KVM: x86: prevent setting unsupported XSAVE states

A guest can still attempt to save and restore XSAVE states even if they
have been masked in CPUID leaf 0Dh.  This usually is not visible to
the guest, but is still wrong: "Any attempt to set a reserved bit (as
determined by the contents of EAX and EDX after executing CPUID with
EAX=0DH, ECX= 0H) in XCR0 for a given processor will result in a #GP
exception".

The patch also performs the same checks as __kvm_set_xcr in KVM_SET_XSAVE.
This catches migration from newer to older kernel/processor before the
guest starts running.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NGleb Natapov <gleb@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -389,6 +389,7 @@ struct kvm_vcpu_arch {
 
 	struct fpu guest_fpu;
 	u64 xcr0;
+	u64 guest_supported_xcr0;
 
 	struct kvm_pio_request pio;
 	void *pio_data;

arch/x86/kvm/cpuid.c

@@ -46,6 +46,14 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			apic->lapic_timer.timer_mode_mask = 1 << 17;
 	}
 
+	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
+	if (!best)
+		vcpu->arch.guest_supported_xcr0 = 0;
+	else
+		vcpu->arch.guest_supported_xcr0 =
+			(best->eax | ((u64)best->edx << 32)) &
+			host_xcr0 & KVM_SUPPORTED_XCR0;
+
 	kvm_pmu_cpuid_update(vcpu);
 }
 

arch/x86/kvm/x86.c

@@ -586,7 +586,7 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
 		return 1;
-	if (xcr0 & ~host_xcr0)
+	if (xcr0 & ~vcpu->arch.guest_supported_xcr0)
 		return 1;
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
@@ -3003,10 +3003,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
 
-	if (cpu_has_xsave)
+	if (cpu_has_xsave) {
+		/*
+		 * Here we allow setting states that are not present in
+		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
+		 * with old userspace.
+		 */
+		if (xstate_bv & ~KVM_SUPPORTED_XCR0)
+			return -EINVAL;
+		if (xstate_bv & ~host_xcr0)
+			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
 			guest_xsave->region, xstate_size);
-	else {
+	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
@@ -6940,6 +6949,9 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
+
+	vcpu->arch.guest_supported_xcr0 = 0;
+
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);