Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753197AbbD3U6s (ORCPT ); Thu, 30 Apr 2015 16:58:48 -0400 Received: from g4t3426.houston.hp.com ([15.201.208.54]:38000 "EHLO g4t3426.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752953AbbD3U6d (ORCPT ); Thu, 30 Apr 2015 16:58:33 -0400 Message-ID: <55429770.2090901@hp.com> Date: Thu, 30 Apr 2015 16:58:24 -0400 From: Waiman Long User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:10.0.12) Gecko/20130109 Thunderbird/10.0.12 MIME-Version: 1.0 To: Davidlohr Bueso CC: Jason Low , Peter Zijlstra , Ingo Molnar , Thomas Gleixner , linux-kernel@vger.kernel.org, "Paul E. McKenney" , Andrew Morton , Oleg Nesterov , Frederic Weisbecker , Mel Gorman , Rik van Riel , Steven Rostedt , Preeti U Murthy , Mike Galbraith , Aswin Chandramouleeswaran , Scott J Norton Subject: Re: [PATCH v2 2/5] sched, numa: Document usages of mm->numa_scan_seq References: <1430251224-5764-1-git-send-email-jason.low2@hp.com> <1430251224-5764-3-git-send-email-jason.low2@hp.com> <55411F91.6050101@hp.com> <1430333101.8722.32.camel@j-VirtualBox> <55427794.30808@hp.com> <1430420047.2011.41.camel@stgolabs.net> In-Reply-To: <1430420047.2011.41.camel@stgolabs.net> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3840 Lines: 80 On 04/30/2015 02:54 PM, Davidlohr Bueso wrote: > On Thu, 2015-04-30 at 14:42 -0400, Waiman Long wrote: >> On 04/29/2015 02:45 PM, Jason Low wrote: >>> On Wed, 2015-04-29 at 14:14 -0400, Waiman Long wrote: >>>> On 04/28/2015 04:00 PM, Jason Low wrote: >>>>> The p->mm->numa_scan_seq is accessed using READ_ONCE/WRITE_ONCE >>>>> and modified without exclusive access. It is not clear why it is >>>>> accessed this way. This patch provides some documentation on that. >>>>> >>>>> Signed-off-by: Jason Low >>>>> --- >>>>> kernel/sched/fair.c | 12 ++++++++++++ >>>>> 1 files changed, 12 insertions(+), 0 deletions(-) >>>>> >>>>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >>>>> index 5a44371..794f7d7 100644 >>>>> --- a/kernel/sched/fair.c >>>>> +++ b/kernel/sched/fair.c >>>>> @@ -1794,6 +1794,11 @@ static void task_numa_placement(struct task_struct *p) >>>>> u64 runtime, period; >>>>> spinlock_t *group_lock = NULL; >>>>> >>>>> + /* >>>>> + * The p->mm->numa_scan_seq gets updated without >>>>> + * exclusive access. Use READ_ONCE() here to ensure >>>>> + * that the field is read in a single access. >>>>> + */ >>>>> seq = READ_ONCE(p->mm->numa_scan_seq); >>>>> if (p->numa_scan_seq == seq) >>>>> return; >>>>> @@ -2107,6 +2112,13 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) >>>>> >>>>> static void reset_ptenuma_scan(struct task_struct *p) >>>>> { >>>>> + /* >>>>> + * We only did a read acquisition of the mmap sem, so >>>>> + * p->mm->numa_scan_seq is written to without exclusive access. >>>>> + * That's not much of an issue though, since this is just used >>>>> + * for statistical sampling. Use WRITE_ONCE and READ_ONCE, which >>>>> + * are not expensive, to avoid load/store tearing. >>>>> + */ >>>>> WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1); >>>>> p->mm->numa_scan_offset = 0; >>>>> } >>>> READ_ONCE followed by a WRITE_ONCE won't stop load/store tearing from >>>> happening unless you use an atomic instruction to do the increment. So I >>>> think your comment may be a bit misleading. >>> Right, the READ and WRITE operations will still be done separately and >>> won't be atomic. Here, we're saying that this prevents load/store >>> tearing on each of those individual write/read operations. Please let me >>> know if you prefer this to be worded differently. >> I do have a question of what kind of tearing you are talking about. Do >> you mean the tearing due to mm being changed in the middle of the >> access? The reason why I don't like this kind of construct is that I am >> not sure if >> the address translation p->mm->numa_scan_seq is being done once or >> twice. I looked at the compiled code and the translation is done only once. >> >> Anyway, the purpose of READ_ONCE and WRITE_ONCE is not for eliminating >> data tearing. They are to make sure that the compiler won't compile away >> data access and they are done in the order they appear in the program. I >> don't think it is a good idea to associate tearing elimination with >> those macros. So I would suggest removing the last sentence in your comment. > I agree. Related, Linus also had some thoughts about the _very specific_ > purposes of these macros: > http://www.spinics.net/lists/linux-next/msg32494.html Actually, I don't think modern compiler will reload a read value unless it runs out of usable registers. It is more likely that it will reuse a previously read value within the same function if READ_ONCE() isn't there. Cheers, Longman -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/