KVM: nVMX: Ignore 'hv_clean_fields' data when eVMCS data is copied in vmx_get_nested_state()

'Clean fields' data from enlightened VMCS is only valid upon vmentry: L1
hypervisor is not obliged to keep it up-to-date while it is mangling L2's
state, KVM_GET_NESTED_STATE request may come at a wrong moment when actual
eVMCS changes are unsynchronized with 'hv_clean_fields'. As upon migration
VMCS12 is used as a source of ultimate truth, we must make sure we pick all
the changes to eVMCS and thus 'clean fields' data must be ignored.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210526132026.270394-8-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx/nested.c

@@ -1586,7 +1586,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
 	vmcs_load(vmx->loaded_vmcs->vmcs);
 }
 
-static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
+static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields)
 {
 	struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
 	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
@@ -1595,7 +1595,7 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 	vmcs12->tpr_threshold = evmcs->tpr_threshold;
 	vmcs12->guest_rip = evmcs->guest_rip;
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
 		vmcs12->guest_rsp = evmcs->guest_rsp;
 		vmcs12->guest_rflags = evmcs->guest_rflags;
@@ -1603,23 +1603,23 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 			evmcs->guest_interruptibility_info;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC))) {
 		vmcs12->cpu_based_vm_exec_control =
 			evmcs->cpu_based_vm_exec_control;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN))) {
 		vmcs12->exception_bitmap = evmcs->exception_bitmap;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY))) {
 		vmcs12->vm_entry_controls = evmcs->vm_entry_controls;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT))) {
 		vmcs12->vm_entry_intr_info_field =
 			evmcs->vm_entry_intr_info_field;
@@ -1629,7 +1629,7 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 			evmcs->vm_entry_instruction_len;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1))) {
 		vmcs12->host_ia32_pat = evmcs->host_ia32_pat;
 		vmcs12->host_ia32_efer = evmcs->host_ia32_efer;
@@ -1649,7 +1649,7 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 		vmcs12->host_tr_selector = evmcs->host_tr_selector;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1))) {
 		vmcs12->pin_based_vm_exec_control =
 			evmcs->pin_based_vm_exec_control;
@@ -1658,18 +1658,18 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 			evmcs->secondary_vm_exec_control;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP))) {
 		vmcs12->io_bitmap_a = evmcs->io_bitmap_a;
 		vmcs12->io_bitmap_b = evmcs->io_bitmap_b;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP))) {
 		vmcs12->msr_bitmap = evmcs->msr_bitmap;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2))) {
 		vmcs12->guest_es_base = evmcs->guest_es_base;
 		vmcs12->guest_cs_base = evmcs->guest_cs_base;
@@ -1709,14 +1709,14 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 		vmcs12->guest_tr_selector = evmcs->guest_tr_selector;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2))) {
 		vmcs12->tsc_offset = evmcs->tsc_offset;
 		vmcs12->virtual_apic_page_addr = evmcs->virtual_apic_page_addr;
 		vmcs12->xss_exit_bitmap = evmcs->xss_exit_bitmap;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR))) {
 		vmcs12->cr0_guest_host_mask = evmcs->cr0_guest_host_mask;
 		vmcs12->cr4_guest_host_mask = evmcs->cr4_guest_host_mask;
@@ -1728,7 +1728,7 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 		vmcs12->guest_dr7 = evmcs->guest_dr7;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER))) {
 		vmcs12->host_fs_base = evmcs->host_fs_base;
 		vmcs12->host_gs_base = evmcs->host_gs_base;
@@ -1738,13 +1738,13 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx)
 		vmcs12->host_rsp = evmcs->host_rsp;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT))) {
 		vmcs12->ept_pointer = evmcs->ept_pointer;
 		vmcs12->virtual_processor_id = evmcs->virtual_processor_id;
 	}
 
-	if (unlikely(!(evmcs->hv_clean_fields &
+	if (unlikely(!(hv_clean_fields &
 		       HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1))) {
 		vmcs12->vmcs_link_pointer = evmcs->vmcs_link_pointer;
 		vmcs12->guest_ia32_debugctl = evmcs->guest_ia32_debugctl;
@@ -3509,7 +3509,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return nested_vmx_failInvalid(vcpu);
 
 	if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
-		copy_enlightened_to_vmcs12(vmx);
+		copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields);
 		/* Enlightened VMCS doesn't have launch state */
 		vmcs12->launch_state = !launch;
 	} else if (enable_shadow_vmcs) {
@@ -6155,7 +6155,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
 		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
 			if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))
-				copy_enlightened_to_vmcs12(vmx);
+				/*
+				 * L1 hypervisor is not obliged to keep eVMCS
+				 * clean fields data always up-to-date while
+				 * not in guest mode, 'hv_clean_fields' is only
+				 * supposed to be actual upon vmentry so we need
+				 * to ignore it here and do full copy.
+				 */
+				copy_enlightened_to_vmcs12(vmx, 0);
 			else if (enable_shadow_vmcs)
 				copy_shadow_to_vmcs12(vmx);
 		}