From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753649Ab2GPRDm (ORCPT ); Mon, 16 Jul 2012 13:03:42 -0400 Received: from hrndva-omtalb.mail.rr.com ([71.74.56.122]:25795 "EHLO hrndva-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752358Ab2GPRDl (ORCPT ); Mon, 16 Jul 2012 13:03:41 -0400 X-Authority-Analysis: v=2.0 cv=ZuBv2qHG c=1 sm=0 a=s5Htg7xnQOKvHEu9STBOug==:17 a=OpT9cpI26MMA:10 a=M1TwID2Q0fYA:10 a=5SG0PmZfjMsA:10 a=IkcTkHD0fZMA:10 a=meVymXHHAAAA:8 a=7RgU5aBSEs_yOgrXDLAA:9 a=QEXdDO2ut3YA:10 a=s5Htg7xnQOKvHEu9STBOug==:117 X-Cloudmark-Score: 0 X-Originating-IP: 72.230.195.127 Subject: Re: 3.4.4-rt13: btrfs + xfstests 006 = BOOM.. and a bonus rt_mutex deadlock report for absolutely free! From: Steven Rostedt To: Mike Galbraith Cc: Chris Mason , "Chris L. Mason" , "linux-rt-users@vger.kernel.org" , LKML , linux-fsdevel , Thomas Gleixner In-Reply-To: <1342456567.7659.97.camel@marge.simpson.net> References: <1342072060.7338.102.camel@marge.simpson.net> <20120713125043.GH30128@shiny> <1342260883.7368.30.camel@marge.simpson.net> <20120715175612.GF25961@shiny.int.fusionio.com> <1342404140.7659.27.camel@marge.simpson.net> <1342454547.5410.3.camel@gandalf.stny.rr.com> <1342455968.7659.93.camel@marge.simpson.net> <1342456567.7659.97.camel@marge.simpson.net> Content-Type: text/plain; charset="UTF-8" Date: Mon, 16 Jul 2012 13:03:15 -0400 Message-ID: <1342458195.2783.5.camel@acer.local.home> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 2012-07-16 at 18:36 +0200, Mike Galbraith wrote: > > > > Ouch, you just turned the rt_read_lock() into a spin lock. If a higher > > > priority process preempted a lower priority process that holds the same > > > lock, it will deadlock. > > > > Hm, how, it's doing cpu_chill()? > > 'course PI is toast, so *poof*. Since just enabling the lockdep bits > seems to fix it up, maybe that's the patchlet to submit (less is more). There's that too. But the issue I was talking about is with all trylock loops. As holding an rt-mutex now disables migration, if a high priority process preempts a task that holds the lock, and then the high prio task starts spinning waiting for that lock to release, the lower priority process will never get to run to release it. The cpu_chill() doesn't help. -- Steve