diff options
Diffstat (limited to 'tools/testing/selftests/kvm/lib/kvm_util.c')
| -rw-r--r-- | tools/testing/selftests/kvm/lib/kvm_util.c | 2178 |
1 files changed, 1002 insertions, 1176 deletions
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8c53f96ab7fe..8279b6ced8d2 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -4,15 +4,15 @@ * * Copyright (C) 2018, Google LLC. */ - -#define _GNU_SOURCE /* for program_invocation_name */ #include "test_util.h" #include "kvm_util.h" -#include "kvm_util_internal.h" #include "processor.h" +#include "ucall_common.h" #include <assert.h> +#include <sched.h> #include <sys/mman.h> +#include <sys/resource.h> #include <sys/types.h> #include <sys/stat.h> #include <unistd.h> @@ -20,19 +20,33 @@ #define KVM_UTIL_MIN_PFN 2 -static int vcpu_mmap_sz(void); +uint32_t guest_random_seed; +struct guest_random_state guest_rng; +static uint32_t last_guest_seed; -int open_path_or_exit(const char *path, int flags) +static size_t vcpu_mmap_sz(void); + +int __open_path_or_exit(const char *path, int flags, const char *enoent_help) { int fd; fd = open(path, flags); - if (fd < 0) { - print_skip("%s not available (errno: %d)", path, errno); - exit(KSFT_SKIP); - } + if (fd < 0) + goto error; return fd; + +error: + if (errno == EACCES || errno == ENOENT) + ksft_exit_skip("- Cannot open '%s': %s. %s\n", + path, strerror(errno), + errno == EACCES ? "Root required?" : enoent_help); + TEST_FAIL("Failed to open '%s'", path); +} + +int open_path_or_exit(const char *path, int flags) +{ + return __open_path_or_exit(path, flags, ""); } /* @@ -46,7 +60,7 @@ int open_path_or_exit(const char *path, int flags) */ static int _open_kvm_dev_path_or_exit(int flags) { - return open_path_or_exit(KVM_DEV_PATH, flags); + return __open_path_or_exit(KVM_DEV_PATH, flags, "Is KVM loaded and enabled?"); } int open_kvm_dev_path_or_exit(void) @@ -54,143 +68,132 @@ int open_kvm_dev_path_or_exit(void) return _open_kvm_dev_path_or_exit(O_RDONLY); } -/* - * Capability - * - * Input Args: - * cap - Capability - * - * Output Args: None - * - * Return: - * On success, the Value corresponding to the capability (KVM_CAP_*) - * specified by the value of cap. On failure a TEST_ASSERT failure - * is produced. - * - * Looks up and returns the value corresponding to the capability - * (KVM_CAP_*) given by cap. - */ -int kvm_check_cap(long cap) +static ssize_t get_module_param(const char *module_name, const char *param, + void *buffer, size_t buffer_size) { - int ret; - int kvm_fd; + const int path_size = 128; + char path[path_size]; + ssize_t bytes_read; + int fd, r; - kvm_fd = open_kvm_dev_path_or_exit(); - ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); + /* Verify KVM is loaded, to provide a more helpful SKIP message. */ + close(open_kvm_dev_path_or_exit()); - close(kvm_fd); + r = snprintf(path, path_size, "/sys/module/%s/parameters/%s", + module_name, param); + TEST_ASSERT(r < path_size, + "Failed to construct sysfs path in %d bytes.", path_size); - return ret; + fd = open_path_or_exit(path, O_RDONLY); + + bytes_read = read(fd, buffer, buffer_size); + TEST_ASSERT(bytes_read > 0, "read(%s) returned %ld, wanted %ld bytes", + path, bytes_read, buffer_size); + + r = close(fd); + TEST_ASSERT(!r, "close(%s) failed", path); + return bytes_read; } -/* VM Check Capability - * - * Input Args: - * vm - Virtual Machine - * cap - Capability - * - * Output Args: None - * - * Return: - * On success, the Value corresponding to the capability (KVM_CAP_*) - * specified by the value of cap. On failure a TEST_ASSERT failure - * is produced. - * - * Looks up and returns the value corresponding to the capability - * (KVM_CAP_*) given by cap. - */ -int vm_check_cap(struct kvm_vm *vm, long cap) +int kvm_get_module_param_integer(const char *module_name, const char *param) { - int ret; + /* + * 16 bytes to hold a 64-bit value (1 byte per char), 1 byte for the + * NUL char, and 1 byte because the kernel sucks and inserts a newline + * at the end. + */ + char value[16 + 1 + 1]; + ssize_t r; - ret = ioctl(vm->fd, KVM_CHECK_EXTENSION, cap); - TEST_ASSERT(ret >= 0, "KVM_CHECK_EXTENSION VM IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); + memset(value, '\0', sizeof(value)); - return ret; + r = get_module_param(module_name, param, value, sizeof(value)); + TEST_ASSERT(value[r - 1] == '\n', + "Expected trailing newline, got char '%c'", value[r - 1]); + + /* + * Squash the newline, otherwise atoi_paranoid() will complain about + * trailing non-NUL characters in the string. + */ + value[r - 1] = '\0'; + return atoi_paranoid(value); } -/* VM Enable Capability - * - * Input Args: - * vm - Virtual Machine - * cap - Capability - * - * Output Args: None - * - * Return: On success, 0. On failure a TEST_ASSERT failure is produced. - * - * Enables a capability (KVM_CAP_*) on the VM. - */ -int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) +bool kvm_get_module_param_bool(const char *module_name, const char *param) { - int ret; + char value; + ssize_t r; - ret = ioctl(vm->fd, KVM_ENABLE_CAP, cap); - TEST_ASSERT(ret == 0, "KVM_ENABLE_CAP IOCTL failed,\n" - " rc: %i errno: %i", ret, errno); + r = get_module_param(module_name, param, &value, sizeof(value)); + TEST_ASSERT_EQ(r, 1); - return ret; + if (value == 'Y') + return true; + else if (value == 'N') + return false; + + TEST_FAIL("Unrecognized value '%c' for boolean module param", value); } -/* VCPU Enable Capability +/* + * Capability * * Input Args: - * vm - Virtual Machine - * vcpu_id - VCPU * cap - Capability * * Output Args: None * - * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * Return: + * On success, the Value corresponding to the capability (KVM_CAP_*) + * specified by the value of cap. On failure a TEST_ASSERT failure + * is produced. * - * Enables a capability (KVM_CAP_*) on the VCPU. + * Looks up and returns the value corresponding to the capability + * (KVM_CAP_*) given by cap. */ -int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, - struct kvm_enable_cap *cap) +unsigned int kvm_check_cap(long cap) { - struct vcpu *vcpu = vcpu_find(vm, vcpu_id); - int r; + int ret; + int kvm_fd; - TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + kvm_fd = open_kvm_dev_path_or_exit(); + ret = __kvm_ioctl(kvm_fd, KVM_CHECK_EXTENSION, (void *)cap); + TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret)); - r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); - TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" - " rc: %i, errno: %i", r, errno); + close(kvm_fd); - return r; + return (unsigned int)ret; } void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size) { - struct kvm_enable_cap cap = { 0 }; - - cap.cap = KVM_CAP_DIRTY_LOG_RING; - cap.args[0] = ring_size; - vm_enable_cap(vm, &cap); + if (vm_check_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL)) + vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING_ACQ_REL, ring_size); + else + vm_enable_cap(vm, KVM_CAP_DIRTY_LOG_RING, ring_size); vm->dirty_ring_size = ring_size; } -static void vm_open(struct kvm_vm *vm, int perm) +static void vm_open(struct kvm_vm *vm) { - vm->kvm_fd = _open_kvm_dev_path_or_exit(perm); + vm->kvm_fd = _open_kvm_dev_path_or_exit(O_RDWR); - if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) { - print_skip("immediate_exit not available"); - exit(KSFT_SKIP); - } + TEST_REQUIRE(kvm_has_cap(KVM_CAP_IMMEDIATE_EXIT)); - vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, vm->type); - TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, " - "rc: %i errno: %i", vm->fd, errno); + vm->fd = __kvm_ioctl(vm->kvm_fd, KVM_CREATE_VM, (void *)vm->type); + TEST_ASSERT(vm->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm->fd)); + + if (kvm_has_cap(KVM_CAP_BINARY_STATS_FD)) + vm->stats.fd = vm_get_stats_fd(vm); + else + vm->stats.fd = -1; } const char *vm_guest_mode_string(uint32_t i) { static const char * const strings[] = { [VM_MODE_P52V48_4K] = "PA-bits:52, VA-bits:48, 4K pages", + [VM_MODE_P52V48_16K] = "PA-bits:52, VA-bits:48, 16K pages", [VM_MODE_P52V48_64K] = "PA-bits:52, VA-bits:48, 64K pages", [VM_MODE_P48V48_4K] = "PA-bits:48, VA-bits:48, 4K pages", [VM_MODE_P48V48_16K] = "PA-bits:48, VA-bits:48, 16K pages", @@ -198,12 +201,13 @@ const char *vm_guest_mode_string(uint32_t i) [VM_MODE_P40V48_4K] = "PA-bits:40, VA-bits:48, 4K pages", [VM_MODE_P40V48_16K] = "PA-bits:40, VA-bits:48, 16K pages", [VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages", - [VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages", + [VM_MODE_PXXVYY_4K] = "PA-bits:ANY, VA-bits:48 or 57, 4K pages", [VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages", [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages", [VM_MODE_P36V48_4K] = "PA-bits:36, VA-bits:48, 4K pages", [VM_MODE_P36V48_16K] = "PA-bits:36, VA-bits:48, 16K pages", [VM_MODE_P36V48_64K] = "PA-bits:36, VA-bits:48, 64K pages", + [VM_MODE_P47V47_16K] = "PA-bits:47, VA-bits:47, 16K pages", [VM_MODE_P36V47_16K] = "PA-bits:36, VA-bits:47, 16K pages", }; _Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES, @@ -216,6 +220,7 @@ const char *vm_guest_mode_string(uint32_t i) const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, + [VM_MODE_P52V48_16K] = { 52, 48, 0x4000, 14 }, [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, [VM_MODE_P48V48_16K] = { 48, 48, 0x4000, 14 }, @@ -223,42 +228,39 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = { [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, [VM_MODE_P40V48_16K] = { 40, 48, 0x4000, 14 }, [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, - [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, + [VM_MODE_PXXVYY_4K] = { 0, 0, 0x1000, 12 }, [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, [VM_MODE_P36V48_4K] = { 36, 48, 0x1000, 12 }, [VM_MODE_P36V48_16K] = { 36, 48, 0x4000, 14 }, [VM_MODE_P36V48_64K] = { 36, 48, 0x10000, 16 }, + [VM_MODE_P47V47_16K] = { 47, 47, 0x4000, 14 }, [VM_MODE_P36V47_16K] = { 36, 47, 0x4000, 14 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); /* - * VM Create - * - * Input Args: - * mode - VM Mode (e.g. VM_MODE_P52V48_4K) - * phy_pages - Physical memory pages - * perm - permission - * - * Output Args: None - * - * Return: - * Pointer to opaque structure that describes the created VM. + * Initializes vm->vpages_valid to match the canonical VA space of the + * architecture. * - * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K). - * When phy_pages is non-zero, a memory region of phy_pages physical pages - * is created and mapped starting at guest physical address 0. The file - * descriptor to control the created VM is created with the permissions - * given by perm (e.g. O_RDWR). + * The default implementation is valid for architectures which split the + * range addressed by a single page table into a low and high region + * based on the MSB of the VA. On architectures with this behavior + * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1]. */ -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +__weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm) { - struct kvm_vm *vm; + sparsebit_set_num(vm->vpages_valid, + 0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift); + sparsebit_set_num(vm->vpages_valid, + (~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift, + (1ULL << (vm->va_bits - 1)) >> vm->page_shift); +} - pr_debug("%s: mode='%s' pages='%ld' perm='%d'\n", __func__, - vm_guest_mode_string(mode), phy_pages, perm); +struct kvm_vm *____vm_create(struct vm_shape shape) +{ + struct kvm_vm *vm; vm = calloc(1, sizeof(*vm)); TEST_ASSERT(vm != NULL, "Insufficient Memory"); @@ -268,13 +270,13 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->regions.hva_tree = RB_ROOT; hash_init(vm->regions.slot_hash); - vm->mode = mode; - vm->type = 0; + vm->mode = shape.mode; + vm->type = shape.type; - vm->pa_bits = vm_guest_mode_params[mode].pa_bits; - vm->va_bits = vm_guest_mode_params[mode].va_bits; - vm->page_size = vm_guest_mode_params[mode].page_size; - vm->page_shift = vm_guest_mode_params[mode].page_shift; + vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits; + vm->va_bits = vm_guest_mode_params[vm->mode].va_bits; + vm->page_size = vm_guest_mode_params[vm->mode].page_size; + vm->page_shift = vm_guest_mode_params[vm->mode].page_shift; /* Setup mode specific traits. */ switch (vm->mode) { @@ -298,31 +300,36 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) case VM_MODE_P36V48_64K: vm->pgtable_levels = 3; break; + case VM_MODE_P52V48_16K: case VM_MODE_P48V48_16K: case VM_MODE_P40V48_16K: case VM_MODE_P36V48_16K: vm->pgtable_levels = 4; break; + case VM_MODE_P47V47_16K: case VM_MODE_P36V47_16K: vm->pgtable_levels = 3; break; - case VM_MODE_PXXV48_4K: + case VM_MODE_PXXVYY_4K: #ifdef __x86_64__ kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits); - /* - * Ignore KVM support for 5-level paging (vm->va_bits == 57), - * it doesn't take effect unless a CR4.LA57 is set, which it - * isn't for this VM_MODE. - */ - TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57, - "Linear address width (%d bits) not supported", - vm->va_bits); + kvm_init_vm_address_properties(vm); + pr_debug("Guest physical address width detected: %d\n", vm->pa_bits); - vm->pgtable_levels = 4; - vm->va_bits = 48; + pr_debug("Guest virtual address width detected: %d\n", + vm->va_bits); + + if (vm->va_bits == 57) { + vm->pgtable_levels = 5; + } else { + TEST_ASSERT(vm->va_bits == 48, + "Unexpected guest virtual address width: %d", + vm->va_bits); + vm->pgtable_levels = 4; + } #else - TEST_FAIL("VM_MODE_PXXV48_4K not supported on non-x86 platforms"); + TEST_FAIL("VM_MODE_PXXVYY_4K not supported on non-x86 platforms"); #endif break; case VM_MODE_P47V64_4K: @@ -332,32 +339,157 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->pgtable_levels = 5; break; default: - TEST_FAIL("Unknown guest mode, mode: 0x%x", mode); + TEST_FAIL("Unknown guest mode: 0x%x", vm->mode); } #ifdef __aarch64__ + TEST_ASSERT(!vm->type, "ARM doesn't support test-provided types"); if (vm->pa_bits != 40) vm->type = KVM_VM_TYPE_ARM_IPA_SIZE(vm->pa_bits); #endif - vm_open(vm, perm); + vm_open(vm); /* Limit to VA-bit canonical virtual addresses. */ vm->vpages_valid = sparsebit_alloc(); - sparsebit_set_num(vm->vpages_valid, - 0, (1ULL << (vm->va_bits - 1)) >> vm->page_shift); - sparsebit_set_num(vm->vpages_valid, - (~((1ULL << (vm->va_bits - 1)) - 1)) >> vm->page_shift, - (1ULL << (vm->va_bits - 1)) >> vm->page_shift); + vm_vaddr_populate_bitmap(vm); /* Limit physical addresses to PA-bits. */ vm->max_gfn = vm_compute_max_gfn(vm); /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); - if (phy_pages != 0) - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - 0, 0, phy_pages, 0); + + return vm; +} + +static uint64_t vm_nr_pages_required(enum vm_guest_mode mode, + uint32_t nr_runnable_vcpus, + uint64_t extra_mem_pages) +{ + uint64_t page_size = vm_guest_mode_params[mode].page_size; + uint64_t nr_pages; + + TEST_ASSERT(nr_runnable_vcpus, + "Use vm_create_barebones() for VMs that _never_ have vCPUs"); + + TEST_ASSERT(nr_runnable_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), + "nr_vcpus = %d too large for host, max-vcpus = %d", + nr_runnable_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); + + /* + * Arbitrarily allocate 512 pages (2mb when page size is 4kb) for the + * test code and other per-VM assets that will be loaded into memslot0. + */ + nr_pages = 512; + + /* Account for the per-vCPU stacks on behalf of the test. */ + nr_pages += nr_runnable_vcpus * DEFAULT_STACK_PGS; + + /* + * Account for the number of pages needed for the page tables. The + * maximum page table size for a memory region will be when the + * smallest page size is used. Considering each page contains x page + * table descriptors, the total extra size for page tables (for extra + * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller + * than N/x*2. + */ + nr_pages += (nr_pages + extra_mem_pages) / PTES_PER_MIN_PAGE * 2; + + /* Account for the number of pages needed by ucall. */ + nr_pages += ucall_nr_pages_required(page_size); + + return vm_adjust_num_guest_pages(mode, nr_pages); +} + +void kvm_set_files_rlimit(uint32_t nr_vcpus) +{ + /* + * Each vCPU will open two file descriptors: the vCPU itself and the + * vCPU's binary stats file descriptor. Add an arbitrary amount of + * buffer for all other files a test may open. + */ + int nr_fds_wanted = nr_vcpus * 2 + 100; + struct rlimit rl; + + /* + * Check that we're allowed to open nr_fds_wanted file descriptors and + * try raising the limits if needed. + */ + TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!"); + + if (rl.rlim_cur < nr_fds_wanted) { + rl.rlim_cur = nr_fds_wanted; + if (rl.rlim_max < nr_fds_wanted) { + int old_rlim_max = rl.rlim_max; + + rl.rlim_max = nr_fds_wanted; + __TEST_REQUIRE(setrlimit(RLIMIT_NOFILE, &rl) >= 0, + "RLIMIT_NOFILE hard limit is too low (%d, wanted %d)", + old_rlim_max, nr_fds_wanted); + } else { + TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!"); + } + } + +} + +static bool is_guest_memfd_required(struct vm_shape shape) +{ +#ifdef __x86_64__ + return shape.type == KVM_X86_SNP_VM; +#else + return false; +#endif +} + +struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus, + uint64_t nr_extra_pages) +{ + uint64_t nr_pages = vm_nr_pages_required(shape.mode, nr_runnable_vcpus, + nr_extra_pages); + struct userspace_mem_region *slot0; + struct kvm_vm *vm; + int i, flags; + + kvm_set_files_rlimit(nr_runnable_vcpus); + + pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__, + vm_guest_mode_string(shape.mode), shape.type, nr_pages); + + vm = ____vm_create(shape); + + /* + * Force GUEST_MEMFD for the primary memory region if necessary, e.g. + * for CoCo VMs that require GUEST_MEMFD backed private memory. + */ + flags = 0; + if (is_guest_memfd_required(shape)) + flags |= KVM_MEM_GUEST_MEMFD; + + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, flags); + for (i = 0; i < NR_MEM_REGIONS; i++) + vm->memslots[i] = 0; + + kvm_vm_elf_load(vm, program_invocation_name); + + /* + * TODO: Add proper defines to protect the library's memslots, and then + * carve out memslot1 for the ucall MMIO address. KVM treats writes to + * read-only memslots as MMIO, and creating a read-only memslot for the + * MMIO region would prevent silently clobbering the MMIO region. + */ + slot0 = memslot2region(vm, 0); + ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size); + + if (guest_random_seed != last_guest_seed) { + pr_info("Random seed: 0x%x\n", guest_random_seed); + last_guest_seed = guest_random_seed; + } + guest_rng = new_guest_random_state(guest_random_seed); + sync_global_to_guest(vm, guest_rng); + + kvm_arch_vm_post_create(vm, nr_runnable_vcpus); return vm; } @@ -368,9 +500,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) * Input Args: * mode - VM Mode (e.g. VM_MODE_P52V48_4K) * nr_vcpus - VCPU count - * slot0_mem_pages - Slot0 physical memory size * extra_mem_pages - Non-slot0 physical memory total size - * num_percpu_pages - Per-cpu physical memory pages * guest_code - Guest entry point * vcpuids - VCPU IDs * @@ -379,76 +509,40 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) * Return: * Pointer to opaque structure that describes the created VM. * - * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K), - * with customized slot0 memory size, at least 512 pages currently. + * Creates a VM with the mode specified by mode (e.g. VM_MODE_P52V48_4K). * extra_mem_pages is only used to calculate the maximum page table size, * no real memory allocation for non-slot0 memory in this function. */ -struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus, - uint64_t slot0_mem_pages, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]) +struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus, + uint64_t extra_mem_pages, + void *guest_code, struct kvm_vcpu *vcpus[]) { - uint64_t vcpu_pages, extra_pg_pages, pages; struct kvm_vm *vm; int i; -#ifdef __x86_64__ - /* - * Permission needs to be requested before KVM_SET_CPUID2. - */ - vm_xsave_req_perm(); -#endif + TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array"); - /* Force slot0 memory size not small than DEFAULT_GUEST_PHY_PAGES */ - if (slot0_mem_pages < DEFAULT_GUEST_PHY_PAGES) - slot0_mem_pages = DEFAULT_GUEST_PHY_PAGES; + vm = __vm_create(shape, nr_vcpus, extra_mem_pages); - /* The maximum page table size for a memory region will be when the - * smallest pages are used. Considering each page contains x page - * table descriptors, the total extra size for page tables (for extra - * N pages) will be: N/x+N/x^2+N/x^3+... which is definitely smaller - * than N/x*2. - */ - vcpu_pages = (DEFAULT_STACK_PGS + num_percpu_pages) * nr_vcpus; - extra_pg_pages = (slot0_mem_pages + extra_mem_pages + vcpu_pages) / PTES_PER_MIN_PAGE * 2; - pages = slot0_mem_pages + vcpu_pages + extra_pg_pages; - - TEST_ASSERT(nr_vcpus <= kvm_check_cap(KVM_CAP_MAX_VCPUS), - "nr_vcpus = %d too large for host, max-vcpus = %d", - nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS)); - - pages = vm_adjust_num_guest_pages(mode, pages); - vm = vm_create(mode, pages, O_RDWR); - - kvm_vm_elf_load(vm, program_invocation_name); - -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - - for (i = 0; i < nr_vcpus; ++i) { - uint32_t vcpuid = vcpuids ? vcpuids[i] : i; - - vm_vcpu_add_default(vm, vcpuid, guest_code); - } + for (i = 0; i < nr_vcpus; ++i) + vcpus[i] = vm_vcpu_add(vm, i, guest_code); + kvm_arch_vm_finalize_vcpus(vm); return vm; } -struct kvm_vm *vm_create_default_with_vcpus(uint32_t nr_vcpus, uint64_t extra_mem_pages, - uint32_t num_percpu_pages, void *guest_code, - uint32_t vcpuids[]) +struct kvm_vm *__vm_create_shape_with_one_vcpu(struct vm_shape shape, + struct kvm_vcpu **vcpu, + uint64_t extra_mem_pages, + void *guest_code) { - return vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, DEFAULT_GUEST_PHY_PAGES, - extra_mem_pages, num_percpu_pages, guest_code, vcpuids); -} + struct kvm_vcpu *vcpus[1]; + struct kvm_vm *vm; -struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, - void *guest_code) -{ - return vm_create_default_with_vcpus(1, extra_mem_pages, 0, guest_code, - (uint32_t []){ vcpuid }); + vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus); + + *vcpu = vcpus[0]; + return vm; } /* @@ -456,7 +550,6 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, * * Input Args: * vm - VM that has been released before - * perm - permission * * Output Args: None * @@ -464,18 +557,19 @@ struct kvm_vm *vm_create_default(uint32_t vcpuid, uint64_t extra_mem_pages, * global state, such as the irqchip and the memory regions that are mapped * into the guest. */ -void kvm_vm_restart(struct kvm_vm *vmp, int perm) +void kvm_vm_restart(struct kvm_vm *vmp) { int ctr; struct userspace_mem_region *region; - vm_open(vmp, perm); + vm_open(vmp); if (vmp->has_irqchip) vm_create_irqchip(vmp); hash_for_each(vmp->regions.slot_hash, ctr, region, slot_node) { - int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" " guest_phys_addr: 0x%llx size: 0x%llx", @@ -486,34 +580,86 @@ void kvm_vm_restart(struct kvm_vm *vmp, int perm) } } -void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log) +__weak struct kvm_vcpu *vm_arch_vcpu_recreate(struct kvm_vm *vm, + uint32_t vcpu_id) { - struct kvm_dirty_log args = { .dirty_bitmap = log, .slot = slot }; - int ret; + return __vm_vcpu_add(vm, vcpu_id); +} + +struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm) +{ + kvm_vm_restart(vm); - ret = ioctl(vm->fd, KVM_GET_DIRTY_LOG, &args); - TEST_ASSERT(ret == 0, "%s: KVM_GET_DIRTY_LOG failed: %s", - __func__, strerror(-ret)); + return vm_vcpu_recreate(vm, 0); } -void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log, - uint64_t first_page, uint32_t num_pages) +int __pin_task_to_cpu(pthread_t task, int cpu) { - struct kvm_clear_dirty_log args = { - .dirty_bitmap = log, .slot = slot, - .first_page = first_page, - .num_pages = num_pages - }; - int ret; + cpu_set_t cpuset; + + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + + return pthread_setaffinity_np(task, sizeof(cpuset), &cpuset); +} + +static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask) +{ + uint32_t pcpu = atoi_non_negative("CPU number", cpu_str); + + TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask), + "Not allowed to run on pCPU '%d', check cgroups?", pcpu); + return pcpu; +} - ret = ioctl(vm->fd, KVM_CLEAR_DIRTY_LOG, &args); - TEST_ASSERT(ret == 0, "%s: KVM_CLEAR_DIRTY_LOG failed: %s", - __func__, strerror(-ret)); +void kvm_print_vcpu_pinning_help(void) +{ + const char *name = program_invocation_name; + + printf(" -c: Pin tasks to physical CPUs. Takes a list of comma separated\n" + " values (target pCPU), one for each vCPU, plus an optional\n" + " entry for the main application task (specified via entry\n" + " <nr_vcpus + 1>). If used, entries must be provided for all\n" + " vCPUs, i.e. pinning vCPUs is all or nothing.\n\n" + " E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n" + " vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n" + " %s -v 3 -c 22,23,24,50\n\n" + " To leave the application task unpinned, drop the final entry:\n\n" + " %s -v 3 -c 22,23,24\n\n" + " (default: no pinning)\n", name, name); } -uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm) +void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[], + int nr_vcpus) { - return ioctl(vm->fd, KVM_RESET_DIRTY_RINGS); + cpu_set_t allowed_mask; + char *cpu, *cpu_list; + char delim[2] = ","; + int i, r; + + cpu_list = strdup(pcpus_string); + TEST_ASSERT(cpu_list, "strdup() allocation failed."); + + r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask); + TEST_ASSERT(!r, "sched_getaffinity() failed"); + + cpu = strtok(cpu_list, delim); + + /* 1. Get all pcpus for vcpus. */ + for (i = 0; i < nr_vcpus; i++) { + TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'", i); + vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask); + cpu = strtok(NULL, delim); + } + + /* 2. Check if the main worker needs to be pinned. */ + if (cpu) { + pin_self_to_cpu(parse_pcpu(cpu, &allowed_mask)); + cpu = strtok(NULL, delim); + } + + TEST_ASSERT(!cpu, "pCPU list contains trailing garbage characters '%s'", cpu); + free(cpu_list); } /* @@ -558,61 +704,23 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end) return NULL; } -/* - * KVM Userspace Memory Region Find - * - * Input Args: - * vm - Virtual Machine - * start - Starting VM physical address - * end - Ending VM physical address, inclusive. - * - * Output Args: None - * - * Return: - * Pointer to overlapping region, NULL if no such region. - * - * Public interface to userspace_mem_region_find. Allows tests to look up - * the memslot datastructure for a given range of guest physical memory. - */ -struct kvm_userspace_memory_region * -kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start, - uint64_t end) +static void kvm_stats_release(struct kvm_binary_stats *stats) { - struct userspace_mem_region *region; + if (stats->fd < 0) + return; - region = userspace_mem_region_find(vm, start, end); - if (!region) - return NULL; + if (stats->desc) { + free(stats->desc); + stats->desc = NULL; + } - return ®ion->region; + kvm_close(stats->fd); + stats->fd = -1; } -/* - * VCPU Find - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: - * Pointer to VCPU structure - * - * Locates a vcpu structure that describes the VCPU specified by vcpuid and - * returns a pointer to it. Returns NULL if the VM doesn't contain a VCPU - * for the specified vcpuid. - */ -struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) +__weak void vcpu_arch_free(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu; - - list_for_each_entry(vcpu, &vm->vcpus, list) { - if (vcpu->id == vcpuid) - return vcpu; - } - return NULL; } /* @@ -627,65 +735,57 @@ struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid) * * Removes a vCPU from a VM and frees its resources. */ -static void vm_vcpu_rm(struct kvm_vm *vm, struct vcpu *vcpu) +static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { - int ret; - if (vcpu->dirty_gfns) { - ret = munmap(vcpu->dirty_gfns, vm->dirty_ring_size); - TEST_ASSERT(ret == 0, "munmap of VCPU dirty ring failed, " - "rc: %i errno: %i", ret, errno); + kvm_munmap(vcpu->dirty_gfns, vm->dirty_ring_size); vcpu->dirty_gfns = NULL; } - ret = munmap(vcpu->state, vcpu_mmap_sz()); - TEST_ASSERT(ret == 0, "munmap of VCPU fd failed, rc: %i " - "errno: %i", ret, errno); - ret = close(vcpu->fd); - TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i " - "errno: %i", ret, errno); + kvm_munmap(vcpu->run, vcpu_mmap_sz()); + + kvm_close(vcpu->fd); + kvm_stats_release(&vcpu->stats); list_del(&vcpu->list); + + vcpu_arch_free(vcpu); free(vcpu); } void kvm_vm_release(struct kvm_vm *vmp) { - struct vcpu *vcpu, *tmp; - int ret; + struct kvm_vcpu *vcpu, *tmp; list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list) vm_vcpu_rm(vmp, vcpu); - ret = close(vmp->fd); - TEST_ASSERT(ret == 0, "Close of vm fd failed,\n" - " vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno); + kvm_close(vmp->fd); + kvm_close(vmp->kvm_fd); + + /* Free cached stats metadata and close FD */ + kvm_stats_release(&vmp->stats); - ret = close(vmp->kvm_fd); - TEST_ASSERT(ret == 0, "Close of /dev/kvm fd failed,\n" - " vmp->kvm_fd: %i rc: %i errno: %i", vmp->kvm_fd, ret, errno); + kvm_arch_vm_release(vmp); } static void __vm_mem_region_delete(struct kvm_vm *vm, - struct userspace_mem_region *region, - bool unlink) + struct userspace_mem_region *region) { - int ret; - - if (unlink) { - rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); - rb_erase(®ion->hva_node, &vm->regions.hva_tree); - hash_del(®ion->slot_node); - } - - region->region.memory_size = 0; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, " - "rc: %i errno: %i", ret, errno); + rb_erase(®ion->gpa_node, &vm->regions.gpa_tree); + rb_erase(®ion->hva_node, &vm->regions.hva_tree); + hash_del(®ion->slot_node); sparsebit_free(®ion->unused_phy_pages); - ret = munmap(region->mmap_start, region->mmap_size); - TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i", ret, errno); + sparsebit_free(®ion->protected_phy_pages); + kvm_munmap(region->mmap_start, region->mmap_size); + if (region->fd >= 0) { + /* There's an extra map when using shared memory. */ + kvm_munmap(region->mmap_alias, region->mmap_size); + close(region->fd); + } + if (region->region.guest_memfd >= 0) + close(region->region.guest_memfd); free(region); } @@ -704,7 +804,7 @@ void kvm_vm_free(struct kvm_vm *vmp) /* Free userspace_mem_regions. */ hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node) - __vm_mem_region_delete(vmp, region, false); + __vm_mem_region_delete(vmp, region); /* Free sparsebit arrays. */ sparsebit_free(&vmp->vpages_valid); @@ -716,74 +816,21 @@ void kvm_vm_free(struct kvm_vm *vmp) free(vmp); } -/* - * Memory Compare, host virtual to guest virtual - * - * Input Args: - * hva - Starting host virtual address - * vm - Virtual Machine - * gva - Starting guest virtual address - * len - number of bytes to compare - * - * Output Args: None - * - * Input/Output Args: None - * - * Return: - * Returns 0 if the bytes starting at hva for a length of len - * are equal the guest virtual bytes starting at gva. Returns - * a value < 0, if bytes at hva are less than those at gva. - * Otherwise a value > 0 is returned. - * - * Compares the bytes starting at the host virtual address hva, for - * a length of len, to the guest bytes starting at the guest virtual - * address given by gva. - */ -int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, vm_vaddr_t gva, size_t len) +int kvm_memfd_alloc(size_t size, bool hugepages) { - size_t amt; + int memfd_flags = MFD_CLOEXEC; + int fd; - /* - * Compare a batch of bytes until either a match is found - * or all the bytes have been compared. - */ - for (uintptr_t offset = 0; offset < len; offset += amt) { - uintptr_t ptr1 = (uintptr_t)hva + offset; + if (hugepages) + memfd_flags |= MFD_HUGETLB; - /* - * Determine host address for guest virtual address - * at offset. - */ - uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset); + fd = memfd_create("kvm_selftest", memfd_flags); + TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd)); - /* - * Determine amount to compare on this pass. - * Don't allow the comparsion to cross a page boundary. - */ - amt = len - offset; - if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr1 % vm->page_size); - if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift)) - amt = vm->page_size - (ptr2 % vm->page_size); + kvm_ftruncate(fd, size); + kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size); - assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift)); - assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift)); - - /* - * Perform the comparison. If there is a difference - * return that result to the caller, otherwise need - * to continue on looking for a mismatch. - */ - int ret = memcmp((void *)ptr1, (void *)ptr2, amt); - if (ret != 0) - return ret; - } - - /* - * No mismatch found. Let the caller know the two memory - * areas are equal. - */ - return 0; + return fd; } static void vm_userspace_mem_region_gpa_insert(struct rb_root *gpa_tree, @@ -837,66 +884,105 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree, rb_insert_color(®ion->hva_node, hva_tree); } -/* - * VM Userspace Memory Region Add - * - * Input Args: - * vm - Virtual Machine - * src_type - Storage source for this region. - * NULL to use anonymous memory. - * guest_paddr - Starting guest physical address - * slot - KVM region slot - * npages - Number of physical pages - * flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES) - * - * Output Args: None - * - * Return: None - * - * Allocates a memory area of the number of pages specified by npages - * and maps it to the VM specified by vm, at a starting physical address - * given by guest_paddr. The region is created with a KVM region slot - * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM. The - * region is created with the flags given by flags. - */ -void vm_userspace_mem_region_add(struct kvm_vm *vm, - enum vm_mem_backing_src_type src_type, - uint64_t guest_paddr, uint32_t slot, uint64_t npages, - uint32_t flags) + +int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + struct kvm_userspace_memory_region region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + }; + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion); +} + +void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva) +{ + int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)", + errno, strerror(errno)); +} + +#define TEST_REQUIRE_SET_USER_MEMORY_REGION2() \ + __TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2), \ + "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)") + +int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + struct kvm_userspace_memory_region2 region = { + .slot = slot, + .flags = flags, + .guest_phys_addr = gpa, + .memory_size = size, + .userspace_addr = (uintptr_t)hva, + .guest_memfd = guest_memfd, + .guest_memfd_offset = guest_memfd_offset, + }; + + TEST_REQUIRE_SET_USER_MEMORY_REGION2(); + + return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, ®ion); +} + +void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags, + uint64_t gpa, uint64_t size, void *hva, + uint32_t guest_memfd, uint64_t guest_memfd_offset) +{ + int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva, + guest_memfd, guest_memfd_offset); + + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)", + errno, strerror(errno)); +} + + +/* FIXME: This thing needs to be ripped apart and rewritten. */ +void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, + uint64_t gpa, uint32_t slot, uint64_t npages, uint32_t flags, + int guest_memfd, uint64_t guest_memfd_offset) { int ret; struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); + size_t mem_size = npages * vm->page_size; size_t alignment; + TEST_REQUIRE_SET_USER_MEMORY_REGION2(); + TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages, "Number of guest pages is not compatible with the host. " "Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages)); - TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical " + TEST_ASSERT((gpa % vm->page_size) == 0, "Guest physical " "address not on a page boundary.\n" - " guest_paddr: 0x%lx vm->page_size: 0x%x", - guest_paddr, vm->page_size); - TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1) + " gpa: 0x%lx vm->page_size: 0x%x", + gpa, vm->page_size); + TEST_ASSERT((((gpa >> vm->page_shift) + npages) - 1) <= vm->max_gfn, "Physical range beyond maximum " "supported physical address,\n" - " guest_paddr: 0x%lx npages: 0x%lx\n" + " gpa: 0x%lx npages: 0x%lx\n" " vm->max_gfn: 0x%lx vm->page_size: 0x%x", - guest_paddr, npages, vm->max_gfn, vm->page_size); + gpa, npages, vm->max_gfn, vm->page_size); /* * Confirm a mem region with an overlapping address doesn't * already exist. */ region = (struct userspace_mem_region *) userspace_mem_region_find( - vm, guest_paddr, (guest_paddr + npages * vm->page_size) - 1); + vm, gpa, (gpa + npages * vm->page_size) - 1); if (region != NULL) TEST_FAIL("overlapping userspace_mem_region already " "exists\n" - " requested guest_paddr: 0x%lx npages: 0x%lx " - "page_size: 0x%x\n" - " existing guest_paddr: 0x%lx size: 0x%lx", - guest_paddr, npages, vm->page_size, + " requested gpa: 0x%lx npages: 0x%lx page_size: 0x%x\n" + " existing gpa: 0x%lx size: 0x%lx", + gpa, npages, vm->page_size, (uint64_t) region->region.guest_phys_addr, (uint64_t) region->region.memory_size); @@ -910,8 +996,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "already exists.\n" " requested slot: %u paddr: 0x%lx npages: 0x%lx\n" " existing slot: %u paddr: 0x%lx size: 0x%lx", - slot, guest_paddr, npages, - region->region.slot, + slot, gpa, npages, region->region.slot, (uint64_t) region->region.guest_phys_addr, (uint64_t) region->region.memory_size); } @@ -919,7 +1004,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* Allocate and initialize new mem region structure. */ region = calloc(1, sizeof(*region)); TEST_ASSERT(region != NULL, "Insufficient Memory"); - region->mmap_size = npages * vm->page_size; + region->mmap_size = mem_size; #ifdef __s390x__ /* On s390x, the host address must be aligned to 1M (due to PGSTEs) */ @@ -937,39 +1022,20 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, if (src_type == VM_MEM_SRC_ANONYMOUS_THP) alignment = max(backing_src_pagesz, alignment); - ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + TEST_ASSERT_EQ(gpa, align_up(gpa, backing_src_pagesz)); /* Add enough memory to align up if necessary */ if (alignment > 1) region->mmap_size += alignment; region->fd = -1; - if (backing_src_is_shared(src_type)) { - int memfd_flags = MFD_CLOEXEC; - - if (src_type == VM_MEM_SRC_SHARED_HUGETLB) - memfd_flags |= MFD_HUGETLB; - - region->fd = memfd_create("kvm_selftest", memfd_flags); - TEST_ASSERT(region->fd != -1, - "memfd_create failed, errno: %i", errno); + if (backing_src_is_shared(src_type)) + region->fd = kvm_memfd_alloc(region->mmap_size, + src_type == VM_MEM_SRC_SHARED_HUGETLB); - ret = ftruncate(region->fd, region->mmap_size); - TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno); - - ret = fallocate(region->fd, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - region->mmap_size); - TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno); - } - - region->mmap_start = mmap(NULL, region->mmap_size, - PROT_READ | PROT_WRITE, - vm_mem_backing_src_alias(src_type)->flag, - region->fd, 0); - TEST_ASSERT(region->mmap_start != MAP_FAILED, - "test_malloc failed, mmap_start: %p errno: %i", - region->mmap_start, errno); + region->mmap_start = kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd); TEST_ASSERT(!is_backing_src_hugetlb(src_type) || region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), @@ -982,28 +1048,53 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) && thp_configured()) { - ret = madvise(region->host_mem, npages * vm->page_size, + ret = madvise(region->host_mem, mem_size, src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE); TEST_ASSERT(ret == 0, "madvise failed, addr: %p length: 0x%lx src_type: %s", - region->host_mem, npages * vm->page_size, + region->host_mem, mem_size, vm_mem_backing_src_alias(src_type)->name); } + region->backing_src_type = src_type; + + if (flags & KVM_MEM_GUEST_MEMFD) { + if (guest_memfd < 0) { + uint32_t guest_memfd_flags = 0; + TEST_ASSERT(!guest_memfd_offset, + "Offset must be zero when creating new guest_memfd"); + guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); + } else { + /* + * Install a unique fd for each memslot so that the fd + * can be closed when the region is deleted without + * needing to track if the fd is owned by the framework + * or by the caller. + */ + guest_memfd = kvm_dup(guest_memfd); + } + + region->region.guest_memfd = guest_memfd; + region->region.guest_memfd_offset = guest_memfd_offset; + } else { + region->region.guest_memfd = -1; + } + region->unused_phy_pages = sparsebit_alloc(); - sparsebit_set_num(region->unused_phy_pages, - guest_paddr >> vm->page_shift, npages); + if (vm_arch_has_protected_memory(vm)) + region->protected_phy_pages = sparsebit_alloc(); + sparsebit_set_num(region->unused_phy_pages, gpa >> vm->page_shift, npages); region->region.slot = slot; region->region.flags = flags; - region->region.guest_phys_addr = guest_paddr; + region->region.guest_phys_addr = gpa; region->region.memory_size = npages * vm->page_size; region->region.userspace_addr = (uintptr_t) region->host_mem; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i\n" " slot: %u flags: 0x%x\n" - " guest_phys_addr: 0x%lx size: 0x%lx", - ret, errno, slot, flags, - guest_paddr, (uint64_t) region->region.memory_size); + " guest_phys_addr: 0x%lx size: 0x%llx guest_memfd: %d", + ret, errno, slot, flags, gpa, region->region.memory_size, + region->region.guest_memfd); /* Add to quick lookup data structures */ vm_userspace_mem_region_gpa_insert(&vm->regions.gpa_tree, region); @@ -1012,18 +1103,24 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, /* If shared memory, create an alias. */ if (region->fd >= 0) { - region->mmap_alias = mmap(NULL, region->mmap_size, - PROT_READ | PROT_WRITE, - vm_mem_backing_src_alias(src_type)->flag, - region->fd, 0); - TEST_ASSERT(region->mmap_alias != MAP_FAILED, - "mmap of alias failed, errno: %i", errno); + region->mmap_alias = kvm_mmap(region->mmap_size, + PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd); /* Align host alias address */ region->host_alias = align_ptr_up(region->mmap_alias, alignment); } } +void vm_userspace_mem_region_add(struct kvm_vm *vm, + enum vm_mem_backing_src_type src_type, + uint64_t gpa, uint32_t slot, uint64_t npages, + uint32_t flags) +{ + vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0); +} + /* * Memslot to region * @@ -1080,13 +1177,23 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags) region->region.flags = flags; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n" + TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION2 IOCTL failed,\n" " rc: %i errno: %i slot: %u flags: 0x%x", ret, errno, slot, flags); } +void vm_mem_region_reload(struct kvm_vm *vm, uint32_t slot) +{ + struct userspace_mem_region *region = memslot2region(vm, slot); + struct kvm_userspace_memory_region2 tmp = region->region; + + tmp.memory_size = 0; + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &tmp); + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); +} + /* * VM Memory Region Move * @@ -1110,9 +1217,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) region->region.guest_phys_addr = new_gpa; - ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, ®ion->region); + ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); - TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed\n" + TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed\n" "ret: %i errno: %i slot: %u new_gpa: 0x%lx", ret, errno, slot, new_gpa); } @@ -1132,83 +1239,105 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa) */ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot) { - __vm_mem_region_delete(vm, memslot2region(vm, slot), true); + struct userspace_mem_region *region = memslot2region(vm, slot); + + region->region.memory_size = 0; + vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, ®ion->region); + + __vm_mem_region_delete(vm, region); } -/* - * VCPU mmap Size - * - * Input Args: None - * - * Output Args: None - * - * Return: - * Size of VCPU state - * - * Returns the size of the structure pointed to by the return value - * of vcpu_state(). - */ -static int vcpu_mmap_sz(void) +void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size, + bool punch_hole) +{ + const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0); + struct userspace_mem_region *region; + uint64_t end = base + size; + uint64_t gpa, len; + off_t fd_offset; + int ret; + + for (gpa = base; gpa < end; gpa += len) { + uint64_t offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, + "Private memory region not found for GPA 0x%lx", gpa); + + offset = gpa - region->region.guest_phys_addr; + fd_offset = region->region.guest_memfd_offset + offset; + len = min_t(uint64_t, end - gpa, region->region.memory_size - offset); + + ret = fallocate(region->region.guest_memfd, mode, fd_offset, len); + TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx", + punch_hole ? "punch hole" : "allocate", gpa, len, + region->region.guest_memfd, mode, fd_offset); + } +} + +/* Returns the size of a vCPU's kvm_run structure. */ +static size_t vcpu_mmap_sz(void) { int dev_fd, ret; dev_fd = open_kvm_dev_path_or_exit(); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); - TEST_ASSERT(ret >= sizeof(struct kvm_run), - "%s KVM_GET_VCPU_MMAP_SIZE ioctl failed, rc: %i errno: %i", - __func__, ret, errno); + TEST_ASSERT(ret >= 0 && ret >= sizeof(struct kvm_run), + KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret)); close(dev_fd); return ret; } +static bool vcpu_exists(struct kvm_vm *vm, uint32_t vcpu_id) +{ + struct kvm_vcpu *vcpu; + + list_for_each_entry(vcpu, &vm->vcpus, list) { + if (vcpu->id == vcpu_id) + return true; + } + + return false; +} + /* - * VM VCPU Add - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: None - * - * Adds a virtual CPU to the VM specified by vm with the ID given by vcpuid. - * No additional VCPU setup is done. + * Adds a virtual CPU to the VM specified by vm with the ID given by vcpu_id. + * No additional vCPU setup is done. Returns the vCPU. */ -void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) +struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id) { - struct vcpu *vcpu; + struct kvm_vcpu *vcpu; /* Confirm a vcpu with the specified id doesn't already exist. */ - vcpu = vcpu_find(vm, vcpuid); - if (vcpu != NULL) - TEST_FAIL("vcpu with the specified id " - "already exists,\n" - " requested vcpuid: %u\n" - " existing vcpuid: %u state: %p", - vcpuid, vcpu->id, vcpu->state); + TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists", vcpu_id); /* Allocate and initialize new vcpu structure. */ vcpu = calloc(1, sizeof(*vcpu)); TEST_ASSERT(vcpu != NULL, "Insufficient Memory"); - vcpu->id = vcpuid; - vcpu->fd = ioctl(vm->fd, KVM_CREATE_VCPU, vcpuid); - TEST_ASSERT(vcpu->fd >= 0, "KVM_CREATE_VCPU failed, rc: %i errno: %i", - vcpu->fd, errno); - - TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->state), "vcpu mmap size " - "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi", - vcpu_mmap_sz(), sizeof(*vcpu->state)); - vcpu->state = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(), - PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0); - TEST_ASSERT(vcpu->state != MAP_FAILED, "mmap vcpu_state failed, " - "vcpu id: %u errno: %i", vcpuid, errno); + + vcpu->vm = vm; + vcpu->id = vcpu_id; + vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id); + TEST_ASSERT_VM_VCPU_IOCTL(vcpu->fd >= 0, KVM_CREATE_VCPU, vcpu->fd, vm); + + TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->run), "vcpu mmap size " + "smaller than expected, vcpu_mmap_sz: %zi expected_min: %zi", + vcpu_mmap_sz(), sizeof(*vcpu->run)); + vcpu->run = kvm_mmap(vcpu_mmap_sz(), PROT_READ | PROT_WRITE, + MAP_SHARED, vcpu->fd); + + if (kvm_has_cap(KVM_CAP_BINARY_STATS_FD)) + vcpu->stats.fd = vcpu_get_stats_fd(vcpu); + else + vcpu->stats.fd = -1; /* Add to linked-list of VCPUs. */ list_add(&vcpu->list, &vm->vcpus); + + return vcpu; } /* @@ -1231,8 +1360,8 @@ void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid) * TEST_ASSERT failure occurs for invalid input or no area of at least * sz unallocated bytes >= vaddr_min is available. */ -static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, - vm_vaddr_t vaddr_min) +vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min) { uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift; @@ -1297,6 +1426,48 @@ va_found: return pgidx_start * vm->page_size; } +static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type, + bool protected) +{ + uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); + + virt_pgd_alloc(vm); + vm_paddr_t paddr = __vm_phy_pages_alloc(vm, pages, + KVM_UTIL_MIN_PFN * vm->page_size, + vm->memslots[type], protected); + + /* + * Find an unused range of virtual page addresses of at least + * pages in length. + */ + vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min); + + /* Map the virtual pages. */ + for (vm_vaddr_t vaddr = vaddr_start; pages > 0; + pages--, vaddr += vm->page_size, paddr += vm->page_size) { + + virt_pg_map(vm, vaddr, paddr); + } + + return vaddr_start; +} + +vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, + vm_arch_has_protected_memory(vm)); +} + +vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz, + vm_vaddr_t vaddr_min, + enum kvm_mem_region_type type) +{ + return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, false); +} + /* * VM Virtual Address Allocate * @@ -1304,8 +1475,6 @@ va_found: * vm - Virtual Machine * sz - Size in bytes * vaddr_min - Minimum starting virtual address - * data_memslot - Memory region slot for data pages - * pgd_memslot - Memory region slot for new virtual translation tables * * Output Args: None * @@ -1316,33 +1485,11 @@ va_found: * given by vm. The allocated bytes are mapped to a virtual address >= * the address given by vaddr_min. Note that each allocation uses a * a unique set of pages, with the minimum real allocation being at least - * a page. + * a page. The allocated physical space comes from the TEST_DATA memory region. */ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min) { - uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0); - - virt_pgd_alloc(vm); - vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages, - KVM_UTIL_MIN_PFN * vm->page_size, 0); - - /* - * Find an unused range of virtual page addresses of at least - * pages in length. - */ - vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min); - - /* Map the virtual pages. */ - for (vm_vaddr_t vaddr = vaddr_start; pages > 0; - pages--, vaddr += vm->page_size, paddr += vm->page_size) { - - virt_pg_map(vm, vaddr, paddr); - - sparsebit_set(vm->vpages_mapped, - vaddr >> vm->page_shift); - } - - return vaddr_start; + return __vm_vaddr_alloc(vm, sz, vaddr_min, MEM_REGION_TEST_DATA); } /* @@ -1364,6 +1511,11 @@ vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages) return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR); } +vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type) +{ + return __vm_vaddr_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type); +} + /* * VM Virtual Address Allocate Page * @@ -1391,7 +1543,6 @@ vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm) * vaddr - Virtuall address to map * paddr - VM Physical Address * npages - The number of pages to map - * pgd_memslot - Memory region slot for new virtual translation tables * * Output Args: None * @@ -1411,6 +1562,7 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, while (npages--) { virt_pg_map(vm, vaddr, paddr); + vaddr += page_size; paddr += page_size; } @@ -1437,6 +1589,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa) { struct userspace_mem_region *region; + gpa = vm_untag_gpa(vm, gpa); + region = userspace_mem_region_find(vm, gpa, gpa); if (!region) { TEST_FAIL("No vm physical memory at 0x%lx", gpa); @@ -1502,11 +1656,10 @@ vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva) * (without failing the test) if the guest memory is not shared (so * no alias exists). * - * When vm_create() and related functions are called with a shared memory - * src_type, we also create a writable, shared alias mapping of the - * underlying guest memory. This allows the host to manipulate guest memory - * without mapping that memory in the guest's address space. And, for - * userfaultfd-based demand paging, we can do so without triggering userfaults. + * Create a writable, shared virtual=>physical alias for the specific GPA. + * The primary use case is to allow the host selftest to manipulate guest + * memory without mapping said memory in the guest's address space. And, for + * userfaultfd-based demand paging, to do so without triggering userfaults. */ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) { @@ -1524,453 +1677,102 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa) return (void *) ((uintptr_t) region->host_alias + offset); } -/* - * VM Create IRQ Chip - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: None - * - * Creates an interrupt controller chip for the VM specified by vm. - */ +/* Create an interrupt controller chip for the specified VM. */ void vm_create_irqchip(struct kvm_vm *vm) { - int ret; + int r; - ret = ioctl(vm->fd, KVM_CREATE_IRQCHIP, 0); - TEST_ASSERT(ret == 0, "KVM_CREATE_IRQCHIP IOCTL failed, " - "rc: %i errno: %i", ret, errno); + /* + * Allocate a fully in-kernel IRQ chip by default, but fall back to a + * split model (x86 only) if that fails (KVM x86 allows compiling out + * support for KVM_CREATE_IRQCHIP). + */ + r = __vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL); + if (r && errno == ENOTTY && kvm_has_cap(KVM_CAP_SPLIT_IRQCHIP)) + vm_enable_cap(vm, KVM_CAP_SPLIT_IRQCHIP, 24); + else + TEST_ASSERT_VM_VCPU_IOCTL(!r, KVM_CREATE_IRQCHIP, r, vm); vm->has_irqchip = true; } -/* - * VM VCPU State - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: - * Pointer to structure that describes the state of the VCPU. - * - * Locates and returns a pointer to a structure that describes the - * state of the VCPU with the given vcpuid. - */ -struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid) +int _vcpu_run(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return vcpu->state; -} - -/* - * VM VCPU Run - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: None - * - * Return: None - * - * Switch to executing the code for the VCPU given by vcpuid, within the VM - * given by vm. - */ -void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) -{ - int ret = _vcpu_run(vm, vcpuid); - TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - -int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); int rc; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); do { - rc = ioctl(vcpu->fd, KVM_RUN, NULL); + rc = __vcpu_run(vcpu); } while (rc == -1 && errno == EINTR); - assert_on_unhandled_exception(vm, vcpuid); + if (!rc) + assert_on_unhandled_exception(vcpu); return rc; } -int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid) +/* + * Invoke KVM_RUN on a vCPU until KVM returns something other than -EINTR. + * Assert if the KVM returns an error (other than -EINTR). + */ +void vcpu_run(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret = _vcpu_run(vcpu); - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return vcpu->fd; + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_RUN, ret)); } -void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) +void vcpu_run_complete_io(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); int ret; - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - vcpu->state->immediate_exit = 1; - ret = ioctl(vcpu->fd, KVM_RUN, NULL); - vcpu->state->immediate_exit = 0; + vcpu->run->immediate_exit = 1; + ret = __vcpu_run(vcpu); + vcpu->run->immediate_exit = 0; TEST_ASSERT(ret == -1 && errno == EINTR, "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i", ret, errno); } -void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_guest_debug *debug) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret = ioctl(vcpu->fd, KVM_SET_GUEST_DEBUG, debug); - - TEST_ASSERT(ret == 0, "KVM_SET_GUEST_DEBUG failed: %d", ret); -} - /* - * VM VCPU Set MP State - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * mp_state - mp_state to be set - * - * Output Args: None - * - * Return: None - * - * Sets the MP state of the VCPU given by vcpuid, to the state given - * by mp_state. - */ -void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_mp_state *mp_state) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_MP_STATE, mp_state); - TEST_ASSERT(ret == 0, "KVM_SET_MP_STATE IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - -/* - * VM VCPU Get Reg List - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: - * None - * - * Return: - * A pointer to an allocated struct kvm_reg_list - * * Get the list of guest registers which are supported for - * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + * KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls. Returns a kvm_reg_list pointer, + * it is the caller's responsibility to free the list. */ -struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu) { struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; int ret; - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + ret = __vcpu_ioctl(vcpu, KVM_GET_REG_LIST, ®_list_n); TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); reg_list->n = reg_list_n.n; - vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + vcpu_ioctl(vcpu, KVM_GET_REG_LIST, reg_list); return reg_list; } -/* - * VM VCPU Regs Get - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: - * regs - current state of VCPU regs - * - * Return: None - * - * Obtains the current register state for the VCPU specified by vcpuid - * and stores it at the location given by regs. - */ -void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_REGS, regs); - TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i", - ret, errno); -} - -/* - * VM VCPU Regs Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * regs - Values to set VCPU regs to - * - * Output Args: None - * - * Return: None - * - * Sets the regs of the VCPU specified by vcpuid to the values - * given by regs. - */ -void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_REGS, regs); - TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i", - ret, errno); -} - -#ifdef __KVM_HAVE_VCPU_EVENTS -void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events); - TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i", - ret, errno); -} - -void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_vcpu_events *events) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events); - TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i", - ret, errno); -} -#endif - -#ifdef __x86_64__ -void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_NESTED_STATE, state); - TEST_ASSERT(ret == 0, - "KVM_SET_NESTED_STATE failed, ret: %i errno: %i", - ret, errno); -} - -int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid, - struct kvm_nested_state *state, bool ignore_error) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, state); - if (!ignore_error) { - TEST_ASSERT(ret == 0, - "KVM_SET_NESTED_STATE failed, ret: %i errno: %i", - ret, errno); - } - - return ret; -} -#endif - -/* - * VM VCPU System Regs Get - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * - * Output Args: - * sregs - current state of VCPU system regs - * - * Return: None - * - * Obtains the current system register state for the VCPU specified by - * vcpuid and stores it at the location given by sregs. - */ -void vcpu_sregs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs); - TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i", - ret, errno); -} - -/* - * VM VCPU System Regs Set - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * sregs - Values to set VCPU system regs to - * - * Output Args: None - * - * Return: None - * - * Sets the system regs of the VCPU specified by vcpuid to the values - * given by sregs. - */ -void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - int ret = _vcpu_sregs_set(vm, vcpuid, sregs); - TEST_ASSERT(ret == 0, "KVM_SET_SREGS IOCTL failed, " - "rc: %i errno: %i", ret, errno); -} - -int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - return ioctl(vcpu->fd, KVM_SET_SREGS, sregs); -} - -void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_FPU, fpu); - TEST_ASSERT(ret == 0, "KVM_GET_FPU failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_FPU, fpu); - TEST_ASSERT(ret == 0, "KVM_SET_FPU failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, reg); - TEST_ASSERT(ret == 0, "KVM_GET_ONE_REG failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, reg); - TEST_ASSERT(ret == 0, "KVM_SET_ONE_REG failed, rc: %i errno: %i (%s)", - ret, errno, strerror(errno)); -} - -/* - * VCPU Ioctl - * - * Input Args: - * vm - Virtual Machine - * vcpuid - VCPU ID - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a VCPU fd. - */ -void vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, - unsigned long cmd, void *arg) -{ - int ret; - - ret = _vcpu_ioctl(vm, vcpuid, cmd, arg); - TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, - unsigned long cmd, void *arg) +void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - int ret; - - TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid); - - ret = ioctl(vcpu->fd, cmd, arg); - - return ret; -} - -void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) -{ - struct vcpu *vcpu; - uint32_t size = vm->dirty_ring_size; + uint32_t page_size = getpagesize(); + uint32_t size = vcpu->vm->dirty_ring_size; TEST_ASSERT(size > 0, "Should enable dirty ring first"); - vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "Cannot find vcpu %u", vcpuid); - if (!vcpu->dirty_gfns) { void *addr; - addr = mmap(NULL, size, PROT_READ, - MAP_PRIVATE, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + addr = mmap(NULL, size, PROT_READ, MAP_PRIVATE, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped private"); - addr = mmap(NULL, size, PROT_READ | PROT_EXEC, - MAP_PRIVATE, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); + addr = mmap(NULL, size, PROT_READ | PROT_EXEC, MAP_PRIVATE, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); TEST_ASSERT(addr == MAP_FAILED, "Dirty ring mapped exec"); - addr = mmap(NULL, size, PROT_READ | PROT_WRITE, - MAP_SHARED, vcpu->fd, - vm->page_size * KVM_DIRTY_LOG_PAGE_OFFSET); - TEST_ASSERT(addr != MAP_FAILED, "Dirty ring map failed"); + addr = __kvm_mmap(size, PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, + page_size * KVM_DIRTY_LOG_PAGE_OFFSET); vcpu->dirty_gfns = addr; vcpu->dirty_gfns_count = size / sizeof(struct kvm_dirty_gfn); @@ -1980,62 +1782,10 @@ void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid) } /* - * VM Ioctl - * - * Input Args: - * vm - Virtual Machine - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a VM fd. - */ -void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - int ret; - - ret = _vm_ioctl(vm, cmd, arg); - TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - return ioctl(vm->fd, cmd, arg); -} - -/* - * KVM system ioctl - * - * Input Args: - * vm - Virtual Machine - * cmd - Ioctl number - * arg - Argument to pass to the ioctl - * - * Return: None - * - * Issues an arbitrary ioctl on a KVM fd. - */ -void kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - int ret; - - ret = ioctl(vm->kvm_fd, cmd, arg); - TEST_ASSERT(ret == 0, "KVM ioctl %lu failed, rc: %i errno: %i (%s)", - cmd, ret, errno, strerror(errno)); -} - -int _kvm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg) -{ - return ioctl(vm->kvm_fd, cmd, arg); -} - -/* * Device Ioctl */ -int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) +int __kvm_has_device_attr(int dev_fd, uint32_t group, uint64_t attr) { struct kvm_device_attr attribute = { .group = group, @@ -2046,43 +1796,31 @@ int _kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) return ioctl(dev_fd, KVM_HAS_DEVICE_ATTR, &attribute); } -int kvm_device_check_attr(int dev_fd, uint32_t group, uint64_t attr) +int __kvm_test_create_device(struct kvm_vm *vm, uint64_t type) { - int ret = _kvm_device_check_attr(dev_fd, group, attr); - - TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR failed, rc: %i errno: %i", ret, errno); - return ret; -} - -int _kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test, int *fd) -{ - struct kvm_create_device create_dev; - int ret; + struct kvm_create_device create_dev = { + .type = type, + .flags = KVM_CREATE_DEVICE_TEST, + }; - create_dev.type = type; - create_dev.fd = -1; - create_dev.flags = test ? KVM_CREATE_DEVICE_TEST : 0; - ret = ioctl(vm_get_fd(vm), KVM_CREATE_DEVICE, &create_dev); - *fd = create_dev.fd; - return ret; + return __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev); } -int kvm_create_device(struct kvm_vm *vm, uint64_t type, bool test) +int __kvm_create_device(struct kvm_vm *vm, uint64_t type) { - int fd, ret; - - ret = _kvm_create_device(vm, type, test, &fd); + struct kvm_create_device create_dev = { + .type = type, + .fd = -1, + .flags = 0, + }; + int err; - if (!test) { - TEST_ASSERT(!ret, - "KVM_CREATE_DEVICE IOCTL failed, rc: %i errno: %i", ret, errno); - return fd; - } - return ret; + err = __vm_ioctl(vm, KVM_CREATE_DEVICE, &create_dev); + TEST_ASSERT(err <= 0, "KVM_CREATE_DEVICE shouldn't return a positive value"); + return err ? : create_dev.fd; } -int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write) +int __kvm_device_attr_get(int dev_fd, uint32_t group, uint64_t attr, void *val) { struct kvm_device_attr kvmattr = { .group = group, @@ -2090,58 +1828,20 @@ int _kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, .flags = 0, .addr = (uintptr_t)val, }; - int ret; - ret = ioctl(dev_fd, write ? KVM_SET_DEVICE_ATTR : KVM_GET_DEVICE_ATTR, - &kvmattr); - return ret; + return __kvm_ioctl(dev_fd, KVM_GET_DEVICE_ATTR, &kvmattr); } -int kvm_device_access(int dev_fd, uint32_t group, uint64_t attr, - void *val, bool write) +int __kvm_device_attr_set(int dev_fd, uint32_t group, uint64_t attr, void *val) { - int ret = _kvm_device_access(dev_fd, group, attr, val, write); - - TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; -} - -int _vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); - - return _kvm_device_check_attr(vcpu->fd, group, attr); -} - -int vcpu_has_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr) -{ - int ret = _vcpu_has_device_attr(vm, vcpuid, group, attr); - - TEST_ASSERT(!ret, "KVM_HAS_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; -} - -int _vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write) -{ - struct vcpu *vcpu = vcpu_find(vm, vcpuid); - - TEST_ASSERT(vcpu, "nonexistent vcpu id: %d", vcpuid); - - return _kvm_device_access(vcpu->fd, group, attr, val, write); -} - -int vcpu_access_device_attr(struct kvm_vm *vm, uint32_t vcpuid, uint32_t group, - uint64_t attr, void *val, bool write) -{ - int ret = _vcpu_access_device_attr(vm, vcpuid, group, attr, val, write); + struct kvm_device_attr kvmattr = { + .group = group, + .attr = attr, + .flags = 0, + .addr = (uintptr_t)val, + }; - TEST_ASSERT(!ret, "KVM_SET|GET_DEVICE_ATTR IOCTL failed, rc: %i errno: %i", ret, errno); - return ret; + return __kvm_ioctl(dev_fd, KVM_SET_DEVICE_ATTR, &kvmattr); } /* @@ -2155,14 +1855,14 @@ int _kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) .level = level, }; - return _vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); + return __vm_ioctl(vm, KVM_IRQ_LINE, &irq_level); } void kvm_irq_line(struct kvm_vm *vm, uint32_t irq, int level) { int ret = _kvm_irq_line(vm, irq, level); - TEST_ASSERT(ret >= 0, "KVM_IRQ_LINE failed, rc: %i errno: %i", ret, errno); + TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret)); } struct kvm_irq_routing *kvm_gsi_routing_create(void) @@ -2201,7 +1901,7 @@ int _kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) int ret; assert(routing); - ret = ioctl(vm_get_fd(vm), KVM_SET_GSI_ROUTING, routing); + ret = __vm_ioctl(vm, KVM_SET_GSI_ROUTING, routing); free(routing); return ret; @@ -2212,8 +1912,7 @@ void kvm_gsi_routing_write(struct kvm_vm *vm, struct kvm_irq_routing *routing) int ret; ret = _kvm_gsi_routing_write(vm, routing); - TEST_ASSERT(ret == 0, "KVM_SET_GSI_ROUTING failed, rc: %i errno: %i", - ret, errno); + TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_SET_GSI_ROUTING, ret)); } /* @@ -2235,7 +1934,7 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) { int ctr; struct userspace_mem_region *region; - struct vcpu *vcpu; + struct kvm_vcpu *vcpu; fprintf(stream, "%*smode: 0x%x\n", indent, "", vm->mode); fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd); @@ -2249,6 +1948,10 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) region->host_mem); fprintf(stream, "%*sunused_phy_pages: ", indent + 2, ""); sparsebit_dump(stream, region->unused_phy_pages, 0); + if (region->protected_phy_pages) { + fprintf(stream, "%*sprotected_phy_pages: ", indent + 2, ""); + sparsebit_dump(stream, region->protected_phy_pages, 0); + } } fprintf(stream, "%*sMapped Virtual Pages:\n", indent, ""); sparsebit_dump(stream, vm->vpages_mapped, indent + 2); @@ -2260,42 +1963,59 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent) virt_dump(stream, vm, indent + 4); } fprintf(stream, "%*sVCPUs:\n", indent, ""); + list_for_each_entry(vcpu, &vm->vcpus, list) - vcpu_dump(stream, vm, vcpu->id, indent + 2); + vcpu_dump(stream, vcpu, indent + 2); } +#define KVM_EXIT_STRING(x) {KVM_EXIT_##x, #x} + /* Known KVM exit reasons */ static struct exit_reason { unsigned int reason; const char *name; } exit_reasons_known[] = { - {KVM_EXIT_UNKNOWN, "UNKNOWN"}, - {KVM_EXIT_EXCEPTION, "EXCEPTION"}, - {KVM_EXIT_IO, "IO"}, - {KVM_EXIT_HYPERCALL, "HYPERCALL"}, - {KVM_EXIT_DEBUG, "DEBUG"}, - {KVM_EXIT_HLT, "HLT"}, - {KVM_EXIT_MMIO, "MMIO"}, - {KVM_EXIT_IRQ_WINDOW_OPEN, "IRQ_WINDOW_OPEN"}, - {KVM_EXIT_SHUTDOWN, "SHUTDOWN"}, - {KVM_EXIT_FAIL_ENTRY, "FAIL_ENTRY"}, - {KVM_EXIT_INTR, "INTR"}, - {KVM_EXIT_SET_TPR, "SET_TPR"}, - {KVM_EXIT_TPR_ACCESS, "TPR_ACCESS"}, - {KVM_EXIT_S390_SIEIC, "S390_SIEIC"}, - {KVM_EXIT_S390_RESET, "S390_RESET"}, - {KVM_EXIT_DCR, "DCR"}, - {KVM_EXIT_NMI, "NMI"}, - {KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"}, - {KVM_EXIT_OSI, "OSI"}, - {KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"}, - {KVM_EXIT_DIRTY_RING_FULL, "DIRTY_RING_FULL"}, - {KVM_EXIT_X86_RDMSR, "RDMSR"}, - {KVM_EXIT_X86_WRMSR, "WRMSR"}, - {KVM_EXIT_XEN, "XEN"}, -#ifdef KVM_EXIT_MEMORY_NOT_PRESENT - {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, -#endif + KVM_EXIT_STRING(UNKNOWN), + KVM_EXIT_STRING(EXCEPTION), + KVM_EXIT_STRING(IO), + KVM_EXIT_STRING(HYPERCALL), + KVM_EXIT_STRING(DEBUG), + KVM_EXIT_STRING(HLT), + KVM_EXIT_STRING(MMIO), + KVM_EXIT_STRING(IRQ_WINDOW_OPEN), + KVM_EXIT_STRING(SHUTDOWN), + KVM_EXIT_STRING(FAIL_ENTRY), + KVM_EXIT_STRING(INTR), + KVM_EXIT_STRING(SET_TPR), + KVM_EXIT_STRING(TPR_ACCESS), + KVM_EXIT_STRING(S390_SIEIC), + KVM_EXIT_STRING(S390_RESET), + KVM_EXIT_STRING(DCR), + KVM_EXIT_STRING(NMI), + KVM_EXIT_STRING(INTERNAL_ERROR), + KVM_EXIT_STRING(OSI), + KVM_EXIT_STRING(PAPR_HCALL), + KVM_EXIT_STRING(S390_UCONTROL), + KVM_EXIT_STRING(WATCHDOG), + KVM_EXIT_STRING(S390_TSCH), + KVM_EXIT_STRING(EPR), + KVM_EXIT_STRING(SYSTEM_EVENT), + KVM_EXIT_STRING(S390_STSI), + KVM_EXIT_STRING(IOAPIC_EOI), + KVM_EXIT_STRING(HYPERV), + KVM_EXIT_STRING(ARM_NISV), + KVM_EXIT_STRING(X86_RDMSR), + KVM_EXIT_STRING(X86_WRMSR), + KVM_EXIT_STRING(DIRTY_RING_FULL), + KVM_EXIT_STRING(AP_RESET_HOLD), + KVM_EXIT_STRING(X86_BUS_LOCK), + KVM_EXIT_STRING(XEN), + KVM_EXIT_STRING(RISCV_SBI), + KVM_EXIT_STRING(RISCV_CSR), + KVM_EXIT_STRING(NOTIFY), + KVM_EXIT_STRING(LOONGARCH_IOCSR), + KVM_EXIT_STRING(MEMORY_FAULT), + KVM_EXIT_STRING(ARM_SEA), }; /* @@ -2333,6 +2053,7 @@ const char *exit_reason_str(unsigned int exit_reason) * num - number of pages * paddr_min - Physical address minimum * memslot - Memory region to allocate page from + * protected - True if the pages will be used as protected/private memory * * Output Args: None * @@ -2344,8 +2065,9 @@ const char *exit_reason_str(unsigned int exit_reason) * and their base address is returned. A TEST_ASSERT failure occurs if * not enough pages are available at or above paddr_min. */ -vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, - vm_paddr_t paddr_min, uint32_t memslot) +vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, + vm_paddr_t paddr_min, uint32_t memslot, + bool protected) { struct userspace_mem_region *region; sparsebit_idx_t pg, base; @@ -2358,8 +2080,10 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, paddr_min, vm->page_size); region = memslot2region(vm, memslot); - base = pg = paddr_min >> vm->page_shift; + TEST_ASSERT(!protected || region->protected_phy_pages, + "Region doesn't support protected memory"); + base = pg = paddr_min >> vm->page_shift; do { for (; pg < base + num; ++pg) { if (!sparsebit_is_set(region->unused_phy_pages, pg)) { @@ -2378,8 +2102,11 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num, abort(); } - for (pg = base; pg < base + num; ++pg) + for (pg = base; pg < base + num; ++pg) { sparsebit_clear(region->unused_phy_pages, pg); + if (protected) + sparsebit_set(region->protected_phy_pages, pg); + } return base * vm->page_size; } @@ -2390,12 +2117,10 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); } -/* Arbitrary minimum physical address used for virtual translation tables. */ -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) { - return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0); + return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, + vm->memslots[MEM_REGION_PT]); } /* @@ -2415,64 +2140,11 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva) return addr_gpa2hva(vm, addr_gva2gpa(vm, gva)); } -/* - * Is Unrestricted Guest - * - * Input Args: - * vm - Virtual Machine - * - * Output Args: None - * - * Return: True if the unrestricted guest is set to 'Y', otherwise return false. - * - * Check if the unrestricted guest flag is enabled. - */ -bool vm_is_unrestricted_guest(struct kvm_vm *vm) -{ - char val = 'N'; - size_t count; - FILE *f; - - if (vm == NULL) { - /* Ensure that the KVM vendor-specific module is loaded. */ - close(open_kvm_dev_path_or_exit()); - } - - f = fopen("/sys/module/kvm_intel/parameters/unrestricted_guest", "r"); - if (f) { - count = fread(&val, sizeof(char), 1, f); - TEST_ASSERT(count == 1, "Unable to read from param file."); - fclose(f); - } - - return val == 'Y'; -} - -unsigned int vm_get_page_size(struct kvm_vm *vm) -{ - return vm->page_size; -} - -unsigned int vm_get_page_shift(struct kvm_vm *vm) -{ - return vm->page_shift; -} - -unsigned long __attribute__((weak)) vm_compute_max_gfn(struct kvm_vm *vm) +unsigned long __weak vm_compute_max_gfn(struct kvm_vm *vm) { return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; } -uint64_t vm_get_max_gfn(struct kvm_vm *vm) -{ - return vm->max_gfn; -} - -int vm_get_fd(struct kvm_vm *vm) -{ - return vm->fd; -} - static unsigned int vm_calc_num_pages(unsigned int num_pages, unsigned int page_shift, unsigned int new_page_shift, @@ -2513,14 +2185,168 @@ unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size) return vm_adjust_num_guest_pages(mode, n); } -int vm_get_stats_fd(struct kvm_vm *vm) +/* + * Read binary stats descriptors + * + * Input Args: + * stats_fd - the file descriptor for the binary stats file from which to read + * header - the binary stats metadata header corresponding to the given FD + * + * Output Args: None + * + * Return: + * A pointer to a newly allocated series of stat descriptors. + * Caller is responsible for freeing the returned kvm_stats_desc. + * + * Read the stats descriptors from the binary stats interface. + */ +struct kvm_stats_desc *read_stats_descriptors(int stats_fd, + struct kvm_stats_header *header) { - return ioctl(vm->fd, KVM_GET_STATS_FD, NULL); + struct kvm_stats_desc *stats_desc; + ssize_t desc_size, total_size, ret; + + desc_size = get_stats_descriptor_size(header); + total_size = header->num_desc * desc_size; + + stats_desc = calloc(header->num_desc, desc_size); + TEST_ASSERT(stats_desc, "Allocate memory for stats descriptors"); + + ret = pread(stats_fd, stats_desc, total_size, header->desc_offset); + TEST_ASSERT(ret == total_size, "Read KVM stats descriptors"); + + return stats_desc; } -int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid) +/* + * Read stat data for a particular stat + * + * Input Args: + * stats_fd - the file descriptor for the binary stats file from which to read + * header - the binary stats metadata header corresponding to the given FD + * desc - the binary stat metadata for the particular stat to be read + * max_elements - the maximum number of 8-byte values to read into data + * + * Output Args: + * data - the buffer into which stat data should be read + * + * Read the data values of a specified stat from the binary stats interface. + */ +void read_stat_data(int stats_fd, struct kvm_stats_header *header, + struct kvm_stats_desc *desc, uint64_t *data, + size_t max_elements) { - struct vcpu *vcpu = vcpu_find(vm, vcpuid); + size_t nr_elements = min_t(ssize_t, desc->size, max_elements); + size_t size = nr_elements * sizeof(*data); + ssize_t ret; + + TEST_ASSERT(desc->size, "No elements in stat '%s'", desc->name); + TEST_ASSERT(max_elements, "Zero elements requested for stat '%s'", desc->name); - return ioctl(vcpu->fd, KVM_GET_STATS_FD, NULL); + ret = pread(stats_fd, data, size, + header->data_offset + desc->offset); + + TEST_ASSERT(ret >= 0, "pread() failed on stat '%s', errno: %i (%s)", + desc->name, errno, strerror(errno)); + TEST_ASSERT(ret == size, + "pread() on stat '%s' read %ld bytes, wanted %lu bytes", + desc->name, size, ret); +} + +void kvm_get_stat(struct kvm_binary_stats *stats, const char *name, + uint64_t *data, size_t max_elements) +{ + struct kvm_stats_desc *desc; + size_t size_desc; + int i; + + if (!stats->desc) { + read_stats_header(stats->fd, &stats->header); + stats->desc = read_stats_descriptors(stats->fd, &stats->header); + } + + size_desc = get_stats_descriptor_size(&stats->header); + + for (i = 0; i < stats->header.num_desc; ++i) { + desc = (void *)stats->desc + (i * size_desc); + + if (strcmp(desc->name, name)) + continue; + + read_stat_data(stats->fd, &stats->header, desc, data, max_elements); + return; + } + + TEST_FAIL("Unable to find stat '%s'", name); +} + +__weak void kvm_arch_vm_post_create(struct kvm_vm *vm, unsigned int nr_vcpus) +{ +} + +__weak void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm) +{ +} + +__weak void kvm_arch_vm_release(struct kvm_vm *vm) +{ +} + +__weak void kvm_selftest_arch_init(void) +{ +} + +static void report_unexpected_signal(int signum) +{ +#define KVM_CASE_SIGNUM(sig) \ + case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum) + + switch (signum) { + KVM_CASE_SIGNUM(SIGBUS); + KVM_CASE_SIGNUM(SIGSEGV); + KVM_CASE_SIGNUM(SIGILL); + KVM_CASE_SIGNUM(SIGFPE); + default: + TEST_FAIL("Unexpected signal %d\n", signum); + } +} + +void __attribute((constructor)) kvm_selftest_init(void) +{ + struct sigaction sig_sa = { + .sa_handler = report_unexpected_signal, + }; + + /* Tell stdout not to buffer its content. */ + setbuf(stdout, NULL); + + sigaction(SIGBUS, &sig_sa, NULL); + sigaction(SIGSEGV, &sig_sa, NULL); + sigaction(SIGILL, &sig_sa, NULL); + sigaction(SIGFPE, &sig_sa, NULL); + + guest_random_seed = last_guest_seed = random(); + pr_info("Random seed: 0x%x\n", guest_random_seed); + + kvm_selftest_arch_init(); +} + +bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr) +{ + sparsebit_idx_t pg = 0; + struct userspace_mem_region *region; + + if (!vm_arch_has_protected_memory(vm)) + return false; + + region = userspace_mem_region_find(vm, paddr, paddr); + TEST_ASSERT(region, "No vm physical memory at 0x%lx", paddr); + + pg = paddr >> vm->page_shift; + return sparsebit_is_set(region->protected_phy_pages, pg); +} + +__weak bool kvm_arch_has_default_irqchip(void) +{ + return false; } |