KVM: nVMX: optimize prepare_vmcs02{,_full} for Enlightened VMCS case

When Enlightened VMCS is in use by L1 hypervisor we can avoid vmwriting
VMCS fields which did not change.

Our first goal is to achieve minimal impact on traditional VMCS case so
we're not wrapping each vmwrite() with an if-changed checker. We also can't
utilize static keys as Enlightened VMCS usage is per-guest.

This patch implements the simpliest solution: checking fields in groups.
We skip single vmwrite() statements as doing the check will cost us
something even in non-evmcs case and the win is tiny. Unfortunately, this
makes prepare_vmcs02_full{,_full}() code Enlightened VMCS-dependent (and
a bit ugly).
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/vmx.c

@@ -12699,6 +12699,10 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 
 static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 {
+	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
+
+	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
 		vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 		vmcs_write16(GUEST_SS_SELECTOR, vmcs12->guest_ss_selector);
 		vmcs_write16(GUEST_DS_SELECTOR, vmcs12->guest_ds_selector);
@@ -12730,13 +12734,28 @@ static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+	}
 
+	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1)) {
 		vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
 		vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
 			    vmcs12->guest_pending_dbg_exceptions);
 		vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
 		vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
 
+		/*
+		 * L1 may access the L2's PDPTR, so save them to construct
+		 * vmcs12
+		 */
+		if (enable_ept) {
+			vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+			vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+			vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+			vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+		}
+	}
+
 	if (nested_cpu_has_xsaves(vmcs12))
 		vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
 
@@ -12778,16 +12797,6 @@ static void prepare_vmcs02_full(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		else
 			vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
 	}
-
-	/*
-	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
-	 */
-	if (enable_ept) {
-		vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
-		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
-		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
-		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-	}
 }
 
 /*
@@ -12805,6 +12814,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			  u32 *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
 
 	if (vmx->nested.dirty_vmcs12 || vmx->nested.hv_evmcs) {
 		prepare_vmcs02_full(vmx, vmcs12);
@@ -12815,12 +12825,14 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * First, the fields that are shadowed.  This must be kept in sync
 	 * with vmx_shadow_fields.h.
 	 */
-
+	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
+			   HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) {
 		vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
 		vmcs_write32(GUEST_CS_LIMIT, vmcs12->guest_cs_limit);
 		vmcs_write32(GUEST_CS_AR_BYTES, vmcs12->guest_cs_ar_bytes);
 		vmcs_writel(GUEST_ES_BASE, vmcs12->guest_es_base);
 		vmcs_writel(GUEST_CS_BASE, vmcs12->guest_cs_base);
+	}
 
 	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {