Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751798AbdG0VmP (ORCPT ); Thu, 27 Jul 2017 17:42:15 -0400 Received: from mail-wm0-f46.google.com ([74.125.82.46]:36006 "EHLO mail-wm0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751788AbdG0VmM (ORCPT ); Thu, 27 Jul 2017 17:42:12 -0400 MIME-Version: 1.0 Reply-To: dmitriyz@waymo.com In-Reply-To: <20170727124855.aeb97ea9f74af2d3e47e1787@linux-foundation.org> References: <20170727164608.12701-1-dmitriyz@waymo.com> <20170727124855.aeb97ea9f74af2d3e47e1787@linux-foundation.org> From: Dima Zavin Date: Thu, 27 Jul 2017 14:41:48 -0700 Message-ID: Subject: Re: [PATCH v2] cpuset: fix a deadlock due to incomplete patching of cpusets_enabled() To: Andrew Morton Cc: Christopher Lameter , Li Zefan , Pekka Enberg , David Rientjes , Joonsoo Kim , cgroups@vger.kernel.org, LKML , linux-mm@kvack.org, Cliff Spradlin , Mel Gorman Content-Type: text/plain; charset="UTF-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2182 Lines: 49 On Thu, Jul 27, 2017 at 12:48 PM, Andrew Morton wrote: > On Thu, 27 Jul 2017 09:46:08 -0700 Dima Zavin wrote: > >> In codepaths that use the begin/retry interface for reading >> mems_allowed_seq with irqs disabled, there exists a race condition that >> stalls the patch process after only modifying a subset of the >> static_branch call sites. >> >> This problem manifested itself as a dead lock in the slub >> allocator, inside get_any_partial. The loop reads >> mems_allowed_seq value (via read_mems_allowed_begin), >> performs the defrag operation, and then verifies the consistency >> of mem_allowed via the read_mems_allowed_retry and the cookie >> returned by xxx_begin. The issue here is that both begin and retry >> first check if cpusets are enabled via cpusets_enabled() static branch. >> This branch can be rewritted dynamically (via cpuset_inc) if a new >> cpuset is created. The x86 jump label code fully synchronizes across >> all CPUs for every entry it rewrites. If it rewrites only one of the >> callsites (specifically the one in read_mems_allowed_retry) and then >> waits for the smp_call_function(do_sync_core) to complete while a CPU is >> inside the begin/retry section with IRQs off and the mems_allowed value >> is changed, we can hang. This is because begin() will always return 0 >> (since it wasn't patched yet) while retry() will test the 0 against >> the actual value of the seq counter. >> >> The fix is to cache the value that's returned by cpusets_enabled() at the >> top of the loop, and only operate on the seqcount (both begin and retry) if >> it was true. > > Tricky. Hence we should have a nice code comment somewhere describing > all of this. > >> --- a/include/linux/cpuset.h >> +++ b/include/linux/cpuset.h >> @@ -16,6 +16,11 @@ >> #include >> #include >> >> +struct cpuset_mems_cookie { >> + unsigned int seq; >> + bool was_enabled; >> +}; > > At cpuset_mems_cookie would be a good site - why it exists, what it > does, when it is used and how. Will do. I actually had a comment here but removed it in lieu of commit message :) Will put it back.