From patchwork Tue Jun 1 06:23:02 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Nicholas Piggin X-Patchwork-Id: 12290467 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=-13.5 required=3.0 tests=BAYES_00, DKIM_ADSP_CUSTOM_MED,DKIM_INVALID,DKIM_SIGNED,FREEMAIL_FORGED_FROMDOMAIN, FREEMAIL_FROM,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham 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 6FF8FC4708F for ; Tue, 1 Jun 2021 06:23:26 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id EDCDF61159 for ; Tue, 1 Jun 2021 06:23:25 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org EDCDF61159 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=gmail.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 8CFB98E0001; Tue, 1 Jun 2021 02:23:25 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 8AA5E940007; Tue, 1 Jun 2021 02:23:25 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 746E48E0003; Tue, 1 Jun 2021 02:23:25 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0035.hostedemail.com [216.40.44.35]) by kanga.kvack.org (Postfix) with ESMTP id 466AB8E0001 for ; Tue, 1 Jun 2021 02:23:25 -0400 (EDT) Received: from smtpin31.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay04.hostedemail.com (Postfix) with ESMTP id CC294A76B for ; Tue, 1 Jun 2021 06:23:24 +0000 (UTC) X-FDA: 78204163128.31.7D9580F Received: from mail-pl1-f179.google.com (mail-pl1-f179.google.com [209.85.214.179]) by imf29.hostedemail.com (Postfix) with ESMTP id 39C43371 for ; Tue, 1 Jun 2021 06:23:09 +0000 (UTC) Received: by mail-pl1-f179.google.com with SMTP id t21so6325462plo.2 for ; Mon, 31 May 2021 23:23:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=7SY6QzuWUSlWj33T26/GRZSVwi+Ld4IHiibBoCb52p4=; b=ePlorr20RYdU83BpwKX/s0RfyvSJGLZuiSfUt1Q5Tf+Uj6s0wJkGx8MFmTlzTq06Ly /QdSin1Qqs2l0J37C68YVuBoCY22xVUnKkbWT5c/25xPZUE4hwRl5CveuKHLOW9KwoLz WMUnhDGfB+gMrKJPdIvTLtMDs5EgLCysNJyB17ago3WfOtWSwQRzdwE9GUfx+u24xoXb YvUh+XKO7EACTncuCcfNhm9MUjn8I6F0IEFKp7B02dAPD0YE4xz1HbQBw17+5uziSWyH 6Hbt03PuVPQDsas/U9JfW6GikTKlAqSmRjtpSQ956IQanhxIOkALHMsFIlrry/0xO4L8 Jh1g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=7SY6QzuWUSlWj33T26/GRZSVwi+Ld4IHiibBoCb52p4=; b=dVu3ZjxMA8TXKtw1SvXRLy2PX4W7CU/NbRfjetLxuaJe/0LnRw4xIi60QYfWYDOJXQ 4BGOCy0eQUFla/sxqgCzsbHGHhPvqrVcQtviJH6nRNYaQKheU82Qy4EQrSbOEgnFrxBb R90uAkVwivS7n3TdQFh+h1yJrkrU+KzU9WTdqxUktWBymADKCF6AolPkUIojPXlz2B9s v8C36f+iEAIYIaLurghDu5UxDfb5gdo8GnkkIsOtenTOtOkVcK954RmjlwxOEH/zOxqy QYjT6V03lsl1FwzYbfrnXFjvrGyx3hyVWBNhMHqkNwD7XnhwyLexFV9HboYKjaCXo9SW SASQ== X-Gm-Message-State: AOAM530A8ru279KqplE0Q8JvGBhw7nwW66tSvU9nEPJJDDqPT5pGgegZ 33F55NI2b4J1x0hAX3aAX6k4BVvKQWc= X-Google-Smtp-Source: ABdhPJw09TNZqBmKx3WQDrsKTZlhlpstv4mz2E1lJZnWicTzFCQBo5ZLvZlMnKhALwZzNq6+juRuaA== X-Received: by 2002:a17:90a:5106:: with SMTP id t6mr3315886pjh.216.1622528603683; Mon, 31 May 2021 23:23:23 -0700 (PDT) Received: from bobo.ibm.com (60-241-69-122.static.tpgi.com.au. [60.241.69.122]) by smtp.gmail.com with ESMTPSA id h1sm12519100pfh.72.2021.05.31.23.23.19 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 31 May 2021 23:23:23 -0700 (PDT) From: Nicholas Piggin To: Andrew Morton Cc: Nicholas Piggin , Randy Dunlap , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-mm@kvack.org, Anton Blanchard , Andy Lutomirski Subject: [PATCH v3 3/4] lazy tlb: shoot lazies, a non-refcounting lazy tlb option Date: Tue, 1 Jun 2021 16:23:02 +1000 Message-Id: <20210601062303.3932513-4-npiggin@gmail.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20210601062303.3932513-1-npiggin@gmail.com> References: <20210601062303.3932513-1-npiggin@gmail.com> MIME-Version: 1.0 Authentication-Results: imf29.hostedemail.com; dkim=pass header.d=gmail.com header.s=20161025 header.b=ePlorr20; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (imf29.hostedemail.com: domain of npiggin@gmail.com designates 209.85.214.179 as permitted sender) smtp.mailfrom=npiggin@gmail.com X-Rspamd-Server: rspam05 X-Rspamd-Queue-Id: 39C43371 X-Stat-Signature: moz91ab7988cenjyanuxzmjz699xzjwp X-HE-Tag: 1622528589-452177 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On big systems, the mm refcount can become highly contented when doing a lot of context switching with threaded applications (particularly switching between the idle thread and an application thread). Abandoning lazy tlb slows switching down quite a bit in the important user->idle->user cases, so instead implement a non-refcounted scheme that causes __mmdrop() to IPI all CPUs in the mm_cpumask and shoot down any remaining lazy ones. Shootdown IPIs are some concern, but they have not been observed to be a big problem with this scheme (the powerpc implementation generated 314 additional interrupts on a 144 CPU system during a kernel compile). There are a number of strategies that could be employed to reduce IPIs if they turn out to be a problem for some workload. Signed-off-by: Nicholas Piggin --- arch/Kconfig | 14 +++++++++++++- kernel/fork.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+), 1 deletion(-) diff --git a/arch/Kconfig b/arch/Kconfig index 276e1c1c0219..91e1882e3284 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -439,11 +439,23 @@ config NO_MMU_LAZY_TLB def_bool n # Use normal mm refcounting for MMU_LAZY_TLB kernel thread references. -# For now, this must be enabled if MMU_LAZY_TLB is enabled. config MMU_LAZY_TLB_REFCOUNT def_bool y depends on MMU_LAZY_TLB +# Instead of refcounting the lazy mm struct for kernel thread references +# (which can cause contention with multi-threaded apps on large multiprocessor +# systems), this option causes __mmdrop to IPI all CPUs in the mm_cpumask and +# switch to init_mm if they were using the to-be-freed mm as the lazy tlb. To +# implement this, architectures must use _lazy_tlb variants of mm refcounting +# when releasing kernel thread mm references, and mm_cpumask must include at +# least all possible CPUs in which the mm might be lazy, at the time of the +# final mmdrop. mmgrab/mmdrop in arch/ code must be switched to _lazy_tlb +# postfix as necessary. +config MMU_LAZY_TLB_SHOOTDOWN + bool + depends on MMU_LAZY_TLB + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/kernel/fork.c b/kernel/fork.c index dc06afd725cb..d485c24426a0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -674,6 +674,53 @@ static void check_mm(struct mm_struct *mm) #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) +static void do_shoot_lazy_tlb(void *arg) +{ + struct mm_struct *mm = arg; + + if (current->active_mm == mm) { + WARN_ON_ONCE(current->mm); + current->active_mm = &init_mm; + switch_mm(mm, &init_mm, current); + } +} + +static void do_check_lazy_tlb(void *arg) +{ + struct mm_struct *mm = arg; + + WARN_ON_ONCE(current->active_mm == mm); +} + +static void shoot_lazy_tlbs(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { + /* + * IPI overheads have not found to be expensive, but they could + * be reduced in a number of possible ways, for example (in + * roughly increasing order of complexity): + * - A batch of mms requiring IPIs could be gathered and freed + * at once. + * - CPUs could store their active mm somewhere that can be + * remotely checked without a lock, to filter out + * false-positives in the cpumask. + * - After mm_users or mm_count reaches zero, switching away + * from the mm could clear mm_cpumask to reduce some IPIs + * (some batching or delaying would help). + * - A delayed freeing and RCU-like quiescing sequence based on + * mm switching to avoid IPIs completely. + */ + on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); + if (IS_ENABLED(CONFIG_DEBUG_VM)) + on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); + } else { + /* + * In this case, lazy tlb mms are refounted and would not reach + * __mmdrop until all CPUs have switched away and mmdrop()ed. + */ + } +} + /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by @@ -683,7 +730,12 @@ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); + + /* Ensure no CPUs are using this as their lazy tlb mm */ + shoot_lazy_tlbs(mm); + WARN_ON_ONCE(mm == current->active_mm); + mm_free_pgd(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm);