Add a second test to "vfio_dma_mapping_perf_test" to evaluate memfd latencies. A key motivator for adding this test is to demonstrate that the IOMMU_IOAS_MAP_FILE ioctl is significantly faster than other methods of mapping DMA regions. While this performance difference is not fully apparent with the test's current capabilities, it will become evident as more features are introduced later in the series. To support this, add IOMMU_IOAS_MAP_FILE ioctl support to the VFIO selftest library via iommufd_map_file(). Signed-off-by: Aaron Lewis --- .../vfio/lib/include/libvfio/iommu.h | 7 ++ tools/testing/selftests/vfio/lib/iommu.c | 24 +++++ .../vfio/vfio_dma_mapping_perf_test.c | 102 ++++++++++++++++++ 3 files changed, 133 insertions(+) diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h index 5c77875240f4..515976fb19be 100644 --- a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h +++ b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h @@ -35,6 +35,13 @@ struct iommu { struct iommu *iommu_init(const char *iommu_mode); void iommu_cleanup(struct iommu *iommu); +int __iommufd_map_file(struct iommu *iommu, struct dma_region *region, int fd); + +static inline void iommufd_map_file(struct iommu *iommu, struct dma_region *region, int fd) +{ + VFIO_ASSERT_EQ(__iommufd_map_file(iommu, region, fd), 0); +} + int __iommu_map(struct iommu *iommu, struct dma_region *region); static inline void iommu_map(struct iommu *iommu, struct dma_region *region) diff --git a/tools/testing/selftests/vfio/lib/iommu.c b/tools/testing/selftests/vfio/lib/iommu.c index b6f3c5c84e01..b76ae0a91c68 100644 --- a/tools/testing/selftests/vfio/lib/iommu.c +++ b/tools/testing/selftests/vfio/lib/iommu.c @@ -97,6 +97,30 @@ iova_t iommu_hva2iova(struct iommu *iommu, void *vaddr) return iova; } +int __iommufd_map_file(struct iommu *iommu, struct dma_region *region, int fd) +{ + VFIO_ASSERT_TRUE(iommu->iommufd, "IOMMU_IOAS_MAP_FILE is an IOMMUFD IOCTL."); + + struct iommu_ioas_map_file args = { + .size = sizeof(args), + .flags = IOMMU_IOAS_MAP_READABLE | + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_FIXED_IOVA, + .ioas_id = iommu->ioas_id, + .fd = fd, + .start = 0, + .iova = region->iova, + .length = region->size, + }; + + if (ioctl(iommu->iommufd, IOMMU_IOAS_MAP_FILE, &args)) + return -errno; + + list_add(®ion->link, &iommu->dma_regions); + + return 0; +} + static int vfio_iommu_map(struct iommu *iommu, struct dma_region *region) { struct vfio_iommu_type1_dma_map args = { diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c index 26c04cabef61..5ef85deba4ee 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_perf_test.c @@ -83,6 +83,108 @@ TEST_F(vfio_dma_mapping_perf_test, dma_map_unmap) TIME("munmap", ASSERT_EQ(0, munmap(region.vaddr, size))); } +FIXTURE(vfio_dma_mapping_perf_memfd_test) { + struct iommu *iommu; + struct vfio_pci_device *device; + struct iova_allocator *iova_allocator; +}; + +FIXTURE_VARIANT(vfio_dma_mapping_perf_memfd_test) { + const char *iommu_mode; + int mmap_flags; + int memfd_flags; +}; + +#define FIXTURE_VARIANT_ADD_MEMFD_MODE(_name, _mmap_flags, _memfd_flags) \ +FIXTURE_VARIANT_ADD(vfio_dma_mapping_perf_memfd_test, iommufd ## _ ## _name) {\ + .iommu_mode = MODE_IOMMUFD, \ + .mmap_flags = MAP_SHARED | MAP_POPULATE | (_mmap_flags), \ + .memfd_flags = (_memfd_flags), \ +} + +FIXTURE_VARIANT_ADD_MEMFD_MODE(memfd, 0, 0); +FIXTURE_VARIANT_ADD_MEMFD_MODE(memfd_hugetlb_2mb, + MAP_HUGETLB | MAP_HUGE_2MB, + MFD_HUGETLB | MFD_HUGE_2MB); +FIXTURE_VARIANT_ADD_MEMFD_MODE(memfd_hugetlb_1gb, + MAP_HUGETLB | MAP_HUGE_1GB, + MFD_HUGETLB | MFD_HUGE_1GB); + +#undef FIXTURE_VARIANT_ADD_MEMFD_MODE + +FIXTURE_SETUP(vfio_dma_mapping_perf_memfd_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_memfd_test) +{ + iova_allocator_cleanup(self->iova_allocator); + vfio_pci_device_cleanup(self->device); + iommu_cleanup(self->iommu); +} + +static void *setup_memfd(int *fd, u64 size, int mmap_flags, int mfd_flags) +{ + void *buf = MAP_FAILED; + + TIME("memfd_create", + *fd = memfd_create("vfio_dma_mapping_perf_memfd_test", mfd_flags)); + if (*fd < 0) + return MAP_FAILED; + + if (ftruncate(*fd, size)) + goto out; + + TIME("mmap", + buf = mmap(NULL, size, PROT_READ | PROT_WRITE, mmap_flags, *fd, 0)); + +out: + if (buf == MAP_FAILED) + close(*fd); + + return buf; +} + +static void teardown_memfd(int fd, u64 size, void *vaddr) +{ + if (vaddr != MAP_FAILED) + TIME("munmap", VFIO_ASSERT_EQ(0, munmap(vaddr, size))); + + if (fd != -1) + TIME("close", VFIO_ASSERT_EQ(0, close(fd))); +} + +TEST_F(vfio_dma_mapping_perf_memfd_test, dma_map_unmap_from_file) +{ + const u64 size = SZ_1G; + const int flags = variant->mmap_flags; + struct dma_region region; + int fd; + + printf("mmap size = %lluG\n", (unsigned long long)(size / SZ_1G)); + + region.vaddr = setup_memfd(&fd, size, variant->mmap_flags, variant->memfd_flags); + + /* Skip the test if there aren't enough HugeTLB pages available. */ + if (flags & MAP_HUGETLB && region.vaddr == MAP_FAILED) + SKIP(return, "setup_memfd() 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", iommufd_map_file(self->iommu, ®ion, fd)); + ASSERT_EQ(region.iova, to_iova(self->device, region.vaddr)); + + TIME("IOMMU unmap", iommu_unmap(self->iommu, ®ion)); + + teardown_memfd(fd, size, region.vaddr); +} + int main(int argc, char *argv[]) { device_bdf = vfio_selftests_get_bdf(&argc, argv); -- 2.55.0.654.g21b8a5bc05-goog