[PATCH v2 2/4] vfio: selftests: Introduce vfio_dma_mapping_perf_test

Introduce vfio_dma_mapping_perf_test to aid in latency testing. Rather
than a traditional pass/fail test, which tends to be flaky when
enforcing latency bounds, this test directly reports the latency of
various stages in the mapping and unmapping process.

Start with a basic test that performs a simple DMA map/unmap and tracks
the duration of each operation. The test reports the following metrics:

1. Time taken by mmap().
2. Time taken to map a DMA region.
3. Time taken to unmap a DMA region.
4. Time taken by munmap().

Subsequent commits in this series will introduce more features to allow
for a wider variety of testing.

To ensure consistent DMA mapping times, the test uses MAP_POPULATE when
calling mmap(). This forces page faults to be handled upfront, isolating
the DMA mapping times from them.

Signed-off-by: Aaron Lewis <[email protected]>
---
 tools/testing/selftests/vfio/Makefile         |  1 +
 .../selftests/vfio/lib/include/libvfio.h      | 28 ++++++
 .../vfio/vfio_dma_mapping_perf_test.c         | 90 +++++++++++++++++++
 3 files changed, 119 insertions(+)
 create mode 100644 tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile
index 2c32c48db509..ed5856af5f9a 100644
--- a/tools/testing/selftests/vfio/Makefile
+++ b/tools/testing/selftests/vfio/Makefile
@@ -8,6 +8,7 @@ else
 CFLAGS = $(KHDR_INCLUDES)
 TEST_GEN_PROGS += vfio_dma_mapping_test
 TEST_GEN_PROGS += vfio_dma_mapping_mmio_test
+TEST_GEN_PROGS += vfio_dma_mapping_perf_test
 TEST_GEN_PROGS += vfio_iommufd_setup_test
 TEST_GEN_PROGS += vfio_pci_device_test
 TEST_GEN_PROGS += vfio_pci_device_init_perf_test
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio.h b/tools/testing/selftests/vfio/lib/include/libvfio.h
index 07862b470777..cf322b499cfb 100644
--- a/tools/testing/selftests/vfio/lib/include/libvfio.h
+++ b/tools/testing/selftests/vfio/lib/include/libvfio.h
@@ -9,6 +9,34 @@
 #include <libvfio/vfio_pci_device.h>
 #include <libvfio/vfio_pci_driver.h>
 
+#include <stdint.h>
+#include <time.h>
+#include <linux/time64.h>
+
+static inline void timer_start(struct timespec *start)
+{
+	clock_gettime(CLOCK_MONOTONIC, start);
+}
+
+static inline uint64_t timer_elapsed_ns(struct timespec start)
+{
+	struct timespec end;
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+
+	return (uint64_t)(end.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (uint64_t)(end.tv_nsec - start.tv_nsec);
+}
+
+#define TIME(_name, _expression) do {				   \
+	struct timespec __start;				   \
+								   \
+	timer_start(&__start);					   \
+	_expression;						   \
+	printf(_name " = %.2lfms\n",				   \
+	       (double)timer_elapsed_ns(__start) / NSEC_PER_MSEC); \
+} while (0)
+
 /*
  * Return the BDF string of the device that the test should use.
  *
diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c
new file mode 100644
index 000000000000..26c04cabef61
--- /dev/null
+++ b/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <limits.h>
+#include <stdio.h>
+#include <sys/mman.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/iommufd.h>
+#include <linux/limits.h>
+#include <linux/memfd.h>
+#include <linux/mman.h>
+#include <linux/sizes.h>
+#include <linux/time64.h>
+#include <linux/vfio.h>
+
+#include <libvfio.h>
+
+#include "kselftest_harness.h"
+
+static const char *device_bdf;
+
+FIXTURE(vfio_dma_mapping_perf_test) {
+	struct iommu *iommu;
+	struct vfio_pci_device *device;
+	struct iova_allocator *iova_allocator;
+};
+
+FIXTURE_VARIANT(vfio_dma_mapping_perf_test) {
+	const char *iommu_mode;
+	int mmap_flags;
+};
+
+#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode, _name, _mmap_flags)		  \
+FIXTURE_VARIANT_ADD(vfio_dma_mapping_perf_test, _iommu_mode ## _ ## _name) {	  \
+	.iommu_mode = #_iommu_mode,						  \
+	.mmap_flags = MAP_ANONYMOUS | MAP_PRIVATE | MAP_POPULATE | (_mmap_flags), \
+}
+
+FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous, 0);
+FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous_hugetlb_2mb, MAP_HUGETLB | MAP_HUGE_2MB);
+FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(anonymous_hugetlb_1gb, MAP_HUGETLB | MAP_HUGE_1GB);
+
+#undef FIXTURE_VARIANT_ADD_IOMMU_MODE
+
+FIXTURE_SETUP(vfio_dma_mapping_perf_test)
+{
+	self->iommu = iommu_init(variant->iommu_mode);
+	self->device = vfio_pci_device_init(device_bdf, self->iommu);
+	self->iova_allocator = iova_allocator_init(self->iommu);
+}
+
+FIXTURE_TEARDOWN(vfio_dma_mapping_perf_test)
+{
+	iova_allocator_cleanup(self->iova_allocator);
+	vfio_pci_device_cleanup(self->device);
+	iommu_cleanup(self->iommu);
+}
+
+TEST_F(vfio_dma_mapping_perf_test, dma_map_unmap)
+{
+	const u64 size = SZ_1G;
+	const int flags = variant->mmap_flags;
+	struct dma_region region;
+
+	printf("mmap size = %lluG\n", (unsigned long long)(size / SZ_1G));
+
+	TIME("mmap",
+	     region.vaddr = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, -1, 0));
+
+	/* Skip the test if there aren't enough HugeTLB pages available. */
+	if (flags & MAP_HUGETLB && region.vaddr == MAP_FAILED)
+		SKIP(return, "mmap() failed: %s (%d)\n", strerror(errno), errno);
+	else
+		ASSERT_NE(region.vaddr, MAP_FAILED);
+
+	region.iova = iova_allocator_alloc(self->iova_allocator, size);
+	region.size = size;
+
+	TIME("IOMMU map", iommu_map(self->iommu, &region));
+	ASSERT_EQ(region.iova, to_iova(self->device, region.vaddr));
+
+	TIME("IOMMU unmap", iommu_unmap(self->iommu, &region));
+	TIME("munmap", ASSERT_EQ(0, munmap(region.vaddr, size)));
+}
+
+int main(int argc, char *argv[])
+{
+	device_bdf = vfio_selftests_get_bdf(&argc, argv);
+	return test_harness_run(argc, argv);
+}
-- 
2.55.0.654.g21b8a5bc05-goog