KVM: x86: handle missing MPX in nested virtualization

When doing nested virtualization, we may be able to read BNDCFGS but
still not be allowed to write to GUEST_BNDCFGS in the VMCS.  Guard
writes to the field with vmx_mpx_supported(), and similarly hide the
MSR from userspace if the processor does not support the field.

We could work around this with the generic MSR save/load machinery,
but there is only a limited number of MSR save/load slots and it is
not really worthwhile to waste one for a scenario that should not
happen except in the nested virtualization case.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c95bea1..1320e0f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -729,6 +729,7 @@
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
+static bool vmx_mpx_supported(void);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
@@ -2501,6 +2502,8 @@
 		data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
+		if (!vmx_mpx_supported())
+			return 1;
 		data = vmcs_read64(GUEST_BNDCFGS);
 		break;
 	case MSR_IA32_FEATURE_CONTROL:
@@ -2572,6 +2575,8 @@
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
+		if (!vmx_mpx_supported())
+			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
 	case MSR_IA32_TSC: