Test IOMMU mapping the BAR mmaps created during vfio_pci_device_setup().
All IOMMU modes are tested: vfio_type1 variants are expected to succeed, while non-type1 modes are expected to fail. iommufd compat mode can be updated to expect success once kernel support lands; native iommufd will not support mapping vaddrs backed by MMIO (it will support dma-buf based MMIO mapping instead).
To: Alex Williamson alex@shazbot.org To: David Matlack dmatlack@google.com To: Shuah Khan shuah@kernel.org Cc: Peter Xu peterx@redhat.com Cc: linux-kernel@vger.kernel.org Cc: kvm@vger.kernel.org Cc: linux-kselftest@vger.kernel.org Cc: Jason Gunthorpe jgg@ziepe.ca
Changes in v2: - Split into patch series - Factor out mmap_aligned() for vaddr alignment - Align BAR mmaps to improve hugepage IOMMU mapping efficiency - Centralize MODE_* string definitions - Add is_power_of_2() assertion for BAR size - Simplify align calculation to min(size, 1G) - Add map_bar_misaligned test case - Link to v1: https://lore.kernel.org/all/aWA4GKp5ld92sY6e@devgpu015.cco6.facebook.com
Signed-off-by: Alex Mastro amastro@fb.com --- Alex Mastro (3): vfio: selftests: Centralize IOMMU mode name definitions vfio: selftests: Align BAR mmaps for efficient IOMMU mapping vfio: selftests: Add vfio_dma_mapping_mmio_test
tools/testing/selftests/vfio/Makefile | 1 + tools/testing/selftests/vfio/lib/include/libvfio.h | 9 ++ .../selftests/vfio/lib/include/libvfio/iommu.h | 6 + tools/testing/selftests/vfio/lib/iommu.c | 12 +- tools/testing/selftests/vfio/lib/libvfio.c | 25 ++++ tools/testing/selftests/vfio/lib/vfio_pci_device.c | 24 +++- .../selftests/vfio/vfio_dma_mapping_mmio_test.c | 144 +++++++++++++++++++++ .../testing/selftests/vfio/vfio_dma_mapping_test.c | 2 +- 8 files changed, 215 insertions(+), 8 deletions(-) --- base-commit: d721f52e31553a848e0e9947ca15a49c5674aef3 change-id: 20260112-map-mmio-test-b4e4c2d917a9
Best regards,
Replace scattered string literals with MODE_* macros in iommu.h. This provides a single source of truth for IOMMU mode name strings.
Signed-off-by: Alex Mastro amastro@fb.com --- tools/testing/selftests/vfio/lib/include/libvfio/iommu.h | 6 ++++++ tools/testing/selftests/vfio/lib/iommu.c | 12 ++++++------ tools/testing/selftests/vfio/vfio_dma_mapping_test.c | 2 +- 3 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h index 5c9b9dc6d993..e9a3386a4719 100644 --- a/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h +++ b/tools/testing/selftests/vfio/lib/include/libvfio/iommu.h @@ -61,6 +61,12 @@ iova_t iommu_hva2iova(struct iommu *iommu, void *vaddr);
struct iommu_iova_range *iommu_iova_ranges(struct iommu *iommu, u32 *nranges);
+#define MODE_VFIO_TYPE1_IOMMU "vfio_type1_iommu" +#define MODE_VFIO_TYPE1V2_IOMMU "vfio_type1v2_iommu" +#define MODE_IOMMUFD_COMPAT_TYPE1 "iommufd_compat_type1" +#define MODE_IOMMUFD_COMPAT_TYPE1V2 "iommufd_compat_type1v2" +#define MODE_IOMMUFD "iommufd" + /* * Generator for VFIO selftests fixture variants that replicate across all * possible IOMMU modes. Tests must define FIXTURE_VARIANT_ADD_IOMMU_MODE() diff --git a/tools/testing/selftests/vfio/lib/iommu.c b/tools/testing/selftests/vfio/lib/iommu.c index 8079d43523f3..27d1d13abfeb 100644 --- a/tools/testing/selftests/vfio/lib/iommu.c +++ b/tools/testing/selftests/vfio/lib/iommu.c @@ -21,32 +21,32 @@ #include "../../../kselftest.h" #include <libvfio.h>
-const char *default_iommu_mode = "iommufd"; +const char *default_iommu_mode = MODE_IOMMUFD;
/* Reminder: Keep in sync with FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(). */ static const struct iommu_mode iommu_modes[] = { { - .name = "vfio_type1_iommu", + .name = MODE_VFIO_TYPE1_IOMMU, .container_path = "/dev/vfio/vfio", .iommu_type = VFIO_TYPE1_IOMMU, }, { - .name = "vfio_type1v2_iommu", + .name = MODE_VFIO_TYPE1V2_IOMMU, .container_path = "/dev/vfio/vfio", .iommu_type = VFIO_TYPE1v2_IOMMU, }, { - .name = "iommufd_compat_type1", + .name = MODE_IOMMUFD_COMPAT_TYPE1, .container_path = "/dev/iommu", .iommu_type = VFIO_TYPE1_IOMMU, }, { - .name = "iommufd_compat_type1v2", + .name = MODE_IOMMUFD_COMPAT_TYPE1V2, .container_path = "/dev/iommu", .iommu_type = VFIO_TYPE1v2_IOMMU, }, { - .name = "iommufd", + .name = MODE_IOMMUFD, }, };
diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 5397822c3dd4..7cd396aa205c 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -166,7 +166,7 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) * IOMMUFD compatibility-mode does not support huge mappings when * using VFIO_TYPE1_IOMMU. */ - if (!strcmp(variant->iommu_mode, "iommufd_compat_type1")) + if (!strcmp(variant->iommu_mode, MODE_IOMMUFD_COMPAT_TYPE1)) mapping_size = SZ_4K;
ASSERT_EQ(0, rc);
Update vfio_pci_bar_map() to align BAR mmaps for efficient huge page mappings. The manual mmap alignment can be removed once mmap(!MAP_FIXED) on vfio device fds improves to automatically return well-aligned addresses.
Signed-off-by: Alex Mastro amastro@fb.com --- tools/testing/selftests/vfio/lib/include/libvfio.h | 9 ++++++++ tools/testing/selftests/vfio/lib/libvfio.c | 25 ++++++++++++++++++++++ tools/testing/selftests/vfio/lib/vfio_pci_device.c | 24 ++++++++++++++++++++- 3 files changed, 57 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/vfio/lib/include/libvfio.h b/tools/testing/selftests/vfio/lib/include/libvfio.h index 279ddcd70194..5ebf8503586e 100644 --- a/tools/testing/selftests/vfio/lib/include/libvfio.h +++ b/tools/testing/selftests/vfio/lib/include/libvfio.h @@ -23,4 +23,13 @@ const char *vfio_selftests_get_bdf(int *argc, char *argv[]); char **vfio_selftests_get_bdfs(int *argc, char *argv[], int *nr_bdfs);
+/* + * Reserve virtual address space of size at an address satisfying + * (vaddr % align) == offset. + * + * Returns the reserved vaddr. The caller is responsible for unmapping + * the returned region. + */ +void *mmap_aligned(size_t size, size_t align, size_t offset); + #endif /* SELFTESTS_VFIO_LIB_INCLUDE_LIBVFIO_H */ diff --git a/tools/testing/selftests/vfio/lib/libvfio.c b/tools/testing/selftests/vfio/lib/libvfio.c index a23a3cc5be69..4529bb1e69d1 100644 --- a/tools/testing/selftests/vfio/lib/libvfio.c +++ b/tools/testing/selftests/vfio/lib/libvfio.c @@ -2,6 +2,9 @@
#include <stdio.h> #include <stdlib.h> +#include <sys/mman.h> + +#include <linux/align.h>
#include "../../../kselftest.h" #include <libvfio.h> @@ -76,3 +79,25 @@ const char *vfio_selftests_get_bdf(int *argc, char *argv[])
return vfio_selftests_get_bdfs(argc, argv, &nr_bdfs)[0]; } + +void *mmap_aligned(size_t size, size_t align, size_t offset) +{ + void *map_base, *map_align; + size_t delta; + + VFIO_ASSERT_GT(align, offset); + delta = align - offset; + + map_base = mmap(NULL, size + align, PROT_NONE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + VFIO_ASSERT_NE(map_base, MAP_FAILED); + + map_align = (void *)(ALIGN((uintptr_t)map_base + delta, align) - delta); + + if (map_align > map_base) + VFIO_ASSERT_EQ(munmap(map_base, map_align - map_base), 0); + + VFIO_ASSERT_EQ(munmap(map_align + size, map_base + align - map_align), 0); + + return map_align; +} diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 13fdb4b0b10f..03f35011b5f7 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -12,10 +12,14 @@ #include <sys/mman.h>
#include <uapi/linux/types.h> +#include <linux/align.h> #include <linux/iommufd.h> +#include <linux/kernel.h> #include <linux/limits.h> +#include <linux/log2.h> #include <linux/mman.h> #include <linux/overflow.h> +#include <linux/sizes.h> #include <linux/types.h> #include <linux/vfio.h>
@@ -124,20 +128,38 @@ static void vfio_pci_region_get(struct vfio_pci_device *device, int index, static void vfio_pci_bar_map(struct vfio_pci_device *device, int index) { struct vfio_pci_bar *bar = &device->bars[index]; + size_t align, size; + void *vaddr; int prot = 0;
VFIO_ASSERT_LT(index, PCI_STD_NUM_BARS); VFIO_ASSERT_NULL(bar->vaddr); VFIO_ASSERT_TRUE(bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP); + VFIO_ASSERT_TRUE(is_power_of_2(bar->info.size));
if (bar->info.flags & VFIO_REGION_INFO_FLAG_READ) prot |= PROT_READ; if (bar->info.flags & VFIO_REGION_INFO_FLAG_WRITE) prot |= PROT_WRITE;
- bar->vaddr = mmap(NULL, bar->info.size, prot, MAP_FILE | MAP_SHARED, + size = bar->info.size; + + /* + * Align BAR mmaps to improve page fault granularity during potential + * subsequent IOMMU mapping of these BAR vaddr. 1G for x86 is the + * largest hugepage size across any architecture, so no benefit from + * larger alignment. BARs smaller than 1G will be aligned by their + * power-of-two size, guaranteeing sufficient alignment for smaller + * hugepages, if present. + */ + align = min_t(size_t, size, SZ_1G); + + vaddr = mmap_aligned(size, align, 0); + bar->vaddr = mmap(vaddr, size, prot, MAP_SHARED | MAP_FIXED, device->fd, bar->info.offset); VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED); + + madvise(bar->vaddr, size, MADV_HUGEPAGE); }
static void vfio_pci_bar_unmap(struct vfio_pci_device *device, int index)
Test IOMMU mapping the BAR mmaps created during vfio_pci_device_setup().
All IOMMU modes are tested: vfio_type1 variants are expected to succeed, while non-type1 modes are expected to fail. iommufd compat mode can be updated to expect success once kernel support lands; native iommufd will not support mapping vaddrs backed by MMIO (it will support dma-buf based MMIO mapping instead).
Signed-off-by: Alex Mastro amastro@fb.com --- tools/testing/selftests/vfio/Makefile | 1 + .../selftests/vfio/vfio_dma_mapping_mmio_test.c | 144 +++++++++++++++++++++ 2 files changed, 145 insertions(+)
diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index 3c796ca99a50..ead27892ab65 100644 --- a/tools/testing/selftests/vfio/Makefile +++ b/tools/testing/selftests/vfio/Makefile @@ -1,5 +1,6 @@ CFLAGS = $(KHDR_INCLUDES) TEST_GEN_PROGS += vfio_dma_mapping_test +TEST_GEN_PROGS += vfio_dma_mapping_mmio_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/vfio_dma_mapping_mmio_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_mmio_test.c new file mode 100644 index 000000000000..5a86b34329ad --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_mmio_test.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdio.h> +#include <sys/mman.h> +#include <unistd.h> + +#include <uapi/linux/types.h> +#include <linux/pci_regs.h> +#include <linux/sizes.h> +#include <linux/vfio.h> + +#include <libvfio.h> + +#include "../kselftest_harness.h" + +static const char *device_bdf; + +static struct vfio_pci_bar *largest_mapped_bar(struct vfio_pci_device *device) +{ + u32 flags = VFIO_REGION_INFO_FLAG_READ | VFIO_REGION_INFO_FLAG_WRITE; + struct vfio_pci_bar *largest = NULL; + u64 bar_size = 0; + + for (int i = 0; i < PCI_STD_NUM_BARS; i++) { + struct vfio_pci_bar *bar = &device->bars[i]; + + if (!bar->vaddr) + continue; + + /* + * iommu_map() maps with READ|WRITE, so require the same + * abilities for the underlying VFIO region. + */ + if ((bar->info.flags & flags) != flags) + continue; + + if (bar->info.size > bar_size) { + bar_size = bar->info.size; + largest = bar; + } + } + + return largest; +} + +FIXTURE(vfio_dma_mapping_mmio_test) { + struct iommu *iommu; + struct vfio_pci_device *device; + struct iova_allocator *iova_allocator; + struct vfio_pci_bar *bar; +}; + +FIXTURE_VARIANT(vfio_dma_mapping_mmio_test) { + const char *iommu_mode; +}; + +#define FIXTURE_VARIANT_ADD_IOMMU_MODE(_iommu_mode) \ +FIXTURE_VARIANT_ADD(vfio_dma_mapping_mmio_test, _iommu_mode) { \ + .iommu_mode = #_iommu_mode, \ +} + +FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(); + +#undef FIXTURE_VARIANT_ADD_IOMMU_MODE + +FIXTURE_SETUP(vfio_dma_mapping_mmio_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); + self->bar = largest_mapped_bar(self->device); + + if (!self->bar) + SKIP(return, "No mappable BAR found on device %s", device_bdf); + + if (self->bar->info.size < 2 * getpagesize()) + SKIP(return, "BAR too small (size=0x%llx)", self->bar->info.size); +} + +FIXTURE_TEARDOWN(vfio_dma_mapping_mmio_test) +{ + iova_allocator_cleanup(self->iova_allocator); + vfio_pci_device_cleanup(self->device); + iommu_cleanup(self->iommu); +} + +static void do_mmio_map_test(struct iommu *iommu, + struct iova_allocator *iova_allocator, + void *vaddr, size_t size) +{ + struct dma_region region = { + .vaddr = vaddr, + .size = size, + .iova = iova_allocator_alloc(iova_allocator, size), + }; + + /* + * NOTE: Check for iommufd compat success once it lands. Native iommufd + * will never support this. + */ + if (!strcmp(iommu->mode->name, MODE_VFIO_TYPE1V2_IOMMU) || + !strcmp(iommu->mode->name, MODE_VFIO_TYPE1_IOMMU)) { + iommu_map(iommu, ®ion); + iommu_unmap(iommu, ®ion); + } else { + VFIO_ASSERT_NE(__iommu_map(iommu, ®ion), 0); + VFIO_ASSERT_NE(__iommu_unmap(iommu, ®ion, NULL), 0); + } +} + +TEST_F(vfio_dma_mapping_mmio_test, map_full_bar) +{ + do_mmio_map_test(self->iommu, self->iova_allocator, + self->bar->vaddr, self->bar->info.size); +} + +TEST_F(vfio_dma_mapping_mmio_test, map_partial_bar) +{ + do_mmio_map_test(self->iommu, self->iova_allocator, + self->bar->vaddr, getpagesize()); +} + +/* Test IOMMU mapping of BAR mmap with intentionally poor vaddr alignment. */ +TEST_F(vfio_dma_mapping_mmio_test, map_bar_misaligned) +{ + /* Limit size to bound test time for large BARs */ + size_t size = min_t(size_t, self->bar->info.size, SZ_1G); + size_t page_size = getpagesize(); + void *vaddr; + + vaddr = mmap_aligned(size, SZ_1G, page_size); + vaddr = mmap(vaddr, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED, + self->device->fd, self->bar->info.offset); + VFIO_ASSERT_NE(vaddr, MAP_FAILED); + + do_mmio_map_test(self->iommu, self->iova_allocator, vaddr, size); + + VFIO_ASSERT_EQ(munmap(vaddr, size), 0); +} + +int main(int argc, char *argv[]) +{ + device_bdf = vfio_selftests_get_bdf(&argc, argv); + return test_harness_run(argc, argv); +}
linux-kselftest-mirror@lists.linaro.org
-
Alex Mastro