR-IOV VF
dev_set"). For example, when running this test with 64 VFs under the
same PF:

Before:

  $ ./vfio_pci_device_init_perf_test -r vfio_pci_device_init_perf_test.iommufd.init 0000:1a:00.0 0000:1a:00.1 ...
  ...
  Wall time: 6.653234463s
  Min init time (per device): 0.101215344s
  Max init time (per device): 6.652755941s
  Avg init time (per device): 3.377609608s

After:

  $ ./vfio_pci_device_init_perf_test -r vfio_pci_device_init_perf_test.iommufd.init 0000:1a:00.0 0000:1a:00.1 ...
  ...
  Wall time: 0.122978332s
  Min init time (per device): 0.108121915s
  Max init time (per device): 0.122762761s
  Avg init time (per device): 0.113816748s

This test does not make any assertions about performance, since any such
assertion is likely to be flaky due to system differences and random
noise. However this test can be fed into automation to detect
regressions, and can be used by developers in the future to measure
performance optimizations.

Suggested-by: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: Alex Mastro <amastro@fb.com>
Tested-by: Alex Mastro <amastro@fb.com>
Signed-off-by: David Matlack <dmatlack@google.com>
---
 tools/testing/selftests/vfio/Makefile         |   3 +
 .../vfio/vfio_pci_device_init_perf_test.c     | 168 ++++++++++++++++++
 2 files changed, 171 insertions(+)
 create mode 100644 tools/testing/selftests/vfio/vfio_pci_device_init_perf_test.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index a29f99395206..3c796ca99a50 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -2,6 +2,7 @@ CFLAGS = $(KHDR_INCLUDES)
 TEST_GEN_PROGS += vfio_dma_mapping_test
 TEST_GEN_PROGS += vfio_iommufd_setup_test
 TEST_GEN_PROGS += vfio_pci_device_test
+TEST_GEN_PROGS += vfio_pci_device_init_perf_test
 TEST_GEN_PROGS += vfio_pci_driver_test
 
 TEST_FILES += scripts/cleanup.sh
@@ -16,6 +17,8 @@ CFLAGS += -I$(top_srcdir)/tools/include
 CFLAGS += -MD
 CFLAGS += $(EXTRA_CFLAGS)
 
+LDFLAGS += -pthread
+
 $(TEST_GEN_PROGS): %: %.o $(LIBVFIO_O)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $< $(LIBVFIO_O) $(LDLIBS) -o $@
 
diff --git a/tools/testing/selftests/vfio/vfio_pci_device_init_perf_test.c b/tools/testing/selftests/vfio/vfio_pci_device_init_perf_test.c
new file mode 100644
index 000000000000..33b0c31fe2ed
--- /dev/null
+++ b/tools/testing/selftests/vfio/vfio_pci_device_init_perf_test.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <pthread.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+
+#include <linux/sizes.h>
+#include <linux/time64.h>
+#include <linux/vfio.h>
+
+#include <libvfio.h>
+
+#include "../kselftest_harness.h"
+
+static char **device_bdfs;
+static int nr_devices;
+
+struct thread_args {
+	struct iommu *iommu;
+	int device_index;
+	struct timespec start;
+	struct timespec end;
+	pthread_barrier_t *barrier;
+};
+
+FIXTURE(vfio_pci_device_init_perf_test) {
+	pthread_t *threads;
+	pthread_barrier_t barrier;
+	struct thread_args *thread_args;
+	struct iommu *iommu;
+};
+
+FIXTURE_VARIANT(vfio_pci_device_init_perf_test) {
+	const char *iommu_mode;
+};
+
+#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode)			\
+FIXTURE_VARIANT_ADD(vfio_pci_device_init_perf_test, _iommu_mode) {	\
+	.iommu_mode = #_iommu_mode,					\
+}
+
+FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES();
+
+FIXTURE_SETUP(vfio_pci_device_init_perf_test)
+{
+	int i;
+
+	self->iommu = iommu_init(variant->iommu_mode);
+	self->threads = calloc(nr_devices, sizeof(self->threads[0]));
+	self->thread_args = calloc(nr_devices, sizeof(self->thread_args[0]));
+
+	pthread_barrier_init(&self->barrier, NULL, nr_devices);
+
+	for (i = 0; i < nr_devices; i++) {
+		self->thread_args[i].iommu = self->iommu;
+		self->thread_args[i].barrier = &self->barrier;
+		self->thread_args[i].device_index = i;
+	}
+}
+
+FIXTURE_TEARDOWN(vfio_pci_device_init_perf_test)
+{
+	iommu_cleanup(self->iommu);
+	free(self->threads);
+	free(self->thread_args);
+}
+
+static s64 to_ns(struct timespec ts)
+{
+	return (s64)ts.tv_nsec + NSEC_PER_SEC * (s64)ts.tv_sec;
+}
+
+static struct timespec to_timespec(s64 ns)
+{
+	struct timespec ts = {
+		.tv_nsec = ns % NSEC_PER_SEC,
+		.tv_sec = ns / NSEC_PER_SEC,
+	};
+
+	return ts;
+}
+
+static struct timespec timespec_sub(struct timespec a, struct timespec b)
+{
+	return to_timespec(to_ns(a) - to_ns(b));
+}
+
+static struct timespec timespec_min(struct timespec a, struct timespec b)
+{
+	return to_ns(a) < to_ns(b) ? a : b;
+}
+
+static struct timespec timespec_max(struct timespec a, struct timespec b)
+{
+	return to_ns(a) > to_ns(b) ? a : b;
+}
+
+static void *thread_main(void *__args)
+{
+	struct thread_args *args = __args;
+	struct vfio_pci_device *device;
+
+	pthread_barrier_wait(args->barrier);
+
+	clock_gettime(CLOCK_MONOTONIC, &args->start);
+	device = vfio_pci_device_init(device_bdfs[args->device_index], args->iommu);
+	clock_gettime(CLOCK_MONOTONIC, &args->end);
+
+	pthread_barrier_wait(args->barrier);
+
+	vfio_pci_device_cleanup(device);
+	return NULL;
+}
+
+TEST_F(vfio_pci_device_init_perf_test, init)
+{
+	struct timespec start = to_timespec(INT64_MAX), end = {};
+	struct timespec min = to_timespec(INT64_MAX);
+	struct timespec max = {};
+	struct timespec avg = {};
+	struct timespec wall_time;
+	s64 thread_ns = 0;
+	int i;
+
+	for (i = 0; i < nr_devices; i++) {
+		pthread_create(&self->threads[i], NULL, thread_main,
+			       &self->thread_args[i]);
+	}
+
+	for (i = 0; i < nr_devices; i++) {
+		struct thread_args *args = &self->thread_args[i];
+		struct timespec init_time;
+
+		pthread_join(self->threads[i], NULL);
+
+		start = timespec_min(start, args->start);
+		end = timespec_max(end, args->end);
+
+		init_time = timespec_sub(args->end, args->start);
+		min = timespec_min(min, init_time);
+		max = timespec_max(max, init_time);
+		thread_ns += to_ns(init_time);
+	}
+
+	avg = to_timespec(thread_ns / nr_devices);
+	wall_time = timespec_sub(end, start);
+
+	printf("Wall time: %lu.%09lus\n",
+	       wall_time.tv_sec, wall_time.tv_nsec);
+	printf("Min init time (per device): %lu.%09lus\n",
+	       min.tv_sec, min.tv_nsec);
+	printf("Max init time (per device): %lu.%09lus\n",
+	       max.tv_sec, max.tv_nsec);
+	printf("Avg init time (per device): %lu.%09lus\n",
+	       avg.tv_sec, avg.tv_nsec);
+}
+
+int main(int argc, char *argv[])
+{
+	int i;
+
+	device_bdfs = vfio_selftests_get_bdfs(&argc, argv, &nr_devices);
+
+	printf("Testing parallel initialization of %d devices:\n", nr_devices);
+	for (i = 0; i < nr_devices; i++)
+		printf("    %s\n", device_bdfs[i]);
+
+	return test_harness_run(argc, argv);
+}
-- 
2.52.0.rc2.455.g230fcf2819-goog