From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: Re: KVM: x86: use proper port value when checking io instruction permission (v2) Date: Thu, 26 May 2011 11:26:39 +0300 Message-ID: <20110526082639.GE29458@redhat.com> References: <20110524171120.GA19906@amt.cnet> <20110524172706.GC22042@redhat.com> <20110525181820.GA14921@amt.cnet> <4DDDF3D6.3000505@redhat.com> <20110526065511.GA29458@redhat.com> <4DDDFB07.2050909@redhat.com> <4DDDFB78.9070307@redhat.com> <20110526070737.GB29458@redhat.com> <4DDE0601.8060008@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Avi Kivity , Marcelo Tosatti , kvm , Joerg Roedel To: Paolo Bonzini Return-path: Received: from mx1.redhat.com ([209.132.183.28]:52941 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752383Ab1EZI0n (ORCPT ); Thu, 26 May 2011 04:26:43 -0400 Content-Disposition: inline In-Reply-To: <4DDE0601.8060008@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Thu, May 26, 2011 at 09:49:21AM +0200, Paolo Bonzini wrote: > On 05/26/2011 09:07 AM, Gleb Natapov wrote: > >> Still, op_bytes is irrelevant for > >> SrcDX, the 16-bit version is always used. > > > >If SrcDX/DstDX will be used only for decoding in/out instruction > >then yes. Otherwise it is nice to have more general decoder. > > Not counting instructions that read/write many registers > (rdmsr/wrmsr, mul/imul/div/idiv, rdtsc, etc.), I think the only > other instruction with an implicit DstDX is cwd/cdq/cqo. Since > cwd/cdq/cqo needs c->dst.bytes = c->src.bytes (not op_bytes) I think > DstDX is not really reusable beyond port instructions. > Why would c->dst.bytes != c->src.bytes for cwd/cdq/cqo if we'll set c->dst.bytes to op_bytes during decode? -- Gleb.