Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964894AbVLIW7X (ORCPT ); Fri, 9 Dec 2005 17:59:23 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S964896AbVLIW7X (ORCPT ); Fri, 9 Dec 2005 17:59:23 -0500 Received: from ns.suse.de ([195.135.220.2]:13441 "EHLO mx1.suse.de") by vger.kernel.org with ESMTP id S964894AbVLIW7W (ORCPT ); Fri, 9 Dec 2005 17:59:22 -0500 Date: Fri, 9 Dec 2005 23:59:21 +0100 From: Andi Kleen To: Rohit Seth Cc: Ravikiran G Thirumalai , Andi Kleen , Andrew Morton , linux-kernel@vger.kernel.org, discuss@x86-64.org, zach@vmware.com, shai@scalex86.org, nippung@calsoftinc.com Subject: Re: [discuss] [patch] x86_64: align and pad x86_64 GDT on page boundary Message-ID: <20051209225921.GO11190@wotan.suse.de> References: <20051208215514.GE3776@localhost.localdomain> <1134083357.7131.21.camel@akash.sc.intel.com> <20051208231141.GX11190@wotan.suse.de> <1134084367.7131.32.camel@akash.sc.intel.com> <20051208232610.GY11190@wotan.suse.de> <1134085511.7131.53.camel@akash.sc.intel.com> <20051208234320.GB11190@wotan.suse.de> <20051209221922.GA3676@localhost.localdomain> <1134169287.21462.7.camel@akash.sc.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1134169287.21462.7.camel@akash.sc.intel.com> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1115 Lines: 29 On Fri, Dec 09, 2005 at 03:01:27PM -0800, Rohit Seth wrote: > > > For the BP case it's ok as > > > long as the beginning is correctly aligned and the rest > > > is read-only. > > > > Just that any writes on the bp GDT will invalidate the idt_table cacheline, > > which is read mostly (as Nippun pointed out). So could we keep the padding > > as it is for the BP too? > > > > Do you write into GDT often for this to be an issue. The reason I'm The context switch writes into the GDT to switch around the TLS segments when they are <4GB. Or in pre NPTL the same would be done for the LDT also used for TLS. > asking this because the per-cpu IDTs that Andi refered in the future. > If we are really not using too many bytes in GDT then rest of the page > can be used for IDT and such mostly RO data. Once I implement that it can be shared with that page. -Andi - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/