From patchwork Thu Jun 22 08:53:35 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Qi Zheng X-Patchwork-Id: 13288661 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id B1548EB64D8 for ; Thu, 22 Jun 2023 08:58:00 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 524438D000E; Thu, 22 Jun 2023 04:58:00 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 4D36F8D0001; Thu, 22 Jun 2023 04:58:00 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 300DA8D000E; Thu, 22 Jun 2023 04:58:00 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id 1BFC28D0001 for ; Thu, 22 Jun 2023 04:58:00 -0400 (EDT) Received: from smtpin24.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay05.hostedemail.com (Postfix) with ESMTP id 92EA440467 for ; Thu, 22 Jun 2023 08:57:59 +0000 (UTC) X-FDA: 80929781478.24.F2B01B7 Received: from mail-pl1-f177.google.com (mail-pl1-f177.google.com [209.85.214.177]) by imf19.hostedemail.com (Postfix) with ESMTP id 7F12B1A000A for ; Thu, 22 Jun 2023 08:57:57 +0000 (UTC) Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=bytedance.com header.s=google header.b=IAFXPAQd; dmarc=pass (policy=quarantine) header.from=bytedance.com; spf=pass (imf19.hostedemail.com: domain of zhengqi.arch@bytedance.com designates 209.85.214.177 as permitted sender) smtp.mailfrom=zhengqi.arch@bytedance.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1687424277; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=PAKGQW5AKOb0i6yhTIQHZdj2Ew7zYpKm64DNJQ5dWlo=; b=VjxA8bN2nrU59DyKSSaMBZVSyv+tGec8Q4zSSb16J9KXIzaH9zHFNiDrpx06uBihMc56rt 0PND/KThjmK70xWU/m/sinrpkOUsefI84NkC10fDdy8QekOJ4BznvQ2F2fvontbCUWPPn3 G/ZOMtsMD++eeuxRTguObZWswaGgM94= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=bytedance.com header.s=google header.b=IAFXPAQd; dmarc=pass (policy=quarantine) header.from=bytedance.com; spf=pass (imf19.hostedemail.com: domain of zhengqi.arch@bytedance.com designates 209.85.214.177 as permitted sender) smtp.mailfrom=zhengqi.arch@bytedance.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1687424277; a=rsa-sha256; cv=none; b=zA8stfFiaSmnvNx+BKY88q6oJYMo7VhZaZNidiyDwik/CuijxP3W6VShmCbDFXkxicGAa7 XZSk9H131/+Sr2nAY2iYfflEhI6qgVtbNzxcKM69/0FZ/UYy8H0hurBdjBszhVqTx3SNR1 T8xfhZQquynCbKYz/w6UXjTbx7wS9oo= Received: by mail-pl1-f177.google.com with SMTP id d9443c01a7336-1b5585e84b4so6829885ad.0 for ; Thu, 22 Jun 2023 01:57:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance.com; s=google; t=1687424276; x=1690016276; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=PAKGQW5AKOb0i6yhTIQHZdj2Ew7zYpKm64DNJQ5dWlo=; b=IAFXPAQdKRfFFdX8R+urqMUX8XywDjZlIZgvkiyvxKq3OuDxGDvyj53uf/GwQxOSgj UCrH4ulAqIMmQ7X056WmoGhyeCnVWVEc9MkUT54moxveVQUVm/n1V13P8OOuQyRngFVd lkgqQbjTLhW3PPA79SQnKo1nifBNALOotV0hDjlRRH90/2Gp8IdTAPqu+2ReapWlGMbq zlnEUk3uncMYp9LT0mLOQRJqCv6RJvoFO7mY6AD+tEO3DKYoCqm/BoBWKqYPC/hMbbbK /L8GxpwKn26Y52nmXelpvPk6gmsdpmYPKF8i9Fu/0MG+e/S0nlhty3rfnlUBtkssiN/B zjDQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1687424276; x=1690016276; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=PAKGQW5AKOb0i6yhTIQHZdj2Ew7zYpKm64DNJQ5dWlo=; b=aRsoveUnTN0tNBJxdN3C28CycFYMCjfCClEbOfDAcKgeSsx9IKP5Ir5dV+HFbCA3zq wdncEn5pYkxCUw8G09a2O8vCZ3gnwVSzF5M39gjEhhuqCt0DmxyL00AxH2wQS2q8BdLo dPCDaPoPZAX0d0Me6X3eOy8ZBhFQKDLkXX9DCMpsJyzZ5IJI6vt6U61AOtQvoR4t8nv/ 42pfVDkf/6dt+W+nBL0WJT2qhxerpObRsnj9XS9mQ/vGAIAfPnPVJaNsZGxOgOMklFvm j/UhecLpTBQqf3kfy2A5pZLW1lbNxyCK3r3rHRgUEzjhcuazNPZyIvmYATHOhz2ONABS AziA== X-Gm-Message-State: AC+VfDyA3Y5q8LkH/UxNu5aRzYUoUb4jStrr7uZA6jqsWkwM7qSMx8p4 30CL5H7C6630Wfb0V62kSTUttw== X-Google-Smtp-Source: ACHHUZ7H5apRKh4VQCyo6UXxNAhEyp0xI76DSHJvkAU1Y/8mfRtLEhaUfJSBdNPbX02WDiX9mNvMOA== X-Received: by 2002:a17:902:ea01:b0:1a9:6467:aa8d with SMTP id s1-20020a170902ea0100b001a96467aa8dmr21676629plg.1.1687424276223; Thu, 22 Jun 2023 01:57:56 -0700 (PDT) Received: from C02DW0BEMD6R.bytedance.net ([139.177.225.254]) by smtp.gmail.com with ESMTPSA id h2-20020a170902f7c200b001b549fce345sm4806971plw.230.2023.06.22.01.57.48 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 22 Jun 2023 01:57:55 -0700 (PDT) From: Qi Zheng To: akpm@linux-foundation.org, david@fromorbit.com, tkhai@ya.ru, vbabka@suse.cz, roman.gushchin@linux.dev, djwong@kernel.org, brauner@kernel.org, paulmck@kernel.org, tytso@mit.edu Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org, intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, dm-devel@redhat.com, linux-raid@vger.kernel.org, linux-bcache@vger.kernel.org, virtualization@lists.linux-foundation.org, linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org, linux-nfs@vger.kernel.org, linux-xfs@vger.kernel.org, linux-btrfs@vger.kernel.org, Qi Zheng Subject: [PATCH 29/29] mm: shrinker: move shrinker-related code into a separate file Date: Thu, 22 Jun 2023 16:53:35 +0800 Message-Id: <20230622085335.77010-30-zhengqi.arch@bytedance.com> X-Mailer: git-send-email 2.24.3 (Apple Git-128) In-Reply-To: <20230622085335.77010-1-zhengqi.arch@bytedance.com> References: <20230622085335.77010-1-zhengqi.arch@bytedance.com> MIME-Version: 1.0 X-Rspam-User: X-Rspamd-Server: rspam12 X-Rspamd-Queue-Id: 7F12B1A000A X-Stat-Signature: rzhehf6ibxg6c7e11qiofrrpd51qrw75 X-HE-Tag: 1687424277-488146 X-HE-Meta: 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 GHY8U8ZR WP0Nv5xWRO/BwRIZDQGmGgffzFMyqHXkkJ0KgyrfUEWK68XXn0vkKEcNsCfXDq3coaMAyyYkwJy0t4npJZdo8ReuAQ6ktim/3EqMxNOEU2eVzmhEyocgmd8/B1UUnDH/SsbM+dwEmMKBdAZfRcO2xBFd3/4EVgtbGddBBlEEkFdFW4ZofnMPVOmmMvkflQlWtDrWQrzc9n/k4eJlTodajg28vP9PkJLtPPecUSHWNxbI6Mbfb6ygK8+RRXPyMOIQd6j3kl9jKxSYSk4JF04LpB7dJfL2NbW8kXU7BMnaVPI73djxHm1Qb6t8UYCDw6sNZ5qOokHtAWq5tObU1JNQLQLurjWboNfdLjD4d6o0rAc6SXboGAisuZDaJZeya3Asar+swvMRLOEtRck5Ukc1SOveamqtWWIGsXmrL 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: The mm/vmscan.c file is too large, so separate the shrinker-related code from it into a separate file. No functional changes. Signed-off-by: Qi Zheng --- include/linux/shrinker.h | 3 + mm/Makefile | 4 +- mm/shrinker.c | 750 +++++++++++++++++++++++++++++++++++++++ mm/vmscan.c | 746 -------------------------------------- 4 files changed, 755 insertions(+), 748 deletions(-) create mode 100644 mm/shrinker.c diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index b0c6c2df9db8..b837b4c0864a 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -104,6 +104,9 @@ struct shrinker { */ #define SHRINKER_NONSLAB (1 << 3) +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority); + extern int __printf(2, 3) prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...); extern void register_shrinker_prepared(struct shrinker *shrinker); diff --git a/mm/Makefile b/mm/Makefile index 678530a07326..891899186608 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -48,8 +48,8 @@ endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page-writeback.o folio-compat.o \ - readahead.o swap.o truncate.o vmscan.o shmem.o \ - util.o mmzone.o vmstat.o backing-dev.o \ + readahead.o swap.o truncate.o vmscan.o shrinker.o \ + shmem.o util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ compaction.o show_mem.o\ interval_tree.o list_lru.o workingset.o \ diff --git a/mm/shrinker.c b/mm/shrinker.c new file mode 100644 index 000000000000..f88966f3d6be --- /dev/null +++ b/mm/shrinker.c @@ -0,0 +1,750 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include + +LIST_HEAD(shrinker_list); +DEFINE_MUTEX(shrinker_mutex); + +#ifdef CONFIG_MEMCG +static int shrinker_nr_max; + +/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ +static inline int shrinker_map_size(int nr_items) +{ + return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); +} + +static inline int shrinker_defer_size(int nr_items) +{ + return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); +} + +static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, + lockdep_is_held(&shrinker_mutex)); +} + +static struct shrinker_info *shrinker_info_rcu(struct mem_cgroup *memcg, + int nid) +{ + return rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); +} + +static int expand_one_shrinker_info(struct mem_cgroup *memcg, + int map_size, int defer_size, + int old_map_size, int old_defer_size, + int new_nr_max) +{ + struct shrinker_info *new, *old; + struct mem_cgroup_per_node *pn; + int nid; + int size = map_size + defer_size; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + old = shrinker_info_protected(memcg, nid); + /* Not yet online memcg */ + if (!old) + return 0; + + /* Already expanded this shrinker_info */ + if (new_nr_max <= old->map_nr_max) + continue; + + new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); + if (!new) + return -ENOMEM; + + new->nr_deferred = (atomic_long_t *)(new + 1); + new->map = (void *)new->nr_deferred + defer_size; + new->map_nr_max = new_nr_max; + + /* map: set all old bits, clear all new bits */ + memset(new->map, (int)0xff, old_map_size); + memset((void *)new->map + old_map_size, 0, map_size - old_map_size); + /* nr_deferred: copy old values, clear all new values */ + memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); + memset((void *)new->nr_deferred + old_defer_size, 0, + defer_size - old_defer_size); + + rcu_assign_pointer(pn->shrinker_info, new); + kvfree_rcu(old, rcu); + } + + return 0; +} + +void free_shrinker_info(struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *pn; + struct shrinker_info *info; + int nid; + + for_each_node(nid) { + pn = memcg->nodeinfo[nid]; + info = rcu_dereference_protected(pn->shrinker_info, true); + kvfree(info); + rcu_assign_pointer(pn->shrinker_info, NULL); + } +} + +int alloc_shrinker_info(struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + int nid, size, ret = 0; + int map_size, defer_size = 0; + + mutex_lock(&shrinker_mutex); + map_size = shrinker_map_size(shrinker_nr_max); + defer_size = shrinker_defer_size(shrinker_nr_max); + size = map_size + defer_size; + for_each_node(nid) { + info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); + if (!info) { + free_shrinker_info(memcg); + ret = -ENOMEM; + break; + } + info->nr_deferred = (atomic_long_t *)(info + 1); + info->map = (void *)info->nr_deferred + defer_size; + info->map_nr_max = shrinker_nr_max; + rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); + } + mutex_unlock(&shrinker_mutex); + + return ret; +} + +static int expand_shrinker_info(int new_id) +{ + int ret = 0; + int new_nr_max = round_up(new_id + 1, BITS_PER_LONG); + int map_size, defer_size = 0; + int old_map_size, old_defer_size = 0; + struct mem_cgroup *memcg; + + if (!root_mem_cgroup) + goto out; + + lockdep_assert_held(&shrinker_mutex); + + map_size = shrinker_map_size(new_nr_max); + defer_size = shrinker_defer_size(new_nr_max); + old_map_size = shrinker_map_size(shrinker_nr_max); + old_defer_size = shrinker_defer_size(shrinker_nr_max); + + memcg = mem_cgroup_iter(NULL, NULL, NULL); + do { + ret = expand_one_shrinker_info(memcg, map_size, defer_size, + old_map_size, old_defer_size, + new_nr_max); + if (ret) { + mem_cgroup_iter_break(NULL, memcg); + goto out; + } + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); +out: + if (!ret) + shrinker_nr_max = new_nr_max; + + return ret; +} + +void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) +{ + if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { + struct shrinker_info *info; + + rcu_read_lock(); + info = shrinker_info_rcu(memcg, nid); + if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); + set_bit(shrinker_id, info->map); + } + rcu_read_unlock(); + } +} + +static DEFINE_IDR(shrinker_idr); + +static int prealloc_memcg_shrinker(struct shrinker *shrinker) +{ + int id, ret = -ENOMEM; + + if (mem_cgroup_disabled()) + return -ENOSYS; + + mutex_lock(&shrinker_mutex); + id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); + if (id < 0) + goto unlock; + + if (id >= shrinker_nr_max) { + if (expand_shrinker_info(id)) { + idr_remove(&shrinker_idr, id); + goto unlock; + } + } + shrinker->id = id; + ret = 0; +unlock: + mutex_unlock(&shrinker_mutex); + return ret; +} + +static void unregister_memcg_shrinker(struct shrinker *shrinker) +{ + int id = shrinker->id; + + BUG_ON(id < 0); + + lockdep_assert_held(&shrinker_mutex); + + idr_remove(&shrinker_idr, id); +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + long nr_deferred; + + rcu_read_lock(); + info = shrinker_info_rcu(memcg, nid); + nr_deferred = atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); + rcu_read_unlock(); + + return nr_deferred; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + struct shrinker_info *info; + long nr_deferred; + + rcu_read_lock(); + info = shrinker_info_rcu(memcg, nid); + nr_deferred = atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); + rcu_read_unlock(); + + return nr_deferred; +} + +void reparent_shrinker_deferred(struct mem_cgroup *memcg) +{ + int i, nid; + long nr; + struct mem_cgroup *parent; + struct shrinker_info *child_info, *parent_info; + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* Prevent from concurrent shrinker_info expand */ + mutex_lock(&shrinker_mutex); + for_each_node(nid) { + child_info = shrinker_info_protected(memcg, nid); + parent_info = shrinker_info_protected(parent, nid); + for (i = 0; i < child_info->map_nr_max; i++) { + nr = atomic_long_read(&child_info->nr_deferred[i]); + atomic_long_add(nr, &parent_info->nr_deferred[i]); + } + } + mutex_unlock(&shrinker_mutex); +} +#else +static int prealloc_memcg_shrinker(struct shrinker *shrinker) +{ + return -ENOSYS; +} + +static void unregister_memcg_shrinker(struct shrinker *shrinker) +{ +} + +static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} + +static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, + struct mem_cgroup *memcg) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +static long xchg_nr_deferred(struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return xchg_nr_deferred_memcg(nid, shrinker, + sc->memcg); + + return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); +} + +static long add_nr_deferred(long nr, struct shrinker *shrinker, + struct shrink_control *sc) +{ + int nid = sc->nid; + + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) + nid = 0; + + if (sc->memcg && + (shrinker->flags & SHRINKER_MEMCG_AWARE)) + return add_nr_deferred_memcg(nr, nid, shrinker, + sc->memcg); + + return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); +} + +#define SHRINK_BATCH 128 + +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, int priority) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long freeable; + long nr; + long new_nr; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + long scanned = 0, next_deferred; + + freeable = shrinker->count_objects(shrinker, shrinkctl); + if (freeable == 0 || freeable == SHRINK_EMPTY) + return freeable; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = xchg_nr_deferred(shrinker, shrinkctl); + + if (shrinker->seeks) { + delta = freeable >> priority; + delta *= 4; + do_div(delta, shrinker->seeks); + } else { + /* + * These objects don't require any IO to create. Trim + * them aggressively under memory pressure to keep + * them from causing refetches in the IO caches. + */ + delta = freeable / 2; + } + + total_scan = nr >> priority; + total_scan += delta; + total_scan = min(total_scan, (2 * freeable)); + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + freeable, delta, total_scan, priority); + + /* + * Normally, we should not scan less than batch_size objects in one + * pass to avoid too frequent shrinker calls, but if the slab has less + * than batch_size objects in total and we are really tight on memory, + * we will try to reclaim all available objects, otherwise we can end + * up failing allocations although there are plenty of reclaimable + * objects spread over several slabs with usage less than the + * batch_size. + * + * We detect the "tight on memory" situations by looking at the total + * number of objects we want to scan (total_scan). If it is greater + * than the total number of objects on slab (freeable), we must be + * scanning at high prio and therefore should try to reclaim as much as + * possible. + */ + while (total_scan >= batch_size || + total_scan >= freeable) { + unsigned long ret; + unsigned long nr_to_scan = min(batch_size, total_scan); + + shrinkctl->nr_to_scan = nr_to_scan; + shrinkctl->nr_scanned = nr_to_scan; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; + + count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); + total_scan -= shrinkctl->nr_scanned; + scanned += shrinkctl->nr_scanned; + + cond_resched(); + } + + /* + * The deferred work is increased by any new work (delta) that wasn't + * done, decreased by old deferred work that was done now. + * + * And it is capped to two times of the freeable items. + */ + next_deferred = max_t(long, (nr + delta - scanned), 0); + next_deferred = min(next_deferred, (2 * freeable)); + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. + */ + new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); + + trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); + return freed; +} + +#ifdef CONFIG_MEMCG +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + struct shrinker_info *info; + unsigned long ret, freed = 0; + int i = 0; + + if (!mem_cgroup_online(memcg)) + return 0; + +again: + rcu_read_lock(); + info = shrinker_info_rcu(memcg, nid); + if (unlikely(!info)) + goto unlock; + + for_each_set_bit_from(i, info->map, info->map_nr_max) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + struct shrinker *shrinker; + + shrinker = idr_find(&shrinker_idr, i); + if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { + if (!shrinker) + clear_bit(i, info->map); + continue; + } + + if (!shrinker_try_get(shrinker)) + continue; + rcu_read_unlock(); + + /* Call non-slab shrinkers even though kmem is disabled */ + if (!memcg_kmem_online() && + !(shrinker->flags & SHRINKER_NONSLAB)) + continue; + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) { + clear_bit(i, info->map); + /* + * After the shrinker reported that it had no objects to + * free, but before we cleared the corresponding bit in + * the memcg shrinker map, a new object might have been + * added. To make sure, we have the bit set in this + * case, we invoke the shrinker one more time and reset + * the bit if it reports that it is not empty anymore. + * The memory barrier here pairs with the barrier in + * set_shrinker_bit(): + * + * list_lru_add() shrink_slab_memcg() + * list_add_tail() clear_bit() + * + * set_bit() do_shrink_slab() + */ + smp_mb__after_atomic(); + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + else + set_shrinker_bit(memcg, nid, i); + } + freed += ret; + + shrinker_put(shrinker); + + /* + * We have already exited the read-side of rcu critical section + * before calling do_shrink_slab(), the shrinker_info may be + * released in expand_one_shrinker_info(), so restart the + * iteration. + */ + i++; + goto again; + } +unlock: + rcu_read_unlock(); + return freed; +} +#else /* CONFIG_MEMCG */ +static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, int priority) +{ + return 0; +} +#endif /* CONFIG_MEMCG */ + +/** + * shrink_slab - shrink slab caches + * @gfp_mask: allocation context + * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target + * @priority: the reclaim priority + * + * Call the shrink functions to age shrinkable caches. + * + * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, + * unaware shrinkers will receive a node id of 0 instead. + * + * @memcg specifies the memory cgroup to target. Unaware shrinkers + * are called only if it is the root cgroup. + * + * @priority is sc->priority, we take the number of objects and >> by priority + * in order to get the scan target. + * + * Returns the number of reclaimed slab objects. + */ +unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, + int priority) +{ + unsigned long ret, freed = 0; + struct shrinker *shrinker; + + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) + return shrink_slab_memcg(gfp_mask, nid, memcg, priority); + + rcu_read_lock(); + list_for_each_entry_rcu(shrinker, &shrinker_list, list) { + struct shrink_control sc = { + .gfp_mask = gfp_mask, + .nid = nid, + .memcg = memcg, + }; + + if (!shrinker_try_get(shrinker)) + continue; + rcu_read_unlock(); + + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + freed += ret; + + rcu_read_lock(); + shrinker_put(shrinker); + } + rcu_read_unlock(); + cond_resched(); + return freed; +} + +/* + * Add a shrinker callback to be called from the vm. + */ +static int __prealloc_shrinker(struct shrinker *shrinker) +{ + unsigned int size; + int err; + + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + err = prealloc_memcg_shrinker(shrinker); + if (err != -ENOSYS) + return err; + + shrinker->flags &= ~SHRINKER_MEMCG_AWARE; + } + + size = sizeof(*shrinker->nr_deferred); + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + + return 0; +} + +#ifdef CONFIG_SHRINKER_DEBUG +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __prealloc_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + + return err; +} +#else +int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __prealloc_shrinker(shrinker); +} +#endif + +void free_prealloced_shrinker(struct shrinker *shrinker) +{ +#ifdef CONFIG_SHRINKER_DEBUG + kfree_const(shrinker->name); + shrinker->name = NULL; +#endif + if (shrinker->flags & SHRINKER_MEMCG_AWARE) { + mutex_lock(&shrinker_mutex); + unregister_memcg_shrinker(shrinker); + mutex_unlock(&shrinker_mutex); + return; + } + + kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; +} + +void register_shrinker_prepared(struct shrinker *shrinker) +{ + mutex_lock(&shrinker_mutex); + refcount_set(&shrinker->refcount, 1); + init_completion(&shrinker->completion_wait); + list_add_tail_rcu(&shrinker->list, &shrinker_list); + shrinker->flags |= SHRINKER_REGISTERED; + shrinker_debugfs_add(shrinker); + mutex_unlock(&shrinker_mutex); +} + +static int __register_shrinker(struct shrinker *shrinker) +{ + int err = __prealloc_shrinker(shrinker); + + if (err) + return err; + register_shrinker_prepared(shrinker); + return 0; +} + +#ifdef CONFIG_SHRINKER_DEBUG +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + va_list ap; + int err; + + va_start(ap, fmt); + shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); + va_end(ap); + if (!shrinker->name) + return -ENOMEM; + + err = __register_shrinker(shrinker); + if (err) { + kfree_const(shrinker->name); + shrinker->name = NULL; + } + return err; +} +#else +int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) +{ + return __register_shrinker(shrinker); +} +#endif +EXPORT_SYMBOL(register_shrinker); + +/* + * Remove one + */ +void unregister_shrinker(struct shrinker *shrinker) +{ + struct dentry *debugfs_entry; + int debugfs_id; + + if (!(shrinker->flags & SHRINKER_REGISTERED)) + return; + + shrinker_put(shrinker); + wait_for_completion(&shrinker->completion_wait); + + mutex_lock(&shrinker_mutex); + list_del_rcu(&shrinker->list); + shrinker->flags &= ~SHRINKER_REGISTERED; + if (shrinker->flags & SHRINKER_MEMCG_AWARE) + unregister_memcg_shrinker(shrinker); + debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); + mutex_unlock(&shrinker_mutex); + + shrinker_debugfs_remove(debugfs_entry, debugfs_id); + + kfree(shrinker->nr_deferred); + shrinker->nr_deferred = NULL; +} +EXPORT_SYMBOL(unregister_shrinker); + +struct shrinker *shrinker_alloc_and_init(count_objects_cb count, + scan_objects_cb scan, long batch, + int seeks, unsigned flags, + void *priv_data) +{ + struct shrinker *shrinker; + + shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); + if (!shrinker) + return NULL; + + shrinker->count_objects = count; + shrinker->scan_objects = scan; + shrinker->batch = batch; + shrinker->seeks = seeks; + shrinker->flags = flags; + shrinker->private_data = priv_data; + + return shrinker; +} +EXPORT_SYMBOL(shrinker_alloc_and_init); + +void shrinker_free(struct shrinker *shrinker) +{ + kfree(shrinker); +} +EXPORT_SYMBOL(shrinker_free); + +void unregister_and_free_shrinker(struct shrinker *shrinker) +{ + unregister_shrinker(shrinker); + kfree_rcu(shrinker, rcu); +} +EXPORT_SYMBOL(unregister_and_free_shrinker); diff --git a/mm/vmscan.c b/mm/vmscan.c index bcdd97caa403..0816c6496483 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -57,7 +56,6 @@ #include #include #include -#include #include #include @@ -189,262 +187,7 @@ struct scan_control { */ int vm_swappiness = 60; -LIST_HEAD(shrinker_list); -DEFINE_MUTEX(shrinker_mutex); - #ifdef CONFIG_MEMCG -static int shrinker_nr_max; - -/* The shrinker_info is expanded in a batch of BITS_PER_LONG */ -static inline int shrinker_map_size(int nr_items) -{ - return (DIV_ROUND_UP(nr_items, BITS_PER_LONG) * sizeof(unsigned long)); -} - -static inline int shrinker_defer_size(int nr_items) -{ - return (round_up(nr_items, BITS_PER_LONG) * sizeof(atomic_long_t)); -} - -static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, - int nid) -{ - return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, - lockdep_is_held(&shrinker_mutex)); -} - -static struct shrinker_info *shrinker_info_rcu(struct mem_cgroup *memcg, - int nid) -{ - return rcu_dereference(memcg->nodeinfo[nid]->shrinker_info); -} - -static int expand_one_shrinker_info(struct mem_cgroup *memcg, - int map_size, int defer_size, - int old_map_size, int old_defer_size, - int new_nr_max) -{ - struct shrinker_info *new, *old; - struct mem_cgroup_per_node *pn; - int nid; - int size = map_size + defer_size; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - old = shrinker_info_protected(memcg, nid); - /* Not yet online memcg */ - if (!old) - return 0; - - /* Already expanded this shrinker_info */ - if (new_nr_max <= old->map_nr_max) - continue; - - new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid); - if (!new) - return -ENOMEM; - - new->nr_deferred = (atomic_long_t *)(new + 1); - new->map = (void *)new->nr_deferred + defer_size; - new->map_nr_max = new_nr_max; - - /* map: set all old bits, clear all new bits */ - memset(new->map, (int)0xff, old_map_size); - memset((void *)new->map + old_map_size, 0, map_size - old_map_size); - /* nr_deferred: copy old values, clear all new values */ - memcpy(new->nr_deferred, old->nr_deferred, old_defer_size); - memset((void *)new->nr_deferred + old_defer_size, 0, - defer_size - old_defer_size); - - rcu_assign_pointer(pn->shrinker_info, new); - kvfree_rcu(old, rcu); - } - - return 0; -} - -void free_shrinker_info(struct mem_cgroup *memcg) -{ - struct mem_cgroup_per_node *pn; - struct shrinker_info *info; - int nid; - - for_each_node(nid) { - pn = memcg->nodeinfo[nid]; - info = rcu_dereference_protected(pn->shrinker_info, true); - kvfree(info); - rcu_assign_pointer(pn->shrinker_info, NULL); - } -} - -int alloc_shrinker_info(struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - int nid, size, ret = 0; - int map_size, defer_size = 0; - - mutex_lock(&shrinker_mutex); - map_size = shrinker_map_size(shrinker_nr_max); - defer_size = shrinker_defer_size(shrinker_nr_max); - size = map_size + defer_size; - for_each_node(nid) { - info = kvzalloc_node(sizeof(*info) + size, GFP_KERNEL, nid); - if (!info) { - free_shrinker_info(memcg); - ret = -ENOMEM; - break; - } - info->nr_deferred = (atomic_long_t *)(info + 1); - info->map = (void *)info->nr_deferred + defer_size; - info->map_nr_max = shrinker_nr_max; - rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); - } - mutex_unlock(&shrinker_mutex); - - return ret; -} - -static int expand_shrinker_info(int new_id) -{ - int ret = 0; - int new_nr_max = round_up(new_id + 1, BITS_PER_LONG); - int map_size, defer_size = 0; - int old_map_size, old_defer_size = 0; - struct mem_cgroup *memcg; - - if (!root_mem_cgroup) - goto out; - - lockdep_assert_held(&shrinker_mutex); - - map_size = shrinker_map_size(new_nr_max); - defer_size = shrinker_defer_size(new_nr_max); - old_map_size = shrinker_map_size(shrinker_nr_max); - old_defer_size = shrinker_defer_size(shrinker_nr_max); - - memcg = mem_cgroup_iter(NULL, NULL, NULL); - do { - ret = expand_one_shrinker_info(memcg, map_size, defer_size, - old_map_size, old_defer_size, - new_nr_max); - if (ret) { - mem_cgroup_iter_break(NULL, memcg); - goto out; - } - } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); -out: - if (!ret) - shrinker_nr_max = new_nr_max; - - return ret; -} - -void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) -{ - if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) { - struct shrinker_info *info; - - rcu_read_lock(); - info = shrinker_info_rcu(memcg, nid); - if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) { - /* Pairs with smp mb in shrink_slab() */ - smp_mb__before_atomic(); - set_bit(shrinker_id, info->map); - } - rcu_read_unlock(); - } -} - -static DEFINE_IDR(shrinker_idr); - -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - int id, ret = -ENOMEM; - - if (mem_cgroup_disabled()) - return -ENOSYS; - - mutex_lock(&shrinker_mutex); - id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); - if (id < 0) - goto unlock; - - if (id >= shrinker_nr_max) { - if (expand_shrinker_info(id)) { - idr_remove(&shrinker_idr, id); - goto unlock; - } - } - shrinker->id = id; - ret = 0; -unlock: - mutex_unlock(&shrinker_mutex); - return ret; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ - int id = shrinker->id; - - BUG_ON(id < 0); - - lockdep_assert_held(&shrinker_mutex); - - idr_remove(&shrinker_idr, id); -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - long nr_deferred; - - rcu_read_lock(); - info = shrinker_info_rcu(memcg, nid); - nr_deferred = atomic_long_xchg(&info->nr_deferred[shrinker->id], 0); - rcu_read_unlock(); - - return nr_deferred; -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - struct shrinker_info *info; - long nr_deferred; - - rcu_read_lock(); - info = shrinker_info_rcu(memcg, nid); - nr_deferred = atomic_long_add_return(nr, &info->nr_deferred[shrinker->id]); - rcu_read_unlock(); - - return nr_deferred; -} - -void reparent_shrinker_deferred(struct mem_cgroup *memcg) -{ - int i, nid; - long nr; - struct mem_cgroup *parent; - struct shrinker_info *child_info, *parent_info; - - parent = parent_mem_cgroup(memcg); - if (!parent) - parent = root_mem_cgroup; - - /* Prevent from concurrent shrinker_info expand */ - mutex_lock(&shrinker_mutex); - for_each_node(nid) { - child_info = shrinker_info_protected(memcg, nid); - parent_info = shrinker_info_protected(parent, nid); - for (i = 0; i < child_info->map_nr_max; i++) { - nr = atomic_long_read(&child_info->nr_deferred[i]); - atomic_long_add(nr, &parent_info->nr_deferred[i]); - } - } - mutex_unlock(&shrinker_mutex); -} - static bool cgroup_reclaim(struct scan_control *sc) { return sc->target_mem_cgroup; @@ -479,27 +222,6 @@ static bool writeback_throttling_sane(struct scan_control *sc) return false; } #else -static int prealloc_memcg_shrinker(struct shrinker *shrinker) -{ - return -ENOSYS; -} - -static void unregister_memcg_shrinker(struct shrinker *shrinker) -{ -} - -static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - -static long add_nr_deferred_memcg(long nr, int nid, struct shrinker *shrinker, - struct mem_cgroup *memcg) -{ - return 0; -} - static bool cgroup_reclaim(struct scan_control *sc) { return false; @@ -568,39 +290,6 @@ static void flush_reclaim_state(struct scan_control *sc) } } -static long xchg_nr_deferred(struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return xchg_nr_deferred_memcg(nid, shrinker, - sc->memcg); - - return atomic_long_xchg(&shrinker->nr_deferred[nid], 0); -} - - -static long add_nr_deferred(long nr, struct shrinker *shrinker, - struct shrink_control *sc) -{ - int nid = sc->nid; - - if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) - nid = 0; - - if (sc->memcg && - (shrinker->flags & SHRINKER_MEMCG_AWARE)) - return add_nr_deferred_memcg(nr, nid, shrinker, - sc->memcg); - - return atomic_long_add_return(nr, &shrinker->nr_deferred[nid]); -} - static bool can_demote(int nid, struct scan_control *sc) { if (!numa_demotion_enabled) @@ -682,441 +371,6 @@ static unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, return size; } -/* - * Add a shrinker callback to be called from the vm. - */ -static int __prealloc_shrinker(struct shrinker *shrinker) -{ - unsigned int size; - int err; - - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - err = prealloc_memcg_shrinker(shrinker); - if (err != -ENOSYS) - return err; - - shrinker->flags &= ~SHRINKER_MEMCG_AWARE; - } - - size = sizeof(*shrinker->nr_deferred); - if (shrinker->flags & SHRINKER_NUMA_AWARE) - size *= nr_node_ids; - - shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); - if (!shrinker->nr_deferred) - return -ENOMEM; - - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __prealloc_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - - return err; -} -#else -int prealloc_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __prealloc_shrinker(shrinker); -} -#endif - -void free_prealloced_shrinker(struct shrinker *shrinker) -{ -#ifdef CONFIG_SHRINKER_DEBUG - kfree_const(shrinker->name); - shrinker->name = NULL; -#endif - if (shrinker->flags & SHRINKER_MEMCG_AWARE) { - mutex_lock(&shrinker_mutex); - unregister_memcg_shrinker(shrinker); - mutex_unlock(&shrinker_mutex); - return; - } - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} - -void register_shrinker_prepared(struct shrinker *shrinker) -{ - mutex_lock(&shrinker_mutex); - refcount_set(&shrinker->refcount, 1); - init_completion(&shrinker->completion_wait); - list_add_tail_rcu(&shrinker->list, &shrinker_list); - shrinker->flags |= SHRINKER_REGISTERED; - shrinker_debugfs_add(shrinker); - mutex_unlock(&shrinker_mutex); -} - -static int __register_shrinker(struct shrinker *shrinker) -{ - int err = __prealloc_shrinker(shrinker); - - if (err) - return err; - register_shrinker_prepared(shrinker); - return 0; -} - -#ifdef CONFIG_SHRINKER_DEBUG -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - va_list ap; - int err; - - va_start(ap, fmt); - shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); - va_end(ap); - if (!shrinker->name) - return -ENOMEM; - - err = __register_shrinker(shrinker); - if (err) { - kfree_const(shrinker->name); - shrinker->name = NULL; - } - return err; -} -#else -int register_shrinker(struct shrinker *shrinker, const char *fmt, ...) -{ - return __register_shrinker(shrinker); -} -#endif -EXPORT_SYMBOL(register_shrinker); - -/* - * Remove one - */ -void unregister_shrinker(struct shrinker *shrinker) -{ - struct dentry *debugfs_entry; - int debugfs_id; - - if (!(shrinker->flags & SHRINKER_REGISTERED)) - return; - - shrinker_put(shrinker); - wait_for_completion(&shrinker->completion_wait); - - mutex_lock(&shrinker_mutex); - list_del_rcu(&shrinker->list); - shrinker->flags &= ~SHRINKER_REGISTERED; - if (shrinker->flags & SHRINKER_MEMCG_AWARE) - unregister_memcg_shrinker(shrinker); - debugfs_entry = shrinker_debugfs_detach(shrinker, &debugfs_id); - mutex_unlock(&shrinker_mutex); - - shrinker_debugfs_remove(debugfs_entry, debugfs_id); - - kfree(shrinker->nr_deferred); - shrinker->nr_deferred = NULL; -} -EXPORT_SYMBOL(unregister_shrinker); - -struct shrinker *shrinker_alloc_and_init(count_objects_cb count, - scan_objects_cb scan, long batch, - int seeks, unsigned flags, - void *priv_data) -{ - struct shrinker *shrinker; - - shrinker = kzalloc(sizeof(struct shrinker), GFP_KERNEL); - if (!shrinker) - return NULL; - - shrinker->count_objects = count; - shrinker->scan_objects = scan; - shrinker->batch = batch; - shrinker->seeks = seeks; - shrinker->flags = flags; - shrinker->private_data = priv_data; - - return shrinker; -} -EXPORT_SYMBOL(shrinker_alloc_and_init); - -void shrinker_free(struct shrinker *shrinker) -{ - kfree(shrinker); -} -EXPORT_SYMBOL(shrinker_free); - -void unregister_and_free_shrinker(struct shrinker *shrinker) -{ - unregister_shrinker(shrinker); - kfree_rcu(shrinker, rcu); -} -EXPORT_SYMBOL(unregister_and_free_shrinker); - -#define SHRINK_BATCH 128 - -static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, - struct shrinker *shrinker, int priority) -{ - unsigned long freed = 0; - unsigned long long delta; - long total_scan; - long freeable; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - long scanned = 0, next_deferred; - - freeable = shrinker->count_objects(shrinker, shrinkctl); - if (freeable == 0 || freeable == SHRINK_EMPTY) - return freeable; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = xchg_nr_deferred(shrinker, shrinkctl); - - if (shrinker->seeks) { - delta = freeable >> priority; - delta *= 4; - do_div(delta, shrinker->seeks); - } else { - /* - * These objects don't require any IO to create. Trim - * them aggressively under memory pressure to keep - * them from causing refetches in the IO caches. - */ - delta = freeable / 2; - } - - total_scan = nr >> priority; - total_scan += delta; - total_scan = min(total_scan, (2 * freeable)); - - trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - freeable, delta, total_scan, priority); - - /* - * Normally, we should not scan less than batch_size objects in one - * pass to avoid too frequent shrinker calls, but if the slab has less - * than batch_size objects in total and we are really tight on memory, - * we will try to reclaim all available objects, otherwise we can end - * up failing allocations although there are plenty of reclaimable - * objects spread over several slabs with usage less than the - * batch_size. - * - * We detect the "tight on memory" situations by looking at the total - * number of objects we want to scan (total_scan). If it is greater - * than the total number of objects on slab (freeable), we must be - * scanning at high prio and therefore should try to reclaim as much as - * possible. - */ - while (total_scan >= batch_size || - total_scan >= freeable) { - unsigned long ret; - unsigned long nr_to_scan = min(batch_size, total_scan); - - shrinkctl->nr_to_scan = nr_to_scan; - shrinkctl->nr_scanned = nr_to_scan; - ret = shrinker->scan_objects(shrinker, shrinkctl); - if (ret == SHRINK_STOP) - break; - freed += ret; - - count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); - total_scan -= shrinkctl->nr_scanned; - scanned += shrinkctl->nr_scanned; - - cond_resched(); - } - - /* - * The deferred work is increased by any new work (delta) that wasn't - * done, decreased by old deferred work that was done now. - * - * And it is capped to two times of the freeable items. - */ - next_deferred = max_t(long, (nr + delta - scanned), 0); - next_deferred = min(next_deferred, (2 * freeable)); - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. - */ - new_nr = add_nr_deferred(next_deferred, shrinker, shrinkctl); - - trace_mm_shrink_slab_end(shrinker, shrinkctl->nid, freed, nr, new_nr, total_scan); - return freed; -} - -#ifdef CONFIG_MEMCG -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - struct shrinker_info *info; - unsigned long ret, freed = 0; - int i = 0; - - if (!mem_cgroup_online(memcg)) - return 0; - -again: - rcu_read_lock(); - info = shrinker_info_rcu(memcg, nid); - if (unlikely(!info)) - goto unlock; - - for_each_set_bit_from(i, info->map, info->map_nr_max) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - struct shrinker *shrinker; - - shrinker = idr_find(&shrinker_idr, i); - if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) { - if (!shrinker) - clear_bit(i, info->map); - continue; - } - - if (!shrinker_try_get(shrinker)) - continue; - rcu_read_unlock(); - - /* Call non-slab shrinkers even though kmem is disabled */ - if (!memcg_kmem_online() && - !(shrinker->flags & SHRINKER_NONSLAB)) - continue; - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) { - clear_bit(i, info->map); - /* - * After the shrinker reported that it had no objects to - * free, but before we cleared the corresponding bit in - * the memcg shrinker map, a new object might have been - * added. To make sure, we have the bit set in this - * case, we invoke the shrinker one more time and reset - * the bit if it reports that it is not empty anymore. - * The memory barrier here pairs with the barrier in - * set_shrinker_bit(): - * - * list_lru_add() shrink_slab_memcg() - * list_add_tail() clear_bit() - * - * set_bit() do_shrink_slab() - */ - smp_mb__after_atomic(); - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - else - set_shrinker_bit(memcg, nid, i); - } - freed += ret; - - shrinker_put(shrinker); - - /* - * We have already exited the read-side of rcu critical section - * before calling do_shrink_slab(), the shrinker_info may be - * released in expand_one_shrinker_info(), so restart the - * iteration. - */ - i++; - goto again; - } -unlock: - rcu_read_unlock(); - return freed; -} -#else /* CONFIG_MEMCG */ -static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, int priority) -{ - return 0; -} -#endif /* CONFIG_MEMCG */ - -/** - * shrink_slab - shrink slab caches - * @gfp_mask: allocation context - * @nid: node whose slab caches to target - * @memcg: memory cgroup whose slab caches to target - * @priority: the reclaim priority - * - * Call the shrink functions to age shrinkable caches. - * - * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, - * unaware shrinkers will receive a node id of 0 instead. - * - * @memcg specifies the memory cgroup to target. Unaware shrinkers - * are called only if it is the root cgroup. - * - * @priority is sc->priority, we take the number of objects and >> by priority - * in order to get the scan target. - * - * Returns the number of reclaimed slab objects. - */ -static unsigned long shrink_slab(gfp_t gfp_mask, int nid, - struct mem_cgroup *memcg, - int priority) -{ - unsigned long ret, freed = 0; - struct shrinker *shrinker; - - /* - * The root memcg might be allocated even though memcg is disabled - * via "cgroup_disable=memory" boot parameter. This could make - * mem_cgroup_is_root() return false, then just run memcg slab - * shrink, but skip global shrink. This may result in premature - * oom. - */ - if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) - return shrink_slab_memcg(gfp_mask, nid, memcg, priority); - - rcu_read_lock(); - list_for_each_entry_rcu(shrinker, &shrinker_list, list) { - struct shrink_control sc = { - .gfp_mask = gfp_mask, - .nid = nid, - .memcg = memcg, - }; - - if (!shrinker_try_get(shrinker)) - continue; - rcu_read_unlock(); - - ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; - freed += ret; - - rcu_read_lock(); - shrinker_put(shrinker); - } - rcu_read_unlock(); - cond_resched(); - return freed; -} - static unsigned long drop_slab_node(int nid) { unsigned long freed = 0;