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=-13.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED autolearn=unavailable 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 5CBE5C4708F for ; Wed, 2 Jun 2021 22:46:02 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 00991613EC for ; Wed, 2 Jun 2021 22:46:01 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 00991613EC Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 68F296B006C; Wed, 2 Jun 2021 18:46:01 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 617556B006E; Wed, 2 Jun 2021 18:46:01 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 491116B0070; Wed, 2 Jun 2021 18:46:01 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0182.hostedemail.com [216.40.44.182]) by kanga.kvack.org (Postfix) with ESMTP id 1517E6B006C for ; Wed, 2 Jun 2021 18:46:01 -0400 (EDT) Received: from smtpin07.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay03.hostedemail.com (Postfix) with ESMTP id 9FCD88249980 for ; Wed, 2 Jun 2021 22:46:00 +0000 (UTC) X-FDA: 78210268080.07.D040B56 Received: from mail-pf1-f169.google.com (mail-pf1-f169.google.com [209.85.210.169]) by imf07.hostedemail.com (Postfix) with ESMTP id 492B0A000241 for ; Wed, 2 Jun 2021 22:45:46 +0000 (UTC) Received: by mail-pf1-f169.google.com with SMTP id t28so3360932pfg.10 for ; Wed, 02 Jun 2021 15:46:00 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:date:from:to:cc:subject:message-id:references:mime-version :content-disposition:in-reply-to; bh=j8gB6sHxvtqHPUqn/iFX+QA2rUO0s936D/nNx7U/sLY=; b=mX6+ZL/lY5axGzlSpybCYuTnQb8oXeFiKHWrgPXoKqhAQ03zjjAKqHwSGAai7EE0Ag zWwIqVu9axM2Q5faw3z9CgAz8qVBuuyxxC/7BC6zw/soKHrD7/rCxAdmVU8qNpKg/B36 diKWrcGQlodV8GlJPdjRiSIzqTtdAGXV/fJcjFpxQrUfaCw1qDY8+ULQYptEIkhzLLk1 3G+evV0Z1CgKpZaQtM0SmERSrDLZ/uj8PpSjipeJx0XEE8yOOT8hXp4jyOuBa+5Born3 +wFLOVZr7KhczZg5miPfv/wRdhqyJjhEgMsjZVK8fReUQpZbvPStbnMckKiLMB8Uz88K pogA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:from:to:cc:subject:message-id :references:mime-version:content-disposition:in-reply-to; bh=j8gB6sHxvtqHPUqn/iFX+QA2rUO0s936D/nNx7U/sLY=; b=GLtVSZwl29SIVvGgnG9D9G+iSSM05cv6xy9ERLZwP3qbDWeNGdoCaSP0IfhJvI8qDy 0FV2Ps+qm+qHpamk8R71oP6BdlMFVRyL5pJBz9YcJV7k5Fzbk06N9XZF+94BZ5CKUvCH SIg5prvNzJ52LJF6Z9lCHkQ1GVUakQrKgvWdWxZv1e+msHWodeqH/QACLbSI7now4hOR KkLayq6HprgPheNaM2iO2Yics9dcAyuC/r9nACXJriXCVBeVqv6Ou0CndV7jncMDDrHv XcgSXMGVI/AJk/ko9rgQdOA9V2mnUbNM9mqQRoGIB/+RhcdXPe0yVbZWLHHLHAXQFNwv 36Ww== X-Gm-Message-State: AOAM530ZrvDlt0ujRs+1pl/YNLZu+9DgEUzY7uxNdo7QhKiN25V3UBPR k8b3IxqW3jQJ43myVkPuiss= X-Google-Smtp-Source: ABdhPJwBzi98blgR3UvYM0bF49NO5vEcOKcUZu3eLkhpjFZdNSrD7WhMnCaFz8cjQZ4WOpq5YTSf0w== X-Received: by 2002:a63:4553:: with SMTP id u19mr36350475pgk.323.1622673959210; Wed, 02 Jun 2021 15:45:59 -0700 (PDT) Received: from google.com ([2620:15c:211:201:2274:6006:ae53:7d6]) by smtp.gmail.com with ESMTPSA id k15sm429552pjf.32.2021.06.02.15.45.56 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 02 Jun 2021 15:45:57 -0700 (PDT) Date: Wed, 2 Jun 2021 15:45:55 -0700 From: Minchan Kim To: Andrew Morton Cc: Chris Goldsworthy , Laura Abbott , Oliver Sang , David Hildenbrand , John Dias , Matthew Wilcox , Michal Hocko , Suren Baghdasaryan , Vlastimil Babka , LKML , lkp@lists.01.org, lkp@intel.com, ying.huang@intel.com, feng.tang@intel.com, zhengjun.xing@intel.com, linux-mm Subject: Re: [PATCH v2] mm: fs: invalidate bh_lrus for only cold path Message-ID: References: <20210601145425.1396981-1-minchan@kernel.org> <20210601161540.9f449314965bd94c84725481@linux-foundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20210601161540.9f449314965bd94c84725481@linux-foundation.org> Authentication-Results: imf07.hostedemail.com; dkim=pass header.d=gmail.com header.s=20161025 header.b="mX6+ZL/l"; dmarc=fail reason="SPF not aligned (relaxed), DKIM not aligned (relaxed)" header.from=kernel.org (policy=none); spf=pass (imf07.hostedemail.com: domain of minchankim@gmail.com designates 209.85.210.169 as permitted sender) smtp.mailfrom=minchankim@gmail.com X-Rspamd-Server: rspam05 X-Rspamd-Queue-Id: 492B0A000241 X-Stat-Signature: sh1etttynahgncyjwg3yyadqenb4p7sc X-HE-Tag: 1622673946-297898 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 Tue, Jun 01, 2021 at 04:15:40PM -0700, Andrew Morton wrote: > On Tue, 1 Jun 2021 07:54:25 -0700 Minchan Kim wrote: > > > kernel test robot reported the regression of fio.write_iops[1] > > with [2]. > > > > Since lru_add_drain is called frequently, invalidate bh_lrus > > there could increase bh_lrus cache miss ratio, which needs > > more IO in the end. > > > > This patch moves the bh_lrus invalidation from the hot path( > > e.g., zap_page_range, pagevec_release) to cold path(i.e., > > lru_add_drain_all, lru_cache_disable). > > This code is starting to hurt my brain. > > What are the locking/context rules for invalidate_bh_lrus_cpu()? > AFAICT it offers no protection against two CPUs concurrently running > __invalidate_bh_lrus() against the same bh_lru. The lru_add_drain_per_cpu will run on per-cpu since it's per-cpu work and invalidate_bh_lrus_cpu will run under bh_lru_lock so I couldn't imagine that race can happen. > > So when CONFIG_SMP=y, invalidate_bh_lrus_cpu() must always and only be > run on the cpu which owns the bh_lru. In which case why does it have > the `cpu' arg? I just wanted to express both lru_add_drain_cpu and invalidate_bh_lrus_cpu in lru_add_and_bh_lrus_drain run in the same cpu but look like a bad idea since it makes people confused. Let me remove the cpu argument from invalidate_bh_lrus_cpu. > > Your new lru_add_and_bh_lrus_drain() follows these rules by calling > invalidate_bh_lrus_cpu() from a per-cpu worker or when CONFIG_SMP=n. > > I think. It's all as clear as mud and undocumented. Could you please > take a look at this? Comment the locking/context rules thoroughly and > check that they are being followed? Not forgetting cpu hotplug... See if > there's a way of simplifying/clarifying the code? > > The fact that swap.c has those #ifdef CONFIG_SMPs in there is a hint > that we're doing something wrong (or poorly) in there. Perhaps that's > unavoidable because of all the fancy footwork in __lru_add_drain_all(). > Hopefully, this is better. >From 8d58e7ade3ed6c080995dec1395b1e130b3d16b3 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 25 May 2021 08:19:17 -0700 Subject: [PATCH] mm: fs: invalidate bh_lrus for only cold path kernel test robot reported the regression of fio.write_iops[1] with [2]. Since lru_add_drain is called frequently, invalidate bh_lrus there could increase bh_lrus cache miss ratio, which needs more IO in the end. This patch moves the bh_lrus invalidation from the hot path( e.g., zap_page_range, pagevec_release) to cold path(i.e., lru_add_drain_all, lru_cache_disable). [1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/ [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration Reported-by: kernel test robot Signed-off-by: Minchan Kim --- fs/buffer.c | 8 ++++++-- include/linux/buffer_head.h | 4 ++-- mm/swap.c | 19 ++++++++++++++++--- 3 files changed, 24 insertions(+), 7 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 673cfbef9eec..bdaffed39030 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1487,12 +1487,16 @@ void invalidate_bh_lrus(void) } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); -void invalidate_bh_lrus_cpu(int cpu) +/* + * It's called from workqueue context so we need a bh_lru_lock to close + * the race with preemption/irq. + */ +void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); - b = per_cpu_ptr(&bh_lrus, cpu); + b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index e7e99da31349..b04d34bab124 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); -void invalidate_bh_lrus_cpu(int cpu); +void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); @@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } -static inline void invalidate_bh_lrus_cpu(int cpu) {} +static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return 0; } #define buffer_heads_over_limit 0 diff --git a/mm/swap.c b/mm/swap.c index 1958d5feb148..4d9ec3c3c5a9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -642,7 +642,6 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); - invalidate_bh_lrus_cpu(cpu); } /** @@ -725,6 +724,20 @@ void lru_add_drain(void) local_unlock(&lru_pvecs.lock); } +/* + * It's called from per-cpu workqueue context in SMP case so + * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on + * the same cpu. It shouldn't be a problem in !SMP case since + * the core is only one and the locks will disable preemption. + */ +static void lru_add_and_bh_lrus_drain(void) +{ + local_lock(&lru_pvecs.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&lru_pvecs.lock); + invalidate_bh_lrus_cpu(); +} + void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); @@ -739,7 +752,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { - lru_add_drain(); + lru_add_and_bh_lrus_drain(); } /* @@ -880,7 +893,7 @@ void lru_cache_disable(void) */ __lru_add_drain_all(true); #else - lru_add_drain(); + lru_add_and_bh_lrus_drain(); #endif } -- 2.32.0.rc0.204.g9fa02ecfa5-goog