From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755277Ab1KAAfU (ORCPT ); Mon, 31 Oct 2011 20:35:20 -0400 Received: from e8.ny.us.ibm.com ([32.97.182.138]:49102 "EHLO e8.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752650Ab1KAAfS (ORCPT ); Mon, 31 Oct 2011 20:35:18 -0400 Date: Mon, 31 Oct 2011 17:34:34 -0700 From: "Paul E. McKenney" To: Steven Rostedt Cc: Wu Fengguang , "linux-kernel@vger.kernel.org" , Ingo Molnar , Lai Jiangshan , Frederic Weisbecker , Carsten Emde Subject: Re: linux-next 20111025: warnings in rcu_idle_exit_common()/rcu_idle_enter_common() Message-ID: <20111101003434.GR6160@linux.vnet.ibm.com> Reply-To: paulmck@linux.vnet.ibm.com References: <20111031082634.GA10348@localhost> <20111031095152.GL6160@linux.vnet.ibm.com> <20111031104325.GA25808@localhost> <20111031114142.GA32555@localhost> <20111031121951.GM6160@linux.vnet.ibm.com> <1320075882.4793.4.camel@gandalf.stny.rr.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1320075882.4793.4.camel@gandalf.stny.rr.com> User-Agent: Mutt/1.5.20 (2009-06-14) x-cbid: 11110100-9360-0000-0000-000000365FE8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Oct 31, 2011 at 11:44:42AM -0400, Steven Rostedt wrote: > On Mon, 2011-10-31 at 05:19 -0700, Paul E. McKenney wrote: > > On Mon, Oct 31, 2011 at 07:41:42PM +0800, Wu Fengguang wrote: > > > On Mon, Oct 31, 2011 at 06:43:25PM +0800, Wu Fengguang wrote: > > > > On Mon, Oct 31, 2011 at 05:51:52PM +0800, Paul E. McKenney wrote: > > > > > On Mon, Oct 31, 2011 at 04:26:34PM +0800, Wu Fengguang wrote: > > > > > > Hi Paul, > > > > > > > > > > > > I got two warnings in rcutree.c. The last working kernels are > > > > > > linux-next 20111014 and linux v3.1. > > > > > > > > > > Interesting. Could you please enable RCU event tracing at boot? > > > > > > > > Sorry I cannot...possibly due to another ftrace bug. > > > > > > > > > The RCU event tracing is at tracing/events/rcu/enable relative to > > > > > the debugfs mount point at runtime, if that helps. > > > > > > > > It's exactly that linux next 20111025 (comparing to 20111014) no > > > > longer produces all the trace events that made me looking into the > > > > dmesg and find the warning from RCU (rather than the expected warning > > > > from ftrace). > > > > > > > > The trace output is now: > > > > > > > > # tracer: nop > > > > # > > > > # WARNING: FUNCTION TRACING IS CORRUPTED > > > > # MAY BE MISSING FUNCTION EVENTS > > > > # TASK-PID CPU# TIMESTAMP FUNCTION > > > > # | | | | | > > > > (nothing more) > > > > > > I checked the other test box and got the same warnings. Below is the > > > full dmesg. > > > > > > No single trace output again.. > > > > Hmmm... I wonder if it is too early during boot for tracing to work > > correctly. > > > > Gah! I have rcu/next set ahead to commits that are not supposed to go > > upstream yet. I reset it back to match the stuff that is targeted for > > the current merge window. Still need to find the bug, of course. > > > > Anyone have any idea why the kworker thread might be trying to enter > > the idle loop? The idle_cpu(smp_processor_id()) call believes that > > this is not the idle task. Or does x86 allow non-idle tasks to enter > > the idle loop? Or to be migrated off-CPU? > > > It's not. Carsten Emde noticed what looked like a bug in ftrace last > week at LinuxCon, and looking deeper at it, I found that the swapper > task for all but CPU0 is named kworker. That's because kworker creates > the idle task for all other CPUs besides CPU 0 and the idle task takes > on kworker name. > > Carsten posted a patch last week too: > > https://lkml.org/lkml/2011/10/26/313 > > I'm glad that this bug shows up outside of just ftrace :) That makes one of us. ;-) Fengguang, does Carsten's patch help? Thanx, Paul