1 files changed, 260 insertions, 113 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 7a8af1821f5d..b2262b5fad9e 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -27,7 +27,8 @@ int open_path_or_exit(const char *path, int flags)
 	int fd;
 
 	fd = open(path, flags);
-	__TEST_REQUIRE(fd >= 0, "%s not available (errno: %d)", path, errno);
+	__TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno));
+	TEST_ASSERT(fd >= 0, "Failed to open '%s'", path);
 
 	return fd;
 }
@@ -51,13 +52,13 @@ int open_kvm_dev_path_or_exit(void)
 	return _open_kvm_dev_path_or_exit(O_RDONLY);
 }
 
-static bool get_module_param_bool(const char *module_name, const char *param)
+static ssize_t get_module_param(const char *module_name, const char *param,
+				void *buffer, size_t buffer_size)
 {
 	const int path_size = 128;
 	char path[path_size];
-	char value;
-	ssize_t r;
-	int fd;
+	ssize_t bytes_read;
+	int fd, r;
 
 	r = snprintf(path, path_size, "/sys/module/%s/parameters/%s",
 		     module_name, param);
@@ -66,11 +67,46 @@ static bool get_module_param_bool(const char *module_name, const char *param)
 
 	fd = open_path_or_exit(path, O_RDONLY);
 
-	r = read(fd, &value, 1);
-	TEST_ASSERT(r == 1, "read(%s) failed", path);
+	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;
+}
+
+static int get_module_param_integer(const char *module_name, const char *param)
+{
+	/*
+	 * 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;
+
+	memset(value, '\0', sizeof(value));
+
+	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);
+}
+
+static bool get_module_param_bool(const char *module_name, const char *param)
+{
+	char value;
+	ssize_t r;
+
+	r = get_module_param(module_name, param, &value, sizeof(value));
+	TEST_ASSERT_EQ(r, 1);
 
 	if (value == 'Y')
 		return true;
@@ -95,6 +131,21 @@ bool get_kvm_amd_param_bool(const char *param)
 	return get_module_param_bool("kvm_amd", param);
 }
 
+int get_kvm_param_integer(const char *param)
+{
+	return get_module_param_integer("kvm", param);
+}
+
+int get_kvm_intel_param_integer(const char *param)
+{
+	return get_module_param_integer("kvm_intel", param);
+}
+
+int get_kvm_amd_param_integer(const char *param)
+{
+	return get_module_param_integer("kvm_amd", param);
+}
+
 /*
  * Capability
  *
@@ -148,6 +199,7 @@ 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",
@@ -173,6 +225,7 @@ 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 },
@@ -209,7 +262,7 @@ __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 		(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
 }
 
-struct kvm_vm *____vm_create(enum vm_guest_mode mode)
+struct kvm_vm *____vm_create(struct vm_shape shape)
 {
 	struct kvm_vm *vm;
 
@@ -221,13 +274,14 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	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->subtype = shape.subtype;
 
-	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) {
@@ -251,6 +305,7 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	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:
@@ -262,10 +317,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 	case VM_MODE_PXXV48_4K:
 #ifdef __x86_64__
 		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
+		kvm_init_vm_address_properties(vm);
 		/*
 		 * 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.
+		 * isn't for this mode (48-bit virtual address space).
 		 */
 		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
 			    "Linear address width (%d bits) not supported",
@@ -285,10 +341,11 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 		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
@@ -316,7 +373,7 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	uint64_t nr_pages;
 
 	TEST_ASSERT(nr_runnable_vcpus,
-		    "Use vm_create_barebones() for VMs that _never_ have vCPUs\n");
+		    "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",
@@ -347,19 +404,19 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	return vm_adjust_num_guest_pages(mode, nr_pages);
 }
 
-struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
+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(mode, nr_runnable_vcpus,
+	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;
 
-	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
-		 vm_guest_mode_string(mode), nr_pages);
+	pr_debug("%s: mode='%s' type='%d', pages='%ld'\n", __func__,
+		 vm_guest_mode_string(shape.mode), shape.type, nr_pages);
 
-	vm = ____vm_create(mode);
+	vm = ____vm_create(shape);
 
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
 	for (i = 0; i < NR_MEM_REGIONS; i++)
@@ -400,7 +457,7 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
  * 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,
+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[])
 {
@@ -409,7 +466,7 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 
 	TEST_ASSERT(!nr_vcpus || vcpus, "Must provide vCPU array");
 
-	vm = __vm_create(mode, nr_vcpus, extra_mem_pages);
+	vm = __vm_create(shape, nr_vcpus, extra_mem_pages);
 
 	for (i = 0; i < nr_vcpus; ++i)
 		vcpus[i] = vm_vcpu_add(vm, i, guest_code);
@@ -417,15 +474,15 @@ struct kvm_vm *__vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus
 	return vm;
 }
 
-struct kvm_vm *__vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
-					 uint64_t extra_mem_pages,
-					 void *guest_code)
+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)
 {
 	struct kvm_vcpu *vcpus[1];
 	struct kvm_vm *vm;
 
-	vm = __vm_create_with_vcpus(VM_MODE_DEFAULT, 1, extra_mem_pages,
-				    guest_code, vcpus);
+	vm = __vm_create_with_vcpus(shape, 1, extra_mem_pages, guest_code, vcpus);
 
 	*vcpu = vcpus[0];
 	return vm;
@@ -453,8 +510,9 @@ void kvm_vm_restart(struct kvm_vm *vmp)
 		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, &region->region);
-		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+		int ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION2, &region->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",
@@ -486,7 +544,7 @@ void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
 	CPU_ZERO(&mask);
 	CPU_SET(pcpu, &mask);
 	r = sched_setaffinity(0, sizeof(mask), &mask);
-	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
+	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu);
 }
 
 static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
@@ -494,7 +552,7 @@ 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?\n", pcpu);
+		    "Not allowed to run on pCPU '%d', check cgroups?", pcpu);
 	return pcpu;
 }
 
@@ -524,7 +582,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 	int i, r;
 
 	cpu_list = strdup(pcpus_string);
-	TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");
+	TEST_ASSERT(cpu_list, "strdup() allocation failed.");
 
 	r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
 	TEST_ASSERT(!r, "sched_getaffinity() failed");
@@ -533,7 +591,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 
 	/* 1. Get all pcpus for vcpus. */
 	for (i = 0; i < nr_vcpus; i++) {
-		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
+		TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'", i);
 		vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
 		cpu = strtok(NULL, delim);
 	}
@@ -590,35 +648,6 @@ 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)
-{
-	struct userspace_mem_region *region;
-
-	region = userspace_mem_region_find(vm, start, end);
-	if (!region)
-		return NULL;
-
-	return &region->region;
-}
-
 __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
 {
 
@@ -686,9 +715,10 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	}
 
 	region->region.memory_size = 0;
-	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
 	sparsebit_free(&region->unused_phy_pages);
+	sparsebit_free(&region->protected_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
 	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
 	if (region->fd >= 0) {
@@ -697,6 +727,8 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
 		close(region->fd);
 	}
+	if (region->region.guest_memfd >= 0)
+		close(region->region.guest_memfd);
 
 	free(region);
 }
@@ -898,36 +930,44 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
-/*
- * 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_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,
+	};
+
+	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
+}
+
+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 guest_paddr, 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_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
@@ -980,7 +1020,7 @@ 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) */
@@ -1027,15 +1067,41 @@ 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 = dup(guest_memfd);
+			TEST_ASSERT(guest_memfd >= 0, __KVM_SYSCALL_ERROR("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();
+	if (vm_arch_has_protected_memory(vm))
+		region->protected_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
 	region->region.slot = slot;
@@ -1043,13 +1109,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	region->region.guest_phys_addr = guest_paddr;
 	region->region.memory_size = npages * vm->page_size;
 	region->region.userspace_addr = (uintptr_t) region->host_mem;
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
-	TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->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",
+		"  guest_phys_addr: 0x%lx size: 0x%lx guest_memfd: %d",
 		ret, errno, slot, flags,
-		guest_paddr, (uint64_t) region->region.memory_size);
+		guest_paddr, (uint64_t) 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);
@@ -1070,6 +1137,14 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	}
 }
 
+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)
+{
+	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+}
+
 /*
  * Memslot to region
  *
@@ -1126,9 +1201,9 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 
 	region->region.flags = flags;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->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);
 }
@@ -1156,9 +1231,9 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa)
 
 	region->region.guest_phys_addr = new_gpa;
 
-	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION, &region->region);
+	ret = __vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->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);
 }
@@ -1181,6 +1256,34 @@ void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot)
 	__vm_mem_region_delete(vm, memslot2region(vm, slot), true);
 }
 
+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 int vcpu_mmap_sz(void)
 {
@@ -1218,7 +1321,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	struct kvm_vcpu *vcpu;
 
 	/* Confirm a vcpu with the specified id doesn't already exist. */
-	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists\n", vcpu_id);
+	TEST_ASSERT(!vcpu_exists(vm, vcpu_id), "vCPU%d already exists", vcpu_id);
 
 	/* Allocate and initialize new vcpu structure. */
 	vcpu = calloc(1, sizeof(*vcpu));
@@ -1227,7 +1330,7 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 	vcpu->vm = vm;
 	vcpu->id = vcpu_id;
 	vcpu->fd = __vm_ioctl(vm, KVM_CREATE_VCPU, (void *)(unsigned long)vcpu_id);
-	TEST_ASSERT(vcpu->fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu->fd));
+	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: %i expected_min: %zi",
@@ -1329,15 +1432,17 @@ va_found:
 	return pgidx_start * vm->page_size;
 }
 
-vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-			    enum kvm_mem_region_type type)
+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]);
+	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
@@ -1357,6 +1462,20 @@ vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 	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
  *
@@ -1479,6 +1598,8 @@ 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);
@@ -1825,6 +1946,10 @@ 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);
@@ -1926,6 +2051,7 @@ 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
  *
@@ -1937,8 +2063,9 @@ 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;
@@ -1951,8 +2078,10 @@ 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)) {
@@ -1971,8 +2100,11 @@ 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;
 }
@@ -2176,3 +2308,18 @@ void __attribute((constructor)) kvm_selftest_init(void)
 
 	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);
+}