From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752310AbaBJPg5 (ORCPT ); Mon, 10 Feb 2014 10:36:57 -0500 Received: from hofr.at ([212.69.189.236]:43821 "EHLO mail.hofr.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751371AbaBJPgz (ORCPT ); Mon, 10 Feb 2014 10:36:55 -0500 Date: Mon, 10 Feb 2014 16:36:53 +0100 From: Nicholas Mc Guire To: linux-rt-users@vger.kernel.org Cc: LKML , Sebastian Andrzej Siewior , Steven Rostedt , Peter Zijlstra , Carsten Emde , Thomas Gleixner , Andreas Platschek Subject: [PATCH RT 0/5] preempt_disable/enable -> migrate_disable/enable pushdown proposals Message-ID: <20140210153653.GA20017@opentech.at> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org a small series of preempt_disable/enable -> migrate_disable/enable pushdown proposals In mainline a number of preempt_disable/enable are actually topology control and not actual concurrency control - these cases can be pushed down to a preemptible migrate_disable/enable. This little series contains a few pushdowns from preempt_disable to migrate_disable where code pattern scans using cocci scripts suggested this to be possible. The cases detected were then reviewed and tested with the migrate_disable/enable respectively with the preempt_disable/enable completely removed in one case. Testing was done but is of very limited use for locking/migration related issues, so a review of the code analysis/rational is requested along with additional testing. thx! hofrat