KVM: nSVM: Optimize vmcb12 to vmcb02 save area copies

Use the vmcb12 control clean field to determine which vmcb12.save
registers were marked dirty in order to minimize register copies
when switching from L1 to L2. Those vmcb12 registers marked as dirty need
to be copied to L0's vmcb02 as they will be used to update the vmcb
state cache for the L2 VMRUN.  In the case where we have a different
vmcb12 from the last L2 VMRUN all vmcb12.save registers must be
copied over to L2.save.

Tested:
kvm-unit-tests
kvm selftests
Fedora L1 L2
Suggested-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NCathy Avery <cavery@redhat.com>
Message-Id: <20210301200844.2000-1-cavery@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/svm/nested.c

@@ -422,19 +422,31 @@ void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm)
 
 static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
+	bool new_vmcb12 = false;
+
 	nested_vmcb02_compute_g_pat(svm);
 
 	/* Load the nested guest state */
-	svm->vmcb->save.es = vmcb12->save.es;
-	svm->vmcb->save.cs = vmcb12->save.cs;
-	svm->vmcb->save.ss = vmcb12->save.ss;
-	svm->vmcb->save.ds = vmcb12->save.ds;
-	svm->vmcb->save.cpl = vmcb12->save.cpl;
-	vmcb_mark_dirty(svm->vmcb, VMCB_SEG);
 
-	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
-	svm->vmcb->save.idtr = vmcb12->save.idtr;
-	vmcb_mark_dirty(svm->vmcb, VMCB_DT);
+	if (svm->nested.vmcb12_gpa != svm->nested.last_vmcb12_gpa) {
+		new_vmcb12 = true;
+		svm->nested.last_vmcb12_gpa = svm->nested.vmcb12_gpa;
+	}
+
+	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_SEG))) {
+		svm->vmcb->save.es = vmcb12->save.es;
+		svm->vmcb->save.cs = vmcb12->save.cs;
+		svm->vmcb->save.ss = vmcb12->save.ss;
+		svm->vmcb->save.ds = vmcb12->save.ds;
+		svm->vmcb->save.cpl = vmcb12->save.cpl;
+		vmcb_mark_dirty(svm->vmcb, VMCB_SEG);
+	}
+
+	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DT))) {
+		svm->vmcb->save.gdtr = vmcb12->save.gdtr;
+		svm->vmcb->save.idtr = vmcb12->save.idtr;
+		vmcb_mark_dirty(svm->vmcb, VMCB_DT);
+	}
 
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
 	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
@@ -442,19 +454,22 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
 
 	svm->vcpu.arch.cr2 = vmcb12->save.cr2;
+
 	kvm_rax_write(&svm->vcpu, vmcb12->save.rax);
 	kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp);
 	kvm_rip_write(&svm->vcpu, vmcb12->save.rip);
 
 	/* In case we don't even reach vcpu_run, the fields are not updated */
-	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2;
 	svm->vmcb->save.rax = vmcb12->save.rax;
 	svm->vmcb->save.rsp = vmcb12->save.rsp;
 	svm->vmcb->save.rip = vmcb12->save.rip;
 
-	svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
-	svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_ACTIVE_LOW;
-	vmcb_mark_dirty(svm->vmcb, VMCB_DR);
+	/* These bits will be set properly on the first execution when new_vmc12 is true */
+	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) {
+		svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
+		svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_ACTIVE_LOW;
+		vmcb_mark_dirty(svm->vmcb, VMCB_DR);
+	}
 }
 
 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)

arch/x86/kvm/svm/svm.c

@@ -1234,6 +1234,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 	svm->asid = 0;
 
 	svm->nested.vmcb12_gpa = 0;
+	svm->nested.last_vmcb12_gpa = 0;
 	vcpu->arch.hflags = 0;
 
 	if (!kvm_pause_in_guest(vcpu->kvm)) {

arch/x86/kvm/svm/svm.h

@@ -93,6 +93,7 @@ struct svm_nested_state {
 	u64 hsave_msr;
 	u64 vm_cr_msr;
 	u64 vmcb12_gpa;
+	u64 last_vmcb12_gpa;
 
 	/* These are the merged vectors */
 	u32 *msrpm;
@@ -247,6 +248,11 @@ static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit)
 	vmcb->control.clean &= ~(1 << bit);
 }
 
+static inline bool vmcb_is_dirty(struct vmcb *vmcb, int bit)
+{
+        return !test_bit(bit, (unsigned long *)&vmcb->control.clean);
+}
+
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {
 	return container_of(vcpu, struct vcpu_svm, vcpu);