Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S264713AbTIDGGJ (ORCPT ); Thu, 4 Sep 2003 02:06:09 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S264718AbTIDGGJ (ORCPT ); Thu, 4 Sep 2003 02:06:09 -0400 Received: from magic-mail.adaptec.com ([216.52.22.10]:13256 "EHLO magic.adaptec.com") by vger.kernel.org with ESMTP id S264713AbTIDGGG (ORCPT ); Thu, 4 Sep 2003 02:06:06 -0400 Date: Wed, 3 Sep 2003 23:33:46 +0530 (IST) From: Nagendra Singh Tomar X-X-Sender: tomar@localhost.localdomain Reply-To: nagendra_tomar@adaptec.com To: Davide Libenzi cc: "Tomar, Nagendra" , Jamie Lokier , Geert Uytterhoeven , Roman Zippel , Kars de Jong , Linux/m68k kernel mailing list , Linux Kernel Development Subject: Re: x86, ARM, PARISC, PPC, MIPS and Sparc folks please run this In-Reply-To: Message-ID: Organization: Adaptec MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1280 Lines: 42 On Thu, 4 Sep 2003, Davide Libenzi wrote: > On Wed, 3 Sep 2003, Nagendra Singh Tomar wrote: > > > Jamie, > > Just wondered if the store buffer is snooped in some > > architectures. In that case I believe the OS need not do anything for > > serialization (except for aliases, if they do not hit the same cache > line). > > In x86 store buffer is not snooped which leads to all these > serialization > > issues (other CPUs looking at stale value of data which is in the > store > > buffer of some other CPU). > > Pl correct me if I have got anything wrong/ > > To avoid the so called 'load hazard' (that, BTW, triggers read over > writes, that are not allowed in x86) you have two options. Snoop the > write > buffer or flush it upon L1 miss. Otherwise you might end up getting > stale > data from L2. > I meant to ask if the store buffer is snooped by *other CPUs*. To maintain self coherence the local store buffer has to be anyway consulted by local loads to give the latest stored value. Thanx, tomar > > > - Davide > - 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/