KVM: nVMX: Unconditionally validate CR3 during nested transitions

Unconditionally check the validity of the incoming CR3 during nested
VM-Enter/VM-Exit to avoid invoking kvm_read_cr3() in the common case
where the guest isn't using PAE paging.  If vmcs.GUEST_CR3 hasn't yet
been cached (common case), kvm_read_cr3() will trigger a VMREAD.  The
VMREAD (~30 cycles) alone is likely slower than nested_cr3_valid()
(~5 cycles if vcpu->arch.maxphyaddr gets a cache hit), and the poor
exchange only gets worse when retpolines are enabled as the call to
kvm_x86_ops.cache_reg() will incur a retpoline (60+ cycles).
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200502043234.12481-3-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx/nested.c

@@ -1119,21 +1119,20 @@ static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu)
 static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
 			       u32 *entry_failure_code)
 {
-	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
-		if (CC(!nested_cr3_valid(vcpu, cr3))) {
-			*entry_failure_code = ENTRY_FAIL_DEFAULT;
-			return -EINVAL;
-		}
+	if (CC(!nested_cr3_valid(vcpu, cr3))) {
+		*entry_failure_code = ENTRY_FAIL_DEFAULT;
+		return -EINVAL;
+	}
 
-		/*
-		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
-		 * must not be dereferenced.
-		 */
-		if (is_pae_paging(vcpu) && !nested_ept) {
-			if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
-				*entry_failure_code = ENTRY_FAIL_PDPTE;
-				return -EINVAL;
-			}
+	/*
+	 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
+	 * must not be dereferenced.
+	 */
+	if (!nested_ept && is_pae_paging(vcpu) &&
+	    (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) {
+		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
+			*entry_failure_code = ENTRY_FAIL_PDPTE;
+			return -EINVAL;
 		}
 	}