From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.0 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,NICE_REPLY_A, SPF_HELO_NONE,SPF_PASS,USER_AGENT_SANE_1 autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 222E7C433FE for ; Wed, 8 Sep 2021 16:11:50 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 0810161153 for ; Wed, 8 Sep 2021 16:11:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237223AbhIHQM5 (ORCPT ); Wed, 8 Sep 2021 12:12:57 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:33333 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1346386AbhIHQM4 (ORCPT ); Wed, 8 Sep 2021 12:12:56 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1631117508; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=TUxZ/+MbrnZB1clpNjfMApdQI0MDXAs5PNHhN+o12Ms=; b=USy9QY0z40brstvD4aRRcYA0SpjQi9qnK5WAFNpKmW8CGak7vRkG8rUH+aaze66i/J+biM /DKuCiGcm6xFJRunOqTqVkURf7fGbGQXDuakGcHPCgXtWzxaxGVcXgo/GDTGm8T9IS9hwL 3sDMc2y1BjqZ6Ppg2J3Ua5J4LFleZTU= Received: from mail-lj1-f200.google.com (mail-lj1-f200.google.com [209.85.208.200]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-155-AZRTLGdxN8u05MvDi4i8yQ-1; Wed, 08 Sep 2021 12:11:46 -0400 X-MC-Unique: AZRTLGdxN8u05MvDi4i8yQ-1 Received: by mail-lj1-f200.google.com with SMTP id a17-20020a2e7f11000000b001dbbb444489so1248521ljd.0 for ; Wed, 08 Sep 2021 09:11:46 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:cc:subject:to:references:message-id:date :user-agent:mime-version:in-reply-to:content-language :content-transfer-encoding; bh=TUxZ/+MbrnZB1clpNjfMApdQI0MDXAs5PNHhN+o12Ms=; b=6wjQFnqpXAJ+34dqSOmxWxyRRno0WO7louia+0oauPjo/tfbzuTenqEqNQjhN9kkb/ qKW3g+NCbpLBhgUkltOyymk7dpLnMMk91XpUzU413495NdTm02AsFIJFmDAZiG2Wyy3Q eSKVAWoiYvodbAx7L79nFjU7eVcMsf6JGteB4UEDChOkgdhXxqowHGBD4ih1RzSnmbHQ wYzrwnJiNcemcbLlBUDGRnyBAQejp8eAQWnt5OKdgvQmnhLuZVj3F9TD/BdIpjO/34L1 8dm04b5Xf0XFV0z+ohI+LwT83pQQrAMRTep+zX0cq+1rfLGKutyhEDFvqsAVVnL/QbtR otcw== X-Gm-Message-State: AOAM532GRewg4KVsBDnxHBC4rGZuADJYXYP1E7canDQsMZMd/ilIdYWY V3CFMDlgCYoyb4zIL5N2Pdt/TL3zATn0KHojd8icGMghSwFL38FNPsMt4U9DNGugRbJkddPgO98 y+nVFTgITY01e3nVVQ+ol4A== X-Received: by 2002:a2e:7a12:: with SMTP id v18mr3293815ljc.204.1631117504827; Wed, 08 Sep 2021 09:11:44 -0700 (PDT) X-Google-Smtp-Source: ABdhPJxGU3Y6eSYjqKTQtWrjLosAwFUJyr0TPoFxGWqqrt1Qyu0OC2Dxsta51JVEQtEL0a78vg2sqw== X-Received: by 2002:a2e:7a12:: with SMTP id v18mr3293803ljc.204.1631117504574; Wed, 08 Sep 2021 09:11:44 -0700 (PDT) Received: from [192.168.42.238] (87-59-106-155-cable.dk.customer.tdc.net. [87.59.106.155]) by smtp.gmail.com with ESMTPSA id p14sm290447lji.56.2021.09.08.09.11.42 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Wed, 08 Sep 2021 09:11:43 -0700 (PDT) From: Jesper Dangaard Brouer X-Google-Original-From: Jesper Dangaard Brouer Cc: brouer@redhat.com Subject: Re: [patch 031/147] mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg To: Vlastimil Babka , Jesper Dangaard Brouer , Andrew Morton , bigeasy@linutronix.de, cl@linux.com, efault@gmx.de, iamjoonsoo.kim@lge.com, jannh@google.com, linux-mm@kvack.org, mgorman@techsingularity.net, mm-commits@vger.kernel.org, penberg@kernel.org, quic_qiancai@quicinc.com, rientjes@google.com, tglx@linutronix.de, torvalds@linux-foundation.org References: <20210908025436.dvsgeCXAh%akpm@linux-foundation.org> Message-ID: <0bc898a0-2c3f-a8db-ef19-e8c5ebc3ed71@redhat.com> Date: Wed, 8 Sep 2021 18:11:42 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.11.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org On 08/09/2021 15.58, Vlastimil Babka wrote: > On 9/8/21 15:05, Jesper Dangaard Brouer wrote: >> >> >> On 08/09/2021 04.54, Andrew Morton wrote: >>> From: Vlastimil Babka >>> Subject: mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg >>> >>> Jann Horn reported [1] the following theoretically possible race: >>> >>> task A: put_cpu_partial() calls preempt_disable() >>> task A: oldpage = this_cpu_read(s->cpu_slab->partial) >>> interrupt: kfree() reaches unfreeze_partials() and discards the page >>> task B (on another CPU): reallocates page as page cache >>> task A: reads page->pages and page->pobjects, which are actually >>> halves of the pointer page->lru.prev >>> task B (on another CPU): frees page >>> interrupt: allocates page as SLUB page and places it on the percpu partial list >>> task A: this_cpu_cmpxchg() succeeds >>> >>> which would cause page->pages and page->pobjects to end up containing >>> halves of pointers that would then influence when put_cpu_partial() >>> happens and show up in root-only sysfs files. Maybe that's acceptable, >>> I don't know. But there should probably at least be a comment for now >>> to point out that we're reading union fields of a page that might be >>> in a completely different state. >>> >>> Additionally, the this_cpu_cmpxchg() approach in put_cpu_partial() is only >>> safe against s->cpu_slab->partial manipulation in ___slab_alloc() if the >>> latter disables irqs, otherwise a __slab_free() in an irq handler could >>> call put_cpu_partial() in the middle of ___slab_alloc() manipulating >>> ->partial and corrupt it. This becomes an issue on RT after a local_lock >>> is introduced in later patch. The fix means taking the local_lock also in >>> put_cpu_partial() on RT. >>> >>> After debugging this issue, Mike Galbraith suggested [2] that to avoid >>> different locking schemes on RT and !RT, we can just protect >>> put_cpu_partial() with disabled irqs (to be converted to >>> local_lock_irqsave() later) everywhere. This should be acceptable as it's >>> not a fast path, and moving the actual partial unfreezing outside of the >>> irq disabled section makes it short, and with the retry loop gone the code >>> can be also simplified. In addition, the race reported by Jann should no >>> longer be possible. >> >> Based on my microbench[0] measurement changing preempt_disable to >> local_irq_save will cost us 11 cycles (TSC). I'm not against the >> change, I just want people to keep this in mind. > > OK, but this is not a fast path for every allocation/free, so it gets > amortized. Also it eliminates a this_cpu_cmpxchg loop, and I'd expect > cmpxchg to be expensive too? Added tests for this: - this_cpu_cmpxchg cost: 5 cycles(tsc) 1.581 ns - cmpxchg cost: 18 cycles(tsc) 5.006 ns >> On my E5-1650 v4 @ 3.60GHz: >> - preempt_disable(+enable) cost: 11 cycles(tsc) 3.161 ns >> - local_irq_save (+restore) cost: 22 cycles(tsc) 6.331 ns >> >> Notice the non-save/restore variant is superfast: >> - local_irq_disable(+enable) cost: 6 cycles(tsc) 1.844 ns > > It actually surprises me that it's that cheap, and would have expected > changing the irq state would be the costly part, not the saving/restoring. > Incidentally, would you know what's the cost of save+restore when the > irqs are already disabled, so it's effectively a no-op? The non-save variant simply translated onto CLI and STI, which seems to be very fast. The cost of save+restore when the irqs are already disabled is the same (did a quick test). Cannot remember who told me, but (apparently) the expensive part is reading the CPU FLAGS. I did a quick test with: /** Loop to measure **/ for (i = 0; i < rec->loops; i++) { local_irq_save(flags); loops_cnt++; barrier(); //local_irq_restore(flags); local_irq_enable(); } Doing a save + enable: This cost 21 cycles(tsc) 6.015 ns. (Cost before was 22 cycles) This confirms reading the CPU FLAGS seems to be the expensive part. --Jesper