From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751839AbdITPEP (ORCPT ); Wed, 20 Sep 2017 11:04:15 -0400 Received: from smtp.codeaurora.org ([198.145.29.96]:46984 "EHLO smtp.codeaurora.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751785AbdITPEM (ORCPT ); Wed, 20 Sep 2017 11:04:12 -0400 DMARC-Filter: OpenDMARC Filter v1.3.2 smtp.codeaurora.org 4A1CD60117 Authentication-Results: pdx-caf-mail.web.codeaurora.org; dmarc=none (p=none dis=none) header.from=codeaurora.org Authentication-Results: pdx-caf-mail.web.codeaurora.org; spf=none smtp.mailfrom=okaya@codeaurora.org Subject: Re: [PATCH] vfio/pci: Virtualize Maximum Payload Size To: Auger Eric , Alex Williamson Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org, jcm@redhat.com, "linux-pci@vger.kernel.org" References: <20170919164952.13200.78849.stgit@gimli.home> <20170919142024.05723289@t450s.home> <3dd92928-3cda-50c1-6a67-10721c003c10@redhat.com> <73d55003-6fcd-3741-73a1-365c73933538@redhat.com> From: Sinan Kaya Message-ID: <97d4a49c-4864-42eb-7385-03747309ae55@codeaurora.org> Date: Wed, 20 Sep 2017 11:04:10 -0400 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.3.0 MIME-Version: 1.0 In-Reply-To: <73d55003-6fcd-3741-73a1-365c73933538@redhat.com> Content-Type: text/plain; charset=windows-1252 Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 9/20/2017 10:26 AM, Auger Eric wrote: >> Because completions are required to be a minimum of MPS size. If MRRS > MPS, >> read response is sent as multiple completions. > With that patch, you can end up with MRRS < MPS. Do I understand > correctly this is an issue? To give the right context, I tried to mean that you can't use MRRS as a length value for completions if MRRS is a fairly large number and bigger than MPS. Therefore, a single completion packet size needs to be less than MRRS and cannot exceed MPS. Spec is even calling for receivers to throw an error if completion length is greater than MPS. single completion <= MPS (128) <= MRRS (4k) I looked at the spec again. I have not seen anything in the spec that prohibits MRRS < MPS as long as completion size is less than MPS. single completion <= MRRS (128) < MPS (256) I think this is also valid. I hope I got it right this time. -- Sinan Kaya Qualcomm Datacenter Technologies, Inc. as an affiliate of Qualcomm Technologies, Inc. Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.