KVM: x86: Fix pkru save/restore when guest CR4.PKE=0, move it to x86.c

Though rdpkru and wrpkru are contingent upon CR4.PKE, the PKRU
resource isn't. It can be read with XSAVE and written with XRSTOR.
So, if we don't set the guest PKRU value here(kvm_load_guest_xsave_state),
the guest can read the host value.

In case of kvm_load_host_xsave_state, guest with CR4.PKE clear could
potentially use XRSTOR to change the host PKRU value.

While at it, move pkru state save/restore to common code and the
host_pkru field to kvm_vcpu_arch.  This will let SVM support protection keys.

Cc: stable@vger.kernel.org
Reported-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Babu Moger <babu.moger@amd.com>
Message-Id: <158932794619.44260.14508381096663848853.stgit@naples-babu.amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/x86.c

@@ -837,11 +837,25 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
 		    vcpu->arch.ia32_xss != host_xss)
 			wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
 	}
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+	    vcpu->arch.pkru != vcpu->arch.host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
 
 void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 {
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+			__write_pkru(vcpu->arch.host_pkru);
+	}
+
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
 
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -3549,6 +3563,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	kvm_x86_ops.vcpu_load(vcpu, cpu);
 
+	/* Save host pkru register if supported */
+	vcpu->arch.host_pkru = read_pkru();
+
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);