Merge tag 'kvm-x86-selftests-6.9' of https://github.com/kvm-x86/linux into HEAD

KVM selftests changes for 6.9:

 - Add macros to reduce the amount of boilerplate code needed to write "simple"
   selftests, and to utilize selftest TAP infrastructure, which is especially
   beneficial for KVM selftests with multiple testcases.

 - Add basic smoke tests for SEV and SEV-ES, along with a pile of library
   support for handling private/encrypted/protected memory.

 - Fix benign bugs where tests neglect to close() guest_memfd files.

tools/testing/selftests/kvm/Makefile

@@ -37,6 +37,7 @@ LIBKVM_x86_64 += lib/x86_64/handlers.S
 LIBKVM_x86_64 += lib/x86_64/hyperv.c
 LIBKVM_x86_64 += lib/x86_64/memstress.c
 LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/sev.c
 LIBKVM_x86_64 += lib/x86_64/svm.c
 LIBKVM_x86_64 += lib/x86_64/ucall.c
 LIBKVM_x86_64 += lib/x86_64/vmx.c
@@ -118,6 +119,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
 TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
 TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
+TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test
 TEST_GEN_PROGS_x86_64 += x86_64/amx_test
 TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test
 TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test

tools/testing/selftests/kvm/guest_memfd_test.c

@@ -167,6 +167,9 @@ static void test_create_guest_memfd_multiple(struct kvm_vm *vm)
 	TEST_ASSERT(ret != -1, "memfd fstat should succeed");
 	TEST_ASSERT(st1.st_size == 4096, "first memfd st_size should still match requested size");
 	TEST_ASSERT(st1.st_ino != st2.st_ino, "different memfd should have different inode numbers");
+
+	close(fd2);
+	close(fd1);
 }
 
 int main(int argc, char *argv[])

tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/kvm_test_harness.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Macros for defining a KVM test
+ *
+ * Copyright (C) 2022, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_TEST_HARNESS_H
+#define SELFTEST_KVM_TEST_HARNESS_H
+
+#include "kselftest_harness.h"
+
+#define KVM_ONE_VCPU_TEST_SUITE(name)					\
+	FIXTURE(name) {							\
+		struct kvm_vcpu *vcpu;					\
+	};								\
+									\
+	FIXTURE_SETUP(name) {						\
+		(void)vm_create_with_one_vcpu(&self->vcpu, NULL);	\
+	}								\
+									\
+	FIXTURE_TEARDOWN(name) {					\
+		kvm_vm_free(self->vcpu->vm);				\
+	}
+
+#define KVM_ONE_VCPU_TEST(suite, test, guestcode)			\
+static void __suite##_##test(struct kvm_vcpu *vcpu);			\
+									\
+TEST_F(suite, test)							\
+{									\
+	vcpu_arch_set_entry_point(self->vcpu, guestcode);		\
+	__suite##_##test(self->vcpu);					\
+}									\
+static void __suite##_##test(struct kvm_vcpu *vcpu)
+
+#endif /* SELFTEST_KVM_TEST_HARNESS_H */

tools/testing/selftests/kvm/include/kvm_util_base.h

@@ -18,9 +18,11 @@
 #include <linux/types.h>
 
 #include <asm/atomic.h>
+#include <asm/kvm.h>
 
 #include <sys/ioctl.h>
 
+#include "kvm_util_arch.h"
 #include "sparsebit.h"
 
 /*
@@ -46,6 +48,7 @@ typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
 struct userspace_mem_region {
 	struct kvm_userspace_memory_region2 region;
 	struct sparsebit *unused_phy_pages;
+	struct sparsebit *protected_phy_pages;
 	int fd;
 	off_t offset;
 	enum vm_mem_backing_src_type backing_src_type;
@@ -90,6 +93,7 @@ enum kvm_mem_region_type {
 struct kvm_vm {
 	int mode;
 	unsigned long type;
+	uint8_t subtype;
 	int kvm_fd;
 	int fd;
 	unsigned int pgtable_levels;
@@ -111,6 +115,9 @@ struct kvm_vm {
 	vm_vaddr_t idt;
 	vm_vaddr_t handlers;
 	uint32_t dirty_ring_size;
+	uint64_t gpa_tag_mask;
+
+	struct kvm_vm_arch arch;
 
 	/* Cache of information for binary stats interface */
 	int stats_fd;
@@ -191,10 +198,14 @@ enum vm_guest_mode {
 };
 
 struct vm_shape {
-	enum vm_guest_mode mode;
-	unsigned int type;
+	uint32_t type;
+	uint8_t  mode;
+	uint8_t  subtype;
+	uint16_t padding;
 };
 
+kvm_static_assert(sizeof(struct vm_shape) == sizeof(uint64_t));
+
 #define VM_TYPE_DEFAULT			0
 
 #define VM_SHAPE(__mode)			\
@@ -564,6 +575,13 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 		uint64_t guest_paddr, uint32_t slot, uint64_t npages,
 		uint32_t flags, int guest_memfd_fd, uint64_t guest_memfd_offset);
 
+#ifndef vm_arch_has_protected_memory
+static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm)
+{
+	return false;
+}
+#endif
+
 void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
 void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
@@ -573,6 +591,9 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_mi
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
 vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 			    enum kvm_mem_region_type type);
+vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz,
+				 vm_vaddr_t vaddr_min,
+				 enum kvm_mem_region_type type);
 vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
 vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm,
 				 enum kvm_mem_region_type type);
@@ -585,6 +606,12 @@ void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
 vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
 void *addr_gpa2alias(struct kvm_vm *vm, vm_paddr_t gpa);
 
+
+static inline vm_paddr_t vm_untag_gpa(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	return gpa & ~vm->gpa_tag_mask;
+}
+
 void vcpu_run(struct kvm_vcpu *vcpu);
 int _vcpu_run(struct kvm_vcpu *vcpu);
 
@@ -827,10 +854,23 @@ const char *exit_reason_str(unsigned int exit_reason);
 
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 			     uint32_t memslot);
-vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
-			      vm_paddr_t paddr_min, uint32_t memslot);
+vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+				vm_paddr_t paddr_min, uint32_t memslot,
+				bool protected);
 vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
 
+static inline vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+					    vm_paddr_t paddr_min, uint32_t memslot)
+{
+	/*
+	 * By default, allocate memory as protected for VMs that support
+	 * protected memory, as the majority of memory for such VMs is
+	 * protected, i.e. using shared memory is effectively opt-in.
+	 */
+	return __vm_phy_pages_alloc(vm, num, paddr_min, memslot,
+				    vm_arch_has_protected_memory(vm));
+}
+
 /*
  * ____vm_create() does KVM_CREATE_VM and little else.  __vm_create() also
  * loads the test binary into guest memory and creates an IRQ chip (x86 only).
@@ -969,15 +1009,18 @@ static inline void vcpu_dump(FILE *stream, struct kvm_vcpu *vcpu,
  * Input Args:
  *   vm - Virtual Machine
  *   vcpu_id - The id of the VCPU to add to the VM.
- *   guest_code - The vCPU's entry point
  */
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code);
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code);
 
 static inline struct kvm_vcpu *vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 					   void *guest_code)
 {
-	return vm_arch_vcpu_add(vm, vcpu_id, guest_code);
+	struct kvm_vcpu *vcpu = vm_arch_vcpu_add(vm, vcpu_id);
+
+	vcpu_arch_set_entry_point(vcpu, guest_code);
+
+	return vcpu;
 }
 
 /* Re-create a vCPU after restarting a VM, e.g. for state save/restore tests. */
@@ -1081,6 +1124,8 @@ void kvm_selftest_arch_init(void);
 
 void kvm_arch_vm_post_create(struct kvm_vm *vm);
 
+bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr);
+
 uint32_t guest_get_vcpuid(void);
 
 #endif /* SELFTEST_KVM_UTIL_BASE_H */

tools/testing/selftests/kvm/include/riscv/kvm_util_arch.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+struct kvm_vm_arch {};
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/sparsebit.h

@@ -30,26 +30,26 @@ typedef uint64_t sparsebit_num_t;
 
 struct sparsebit *sparsebit_alloc(void);
 void sparsebit_free(struct sparsebit **sbitp);
-void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src);
+void sparsebit_copy(struct sparsebit *dstp, const struct sparsebit *src);
 
-bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx);
-bool sparsebit_is_set_num(struct sparsebit *sbit,
+bool sparsebit_is_set(const struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_set_num(const struct sparsebit *sbit,
 			  sparsebit_idx_t idx, sparsebit_num_t num);
-bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx);
-bool sparsebit_is_clear_num(struct sparsebit *sbit,
+bool sparsebit_is_clear(const struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_clear_num(const struct sparsebit *sbit,
 			    sparsebit_idx_t idx, sparsebit_num_t num);
-sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit);
-bool sparsebit_any_set(struct sparsebit *sbit);
-bool sparsebit_any_clear(struct sparsebit *sbit);
-bool sparsebit_all_set(struct sparsebit *sbit);
-bool sparsebit_all_clear(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit);
-sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev);
-sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev);
-sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit,
+sparsebit_num_t sparsebit_num_set(const struct sparsebit *sbit);
+bool sparsebit_any_set(const struct sparsebit *sbit);
+bool sparsebit_any_clear(const struct sparsebit *sbit);
+bool sparsebit_all_set(const struct sparsebit *sbit);
+bool sparsebit_all_clear(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_set(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_next_set(const struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *sbit,
 				       sparsebit_idx_t start, sparsebit_num_t num);
-sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit,
+sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *sbit,
 					 sparsebit_idx_t start, sparsebit_num_t num);
 
 void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx);
@@ -62,9 +62,29 @@ void sparsebit_clear_num(struct sparsebit *sbitp,
 			 sparsebit_idx_t start, sparsebit_num_t num);
 void sparsebit_clear_all(struct sparsebit *sbitp);
 
-void sparsebit_dump(FILE *stream, struct sparsebit *sbit,
+void sparsebit_dump(FILE *stream, const struct sparsebit *sbit,
 		    unsigned int indent);
-void sparsebit_validate_internal(struct sparsebit *sbit);
+void sparsebit_validate_internal(const struct sparsebit *sbit);
+
+/*
+ * Iterate over an inclusive ranges within sparsebit @s. In each iteration,
+ * @range_begin and @range_end will take the beginning and end of the set
+ * range, which are of type sparsebit_idx_t.
+ *
+ * For example, if the range [3, 7] (inclusive) is set, within the
+ * iteration,@range_begin will take the value 3 and @range_end will take
+ * the value 7.
+ *
+ * Ensure that there is at least one bit set before using this macro with
+ * sparsebit_any_set(), because sparsebit_first_set() will abort if none
+ * are set.
+ */
+#define sparsebit_for_each_set_range(s, range_begin, range_end)         \
+	for (range_begin = sparsebit_first_set(s),                      \
+	     range_end = sparsebit_next_clear(s, range_begin) - 1;	\
+	     range_begin && range_end;                                  \
+	     range_begin = sparsebit_next_set(s, range_end),            \
+	     range_end = sparsebit_next_clear(s, range_begin) - 1)
 
 #ifdef __cplusplus
 }

tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_UTIL_ARCH_H
+#define SELFTEST_KVM_UTIL_ARCH_H
+
+#include <stdbool.h>
+#include <stdint.h>
+
+struct kvm_vm_arch {
+	uint64_t c_bit;
+	uint64_t s_bit;
+	int sev_fd;
+	bool is_pt_protected;
+};
+
+static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch)
+{
+	return arch->c_bit || arch->s_bit;
+}
+
+#define vm_arch_has_protected_memory(vm) \
+	__vm_arch_has_protected_memory(&(vm)->arch)
+
+#endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/x86_64/processor.h

@@ -23,6 +23,12 @@
 extern bool host_cpu_is_intel;
 extern bool host_cpu_is_amd;
 
+enum vm_guest_x86_subtype {
+	VM_SUBTYPE_NONE = 0,
+	VM_SUBTYPE_SEV,
+	VM_SUBTYPE_SEV_ES,
+};
+
 #define NMI_VECTOR		0x02
 
 #define X86_EFLAGS_FIXED	 (1u << 1)
@@ -273,6 +279,7 @@ struct kvm_x86_cpu_property {
 #define X86_PROPERTY_MAX_EXT_LEAF		KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31)
 #define X86_PROPERTY_MAX_PHY_ADDR		KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7)
 #define X86_PROPERTY_MAX_VIRT_ADDR		KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15)
+#define X86_PROPERTY_SEV_C_BIT			KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 0, 5)
 #define X86_PROPERTY_PHYS_ADDR_REDUCTION	KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11)
 
 #define X86_PROPERTY_MAX_CENTAUR_LEAF		KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31)
@@ -1059,6 +1066,7 @@ do {											\
 } while (0)
 
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
+void kvm_init_vm_address_properties(struct kvm_vm *vm);
 bool vm_is_unrestricted_guest(struct kvm_vm *vm);
 
 struct ex_regs {

tools/testing/selftests/kvm/include/x86_64/sev.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Helpers used for SEV guests
+ *
+ */
+#ifndef SELFTEST_KVM_SEV_H
+#define SELFTEST_KVM_SEV_H
+
+#include <stdint.h>
+#include <stdbool.h>
+
+#include "linux/psp-sev.h"
+
+#include "kvm_util.h"
+#include "svm_util.h"
+#include "processor.h"
+
+enum sev_guest_state {
+	SEV_GUEST_STATE_UNINITIALIZED = 0,
+	SEV_GUEST_STATE_LAUNCH_UPDATE,
+	SEV_GUEST_STATE_LAUNCH_SECRET,
+	SEV_GUEST_STATE_RUNNING,
+};
+
+#define SEV_POLICY_NO_DBG	(1UL << 0)
+#define SEV_POLICY_ES		(1UL << 2)
+
+#define GHCB_MSR_TERM_REQ	0x100
+
+void sev_vm_launch(struct kvm_vm *vm, uint32_t policy);
+void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement);
+void sev_vm_launch_finish(struct kvm_vm *vm);
+
+struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code,
+					   struct kvm_vcpu **cpu);
+
+kvm_static_assert(SEV_RET_SUCCESS == 0);
+
+/*
+ * The KVM_MEMORY_ENCRYPT_OP uAPI is utter garbage and takes an "unsigned long"
+ * instead of a proper struct.  The size of the parameter is embedded in the
+ * ioctl number, i.e. is ABI and thus immutable.  Hack around the mess by
+ * creating an overlay to pass in an "unsigned long" without a cast (casting
+ * will make the compiler unhappy due to dereferencing an aliased pointer).
+ */
+#define __vm_sev_ioctl(vm, cmd, arg)					\
+({									\
+	int r;								\
+									\
+	union {								\
+		struct kvm_sev_cmd c;					\
+		unsigned long raw;					\
+	} sev_cmd = { .c = {						\
+		.id = (cmd),						\
+		.data = (uint64_t)(arg),				\
+		.sev_fd = (vm)->arch.sev_fd,				\
+	} };								\
+									\
+	r = __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_OP, &sev_cmd.raw);	\
+	r ?: sev_cmd.c.error;						\
+})
+
+#define vm_sev_ioctl(vm, cmd, arg)					\
+({									\
+	int ret = __vm_sev_ioctl(vm, cmd, arg);				\
+									\
+	__TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd,	ret, vm);		\
+})
+
+static inline void sev_vm_init(struct kvm_vm *vm)
+{
+	vm->arch.sev_fd = open_sev_dev_path_or_exit();
+
+	vm_sev_ioctl(vm, KVM_SEV_INIT, NULL);
+}
+
+
+static inline void sev_es_vm_init(struct kvm_vm *vm)
+{
+	vm->arch.sev_fd = open_sev_dev_path_or_exit();
+
+	vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL);
+}
+
+static inline void sev_register_encrypted_memory(struct kvm_vm *vm,
+						 struct userspace_mem_region *region)
+{
+	struct kvm_enc_region range = {
+		.addr = region->region.userspace_addr,
+		.size = region->region.memory_size,
+	};
+
+	vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range);
+}
+
+static inline void sev_launch_update_data(struct kvm_vm *vm, vm_paddr_t gpa,
+					  uint64_t size)
+{
+	struct kvm_sev_launch_update_data update_data = {
+		.uaddr = (unsigned long)addr_gpa2hva(vm, gpa),
+		.len = size,
+	};
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_DATA, &update_data);
+}
+
+#endif /* SELFTEST_KVM_SEV_H */

tools/testing/selftests/kvm/lib/aarch64/processor.c

@@ -365,8 +365,13 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 		indent, "", pstate, pc);
 }
 
-struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  struct kvm_vcpu_init *init, void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+}
+
+static struct kvm_vcpu *__aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+					   struct kvm_vcpu_init *init)
 {
 	size_t stack_size;
 	uint64_t stack_vaddr;
@@ -381,15 +386,22 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	aarch64_vcpu_setup(vcpu, init);
 
 	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
-	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+	return vcpu;
+}
+
+struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+				  struct kvm_vcpu_init *init, void *guest_code)
+{
+	struct kvm_vcpu *vcpu = __aarch64_vcpu_add(vm, vcpu_id, init);
+
+	vcpu_arch_set_entry_point(vcpu, guest_code);
 
 	return vcpu;
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
-	return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code);
+	return __aarch64_vcpu_add(vm, vcpu_id, NULL);
 }
 
 void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -226,6 +226,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 
 	vm->mode = shape.mode;
 	vm->type = shape.type;
+	vm->subtype = shape.subtype;
 
 	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
 	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
@@ -266,6 +267,7 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 	case VM_MODE_PXXV48_4K:
 #ifdef __x86_64__
 		kvm_get_cpu_address_width(&vm->pa_bits, &vm->va_bits);
+		kvm_init_vm_address_properties(vm);
 		/*
 		 * Ignore KVM support for 5-level paging (vm->va_bits == 57),
 		 * it doesn't take effect unless a CR4.LA57 is set, which it
@@ -666,6 +668,7 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	vm_ioctl(vm, KVM_SET_USER_MEMORY_REGION2, &region->region);
 
 	sparsebit_free(&region->unused_phy_pages);
+	sparsebit_free(&region->protected_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
 	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
 	if (region->fd >= 0) {
@@ -1047,6 +1050,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	}
 
 	region->unused_phy_pages = sparsebit_alloc();
+	if (vm_arch_has_protected_memory(vm))
+		region->protected_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
 	region->region.slot = slot;
@@ -1377,15 +1382,17 @@ vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
 	return pgidx_start * vm->page_size;
 }
 
-vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
-			    enum kvm_mem_region_type type)
+static vm_vaddr_t ____vm_vaddr_alloc(struct kvm_vm *vm, size_t sz,
+				     vm_vaddr_t vaddr_min,
+				     enum kvm_mem_region_type type,
+				     bool protected)
 {
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm);
-	vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
-					      KVM_UTIL_MIN_PFN * vm->page_size,
-					      vm->memslots[type]);
+	vm_paddr_t paddr = __vm_phy_pages_alloc(vm, pages,
+						KVM_UTIL_MIN_PFN * vm->page_size,
+						vm->memslots[type], protected);
 
 	/*
 	 * Find an unused range of virtual page addresses of at least
@@ -1405,6 +1412,20 @@ vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
 	return vaddr_start;
 }
 
+vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+			    enum kvm_mem_region_type type)
+{
+	return ____vm_vaddr_alloc(vm, sz, vaddr_min, type,
+				  vm_arch_has_protected_memory(vm));
+}
+
+vm_vaddr_t vm_vaddr_alloc_shared(struct kvm_vm *vm, size_t sz,
+				 vm_vaddr_t vaddr_min,
+				 enum kvm_mem_region_type type)
+{
+	return ____vm_vaddr_alloc(vm, sz, vaddr_min, type, false);
+}
+
 /*
  * VM Virtual Address Allocate
  *
@@ -1527,6 +1548,8 @@ void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
 {
 	struct userspace_mem_region *region;
 
+	gpa = vm_untag_gpa(vm, gpa);
+
 	region = userspace_mem_region_find(vm, gpa, gpa);
 	if (!region) {
 		TEST_FAIL("No vm physical memory at 0x%lx", gpa);
@@ -1873,6 +1896,10 @@ void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 			region->host_mem);
 		fprintf(stream, "%*sunused_phy_pages: ", indent + 2, "");
 		sparsebit_dump(stream, region->unused_phy_pages, 0);
+		if (region->protected_phy_pages) {
+			fprintf(stream, "%*sprotected_phy_pages: ", indent + 2, "");
+			sparsebit_dump(stream, region->protected_phy_pages, 0);
+		}
 	}
 	fprintf(stream, "%*sMapped Virtual Pages:\n", indent, "");
 	sparsebit_dump(stream, vm->vpages_mapped, indent + 2);
@@ -1974,6 +2001,7 @@ const char *exit_reason_str(unsigned int exit_reason)
  *   num - number of pages
  *   paddr_min - Physical address minimum
  *   memslot - Memory region to allocate page from
+ *   protected - True if the pages will be used as protected/private memory
  *
  * Output Args: None
  *
@@ -1985,8 +2013,9 @@ const char *exit_reason_str(unsigned int exit_reason)
  * and their base address is returned. A TEST_ASSERT failure occurs if
  * not enough pages are available at or above paddr_min.
  */
-vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
-			      vm_paddr_t paddr_min, uint32_t memslot)
+vm_paddr_t __vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
+				vm_paddr_t paddr_min, uint32_t memslot,
+				bool protected)
 {
 	struct userspace_mem_region *region;
 	sparsebit_idx_t pg, base;
@@ -1999,8 +2028,10 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
 		paddr_min, vm->page_size);
 
 	region = memslot2region(vm, memslot);
-	base = pg = paddr_min >> vm->page_shift;
+	TEST_ASSERT(!protected || region->protected_phy_pages,
+		    "Region doesn't support protected memory");
 
+	base = pg = paddr_min >> vm->page_shift;
 	do {
 		for (; pg < base + num; ++pg) {
 			if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
@@ -2019,8 +2050,11 @@ vm_paddr_t vm_phy_pages_alloc(struct kvm_vm *vm, size_t num,
 		abort();
 	}
 
-	for (pg = base; pg < base + num; ++pg)
+	for (pg = base; pg < base + num; ++pg) {
 		sparsebit_clear(region->unused_phy_pages, pg);
+		if (protected)
+			sparsebit_set(region->protected_phy_pages, pg);
+	}
 
 	return base * vm->page_size;
 }
@@ -2224,3 +2258,18 @@ void __attribute((constructor)) kvm_selftest_init(void)
 
 	kvm_selftest_arch_init();
 }
+
+bool vm_is_gpa_protected(struct kvm_vm *vm, vm_paddr_t paddr)
+{
+	sparsebit_idx_t pg = 0;
+	struct userspace_mem_region *region;
+
+	if (!vm_arch_has_protected_memory(vm))
+		return false;
+
+	region = userspace_mem_region_find(vm, paddr, paddr);
+	TEST_ASSERT(region, "No vm physical memory at 0x%lx", paddr);
+
+	pg = paddr >> vm->page_shift;
+	return sparsebit_is_set(region->protected_phy_pages, pg);
+}

tools/testing/selftests/kvm/lib/riscv/processor.c

@@ -289,8 +289,12 @@ static void __aligned(16) guest_unexp_trap(void)
 		  0, 0, 0, 0, 0, 0);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	int r;
 	size_t stack_size;
@@ -324,7 +328,6 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 
 	/* Setup stack pointer and program counter of guest */
 	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.sp), stack_vaddr + stack_size);
-	vcpu_set_reg(vcpu, RISCV_CORE_REG(regs.pc), (unsigned long)guest_code);
 
 	/* Setup sscratch for guest_get_vcpuid() */
 	vcpu_set_reg(vcpu, RISCV_GENERAL_CSR_REG(sscratch), vcpu_id);

tools/testing/selftests/kvm/lib/s390x/processor.c

@@ -155,15 +155,18 @@ void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
 	virt_dump_region(stream, vm, indent, vm->pgd);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	vcpu->run->psw_addr = (uintptr_t)guest_code;
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	size_t stack_size =  DEFAULT_STACK_PGS * getpagesize();
 	uint64_t stack_vaddr;
 	struct kvm_regs regs;
 	struct kvm_sregs sregs;
 	struct kvm_vcpu *vcpu;
-	struct kvm_run *run;
 
 	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
 		    vm->page_size);
@@ -184,9 +187,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	sregs.crs[1] = vm->pgd | 0xf;		/* Primary region table */
 	vcpu_sregs_set(vcpu, &sregs);
 
-	run = vcpu->run;
-	run->psw_mask = 0x0400000180000000ULL;  /* DAT enabled + 64 bit mode */
-	run->psw_addr = (uintptr_t)guest_code;
+	vcpu->run->psw_mask = 0x0400000180000000ULL;  /* DAT enabled + 64 bit mode */
 
 	return vcpu;
 }

tools/testing/selftests/kvm/lib/sparsebit.c

@@ -202,7 +202,7 @@ static sparsebit_num_t node_num_set(struct node *nodep)
 /* Returns a pointer to the node that describes the
  * lowest bit index.
  */
-static struct node *node_first(struct sparsebit *s)
+static struct node *node_first(const struct sparsebit *s)
 {
 	struct node *nodep;
 
@@ -216,7 +216,7 @@ static struct node *node_first(struct sparsebit *s)
  * lowest bit index > the index of the node pointed to by np.
  * Returns NULL if no node with a higher index exists.
  */
-static struct node *node_next(struct sparsebit *s, struct node *np)
+static struct node *node_next(const struct sparsebit *s, struct node *np)
 {
 	struct node *nodep = np;
 
@@ -244,7 +244,7 @@ static struct node *node_next(struct sparsebit *s, struct node *np)
  * highest index < the index of the node pointed to by np.
  * Returns NULL if no node with a lower index exists.
  */
-static struct node *node_prev(struct sparsebit *s, struct node *np)
+static struct node *node_prev(const struct sparsebit *s, struct node *np)
 {
 	struct node *nodep = np;
 
@@ -273,7 +273,7 @@ static struct node *node_prev(struct sparsebit *s, struct node *np)
  * subtree and duplicates the bit settings to the newly allocated nodes.
  * Returns the newly allocated copy of subtree.
  */
-static struct node *node_copy_subtree(struct node *subtree)
+static struct node *node_copy_subtree(const struct node *subtree)
 {
 	struct node *root;
 
@@ -307,7 +307,7 @@ static struct node *node_copy_subtree(struct node *subtree)
  * index is within the bits described by the mask bits or the number of
  * contiguous bits set after the mask.  Returns NULL if there is no such node.
  */
-static struct node *node_find(struct sparsebit *s, sparsebit_idx_t idx)
+static struct node *node_find(const struct sparsebit *s, sparsebit_idx_t idx)
 {
 	struct node *nodep;
 
@@ -393,7 +393,7 @@ static struct node *node_add(struct sparsebit *s, sparsebit_idx_t idx)
 }
 
 /* Returns whether all the bits in the sparsebit array are set.  */
-bool sparsebit_all_set(struct sparsebit *s)
+bool sparsebit_all_set(const struct sparsebit *s)
 {
 	/*
 	 * If any nodes there must be at least one bit set.  Only case
@@ -775,7 +775,7 @@ static void node_reduce(struct sparsebit *s, struct node *nodep)
 /* Returns whether the bit at the index given by idx, within the
  * sparsebit array is set or not.
  */
-bool sparsebit_is_set(struct sparsebit *s, sparsebit_idx_t idx)
+bool sparsebit_is_set(const struct sparsebit *s, sparsebit_idx_t idx)
 {
 	struct node *nodep;
 
@@ -921,7 +921,7 @@ static inline sparsebit_idx_t node_first_clear(struct node *nodep, int start)
  * used by test cases after they detect an unexpected condition, as a means
  * to capture diagnostic information.
  */
-static void sparsebit_dump_internal(FILE *stream, struct sparsebit *s,
+static void sparsebit_dump_internal(FILE *stream, const struct sparsebit *s,
 	unsigned int indent)
 {
 	/* Dump the contents of s */
@@ -969,7 +969,7 @@ void sparsebit_free(struct sparsebit **sbitp)
  * sparsebit_alloc().  It can though already have bits set, which
  * if different from src will be cleared.
  */
-void sparsebit_copy(struct sparsebit *d, struct sparsebit *s)
+void sparsebit_copy(struct sparsebit *d, const struct sparsebit *s)
 {
 	/* First clear any bits already set in the destination */
 	sparsebit_clear_all(d);
@@ -981,7 +981,7 @@ void sparsebit_copy(struct sparsebit *d, struct sparsebit *s)
 }
 
 /* Returns whether num consecutive bits starting at idx are all set.  */
-bool sparsebit_is_set_num(struct sparsebit *s,
+bool sparsebit_is_set_num(const struct sparsebit *s,
 	sparsebit_idx_t idx, sparsebit_num_t num)
 {
 	sparsebit_idx_t next_cleared;
@@ -1005,14 +1005,14 @@ bool sparsebit_is_set_num(struct sparsebit *s,
 }
 
 /* Returns whether the bit at the index given by idx.  */
-bool sparsebit_is_clear(struct sparsebit *s,
+bool sparsebit_is_clear(const struct sparsebit *s,
 	sparsebit_idx_t idx)
 {
 	return !sparsebit_is_set(s, idx);
 }
 
 /* Returns whether num consecutive bits starting at idx are all cleared.  */
-bool sparsebit_is_clear_num(struct sparsebit *s,
+bool sparsebit_is_clear_num(const struct sparsebit *s,
 	sparsebit_idx_t idx, sparsebit_num_t num)
 {
 	sparsebit_idx_t next_set;
@@ -1041,13 +1041,13 @@ bool sparsebit_is_clear_num(struct sparsebit *s,
  * value.  Use sparsebit_any_set(), instead of sparsebit_num_set() > 0,
  * to determine if the sparsebit array has any bits set.
  */
-sparsebit_num_t sparsebit_num_set(struct sparsebit *s)
+sparsebit_num_t sparsebit_num_set(const struct sparsebit *s)
 {
 	return s->num_set;
 }
 
 /* Returns whether any bit is set in the sparsebit array.  */
-bool sparsebit_any_set(struct sparsebit *s)
+bool sparsebit_any_set(const struct sparsebit *s)
 {
 	/*
 	 * Nodes only describe set bits.  If any nodes then there
@@ -1070,20 +1070,20 @@ bool sparsebit_any_set(struct sparsebit *s)
 }
 
 /* Returns whether all the bits in the sparsebit array are cleared.  */
-bool sparsebit_all_clear(struct sparsebit *s)
+bool sparsebit_all_clear(const struct sparsebit *s)
 {
 	return !sparsebit_any_set(s);
 }
 
 /* Returns whether all the bits in the sparsebit array are set.  */
-bool sparsebit_any_clear(struct sparsebit *s)
+bool sparsebit_any_clear(const struct sparsebit *s)
 {
 	return !sparsebit_all_set(s);
 }
 
 /* Returns the index of the first set bit.  Abort if no bits are set.
  */
-sparsebit_idx_t sparsebit_first_set(struct sparsebit *s)
+sparsebit_idx_t sparsebit_first_set(const struct sparsebit *s)
 {
 	struct node *nodep;
 
@@ -1097,7 +1097,7 @@ sparsebit_idx_t sparsebit_first_set(struct sparsebit *s)
 /* Returns the index of the first cleared bit.  Abort if
  * no bits are cleared.
  */
-sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s)
+sparsebit_idx_t sparsebit_first_clear(const struct sparsebit *s)
 {
 	struct node *nodep1, *nodep2;
 
@@ -1151,7 +1151,7 @@ sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s)
 /* Returns index of next bit set within s after the index given by prev.
  * Returns 0 if there are no bits after prev that are set.
  */
-sparsebit_idx_t sparsebit_next_set(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_set(const struct sparsebit *s,
 	sparsebit_idx_t prev)
 {
 	sparsebit_idx_t lowest_possible = prev + 1;
@@ -1244,7 +1244,7 @@ sparsebit_idx_t sparsebit_next_set(struct sparsebit *s,
 /* Returns index of next bit cleared within s after the index given by prev.
  * Returns 0 if there are no bits after prev that are cleared.
  */
-sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_clear(const struct sparsebit *s,
 	sparsebit_idx_t prev)
 {
 	sparsebit_idx_t lowest_possible = prev + 1;
@@ -1300,7 +1300,7 @@ sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s,
  * and returns the index of the first sequence of num consecutively set
  * bits.  Returns a value of 0 of no such sequence exists.
  */
-sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_set_num(const struct sparsebit *s,
 	sparsebit_idx_t start, sparsebit_num_t num)
 {
 	sparsebit_idx_t idx;
@@ -1335,7 +1335,7 @@ sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s,
  * and returns the index of the first sequence of num consecutively cleared
  * bits.  Returns a value of 0 of no such sequence exists.
  */
-sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *s,
+sparsebit_idx_t sparsebit_next_clear_num(const struct sparsebit *s,
 	sparsebit_idx_t start, sparsebit_num_t num)
 {
 	sparsebit_idx_t idx;
@@ -1583,7 +1583,7 @@ static size_t display_range(FILE *stream, sparsebit_idx_t low,
  * contiguous bits.  This is done because '-' is used to specify command-line
  * options, and sometimes ranges are specified as command-line arguments.
  */
-void sparsebit_dump(FILE *stream, struct sparsebit *s,
+void sparsebit_dump(FILE *stream, const struct sparsebit *s,
 	unsigned int indent)
 {
 	size_t current_line_len = 0;
@@ -1681,7 +1681,7 @@ void sparsebit_dump(FILE *stream, struct sparsebit *s,
  * s.  On error, diagnostic information is printed to stderr and
  * abort is called.
  */
-void sparsebit_validate_internal(struct sparsebit *s)
+void sparsebit_validate_internal(const struct sparsebit *s)
 {
 	bool error_detected = false;
 	struct node *nodep, *prev = NULL;

tools/testing/selftests/kvm/lib/ucall_common.c

@@ -29,7 +29,8 @@ void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 	vm_vaddr_t vaddr;
 	int i;
 
-	vaddr = __vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR, MEM_REGION_DATA);
+	vaddr = vm_vaddr_alloc_shared(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR,
+				      MEM_REGION_DATA);
 	hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr);
 	memset(hdr, 0, sizeof(*hdr));
 

tools/testing/selftests/kvm/lib/x86_64/processor.c

@@ -9,6 +9,7 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "sev.h"
 
 #ifndef NUM_INTERRUPTS
 #define NUM_INTERRUPTS 256
@@ -157,6 +158,8 @@ static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
 {
 	uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level);
 
+	paddr = vm_untag_gpa(vm, paddr);
+
 	if (!(*pte & PTE_PRESENT_MASK)) {
 		*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
 		if (current_level == target_level)
@@ -200,6 +203,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 		    "Physical address beyond maximum supported,\n"
 		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
+	TEST_ASSERT(vm_untag_gpa(vm, paddr) == paddr,
+		    "Unexpected bits in paddr: %lx", paddr);
 
 	/*
 	 * Allocate upper level page tables, if not already present.  Return
@@ -222,6 +227,15 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 	TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
 		    "PTE already present for 4k page at vaddr: 0x%lx", vaddr);
 	*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
+
+	/*
+	 * Neither SEV nor TDX supports shared page tables, so only the final
+	 * leaf PTE needs manually set the C/S-bit.
+	 */
+	if (vm_is_gpa_protected(vm, paddr))
+		*pte |= vm->arch.c_bit;
+	else
+		*pte |= vm->arch.s_bit;
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -265,6 +279,9 @@ uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
 {
 	uint64_t *pml4e, *pdpe, *pde;
 
+	TEST_ASSERT(!vm->arch.is_pt_protected,
+		    "Walking page tables of protected guests is impossible");
+
 	TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
 		    "Invalid PG_LEVEL_* '%d'", *level);
 
@@ -496,7 +513,7 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	 * No need for a hugepage mask on the PTE, x86-64 requires the "unused"
 	 * address bits to be zero.
 	 */
-	return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level));
+	return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level));
 }
 
 static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
@@ -560,10 +577,23 @@ void kvm_arch_vm_post_create(struct kvm_vm *vm)
 	vm_create_irqchip(vm);
 	sync_global_to_guest(vm, host_cpu_is_intel);
 	sync_global_to_guest(vm, host_cpu_is_amd);
+
+	if (vm->subtype == VM_SUBTYPE_SEV)
+		sev_vm_init(vm);
+	else if (vm->subtype == VM_SUBTYPE_SEV_ES)
+		sev_es_vm_init(vm);
+}
+
+void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
+{
+	struct kvm_regs regs;
+
+	vcpu_regs_get(vcpu, &regs);
+	regs.rip = (unsigned long) guest_code;
+	vcpu_regs_set(vcpu, &regs);
 }
 
-struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
-				  void *guest_code)
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 {
 	struct kvm_mp_state mp_state;
 	struct kvm_regs regs;
@@ -597,7 +627,6 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vcpu_regs_get(vcpu, &regs);
 	regs.rflags = regs.rflags | 0x2;
 	regs.rsp = stack_vaddr;
-	regs.rip = (unsigned long) guest_code;
 	vcpu_regs_set(vcpu, &regs);
 
 	/* Setup the MP state */
@@ -1041,6 +1070,14 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 	}
 }
 
+void kvm_init_vm_address_properties(struct kvm_vm *vm)
+{
+	if (vm->subtype == VM_SUBTYPE_SEV || vm->subtype == VM_SUBTYPE_SEV_ES) {
+		vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT));
+		vm->gpa_tag_mask = vm->arch.c_bit;
+	}
+}
+
 static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
 			  int dpl, unsigned short selector)
 {

tools/testing/selftests/kvm/lib/x86_64/sev.c

+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <stdint.h>
+#include <stdbool.h>
+
+#include "sev.h"
+
+/*
+ * sparsebit_next_clear() can return 0 if [x, 2**64-1] are all set, and the
+ * -1 would then cause an underflow back to 2**64 - 1. This is expected and
+ * correct.
+ *
+ * If the last range in the sparsebit is [x, y] and we try to iterate,
+ * sparsebit_next_set() will return 0, and sparsebit_next_clear() will try
+ * and find the first range, but that's correct because the condition
+ * expression would cause us to quit the loop.
+ */
+static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *region)
+{
+	const struct sparsebit *protected_phy_pages = region->protected_phy_pages;
+	const vm_paddr_t gpa_base = region->region.guest_phys_addr;
+	const sparsebit_idx_t lowest_page_in_region = gpa_base >> vm->page_shift;
+	sparsebit_idx_t i, j;
+
+	if (!sparsebit_any_set(protected_phy_pages))
+		return;
+
+	sev_register_encrypted_memory(vm, region);
+
+	sparsebit_for_each_set_range(protected_phy_pages, i, j) {
+		const uint64_t size = (j - i + 1) * vm->page_size;
+		const uint64_t offset = (i - lowest_page_in_region) * vm->page_size;
+
+		sev_launch_update_data(vm, gpa_base + offset, size);
+	}
+}
+
+void sev_vm_launch(struct kvm_vm *vm, uint32_t policy)
+{
+	struct kvm_sev_launch_start launch_start = {
+		.policy = policy,
+	};
+	struct userspace_mem_region *region;
+	struct kvm_sev_guest_status status;
+	int ctr;
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_START, &launch_start);
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+
+	TEST_ASSERT_EQ(status.policy, policy);
+	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_LAUNCH_UPDATE);
+
+	hash_for_each(vm->regions.slot_hash, ctr, region, slot_node)
+		encrypt_region(vm, region);
+
+	if (policy & SEV_POLICY_ES)
+		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+
+	vm->arch.is_pt_protected = true;
+}
+
+void sev_vm_launch_measure(struct kvm_vm *vm, uint8_t *measurement)
+{
+	struct kvm_sev_launch_measure launch_measure;
+	struct kvm_sev_guest_status guest_status;
+
+	launch_measure.len = 256;
+	launch_measure.uaddr = (__u64)measurement;
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_MEASURE, &launch_measure);
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &guest_status);
+	TEST_ASSERT_EQ(guest_status.state, SEV_GUEST_STATE_LAUNCH_SECRET);
+}
+
+void sev_vm_launch_finish(struct kvm_vm *vm)
+{
+	struct kvm_sev_guest_status status;
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+	TEST_ASSERT(status.state == SEV_GUEST_STATE_LAUNCH_UPDATE ||
+		    status.state == SEV_GUEST_STATE_LAUNCH_SECRET,
+		    "Unexpected guest state: %d", status.state);
+
+	vm_sev_ioctl(vm, KVM_SEV_LAUNCH_FINISH, NULL);
+
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
+	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING);
+}
+
+struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code,
+					   struct kvm_vcpu **cpu)
+{
+	struct vm_shape shape = {
+		.type = VM_TYPE_DEFAULT,
+		.mode = VM_MODE_DEFAULT,
+		.subtype = policy & SEV_POLICY_ES ? VM_SUBTYPE_SEV_ES :
+						    VM_SUBTYPE_SEV,
+	};
+	struct kvm_vm *vm;
+	struct kvm_vcpu *cpus[1];
+	uint8_t measurement[512];
+
+	vm = __vm_create_with_vcpus(shape, 1, 0, guest_code, cpus);
+	*cpu = cpus[0];
+
+	sev_vm_launch(vm, policy);
+
+	/* TODO: Validate the measurement is as expected. */
+	sev_vm_launch_measure(vm, measurement);
+
+	sev_vm_launch_finish(vm);
+
+	return vm;
+}

tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c

@@ -9,6 +9,7 @@
 #include <linux/stringify.h>
 #include <stdint.h>
 
+#include "kvm_test_harness.h"
 #include "apic.h"
 #include "test_util.h"
 #include "kvm_util.h"
@@ -83,6 +84,8 @@ static void guest_main(void)
 	GUEST_DONE();
 }
 
+KVM_ONE_VCPU_TEST_SUITE(fix_hypercall);
+
 static void enter_guest(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
@@ -103,14 +106,11 @@ static void enter_guest(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void test_fix_hypercall(bool disable_quirk)
+static void test_fix_hypercall(struct kvm_vcpu *vcpu, bool disable_quirk)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	vm = vm_create_with_one_vcpu(&vcpu, guest_main);
+	struct kvm_vm *vm = vcpu->vm;
 
-	vm_init_descriptor_tables(vcpu->vm);
+	vm_init_descriptor_tables(vm);
 	vcpu_init_descriptor_tables(vcpu);
 	vm_install_exception_handler(vcpu->vm, UD_VECTOR, guest_ud_handler);
 
@@ -126,10 +126,19 @@ static void test_fix_hypercall(bool disable_quirk)
 	enter_guest(vcpu);
 }
 
-int main(void)
+KVM_ONE_VCPU_TEST(fix_hypercall, enable_quirk, guest_main)
+{
+	test_fix_hypercall(vcpu, false);
+}
+
+KVM_ONE_VCPU_TEST(fix_hypercall, disable_quirk, guest_main)
+{
+	test_fix_hypercall(vcpu, true);
+}
+
+int main(int argc, char *argv[])
 {
 	TEST_REQUIRE(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_FIX_HYPERCALL_INSN);
 
-	test_fix_hypercall(false);
-	test_fix_hypercall(true);
+	return test_harness_run(argc, argv);
 }

tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c

@@ -434,6 +434,8 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, uint32_t
 
 	r = fallocate(memfd, FALLOC_FL_KEEP_SIZE, 0, memfd_size);
 	TEST_ASSERT(!r, __KVM_SYSCALL_ERROR("fallocate()", r));
+
+	close(memfd);
 }
 
 static void usage(const char *cmd)

tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c

@@ -10,11 +10,9 @@
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
-#include "svm_util.h"
+#include "sev.h"
 #include "kselftest.h"
 
-#define SEV_POLICY_ES 0b100
-
 #define NR_MIGRATE_TEST_VCPUS 4
 #define NR_MIGRATE_TEST_VMS 3
 #define NR_LOCK_TESTING_THREADS 3
@@ -22,46 +20,24 @@
 
 bool have_sev_es;
 
-static int __sev_ioctl(int vm_fd, int cmd_id, void *data, __u32 *fw_error)
-{
-	struct kvm_sev_cmd cmd = {
-		.id = cmd_id,
-		.data = (uint64_t)data,
-		.sev_fd = open_sev_dev_path_or_exit(),
-	};
-	int ret;
-
-	ret = ioctl(vm_fd, KVM_MEMORY_ENCRYPT_OP, &cmd);
-	*fw_error = cmd.error;
-	return ret;
-}
-
-static void sev_ioctl(int vm_fd, int cmd_id, void *data)
-{
-	int ret;
-	__u32 fw_error;
-
-	ret = __sev_ioctl(vm_fd, cmd_id, data, &fw_error);
-	TEST_ASSERT(ret == 0 && fw_error == SEV_RET_SUCCESS,
-		    "%d failed: return code: %d, errno: %d, fw error: %d",
-		    cmd_id, ret, errno, fw_error);
-}
-
 static struct kvm_vm *sev_vm_create(bool es)
 {
 	struct kvm_vm *vm;
-	struct kvm_sev_launch_start start = { 0 };
 	int i;
 
 	vm = vm_create_barebones();
-	sev_ioctl(vm->fd, es ? KVM_SEV_ES_INIT : KVM_SEV_INIT, NULL);
+	if (!es)
+		sev_vm_init(vm);
+	else
+		sev_es_vm_init(vm);
+
 	for (i = 0; i < NR_MIGRATE_TEST_VCPUS; ++i)
 		__vm_vcpu_add(vm, i);
+
+	sev_vm_launch(vm, es ? SEV_POLICY_ES : 0);
+
 	if (es)
-		start.policy |= SEV_POLICY_ES;
-	sev_ioctl(vm->fd, KVM_SEV_LAUNCH_START, &start);
-	if (es)
-		sev_ioctl(vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
 	return vm;
 }
 
@@ -181,7 +157,7 @@ static void test_sev_migrate_parameters(void)
 	sev_vm = sev_vm_create(/* es= */ false);
 	sev_es_vm = sev_vm_create(/* es= */ true);
 	sev_es_vm_no_vmsa = vm_create_barebones();
-	sev_ioctl(sev_es_vm_no_vmsa->fd, KVM_SEV_ES_INIT, NULL);
+	sev_es_vm_init(sev_es_vm_no_vmsa);
 	__vm_vcpu_add(sev_es_vm_no_vmsa, 1);
 
 	ret = __sev_migrate_from(sev_vm, sev_es_vm);
@@ -230,13 +206,13 @@ static void sev_mirror_create(struct kvm_vm *dst, struct kvm_vm *src)
 	TEST_ASSERT(!ret, "Copying context failed, ret: %d, errno: %d", ret, errno);
 }
 
-static void verify_mirror_allowed_cmds(int vm_fd)
+static void verify_mirror_allowed_cmds(struct kvm_vm *vm)
 {
 	struct kvm_sev_guest_status status;
+	int cmd_id;
 
-	for (int cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
+	for (cmd_id = KVM_SEV_INIT; cmd_id < KVM_SEV_NR_MAX; ++cmd_id) {
 		int ret;
-		__u32 fw_error;
 
 		/*
 		 * These commands are allowed for mirror VMs, all others are
@@ -256,14 +232,14 @@ static void verify_mirror_allowed_cmds(int vm_fd)
 		 * These commands should be disallowed before the data
 		 * parameter is examined so NULL is OK here.
 		 */
-		ret = __sev_ioctl(vm_fd, cmd_id, NULL, &fw_error);
+		ret = __vm_sev_ioctl(vm, cmd_id, NULL);
 		TEST_ASSERT(
 			ret == -1 && errno == EINVAL,
 			"Should not be able call command: %d. ret: %d, errno: %d",
 			cmd_id, ret, errno);
 	}
 
-	sev_ioctl(vm_fd, KVM_SEV_GUEST_STATUS, &status);
+	vm_sev_ioctl(vm, KVM_SEV_GUEST_STATUS, &status);
 }
 
 static void test_sev_mirror(bool es)
@@ -281,9 +257,9 @@ static void test_sev_mirror(bool es)
 		__vm_vcpu_add(dst_vm, i);
 
 	if (es)
-		sev_ioctl(dst_vm->fd, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
+		vm_sev_ioctl(dst_vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
 
-	verify_mirror_allowed_cmds(dst_vm->fd);
+	verify_mirror_allowed_cmds(dst_vm);
 
 	kvm_vm_free(src_vm);
 	kvm_vm_free(dst_vm);

tools/testing/selftests/kvm/x86_64/sev_smoke_test.c

+// SPDX-License-Identifier: GPL-2.0-only
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+#include "linux/psp-sev.h"
+#include "sev.h"
+
+
+static void guest_sev_es_code(void)
+{
+	/* TODO: Check CPUID after GHCB-based hypercall support is added. */
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ES_ENABLED);
+
+	/*
+	 * TODO: Add GHCB and ucall support for SEV-ES guests.  For now, simply
+	 * force "termination" to signal "done" via the GHCB MSR protocol.
+	 */
+	wrmsr(MSR_AMD64_SEV_ES_GHCB, GHCB_MSR_TERM_REQ);
+	__asm__ __volatile__("rep; vmmcall");
+}
+
+static void guest_sev_code(void)
+{
+	GUEST_ASSERT(this_cpu_has(X86_FEATURE_SEV));
+	GUEST_ASSERT(rdmsr(MSR_AMD64_SEV) & MSR_AMD64_SEV_ENABLED);
+
+	GUEST_DONE();
+}
+
+static void test_sev(void *guest_code, uint64_t policy)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+	struct ucall uc;
+
+	vm = vm_sev_create_with_one_vcpu(policy, guest_code, &vcpu);
+
+	for (;;) {
+		vcpu_run(vcpu);
+
+		if (policy & SEV_POLICY_ES) {
+			TEST_ASSERT(vcpu->run->exit_reason == KVM_EXIT_SYSTEM_EVENT,
+				    "Wanted SYSTEM_EVENT, got %s",
+				    exit_reason_str(vcpu->run->exit_reason));
+			TEST_ASSERT_EQ(vcpu->run->system_event.type, KVM_SYSTEM_EVENT_SEV_TERM);
+			TEST_ASSERT_EQ(vcpu->run->system_event.ndata, 1);
+			TEST_ASSERT_EQ(vcpu->run->system_event.data[0], GHCB_MSR_TERM_REQ);
+			break;
+		}
+
+		switch (get_ucall(vcpu, &uc)) {
+		case UCALL_SYNC:
+			continue;
+		case UCALL_DONE:
+			return;
+		case UCALL_ABORT:
+			REPORT_GUEST_ASSERT(uc);
+		default:
+			TEST_FAIL("Unexpected exit: %s",
+				  exit_reason_str(vcpu->run->exit_reason));
+		}
+	}
+
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SEV));
+
+	test_sev(guest_sev_code, SEV_POLICY_NO_DBG);
+	test_sev(guest_sev_code, 0);
+
+	if (kvm_cpu_has(X86_FEATURE_SEV_ES)) {
+		test_sev(guest_sev_es_code, SEV_POLICY_ES | SEV_POLICY_NO_DBG);
+		test_sev(guest_sev_es_code, SEV_POLICY_ES);
+	}
+
+	return 0;
+}

tools/testing/selftests/kvm/x86_64/sync_regs_test.c

@@ -17,6 +17,7 @@
 #include <sys/ioctl.h>
 #include <pthread.h>
 
+#include "kvm_test_harness.h"
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
@@ -41,6 +42,8 @@ void guest_code(void)
 		     : "rax", "rbx");
 }
 
+KVM_ONE_VCPU_TEST_SUITE(sync_regs_test);
+
 static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
 {
 #define REG_COMPARE(reg) \
@@ -152,18 +155,15 @@ static noinline void *race_sregs_cr4(void *arg)
 	return NULL;
 }
 
-static void race_sync_regs(void *racer)
+static void race_sync_regs(struct kvm_vcpu *vcpu, void *racer)
 {
 	const time_t TIMEOUT = 2; /* seconds, roughly */
 	struct kvm_x86_state *state;
 	struct kvm_translation tr;
-	struct kvm_vcpu *vcpu;
 	struct kvm_run *run;
-	struct kvm_vm *vm;
 	pthread_t thread;
 	time_t t;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 	run = vcpu->run;
 
 	run->kvm_valid_regs = KVM_SYNC_X86_SREGS;
@@ -205,26 +205,12 @@ static void race_sync_regs(void *racer)
 	TEST_ASSERT_EQ(pthread_join(thread, NULL), 0);
 
 	kvm_x86_state_cleanup(state);
-	kvm_vm_free(vm);
 }
 
-int main(int argc, char *argv[])
+KVM_ONE_VCPU_TEST(sync_regs_test, read_invalid, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
-	struct kvm_regs regs;
-	struct kvm_sregs sregs;
-	struct kvm_vcpu_events events;
-	int rv, cap;
-
-	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
-	TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS);
-	TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD));
-
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
-	run = vcpu->run;
+	struct kvm_run *run = vcpu->run;
+	int rv;
 
 	/* Request reading invalid register set from VCPU. */
 	run->kvm_valid_regs = INVALID_SYNC_FIELD;
@@ -240,6 +226,12 @@ int main(int argc, char *argv[])
 		    "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_valid_regs = 0;
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, set_invalid, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	int rv;
 
 	/* Request setting invalid register set into VCPU. */
 	run->kvm_dirty_regs = INVALID_SYNC_FIELD;
@@ -255,11 +247,19 @@ int main(int argc, char *argv[])
 		    "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d",
 		    rv);
 	run->kvm_dirty_regs = 0;
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, req_and_verify_all_valid, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vcpu_events events;
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
 
 	/* Request and verify all valid register sets. */
 	/* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	vcpu_regs_get(vcpu, &regs);
@@ -270,6 +270,19 @@ int main(int argc, char *argv[])
 
 	vcpu_events_get(vcpu, &events);
 	compare_vcpu_events(&events, &run->s.regs.events);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, set_and_verify_various, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_vcpu_events events;
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Set and verify various register values. */
 	run->s.regs.regs.rbx = 0xBAD1DEA;
@@ -278,7 +291,7 @@ int main(int argc, char *argv[])
 
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xBAD1DEA + 1,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -295,6 +308,11 @@ int main(int argc, char *argv[])
 
 	vcpu_events_get(vcpu, &events);
 	compare_vcpu_events(&events, &run->s.regs.events);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_dirty_regs_bits, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
 
 	/* Clear kvm_dirty_regs bits, verify new s.regs values are
 	 * overwritten with existing guest values.
@@ -302,11 +320,22 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = TEST_SYNC_FIELDS;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.rbx = 0xDEADBEEF;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx != 0xDEADBEEF,
 		    "rbx sync regs value incorrect 0x%llx.",
 		    run->s.regs.regs.rbx);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_and_dirty_regs, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Clear kvm_valid_regs bits and kvm_dirty_bits.
 	 * Verify s.regs values are not overwritten with existing guest values
@@ -315,9 +344,10 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = 0;
 	run->s.regs.regs.rbx = 0xAAAA;
+	vcpu_regs_get(vcpu, &regs);
 	regs.rbx = 0xBAC0;
 	vcpu_regs_set(vcpu, &regs);
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xAAAA,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -326,6 +356,17 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(regs.rbx == 0xBAC0 + 1,
 		    "rbx guest value incorrect 0x%llx.",
 		    regs.rbx);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, clear_kvm_valid_regs_bits, guest_code)
+{
+	struct kvm_run *run = vcpu->run;
+	struct kvm_regs regs;
+
+	/* Run once to get register set */
+	run->kvm_valid_regs = TEST_SYNC_FIELDS;
+	vcpu_run(vcpu);
+	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 
 	/* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
 	 * with existing guest values but that guest values are overwritten
@@ -334,7 +375,7 @@ int main(int argc, char *argv[])
 	run->kvm_valid_regs = 0;
 	run->kvm_dirty_regs = TEST_SYNC_FIELDS;
 	run->s.regs.regs.rbx = 0xBBBB;
-	rv = _vcpu_run(vcpu);
+	vcpu_run(vcpu);
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_IO);
 	TEST_ASSERT(run->s.regs.regs.rbx == 0xBBBB,
 		    "rbx sync regs value incorrect 0x%llx.",
@@ -343,12 +384,30 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(regs.rbx == 0xBBBB + 1,
 		    "rbx guest value incorrect 0x%llx.",
 		    regs.rbx);
+}
 
-	kvm_vm_free(vm);
+KVM_ONE_VCPU_TEST(sync_regs_test, race_cr4, guest_code)
+{
+	race_sync_regs(vcpu, race_sregs_cr4);
+}
+
+KVM_ONE_VCPU_TEST(sync_regs_test, race_exc, guest_code)
+{
+	race_sync_regs(vcpu, race_events_exc);
+}
 
-	race_sync_regs(race_sregs_cr4);
-	race_sync_regs(race_events_exc);
-	race_sync_regs(race_events_inj_pen);
+KVM_ONE_VCPU_TEST(sync_regs_test, race_inj_pen, guest_code)
+{
+	race_sync_regs(vcpu, race_events_inj_pen);
+}
+
+int main(int argc, char *argv[])
+{
+	int cap;
+
+	cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
+	TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS);
+	TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD));
 
-	return 0;
+	return test_harness_run(argc, argv);
 }

tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c

@@ -8,6 +8,7 @@
 #define _GNU_SOURCE /* for program_invocation_short_name */
 #include <sys/ioctl.h>
 
+#include "kvm_test_harness.h"
 #include "test_util.h"
 #include "kvm_util.h"
 #include "vmx.h"
@@ -527,14 +528,13 @@ static void run_guest_then_process_ucall_done(struct kvm_vcpu *vcpu)
 	process_ucall_done(vcpu);
 }
 
-static void test_msr_filter_allow(void)
+KVM_ONE_VCPU_TEST_SUITE(user_msr);
+
+KVM_ONE_VCPU_TEST(user_msr, msr_filter_allow, guest_code_filter_allow)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
+	struct kvm_vm *vm = vcpu->vm;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_allow);
-
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
 	vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER);
@@ -585,8 +585,6 @@ static void test_msr_filter_allow(void)
 	} else {
 		printf("To run the instruction emulated tests set the module parameter 'kvm.force_emulation_prefix=1'\n");
 	}
-
-	kvm_vm_free(vm);
 }
 
 static int handle_ucall(struct kvm_vcpu *vcpu)
@@ -646,16 +644,12 @@ static void handle_wrmsr(struct kvm_run *run)
 	}
 }
 
-static void test_msr_filter_deny(void)
+KVM_ONE_VCPU_TEST(user_msr, msr_filter_deny, guest_code_filter_deny)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-	struct kvm_run *run;
+	struct kvm_vm *vm = vcpu->vm;
+	struct kvm_run *run = vcpu->run;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_filter_deny);
-	run = vcpu->run;
-
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
 	vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_INVAL |
@@ -689,18 +683,13 @@ static void test_msr_filter_deny(void)
 done:
 	TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space");
 	TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space");
-
-	kvm_vm_free(vm);
 }
 
-static void test_msr_permission_bitmap(void)
+KVM_ONE_VCPU_TEST(user_msr, msr_permission_bitmap, guest_code_permission_bitmap)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
+	struct kvm_vm *vm = vcpu->vm;
 	int rc;
 
-	vm = vm_create_with_one_vcpu(&vcpu, guest_code_permission_bitmap);
-
 	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
 	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
 	vm_enable_cap(vm, KVM_CAP_X86_USER_SPACE_MSR, KVM_MSR_EXIT_REASON_FILTER);
@@ -715,8 +704,6 @@ static void test_msr_permission_bitmap(void)
 	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter_gs);
 	run_guest_then_process_rdmsr(vcpu, MSR_GS_BASE);
 	run_guest_then_process_ucall_done(vcpu);
-
-	kvm_vm_free(vm);
 }
 
 #define test_user_exit_msr_ioctl(vm, cmd, arg, flag, valid_mask)	\
@@ -786,31 +773,18 @@ static void run_msr_filter_flag_test(struct kvm_vm *vm)
 }
 
 /* Test that attempts to write to the unused bits in a flag fails. */
-static void test_user_exit_msr_flags(void)
+KVM_ONE_VCPU_TEST(user_msr, user_exit_msr_flags, NULL)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
-
-	vm = vm_create_with_one_vcpu(&vcpu, NULL);
+	struct kvm_vm *vm = vcpu->vm;
 
 	/* Test flags for KVM_CAP_X86_USER_SPACE_MSR. */
 	run_user_space_msr_flag_test(vm);
 
 	/* Test flags and range flags for KVM_X86_SET_MSR_FILTER. */
 	run_msr_filter_flag_test(vm);
-
-	kvm_vm_free(vm);
 }
 
 int main(int argc, char *argv[])
 {
-	test_msr_filter_allow();
-
-	test_msr_filter_deny();
-
-	test_msr_permission_bitmap();
-
-	test_user_exit_msr_flags();
-
-	return 0;
+	return test_harness_run(argc, argv);
 }

tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c

@@ -15,10 +15,11 @@
 
 #include <linux/bitmap.h>
 
+#include "kvm_test_harness.h"
 #include "kvm_util.h"
 #include "vmx.h"
 
-union perf_capabilities {
+static union perf_capabilities {
 	struct {
 		u64	lbr_format:6;
 		u64	pebs_trap:1;
@@ -32,7 +33,7 @@ union perf_capabilities {
 		u64	anythread_deprecated:1;
 	};
 	u64	capabilities;
-};
+} host_cap;
 
 /*
  * The LBR format and most PEBS features are immutable, all other features are
@@ -73,19 +74,19 @@ static void guest_code(uint64_t current_val)
 	GUEST_DONE();
 }
 
+KVM_ONE_VCPU_TEST_SUITE(vmx_pmu_caps);
+
 /*
  * Verify that guest WRMSRs to PERF_CAPABILITIES #GP regardless of the value
  * written, that the guest always sees the userspace controlled value, and that
  * PERF_CAPABILITIES is immutable after KVM_RUN.
  */
-static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, guest_wrmsr_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 	struct ucall uc;
 	int r, i;
 
-	vm_init_descriptor_tables(vm);
+	vm_init_descriptor_tables(vcpu->vm);
 	vcpu_init_descriptor_tables(vcpu);
 
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
@@ -117,31 +118,21 @@ static void test_guest_wrmsr_perf_capabilities(union perf_capabilities host_cap)
 		TEST_ASSERT(!r, "Post-KVM_RUN write '0x%llx'didn't fail",
 			    host_cap.capabilities ^ BIT_ULL(i));
 	}
-
-	kvm_vm_free(vm);
 }
 
 /*
  * Verify KVM allows writing PERF_CAPABILITIES with all KVM-supported features
  * enabled, as well as '0' (to disable all features).
  */
-static void test_basic_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, basic_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
-
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0);
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
-
-	kvm_vm_free(vm);
 }
 
-static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, fungible_perf_capabilities, guest_code)
 {
 	const uint64_t fungible_caps = host_cap.capabilities & ~immutable_caps.capabilities;
-
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	int bit;
 
 	for_each_set_bit(bit, &fungible_caps, 64) {
@@ -150,8 +141,6 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
 			     host_cap.capabilities & ~BIT_ULL(bit));
 	}
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
-
-	kvm_vm_free(vm);
 }
 
 /*
@@ -160,14 +149,11 @@ static void test_fungible_perf_capabilities(union perf_capabilities host_cap)
  * separately as they are multi-bit values, e.g. toggling or setting a single
  * bit can generate a false positive without dedicated safeguards.
  */
-static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, immutable_perf_capabilities, guest_code)
 {
 	const uint64_t reserved_caps = (~host_cap.capabilities |
 					immutable_caps.capabilities) &
 				       ~format_caps.capabilities;
-
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm = vm_create_with_one_vcpu(&vcpu, NULL);
 	union perf_capabilities val = host_cap;
 	int r, bit;
 
@@ -201,8 +187,6 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
 		TEST_ASSERT(!r, "Bad PEBS FMT = 0x%x didn't fail, host = 0x%x",
 			    val.pebs_format, host_cap.pebs_format);
 	}
-
-	kvm_vm_free(vm);
 }
 
 /*
@@ -211,17 +195,13 @@ static void test_immutable_perf_capabilities(union perf_capabilities host_cap)
  * LBR_TOS as those bits are writable across all uarch implementations (arch
  * LBRs will need to poke a different MSR).
  */
-static void test_lbr_perf_capabilities(union perf_capabilities host_cap)
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code)
 {
-	struct kvm_vcpu *vcpu;
-	struct kvm_vm *vm;
 	int r;
 
 	if (!host_cap.lbr_format)
 		return;
 
-	vm = vm_create_with_one_vcpu(&vcpu, NULL);
-
 	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
 	vcpu_set_msr(vcpu, MSR_LBR_TOS, 7);
 
@@ -229,14 +209,10 @@ static void test_lbr_perf_capabilities(union perf_capabilities host_cap)
 
 	r = _vcpu_set_msr(vcpu, MSR_LBR_TOS, 7);
 	TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU");
-
-	kvm_vm_free(vm);
 }
 
 int main(int argc, char *argv[])
 {
-	union perf_capabilities host_cap;
-
 	TEST_REQUIRE(get_kvm_param_bool("enable_pmu"));
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM));
 
@@ -248,9 +224,5 @@ int main(int argc, char *argv[])
 	TEST_ASSERT(host_cap.full_width_write,
 		    "Full-width writes should always be supported");
 
-	test_basic_perf_capabilities(host_cap);
-	test_fungible_perf_capabilities(host_cap);
-	test_immutable_perf_capabilities(host_cap);
-	test_guest_wrmsr_perf_capabilities(host_cap);
-	test_lbr_perf_capabilities(host_cap);
+	return test_harness_run(argc, argv);
 }