Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751494AbcLDNJD (ORCPT ); Sun, 4 Dec 2016 08:09:03 -0500 Received: from gateway22.websitewelcome.com ([192.185.46.131]:56337 "EHLO gateway22.websitewelcome.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751223AbcLDNJC (ORCPT ); Sun, 4 Dec 2016 08:09:02 -0500 Message-ID: <9e62994cb4086557b3d1199111d1cf26.squirrel@webmail.raithlin.com> In-Reply-To: References: <20161123215510.GA16311@obsidianresearch.com> <91d28749-bc64-622f-56a1-26c00e6b462a@deltatee.com> <20161124164249.GD20818@obsidianresearch.com> <3f2d2db3-fb75-2422-2a18-a8497fd5d70e@amd.com> <20161125193252.GC16504@obsidianresearch.com> <20161128165751.GB28381@obsidianresearch.com> <1480357179.19407.13.camel@mellanox.com> <20161128190244.GA21975@obsidianresearch.com> <20161130162353.GA24639@obsidianresearch.com> <5f5b7989-84f5-737e-47c8-831f752d6280@deltatee.com> Date: Sun, 4 Dec 2016 07:06:49 -0600 Subject: Re: Enabling peer to peer device transactions for PCIe devices From: "Stephen Bates" To: "Haggai Eran" Cc: "Logan Gunthorpe" , "Jason Gunthorpe" , "linux-kernel@vger.kernel.org" , "linux-rdma@vger.kernel.org" , "linux-nvdimm@ml01.01.org" , "christian.koenig@amd.com" , "Suravee.Suthikulpanit@amd.com" , "John.Bridgman@amd.com" , "Alexander.Deucher@amd.com" , "Linux-media@vger.kernel.org" , "dan.j.williams@intel.com" , "dri-devel@lists.freedesktop.org" , "Max Gurtovoy" , "linux-pci@vger.kernel.org" , "serguei.sagalovitch@amd.com" , "Paul.Blinzer@amd.com" , "Felix.Kuehling@amd.com" , "ben.sander@amd.com" User-Agent: SquirrelMail/1.5.2 [SVN] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - estate.websitewelcome.com X-AntiAbuse: Original Domain - vger.kernel.org X-AntiAbuse: Originator/Caller UID/GID - [1547 32008] / [47 12] X-AntiAbuse: Sender Address Domain - raithlin.com X-BWhitelist: no X-Source-IP: X-Exim-ID: 1cDWVF-0005Gt-37 X-Source: X-Source-Args: /usr/local/cpanel/3rdparty/php/54/bin/php-cgi /usr/local/cpanel/base/3rdparty/squirrelmail/src/compose.php X-Source-Dir: /usr/local/cpanel/base/3rdparty/squirrelmail/src X-Source-Sender: X-Source-Auth: raithlin X-Email-Count: 16 X-Source-Cap: cmFpdGhsaW47c2NvdHQ7ZXN0YXRlLndlYnNpdGV3ZWxjb21lLmNvbQ== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 612 Lines: 14 >> >> The NVMe fabrics stuff could probably make use of this. It's an >> in-kernel system to allow remote access to an NVMe device over RDMA. So >> they ought to be able to optimize their transfers by DMAing directly to >> the NVMe's CMB -- no userspace interface would be required but there >> would need some kernel infrastructure. > > Yes, that's what I was thinking. The NVMe/f driver needs to map the CMB > for RDMA. I guess if it used ZONE_DEVICE like in the iopmem patches it > would be relatively easy to do. > Haggai, yes that was one of the use cases we considered when we put together the patchset.