From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751681Ab3LJXqN (ORCPT ); Tue, 10 Dec 2013 18:46:13 -0500 Received: from mx1.redhat.com ([209.132.183.28]:48159 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751178Ab3LJXqJ (ORCPT ); Tue, 10 Dec 2013 18:46:09 -0500 Date: Tue, 10 Dec 2013 18:00:09 -0500 From: Dave Jones To: Linus Torvalds Cc: Thomas Gleixner , Oleg Nesterov , Darren Hart , Andrea Arcangeli , Linux Kernel Mailing List , Peter Zijlstra , Mel Gorman Subject: Re: process 'stuck' at exit. Message-ID: <20131210230009.GF5050@redhat.com> Mail-Followup-To: Dave Jones , Linus Torvalds , Thomas Gleixner , Oleg Nesterov , Darren Hart , Andrea Arcangeli , Linux Kernel Mailing List , Peter Zijlstra , Mel Gorman References: <20131210203559.GA1209@redhat.com> <20131210204925.GB27373@redhat.com> <20131210213431.GA6342@redhat.com> <20131210214143.GG27373@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Dec 10, 2013 at 02:48:52PM -0800, Linus Torvalds wrote: > On Tue, Dec 10, 2013 at 2:42 PM, Thomas Gleixner wrote: > > > > And yes, I remember that we do not do an extra check for the fshared > > case, because get_user_pages_fast() should do it for us already. If > > not we are fubared not only in the futex code. > > Yeah. It turns out we do do the access check indirectly - by looking > at the PAGE_USER bit, even if we don't necessarily check the actual > limits. So get_user_pages_fast() is fine. > > > But there is a subtle detail: > > Yup, see my email from ten minutes ago, we found the same thing. And > that would seem to explain the endless loop, and also the timing > (since Dave mentions he started doing large-pages lately). > > So I think the "__get_user_pages_fast(address, 1, !ro, &page)" thing > should work. > > Dave, can you re-create that trinity run and test that patch? I think > we've got this, but it might be nice to leave the hung machine up and > running until it's verified.. Although I don't really see what else we > could need or get out of it, so.. The only thing I'm still unclear on, is how that pid allegedly wasn't doing a futex call as part of its run. The only thing I can think of is that the other pid that _did_ do a futex call did it on a page that was MAP_SHARED between all the other children, and this 'spin forever' thing only happens when the last process with a reference on that page exits ? does that make sense? Dave