7 files changed, 48 insertions, 32 deletions

diff --git a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h
index bad381d63b6a..05a1fc1780f2 100644
--- a/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h
+++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h
@@ -26,6 +26,8 @@ struct kvm_mmu_arch {
 	struct pte_masks pte_masks;
 };
 
+struct kvm_mmu;
+
 struct kvm_vm_arch {
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
@@ -35,6 +37,8 @@ struct kvm_vm_arch {
 	uint64_t s_bit;
 	int sev_fd;
 	bool is_pt_protected;
+
+	struct kvm_mmu *tdp_mmu;
 };
 
 static inline bool __vm_arch_has_protected_memory(struct kvm_vm_arch *arch)
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 55dac84cd4a7..0164ef090787 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -1459,6 +1459,9 @@ enum pg_level {
 #define is_huge_pte(mmu, pte)		(!!(*(pte) & PTE_HUGE_MASK(mmu)))
 #define is_nx_pte(mmu, pte)		(!!(*(pte) & PTE_NX_MASK(mmu)))
 
+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,
diff --git a/tools/testing/selftests/kvm/include/x86/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h
index 04b8231d032a..1fd83c23529a 100644
--- a/tools/testing/selftests/kvm/include/x86/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86/vmx.h
@@ -520,13 +520,11 @@ struct vmx_pages {
 	uint64_t vmwrite_gpa;
 	void *vmwrite;
 
-	void *eptp_hva;
-	uint64_t eptp_gpa;
-	void *eptp;
-
 	void *apic_access_hva;
 	uint64_t apic_access_gpa;
 	void *apic_access;
+
+	uint64_t eptp_gpa;
 };
 
 union vmx_basic {
@@ -568,7 +566,7 @@ void tdp_identity_map_default_memslots(struct vmx_pages *vmx,
 void tdp_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
 			 uint64_t addr, uint64_t size);
 bool kvm_cpu_has_ept(void);
-void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm);
+void vm_enable_ept(struct kvm_vm *vm);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
 
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c
index 1928b00bde51..00f7f11e5f0e 100644
--- a/tools/testing/selftests/kvm/lib/x86/memstress.c
+++ b/tools/testing/selftests/kvm/lib/x86/memstress.c
@@ -59,12 +59,10 @@ uint64_t memstress_nested_pages(int nr_vcpus)
 	return 513 + 10 * nr_vcpus;
 }
 
-void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
+static void memstress_setup_ept_mappings(struct vmx_pages *vmx, struct kvm_vm *vm)
 {
 	uint64_t start, end;
 
-	prepare_eptp(vmx, vm);
-
 	/*
 	 * Identity map the first 4G and the test region with 1G pages so that
 	 * KVM can shadow the EPT12 with the maximum huge page size supported
@@ -79,7 +77,7 @@ void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
 
 void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[])
 {
-	struct vmx_pages *vmx, *vmx0 = NULL;
+	struct vmx_pages *vmx;
 	struct kvm_regs regs;
 	vm_vaddr_t vmx_gva;
 	int vcpu_id;
@@ -87,18 +85,13 @@ void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc
 	TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
 	TEST_REQUIRE(kvm_cpu_has_ept());
 
+	vm_enable_ept(vm);
 	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
 		vmx = vcpu_alloc_vmx(vm, &vmx_gva);
 
-		if (vcpu_id == 0) {
-			memstress_setup_ept(vmx, vm);
-			vmx0 = vmx;
-		} else {
-			/* Share the same EPT table across all vCPUs. */
-			vmx->eptp = vmx0->eptp;
-			vmx->eptp_hva = vmx0->eptp_hva;
-			vmx->eptp_gpa = vmx0->eptp_gpa;
-		}
+		/* The EPTs are shared across vCPUs, setup the mappings once */
+		if (vcpu_id == 0)
+			memstress_setup_ept_mappings(vmx, vm);
 
 		/*
 		 * Override the vCPU to run memstress_l1_guest_code() which will
diff --git a/tools/testing/selftests/kvm/lib/x86/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 3800f4ff6770..8a9298a72897 100644
--- a/tools/testing/selftests/kvm/lib/x86/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -187,6 +187,15 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 	virt_mmu_init(vm, &vm->mmu, &pte_masks);
 }
 
+void tdp_mmu_init(struct kvm_vm *vm, int pgtable_levels,
+		  struct pte_masks *pte_masks)
+{
+	TEST_ASSERT(!vm->arch.tdp_mmu, "TDP MMU already initialized");
+
+	vm->arch.tdp_mmu = calloc(1, sizeof(*vm->arch.tdp_mmu));
+	virt_mmu_init(vm, vm->arch.tdp_mmu, pte_masks);
+}
+
 static void *virt_get_pte(struct kvm_vm *vm, struct kvm_mmu *mmu,
 			  uint64_t *parent_pte, uint64_t vaddr, int level)
 {
diff --git a/tools/testing/selftests/kvm/lib/x86/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index a3e2eae981da..9d4e391fdf2c 100644
--- a/tools/testing/selftests/kvm/lib/x86/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -56,6 +56,21 @@ int vcpu_enable_evmcs(struct kvm_vcpu *vcpu)
 	return evmcs_ver;
 }
 
+void vm_enable_ept(struct kvm_vm *vm)
+{
+	TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT");
+	if (vm->arch.tdp_mmu)
+		return;
+
+	/* TODO: Drop eptPageTableEntry in favor of PTE masks. */
+	struct pte_masks pte_masks = (struct pte_masks) {
+
+	};
+
+	/* TODO: Add support for 5-level EPT. */
+	tdp_mmu_init(vm, 4, &pte_masks);
+}
+
 /* Allocate memory regions for nested VMX tests.
  *
  * Input Args:
@@ -105,6 +120,9 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
 	vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
 	memset(vmx->vmwrite_hva, 0, getpagesize());
 
+	if (vm->arch.tdp_mmu)
+		vmx->eptp_gpa = vm->arch.tdp_mmu->pgd;
+
 	*p_vmx_gva = vmx_gva;
 	return vmx;
 }
@@ -395,7 +413,8 @@ void __tdp_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint64_t nested_paddr, uint64_t paddr, int target_level)
 {
 	const uint64_t page_size = PG_LEVEL_SIZE(target_level);
-	struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
+	void *eptp_hva = addr_gpa2hva(vm, vm->arch.tdp_mmu->pgd);
+	struct eptPageTableEntry *pt = eptp_hva, *pte;
 	uint16_t index;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXVYY_4K,
@@ -525,15 +544,6 @@ bool kvm_cpu_has_ept(void)
 	return ctrl & SECONDARY_EXEC_ENABLE_EPT;
 }
 
-void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm)
-{
-	TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT");
-
-	vmx->eptp = (void *)vm_vaddr_alloc_page(vm);
-	vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
-	vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
-}
-
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm)
 {
 	vmx->apic_access = (void *)vm_vaddr_alloc_page(vm);
diff --git a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
index e7d0c08ba29d..5c8cf8ac42a2 100644
--- a/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
@@ -93,6 +93,9 @@ static void test_vmx_dirty_log(bool enable_ept)
 
 	/* Create VM */
 	vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+	if (enable_ept)
+		vm_enable_ept(vm);
+
 	vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
 	vcpu_args_set(vcpu, 1, vmx_pages_gva);
 
@@ -113,14 +116,10 @@ static void test_vmx_dirty_log(bool enable_ept)
 	 * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to
 	 * 0xc0000000.
 	 *
-	 * Note that prepare_eptp should be called only L1's GPA map is done,
-	 * meaning after the last call to virt_map.
-	 *
 	 * When EPT is disabled, the L2 guest code will still access the same L1
 	 * GPAs as the EPT enabled case.
 	 */
 	if (enable_ept) {
-		prepare_eptp(vmx, vm);
 		tdp_identity_map_default_memslots(vmx, vm);
 		tdp_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, PAGE_SIZE);
 		tdp_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, PAGE_SIZE);