From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp1.linuxfoundation.org (smtp1.linux-foundation.org [172.17.192.35]) by mail.linuxfoundation.org (Postfix) with ESMTPS id 56A8CFE7 for ; Sat, 22 Sep 2018 13:34:38 +0000 (UTC) Received: from mail-ed1-f67.google.com (mail-ed1-f67.google.com [209.85.208.67]) by smtp1.linuxfoundation.org (Postfix) with ESMTPS id 82E59A8 for ; Sat, 22 Sep 2018 13:34:37 +0000 (UTC) Received: by mail-ed1-f67.google.com with SMTP id a20-v6so12850100edd.4 for ; Sat, 22 Sep 2018 06:34:37 -0700 (PDT) Date: Sat, 22 Sep 2018 15:34:27 +0200 From: Andrea Parri To: ksummit-discuss@lists.linuxfoundation.org Message-ID: <20180922133427.GA3998@andrea> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Cc: "Paul E. McKenney" Subject: [Ksummit-discuss] [TECH TOPIC] Concurrency with tools/memory-model/ List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hi all, Paul E. McKenney and myself would like to propose the following topic for the technical track. --- Concurrency is "tricky", it has been said, due to numerous optimizations implemented in today's multiprocessors and by the compiler. Traditionally, developers have relied on informal documentation such as memory-barriers.txt to avoid the "pitfalls of concurrency". However, this doesn't always happen right: this documentation is subject of misinterpretations, incomplete, and yet all but concise! This talk will go over a new approach to study concurrency issues in the kernel using the Linux-kernel memory consistency model [1]. What can this model do? and, most importantly, how can it be used? This hands-on talk aims at addressing these questions. [1] 1c27b644c0fdbc ("Automate memory-barriers.txt; provide Linux-kernel memory model") --- Thanks, Andrea