From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753391AbaE0SiU (ORCPT ); Tue, 27 May 2014 14:38:20 -0400 Received: from mail-pa0-f42.google.com ([209.85.220.42]:46174 "EHLO mail-pa0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753237AbaE0SiR (ORCPT ); Tue, 27 May 2014 14:38:17 -0400 Message-ID: <5384DB97.70606@kernel.dk> Date: Tue, 27 May 2014 12:38:15 -0600 From: Jens Axboe User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.4.0 MIME-Version: 1.0 To: Christoph Hellwig , Ming Lei CC: Linux Kernel Mailing List , stable Subject: Re: [PATCH] block: mq flush: fix race between IPI handler and mq flush worker References: <1400511950-18522-1-git-send-email-tom.leiming@gmail.com> <20140519151824.GA21762@lst.de> <20140520152303.GA20352@lst.de> <20140521053634.GA4764@lst.de> <20140527181305.GA7975@lst.de> In-Reply-To: <20140527181305.GA7975@lst.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 2014-05-27 12:13, Christoph Hellwig wrote: > Here is my counter proposal that requeues via two lists and a work struct > in the request_queue. I've also tested it with scsi-mq. > I like this, moves the state out of the request. But how about we consolidate the two requeue requests lists, and just mark the request as needing head insertion instead? Just add a cmd_flags flag, REQ_REQUEUE_HEAD or something. -- Jens Axboe