Add a basic helper library to be used by VFIO selftests.

The basic unit of the library is struct vfio_pci_device, which represents a single PCI device that is bound to the vfio-pci driver. The library currently only supports a single device per group and container, and VFIO IOMMU types.

The code in this library was heavily based on prior work done by Raghavendra Rao Ananta rananta@google.com, and the VFIO_ASSERT*() macros were written by Vipin Sharma vipinsh@google.com.

Separate that Makefile rules for building the library into a separate script so that the library can be built by and linked into KVM selftests in a subsequent commit.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/Makefile | 14 + .../selftests/vfio/lib/include/vfio_util.h | 140 +++++++ tools/testing/selftests/vfio/lib/libvfio.mk | 15 + .../selftests/vfio/lib/vfio_pci_device.c | 365 ++++++++++++++++++ 4 files changed, 534 insertions(+) create mode 100644 tools/testing/selftests/vfio/lib/include/vfio_util.h create mode 100644 tools/testing/selftests/vfio/lib/libvfio.mk create mode 100644 tools/testing/selftests/vfio/lib/vfio_pci_device.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index 2bba39aff5d9..db3e4db1a6dd 100644 --- a/tools/testing/selftests/vfio/Makefile +++ b/tools/testing/selftests/vfio/Makefile @@ -1,2 +1,16 @@ CFLAGS = $(KHDR_INCLUDES) include ../lib.mk +include lib/libvfio.mk + +CFLAGS += -I$(top_srcdir)/tools/include +CFLAGS += -MD +CFLAGS += $(EXTRA_CFLAGS) + +$(TEST_GEN_PROGS): %: %.o $(LIBVFIO_O) + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $< $(LIBVFIO_O) $(LDLIBS) -o $@ + +TEST_GEN_PROGS_O = $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_PROGS_O) $(LIBVFIO_O)) +-include $(TEST_DEP_FILES) + +EXTRA_CLEAN += $(TEST_GEN_PROGS_O) $(TEST_DEP_FILES) diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h new file mode 100644 index 000000000000..b7d2bb8c18ba --- /dev/null +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H +#define SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H + +#include <string.h> +#include <linux/vfio.h> +#include <linux/list.h> +#include <linux/pci_regs.h> + +#include "../../../kselftest.h" + +#define VFIO_LOG_AND_EXIT(...) do { \ + fprintf(stderr, " " __VA_ARGS__); \ + fprintf(stderr, "\n"); \ + exit(KSFT_FAIL); \ +} while (0) + +#define VFIO_ASSERT_OP(_lhs, _rhs, _op, ...) do { \ + typeof(_lhs) __lhs = (_lhs); \ + typeof(_rhs) __rhs = (_rhs); \ + \ + if (__lhs _op __rhs) \ + break; \ + \ + fprintf(stderr, "%s:%u: Assertion Failure\n\n", __FILE__, __LINE__); \ + fprintf(stderr, " Expression: " #_lhs " " #_op " " #_rhs "\n"); \ + fprintf(stderr, " Observed: %#lx %s %#lx\n", \ + (u64)__lhs, #_op, (u64)__rhs); \ + fprintf(stderr, " [errno: %d - %s]\n", errno, strerror(errno)); \ + VFIO_LOG_AND_EXIT(__VA_ARGS__); \ +} while (0) + +#define VFIO_ASSERT_EQ(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, ==, ##__VA_ARGS__) +#define VFIO_ASSERT_NE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, !=, ##__VA_ARGS__) +#define VFIO_ASSERT_LT(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, <, ##__VA_ARGS__) +#define VFIO_ASSERT_LE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, <=, ##__VA_ARGS__) +#define VFIO_ASSERT_GT(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, >, ##__VA_ARGS__) +#define VFIO_ASSERT_GE(_a, _b, ...) VFIO_ASSERT_OP(_a, _b, >=, ##__VA_ARGS__) +#define VFIO_ASSERT_TRUE(_a, ...) VFIO_ASSERT_NE(false, (_a), ##__VA_ARGS__) +#define VFIO_ASSERT_FALSE(_a, ...) VFIO_ASSERT_EQ(false, (_a), ##__VA_ARGS__) +#define VFIO_ASSERT_NULL(_a, ...) VFIO_ASSERT_EQ(NULL, _a, ##__VA_ARGS__) +#define VFIO_ASSERT_NOT_NULL(_a, ...) VFIO_ASSERT_NE(NULL, _a, ##__VA_ARGS__) + +#define VFIO_FAIL(_fmt, ...) do { \ + fprintf(stderr, "%s:%u: FAIL\n\n", __FILE__, __LINE__); \ + VFIO_LOG_AND_EXIT(_fmt, ##__VA_ARGS__); \ +} while (0) + +struct vfio_pci_bar { + struct vfio_region_info info; + void *vaddr; +}; + +struct vfio_pci_device { + int fd; + int group_fd; + int container_fd; + + struct vfio_device_info info; + struct vfio_region_info config_space; + struct vfio_pci_bar bars[PCI_STD_NUM_BARS]; + + struct vfio_irq_info msi_info; + struct vfio_irq_info msix_info; + + /* eventfds for MSI and MSI-x interrupts */ + int msi_eventfds[PCI_MSIX_FLAGS_QSIZE + 1]; +}; + +/* + * Return the BDF string of the device that the test should use. + * + * If a BDF string is provided by the user on the command line (as the last + * element of argv[]), then this function will return that and decrement argc + * by 1. + * + * Otherwise this function will attempt to use the environment variable + * $VFIO_SELFTESTS_BDF. + * + * If BDF cannot be determined then the test will exit with KSFT_SKIP. + */ +const char *vfio_selftests_get_bdf(int *argc, char *argv[]); + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type); +void vfio_pci_device_cleanup(struct vfio_pci_device *device); + +void vfio_pci_dma_map(struct vfio_pci_device *device, u64 iova, u64 size, + void *vaddr); +void vfio_pci_dma_unmap(struct vfio_pci_device *device, u64 iova, u64 size); + +void vfio_pci_config_access(struct vfio_pci_device *device, bool write, + size_t config, size_t size, void *data); + +#define vfio_pci_config_read(_device, _offset, _type) ({ \ + _type __data; \ + vfio_pci_config_access((_device), false, _offset, sizeof(__data), &__data); \ + __data; \ +}) + +#define vfio_pci_config_readb(_d, _o) vfio_pci_config_read(_d, _o, u8) +#define vfio_pci_config_readw(_d, _o) vfio_pci_config_read(_d, _o, u16) +#define vfio_pci_config_readl(_d, _o) vfio_pci_config_read(_d, _o, u32) + +#define vfio_pci_config_write(_device, _offset, _value, _type) do { \ + _type __data = (_value); \ + vfio_pci_config_access((_device), true, _offset, sizeof(_type), &__data); \ +} while (0) + +#define vfio_pci_config_writeb(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u8) +#define vfio_pci_config_writew(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u16) +#define vfio_pci_config_writel(_d, _o, _v) vfio_pci_config_write(_d, _o, _v, u32) + +void vfio_pci_irq_enable(struct vfio_pci_device *device, u32 index, + u32 vector, int count); +void vfio_pci_irq_disable(struct vfio_pci_device *device, u32 index); +void vfio_pci_irq_trigger(struct vfio_pci_device *device, u32 index, u32 vector); + +static inline void vfio_pci_msi_enable(struct vfio_pci_device *device, + u32 vector, int count) +{ + vfio_pci_irq_enable(device, VFIO_PCI_MSI_IRQ_INDEX, vector, count); +} + +static inline void vfio_pci_msi_disable(struct vfio_pci_device *device) +{ + vfio_pci_irq_disable(device, VFIO_PCI_MSI_IRQ_INDEX); +} + +static inline void vfio_pci_msix_enable(struct vfio_pci_device *device, + u32 vector, int count) +{ + vfio_pci_irq_enable(device, VFIO_PCI_MSIX_IRQ_INDEX, vector, count); +} + +static inline void vfio_pci_msix_disable(struct vfio_pci_device *device) +{ + vfio_pci_irq_disable(device, VFIO_PCI_MSIX_IRQ_INDEX); +} + +#endif /* SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H */ diff --git a/tools/testing/selftests/vfio/lib/libvfio.mk b/tools/testing/selftests/vfio/lib/libvfio.mk new file mode 100644 index 000000000000..72e55a560eeb --- /dev/null +++ b/tools/testing/selftests/vfio/lib/libvfio.mk @@ -0,0 +1,15 @@ +VFIO_DIR := $(selfdir)/vfio + +LIBVFIO_C := lib/vfio_pci_device.c + +LIBVFIO_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBVFIO_C)) + +LIBVFIO_O_DIRS := $(shell dirname $(LIBVFIO_O) | uniq) +$(shell mkdir -p $(LIBVFIO_O_DIRS)) + +CFLAGS += -I$(VFIO_DIR)/lib/include + +$(LIBVFIO_O): $(OUTPUT)/%.o : $(VFIO_DIR)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(LIBVFIO_O) diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c new file mode 100644 index 000000000000..76adb1841f16 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <fcntl.h> +#include <libgen.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <sys/eventfd.h> +#include <sys/ioctl.h> +#include <sys/mman.h> + +#include <linux/limits.h> +#include <linux/mman.h> +#include <linux/types.h> +#include <linux/vfio.h> + +#include "../../../kselftest.h" +#include <vfio_util.h> + +#define VFIO_DEV_PATH "/dev/vfio/vfio" +#define PCI_SYSFS_PATH "/sys/bus/pci/devices" + +#define ioctl_assert(_fd, _op, _arg) do { \ + void *__arg = (_arg); \ + int __ret = ioctl((_fd), (_op), (__arg)); \ + VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \ +} while (0) + +static void vfio_pci_irq_set(struct vfio_pci_device *device, + u32 index, u32 vector, u32 count, int *fds) +{ + u8 buf[sizeof(struct vfio_irq_set) + sizeof(int) * count] = {}; + struct vfio_irq_set *irq = (void *)&buf; + int *irq_fds = (void *)&irq->data; + + irq->argsz = sizeof(buf); + irq->flags = VFIO_IRQ_SET_ACTION_TRIGGER; + irq->index = index; + irq->start = vector; + irq->count = count; + + if (count) { + irq->flags |= VFIO_IRQ_SET_DATA_EVENTFD; + memcpy(irq_fds, fds, sizeof(int) * count); + } else { + irq->flags |= VFIO_IRQ_SET_DATA_NONE; + } + + ioctl_assert(device->fd, VFIO_DEVICE_SET_IRQS, irq); +} + +void vfio_pci_irq_trigger(struct vfio_pci_device *device, u32 index, u32 vector) +{ + struct vfio_irq_set irq = { + .argsz = sizeof(irq), + .flags = VFIO_IRQ_SET_ACTION_TRIGGER | VFIO_IRQ_SET_DATA_NONE, + .index = index, + .start = vector, + .count = 1, + }; + + ioctl_assert(device->fd, VFIO_DEVICE_SET_IRQS, &irq); +} + +static void check_supported_irq_index(u32 index) +{ + /* VFIO selftests only supports MSI and MSI-x for now. */ + VFIO_ASSERT_TRUE(index == VFIO_PCI_MSI_IRQ_INDEX || + index == VFIO_PCI_MSIX_IRQ_INDEX, + "Unsupported IRQ index: %u\n", index); +} + +void vfio_pci_irq_enable(struct vfio_pci_device *device, u32 index, u32 vector, + int count) +{ + int i; + + check_supported_irq_index(index); + + for (i = vector; i < vector + count; i++) { + VFIO_ASSERT_LT(device->msi_eventfds[i], 0); + device->msi_eventfds[i] = eventfd(0, 0); + VFIO_ASSERT_GE(device->msi_eventfds[i], 0); + } + + vfio_pci_irq_set(device, index, vector, count, device->msi_eventfds + vector); +} + +void vfio_pci_irq_disable(struct vfio_pci_device *device, u32 index) +{ + int i; + + check_supported_irq_index(index); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) { + if (device->msi_eventfds[i] < 0) + continue; + + VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0); + device->msi_eventfds[i] = -1; + } + + vfio_pci_irq_set(device, index, 0, 0, NULL); +} + +static void vfio_pci_irq_get(struct vfio_pci_device *device, u32 index, + struct vfio_irq_info *irq_info) +{ + irq_info->argsz = sizeof(*irq_info); + irq_info->index = index; + + ioctl_assert(device->fd, VFIO_DEVICE_GET_IRQ_INFO, irq_info); +} + +void vfio_pci_dma_map(struct vfio_pci_device *device, u64 iova, u64 size, void *vaddr) +{ + struct vfio_iommu_type1_dma_map map = { + .argsz = sizeof(map), + .flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE, + .vaddr = (u64)vaddr, + .iova = iova, + .size = size, + }; + + ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &map); +} + +void vfio_pci_dma_unmap(struct vfio_pci_device *device, u64 iova, u64 size) +{ + struct vfio_iommu_type1_dma_unmap unmap = { + .argsz = sizeof(unmap), + .iova = iova, + .size = size, + }; + + ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &unmap); +} + +static void vfio_pci_region_get(struct vfio_pci_device *device, int index, + struct vfio_region_info *info) +{ + memset(info, 0, sizeof(*info)); + + info->argsz = sizeof(*info); + info->index = index; + + ioctl_assert(device->fd, VFIO_DEVICE_GET_REGION_INFO, info); +} + +static void vfio_pci_bar_map(struct vfio_pci_device *device, int index) +{ + struct vfio_pci_bar *bar = &device->bars[index]; + 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); + + 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, + device->fd, bar->info.offset); + VFIO_ASSERT_NE(bar->vaddr, MAP_FAILED); +} + +static void vfio_pci_bar_unmap(struct vfio_pci_device *device, int index) +{ + struct vfio_pci_bar *bar = &device->bars[index]; + + VFIO_ASSERT_LT(index, PCI_STD_NUM_BARS); + VFIO_ASSERT_NOT_NULL(bar->vaddr); + + VFIO_ASSERT_EQ(munmap(bar->vaddr, bar->info.size), 0); + bar->vaddr = NULL; +} + +static void vfio_pci_bar_unmap_all(struct vfio_pci_device *device) +{ + int i; + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (device->bars[i].vaddr) + vfio_pci_bar_unmap(device, i); + } +} + +void vfio_pci_config_access(struct vfio_pci_device *device, bool write, + size_t config, size_t size, void *data) +{ + struct vfio_region_info *config_space = &device->config_space; + int ret; + + if (write) + ret = pwrite(device->fd, data, size, config_space->offset + config); + else + ret = pread(device->fd, data, size, config_space->offset + config); + + VFIO_ASSERT_EQ(ret, size, "Failed to %s PCI config space: 0x%lx\n", + write ? "write to" : "read from", config); +} + +static unsigned int vfio_pci_get_group_from_dev(const char *bdf) +{ + char dev_iommu_group_path[PATH_MAX] = {0}; + char sysfs_path[PATH_MAX] = {0}; + unsigned int group; + int ret; + + snprintf(sysfs_path, PATH_MAX, "%s/%s/iommu_group", PCI_SYSFS_PATH, bdf); + + ret = readlink(sysfs_path, dev_iommu_group_path, sizeof(dev_iommu_group_path)); + VFIO_ASSERT_NE(ret, -1, "Failed to get the IOMMU group for device: %s\n", bdf); + + ret = sscanf(basename(dev_iommu_group_path), "%u", &group); + VFIO_ASSERT_EQ(ret, 1, "Failed to get the IOMMU group for device: %s\n", bdf); + + return group; +} + +static void vfio_pci_container_setup(struct vfio_pci_device *device) +{ + int version; + + device->container_fd = open(VFIO_DEV_PATH, O_RDWR); + VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", VFIO_DEV_PATH); + + version = ioctl(device->container_fd, VFIO_GET_API_VERSION); + VFIO_ASSERT_EQ(version, VFIO_API_VERSION); +} + +static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf) +{ + struct vfio_group_status group_status = { + .argsz = sizeof(group_status), + }; + char group_path[32]; + int group; + + group = vfio_pci_get_group_from_dev(bdf); + snprintf(group_path, sizeof(group_path), "/dev/vfio/%d", group); + + device->group_fd = open(group_path, O_RDWR); + VFIO_ASSERT_GE(device->group_fd, 0, "open(%s) failed\n", group_path); + + ioctl_assert(device->group_fd, VFIO_GROUP_GET_STATUS, &group_status); + VFIO_ASSERT_TRUE(group_status.flags & VFIO_GROUP_FLAGS_VIABLE); + + ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->container_fd); +} + +static void vfio_pci_iommu_setup(struct vfio_pci_device *device, unsigned long iommu_type) +{ + int ret; + + ret = ioctl(device->container_fd, VFIO_CHECK_EXTENSION, iommu_type); + VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type); + + ioctl_assert(device->container_fd, VFIO_SET_IOMMU, (void *)iommu_type); +} + +static void vfio_pci_device_setup(struct vfio_pci_device *device, const char *bdf) +{ + int i; + + device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf); + VFIO_ASSERT_GE(device->fd, 0); + + device->info.argsz = sizeof(device->info); + ioctl_assert(device->fd, VFIO_DEVICE_GET_INFO, &device->info); + + vfio_pci_region_get(device, VFIO_PCI_CONFIG_REGION_INDEX, &device->config_space); + + /* Sanity check VFIO does not advertise mmap for config space */ + VFIO_ASSERT_TRUE(!(device->config_space.flags & VFIO_REGION_INFO_FLAG_MMAP), + "PCI config space should not support mmap()\n"); + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + struct vfio_pci_bar *bar = device->bars + i; + + vfio_pci_region_get(device, i, &bar->info); + if (bar->info.flags & VFIO_REGION_INFO_FLAG_MMAP) + vfio_pci_bar_map(device, i); + } + + vfio_pci_irq_get(device, VFIO_PCI_MSI_IRQ_INDEX, &device->msi_info); + vfio_pci_irq_get(device, VFIO_PCI_MSIX_IRQ_INDEX, &device->msix_info); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) + device->msi_eventfds[i] = -1; +} + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type) +{ + struct vfio_pci_device *device; + + device = calloc(1, sizeof(*device)); + VFIO_ASSERT_NOT_NULL(device); + + vfio_pci_container_setup(device); + vfio_pci_group_setup(device, bdf); + vfio_pci_iommu_setup(device, iommu_type); + vfio_pci_device_setup(device, bdf); + + return device; +} + +void vfio_pci_device_cleanup(struct vfio_pci_device *device) +{ + int i; + + vfio_pci_bar_unmap_all(device); + + VFIO_ASSERT_EQ(close(device->fd), 0); + + for (i = 0; i < ARRAY_SIZE(device->msi_eventfds); i++) { + if (device->msi_eventfds[i] < 0) + continue; + + VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0); + } + + VFIO_ASSERT_EQ(close(device->group_fd), 0); + VFIO_ASSERT_EQ(close(device->container_fd), 0); + + free(device); +} + +static bool is_bdf(const char *str) +{ + unsigned int s, b, d, f; + int length, count; + + count = sscanf(str, "%4x:%2x:%2x.%2x%n", &s, &b, &d, &f, &length); + return count == 4 && length == strlen(str); +} + +const char *vfio_selftests_get_bdf(int *argc, char *argv[]) +{ + char *bdf; + + if (*argc > 1 && is_bdf(argv[*argc - 1])) + return argv[--(*argc)]; + + bdf = getenv("VFIO_SELFTESTS_BDF"); + if (bdf) { + VFIO_ASSERT_TRUE(is_bdf(bdf), "Invalid BDF: %s\n", bdf); + return bdf; + } + + fprintf(stderr, "Unable to determine which device to use, skipping test.\n"); + fprintf(stderr, "\n"); + fprintf(stderr, "To pass the device address via environment variable:\n"); + fprintf(stderr, "\n"); + fprintf(stderr, " export VFIO_SELFTESTS_BDF=segment:bus:device.function\n"); + fprintf(stderr, " %s [options]\n", argv[0]); + fprintf(stderr, "\n"); + fprintf(stderr, "To pass the device address via argv:\n"); + fprintf(stderr, "\n"); + fprintf(stderr, " %s [options] segment:bus:device.function\n", argv[0]); + fprintf(stderr, "\n"); + exit(KSFT_SKIP); +}

From: Josh Hilke jrhilke@google.com

Add a vfio test suite which verifies that userspace can bind and unbind devices, allocate I/O address space, and attach a device to an IOMMU domain using the cdev + IOMMUfd VFIO interface.

Signed-off-by: Josh Hilke jrhilke@google.com Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/Makefile | 1 + .../selftests/vfio/vfio_iommufd_setup_test.c | 157 ++++++++++++++++++ 2 files changed, 158 insertions(+) create mode 100644 tools/testing/selftests/vfio/vfio_iommufd_setup_test.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index 828419537250..e4a5d6eadff3 100644 --- a/tools/testing/selftests/vfio/Makefile +++ b/tools/testing/selftests/vfio/Makefile @@ -1,4 +1,5 @@ CFLAGS = $(KHDR_INCLUDES) +TEST_GEN_PROGS += vfio_iommufd_setup_test TEST_GEN_PROGS += vfio_pci_device_test include ../lib.mk include lib/libvfio.mk diff --git a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c new file mode 100644 index 000000000000..f45335d9260f --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <assert.h> +#include <dirent.h> +#include <fcntl.h> + +#include <uapi/linux/types.h> +#include <linux/limits.h> +#include <linux/sizes.h> +#include <linux/vfio.h> +#include <linux/iommufd.h> + +#include <stdint.h> +#include <stdio.h> +#include <string.h> +#include <sys/ioctl.h> +#include <unistd.h> + +#include <vfio_util.h> +#include "../kselftest_harness.h" + +static const char iommu_dev_path[] = "/dev/iommu"; +static char cdev_path[PATH_MAX] = { '\0' }; + +static void set_cdev_path(const char *bdf) +{ + char dir_path[PATH_MAX]; + DIR *dir; + struct dirent *entry; + + snprintf(dir_path, sizeof(dir_path), "/sys/bus/pci/devices/%s/vfio-dev/", bdf); + + dir = opendir(dir_path); + assert(dir); + + /* Find the file named "vfio<number>" */ + while ((entry = readdir(dir)) != NULL) { + if (!strncmp("vfio", entry->d_name, 4)) { + snprintf(cdev_path, sizeof(cdev_path), "/dev/vfio/devices/%s", + entry->d_name); + break; + } + } + + assert(strlen(cdev_path) > 0); + + closedir(dir); +} + +static int vfio_device_bind_iommufd_ioctl(int cdev_fd, int iommufd) +{ + struct vfio_device_bind_iommufd bind_args = { + .argsz = sizeof(bind_args), + .iommufd = iommufd, + }; + + return ioctl(cdev_fd, VFIO_DEVICE_BIND_IOMMUFD, &bind_args); +} + +static int vfio_device_get_info_ioctl(int cdev_fd) +{ + struct vfio_device_info info_args = { .argsz = sizeof(info_args) }; + + return ioctl(cdev_fd, VFIO_DEVICE_GET_INFO, &info_args); +} + +static int vfio_device_ioas_alloc_ioctl(int iommufd, struct iommu_ioas_alloc *alloc_args) +{ + *alloc_args = (struct iommu_ioas_alloc){ + .size = sizeof(struct iommu_ioas_alloc), + }; + + return ioctl(iommufd, IOMMU_IOAS_ALLOC, alloc_args); +} + +static int vfio_device_attach_iommufd_pt_ioctl(int cdev_fd, u32 pt_id) +{ + struct vfio_device_attach_iommufd_pt attach_args = { + .argsz = sizeof(attach_args), + .pt_id = pt_id, + }; + + return ioctl(cdev_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &attach_args); +} + +static int vfio_device_detach_iommufd_pt_ioctl(int cdev_fd) +{ + struct vfio_device_detach_iommufd_pt detach_args = { + .argsz = sizeof(detach_args), + }; + + return ioctl(cdev_fd, VFIO_DEVICE_DETACH_IOMMUFD_PT, &detach_args); +} + +FIXTURE(vfio_cdev) { + int cdev_fd; + int iommufd; +}; + +FIXTURE_SETUP(vfio_cdev) +{ + ASSERT_LE(0, (self->cdev_fd = open(cdev_path, O_RDWR, 0))); + ASSERT_LE(0, (self->iommufd = open(iommu_dev_path, O_RDWR, 0))); +} + +FIXTURE_TEARDOWN(vfio_cdev) +{ + ASSERT_EQ(0, close(self->cdev_fd)); + ASSERT_EQ(0, close(self->iommufd)); +} + +TEST_F(vfio_cdev, bind) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_EQ(0, vfio_device_get_info_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, get_info_without_bind_fails) +{ + ASSERT_NE(0, vfio_device_get_info_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, bind_bad_iommufd_fails) +{ + ASSERT_NE(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, -2)); +} + +TEST_F(vfio_cdev, repeated_bind_fails) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_NE(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); +} + +TEST_F(vfio_cdev, attach_detatch_pt) +{ + struct iommu_ioas_alloc alloc_args; + + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_EQ(0, vfio_device_ioas_alloc_ioctl(self->iommufd, &alloc_args)); + ASSERT_EQ(0, vfio_device_attach_iommufd_pt_ioctl(self->cdev_fd, alloc_args.out_ioas_id)); + ASSERT_EQ(0, vfio_device_detach_iommufd_pt_ioctl(self->cdev_fd)); +} + +TEST_F(vfio_cdev, attach_invalid_pt_fails) +{ + ASSERT_EQ(0, vfio_device_bind_iommufd_ioctl(self->cdev_fd, self->iommufd)); + ASSERT_NE(0, vfio_device_attach_iommufd_pt_ioctl(self->cdev_fd, UINT32_MAX)); +} + +int main(int argc, char *argv[]) +{ + const char *device_bdf = vfio_selftests_get_bdf(&argc, argv); + + set_cdev_path(device_bdf); + printf("Using cdev device %s\n", cdev_path); + + return test_harness_run(argc, argv); +}

From: Josh Hilke jrhilke@google.com

Add a test to vfio_pci_device_test which resets the device. If reset is not supported by the device, the test is skipped.

Signed-off-by: Josh Hilke jrhilke@google.com Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/lib/include/vfio_util.h | 1 + tools/testing/selftests/vfio/lib/vfio_pci_device.c | 5 +++++ tools/testing/selftests/vfio/vfio_pci_device_test.c | 8 ++++++++ 3 files changed, 14 insertions(+)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index b7d2bb8c18ba..234403b442af 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -83,6 +83,7 @@ const char *vfio_selftests_get_bdf(int *argc, char *argv[]);

struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type); void vfio_pci_device_cleanup(struct vfio_pci_device *device); +void vfio_pci_device_reset(struct vfio_pci_device *device);

void vfio_pci_dma_map(struct vfio_pci_device *device, u64 iova, u64 size, void *vaddr); diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 76adb1841f16..98cce0a6ecd7 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -202,6 +202,11 @@ void vfio_pci_config_access(struct vfio_pci_device *device, bool write, write ? "write to" : "read from", config); }

+void vfio_pci_device_reset(struct vfio_pci_device *device) +{ + ioctl_assert(device->fd, VFIO_DEVICE_RESET, NULL); +} + static unsigned int vfio_pci_get_group_from_dev(const char *bdf) { char dev_iommu_group_path[PATH_MAX] = {0}; diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c index a2e41398d184..82e3c947f45d 100644 --- a/tools/testing/selftests/vfio/vfio_pci_device_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c @@ -155,6 +155,14 @@ TEST_F(vfio_pci_irq_test, enable_trigger_disable) vfio_pci_irq_disable(self->device, variant->irq_index); }

+TEST_F(vfio_pci_device_test, reset) +{ + if (!(self->device->info.flags & VFIO_DEVICE_FLAGS_RESET)) + SKIP(return, "Device does not support reset\n"); + + vfio_pci_device_reset(self->device); +} + int main(int argc, char *argv[]) { device_bdf = vfio_selftests_get_bdf(&argc, argv);

From: Josh Hilke jrhilke@google.com

Update vfio dma mapping test to verify that the IOMMU uses 2M and 1G mappings when 2M and 1G HugeTLB pages are mapped into a device respectively.

This validation is done by inspecting the contents of the I/O page tables via /sys/kernel/debug/iommu/intel/. This validation is skipped if that directory is not available (i.e. non-Intel IOMMUs).

Signed-off-by: Josh Hilke jrhilke@google.com [reword commit message, refactor code] Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/vfio_dma_mapping_test.c | 111 ++++++++++++++++++ 1 file changed, 111 insertions(+)

diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 97bbe031b10d..9cdf25b293c5 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -14,6 +14,83 @@

static const char *device_bdf;

+struct iommu_mapping { + u64 pgd; + u64 p4d; + u64 pud; + u64 pmd; + u64 pte; +}; + +static void parse_next_value(char **line, u64 *value) +{ + char *token; + + token = strtok_r(*line, " \t|\n", line); + if (!token) + return; + + /* Caller verifies `value`. No need to check return value. */ + sscanf(token, "0x%lx", value); +} + +static int intel_iommu_mapping_get(const char *bdf, u64 iova, + struct iommu_mapping *mapping) +{ + char iommu_mapping_path[PATH_MAX], line[PATH_MAX]; + u64 line_iova = -1; + int ret = -ENOENT; + FILE *file; + char *rest; + + snprintf(iommu_mapping_path, sizeof(iommu_mapping_path), + "/sys/kernel/debug/iommu/intel/%s/domain_translation_struct", + bdf); + + printf("Searching for IOVA 0x%lx in %s\n", iova, iommu_mapping_path); + + file = fopen(iommu_mapping_path, "r"); + VFIO_ASSERT_NOT_NULL(file, "fopen(%s) failed", iommu_mapping_path); + + while (fgets(line, sizeof(line), file)) { + rest = line; + + parse_next_value(&rest, &line_iova); + if (line_iova != (iova / getpagesize())) + continue; + + /* + * Ensure each struct field is initialized in case of empty + * page table values. + */ + memset(mapping, 0, sizeof(*mapping)); + parse_next_value(&rest, &mapping->pgd); + parse_next_value(&rest, &mapping->p4d); + parse_next_value(&rest, &mapping->pud); + parse_next_value(&rest, &mapping->pmd); + parse_next_value(&rest, &mapping->pte); + + ret = 0; + break; + } + + fclose(file); + + if (ret) + printf("IOVA not found\n"); + + return ret; +} + +static int iommu_mapping_get(const char *bdf, u64 iova, + struct iommu_mapping *mapping) +{ + if (!access("/sys/kernel/debug/iommu/intel", F_OK)) + return intel_iommu_mapping_get(bdf, iova, mapping); + + return -EOPNOTSUPP; +} + FIXTURE(vfio_dma_mapping_test) { struct vfio_pci_device *device; }; @@ -51,8 +128,10 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) { const u64 size = variant->size ?: getpagesize(); const int flags = variant->mmap_flags; + struct iommu_mapping mapping; const u64 iova = 0; void *mem; + int rc;

mem = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, -1, 0);

@@ -65,7 +144,39 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) vfio_pci_dma_map(self->device, iova, size, mem); printf("Mapped HVA %p (size 0x%lx) at IOVA 0x%lx\n", mem, size, iova);

+ rc = iommu_mapping_get(device_bdf, iova, &mapping); + if (rc == -EOPNOTSUPP) + goto unmap; + + ASSERT_EQ(0, rc); + printf("Found IOMMU mappings for IOVA 0x%lx:\n", iova); + printf("PGD: 0x%016lx\n", mapping.pgd); + printf("P4D: 0x%016lx\n", mapping.p4d); + printf("PUD: 0x%016lx\n", mapping.pud); + printf("PMD: 0x%016lx\n", mapping.pmd); + printf("PTE: 0x%016lx\n", mapping.pte); + + switch (size) { + case SZ_4K: + ASSERT_NE(0, mapping.pte); + break; + case SZ_2M: + ASSERT_EQ(0, mapping.pte); + ASSERT_NE(0, mapping.pmd); + break; + case SZ_1G: + ASSERT_EQ(0, mapping.pte); + ASSERT_EQ(0, mapping.pmd); + ASSERT_NE(0, mapping.pud); + break; + default: + VFIO_FAIL("Unrecognized size: 0x%lx\n", size); + } + +unmap: vfio_pci_dma_unmap(self->device, iova, size); + printf("Unmapped IOVA 0x%lx\n", iova); + ASSERT_NE(0, iommu_mapping_get(device_bdf, iova, &mapping));

ASSERT_TRUE(!munmap(mem, size)); }

Import the asm-generic MMIO helper functions from the kernel headers into tools/include/. The top-level include is <linux/io.h> which then includes the arch-specific <asm/io.h>, which then includes <asm-generic/io.h>. This layout is chosen to match the kernel header layout and to appease checkpatch.pl (which warns against including <asm/io.h> or <asm-generic/io.h> directly).

Changes made when importing:

- Add missing includes at the top. - Stub out mmiowb_set_pending(). - Stub out _THIS_IP_. - Stub out log_*_mmio() calls. - Drop the CONFIG_64BIT checks, since tools/include/linux/types.h always defines u64.

Signed-off-by: David Matlack dmatlack@google.com --- tools/include/asm-generic/io.h | 482 +++++++++++++++++++++++++++++++++ tools/include/asm/io.h | 7 + tools/include/linux/io.h | 4 +- 3 files changed, 492 insertions(+), 1 deletion(-) create mode 100644 tools/include/asm-generic/io.h create mode 100644 tools/include/asm/io.h

diff --git a/tools/include/asm-generic/io.h b/tools/include/asm-generic/io.h new file mode 100644 index 000000000000..e5a0b07ad452 --- /dev/null +++ b/tools/include/asm-generic/io.h @@ -0,0 +1,482 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_ASM_GENERIC_IO_H +#define _TOOLS_ASM_GENERIC_IO_H + +#include <asm/barrier.h> +#include <asm/byteorder.h> + +#include <linux/compiler.h> +#include <linux/kernel.h> +#include <linux/types.h> + +#ifndef mmiowb_set_pending +#define mmiowb_set_pending() do { } while (0) +#endif + +#ifndef __io_br +#define __io_br() barrier() +#endif + +/* prevent prefetching of coherent DMA data ahead of a dma-complete */ +#ifndef __io_ar +#ifdef rmb +#define __io_ar(v) rmb() +#else +#define __io_ar(v) barrier() +#endif +#endif + +/* flush writes to coherent DMA data before possibly triggering a DMA read */ +#ifndef __io_bw +#ifdef wmb +#define __io_bw() wmb() +#else +#define __io_bw() barrier() +#endif +#endif + +/* serialize device access against a spin_unlock, usually handled there. */ +#ifndef __io_aw +#define __io_aw() mmiowb_set_pending() +#endif + +#ifndef __io_pbw +#define __io_pbw() __io_bw() +#endif + +#ifndef __io_paw +#define __io_paw() __io_aw() +#endif + +#ifndef __io_pbr +#define __io_pbr() __io_br() +#endif + +#ifndef __io_par +#define __io_par(v) __io_ar(v) +#endif + +#ifndef _THIS_IP_ +#define _THIS_IP_ 0 +#endif + +static inline void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr, unsigned long caller_addr0) {} +static inline void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr, unsigned long caller_addr0) {} +static inline void log_read_mmio(u8 width, const volatile void __iomem *addr, + unsigned long caller_addr, unsigned long caller_addr0) {} +static inline void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr, + unsigned long caller_addr, unsigned long caller_addr0) {} + +/* + * __raw_{read,write}{b,w,l,q}() access memory in native endianness. + * + * On some architectures memory mapped IO needs to be accessed differently. + * On the simple architectures, we just read/write the memory location + * directly. + */ + +#ifndef __raw_readb +#define __raw_readb __raw_readb +static inline u8 __raw_readb(const volatile void __iomem *addr) +{ + return *(const volatile u8 __force *)addr; +} +#endif + +#ifndef __raw_readw +#define __raw_readw __raw_readw +static inline u16 __raw_readw(const volatile void __iomem *addr) +{ + return *(const volatile u16 __force *)addr; +} +#endif + +#ifndef __raw_readl +#define __raw_readl __raw_readl +static inline u32 __raw_readl(const volatile void __iomem *addr) +{ + return *(const volatile u32 __force *)addr; +} +#endif + +#ifndef __raw_readq +#define __raw_readq __raw_readq +static inline u64 __raw_readq(const volatile void __iomem *addr) +{ + return *(const volatile u64 __force *)addr; +} +#endif + +#ifndef __raw_writeb +#define __raw_writeb __raw_writeb +static inline void __raw_writeb(u8 value, volatile void __iomem *addr) +{ + *(volatile u8 __force *)addr = value; +} +#endif + +#ifndef __raw_writew +#define __raw_writew __raw_writew +static inline void __raw_writew(u16 value, volatile void __iomem *addr) +{ + *(volatile u16 __force *)addr = value; +} +#endif + +#ifndef __raw_writel +#define __raw_writel __raw_writel +static inline void __raw_writel(u32 value, volatile void __iomem *addr) +{ + *(volatile u32 __force *)addr = value; +} +#endif + +#ifndef __raw_writeq +#define __raw_writeq __raw_writeq +static inline void __raw_writeq(u64 value, volatile void __iomem *addr) +{ + *(volatile u64 __force *)addr = value; +} +#endif + +/* + * {read,write}{b,w,l,q}() access little endian memory and return result in + * native endianness. + */ + +#ifndef readb +#define readb readb +static inline u8 readb(const volatile void __iomem *addr) +{ + u8 val; + + log_read_mmio(8, addr, _THIS_IP_, _RET_IP_); + __io_br(); + val = __raw_readb(addr); + __io_ar(val); + log_post_read_mmio(val, 8, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef readw +#define readw readw +static inline u16 readw(const volatile void __iomem *addr) +{ + u16 val; + + log_read_mmio(16, addr, _THIS_IP_, _RET_IP_); + __io_br(); + val = __le16_to_cpu((__le16 __force)__raw_readw(addr)); + __io_ar(val); + log_post_read_mmio(val, 16, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef readl +#define readl readl +static inline u32 readl(const volatile void __iomem *addr) +{ + u32 val; + + log_read_mmio(32, addr, _THIS_IP_, _RET_IP_); + __io_br(); + val = __le32_to_cpu((__le32 __force)__raw_readl(addr)); + __io_ar(val); + log_post_read_mmio(val, 32, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef readq +#define readq readq +static inline u64 readq(const volatile void __iomem *addr) +{ + u64 val; + + log_read_mmio(64, addr, _THIS_IP_, _RET_IP_); + __io_br(); + val = __le64_to_cpu((__le64 __force)__raw_readq(addr)); + __io_ar(val); + log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef writeb +#define writeb writeb +static inline void writeb(u8 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_); + __io_bw(); + __raw_writeb(value, addr); + __io_aw(); + log_post_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#ifndef writew +#define writew writew +static inline void writew(u16 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); + __io_bw(); + __raw_writew((u16 __force)cpu_to_le16(value), addr); + __io_aw(); + log_post_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#ifndef writel +#define writel writel +static inline void writel(u32 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); + __io_bw(); + __raw_writel((u32 __force)__cpu_to_le32(value), addr); + __io_aw(); + log_post_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#ifndef writeq +#define writeq writeq +static inline void writeq(u64 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); + __io_bw(); + __raw_writeq((u64 __force)__cpu_to_le64(value), addr); + __io_aw(); + log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); +} +#endif + +/* + * {read,write}{b,w,l,q}_relaxed() are like the regular version, but + * are not guaranteed to provide ordering against spinlocks or memory + * accesses. + */ +#ifndef readb_relaxed +#define readb_relaxed readb_relaxed +static inline u8 readb_relaxed(const volatile void __iomem *addr) +{ + u8 val; + + log_read_mmio(8, addr, _THIS_IP_, _RET_IP_); + val = __raw_readb(addr); + log_post_read_mmio(val, 8, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef readw_relaxed +#define readw_relaxed readw_relaxed +static inline u16 readw_relaxed(const volatile void __iomem *addr) +{ + u16 val; + + log_read_mmio(16, addr, _THIS_IP_, _RET_IP_); + val = __le16_to_cpu((__le16 __force)__raw_readw(addr)); + log_post_read_mmio(val, 16, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef readl_relaxed +#define readl_relaxed readl_relaxed +static inline u32 readl_relaxed(const volatile void __iomem *addr) +{ + u32 val; + + log_read_mmio(32, addr, _THIS_IP_, _RET_IP_); + val = __le32_to_cpu((__le32 __force)__raw_readl(addr)); + log_post_read_mmio(val, 32, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#if defined(readq) && !defined(readq_relaxed) +#define readq_relaxed readq_relaxed +static inline u64 readq_relaxed(const volatile void __iomem *addr) +{ + u64 val; + + log_read_mmio(64, addr, _THIS_IP_, _RET_IP_); + val = __le64_to_cpu((__le64 __force)__raw_readq(addr)); + log_post_read_mmio(val, 64, addr, _THIS_IP_, _RET_IP_); + return val; +} +#endif + +#ifndef writeb_relaxed +#define writeb_relaxed writeb_relaxed +static inline void writeb_relaxed(u8 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_); + __raw_writeb(value, addr); + log_post_write_mmio(value, 8, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#ifndef writew_relaxed +#define writew_relaxed writew_relaxed +static inline void writew_relaxed(u16 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); + __raw_writew((u16 __force)cpu_to_le16(value), addr); + log_post_write_mmio(value, 16, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#ifndef writel_relaxed +#define writel_relaxed writel_relaxed +static inline void writel_relaxed(u32 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); + __raw_writel((u32 __force)__cpu_to_le32(value), addr); + log_post_write_mmio(value, 32, addr, _THIS_IP_, _RET_IP_); +} +#endif + +#if defined(writeq) && !defined(writeq_relaxed) +#define writeq_relaxed writeq_relaxed +static inline void writeq_relaxed(u64 value, volatile void __iomem *addr) +{ + log_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); + __raw_writeq((u64 __force)__cpu_to_le64(value), addr); + log_post_write_mmio(value, 64, addr, _THIS_IP_, _RET_IP_); +} +#endif + +/* + * {read,write}s{b,w,l,q}() repeatedly access the same memory address in + * native endianness in 8-, 16-, 32- or 64-bit chunks (@count times). + */ +#ifndef readsb +#define readsb readsb +static inline void readsb(const volatile void __iomem *addr, void *buffer, + unsigned int count) +{ + if (count) { + u8 *buf = buffer; + + do { + u8 x = __raw_readb(addr); + *buf++ = x; + } while (--count); + } +} +#endif + +#ifndef readsw +#define readsw readsw +static inline void readsw(const volatile void __iomem *addr, void *buffer, + unsigned int count) +{ + if (count) { + u16 *buf = buffer; + + do { + u16 x = __raw_readw(addr); + *buf++ = x; + } while (--count); + } +} +#endif + +#ifndef readsl +#define readsl readsl +static inline void readsl(const volatile void __iomem *addr, void *buffer, + unsigned int count) +{ + if (count) { + u32 *buf = buffer; + + do { + u32 x = __raw_readl(addr); + *buf++ = x; + } while (--count); + } +} +#endif + +#ifndef readsq +#define readsq readsq +static inline void readsq(const volatile void __iomem *addr, void *buffer, + unsigned int count) +{ + if (count) { + u64 *buf = buffer; + + do { + u64 x = __raw_readq(addr); + *buf++ = x; + } while (--count); + } +} +#endif + +#ifndef writesb +#define writesb writesb +static inline void writesb(volatile void __iomem *addr, const void *buffer, + unsigned int count) +{ + if (count) { + const u8 *buf = buffer; + + do { + __raw_writeb(*buf++, addr); + } while (--count); + } +} +#endif + +#ifndef writesw +#define writesw writesw +static inline void writesw(volatile void __iomem *addr, const void *buffer, + unsigned int count) +{ + if (count) { + const u16 *buf = buffer; + + do { + __raw_writew(*buf++, addr); + } while (--count); + } +} +#endif + +#ifndef writesl +#define writesl writesl +static inline void writesl(volatile void __iomem *addr, const void *buffer, + unsigned int count) +{ + if (count) { + const u32 *buf = buffer; + + do { + __raw_writel(*buf++, addr); + } while (--count); + } +} +#endif + +#ifndef writesq +#define writesq writesq +static inline void writesq(volatile void __iomem *addr, const void *buffer, + unsigned int count) +{ + if (count) { + const u64 *buf = buffer; + + do { + __raw_writeq(*buf++, addr); + } while (--count); + } +} +#endif + +#endif /* _TOOLS_ASM_GENERIC_IO_H */ diff --git a/tools/include/asm/io.h b/tools/include/asm/io.h new file mode 100644 index 000000000000..9ae219b12604 --- /dev/null +++ b/tools/include/asm/io.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_ASM_IO_H +#define _TOOLS_ASM_IO_H + +#include <asm-generic/io.h> + +#endif /* _TOOLS_ASM_IO_H */ diff --git a/tools/include/linux/io.h b/tools/include/linux/io.h index e129871fe661..4b94b84160b8 100644 --- a/tools/include/linux/io.h +++ b/tools/include/linux/io.h @@ -2,4 +2,6 @@ #ifndef _TOOLS_IO_H #define _TOOLS_IO_H

-#endif +#include <asm/io.h> + +#endif /* _TOOLS_IO_H */

Import iosubmit_cmds512() from arch/x86/include/asm/io.h into tools/ so it can be used by VFIO selftests to interact with Intel DSA devices.

Also pull in movdir64b() from arch/x86/include/asm/special_insns.h into tools/, which is the underlying instruction used by iosubmit_cmds512().

Changes made when importing: None

Signed-off-by: David Matlack dmatlack@google.com --- tools/arch/x86/include/asm/io.h | 26 +++++++++++++++++++++ tools/arch/x86/include/asm/special_insns.h | 27 ++++++++++++++++++++++ 2 files changed, 53 insertions(+) create mode 100644 tools/arch/x86/include/asm/special_insns.h

diff --git a/tools/arch/x86/include/asm/io.h b/tools/arch/x86/include/asm/io.h index 4c787a2363de..ecad61a3ea52 100644 --- a/tools/arch/x86/include/asm/io.h +++ b/tools/arch/x86/include/asm/io.h @@ -4,6 +4,7 @@

#include <linux/compiler.h> #include <linux/types.h> +#include "special_insns.h"

#define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -72,4 +73,29 @@ build_mmio_write(__writeq, "q", u64, "r", )

#include <asm-generic/io.h>

+/** + * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units + * @dst: destination, in MMIO space (must be 512-bit aligned) + * @src: source + * @count: number of 512 bits quantities to submit + * + * Submit data from kernel space to MMIO space, in units of 512 bits at a + * time. Order of access is not guaranteed, nor is a memory barrier + * performed afterwards. + * + * Warning: Do not use this helper unless your driver has checked that the CPU + * instruction is supported on the platform. + */ +static inline void iosubmit_cmds512(void __iomem *dst, const void *src, + size_t count) +{ + const u8 *from = src; + const u8 *end = from + count * 64; + + while (from < end) { + movdir64b(dst, from); + from += 64; + } +} + #endif /* _TOOLS_ASM_X86_IO_H */ diff --git a/tools/arch/x86/include/asm/special_insns.h b/tools/arch/x86/include/asm/special_insns.h new file mode 100644 index 000000000000..04af42a99c38 --- /dev/null +++ b/tools/arch/x86/include/asm/special_insns.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_ASM_X86_SPECIAL_INSNS_H +#define _TOOLS_ASM_X86_SPECIAL_INSNS_H + +/* The dst parameter must be 64-bytes aligned */ +static inline void movdir64b(void *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } *__dst = dst; + + /* + * MOVDIR64B %(rdx), rax. + * + * Both __src and __dst must be memory constraints in order to tell the + * compiler that no other memory accesses should be reordered around + * this one. + * + * Also, both must be supplied as lvalues because this tells + * the compiler what the object is (its size) the instruction accesses. + * I.e., not the pointers but what they point to, thus the deref'ing '*'. + */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); +} + +#endif /* _TOOLS_ASM_X86_SPECIAL_INSNS_H */

Keep track of the list of DMA regions that are mapped into the device using a linked list and a new struct vfio_dma_region and use that to add {__,}to_iova() for converting host virtual addresses into IOVAs.

This will be used in a subsequent commit to map multiple DMA regions into a device that are then used by drivers.

Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/lib/include/vfio_util.h | 23 +++++++-- .../selftests/vfio/lib/vfio_pci_device.c | 49 ++++++++++++++++--- .../selftests/vfio/vfio_dma_mapping_test.c | 21 +++++--- 3 files changed, 75 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index 234403b442af..db08646c2819 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -51,6 +51,17 @@ struct vfio_pci_bar { void *vaddr; };

+typedef u64 iova_t; + +#define INVALID_IOVA UINT64_MAX + +struct vfio_dma_region { + struct list_head link; + void *vaddr; + iova_t iova; + u64 size; +}; + struct vfio_pci_device { int fd; int group_fd; @@ -63,6 +74,8 @@ struct vfio_pci_device { struct vfio_irq_info msi_info; struct vfio_irq_info msix_info;

+ struct list_head dma_regions; + /* eventfds for MSI and MSI-x interrupts */ int msi_eventfds[PCI_MSIX_FLAGS_QSIZE + 1]; }; @@ -85,9 +98,10 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type); void vfio_pci_device_cleanup(struct vfio_pci_device *device); void vfio_pci_device_reset(struct vfio_pci_device *device);

-void vfio_pci_dma_map(struct vfio_pci_device *device, u64 iova, u64 size, - void *vaddr); -void vfio_pci_dma_unmap(struct vfio_pci_device *device, u64 iova, u64 size); +void vfio_pci_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region); +void vfio_pci_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region);

void vfio_pci_config_access(struct vfio_pci_device *device, bool write, size_t config, size_t size, void *data); @@ -138,4 +152,7 @@ static inline void vfio_pci_msix_disable(struct vfio_pci_device *device) vfio_pci_irq_disable(device, VFIO_PCI_MSIX_IRQ_INDEX); }

+iova_t __to_iova(struct vfio_pci_device *device, void *vaddr); +iova_t to_iova(struct vfio_pci_device *device, void *vaddr); + #endif /* SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H */ diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 98cce0a6ecd7..36b4b30b75cf 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -26,6 +26,33 @@ VFIO_ASSERT_EQ(__ret, 0, "ioctl(%s, %s, %s) returned %d\n", #_fd, #_op, #_arg, __ret); \ } while (0)

+iova_t __to_iova(struct vfio_pci_device *device, void *vaddr) +{ + struct vfio_dma_region *region; + + list_for_each_entry(region, &device->dma_regions, link) { + if (vaddr < region->vaddr) + continue; + + if (vaddr >= region->vaddr + region->size) + continue; + + return region->iova + (vaddr - region->vaddr); + } + + return INVALID_IOVA; +} + +iova_t to_iova(struct vfio_pci_device *device, void *vaddr) +{ + iova_t iova; + + iova = __to_iova(device, vaddr); + VFIO_ASSERT_NE(iova, INVALID_IOVA, "%p is not mapped into device.\n", vaddr); + + return iova; +} + static void vfio_pci_irq_set(struct vfio_pci_device *device, u32 index, u32 vector, u32 count, int *fds) { @@ -112,28 +139,34 @@ static void vfio_pci_irq_get(struct vfio_pci_device *device, u32 index, ioctl_assert(device->fd, VFIO_DEVICE_GET_IRQ_INFO, irq_info); }

-void vfio_pci_dma_map(struct vfio_pci_device *device, u64 iova, u64 size, void *vaddr) +void vfio_pci_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) { struct vfio_iommu_type1_dma_map map = { .argsz = sizeof(map), .flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE, - .vaddr = (u64)vaddr, - .iova = iova, - .size = size, + .vaddr = (u64)region->vaddr, + .iova = region->iova, + .size = region->size, };

ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &map); + + list_add(&region->link, &device->dma_regions); }

-void vfio_pci_dma_unmap(struct vfio_pci_device *device, u64 iova, u64 size) +void vfio_pci_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) { struct vfio_iommu_type1_dma_unmap unmap = { .argsz = sizeof(unmap), - .iova = iova, - .size = size, + .iova = region->iova, + .size = region->size, };

ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &unmap); + + list_del(&region->link); }

static void vfio_pci_region_get(struct vfio_pci_device *device, int index, @@ -260,6 +293,8 @@ static void vfio_pci_iommu_setup(struct vfio_pci_device *device, unsigned long i { int ret;

+ INIT_LIST_HEAD(&device->dma_regions); + ret = ioctl(device->container_fd, VFIO_CHECK_EXTENSION, iommu_type); VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type);

diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 9cdf25b293c5..8cec09ba8ec3 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -128,21 +128,25 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) { const u64 size = variant->size ?: getpagesize(); const int flags = variant->mmap_flags; + struct vfio_dma_region region; struct iommu_mapping mapping; const u64 iova = 0; - void *mem; int rc;

- mem = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, -1, 0); + region.iova = iova; + region.size = size; + 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 && mem == MAP_FAILED) + if (flags & MAP_HUGETLB && region.vaddr == MAP_FAILED) SKIP(return, "mmap() failed: %s (%d)\n", strerror(errno), errno); else - ASSERT_NE(mem, MAP_FAILED); + ASSERT_NE(region.vaddr, MAP_FAILED);

- vfio_pci_dma_map(self->device, iova, size, mem); - printf("Mapped HVA %p (size 0x%lx) at IOVA 0x%lx\n", mem, size, iova); + vfio_pci_dma_map(self->device, &region); + printf("Mapped HVA %p (size 0x%lx) at IOVA 0x%lx\n", region.vaddr, size, iova); + + ASSERT_EQ(iova, to_iova(self->device, region.vaddr));

rc = iommu_mapping_get(device_bdf, iova, &mapping); if (rc == -EOPNOTSUPP) @@ -174,11 +178,12 @@ TEST_F(vfio_dma_mapping_test, dma_map_unmap) }

unmap: - vfio_pci_dma_unmap(self->device, iova, size); + vfio_pci_dma_unmap(self->device, &region); printf("Unmapped IOVA 0x%lx\n", iova); + ASSERT_EQ(INVALID_IOVA, __to_iova(self->device, region.vaddr)); ASSERT_NE(0, iommu_mapping_get(device_bdf, iova, &mapping));

- ASSERT_TRUE(!munmap(mem, size)); + ASSERT_TRUE(!munmap(region.vaddr, size)); }

int main(int argc, char *argv[])

Add a helper function for matching a device against a given vendor and device ID. This will be used in a subsequent commit to match devices against drivers.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/lib/include/vfio_util.h | 7 +++++++ tools/testing/selftests/vfio/vfio_pci_device_test.c | 4 +--- 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index 9c928fcc00e2..a51c971004cd 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -167,4 +167,11 @@ static inline void vfio_pci_msix_disable(struct vfio_pci_device *device) iova_t __to_iova(struct vfio_pci_device *device, void *vaddr); iova_t to_iova(struct vfio_pci_device *device, void *vaddr);

+static inline bool vfio_pci_device_match(struct vfio_pci_device *device, + u16 vendor_id, u16 device_id) +{ + return (vendor_id == vfio_pci_config_readw(device, PCI_VENDOR_ID)) && + (device_id == vfio_pci_config_readw(device, PCI_DEVICE_ID)); +} + #endif /* SELFTESTS_VFIO_LIB_INCLUDE_VFIO_UTIL_H */ diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c index 1b5c2ff77e3f..8856205d52a6 100644 --- a/tools/testing/selftests/vfio/vfio_pci_device_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c @@ -56,9 +56,7 @@ TEST_F(vfio_pci_device_test, config_space_read_write) /* Check that Vendor and Device match what the kernel reports. */ vendor = read_pci_id_from_sysfs("vendor"); device = read_pci_id_from_sysfs("device"); - - ASSERT_EQ(vendor, vfio_pci_config_readw(self->device, PCI_VENDOR_ID)); - ASSERT_EQ(device, vfio_pci_config_readw(self->device, PCI_DEVICE_ID)); + ASSERT_TRUE(vfio_pci_device_match(self->device, vendor, device));

printf("Vendor: %04x, Device: %04x\n", vendor, device);

Add a new selftest that tests all driver operations. This test serves both as a demonstration of the driver framework, and also as a correctness test for future drivers.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/Makefile | 1 + .../selftests/vfio/vfio_pci_driver_test.c | 236 ++++++++++++++++++ 2 files changed, 237 insertions(+) create mode 100644 tools/testing/selftests/vfio/vfio_pci_driver_test.c

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index 05c5a585cca6..ee09c027ade5 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_driver_test include ../lib.mk include lib/libvfio.mk

diff --git a/tools/testing/selftests/vfio/vfio_pci_driver_test.c b/tools/testing/selftests/vfio/vfio_pci_driver_test.c new file mode 100644 index 000000000000..ab22b7e357fd --- /dev/null +++ b/tools/testing/selftests/vfio/vfio_pci_driver_test.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/ioctl.h> +#include <sys/mman.h> + +#include <linux/pci_regs.h> +#include <linux/sizes.h> +#include <linux/vfio.h> +#include <linux/io.h> + +#include <vfio_util.h> + +#include "../kselftest_harness.h" + +static const char *device_bdf; + +#define ASSERT_NO_MSI(_eventfd) do { \ + u64 __value; \ + \ + ASSERT_EQ(-1, read(_eventfd, &__value, 8)); \ + ASSERT_EQ(EAGAIN, errno); \ +} while (0) + +static void region_setup(struct vfio_pci_device *device, + struct vfio_dma_region *region, + iova_t iova, u64 size) +{ + const int flags = MAP_SHARED | MAP_ANONYMOUS; + const int prot = PROT_READ | PROT_WRITE; + void *vaddr; + + vaddr = mmap(NULL, size, prot, flags, -1, 0); + VFIO_ASSERT_NE(vaddr, MAP_FAILED); + + region->vaddr = vaddr; + region->iova = iova; + region->size = size; + + vfio_pci_dma_map(device, region); +} + +static void region_teardown(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + vfio_pci_dma_unmap(device, region); + VFIO_ASSERT_EQ(munmap(region->vaddr, region->size), 0); +} + +FIXTURE(vfio_pci_driver_test) { + struct vfio_pci_device *device; + struct vfio_dma_region memcpy_region; + void *vaddr; + int msi_fd; + + u64 size; + void *src; + void *dst; + iova_t src_iova; + iova_t dst_iova; + iova_t unmapped_iova; +}; + +FIXTURE_SETUP(vfio_pci_driver_test) +{ + struct vfio_pci_driver *driver; + + self->device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + + driver = &self->device->driver; + + region_setup(self->device, &self->memcpy_region, SZ_1G, SZ_1G); + region_setup(self->device, &driver->region, SZ_4G, SZ_2M); + + /* Any IOVA that doesn't overlap memcpy_region and driver->region. */ + self->unmapped_iova = 8UL * SZ_1G; + + vfio_pci_driver_init(self->device); + self->msi_fd = self->device->msi_eventfds[driver->msi]; + + /* + * Use the maximum size supported by the device for memcpy operations, + * slimmed down to fit into the memcpy region (divided by 2 so src and + * dst regions do not overlap). + */ + self->size = self->device->driver.max_memcpy_size; + self->size = min(self->size, self->memcpy_region.size / 2); + + self->src = self->memcpy_region.vaddr; + self->dst = self->src + self->size; + + self->src_iova = to_iova(self->device, self->src); + self->dst_iova = to_iova(self->device, self->dst); +} + +FIXTURE_TEARDOWN(vfio_pci_driver_test) +{ + struct vfio_pci_driver *driver = &self->device->driver; + + vfio_pci_driver_remove(self->device); + + region_teardown(self->device, &self->memcpy_region); + region_teardown(self->device, &driver->region); + + vfio_pci_device_cleanup(self->device); +} + +TEST_F(vfio_pci_driver_test, init_remove) +{ + int i; + + for (i = 0; i < 10; i++) { + vfio_pci_driver_remove(self->device); + vfio_pci_driver_init(self->device); + } +} + +TEST_F(vfio_pci_driver_test, memcpy_success) +{ + fcntl_set_nonblock(self->msi_fd); + + memset(self->src, 'x', self->size); + memset(self->dst, 'y', self->size); + + ASSERT_EQ(0, vfio_pci_driver_memcpy(self->device, + self->src_iova, + self->dst_iova, + self->size)); + + ASSERT_EQ(0, memcmp(self->src, self->dst, self->size)); + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, memcpy_from_unmapped_iova) +{ + fcntl_set_nonblock(self->msi_fd); + + /* + * Ignore the return value since not all devices will detect and report + * accesses to unmapped IOVAs as errors. + */ + vfio_pci_driver_memcpy(self->device, self->unmapped_iova, + self->dst_iova, self->size); + + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, memcpy_to_unmapped_iova) +{ + fcntl_set_nonblock(self->msi_fd); + + /* + * Ignore the return value since not all devices will detect and report + * accesses to unmapped IOVAs as errors. + */ + vfio_pci_driver_memcpy(self->device, self->src_iova, + self->unmapped_iova, self->size); + + ASSERT_NO_MSI(self->msi_fd); +} + +TEST_F(vfio_pci_driver_test, send_msi) +{ + u64 value; + + vfio_pci_driver_send_msi(self->device); + ASSERT_EQ(8, read(self->msi_fd, &value, 8)); + ASSERT_EQ(1, value); +} + +TEST_F(vfio_pci_driver_test, mix_and_match) +{ + u64 value; + int i; + + for (i = 0; i < 10; i++) { + memset(self->src, 'x', self->size); + memset(self->dst, 'y', self->size); + + ASSERT_EQ(0, vfio_pci_driver_memcpy(self->device, + self->src_iova, + self->dst_iova, + self->size)); + + ASSERT_EQ(0, memcmp(self->src, self->dst, self->size)); + + vfio_pci_driver_memcpy(self->device, + self->unmapped_iova, + self->dst_iova, + self->size); + + vfio_pci_driver_send_msi(self->device); + ASSERT_EQ(8, read(self->msi_fd, &value, 8)); + ASSERT_EQ(1, value); + } +} + +TEST_F_TIMEOUT(vfio_pci_driver_test, memcpy_storm, 60) +{ + struct vfio_pci_driver *driver = &self->device->driver; + u64 total_size; + u64 count; + + fcntl_set_nonblock(self->msi_fd); + + /* + * Perform up to 250GiB worth of DMA reads and writes across several + * memcpy operations. Some devices can support even more but the test + * will take too long. + */ + total_size = 250UL * SZ_1G; + count = min(total_size / self->size, driver->max_memcpy_count); + + printf("Kicking off %lu memcpys of size 0x%lx\n", count, self->size); + vfio_pci_driver_memcpy_start(self->device, + self->src_iova, + self->dst_iova, + self->size, count); + + ASSERT_EQ(0, vfio_pci_driver_memcpy_wait(self->device)); + ASSERT_NO_MSI(self->msi_fd); +} + +int main(int argc, char *argv[]) +{ + struct vfio_pci_device *device; + + device_bdf = vfio_selftests_get_bdf(&argc, argv); + + device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + if (!device->driver.ops) { + fprintf(stderr, "No driver found for device %s\n", device_bdf); + return KSFT_SKIP; + } + vfio_pci_device_cleanup(device); + + return test_harness_run(argc, argv); +}

Add a driver for the Intel CBDMA device. This driver is based on and named after the Linux driver for this device (drivers/dma/ioat/) and also based on previous work from Peter Shier pshier@google.com.

The driver aims to be as simple as possible. It uses a single descriptor to issue DMA operations, and only supports the copy operation. For "DMA storms", the driver kicks off the maximum number of maximum-sized DMA operations. On Skylake server parts, this was 2^16-1 copies of size 2M and lasts about 15 seconds.

Create symlinks to drivers/dma/ioat/{hw.h,registers.h} to get access to various macros (e.g. IOAT_CHANCMD_RESET) and struct ioat_dma_descriptor.

Cc: Dave Jiang dave.jiang@intel.com Cc: Dan Williams dan.j.williams@intel.com Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/lib/drivers/ioat/hw.h | 1 + .../selftests/vfio/lib/drivers/ioat/ioat.c | 235 ++++++++++++++++++ .../vfio/lib/drivers/ioat/registers.h | 1 + tools/testing/selftests/vfio/lib/libvfio.mk | 7 + .../selftests/vfio/lib/vfio_pci_driver.c | 10 +- 5 files changed, 253 insertions(+), 1 deletion(-) create mode 120000 tools/testing/selftests/vfio/lib/drivers/ioat/hw.h create mode 100644 tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c create mode 120000 tools/testing/selftests/vfio/lib/drivers/ioat/registers.h

diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h b/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h new file mode 120000 index 000000000000..8ab52ddd4458 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/hw.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/ioat/hw.h \ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c b/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c new file mode 100644 index 000000000000..c3b91d9b1f59 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/ioat.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdint.h> +#include <unistd.h> + +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/pci_ids.h> +#include <linux/sizes.h> + +#include <vfio_util.h> + +#include "hw.h" +#include "registers.h" + +#define IOAT_DMACOUNT_MAX UINT16_MAX + +struct ioat_state { + /* Single descriptor used to issue DMA memcpy operations */ + struct ioat_dma_descriptor desc; + + /* Copy buffers used by ioat_send_msi() to generate an interrupt. */ + u64 send_msi_src; + u64 send_msi_dst; +}; + +static inline struct ioat_state *to_ioat_state(struct vfio_pci_device *device) +{ + return device->driver.region.vaddr; +} + +static inline void *ioat_channel_registers(struct vfio_pci_device *device) +{ + return device->bars[0].vaddr + IOAT_CHANNEL_MMIO_SIZE; +} + +static int ioat_probe(struct vfio_pci_device *device) +{ + u8 version; + int r; + + if (!vfio_pci_device_match(device, PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_IOAT_SKX)) + return -EINVAL; + + VFIO_ASSERT_NOT_NULL(device->bars[0].vaddr); + + version = readb(device->bars[0].vaddr + IOAT_VER_OFFSET); + switch (version) { + case IOAT_VER_3_2: + case IOAT_VER_3_3: + r = 0; + break; + default: + printf("ioat: Unsupported version: 0x%x\n", version); + r = -EINVAL; + } + return r; +} + +static u64 ioat_channel_status(void *bar) +{ + return readq(bar + IOAT_CHANSTS_OFFSET) & IOAT_CHANSTS_STATUS; +} + +static void ioat_clear_errors(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u32 errors; + + errors = vfio_pci_config_readl(device, IOAT_PCI_CHANERR_INT_OFFSET); + vfio_pci_config_writel(device, IOAT_PCI_CHANERR_INT_OFFSET, errors); + + errors = vfio_pci_config_readl(device, IOAT_PCI_DMAUNCERRSTS_OFFSET); + vfio_pci_config_writel(device, IOAT_PCI_CHANERR_INT_OFFSET, errors); + + errors = readl(registers + IOAT_CHANERR_OFFSET); + writel(errors, registers + IOAT_CHANERR_OFFSET); +} + +static void ioat_reset(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u32 sleep_ms = 1, attempts = 5000 / sleep_ms; + u8 chancmd; + + ioat_clear_errors(device); + + writeb(IOAT_CHANCMD_RESET, registers + IOAT2_CHANCMD_OFFSET); + + for (;;) { + chancmd = readb(registers + IOAT2_CHANCMD_OFFSET); + if (!(chancmd & IOAT_CHANCMD_RESET)) + break; + + VFIO_ASSERT_GT(--attempts, 0); + usleep(sleep_ms * 1000); + } + + VFIO_ASSERT_EQ(ioat_channel_status(registers), IOAT_CHANSTS_HALTED); +} + +static void ioat_init(struct vfio_pci_device *device) +{ + struct ioat_state *ioat = to_ioat_state(device); + u8 intrctrl; + + VFIO_ASSERT_GE(device->driver.region.size, sizeof(*ioat)); + + vfio_pci_config_writew(device, PCI_COMMAND, + PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | + PCI_COMMAND_INTX_DISABLE); + + ioat_reset(device); + + /* Enable the use of MXI-x interrupts for channel interrupts. */ + intrctrl = IOAT_INTRCTRL_MSIX_VECTOR_CONTROL; + writeb(intrctrl, device->bars[0].vaddr + IOAT_INTRCTRL_OFFSET); + + vfio_pci_msix_enable(device, 0, device->msix_info.count); + + device->driver.msi = 0; + device->driver.max_memcpy_size = + 1UL << readb(device->bars[0].vaddr + IOAT_XFERCAP_OFFSET); + device->driver.max_memcpy_count = IOAT_DMACOUNT_MAX; +} + +static void ioat_remove(struct vfio_pci_device *device) +{ + ioat_reset(device); + vfio_pci_msix_disable(device); +} + +static void ioat_handle_error(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + + printf("Error detected during memcpy operation!\n" + " CHANERR: 0x%x\n" + " CHANERR_INT: 0x%x\n" + " DMAUNCERRSTS: 0x%x\n", + readl(registers + IOAT_CHANERR_OFFSET), + vfio_pci_config_readl(device, IOAT_PCI_CHANERR_INT_OFFSET), + vfio_pci_config_readl(device, IOAT_PCI_DMAUNCERRSTS_OFFSET)); + + ioat_reset(device); +} + +static int ioat_memcpy_wait(struct vfio_pci_device *device) +{ + void *registers = ioat_channel_registers(device); + u64 status; + int r = 0; + + /* Wait until all operations complete. */ + for (;;) { + status = ioat_channel_status(registers); + if (status == IOAT_CHANSTS_DONE) + break; + + if (status == IOAT_CHANSTS_HALTED) { + ioat_handle_error(device); + return -1; + } + } + + /* Put the channel into the SUSPENDED state. */ + writeb(IOAT_CHANCMD_SUSPEND, registers + IOAT2_CHANCMD_OFFSET); + for (;;) { + status = ioat_channel_status(registers); + if (status == IOAT_CHANSTS_SUSPENDED) + break; + } + + return r; +} + +static void __ioat_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u16 count, bool interrupt) +{ + void *registers = ioat_channel_registers(device); + struct ioat_state *ioat = to_ioat_state(device); + u64 desc_iova; + u16 chanctrl; + + desc_iova = to_iova(device, &ioat->desc); + ioat->desc = (struct ioat_dma_descriptor) { + .ctl_f.op = IOAT_OP_COPY, + .ctl_f.int_en = interrupt, + .src_addr = src, + .dst_addr = dst, + .size = size, + .next = desc_iova, + }; + + /* Tell the device the address of the descriptor. */ + writeq(desc_iova, registers + IOAT2_CHAINADDR_OFFSET); + + /* (Re)Enable the channel interrupt and abort on any errors */ + chanctrl = IOAT_CHANCTRL_INT_REARM | IOAT_CHANCTRL_ANY_ERR_ABORT_EN; + writew(chanctrl, registers + IOAT_CHANCTRL_OFFSET); + + /* Kick off @count DMA copy operation(s). */ + writew(count, registers + IOAT_CHAN_DMACOUNT_OFFSET); +} + +static void ioat_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, + u64 count) +{ + __ioat_memcpy_start(device, src, dst, size, count, false); +} + +static void ioat_send_msi(struct vfio_pci_device *device) +{ + struct ioat_state *ioat = to_ioat_state(device); + + __ioat_memcpy_start(device, + to_iova(device, &ioat->send_msi_src), + to_iova(device, &ioat->send_msi_dst), + sizeof(ioat->send_msi_src), 1, true); + + VFIO_ASSERT_EQ(ioat_memcpy_wait(device), 0); +} + +const struct vfio_pci_driver_ops ioat_ops = { + .name = "ioat", + .probe = ioat_probe, + .init = ioat_init, + .remove = ioat_remove, + .memcpy_start = ioat_memcpy_start, + .memcpy_wait = ioat_memcpy_wait, + .send_msi = ioat_send_msi, +}; diff --git a/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h b/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h new file mode 120000 index 000000000000..0b809cfd8fe6 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/ioat/registers.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/ioat/registers.h \ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/libvfio.mk b/tools/testing/selftests/vfio/lib/libvfio.mk index a3c3bc9a7c00..624dc267a879 100644 --- a/tools/testing/selftests/vfio/lib/libvfio.mk +++ b/tools/testing/selftests/vfio/lib/libvfio.mk @@ -1,8 +1,15 @@ +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + VFIO_DIR := $(selfdir)/vfio

LIBVFIO_C := lib/vfio_pci_device.c LIBVFIO_C += lib/vfio_pci_driver.c

+ifeq ($(ARCH:x86_64=x86),x86) +LIBVFIO_C += lib/drivers/ioat/ioat.c +endif + LIBVFIO_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBVFIO_C))

LIBVFIO_O_DIRS := $(shell dirname $(LIBVFIO_O) | uniq) diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c index c98bd2d31d8a..aa47360e47a9 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c @@ -4,7 +4,15 @@ #include "../../../kselftest.h" #include <vfio_util.h>

-static struct vfio_pci_driver_ops *driver_ops[] = {}; +#ifdef __x86_64__ +extern struct vfio_pci_driver_ops ioat_ops; +#endif + +static struct vfio_pci_driver_ops *driver_ops[] = { +#ifdef __x86_64__ + &ioat_ops, +#endif +};

void vfio_pci_driver_probe(struct vfio_pci_device *device) {

Add a driver to VFIO selftests for Intel DSA devices.

For now the driver only supports up to 32 batches and 1024 copies per batch, which were the limits of the hardware this commit was tested with. This is sufficient to generate 9+ minutes of DMA memcpys at a rate of over 30 GB/s. This should be plenty to stress test VFIO and the IOMMU.

The driver does not yet support requesting interrupt handles, as this commit was not tested against hardware that requires it.

Cc: Vinicius Costa Gomes vinicius.gomes@intel.com Cc: Dave Jiang dave.jiang@intel.com Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/lib/drivers/dsa/dsa.c | 416 ++++++++++++++++++ .../vfio/lib/drivers/dsa/registers.h | 1 + tools/testing/selftests/vfio/lib/libvfio.mk | 1 + .../selftests/vfio/lib/vfio_pci_driver.c | 2 + 4 files changed, 420 insertions(+) create mode 100644 tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c create mode 120000 tools/testing/selftests/vfio/lib/drivers/dsa/registers.h

diff --git a/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c b/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c new file mode 100644 index 000000000000..0ca2cbc2a316 --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/dsa/dsa.c @@ -0,0 +1,416 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <stdint.h> +#include <unistd.h> + +#include <linux/bits.h> +#include <linux/errno.h> +#include <linux/idxd.h> +#include <linux/io.h> +#include <linux/pci_ids.h> +#include <linux/sizes.h> + +#include <vfio_util.h> + +#include "registers.h" + +/* Vectors 1+ are available for work queue completion interrupts. */ +#define MSIX_VECTOR 1 + +struct dsa_state { + /* Descriptors for copy and batch operations. */ + struct dsa_hw_desc batch[32]; + struct dsa_hw_desc copy[1024]; + + /* Completion records for copy and batch operations. */ + struct dsa_completion_record copy_completion; + struct dsa_completion_record batch_completion; + + /* Cached device registers (and derived data) for easy access */ + union gen_cap_reg gen_cap; + union wq_cap_reg wq_cap; + union group_cap_reg group_cap; + union engine_cap_reg engine_cap; + union offsets_reg table_offsets; + void *wqcfg_table; + void *grpcfg_table; + u64 max_batches; + u64 max_copies_per_batch; + + /* The number of ongoing memcpy operations. */ + u64 memcpy_count; + + /* Buffers used by dsa_send_msi() to generate an interrupt */ + u64 send_msi_src; + u64 send_msi_dst; +}; + +static inline struct dsa_state *to_dsa_state(struct vfio_pci_device *device) +{ + return device->driver.region.vaddr; +} + +static bool dsa_int_handle_request_required(struct vfio_pci_device *device) +{ + void *bar0 = device->bars[0].vaddr; + union gen_cap_reg gen_cap; + u32 cmd_cap; + + gen_cap.bits = readq(bar0 + IDXD_GENCAP_OFFSET); + if (!gen_cap.cmd_cap) + return false; + + cmd_cap = readl(bar0 + IDXD_CMDCAP_OFFSET); + return (cmd_cap >> IDXD_CMD_REQUEST_INT_HANDLE) & 1; +} + +static int dsa_probe(struct vfio_pci_device *device) +{ + if (!vfio_pci_device_match(device, PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_DSA_SPR0)) + return -EINVAL; + + if (dsa_int_handle_request_required(device)) { + printf("Device requires requesting interrupt handles\n"); + return -EINVAL; + } + + return 0; +} + +static void dsa_check_sw_err(struct vfio_pci_device *device) +{ + void *reg = device->bars[0].vaddr + IDXD_SWERR_OFFSET; + union sw_err_reg err = {}; + int i; + + for (i = 0; i < ARRAY_SIZE(err.bits); i++) { + err.bits[i] = readq(reg + offsetof(union sw_err_reg, bits[i])); + + /* No errors */ + if (i == 0 && !err.valid) + return; + } + + fprintf(stderr, "SWERR: 0x%016lx 0x%016lx 0x%016lx 0x%016lx\n", + err.bits[0], err.bits[1], err.bits[2], err.bits[3]); + + fprintf(stderr, " valid: 0x%x\n", err.valid); + fprintf(stderr, " overflow: 0x%x\n", err.overflow); + fprintf(stderr, " desc_valid: 0x%x\n", err.desc_valid); + fprintf(stderr, " wq_idx_valid: 0x%x\n", err.wq_idx_valid); + fprintf(stderr, " batch: 0x%x\n", err.batch); + fprintf(stderr, " fault_rw: 0x%x\n", err.fault_rw); + fprintf(stderr, " priv: 0x%x\n", err.priv); + fprintf(stderr, " error: 0x%x\n", err.error); + fprintf(stderr, " wq_idx: 0x%x\n", err.wq_idx); + fprintf(stderr, " operation: 0x%x\n", err.operation); + fprintf(stderr, " pasid: 0x%x\n", err.pasid); + fprintf(stderr, " batch_idx: 0x%x\n", err.batch_idx); + fprintf(stderr, " invalid_flags: 0x%x\n", err.invalid_flags); + fprintf(stderr, " fault_addr: 0x%lx\n", err.fault_addr); + + VFIO_FAIL("Software Error Detected!\n"); +} + +static void dsa_command(struct vfio_pci_device *device, u32 cmd) +{ + union idxd_command_reg cmd_reg = { .cmd = cmd }; + u32 sleep_ms = 1, attempts = 5000 / sleep_ms; + void *bar0 = device->bars[0].vaddr; + u32 status; + u8 err; + + writel(cmd_reg.bits, bar0 + IDXD_CMD_OFFSET); + + for (;;) { + dsa_check_sw_err(device); + + status = readl(bar0 + IDXD_CMDSTS_OFFSET); + if (!(status & IDXD_CMDSTS_ACTIVE)) + break; + + VFIO_ASSERT_GT(--attempts, 0); + usleep(sleep_ms * 1000); + } + + err = status & IDXD_CMDSTS_ERR_MASK; + VFIO_ASSERT_EQ(err, 0, "Error issuing command 0x%x: 0x%x\n", cmd, err); +} + +static void dsa_wq_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + union wq_cap_reg wq_cap = dsa->wq_cap; + union wqcfg wqcfg; + u64 wqcfg_size; + int i; + + VFIO_ASSERT_GT((u32)wq_cap.num_wqs, 0); + + wqcfg = (union wqcfg) { + .wq_size = wq_cap.total_wq_size, + .mode = 1, + .priority = 1, + /* + * Disable Address Translation Service (if enabled) so that VFIO + * selftests using this driver can generate I/O page faults. + */ + .wq_ats_disable = wq_cap.wq_ats_support, + .max_xfer_shift = dsa->gen_cap.max_xfer_shift, + .max_batch_shift = dsa->gen_cap.max_batch_shift, + .op_config[0] = BIT(DSA_OPCODE_MEMMOVE) | BIT(DSA_OPCODE_BATCH), + }; + + wqcfg_size = 1UL << (wq_cap.wqcfg_size + IDXD_WQCFG_MIN); + + for (i = 0; i < wqcfg_size / sizeof(wqcfg.bits[0]); i++) + writel(wqcfg.bits[i], dsa->wqcfg_table + offsetof(union wqcfg, bits[i])); +} + +static void dsa_group_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + union group_cap_reg group_cap = dsa->group_cap; + union engine_cap_reg engine_cap = dsa->engine_cap; + + VFIO_ASSERT_GT((u32)group_cap.num_groups, 0); + VFIO_ASSERT_GT((u32)engine_cap.num_engines, 0); + + /* Assign work queue 0 and engine 0 to group 0 */ + writeq(1, dsa->grpcfg_table + offsetof(struct grpcfg, wqs[0])); + writeq(1, dsa->grpcfg_table + offsetof(struct grpcfg, engines)); +} + +static void dsa_register_cache_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + void *bar0 = device->bars[0].vaddr; + + dsa->gen_cap.bits = readq(bar0 + IDXD_GENCAP_OFFSET); + dsa->wq_cap.bits = readq(bar0 + IDXD_WQCAP_OFFSET); + dsa->group_cap.bits = readq(bar0 + IDXD_GRPCAP_OFFSET); + dsa->engine_cap.bits = readq(bar0 + IDXD_ENGCAP_OFFSET); + + dsa->table_offsets.bits[0] = readq(bar0 + IDXD_TABLE_OFFSET); + dsa->table_offsets.bits[1] = readq(bar0 + IDXD_TABLE_OFFSET + 8); + + dsa->wqcfg_table = bar0 + dsa->table_offsets.wqcfg * IDXD_TABLE_MULT; + dsa->grpcfg_table = bar0 + dsa->table_offsets.grpcfg * IDXD_TABLE_MULT; + + dsa->max_batches = 1U << (dsa->wq_cap.total_wq_size + IDXD_WQCFG_MIN); + dsa->max_batches = min(dsa->max_batches, ARRAY_SIZE(dsa->batch)); + + dsa->max_copies_per_batch = 1UL << dsa->gen_cap.max_batch_shift; + dsa->max_copies_per_batch = min(dsa->max_copies_per_batch, ARRAY_SIZE(dsa->copy)); +} + +static void dsa_init(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + + VFIO_ASSERT_GE(device->driver.region.size, sizeof(*dsa)); + + vfio_pci_config_writew(device, PCI_COMMAND, + PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | + PCI_COMMAND_INTX_DISABLE); + + dsa_command(device, IDXD_CMD_RESET_DEVICE); + + dsa_register_cache_init(device); + dsa_wq_init(device); + dsa_group_init(device); + + dsa_command(device, IDXD_CMD_ENABLE_DEVICE); + dsa_command(device, IDXD_CMD_ENABLE_WQ); + + vfio_pci_msix_enable(device, MSIX_VECTOR, 1); + + device->driver.max_memcpy_count = + dsa->max_batches * dsa->max_copies_per_batch; + device->driver.max_memcpy_size = 1UL << dsa->gen_cap.max_xfer_shift; + device->driver.msi = MSIX_VECTOR; +} + +static void dsa_remove(struct vfio_pci_device *device) +{ + dsa_command(device, IDXD_CMD_RESET_DEVICE); + vfio_pci_msix_disable(device); +} + +static int dsa_completion_wait(struct vfio_pci_device *device, + struct dsa_completion_record *completion) +{ + u8 status; + + for (;;) { + dsa_check_sw_err(device); + + status = READ_ONCE(completion->status); + if (status) + break; + + usleep(1000); + } + + if (status == DSA_COMP_SUCCESS) + return 0; + + printf("Error detected during memcpy operation: 0x%x\n", status); + return -1; +} + +static void dsa_copy_desc_init(struct vfio_pci_device *device, + struct dsa_hw_desc *desc, + iova_t src, iova_t dst, u64 size, + bool interrupt) +{ + struct dsa_state *dsa = to_dsa_state(device); + u16 flags; + + flags = IDXD_OP_FLAG_CRAV | IDXD_OP_FLAG_RCR; + + if (interrupt) + flags |= IDXD_OP_FLAG_RCI; + + *desc = (struct dsa_hw_desc) { + .opcode = DSA_OPCODE_MEMMOVE, + .flags = flags, + .priv = 1, + .src_addr = src, + .dst_addr = dst, + .xfer_size = size, + .completion_addr = to_iova(device, &dsa->copy_completion), + .int_handle = interrupt ? MSIX_VECTOR : 0, + }; +} + +static void dsa_batch_desc_init(struct vfio_pci_device *device, + struct dsa_hw_desc *desc, + u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + + *desc = (struct dsa_hw_desc) { + .opcode = DSA_OPCODE_BATCH, + .flags = IDXD_OP_FLAG_CRAV, + .priv = 1, + .completion_addr = to_iova(device, &dsa->batch_completion), + .desc_list_addr = to_iova(device, &dsa->copy[0]), + .desc_count = count, + }; +} + +static void dsa_desc_write(struct vfio_pci_device *device, struct dsa_hw_desc *desc) +{ + /* Write the contents (not address) of the 64-byte descriptor to the device. */ + iosubmit_cmds512(device->bars[2].vaddr, desc, 1); +} + +static void dsa_memcpy_one(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, bool interrupt) +{ + struct dsa_state *dsa = to_dsa_state(device); + + memset(&dsa->copy_completion, 0, sizeof(dsa->copy_completion)); + + dsa_copy_desc_init(device, &dsa->copy[0], src, dst, size, interrupt); + dsa_desc_write(device, &dsa->copy[0]); +} + +static void dsa_memcpy_batch(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + int i; + + memset(&dsa->batch_completion, 0, sizeof(dsa->batch_completion)); + + for (i = 0; i < ARRAY_SIZE(dsa->copy); i++) { + struct dsa_hw_desc *copy_desc = &dsa->copy[i]; + + dsa_copy_desc_init(device, copy_desc, src, dst, size, false); + + /* Don't request completions for individual copies. */ + copy_desc->flags &= ~IDXD_OP_FLAG_RCR; + } + + for (i = 0; i < ARRAY_SIZE(dsa->batch) && count; i++) { + struct dsa_hw_desc *batch_desc = &dsa->batch[i]; + int nr_copies; + + nr_copies = min(count, dsa->max_copies_per_batch); + count -= nr_copies; + + /* + * Batches must have at least 2 copies, so handle the case where + * there is exactly 1 copy left by doing one less copy in this + * batch and then 2 in the next. + */ + if (count == 1) { + nr_copies--; + count++; + } + + dsa_batch_desc_init(device, batch_desc, nr_copies); + + /* Request a completion for the last batch. */ + if (!count) + batch_desc->flags |= IDXD_OP_FLAG_RCR; + + dsa_desc_write(device, batch_desc); + } + + VFIO_ASSERT_EQ(count, 0, "Failed to start %lu copies.\n", count); +} + +static void dsa_memcpy_start(struct vfio_pci_device *device, + iova_t src, iova_t dst, u64 size, u64 count) +{ + struct dsa_state *dsa = to_dsa_state(device); + + /* DSA devices require at least 2 copies per batch. */ + if (count == 1) + dsa_memcpy_one(device, src, dst, size, false); + else + dsa_memcpy_batch(device, src, dst, size, count); + + dsa->memcpy_count = count; +} + +static int dsa_memcpy_wait(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + int r; + + if (dsa->memcpy_count == 1) + r = dsa_completion_wait(device, &dsa->copy_completion); + else + r = dsa_completion_wait(device, &dsa->batch_completion); + + dsa->memcpy_count = 0; + + return r; +} + +static void dsa_send_msi(struct vfio_pci_device *device) +{ + struct dsa_state *dsa = to_dsa_state(device); + + dsa_memcpy_one(device, + to_iova(device, &dsa->send_msi_src), + to_iova(device, &dsa->send_msi_dst), + sizeof(dsa->send_msi_src), true); + + VFIO_ASSERT_EQ(dsa_completion_wait(device, &dsa->copy_completion), 0); +} + +const struct vfio_pci_driver_ops dsa_ops = { + .name = "dsa", + .probe = dsa_probe, + .init = dsa_init, + .remove = dsa_remove, + .memcpy_start = dsa_memcpy_start, + .memcpy_wait = dsa_memcpy_wait, + .send_msi = dsa_send_msi, +}; diff --git a/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h b/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h new file mode 120000 index 000000000000..bde657c3c2af --- /dev/null +++ b/tools/testing/selftests/vfio/lib/drivers/dsa/registers.h @@ -0,0 +1 @@ +../../../../../../../drivers/dma/idxd/registers.h \ No newline at end of file diff --git a/tools/testing/selftests/vfio/lib/libvfio.mk b/tools/testing/selftests/vfio/lib/libvfio.mk index 624dc267a879..5d11c3a89a28 100644 --- a/tools/testing/selftests/vfio/lib/libvfio.mk +++ b/tools/testing/selftests/vfio/lib/libvfio.mk @@ -8,6 +8,7 @@ LIBVFIO_C += lib/vfio_pci_driver.c

ifeq ($(ARCH:x86_64=x86),x86) LIBVFIO_C += lib/drivers/ioat/ioat.c +LIBVFIO_C += lib/drivers/dsa/dsa.c endif

LIBVFIO_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBVFIO_C)) diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c index aa47360e47a9..e5e8723ecb41 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c @@ -5,11 +5,13 @@ #include <vfio_util.h>

#ifdef __x86_64__ +extern struct vfio_pci_driver_ops dsa_ops; extern struct vfio_pci_driver_ops ioat_ops; #endif

static struct vfio_pci_driver_ops *driver_ops[] = { #ifdef __x86_64__ + &dsa_ops, &ioat_ops, #endif };

Encapsulate the "IOMMU mode" a test should use behind a new struct. In the future this will be used to support other types of IOMMUs besides VFIO_TYPE1_IOMMU, and allow users to select the mode on the command line.

No functional change intended.

Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/lib/include/vfio_util.h | 12 +++++- .../selftests/vfio/lib/vfio_pci_device.c | 42 ++++++++++++++++--- .../selftests/vfio/vfio_dma_mapping_test.c | 2 +- .../selftests/vfio/vfio_pci_device_test.c | 4 +- .../selftests/vfio/vfio_pci_driver_test.c | 4 +- 5 files changed, 52 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index 05a10417e0d7..d50debd84813 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -47,6 +47,12 @@ VFIO_LOG_AND_EXIT(_fmt, ##__VA_ARGS__); \ } while (0)

+struct vfio_iommu_mode { + const char *name; + const char *container_path; + unsigned long iommu_type; +}; + struct vfio_pci_bar { struct vfio_region_info info; void *vaddr; @@ -144,6 +150,8 @@ struct vfio_pci_driver {

struct vfio_pci_device { int fd; + + const struct vfio_iommu_mode *iommu_mode; int group_fd; int container_fd;

@@ -177,7 +185,9 @@ struct vfio_pci_device { const char *vfio_selftests_get_bdf(int *argc, char *argv[]); const char *vfio_pci_get_cdev_path(const char *bdf);

-struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type); +extern const char *default_iommu_mode; + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode); void vfio_pci_device_cleanup(struct vfio_pci_device *device); void vfio_pci_device_reset(struct vfio_pci_device *device);

diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index d53e2d682c7e..15e5adb770c3 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -18,7 +18,6 @@ #include "../../../kselftest.h" #include <vfio_util.h>

-#define VFIO_DEV_PATH "/dev/vfio/vfio" #define PCI_SYSFS_PATH "/sys/bus/pci/devices"

#define ioctl_assert(_fd, _op, _arg) do { \ @@ -261,10 +260,11 @@ static unsigned int vfio_pci_get_group_from_dev(const char *bdf)

static void vfio_pci_container_setup(struct vfio_pci_device *device) { + const char *path = device->iommu_mode->container_path; int version;

- device->container_fd = open(VFIO_DEV_PATH, O_RDWR); - VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", VFIO_DEV_PATH); + device->container_fd = open(path, O_RDWR); + VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", path);

version = ioctl(device->container_fd, VFIO_GET_API_VERSION); VFIO_ASSERT_EQ(version, VFIO_API_VERSION); @@ -290,8 +290,9 @@ static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->container_fd); }

-static void vfio_pci_iommu_setup(struct vfio_pci_device *device, unsigned long iommu_type) +static void vfio_pci_iommu_setup(struct vfio_pci_device *device) { + unsigned long iommu_type = device->iommu_mode->iommu_type; int ret;

INIT_LIST_HEAD(&device->dma_regions); @@ -363,16 +364,45 @@ const char *vfio_pci_get_cdev_path(const char *bdf) return cdev_path; }

-struct vfio_pci_device *vfio_pci_device_init(const char *bdf, int iommu_type) +static const struct vfio_iommu_mode iommu_modes[] = { + { + .name = "vfio_type1_iommu", + .container_path = "/dev/vfio/vfio", + .iommu_type = VFIO_TYPE1_IOMMU, + }, +}; + +const char *default_iommu_mode = "vfio_type1_iommu"; + +static const struct vfio_iommu_mode *lookup_iommu_mode(const char *iommu_mode) +{ + int i; + + if (!iommu_mode) + iommu_mode = default_iommu_mode; + + for (i = 0; i < ARRAY_SIZE(iommu_modes); i++) { + if (strcmp(iommu_mode, iommu_modes[i].name)) + continue; + + return &iommu_modes[i]; + } + + VFIO_FAIL("Unrecognized IOMMU mode: %s\n", iommu_mode); +} + +struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode) { struct vfio_pci_device *device;

device = calloc(1, sizeof(*device)); VFIO_ASSERT_NOT_NULL(device);

+ device->iommu_mode = lookup_iommu_mode(iommu_mode); + vfio_pci_container_setup(device); vfio_pci_group_setup(device, bdf); - vfio_pci_iommu_setup(device, iommu_type); + vfio_pci_iommu_setup(device); vfio_pci_device_setup(device, bdf);

vfio_pci_driver_probe(device); diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 8cec09ba8ec3..dfc14c40bcf6 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -116,7 +116,7 @@ FIXTURE_VARIANT_ADD(vfio_dma_mapping_test, anonymous_hugetlb_1gb) {

FIXTURE_SETUP(vfio_dma_mapping_test) { - self->device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode); }

FIXTURE_TEARDOWN(vfio_dma_mapping_test) diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c index 8856205d52a6..7a270698e4d2 100644 --- a/tools/testing/selftests/vfio/vfio_pci_device_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c @@ -28,7 +28,7 @@ FIXTURE(vfio_pci_device_test) {

FIXTURE_SETUP(vfio_pci_device_test) { - self->device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode); }

FIXTURE_TEARDOWN(vfio_pci_device_test) @@ -116,7 +116,7 @@ FIXTURE_VARIANT_ADD(vfio_pci_irq_test, msix) {

FIXTURE_SETUP(vfio_pci_irq_test) { - self->device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode); }

FIXTURE_TEARDOWN(vfio_pci_irq_test) diff --git a/tools/testing/selftests/vfio/vfio_pci_driver_test.c b/tools/testing/selftests/vfio/vfio_pci_driver_test.c index ab22b7e357fd..30cbfbb9225f 100644 --- a/tools/testing/selftests/vfio/vfio_pci_driver_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_driver_test.c @@ -63,7 +63,7 @@ FIXTURE_SETUP(vfio_pci_driver_test) { struct vfio_pci_driver *driver;

- self->device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + self->device = vfio_pci_device_init(device_bdf, default_iommu_mode);

driver = &self->device->driver;

@@ -225,7 +225,7 @@ int main(int argc, char *argv[])

device_bdf = vfio_selftests_get_bdf(&argc, argv);

- device = vfio_pci_device_init(device_bdf, VFIO_TYPE1_IOMMU); + device = vfio_pci_device_init(device_bdf, default_iommu_mode); if (!device->driver.ops) { fprintf(stderr, "No driver found for device %s\n", device_bdf); return KSFT_SKIP;

Add a new IOMMU mode for using VFIO_TYPE1v2_IOMMU.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/lib/include/vfio_util.h | 3 ++- tools/testing/selftests/vfio/lib/vfio_pci_device.c | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index bf0b636a9c0c..981ddc9a52a9 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -59,7 +59,8 @@ struct vfio_iommu_mode { * which should then use FIXTURE_VARIANT_ADD() to create the variant. */ #define FIXTURE_VARIANT_ADD_ALL_IOMMU_MODES(...) \ -FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1_iommu, ##__VA_ARGS__) +FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1_iommu, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1v2_iommu, ##__VA_ARGS__)

struct vfio_pci_bar { struct vfio_region_info info; diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 5c4d008f2a25..cc1b732dd8ba 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -371,6 +371,11 @@ static const struct vfio_iommu_mode iommu_modes[] = { .container_path = "/dev/vfio/vfio", .iommu_type = VFIO_TYPE1_IOMMU, }, + { + .name = "vfio_type1v2_iommu", + .container_path = "/dev/vfio/vfio", + .iommu_type = VFIO_TYPE1v2_IOMMU, + }, };

const char *default_iommu_mode = "vfio_type1_iommu";

Add a new IOMMU mode for using iommufd directly. In this mode userspace opens /dev/iommu and binds it to a device FD acquired through /dev/vfio/devices/vfioX.

Signed-off-by: David Matlack dmatlack@google.com --- .../selftests/vfio/lib/include/vfio_util.h | 6 +- .../selftests/vfio/lib/vfio_pci_device.c | 175 ++++++++++++++---- 2 files changed, 146 insertions(+), 35 deletions(-)

diff --git a/tools/testing/selftests/vfio/lib/include/vfio_util.h b/tools/testing/selftests/vfio/lib/include/vfio_util.h index 035ef5b9d678..ed31606e01b7 100644 --- a/tools/testing/selftests/vfio/lib/include/vfio_util.h +++ b/tools/testing/selftests/vfio/lib/include/vfio_util.h @@ -62,7 +62,8 @@ struct vfio_iommu_mode { FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1_iommu, ##__VA_ARGS__); \ FIXTURE_VARIANT_ADD_IOMMU_MODE(vfio_type1v2_iommu, ##__VA_ARGS__); \ FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd_compat_type1, ##__VA_ARGS__); \ -FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd_compat_type1v2, ##__VA_ARGS__) +FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd_compat_type1v2, ##__VA_ARGS__); \ +FIXTURE_VARIANT_ADD_IOMMU_MODE(iommufd, ##__VA_ARGS__)

struct vfio_pci_bar { struct vfio_region_info info; @@ -166,6 +167,9 @@ struct vfio_pci_device { int group_fd; int container_fd;

+ int iommufd; + u32 ioas_id; + struct vfio_device_info info; struct vfio_region_info config_space; struct vfio_pci_bar bars[PCI_STD_NUM_BARS]; diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index b6fefe2b3ec8..5d8944a37982 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -10,10 +10,12 @@ #include <sys/ioctl.h> #include <sys/mman.h>

+#include <uapi/linux/types.h> #include <linux/limits.h> #include <linux/mman.h> #include <linux/types.h> #include <linux/vfio.h> +#include <linux/iommufd.h>

#include "../../../kselftest.h" #include <vfio_util.h> @@ -139,32 +141,80 @@ static void vfio_pci_irq_get(struct vfio_pci_device *device, u32 index, ioctl_assert(device->fd, VFIO_DEVICE_GET_IRQ_INFO, irq_info); }

-void vfio_pci_dma_map(struct vfio_pci_device *device, - struct vfio_dma_region *region) +static void vfio_iommu_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) { - struct vfio_iommu_type1_dma_map map = { - .argsz = sizeof(map), + struct vfio_iommu_type1_dma_map args = { + .argsz = sizeof(args), .flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE, .vaddr = (u64)region->vaddr, .iova = region->iova, .size = region->size, };

- ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &map); + ioctl_assert(device->container_fd, VFIO_IOMMU_MAP_DMA, &args); +} + +static void iommufd_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct iommu_ioas_map args = { + .size = sizeof(args), + .flags = IOMMU_IOAS_MAP_READABLE | + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_FIXED_IOVA, + .user_va = (u64)region->vaddr, + .iova = region->iova, + .length = region->size, + .ioas_id = device->ioas_id, + }; + + ioctl_assert(device->iommufd, IOMMU_IOAS_MAP, &args); +} + +void vfio_pci_dma_map(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + if (device->iommufd) + iommufd_dma_map(device, region); + else + vfio_iommu_dma_map(device, region);

list_add(&region->link, &device->dma_regions); }

-void vfio_pci_dma_unmap(struct vfio_pci_device *device, - struct vfio_dma_region *region) +static void vfio_iommu_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) { - struct vfio_iommu_type1_dma_unmap unmap = { - .argsz = sizeof(unmap), + struct vfio_iommu_type1_dma_unmap args = { + .argsz = sizeof(args), .iova = region->iova, .size = region->size, };

- ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &unmap); + ioctl_assert(device->container_fd, VFIO_IOMMU_UNMAP_DMA, &args); +} + +static void iommufd_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + struct iommu_ioas_unmap args = { + .size = sizeof(args), + .iova = region->iova, + .length = region->size, + .ioas_id = device->ioas_id, + }; + + ioctl_assert(device->iommufd, IOMMU_IOAS_UNMAP, &args); +} + +void vfio_pci_dma_unmap(struct vfio_pci_device *device, + struct vfio_dma_region *region) +{ + if (device->iommufd) + iommufd_dma_unmap(device, region); + else + vfio_iommu_dma_unmap(device, region);

list_del(&region->link); } @@ -258,18 +308,6 @@ static unsigned int vfio_pci_get_group_from_dev(const char *bdf) return group; }

-static void vfio_pci_container_setup(struct vfio_pci_device *device) -{ - const char *path = device->iommu_mode->container_path; - int version; - - device->container_fd = open(path, O_RDWR); - VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", path); - - version = ioctl(device->container_fd, VFIO_GET_API_VERSION); - VFIO_ASSERT_EQ(version, VFIO_API_VERSION); -} - static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf) { struct vfio_group_status group_status = { @@ -290,26 +328,34 @@ static void vfio_pci_group_setup(struct vfio_pci_device *device, const char *bdf ioctl_assert(device->group_fd, VFIO_GROUP_SET_CONTAINER, &device->container_fd); }

-static void vfio_pci_iommu_setup(struct vfio_pci_device *device) +static void vfio_pci_container_setup(struct vfio_pci_device *device, const char *bdf) { unsigned long iommu_type = device->iommu_mode->iommu_type; + const char *path = device->iommu_mode->container_path; + int version; int ret;

- INIT_LIST_HEAD(&device->dma_regions); + device->container_fd = open(path, O_RDWR); + VFIO_ASSERT_GE(device->container_fd, 0, "open(%s) failed\n", path); + + version = ioctl(device->container_fd, VFIO_GET_API_VERSION); + VFIO_ASSERT_EQ(version, VFIO_API_VERSION, "Unsupported version: %d\n", version); + + vfio_pci_group_setup(device, bdf);

ret = ioctl(device->container_fd, VFIO_CHECK_EXTENSION, iommu_type); VFIO_ASSERT_GT(ret, 0, "VFIO IOMMU type %lu not supported\n", iommu_type);

ioctl_assert(device->container_fd, VFIO_SET_IOMMU, (void *)iommu_type); + + device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf); + VFIO_ASSERT_GE(device->fd, 0); }

-static void vfio_pci_device_setup(struct vfio_pci_device *device, const char *bdf) +static void vfio_pci_device_setup(struct vfio_pci_device *device) { int i;

- device->fd = ioctl(device->group_fd, VFIO_GROUP_GET_DEVICE_FD, bdf); - VFIO_ASSERT_GE(device->fd, 0); - device->info.argsz = sizeof(device->info); ioctl_assert(device->fd, VFIO_DEVICE_GET_INFO, &device->info);

@@ -386,6 +432,9 @@ static const struct vfio_iommu_mode iommu_modes[] = { .container_path = "/dev/iommu", .iommu_type = VFIO_TYPE1v2_IOMMU, }, + { + .name = "iommufd", + }, };

const char *default_iommu_mode = "vfio_type1_iommu"; @@ -407,6 +456,57 @@ static const struct vfio_iommu_mode *lookup_iommu_mode(const char *iommu_mode) VFIO_FAIL("Unrecognized IOMMU mode: %s\n", iommu_mode); }

+static void vfio_device_bind_iommufd(int device_fd, int iommufd) +{ + struct vfio_device_bind_iommufd args = { + .argsz = sizeof(args), + .iommufd = iommufd, + }; + + ioctl_assert(device_fd, VFIO_DEVICE_BIND_IOMMUFD, &args); +} + +static u32 iommufd_ioas_alloc(int iommufd) +{ + struct iommu_ioas_alloc args = { + .size = sizeof(args), + }; + + ioctl_assert(iommufd, IOMMU_IOAS_ALLOC, &args); + return args.out_ioas_id; +} + +static void vfio_device_attach_iommufd_pt(int device_fd, u32 pt_id) +{ + struct vfio_device_attach_iommufd_pt args = { + .argsz = sizeof(args), + .pt_id = pt_id, + }; + + ioctl_assert(device_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &args); +} + +static void vfio_pci_iommufd_setup(struct vfio_pci_device *device, const char *bdf) +{ + const char *cdev_path = vfio_pci_get_cdev_path(bdf); + + device->fd = open(cdev_path, O_RDWR); + VFIO_ASSERT_GE(device->fd, 0); + free((void *)cdev_path); + + /* + * Require device->iommufd to be >0 so that a simple non-0 check can be + * used to check if iommufd is enabled. In practice open() will never + * return 0 unless stdin is closed. + */ + device->iommufd = open("/dev/iommu", O_RDWR); + VFIO_ASSERT_GT(device->iommufd, 0); + + vfio_device_bind_iommufd(device->fd, device->iommufd); + device->ioas_id = iommufd_ioas_alloc(device->iommufd); + vfio_device_attach_iommufd_pt(device->fd, device->ioas_id); +} + struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_mode) { struct vfio_pci_device *device; @@ -414,13 +514,16 @@ struct vfio_pci_device *vfio_pci_device_init(const char *bdf, const char *iommu_ device = calloc(1, sizeof(*device)); VFIO_ASSERT_NOT_NULL(device);

+ INIT_LIST_HEAD(&device->dma_regions); + device->iommu_mode = lookup_iommu_mode(iommu_mode);

- vfio_pci_container_setup(device); - vfio_pci_group_setup(device, bdf); - vfio_pci_iommu_setup(device); - vfio_pci_device_setup(device, bdf); + if (device->iommu_mode->container_path) + vfio_pci_container_setup(device, bdf); + else + vfio_pci_iommufd_setup(device, bdf);

+ vfio_pci_device_setup(device); vfio_pci_driver_probe(device);

return device; @@ -444,8 +547,12 @@ void vfio_pci_device_cleanup(struct vfio_pci_device *device) VFIO_ASSERT_EQ(close(device->msi_eventfds[i]), 0); }

- VFIO_ASSERT_EQ(close(device->group_fd), 0); - VFIO_ASSERT_EQ(close(device->container_fd), 0); + if (device->iommufd) { + VFIO_ASSERT_EQ(close(device->iommufd), 0); + } else { + VFIO_ASSERT_EQ(close(device->group_fd), 0); + VFIO_ASSERT_EQ(close(device->container_fd), 0); + }

free(device); }

Introduce run.sh, a script to help with running VFIO selftests. The script is intended to be used for both humans manually running VFIO selftests, and to incorporate into test automation where VFIO selftests may run alongside other tests. As such the script aims to be hermetic, returning the system to the state it was before the test started.

The script takes as input the BDF of a device to use and a command to run (typically the command would be a VFIO selftest). e.g.

$ ./run.sh -d 0000:6a:01.0 ./vfio_pci_device_test

or

$ ./run.sh -d 0000:6a:01.0 -- ./vfio_pci_device_test

The script then handles unbinding device 0000:6a:01.0 from its current driver, binding it to vfio-pci, running the test, unbinding from vfio-pci, and binding back to the original driver.

When run.sh runs the provided test, it does so by appending the BDF as the last parameter. For example:

$ ./run.sh -d 0000:6a:01.0 -- echo hello

Results in the following being printed to stdout:

hello 0000:6a:01.0

The script also supports a mode where it can break out into a shell so that multiple tests can be run manually.

$ ./run.sh -d 0000:6a:01.0 -s $ echo $VFIO_SELFTESTS_BDF $ ./vfio_pci_device_test $ exit

Choosing which device to use is up to the user.

In the future this script should be extensible to tests that want to use multiple devices. The script can support accepting -d BDF multiple times and parse them into an array, setup all the devices, pass the list of BDFs to the test, and then cleanup all the devices.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/vfio/Makefile | 1 + tools/testing/selftests/vfio/run.sh | 109 ++++++++++++++++++++++++++ 2 files changed, 110 insertions(+) create mode 100755 tools/testing/selftests/vfio/run.sh

diff --git a/tools/testing/selftests/vfio/Makefile b/tools/testing/selftests/vfio/Makefile index ee09c027ade5..324ba0175a33 100644 --- a/tools/testing/selftests/vfio/Makefile +++ b/tools/testing/selftests/vfio/Makefile @@ -3,6 +3,7 @@ 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_driver_test +TEST_PROGS_EXTENDED := run.sh include ../lib.mk include lib/libvfio.mk

diff --git a/tools/testing/selftests/vfio/run.sh b/tools/testing/selftests/vfio/run.sh new file mode 100755 index 000000000000..0476b6d7adc3 --- /dev/null +++ b/tools/testing/selftests/vfio/run.sh @@ -0,0 +1,109 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +# Global variables initialized in main() and then used during cleanup() when +# the script exits. +declare DEVICE_BDF +declare NEW_DRIVER +declare OLD_DRIVER +declare OLD_NUMVFS +declare DRIVER_OVERRIDE + +function write_to() { + # Unfortunately set -x does not show redirects so use echo to manually + # tell the user what commands are being run. + echo "+ echo "${2}" > ${1}" + echo "${2}" > ${1} +} + +function bind() { + write_to /sys/bus/pci/drivers/${2}/bind ${1} +} + +function unbind() { + write_to /sys/bus/pci/drivers/${2}/unbind ${1} +} + +function set_sriov_numvfs() { + write_to /sys/bus/pci/devices/${1}/sriov_numvfs ${2} +} + +function set_driver_override() { + write_to /sys/bus/pci/devices/${1}/driver_override ${2} +} + +function clear_driver_override() { + set_driver_override ${1} "" +} + +function cleanup() { + if [ "${NEW_DRIVER}" ]; then unbind ${DEVICE_BDF} ${NEW_DRIVER} ; fi + if [ "${DRIVER_OVERRIDE}" ]; then clear_driver_override ${DEVICE_BDF} ; fi + if [ "${OLD_DRIVER}" ]; then bind ${DEVICE_BDF} ${OLD_DRIVER} ; fi + if [ "${OLD_NUMVFS}" ]; then set_sriov_numvfs ${DEVICE_BDF} ${OLD_NUMVFS} ; fi +} + +function usage() { + echo "usage: $0 [-d segment:bus:device.function] [-s] [-h] [cmd ...]" >&2 + echo >&2 + echo " -d: The BDF of the device to use for the test (required)" >&2 + echo " -h: Show this help message" >&2 + echo " -s: Drop into a shell rather than running a command" >&2 + echo >&2 + echo " cmd: The command to run and arguments to pass to it." >&2 + echo " Required when not using -s. The SBDF will be " >&2 + echo " appended to the argument list." >&2 + exit 1 +} + +function main() { + local shell + + while getopts "d:hs" opt; do + case $opt in + d) DEVICE_BDF="$OPTARG" ;; + s) shell=true ;; + *) usage ;; + esac + done + + # Shift past all optional arguments. + shift $((OPTIND - 1)) + + # Check that the user passed in the command to run. + [ ! "${shell}" ] && [ $# = 0 ] && usage + + # Check that the user passed in a BDF. + [ "${DEVICE_BDF}" ] || usage + + trap cleanup EXIT + set -e + + test -d /sys/bus/pci/devices/${DEVICE_BDF} + + if [ -f /sys/bus/pci/devices/${DEVICE_BDF}/sriov_numvfs ]; then + OLD_NUMVFS=$(cat /sys/bus/pci/devices/${DEVICE_BDF}/sriov_numvfs) + set_sriov_numvfs ${DEVICE_BDF} 0 + fi + + if [ -L /sys/bus/pci/devices/${DEVICE_BDF}/driver ]; then + OLD_DRIVER=$(basename $(readlink -m /sys/bus/pci/devices/${DEVICE_BDF}/driver)) + unbind ${DEVICE_BDF} ${OLD_DRIVER} + fi + + set_driver_override ${DEVICE_BDF} vfio-pci + DRIVER_OVERRIDE=true + + bind ${DEVICE_BDF} vfio-pci + NEW_DRIVER=vfio-pci + + echo + if [ "${shell}" ]; then + echo "Dropping into ${SHELL} with VFIO_SELFTESTS_BDF=${DEVICE_BDF}" + VFIO_SELFTESTS_BDF=${DEVICE_BDF} ${SHELL} + else + "$@" ${DEVICE_BDF} + fi + echo +} + +main "$@"

Add a new selftest called vfio_pci_device_irq_test that routes and delivers an MSI from a vfio-pci device into a guest.

Note that this test currently uses vfio_pci_irq_trigger(), in which VFIO emulates a device sending the MSI. In the future we want to replace this with a real MSI so we can test the hardware path (e.g. VT-d on Intel).

This test only supports x86_64 for now, but can be ported to other architectures in the future.

Signed-off-by: David Matlack dmatlack@google.com --- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../testing/selftests/kvm/include/kvm_util.h | 4 + tools/testing/selftests/kvm/lib/kvm_util.c | 21 +++ .../selftests/kvm/vfio_pci_device_irq_test.c | 123 ++++++++++++++++++ 4 files changed, 149 insertions(+) create mode 100644 tools/testing/selftests/kvm/vfio_pci_device_irq_test.c

diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 5a9644ce910b..ba6727dcf59d 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -146,6 +146,7 @@ TEST_GEN_PROGS_x86 += rseq_test TEST_GEN_PROGS_x86 += steal_time TEST_GEN_PROGS_x86 += system_counter_offset_test TEST_GEN_PROGS_x86 += pre_fault_memory_test +TEST_GEN_PROGS_x86 += vfio_pci_device_irq_test

# Compiled outputs used by test targets TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bee65ca08721..8afa6d6f1435 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -907,6 +907,8 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...); void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level); int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level);

+void kvm_add_irqfd(struct kvm_vm *vm, u32 gsi, int fd); + #define KVM_MAX_IRQ_ROUTES 4096

struct kvm_irq_routing *kvm_gsi_routing_create(void); @@ -915,6 +917,8 @@ void kvm_gsi_routing_irqchip_add(struct kvm_irq_routing *routing, int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing); void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing);

+void kvm_route_gsi(struct kvm_vm *vm, struct kvm_irq_routing_entry *entry); + const char *exit_reason_str(unsigned int exit_reason);

vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index a055343a7bf7..737252812d15 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1891,6 +1891,16 @@ void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret)); }

+void kvm_add_irqfd(struct kvm_vm *vm, u32 gsi, int fd) +{ + struct kvm_irqfd arg = { + .gsi = gsi, + .fd = fd, + }; + + vm_ioctl(vm, KVM_IRQFD, &arg); +} + struct kvm_irq_routing *kvm_gsi_routing_create(void) { struct kvm_irq_routing *routing; @@ -1941,6 +1951,17 @@ void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_GSI_ROUTING, ret)); }

+void kvm_route_gsi(struct kvm_vm *vm, struct kvm_irq_routing_entry *entry) +{ + u8 buf[sizeof(struct kvm_irq_routing) + sizeof(*entry)] = {}; + struct kvm_irq_routing *routes = (void *)&buf; + + routes->nr = 1; + routes->entries[0] = *entry; + + vm_ioctl(vm, KVM_SET_GSI_ROUTING, routes); +} + /* * VM Dump * diff --git a/tools/testing/selftests/kvm/vfio_pci_device_irq_test.c b/tools/testing/selftests/kvm/vfio_pci_device_irq_test.c new file mode 100644 index 000000000000..9b90cf9dd38f --- /dev/null +++ b/tools/testing/selftests/kvm/vfio_pci_device_irq_test.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "kvm_util.h" +#include "test_util.h" +#include "apic.h" +#include "processor.h" + +#include <pthread.h> +#include <time.h> +#include <linux/vfio.h> +#include <vfio_util.h> + +static bool guest_ready_for_irq; +static bool guest_received_irq; + +#define TIMEOUT_NS (10ULL * 1000 * 1000 * 1000) + +static void guest_enable_interrupts(void) +{ + x2apic_enable(); + asm volatile ("sti"); +} + +void kvm_route_msi(struct kvm_vm *vm, u32 gsi, struct kvm_vcpu *vcpu, u8 vector) +{ + struct kvm_irq_routing_entry entry = { + .gsi = gsi, + .type = KVM_IRQ_ROUTING_MSI, + .u.msi.address_lo = 0xFEE00000 | (vcpu->id << 12), + .u.msi.data = vector, + }; + + kvm_route_gsi(vm, &entry); +} + +static void guest_irq_handler(struct ex_regs *regs) +{ + WRITE_ONCE(guest_received_irq, true); + GUEST_DONE(); +} + +static void guest_code(void) +{ + guest_enable_interrupts(); + WRITE_ONCE(guest_ready_for_irq, true); + + for (;;) + continue; +} + +void *vcpu_thread_main(void *arg) +{ + struct kvm_vcpu *vcpu = arg; + struct ucall uc; + + vcpu_run(vcpu); + TEST_ASSERT_EQ(UCALL_DONE, get_ucall(vcpu, &uc)); + + return NULL; +} + +static void help(const char *name) +{ + printf("Usage: %s [-i iommu_mode] [segment:bus:device.function]\n", name); + exit(KSFT_FAIL); +} + +int main(int argc, char **argv) +{ + /* Random non-reserved vector and GSI to use for the device IRQ */ + const u8 vector = 0xe0; + const u32 gsi = 32; + + struct timespec start, elapsed; + struct vfio_pci_device *device; + const char *iommu_mode = NULL; + const char *device_bdf; + struct kvm_vcpu *vcpu; + pthread_t vcpu_thread; + struct kvm_vm *vm; + int c; + + device_bdf = vfio_selftests_get_bdf(&argc, argv); + + while ((c = getopt(argc, argv, "i:")) != -1) { + switch (c) { + case 'i': + iommu_mode = optarg; + break; + default: + help(argv[0]); + } + } + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + vm_install_exception_handler(vm, vector, guest_irq_handler); + + device = vfio_pci_device_init(device_bdf, iommu_mode); + TEST_REQUIRE(device->msix_info.count > 0); + + vfio_pci_msix_enable(device, 0, 1); + kvm_add_irqfd(vm, gsi, device->msi_eventfds[0]); + kvm_route_msi(vm, gsi, vcpu, vector); + + pthread_create(&vcpu_thread, NULL, vcpu_thread_main, vcpu); + + while (!READ_ONCE(guest_ready_for_irq)) + sync_global_from_guest(vm, guest_ready_for_irq); + + vfio_pci_irq_trigger(device, VFIO_PCI_MSIX_IRQ_INDEX, 0); + + clock_gettime(CLOCK_MONOTONIC, &start); + + while (!READ_ONCE(guest_received_irq)) { + elapsed = timespec_elapsed(start); + TEST_ASSERT(timespec_to_ns(elapsed) < TIMEOUT_NS, "vCPU never received IRQ\n"); + sync_global_from_guest(vm, guest_received_irq); + } + + pthread_join(vcpu_thread, NULL); + vfio_pci_device_cleanup(device); + + return 0; +}