Merging upstream version 6.9.2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

52 files changed, 2810 insertions, 774 deletions

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 492e937fab..741c7dc16a 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -36,7 +36,9 @@ LIBKVM_x86_64 += lib/x86_64/apic.c
 LIBKVM_x86_64 += lib/x86_64/handlers.S
 LIBKVM_x86_64 += lib/x86_64/hyperv.c
 LIBKVM_x86_64 += lib/x86_64/memstress.c
+LIBKVM_x86_64 += lib/x86_64/pmu.c
 LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/sev.c
 LIBKVM_x86_64 += lib/x86_64/svm.c
 LIBKVM_x86_64 += lib/x86_64/ucall.c
 LIBKVM_x86_64 += lib/x86_64/vmx.c
@@ -53,6 +55,7 @@ LIBKVM_s390x += lib/s390x/diag318_test_handler.c
 LIBKVM_s390x += lib/s390x/processor.c
 LIBKVM_s390x += lib/s390x/ucall.c
 
+LIBKVM_riscv += lib/riscv/handlers.S
 LIBKVM_riscv += lib/riscv/processor.c
 LIBKVM_riscv += lib/riscv/ucall.c
 
@@ -80,6 +83,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
 TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test
 TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
 TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test
 TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test
@@ -117,6 +121,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
+TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test
 TEST_GEN_PROGS_x86_64 += x86_64/amx_test
 TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test
 TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test
@@ -143,7 +148,6 @@ TEST_GEN_PROGS_x86_64 += system_counter_offset_test
 TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test
 
 TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs
-TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
 TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
 TEST_GEN_PROGS_aarch64 += aarch64/hypercalls
 TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test
@@ -155,6 +159,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
 TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
+TEST_GEN_PROGS_aarch64 += arch_timer
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
@@ -184,6 +189,7 @@ TEST_GEN_PROGS_s390x += rseq_test
 TEST_GEN_PROGS_s390x += set_memory_region_test
 TEST_GEN_PROGS_s390x += kvm_binary_stats_test
 
+TEST_GEN_PROGS_riscv += arch_timer
 TEST_GEN_PROGS_riscv += demand_paging_test
 TEST_GEN_PROGS_riscv += dirty_log_test
 TEST_GEN_PROGS_riscv += get-reg-list
@@ -194,6 +200,7 @@ TEST_GEN_PROGS_riscv += kvm_page_table_test
 TEST_GEN_PROGS_riscv += set_memory_region_test
 TEST_GEN_PROGS_riscv += steal_time
 
+SPLIT_TESTS += arch_timer
 SPLIT_TESTS += get-reg-list
 
 TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
@@ -217,7 +224,7 @@ else
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD -MP \
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \
 	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-builtin-strnlen \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
@@ -260,32 +267,36 @@ LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
 LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
 LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
-SPLIT_TESTS_TARGETS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
-SPLIT_TESTS_OBJS := $(patsubst %, $(ARCH_DIR)/%.o, $(SPLIT_TESTS))
+SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
+SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH_DIR)/%.o, $(SPLIT_TESTS))
 
 TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS))
 TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
 TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ))
 TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS))
-TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TESTS_OBJS))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ))
 -include $(TEST_DEP_FILES)
 
-$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): %: %.o
+$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+
+$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \
+$(TEST_GEN_PROGS_EXTENDED): %: %.o
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@
 $(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-$(SPLIT_TESTS_TARGETS): %: %.o $(SPLIT_TESTS_OBJS)
+$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH_DIR)/%.o
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@
+$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH_DIR)/%.o: $(ARCH_DIR)/%.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
 EXTRA_CLEAN += $(GEN_HDRS) \
 	       $(LIBKVM_OBJS) \
-	       $(SPLIT_TESTS_OBJS) \
+	       $(SPLIT_TEST_GEN_OBJ) \
 	       $(TEST_DEP_FILES) \
 	       $(TEST_GEN_OBJ) \
 	       cscope.*
 
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS)
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
@@ -298,8 +309,8 @@ $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS)
 $(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
 
-x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-$(SPLIT_TESTS_OBJS): $(GEN_HDRS)
+$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
+$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS)
 $(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 $(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
 $(TEST_GEN_OBJ): $(GEN_HDRS)
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 2cb8dd1f82..4eaba83cdc 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -1,64 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * arch_timer.c - Tests the aarch64 timer IRQ functionality
- *
  * The test validates both the virtual and physical timer IRQs using
- * CVAL and TVAL registers. This consitutes the four stages in the test.
- * The guest's main thread configures the timer interrupt for a stage
- * and waits for it to fire, with a timeout equal to the timer period.
- * It asserts that the timeout doesn't exceed the timer period.
- *
- * On the other hand, upon receipt of an interrupt, the guest's interrupt
- * handler validates the interrupt by checking if the architectural state
- * is in compliance with the specifications.
- *
- * The test provides command-line options to configure the timer's
- * period (-p), number of vCPUs (-n), and iterations per stage (-i).
- * To stress-test the timer stack even more, an option to migrate the
- * vCPUs across pCPUs (-m), at a particular rate, is also provided.
+ * CVAL and TVAL registers.
  *
  * Copyright (c) 2021, Google LLC.
  */
 #define _GNU_SOURCE
 
-#include <stdlib.h>
-#include <pthread.h>
-#include <linux/kvm.h>
-#include <linux/sizes.h>
-#include <linux/bitmap.h>
-#include <sys/sysinfo.h>
-
-#include "kvm_util.h"
-#include "processor.h"
-#include "delay.h"
 #include "arch_timer.h"
+#include "delay.h"
 #include "gic.h"
+#include "processor.h"
+#include "timer_test.h"
 #include "vgic.h"
 
-#define NR_VCPUS_DEF			4
-#define NR_TEST_ITERS_DEF		5
-#define TIMER_TEST_PERIOD_MS_DEF	10
-#define TIMER_TEST_ERR_MARGIN_US	100
-#define TIMER_TEST_MIGRATION_FREQ_MS	2
-
-struct test_args {
-	int nr_vcpus;
-	int nr_iter;
-	int timer_period_ms;
-	int migration_freq_ms;
-	struct kvm_arm_counter_offset offset;
-};
-
-static struct test_args test_args = {
-	.nr_vcpus = NR_VCPUS_DEF,
-	.nr_iter = NR_TEST_ITERS_DEF,
-	.timer_period_ms = TIMER_TEST_PERIOD_MS_DEF,
-	.migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS,
-	.offset = { .reserved = 1 },
-};
-
-#define msecs_to_usecs(msec)		((msec) * 1000LL)
-
 #define GICD_BASE_GPA			0x8000000ULL
 #define GICR_BASE_GPA			0x80A0000ULL
 
@@ -70,22 +25,8 @@ enum guest_stage {
 	GUEST_STAGE_MAX,
 };
 
-/* Shared variables between host and guest */
-struct test_vcpu_shared_data {
-	int nr_iter;
-	enum guest_stage guest_stage;
-	uint64_t xcnt;
-};
-
-static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
-static pthread_t pt_vcpu_run[KVM_MAX_VCPUS];
-static struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS];
-
 static int vtimer_irq, ptimer_irq;
 
-static unsigned long *vcpu_done_map;
-static pthread_mutex_t vcpu_done_map_lock;
-
 static void
 guest_configure_timer_action(struct test_vcpu_shared_data *shared_data)
 {
@@ -158,9 +99,9 @@ static void guest_validate_irq(unsigned int intid,
 
 	/* Basic 'timer condition met' check */
 	__GUEST_ASSERT(xcnt >= cval,
-		       "xcnt = 0x%llx, cval = 0x%llx, xcnt_diff_us = 0x%llx",
+		       "xcnt = 0x%lx, cval = 0x%lx, xcnt_diff_us = 0x%lx",
 		       xcnt, cval, xcnt_diff_us);
-	__GUEST_ASSERT(xctl & CTL_ISTATUS, "xcnt = 0x%llx", xcnt);
+	__GUEST_ASSERT(xctl & CTL_ISTATUS, "xctl = 0x%lx", xctl);
 
 	WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
 }
@@ -190,10 +131,14 @@ static void guest_run_stage(struct test_vcpu_shared_data *shared_data,
 
 		/* Setup a timeout for the interrupt to arrive */
 		udelay(msecs_to_usecs(test_args.timer_period_ms) +
-			TIMER_TEST_ERR_MARGIN_US);
+			test_args.timer_err_margin_us);
 
 		irq_iter = READ_ONCE(shared_data->nr_iter);
-		GUEST_ASSERT_EQ(config_iter + 1, irq_iter);
+		__GUEST_ASSERT(config_iter + 1 == irq_iter,
+				"config_iter + 1 = 0x%x, irq_iter = 0x%x.\n"
+				"  Guest timer interrupt was not triggered within the specified\n"
+				"  interval, try to increase the error margin by [-e] option.\n",
+				config_iter + 1, irq_iter);
 	}
 }
 
@@ -222,137 +167,6 @@ static void guest_code(void)
 	GUEST_DONE();
 }
 
-static void *test_vcpu_run(void *arg)
-{
-	unsigned int vcpu_idx = (unsigned long)arg;
-	struct ucall uc;
-	struct kvm_vcpu *vcpu = vcpus[vcpu_idx];
-	struct kvm_vm *vm = vcpu->vm;
-	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpu_idx];
-
-	vcpu_run(vcpu);
-
-	/* Currently, any exit from guest is an indication of completion */
-	pthread_mutex_lock(&vcpu_done_map_lock);
-	__set_bit(vcpu_idx, vcpu_done_map);
-	pthread_mutex_unlock(&vcpu_done_map_lock);
-
-	switch (get_ucall(vcpu, &uc)) {
-	case UCALL_SYNC:
-	case UCALL_DONE:
-		break;
-	case UCALL_ABORT:
-		sync_global_from_guest(vm, *shared_data);
-		fprintf(stderr, "Guest assert failed,  vcpu %u; stage; %u; iter: %u\n",
-			vcpu_idx, shared_data->guest_stage, shared_data->nr_iter);
-		REPORT_GUEST_ASSERT(uc);
-		break;
-	default:
-		TEST_FAIL("Unexpected guest exit");
-	}
-
-	return NULL;
-}
-
-static uint32_t test_get_pcpu(void)
-{
-	uint32_t pcpu;
-	unsigned int nproc_conf;
-	cpu_set_t online_cpuset;
-
-	nproc_conf = get_nprocs_conf();
-	sched_getaffinity(0, sizeof(cpu_set_t), &online_cpuset);
-
-	/* Randomly find an available pCPU to place a vCPU on */
-	do {
-		pcpu = rand() % nproc_conf;
-	} while (!CPU_ISSET(pcpu, &online_cpuset));
-
-	return pcpu;
-}
-
-static int test_migrate_vcpu(unsigned int vcpu_idx)
-{
-	int ret;
-	cpu_set_t cpuset;
-	uint32_t new_pcpu = test_get_pcpu();
-
-	CPU_ZERO(&cpuset);
-	CPU_SET(new_pcpu, &cpuset);
-
-	pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu);
-
-	ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx],
-				     sizeof(cpuset), &cpuset);
-
-	/* Allow the error where the vCPU thread is already finished */
-	TEST_ASSERT(ret == 0 || ret == ESRCH,
-		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d",
-		    vcpu_idx, new_pcpu, ret);
-
-	return ret;
-}
-
-static void *test_vcpu_migration(void *arg)
-{
-	unsigned int i, n_done;
-	bool vcpu_done;
-
-	do {
-		usleep(msecs_to_usecs(test_args.migration_freq_ms));
-
-		for (n_done = 0, i = 0; i < test_args.nr_vcpus; i++) {
-			pthread_mutex_lock(&vcpu_done_map_lock);
-			vcpu_done = test_bit(i, vcpu_done_map);
-			pthread_mutex_unlock(&vcpu_done_map_lock);
-
-			if (vcpu_done) {
-				n_done++;
-				continue;
-			}
-
-			test_migrate_vcpu(i);
-		}
-	} while (test_args.nr_vcpus != n_done);
-
-	return NULL;
-}
-
-static void test_run(struct kvm_vm *vm)
-{
-	pthread_t pt_vcpu_migration;
-	unsigned int i;
-	int ret;
-
-	pthread_mutex_init(&vcpu_done_map_lock, NULL);
-	vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
-	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap");
-
-	for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) {
-		ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run,
-				     (void *)(unsigned long)i);
-		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i);
-	}
-
-	/* Spawn a thread to control the vCPU migrations */
-	if (test_args.migration_freq_ms) {
-		srand(time(NULL));
-
-		ret = pthread_create(&pt_vcpu_migration, NULL,
-					test_vcpu_migration, NULL);
-		TEST_ASSERT(!ret, "Failed to create the migration pthread");
-	}
-
-
-	for (i = 0; i < test_args.nr_vcpus; i++)
-		pthread_join(pt_vcpu_run[i], NULL);
-
-	if (test_args.migration_freq_ms)
-		pthread_join(pt_vcpu_migration, NULL);
-
-	bitmap_free(vcpu_done_map);
-}
-
 static void test_init_timer_irq(struct kvm_vm *vm)
 {
 	/* Timer initid should be same for all the vCPUs, so query only vCPU-0 */
@@ -369,7 +183,7 @@ static void test_init_timer_irq(struct kvm_vm *vm)
 
 static int gic_fd;
 
-static struct kvm_vm *test_vm_create(void)
+struct kvm_vm *test_vm_create(void)
 {
 	struct kvm_vm *vm;
 	unsigned int i;
@@ -380,10 +194,14 @@ static struct kvm_vm *test_vm_create(void)
 	vm_init_descriptor_tables(vm);
 	vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler);
 
-	if (!test_args.offset.reserved) {
-		if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET))
-			vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &test_args.offset);
-		else
+	if (!test_args.reserved) {
+		if (kvm_has_cap(KVM_CAP_COUNTER_OFFSET)) {
+			struct kvm_arm_counter_offset offset = {
+				.counter_offset = test_args.counter_offset,
+				.reserved = 0,
+			};
+			vm_ioctl(vm, KVM_ARM_SET_COUNTER_OFFSET, &offset);
+		} else
 			TEST_FAIL("no support for global offset");
 	}
 
@@ -400,81 +218,8 @@ static struct kvm_vm *test_vm_create(void)
 	return vm;
 }
 
-static void test_vm_cleanup(struct kvm_vm *vm)
+void test_vm_cleanup(struct kvm_vm *vm)
 {
 	close(gic_fd);
 	kvm_vm_free(vm);
 }
-
-static void test_print_help(char *name)
-{
-	pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
-		name);
-	pr_info("\t-n: Number of vCPUs to configure (default: %u; max: %u)\n",
-		NR_VCPUS_DEF, KVM_MAX_VCPUS);
-	pr_info("\t-i: Number of iterations per stage (default: %u)\n",
-		NR_TEST_ITERS_DEF);
-	pr_info("\t-p: Periodicity (in ms) of the guest timer (default: %u)\n",
-		TIMER_TEST_PERIOD_MS_DEF);
-	pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n",
-		TIMER_TEST_MIGRATION_FREQ_MS);
-	pr_info("\t-o: Counter offset (in counter cycles, default: 0)\n");
-	pr_info("\t-h: print this help screen\n");
-}
-
-static bool parse_args(int argc, char *argv[])
-{
-	int opt;
-
-	while ((opt = getopt(argc, argv, "hn:i:p:m:o:")) != -1) {
-		switch (opt) {
-		case 'n':
-			test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg);
-			if (test_args.nr_vcpus > KVM_MAX_VCPUS) {
-				pr_info("Max allowed vCPUs: %u\n",
-					KVM_MAX_VCPUS);
-				goto err;
-			}
-			break;
-		case 'i':
-			test_args.nr_iter = atoi_positive("Number of iterations", optarg);
-			break;
-		case 'p':
-			test_args.timer_period_ms = atoi_positive("Periodicity", optarg);
-			break;
-		case 'm':
-			test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg);
-			break;
-		case 'o':
-			test_args.offset.counter_offset = strtol(optarg, NULL, 0);
-			test_args.offset.reserved = 0;
-			break;
-		case 'h':
-		default:
-			goto err;
-		}
-	}
-
-	return true;
-
-err:
-	test_print_help(argv[0]);
-	return false;
-}
-
-int main(int argc, char *argv[])
-{
-	struct kvm_vm *vm;
-
-	if (!parse_args(argc, argv))
-		exit(KSFT_SKIP);
-
-	__TEST_REQUIRE(!test_args.migration_freq_ms || get_nprocs() >= 2,
-		       "At least two physical CPUs needed for vCPU migration");
-
-	vm = test_vm_create();
-	test_run(vm);
-	test_vm_cleanup(vm);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index 8660029174..2582c49e52 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -365,7 +365,7 @@ static void guest_wp_handler(struct ex_regs *regs)
 
 static void guest_ss_handler(struct ex_regs *regs)
 {
-	__GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%u'", ss_idx);
+	__GUEST_ASSERT(ss_idx < 4, "Expected index < 4, got '%lu'", ss_idx);
 	ss_addr[ss_idx++] = regs->pc;
 	regs->pstate |= SPSR_SS;
 }
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index 27c10e7a7e..9d192ce007 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -105,12 +105,12 @@ static void guest_test_hvc(const struct test_hvc_info *hc_info)
 		case TEST_STAGE_HVC_IFACE_FEAT_DISABLED:
 		case TEST_STAGE_HVC_IFACE_FALSE_INFO:
 			__GUEST_ASSERT(res.a0 == SMCCC_RET_NOT_SUPPORTED,
-				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u",
 					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		case TEST_STAGE_HVC_IFACE_FEAT_ENABLED:
 			__GUEST_ASSERT(res.a0 != SMCCC_RET_NOT_SUPPORTED,
-				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%llx, stage = %u",
+				       "a0 = 0x%lx, func_id = 0x%x, arg1 = 0x%lx, stage = %u",
 					res.a0, hc_info->func_id, hc_info->arg1, stage);
 			break;
 		default:
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index 53fddad57c..5972905275 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -292,7 +292,7 @@ static void guest_code(struct test_desc *test)
 
 static void no_dabt_handler(struct ex_regs *regs)
 {
-	GUEST_FAIL("Unexpected dabt, far_el1 = 0x%llx", read_sysreg(far_el1));
+	GUEST_FAIL("Unexpected dabt, far_el1 = 0x%lx", read_sysreg(far_el1));
 }
 
 static void no_iabt_handler(struct ex_regs *regs)
diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
index bac05210b5..16e2338686 100644
--- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c
@@ -32,6 +32,10 @@ struct reg_ftr_bits {
 	enum ftr_type type;
 	uint8_t shift;
 	uint64_t mask;
+	/*
+	 * For FTR_EXACT, safe_val is used as the exact safe value.
+	 * For FTR_LOWER_SAFE, safe_val is used as the minimal safe value.
+	 */
 	int64_t safe_val;
 };
 
@@ -65,13 +69,13 @@ struct test_feature_reg {
 
 static const struct reg_ftr_bits ftr_id_aa64dfr0_el1[] = {
 	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, PMUVer, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, 0),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64DFR0_EL1, DebugVer, ID_AA64DFR0_EL1_DebugVer_IMP),
 	REG_FTR_END,
 };
 
 static const struct reg_ftr_bits ftr_id_dfr0_el1[] = {
-	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, 0),
+	S_REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, PerfMon, ID_DFR0_EL1_PerfMon_PMUv3),
+	REG_FTR_BITS(FTR_LOWER_SAFE, ID_DFR0_EL1, CopDbg, ID_DFR0_EL1_CopDbg_Armv8),
 	REG_FTR_END,
 };
 
@@ -224,13 +228,13 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 {
 	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
 
-	if (ftr_bits->type == FTR_UNSIGNED) {
+	if (ftr_bits->sign == FTR_UNSIGNED) {
 		switch (ftr_bits->type) {
 		case FTR_EXACT:
 			ftr = ftr_bits->safe_val;
 			break;
 		case FTR_LOWER_SAFE:
-			if (ftr > 0)
+			if (ftr > ftr_bits->safe_val)
 				ftr--;
 			break;
 		case FTR_HIGHER_SAFE:
@@ -252,7 +256,7 @@ uint64_t get_safe_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 			ftr = ftr_bits->safe_val;
 			break;
 		case FTR_LOWER_SAFE:
-			if (ftr > 0)
+			if (ftr > ftr_bits->safe_val)
 				ftr--;
 			break;
 		case FTR_HIGHER_SAFE:
@@ -276,7 +280,7 @@ uint64_t get_invalid_value(const struct reg_ftr_bits *ftr_bits, uint64_t ftr)
 {
 	uint64_t ftr_max = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
 
-	if (ftr_bits->type == FTR_UNSIGNED) {
+	if (ftr_bits->sign == FTR_UNSIGNED) {
 		switch (ftr_bits->type) {
 		case FTR_EXACT:
 			ftr = max((uint64_t)ftr_bits->safe_val + 1, ftr + 1);
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
index 5f97133646..f2fb0e3f14 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -93,22 +93,6 @@ static inline void write_sel_evtyper(int sel, unsigned long val)
 	isb();
 }
 
-static inline void enable_counter(int idx)
-{
-	uint64_t v = read_sysreg(pmcntenset_el0);
-
-	write_sysreg(BIT(idx) | v, pmcntenset_el0);
-	isb();
-}
-
-static inline void disable_counter(int idx)
-{
-	uint64_t v = read_sysreg(pmcntenset_el0);
-
-	write_sysreg(BIT(idx) | v, pmcntenclr_el0);
-	isb();
-}
-
 static void pmu_disable_reset(void)
 {
 	uint64_t pmcr = read_sysreg(pmcr_el0);
@@ -195,11 +179,11 @@ struct pmc_accessor pmc_accessors[] = {
 										 \
 	if (set_expected)							 \
 		__GUEST_ASSERT((_tval & mask),					 \
-				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: %u",	 \
 				_tval, mask, set_expected);			 \
 	else									 \
 		__GUEST_ASSERT(!(_tval & mask),					 \
-				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: %u",	 \
 				_tval, mask, set_expected);			 \
 }
 
@@ -286,7 +270,7 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
 	acc->write_typer(pmc_idx, write_data);
 	read_data = acc->read_typer(pmc_idx);
 	__GUEST_ASSERT(read_data == write_data,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
 
 	/*
@@ -297,14 +281,14 @@ static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
 
 	/* The count value must be 0, as it is disabled and reset */
 	__GUEST_ASSERT(read_data == 0,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data);
 
 	write_data = read_data + pmc_idx + 0x12345;
 	acc->write_cntr(pmc_idx, write_data);
 	read_data = acc->read_cntr(pmc_idx);
 	__GUEST_ASSERT(read_data == write_data,
-		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       "pmc_idx: 0x%x; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
 		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
 }
 
@@ -379,7 +363,7 @@ static void guest_code(uint64_t expected_pmcr_n)
 	int i, pmc;
 
 	__GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS,
-			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%lx",
+			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%x",
 			expected_pmcr_n, ARMV8_PMU_MAX_GENERAL_COUNTERS);
 
 	pmcr = read_sysreg(pmcr_el0);
diff --git a/tools/testing/selftests/kvm/arch_timer.c b/tools/testing/selftests/kvm/arch_timer.c
new file mode 100644
index 0000000000..ae1f1a6d83
--- /dev/null
+++ b/tools/testing/selftests/kvm/arch_timer.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arch_timer.c - Tests the arch timer IRQ functionality
+ *
+ * The guest's main thread configures the timer interrupt and waits
+ * for it to fire, with a timeout equal to the timer period.
+ * It asserts that the timeout doesn't exceed the timer period plus
+ * a user configurable error margin(default to 100us)
+ *
+ * On the other hand, upon receipt of an interrupt, the guest's interrupt
+ * handler validates the interrupt by checking if the architectural state
+ * is in compliance with the specifications.
+ *
+ * The test provides command-line options to configure the timer's
+ * period (-p), number of vCPUs (-n), iterations per stage (-i) and timer
+ * interrupt arrival error margin (-e). To stress-test the timer stack
+ * even more, an option to migrate the vCPUs across pCPUs (-m), at a
+ * particular rate, is also provided.
+ *
+ * Copyright (c) 2021, Google LLC.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <pthread.h>
+#include <linux/sizes.h>
+#include <linux/bitmap.h>
+#include <sys/sysinfo.h>
+
+#include "timer_test.h"
+
+struct test_args test_args = {
+	.nr_vcpus = NR_VCPUS_DEF,
+	.nr_iter = NR_TEST_ITERS_DEF,
+	.timer_period_ms = TIMER_TEST_PERIOD_MS_DEF,
+	.migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS,
+	.timer_err_margin_us = TIMER_TEST_ERR_MARGIN_US,
+	.reserved = 1,
+};
+
+struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
+struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS];
+
+static pthread_t pt_vcpu_run[KVM_MAX_VCPUS];
+static unsigned long *vcpu_done_map;
+static pthread_mutex_t vcpu_done_map_lock;
+
+static void *test_vcpu_run(void *arg)
+{
+	unsigned int vcpu_idx = (unsigned long)arg;
+	struct ucall uc;
+	struct kvm_vcpu *vcpu = vcpus[vcpu_idx];
+	struct kvm_vm *vm = vcpu->vm;
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpu_idx];
+
+	vcpu_run(vcpu);
+
+	/* Currently, any exit from guest is an indication of completion */
+	pthread_mutex_lock(&vcpu_done_map_lock);
+	__set_bit(vcpu_idx, vcpu_done_map);
+	pthread_mutex_unlock(&vcpu_done_map_lock);
+
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_SYNC:
+	case UCALL_DONE:
+		break;
+	case UCALL_ABORT:
+		sync_global_from_guest(vm, *shared_data);
+		fprintf(stderr, "Guest assert failed,  vcpu %u; stage; %u; iter: %u\n",
+			vcpu_idx, shared_data->guest_stage, shared_data->nr_iter);
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	default:
+		TEST_FAIL("Unexpected guest exit");
+	}
+
+	pr_info("PASS(vCPU-%d).\n", vcpu_idx);
+
+	return NULL;
+}
+
+static uint32_t test_get_pcpu(void)
+{
+	uint32_t pcpu;
+	unsigned int nproc_conf;
+	cpu_set_t online_cpuset;
+
+	nproc_conf = get_nprocs_conf();
+	sched_getaffinity(0, sizeof(cpu_set_t), &online_cpuset);
+
+	/* Randomly find an available pCPU to place a vCPU on */
+	do {
+		pcpu = rand() % nproc_conf;
+	} while (!CPU_ISSET(pcpu, &online_cpuset));
+
+	return pcpu;
+}
+
+static int test_migrate_vcpu(unsigned int vcpu_idx)
+{
+	int ret;
+	cpu_set_t cpuset;
+	uint32_t new_pcpu = test_get_pcpu();
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(new_pcpu, &cpuset);
+
+	pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu_idx, new_pcpu);
+
+	ret = pthread_setaffinity_np(pt_vcpu_run[vcpu_idx],
+				     sizeof(cpuset), &cpuset);
+
+	/* Allow the error where the vCPU thread is already finished */
+	TEST_ASSERT(ret == 0 || ret == ESRCH,
+		    "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d",
+		    vcpu_idx, new_pcpu, ret);
+
+	return ret;
+}
+
+static void *test_vcpu_migration(void *arg)
+{
+	unsigned int i, n_done;
+	bool vcpu_done;
+
+	do {
+		usleep(msecs_to_usecs(test_args.migration_freq_ms));
+
+		for (n_done = 0, i = 0; i < test_args.nr_vcpus; i++) {
+			pthread_mutex_lock(&vcpu_done_map_lock);
+			vcpu_done = test_bit(i, vcpu_done_map);
+			pthread_mutex_unlock(&vcpu_done_map_lock);
+
+			if (vcpu_done) {
+				n_done++;
+				continue;
+			}
+
+			test_migrate_vcpu(i);
+		}
+	} while (test_args.nr_vcpus != n_done);
+
+	return NULL;
+}
+
+static void test_run(struct kvm_vm *vm)
+{
+	pthread_t pt_vcpu_migration;
+	unsigned int i;
+	int ret;
+
+	pthread_mutex_init(&vcpu_done_map_lock, NULL);
+	vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
+	TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap");
+
+	for (i = 0; i < (unsigned long)test_args.nr_vcpus; i++) {
+		ret = pthread_create(&pt_vcpu_run[i], NULL, test_vcpu_run,
+				     (void *)(unsigned long)i);
+		TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread", i);
+	}
+
+	/* Spawn a thread to control the vCPU migrations */
+	if (test_args.migration_freq_ms) {
+		srand(time(NULL));
+
+		ret = pthread_create(&pt_vcpu_migration, NULL,
+					test_vcpu_migration, NULL);
+		TEST_ASSERT(!ret, "Failed to create the migration pthread");
+	}
+
+
+	for (i = 0; i < test_args.nr_vcpus; i++)
+		pthread_join(pt_vcpu_run[i], NULL);
+
+	if (test_args.migration_freq_ms)
+		pthread_join(pt_vcpu_migration, NULL);
+
+	bitmap_free(vcpu_done_map);
+}
+
+static void test_print_help(char *name)
+{
+	pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n"
+		"\t\t    [-m migration_freq_ms] [-o counter_offset]\n"
+		"\t\t    [-e timer_err_margin_us]\n", name);
+	pr_info("\t-n: Number of vCPUs to configure (default: %u; max: %u)\n",
+		NR_VCPUS_DEF, KVM_MAX_VCPUS);
+	pr_info("\t-i: Number of iterations per stage (default: %u)\n",
+		NR_TEST_ITERS_DEF);
+	pr_info("\t-p: Periodicity (in ms) of the guest timer (default: %u)\n",
+		TIMER_TEST_PERIOD_MS_DEF);
+	pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n",
+		TIMER_TEST_MIGRATION_FREQ_MS);
+	pr_info("\t-o: Counter offset (in counter cycles, default: 0) [aarch64-only]\n");
+	pr_info("\t-e: Interrupt arrival error margin (in us) of the guest timer (default: %u)\n",
+		TIMER_TEST_ERR_MARGIN_US);
+	pr_info("\t-h: print this help screen\n");
+}
+
+static bool parse_args(int argc, char *argv[])
+{
+	int opt;
+
+	while ((opt = getopt(argc, argv, "hn:i:p:m:o:e:")) != -1) {
+		switch (opt) {
+		case 'n':
+			test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+			if (test_args.nr_vcpus > KVM_MAX_VCPUS) {
+				pr_info("Max allowed vCPUs: %u\n",
+					KVM_MAX_VCPUS);
+				goto err;
+			}
+			break;
+		case 'i':
+			test_args.nr_iter = atoi_positive("Number of iterations", optarg);
+			break;
+		case 'p':
+			test_args.timer_period_ms = atoi_positive("Periodicity", optarg);
+			break;
+		case 'm':
+			test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg);
+			break;
+		case 'e':
+			test_args.timer_err_margin_us = atoi_non_negative("Error Margin", optarg);
+			break;
+		case 'o':
+			test_args.counter_offset = strtol(optarg, NULL, 0);
+			test_args.reserved = 0;
+			break;
+		case 'h':
+		default:
+			goto err;
+		}
+	}
+
+	return true;
+
+err:
+	test_print_help(argv[0]);
+	return false;
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+
+	if (!parse_args(argc, argv))
+		exit(KSFT_SKIP);
+
+	__TEST_REQUIRE(!test_args.migration_freq_ms || get_nprocs() >= 2,
+		       "At least two physical CPUs needed for vCPU migration");
+
+	vm = test_vm_create();
+	test_run(vm);
+	test_vm_cleanup(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/guest_memfd_test.c b/tools/testing/selftests/kvm/guest_memfd_test.c
index c78a98c1a9..92eae206ba 100644
--- a/tools/testing/selftests/kvm/guest_memfd_test.c
+++ b/tools/testing/selftests/kvm/guest_memfd_test.c
@@ -167,6 +167,9 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
 	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
 	TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size");
 	TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers");
+
+	close(fd2);
+	close(fd1);
 }
 
 int main(int argc, char *argv[])
diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h
new file mode 100644
index 0000000000..e43a57d99b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index cf20e44e86..9e518b5628 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -226,8 +226,4 @@ void smccc_smc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
 	       uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
 	       uint64_t arg6, struct arm_smccc_res *res);
 
-
-
-uint32_t guest_get_vcpuid(void);
-
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_test_harness.h b/tools/testing/selftests/kvm/include/kvm_test_harness.h
new file mode 100644
index 0000000000..8f7c6858e8
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_test_harness.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Macros for defining a KVM test
+ *
+ * Copyright (C) 2022, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_TEST_HARNESS_H
+#define SELFTEST_KVM_TEST_HARNESS_H
+
+#include "kselftest_harness.h"
+
+#define KVM_ONE_VCPU_TEST_SUITE(name)					\
+	FIXTURE(name) {							\
+		struct kvm_vcpu *vcpu;					\
+	};								\
+									\
+	FIXTURE_SETUP(name) {						\
+		(void)vm_create_with_one_vcpu(&self->vcpu, NULL);	\
+	}								\
+									\
+	FIXTURE_TEARDOWN(name) {					\
+		kvm_vm_free(self->vcpu->vm);				\
+	}
+
+#define KVM_ONE_VCPU_TEST(suite, test, guestcode)			\
+static void __suite##_##test(struct kvm_vcpu *vcpu);			\
+									\
+TEST_F(suite, test)							\
+{									\
+	vcpu_arch_set_entry_point(self->vcpu, guestcode);		\
+	__suite##_##test(self->vcpu);					\
+}									\
+static void __suite##_##test(struct kvm_vcpu *vcpu)
+
+#endif /* SELFTEST_KVM_TEST_HARNESS_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 9e5afc472c..3e0db283a4 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -18,9 +18,11 @@
 #include <linux/types.h>
 
 #include <asm/atomic.h>
+#include <asm/kvm.h>
 
 #include <sys/ioctl.h>
 
+#include "kvm_util_arch.h"
 #include "sparsebit.h"
 
 /*
@@ -46,6 +48,7 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 struct userspace_mem_region {
 	struct kvm_userspace_memory_region2 region;
 	struct sparsebit *unused_phy_pages;
+	struct sparsebit *protected_phy_pages;
 	int fd;
 	off_t offset;
 	enum vm_mem_backing_src_type backing_src_type;
@@ -90,6 +93,7 @@ enum kvm_mem_region_type {
 struct kvm_vm {
 	int mode;
 	unsigned long type;
+	uint8_t subtype;
 	int kvm_fd;
 	int fd;
 	unsigned int pgtable_levels;
@@ -111,6 +115,9 @@ struct kvm_vm {
 	vm_vaddr_t idt;
 	vm_vaddr_t handlers;
 	uint32_t dirty_ring_size;
+	uint64_t gpa_tag_mask;
+
+	struct kvm_vm_arch arch;
 
 	/* Cache of information for binary stats interface */
 	int stats_fd;
@@ -191,10 +198,14 @@ enum vm_guest_mode {
 };
 
 struct vm_shape {
-	enum vm_guest_mode mode;
-	unsigned int type;
+	uint32_t type;
+	uint8_t  mode;
+	uint8_t  subtype;
+	uint16_t padding;
 };
 
+kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t));
+
 #define VM_TYPE_DEFAULT			0
 
 #define VM_SHAPE(__mode)			\
@@ -259,6 +270,10 @@ bool get_kvm_param_bool(const char *param);
 bool get_kvm_intel_param_bool(const char *param);
 bool get_kvm_amd_param_bool(const char *param);
 
+int get_kvm_param_integer(const char *param);
+int get_kvm_intel_param_integer(const char *param);
+int get_kvm_amd_param_integer(const char *param);
+
 unsigned int kvm_check_cap(long cap);
 
 static inline bool kvm_has_cap(long cap)
@@ -564,6 +579,13 @@ 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);
 
+#ifndef vm_arch_has_protected_memory
+static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
+{
+	return false;
+}
+#endif
+
 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);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
@@ -573,6 +595,9 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_mi
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
 vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 			    enum kvm_mem_region_type type);
+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);
 vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
 vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm,
 				 enum kvm_mem_region_type type);
@@ -585,6 +610,12 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
 void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
 
+
+static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	return gpa & ~vm->gpa_tag_mask;
+}
+
 void vcpu_run(struct kvm_vcpu *vcpu);
 int _vcpu_run(struct kvm_vcpu *vcpu);
 
@@ -827,10 +858,23 @@ const char *exit_reason_str(unsigned int exit_reason);
 
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, 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);
+vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+				vm_paddr_t paddr_min, uint32_t memslot,
+				bool protected);
 vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
 
+static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+					    vm_paddr_t paddr_min, uint32_t memslot)
+{
+	/*
+	 * By default, allocate memory as protected for VMs that support
+	 * protected memory, as the majority of memory for such VMs is
+	 * protected, i.e. using shared memory is effectively opt-in.
+	 */
+	return __vm_phy_pages_alloc(vm, num, paddr_min, memslot,
+				    vm_arch_has_protected_memory(vm));
+}
+
 /*
  * ____vm_create() does KVM_CREATE_VM and little else.  __vm_create() also
  * loads the test binary into guest memory and creates an IRQ chip (x86 only).
@@ -969,15 +1013,18 @@ static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu,
  * Input Args:
  *   vm - Virtual Machine
  *   vcpu_id - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
  */
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code);
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code);
 
 static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 					   void *guest_code)
 {
-	return vm_arch_vcpu_add(vm, vcpu_id, guest_code);
+	struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id);
+
+	vcpu_arch_set_entry_point(vcpu, guest_code);
+
+	return vcpu;
 }
 
 /* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */
@@ -1081,4 +1128,8 @@ void kvm_selftest_arch_init(void);
 
 void kvm_arch_vm_post_create(struct kvm_vm *vm);
 
+bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr);
+
+uint32_t guest_get_vcpuid(void);
+
 #endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/arch_timer.h b/tools/testing/selftests/kvm/include/riscv/arch_timer.h
new file mode 100644
index 0000000000..225d81dad0
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/arch_timer.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * RISC-V Arch Timer(sstc) specific interface
+ *
+ * Copyright (c) 2024 Intel Corporation
+ */
+
+#ifndef SELFTEST_KVM_ARCH_TIMER_H
+#define SELFTEST_KVM_ARCH_TIMER_H
+
+#include <asm/csr.h>
+#include <asm/vdso/processor.h>
+
+static unsigned long timer_freq;
+
+#define msec_to_cycles(msec)	\
+	((timer_freq) * (uint64_t)(msec) / 1000)
+
+#define usec_to_cycles(usec)	\
+	((timer_freq) * (uint64_t)(usec) / 1000000)
+
+#define cycles_to_usec(cycles) \
+	((uint64_t)(cycles) * 1000000 / (timer_freq))
+
+static inline uint64_t timer_get_cycles(void)
+{
+	return csr_read(CSR_TIME);
+}
+
+static inline void timer_set_cmp(uint64_t cval)
+{
+	csr_write(CSR_STIMECMP, cval);
+}
+
+static inline uint64_t timer_get_cmp(void)
+{
+	return csr_read(CSR_STIMECMP);
+}
+
+static inline void timer_irq_enable(void)
+{
+	csr_set(CSR_SIE, IE_TIE);
+}
+
+static inline void timer_irq_disable(void)
+{
+	csr_clear(CSR_SIE, IE_TIE);
+}
+
+static inline void timer_set_next_cmp_ms(uint32_t msec)
+{
+	uint64_t now_ct = timer_get_cycles();
+	uint64_t next_ct = now_ct + msec_to_cycles(msec);
+
+	timer_set_cmp(next_ct);
+}
+
+static inline void __delay(uint64_t cycles)
+{
+	uint64_t start = timer_get_cycles();
+
+	while ((timer_get_cycles() - start) < cycles)
+		cpu_relax();
+}
+
+static inline void udelay(unsigned long usec)
+{
+	__delay(usec_to_cycles(usec));
+}
+
+#endif /* SELFTEST_KVM_ARCH_TIMER_H */
diff --git a/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h
new file mode 100644
index 0000000000..e43a57d99b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index a0f9efe5a2..ce473fe251 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -7,8 +7,9 @@
 #ifndef SELFTEST_KVM_PROCESSOR_H
 #define SELFTEST_KVM_PROCESSOR_H
 
-#include "kvm_util.h"
 #include <linux/stringify.h>
+#include <asm/csr.h>
+#include "kvm_util.h"
 
 static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 				    uint64_t idx, uint64_t size)
@@ -47,6 +48,58 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 						     KVM_REG_RISCV_SBI_SINGLE,		\
 						     idx, KVM_REG_SIZE_ULONG)
 
+bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext);
+
+struct ex_regs {
+	unsigned long ra;
+	unsigned long sp;
+	unsigned long gp;
+	unsigned long tp;
+	unsigned long t0;
+	unsigned long t1;
+	unsigned long t2;
+	unsigned long s0;
+	unsigned long s1;
+	unsigned long a0;
+	unsigned long a1;
+	unsigned long a2;
+	unsigned long a3;
+	unsigned long a4;
+	unsigned long a5;
+	unsigned long a6;
+	unsigned long a7;
+	unsigned long s2;
+	unsigned long s3;
+	unsigned long s4;
+	unsigned long s5;
+	unsigned long s6;
+	unsigned long s7;
+	unsigned long s8;
+	unsigned long s9;
+	unsigned long s10;
+	unsigned long s11;
+	unsigned long t3;
+	unsigned long t4;
+	unsigned long t5;
+	unsigned long t6;
+	unsigned long epc;
+	unsigned long status;
+	unsigned long cause;
+};
+
+#define NR_VECTORS  2
+#define NR_EXCEPTIONS  32
+#define EC_MASK  (NR_EXCEPTIONS - 1)
+
+typedef void(*exception_handler_fn)(struct ex_regs *);
+
+void vm_init_vector_tables(struct kvm_vm *vm);
+void vcpu_init_vector_tables(struct kvm_vcpu *vcpu);
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler);
+
+void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handler);
+
 /* L3 index Bit[47:39] */
 #define PGTBL_L3_INDEX_MASK			0x0000FF8000000000ULL
 #define PGTBL_L3_INDEX_SHIFT			39
@@ -101,13 +154,6 @@ static inline uint64_t __kvm_reg_id(uint64_t type, uint64_t subtype,
 #define PGTBL_PAGE_SIZE				PGTBL_L0_BLOCK_SIZE
 #define PGTBL_PAGE_SIZE_SHIFT			PGTBL_L0_BLOCK_SHIFT
 
-#define SATP_PPN				_AC(0x00000FFFFFFFFFFF, UL)
-#define SATP_MODE_39				_AC(0x8000000000000000, UL)
-#define SATP_MODE_48				_AC(0x9000000000000000, UL)
-#define SATP_ASID_BITS				16
-#define SATP_ASID_SHIFT				44
-#define SATP_ASID_MASK				_AC(0xFFFF, UL)
-
 /* SBI return error codes */
 #define SBI_SUCCESS				0
 #define SBI_ERR_FAILURE				-1
@@ -147,4 +193,14 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
 
 bool guest_sbi_probe_extension(int extid, long *out_val);
 
+static inline void local_irq_enable(void)
+{
+	csr_set(CSR_SSTATUS, SR_SIE);
+}
+
+static inline void local_irq_disable(void)
+{
+	csr_clear(CSR_SSTATUS, SR_SIE);
+}
+
 #endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h
new file mode 100644
index 0000000000..e43a57d99b
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
index 12a9a4b9ce..bc760761e1 100644
--- a/tools/testing/selftests/kvm/include/sparsebit.h
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -30,26 +30,26 @@ typedef uint64_t sparsebit_num_t;
 
 struct sparsebit *sparsebit_alloc(void);
 void sparsebit_free(struct sparsebit **sbitp);
-void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src);
+void sparsebit_copy(struct sparsebit *dstp, const struct sparsebit *src);
 
-bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx);
-bool sparsebit_is_set_num(struct sparsebit *sbit,
+bool sparsebit_is_set(const struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_set_num(const struct sparsebit *sbit,
 			  sparsebit_idx_t idx, sparsebit_num_t num);
-bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx);
-bool sparsebit_is_clear_num(struct sparsebit *sbit,
+bool sparsebit_is_clear(const struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_clear_num(const struct sparsebit *sbit,
 			    sparsebit_idx_t idx, sparsebit_num_t num);
-sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit);
-bool sparsebit_any_set(struct sparsebit *sbit);
-bool sparsebit_any_clear(struct sparsebit *sbit);
-bool sparsebit_all_set(struct sparsebit *sbit);
-bool sparsebit_all_clear(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev);
-sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev);
-sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit,
+sparsebit_num_t sparsebit_num_set(const struct sparsebit *sbit);
+bool sparsebit_any_set(const struct sparsebit *sbit);
+bool sparsebit_any_clear(const struct sparsebit *sbit);
+bool sparsebit_all_set(const struct sparsebit *sbit);
+bool sparsebit_all_clear(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_set(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_next_set(const struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *sbit,
 				       sparsebit_idx_t start, sparsebit_num_t num);
-sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit,
+sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *sbit,
 					 sparsebit_idx_t start, sparsebit_num_t num);
 
 void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx);
@@ -62,9 +62,29 @@ void sparsebit_clear_num(struct sparsebit *sbitp,
 			 sparsebit_idx_t start, sparsebit_num_t num);
 void sparsebit_clear_all(struct sparsebit *sbitp);
 
-void sparsebit_dump(FILE *stream, struct sparsebit *sbit,
+void sparsebit_dump(FILE *stream, const struct sparsebit *sbit,
 		    unsigned int indent);
-void sparsebit_validate_internal(struct sparsebit *sbit);
+void sparsebit_validate_internal(const struct sparsebit *sbit);
+
+/*
+ * Iterate over an inclusive ranges within sparsebit @s. In each iteration,
+ * @range_begin and @range_end will take the beginning and end of the set
+ * range, which are of type sparsebit_idx_t.
+ *
+ * For example, if the range [3, 7] (inclusive) is set, within the
+ * iteration,@range_begin will take the value 3 and @range_end will take
+ * the value 7.
+ *
+ * Ensure that there is at least one bit set before using this macro with
+ * sparsebit_any_set(), because sparsebit_first_set() will abort if none
+ * are set.
+ */
+#define sparsebit_for_each_set_range(s, range_begin, range_end)         \
+	for (range_begin = sparsebit_first_set(s),                      \
+	     range_end = sparsebit_next_clear(s, range_begin) - 1;	\
+	     range_begin && range_end;                                  \
+	     range_begin = sparsebit_next_set(s, range_end),            \
+	     range_end = sparsebit_next_clear(s, range_begin) - 1)
 
 #ifdef __cplusplus
 }
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 50a5e31ba8..8a6e30612c 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -20,6 +20,8 @@
 #include <sys/mman.h>
 #include "kselftest.h"
 
+#define msecs_to_usecs(msec)    ((msec) * 1000ULL)
+
 static inline int _no_printf(const char *format, ...) { return 0; }
 
 #ifdef DEBUG
diff --git a/tools/testing/selftests/kvm/include/timer_test.h b/tools/testing/selftests/kvm/include/timer_test.h
new file mode 100644
index 0000000000..9b6edaafe6
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/timer_test.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * timer test specific header
+ *
+ * Copyright (C) 2018, Google LLC
+ */
+
+#ifndef SELFTEST_KVM_TIMER_TEST_H
+#define SELFTEST_KVM_TIMER_TEST_H
+
+#include "kvm_util.h"
+
+#define NR_VCPUS_DEF            4
+#define NR_TEST_ITERS_DEF       5
+#define TIMER_TEST_PERIOD_MS_DEF    10
+#define TIMER_TEST_ERR_MARGIN_US    100
+#define TIMER_TEST_MIGRATION_FREQ_MS    2
+
+/* Timer test cmdline parameters */
+struct test_args {
+	uint32_t nr_vcpus;
+	uint32_t nr_iter;
+	uint32_t timer_period_ms;
+	uint32_t migration_freq_ms;
+	uint32_t timer_err_margin_us;
+	/* Members of struct kvm_arm_counter_offset */
+	uint64_t counter_offset;
+	uint64_t reserved;
+};
+
+/* Shared variables between host and guest */
+struct test_vcpu_shared_data {
+	uint32_t nr_iter;
+	int guest_stage;
+	uint64_t xcnt;
+};
+
+extern struct test_args test_args;
+extern struct kvm_vcpu *vcpus[];
+extern struct test_vcpu_shared_data vcpu_shared_data[];
+
+struct kvm_vm *test_vm_create(void);
+void test_vm_cleanup(struct kvm_vm *vm);
+
+#endif /* SELFTEST_KVM_TIMER_TEST_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h
new file mode 100644
index 0000000000..9f1725192a
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+#include <stdbool.h>
+#include <stdint.h>
+
+struct kvm_vm_arch {
+	uint64_t c_bit;
+	uint64_t s_bit;
+	int sev_fd;
+	bool is_pt_protected;
+};
+
+static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch)
+{
+	return arch->c_bit || arch->s_bit;
+}
+
+#define vm_arch_has_protected_memory(vm) \
+	__vm_arch_has_protected_memory(&(vm)->arch)
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H
diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86_64/pmu.h
new file mode 100644
index 0000000000..3c10c4dc0a
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/pmu.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023, Tencent, Inc.
+ */
+#ifndef SELFTEST_KVM_PMU_H
+#define SELFTEST_KVM_PMU_H
+
+#include <stdint.h>
+
+#define KVM_PMU_EVENT_FILTER_MAX_EVENTS			300
+
+/*
+ * Encode an eventsel+umask pair into event-select MSR format.  Note, this is
+ * technically AMD's format, as Intel's format only supports 8 bits for the
+ * event selector, i.e. doesn't use bits 24:16 for the selector.  But, OR-ing
+ * in '0' is a nop and won't clobber the CMASK.
+ */
+#define RAW_EVENT(eventsel, umask) (((eventsel & 0xf00UL) << 24) |	\
+				    ((eventsel) & 0xff) |		\
+				    ((umask) & 0xff) << 8)
+
+/*
+ * These are technically Intel's definitions, but except for CMASK (see above),
+ * AMD's layout is compatible with Intel's.
+ */
+#define ARCH_PERFMON_EVENTSEL_EVENT		GENMASK_ULL(7, 0)
+#define ARCH_PERFMON_EVENTSEL_UMASK		GENMASK_ULL(15, 8)
+#define ARCH_PERFMON_EVENTSEL_USR		BIT_ULL(16)
+#define ARCH_PERFMON_EVENTSEL_OS		BIT_ULL(17)
+#define ARCH_PERFMON_EVENTSEL_EDGE		BIT_ULL(18)
+#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL	BIT_ULL(19)
+#define ARCH_PERFMON_EVENTSEL_INT		BIT_ULL(20)
+#define ARCH_PERFMON_EVENTSEL_ANY		BIT_ULL(21)
+#define ARCH_PERFMON_EVENTSEL_ENABLE		BIT_ULL(22)
+#define ARCH_PERFMON_EVENTSEL_INV		BIT_ULL(23)
+#define ARCH_PERFMON_EVENTSEL_CMASK		GENMASK_ULL(31, 24)
+
+/* RDPMC control flags, Intel only. */
+#define INTEL_RDPMC_METRICS			BIT_ULL(29)
+#define INTEL_RDPMC_FIXED			BIT_ULL(30)
+#define INTEL_RDPMC_FAST			BIT_ULL(31)
+
+/* Fixed PMC controls, Intel only. */
+#define FIXED_PMC_GLOBAL_CTRL_ENABLE(_idx)	BIT_ULL((32 + (_idx)))
+
+#define FIXED_PMC_KERNEL			BIT_ULL(0)
+#define FIXED_PMC_USER				BIT_ULL(1)
+#define FIXED_PMC_ANYTHREAD			BIT_ULL(2)
+#define FIXED_PMC_ENABLE_PMI			BIT_ULL(3)
+#define FIXED_PMC_NR_BITS			4
+#define FIXED_PMC_CTRL(_idx, _val)		((_val) << ((_idx) * FIXED_PMC_NR_BITS))
+
+#define PMU_CAP_FW_WRITES			BIT_ULL(13)
+#define PMU_CAP_LBR_FMT				0x3f
+
+#define	INTEL_ARCH_CPU_CYCLES			RAW_EVENT(0x3c, 0x00)
+#define	INTEL_ARCH_INSTRUCTIONS_RETIRED		RAW_EVENT(0xc0, 0x00)
+#define	INTEL_ARCH_REFERENCE_CYCLES		RAW_EVENT(0x3c, 0x01)
+#define	INTEL_ARCH_LLC_REFERENCES		RAW_EVENT(0x2e, 0x4f)
+#define	INTEL_ARCH_LLC_MISSES			RAW_EVENT(0x2e, 0x41)
+#define	INTEL_ARCH_BRANCHES_RETIRED		RAW_EVENT(0xc4, 0x00)
+#define	INTEL_ARCH_BRANCHES_MISPREDICTED	RAW_EVENT(0xc5, 0x00)
+#define	INTEL_ARCH_TOPDOWN_SLOTS		RAW_EVENT(0xa4, 0x01)
+
+#define	AMD_ZEN_CORE_CYCLES			RAW_EVENT(0x76, 0x00)
+#define	AMD_ZEN_INSTRUCTIONS_RETIRED		RAW_EVENT(0xc0, 0x00)
+#define	AMD_ZEN_BRANCHES_RETIRED		RAW_EVENT(0xc2, 0x00)
+#define	AMD_ZEN_BRANCHES_MISPREDICTED		RAW_EVENT(0xc3, 0x00)
+
+/*
+ * Note!  The order and thus the index of the architectural events matters as
+ * support for each event is enumerated via CPUID using the index of the event.
+ */
+enum intel_pmu_architectural_events {
+	INTEL_ARCH_CPU_CYCLES_INDEX,
+	INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX,
+	INTEL_ARCH_REFERENCE_CYCLES_INDEX,
+	INTEL_ARCH_LLC_REFERENCES_INDEX,
+	INTEL_ARCH_LLC_MISSES_INDEX,
+	INTEL_ARCH_BRANCHES_RETIRED_INDEX,
+	INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX,
+	INTEL_ARCH_TOPDOWN_SLOTS_INDEX,
+	NR_INTEL_ARCH_EVENTS,
+};
+
+enum amd_pmu_zen_events {
+	AMD_ZEN_CORE_CYCLES_INDEX,
+	AMD_ZEN_INSTRUCTIONS_INDEX,
+	AMD_ZEN_BRANCHES_INDEX,
+	AMD_ZEN_BRANCH_MISSES_INDEX,
+	NR_AMD_ZEN_EVENTS,
+};
+
+extern const uint64_t intel_pmu_arch_events[];
+extern const uint64_t amd_pmu_zen_events[];
+
+#endif /* SELFTEST_KVM_PMU_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 5bca8c947c..81ce37ec40 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -23,6 +23,15 @@
 extern bool host_cpu_is_intel;
 extern bool host_cpu_is_amd;
 
+enum vm_guest_x86_subtype {
+	VM_SUBTYPE_NONE = 0,
+	VM_SUBTYPE_SEV,
+	VM_SUBTYPE_SEV_ES,
+};
+
+/* Forced emulation prefix, used to invoke the emulator unconditionally. */
+#define KVM_FEP "ud2; .byte 'k', 'v', 'm';"
+
 #define NMI_VECTOR		0x02
 
 #define X86_EFLAGS_FIXED	 (1u << 1)
@@ -273,6 +282,7 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_MAX_EXT_LEAF		KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31)
 #define X86_PROPERTY_MAX_PHY_ADDR		KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7)
 #define X86_PROPERTY_MAX_VIRT_ADDR		KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15)
+#define X86_PROPERTY_SEV_C_BIT			KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5)
 #define X86_PROPERTY_PHYS_ADDR_REDUCTION	KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11)
 
 #define X86_PROPERTY_MAX_CENTAUR_LEAF		KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31)
@@ -282,24 +292,41 @@ struct kvm_x86_cpu_property {
  * that indicates the feature is _not_ supported, and a property that states
  * the length of the bit mask of unsupported features.  A feature is supported
  * if the size of the bit mask is larger than the "unavailable" bit, and said
- * bit is not set.
+ * bit is not set.  Fixed counters also bizarre enumeration, but inverted from
+ * arch events for general purpose counters.  Fixed counters are supported if a
+ * feature flag is set **OR** the total number of fixed counters is greater
+ * than index of the counter.
  *
- * Wrap the "unavailable" feature to simplify checking whether or not a given
- * architectural event is supported.
+ * Wrap the events for general purpose and fixed counters to simplify checking
+ * whether or not a given architectural event is supported.
  */
 struct kvm_x86_pmu_feature {
-	struct kvm_x86_cpu_feature anti_feature;
+	struct kvm_x86_cpu_feature f;
 };
-#define	KVM_X86_PMU_FEATURE(name, __bit)					\
-({										\
-	struct kvm_x86_pmu_feature feature = {					\
-		.anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit),	\
-	};									\
-										\
-	feature;								\
+#define	KVM_X86_PMU_FEATURE(__reg, __bit)				\
+({									\
+	struct kvm_x86_pmu_feature feature = {				\
+		.f = KVM_X86_CPU_FEATURE(0xa, 0, __reg, __bit),		\
+	};								\
+									\
+	kvm_static_assert(KVM_CPUID_##__reg == KVM_CPUID_EBX ||		\
+			  KVM_CPUID_##__reg == KVM_CPUID_ECX);		\
+	feature;							\
 })
 
-#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED	KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5)
+#define X86_PMU_FEATURE_CPU_CYCLES			KVM_X86_PMU_FEATURE(EBX, 0)
+#define X86_PMU_FEATURE_INSNS_RETIRED			KVM_X86_PMU_FEATURE(EBX, 1)
+#define X86_PMU_FEATURE_REFERENCE_CYCLES		KVM_X86_PMU_FEATURE(EBX, 2)
+#define X86_PMU_FEATURE_LLC_REFERENCES			KVM_X86_PMU_FEATURE(EBX, 3)
+#define X86_PMU_FEATURE_LLC_MISSES			KVM_X86_PMU_FEATURE(EBX, 4)
+#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED		KVM_X86_PMU_FEATURE(EBX, 5)
+#define X86_PMU_FEATURE_BRANCHES_MISPREDICTED		KVM_X86_PMU_FEATURE(EBX, 6)
+#define X86_PMU_FEATURE_TOPDOWN_SLOTS			KVM_X86_PMU_FEATURE(EBX, 7)
+
+#define X86_PMU_FEATURE_INSNS_RETIRED_FIXED		KVM_X86_PMU_FEATURE(ECX, 0)
+#define X86_PMU_FEATURE_CPU_CYCLES_FIXED		KVM_X86_PMU_FEATURE(ECX, 1)
+#define X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED	KVM_X86_PMU_FEATURE(ECX, 2)
+#define X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED		KVM_X86_PMU_FEATURE(ECX, 3)
 
 static inline unsigned int x86_family(unsigned int eax)
 {
@@ -698,10 +725,16 @@ static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property)
 
 static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature)
 {
-	uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+	uint32_t nr_bits;
 
-	return nr_bits > feature.anti_feature.bit &&
-	       !this_cpu_has(feature.anti_feature);
+	if (feature.f.reg == KVM_CPUID_EBX) {
+		nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+		return nr_bits > feature.f.bit && !this_cpu_has(feature.f);
+	}
+
+	GUEST_ASSERT(feature.f.reg == KVM_CPUID_ECX);
+	nr_bits = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+	return nr_bits > feature.f.bit || this_cpu_has(feature.f);
 }
 
 static __always_inline uint64_t this_cpu_supported_xcr0(void)
@@ -917,10 +950,16 @@ static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property)
 
 static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature)
 {
-	uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+	uint32_t nr_bits;
+
+	if (feature.f.reg == KVM_CPUID_EBX) {
+		nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+		return nr_bits > feature.f.bit && !kvm_cpu_has(feature.f);
+	}
 
-	return nr_bits > feature.anti_feature.bit &&
-	       !kvm_cpu_has(feature.anti_feature);
+	TEST_ASSERT_EQ(feature.f.reg, KVM_CPUID_ECX);
+	nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+	return nr_bits > feature.f.bit || kvm_cpu_has(feature.f);
 }
 
 static __always_inline uint64_t kvm_cpu_supported_xcr0(void)
@@ -995,9 +1034,22 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu)
 	vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid);
 }
 
+void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu,
+			     struct kvm_x86_cpu_property property,
+			     uint32_t value);
 void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr);
 
 void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function);
+
+static inline bool vcpu_cpuid_has(struct kvm_vcpu *vcpu,
+				  struct kvm_x86_cpu_feature feature)
+{
+	struct kvm_cpuid_entry2 *entry;
+
+	entry = __vcpu_get_cpuid_entry(vcpu, feature.function, feature.index);
+	return *((&entry->eax) + feature.reg) & BIT(feature.bit);
+}
+
 void vcpu_set_or_clear_cpuid_feature(struct kvm_vcpu *vcpu,
 				     struct kvm_x86_cpu_feature feature,
 				     bool set);
@@ -1059,6 +1111,7 @@ do {											\
 } while (0)
 
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
+void kvm_init_vm_address_properties(struct kvm_vm *vm);
 bool vm_is_unrestricted_guest(struct kvm_vm *vm);
 
 struct ex_regs {
@@ -1120,16 +1173,19 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
  * r9  = exception vector (non-zero)
  * r10 = error code
  */
-#define KVM_ASM_SAFE(insn)					\
+#define __KVM_ASM_SAFE(insn, fep)				\
 	"mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t"	\
 	"lea 1f(%%rip), %%r10\n\t"				\
 	"lea 2f(%%rip), %%r11\n\t"				\
-	"1: " insn "\n\t"					\
+	fep "1: " insn "\n\t"					\
 	"xor %%r9, %%r9\n\t"					\
 	"2:\n\t"						\
 	"mov  %%r9b, %[vector]\n\t"				\
 	"mov  %%r10, %[error_code]\n\t"
 
+#define KVM_ASM_SAFE(insn) __KVM_ASM_SAFE(insn, "")
+#define KVM_ASM_SAFE_FEP(insn) __KVM_ASM_SAFE(insn, KVM_FEP)
+
 #define KVM_ASM_SAFE_OUTPUTS(v, ec)	[vector] "=qm"(v), [error_code] "=rm"(ec)
 #define KVM_ASM_SAFE_CLOBBERS	"r9", "r10", "r11"
 
@@ -1156,21 +1212,58 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
 	vector;								\
 })
 
-static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val)
-{
-	uint64_t error_code;
-	uint8_t vector;
-	uint32_t a, d;
+#define kvm_asm_safe_fep(insn, inputs...)				\
+({									\
+	uint64_t ign_error_code;					\
+	uint8_t vector;							\
+									\
+	asm volatile(KVM_ASM_SAFE(insn)					\
+		     : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code)	\
+		     : inputs						\
+		     : KVM_ASM_SAFE_CLOBBERS);				\
+	vector;								\
+})
 
-	asm volatile(KVM_ASM_SAFE("rdmsr")
-		     : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code)
-		     : "c"(msr)
-		     : KVM_ASM_SAFE_CLOBBERS);
+#define kvm_asm_safe_ec_fep(insn, error_code, inputs...)		\
+({									\
+	uint8_t vector;							\
+									\
+	asm volatile(KVM_ASM_SAFE_FEP(insn)				\
+		     : KVM_ASM_SAFE_OUTPUTS(vector, error_code)		\
+		     : inputs						\
+		     : KVM_ASM_SAFE_CLOBBERS);				\
+	vector;								\
+})
 
-	*val = (uint64_t)a | ((uint64_t)d << 32);
-	return vector;
+#define BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP)			\
+static inline uint8_t insn##_safe ##_fep(uint32_t idx, uint64_t *val)	\
+{									\
+	uint64_t error_code;						\
+	uint8_t vector;							\
+	uint32_t a, d;							\
+									\
+	asm volatile(KVM_ASM_SAFE##_FEP(#insn)				\
+		     : "=a"(a), "=d"(d),				\
+		       KVM_ASM_SAFE_OUTPUTS(vector, error_code)		\
+		     : "c"(idx)						\
+		     : KVM_ASM_SAFE_CLOBBERS);				\
+									\
+	*val = (uint64_t)a | ((uint64_t)d << 32);			\
+	return vector;							\
 }
 
+/*
+ * Generate {insn}_safe() and {insn}_safe_fep() helpers for instructions that
+ * use ECX as in input index, and EDX:EAX as a 64-bit output.
+ */
+#define BUILD_READ_U64_SAFE_HELPERS(insn)				\
+	BUILD_READ_U64_SAFE_HELPER(insn, , )				\
+	BUILD_READ_U64_SAFE_HELPER(insn, _fep, _FEP)			\
+
+BUILD_READ_U64_SAFE_HELPERS(rdmsr)
+BUILD_READ_U64_SAFE_HELPERS(rdpmc)
+BUILD_READ_U64_SAFE_HELPERS(xgetbv)
+
 static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val)
 {
 	return kvm_asm_safe("wrmsr", "a"(val & -1u), "d"(val >> 32), "c"(msr));
@@ -1186,6 +1279,16 @@ static inline uint8_t xsetbv_safe(uint32_t index, uint64_t value)
 
 bool kvm_is_tdp_enabled(void);
 
+static inline bool kvm_is_pmu_enabled(void)
+{
+	return get_kvm_param_bool("enable_pmu");
+}
+
+static inline bool kvm_is_forced_emulation_enabled(void)
+{
+	return !!get_kvm_param_integer("force_emulation_prefix");
+}
+
 uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 				    int *level);
 uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86_64/sev.h
new file mode 100644
index 0000000000..8a1bf88474
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86_64/sev.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Helpers used for SEV guests
+ *
+ */
+#ifndef SELFTEST_KVM_SEV_H
+#define SELFTEST_KVM_SEV_H
+
+#include <stdint.h>
+#include <stdbool.h>
+
+#include "linux/psp-sev.h"
+
+#include "kvm_util.h"
+#include "svm_util.h"
+#include "processor.h"
+
+enum sev_guest_state {
+	SEV_GUEST_STATE_UNINITIALIZED = 0,
+	SEV_GUEST_STATE_LAUNCH_UPDATE,
+	SEV_GUEST_STATE_LAUNCH_SECRET,
+	SEV_GUEST_STATE_RUNNING,
+};
+
+#define SEV_POLICY_NO_DBG	(1UL << 0)
+#define SEV_POLICY_ES		(1UL << 2)
+
+#define GHCB_MSR_TERM_REQ	0x100
+
+void sev_vm_launch(struct kvm_vm *vm, uint32_t policy);
+void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement);
+void sev_vm_launch_finish(struct kvm_vm *vm);
+
+struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code,
+					   struct kvm_vcpu **cpu);
+
+kvm_static_assert(SEV_RET_SUCCESS == 0);
+
+/*
+ * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long"
+ * instead of a proper struct.  The size of the parameter is embedded in the
+ * ioctl number, i.e. is ABI and thus immutable.  Hack around the mess by
+ * creating an overlay to pass in an "unsigned long" without a cast (casting
+ * will make the compiler unhappy due to dereferencing an aliased pointer).
+ */
+#define __vm_sev_ioctl(vm, cmd, arg)					\
+({									\
+	int r;								\
+									\
+	union {								\
+		struct kvm_sev_cmd c;					\
+		unsigned long raw;					\
+	} sev_cmd = { .c = {						\
+		.id = (cmd),						\
+		.data = (uint64_t)(arg),				\
+		.sev_fd = (vm)->arch.sev_fd,				\
+	} };								\
+									\
+	r = __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_OP, &sev_cmd.raw);	\
+	r ?: sev_cmd.c.error;						\
+})
+
+#define vm_sev_ioctl(vm, cmd, arg)					\
+({									\
+	int ret = __vm_sev_ioctl(vm, cmd, arg);				\
+									\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd,	ret, vm);		\
+})
+
+static inline void sev_vm_init(struct kvm_vm *vm)
+{
+	vm->arch.sev_fd = open_sev_dev_path_or_exit();
+
+	vm_sev_ioctl(vm, KVM_SEV_INIT, NULL);
+}
+
+
+static inline void sev_es_vm_init(struct kvm_vm *vm)
+{
+	vm->arch.sev_fd = open_sev_dev_path_or_exit();
+
+	vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL);
+}
+
+static inline void sev_register_encrypted_memory(struct kvm_vm *vm,
+						 struct userspace_mem_region *region)
+{
+	struct kvm_enc_region range = {
+		.addr = region->region.userspace_addr,
+		.size = region->region.memory_size,
+	};
+
+	vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range);
+}
+
+static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa,
+					  uint64_t size)
+{
+	struct kvm_sev_launch_update_data update_data = {
+		.uaddr = (unsigned long)addr_gpa2hva(vm, gpa),
+		.len = size,
+	};
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data);
+}
+
+#endif /* SELFTEST_KVM_SEV_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 43b9a72833..a9eb17295b 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -365,8 +365,13 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 		indent, "", pstate, pc);
 }
 
-struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  struct kvm_vcpu_init *init, void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+}
+
+static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+					   struct kvm_vcpu_init *init)
 {
 	size_t stack_size;
 	uint64_t stack_vaddr;
@@ -381,15 +386,22 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	aarch64_vcpu_setup(vcpu, init);
 
 	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
-	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+	return vcpu;
+}
+
+struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+				  struct kvm_vcpu_init *init, void *guest_code)
+{
+	struct kvm_vcpu *vcpu = __aarch64_vcpu_add(vm, vcpu_id, init);
+
+	vcpu_arch_set_entry_point(vcpu, guest_code);
 
 	return vcpu;
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
-	return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code);
+	return __aarch64_vcpu_add(vm, vcpu_id, NULL);
 }
 
 void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 1b197426f2..b2262b5fad 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -52,13 +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);
@@ -67,11 +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;
@@ -96,6 +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
  *
@@ -226,6 +276,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 
 	vm->mode = shape.mode;
 	vm->type = shape.type;
+	vm->subtype = shape.subtype;
 
 	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
 	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
@@ -266,6 +317,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	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
@@ -666,6 +718,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	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) {
@@ -1047,6 +1100,8 @@ 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);
 	region->region.slot = slot;
@@ -1377,15 +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
@@ -1405,6 +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
  *
@@ -1527,6 +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);
@@ -1873,6 +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);
@@ -1974,6 +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
  *
@@ -1985,8 +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;
@@ -1999,8 +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)) {
@@ -2019,8 +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;
 }
@@ -2224,3 +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);
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/handlers.S b/tools/testing/selftests/kvm/lib/riscv/handlers.S
new file mode 100644
index 0000000000..aa0abd3f35
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/riscv/handlers.S
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Intel Corporation
+ */
+
+#ifndef __ASSEMBLY__
+#define __ASSEMBLY__
+#endif
+
+#include <asm/csr.h>
+
+.macro save_context
+	addi  sp, sp, (-8*34)
+	sd    x1, 0(sp)
+	sd    x2, 8(sp)
+	sd    x3, 16(sp)
+	sd    x4, 24(sp)
+	sd    x5, 32(sp)
+	sd    x6, 40(sp)
+	sd    x7, 48(sp)
+	sd    x8, 56(sp)
+	sd    x9, 64(sp)
+	sd    x10, 72(sp)
+	sd    x11, 80(sp)
+	sd    x12, 88(sp)
+	sd    x13, 96(sp)
+	sd    x14, 104(sp)
+	sd    x15, 112(sp)
+	sd    x16, 120(sp)
+	sd    x17, 128(sp)
+	sd    x18, 136(sp)
+	sd    x19, 144(sp)
+	sd    x20, 152(sp)
+	sd    x21, 160(sp)
+	sd    x22, 168(sp)
+	sd    x23, 176(sp)
+	sd    x24, 184(sp)
+	sd    x25, 192(sp)
+	sd    x26, 200(sp)
+	sd    x27, 208(sp)
+	sd    x28, 216(sp)
+	sd    x29, 224(sp)
+	sd    x30, 232(sp)
+	sd    x31, 240(sp)
+	csrr  s0, CSR_SEPC
+	csrr  s1, CSR_SSTATUS
+	csrr  s2, CSR_SCAUSE
+	sd    s0, 248(sp)
+	sd    s1, 256(sp)
+	sd    s2, 264(sp)
+.endm
+
+.macro restore_context
+	ld    s2, 264(sp)
+	ld    s1, 256(sp)
+	ld    s0, 248(sp)
+	csrw  CSR_SCAUSE, s2
+	csrw  CSR_SSTATUS, s1
+	csrw  CSR_SEPC, s0
+	ld    x31, 240(sp)
+	ld    x30, 232(sp)
+	ld    x29, 224(sp)
+	ld    x28, 216(sp)
+	ld    x27, 208(sp)
+	ld    x26, 200(sp)
+	ld    x25, 192(sp)
+	ld    x24, 184(sp)
+	ld    x23, 176(sp)
+	ld    x22, 168(sp)
+	ld    x21, 160(sp)
+	ld    x20, 152(sp)
+	ld    x19, 144(sp)
+	ld    x18, 136(sp)
+	ld    x17, 128(sp)
+	ld    x16, 120(sp)
+	ld    x15, 112(sp)
+	ld    x14, 104(sp)
+	ld    x13, 96(sp)
+	ld    x12, 88(sp)
+	ld    x11, 80(sp)
+	ld    x10, 72(sp)
+	ld    x9, 64(sp)
+	ld    x8, 56(sp)
+	ld    x7, 48(sp)
+	ld    x6, 40(sp)
+	ld    x5, 32(sp)
+	ld    x4, 24(sp)
+	ld    x3, 16(sp)
+	ld    x2, 8(sp)
+	ld    x1, 0(sp)
+	addi  sp, sp, (8*34)
+.endm
+
+.balign 4
+.global exception_vectors
+exception_vectors:
+	save_context
+	move  a0, sp
+	call  route_exception
+	restore_context
+	sret
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 2bb33a8ac0..e8211f5d68 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -13,6 +13,18 @@
 
 #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN	0xac0000
 
+static vm_vaddr_t exception_handlers;
+
+bool __vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext)
+{
+	unsigned long value = 0;
+	int ret;
+
+	ret = __vcpu_get_reg(vcpu, ext, &value);
+
+	return !ret && !!value;
+}
+
 static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
 {
 	return (v + vm->page_size) & ~(vm->page_size - 1);
@@ -277,8 +289,12 @@ static void __aligned(16) guest_unexp_trap(void)
 		  0, 0, 0, 0, 0, 0);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	int r;
 	size_t stack_size;
@@ -312,7 +328,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 
 	/* Setup stack pointer and program counter of guest */
 	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size);
-	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
+
+	/* Setup sscratch for guest_get_vcpuid() */
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id);
 
 	/* Setup default exception vector of guest */
 	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)guest_unexp_trap);
@@ -364,8 +382,80 @@ void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
 	va_end(ap);
 }
 
+void kvm_exit_unexpected_exception(int vector, int ec)
+{
+	ucall(UCALL_UNHANDLED, 2, vector, ec);
+}
+
 void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
 {
+	struct ucall uc;
+
+	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED) {
+		TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)",
+			uc.args[0], uc.args[1]);
+	}
+}
+
+struct handlers {
+	exception_handler_fn exception_handlers[NR_VECTORS][NR_EXCEPTIONS];
+};
+
+void route_exception(struct ex_regs *regs)
+{
+	struct handlers *handlers = (struct handlers *)exception_handlers;
+	int vector = 0, ec;
+
+	ec = regs->cause & ~CAUSE_IRQ_FLAG;
+	if (ec >= NR_EXCEPTIONS)
+		goto unexpected_exception;
+
+	/* Use the same handler for all the interrupts */
+	if (regs->cause & CAUSE_IRQ_FLAG) {
+		vector = 1;
+		ec = 0;
+	}
+
+	if (handlers && handlers->exception_handlers[vector][ec])
+		return handlers->exception_handlers[vector][ec](regs);
+
+unexpected_exception:
+	return kvm_exit_unexpected_exception(vector, ec);
+}
+
+void vcpu_init_vector_tables(struct kvm_vcpu *vcpu)
+{
+	extern char exception_vectors;
+
+	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(stvec), (unsigned long)&exception_vectors);
+}
+
+void vm_init_vector_tables(struct kvm_vm *vm)
+{
+	vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers),
+				   vm->page_size, MEM_REGION_DATA);
+
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector, exception_handler_fn handler)
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(vector < NR_EXCEPTIONS);
+	handlers->exception_handlers[0][vector] = handler;
+}
+
+void vm_install_interrupt_handler(struct kvm_vm *vm, exception_handler_fn handler)
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	handlers->exception_handlers[1][0] = handler;
+}
+
+uint32_t guest_get_vcpuid(void)
+{
+	return csr_read(CSR_SSCRATCH);
 }
 
 struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index f6d227892c..4ad4492eea 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -155,15 +155,18 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	virt_dump_region(stream, vm, indent, vm->pgd);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu->run->psw_addr = (uintptr_t)guest_code;
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	size_t stack_size =  DEFAULT_STACK_PGS * getpagesize();
 	uint64_t stack_vaddr;
 	struct kvm_regs regs;
 	struct kvm_sregs sregs;
 	struct kvm_vcpu *vcpu;
-	struct kvm_run *run;
 
 	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
 		    vm->page_size);
@@ -184,9 +187,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	sregs.crs[1] = vm->pgd | 0xf;		/* Primary region table */
 	vcpu_sregs_set(vcpu, &sregs);
 
-	run = vcpu->run;
-	run->psw_mask = 0x0400000180000000ULL;  /* DAT enabled + 64 bit mode */
-	run->psw_addr = (uintptr_t)guest_code;
+	vcpu->run->psw_mask = 0x0400000180000000ULL;  /* DAT enabled + 64 bit mode */
 
 	return vcpu;
 }
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
index 88cb6b84e6..cfed9d26cc 100644
--- a/tools/testing/selftests/kvm/lib/sparsebit.c
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -202,7 +202,7 @@ static sparsebit_num_t node_num_set(struct node *nodep)
 /* Returns a pointer to the node that describes the
  * lowest bit index.
  */
-static struct node *node_first(struct sparsebit *s)
+static struct node *node_first(const struct sparsebit *s)
 {
 	struct node *nodep;
 
@@ -216,7 +216,7 @@ static struct node *node_first(struct sparsebit *s)
  * lowest bit index > the index of the node pointed to by np.
  * Returns NULL if no node with a higher index exists.
  */
-static struct node *node_next(struct sparsebit *s, struct node *np)
+static struct node *node_next(const struct sparsebit *s, struct node *np)
 {
 	struct node *nodep = np;
 
@@ -244,7 +244,7 @@ static struct node *node_next(struct sparsebit *s, struct node *np)
  * highest index < the index of the node pointed to by np.
  * Returns NULL if no node with a lower index exists.
  */
-static struct node *node_prev(struct sparsebit *s, struct node *np)
+static struct node *node_prev(const struct sparsebit *s, struct node *np)
 {
 	struct node *nodep = np;
 
@@ -273,7 +273,7 @@ static struct node *node_prev(struct sparsebit *s, struct node *np)
  * subtree and duplicates the bit settings to the newly allocated nodes.
  * Returns the newly allocated copy of subtree.
  */
-static struct node *node_copy_subtree(struct node *subtree)
+static struct node *node_copy_subtree(const struct node *subtree)
 {
 	struct node *root;
 
@@ -307,7 +307,7 @@ static struct node *node_copy_subtree(struct node *subtree)
  * index is within the bits described by the mask bits or the number of
  * contiguous bits set after the mask.  Returns NULL if there is no such node.
  */
-static struct node *node_find(struct sparsebit *s, sparsebit_idx_t idx)
+static struct node *node_find(const struct sparsebit *s, sparsebit_idx_t idx)
 {
 	struct node *nodep;
 
@@ -393,7 +393,7 @@ static struct node *node_add(struct sparsebit *s, sparsebit_idx_t idx)
 }
 
 /* Returns whether all the bits in the sparsebit array are set.  */
-bool sparsebit_all_set(struct sparsebit *s)
+bool sparsebit_all_set(const struct sparsebit *s)
 {
 	/*
 	 * If any nodes there must be at least one bit set.  Only case
@@ -775,7 +775,7 @@ static void node_reduce(struct sparsebit *s, struct node *nodep)
 /* Returns whether the bit at the index given by idx, within the
  * sparsebit array is set or not.
  */
-bool sparsebit_is_set(struct sparsebit *s, sparsebit_idx_t idx)
+bool sparsebit_is_set(const struct sparsebit *s, sparsebit_idx_t idx)
 {
 	struct node *nodep;
 
@@ -921,7 +921,7 @@ static inline sparsebit_idx_t node_first_clear(struct node *nodep, int start)
  * used by test cases after they detect an unexpected condition, as a means
  * to capture diagnostic information.
  */
-static void sparsebit_dump_internal(FILE *stream, struct sparsebit *s,
+static void sparsebit_dump_internal(FILE *stream, const struct sparsebit *s,
 	unsigned int indent)
 {
 	/* Dump the contents of s */
@@ -969,7 +969,7 @@ void sparsebit_free(struct sparsebit **sbitp)
  * sparsebit_alloc().  It can though already have bits set, which
  * if different from src will be cleared.
  */
-void sparsebit_copy(struct sparsebit *d, struct sparsebit *s)
+void sparsebit_copy(struct sparsebit *d, const struct sparsebit *s)
 {
 	/* First clear any bits already set in the destination */
 	sparsebit_clear_all(d);
@@ -981,7 +981,7 @@ void sparsebit_copy(struct sparsebit *d, struct sparsebit *s)
 }
 
 /* Returns whether num consecutive bits starting at idx are all set.  */
-bool sparsebit_is_set_num(struct sparsebit *s,
+bool sparsebit_is_set_num(const struct sparsebit *s,
 	sparsebit_idx_t idx, sparsebit_num_t num)
 {
 	sparsebit_idx_t next_cleared;
@@ -1005,14 +1005,14 @@ bool sparsebit_is_set_num(struct sparsebit *s,
 }
 
 /* Returns whether the bit at the index given by idx.  */
-bool sparsebit_is_clear(struct sparsebit *s,
+bool sparsebit_is_clear(const struct sparsebit *s,
 	sparsebit_idx_t idx)
 {
 	return !sparsebit_is_set(s, idx);
 }
 
 /* Returns whether num consecutive bits starting at idx are all cleared.  */
-bool sparsebit_is_clear_num(struct sparsebit *s,
+bool sparsebit_is_clear_num(const struct sparsebit *s,
 	sparsebit_idx_t idx, sparsebit_num_t num)
 {
 	sparsebit_idx_t next_set;
@@ -1041,13 +1041,13 @@ bool sparsebit_is_clear_num(struct sparsebit *s,
  * value.  Use sparsebit_any_set(), instead of sparsebit_num_set() > 0,
  * to determine if the sparsebit array has any bits set.
  */
-sparsebit_num_t sparsebit_num_set(struct sparsebit *s)
+sparsebit_num_t sparsebit_num_set(const struct sparsebit *s)
 {
 	return s->num_set;
 }
 
 /* Returns whether any bit is set in the sparsebit array.  */
-bool sparsebit_any_set(struct sparsebit *s)
+bool sparsebit_any_set(const struct sparsebit *s)
 {
 	/*
 	 * Nodes only describe set bits.  If any nodes then there
@@ -1070,20 +1070,20 @@ bool sparsebit_any_set(struct sparsebit *s)
 }
 
 /* Returns whether all the bits in the sparsebit array are cleared.  */
-bool sparsebit_all_clear(struct sparsebit *s)
+bool sparsebit_all_clear(const struct sparsebit *s)
 {
 	return !sparsebit_any_set(s);
 }
 
 /* Returns whether all the bits in the sparsebit array are set.  */
-bool sparsebit_any_clear(struct sparsebit *s)
+bool sparsebit_any_clear(const struct sparsebit *s)
 {
 	return !sparsebit_all_set(s);
 }
 
 /* Returns the index of the first set bit.  Abort if no bits are set.
  */
-sparsebit_idx_t sparsebit_first_set(struct sparsebit *s)
+sparsebit_idx_t sparsebit_first_set(const struct sparsebit *s)
 {
 	struct node *nodep;
 
@@ -1097,7 +1097,7 @@ sparsebit_idx_t sparsebit_first_set(struct sparsebit *s)
 /* Returns the index of the first cleared bit.  Abort if
  * no bits are cleared.
  */
-sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s)
+sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *s)
 {
 	struct node *nodep1, *nodep2;
 
@@ -1151,7 +1151,7 @@ sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s)
 /* Returns index of next bit set within s after the index given by prev.
  * Returns 0 if there are no bits after prev that are set.
  */
-sparsebit_idx_t sparsebit_next_set(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_set(const struct sparsebit *s,
 	sparsebit_idx_t prev)
 {
 	sparsebit_idx_t lowest_possible = prev + 1;
@@ -1244,7 +1244,7 @@ sparsebit_idx_t sparsebit_next_set(struct sparsebit *s,
 /* Returns index of next bit cleared within s after the index given by prev.
  * Returns 0 if there are no bits after prev that are cleared.
  */
-sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *s,
 	sparsebit_idx_t prev)
 {
 	sparsebit_idx_t lowest_possible = prev + 1;
@@ -1300,7 +1300,7 @@ sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s,
  * and returns the index of the first sequence of num consecutively set
  * bits.  Returns a value of 0 of no such sequence exists.
  */
-sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *s,
 	sparsebit_idx_t start, sparsebit_num_t num)
 {
 	sparsebit_idx_t idx;
@@ -1335,7 +1335,7 @@ sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s,
  * and returns the index of the first sequence of num consecutively cleared
  * bits.  Returns a value of 0 of no such sequence exists.
  */
-sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *s,
 	sparsebit_idx_t start, sparsebit_num_t num)
 {
 	sparsebit_idx_t idx;
@@ -1583,7 +1583,7 @@ static size_t display_range(FILE *stream, sparsebit_idx_t low,
  * contiguous bits.  This is done because '-' is used to specify command-line
  * options, and sometimes ranges are specified as command-line arguments.
  */
-void sparsebit_dump(FILE *stream, struct sparsebit *s,
+void sparsebit_dump(FILE *stream, const struct sparsebit *s,
 	unsigned int indent)
 {
 	size_t current_line_len = 0;
@@ -1681,7 +1681,7 @@ void sparsebit_dump(FILE *stream, struct sparsebit *s,
  * s.  On error, diagnostic information is printed to stderr and
  * abort is called.
  */
-void sparsebit_validate_internal(struct sparsebit *s)
+void sparsebit_validate_internal(const struct sparsebit *s)
 {
 	bool error_detected = false;
 	struct node *nodep, *prev = NULL;
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index 816a3fa109..f5af65a41c 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -29,7 +29,8 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 	vm_vaddr_t vaddr;
 	int i;
 
-	vaddr = __vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, MEM_REGION_DATA);
+	vaddr = vm_vaddr_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR,
+				      MEM_REGION_DATA);
 	hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr);
 	memset(hdr, 0, sizeof(*hdr));
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86_64/pmu.c
new file mode 100644
index 0000000000..f31f0427c1
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/pmu.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023, Tencent, Inc.
+ */
+
+#include <stdint.h>
+
+#include <linux/kernel.h>
+
+#include "kvm_util.h"
+#include "pmu.h"
+
+const uint64_t intel_pmu_arch_events[] = {
+	INTEL_ARCH_CPU_CYCLES,
+	INTEL_ARCH_INSTRUCTIONS_RETIRED,
+	INTEL_ARCH_REFERENCE_CYCLES,
+	INTEL_ARCH_LLC_REFERENCES,
+	INTEL_ARCH_LLC_MISSES,
+	INTEL_ARCH_BRANCHES_RETIRED,
+	INTEL_ARCH_BRANCHES_MISPREDICTED,
+	INTEL_ARCH_TOPDOWN_SLOTS,
+};
+kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS);
+
+const uint64_t amd_pmu_zen_events[] = {
+	AMD_ZEN_CORE_CYCLES,
+	AMD_ZEN_INSTRUCTIONS_RETIRED,
+	AMD_ZEN_BRANCHES_RETIRED,
+	AMD_ZEN_BRANCHES_MISPREDICTED,
+};
+kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS);
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f639b3e062..74a4c736c9 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -9,6 +9,7 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "sev.h"
 
 #ifndef NUM_INTERRUPTS
 #define NUM_INTERRUPTS 256
@@ -157,6 +158,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 {
 	uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level);
 
+	paddr = vm_untag_gpa(vm, paddr);
+
 	if (!(*pte & PTE_PRESENT_MASK)) {
 		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
 		if (current_level == target_level)
@@ -200,6 +203,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 		    "Physical address beyond maximum supported,\n"
 		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
+	TEST_ASSERT(vm_untag_gpa(vm, paddr) == paddr,
+		    "Unexpected bits in paddr: %lx", paddr);
 
 	/*
 	 * Allocate upper level page tables, if not already present.  Return
@@ -222,6 +227,15 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
+
+	/*
+	 * Neither SEV nor TDX supports shared page tables, so only the final
+	 * leaf PTE needs manually set the C/S-bit.
+	 */
+	if (vm_is_gpa_protected(vm, paddr))
+		*pte |= vm->arch.c_bit;
+	else
+		*pte |= vm->arch.s_bit;
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -265,6 +279,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 {
 	uint64_t *pml4e, *pdpe, *pde;
 
+	TEST_ASSERT(!vm->arch.is_pt_protected,
+		    "Walking page tables of protected guests is impossible");
+
 	TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
 		    "Invalid PG_LEVEL_* '%d'", *level);
 
@@ -496,7 +513,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	 * No need for a hugepage mask on the PTE, x86-64 requires the "unused"
 	 * address bits to be zero.
 	 */
-	return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level));
+	return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level));
 }
 
 static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
@@ -560,10 +577,23 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm)
 	vm_create_irqchip(vm);
 	sync_global_to_guest(vm, host_cpu_is_intel);
 	sync_global_to_guest(vm, host_cpu_is_amd);
+
+	if (vm->subtype == VM_SUBTYPE_SEV)
+		sev_vm_init(vm);
+	else if (vm->subtype == VM_SUBTYPE_SEV_ES)
+		sev_es_vm_init(vm);
+}
+
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	struct kvm_regs regs;
+
+	vcpu_regs_get(vcpu, &regs);
+	regs.rip = (unsigned long) guest_code;
+	vcpu_regs_set(vcpu, &regs);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	struct kvm_mp_state mp_state;
 	struct kvm_regs regs;
@@ -597,7 +627,6 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vcpu_regs_get(vcpu, &regs);
 	regs.rflags = regs.rflags | 0x2;
 	regs.rsp = stack_vaddr;
-	regs.rip = (unsigned long) guest_code;
 	vcpu_regs_set(vcpu, &regs);
 
 	/* Setup the MP state */
@@ -752,12 +781,21 @@ void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid)
 	vcpu_set_cpuid(vcpu);
 }
 
-void vcpu_set_cpuid_maxphyaddr(struct kvm_vcpu *vcpu, uint8_t maxphyaddr)
+void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu,
+			     struct kvm_x86_cpu_property property,
+			     uint32_t value)
 {
-	struct kvm_cpuid_entry2 *entry = vcpu_get_cpuid_entry(vcpu, 0x80000008);
+	struct kvm_cpuid_entry2 *entry;
+
+	entry = __vcpu_get_cpuid_entry(vcpu, property.function, property.index);
+
+	(&entry->eax)[property.reg] &= ~GENMASK(property.hi_bit, property.lo_bit);
+	(&entry->eax)[property.reg] |= value << property.lo_bit;
 
-	entry->eax = (entry->eax & ~0xff) | maxphyaddr;
 	vcpu_set_cpuid(vcpu);
+
+	/* Sanity check that @value doesn't exceed the bounds in any way. */
+	TEST_ASSERT_EQ(kvm_cpuid_property(vcpu->cpuid, property), value);
 }
 
 void vcpu_clear_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function)
@@ -1041,6 +1079,14 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 	}
 }
 
+void kvm_init_vm_address_properties(struct kvm_vm *vm)
+{
+	if (vm->subtype == VM_SUBTYPE_SEV || vm->subtype == VM_SUBTYPE_SEV_ES) {
+		vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT));
+		vm->gpa_tag_mask = vm->arch.c_bit;
+	}
+}
+
 static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 			  int dpl, unsigned short selector)
 {
diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c
new file mode 100644
index 0000000000..e248d3364b
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <stdint.h>
+#include <stdbool.h>
+
+#include "sev.h"
+
+/*
+ * sparsebit_next_clear() can return 0 if [x, 2**64-1] are all set, and the
+ * -1 would then cause an underflow back to 2**64 - 1. This is expected and
+ * correct.
+ *
+ * If the last range in the sparsebit is [x, y] and we try to iterate,
+ * sparsebit_next_set() will return 0, and sparsebit_next_clear() will try
+ * and find the first range, but that's correct because the condition
+ * expression would cause us to quit the loop.
+ */
+static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region)
+{
+	const struct sparsebit *protected_phy_pages = region->protected_phy_pages;
+	const vm_paddr_t gpa_base = region->region.guest_phys_addr;
+	const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift;
+	sparsebit_idx_t i, j;
+
+	if (!sparsebit_any_set(protected_phy_pages))
+		return;
+
+	sev_register_encrypted_memory(vm, region);
+
+	sparsebit_for_each_set_range(protected_phy_pages, i, j) {
+		const uint64_t size = (j - i + 1) * vm->page_size;
+		const uint64_t offset = (i - lowest_page_in_region) * vm->page_size;
+
+		sev_launch_update_data(vm, gpa_base + offset, size);
+	}
+}
+
+void sev_vm_launch(struct kvm_vm *vm, uint32_t policy)
+{
+	struct kvm_sev_launch_start launch_start = {
+		.policy = policy,
+	};
+	struct userspace_mem_region *region;
+	struct kvm_sev_guest_status status;
+	int ctr;
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_START, &launch_start);
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+
+	TEST_ASSERT_EQ(status.policy, policy);
+	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_LAUNCH_UPDATE);
+
+	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node)
+		encrypt_region(vm, region);
+
+	if (policy & SEV_POLICY_ES)
+		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+
+	vm->arch.is_pt_protected = true;
+}
+
+void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement)
+{
+	struct kvm_sev_launch_measure launch_measure;
+	struct kvm_sev_guest_status guest_status;
+
+	launch_measure.len = 256;
+	launch_measure.uaddr = (__u64)measurement;
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_MEASURE, &launch_measure);
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &guest_status);
+	TEST_ASSERT_EQ(guest_status.state, SEV_GUEST_STATE_LAUNCH_SECRET);
+}
+
+void sev_vm_launch_finish(struct kvm_vm *vm)
+{
+	struct kvm_sev_guest_status status;
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+	TEST_ASSERT(status.state == SEV_GUEST_STATE_LAUNCH_UPDATE ||
+		    status.state == SEV_GUEST_STATE_LAUNCH_SECRET,
+		    "Unexpected guest state: %d", status.state);
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_FINISH, NULL);
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING);
+}
+
+struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code,
+					   struct kvm_vcpu **cpu)
+{
+	struct vm_shape shape = {
+		.type = VM_TYPE_DEFAULT,
+		.mode = VM_MODE_DEFAULT,
+		.subtype = policy & SEV_POLICY_ES ? VM_SUBTYPE_SEV_ES :
+						    VM_SUBTYPE_SEV,
+	};
+	struct kvm_vm *vm;
+	struct kvm_vcpu *cpus[1];
+	uint8_t measurement[512];
+
+	vm = __vm_create_with_vcpus(shape, 1, 0, guest_code, cpus);
+	*cpu = cpus[0];
+
+	sev_vm_launch(vm, policy);
+
+	/* TODO: Validate the measurement is as expected. */
+	sev_vm_launch_measure(vm, measurement);
+
+	sev_vm_launch_finish(vm);
+
+	return vm;
+}
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 6628dc4dda..1a6da7389b 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -22,10 +22,11 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
 	uint64_t gpa;
 
-	for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
-		*((volatile uint64_t *)gpa) = gpa;
-
-	GUEST_DONE();
+	for (;;) {
+		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+			*((volatile uint64_t *)gpa) = gpa;
+		GUEST_SYNC(0);
+	}
 }
 
 struct vcpu_info {
@@ -55,7 +56,7 @@ static void rendezvous_with_boss(void)
 static void run_vcpu(struct kvm_vcpu *vcpu)
 {
 	vcpu_run(vcpu);
-	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
 }
 
 static void *vcpu_worker(void *data)
@@ -64,17 +65,13 @@ static void *vcpu_worker(void *data)
 	struct kvm_vcpu *vcpu = info->vcpu;
 	struct kvm_vm *vm = vcpu->vm;
 	struct kvm_sregs sregs;
-	struct kvm_regs regs;
 
 	vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
 
-	/* Snapshot regs before the first run. */
-	vcpu_regs_get(vcpu, &regs);
 	rendezvous_with_boss();
 
 	run_vcpu(vcpu);
 	rendezvous_with_boss();
-	vcpu_regs_set(vcpu, &regs);
 	vcpu_sregs_get(vcpu, &sregs);
 #ifdef __x86_64__
 	/* Toggle CR0.WP to trigger a MMU context reset. */
diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c
new file mode 100644
index 0000000000..0f9cabd99f
--- /dev/null
+++ b/tools/testing/selftests/kvm/riscv/arch_timer.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arch_timer.c - Tests the riscv64 sstc timer IRQ functionality
+ *
+ * The test validates the sstc timer IRQs using vstimecmp registers.
+ * It's ported from the aarch64 arch_timer test.
+ *
+ * Copyright (c) 2024, Intel Corporation.
+ */
+
+#define _GNU_SOURCE
+
+#include "arch_timer.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "timer_test.h"
+
+static int timer_irq = IRQ_S_TIMER;
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+	uint64_t xcnt, xcnt_diff_us, cmp;
+	unsigned int intid = regs->cause & ~CAUSE_IRQ_FLAG;
+	uint32_t cpu = guest_get_vcpuid();
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	timer_irq_disable();
+
+	xcnt = timer_get_cycles();
+	cmp = timer_get_cmp();
+	xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt);
+
+	/* Make sure we are dealing with the correct timer IRQ */
+	GUEST_ASSERT_EQ(intid, timer_irq);
+
+	__GUEST_ASSERT(xcnt >= cmp,
+			"xcnt = 0x%"PRIx64", cmp = 0x%"PRIx64", xcnt_diff_us = 0x%" PRIx64,
+			xcnt, cmp, xcnt_diff_us);
+
+	WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
+}
+
+static void guest_run(struct test_vcpu_shared_data *shared_data)
+{
+	uint32_t irq_iter, config_iter;
+
+	shared_data->nr_iter = 0;
+	shared_data->guest_stage = 0;
+
+	for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+		/* Setup the next interrupt */
+		timer_set_next_cmp_ms(test_args.timer_period_ms);
+		shared_data->xcnt = timer_get_cycles();
+		timer_irq_enable();
+
+		/* Setup a timeout for the interrupt to arrive */
+		udelay(msecs_to_usecs(test_args.timer_period_ms) +
+			test_args.timer_err_margin_us);
+
+		irq_iter = READ_ONCE(shared_data->nr_iter);
+		__GUEST_ASSERT(config_iter + 1 == irq_iter,
+				"config_iter + 1 = 0x%x, irq_iter = 0x%x.\n"
+				"  Guest timer interrupt was not triggered within the specified\n"
+				"  interval, try to increase the error margin by [-e] option.\n",
+				config_iter + 1, irq_iter);
+	}
+}
+
+static void guest_code(void)
+{
+	uint32_t cpu = guest_get_vcpuid();
+	struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+	timer_irq_disable();
+	local_irq_enable();
+
+	guest_run(shared_data);
+
+	GUEST_DONE();
+}
+
+struct kvm_vm *test_vm_create(void)
+{
+	struct kvm_vm *vm;
+	int nr_vcpus = test_args.nr_vcpus;
+
+	vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
+	__TEST_REQUIRE(__vcpu_has_ext(vcpus[0], RISCV_ISA_EXT_REG(KVM_RISCV_ISA_EXT_SSTC)),
+				   "SSTC not available, skipping test\n");
+
+	vm_init_vector_tables(vm);
+	vm_install_interrupt_handler(vm, guest_irq_handler);
+
+	for (int i = 0; i < nr_vcpus; i++)
+		vcpu_init_vector_tables(vcpus[i]);
+
+	/* Initialize guest timer frequency. */
+	vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq);
+	sync_global_to_guest(vm, timer_freq);
+	pr_debug("timer_freq: %lu\n", timer_freq);
+
+	/* Make all the test's cmdline args visible to the guest */
+	sync_global_to_guest(vm, test_args);
+
+	return vm;
+}
+
+void test_vm_cleanup(struct kvm_vm *vm)
+{
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c
index 6435e7a656..b882b7b9b7 100644
--- a/tools/testing/selftests/kvm/riscv/get-reg-list.c
+++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c
@@ -47,6 +47,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZACAS:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBB:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBC:
@@ -73,6 +74,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSED:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKSH:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZKT:
+	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZTSO:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBB:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVBC:
 	case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZVFH:
@@ -123,15 +125,6 @@ bool check_reject_set(int err)
 	return err == EINVAL;
 }
 
-static bool vcpu_has_ext(struct kvm_vcpu *vcpu, uint64_t ext_id)
-{
-	int ret;
-	unsigned long value;
-
-	ret = __vcpu_get_reg(vcpu, ext_id, &value);
-	return (ret) ? false : !!value;
-}
-
 void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 {
 	unsigned long isa_ext_state[KVM_RISCV_ISA_EXT_MAX] = { 0 };
@@ -176,7 +169,7 @@ void finalize_vcpu(struct kvm_vcpu *vcpu, struct vcpu_reg_list *c)
 		__vcpu_set_reg(vcpu, feature, 1);
 
 		/* Double check whether the desired extension was enabled */
-		__TEST_REQUIRE(vcpu_has_ext(vcpu, feature),
+		__TEST_REQUIRE(__vcpu_has_ext(vcpu, feature),
 			       "%s not available, skipping tests", s->name);
 	}
 }
@@ -419,6 +412,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(SVINVAL),
 		KVM_ISA_EXT_ARR(SVNAPOT),
 		KVM_ISA_EXT_ARR(SVPBMT),
+		KVM_ISA_EXT_ARR(ZACAS),
 		KVM_ISA_EXT_ARR(ZBA),
 		KVM_ISA_EXT_ARR(ZBB),
 		KVM_ISA_EXT_ARR(ZBC),
@@ -445,6 +439,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off)
 		KVM_ISA_EXT_ARR(ZKSED),
 		KVM_ISA_EXT_ARR(ZKSH),
 		KVM_ISA_EXT_ARR(ZKT),
+		KVM_ISA_EXT_ARR(ZTSO),
 		KVM_ISA_EXT_ARR(ZVBB),
 		KVM_ISA_EXT_ARR(ZVBC),
 		KVM_ISA_EXT_ARR(ZVFH),
@@ -940,6 +935,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(sstc, SSTC);
 KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL);
 KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT);
 KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT);
+KVM_ISA_EXT_SIMPLE_CONFIG(zacas, ZACAS);
 KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbb, ZBB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zbc, ZBC);
@@ -966,6 +962,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zkr, ZKR);
 KVM_ISA_EXT_SIMPLE_CONFIG(zksed, ZKSED);
 KVM_ISA_EXT_SIMPLE_CONFIG(zksh, ZKSH);
 KVM_ISA_EXT_SIMPLE_CONFIG(zkt, ZKT);
+KVM_ISA_EXT_SIMPLE_CONFIG(ztso, ZTSO);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvbb, ZVBB);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvbc, ZVBC);
 KVM_ISA_EXT_SIMPLE_CONFIG(zvfh, ZVFH);
@@ -993,6 +990,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_svinval,
 	&config_svnapot,
 	&config_svpbmt,
+	&config_zacas,
 	&config_zba,
 	&config_zbb,
 	&config_zbc,
@@ -1019,6 +1017,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_zksed,
 	&config_zksh,
 	&config_zkt,
+	&config_ztso,
 	&config_zvbb,
 	&config_zvbc,
 	&config_zvfh,
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index bb3ca9a5d7..48cb910e66 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -375,6 +375,32 @@ static void test_copy(void)
 	kvm_vm_free(t.kvm_vm);
 }
 
+static void test_copy_access_register(void)
+{
+	struct test_default t = test_default_init(guest_copy);
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+
+	prepare_mem12();
+	t.run->psw_mask &= ~(3UL << (63 - 17));
+	t.run->psw_mask |= 1UL << (63 - 17);  /* Enable AR mode */
+
+	/*
+	 * Primary address space gets used if an access register
+	 * contains zero. The host makes use of AR[1] so is a good
+	 * candidate to ensure the guest AR (of zero) is used.
+	 */
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size,
+		   GADDR_V(mem1), AR(1));
+	HOST_SYNC(t.vcpu, STAGE_COPIED);
+
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, t.size,
+		   GADDR_V(mem2), AR(1));
+	ASSERT_MEM_EQ(mem1, mem2, t.size);
+
+	kvm_vm_free(t.kvm_vm);
+}
+
 static void set_storage_key_range(void *addr, size_t len, uint8_t key)
 {
 	uintptr_t _addr, abs, i;
@@ -489,6 +515,8 @@ static __uint128_t rotate(int size, __uint128_t val, int amount)
 
 	amount = (amount + bits) % bits;
 	val = cut_to_size(size, val);
+	if (!amount)
+		return val;
 	return (val << (bits - amount)) | (val >> amount);
 }
 
@@ -1102,6 +1130,11 @@ int main(int argc, char *argv[])
 			.requirements_met = extension_cap > 0,
 		},
 		{
+			.name = "copy with access register mode",
+			.test = test_copy_access_register,
+			.requirements_met = true,
+		},
+		{
 			.name = "error checks with key",
 			.test = test_errors_key,
 			.requirements_met = extension_cap > 0,
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 06b43ed235..bd57d991e2 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -333,7 +333,7 @@ static void test_invalid_memory_region_flags(void)
 	struct kvm_vm *vm;
 	int r, i;
 
-#if defined __aarch64__ || defined __x86_64__
+#if defined __aarch64__ || defined __riscv || defined __x86_64__
 	supported_flags |= KVM_MEM_READONLY;
 #endif
 
diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
index 0f728f05ea..f3c2239228 100644
--- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
@@ -9,6 +9,7 @@
 #include <linux/stringify.h>
 #include <stdint.h>
 
+#include "kvm_test_harness.h"
 #include "apic.h"
 #include "test_util.h"
 #include "kvm_util.h"
@@ -83,6 +84,8 @@ static void guest_main(void)
 	GUEST_DONE();
 }
 
+KVM_ONE_VCPU_TEST_SUITE(fix_hypercall);
+
 static void enter_guest(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
@@ -103,14 +106,11 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void test_fix_hypercall(bool disable_quirk)
+static void test_fix_hypercall(struct kvm_vcpu *vcpu, bool disable_quirk)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
+	struct kvm_vm *vm = vcpu->vm;
 
-	vm_init_descriptor_tables(vcpu->vm);
+	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vcpu);
 	vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler);
 
@@ -126,10 +126,19 @@ static void test_fix_hypercall(bool disable_quirk)
 	enter_guest(vcpu);
 }
 
-int main(void)
+KVM_ONE_VCPU_TEST(fix_hypercall, enable_quirk, guest_main)
+{
+	test_fix_hypercall(vcpu, false);
+}
+
+KVM_ONE_VCPU_TEST(fix_hypercall, disable_quirk, guest_main)
+{
+	test_fix_hypercall(vcpu, true);
+}
+
+int main(int argc, char *argv[])
 {
 	TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN);
 
-	test_fix_hypercall(false);
-	test_fix_hypercall(true);
+	return test_harness_run(argc, argv);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
index 9e2879af7c..40cc59f4e6 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
@@ -133,6 +133,43 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void test_pv_unhalt(void)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct kvm_cpuid_entry2 *ent;
+	u32 kvm_sig_old;
+
+	pr_info("testing KVM_FEATURE_PV_UNHALT\n");
+
+	TEST_REQUIRE(KVM_CAP_X86_DISABLE_EXITS);
+
+	/* KVM_PV_UNHALT test */
+	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
+	vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT);
+
+	TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT),
+		    "Enabling X86_FEATURE_KVM_PV_UNHALT had no effect");
+
+	/* Make sure KVM clears vcpu->arch.kvm_cpuid */
+	ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE);
+	kvm_sig_old = ent->ebx;
+	ent->ebx = 0xdeadbeef;
+	vcpu_set_cpuid(vcpu);
+
+	vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT);
+	ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE);
+	ent->ebx = kvm_sig_old;
+	vcpu_set_cpuid(vcpu);
+
+	TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT),
+		    "KVM_FEATURE_PV_UNHALT is set with KVM_CAP_X86_DISABLE_EXITS");
+
+	/* FIXME: actually test KVM_FEATURE_PV_UNHALT feature */
+
+	kvm_vm_free(vm);
+}
+
 int main(void)
 {
 	struct kvm_vcpu *vcpu;
@@ -151,4 +188,6 @@ int main(void)
 
 	enter_guest(vcpu);
 	kvm_vm_free(vm);
+
+	test_pv_unhalt();
 }
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
new file mode 100644
index 0000000000..26c85815f7
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
@@ -0,0 +1,638 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023, Tencent, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <x86intrin.h>
+
+#include "pmu.h"
+#include "processor.h"
+
+/* Number of LOOP instructions for the guest measurement payload. */
+#define NUM_BRANCHES		10
+/*
+ * Number of "extra" instructions that will be counted, i.e. the number of
+ * instructions that are needed to set up the loop and then disabled the
+ * counter.  1 CLFLUSH/CLFLUSHOPT/NOP, 1 MFENCE, 2 MOV, 2 XOR, 1 WRMSR.
+ */
+#define NUM_EXTRA_INSNS		7
+#define NUM_INSNS_RETIRED	(NUM_BRANCHES + NUM_EXTRA_INSNS)
+
+static uint8_t kvm_pmu_version;
+static bool kvm_has_perf_caps;
+static bool is_forced_emulation_enabled;
+
+static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
+						  void *guest_code,
+						  uint8_t pmu_version,
+						  uint64_t perf_capabilities)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create_with_one_vcpu(vcpu, guest_code);
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(*vcpu);
+
+	sync_global_to_guest(vm, kvm_pmu_version);
+	sync_global_to_guest(vm, is_forced_emulation_enabled);
+
+	/*
+	 * Set PERF_CAPABILITIES before PMU version as KVM disallows enabling
+	 * features via PERF_CAPABILITIES if the guest doesn't have a vPMU.
+	 */
+	if (kvm_has_perf_caps)
+		vcpu_set_msr(*vcpu, MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+
+	vcpu_set_cpuid_property(*vcpu, X86_PROPERTY_PMU_VERSION, pmu_version);
+	return vm;
+}
+
+static void run_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+
+	do {
+		vcpu_run(vcpu);
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			break;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+			break;
+		case UCALL_PRINTF:
+			pr_info("%s", uc.buffer);
+			break;
+		case UCALL_DONE:
+			break;
+		default:
+			TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+		}
+	} while (uc.cmd != UCALL_DONE);
+}
+
+static uint8_t guest_get_pmu_version(void)
+{
+	/*
+	 * Return the effective PMU version, i.e. the minimum between what KVM
+	 * supports and what is enumerated to the guest.  The host deliberately
+	 * advertises a PMU version to the guest beyond what is actually
+	 * supported by KVM to verify KVM doesn't freak out and do something
+	 * bizarre with an architecturally valid, but unsupported, version.
+	 */
+	return min_t(uint8_t, kvm_pmu_version, this_cpu_property(X86_PROPERTY_PMU_VERSION));
+}
+
+/*
+ * If an architectural event is supported and guaranteed to generate at least
+ * one "hit, assert that its count is non-zero.  If an event isn't supported or
+ * the test can't guarantee the associated action will occur, then all bets are
+ * off regarding the count, i.e. no checks can be done.
+ *
+ * Sanity check that in all cases, the event doesn't count when it's disabled,
+ * and that KVM correctly emulates the write of an arbitrary value.
+ */
+static void guest_assert_event_count(uint8_t idx,
+				     struct kvm_x86_pmu_feature event,
+				     uint32_t pmc, uint32_t pmc_msr)
+{
+	uint64_t count;
+
+	count = _rdpmc(pmc);
+	if (!this_pmu_has(event))
+		goto sanity_checks;
+
+	switch (idx) {
+	case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX:
+		GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED);
+		break;
+	case INTEL_ARCH_BRANCHES_RETIRED_INDEX:
+		GUEST_ASSERT_EQ(count, NUM_BRANCHES);
+		break;
+	case INTEL_ARCH_LLC_REFERENCES_INDEX:
+	case INTEL_ARCH_LLC_MISSES_INDEX:
+		if (!this_cpu_has(X86_FEATURE_CLFLUSHOPT) &&
+		    !this_cpu_has(X86_FEATURE_CLFLUSH))
+			break;
+		fallthrough;
+	case INTEL_ARCH_CPU_CYCLES_INDEX:
+	case INTEL_ARCH_REFERENCE_CYCLES_INDEX:
+		GUEST_ASSERT_NE(count, 0);
+		break;
+	case INTEL_ARCH_TOPDOWN_SLOTS_INDEX:
+		GUEST_ASSERT(count >= NUM_INSNS_RETIRED);
+		break;
+	default:
+		break;
+	}
+
+sanity_checks:
+	__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+	GUEST_ASSERT_EQ(_rdpmc(pmc), count);
+
+	wrmsr(pmc_msr, 0xdead);
+	GUEST_ASSERT_EQ(_rdpmc(pmc), 0xdead);
+}
+
+/*
+ * Enable and disable the PMC in a monolithic asm blob to ensure that the
+ * compiler can't insert _any_ code into the measured sequence.  Note, ECX
+ * doesn't need to be clobbered as the input value, @pmc_msr, is restored
+ * before the end of the sequence.
+ *
+ * If CLFUSH{,OPT} is supported, flush the cacheline containing (at least) the
+ * start of the loop to force LLC references and misses, i.e. to allow testing
+ * that those events actually count.
+ *
+ * If forced emulation is enabled (and specified), force emulation on a subset
+ * of the measured code to verify that KVM correctly emulates instructions and
+ * branches retired events in conjunction with hardware also counting said
+ * events.
+ */
+#define GUEST_MEASURE_EVENT(_msr, _value, clflush, FEP)				\
+do {										\
+	__asm__ __volatile__("wrmsr\n\t"					\
+			     clflush "\n\t"					\
+			     "mfence\n\t"					\
+			     "1: mov $" __stringify(NUM_BRANCHES) ", %%ecx\n\t"	\
+			     FEP "loop .\n\t"					\
+			     FEP "mov %%edi, %%ecx\n\t"				\
+			     FEP "xor %%eax, %%eax\n\t"				\
+			     FEP "xor %%edx, %%edx\n\t"				\
+			     "wrmsr\n\t"					\
+			     :: "a"((uint32_t)_value), "d"(_value >> 32),	\
+				"c"(_msr), "D"(_msr)				\
+	);									\
+} while (0)
+
+#define GUEST_TEST_EVENT(_idx, _event, _pmc, _pmc_msr, _ctrl_msr, _value, FEP)	\
+do {										\
+	wrmsr(pmc_msr, 0);							\
+										\
+	if (this_cpu_has(X86_FEATURE_CLFLUSHOPT))				\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt 1f", FEP);	\
+	else if (this_cpu_has(X86_FEATURE_CLFLUSH))				\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush 1f", FEP);	\
+	else									\
+		GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP);		\
+										\
+	guest_assert_event_count(_idx, _event, _pmc, _pmc_msr);			\
+} while (0)
+
+static void __guest_test_arch_event(uint8_t idx, struct kvm_x86_pmu_feature event,
+				    uint32_t pmc, uint32_t pmc_msr,
+				    uint32_t ctrl_msr, uint64_t ctrl_msr_value)
+{
+	GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, "");
+
+	if (is_forced_emulation_enabled)
+		GUEST_TEST_EVENT(idx, event, pmc, pmc_msr, ctrl_msr, ctrl_msr_value, KVM_FEP);
+}
+
+#define X86_PMU_FEATURE_NULL						\
+({									\
+	struct kvm_x86_pmu_feature feature = {};			\
+									\
+	feature;							\
+})
+
+static bool pmu_is_null_feature(struct kvm_x86_pmu_feature event)
+{
+	return !(*(u64 *)&event);
+}
+
+static void guest_test_arch_event(uint8_t idx)
+{
+	const struct {
+		struct kvm_x86_pmu_feature gp_event;
+		struct kvm_x86_pmu_feature fixed_event;
+	} intel_event_to_feature[] = {
+		[INTEL_ARCH_CPU_CYCLES_INDEX]		 = { X86_PMU_FEATURE_CPU_CYCLES, X86_PMU_FEATURE_CPU_CYCLES_FIXED },
+		[INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX]	 = { X86_PMU_FEATURE_INSNS_RETIRED, X86_PMU_FEATURE_INSNS_RETIRED_FIXED },
+		/*
+		 * Note, the fixed counter for reference cycles is NOT the same
+		 * as the general purpose architectural event.  The fixed counter
+		 * explicitly counts at the same frequency as the TSC, whereas
+		 * the GP event counts at a fixed, but uarch specific, frequency.
+		 * Bundle them here for simplicity.
+		 */
+		[INTEL_ARCH_REFERENCE_CYCLES_INDEX]	 = { X86_PMU_FEATURE_REFERENCE_CYCLES, X86_PMU_FEATURE_REFERENCE_TSC_CYCLES_FIXED },
+		[INTEL_ARCH_LLC_REFERENCES_INDEX]	 = { X86_PMU_FEATURE_LLC_REFERENCES, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_LLC_MISSES_INDEX]		 = { X86_PMU_FEATURE_LLC_MISSES, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_BRANCHES_RETIRED_INDEX]	 = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL },
+		[INTEL_ARCH_TOPDOWN_SLOTS_INDEX]	 = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED },
+	};
+
+	uint32_t nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+	uint32_t pmu_version = guest_get_pmu_version();
+	/* PERF_GLOBAL_CTRL exists only for Architectural PMU Version 2+. */
+	bool guest_has_perf_global_ctrl = pmu_version >= 2;
+	struct kvm_x86_pmu_feature gp_event, fixed_event;
+	uint32_t base_pmc_msr;
+	unsigned int i;
+
+	/* The host side shouldn't invoke this without a guest PMU. */
+	GUEST_ASSERT(pmu_version);
+
+	if (this_cpu_has(X86_FEATURE_PDCM) &&
+	    rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
+		base_pmc_msr = MSR_IA32_PMC0;
+	else
+		base_pmc_msr = MSR_IA32_PERFCTR0;
+
+	gp_event = intel_event_to_feature[idx].gp_event;
+	GUEST_ASSERT_EQ(idx, gp_event.f.bit);
+
+	GUEST_ASSERT(nr_gp_counters);
+
+	for (i = 0; i < nr_gp_counters; i++) {
+		uint64_t eventsel = ARCH_PERFMON_EVENTSEL_OS |
+				    ARCH_PERFMON_EVENTSEL_ENABLE |
+				    intel_pmu_arch_events[idx];
+
+		wrmsr(MSR_P6_EVNTSEL0 + i, 0);
+		if (guest_has_perf_global_ctrl)
+			wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i));
+
+		__guest_test_arch_event(idx, gp_event, i, base_pmc_msr + i,
+					MSR_P6_EVNTSEL0 + i, eventsel);
+	}
+
+	if (!guest_has_perf_global_ctrl)
+		return;
+
+	fixed_event = intel_event_to_feature[idx].fixed_event;
+	if (pmu_is_null_feature(fixed_event) || !this_pmu_has(fixed_event))
+		return;
+
+	i = fixed_event.f.bit;
+
+	wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL));
+
+	__guest_test_arch_event(idx, fixed_event, i | INTEL_RDPMC_FIXED,
+				MSR_CORE_PERF_FIXED_CTR0 + i,
+				MSR_CORE_PERF_GLOBAL_CTRL,
+				FIXED_PMC_GLOBAL_CTRL_ENABLE(i));
+}
+
+static void guest_test_arch_events(void)
+{
+	uint8_t i;
+
+	for (i = 0; i < NR_INTEL_ARCH_EVENTS; i++)
+		guest_test_arch_event(i);
+
+	GUEST_DONE();
+}
+
+static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities,
+			     uint8_t length, uint8_t unavailable_mask)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	/* Testing arch events requires a vPMU (there are no negative tests). */
+	if (!pmu_version)
+		return;
+
+	vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events,
+					 pmu_version, perf_capabilities);
+
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH,
+				length);
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EVENTS_MASK,
+				unavailable_mask);
+
+	run_vcpu(vcpu);
+
+	kvm_vm_free(vm);
+}
+
+/*
+ * Limit testing to MSRs that are actually defined by Intel (in the SDM).  MSRs
+ * that aren't defined counter MSRs *probably* don't exist, but there's no
+ * guarantee that currently undefined MSR indices won't be used for something
+ * other than PMCs in the future.
+ */
+#define MAX_NR_GP_COUNTERS	8
+#define MAX_NR_FIXED_COUNTERS	3
+
+#define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector)		\
+__GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector,			\
+	       "Expected %s on " #insn "(0x%x), got vector %u",			\
+	       expect_gp ? "#GP" : "no fault", msr, vector)			\
+
+#define GUEST_ASSERT_PMC_VALUE(insn, msr, val, expected)			\
+	__GUEST_ASSERT(val == expected_val,					\
+		       "Expected " #insn "(0x%x) to yield 0x%lx, got 0x%lx",	\
+		       msr, expected_val, val);
+
+static void guest_test_rdpmc(uint32_t rdpmc_idx, bool expect_success,
+			     uint64_t expected_val)
+{
+	uint8_t vector;
+	uint64_t val;
+
+	vector = rdpmc_safe(rdpmc_idx, &val);
+	GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector);
+	if (expect_success)
+		GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val);
+
+	if (!is_forced_emulation_enabled)
+		return;
+
+	vector = rdpmc_safe_fep(rdpmc_idx, &val);
+	GUEST_ASSERT_PMC_MSR_ACCESS(RDPMC, rdpmc_idx, !expect_success, vector);
+	if (expect_success)
+		GUEST_ASSERT_PMC_VALUE(RDPMC, rdpmc_idx, val, expected_val);
+}
+
+static void guest_rd_wr_counters(uint32_t base_msr, uint8_t nr_possible_counters,
+				 uint8_t nr_counters, uint32_t or_mask)
+{
+	const bool pmu_has_fast_mode = !guest_get_pmu_version();
+	uint8_t i;
+
+	for (i = 0; i < nr_possible_counters; i++) {
+		/*
+		 * TODO: Test a value that validates full-width writes and the
+		 * width of the counters.
+		 */
+		const uint64_t test_val = 0xffff;
+		const uint32_t msr = base_msr + i;
+
+		/*
+		 * Fixed counters are supported if the counter is less than the
+		 * number of enumerated contiguous counters *or* the counter is
+		 * explicitly enumerated in the supported counters mask.
+		 */
+		const bool expect_success = i < nr_counters || (or_mask & BIT(i));
+
+		/*
+		 * KVM drops writes to MSR_P6_PERFCTR[0|1] if the counters are
+		 * unsupported, i.e. doesn't #GP and reads back '0'.
+		 */
+		const uint64_t expected_val = expect_success ? test_val : 0;
+		const bool expect_gp = !expect_success && msr != MSR_P6_PERFCTR0 &&
+				       msr != MSR_P6_PERFCTR1;
+		uint32_t rdpmc_idx;
+		uint8_t vector;
+		uint64_t val;
+
+		vector = wrmsr_safe(msr, test_val);
+		GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector);
+
+		vector = rdmsr_safe(msr, &val);
+		GUEST_ASSERT_PMC_MSR_ACCESS(RDMSR, msr, expect_gp, vector);
+
+		/* On #GP, the result of RDMSR is undefined. */
+		if (!expect_gp)
+			GUEST_ASSERT_PMC_VALUE(RDMSR, msr, val, expected_val);
+
+		/*
+		 * Redo the read tests with RDPMC, which has different indexing
+		 * semantics and additional capabilities.
+		 */
+		rdpmc_idx = i;
+		if (base_msr == MSR_CORE_PERF_FIXED_CTR0)
+			rdpmc_idx |= INTEL_RDPMC_FIXED;
+
+		guest_test_rdpmc(rdpmc_idx, expect_success, expected_val);
+
+		/*
+		 * KVM doesn't support non-architectural PMUs, i.e. it should
+		 * impossible to have fast mode RDPMC.  Verify that attempting
+		 * to use fast RDPMC always #GPs.
+		 */
+		GUEST_ASSERT(!expect_success || !pmu_has_fast_mode);
+		rdpmc_idx |= INTEL_RDPMC_FAST;
+		guest_test_rdpmc(rdpmc_idx, false, -1ull);
+
+		vector = wrmsr_safe(msr, 0);
+		GUEST_ASSERT_PMC_MSR_ACCESS(WRMSR, msr, expect_gp, vector);
+	}
+}
+
+static void guest_test_gp_counters(void)
+{
+	uint8_t pmu_version = guest_get_pmu_version();
+	uint8_t nr_gp_counters = 0;
+	uint32_t base_msr;
+
+	if (pmu_version)
+		nr_gp_counters = this_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+
+	/*
+	 * For v2+ PMUs, PERF_GLOBAL_CTRL's architectural post-RESET value is
+	 * "Sets bits n-1:0 and clears the upper bits", where 'n' is the number
+	 * of GP counters.  If there are no GP counters, require KVM to leave
+	 * PERF_GLOBAL_CTRL '0'.  This edge case isn't covered by the SDM, but
+	 * follow the spirit of the architecture and only globally enable GP
+	 * counters, of which there are none.
+	 */
+	if (pmu_version > 1) {
+		uint64_t global_ctrl = rdmsr(MSR_CORE_PERF_GLOBAL_CTRL);
+
+		if (nr_gp_counters)
+			GUEST_ASSERT_EQ(global_ctrl, GENMASK_ULL(nr_gp_counters - 1, 0));
+		else
+			GUEST_ASSERT_EQ(global_ctrl, 0);
+	}
+
+	if (this_cpu_has(X86_FEATURE_PDCM) &&
+	    rdmsr(MSR_IA32_PERF_CAPABILITIES) & PMU_CAP_FW_WRITES)
+		base_msr = MSR_IA32_PMC0;
+	else
+		base_msr = MSR_IA32_PERFCTR0;
+
+	guest_rd_wr_counters(base_msr, MAX_NR_GP_COUNTERS, nr_gp_counters, 0);
+	GUEST_DONE();
+}
+
+static void test_gp_counters(uint8_t pmu_version, uint64_t perf_capabilities,
+			     uint8_t nr_gp_counters)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_gp_counters,
+					 pmu_version, perf_capabilities);
+
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_GP_COUNTERS,
+				nr_gp_counters);
+
+	run_vcpu(vcpu);
+
+	kvm_vm_free(vm);
+}
+
+static void guest_test_fixed_counters(void)
+{
+	uint64_t supported_bitmask = 0;
+	uint8_t nr_fixed_counters = 0;
+	uint8_t i;
+
+	/* Fixed counters require Architectural vPMU Version 2+. */
+	if (guest_get_pmu_version() >= 2)
+		nr_fixed_counters = this_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+
+	/*
+	 * The supported bitmask for fixed counters was introduced in PMU
+	 * version 5.
+	 */
+	if (guest_get_pmu_version() >= 5)
+		supported_bitmask = this_cpu_property(X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK);
+
+	guest_rd_wr_counters(MSR_CORE_PERF_FIXED_CTR0, MAX_NR_FIXED_COUNTERS,
+			     nr_fixed_counters, supported_bitmask);
+
+	for (i = 0; i < MAX_NR_FIXED_COUNTERS; i++) {
+		uint8_t vector;
+		uint64_t val;
+
+		if (i >= nr_fixed_counters && !(supported_bitmask & BIT_ULL(i))) {
+			vector = wrmsr_safe(MSR_CORE_PERF_FIXED_CTR_CTRL,
+					    FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL));
+			__GUEST_ASSERT(vector == GP_VECTOR,
+				       "Expected #GP for counter %u in FIXED_CTR_CTRL", i);
+
+			vector = wrmsr_safe(MSR_CORE_PERF_GLOBAL_CTRL,
+					    FIXED_PMC_GLOBAL_CTRL_ENABLE(i));
+			__GUEST_ASSERT(vector == GP_VECTOR,
+				       "Expected #GP for counter %u in PERF_GLOBAL_CTRL", i);
+			continue;
+		}
+
+		wrmsr(MSR_CORE_PERF_FIXED_CTR0 + i, 0);
+		wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(i, FIXED_PMC_KERNEL));
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(i));
+		__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+		val = rdmsr(MSR_CORE_PERF_FIXED_CTR0 + i);
+
+		GUEST_ASSERT_NE(val, 0);
+	}
+	GUEST_DONE();
+}
+
+static void test_fixed_counters(uint8_t pmu_version, uint64_t perf_capabilities,
+				uint8_t nr_fixed_counters,
+				uint32_t supported_bitmask)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_fixed_counters,
+					 pmu_version, perf_capabilities);
+
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK,
+				supported_bitmask);
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_FIXED_COUNTERS,
+				nr_fixed_counters);
+
+	run_vcpu(vcpu);
+
+	kvm_vm_free(vm);
+}
+
+static void test_intel_counters(void)
+{
+	uint8_t nr_arch_events = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+	uint8_t nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
+	uint8_t nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+	uint8_t pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
+	unsigned int i;
+	uint8_t v, j;
+	uint32_t k;
+
+	const uint64_t perf_caps[] = {
+		0,
+		PMU_CAP_FW_WRITES,
+	};
+
+	/*
+	 * Test up to PMU v5, which is the current maximum version defined by
+	 * Intel, i.e. is the last version that is guaranteed to be backwards
+	 * compatible with KVM's existing behavior.
+	 */
+	uint8_t max_pmu_version = max_t(typeof(pmu_version), pmu_version, 5);
+
+	/*
+	 * Detect the existence of events that aren't supported by selftests.
+	 * This will (obviously) fail any time the kernel adds support for a
+	 * new event, but it's worth paying that price to keep the test fresh.
+	 */
+	TEST_ASSERT(nr_arch_events <= NR_INTEL_ARCH_EVENTS,
+		    "New architectural event(s) detected; please update this test (length = %u, mask = %x)",
+		    nr_arch_events, kvm_cpu_property(X86_PROPERTY_PMU_EVENTS_MASK));
+
+	/*
+	 * Force iterating over known arch events regardless of whether or not
+	 * KVM/hardware supports a given event.
+	 */
+	nr_arch_events = max_t(typeof(nr_arch_events), nr_arch_events, NR_INTEL_ARCH_EVENTS);
+
+	for (v = 0; v <= max_pmu_version; v++) {
+		for (i = 0; i < ARRAY_SIZE(perf_caps); i++) {
+			if (!kvm_has_perf_caps && perf_caps[i])
+				continue;
+
+			pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n",
+				v, perf_caps[i]);
+			/*
+			 * To keep the total runtime reasonable, test every
+			 * possible non-zero, non-reserved bitmap combination
+			 * only with the native PMU version and the full bit
+			 * vector length.
+			 */
+			if (v == pmu_version) {
+				for (k = 1; k < (BIT(nr_arch_events) - 1); k++)
+					test_arch_events(v, perf_caps[i], nr_arch_events, k);
+			}
+			/*
+			 * Test single bits for all PMU version and lengths up
+			 * the number of events +1 (to verify KVM doesn't do
+			 * weird things if the guest length is greater than the
+			 * host length).  Explicitly test a mask of '0' and all
+			 * ones i.e. all events being available and unavailable.
+			 */
+			for (j = 0; j <= nr_arch_events + 1; j++) {
+				test_arch_events(v, perf_caps[i], j, 0);
+				test_arch_events(v, perf_caps[i], j, 0xff);
+
+				for (k = 0; k < nr_arch_events; k++)
+					test_arch_events(v, perf_caps[i], j, BIT(k));
+			}
+
+			pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n",
+				v, perf_caps[i]);
+			for (j = 0; j <= nr_gp_counters; j++)
+				test_gp_counters(v, perf_caps[i], j);
+
+			pr_info("Testing fixed counters, PMU version %u, perf_caps = %lx\n",
+				v, perf_caps[i]);
+			for (j = 0; j <= nr_fixed_counters; j++) {
+				for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++)
+					test_fixed_counters(v, perf_caps[i], j, k);
+			}
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_is_pmu_enabled());
+
+	TEST_REQUIRE(host_cpu_is_intel);
+	TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION));
+	TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0);
+
+	kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
+	kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM);
+	is_forced_emulation_enabled = kvm_is_forced_emulation_enabled();
+
+	test_intel_counters();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index a3bd54b925..3c85d1ae98 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -11,72 +11,18 @@
  */
 
 #define _GNU_SOURCE /* for program_invocation_short_name */
-#include "test_util.h"
+
 #include "kvm_util.h"
+#include "pmu.h"
 #include "processor.h"
-
-/*
- * In lieu of copying perf_event.h into tools...
- */
-#define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
-#define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
-
-/* End of stuff taken from perf_event.h. */
-
-/* Oddly, this isn't in perf_event.h. */
-#define ARCH_PERFMON_BRANCHES_RETIRED		5
+#include "test_util.h"
 
 #define NUM_BRANCHES 42
-#define INTEL_PMC_IDX_FIXED		32
-
-/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */
-#define MAX_FILTER_EVENTS		300
 #define MAX_TEST_EVENTS		10
 
 #define PMU_EVENT_FILTER_INVALID_ACTION		(KVM_PMU_EVENT_DENY + 1)
 #define PMU_EVENT_FILTER_INVALID_FLAGS			(KVM_PMU_EVENT_FLAGS_VALID_MASK << 1)
-#define PMU_EVENT_FILTER_INVALID_NEVENTS		(MAX_FILTER_EVENTS + 1)
-
-/*
- * This is how the event selector and unit mask are stored in an AMD
- * core performance event-select register. Intel's format is similar,
- * but the event selector is only 8 bits.
- */
-#define EVENT(select, umask) ((select & 0xf00UL) << 24 | (select & 0xff) | \
-			      (umask & 0xff) << 8)
-
-/*
- * "Branch instructions retired", from the Intel SDM, volume 3,
- * "Pre-defined Architectural Performance Events."
- */
-
-#define INTEL_BR_RETIRED EVENT(0xc4, 0)
-
-/*
- * "Retired branch instructions", from Processor Programming Reference
- * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors,
- * Preliminary Processor Programming Reference (PPR) for AMD Family
- * 17h Model 31h, Revision B0 Processors, and Preliminary Processor
- * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision
- * B1 Processors Volume 1 of 2.
- */
-
-#define AMD_ZEN_BR_RETIRED EVENT(0xc2, 0)
-
-
-/*
- * "Retired instructions", from Processor Programming Reference
- * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors,
- * Preliminary Processor Programming Reference (PPR) for AMD Family
- * 17h Model 31h, Revision B0 Processors, and Preliminary Processor
- * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision
- * B1 Processors Volume 1 of 2.
- *                      --- and ---
- * "Instructions retired", from the Intel SDM, volume 3,
- * "Pre-defined Architectural Performance Events."
- */
-
-#define INST_RETIRED EVENT(0xc0, 0)
+#define PMU_EVENT_FILTER_INVALID_NEVENTS		(KVM_PMU_EVENT_FILTER_MAX_EVENTS + 1)
 
 struct __kvm_pmu_event_filter {
 	__u32 action;
@@ -84,26 +30,28 @@ struct __kvm_pmu_event_filter {
 	__u32 fixed_counter_bitmap;
 	__u32 flags;
 	__u32 pad[4];
-	__u64 events[MAX_FILTER_EVENTS];
+	__u64 events[KVM_PMU_EVENT_FILTER_MAX_EVENTS];
 };
 
 /*
- * This event list comprises Intel's eight architectural events plus
- * AMD's "retired branch instructions" for Zen[123] (and possibly
- * other AMD CPUs).
+ * This event list comprises Intel's known architectural events, plus AMD's
+ * "retired branch instructions" for Zen1-Zen3 (and* possibly other AMD CPUs).
+ * Note, AMD and Intel use the same encoding for instructions retired.
  */
+kvm_static_assert(INTEL_ARCH_INSTRUCTIONS_RETIRED == AMD_ZEN_INSTRUCTIONS_RETIRED);
+
 static const struct __kvm_pmu_event_filter base_event_filter = {
 	.nevents = ARRAY_SIZE(base_event_filter.events),
 	.events = {
-		EVENT(0x3c, 0),
-		INST_RETIRED,
-		EVENT(0x3c, 1),
-		EVENT(0x2e, 0x4f),
-		EVENT(0x2e, 0x41),
-		EVENT(0xc4, 0),
-		EVENT(0xc5, 0),
-		EVENT(0xa4, 1),
-		AMD_ZEN_BR_RETIRED,
+		INTEL_ARCH_CPU_CYCLES,
+		INTEL_ARCH_INSTRUCTIONS_RETIRED,
+		INTEL_ARCH_REFERENCE_CYCLES,
+		INTEL_ARCH_LLC_REFERENCES,
+		INTEL_ARCH_LLC_MISSES,
+		INTEL_ARCH_BRANCHES_RETIRED,
+		INTEL_ARCH_BRANCHES_MISPREDICTED,
+		INTEL_ARCH_TOPDOWN_SLOTS,
+		AMD_ZEN_BRANCHES_RETIRED,
 	},
 };
 
@@ -165,9 +113,9 @@ static void intel_guest_code(void)
 	for (;;) {
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 		wrmsr(MSR_P6_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
-		      ARCH_PERFMON_EVENTSEL_OS | INTEL_BR_RETIRED);
+		      ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_BRANCHES_RETIRED);
 		wrmsr(MSR_P6_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE |
-		      ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED);
+		      ARCH_PERFMON_EVENTSEL_OS | INTEL_ARCH_INSTRUCTIONS_RETIRED);
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x3);
 
 		run_and_measure_loop(MSR_IA32_PMC0);
@@ -189,9 +137,9 @@ static void amd_guest_code(void)
 	for (;;) {
 		wrmsr(MSR_K7_EVNTSEL0, 0);
 		wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE |
-		      ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BR_RETIRED);
+		      ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_BRANCHES_RETIRED);
 		wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE |
-		      ARCH_PERFMON_EVENTSEL_OS | INST_RETIRED);
+		      ARCH_PERFMON_EVENTSEL_OS | AMD_ZEN_INSTRUCTIONS_RETIRED);
 
 		run_and_measure_loop(MSR_K7_PERFCTR0);
 		GUEST_SYNC(0);
@@ -312,7 +260,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu)
 		.action = KVM_PMU_EVENT_DENY,
 		.nevents = 1,
 		.events = {
-			EVENT(0x1C2, 0),
+			RAW_EVENT(0x1C2, 0),
 		},
 	};
 
@@ -347,9 +295,9 @@ static void test_not_member_deny_list(struct kvm_vcpu *vcpu)
 
 	f.action = KVM_PMU_EVENT_DENY;
 
-	remove_event(&f, INST_RETIRED);
-	remove_event(&f, INTEL_BR_RETIRED);
-	remove_event(&f, AMD_ZEN_BR_RETIRED);
+	remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED);
+	remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED);
+	remove_event(&f, AMD_ZEN_BRANCHES_RETIRED);
 	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_COUNTING_INSTRUCTIONS();
@@ -361,9 +309,9 @@ static void test_not_member_allow_list(struct kvm_vcpu *vcpu)
 
 	f.action = KVM_PMU_EVENT_ALLOW;
 
-	remove_event(&f, INST_RETIRED);
-	remove_event(&f, INTEL_BR_RETIRED);
-	remove_event(&f, AMD_ZEN_BR_RETIRED);
+	remove_event(&f, INTEL_ARCH_INSTRUCTIONS_RETIRED);
+	remove_event(&f, INTEL_ARCH_BRANCHES_RETIRED);
+	remove_event(&f, AMD_ZEN_BRANCHES_RETIRED);
 	test_with_filter(vcpu, &f);
 
 	ASSERT_PMC_NOT_COUNTING_INSTRUCTIONS();
@@ -452,9 +400,9 @@ static bool use_amd_pmu(void)
  *  - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake.
  */
 #define MEM_INST_RETIRED		0xD0
-#define MEM_INST_RETIRED_LOAD		EVENT(MEM_INST_RETIRED, 0x81)
-#define MEM_INST_RETIRED_STORE		EVENT(MEM_INST_RETIRED, 0x82)
-#define MEM_INST_RETIRED_LOAD_STORE	EVENT(MEM_INST_RETIRED, 0x83)
+#define MEM_INST_RETIRED_LOAD		RAW_EVENT(MEM_INST_RETIRED, 0x81)
+#define MEM_INST_RETIRED_STORE		RAW_EVENT(MEM_INST_RETIRED, 0x82)
+#define MEM_INST_RETIRED_LOAD_STORE	RAW_EVENT(MEM_INST_RETIRED, 0x83)
 
 static bool supports_event_mem_inst_retired(void)
 {
@@ -486,9 +434,9 @@ static bool supports_event_mem_inst_retired(void)
  * B1 Processors Volume 1 of 2.
  */
 #define LS_DISPATCH		0x29
-#define LS_DISPATCH_LOAD	EVENT(LS_DISPATCH, BIT(0))
-#define LS_DISPATCH_STORE	EVENT(LS_DISPATCH, BIT(1))
-#define LS_DISPATCH_LOAD_STORE	EVENT(LS_DISPATCH, BIT(2))
+#define LS_DISPATCH_LOAD	RAW_EVENT(LS_DISPATCH, BIT(0))
+#define LS_DISPATCH_STORE	RAW_EVENT(LS_DISPATCH, BIT(1))
+#define LS_DISPATCH_LOAD_STORE	RAW_EVENT(LS_DISPATCH, BIT(2))
 
 #define INCLUDE_MASKED_ENTRY(event_select, mask, match) \
 	KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false)
@@ -729,14 +677,14 @@ static void add_dummy_events(uint64_t *events, int nevents)
 
 static void test_masked_events(struct kvm_vcpu *vcpu)
 {
-	int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS;
-	uint64_t events[MAX_FILTER_EVENTS];
+	int nevents = KVM_PMU_EVENT_FILTER_MAX_EVENTS - MAX_TEST_EVENTS;
+	uint64_t events[KVM_PMU_EVENT_FILTER_MAX_EVENTS];
 
 	/* Run the test cases against a sparse PMU event filter. */
 	run_masked_events_tests(vcpu, events, 0);
 
 	/* Run the test cases against a dense PMU event filter. */
-	add_dummy_events(events, MAX_FILTER_EVENTS);
+	add_dummy_events(events, KVM_PMU_EVENT_FILTER_MAX_EVENTS);
 	run_masked_events_tests(vcpu, events, nevents);
 }
 
@@ -809,20 +757,19 @@ static void test_filter_ioctl(struct kvm_vcpu *vcpu)
 	TEST_ASSERT(!r, "Masking non-existent fixed counters should be allowed");
 }
 
-static void intel_run_fixed_counter_guest_code(uint8_t fixed_ctr_idx)
+static void intel_run_fixed_counter_guest_code(uint8_t idx)
 {
 	for (;;) {
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
-		wrmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx, 0);
+		wrmsr(MSR_CORE_PERF_FIXED_CTR0 + idx, 0);
 
 		/* Only OS_EN bit is enabled for fixed counter[idx]. */
-		wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, BIT_ULL(4 * fixed_ctr_idx));
-		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL,
-		      BIT_ULL(INTEL_PMC_IDX_FIXED + fixed_ctr_idx));
+		wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(idx, FIXED_PMC_KERNEL));
+		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, FIXED_PMC_GLOBAL_CTRL_ENABLE(idx));
 		__asm__ __volatile__("loop ." : "+c"((int){NUM_BRANCHES}));
 		wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
-		GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + fixed_ctr_idx));
+		GUEST_SYNC(rdmsr(MSR_CORE_PERF_FIXED_CTR0 + idx));
 	}
 }
 
@@ -920,7 +867,7 @@ int main(int argc, char *argv[])
 	struct kvm_vcpu *vcpu, *vcpu2 = NULL;
 	struct kvm_vm *vm;
 
-	TEST_REQUIRE(get_kvm_param_bool("enable_pmu"));
+	TEST_REQUIRE(kvm_is_pmu_enabled());
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS));
 
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
index 65ad38b6be..e0f642d2a3 100644
--- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
@@ -434,6 +434,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 
 	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
 	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+
+	close(memfd);
 }
 
 static void usage(const char *cmd)
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
index a49828adf2..0a6dfba390 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -10,11 +10,9 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
-#include "svm_util.h"
+#include "sev.h"
 #include "kselftest.h"
 
-#define SEV_POLICY_ES 0b100
-
 #define NR_MIGRATE_TEST_VCPUS 4
 #define NR_MIGRATE_TEST_VMS 3
 #define NR_LOCK_TESTING_THREADS 3
@@ -22,46 +20,24 @@
 
 bool have_sev_es;
 
-static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error)
-{
-	struct kvm_sev_cmd cmd = {
-		.id = cmd_id,
-		.data = (uint64_t)data,
-		.sev_fd = open_sev_dev_path_or_exit(),
-	};
-	int ret;
-
-	ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd);
-	*fw_error = cmd.error;
-	return ret;
-}
-
-static void sev_ioctl(int vm_fd, int cmd_id, void *data)
-{
-	int ret;
-	__u32 fw_error;
-
-	ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error);
-	TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS,
-		    "%d failed: return code: %d, errno: %d, fw error: %d",
-		    cmd_id, ret, errno, fw_error);
-}
-
 static struct kvm_vm *sev_vm_create(bool es)
 {
 	struct kvm_vm *vm;
-	struct kvm_sev_launch_start start = { 0 };
 	int i;
 
 	vm = vm_create_barebones();
-	sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL);
+	if (!es)
+		sev_vm_init(vm);
+	else
+		sev_es_vm_init(vm);
+
 	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
 		__vm_vcpu_add(vm, i);
+
+	sev_vm_launch(vm, es ? SEV_POLICY_ES : 0);
+
 	if (es)
-		start.policy |= SEV_POLICY_ES;
-	sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start);
-	if (es)
-		sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
 	return vm;
 }
 
@@ -181,7 +157,7 @@ static void test_sev_migrate_parameters(void)
 	sev_vm = sev_vm_create(/* es= */ false);
 	sev_es_vm = sev_vm_create(/* es= */ true);
 	sev_es_vm_no_vmsa = vm_create_barebones();
-	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
+	sev_es_vm_init(sev_es_vm_no_vmsa);
 	__vm_vcpu_add(sev_es_vm_no_vmsa, 1);
 
 	ret = __sev_migrate_from(sev_vm, sev_es_vm);
@@ -230,13 +206,13 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src)
 	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno);
 }
 
-static void verify_mirror_allowed_cmds(int vm_fd)
+static void verify_mirror_allowed_cmds(struct kvm_vm *vm)
 {
 	struct kvm_sev_guest_status status;
+	int cmd_id;
 
-	for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
+	for (cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
 		int ret;
-		__u32 fw_error;
 
 		/*
 		 * These commands are allowed for mirror VMs, all others are
@@ -256,14 +232,14 @@ static void verify_mirror_allowed_cmds(int vm_fd)
 		 * These commands should be disallowed before the data
 		 * parameter is examined so NULL is OK here.
 		 */
-		ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
+		ret = __vm_sev_ioctl(vm, cmd_id, NULL);
 		TEST_ASSERT(
 			ret == -1 && errno == EINVAL,
 			"Should not be able call command: %d. ret: %d, errno: %d",
 			cmd_id, ret, errno);
 	}
 
-	sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status);
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
 }
 
 static void test_sev_mirror(bool es)
@@ -281,9 +257,9 @@ static void test_sev_mirror(bool es)
 		__vm_vcpu_add(dst_vm, i);
 
 	if (es)
-		sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+		vm_sev_ioctl(dst_vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
 
-	verify_mirror_allowed_cmds(dst_vm->fd);
+	verify_mirror_allowed_cmds(dst_vm);
 
 	kvm_vm_free(src_vm);
 	kvm_vm_free(dst_vm);
diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
new file mode 100644
index 0000000000..026779f3ed
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "linux/psp-sev.h"
+#include "sev.h"
+
+
+static void guest_sev_es_code(void)
+{
+	/* TODO: Check CPUID after GHCB-based hypercall support is added. */
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED);
+
+	/*
+	 * TODO: Add GHCB and ucall support for SEV-ES guests.  For now, simply
+	 * force "termination" to signal "done" via the GHCB MSR protocol.
+	 */
+	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
+	__asm__ __volatile__("rep; vmmcall");
+}
+
+static void guest_sev_code(void)
+{
+	GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV));
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
+
+	GUEST_DONE();
+}
+
+static void test_sev(void *guest_code, uint64_t policy)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_sev_create_with_one_vcpu(policy, guest_code, &vcpu);
+
+	for (;;) {
+		vcpu_run(vcpu);
+
+		if (policy & SEV_POLICY_ES) {
+			TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT,
+				    "Wanted SYSTEM_EVENT, got %s",
+				    exit_reason_str(vcpu->run->exit_reason));
+			TEST_ASSERT_EQ(vcpu->run->system_event.type, KVM_SYSTEM_EVENT_SEV_TERM);
+			TEST_ASSERT_EQ(vcpu->run->system_event.ndata, 1);
+			TEST_ASSERT_EQ(vcpu->run->system_event.data[0], GHCB_MSR_TERM_REQ);
+			break;
+		}
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			continue;
+		case UCALL_DONE:
+			return;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		default:
+			TEST_FAIL("Unexpected exit: %s",
+				  exit_reason_str(vcpu->run->exit_reason));
+		}
+	}
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
+
+	test_sev(guest_sev_code, SEV_POLICY_NO_DBG);
+	test_sev(guest_sev_code, 0);
+
+	if (kvm_cpu_has(X86_FEATURE_SEV_ES)) {
+		test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG);
+		test_sev(guest_sev_es_code, SEV_POLICY_ES);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
index 1a46dd7bb3..416207c38a 100644
--- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
@@ -63,7 +63,7 @@ int main(int argc, char *argv[])
 	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vcpu);
 
-	vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR);
+	vcpu_set_cpuid_property(vcpu, X86_PROPERTY_MAX_PHY_ADDR, MAXPHYADDR);
 
 	rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
 	TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index a91b5b145f..adb5593daf 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -17,6 +17,7 @@
 #include <sys/ioctl.h>
 #include <pthread.h>
 
+#include "kvm_test_harness.h"
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
@@ -41,6 +42,8 @@ void guest_code(void)
 		     : "rax", "rbx");
 }
 
+KVM_ONE_VCPU_TEST_SUITE(sync_regs_test);
+
 static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
 {
 #define REG_COMPARE(reg) \
@@ -152,18 +155,15 @@ static noinline void *race_sregs_cr4(void *arg)
 	return NULL;
 }
 
-static void race_sync_regs(void *racer)
+static void race_sync_regs(struct kvm_vcpu *vcpu, void *racer)
 {
 	const time_t TIMEOUT = 2; /* seconds, roughly */
 	struct kvm_x86_state *state;
 	struct kvm_translation tr;
-	struct kvm_vcpu *vcpu;
 	struct kvm_run *run;
-	struct kvm_vm *vm;
 	pthread_t thread;
 	time_t t;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 	run = vcpu->run;
 
 	run->kvm_valid_regs = KVM_SYNC_X86_SREGS;
@@ -205,26 +205,12 @@ static void race_sync_regs(void *racer)
 	TEST_ASSERT_EQ(pthread_join(thread, NULL), 0);
 
 	kvm_x86_state_cleanup(state);
-	kvm_vm_free(vm);
 }
 
-int main(int argc, char *argv[])
+KVM_ONE_VCPU_TEST(sync_regs_test, read_invalid, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_regs regs;
-	struct kvm_sregs sregs;
-	struct kvm_vcpu_events events;
-	int rv, cap;
-
-	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS);
-	TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD));
-
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
-	run = vcpu->run;
+	struct kvm_run *run = vcpu->run;
+	int rv;
 
 	/* Request reading invalid register set from VCPU. */
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
@@ -240,6 +226,12 @@ int main(int argc, char *argv[])
 		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, set_invalid, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	int rv;
 
 	/* Request setting invalid register set into VCPU. */
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
@@ -255,11 +247,19 @@ int main(int argc, char *argv[])
 		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, req_and_verify_all_valid, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vcpu_events events;
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
 
 	/* Request and verify all valid register sets. */
 	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	vcpu_regs_get(vcpu, &regs);
@@ -270,6 +270,19 @@ int main(int argc, char *argv[])
 
 	vcpu_events_get(vcpu, &events);
 	compare_vcpu_events(&events, &run->s.regs.events);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, set_and_verify_various, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vcpu_events events;
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Set and verify various register values. */
 	run->s.regs.regs.rbx = 0xBAD1DEA;
@@ -278,7 +291,7 @@ int main(int argc, char *argv[])
 
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xBAD1DEA + 1,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -295,6 +308,11 @@ int main(int argc, char *argv[])
 
 	vcpu_events_get(vcpu, &events);
 	compare_vcpu_events(&events, &run->s.regs.events);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_dirty_regs_bits, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
 
 	/* Clear kvm_dirty_regs bits, verify new s.regs values are
 	 * overwritten with existing guest values.
@@ -302,11 +320,22 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.rbx = 0xDEADBEEF;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx != 0xDEADBEEF,
 		    "rbx sync regs value incorrect 0x%llx.",
 		    run->s.regs.regs.rbx);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_and_dirty_regs, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
 	 * Verify s.regs values are not overwritten with existing guest values
@@ -315,9 +344,10 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.rbx = 0xAAAA;
+	vcpu_regs_get(vcpu, &regs);
 	regs.rbx = 0xBAC0;
 	vcpu_regs_set(vcpu, &regs);
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -326,6 +356,17 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(regs.rbx == 0xBAC0 + 1,
 		    "rbx guest value incorrect 0x%llx.",
 		    regs.rbx);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_regs_bits, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
 	 * with existing guest values but that guest values are overwritten
@@ -334,7 +375,7 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
 	run->s.regs.regs.rbx = 0xBBBB;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -343,12 +384,30 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(regs.rbx == 0xBBBB + 1,
 		    "rbx guest value incorrect 0x%llx.",
 		    regs.rbx);
+}
 
-	kvm_vm_free(vm);
+KVM_ONE_VCPU_TEST(sync_regs_test, race_cr4, guest_code)
+{
+	race_sync_regs(vcpu, race_sregs_cr4);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, race_exc, guest_code)
+{
+	race_sync_regs(vcpu, race_events_exc);
+}
 
-	race_sync_regs(race_sregs_cr4);
-	race_sync_regs(race_events_exc);
-	race_sync_regs(race_events_inj_pen);
+KVM_ONE_VCPU_TEST(sync_regs_test, race_inj_pen, guest_code)
+{
+	race_sync_regs(vcpu, race_events_inj_pen);
+}
+
+int main(int argc, char *argv[])
+{
+	int cap;
+
+	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
+	TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS);
+	TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD));
 
-	return 0;
+	return test_harness_run(argc, argv);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
index 3533dc2fbf..f4f61a2d24 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
@@ -8,14 +8,12 @@
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <sys/ioctl.h>
 
+#include "kvm_test_harness.h"
 #include "test_util.h"
 #include "kvm_util.h"
 #include "vmx.h"
 
-/* Forced emulation prefix, used to invoke the emulator unconditionally. */
-#define KVM_FEP "ud2; .byte 'k', 'v', 'm';"
-#define KVM_FEP_LENGTH 5
-static int fep_available = 1;
+static bool fep_available;
 
 #define MSR_NON_EXISTENT 0x474f4f00
 
@@ -260,13 +258,6 @@ static void guest_code_filter_allow(void)
 	GUEST_ASSERT(data == 2);
 	GUEST_ASSERT(guest_exception_count == 0);
 
-	/*
-	 * Test to see if the instruction emulator is available (ie: the module
-	 * parameter 'kvm.force_emulation_prefix=1' is set).  This instruction
-	 * will #UD if it isn't available.
-	 */
-	__asm__ __volatile__(KVM_FEP "nop");
-
 	if (fep_available) {
 		/* Let userspace know we aren't done. */
 		GUEST_SYNC(0);
@@ -388,12 +379,6 @@ static void guest_fep_gp_handler(struct ex_regs *regs)
 			   &em_wrmsr_start, &em_wrmsr_end);
 }
 
-static void guest_ud_handler(struct ex_regs *regs)
-{
-	fep_available = 0;
-	regs->rip += KVM_FEP_LENGTH;
-}
-
 static void check_for_guest_assert(struct kvm_vcpu *vcpu)
 {
 	struct ucall uc;
@@ -527,13 +512,15 @@ static void run_guest_then_process_ucall_done(struct kvm_vcpu *vcpu)
 	process_ucall_done(vcpu);
 }
 
-static void test_msr_filter_allow(void)
+KVM_ONE_VCPU_TEST_SUITE(user_msr);
+
+KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
+	struct kvm_vm *vm = vcpu->vm;
+	uint64_t cmd;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_allow);
+	sync_global_to_guest(vm, fep_available);
 
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
@@ -561,11 +548,11 @@ static void test_msr_filter_allow(void)
 	run_guest_then_process_wrmsr(vcpu, MSR_NON_EXISTENT);
 	run_guest_then_process_rdmsr(vcpu, MSR_NON_EXISTENT);
 
-	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
 	vcpu_run(vcpu);
-	vm_install_exception_handler(vm, UD_VECTOR, NULL);
+	cmd = process_ucall(vcpu);
 
-	if (process_ucall(vcpu) != UCALL_DONE) {
+	if (fep_available) {
+		TEST_ASSERT_EQ(cmd, UCALL_SYNC);
 		vm_install_exception_handler(vm, GP_VECTOR, guest_fep_gp_handler);
 
 		/* Process emulated rdmsr and wrmsr instructions. */
@@ -583,10 +570,9 @@ static void test_msr_filter_allow(void)
 		/* Confirm the guest completed without issues. */
 		run_guest_then_process_ucall_done(vcpu);
 	} else {
+		TEST_ASSERT_EQ(cmd, UCALL_DONE);
 		printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n");
 	}
-
-	kvm_vm_free(vm);
 }
 
 static int handle_ucall(struct kvm_vcpu *vcpu)
@@ -646,16 +632,12 @@ static void handle_wrmsr(struct kvm_run *run)
 	}
 }
 
-static void test_msr_filter_deny(void)
+KVM_ONE_VCPU_TEST(user_msr, msr_filter_deny, guest_code_filter_deny)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
+	struct kvm_vm *vm = vcpu->vm;
+	struct kvm_run *run = vcpu->run;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_deny);
-	run = vcpu->run;
-
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
 	vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_INVAL |
@@ -689,18 +671,13 @@ static void test_msr_filter_deny(void)
 done:
 	TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space");
 	TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space");
-
-	kvm_vm_free(vm);
 }
 
-static void test_msr_permission_bitmap(void)
+KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
+	struct kvm_vm *vm = vcpu->vm;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_permission_bitmap);
-
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
 	vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER);
@@ -715,8 +692,6 @@ static void test_msr_permission_bitmap(void)
 	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs);
 	run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE);
 	run_guest_then_process_ucall_done(vcpu);
-
-	kvm_vm_free(vm);
 }
 
 #define test_user_exit_msr_ioctl(vm, cmd, arg, flag, valid_mask)	\
@@ -786,31 +761,20 @@ static void run_msr_filter_flag_test(struct kvm_vm *vm)
 }
 
 /* Test that attempts to write to the unused bits in a flag fails. */
-static void test_user_exit_msr_flags(void)
+KVM_ONE_VCPU_TEST(user_msr, user_exit_msr_flags, NULL)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	vm = vm_create_with_one_vcpu(&vcpu, NULL);
+	struct kvm_vm *vm = vcpu->vm;
 
 	/* Test flags for KVM_CAP_X86_USER_SPACE_MSR. */
 	run_user_space_msr_flag_test(vm);
 
 	/* Test flags and range flags for KVM_X86_SET_MSR_FILTER. */
 	run_msr_filter_flag_test(vm);
-
-	kvm_vm_free(vm);
 }
 
 int main(int argc, char *argv[])
 {
-	test_msr_filter_allow();
-
-	test_msr_filter_deny();
-
-	test_msr_permission_bitmap();
+	fep_available = kvm_is_forced_emulation_enabled();
 
-	test_user_exit_msr_flags();
-
-	return 0;
+	return test_harness_run(argc, argv);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 7f6f5f23fb..977948fd52 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -28,16 +28,16 @@
 #define NESTED_TEST_MEM1		0xc0001000
 #define NESTED_TEST_MEM2		0xc0002000
 
-static void l2_guest_code(void)
+static void l2_guest_code(u64 *a, u64 *b)
 {
-	*(volatile uint64_t *)NESTED_TEST_MEM1;
-	*(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+	READ_ONCE(*a);
+	WRITE_ONCE(*a, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
-	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	WRITE_ONCE(*b, 1);
 	GUEST_SYNC(true);
 	GUEST_SYNC(false);
 
@@ -45,17 +45,33 @@ static void l2_guest_code(void)
 	vmcall();
 }
 
+static void l2_guest_code_ept_enabled(void)
+{
+	l2_guest_code((u64 *)NESTED_TEST_MEM1, (u64 *)NESTED_TEST_MEM2);
+}
+
+static void l2_guest_code_ept_disabled(void)
+{
+	/* Access the same L1 GPAs as l2_guest_code_ept_enabled() */
+	l2_guest_code((u64 *)GUEST_TEST_MEM, (u64 *)GUEST_TEST_MEM);
+}
+
 void l1_guest_code(struct vmx_pages *vmx)
 {
 #define L2_GUEST_STACK_SIZE 64
 	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	void *l2_rip;
 
 	GUEST_ASSERT(vmx->vmcs_gpa);
 	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
 	GUEST_ASSERT(load_vmcs(vmx));
 
-	prepare_vmcs(vmx, l2_guest_code,
-		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+	if (vmx->eptp_gpa)
+		l2_rip = l2_guest_code_ept_enabled;
+	else
+		l2_rip = l2_guest_code_ept_disabled;
+
+	prepare_vmcs(vmx, l2_rip, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
 
 	GUEST_SYNC(false);
 	GUEST_ASSERT(!vmlaunch());
@@ -64,7 +80,7 @@ void l1_guest_code(struct vmx_pages *vmx)
 	GUEST_DONE();
 }
 
-int main(int argc, char *argv[])
+static void test_vmx_dirty_log(bool enable_ept)
 {
 	vm_vaddr_t vmx_pages_gva = 0;
 	struct vmx_pages *vmx;
@@ -76,8 +92,7 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	bool done = false;
 
-	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
-	TEST_REQUIRE(kvm_cpu_has_ept());
+	pr_info("Nested EPT: %s\n", enable_ept ? "enabled" : "disabled");
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
@@ -103,11 +118,16 @@ int main(int argc, char *argv[])
 	 *
 	 * Note that prepare_eptp should be called only L1's GPA map is done,
 	 * meaning after the last call to virt_map.
+	 *
+	 * When EPT is disabled, the L2 guest code will still access the same L1
+	 * GPAs as the EPT enabled case.
 	 */
-	prepare_eptp(vmx, vm, 0);
-	nested_map_memslot(vmx, vm, 0);
-	nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
-	nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	if (enable_ept) {
+		prepare_eptp(vmx, vm, 0);
+		nested_map_memslot(vmx, vm, 0);
+		nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096);
+		nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096);
+	}
 
 	bmap = bitmap_zalloc(TEST_MEM_PAGES);
 	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
@@ -148,3 +168,15 @@ int main(int argc, char *argv[])
 		}
 	}
 }
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+
+	test_vmx_dirty_log(/*enable_ept=*/false);
+
+	if (kvm_cpu_has_ept())
+		test_vmx_dirty_log(/*enable_ept=*/true);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index 2a8d4ac2f0..ea0cb3cae0 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -15,10 +15,11 @@
 
 #include <linux/bitmap.h>
 
+#include "kvm_test_harness.h"
 #include "kvm_util.h"
 #include "vmx.h"
 
-union perf_capabilities {
+static union perf_capabilities {
 	struct {
 		u64	lbr_format:6;
 		u64	pebs_trap:1;
@@ -32,7 +33,7 @@ union perf_capabilities {
 		u64	anythread_deprecated:1;
 	};
 	u64	capabilities;
-};
+} host_cap;
 
 /*
  * The LBR format and most PEBS features are immutable, all other features are
@@ -73,19 +74,19 @@ static void guest_code(uint64_t current_val)
 	GUEST_DONE();
 }
 
+KVM_ONE_VCPU_TEST_SUITE(vmx_pmu_caps);
+
 /*
  * Verify that guest WRMSRs to PERF_CAPABILITIES #GP regardless of the value
  * written, that the guest always sees the userspace controlled value, and that
  * PERF_CAPABILITIES is immutable after KVM_RUN.
  */
-static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, guest_wrmsr_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 	struct ucall uc;
 	int r, i;
 
-	vm_init_descriptor_tables(vm);
+	vm_init_descriptor_tables(vcpu->vm);
 	vcpu_init_descriptor_tables(vcpu);
 
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
@@ -117,31 +118,21 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
 		TEST_ASSERT(!r, "Post-KVM_RUN write '0x%llx'didn't fail",
 			    host_cap.capabilities ^ BIT_ULL(i));
 	}
-
-	kvm_vm_free(vm);
 }
 
 /*
  * Verify KVM allows writing PERF_CAPABILITIES with all KVM-supported features
  * enabled, as well as '0' (to disable all features).
  */
-static void test_basic_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, basic_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
-
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0);
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
-
-	kvm_vm_free(vm);
 }
 
-static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code)
 {
 	const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities;
-
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	int bit;
 
 	for_each_set_bit(bit, &fungible_caps, 64) {
@@ -150,8 +141,6 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
 			     host_cap.capabilities & ~BIT_ULL(bit));
 	}
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
-
-	kvm_vm_free(vm);
 }
 
 /*
@@ -160,14 +149,11 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
  * separately as they are multi-bit values, e.g. toggling or setting a single
  * bit can generate a false positive without dedicated safeguards.
  */
-static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, immutable_perf_capabilities, guest_code)
 {
 	const uint64_t reserved_caps = (~host_cap.capabilities |
 					immutable_caps.capabilities) &
 				       ~format_caps.capabilities;
-
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	union perf_capabilities val = host_cap;
 	int r, bit;
 
@@ -201,8 +187,6 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
 		TEST_ASSERT(!r, "Bad PEBS FMT = 0x%x didn't fail, host = 0x%x",
 			    val.pebs_format, host_cap.pebs_format);
 	}
-
-	kvm_vm_free(vm);
 }
 
 /*
@@ -211,17 +195,13 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
  * LBR_TOS as those bits are writable across all uarch implementations (arch
  * LBRs will need to poke a different MSR).
  */
-static void test_lbr_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
 	int r;
 
 	if (!host_cap.lbr_format)
 		return;
 
-	vm = vm_create_with_one_vcpu(&vcpu, NULL);
-
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
 	vcpu_set_msr(vcpu, MSR_LBR_TOS, 7);
 
@@ -229,15 +209,11 @@ static void test_lbr_perf_capabilities(union perf_capabilities host_cap)
 
 	r = _vcpu_set_msr(vcpu, MSR_LBR_TOS, 7);
 	TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU");
-
-	kvm_vm_free(vm);
 }
 
 int main(int argc, char *argv[])
 {
-	union perf_capabilities host_cap;
-
-	TEST_REQUIRE(get_kvm_param_bool("enable_pmu"));
+	TEST_REQUIRE(kvm_is_pmu_enabled());
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM));
 
 	TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION));
@@ -248,9 +224,5 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(host_cap.full_width_write,
 		    "Full-width writes should always be supported");
 
-	test_basic_perf_capabilities(host_cap);
-	test_fungible_perf_capabilities(host_cap);
-	test_immutable_perf_capabilities(host_cap);
-	test_guest_wrmsr_perf_capabilities(host_cap);
-	test_lbr_perf_capabilities(host_cap);
+	return test_harness_run(argc, argv);
 }
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 9ec9ab60b6..d2ea0435f4 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -62,6 +62,7 @@ enum {
 	TEST_POLL_TIMEOUT,
 	TEST_POLL_MASKED,
 	TEST_POLL_WAKE,
+	SET_VCPU_INFO,
 	TEST_TIMER_PAST,
 	TEST_LOCKING_SEND_RACE,
 	TEST_LOCKING_POLL_RACE,
@@ -321,6 +322,10 @@ static void guest_code(void)
 
 	GUEST_SYNC(TEST_POLL_WAKE);
 
+	/* Set the vcpu_info to point at exactly the place it already is to
+	 * make sure the attribute is functional. */
+	GUEST_SYNC(SET_VCPU_INFO);
+
 	/* A timer wake an *unmasked* port which should wake us with an
 	 * actual interrupt, while we're polling on a different port. */
 	ports[0]++;
@@ -389,6 +394,7 @@ static int cmp_timespec(struct timespec *a, struct timespec *b)
 		return 0;
 }
 
+static struct shared_info *shinfo;
 static struct vcpu_info *vinfo;
 static struct kvm_vcpu *vcpu;
 
@@ -404,20 +410,38 @@ static void *juggle_shinfo_state(void *arg)
 {
 	struct kvm_vm *vm = (struct kvm_vm *)arg;
 
-	struct kvm_xen_hvm_attr cache_activate = {
+	struct kvm_xen_hvm_attr cache_activate_gfn = {
 		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
 		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE
 	};
 
-	struct kvm_xen_hvm_attr cache_deactivate = {
+	struct kvm_xen_hvm_attr cache_deactivate_gfn = {
 		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
 		.u.shared_info.gfn = KVM_XEN_INVALID_GFN
 	};
 
+	struct kvm_xen_hvm_attr cache_activate_hva = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA,
+		.u.shared_info.hva = (unsigned long)shinfo
+	};
+
+	struct kvm_xen_hvm_attr cache_deactivate_hva = {
+		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+		.u.shared_info.hva = 0
+	};
+
+	int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM);
+
 	for (;;) {
-		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate);
-		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate);
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_gfn);
 		pthread_testcancel();
+		__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_gfn);
+
+		if (xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA) {
+			__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate_hva);
+			pthread_testcancel();
+			__vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate_hva);
+		}
 	}
 
 	return NULL;
@@ -442,6 +466,7 @@ int main(int argc, char *argv[])
 	bool do_runstate_flag = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG);
 	bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL);
 	bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND);
+	bool has_shinfo_hva = !!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA);
 
 	clock_gettime(CLOCK_REALTIME, &min_ts);
 
@@ -452,7 +477,7 @@ int main(int argc, char *argv[])
 				    SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 3, 0);
 	virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 3);
 
-	struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
+	shinfo = addr_gpa2hva(vm, SHINFO_VADDR);
 
 	int zero_fd = open("/dev/zero", O_RDONLY);
 	TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero");
@@ -488,10 +513,16 @@ int main(int argc, char *argv[])
 			    "Failed to read back RUNSTATE_UPDATE_FLAG attr");
 	}
 
-	struct kvm_xen_hvm_attr ha = {
-		.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
-		.u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE,
-	};
+	struct kvm_xen_hvm_attr ha = {};
+
+	if (has_shinfo_hva) {
+		ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA;
+		ha.u.shared_info.hva = (unsigned long)shinfo;
+	} else {
+		ha.type = KVM_XEN_ATTR_TYPE_SHARED_INFO;
+		ha.u.shared_info.gfn = SHINFO_ADDR / PAGE_SIZE;
+	}
+
 	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha);
 
 	/*
@@ -862,6 +893,16 @@ int main(int argc, char *argv[])
 				alarm(1);
 				break;
 
+			case SET_VCPU_INFO:
+				if (has_shinfo_hva) {
+					struct kvm_xen_vcpu_attr vih = {
+						.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA,
+						.u.hva = (unsigned long)vinfo
+					};
+					vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &vih);
+				}
+				break;
+
 			case TEST_TIMER_PAST:
 				TEST_ASSERT(!evtchn_irq_expected,
 					    "Expected event channel IRQ but it didn't happen");