From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Jan Beulich" Subject: Re: [patch] x86: Add CPU Feature Mask support (cpu spoof) for NHM Date: Tue, 15 Jun 2010 08:50:02 +0100 Message-ID: <4C174CCB0200007800006719@vpn.id2.novell.com> References: <789F9655DD1B8F43B48D77C5D30659731E84D241@shsmsx501.ccr.corp.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: <789F9655DD1B8F43B48D77C5D30659731E84D241@shsmsx501.ccr.corp.intel.com> Content-Disposition: inline List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Jun Nakajima , Liping Ke , Xin Li Cc: xen-devel@lists.xensource.com, Keir Fraser List-Id: xen-devel@lists.xenproject.org >>> On 04.06.10 at 04:57, "Ke, Liping" wrote: > This is a small patch for adding cpu feature mask feature for=20 > NHMs. This patch has been tested under several types of CPUs. This isn't fully consistent with the just released documentation: - for model 0x17, you reject steppings below 4 (doc says all steppings = qualify) - for model 0x1a, you reject steppings up to 2 (doc says all steppings = qualify) - you don't allow model 0x1f at all (doc says it qualifies) In a patch I'll submit (presumably) later today I'll leave the stepping handling as is, but include model 0x1f as per the documentation. It would be nice if you could clarify matters. Thanks, Jan