From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752430AbeENVFI (ORCPT ); Mon, 14 May 2018 17:05:08 -0400 Received: from mail-wm0-f68.google.com ([74.125.82.68]:34770 "EHLO mail-wm0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752650AbeENVEO (ORCPT ); Mon, 14 May 2018 17:04:14 -0400 X-Google-Smtp-Source: AB8JxZqHuWIUxRtFxQKpQV8cUgKzBOtJzMo8FwfcuPV3XdPcHcNgpLgnSlk8BJWj+rcVFzL3pt10ig== Date: Mon, 14 May 2018 15:04:08 -0600 From: Jason Gunthorpe To: =?utf-8?B?SMOla29u?= Bugge Cc: Hal Rosenstock , Doug Ledford , Don Hiatt , Ira Weiny , Sean Hefty , OFED mailing list , linux-kernel@vger.kernel.org Subject: Re: [PATCH IB/core 2/2] IB/cm: Send authentic pkey in REQ msg and check eligibility of the pkeys Message-ID: <20180514210408.GO21531@ziepe.ca> References: <20180509093020.24503-1-Haakon.Bugge@oracle.com> <20180509093020.24503-3-Haakon.Bugge@oracle.com> <3bee76df-49a6-cf3c-6df4-749a6309358e@dev.mellanox.co.il> <325ba4af-b52e-4f70-9d89-38dafe10ba99@dev.mellanox.co.il> <23B160D2-6631-42A6-8A4D-644E90E8A704@oracle.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <23B160D2-6631-42A6-8A4D-644E90E8A704@oracle.com> User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, May 11, 2018 at 12:55:00PM +0200, Håkon Bugge wrote: > > I'll check upstream OpenSM when I get a chance to see if same problem > > exists. Oracle OpenSM forked from upstream long time ago and not sure > > how similar the path record code is. There were various impacts for the > > shared port virtualization (for CX-3) in terms of adding the ability to > > allow both pkeys. > > I just had a chat with Line H. here in Oracle. She confirms that Oracle’s SM and the upstream one act similar in this matter. > > Further, using shared port virtualization, OpenSM will adhere to the > physical ports only, and doesn’t even know the PKey assignments to > the VFs assigned the VMs. Yes, but that isn't the point. If the VM receives a PR with a pkey that is not found in the VM's table then it should not even send a CM REQ in the first place. Jason