Merge tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "ARM:
   - Improved guest IPA space support (32 to 52 bits)

   - RAS event delivery for 32bit

   - PMU fixes

   - Guest entry hardening

   - Various cleanups

   - Port of dirty_log_test selftest

  PPC:
   - Nested HV KVM support for radix guests on POWER9. The performance
     is much better than with PR KVM. Migration and arbitrary level of
     nesting is supported.

   - Disable nested HV-KVM on early POWER9 chips that need a particular
     hardware bug workaround

   - One VM per core mode to prevent potential data leaks

   - PCI pass-through optimization

   - merge ppc-kvm topic branch and kvm-ppc-fixes to get a better base

  s390:
   - Initial version of AP crypto virtualization via vfio-mdev

   - Improvement for vfio-ap

   - Set the host program identifier

   - Optimize page table locking

  x86:
   - Enable nested virtualization by default

   - Implement Hyper-V IPI hypercalls

   - Improve #PF and #DB handling

   - Allow guests to use Enlightened VMCS

   - Add migration selftests for VMCS and Enlightened VMCS

   - Allow coalesced PIO accesses

   - Add an option to perform nested VMCS host state consistency check
     through hardware

   - Automatic tuning of lapic_timer_advance_ns

   - Many fixes, minor improvements, and cleanups"

* tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  KVM/nVMX: Do not validate that posted_intr_desc_addr is page aligned
  Revert "kvm: x86: optimize dr6 restore"
  KVM: PPC: Optimize clearing TCEs for sparse tables
  x86/kvm/nVMX: tweak shadow fields
  selftests/kvm: add missing executables to .gitignore
  KVM: arm64: Safety check PSTATE when entering guest and handle IL
  KVM: PPC: Book3S HV: Don't use streamlined entry path on early POWER9 chips
  arm/arm64: KVM: Enable 32 bits kvm vcpu events support
  arm/arm64: KVM: Rename function kvm_arch_dev_ioctl_check_extension()
  KVM: arm64: Fix caching of host MDCR_EL2 value
  KVM: VMX: enable nested virtualization by default
  KVM/x86: Use 32bit xor to clear registers in svm.c
  kvm: x86: Introduce KVM_CAP_EXCEPTION_PAYLOAD
  kvm: vmx: Defer setting of DR6 until #DB delivery
  kvm: x86: Defer setting of CR2 until #PF delivery
  kvm: x86: Add payload operands to kvm_multiple_exception
  kvm: x86: Add exception payload fields to kvm_vcpu_events
  kvm: x86: Add has_payload and payload to kvm_queued_exception
  KVM: Documentation: Fix omission in struct kvm_vcpu_events
  KVM: selftests: add Enlightened VMCS test
  ...

24 files changed, 2749 insertions, 710 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 5c34752e1cff..6210ba41c29e 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,8 @@
-cr4_cpuid_sync_test
-platform_info_test
-set_sregs_test
-sync_regs_test
-vmx_tsc_adjust_test
-state_test
+/x86_64/cr4_cpuid_sync_test
+/x86_64/evmcs_test
+/x86_64/platform_info_test
+/x86_64/set_sregs_test
+/x86_64/sync_regs_test
+/x86_64/vmx_tsc_adjust_test
+/x86_64/state_test
+/dirty_log_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index ec32dad3c3f0..01a219229238 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,26 +1,30 @@
 all:
 
-top_srcdir = ../../../../
+top_srcdir = ../../../..
 UNAME_M := $(shell uname -m)
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c lib/vmx.c
-
-TEST_GEN_PROGS_x86_64 = platform_info_test
-TEST_GEN_PROGS_x86_64 += set_sregs_test
-TEST_GEN_PROGS_x86_64 += sync_regs_test
-TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86_64 += cr4_cpuid_sync_test
-TEST_GEN_PROGS_x86_64 += state_test
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/ucall.c lib/sparsebit.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c
+LIBKVM_aarch64 = lib/aarch64/processor.c
+
+TEST_GEN_PROGS_x86_64 = x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
+TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/state_test
+TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 
+TEST_GEN_PROGS_aarch64 += dirty_log_test
+
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-LINUX_TOOL_INCLUDE = $(top_srcdir)tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
 LDFLAGS += -pthread
 
 # After inclusion, $(OUTPUT) is defined and
@@ -29,7 +33,7 @@ include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS)
+EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
 $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
@@ -41,3 +45,12 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
 all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
 $(STATIC_LIBS):| khdr
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+cscope:
+	$(RM) cscope.*
+	(find $(include_paths) -name '*.h' \
+		-exec realpath --relative-base=$(PWD) {} \;; \
+	find . -name '*.c' \
+		-exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
+	cscope -b
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 0c2cdc105f96..d59820cc2d39 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2018, Red Hat, Inc.
  */
 
+#define _GNU_SOURCE /* for program_invocation_name */
+
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -15,76 +17,78 @@
 
 #include "test_util.h"
 #include "kvm_util.h"
+#include "processor.h"
+
+#define DEBUG printf
 
-#define  DEBUG                 printf
+#define VCPU_ID				1
 
-#define  VCPU_ID                        1
 /* The memory slot index to track dirty pages */
-#define  TEST_MEM_SLOT_INDEX            1
-/*
- * GPA offset of the testing memory slot. Must be bigger than the
- * default vm mem slot, which is DEFAULT_GUEST_PHY_PAGES.
- */
-#define  TEST_MEM_OFFSET                (1ULL << 30) /* 1G */
-/* Size of the testing memory slot */
-#define  TEST_MEM_PAGES                 (1ULL << 18) /* 1G for 4K pages */
+#define TEST_MEM_SLOT_INDEX		1
+
+/* Default guest test memory offset, 1G */
+#define DEFAULT_GUEST_TEST_MEM		0x40000000
+
 /* How many pages to dirty for each guest loop */
-#define  TEST_PAGES_PER_LOOP            1024
+#define TEST_PAGES_PER_LOOP		1024
+
 /* How many host loops to run (one KVM_GET_DIRTY_LOG for each loop) */
-#define  TEST_HOST_LOOP_N               32
+#define TEST_HOST_LOOP_N		32
+
 /* Interval for each host loop (ms) */
-#define  TEST_HOST_LOOP_INTERVAL        10
+#define TEST_HOST_LOOP_INTERVAL		10
+
+/*
+ * Guest/Host shared variables. Ensure addr_gva2hva() and/or
+ * sync_global_to/from_guest() are used when accessing from
+ * the host. READ/WRITE_ONCE() should also be used with anything
+ * that may change.
+ */
+static uint64_t host_page_size;
+static uint64_t guest_page_size;
+static uint64_t guest_num_pages;
+static uint64_t random_array[TEST_PAGES_PER_LOOP];
+static uint64_t iteration;
 
 /*
- * Guest variables.  We use these variables to share data between host
- * and guest.  There are two copies of the variables, one in host memory
- * (which is unused) and one in guest memory.  When the host wants to
- * access these variables, it needs to call addr_gva2hva() to access the
- * guest copy.
+ * GPA offset of the testing memory slot. Must be bigger than
+ * DEFAULT_GUEST_PHY_PAGES.
  */
-uint64_t guest_random_array[TEST_PAGES_PER_LOOP];
-uint64_t guest_iteration;
-uint64_t guest_page_size;
+static uint64_t guest_test_mem = DEFAULT_GUEST_TEST_MEM;
 
 /*
- * Writes to the first byte of a random page within the testing memory
- * region continuously.
+ * Continuously write to the first 8 bytes of a random pages within
+ * the testing memory region.
  */
-void guest_code(void)
+static void guest_code(void)
 {
-	int i = 0;
-	uint64_t volatile *array = guest_random_array;
-	uint64_t volatile *guest_addr;
+	int i;
 
 	while (true) {
 		for (i = 0; i < TEST_PAGES_PER_LOOP; i++) {
-			/*
-			 * Write to the first 8 bytes of a random page
-			 * on the testing memory region.
-			 */
-			guest_addr = (uint64_t *)
-			    (TEST_MEM_OFFSET +
-			     (array[i] % TEST_MEM_PAGES) * guest_page_size);
-			*guest_addr = guest_iteration;
+			uint64_t addr = guest_test_mem;
+			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
+				* guest_page_size;
+			addr &= ~(host_page_size - 1);
+			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
+
 		/* Tell the host that we need more random numbers */
 		GUEST_SYNC(1);
 	}
 }
 
-/*
- * Host variables.  These variables should only be used by the host
- * rather than the guest.
- */
-bool host_quit;
+/* Host variables */
+static bool host_quit;
 
 /* Points to the test VM memory region on which we track dirty logs */
-void *host_test_mem;
+static void *host_test_mem;
+static uint64_t host_num_pages;
 
 /* For statistics only */
-uint64_t host_dirty_count;
-uint64_t host_clear_count;
-uint64_t host_track_next_count;
+static uint64_t host_dirty_count;
+static uint64_t host_clear_count;
+static uint64_t host_track_next_count;
 
 /*
  * We use this bitmap to track some pages that should have its dirty
@@ -93,40 +97,34 @@ uint64_t host_track_next_count;
  * page bit is cleared in the latest bitmap, then the system must
  * report that write in the next get dirty log call.
  */
-unsigned long *host_bmap_track;
+static unsigned long *host_bmap_track;
 
-void generate_random_array(uint64_t *guest_array, uint64_t size)
+static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
 
-	for (i = 0; i < size; i++) {
+	for (i = 0; i < size; i++)
 		guest_array[i] = random();
-	}
 }
 
-void *vcpu_worker(void *data)
+static void *vcpu_worker(void *data)
 {
 	int ret;
-	uint64_t loops, *guest_array, pages_count = 0;
 	struct kvm_vm *vm = data;
+	uint64_t *guest_array;
+	uint64_t pages_count = 0;
 	struct kvm_run *run;
-	struct guest_args args;
+	struct ucall uc;
 
 	run = vcpu_state(vm, VCPU_ID);
 
-	/* Retrieve the guest random array pointer and cache it */
-	guest_array = addr_gva2hva(vm, (vm_vaddr_t)guest_random_array);
-
-	DEBUG("VCPU starts\n");
-
+	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
 	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 
 	while (!READ_ONCE(host_quit)) {
-		/* Let the guest to dirty these random pages */
+		/* Let the guest dirty the random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
-		guest_args_read(vm, VCPU_ID, &args);
-		if (run->exit_reason == KVM_EXIT_IO &&
-		    args.port == GUEST_PORT_SYNC) {
+		if (get_ucall(vm, VCPU_ID, &uc) == UCALL_SYNC) {
 			pages_count += TEST_PAGES_PER_LOOP;
 			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		} else {
@@ -137,18 +135,20 @@ void *vcpu_worker(void *data)
 		}
 	}
 
-	DEBUG("VCPU exits, dirtied %"PRIu64" pages\n", pages_count);
+	DEBUG("Dirtied %"PRIu64" pages\n", pages_count);
 
 	return NULL;
 }
 
-void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
+static void vm_dirty_log_verify(unsigned long *bmap)
 {
 	uint64_t page;
-	uint64_t volatile *value_ptr;
+	uint64_t *value_ptr;
+	uint64_t step = host_page_size >= guest_page_size ? 1 :
+				guest_page_size / host_page_size;
 
-	for (page = 0; page < TEST_MEM_PAGES; page++) {
-		value_ptr = host_test_mem + page * getpagesize();
+	for (page = 0; page < host_num_pages; page += step) {
+		value_ptr = host_test_mem + page * host_page_size;
 
 		/* If this is a special page that we were tracking... */
 		if (test_and_clear_bit(page, host_bmap_track)) {
@@ -208,88 +208,117 @@ void vm_dirty_log_verify(unsigned long *bmap, uint64_t iteration)
 	}
 }
 
-void help(char *name)
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
+				uint64_t extra_mem_pages, void *guest_code)
 {
-	puts("");
-	printf("usage: %s [-i iterations] [-I interval] [-h]\n", name);
-	puts("");
-	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
-	       TEST_HOST_LOOP_N);
-	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
-	       TEST_HOST_LOOP_INTERVAL);
-	puts("");
-	exit(0);
+	struct kvm_vm *vm;
+	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
+
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	vm_vcpu_add_default(vm, vcpuid, guest_code);
+	return vm;
 }
 
-int main(int argc, char *argv[])
+static void run_test(enum vm_guest_mode mode, unsigned long iterations,
+		     unsigned long interval, bool top_offset)
 {
+	unsigned int guest_pa_bits, guest_page_shift;
 	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
-	uint64_t volatile *psize, *iteration;
-	unsigned long *bmap, iterations = TEST_HOST_LOOP_N,
-	    interval = TEST_HOST_LOOP_INTERVAL;
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hi:I:")) != -1) {
-		switch (opt) {
-		case 'i':
-			iterations = strtol(optarg, NULL, 10);
-			break;
-		case 'I':
-			interval = strtol(optarg, NULL, 10);
-			break;
-		case 'h':
-		default:
-			help(argv[0]);
-			break;
-		}
+	uint64_t max_gfn;
+	unsigned long *bmap;
+
+	switch (mode) {
+	case VM_MODE_P52V48_4K:
+		guest_pa_bits = 52;
+		guest_page_shift = 12;
+		break;
+	case VM_MODE_P52V48_64K:
+		guest_pa_bits = 52;
+		guest_page_shift = 16;
+		break;
+	case VM_MODE_P40V48_4K:
+		guest_pa_bits = 40;
+		guest_page_shift = 12;
+		break;
+	case VM_MODE_P40V48_64K:
+		guest_pa_bits = 40;
+		guest_page_shift = 16;
+		break;
+	default:
+		TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
 	}
 
-	TEST_ASSERT(iterations > 2, "Iteration must be bigger than zero\n");
-	TEST_ASSERT(interval > 0, "Interval must be bigger than zero");
+	DEBUG("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
-	      iterations, interval);
+	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
+	guest_page_size = (1ul << guest_page_shift);
+	/* 1G of guest page sized pages */
+	guest_num_pages = (1ul << (30 - guest_page_shift));
+	host_page_size = getpagesize();
+	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
+			 !!((guest_num_pages * guest_page_size) % host_page_size);
 
-	srandom(time(0));
+	if (top_offset) {
+		guest_test_mem = (max_gfn - guest_num_pages) * guest_page_size;
+		guest_test_mem &= ~(host_page_size - 1);
+	}
 
-	bmap = bitmap_alloc(TEST_MEM_PAGES);
-	host_bmap_track = bitmap_alloc(TEST_MEM_PAGES);
+	DEBUG("guest test mem offset: 0x%lx\n", guest_test_mem);
 
-	vm = vm_create_default(VCPU_ID, TEST_MEM_PAGES, guest_code);
+	bmap = bitmap_alloc(host_num_pages);
+	host_bmap_track = bitmap_alloc(host_num_pages);
+
+	vm = create_vm(mode, VCPU_ID, guest_num_pages, guest_code);
 
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-				    TEST_MEM_OFFSET,
+				    guest_test_mem,
 				    TEST_MEM_SLOT_INDEX,
-				    TEST_MEM_PAGES,
+				    guest_num_pages,
 				    KVM_MEM_LOG_DIRTY_PAGES);
-	/* Cache the HVA pointer of the region */
-	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)TEST_MEM_OFFSET);
 
 	/* Do 1:1 mapping for the dirty track memory slot */
-	virt_map(vm, TEST_MEM_OFFSET, TEST_MEM_OFFSET,
-		 TEST_MEM_PAGES * getpagesize(), 0);
+	virt_map(vm, guest_test_mem, guest_test_mem,
+		 guest_num_pages * guest_page_size, 0);
+
+	/* Cache the HVA pointer of the region */
+	host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_mem);
 
+#ifdef __x86_64__
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+#endif
+#ifdef __aarch64__
+	ucall_init(vm, UCALL_MMIO, NULL);
+#endif
 
-	/* Tell the guest about the page size on the system */
-	psize = addr_gva2hva(vm, (vm_vaddr_t)&guest_page_size);
-	*psize = getpagesize();
+	/* Export the shared variables to the guest */
+	sync_global_to_guest(vm, host_page_size);
+	sync_global_to_guest(vm, guest_page_size);
+	sync_global_to_guest(vm, guest_test_mem);
+	sync_global_to_guest(vm, guest_num_pages);
 
 	/* Start the iterations */
-	iteration = addr_gva2hva(vm, (vm_vaddr_t)&guest_iteration);
-	*iteration = 1;
+	iteration = 1;
+	sync_global_to_guest(vm, iteration);
+	host_quit = false;
+	host_dirty_count = 0;
+	host_clear_count = 0;
+	host_track_next_count = 0;
 
-	/* Start dirtying pages */
 	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
 
-	while (*iteration < iterations) {
+	while (iteration < iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
 		usleep(interval * 1000);
 		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-		vm_dirty_log_verify(bmap, *iteration);
-		(*iteration)++;
+		vm_dirty_log_verify(bmap);
+		iteration++;
+		sync_global_to_guest(vm, iteration);
 	}
 
 	/* Tell the vcpu thread to quit */
@@ -302,7 +331,118 @@ int main(int argc, char *argv[])
 
 	free(bmap);
 	free(host_bmap_track);
+	ucall_uninit(vm);
 	kvm_vm_free(vm);
+}
+
+static struct vm_guest_modes {
+	enum vm_guest_mode mode;
+	bool supported;
+	bool enabled;
+} vm_guest_modes[NUM_VM_MODES] = {
+#if defined(__x86_64__)
+	{ VM_MODE_P52V48_4K,	1, 1, },
+	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	0, 0, },
+	{ VM_MODE_P40V48_64K,	0, 0, },
+#elif defined(__aarch64__)
+	{ VM_MODE_P52V48_4K,	0, 0, },
+	{ VM_MODE_P52V48_64K,	0, 0, },
+	{ VM_MODE_P40V48_4K,	1, 1, },
+	{ VM_MODE_P40V48_64K,	1, 1, },
+#endif
+};
+
+static void help(char *name)
+{
+	int i;
+
+	puts("");
+	printf("usage: %s [-h] [-i iterations] [-I interval] "
+	       "[-o offset] [-t] [-m mode]\n", name);
+	puts("");
+	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
+	       TEST_HOST_LOOP_N);
+	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",
+	       TEST_HOST_LOOP_INTERVAL);
+	printf(" -o: guest test memory offset (default: 0x%lx)\n",
+	       DEFAULT_GUEST_TEST_MEM);
+	printf(" -t: map guest test memory at the top of the allowed "
+	       "physical address range\n");
+	printf(" -m: specify the guest mode ID to test "
+	       "(default: test all supported modes)\n"
+	       "     This option may be used multiple times.\n"
+	       "     Guest mode IDs:\n");
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		printf("         %d:    %s%s\n",
+		       vm_guest_modes[i].mode,
+		       vm_guest_mode_string(vm_guest_modes[i].mode),
+		       vm_guest_modes[i].supported ? " (supported)" : "");
+	}
+	puts("");
+	exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned long iterations = TEST_HOST_LOOP_N;
+	unsigned long interval = TEST_HOST_LOOP_INTERVAL;
+	bool mode_selected = false;
+	bool top_offset = false;
+	unsigned int mode;
+	int opt, i;
+
+	while ((opt = getopt(argc, argv, "hi:I:o:tm:")) != -1) {
+		switch (opt) {
+		case 'i':
+			iterations = strtol(optarg, NULL, 10);
+			break;
+		case 'I':
+			interval = strtol(optarg, NULL, 10);
+			break;
+		case 'o':
+			guest_test_mem = strtoull(optarg, NULL, 0);
+			break;
+		case 't':
+			top_offset = true;
+			break;
+		case 'm':
+			if (!mode_selected) {
+				for (i = 0; i < NUM_VM_MODES; ++i)
+					vm_guest_modes[i].enabled = 0;
+				mode_selected = true;
+			}
+			mode = strtoul(optarg, NULL, 10);
+			TEST_ASSERT(mode < NUM_VM_MODES,
+				    "Guest mode ID %d too big", mode);
+			vm_guest_modes[mode].enabled = 1;
+			break;
+		case 'h':
+		default:
+			help(argv[0]);
+			break;
+		}
+	}
+
+	TEST_ASSERT(iterations > 2, "Iterations must be greater than two");
+	TEST_ASSERT(interval > 0, "Interval must be greater than zero");
+	TEST_ASSERT(!top_offset || guest_test_mem == DEFAULT_GUEST_TEST_MEM,
+		    "Cannot use both -o [offset] and -t at the same time");
+
+	DEBUG("Test iterations: %"PRIu64", interval: %"PRIu64" (ms)\n",
+	      iterations, interval);
+
+	srandom(time(0));
+
+	for (i = 0; i < NUM_VM_MODES; ++i) {
+		if (!vm_guest_modes[i].enabled)
+			continue;
+		TEST_ASSERT(vm_guest_modes[i].supported,
+			    "Guest mode ID %d (%s) not supported.",
+			    vm_guest_modes[i].mode,
+			    vm_guest_mode_string(vm_guest_modes[i].mode));
+		run_test(vm_guest_modes[i].mode, iterations, interval, top_offset);
+	}
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
new file mode 100644
index 000000000000..9ef2ab1a0c08
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch64 processor specific defines
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#ifndef SELFTEST_KVM_PROCESSOR_H
+#define SELFTEST_KVM_PROCESSOR_H
+
+#include "kvm_util.h"
+
+
+#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+			   KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
+
+#define CPACR_EL1	3, 0,  1, 0, 2
+#define TCR_EL1		3, 0,  2, 0, 2
+#define MAIR_EL1	3, 0, 10, 2, 0
+#define TTBR0_EL1	3, 0,  2, 0, 0
+#define SCTLR_EL1	3, 0,  1, 0, 0
+
+/*
+ * Default MAIR
+ *                  index   attribute
+ * DEVICE_nGnRnE      0     0000:0000
+ * DEVICE_nGnRE       1     0000:0100
+ * DEVICE_GRE         2     0000:1100
+ * NORMAL_NC          3     0100:0100
+ * NORMAL             4     1111:1111
+ * NORMAL_WT          5     1011:1011
+ */
+#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \
+			  (0x04ul << (1 * 8)) | \
+			  (0x0cul << (2 * 8)) | \
+			  (0x44ul << (3 * 8)) | \
+			  (0xfful << (4 * 8)) | \
+			  (0xbbul << (5 * 8)))
+
+static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)addr;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, &reg);
+}
+
+static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t val)
+{
+	struct kvm_one_reg reg;
+	reg.id = id;
+	reg.addr = (uint64_t)&val;
+	vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, &reg);
+}
+
+#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h
new file mode 100644
index 000000000000..4059014d93ea
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/evmcs.h
@@ -0,0 +1,1098 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ */
+
+#ifndef SELFTEST_KVM_EVMCS_H
+#define SELFTEST_KVM_EVMCS_H
+
+#include <stdint.h>
+#include "vmx.h"
+
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+extern bool enable_evmcs;
+
+struct hv_vp_assist_page {
+	__u32 apic_assist;
+	__u32 reserved;
+	__u64 vtl_control[2];
+	__u64 nested_enlightenments_control[2];
+	__u32 enlighten_vmentry;
+	__u64 current_nested_vmcs;
+};
+
+struct hv_enlightened_vmcs {
+	u32 revision_id;
+	u32 abort;
+
+	u16 host_es_selector;
+	u16 host_cs_selector;
+	u16 host_ss_selector;
+	u16 host_ds_selector;
+	u16 host_fs_selector;
+	u16 host_gs_selector;
+	u16 host_tr_selector;
+
+	u64 host_ia32_pat;
+	u64 host_ia32_efer;
+
+	u64 host_cr0;
+	u64 host_cr3;
+	u64 host_cr4;
+
+	u64 host_ia32_sysenter_esp;
+	u64 host_ia32_sysenter_eip;
+	u64 host_rip;
+	u32 host_ia32_sysenter_cs;
+
+	u32 pin_based_vm_exec_control;
+	u32 vm_exit_controls;
+	u32 secondary_vm_exec_control;
+
+	u64 io_bitmap_a;
+	u64 io_bitmap_b;
+	u64 msr_bitmap;
+
+	u16 guest_es_selector;
+	u16 guest_cs_selector;
+	u16 guest_ss_selector;
+	u16 guest_ds_selector;
+	u16 guest_fs_selector;
+	u16 guest_gs_selector;
+	u16 guest_ldtr_selector;
+	u16 guest_tr_selector;
+
+	u32 guest_es_limit;
+	u32 guest_cs_limit;
+	u32 guest_ss_limit;
+	u32 guest_ds_limit;
+	u32 guest_fs_limit;
+	u32 guest_gs_limit;
+	u32 guest_ldtr_limit;
+	u32 guest_tr_limit;
+	u32 guest_gdtr_limit;
+	u32 guest_idtr_limit;
+
+	u32 guest_es_ar_bytes;
+	u32 guest_cs_ar_bytes;
+	u32 guest_ss_ar_bytes;
+	u32 guest_ds_ar_bytes;
+	u32 guest_fs_ar_bytes;
+	u32 guest_gs_ar_bytes;
+	u32 guest_ldtr_ar_bytes;
+	u32 guest_tr_ar_bytes;
+
+	u64 guest_es_base;
+	u64 guest_cs_base;
+	u64 guest_ss_base;
+	u64 guest_ds_base;
+	u64 guest_fs_base;
+	u64 guest_gs_base;
+	u64 guest_ldtr_base;
+	u64 guest_tr_base;
+	u64 guest_gdtr_base;
+	u64 guest_idtr_base;
+
+	u64 padding64_1[3];
+
+	u64 vm_exit_msr_store_addr;
+	u64 vm_exit_msr_load_addr;
+	u64 vm_entry_msr_load_addr;
+
+	u64 cr3_target_value0;
+	u64 cr3_target_value1;
+	u64 cr3_target_value2;
+	u64 cr3_target_value3;
+
+	u32 page_fault_error_code_mask;
+	u32 page_fault_error_code_match;
+
+	u32 cr3_target_count;
+	u32 vm_exit_msr_store_count;
+	u32 vm_exit_msr_load_count;
+	u32 vm_entry_msr_load_count;
+
+	u64 tsc_offset;
+	u64 virtual_apic_page_addr;
+	u64 vmcs_link_pointer;
+
+	u64 guest_ia32_debugctl;
+	u64 guest_ia32_pat;
+	u64 guest_ia32_efer;
+
+	u64 guest_pdptr0;
+	u64 guest_pdptr1;
+	u64 guest_pdptr2;
+	u64 guest_pdptr3;
+
+	u64 guest_pending_dbg_exceptions;
+	u64 guest_sysenter_esp;
+	u64 guest_sysenter_eip;
+
+	u32 guest_activity_state;
+	u32 guest_sysenter_cs;
+
+	u64 cr0_guest_host_mask;
+	u64 cr4_guest_host_mask;
+	u64 cr0_read_shadow;
+	u64 cr4_read_shadow;
+	u64 guest_cr0;
+	u64 guest_cr3;
+	u64 guest_cr4;
+	u64 guest_dr7;
+
+	u64 host_fs_base;
+	u64 host_gs_base;
+	u64 host_tr_base;
+	u64 host_gdtr_base;
+	u64 host_idtr_base;
+	u64 host_rsp;
+
+	u64 ept_pointer;
+
+	u16 virtual_processor_id;
+	u16 padding16[3];
+
+	u64 padding64_2[5];
+	u64 guest_physical_address;
+
+	u32 vm_instruction_error;
+	u32 vm_exit_reason;
+	u32 vm_exit_intr_info;
+	u32 vm_exit_intr_error_code;
+	u32 idt_vectoring_info_field;
+	u32 idt_vectoring_error_code;
+	u32 vm_exit_instruction_len;
+	u32 vmx_instruction_info;
+
+	u64 exit_qualification;
+	u64 exit_io_instruction_ecx;
+	u64 exit_io_instruction_esi;
+	u64 exit_io_instru