Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761922AbYBEUzn (ORCPT ); Tue, 5 Feb 2008 15:55:43 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1761503AbYBEUze (ORCPT ); Tue, 5 Feb 2008 15:55:34 -0500 Received: from host36-195-149-62.serverdedicati.aruba.it ([62.149.195.36]:41426 "EHLO mx.cpushare.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1761482AbYBEUzc (ORCPT ); Tue, 5 Feb 2008 15:55:32 -0500 Date: Tue, 5 Feb 2008 21:55:19 +0100 From: Andrea Arcangeli To: Christoph Lameter Cc: Robin Holt , Avi Kivity , Izik Eidus , kvm-devel@lists.sourceforge.net, Peter Zijlstra , steiner@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, daniel.blueman@quadrics.com Subject: Re: [PATCH] mmu notifiers #v5 Message-ID: <20080205205519.GF7441@v2.random> References: <20080131234101.GS7185@v2.random> <20080201120955.GX7185@v2.random> <20080203021704.GC7185@v2.random> <20080205052525.GD7441@v2.random> <20080205180802.GE7441@v2.random> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1540 Lines: 31 On Tue, Feb 05, 2008 at 10:17:41AM -0800, Christoph Lameter wrote: > The other approach will not have any remote ptes at that point. Why would > there be a coherency issue? It never happens that two threads writes to two different physical pages by working on the same process virtual address. This is an issue only for KVM which is probably ok with it but certainly you can't consider the dependency on the page-pin less fragile or less complex than my PT lock approach. > No. It only has to lock the affected range. Remote page faults can occur > while another part of the address space is being invalidated. The > complexity of locking is up to the user of the mmu notifier. A simple > implementation is satisfactory for the GRU right now. Should it become a > problem then the lock granularity can be refined without changing the API. That will make the follow_page fast path even slower if it has to lookup a rbtree or a list of locked ranges. Still not comparable to the PT lock that 1) it's zero cost and 2) it'll provide an even more granular scalability. > Still not sure what we are talking about here. The apps using GRU/KVM never trigger large munmap/mremap/do_exit. You're optimizing for the irrelevant workload, by requiring unnecessary new locking in the GRU fast path. -- 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/