From: Miaohe Lin Date: Sat, 28 Dec 2019 06:25:24 +0000 (+0800) Subject: KVM: nVMX: vmread should not set rflags to specify success in case of #PF X-Git-Tag: v3.16.84~41 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=36f73419847a5e2b79a85552faaf7e673f794bb7;p=thirdparty%2Fkernel%2Fstable.git KVM: nVMX: vmread should not set rflags to specify success in case of #PF commit a4d956b9390418623ae5d07933e2679c68b6f83c upstream. In case writing to vmread destination operand result in a #PF, vmread should not call nested_vmx_succeed() to set rflags to specify success. Similar to as done in VMPTRST (See handle_vmptrst()). Reviewed-by: Liran Alon Signed-off-by: Miaohe Lin Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini [bwh: Backported to 3.16: adjust filename, context] Signed-off-by: Ben Hutchings --- diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1faaa78505f4a..0566fd97b58e8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6455,8 +6455,10 @@ static int handle_vmread(struct kvm_vcpu *vcpu) /* _system ok, as nested_vmx_check_permission verified cpl=0 */ if (kvm_write_guest_virt_system(vcpu, gva, &field_value, (is_long_mode(vcpu) ? 8 : 4), - &e)) + &e)) { kvm_inject_page_fault(vcpu, &e); + return 1; + } } nested_vmx_succeed(vcpu);