From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751939Ab1L0WHn (ORCPT ); Tue, 27 Dec 2011 17:07:43 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:54161 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750768Ab1L0WHk (ORCPT ); Tue, 27 Dec 2011 17:07:40 -0500 Date: Tue, 27 Dec 2011 14:07:38 -0800 From: Andrew Morton To: Jens Axboe Cc: Tejun Heo , Stephen Rothwell , linux-next@vger.kernel.org, LKML , linux-scsi@vger.kernel.org, linux-ide@vger.kernel.org, Hugh Dickins , x86@kernel.org Subject: Re: [PATCH block/for-3.3/core] block: an exiting task should be allowed to create io_context Message-Id: <20111227140738.c9eedb7c.akpm@linux-foundation.org> In-Reply-To: <4EF7253E.3070606@kernel.dk> References: <20111221174733.9ba0861e762e8d96844b060b@canb.auug.org.au> <20111221151503.4d78f94f.akpm@linux-foundation.org> <20111222150836.af172886.akpm@linux-foundation.org> <20111222232036.GP17084@google.com> <20111222152427.c944c747.akpm@linux-foundation.org> <20111222233843.GR17084@google.com> <20111222154427.89b245c7.akpm@linux-foundation.org> <20111222234639.GS17084@google.com> <20111223004244.GU17084@google.com> <20111225010238.GA6013@htj.dyndns.org> <4EF7253E.3070606@kernel.dk> X-Mailer: Sylpheed 3.0.2 (GTK+ 2.20.1; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sun, 25 Dec 2011 14:29:34 +0100 Jens Axboe wrote: > On 2011-12-25 02:02, Tejun Heo wrote: > > While fixing io_context creation / task exit race condition, > > 6e736be7f2 "block: make ioc get/put interface more conventional and > > fix race on alloction" also prevented an exiting (%PF_EXITING) task > > from creating its own io_context. This is incorrect as exit path may > > issue IOs, e.g. from exit_files(), and if those IOs are the first ones > > issued by the task, io_context needs to be created to process the IOs. > > > > Combined with the existing problem of io_context / io_cq creation > > failure having the possibility of stalling IO, this problem results in > > deterministic full IO lockup with certain workloads. > > > > Fix it by allowing io_context creation regardless of %PF_EXITING for > > %current. The patch works for me. > Thanks, applied. So we get another great big bisection hole in mainline. I feel duty bound to rewhine about this :(