1 files changed, 257 insertions, 179 deletions

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 480e3a40d197..8279b6ced8d2 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -12,6 +12,7 @@
 #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>
@@ -23,17 +24,29 @@ uint32_t guest_random_seed;
 struct guest_random_state guest_rng;
 static uint32_t last_guest_seed;
 
-static int vcpu_mmap_sz(void);
+static size_t vcpu_mmap_sz(void);
 
-int open_path_or_exit(const char *path, int flags)
+int __open_path_or_exit(const char *path, int flags, const char *enoent_help)
 {
 	int fd;
 
 	fd = open(path, flags);
-	__TEST_REQUIRE(fd >= 0 || errno != ENOENT, "Cannot open %s: %s", path, strerror(errno));
-	TEST_ASSERT(fd >= 0, "Failed to open '%s'", path);
+	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, "");
 }
 
 /*
@@ -47,7 +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)
@@ -63,6 +76,9 @@ static ssize_t get_module_param(const char *module_name, const char *param,
 	ssize_t bytes_read;
 	int fd, r;
 
+	/* Verify KVM is loaded, to provide a more helpful SKIP message. */
+	close(open_kvm_dev_path_or_exit());
+
 	r = snprintf(path, path_size, "/sys/module/%s/parameters/%s",
 		     module_name, param);
 	TEST_ASSERT(r < path_size,
@@ -79,7 +95,7 @@ static ssize_t get_module_param(const char *module_name, const char *param,
 	return bytes_read;
 }
 
-static int get_module_param_integer(const char *module_name, const char *param)
+int kvm_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
@@ -103,7 +119,7 @@ static int get_module_param_integer(const char *module_name, const char *param)
 	return atoi_paranoid(value);
 }
 
-static bool get_module_param_bool(const char *module_name, const char *param)
+bool kvm_get_module_param_bool(const char *module_name, const char *param)
 {
 	char value;
 	ssize_t r;
@@ -119,36 +135,6 @@ static bool get_module_param_bool(const char *module_name, const char *param)
 	TEST_FAIL("Unrecognized value '%c' for boolean module param", value);
 }
 
-bool get_kvm_param_bool(const char *param)
-{
-	return get_module_param_bool("kvm", param);
-}
-
-bool get_kvm_intel_param_bool(const char *param)
-{
-	return get_module_param_bool("kvm_intel", param);
-}
-
-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
  *
@@ -196,6 +182,11 @@ static void vm_open(struct kvm_vm *vm)
 
 	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)
@@ -210,12 +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,
@@ -236,12 +228,13 @@ 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,
@@ -313,27 +306,30 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	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);
 		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 mode (48-bit virtual address space).
-		 */
-		TEST_ASSERT(vm->va_bits == 48 || vm->va_bits == 57,
-			    "Linear address width (%d bits) not supported",
-			    vm->va_bits);
+
 		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:
@@ -406,6 +402,47 @@ static uint64_t vm_nr_pages_required(enum vm_guest_mode mode,
 	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)
 {
@@ -413,14 +450,24 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct userspace_mem_region *slot0;
 	struct kvm_vm *vm;
-	int i;
+	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);
 
-	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
+	/*
+	 * 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;
 
@@ -442,7 +489,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 	guest_rng = new_guest_random_state(guest_random_seed);
 	sync_global_to_guest(vm, guest_rng);
 
-	kvm_arch_vm_post_create(vm);
+	kvm_arch_vm_post_create(vm, nr_runnable_vcpus);
 
 	return vm;
 }
@@ -480,6 +527,7 @@ struct kvm_vm *__vm_create_with_vcpus(struct vm_shape shape, uint32_t nr_vcpus,
 	for (i = 0; i < nr_vcpus; ++i)
 		vcpus[i] = vm_vcpu_add(vm, i, guest_code);
 
+	kvm_arch_vm_finalize_vcpus(vm);
 	return vm;
 }
 
@@ -545,15 +593,14 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm)
 	return vm_vcpu_recreate(vm, 0);
 }
 
-void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
+int __pin_task_to_cpu(pthread_t task, int cpu)
 {
-	cpu_set_t mask;
-	int r;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
 
-	CPU_ZERO(&mask);
-	CPU_SET(pcpu, &mask);
-	r = sched_setaffinity(0, sizeof(mask), &mask);
-	TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.", pcpu);
+	return pthread_setaffinity_np(task, sizeof(cpuset), &cpuset);
 }
 
 static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
@@ -607,7 +654,7 @@ void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
 
 	/* 2. Check if the main worker needs to be pinned. */
 	if (cpu) {
-		kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask));
+		pin_self_to_cpu(parse_pcpu(cpu, &allowed_mask));
 		cpu = strtok(NULL, delim);
 	}
 
@@ -657,6 +704,20 @@ userspace_mem_region_find(struct kvm_vm *vm, uint64_t start, uint64_t end)
 	return NULL;
 }
 
+static void kvm_stats_release(struct kvm_binary_stats *stats)
+{
+	if (stats->fd < 0)
+		return;
+
+	if (stats->desc) {
+		free(stats->desc);
+		stats->desc = NULL;
+	}
+
+	kvm_close(stats->fd);
+	stats->fd = -1;
+}
+
 __weak void vcpu_arch_free(struct kvm_vcpu *vcpu)
 {
 
@@ -676,19 +737,15 @@ __weak void vcpu_arch_free(struct kvm_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, __KVM_SYSCALL_ERROR("munmap()", ret));
+		kvm_munmap(vcpu->dirty_gfns, vm->dirty_ring_size);
 		vcpu->dirty_gfns = NULL;
 	}
 
-	ret = munmap(vcpu->run, vcpu_mmap_sz());
-	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+	kvm_munmap(vcpu->run, vcpu_mmap_sz());
 
-	ret = close(vcpu->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_close(vcpu->fd);
+	kvm_stats_release(&vcpu->stats);
 
 	list_del(&vcpu->list);
 
@@ -699,35 +756,32 @@ static void vm_vcpu_rm(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 void kvm_vm_release(struct kvm_vm *vmp)
 {
 	struct kvm_vcpu *vcpu, *tmp;
-	int ret;
 
 	list_for_each_entry_safe(vcpu, tmp, &vmp->vcpus, list)
 		vm_vcpu_rm(vmp, vcpu);
 
-	ret = close(vmp->fd);
-	TEST_ASSERT(!ret,  __KVM_SYSCALL_ERROR("close()", ret));
+	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,  __KVM_SYSCALL_ERROR("close()", ret));
+	kvm_arch_vm_release(vmp);
 }
 
 static void __vm_mem_region_delete(struct kvm_vm *vm,
 				   struct userspace_mem_region *region)
 {
-	int ret;
-
 	rb_erase(&region->gpa_node, &vm->regions.gpa_tree);
 	rb_erase(&region->hva_node, &vm->regions.hva_tree);
 	hash_del(&region->slot_node);
 
 	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));
+	kvm_munmap(region->mmap_start, region->mmap_size);
 	if (region->fd >= 0) {
 		/* There's an extra map when using shared memory. */
-		ret = munmap(region->mmap_alias, region->mmap_size);
-		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+		kvm_munmap(region->mmap_alias, region->mmap_size);
 		close(region->fd);
 	}
 	if (region->region.guest_memfd >= 0)
@@ -748,12 +802,6 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	if (vmp == NULL)
 		return;
 
-	/* Free cached stats metadata and close FD */
-	if (vmp->stats_fd) {
-		free(vmp->stats_desc);
-		close(vmp->stats_fd);
-	}
-
 	/* Free userspace_mem_regions. */
 	hash_for_each_safe(vmp->regions.slot_hash, ctr, node, region, slot_node)
 		__vm_mem_region_delete(vmp, region);
@@ -771,7 +819,7 @@ void kvm_vm_free(struct kvm_vm *vmp)
 int kvm_memfd_alloc(size_t size, bool hugepages)
 {
 	int memfd_flags = MFD_CLOEXEC;
-	int fd, r;
+	int fd;
 
 	if (hugepages)
 		memfd_flags |= MFD_HUGETLB;
@@ -779,11 +827,8 @@ int kvm_memfd_alloc(size_t size, bool hugepages)
 	fd = memfd_create("kvm_selftest", memfd_flags);
 	TEST_ASSERT(fd != -1, __KVM_SYSCALL_ERROR("memfd_create()", fd));
 
-	r = ftruncate(fd, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("ftruncate()", r));
-
-	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
-	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+	kvm_ftruncate(fd, size);
+	kvm_fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
 
 	return fd;
 }
@@ -900,8 +945,8 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags
 
 /* 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)
+		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;
@@ -915,30 +960,29 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		"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);
 
@@ -952,8 +996,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			"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);
 	}
@@ -979,7 +1022,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
-	TEST_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)
@@ -990,12 +1033,9 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		region->fd = kvm_memfd_alloc(region->mmap_size,
 					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
 
-	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,
-		    __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED));
+	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),
@@ -1030,8 +1070,7 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 			 * 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));
+			guest_memfd = kvm_dup(guest_memfd);
 		}
 
 		region->region.guest_memfd = guest_memfd;
@@ -1043,20 +1082,18 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	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);
+	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 = __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_memfd: %d",
-		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 */
@@ -1066,12 +1103,10 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 
 	/* 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,
-			    __KVM_SYSCALL_ERROR("mmap()",  (int)(unsigned long)MAP_FAILED));
+		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);
@@ -1080,10 +1115,10 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 
 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)
+				 uint64_t gpa, uint32_t slot, uint64_t npages,
+				 uint32_t flags)
 {
-	vm_mem_add(vm, src_type, guest_paddr, slot, npages, flags, -1, 0);
+	vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0);
 }
 
 /*
@@ -1149,6 +1184,16 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
 		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, &region->region);
+}
+
 /*
  * VM Memory Region Move
  *
@@ -1231,14 +1276,14 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, uint64_t base, uint64_t size,
 }
 
 /* Returns the size of a vCPU's kvm_run structure. */
-static int vcpu_mmap_sz(void)
+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),
+	TEST_ASSERT(ret >= 0 && ret >= sizeof(struct kvm_run),
 		    KVM_IOCTL_ERROR(KVM_GET_VCPU_MMAP_SIZE, ret));
 
 	close(dev_fd);
@@ -1279,12 +1324,15 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t 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: %i expected_min: %zi",
+		"smaller than expected, vcpu_mmap_sz: %zi expected_min: %zi",
 		vcpu_mmap_sz(), sizeof(*vcpu->run));
-	vcpu->run = (struct kvm_run *) mmap(NULL, vcpu_mmap_sz(),
-		PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);
-	TEST_ASSERT(vcpu->run != MAP_FAILED,
-		    __KVM_SYSCALL_ERROR("mmap()", (int)(unsigned long)MAP_FAILED));
+	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);
@@ -1401,8 +1449,6 @@ static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz,
 		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;
@@ -1516,7 +1562,6 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 	while (npages--) {
 		virt_pg_map(vm, vaddr, paddr);
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 
 		vaddr += page_size;
 		paddr += page_size;
@@ -1635,7 +1680,18 @@ void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa)
 /* Create an interrupt controller chip for the specified VM. */
 void vm_create_irqchip(struct kvm_vm *vm)
 {
-	vm_ioctl(vm, KVM_CREATE_IRQCHIP, NULL);
+	int r;
+
+	/*
+	 * 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;
 }
@@ -1648,7 +1704,8 @@ int _vcpu_run(struct kvm_vcpu *vcpu)
 		rc = __vcpu_run(vcpu);
 	} while (rc == -1 && errno == EINTR);
 
-	assert_on_unhandled_exception(vcpu);
+	if (!rc)
+		assert_on_unhandled_exception(vcpu);
 
 	return rc;
 }
@@ -1714,9 +1771,8 @@ void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu)
 			    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,
-			    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);
@@ -1957,9 +2013,9 @@ static struct exit_reason {
 	KVM_EXIT_STRING(RISCV_SBI),
 	KVM_EXIT_STRING(RISCV_CSR),
 	KVM_EXIT_STRING(NOTIFY),
-#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
-	KVM_EXIT_STRING(MEMORY_NOT_PRESENT),
-#endif
+	KVM_EXIT_STRING(LOONGARCH_IOCSR),
+	KVM_EXIT_STRING(MEMORY_FAULT),
+	KVM_EXIT_STRING(ARM_SEA),
 };
 
 /*
@@ -2197,49 +2253,42 @@ void read_stat_data(int stats_fd, struct kvm_stats_header *header,
 		    desc->name, size, ret);
 }
 
-/*
- * Read the data of the named stat
- *
- * Input Args:
- *   vm - the VM for which the stat should be read
- *   stat_name - the name of the stat to 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 __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
-		   size_t max_elements)
+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 (!vm->stats_fd) {
-		vm->stats_fd = vm_get_stats_fd(vm);
-		read_stats_header(vm->stats_fd, &vm->stats_header);
-		vm->stats_desc = read_stats_descriptors(vm->stats_fd,
-							&vm->stats_header);
+	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(&vm->stats_header);
+	size_desc = get_stats_descriptor_size(&stats->header);
 
-	for (i = 0; i < vm->stats_header.num_desc; ++i) {
-		desc = (void *)vm->stats_desc + (i * size_desc);
+	for (i = 0; i < stats->header.num_desc; ++i) {
+		desc = (void *)stats->desc + (i * size_desc);
 
-		if (strcmp(desc->name, stat_name))
+		if (strcmp(desc->name, name))
 			continue;
 
-		read_stat_data(vm->stats_fd, &vm->stats_header, desc,
-			       data, max_elements);
-
-		break;
+		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_post_create(struct kvm_vm *vm)
+__weak void kvm_arch_vm_finalize_vcpus(struct kvm_vm *vm)
+{
+}
+
+__weak void kvm_arch_vm_release(struct kvm_vm *vm)
 {
 }
 
@@ -2247,11 +2296,35 @@ __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);
 
@@ -2272,3 +2345,8 @@ bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t 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;
+}