From mboxrd@z Thu Jan 1 00:00:00 1970 From: Nick Piggin Subject: Re: [patch 9/9] mm: fix pagecache write deadlocks Date: Sun, 4 Feb 2007 11:50:15 +0100 Message-ID: <20070204105015.GB29943@wotan.suse.de> References: <20070204063707.23659.20741.sendpatchset@linux.site> <20070204063833.23659.55105.sendpatchset@linux.site> <20070204014445.88e6c8c7.akpm@linux-foundation.org> <20070204101529.GA22004@wotan.suse.de> <20070204023055.2583fd65.akpm@linux-foundation.org> <20070204104609.GA29943@wotan.suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Linux Kernel , Linux Filesystems , Linux Memory Management To: Andrew Morton Return-path: Received: from mail.suse.de ([195.135.220.2]:56511 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752275AbXBDKuQ (ORCPT ); Sun, 4 Feb 2007 05:50:16 -0500 Content-Disposition: inline In-Reply-To: <20070204104609.GA29943@wotan.suse.de> Sender: linux-fsdevel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On Sun, Feb 04, 2007 at 11:46:09AM +0100, Nick Piggin wrote: > > > It's better than taking mmap_sem and walking pagetables... > > I'm not convinced. Though I am more convinced that looking at mm *at all* (either to take the mmap_sem and find the vma, or to take the mmap_sem and run get_user_pages) is going to hurt. We'd have to special case kernel threads, which don't even have an mm, let alone the vmas... too ugly. I'll revert to my temporary-page approach: at least that will fix the problem.