From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754243AbbIMRsD (ORCPT ); Sun, 13 Sep 2015 13:48:03 -0400 Received: from smtp.citrix.com ([66.165.176.89]:23985 "EHLO SMTP.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750761AbbIMRrp (ORCPT ); Sun, 13 Sep 2015 13:47:45 -0400 X-IronPort-AV: E=Sophos;i="5.17,523,1437436800"; d="scan'208";a="299728417" Subject: Re: [Xen-devel] [PATCH 0/2] block/xen-blkfront: Support non-indirect with 64KB page granularity To: Bob Liu References: <1441999920-3639-1-git-send-email-julien.grall@citrix.com> <55F3F460.7000702@oracle.com> <55F566DC.7080804@citrix.com> <55F56FC7.4050600@oracle.com> CC: , , , , "David Vrabel" , Boris Ostrovsky , =?UTF-8?Q?Roger_Pau_Monn=c3=a9?= From: Julien Grall Message-ID: <55F5B6BD.4030904@citrix.com> Date: Sun, 13 Sep 2015 18:47:41 +0100 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:38.0) Gecko/20100101 Thunderbird/38.2.0 MIME-Version: 1.0 In-Reply-To: <55F56FC7.4050600@oracle.com> Content-Type: text/plain; charset="utf-8"; format=flowed Content-Transfer-Encoding: 7bit X-DLP: MIA2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 13/09/2015 13:44, Bob Liu wrote: > I may misunderstood here. > But I think same changes are also required even if backend supports indirect grant when frontend is using 64KB page granularity. > Else > 1) How to set up the grant map for requests in domU? > The minimum segment buffer size in a request is PAGE_SIZE(64KB) while grant is 4KB based. > > 2) Codes like below in blkback.c may not work correctly? > if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) || > > Because PAGE_SIZE in backend is 4KB, while the written value by domU is 64KB based. As mention in my cover letter, this patch is not self-sufficient to support 64KB guest. It's a follow-up of the 64KB page granularity support I sent on the ML (the new version was sent earlier this week [1]). One of the patch [2] is taking care of breaking down the I/O request in multiple 4KB segment that will be used in the ring request. You may want to give a look to this patch before looking to this series. Regards, [1] https://lwn.net/Articles/656797/ [2] http://www.spinics.net/lists/arm-kernel/msg430468.html -- Julien Grall