Merge tag 'kvm-x86-selftests-6.20' of https://github.com/kvm-x86/linux into HEAD

KVM selftests changes for 6.20

 - Add a regression test for TPR<=>CR8 synchronization and IRQ masking.

 - Overhaul selftest's MMU infrastructure to genericize stage-2 MMU support,
   and extend x86's infrastructure to support EPT and NPT (for L2 guests).

 - Extend several nested VMX tests to also cover nested SVM.

 - Add a selftest for nested VMLOAD/VMSAVE.

 - Rework the nested dirty log test, originally added as a regression test for
   PML where KVM logged L2 GPAs instead of L1 GPAs, to improve test coverage
   and to hopefully make the test easier to understand and maintain.

Author: bonzini

tools/testing/selftests/kvm/Makefile.kvm

@@ -89,11 +89,13 @@ TEST_GEN_PROGS_x86 += x86/kvm_buslock_test
 TEST_GEN_PROGS_x86 += x86/monitor_mwait_test
 TEST_GEN_PROGS_x86 += x86/msrs_test
 TEST_GEN_PROGS_x86 += x86/nested_close_kvm_test
+TEST_GEN_PROGS_x86 += x86/nested_dirty_log_test
 TEST_GEN_PROGS_x86 += x86/nested_emulation_test
 TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
 TEST_GEN_PROGS_x86 += x86/nested_invalid_cr3_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_adjust_test
 TEST_GEN_PROGS_x86 += x86/nested_tsc_scaling_test
+TEST_GEN_PROGS_x86 += x86/nested_vmsave_vmload_test
 TEST_GEN_PROGS_x86 += x86/platform_info_test
 TEST_GEN_PROGS_x86 += x86/pmu_counters_test
 TEST_GEN_PROGS_x86 += x86/pmu_event_filter_test
@@ -115,7 +117,6 @@ TEST_GEN_PROGS_x86 += x86/ucna_injection_test
 TEST_GEN_PROGS_x86 += x86/userspace_io_test
 TEST_GEN_PROGS_x86 += x86/userspace_msr_exit_test
 TEST_GEN_PROGS_x86 += x86/vmx_apic_access_test
-TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test
 TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state
 TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
 TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state
@@ -124,6 +125,7 @@ TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test
 TEST_GEN_PROGS_x86 += x86/xapic_ipi_test
 TEST_GEN_PROGS_x86 += x86/xapic_state_test
+TEST_GEN_PROGS_x86 += x86/xapic_tpr_test
 TEST_GEN_PROGS_x86 += x86/xcr0_cpuid_test
 TEST_GEN_PROGS_x86 += x86/xss_msr_test
 TEST_GEN_PROGS_x86 += x86/debug_regs

tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h

@@ -2,6 +2,8 @@
 #ifndef SELFTEST_KVM_UTIL_ARCH_H
 #define SELFTEST_KVM_UTIL_ARCH_H
 
+struct kvm_mmu_arch {};
+
 struct kvm_vm_arch {
 	bool	has_gic;
 	int	gic_fd;

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

@@ -88,12 +88,19 @@ enum kvm_mem_region_type {
 	NR_MEM_REGIONS,
 };
 
+struct kvm_mmu {
+	bool pgd_created;
+	uint64_t pgd;
+	int pgtable_levels;
+
+	struct kvm_mmu_arch arch;
+};
+
 struct kvm_vm {
 	int mode;
 	unsigned long type;
 	int kvm_fd;
 	int fd;
-	unsigned int pgtable_levels;
 	unsigned int page_size;
 	unsigned int page_shift;
 	unsigned int pa_bits;
@@ -104,13 +111,18 @@ struct kvm_vm {
 	struct sparsebit *vpages_valid;
 	struct sparsebit *vpages_mapped;
 	bool has_irqchip;
-	bool pgd_created;
 	vm_paddr_t ucall_mmio_addr;
-	vm_paddr_t pgd;
 	vm_vaddr_t handlers;
 	uint32_t dirty_ring_size;
 	uint64_t gpa_tag_mask;
 
+	/*
+	 * "mmu" is the guest's stage-1, with a short name because the vast
+	 * majority of tests only care about the stage-1 MMU.
+	 */
+	struct kvm_mmu mmu;
+	struct kvm_mmu stage2_mmu;
+
 	struct kvm_vm_arch arch;
 
 	struct kvm_binary_stats stats;

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

@@ -2,6 +2,7 @@
 #ifndef SELFTEST_KVM_UTIL_ARCH_H
 #define SELFTEST_KVM_UTIL_ARCH_H
 
+struct kvm_mmu_arch {};
 struct kvm_vm_arch {};
 
 #endif  // SELFTEST_KVM_UTIL_ARCH_H

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

@@ -2,6 +2,7 @@
 #ifndef SELFTEST_KVM_UTIL_ARCH_H
 #define SELFTEST_KVM_UTIL_ARCH_H
 
+struct kvm_mmu_arch {};
 struct kvm_vm_arch {};
 
 #endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/s390/kvm_util_arch.h

@@ -2,6 +2,7 @@
 #ifndef SELFTEST_KVM_UTIL_ARCH_H
 #define SELFTEST_KVM_UTIL_ARCH_H
 
+struct kvm_mmu_arch {};
 struct kvm_vm_arch {};
 
 #endif  // SELFTEST_KVM_UTIL_ARCH_H

tools/testing/selftests/kvm/include/x86/apic.h

@@ -28,6 +28,8 @@
 #define		GET_APIC_ID_FIELD(x)	(((x) >> 24) & 0xFF)
 #define	APIC_TASKPRI	0x80
 #define	APIC_PROCPRI	0xA0
+#define	GET_APIC_PRI(x) (((x) & GENMASK(7, 4)) >> 4)
+#define	SET_APIC_PRI(x, y) (((x) & ~GENMASK(7, 4)) | (y << 4))
 #define	APIC_EOI	0xB0
 #define	APIC_SPIV	0xF0
 #define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
@@ -67,6 +69,7 @@
 #define	APIC_TMICT	0x380
 #define	APIC_TMCCT	0x390
 #define	APIC_TDCR	0x3E0
+#define	APIC_SELF_IPI	0x3F0
 
 void apic_disable(void);
 void xapic_enable(void);

tools/testing/selftests/kvm/include/x86/kvm_util_arch.h

@@ -10,6 +10,28 @@
 
 extern bool is_forced_emulation_enabled;
 
+struct pte_masks {
+	uint64_t present;
+	uint64_t writable;
+	uint64_t user;
+	uint64_t readable;
+	uint64_t executable;
+	uint64_t accessed;
+	uint64_t dirty;
+	uint64_t huge;
+	uint64_t nx;
+	uint64_t c;
+	uint64_t s;
+
+	uint64_t always_set;
+};
+
+struct kvm_mmu_arch {
+	struct pte_masks pte_masks;
+};
+
+struct kvm_mmu;
+
 struct kvm_vm_arch {
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;

tools/testing/selftests/kvm/include/x86/processor.h

@@ -201,6 +201,7 @@ struct kvm_x86_cpu_feature {
 #define X86_FEATURE_TSCRATEMSR          KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 4)
 #define X86_FEATURE_PAUSEFILTER         KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 10)
 #define X86_FEATURE_PFTHRESHOLD         KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 12)
+#define	X86_FEATURE_V_VMSAVE_VMLOAD	KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 15)
 #define	X86_FEATURE_VGIF		KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 16)
 #define X86_FEATURE_IDLE_HLT		KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 30)
 #define X86_FEATURE_SEV			KVM_X86_CPU_FEATURE(0x8000001F, 0, EAX, 1)
@@ -362,16 +363,6 @@ static inline unsigned int x86_model(unsigned int eax)
 	return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
 }
 
-/* Page table bitfield declarations */
-#define PTE_PRESENT_MASK        BIT_ULL(0)
-#define PTE_WRITABLE_MASK       BIT_ULL(1)
-#define PTE_USER_MASK           BIT_ULL(2)
-#define PTE_ACCESSED_MASK       BIT_ULL(5)
-#define PTE_DIRTY_MASK          BIT_ULL(6)
-#define PTE_LARGE_MASK          BIT_ULL(7)
-#define PTE_GLOBAL_MASK         BIT_ULL(8)
-#define PTE_NX_MASK             BIT_ULL(63)
-
 #define PHYSICAL_PAGE_MASK      GENMASK_ULL(51, 12)
 
 #define PAGE_SHIFT		12
@@ -436,8 +427,10 @@ struct kvm_x86_state {
 
 static inline uint64_t get_desc64_base(const struct desc64 *desc)
 {
-	return ((uint64_t)desc->base3 << 32) |
-		(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
+	return (uint64_t)desc->base3 << 32 |
+	       (uint64_t)desc->base2 << 24 |
+	       (uint64_t)desc->base1 << 16 |
+	       (uint64_t)desc->base0;
 }
 
 static inline uint64_t rdtsc(void)
@@ -1367,9 +1360,7 @@ static inline bool kvm_is_ignore_msrs(void)
 	return get_kvm_param_bool("ignore_msrs");
 }
 
-uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
-				    int *level);
-uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
+uint64_t *vm_get_pte(struct kvm_vm *vm, uint64_t vaddr);
 
 uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
 		       uint64_t a3);
@@ -1451,10 +1442,52 @@ enum pg_level {
 #define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
 #define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
 
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
+#define PTE_PRESENT_MASK(mmu)		((mmu)->arch.pte_masks.present)
+#define PTE_WRITABLE_MASK(mmu)		((mmu)->arch.pte_masks.writable)
+#define PTE_USER_MASK(mmu)		((mmu)->arch.pte_masks.user)
+#define PTE_READABLE_MASK(mmu)		((mmu)->arch.pte_masks.readable)
+#define PTE_EXECUTABLE_MASK(mmu)	((mmu)->arch.pte_masks.executable)
+#define PTE_ACCESSED_MASK(mmu)		((mmu)->arch.pte_masks.accessed)
+#define PTE_DIRTY_MASK(mmu)		((mmu)->arch.pte_masks.dirty)
+#define PTE_HUGE_MASK(mmu)		((mmu)->arch.pte_masks.huge)
+#define PTE_NX_MASK(mmu)		((mmu)->arch.pte_masks.nx)
+#define PTE_C_BIT_MASK(mmu)		((mmu)->arch.pte_masks.c)
+#define PTE_S_BIT_MASK(mmu)		((mmu)->arch.pte_masks.s)
+#define PTE_ALWAYS_SET_MASK(mmu)	((mmu)->arch.pte_masks.always_set)
+
+/*
+ * For PTEs without a PRESENT bit (i.e. EPT entries), treat the PTE as present
+ * if it's executable or readable, as EPT supports execute-only PTEs, but not
+ * write-only PTEs.
+ */
+#define is_present_pte(mmu, pte)		\
+	(PTE_PRESENT_MASK(mmu) ?		\
+	 !!(*(pte) & PTE_PRESENT_MASK(mmu)) :	\
+	 !!(*(pte) & (PTE_READABLE_MASK(mmu) | PTE_EXECUTABLE_MASK(mmu))))
+#define is_executable_pte(mmu, pte)	\
+	((*(pte) & (PTE_EXECUTABLE_MASK(mmu) | PTE_NX_MASK(mmu))) == PTE_EXECUTABLE_MASK(mmu))
+#define is_writable_pte(mmu, pte)	(!!(*(pte) & PTE_WRITABLE_MASK(mmu)))
+#define is_user_pte(mmu, pte)		(!!(*(pte) & PTE_USER_MASK(mmu)))
+#define is_accessed_pte(mmu, pte)	(!!(*(pte) & PTE_ACCESSED_MASK(mmu)))
+#define is_dirty_pte(mmu, pte)		(!!(*(pte) & PTE_DIRTY_MASK(mmu)))
+#define is_huge_pte(mmu, pte)		(!!(*(pte) & PTE_HUGE_MASK(mmu)))
+#define is_nx_pte(mmu, pte)		(!is_executable_pte(mmu, pte))
+
+void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels,
+		  struct pte_masks *pte_masks);
+
+void __virt_pg_map(struct kvm_vm *vm, struct kvm_mmu *mmu, uint64_t vaddr,
+		   uint64_t paddr,  int level);
 void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 		    uint64_t nr_bytes, int level);
 
+void vm_enable_tdp(struct kvm_vm *vm);
+bool kvm_cpu_has_tdp(void);
+void tdp_map(struct kvm_vm *vm, uint64_t nested_paddr, uint64_t paddr, uint64_t size);
+void tdp_identity_map_default_memslots(struct kvm_vm *vm);
+void tdp_identity_map_1g(struct kvm_vm *vm,  uint64_t addr, uint64_t size);
+uint64_t *tdp_get_pte(struct kvm_vm *vm, uint64_t l2_gpa);
+
 /*
  * Basic CPU control in CR0
  */

tools/testing/selftests/kvm/include/x86/svm_util.h

@@ -27,6 +27,9 @@ struct svm_test_data {
 	void *msr; /* gva */
 	void *msr_hva;
 	uint64_t msr_gpa;
+
+	/* NPT */
+	uint64_t ncr3_gpa;
 };
 
 static inline void vmmcall(void)
@@ -57,6 +60,12 @@ struct svm_test_data *vcpu_alloc_svm(struct kvm_vm *vm, vm_vaddr_t *p_svm_gva);
 void generic_svm_setup(struct svm_test_data *svm, void *guest_rip, void *guest_rsp);
 void run_guest(struct vmcb *vmcb, uint64_t vmcb_gpa);
 
+static inline bool kvm_cpu_has_npt(void)
+{
+	return kvm_cpu_has(X86_FEATURE_NPT);
+}
+void vm_enable_npt(struct kvm_vm *vm);
+
 int open_sev_dev_path_or_exit(void);
 
 #endif /* SELFTEST_KVM_SVM_UTILS_H */