Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Proper emulation of the OSLock feature of the debug architecture

   - Scalibility improvements for the MMU lock when dirty logging is on

   - New VMID allocator, which will eventually help with SVA in VMs

   - Better support for PMUs in heterogenous systems

   - PSCI 1.1 support, enabling support for SYSTEM_RESET2

   - Implement CONFIG_DEBUG_LIST at EL2

   - Make CONFIG_ARM64_ERRATUM_2077057 default y

   - Reduce the overhead of VM exit when no interrupt is pending

   - Remove traces of 32bit ARM host support from the documentation

   - Updated vgic selftests

   - Various cleanups, doc updates and spelling fixes

  RISC-V:
   - Prevent KVM_COMPAT from being selected

   - Optimize __kvm_riscv_switch_to() implementation

   - RISC-V SBI v0.3 support

  s390:
   - memop selftest

   - fix SCK locking

   - adapter interruptions virtualization for secure guests

   - add Claudio Imbrenda as maintainer

   - first step to do proper storage key checking

  x86:
   - Continue switching kvm_x86_ops to static_call(); introduce
     static_call_cond() and __static_call_ret0 when applicable.

   - Cleanup unused arguments in several functions

   - Synthesize AMD 0x80000021 leaf

   - Fixes and optimization for Hyper-V sparse-bank hypercalls

   - Implement Hyper-V's enlightened MSR bitmap for nested SVM

   - Remove MMU auditing

   - Eager splitting of page tables (new aka "TDP" MMU only) when dirty
     page tracking is enabled

   - Cleanup the implementation of the guest PGD cache

   - Preparation for the implementation of Intel IPI virtualization

   - Fix some segment descriptor checks in the emulator

   - Allow AMD AVIC support on systems with physical APIC ID above 255

   - Better API to disable virtualization quirks

   - Fixes and optimizations for the zapping of page tables:

      - Zap roots in two passes, avoiding RCU read-side critical
        sections that last too long for very large guests backed by 4
        KiB SPTEs.

      - Zap invalid and defunct roots asynchronously via
        concurrency-managed work queue.

      - Allowing yielding when zapping TDP MMU roots in response to the
        root's last reference being put.

      - Batch more TLB flushes with an RCU trick. Whoever frees the
        paging structure now holds RCU as a proxy for all vCPUs running
        in the guest, i.e. to prolongs the grace period on their behalf.
        It then kicks the the vCPUs out of guest mode before doing
        rcu_read_unlock().

  Generic:
   - Introduce __vcalloc and use it for very large allocations that need
     memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (246 commits)
  KVM: use kvcalloc for array allocations
  KVM: x86: Introduce KVM_CAP_DISABLE_QUIRKS2
  kvm: x86: Require const tsc for RT
  KVM: x86: synthesize CPUID leaf 0x80000021h if useful
  KVM: x86: add support for CPUID leaf 0x80000021
  KVM: x86: do not use KVM_X86_OP_OPTIONAL_RET0 for get_mt_mask
  Revert "KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()"
  kvm: x86/mmu: Flush TLB before zap_gfn_range releases RCU
  KVM: arm64: fix typos in comments
  KVM: arm64: Generalise VM features into a set of flags
  KVM: s390: selftests: Add error memop tests
  KVM: s390: selftests: Add more copy memop tests
  KVM: s390: selftests: Add named stages for memop test
  KVM: s390: selftests: Add macro as abstraction for MEM_OP
  KVM: s390: selftests: Split memop tests
  KVM: s390x: fix SCK locking
  RISC-V: KVM: Implement SBI HSM suspend call
  RISC-V: KVM: Add common kvm_riscv_vcpu_wfi() function
  RISC-V: Add SBI HSM suspend related defines
  RISC-V: KVM: Implement SBI v0.3 SRST extension
  ...

27 files changed, 2054 insertions, 243 deletions

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 62f9b781545b..d1e8f5237469 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -8,6 +8,7 @@
 /s390x/memop
 /s390x/resets
 /s390x/sync_regs_test
+/s390x/tprot
 /x86_64/amx_test
 /x86_64/cpuid_test
 /x86_64/cr4_cpuid_sync_test
@@ -46,6 +47,7 @@
 /x86_64/vmx_tsc_adjust_test
 /x86_64/vmx_nested_tsc_scaling_test
 /x86_64/xapic_ipi_test
+/x86_64/xapic_state_test
 /x86_64/xen_shinfo_test
 /x86_64/xen_vmcall_test
 /x86_64/xss_msr_test
@@ -57,6 +59,7 @@
 /hardware_disable_test
 /kvm_create_max_vcpus
 /kvm_page_table_test
+/max_guest_memory_test
 /memslot_modification_stress_test
 /memslot_perf_test
 /rseq_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index b970397f725c..21c2dbd21a81 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -51,6 +51,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
 TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
@@ -76,6 +77,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test
 TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test
+TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
@@ -91,6 +93,7 @@ TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += hardware_disable_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += kvm_page_table_test
+TEST_GEN_PROGS_x86_64 += max_guest_memory_test
 TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
 TEST_GEN_PROGS_x86_64 += memslot_perf_test
 TEST_GEN_PROGS_x86_64 += rseq_test
@@ -120,6 +123,7 @@ TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test
 TEST_GEN_PROGS_s390x = s390x/memop
 TEST_GEN_PROGS_s390x += s390x/resets
 TEST_GEN_PROGS_s390x += s390x/sync_regs_test
+TEST_GEN_PROGS_s390x += s390x/tprot
 TEST_GEN_PROGS_s390x += demand_paging_test
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index ea189d83abf7..63b2178210c4 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -23,7 +23,7 @@
 #define SPSR_D		(1 << 9)
 #define SPSR_SS		(1 << 21)
 
-extern unsigned char sw_bp, hw_bp, bp_svc, bp_brk, hw_wp, ss_start;
+extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start;
 static volatile uint64_t sw_bp_addr, hw_bp_addr;
 static volatile uint64_t wp_addr, wp_data_addr;
 static volatile uint64_t svc_addr;
@@ -47,6 +47,14 @@ static void reset_debug_state(void)
 	isb();
 }
 
+static void enable_os_lock(void)
+{
+	write_sysreg(1, oslar_el1);
+	isb();
+
+	GUEST_ASSERT(read_sysreg(oslsr_el1) & 2);
+}
+
 static void install_wp(uint64_t addr)
 {
 	uint32_t wcr;
@@ -99,6 +107,7 @@ static void guest_code(void)
 	GUEST_SYNC(0);
 
 	/* Software-breakpoint */
+	reset_debug_state();
 	asm volatile("sw_bp: brk #0");
 	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp));
 
@@ -152,6 +161,51 @@ static void guest_code(void)
 	GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4);
 	GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8);
 
+	GUEST_SYNC(6);
+
+	/* OS Lock does not block software-breakpoint */
+	reset_debug_state();
+	enable_os_lock();
+	sw_bp_addr = 0;
+	asm volatile("sw_bp2: brk #0");
+	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp2));
+
+	GUEST_SYNC(7);
+
+	/* OS Lock blocking hardware-breakpoint */
+	reset_debug_state();
+	enable_os_lock();
+	install_hw_bp(PC(hw_bp2));
+	hw_bp_addr = 0;
+	asm volatile("hw_bp2: nop");
+	GUEST_ASSERT_EQ(hw_bp_addr, 0);
+
+	GUEST_SYNC(8);
+
+	/* OS Lock blocking watchpoint */
+	reset_debug_state();
+	enable_os_lock();
+	write_data = '\0';
+	wp_data_addr = 0;
+	install_wp(PC(write_data));
+	write_data = 'x';
+	GUEST_ASSERT_EQ(write_data, 'x');
+	GUEST_ASSERT_EQ(wp_data_addr, 0);
+
+	GUEST_SYNC(9);
+
+	/* OS Lock blocking single-step */
+	reset_debug_state();
+	enable_os_lock();
+	ss_addr[0] = 0;
+	install_ss();
+	ss_idx = 0;
+	asm volatile("mrs x0, esr_el1\n\t"
+		     "add x0, x0, #1\n\t"
+		     "msr daifset, #8\n\t"
+		     : : : "x0");
+	GUEST_ASSERT_EQ(ss_addr[0], 0);
+
 	GUEST_DONE();
 }
 
@@ -223,7 +277,7 @@ int main(int argc, char *argv[])
 	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
 				ESR_EC_SVC64, guest_svc_handler);
 
-	for (stage = 0; stage < 7; stage++) {
+	for (stage = 0; stage < 11; stage++) {
 		vcpu_run(vm, VCPU_ID);
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f769fc6cd927..f12147c43464 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -760,6 +760,7 @@ static __u64 base_regs[] = {
 	ARM64_SYS_REG(2, 0, 0, 15, 5),
 	ARM64_SYS_REG(2, 0, 0, 15, 6),
 	ARM64_SYS_REG(2, 0, 0, 15, 7),
+	ARM64_SYS_REG(2, 0, 1, 1, 4),	/* OSLSR_EL1 */
 	ARM64_SYS_REG(2, 4, 0, 7, 0),	/* DBGVCR32_EL2 */
 	ARM64_SYS_REG(3, 0, 0, 0, 5),	/* MPIDR_EL1 */
 	ARM64_SYS_REG(3, 0, 0, 1, 0),	/* ID_PFR0_EL1 */
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 7eca97799917..554ca649d470 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -306,7 +306,8 @@ static void guest_restore_active(struct test_args *args,
 	uint32_t prio, intid, ap1r;
 	int i;
 
-	/* Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
+	/*
+	 * Set the priorities of the first (KVM_NUM_PRIOS - 1) IRQs
 	 * in descending order, so intid+1 can preempt intid.
 	 */
 	for (i = 0, prio = (num - 1) * 8; i < num; i++, prio -= 8) {
@@ -315,7 +316,8 @@ static void guest_restore_active(struct test_args *args,
 		gic_set_priority(intid, prio);
 	}
 
-	/* In a real migration, KVM would restore all GIC state before running
+	/*
+	 * In a real migration, KVM would restore all GIC state before running
 	 * guest code.
 	 */
 	for (i = 0; i < num; i++) {
@@ -472,10 +474,10 @@ static void test_restore_active(struct test_args *args, struct kvm_inject_desc *
 		guest_restore_active(args, MIN_SPI, 4, f->cmd);
 }
 
-static void guest_code(struct test_args args)
+static void guest_code(struct test_args *args)
 {
-	uint32_t i, nr_irqs = args.nr_irqs;
-	bool level_sensitive = args.level_sensitive;
+	uint32_t i, nr_irqs = args->nr_irqs;
+	bool level_sensitive = args->level_sensitive;
 	struct kvm_inject_desc *f, *inject_fns;
 
 	gic_init(GIC_V3, 1, dist, redist);
@@ -484,11 +486,11 @@ static void guest_code(struct test_args args)
 		gic_irq_enable(i);
 
 	for (i = MIN_SPI; i < nr_irqs; i++)
-		gic_irq_set_config(i, !args.level_sensitive);
+		gic_irq_set_config(i, !level_sensitive);
 
-	gic_set_eoi_split(args.eoi_split);
+	gic_set_eoi_split(args->eoi_split);
 
-	reset_priorities(&args);
+	reset_priorities(args);
 	gic_set_priority_mask(CPU_PRIO_MASK);
 
 	inject_fns  = level_sensitive ? inject_level_fns
@@ -497,17 +499,18 @@ static void guest_code(struct test_args args)
 	local_irq_enable();
 
 	/* Start the tests. */
-	for_each_supported_inject_fn(&args, inject_fns, f) {
-		test_injection(&args, f);
-		test_preemption(&args, f);
-		test_injection_failure(&args, f);
+	for_each_supported_inject_fn(args, inject_fns, f) {
+		test_injection(args, f);
+		test_preemption(args, f);
+		test_injection_failure(args, f);
 	}
 
-	/* Restore the active state of IRQs. This would happen when live
+	/*
+	 * Restore the active state of IRQs. This would happen when live
 	 * migrating IRQs in the middle of being handled.
 	 */
-	for_each_supported_activate_fn(&args, set_active_fns, f)
-		test_restore_active(&args, f);
+	for_each_supported_activate_fn(args, set_active_fns, f)
+		test_restore_active(args, f);
 
 	GUEST_DONE();
 }
@@ -573,8 +576,8 @@ static void kvm_set_gsi_routing_irqchip_check(struct kvm_vm *vm,
 		kvm_gsi_routing_write(vm, routing);
 	} else {
 		ret = _kvm_gsi_routing_write(vm, routing);
-		/* The kernel only checks for KVM_IRQCHIP_NUM_PINS. */
-		if (intid >= KVM_IRQCHIP_NUM_PINS)
+		/* The kernel only checks e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS */
+		if (((uint64_t)intid + num - 1 - MIN_SPI) >= KVM_IRQCHIP_NUM_PINS)
 			TEST_ASSERT(ret != 0 && errno == EINVAL,
 				"Bad intid %u did not cause KVM_SET_GSI_ROUTING "
 				"error: rc: %i errno: %i", intid, ret, errno);
@@ -739,6 +742,7 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 	int gic_fd;
 	struct kvm_vm *vm;
 	struct kvm_inject_args inject_args;
+	vm_vaddr_t args_gva;
 
 	struct test_args args = {
 		.nr_irqs = nr_irqs,
@@ -757,7 +761,9 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
 	vcpu_init_descriptor_tables(vm, VCPU_ID);
 
 	/* Setup the guest args page (so it gets the args). */
-	vcpu_args_set(vm, 0, 1, args);
+	args_gva = vm_vaddr_alloc_page(vm);
+	memcpy(addr_gva2hva(vm, args_gva), &args, sizeof(args));
+	vcpu_args_set(vm, 0, 1, args_gva);
 
 	gic_fd = vgic_v3_setup(vm, 1, nr_irqs,
 			GICD_BASE_GPA, GICR_BASE_GPA);
@@ -841,7 +847,8 @@ int main(int argc, char **argv)
 		}
 	}
 
-	/* If the user just specified nr_irqs and/or gic_version, then run all
+	/*
+	 * If the user just specified nr_irqs and/or gic_version, then run all
 	 * combinations.
 	 */
 	if (default_args) {
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 1954b964d1cf..c9d9e513ca04 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -18,6 +18,12 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+#ifdef __aarch64__
+#include "aarch64/vgic.h"
+
+#define GICD_BASE_GPA			0x8000000ULL
+#define GICR_BASE_GPA			0x80A0000ULL
+#endif
 
 /* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
 #define TEST_HOST_LOOP_N		2UL
@@ -200,6 +206,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
+#ifdef __aarch64__
+	vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+#endif
+
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
@@ -298,12 +308,18 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-p offset] "
+	printf("usage: %s [-h] [-i iterations] [-p offset] [-g]"
 	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
 	       "[-x memslots]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
+	printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n"
+	       "     makes KVM_GET_DIRTY_LOG clear the dirty log (i.e.\n"
+	       "     KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE is not enabled)\n"
+	       "     and writes will be tracked as soon as dirty logging is\n"
+	       "     enabled on the memslot (i.e. KVM_DIRTY_LOG_INITIALLY_SET\n"
+	       "     is not enabled).\n");
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
 	guest_modes_help();
@@ -343,8 +359,11 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:os:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) {
 		switch (opt) {
+		case 'g':
+			dirty_log_manual_caps = 0;
+			break;
 		case 'i':
 			p.iterations = atoi(optarg);
 			break;
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 4ed6aa049a91..92cef0ffb19e 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -123,6 +123,7 @@ int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
 		       size_t len);
 
 void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename);
+int kvm_memfd_alloc(size_t size, bool hugepages);
 
 void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
 
@@ -147,6 +148,10 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid,
 
 void vm_create_irqchip(struct kvm_vm *vm);
 
+void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+			       uint64_t gpa, uint64_t size, void *hva);
+int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva);
 void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	enum vm_mem_backing_src_type src_type,
 	uint64_t guest_paddr, uint32_t slot, uint64_t npages,
@@ -336,6 +341,9 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
 				    uint32_t num_percpu_pages, void *guest_code,
 				    uint32_t vcpuids[]);
 
+/* Create a default VM without any vcpus. */
+struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages);
+
 /*
  * Adds a vCPU with reasonable defaults (e.g. a stack)
  *
diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390x/processor.h
index e0e96a5f608c..255c9b990f4c 100644
--- a/tools/testing/selftests/kvm/include/s390x/processor.h
+++ b/tools/testing/selftests/kvm/include/s390x/processor.h
@@ -5,6 +5,8 @@
 #ifndef SELFTEST_KVM_PROCESSOR_H
 #define SELFTEST_KVM_PROCESSOR_H
 
+#include <linux/compiler.h>
+
 /* Bits in the region/segment table entry */
 #define REGION_ENTRY_ORIGIN	~0xfffUL /* region/segment table origin	   */
 #define REGION_ENTRY_PROTECT	0x200	 /* region protection bit	   */
@@ -19,4 +21,10 @@
 #define PAGE_PROTECT	0x200		/* HW read-only bit  */
 #define PAGE_NOEXEC	0x100		/* HW no-execute bit */
 
+/* Is there a portable way to do this? */
+static inline void cpu_relax(void)
+{
+	barrier();
+}
+
 #endif
diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86_64/apic.h
index 0be4757f1f20..ac88557dcc9a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/apic.h
+++ b/tools/testing/selftests/kvm/include/x86_64/apic.h
@@ -33,6 +33,7 @@
 #define	APIC_SPIV	0xF0
 #define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
 #define		APIC_SPIV_APIC_ENABLED		(1 << 8)
+#define APIC_IRR	0x200
 #define	APIC_ICR	0x300
 #define		APIC_DEST_SELF		0x40000
 #define		APIC_DEST_ALLINC	0x80000
diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
index c9af97abd622..cc5d14a45702 100644
--- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h
+++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
@@ -213,6 +213,25 @@ struct hv_enlightened_vmcs {
 	u64 padding64_6[7];
 };
 
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE                     0
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP                BIT(0)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP               BIT(1)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2             BIT(2)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1             BIT(3)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC             BIT(4)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT            BIT(5)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY            BIT(6)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN            BIT(7)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR                     BIT(8)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT             BIT(9)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC              BIT(10)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1               BIT(11)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2               BIT(12)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER             BIT(13)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1                BIT(14)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL    BIT(15)
+#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL                      0xFFFF
+
 #define HV_X64_MSR_VP_ASSIST_PAGE		0x40000073
 #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE	0x00000001
 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT	12
@@ -648,381 +667,507 @@ static inline int evmcs_vmwrite(uint64_t encoding, uint64_t value)
 	switch (encoding) {
 	case GUEST_RIP:
 		current_evmcs->guest_rip = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case GUEST_RSP:
 		current_evmcs->guest_rsp = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
 		break;
 	case GUEST_RFLAGS:
 		current_evmcs->guest_rflags = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
 		break;
 	case HOST_IA32_PAT:
 		current_evmcs->host_ia32_pat = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_IA32_EFER:
 		current_evmcs->host_ia32_efer = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_CR0:
 		current_evmcs->host_cr0 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_CR3:
 		current_evmcs->host_cr3 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_CR4:
 		current_evmcs->host_cr4 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_IA32_SYSENTER_ESP:
 		current_evmcs->host_ia32_sysenter_esp = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_IA32_SYSENTER_EIP:
 		current_evmcs->host_ia32_sysenter_eip = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_RIP:
 		current_evmcs->host_rip = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case IO_BITMAP_A:
 		current_evmcs->io_bitmap_a = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP;
 		break;
 	case IO_BITMAP_B:
 		current_evmcs->io_bitmap_b = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP;
 		break;
 	case MSR_BITMAP:
 		current_evmcs->msr_bitmap = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
 		break;
 	case GUEST_ES_BASE:
 		current_evmcs->guest_es_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_CS_BASE:
 		current_evmcs->guest_cs_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_SS_BASE:
 		current_evmcs->guest_ss_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_DS_BASE:
 		current_evmcs->guest_ds_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_FS_BASE:
 		current_evmcs->guest_fs_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GS_BASE:
 		current_evmcs->guest_gs_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_LDTR_BASE:
 		current_evmcs->guest_ldtr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_TR_BASE:
 		current_evmcs->guest_tr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GDTR_BASE:
 		current_evmcs->guest_gdtr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_IDTR_BASE:
 		current_evmcs->guest_idtr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case TSC_OFFSET:
 		current_evmcs->tsc_offset = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
 		break;
 	case VIRTUAL_APIC_PAGE_ADDR:
 		current_evmcs->virtual_apic_page_addr = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
 		break;
 	case VMCS_LINK_POINTER:
 		current_evmcs->vmcs_link_pointer = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_IA32_DEBUGCTL:
 		current_evmcs->guest_ia32_debugctl = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_IA32_PAT:
 		current_evmcs->guest_ia32_pat = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_IA32_EFER:
 		current_evmcs->guest_ia32_efer = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_PDPTR0:
 		current_evmcs->guest_pdptr0 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_PDPTR1:
 		current_evmcs->guest_pdptr1 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_PDPTR2:
 		current_evmcs->guest_pdptr2 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_PDPTR3:
 		current_evmcs->guest_pdptr3 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_PENDING_DBG_EXCEPTIONS:
 		current_evmcs->guest_pending_dbg_exceptions = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_SYSENTER_ESP:
 		current_evmcs->guest_sysenter_esp = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_SYSENTER_EIP:
 		current_evmcs->guest_sysenter_eip = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case CR0_GUEST_HOST_MASK:
 		current_evmcs->cr0_guest_host_mask = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case CR4_GUEST_HOST_MASK:
 		current_evmcs->cr4_guest_host_mask = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case CR0_READ_SHADOW:
 		current_evmcs->cr0_read_shadow = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case CR4_READ_SHADOW:
 		current_evmcs->cr4_read_shadow = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case GUEST_CR0:
 		current_evmcs->guest_cr0 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case GUEST_CR3:
 		current_evmcs->guest_cr3 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case GUEST_CR4:
 		current_evmcs->guest_cr4 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case GUEST_DR7:
 		current_evmcs->guest_dr7 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR;
 		break;
 	case HOST_FS_BASE:
 		current_evmcs->host_fs_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case HOST_GS_BASE:
 		current_evmcs->host_gs_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case HOST_TR_BASE:
 		current_evmcs->host_tr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case HOST_GDTR_BASE:
 		current_evmcs->host_gdtr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case HOST_IDTR_BASE:
 		current_evmcs->host_idtr_base = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case HOST_RSP:
 		current_evmcs->host_rsp = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 		break;
 	case EPT_POINTER:
 		current_evmcs->ept_pointer = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT;
 		break;
 	case GUEST_BNDCFGS:
 		current_evmcs->guest_bndcfgs = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case XSS_EXIT_BITMAP:
 		current_evmcs->xss_exit_bitmap = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2;
 		break;
 	case GUEST_PHYSICAL_ADDRESS:
 		current_evmcs->guest_physical_address = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case EXIT_QUALIFICATION:
 		current_evmcs->exit_qualification = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case GUEST_LINEAR_ADDRESS:
 		current_evmcs->guest_linear_address = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VM_EXIT_MSR_STORE_ADDR:
 		current_evmcs->vm_exit_msr_store_addr = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case VM_EXIT_MSR_LOAD_ADDR:
 		current_evmcs->vm_exit_msr_load_addr = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case VM_ENTRY_MSR_LOAD_ADDR:
 		current_evmcs->vm_entry_msr_load_addr = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case CR3_TARGET_VALUE0:
 		current_evmcs->cr3_target_value0 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case CR3_TARGET_VALUE1:
 		current_evmcs->cr3_target_value1 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case CR3_TARGET_VALUE2:
 		current_evmcs->cr3_target_value2 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case CR3_TARGET_VALUE3:
 		current_evmcs->cr3_target_value3 = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case TPR_THRESHOLD:
 		current_evmcs->tpr_threshold = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case GUEST_INTERRUPTIBILITY_INFO:
 		current_evmcs->guest_interruptibility_info = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC;
 		break;
 	case CPU_BASED_VM_EXEC_CONTROL:
 		current_evmcs->cpu_based_vm_exec_control = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC;
 		break;
 	case EXCEPTION_BITMAP:
 		current_evmcs->exception_bitmap = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN;
 		break;
 	case VM_ENTRY_CONTROLS:
 		current_evmcs->vm_entry_controls = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY;
 		break;
 	case VM_ENTRY_INTR_INFO_FIELD:
 		current_evmcs->vm_entry_intr_info_field = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
 		break;
 	case VM_ENTRY_EXCEPTION_ERROR_CODE:
 		current_evmcs->vm_entry_exception_error_code = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
 		break;
 	case VM_ENTRY_INSTRUCTION_LEN:
 		current_evmcs->vm_entry_instruction_len = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT;
 		break;
 	case HOST_IA32_SYSENTER_CS:
 		current_evmcs->host_ia32_sysenter_cs = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case PIN_BASED_VM_EXEC_CONTROL:
 		current_evmcs->pin_based_vm_exec_control = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
 		break;
 	case VM_EXIT_CONTROLS:
 		current_evmcs->vm_exit_controls = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
 		break;
 	case SECONDARY_VM_EXEC_CONTROL:
 		current_evmcs->secondary_vm_exec_control = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1;
 		break;
 	case GUEST_ES_LIMIT:
 		current_evmcs->guest_es_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_CS_LIMIT:
 		current_evmcs->guest_cs_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_SS_LIMIT:
 		current_evmcs->guest_ss_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_DS_LIMIT:
 		current_evmcs->guest_ds_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_FS_LIMIT:
 		current_evmcs->guest_fs_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GS_LIMIT:
 		current_evmcs->guest_gs_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_LDTR_LIMIT:
 		current_evmcs->guest_ldtr_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_TR_LIMIT:
 		current_evmcs->guest_tr_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GDTR_LIMIT:
 		current_evmcs->guest_gdtr_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_IDTR_LIMIT:
 		current_evmcs->guest_idtr_limit = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_ES_AR_BYTES:
 		current_evmcs->guest_es_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_CS_AR_BYTES:
 		current_evmcs->guest_cs_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_SS_AR_BYTES:
 		current_evmcs->guest_ss_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_DS_AR_BYTES:
 		current_evmcs->guest_ds_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_FS_AR_BYTES:
 		current_evmcs->guest_fs_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GS_AR_BYTES:
 		current_evmcs->guest_gs_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_LDTR_AR_BYTES:
 		current_evmcs->guest_ldtr_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_TR_AR_BYTES:
 		current_evmcs->guest_tr_ar_bytes = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_ACTIVITY_STATE:
 		current_evmcs->guest_activity_state = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case GUEST_SYSENTER_CS:
 		current_evmcs->guest_sysenter_cs = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1;
 		break;
 	case VM_INSTRUCTION_ERROR:
 		current_evmcs->vm_instruction_error = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VM_EXIT_REASON:
 		current_evmcs->vm_exit_reason = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VM_EXIT_INTR_INFO:
 		current_evmcs->vm_exit_intr_info = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VM_EXIT_INTR_ERROR_CODE:
 		current_evmcs->vm_exit_intr_error_code = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case IDT_VECTORING_INFO_FIELD:
 		current_evmcs->idt_vectoring_info_field = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case IDT_VECTORING_ERROR_CODE:
 		current_evmcs->idt_vectoring_error_code = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VM_EXIT_INSTRUCTION_LEN:
 		current_evmcs->vm_exit_instruction_len = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case VMX_INSTRUCTION_INFO:
 		current_evmcs->vmx_instruction_info = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE;
 		break;
 	case PAGE_FAULT_ERROR_CODE_MASK:
 		current_evmcs->page_fault_error_code_mask = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case PAGE_FAULT_ERROR_CODE_MATCH:
 		current_evmcs->page_fault_error_code_match = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case CR3_TARGET_COUNT:
 		current_evmcs->cr3_target_count = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case VM_EXIT_MSR_STORE_COUNT:
 		current_evmcs->vm_exit_msr_store_count = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case VM_EXIT_MSR_LOAD_COUNT:
 		current_evmcs->vm_exit_msr_load_count = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case VM_ENTRY_MSR_LOAD_COUNT:
 		current_evmcs->vm_entry_msr_load_count = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 		break;
 	case HOST_ES_SELECTOR:
 		current_evmcs->host_es_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_CS_SELECTOR:
 		current_evmcs->host_cs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_SS_SELECTOR:
 		current_evmcs->host_ss_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_DS_SELECTOR:
 		current_evmcs->host_ds_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_FS_SELECTOR:
 		current_evmcs->host_fs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_GS_SELECTOR:
 		current_evmcs->host_gs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case HOST_TR_SELECTOR:
 		current_evmcs->host_tr_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
 		break;
 	case GUEST_ES_SELECTOR:
 		current_evmcs->guest_es_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_CS_SELECTOR:
 		current_evmcs->guest_cs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_SS_SELECTOR:
 		current_evmcs->guest_ss_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_DS_SELECTOR:
 		current_evmcs->guest_ds_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_FS_SELECTOR:
 		current_evmcs->guest_fs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_GS_SELECTOR:
 		current_evmcs->guest_gs_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_LDTR_SELECTOR:
 		current_evmcs->guest_ldtr_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case GUEST_TR_SELECTOR:
 		current_evmcs->guest_tr_selector = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2;
 		break;
 	case VIRTUAL_PROCESSOR_ID:
 		current_evmcs->virtual_processor_id = value;
+		current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT;
 		break;
 	default: return 1;
 	}
@@ -1070,7 +1215,10 @@ static inline int evmcs_vmresume(void)
 {
 	int ret;
 
-	current_evmcs->hv_clean_fields = 0;
+	/* HOST_RIP */
+	current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1;
+	/* HOST_RSP */
+	current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER;
 
 	__asm__ __volatile__("push %%rbp;"
 			     "push %%rcx;"
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 8a470da7b71a..37db341d4cc5 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -363,6 +363,11 @@ static inline unsigned long get_xmm(int n)
 	return 0;
 }
 
+static inline void cpu_relax(void)
+{
+	asm volatile("rep; nop" ::: "memory");
+}
+
 bool is_intel_cpu(void);
 bool is_amd_cpu(void);
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h
index f4ea2355dbc2..2225e5077350 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm.h
@@ -99,7 +99,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u8 reserved_6[8];	/* Offset 0xe8 */
 	u64 avic_logical_id;	/* Offset 0xf0 */
 	u64 avic_physical_id;	/* Offset 0xf8 */
-	u8 reserved_7[768];
+	u8 reserved_7[8];
+	u64 vmsa_pa;		/* Used for an SEV-ES guest */
+	u8 reserved_8[720];
+	/*
+	 * Offset 0x3e0, 32 bytes reserved
+	 * for use by hypervisor/software.
+	 */
+	u8 reserved_sw[32];
 };
 
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
index 587fbe408b99..a25aabd8f5e7 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -16,6 +16,7 @@
 #define CPUID_SVM_BIT		2
 #define CPUID_SVM		BIT_ULL(CPUID_SVM_BIT)
 
+#define SVM_EXIT_MSR		0x07c
 #define SVM_EXIT_VMMCALL	0x081
 
 struct svm_test_data {
@@ -28,6 +29,11 @@ struct svm_test_data {
 	struct vmcb_save_area *save_area; /* gva */
 	void *save_area_hva;
 	uint64_t save_area_gpa;
+
+	/* MSR-Bitmap */
+	void *msr; /* gva */
+	void *msr_hva;
+	uint64_t msr_gpa;
 };
 
 struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 00f613c0583c..263bf3ed8fd5 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -19,7 +19,7 @@ struct gicv3_data {
 	unsigned int nr_spis;
 };
 
-#define sgi_base_from_redist(redist_base) 	(redist_base + SZ_64K)
+#define sgi_base_from_redist(redist_base)	(redist_base + SZ_64K)
 #define DIST_BIT				(1U << 31)
 
 enum gicv3_intid_range {
@@ -105,7 +105,8 @@ static void gicv3_set_eoi_split(bool split)
 {
 	uint32_t val;
 
-	/* All other fields are read-only, so no need to read CTLR first. In
+	/*
+	 * All other fields are read-only, so no need to read CTLR first. In
 	 * fact, the kernel does the same.
 	 */
 	val = split ? (1U << 1) : 0;
@@ -159,9 +160,10 @@ static void gicv3_access_reg(uint32_t intid, uint64_t offset,
 	uint32_t cpu_or_dist;
 
 	GUEST_ASSERT(bits_per_field <= reg_bits);
-	GUEST_ASSERT(*val < (1U << bits_per_field));
-	/* Some registers like IROUTER are 64 bit long. Those are currently not
-	 * supported by readl nor writel, so just asserting here until then.
+	GUEST_ASSERT(!write || *val < (1U << bits_per_field));
+	/*
+	 * This function does not support 64 bit accesses. Just asserting here
+	 * until we implement readq/writeq.
 	 */
 	GUEST_ASSERT(reg_bits == 32);
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index f5cd0c536d85..5d45046c1b80 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -140,9 +140,6 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
 	uint64_t val;
 	bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);
 
-	/* Check that the addr part of the attr is within 32 bits. */
-	assert(attr <= KVM_DEV_ARM_VGIC_OFFSET_MASK);
-
 	uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
 					  : KVM_DEV_ARM_VGIC_GRP_DIST_REGS;
 
@@ -152,7 +149,11 @@ static void vgic_poke_irq(int gic_fd, uint32_t intid,
 		attr += SZ_64K;
 	}
 
-	/* All calls will succeed, even with invalid intid's, as long as the
+	/* Check that the addr part of the attr is within 32 bits. */
+	assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0);
+
+	/*
+	 * All calls will succeed, even with invalid intid's, as long as the
 	 * addr part of the attr is within 32 bits (checked above). An invalid
 	 * intid will just make the read/writes point to above the intended
 	 * register space (i.e., ICPENDR after ISPENDR).
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index d8cf851ab119..1665a220abcb 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -362,6 +362,20 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
+struct kvm_vm *vm_create_without_vcpus(enum vm_guest_mode mode, uint64_t pages)
+{
+	struct kvm_vm *vm;
+
+	vm = vm_create(mode, pages, O_RDWR);
+
+	kvm_vm_elf_load(vm, program_invocation_name);
+
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+	return vm;
+}
+
 /*
  * VM Create with customized parameters
  *
@@ -412,13 +426,8 @@ struct kvm_vm *vm_create_with_vcpus(enum vm_guest_mode mode, uint32_t nr_vcpus,
 		    nr_vcpus, kvm_check_cap(KVM_CAP_MAX_VCPUS));
 
 	pages = vm_adjust_num_guest_pages(mode, pages);
-	vm = vm_create(mode, pages, O_RDWR);
 
-	kvm_vm_elf_load(vm, program_invocation_name);
-
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
+	vm = vm_create_without_vcpus(mode, pages);
 
 	for (i = 0; i < nr_vcpus; ++i) {
 		uint32_t vcpuid = vcpuids ? vcpuids[i] : i;
@@ -709,6 +718,27 @@ void kvm_vm_free(struct kvm_vm *vmp)
 	free(vmp);
 }
 
+int kvm_memfd_alloc(size_t size, bool hugepages)
+{
+	int memfd_flags = MFD_CLOEXEC;
+	int fd, r;
+
+	if (hugepages)
+		memfd_flags |= MFD_HUGETLB;
+
+	fd = memfd_create("kvm_selftest", memfd_flags);
+	TEST_ASSERT(fd != -1, "memfd_create() failed, errno: %i (%s)",
+		    errno, strerror(errno));
+
+	r = ftruncate(fd, size);
+	TEST_ASSERT(!r, "ftruncate() failed, errno: %i (%s)", errno, strerror(errno));
+
+	r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, size);
+	TEST_ASSERT(!r, "fallocate() failed, errno: %i (%s)", errno, strerror(errno));
+
+	return fd;
+}
+
 /*
  * Memory Compare, host virtual to guest virtual
  *
@@ -830,6 +860,30 @@ static void vm_userspace_mem_region_hva_insert(struct rb_root *hva_tree,
 	rb_insert_color(&region->hva_node, hva_tree);
 }
 
+
+int __vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+				uint64_t gpa, uint64_t size, void *hva)
+{
+	struct kvm_userspace_memory_region region = {
+		.slot = slot,
+		.flags = flags,
+		.guest_phys_addr = gpa,
+		.memory_size = size,
+		.userspace_addr = (uintptr_t)hva,
+	};
+
+	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region);
+}
+
+void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
+			       uint64_t gpa, uint64_t size, void *hva)
+{
+	int ret = __vm_set_user_memory_region(vm, slot, flags, gpa, size, hva);
+
+	TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION failed, errno = %d (%s)",
+		    errno, strerror(errno));
+}
+
 /*
  * VM Userspace Memory Region Add
  *
@@ -937,24 +991,9 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		region->mmap_size += alignment;
 
 	region->fd = -1;
-	if (backing_src_is_shared(src_type)) {
-		int memfd_flags = MFD_CLOEXEC;
-
-		if (src_type == VM_MEM_SRC_SHARED_HUGETLB)
-			memfd_flags |= MFD_HUGETLB;
-
-		region->fd = memfd_create("kvm_selftest", memfd_flags);
-		TEST_ASSERT(region->fd != -1,
-			    "memfd_create failed, errno: %i", errno);
-
-		ret = ftruncate(region->fd, region->mmap_size);
-		TEST_ASSERT(ret == 0, "ftruncate failed, errno: %i", errno);
-
-		ret = fallocate(region->fd,
-				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0,
-				region->mmap_size);
-		TEST_ASSERT(ret == 0, "fallocate failed, errno: %i", errno);
-	}
+	if (backing_src_is_shared(src_type))
+		region->fd = kvm_memfd_alloc(region->mmap_size,
+					     src_type == VM_MEM_SRC_SHARED_HUGETLB);
 
 	region->mmap_start = mmap(NULL, region->mmap_size,
 				  PROT_READ | PROT_WRITE,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86_64/svm.c
index 0ebc03ce079c..736ee4a23df6 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/svm.c
@@ -43,6 +43,11 @@ vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva)
 	svm->save_area_hva = addr_gva2hva(vm, (uintptr_t)svm->save_area);
 	svm->save_area_gpa = addr_gva2gpa(vm, (uintptr_t)svm->save_area);
 
+	svm->msr = (void *)vm_vaddr_alloc_page(vm);
+	svm->msr_hva = addr_gva2hva(vm, (uintptr_t)svm->msr);
+	svm->msr_gpa = addr_gva2gpa(vm, (uintptr_t)svm->msr);
+	memset(svm->msr_hva, 0, getpagesize());
+
 	*p_svm_gva = svm_gva;
 	return svm;
 }
@@ -106,6 +111,7 @@ void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_r
 	save->dbgctl = rdmsr(MSR_IA32_DEBUGCTLMSR);
 	ctrl->intercept = (1ULL << INTERCEPT_VMRUN) |
 				(1ULL << INTERCEPT_VMMCALL);
+	ctrl->msrpm_base_pa = svm->msr_gpa;
 
 	vmcb->save.rip = (u64)guest_rip;
 	vmcb->save.rsp = (u64)guest_rsp;
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
new file mode 100644
index 000000000000..3875c4b23a04
--- /dev/null
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <pthread.h>
+#include <semaphore.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/atomic.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "guest_modes.h"
+#include "processor.h"
+
+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();
+}
+
+struct vcpu_info {
+	struct kvm_vm *vm;
+	uint32_t id;
+	uint64_t start_gpa;
+	uint64_t end_gpa;
+};
+
+static int nr_vcpus;
+static atomic_t rendezvous;
+
+static void rendezvous_with_boss(void)
+{
+	int orig = atomic_read(&rendezvous);
+
+	if (orig > 0) {
+		atomic_dec_and_test(&rendezvous);
+		while (atomic_read(&rendezvous) > 0)
+			cpu_relax();
+	} else {
+		atomic_inc(&rendezvous);
+		while (atomic_read(&rendezvous) < 0)
+			cpu_relax();
+	}
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpu_id)
+{
+	vcpu_run(vm, vcpu_id);
+	ASSERT_EQ(get_ucall(vm, vcpu_id, NULL), UCALL_DONE);
+}
+
+static void *vcpu_worker(void *data)
+{
+	struct vcpu_info *vcpu = data;
+	struct kvm_vm *vm = vcpu->vm;
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
+
+	vcpu_args_set(vm, vcpu->id, 3, vcpu->start_gpa, vcpu->end_gpa,
+		      vm_get_page_size(vm));
+
+	/* Snapshot regs before the first run. */
+	vcpu_regs_get(vm, vcpu->id, &regs);
+	rendezvous_with_boss();
+
+	run_vcpu(vm, vcpu->id);
+	rendezvous_with_boss();
+	vcpu_regs_set(vm, vcpu->id, &regs);
+	vcpu_sregs_get(vm, vcpu->id, &sregs);
+#ifdef __x86_64__
+	/* Toggle CR0.WP to trigger a MMU context reset. */
+	sregs.cr0 ^= X86_CR0_WP;
+#endif
+	vcpu_sregs_set(vm, vcpu->id, &sregs);
+	rendezvous_with_boss();
+
+	run_vcpu(vm, vcpu->id);
+	rendezvous_with_boss();
+
+	return NULL;
+}
+
+static pthread_t *spawn_workers(struct kvm_vm *vm, uint64_t start_gpa,
+				uint64_t end_gpa)
+{
+	struct vcpu_info *info;
+	uint64_t gpa, nr_bytes;
+	pthread_t *threads;
+	int i;
+
+	threads = malloc(nr_vcpus * sizeof(*threads));
+	TEST_ASSERT(threads, "Failed to allocate vCPU threads");
+
+	info = malloc(nr_vcpus * sizeof(*info));
+	TEST_ASSERT(info, "Failed to allocate vCPU gpa ranges");
+
+	nr_bytes = ((end_gpa - start_gpa) / nr_vcpus) &
+			~((uint64_t)vm_get_page_size(vm) - 1);
+	TEST_ASSERT(nr_bytes, "C'mon, no way you have %d CPUs", nr_vcpus);
+
+	for (i = 0, gpa = start_gpa; i < nr_vcpus; i++, gpa += nr_bytes) {
+		info[i].vm = vm;
+		info[i].id = i;
+		info[i].start_gpa = gpa;
+		info[i].end_gpa = gpa + nr_bytes;
+		pthread_create(&threads[i], NULL, vcpu_worker, &info[i]);
+	}
+	return threads;
+}
+
+static void rendezvous_with_vcpus(struct timespec *time, const char *name)
+{
+	int i, rendezvoused;
+
+	pr_info("Waiting for vCPUs to finish %s...\n", name);
+
+	rendezvoused = atomic_read(&rendezvous);
+	for (i = 0; abs(rendezvoused) != 1; i++) {
+		usleep(100);
+		if (!(i & 0x3f))
+			pr_info("\r%d vCPUs haven't rendezvoused...",
+				abs(rendezvoused) - 1);
+		rendezvoused = atomic_read(&rendezvous);
+	}
+
+	clock_gettime(CLOCK_MONOTONIC, time);
+
+	/* Release the vCPUs after getting the time of the previous action. */
+	pr_info("\rAll vCPUs finished %s, releasing...\n", name);
+	if (rendezvoused > 0)
+		atomic_set(&rendezvous, -nr_vcpus - 1);
+	else
+		atomic_set(&rendezvous, nr_vcpus + 1);
+}
+
+static void calc_default_nr_vcpus(void)
+{
+	cpu_set_t possible_mask;
+	int r;
+
+	r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
+	TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)",
+		    errno, strerror(errno));
+
+	nr_vcpus = CPU_COUNT(&possible_mask) * 3/4;
+	TEST_ASSERT(nr_vcpus > 0, "Uh, no CPUs?");
+}
+
+int main(int argc, char *argv[])
+{
+	/*
+	 * Skip the first 4gb and slot0.  slot0 maps <1gb and is used to back
+	 * the guest's code, stack, and page tables.  Because selftests creates
+	 * an IRQCHIP, a.k.a. a local APIC, KVM creates an internal memslot
+	 * just below the 4gb boundary.  This test could create memory at
+	 * 1gb-3gb,but it's simpler to skip straight to 4gb.
+	 */
+	const uint64_t size_1gb = (1 << 30);
+	const uint64_t start_gpa = (4ull * size_1gb);
+	const int first_slot = 1;
+
+	struct timespec time_start, time_run1, time_reset, time_run2;
+	uint64_t max_gpa, gpa, slot_size, max_mem, i;
+	int max_slots, slot, opt, fd;
+	bool hugepages = false;
+	pthread_t *threads;
+	struct kvm_vm *vm;
+	void *mem;
+
+	/*
+	 * Default to 2gb so that maxing out systems with MAXPHADDR=46, which
+	 * are quite common for x86, requires changing only max_mem (KVM allows
+	 * 32k memslots, 32k * 2gb == ~64tb of guest memory).
+	 */
+	slot_size = 2 * size_1gb;
+
+	max_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
+	TEST_ASSERT(max_slots > first_slot, "KVM is broken");
+
+	/* All KVM MMUs should be able to survive a 128gb guest. */
+	max_mem = 128 * size_1gb;
+
+	calc_default_nr_vcpus();
+
+	while ((opt = getopt(argc, argv, "c:h:m:s:H")) != -1) {
+		switch (opt) {
+		case 'c':
+			nr_vcpus = atoi(optarg);
+			TEST_ASSERT(nr_vcpus > 0, "number of vcpus must be >0");
+			break;
+		case 'm':
+			max_mem = atoi(optarg) * size_1gb;
+			TEST_ASSERT(max_mem > 0, "memory size must be >0");
+			break;
+		case 's':
+			slot_size = atoi(optarg) * size_1gb;
+			TEST_ASSERT(slot_size > 0, "slot size must be >0");
+			break;
+		case 'H':
+			hugepages = true;
+			break;
+		case 'h':
+		default:
+			printf("usage: %s [-c nr_vcpus] [-m max_mem_in_gb] [-s slot_size_in_gb] [-H]\n", argv[0]);
+			exit(1);
+		}
+	}
+
+	vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
+
+	max_gpa = vm_get_max_gfn(vm) << vm_get_page_shift(vm);
+	TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb ");
+
+	fd = kvm_memfd_alloc(slot_size, hugepages);
+	mem = mmap(NULL, slot_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	TEST_ASSERT(mem != MAP_FAILED, "mmap() failed");
+
+	TEST_ASSERT(!madvise(mem, slot_size, MADV_NOHUGEPAGE), "madvise() failed");
+
+	/* Pre-fault the memory to avoid taking mmap_sem on guest page faults. */
+	for (i = 0; i < slot_size; i += vm_get_page_size(vm))
+		((uint8_t *)mem)[i] = 0xaa;
+
+	gpa = 0;
+	for (slot = first_slot; slot < max_slots; slot++) {
+		gpa = start_gpa + ((slot - first_slot) * slot_size);
+		if (gpa + slot_size > max_gpa)
+			break;
+
+		if ((gpa - start_gpa) >= max_mem)
+			break;
+
+		vm_set_user_memory_region(vm, slot, 0, gpa, slot_size, mem);
+
+#ifdef __x86_64__
+		/* Identity map memory in the guest using 1gb pages. */
+		for (i = 0; i < slot_size; i += size_1gb)
+			__virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+#else
+		for (i = 0; i < slot_size; i += vm_get_page_size(vm))
+			virt_pg_map(vm, gpa + i, gpa + i);
+#endif
+	}
+
+	atomic_set(&rendezvous, nr_vcpus + 1);
+	threads = spawn_workers(vm, start_gpa, gpa);
+
+	pr_info("Running with %lugb of guest memory and %u vCPUs\n",
+		(gpa - start_gpa) / size_1gb, nr_vcpus);
+
+	rendezvous_with_vcpus(&time_start, "spawning");
+	rendezvous_with_vcpus(&time_run1, "run 1");
+	rendezvous_with_vcpus(&time_reset, "reset");
+	rendezvous_with_vcpus(&time_run2, "run 2");
+
+	time_run2  = timespec_sub(time_run2,   time_reset);
+	time_reset = timespec_sub(time_reset, time_run1);
+	time_run1  = timespec_sub(time_run1,   time_start);
+
+	pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 =  %ld.%.9lds\n",
+		time_run1.tv_sec, time_run1.tv_nsec,
+		time_reset.tv_sec, time_reset.tv_nsec,
+		time_run2.tv_sec, time_run2.tv_nsec);
+
+	/*
+	 * Delete even numbered slots (arbitrary) and unmap the first half of
+	 * the backing (also arbitrary) to verify KVM correctly drops all
+	 * references to the removed regions.
+	 */
+	for (slot = (slot - 1) & ~1ull; slot >= first_slot; slot -= 2)
+		vm_set_user_memory_region(vm, slot, 0, 0, 0, NULL);
+
+	munmap(mem, slot_size / 2);
+
+	/* Sanity check that the vCPUs actually ran. */
+	for (i = 0; i < nr_vcpus; i++)
+		pthread_join(threads[i], NULL);
+
+	/*
+	 * Deliberately exit without deleting the remaining memslots or closing
+	 * kvm_fd to test cleanup via mmu_notifier.release.
+	 */
+}
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index 9f49ead380ab..b04c2c1b3c30 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -13,154 +13,668 @@
 #include "test_util.h"
 #include "kvm_util.h"
 
+enum mop_target {
+	LOGICAL,
+	SIDA,
+	ABSOLUTE,
+	INVALID,
+};
+
+enum mop_access_mode {
+	READ,
+	WRITE,
+};
+
+struct mop_desc {
+	uintptr_t gaddr;
+	uintptr_t gaddr_v;
+	uint64_t set_flags;
+	unsigned int f_check : 1;
+	unsigned int f_inject : 1;
+	unsigned int f_key : 1;
+	unsigned int _gaddr_v : 1;
+	unsigned int _set_flags : 1;
+	unsigned int _sida_offset : 1;
+	unsigned int _ar : 1;
+	uint32_t size;
+	enum mop_target target;
+	enum mop_access_mode mode;
+	void *buf;
+	uint32_t sida_offset;
+	uint8_t ar;
+	uint8_t key;
+};
+
+static struct kvm_s390_mem_op ksmo_from_desc(struct mop_desc desc)
+{
+	struct kvm_s390_mem_op ksmo = {
+		.gaddr = (uintptr_t)desc.gaddr,
+		.size = desc.size,
+		.buf = ((uintptr_t)desc.buf),
+		.reserved = "ignored_ignored_ignored_ignored"
+	};
+
+	switch (desc.target) {
+	case LOGICAL:
+		if (desc.mode == READ)
+			ksmo.op = KVM_S390_MEMOP_LOGICAL_READ;
+		if (desc.mode == WRITE)
+			ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
+		break;
+	case SIDA:
+		if (desc.mode == READ)
+			ksmo.op = KVM_S390_MEMOP_SIDA_READ;
+		if (desc.mode == WRITE)
+			ksmo.op = KVM_S390_MEMOP_SIDA_WRITE;
+		break;
+	case ABSOLUTE:
+		if (desc.mode == READ)
+			ksmo.op = KVM_S390_MEMOP_ABSOLUTE_READ;
+		if (desc.mode == WRITE)
+			ksmo.op = KVM_S390_MEMOP_ABSOLUTE_WRITE;
+		break;
+	case INVALID:
+		ksmo.op = -1;
+	}
+	if (desc.f_check)
+		ksmo.flags |= KVM_S390_MEMOP_F_CHECK_ONLY;
+	if (desc.f_inject)
+		ksmo.flags |= KVM_S390_MEMOP_F_INJECT_EXCEPTION;
+	if (desc._set_flags)
+		ksmo.flags = desc.set_flags;
+	if (desc.f_key) {
+		ksmo.flags |= KVM_S390_MEMOP_F_SKEY_PROTECTION;
+		ksmo.key = desc.key;
+	}
+	if (desc._ar)
+		ksmo.ar = desc.ar;
+	else
+		ksmo.ar = 0;
+	if (desc._sida_offset)
+		ksmo.sida_offset = desc.sida_offset;
+
+	return ksmo;
+}
+
+/* vcpu dummy id signifying that vm instead of vcpu ioctl is to occur */
+const uint32_t VM_VCPU_ID = (uint32_t)-1;
+
+struct test_vcpu {
+	struct kvm_vm *vm;
+	uint32_t id;
+};
+
+#define PRINT_MEMOP false
+static void print_memop(uint32_t vcpu_id, const struct kvm_s390_mem_op *ksmo)
+{
+	if (!PRINT_MEMOP)
+		return;
+
+	if (vcpu_id == VM_VCPU_ID)
+		printf("vm memop(");
+	else
+		printf("vcpu memop(");
+	switch (ksmo->op) {
+	case KVM_S390_MEMOP_LOGICAL_READ:
+		printf("LOGICAL, READ, ");
+		break;
+	case KVM_S390_MEMOP_LOGICAL_WRITE:
+		printf("LOGICAL, WRITE, ");
+		break;
+	case KVM_S390_MEMOP_SIDA_READ:
+		printf("SIDA, READ, ");
+		break;
+	case KVM_S390_MEMOP_SIDA_WRITE:
+		printf("SIDA, WRITE, ");
+		break;
+	case KVM_S390_MEMOP_ABSOLUTE_READ:
+		printf("ABSOLUTE, READ, ");
+		break;
+	case KVM_S390_MEMOP_ABSOLUTE_WRITE:
+		printf("ABSOLUTE, WRITE, ");
+		break;
+	}
+	printf("gaddr=%llu, size=%u, buf=%llu, ar=%u, key=%u",
+	       ksmo->gaddr, ksmo->size, ksmo->buf, ksmo->ar, ksmo->key);
+	if (ksmo->flags & KVM_S390_MEMOP_F_CHECK_ONLY)
+		printf(", CHECK_ONLY");
+	if (ksmo->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION)
+		printf(", INJECT_EXCEPTION");
+	if (ksmo->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION)
+		printf(", SKEY_PROTECTION");
+	puts(")");
+}
+
+static void memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo)
+{
+	if (vcpu.id == VM_VCPU_ID)
+		vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo);
+	else
+		vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo);
+}
+
+static int err_memop_ioctl(struct test_vcpu vcpu, struct kvm_s390_mem_op *ksmo)
+{
+	if (vcpu.id == VM_VCPU_ID)
+		return _vm_ioctl(vcpu.vm, KVM_S390_MEM_OP, ksmo);
+	else
+		return _vcpu_ioctl(vcpu.vm, vcpu.id, KVM_S390_MEM_OP, ksmo);
+}
+
+#define MEMOP(err, vcpu_p, mop_target_p, access_mode_p, buf_p, size_p, ...)	\
+({										\
+	struct test_vcpu __vcpu = (vcpu_p);					\
+	struct mop_desc __desc = {						\
+		.target = (mop_target_p),					\
+		.mode = (access_mode_p),					\
+		.buf = (buf_p),							\
+		.size = (size_p),						\
+		__VA_ARGS__							\
+	};									\
+	struct kvm_s390_mem_op __ksmo;						\
+										\
+	if (__desc._gaddr_v) {							\
+		if (__desc.target == ABSOLUTE)					\
+			__desc.gaddr = addr_gva2gpa(__vcpu.vm, __desc.gaddr_v);	\
+		else								\
+			__desc.gaddr = __desc.gaddr_v;				\
+	}									\
+	__ksmo = ksmo_from_desc(__desc);					\
+	print_memop(__vcpu.id, &__ksmo);					\
+	err##memop_ioctl(__vcpu, &__ksmo);					\
+})
+
+#define MOP(...) MEMOP(, __VA_ARGS__)
+#define ERR_MOP(...) MEMOP(err_, __VA_ARGS__)
+
+#define GADDR(a) .gaddr = ((uintptr_t)a)
+#define GADDR_V(v) ._gaddr_v = 1, .gaddr_v = ((uintptr_t)v)
+#define CHECK_ONLY .f_check = 1
+#define SET_FLAGS(f) ._set_flags = 1, .set_flags = (f)
+#define SIDA_OFFSET(o) ._sida_offset = 1, .sida_offset = (o)
+#define AR(a) ._ar = 1, .ar = (a)
+#define KEY(a) .f_key = 1, .key = (a)
+
+#define CHECK_N_DO(f, ...) ({ f(__VA_ARGS__, CHECK_ONLY); f(__VA_ARGS__); })
+
 #define VCPU_ID 1
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1ULL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+#define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
+#define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
 
 static uint8_t mem1[65536];
 static uint8_t mem2[65536];
 
-static void guest_code(void)
+struct test_default {
+	struct kvm_vm *kvm_vm;
+	struct test_vcpu vm;
+	struct test_vcpu vcpu;
+	struct kvm_run *run;
+	int size;
+};
+
+static struct test_default test_default_init(void *guest_code)
+{
+	struct test_default t;
+
+	t.size = min((size_t)kvm_check_cap(KVM_CAP_S390_MEM_OP), sizeof(mem1));
+	t.kvm_vm = vm_create_default(VCPU_ID, 0, guest_code);
+	t.vm = (struct test_vcpu) { t.kvm_vm, VM_VCPU_ID };
+	t.vcpu = (struct test_vcpu) { t.kvm_vm, VCPU_ID };
+	t.run = vcpu_state(t.kvm_vm, VCPU_ID);
+	return t;
+}
+
+enum stage {
+	/* Synced state set by host, e.g. DAT */
+	STAGE_INITED,
+	/* Guest did nothing */
+	STAGE_IDLED,
+	/* Guest set storage keys (specifics up to test case) */
+	STAGE_SKEYS_SET,
+	/* Guest copied memory (locations up to test case) */
+	STAGE_COPIED,
+};
+
+#define HOST_SYNC(vcpu_p, stage)					\
+({									\
+	struct test_vcpu __vcpu = (vcpu_p);				\
+	struct ucall uc;						\
+	int __stage = (stage);						\
+									\
+	vcpu_run(__vcpu.vm, __vcpu.id);					\
+	get_ucall(__vcpu.vm, __vcpu.id, &uc);				\
+	ASSERT_EQ(uc.cmd, UCALL_SYNC);					\
+	ASSERT_EQ(uc.args[1], __stage);					\
+})									\
+
+static void prepare_mem12(void)
 {
 	int i;
 
+	for (i = 0; i < sizeof(mem1); i++)
+		mem1[i] = rand();
+	memset(mem2, 0xaa, sizeof(mem2));
+}
+
+#define ASSERT_MEM_EQ(p1, p2, size) \
+	TEST_ASSERT(!memcmp(p1, p2, size), "Memory contents do not match!")
+
+#define DEFAULT_WRITE_READ(copy_cpu, mop_cpu, mop_target_p, size, ...)		\
+({										\
+	struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu);	\
+	enum mop_target __target = (mop_target_p);				\
+	uint32_t __size = (size);						\
+										\
+	prepare_mem12();							\
+	CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size,		\
+			GADDR_V(mem1), ##__VA_ARGS__);				\
+	HOST_SYNC(__copy_cpu, STAGE_COPIED);					\
+	CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size,		\
+			GADDR_V(mem2), ##__VA_ARGS__);				\
+	ASSERT_MEM_EQ(mem1, mem2, __size);					\
+})
+
+#define DEFAULT_READ(copy_cpu, mop_cpu, mop_target_p, size, ...)		\
+({										\
+	struct test_vcpu __copy_cpu = (copy_cpu), __mop_cpu = (mop_cpu);	\
+	enum mop_target __target = (mop_target_p);				\
+	uint32_t __size = (size);						\
+										\
+	prepare_mem12();							\
+	CHECK_N_DO(MOP, __mop_cpu, __target, WRITE, mem1, __size,		\
+			GADDR_V(mem1));						\
+	HOST_SYNC(__copy_cpu, STAGE_COPIED);					\
+	CHECK_N_DO(MOP, __mop_cpu, __target, READ, mem2, __size, ##__VA_ARGS__);\
+	ASSERT_MEM_EQ(mem1, mem2, __size);					\
+})
+
+static void guest_copy(void)
+{
+	GUEST_SYNC(STAGE_INITED);
+	memcpy(&mem2, &mem1, sizeof(mem2));
+	GUEST_SYNC(STAGE_COPIED);
+}
+
+static void test_copy(void)
+{
+	struct test_default t = test_default_init(guest_copy);
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 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;
+	int not_mapped = 0;
+
+	_addr = (uintptr_t)addr;
+	for (i = _addr & PAGE_MASK; i < _addr + len; i += PAGE_SIZE) {
+		abs = i;
+		asm volatile (
+			       "lra	%[abs], 0(0,%[abs])\n"
+			"	jz	0f\n"
+			"	llill	%[not_mapped],1\n"
+			"	j	1f\n"
+			"0:	sske	%[key], %[abs]\n"
+			"1:"
+			: [abs] "+&a" (abs), [not_mapped] "+r" (not_mapped)
+			: [key] "r" (key)
+			: "cc"
+		);
+		GUEST_ASSERT_EQ(not_mapped, 0);
+	}
+}
+
+static void guest_copy_key(void)
+{
+	set_storage_key_range(mem1, sizeof(mem1), 0x90);
+	set_storage_key_range(mem2, sizeof(mem2), 0x90);
+	GUEST_SYNC(STAGE_SKEYS_SET);
+
 	for (;;) {
-		for (i = 0; i < sizeof(mem2); i++)
-			mem2[i] = mem1[i];
-		GUEST_SYNC(0);
+		memcpy(&mem2, &mem1, sizeof(mem2));
+		GUEST_SYNC(STAGE_COPIED);
 	}
 }
 
-int main(int argc, char *argv[])
+static void test_copy_key(void)
 {
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_s390_mem_op ksmo;
-	int rv, i, maxsize;
+	struct test_default t = test_default_init(guest_copy_key);
 
-	setbuf(stdout, NULL);	/* Tell stdout not to buffer its content */
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
 
-	maxsize = kvm_check_cap(KVM_CAP_S390_MEM_OP);
-	if (!maxsize) {
-		print_skip("CAP_S390_MEM_OP not supported");
-		exit(KSFT_SKIP);
+	/* vm, no key */
+	DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size);
+
+	/* vm/vcpu, machting key or key 0 */
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(0));
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(9));
+	DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(0));
+	DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, t.size, KEY(9));
+	/*
+	 * There used to be different code paths for key handling depending on
+	 * if the region crossed a page boundary.
+	 * There currently are not, but the more tests the merrier.
+	 */
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(0));
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, 1, KEY(9));
+	DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(0));
+	DEFAULT_WRITE_READ(t.vcpu, t.vm, ABSOLUTE, 1, KEY(9));
+
+	/* vm/vcpu, mismatching keys on read, but no fetch protection */
+	DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(2));
+	DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem1), KEY(2));
+
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void guest_copy_key_fetch_prot(void)
+{
+	/*
+	 * For some reason combining the first sync with override enablement
+	 * results in an exception when calling HOST_SYNC.
+	 */
+	GUEST_SYNC(STAGE_INITED);
+	/* Storage protection override applies to both store and fetch. */
+	set_storage_key_range(mem1, sizeof(mem1), 0x98);
+	set_storage_key_range(mem2, sizeof(mem2), 0x98);
+	GUEST_SYNC(STAGE_SKEYS_SET);
+
+	for (;;) {
+		memcpy(&mem2, &mem1, sizeof(mem2));
+		GUEST_SYNC(STAGE_COPIED);
 	}
-	if (maxsize > sizeof(mem1))
-		maxsize = sizeof(mem1);
+}
 
-	/* Create VM */
-	vm = vm_create_default(VCPU_ID, 0, guest_code);
-	run = vcpu_state(vm, VCPU_ID);
+static void test_copy_key_storage_prot_override(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot);
 
-	for (i = 0; i < sizeof(mem1); i++)
-		mem1[i] = i * i + i;
-
-	/* Set the first array */
-	ksmo.gaddr = addr_gva2gpa(vm, (uintptr_t)mem1);
-	ksmo.flags = 0;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
-
-	/* Let the guest code copy the first array to the second */
-	vcpu_run(vm, VCPU_ID);
-	TEST_ASSERT(run->exit_reason == KVM_EXIT_S390_SIEIC,
-		    "Unexpected exit reason: %u (%s)\n",
-		    run->exit_reason,
-		    exit_reason_str(run->exit_reason));
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+	t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
 
-	memset(mem2, 0xaa, sizeof(mem2));
+	/* vcpu, mismatching keys, storage protection override in effect */
+	DEFAULT_WRITE_READ(t.vcpu, t.vcpu, LOGICAL, t.size, KEY(2));
+
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void test_copy_key_fetch_prot(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot);
 
-	/* Get the second array */
-	ksmo.gaddr = (uintptr_t)mem2;
-	ksmo.flags = 0;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_READ;
-	ksmo.buf = (uintptr_t)mem2;
-	ksmo.ar = 0;
-	vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
-
-	TEST_ASSERT(!memcmp(mem1, mem2, maxsize),
-		    "Memory contents do not match!");
-
-	/* Check error conditions - first bad size: */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = 0;
-	ksmo.size = -1;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/* vm/vcpu, matching key, fetch protection in effect */
+	DEFAULT_READ(t.vcpu, t.vcpu, LOGICAL, t.size, GADDR_V(mem2), KEY(9));
+	DEFAULT_READ(t.vcpu, t.vm, ABSOLUTE, t.size, GADDR_V(mem2), KEY(9));
+
+	kvm_vm_free(t.kvm_vm);
+}
+
+#define ERR_PROT_MOP(...)							\
+({										\
+	int rv;									\
+										\
+	rv = ERR_MOP(__VA_ARGS__);						\
+	TEST_ASSERT(rv == 4, "Should result in protection exception");		\
+})
+
+static void test_errors_key(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/* vm/vcpu, mismatching keys, fetch protection in effect */
+	CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, t.size, GADDR_V(mem2), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2));
+
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_storage_prot_override(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot);
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	t.run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+	t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/* vm, mismatching keys, storage protection override not applicable to vm */
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, WRITE, mem1, t.size, GADDR_V(mem1), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, t.size, GADDR_V(mem2), KEY(2));
+
+	kvm_vm_free(t.kvm_vm);
+}
+
+const uint64_t last_page_addr = -PAGE_SIZE;
+
+static void guest_copy_key_fetch_prot_override(void)
+{
+	int i;
+	char *page_0 = 0;
+
+	GUEST_SYNC(STAGE_INITED);
+	set_storage_key_range(0, PAGE_SIZE, 0x18);
+	set_storage_key_range((void *)last_page_addr, PAGE_SIZE, 0x0);
+	asm volatile ("sske %[key],%[addr]\n" :: [addr] "r"(0), [key] "r"(0x18) : "cc");
+	GUEST_SYNC(STAGE_SKEYS_SET);
+
+	for (;;) {
+		for (i = 0; i < PAGE_SIZE; i++)
+			page_0[i] = mem1[i];
+		GUEST_SYNC(STAGE_COPIED);
+	}
+}
+
+static void test_copy_key_fetch_prot_override(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+	vm_vaddr_t guest_0_page, guest_last_page;
+
+	guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+	guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+	if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+		print_skip("did not allocate guest pages at required positions");
+		goto out;
+	}
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+	t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/* vcpu, mismatching keys on fetch, fetch protection override applies */
+	prepare_mem12();
+	MOP(t.vcpu, LOGICAL, WRITE, mem1, PAGE_SIZE, GADDR_V(mem1));
+	HOST_SYNC(t.vcpu, STAGE_COPIED);
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2));
+	ASSERT_MEM_EQ(mem1, mem2, 2048);
+
+	/*
+	 * vcpu, mismatching keys on fetch, fetch protection override applies,
+	 * wraparound
+	 */
+	prepare_mem12();
+	MOP(t.vcpu, LOGICAL, WRITE, mem1, 2 * PAGE_SIZE, GADDR_V(guest_last_page));
+	HOST_SYNC(t.vcpu, STAGE_COPIED);
+	CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048,
+		   GADDR_V(guest_last_page), KEY(2));
+	ASSERT_MEM_EQ(mem1, mem2, 2048);
+
+out:
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_fetch_prot_override_not_enabled(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+	vm_vaddr_t guest_0_page, guest_last_page;
+
+	guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+	guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+	if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+		print_skip("did not allocate guest pages at required positions");
+		goto out;
+	}
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/* vcpu, mismatching keys on fetch, fetch protection override not enabled */
+	CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048, GADDR_V(0), KEY(2));
+
+out:
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void test_errors_key_fetch_prot_override_enabled(void)
+{
+	struct test_default t = test_default_init(guest_copy_key_fetch_prot_override);
+	vm_vaddr_t guest_0_page, guest_last_page;
+
+	guest_0_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, 0);
+	guest_last_page = vm_vaddr_alloc(t.kvm_vm, PAGE_SIZE, last_page_addr);
+	if (guest_0_page != 0 || guest_last_page != last_page_addr) {
+		print_skip("did not allocate guest pages at required positions");
+		goto out;
+	}
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+	t.run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+	t.run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(t.vcpu, STAGE_SKEYS_SET);
+
+	/*
+	 * vcpu, mismatching keys on fetch,
+	 * fetch protection override does not apply because memory range acceeded
+	 */
+	CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, 2048 + 1, GADDR_V(0), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vcpu, LOGICAL, READ, mem2, PAGE_SIZE + 2048 + 1,
+		   GADDR_V(guest_last_page), KEY(2));
+	/* vm, fetch protected override does not apply */
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR(0), KEY(2));
+	CHECK_N_DO(ERR_PROT_MOP, t.vm, ABSOLUTE, READ, mem2, 2048, GADDR_V(guest_0_page), KEY(2));
+
+out:
+	kvm_vm_free(t.kvm_vm);
+}
+
+static void guest_idle(void)
+{
+	GUEST_SYNC(STAGE_INITED); /* for consistency's sake */
+	for (;;)
+		GUEST_SYNC(STAGE_IDLED);
+}
+
+static void _test_errors_common(struct test_vcpu vcpu, enum mop_target target, int size)
+{
+	int rv;
+
+	/* Bad size: */
+	rv = ERR_MOP(vcpu, target, WRITE, mem1, -1, GADDR_V(mem1));
 	TEST_ASSERT(rv == -1 && errno == E2BIG, "ioctl allows insane sizes");
 
 	/* Zero size: */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = 0;
-	ksmo.size = 0;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	rv = ERR_MOP(vcpu, target, WRITE, mem1, 0, GADDR_V(mem1));
 	TEST_ASSERT(rv == -1 && (errno == EINVAL || errno == ENOMEM),
 		    "ioctl allows 0 as size");
 
 	/* Bad flags: */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = -1;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), SET_FLAGS(-1));
 	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows all flags");
 
-	/* Bad operation: */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = 0;
-	ksmo.size = maxsize;
-	ksmo.op = -1;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
-	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations");
-
 	/* Bad guest address: */
-	ksmo.gaddr = ~0xfffUL;
-	ksmo.flags = KVM_S390_MEMOP_F_CHECK_ONLY;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR((void *)~0xfffUL), CHECK_ONLY);
 	TEST_ASSERT(rv > 0, "ioctl does not report bad guest memory access");
 
 	/* Bad host address: */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = 0;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = 0;
-	ksmo.ar = 0;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	rv = ERR_MOP(vcpu, target, WRITE, 0, size, GADDR_V(mem1));
 	TEST_ASSERT(rv == -1 && errno == EFAULT,
 		    "ioctl does not report bad host memory address");
 
+	/* Bad key: */
+	rv = ERR_MOP(vcpu, target, WRITE, mem1, size, GADDR_V(mem1), KEY(17));
+	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows invalid key");
+}
+
+static void test_errors(void)
+{
+	struct test_default t = test_default_init(guest_idle);
+	int rv;
+
+	HOST_SYNC(t.vcpu, STAGE_INITED);
+
+	_test_errors_common(t.vcpu, LOGICAL, t.size);
+	_test_errors_common(t.vm, ABSOLUTE, t.size);
+
+	/* Bad operation: */
+	rv = ERR_MOP(t.vcpu, INVALID, WRITE, mem1, t.size, GADDR_V(mem1));
+	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations");
+	/* virtual addresses are not translated when passing INVALID */
+	rv = ERR_MOP(t.vm, INVALID, WRITE, mem1, PAGE_SIZE, GADDR(0));
+	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows bad operations");
+
 	/* Bad access register: */
-	run->psw_mask &= ~(3UL << (63 - 17));
-	run->psw_mask |= 1UL << (63 - 17);  /* Enable AR mode */
-	vcpu_run(vm, VCPU_ID);              /* To sync new state to SIE block */
-	ksmo.gaddr = (uintptr_t)mem1;
-	ksmo.flags = 0;
-	ksmo.size = maxsize;
-	ksmo.op = KVM_S390_MEMOP_LOGICAL_WRITE;
-	ksmo.buf = (uintptr_t)mem1;
-	ksmo.ar = 17;
-	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_MEM_OP, &ksmo);
+	t.run->psw_mask &= ~(3UL << (63 - 17));
+	t.run->psw_mask |= 1UL << (63 - 17);  /* Enable AR mode */
+	HOST_SYNC(t.vcpu, STAGE_IDLED); /* To sync new state to SIE block */
+	rv = ERR_MOP(t.vcpu, LOGICAL, WRITE, mem1, t.size, GADDR_V(mem1), AR(17));
 	TEST_ASSERT(rv == -1 && errno == EINVAL, "ioctl allows ARs > 15");
-	run->psw_mask &= ~(3UL << (63 - 17));   /* Disable AR mode */
-	vcpu_run(vm, VCPU_ID);                  /* Run to sync new state */
+	t.run->psw_mask &= ~(3UL << (63 - 17));   /* Disable AR mode */
+	HOST_SYNC(t.vcpu, STAGE_IDLED); /* Run to sync new state */
+
+	/* Check that the SIDA calls are rejected for non-protected guests */
+	rv = ERR_MOP(t.vcpu, SIDA, READ, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0));
+	TEST_ASSERT(rv == -1 && errno == EINVAL,
+		    "ioctl does not reject SIDA_READ in non-protected mode");
+	rv = ERR_MOP(t.vcpu, SIDA, WRITE, mem1, 8, GADDR(0), SIDA_OFFSET(0x1c0));
+	TEST_ASSERT(rv == -1 && errno == EINVAL,
+		    "ioctl does not reject SIDA_WRITE in non-protected mode");
+
+	kvm_vm_free(t.kvm_vm);
+}
 
-	kvm_vm_free(vm);
+int main(int argc, char *argv[])
+{
+	int memop_cap, extension_cap;
+
+	setbuf(stdout, NULL);	/* Tell stdout not to buffer its content */
+
+	memop_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP);
+	extension_cap = kvm_check_cap(KVM_CAP_S390_MEM_OP_EXTENSION);
+	if (!memop_cap) {
+		print_skip("CAP_S390_MEM_OP not supported");
+		exit(KSFT_SKIP);
+	}
+
+	test_copy();
+	if (extension_cap > 0) {
+		test_copy_key();
+		test_copy_key_storage_prot_override();
+		test_copy_key_fetch_prot();
+		test_copy_key_fetch_prot_override();
+		test_errors_key();
+		test_errors_key_storage_prot_override();
+		test_errors_key_fetch_prot_override_not_enabled();
+		test_errors_key_fetch_prot_override_enabled();
+	} else {
+		print_skip("storage key memop extension not supported");
+	}
+	test_errors();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390x/tprot.c
new file mode 100644
index 000000000000..c097b9db495e
--- /dev/null
+++ b/tools/testing/selftests/kvm/s390x/tprot.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test TEST PROTECTION emulation.
+ *
+ * Copyright IBM Corp. 2021
+ */
+
+#include <sys/mman.h>
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1 << PAGE_SHIFT)
+#define CR0_FETCH_PROTECTION_OVERRIDE	(1UL << (63 - 38))
+#define CR0_STORAGE_PROTECTION_OVERRIDE	(1UL << (63 - 39))
+
+#define VCPU_ID 1
+
+static __aligned(PAGE_SIZE) uint8_t pages[2][PAGE_SIZE];
+static uint8_t *const page_store_prot = pages[0];
+static uint8_t *const page_fetch_prot = pages[1];
+
+/* Nonzero return value indicates that address not mapped */
+static int set_storage_key(void *addr, uint8_t key)
+{
+	int not_mapped = 0;
+
+	asm volatile (
+		       "lra	%[addr], 0(0,%[addr])\n"
+		"	jz	0f\n"
+		"	llill	%[not_mapped],1\n"
+		"	j	1f\n"
+		"0:	sske	%[key], %[addr]\n"
+		"1:"
+		: [addr] "+&a" (addr), [not_mapped] "+r" (not_mapped)
+		: [key] "r" (key)
+		: "cc"
+	);
+	return -not_mapped;
+}
+
+enum permission {
+	READ_WRITE = 0,
+	READ = 1,
+	RW_PROTECTED = 2,
+	TRANSL_UNAVAIL = 3,
+};
+
+static enum permission test_protection(void *addr, uint8_t key)
+{
+	uint64_t mask;
+
+	asm volatile (
+		       "tprot	%[addr], 0(%[key])\n"
+		"	ipm	%[mask]\n"
+		: [mask] "=r" (mask)
+		: [addr] "Q" (*(char *)addr),
+		  [key] "a" (key)
+		: "cc"
+	);
+
+	return (enum permission)(mask >> 28);
+}
+
+enum stage {
+	STAGE_END,
+	STAGE_INIT_SIMPLE,
+	TEST_SIMPLE,
+	STAGE_INIT_FETCH_PROT_OVERRIDE,
+	TEST_FETCH_PROT_OVERRIDE,
+	TEST_STORAGE_PROT_OVERRIDE,
+};
+
+struct test {
+	enum stage stage;
+	void *addr;
+	uint8_t key;
+	enum permission expected;
+} tests[] = {
+	/*
+	 * We perform each test in the array by executing TEST PROTECTION on
+	 * the specified addr with the specified key and checking if the returned
+	 * permissions match the expected value.
+	 * Both guest and host cooperate to set up the required test conditions.
+	 * A central condition is that the page targeted by addr has to be DAT
+	 * protected in the host mappings, in order for KVM to emulate the
+	 * TEST PROTECTION instruction.
+	 * Since the page tables are shared, the host uses mprotect to achieve
+	 * this.
+	 *
+	 * Test resulting in RW_PROTECTED/TRANSL_UNAVAIL will be interpreted
+	 * by SIE, not KVM, but there is no harm in testing them also.
+	 * See Enhanced Suppression-on-Protection Facilities in the
+	 * Interpretive-Execution Mode
+	 */
+	/*
+	 * guest: set storage key of page_store_prot to 1
+	 *        storage key of page_fetch_prot to 9 and enable
+	 *        protection for it
+	 * STAGE_INIT_SIMPLE
+	 * host: write protect both via mprotect
+	 */
+	/* access key 0 matches any storage key -> RW */
+	{ TEST_SIMPLE, page_store_prot, 0x00, READ_WRITE },
+	/* access key matches storage key -> RW */
+	{ TEST_SIMPLE, page_store_prot, 0x10, READ_WRITE },
+	/* mismatched keys, but no fetch protection -> RO */
+	{ TEST_SIMPLE, page_store_prot, 0x20, READ },
+	/* access key 0 matches any storage key -> RW */
+	{ TEST_SIMPLE, page_fetch_prot, 0x00, READ_WRITE },
+	/* access key matches storage key -> RW */
+	{ TEST_SIMPLE, page_fetch_prot, 0x90, READ_WRITE },
+	/* mismatched keys, fetch protection -> inaccessible */
+	{ TEST_SIMPLE, page_fetch_prot, 0x10, RW_PROTECTED },
+	/* page 0 not mapped yet -> translation not available */
+	{ TEST_SIMPLE, (void *)0x00, 0x10, TRANSL_UNAVAIL },
+	/*
+	 * host: try to map page 0
+	 * guest: set storage key of page 0 to 9 and enable fetch protection
+	 * STAGE_INIT_FETCH_PROT_OVERRIDE
+	 * host: write protect page 0
+	 *       enable fetch protection override
+	 */
+	/* mismatched keys, fetch protection, but override applies -> RO */
+	{ TEST_FETCH_PROT_OVERRIDE, (void *)0x00, 0x10, READ },
+	/* mismatched keys, fetch protection, override applies to 0-2048 only -> inaccessible */
+	{ TEST_FETCH_PROT_OVERRIDE, (void *)2049, 0x10, RW_PROTECTED },
+	/*
+	 * host: enable storage protection override
+	 */
+	/* mismatched keys, but override applies (storage key 9) -> RW */
+	{ TEST_STORAGE_PROT_OVERRIDE, page_fetch_prot, 0x10, READ_WRITE },
+	/* mismatched keys, no fetch protection, override doesn't apply -> RO */
+	{ TEST_STORAGE_PROT_OVERRIDE, page_store_prot, 0x20, READ },
+	/* mismatched keys, but override applies (storage key 9) -> RW */
+	{ TEST_STORAGE_PROT_OVERRIDE, (void *)2049, 0x10, READ_WRITE },
+	/* end marker */
+	{ STAGE_END, 0, 0, 0 },
+};
+
+static enum stage perform_next_stage(int *i, bool mapped_0)
+{
+	enum stage stage = tests[*i].stage;
+	enum permission result;
+	bool skip;
+
+	for (; tests[*i].stage == stage; (*i)++) {
+		/*
+		 * Some fetch protection override tests require that page 0
+		 * be mapped, however, when the hosts tries to map that page via
+		 * vm_vaddr_alloc, it may happen that some other page gets mapped
+		 * instead.
+		 * In order to skip these tests we detect this inside the guest
+		 */
+		skip = tests[*i].addr < (void *)4096 &&
+		       tests[*i].expected != TRANSL_UNAVAIL &&
+		       !mapped_0;
+		if (!skip) {
+			result = test_protection(tests[*i].addr, tests[*i].key);
+			GUEST_ASSERT_2(result == tests[*i].expected, *i, result);
+		}
+	}
+	return stage;
+}
+
+static void guest_code(void)
+{
+	bool mapped_0;
+	int i = 0;
+
+	GUEST_ASSERT_EQ(set_storage_key(page_store_prot, 0x10), 0);
+	GUEST_ASSERT_EQ(set_storage_key(page_fetch_prot, 0x98), 0);
+	GUEST_SYNC(STAGE_INIT_SIMPLE);
+	GUEST_SYNC(perform_next_stage(&i, false));
+
+	/* Fetch-protection override */
+	mapped_0 = !set_storage_key((void *)0, 0x98);
+	GUEST_SYNC(STAGE_INIT_FETCH_PROT_OVERRIDE);
+	GUEST_SYNC(perform_next_stage(&i, mapped_0));
+
+	/* Storage-protection override */
+	GUEST_SYNC(perform_next_stage(&i, mapped_0));
+}
+
+#define HOST_SYNC(vmp, stage)							\
+({										\
+	struct kvm_vm *__vm = (vmp);						\
+	struct ucall uc;							\
+	int __stage = (stage);							\
+										\
+	vcpu_run(__vm, VCPU_ID);						\
+	get_ucall(__vm, VCPU_ID, &uc);						\
+	if (uc.cmd == UCALL_ABORT) {						\
+		TEST_FAIL("line %lu: %s, hints: %lu, %lu", uc.args[1],		\
+			  (const char *)uc.args[0], uc.args[2], uc.args[3]);	\
+	}									\
+	ASSERT_EQ(uc.cmd, UCALL_SYNC);						\
+	ASSERT_EQ(uc.args[1], __stage);						\
+})
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	vm_vaddr_t guest_0_page;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	run = vcpu_state(vm, VCPU_ID);
+
+	HOST_SYNC(vm, STAGE_INIT_SIMPLE);
+	mprotect(addr_gva2hva(vm, (vm_vaddr_t)pages), PAGE_SIZE * 2, PROT_READ);
+	HOST_SYNC(vm, TEST_SIMPLE);
+
+	guest_0_page = vm_vaddr_alloc(vm, PAGE_SIZE, 0);
+	if (guest_0_page != 0)
+		print_skip("Did not allocate page at 0 for fetch protection override tests");
+	HOST_SYNC(vm, STAGE_INIT_FETCH_PROT_OVERRIDE);
+	if (guest_0_page == 0)
+		mprotect(addr_gva2hva(vm, (vm_vaddr_t)0), PAGE_SIZE, PROT_READ);
+	run->s.regs.crs[0] |= CR0_FETCH_PROTECTION_OVERRIDE;
+	run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(vm, TEST_FETCH_PROT_OVERRIDE);
+
+	run->s.regs.crs[0] |= CR0_STORAGE_PROTECTION_OVERRIDE;
+	run->kvm_dirty_regs = KVM_SYNC_CRS;
+	HOST_SYNC(vm, TEST_STORAGE_PROT_OVERRIDE);
+}
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 72a1c9b4882c..73bc297dabe6 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -329,22 +329,6 @@ static void test_zero_memory_regions(void)
 }
 #endif /* __x86_64__ */
 
-static int test_memory_region_add(struct kvm_vm *vm, void *mem, uint32_t slot,
-				   uint32_t size, uint64_t guest_addr)
-{
-	struct kvm_userspace_memory_region region;
-	int ret;
-
-	region.slot = slot;
-	region.flags = 0;
-	region.guest_phys_addr = guest_addr;
-	region.memory_size = size;
-	region.userspace_addr = (uintptr_t) mem;
-	ret = ioctl(vm_get_fd(vm), KVM_SET_USER_MEMORY_REGION, &region);
-
-	return ret;
-}
-
 /*
  * Test it can be added memory slots up to KVM_CAP_NR_MEMSLOTS, then any
  * tentative to add further slots should fail.
@@ -382,23 +366,20 @@ static void test_add_max_memory_regions(void)
 	TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
 	mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
 
-	for (slot = 0; slot < max_mem_slots; slot++) {
-		ret = test_memory_region_add(vm, mem_aligned +
-					     ((uint64_t)slot * MEM_REGION_SIZE),
-					     slot, MEM_REGION_SIZE,
-					     (uint64_t)slot * MEM_REGION_SIZE);
-		TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
-			    "  rc: %i errno: %i slot: %i\n",
-			    ret, errno, slot);
-	}
+	for (slot = 0; slot < max_mem_slots; slot++)
+		vm_set_user_memory_region(vm, slot, 0,
+					  ((uint64_t)slot * MEM_REGION_SIZE),
+					  MEM_REGION_SIZE,
+					  mem_aligned + (uint64_t)slot * MEM_REGION_SIZE);
 
 	/* Check it cannot be added memory slots beyond the limit */
 	mem_extra = mmap(NULL, MEM_REGION_SIZE, PROT_READ | PROT_WRITE,
 			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
 	TEST_ASSERT(mem_extra != MAP_FAILED, "Failed to mmap() host");
 
-	ret = test_memory_region_add(vm, mem_extra, max_mem_slots, MEM_REGION_SIZE,
-				     (uint64_t)max_mem_slots * MEM_REGION_SIZE);
+	ret = __vm_set_user_memory_region(vm, max_mem_slots, 0,
+					  (uint64_t)max_mem_slots * MEM_REGION_SIZE,
+					  MEM_REGION_SIZE, mem_extra);
 	TEST_ASSERT(ret == -1 && errno == EINVAL,
 		    "Adding one more memory slot should fail with EINVAL");
 
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index 4c7841dfd481..d12e043aa2ee 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -10,6 +10,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/ioctl.h>
+#include <linux/bitmap.h>
 
 #include "test_util.h"
 
@@ -32,6 +33,22 @@ static void guest_nmi_handler(struct ex_regs *regs)
 {
 }
 
+/* Exits to L1 destroy GRPs! */
+static inline void rdmsr_fs_base(void)
+{
+	__asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : :
+			      "rax", "rbx", "rcx", "rdx",
+			      "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
+			      "r13", "r14", "r15");
+}
+static inline void rdmsr_gs_base(void)
+{
+	__asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : :
+			      "rax", "rbx", "rcx", "rdx",
+			      "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
+			      "r13", "r14", "r15");
+}
+
 void l2_guest_code(void)
 {
 	GUEST_SYNC(7);
@@ -41,6 +58,15 @@ void l2_guest_code(void)
 	/* Forced exit to L1 upon restore */
 	GUEST_SYNC(9);
 
+	vmcall();
+
+	/* MSR-Bitmap tests */
+	rdmsr_fs_base(); /* intercepted */
+	rdmsr_fs_base(); /* intercepted */
+	rdmsr_gs_base(); /* not intercepted */
+	vmcall();
+	rdmsr_gs_base(); /* intercepted */
+
 	/* Done, exit to L1 and never come back.  */
 	vmcall();
 }
@@ -76,8 +102,9 @@ void guest_code(struct vmx_pages *vmx_pages)
 	current_evmcs->revision_id = EVMCS_VERSION;
 	GUEST_SYNC(6);
 
-	current_evmcs->pin_based_vm_exec_control |=
-		PIN_BASED_NMI_EXITING;
+	vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) |
+		PIN_BASED_NMI_EXITING);
+
 	GUEST_ASSERT(!vmlaunch());
 	GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
 
@@ -91,6 +118,39 @@ void guest_code(struct vmx_pages *vmx_pages)
 	GUEST_SYNC(10);
 
 	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	current_evmcs->guest_rip += 3; /* vmcall */
+
+	/* Intercept RDMSR 0xc0000100 */
+	vmwrite(CPU_BASED_VM_EXEC_CONTROL, vmreadz(CPU_BASED_VM_EXEC_CONTROL) |
+		CPU_BASED_USE_MSR_BITMAPS);
+	set_bit(MSR_FS_BASE & 0x1fff, vmx_pages->msr + 0x400);
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
+	current_evmcs->guest_rip += 2; /* rdmsr */
+
+	/* Enable enlightened MSR bitmap */
+	current_evmcs->hv_enlightenments_control.msr_bitmap = 1;
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
+	current_evmcs->guest_rip += 2; /* rdmsr */
+
+	/* Intercept RDMSR 0xc0000101 without telling KVM about it */
+	set_bit(MSR_GS_BASE & 0x1fff, vmx_pages->msr + 0x400);
+	/* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */
+	current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+	GUEST_ASSERT(!vmresume());
+	/* Make sure we don't see EXIT_REASON_MSR_READ here so eMSR bitmap works */
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	current_evmcs->guest_rip += 3; /* vmcall */
+
+	/* Now tell KVM we've changed MSR-Bitmap */
+	current_evmcs->hv_clean_fields &= ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP;
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
+	current_evmcs->guest_rip += 2; /* rdmsr */
+
+	GUEST_ASSERT(!vmresume());
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
 	GUEST_SYNC(11);
 
 	/* Try enlightened vmptrld with an incorrect GPA */
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 7e2d2d17d2ed..8c245ab2d98a 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -49,16 +49,13 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			  bool evmcs_expected)
 {
 	int i;
-	int nent = 9;
+	int nent_expected = 10;
 	u32 test_val;
 
-	if (evmcs_expected)
-		nent += 1; /* 0x4000000A */
-
-	TEST_ASSERT(hv_cpuid_entries->nent == nent,
+	TEST_ASSERT(hv_cpuid_entries->nent == nent_expected,
 		    "KVM_GET_SUPPORTED_HV_CPUID should return %d entries"
-		    " with evmcs=%d (returned %d)",
-		    nent, evmcs_expected, hv_cpuid_entries->nent);
+		    " (returned %d)",
+		    nent_expected, hv_cpuid_entries->nent);
 
 	for (i = 0; i < hv_cpuid_entries->nent; i++) {
 		struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
@@ -68,9 +65,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 			    "function %x is our of supported range",
 			    entry->function);
 
-		TEST_ASSERT(evmcs_expected || (entry->function != 0x4000000A),
-			    "0x4000000A leaf should not be reported");
-
 		TEST_ASSERT(entry->index == 0,
 			    ".index field should be zero");
 
@@ -97,8 +91,20 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 				    "NoNonArchitecturalCoreSharing bit"
 				    " doesn't reflect SMT setting");
 			break;
-		}
+		case 0x4000000A:
+			TEST_ASSERT(entry->eax & (1UL << 19),
+				    "Enlightened MSR-Bitmap should always be supported"
+				    " 0x40000000.EAX: %x", entry->eax);
+			if (evmcs_expected)
+				TEST_ASSERT((entry->eax & 0xffff) == 0x101,
+				    "Supported Enlightened VMCS version range is supposed to be 1:1"
+				    " 0x40000000.EAX: %x", entry->eax);
+
+			break;
+		default:
+			break;
 
+		}
 		/*
 		 * If needed for debug:
 		 * fprintf(stdout,
@@ -107,7 +113,6 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
 		 *	entry->edx);
 		 */
 	}
-
 }
 
 void test_hv_cpuid_e2big(struct kvm_vm *vm, bool system)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
new file mode 100644
index 000000000000..21f5ca9197da
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM_GET/SET_* tests
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ * Tests for Hyper-V extensions to SVM.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <linux/bitmap.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "hyperv.h"
+
+#define VCPU_ID		1
+#define L2_GUEST_STACK_SIZE 256
+
+struct hv_enlightenments {
+	struct __packed hv_enlightenments_control {
+		u32 nested_flush_hypercall:1;
+		u32 msr_bitmap:1;
+		u32 enlightened_npt_tlb: 1;
+		u32 reserved:29;
+	} __packed hv_enlightenments_control;
+	u32 hv_vp_id;
+	u64 hv_vm_id;
+	u64 partition_assist_page;
+	u64 reserved;
+} __packed;
+
+/*
+ * Hyper-V uses the software reserved clean bit in VMCB
+ */
+#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31)
+
+static inline void vmmcall(void)
+{
+	__asm__ __volatile__("vmmcall");
+}
+
+void l2_guest_code(void)
+{
+	GUEST_SYNC(3);
+	/* Exit to L1 */
+	vmmcall();
+
+	/* MSR-Bitmap tests */
+	rdmsr(MSR_FS_BASE); /* intercepted */
+	rdmsr(MSR_FS_BASE); /* intercepted */
+	rdmsr(MSR_GS_BASE); /* not intercepted */
+	vmmcall();
+	rdmsr(MSR_GS_BASE); /* intercepted */
+
+	GUEST_SYNC(5);
+
+	/* Done, exit to L1 and never come back.  */
+	vmmcall();
+}
+
+static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm)
+{
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+	struct vmcb *vmcb = svm->vmcb;
+	struct hv_enlightenments *hve =
+		(struct hv_enlightenments *)vmcb->control.reserved_sw;
+
+	GUEST_SYNC(1);
+
+	wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+
+	GUEST_ASSERT(svm->vmcb_gpa);
+	/* Prepare for L2 execution. */
+	generic_svm_setup(svm, l2_guest_code,
+			  &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(2);
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	GUEST_SYNC(4);
+	vmcb->save.rip += 3;
+
+	/* Intercept RDMSR 0xc0000100 */
+	vmcb->control.intercept |= 1ULL << INTERCEPT_MSR_PROT;
+	set_bit(2 * (MSR_FS_BASE & 0x1fff), svm->msr + 0x800);
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
+	vmcb->save.rip += 2; /* rdmsr */
+
+	/* Enable enlightened MSR bitmap */
+	hve->hv_enlightenments_control.msr_bitmap = 1;
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
+	vmcb->save.rip += 2; /* rdmsr */
+
+	/* Intercept RDMSR 0xc0000101 without telling KVM about it */
+	set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800);
+	/* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */
+	vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS;
+	run_guest(vmcb, svm->vmcb_gpa);
+	/* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	vmcb->save.rip += 3; /* vmcall */
+
+	/* Now tell KVM we've changed MSR-Bitmap */
+	vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS;
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
+	vmcb->save.rip += 2; /* rdmsr */
+
+	run_guest(vmcb, svm->vmcb_gpa);
+	GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
+	GUEST_SYNC(6);
+
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t nested_gva = 0;
+
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct ucall uc;
+	int stage;
+
+	if (!nested_svm_supported()) {
+		print_skip("Nested SVM not supported");
+		exit(KSFT_SKIP);
+	}
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_hv_cpuid(vm, VCPU_ID);
+	run = vcpu_state(vm, VCPU_ID);
+	vcpu_alloc_svm(vm, &nested_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, nested_gva);
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+				  __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		}
+
+		/* UCALL_SYNC is handled here.  */
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+			    uc.args[1] == stage, "Stage %d: Unexpected register values vmexit, got %lx",
+			    stage, (ulong)uc.args[1]);
+
+	}
+
+done:
+	kvm_vm_free(vm);
+}
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 c715adcbd487..0d06ffa95d9d 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
@@ -326,6 +326,37 @@ static void test_not_member_allow_list(struct kvm_vm *vm)
 }
 
 /*
+ * Verify that setting KVM_PMU_CAP_DISABLE prevents the use of the PMU.
+ *
+ * Note that KVM_CAP_PMU_CAPABILITY must be invoked prior to creating VCPUs.
+ */
+static void test_pmu_config_disable(void (*guest_code)(void))
+{
+	int r;
+	struct kvm_vm *vm;
+	struct kvm_enable_cap cap = { 0 };
+
+	r = kvm_check_cap(KVM_CAP_PMU_CAPABILITY);
+	if (!(r & KVM_PMU_CAP_DISABLE))
+		return;
+
+	vm = vm_create_without_vcpus(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES);
+
+	cap.cap = KVM_CAP_PMU_CAPABILITY;
+	cap.args[0] = KVM_PMU_CAP_DISABLE;
+	TEST_ASSERT(!vm_enable_cap(vm, &cap), "Failed to set KVM_PMU_CAP_DISABLE.");
+
+	vm_vcpu_add_default(vm, VCPU_ID, guest_code);
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+
+	TEST_ASSERT(!sanity_check_pmu(vm),
+		    "Guest should not be able to use disabled PMU.");
+
+	kvm_vm_free(vm);
+}
+
+/*
  * Check for a non-zero PMU version, at least one general-purpose
  * counter per logical processor, an EBX bit vector of length greater
  * than 5, and EBX[5] clear.
@@ -430,5 +461,7 @@ int main(int argc, char *argv[])
 
 	kvm_vm_free(vm);
 
+	test_pmu_config_disable(guest_code);
+
 	return 0;
 }
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 80056bbbb003..d1dc1acf997c 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
@@ -21,6 +21,8 @@
 #define NR_LOCK_TESTING_THREADS 3
 #define NR_LOCK_TESTING_ITERATIONS 10000
 
+bool have_sev_es;
+
 static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error)
 {
 	struct kvm_sev_cmd cmd = {
@@ -172,10 +174,18 @@ static void test_sev_migrate_parameters(void)
 		*sev_es_vm_no_vmsa;
 	int ret;
 
-	sev_vm = sev_vm_create(/* es= */ false);
-	sev_es_vm = sev_vm_create(/* es= */ true);
 	vm_no_vcpu = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
 	vm_no_sev = aux_vm_create(true);
+	ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
+		    errno);
+
+	if (!have_sev_es)
+		goto out;
+
+	sev_vm = sev_vm_create(/* es= */ false);
+	sev_es_vm = sev_vm_create(/* es= */ true);
 	sev_es_vm_no_vmsa = vm_create(VM_MODE_DEFAULT, 0, O_RDWR);
 	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
 	vm_vcpu_add(sev_es_vm_no_vmsa, 1);
@@ -204,14 +214,10 @@ static void test_sev_migrate_parameters(void)
 		"SEV-ES migrations require UPDATE_VMSA. ret %d, errno: %d\n",
 		ret, errno);
 
-	ret = __sev_migrate_from(vm_no_vcpu->fd, vm_no_sev->fd);
-	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Migrations require SEV enabled. ret %d, errno: %d\n", ret,
-		    errno);
-
 	kvm_vm_free(sev_vm);
 	kvm_vm_free(sev_es_vm);
 	kvm_vm_free(sev_es_vm_no_vmsa);
+out:
 	kvm_vm_free(vm_no_vcpu);
 	kvm_vm_free(vm_no_sev);
 }
@@ -300,7 +306,6 @@ static void test_sev_mirror_parameters(void)
 	int ret;
 
 	sev_vm = sev_vm_create(/* es= */ false);
-	sev_es_vm = sev_vm_create(/* es= */ true);
 	vm_with_vcpu = aux_vm_create(true);
 	vm_no_vcpu = aux_vm_create(false);
 
@@ -310,6 +315,21 @@ static void test_sev_mirror_parameters(void)
 		"Should not be able copy context to self. ret: %d, errno: %d\n",
 		ret, errno);
 
+	ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd);
+	TEST_ASSERT(ret == -1 && errno == EINVAL,
+		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
+		    errno);
+
+	ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd);
+	TEST_ASSERT(
+		ret == -1 && errno == EINVAL,
+		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
+		ret, errno);
+
+	if (!have_sev_es)
+		goto out;
+
+	sev_es_vm = sev_vm_create(/* es= */ true);
 	ret = __sev_mirror_create(sev_vm->fd, sev_es_vm->fd);
 	TEST_ASSERT(
 		ret == -1 && errno == EINVAL,
@@ -322,63 +342,97 @@ static void test_sev_mirror_parameters(void)
 		"Should not be able copy context to SEV-ES enabled VM. ret: %d, errno: %d\n",
 		ret, errno);
 
-	ret = __sev_mirror_create(vm_no_vcpu->fd, vm_with_vcpu->fd);
-	TEST_ASSERT(ret == -1 && errno == EINVAL,
-		    "Copy context requires SEV enabled. ret %d, errno: %d\n", ret,
-		    errno);
-
-	ret = __sev_mirror_create(vm_with_vcpu->fd, sev_vm->fd);
-	TEST_ASSERT(
-		ret == -1 && errno == EINVAL,
-		"SEV copy context requires no vCPUS on the destination. ret: %d, errno: %d\n",
-		ret, errno);
+	kvm_vm_free(sev_es_vm);
 
+out:
 	kvm_vm_free(sev_vm);
-	kvm_vm_free(sev_es_vm);
 	kvm_vm_free(vm_with_vcpu);
 	kvm_vm_free(vm_no_vcpu);
 }
 
 static void test_sev_move_copy(void)
 {
-	struct kvm_vm *dst_vm, *sev_vm, *mirror_vm, *dst_mirror_vm;
-	int ret;
+	struct kvm_vm *dst_vm, *dst2_vm, *dst3_vm, *sev_vm, *mirror_vm,
+		      *dst_mirror_vm, *dst2_mirror_vm, *dst3_mirror_vm;
 
 	sev_vm = sev_vm_create(/* es= */ false);
 	dst_vm = aux_vm_create(true);
+	dst2_vm = aux_vm_create(true);
+	dst3_vm = aux_vm_create(true);
 	mirror_vm = aux_vm_create(false);
 	dst_mirror_vm = aux_vm_create(false);
+	dst2_mirror_vm = aux_vm_create(false);
+	dst3_mirror_vm = aux_vm_create(false);
 
 	sev_mirror_create(mirror_vm->fd, sev_vm->fd);
-	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
-	TEST_ASSERT(ret == -1 && errno == EBUSY,
-		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
-		    errno);
 
-	/* The mirror itself can be migrated.  */
 	sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd);
-	ret = __sev_migrate_from(dst_vm->fd, sev_vm->fd);
-	TEST_ASSERT(ret == -1 && errno == EBUSY,
-		    "Cannot migrate VM that has mirrors. ret %d, errno: %d\n", ret,
-		    errno);
+	sev_migrate_from(dst_vm->fd, sev_vm->fd);
+
+	sev_migrate_from(dst2_vm->fd, dst_vm->fd);
+	sev_migrate_from(dst2_mirror_vm->fd, dst_mirror_vm->fd);
+
+	sev_migrate_from(dst3_mirror_vm->fd, dst2_mirror_vm->fd);
+	sev_migrate_from(dst3_vm->fd, dst2_vm->fd);
+
+	kvm_vm_free(dst_vm);
+	kvm_vm_free(sev_vm);
+	kvm_vm_free(dst2_vm);
+	kvm_vm_free(dst3_vm);
+	kvm_vm_free(mirror_vm);
+	kvm_vm_free(dst_mirror_vm);
+	kvm_vm_free(dst2_mirror_vm);
+	kvm_vm_free(dst3_mirror_vm);
 
 	/*
-	 * mirror_vm is not a mirror anymore, dst_mirror_vm is.  Thus,
-	 * the owner can be copied as soon as dst_mirror_vm is gone.
+	 * Run similar test be destroy mirrors before mirrored VMs to ensure
+	 * destruction is done safely.
 	 */
-	kvm_vm_free(dst_mirror_vm);
+	sev_vm = sev_vm_create(/* es= */ false);
+	dst_vm = aux_vm_create(true);
+	mirror_vm = aux_vm_create(false);
+	dst_mirror_vm = aux_vm_create(false);
+
+	sev_mirror_create(mirror_vm->fd, sev_vm->fd);
+
+	sev_migrate_from(dst_mirror_vm->fd, mirror_vm->fd);
 	sev_migrate_from(dst_vm->fd, sev_vm->fd);
 
 	kvm_vm_free(mirror_vm);
+	kvm_vm_free(dst_mirror_vm);
 	kvm_vm_free(dst_vm);
 	kvm_vm_free(sev_vm);
 }
 
+#define X86_FEATURE_SEV (1 << 1)
+#define X86_FEATURE_SEV_ES (1 << 3)
+
 int main(int argc, char *argv[])
 {
+	struct kvm_cpuid_entry2 *cpuid;
+
+	if (!kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM) &&
+	    !kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) {
+		print_skip("Capabilities not available");
+		exit(KSFT_SKIP);
+	}
+
+	cpuid = kvm_get_supported_cpuid_entry(0x80000000);
+	if (cpuid->eax < 0x8000001f) {
+		print_skip("AMD memory encryption not available");
+		exit(KSFT_SKIP);
+	}
+	cpuid = kvm_get_supported_cpuid_entry(0x8000001f);
+	if (!(cpuid->eax & X86_FEATURE_SEV)) {
+		print_skip("AMD SEV not available");
+		exit(KSFT_SKIP);
+	}
+	have_sev_es = !!(cpuid->eax & X86_FEATURE_SEV_ES);
+
 	if (kvm_check_cap(KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM)) {
 		test_sev_migrate_from(/* es= */ false);
-		test_sev_migrate_from(/* es= */ true);
+		if (have_sev_es)
+			test_sev_migrate_from(/* es= */ true);
 		test_sev_migrate_locking();
 		test_sev_migrate_parameters();
 		if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM))
@@ -386,7 +440,8 @@ int main(int argc, char *argv[])
 	}
 	if (kvm_check_cap(KVM_CAP_VM_COPY_ENC_CONTEXT_FROM)) {
 		test_sev_mirror(/* es= */ false);
-		test_sev_mirror(/* es= */ true);
+		if (have_sev_es)
+			test_sev_mirror(/* es= */ true);
 		test_sev_mirror_parameters();
 	}
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
new file mode 100644
index 000000000000..0792334ba243
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "apic.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+struct kvm_vcpu {
+	uint32_t id;
+	bool is_x2apic;
+};
+
+static void xapic_guest_code(void)
+{
+	asm volatile("cli");
+
+	xapic_enable();
+
+	while (1) {
+		uint64_t val = (u64)xapic_read_reg(APIC_IRR) |
+			       (u64)xapic_read_reg(APIC_IRR + 0x10) << 32;
+
+		xapic_write_reg(APIC_ICR2, val >> 32);
+		xapic_write_reg(APIC_ICR, val);
+		GUEST_SYNC(val);
+	}
+}
+
+static void x2apic_guest_code(void)
+{
+	asm volatile("cli");
+
+	x2apic_enable();
+
+	do {
+		uint64_t val = x2apic_read_reg(APIC_IRR) |
+			       x2apic_read_reg(APIC_IRR + 0x10) << 32;
+
+		x2apic_write_reg(APIC_ICR, val);
+		GUEST_SYNC(val);
+	} while (1);
+}
+
+static void ____test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val)
+{
+	struct kvm_lapic_state xapic;
+	struct ucall uc;
+	uint64_t icr;
+
+	/*
+	 * Tell the guest what ICR value to write.  Use the IRR to pass info,
+	 * all bits are valid and should not be modified by KVM (ignoring the
+	 * fact that vectors 0-15 are technically illegal).
+	 */
+	vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic);
+	*((u32 *)&xapic.regs[APIC_IRR]) = val;
+	*((u32 *)&xapic.regs[APIC_IRR + 0x10]) = val >> 32;
+	vcpu_ioctl(vm, vcpu->id, KVM_SET_LAPIC, &xapic);
+
+	vcpu_run(vm, vcpu->id);
+	ASSERT_EQ(get_ucall(vm, vcpu->id, &uc), UCALL_SYNC);
+	ASSERT_EQ(uc.args[1], val);
+
+	vcpu_ioctl(vm, vcpu->id, KVM_GET_LAPIC, &xapic);
+	icr = (u64)(*((u32 *)&xapic.regs[APIC_ICR])) |
+	      (u64)(*((u32 *)&xapic.regs[APIC_ICR2])) << 32;
+	if (!vcpu->is_x2apic)
+		val &= (-1u | (0xffull << (32 + 24)));
+	ASSERT_EQ(icr, val & ~APIC_ICR_BUSY);
+}
+
+static void __test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu, uint64_t val)
+{
+	____test_icr(vm, vcpu, val | APIC_ICR_BUSY);
+	____test_icr(vm, vcpu, val & ~(u64)APIC_ICR_BUSY);
+}
+
+static void test_icr(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+{
+	uint64_t icr, i, j;
+
+	icr = APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_FIXED;
+	for (i = 0; i <= 0xff; i++)
+		__test_icr(vm, vcpu, icr | i);
+
+	icr = APIC_INT_ASSERT | APIC_DM_FIXED;
+	for (i = 0; i <= 0xff; i++)
+		__test_icr(vm, vcpu, icr | i);
+
+	/*
+	 * Send all flavors of IPIs to non-existent vCPUs.  TODO: use number of
+	 * vCPUs, not vcpu.id + 1.  Arbitrarily use vector 0xff.
+	 */
+	icr = APIC_INT_ASSERT | 0xff;
+	for (i = vcpu->id + 1; i < 0xff; i++) {
+		for (j = 0; j < 8; j++)
+			__test_icr(vm, vcpu, i << (32 + 24) | APIC_INT_ASSERT | (j << 8));
+	}
+
+	/* And again with a shorthand destination for all types of IPIs. */
+	icr = APIC_DEST_ALLBUT | APIC_INT_ASSERT;
+	for (i = 0; i < 8; i++)
+		__test_icr(vm, vcpu, icr | (i << 8));
+
+	/* And a few garbage value, just make sure it's an IRQ (blocked). */
+	__test_icr(vm, vcpu, 0xa5a5a5a5a5a5a5a5 & ~APIC_DM_FIXED_MASK);
+	__test_icr(vm, vcpu, 0x5a5a5a5a5a5a5a5a & ~APIC_DM_FIXED_MASK);
+	__test_icr(vm, vcpu, -1ull & ~APIC_DM_FIXED_MASK);
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_vcpu vcpu = {
+		.id = 0,
+		.is_x2apic = true,
+	};
+	struct kvm_cpuid2 *cpuid;
+	struct kvm_vm *vm;
+	int i;
+
+	vm = vm_create_default(vcpu.id, 0, x2apic_guest_code);
+	test_icr(vm, &vcpu);
+	kvm_vm_free(vm);
+
+	/*
+	 * Use a second VM for the xAPIC test so that x2APIC can be hidden from
+	 * the guest in order to test AVIC.  KVM disallows changing CPUID after
+	 * KVM_RUN and AVIC is disabled if _any_ vCPU is allowed to use x2APIC.
+	 */
+	vm = vm_create_default(vcpu.id, 0, xapic_guest_code);
+	vcpu.is_x2apic = false;
+
+	cpuid = vcpu_get_cpuid(vm, vcpu.id);
+	for (i = 0; i < cpuid->nent; i++) {
+		if (cpuid->entries[i].function == 1)
+			break;
+	}
+	cpuid->entries[i].ecx &= ~BIT(21);
+	vcpu_set_cpuid(vm, vcpu.id, cpuid);
+
+	virt_pg_map(vm, APIC_DEFAULT_GPA, APIC_DEFAULT_GPA);
+	test_icr(vm, &vcpu);
+	kvm_vm_free(vm);
+}