From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756426AbYGVSkr (ORCPT ); Tue, 22 Jul 2008 14:40:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754113AbYGVSkQ (ORCPT ); Tue, 22 Jul 2008 14:40:16 -0400 Received: from rv-out-0506.google.com ([209.85.198.239]:29759 "EHLO rv-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755750AbYGVSkO (ORCPT ); Tue, 22 Jul 2008 14:40:14 -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=DTBgLsU9MVVcjuIdcY4qOUng1sCvG2dH3+UHM7OfU+4zKzyjm7z0JunKI0a7r84X3q O86mJxmW2AQ8QAAxoCNsiD0pb2V+45sRccI+jWYX/8uyFXrVBv4558TYucccfYufMt+N 0IVF5RwIej+BljzeFsJFS4EFDEX7uZxYxnJj4= Message-ID: <86802c440807221140o20dcc31fjc10f86a22a1125bb@mail.gmail.com> Date: Tue, 22 Jul 2008 11:40:13 -0700 From: "Yinghai Lu" To: "Suresh Siddha" Subject: Re: [PATCH] x86: add apic probe for genapic 64bit v2 Cc: "Ingo Molnar" , "Thomas Gleixner" , "H. Peter Anvin" , "Jack Steiner" , "linux-kernel@vger.kernel.org" In-Reply-To: <20080722181056.GD14380@linux-os.sc.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <200807211836.27282.yhlu.kernel@gmail.com> <200807212208.22116.yhlu.kernel@gmail.com> <20080722175757.GC14380@linux-os.sc.intel.com> <86802c440807221105s77372df8re2e59440a8f644bd@mail.gmail.com> <20080722181056.GD14380@linux-os.sc.intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jul 22, 2008 at 11:10 AM, Suresh Siddha wrote: > On Tue, Jul 22, 2008 at 11:05:17AM -0700, Yinghai Lu wrote: >> On Tue, Jul 22, 2008 at 10:57 AM, Suresh Siddha >> wrote: >> > Yinghai, though not directly realted to this probe cleanup, what is this >> > 'max_physical_apicid' doing. >> > >> > I don't understand the need for this commit. >> > >> >> commit e0da33646826b66ef933d47ea2fb7a693fd849bf >> >> Author: Yinghai Lu >> >> Date: Sun Jun 8 18:29:22 2008 -0700 >> >> >> >> x86: introduce max_physical_apicid for bigsmp switching >> >> >> >> a multi-socket test-system with 3 or 4 ioapics, when 4 dualcore cpus or >> >> 2 quadcore cpus installed, needs to switch to bigsmp or physflat. >> >> >> >> CPU apic id is [4,11] instead of [0,7], and we need to check max apic >> >> id instead of cpu numbers. >> > >> > for logical flat, it really shouldn't matter how large the physical apic id >> > is. In logical flat, OS programs the LDR and the limitation is the >> > number of cpu's which is '8'. >> >> before i clean up 32bit, 64bit already used max_physical_apicid to >> check if need to switch to physflat. > > No. It was introduced by your commit e0da33646826b66ef933d47ea2fb7a693fd849bf > > we were using num_possible_cpus > 8 check before. yes. 64bit is changed to use max_phys_apicid at same patch > >> for 32bit, if not switch to bigsmp, cpu with physical apic id >=8 can >> not be started by BSP. > > why? could be apic mode is set to phys flat mode by BIOS. get APIC error (0x40)... that is the reason for introducing max_phys_apicid.