From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755297AbXGIKMn (ORCPT ); Mon, 9 Jul 2007 06:12:43 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751686AbXGIKMg (ORCPT ); Mon, 9 Jul 2007 06:12:36 -0400 Received: from smtp102.mail.mud.yahoo.com ([209.191.85.212]:39720 "HELO smtp102.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751315AbXGIKMf (ORCPT ); Mon, 9 Jul 2007 06:12:35 -0400 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com.au; h=Received:X-YMail-OSG:Message-ID:Date:From:User-Agent:X-Accept-Language:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=fXA9oXSs/RK7RS8M+zVhfNG6jNTwlyoTm8l1I1C3KbyRXdvQ8ZRet3S5S3whC8l72lqCZEnw4/QgxCE1J1rtzx3fZdGxDG8SqUVz9rqZDGSI0zwI2PoJYT2t4+MfOBGFES5Qve5fklNGbJ1fW7R5FgUVP3U/l9vb5hyUMk204jw= ; X-YMail-OSG: 3gcGUIsVM1kwz9YjmytmAq4B5.uwq3pfgwukJ3RnFjEJ5QhyaqQwp4fPFFW.4AI5NBavs1uXZg-- Message-ID: <46920A0C.3040400@yahoo.com.au> Date: Mon, 09 Jul 2007 20:12:28 +1000 From: Nick Piggin User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.12) Gecko/20051007 Debian/1.7.12-1 X-Accept-Language: en MIME-Version: 1.0 To: Benjamin Herrenschmidt CC: linux-mm@kvack.org, Linux Kernel list Subject: Re: [RFC/PATCH] Use mmu_gather for fork() instead of flush_tlb_mm() References: <1183952874.3388.349.camel@localhost.localdomain> <1183962981.5961.3.camel@localhost.localdomain> <1183963544.5961.6.camel@localhost.localdomain> <4691E64F.5070506@yahoo.com.au> <1183972349.5961.25.camel@localhost.localdomain> <4691FFDC.5020808@yahoo.com.au> <1183974458.5961.42.camel@localhost.localdomain> In-Reply-To: <1183974458.5961.42.camel@localhost.localdomain> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Benjamin Herrenschmidt wrote: > On Mon, 2007-07-09 at 19:29 +1000, Nick Piggin wrote: > >>They could just #define one to the other though, there are only a >>small >>number of them. Is there a downside to not making them distinct? i386 >>for example probably would just keep doing a tlb flush for fork and >>not >>want to worry about touching the tlb gather stuff. > > > But the tlb gather stuff just does ... a flush_tlb_mm() on x86 :-) But it still does the get_cpu of the mmu gather data structure and has to look in there and touch the cacheline. You're also having to do more work when unlocking/relocking the ptl etc. > I really think it's the right API -- SUSE Labs, Novell Inc.