typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
struct userspace_mem_region {
- struct kvm_userspace_memory_region region;
+ struct kvm_userspace_memory_region2 region;
struct sparsebit *unused_phy_pages;
int fd;
off_t offset;
const char *name;
long capability;
int feature;
+ int feature_type;
bool finalize;
__u64 *regs;
__u64 regs_n;
NUM_VM_MODES,
};
+struct vm_shape {
+ enum vm_guest_mode mode;
+ unsigned int type;
+};
+
+#define VM_TYPE_DEFAULT 0
+
+#define VM_SHAPE(__mode) \
+({ \
+ struct vm_shape shape = { \
+ .mode = (__mode), \
+ .type = VM_TYPE_DEFAULT \
+ }; \
+ \
+ shape; \
+})
+
#if defined(__aarch64__)
extern enum vm_guest_mode vm_mode_default;
#endif
+#define VM_SHAPE_DEFAULT VM_SHAPE(VM_MODE_DEFAULT)
+
#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
#define __KVM_SYSCALL_ERROR(_name, _ret) \
"%s failed, rc: %i errno: %i (%s)", (_name), (_ret), errno, strerror(errno)
+/*
+ * Use the "inner", double-underscore macro when reporting errors from within
+ * other macros so that the name of ioctl() and not its literal numeric value
+ * is printed on error. The "outer" macro is strongly preferred when reporting
+ * errors "directly", i.e. without an additional layer of macros, as it reduces
+ * the probability of passing in the wrong string.
+ */
#define __KVM_IOCTL_ERROR(_name, _ret) __KVM_SYSCALL_ERROR(_name, _ret)
#define KVM_IOCTL_ERROR(_ioctl, _ret) __KVM_IOCTL_ERROR(#_ioctl, _ret)
#define __kvm_ioctl(kvm_fd, cmd, arg) \
kvm_do_ioctl(kvm_fd, cmd, arg)
-
-#define _kvm_ioctl(kvm_fd, cmd, name, arg) \
+#define kvm_ioctl(kvm_fd, cmd, arg) \
({ \
int ret = __kvm_ioctl(kvm_fd, cmd, arg); \
\
- TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+ TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \
})
-#define kvm_ioctl(kvm_fd, cmd, arg) \
- _kvm_ioctl(kvm_fd, cmd, #cmd, arg)
-
static __always_inline void static_assert_is_vm(struct kvm_vm *vm) { }
#define __vm_ioctl(vm, cmd, arg) \
kvm_do_ioctl((vm)->fd, cmd, arg); \
})
-#define _vm_ioctl(vm, cmd, name, arg) \
+/*
+ * Assert that a VM or vCPU ioctl() succeeded, with extra magic to detect if
+ * the ioctl() failed because KVM killed/bugged the VM. To detect a dead VM,
+ * probe KVM_CAP_USER_MEMORY, which (a) has been supported by KVM since before
+ * selftests existed and (b) should never outright fail, i.e. is supposed to
+ * return 0 or 1. If KVM kills a VM, KVM returns -EIO for all ioctl()s for the
+ * VM and its vCPUs, including KVM_CHECK_EXTENSION.
+ */
+#define __TEST_ASSERT_VM_VCPU_IOCTL(cond, name, ret, vm) \
+do { \
+ int __errno = errno; \
+ \
+ static_assert_is_vm(vm); \
+ \
+ if (cond) \
+ break; \
+ \
+ if (errno == EIO && \
+ __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY) < 0) { \
+ TEST_ASSERT(errno == EIO, "KVM killed the VM, should return -EIO"); \
+ TEST_FAIL("KVM killed/bugged the VM, check the kernel log for clues"); \
+ } \
+ errno = __errno; \
+ TEST_ASSERT(cond, __KVM_IOCTL_ERROR(name, ret)); \
+} while (0)
+
+#define TEST_ASSERT_VM_VCPU_IOCTL(cond, cmd, ret, vm) \
+ __TEST_ASSERT_VM_VCPU_IOCTL(cond, #cmd, ret, vm)
+
+#define vm_ioctl(vm, cmd, arg) \
({ \
int ret = __vm_ioctl(vm, cmd, arg); \
\
- TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+ __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, vm); \
})
-#define vm_ioctl(vm, cmd, arg) \
- _vm_ioctl(vm, cmd, #cmd, arg)
-
-
static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { }
#define __vcpu_ioctl(vcpu, cmd, arg) \
kvm_do_ioctl((vcpu)->fd, cmd, arg); \
})
-#define _vcpu_ioctl(vcpu, cmd, name, arg) \
+#define vcpu_ioctl(vcpu, cmd, arg) \
({ \
int ret = __vcpu_ioctl(vcpu, cmd, arg); \
\
- TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(name, ret)); \
+ __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \
})
-#define vcpu_ioctl(vcpu, cmd, arg) \
- _vcpu_ioctl(vcpu, cmd, #cmd, arg)
-
/*
* Looks up and returns the value corresponding to the capability
* (KVM_CAP_*) given by cap.
{
int ret = __vm_ioctl(vm, KVM_CHECK_EXTENSION, (void *)cap);
- TEST_ASSERT(ret >= 0, KVM_IOCTL_ERROR(KVM_CHECK_EXTENSION, ret));
+ TEST_ASSERT_VM_VCPU_IOCTL(ret >= 0, KVM_CHECK_EXTENSION, ret, vm);
return ret;
}
vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap);
}
+static inline void vm_set_memory_attributes(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size, uint64_t attributes)
+{
+ struct kvm_memory_attributes attr = {
+ .attributes = attributes,
+ .address = gpa,
+ .size = size,
+ .flags = 0,
+ };
+
+ /*
+ * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows
+ * need significant enhancements to support multiple attributes.
+ */
+ TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE,
+ "Update me to support multiple attributes!");
+
+ vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr);
+}
+
+
+static inline void vm_mem_set_private(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE);
+}
+
+static inline void vm_mem_set_shared(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_set_memory_attributes(vm, gpa, size, 0);
+}
+
+void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t gpa, uint64_t size,
+ bool punch_hole);
+
+static inline void vm_guest_mem_punch_hole(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_guest_mem_fallocate(vm, gpa, size, true);
+}
+
+static inline void vm_guest_mem_allocate(struct kvm_vm *vm, uint64_t gpa,
+ uint64_t size)
+{
+ vm_guest_mem_fallocate(vm, gpa, size, false);
+}
+
void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
const char *vm_guest_mode_string(uint32_t i);
{
int fd = __vm_ioctl(vm, KVM_GET_STATS_FD, NULL);
- TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+ TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_GET_STATS_FD, fd, vm);
return fd;
}
void vm_create_irqchip(struct kvm_vm *vm);
+static inline int __vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+ uint64_t flags)
+{
+ struct kvm_create_guest_memfd guest_memfd = {
+ .size = size,
+ .flags = flags,
+ };
+
+ return __vm_ioctl(vm, KVM_CREATE_GUEST_MEMFD, &guest_memfd);
+}
+
+static inline int vm_create_guest_memfd(struct kvm_vm *vm, uint64_t size,
+ uint64_t flags)
+{
+ int fd = __vm_create_guest_memfd(vm, size, flags);
+
+ TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_GUEST_MEMFD, fd));
+ return fd;
+}
+
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 __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
uint64_t gpa, uint64_t size, void *hva);
+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 __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);
+
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);
+void vm_mem_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 guest_memfd_fd, uint64_t guest_memfd_offset);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
{
int fd = __vcpu_ioctl(vcpu, KVM_GET_STATS_FD, NULL);
- TEST_ASSERT(fd >= 0, KVM_IOCTL_ERROR(KVM_GET_STATS_FD, fd));
+ TEST_ASSERT_VM_VCPU_IOCTL(fd >= 0, KVM_CHECK_EXTENSION, fd, vcpu->vm);
return fd;
}
* __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
* calculate the amount of memory needed for per-vCPU data, e.g. stacks.
*/
-struct kvm_vm *____vm_create(enum vm_guest_mode mode);
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+struct kvm_vm *____vm_create(struct vm_shape shape);
+struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
uint64_t nr_extra_pages);
static inline struct kvm_vm *vm_create_barebones(void)
{
- return ____vm_create(VM_MODE_DEFAULT);
+ return ____vm_create(VM_SHAPE_DEFAULT);
}
+#ifdef __x86_64__
+static inline struct kvm_vm *vm_create_barebones_protected_vm(void)
+{
+ const struct vm_shape shape = {
+ .mode = VM_MODE_DEFAULT,
+ .type = KVM_X86_SW_PROTECTED_VM,
+ };
+
+ return ____vm_create(shape);
+}
+#endif
+
static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
{
- return __vm_create(VM_MODE_DEFAULT, nr_runnable_vcpus, 0);
+ return __vm_create(VM_SHAPE_DEFAULT, nr_runnable_vcpus, 0);
}
-struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
+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[]);
void *guest_code,
struct kvm_vcpu *vcpus[])
{
- return __vm_create_with_vcpus(VM_MODE_DEFAULT, nr_vcpus, 0,
+ return __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, 0,
guest_code, vcpus);
}
+
+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);
+
/*
* Create a VM with a single vCPU with reasonable defaults and @extra_mem_pages
* additional pages of guest memory. Returns the VM and vCPU (via out param).
*/
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
- uint64_t extra_mem_pages,
- void *guest_code);
+static inline struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+ uint64_t extra_mem_pages,
+ void *guest_code)
+{
+ return __vm_create_shape_with_one_vcpu(VM_SHAPE_DEFAULT, vcpu,
+ extra_mem_pages, guest_code);
+}
static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
void *guest_code)
return __vm_create_with_one_vcpu(vcpu, 0, guest_code);
}
+static inline struct kvm_vm *vm_create_shape_with_one_vcpu(struct vm_shape shape,
+ struct kvm_vcpu **vcpu,
+ void *guest_code)
+{
+ return __vm_create_shape_with_one_vcpu(shape, vcpu, 0, guest_code);
+}
+
struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
return n;
}
-struct kvm_userspace_memory_region *
-kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
- uint64_t end);
-
#define sync_global_to_guest(vm, g) ({ \
typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
memcpy(_p, &(g), sizeof(g)); \
projects / thirdparty / kernel / stable.git / blobdiff