From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752696Ab1FHT6V (ORCPT ); Wed, 8 Jun 2011 15:58:21 -0400 Received: from e3.ny.us.ibm.com ([32.97.182.143]:45344 "EHLO e3.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751500Ab1FHT6U (ORCPT ); Wed, 8 Jun 2011 15:58:20 -0400 Date: Wed, 8 Jun 2011 12:58:16 -0700 From: "Paul E. McKenney" To: Peter Zijlstra Cc: Frederic Weisbecker , LKML , Ingo Molnar Subject: Re: [PATCH 2/4] sched: Isolate preempt counting in its own config option Message-ID: <20110608195816.GJ2324@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <1307555315-30989-1-git-send-email-fweisbec@gmail.com> <1307555315-30989-3-git-send-email-fweisbec@gmail.com> <1307562434.3941.22.camel@twins> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1307562434.3941.22.camel@twins> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Jun 08, 2011 at 09:47:14PM +0200, Peter Zijlstra wrote: > On Wed, 2011-06-08 at 19:48 +0200, Frederic Weisbecker wrote: > > > > Create a new CONFIG_PREEMPT_COUNT that handles the inc/dec > > of preempt count offset independently. So that the offset > > can be updated by preempt_disable() and preempt_enable() > > even without the need for CONFIG_PREEMPT beeing set. > > > > This prepares to make CONFIG_DEBUG_SPINLOCK_SLEEP working > > with !CONFIG_PREEMPT where it currently doesn't detect > > code that sleeps inside explicit preemption disabled > > sections. > > The last time this got proposed it got shot down due to the extra > inc/dec stuff all over the place increasing overhead significantly. Even given that the extra inc/dec stuff only happens in kernels built with DEBUG_SPINLOCK_SLEEP=y (DEBUG_ATOMIC_SLEEP=y after patch 4/4)? Thanx, Paul