KVM: nVMX: Allow L1 to use 5-level page walks for nested EPT

Add support for 5-level nested EPT, and advertise said support in the
EPT capabilities MSR.  KVM's MMU can already handle 5-level legacy page
tables, there's no reason to force an L1 VMM to use shadow paging if it
wants to employ 5-level page tables.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 25 insertions, 12 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 374ccbcb92e1..a214e103af07 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5008,14 +5008,14 @@ EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
 static union kvm_mmu_role
 kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
-				   bool execonly)
+				   bool execonly, u8 level)
 {
 	union kvm_mmu_role role = {0};
 
 	/* SMM flag is inherited from root_mmu */
 	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
 
-	role.base.level = PT64_ROOT_4LEVEL;
+	role.base.level = level;
 	role.base.gpte_is_8_bytes = true;
 	role.base.direct = false;
 	role.base.ad_disabled = !accessed_dirty;
@@ -5039,16 +5039,17 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty, gpa_t new_eptp)
 {
 	struct kvm_mmu *context = vcpu->arch.mmu;
+	u8 level = vmx_eptp_page_walk_level(new_eptp);
 	union kvm_mmu_role new_role =
 		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
-						   execonly);
+						   execonly, level);
 
 	__kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
 
 	if (new_role.as_u64 == context->mmu_role.as_u64)
 		return;
 
-	context->shadow_root_level = PT64_ROOT_4LEVEL;
+	context->shadow_root_level = level;
 
 	context->nx = true;
 	context->ept_ad = accessed_dirty;
@@ -5057,7 +5058,7 @@ 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 = PT64_ROOT_4LEVEL;
+	context->root_level = level;
 	context->direct_map = false;
 	context->mmu_role.as_u64 = new_role.as_u64;
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index e4c8a4cbf407..6b15b58f3ecc 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -66,7 +66,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT 8
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad)
 	#define CMPXCHG cmpxchg64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 #else
 	#error Invalid PTTYPE value
 #endif
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 300d87ff23c2..5f19b906d94a 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2582,9 +2582,19 @@ static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
 		return false;
 	}
 
-	/* only 4 levels page-walk length are valid */
-	if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4))
+	/* Page-walk levels validity. */
+	switch (address & VMX_EPTP_PWL_MASK) {
+	case VMX_EPTP_PWL_5:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT)))
+			return false;
+		break;
+	case VMX_EPTP_PWL_4:
+		if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT)))
+			return false;
+		break;
+	default:
 		return false;
+	}
 
 	/* Reserved bits should not be set */
 	if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f)))
@@ -6119,8 +6129,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 		/* nested EPT: emulate EPT also to L1 */
 		msrs->secondary_ctls_high |=
 			SECONDARY_EXEC_ENABLE_EPT;
-		msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
-			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+		msrs->ept_caps =
+			VMX_EPT_PAGE_WALK_4_BIT |
+			VMX_EPT_PAGE_WALK_5_BIT |
+			VMX_EPTP_WB_BIT |
+			VMX_EPT_INVEPT_BIT;
 		if (cpu_has_vmx_ept_execute_only())
 			msrs->ept_caps |=
 				VMX_EPT_EXECUTE_ONLY_BIT;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index de4bf790b3f4..c369ab30d4e6 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2985,9 +2985,8 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
-	/* Nested EPT currently only supports 4-level walks. */
 	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
-		return 4;
+		return vmx_eptp_page_walk_level(nested_ept_get_cr3(vcpu));
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;