KVM: MMU: Add 5 level EPT & Shadow page table support.

Extends the shadow paging code, so that 5 level shadow page
table can be constructed if VM is running in 5 level paging
mode.

Also extends the ept code, so that 5 level ept table can be
constructed if maxphysaddr of VM exceeds 48 bits. Unlike the
shadow logic, KVM should still use 4 level ept table for a VM
whose physical address width is less than 48 bits, even when
the VM is running in 5 level paging mode.
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
[Unconditionally reset the MMU context in kvm_cpuid_update.
 Changing MAXPHYADDR invalidates the reserved bit bitmasks.
 - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -315,7 +315,7 @@ struct kvm_pio_request {
 	int size;
 };
 
-#define PT64_ROOT_MAX_LEVEL 4
+#define PT64_ROOT_MAX_LEVEL 5
 
 struct rsvd_bits_validate {
 	u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL];
@@ -323,9 +323,9 @@ struct rsvd_bits_validate {
 };
 
 /*
- * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
- * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
- * mode.
+ * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit,
+ * and 2-level 32-bit).  The kvm_mmu structure abstracts the details of the
+ * current mmu mode.
  */
 struct kvm_mmu {
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
@@ -982,7 +982,7 @@ struct kvm_x86_ops {
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
-	int (*get_tdp_level)(void);
+	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);

arch/x86/include/asm/vmx.h

@@ -453,6 +453,7 @@ enum vmcs_field {
 
 #define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
 #define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
+#define VMX_EPT_PAGE_WALK_5_BIT			(1ull << 7)
 #define VMX_EPTP_UC_BIT				(1ull << 8)
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
@@ -471,6 +472,7 @@ enum vmcs_field {
 #define VMX_EPT_MT_EPTE_SHIFT			3
 #define VMX_EPTP_PWL_MASK			0x38ull
 #define VMX_EPTP_PWL_4				0x18ull
+#define VMX_EPTP_PWL_5				0x20ull
 #define VMX_EPTP_AD_ENABLE_BIT			(1ull << 6)
 #define VMX_EPTP_MT_MASK			0x7ull
 #define VMX_EPTP_MT_WB				0x6ull

arch/x86/kvm/cpuid.c

@@ -136,6 +136,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu)
 
 	/* Update physical-address width */
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+	kvm_mmu_reset_context(vcpu);
 
 	kvm_pmu_refresh(vcpu);
 	return 0;

arch/x86/kvm/mmu.c

@@ -3322,8 +3322,8 @@ static void mmu_free_roots(struct kvm_vcpu *vcpu)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL &&
-	    (vcpu->arch.mmu.root_level == PT64_ROOT_4LEVEL ||
+	if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL &&
+	    (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL ||
 	     vcpu->arch.mmu.direct_map)) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
@@ -3375,13 +3375,14 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 	struct kvm_mmu_page *sp;
 	unsigned i;
 
-	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL) {
 		spin_lock(&vcpu->kvm->mmu_lock);
 		if(make_mmu_pages_available(vcpu) < 0) {
 			spin_unlock(&vcpu->kvm->mmu_lock);
 			return 1;
 		}
-		sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_4LEVEL, 1, ACC_ALL);
+		sp = kvm_mmu_get_page(vcpu, 0, 0,
+				vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
 		vcpu->arch.mmu.root_hpa = __pa(sp->spt);
@@ -3425,7 +3426,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 	 * Do we shadow a long mode page table? If so we need to
 	 * write-protect the guests page table root.
 	 */
-	if (vcpu->arch.mmu.root_level == PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
 		MMU_WARN_ON(VALID_PAGE(root));
@@ -3435,8 +3436,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 			spin_unlock(&vcpu->kvm->mmu_lock);
 			return 1;
 		}
-		sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_4LEVEL,
-				      0, ACC_ALL);
+		sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
+				vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL);
 		root = __pa(sp->spt);
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3531,7 +3532,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
 
 	vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
 	kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
-	if (vcpu->arch.mmu.root_level == PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 		sp = page_header(root);
 		mmu_sync_children(vcpu, sp);
@@ -4057,6 +4058,12 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 		rsvd_check->rsvd_bits_mask[1][0] =
 			rsvd_check->rsvd_bits_mask[0][0];
 		break;
+	case PT64_ROOT_5LEVEL:
+		rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd |
+			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
+			rsvd_bits(maxphyaddr, 51);
+		rsvd_check->rsvd_bits_mask[1][4] =
+			rsvd_check->rsvd_bits_mask[0][4];
 	case PT64_ROOT_4LEVEL:
 		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
@@ -4098,6 +4105,8 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
 {
 	u64 bad_mt_xwr;
 
+	rsvd_check->rsvd_bits_mask[0][4] =
+		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
 	rsvd_check->rsvd_bits_mask[0][3] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
 	rsvd_check->rsvd_bits_mask[0][2] =
@@ -4107,6 +4116,7 @@ __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check,
 	rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
 
 	/* large page */
+	rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4];
 	rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3];
 	rsvd_check->rsvd_bits_mask[1][2] =
 		rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
@@ -4367,7 +4377,10 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu,
 static void paging64_init_context(struct kvm_vcpu *vcpu,
 				  struct kvm_mmu *context)
 {
-	paging64_init_context_common(vcpu, context, PT64_ROOT_4LEVEL);
+	int root_level = is_la57_mode(vcpu) ?
+			 PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
+
+	paging64_init_context_common(vcpu, context, root_level);
 }
 
 static void paging32_init_context(struct kvm_vcpu *vcpu,
@@ -4408,7 +4421,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
 	context->update_pte = nonpaging_update_pte;
-	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+	context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu);
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = true;
 	context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
@@ -4422,7 +4435,8 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->root_level = 0;
 	} else if (is_long_mode(vcpu)) {
 		context->nx = is_nx(vcpu);
-		context->root_level = PT64_ROOT_4LEVEL;
+		context->root_level = is_la57_mode(vcpu) ?
+				PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
 		reset_rsvds_bits_mask(vcpu, context);
 		context->gva_to_gpa = paging64_gva_to_gpa;
 	} else if (is_pae(vcpu)) {
@@ -4479,7 +4493,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 
 	MMU_WARN_ON(VALID_PAGE(context->root_hpa));
 
-	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+	context->shadow_root_level = PT64_ROOT_4LEVEL;
 
 	context->nx = true;
 	context->ept_ad = accessed_dirty;
@@ -4488,7 +4502,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 	context->sync_page = ept_sync_page;
 	context->invlpg = ept_invlpg;
 	context->update_pte = ept_update_pte;
-	context->root_level = context->shadow_root_level;
+	context->root_level = PT64_ROOT_4LEVEL;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
 	context->base_role.ad_disabled = !accessed_dirty;
@@ -4533,7 +4547,8 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = nonpaging_gva_to_gpa_nested;
 	} else if (is_long_mode(vcpu)) {
 		g_context->nx = is_nx(vcpu);
-		g_context->root_level = PT64_ROOT_4LEVEL;
+		g_context->root_level = is_la57_mode(vcpu) ?
+					PT64_ROOT_5LEVEL : PT64_ROOT_4LEVEL;
 		reset_rsvds_bits_mask(vcpu, g_context);
 		g_context->gva_to_gpa = paging64_gva_to_gpa_nested;
 	} else if (is_pae(vcpu)) {

arch/x86/kvm/mmu.h

@@ -37,6 +37,7 @@
 #define PT32_DIR_PSE36_MASK \
 	(((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT)
 
+#define PT64_ROOT_5LEVEL 5
 #define PT64_ROOT_4LEVEL 4
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3

arch/x86/kvm/mmu_audit.c

@@ -62,11 +62,11 @@ static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
 	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
 		return;
 
-	if (vcpu->arch.mmu.root_level == PT64_ROOT_4LEVEL) {
+	if (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL) {
 		hpa_t root = vcpu->arch.mmu.root_hpa;
 
 		sp = page_header(root);
-		__mmu_spte_walk(vcpu, sp, fn, PT64_ROOT_4LEVEL);
+		__mmu_spte_walk(vcpu, sp, fn, vcpu->arch.mmu.root_level);
 		return;
 	}
 

arch/x86/kvm/svm.c

@@ -581,7 +581,7 @@ static inline void invlpga(unsigned long addr, u32 asid)
 	asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
 }
 
-static int get_npt_level(void)
+static int get_npt_level(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
 	return PT64_ROOT_4LEVEL;
@@ -2402,7 +2402,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.get_cr3           = nested_svm_get_tdp_cr3;
 	vcpu->arch.mmu.get_pdptr         = nested_svm_get_tdp_pdptr;
 	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
-	vcpu->arch.mmu.shadow_root_level = get_npt_level();
+	vcpu->arch.mmu.shadow_root_level = get_npt_level(vcpu);
 	reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu);
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
 }

arch/x86/kvm/vmx.c

@@ -1207,6 +1207,11 @@ static inline bool cpu_has_vmx_ept_mt_wb(void)
 	return vmx_capability.ept & VMX_EPTP_WB_BIT;
 }
 
+static inline bool cpu_has_vmx_ept_5levels(void)
+{
+	return vmx_capability.ept & VMX_EPT_PAGE_WALK_5_BIT;
+}
+
 static inline bool cpu_has_vmx_ept_ad_bits(void)
 {
 	return vmx_capability.ept & VMX_EPT_AD_BIT;
@@ -4304,9 +4309,18 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	vmx->emulation_required = emulation_required(vcpu);
 }
 
+static int get_ept_level(struct kvm_vcpu *vcpu)
+{
+	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
+		return 5;
+	return 4;
+}
+
 static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 {
-	u64 eptp = VMX_EPTP_MT_WB | VMX_EPTP_PWL_4;
+	u64 eptp = VMX_EPTP_MT_WB;
+
+	eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
 
 	if (enable_ept_ad_bits &&
 	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
@@ -9612,11 +9626,6 @@ static void __init vmx_check_processor_compat(void *rtn)
 	}
 }
 
-static int get_ept_level(void)
-{
-	return 4;
-}
-
 static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
 	u8 cache;

arch/x86/kvm/x86.h

@@ -62,6 +62,16 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
 	return cs_l;
 }
 
+static inline bool is_la57_mode(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_X86_64
+	return (vcpu->arch.efer & EFER_LMA) &&
+		 kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+#else
+	return 0;
+#endif
+}
+
 static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;