From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756884AbbAZUeV (ORCPT ); Mon, 26 Jan 2015 15:34:21 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:44624 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755922AbbAZUeT (ORCPT ); Mon, 26 Jan 2015 15:34:19 -0500 Date: Mon, 26 Jan 2015 12:27:25 -0800 From: Greg Kroah-Hartman To: Sudeep Dutt Cc: Arnd Bergmann , Jonathan Corbet , linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, Dave Jiang , Nikhil Rao , Ashutosh Dixit Subject: Re: [PATCH char-misc-next v2 00/13] misc: mic: SCIF driver Message-ID: <20150126202725.GA24523@kroah.com> References: <20150125124429.GC21763@kroah.com> <1422295627.9362.173.camel@rbtaylor-desk1.amr.corp.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1422295627.9362.173.camel@rbtaylor-desk1.amr.corp.intel.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jan 26, 2015 at 10:07:07AM -0800, Sudeep Dutt wrote: > On Sun, 2015-01-25 at 20:44 +0800, Greg Kroah-Hartman wrote: > > On Mon, Jan 12, 2015 at 03:09:54PM -0800, Sudeep Dutt wrote: > > > ChangeLog: > > > ========= > > > v1 => v2: > > > a) Use kernel-doc formatting for SCIF header file documentation, enhance > > > SCIF ring buffer documentation and formatting cleanup in patch 4 as > > > per feedback from Greg Kroah-Hartman > > > b) SCIF bug fixes and cleanups since initial post > > > > > > v1: Initial post @ https://lkml.org/lkml/2014/12/10/546 > > > > Do you have any test code that can be added to the tree to exercise this > > api and at least give a hint as to how it all works from the userspace > > side? You don't have any pointers to any userspace code, what is using > > this API? > > > > SCIF has been used to implement an ICC offload compiler runtime in user > space. We will be submitting a kernel client as well if this initial > patch series is accepted upstream. SCIF has a user space library which > is a thin IOCTL wrapper providing a user space API similar to the kernel > API in scif.h. The SCIF user space library is distributed separately via > https://software.intel.com/en-us/mic-developer > > Here is some SCIF pseudo code as an example: > > Process A (on host) Process B (on MIC Coprocessor) > > scif_open(..) scif_open(..) > scif_bind(..) scif_bind(..) > scif_listen(..) > scif_accept(..) scif_connect(..) > /* SCIF connection established */ > > /* Send and receive control messages */ > scif_send(..)/scif_recv(..) scif_send(..)/scif_recv(..) > > /* Register memory */ > scif_register(..) scif_register(..) > > /* RDMA */ > scif_readfrom(..)/scif_writeto(..) scif_readfrom(..)/scif_writeto(..) > > mmap(..) mmap(..) > /* Access remote registered memory */ > > /* Close the endpoints */ > scif_close(..) scif_close(..) Document this somewhere in your submission so that people know where to look for userspace stuff. > The user space code has been distributed and maintained separately from > the kernel so we did not include it as part of this patch series to > avoid bloating the kernel. Do you think we should include the user space > SCIF library and some sample user space test applications under > Documentation/mic with this patch series? sample test applications are always good, if they work on their own without requiring the library. I wouldn't put the whole library in the kernel tree unless you feel it is needed there. thanks, greg k-h