From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753442AbYHWFwP (ORCPT ); Sat, 23 Aug 2008 01:52:15 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751678AbYHWFwH (ORCPT ); Sat, 23 Aug 2008 01:52:07 -0400 Received: from rv-out-0506.google.com ([209.85.198.230]:51964 "EHLO rv-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751500AbYHWFwG (ORCPT ); Sat, 23 Aug 2008 01:52:06 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=message-id:date:from:to:subject:cc:in-reply-to:mime-version :content-type:content-transfer-encoding:content-disposition :references; b=vyp8NCLy+46x4WQJFp5KMjRHDkb5DlcDRfpd8nDdIa2k8N6xR1x0jBj9EXhP103r0d yPoo+zoqFeI7+cLmzCC+EA4VJxeIcTDFEq7vF5DUpOfT6bROp/BT6kQ8IlwRlVIf0IvM Uh0E5L7VYU3rX0kSE1HXzzaTfEtGJklVMUwwc= Message-ID: <86802c440808222252j6f900f1dlfbf1378a7bc35ee4@mail.gmail.com> Date: Fri, 22 Aug 2008 22:52:05 -0700 From: "Yinghai Lu" To: "Joshua Hoblitt" Subject: Re: [Bug 11388] New: 2.6.27-rc3 warns about MTRR range; only 3 of 16gb of memory is usable Cc: "Ingo Molnar" , "Andrew Morton" , bugme-daemon@bugzilla.kernel.org, linux-kernel@vger.kernel.org In-Reply-To: <20080823002235.GL23377@hoblitt.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20080822002952.GG23377@hoblitt.com> <20080822011055.GI23377@hoblitt.com> <86802c440808211855h50ea65faudc169e48f83e18e2@mail.gmail.com> <20080822021512.GJ23377@hoblitt.com> <86802c440808211926k1ec5b2a2g2bec1b7faee7ebbb@mail.gmail.com> <86802c440808212024v3ccd2a7ey6517c180464275f0@mail.gmail.com> <20080822035024.GB30284@elte.hu> <20080822035609.GD30284@elte.hu> <86802c440808212148k74e56fa2mdb2e329ed4df1271@mail.gmail.com> <20080823002235.GL23377@hoblitt.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Aug 22, 2008 at 5:22 PM, Joshua Hoblitt wrote: > I've confirmed that the boards in these systems are Tyan Tempest i5400PW > (S5397)s. We've discovered a workload that will deadlock the system > under both 2.6.24.2 and -tip kernel with the mtrr masking patch. The > only thing unusual about this workload is that one of the binaries in > it constantly segvs... Is it possible that these deadlocks (no kernel > oops on console) are caused by MSR setup wierdness or is it likely unrelated? could be other problem. cpu should be smarter enough to understand the missing bits in mask. at least amd cpu. remember that we didn't set mask bits to 40bits with opteron with LinuxBIOS, and everything still works well. YH