linux-kernel - Re: [PATCH char-misc-next v2 00/13] misc: mic: SCIF driver

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Mon, 26 Jan 2015 12:27:25 -0800
From:	Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:	Sudeep Dutt <sudeep.dutt@...el.com>
Cc:	Arnd Bergmann <arnd@...db.de>, Jonathan Corbet <corbet@....net>,
	linux-kernel@...r.kernel.org, linux-doc@...r.kernel.org,
	Dave Jiang <dave.jiang@...el.com>,
	Nikhil Rao <nikhil.rao@...el.com>,
	Ashutosh Dixit <ashutosh.dixit@...el.com>
Subject: Re: [PATCH char-misc-next v2 00/13] misc: mic: SCIF driver

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
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/