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 Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id C86C2FCC9AF for ; Tue, 10 Mar 2026 03:13:12 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 3ACB16B0095; Mon, 9 Mar 2026 23:13:12 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 380086B0096; Mon, 9 Mar 2026 23:13:12 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 2A6576B0098; Mon, 9 Mar 2026 23:13:12 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id 1BA786B0095 for ; Mon, 9 Mar 2026 23:13:12 -0400 (EDT) Received: from smtpin10.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id C6643B8D7C for ; Tue, 10 Mar 2026 03:13:11 +0000 (UTC) X-FDA: 84528682182.10.18D6AB3 Received: from mail-pj1-f42.google.com (mail-pj1-f42.google.com [209.85.216.42]) by imf16.hostedemail.com (Postfix) with ESMTP id E09D9180004 for ; Tue, 10 Mar 2026 03:13:09 +0000 (UTC) Authentication-Results: imf16.hostedemail.com; dkim=pass header.d=shopee.com header.s=shopee.com header.b=BhDzZDrg; spf=pass (imf16.hostedemail.com: domain of haifeng.xu@shopee.com designates 209.85.216.42 as permitted sender) smtp.mailfrom=haifeng.xu@shopee.com; dmarc=pass (policy=reject) header.from=shopee.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1773112390; 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=wsmX9IqTgTtiIKR5iSvwZiEzuk2SZ9FYiHutnUA3cX0=; b=3r3WjH5Ar+h8z9tv5ESRIxxq6HspKASB4HRUb/aMm9X9yhe2Hvq06sPt+j6lb0Cce1BFWG 09TbsIVKNy4sZ/EQ+JstIoXg8gpsyW53KBLW6d1uQjxJmVd9D1GV9OLlLopovDnBU0wsGJ 74V65IW4G3LUtnHnC5jA4UaShDFuKHs= ARC-Authentication-Results: i=1; imf16.hostedemail.com; dkim=pass header.d=shopee.com header.s=shopee.com header.b=BhDzZDrg; spf=pass (imf16.hostedemail.com: domain of haifeng.xu@shopee.com designates 209.85.216.42 as permitted sender) smtp.mailfrom=haifeng.xu@shopee.com; dmarc=pass (policy=reject) header.from=shopee.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1773112390; a=rsa-sha256; cv=none; b=6KmPdU5bTq638K2EYdRY69rxS/nGKSMLqkVmKNFT0Gr/N2TSliMzIcEwxAeZcCMzfv81y+ bFvqULanCYLvRC/vcKD5HPwXy66YKQcm78ZYKCBy7Y2FeUyyg141wA7cc/qsN332QZJZuO GqfiQv1hV98CG+0XZrXRAfj3hhDs11Q= Received: by mail-pj1-f42.google.com with SMTP id 98e67ed59e1d1-354a18c48b5so11186871a91.1 for ; Mon, 09 Mar 2026 20:13:09 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=shopee.com; s=shopee.com; t=1773112388; x=1773717188; darn=kvack.org; 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=wsmX9IqTgTtiIKR5iSvwZiEzuk2SZ9FYiHutnUA3cX0=; b=BhDzZDrgzIGNYz1gl/LJhFlQ452bx6OFMBkQH5nIcmnyhVHQ/6rfoakxRCnqjrLtu2 x/z6IpYZsP0siWuud+zQq03m3VjOYChXePIGPCvM6KPqYKfjmrvCVRJZEN9iD4iNuSW4 nIrLECSEqfuSfBYheB3SSj2VodEUqDtC2HmLQL21XzOAf4fltFiHETnKIf2d25slPiYe IRBr4ZLXt6AA/eefvHjBKegzO5Q1Uv5WQdpgBTsJKbKmnFQRfWBcZVbSSAYGjUovhjbB d33HipJFzy7ow/VyI9zzhSvDh9svEMsUHHJhGblf1MzxnBg9vTHCJkPP9yTYEoAZo1lR 67HQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1773112388; x=1773717188; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=wsmX9IqTgTtiIKR5iSvwZiEzuk2SZ9FYiHutnUA3cX0=; b=ONXDzmyxZo7s9INWEwmQlh1HaHmgzjO4j0dFqyZLP6+uVQN+v1EYKjYh/1Rq7WGDqb yDOPMjwidxVq1G9xKyDJeIpGKTZYJ4ZwpfXT/xavdOGMekc+3H5viV4lmIjLdpfq4KZe Uwbvl5cLVomW3cXjHPzNyVybpfqmjIeOxrfsIO2iv5bYdXjnvh9scoXTgD9XN+VCCV88 k69O0VzfrLI4qIrXziSSZfiYv1KwLARteTXM3w9Gua6Jko7wX7LSpx5np7Ff4+29h0RM UgSHzMcP4lamGyZMdEF8ktmJLYux8XCgFZ6ZYB+qjsJnpWbBrW/G3EpkQJD40H7SU6Vp G49w== X-Forwarded-Encrypted: i=1; AJvYcCW51/ZAcV8hmRsO9Mk90k90LXLQSmKP5rN7ZyBfN9WugpJTigBoXsov0r9QAlDRtutfY2ceQg23CA==@kvack.org X-Gm-Message-State: AOJu0YzOvwatIw72H3JB97aEDpCNP00b7EIc6bcXSKM1Nj1hCJz52gnM /NK5eJbTFd07xTgpTpiSzqJj9KD8deLdC1CWXyNhJqIar6E4eWqaHFp4504h5/rjz2k= X-Gm-Gg: ATEYQzxI6M2Dtaxti2/qE+d2njFgezkPdZdV4guhxwur2S5NDj10h6iGz8OELyXddx9 laOcmPpZo3mfOlg3sYYp9Sixie7pW3dMkbv6gTM+KuGLCU79SNLC0RW0c7GLtNKJaAWGYFejKG4 0746VwgxBKyMzjJeBHB7u7Z6PGTz0WuMyP+Vs7Tv00n/oD4a7ohyPUM3jLDN3kC3+8EI3hUoF3g xPEFMIK3vv3b1KHwphRnWghadkk2vgvHoBQQE8YGfNl0RFutcgnAntEX/rKbKTDjDmkNATX0RUK 61Umt5r3asv9oD35q+rG/WZVdQTjsg6rwxF0Wu0O9M82GAsDL05mPsCWFSGWU7zAf4zPnMZrFUM vdZH0YQ8wjY7bcH3WgMct2YvVJFJboN7YsftC1ram5hxHMOTPe0qnxLPvAI6XQhQ/DcTFLfVq3M p7eXOer4B89rZUHX9kYMmVwkpzsUoucF3dtBqcCjR3IvjeujzQ X-Received: by 2002:a17:90b:2604:b0:359:92b5:da70 with SMTP id 98e67ed59e1d1-359be2725f4mr11208013a91.9.1773112388515; Mon, 09 Mar 2026 20:13:08 -0700 (PDT) Received: from localhost.localdomain ([147.136.157.0]) by smtp.gmail.com with ESMTPSA id 98e67ed59e1d1-359bcc28f0fsm5169284a91.13.2026.03.09.20.13.06 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 09 Mar 2026 20:13:08 -0700 (PDT) From: Haifeng Xu To: akpm@linux-foundation.org, david@fromorbit.com, roman.gushchin@linux.dev Cc: zhengqi.arch@bytedance.com, muchun.song@linux.dev, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Haifeng Xu Subject: [PATCH V2 3/4] mm: shrinker: optimize the allocation of shrinker_info when setting cgroup_memory_nokmem Date: Tue, 10 Mar 2026 11:12:49 +0800 Message-ID: <20260310031250.289851-4-haifeng.xu@shopee.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20260310031250.289851-1-haifeng.xu@shopee.com> References: <20260310031250.289851-1-haifeng.xu@shopee.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Rspam-User: X-Rspamd-Queue-Id: E09D9180004 X-Rspamd-Server: rspam08 X-Stat-Signature: myn6qpxbk8ncpbckstfn9qmzg3cg4qry X-HE-Tag: 1773112389-557519 X-HE-Meta: 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 0CafPCmr tY0iDn9ltudtRDEE6i92pdGf5WXA4wsj7hv78vhAYLCRGXnSmljOHt2J9K4/6vvY4B4tKNKkOouBONmEk4JazE9mQZSy1u3JSn6GS1EQmX7OM5fLXHhsorXtYaAZyRub4Vb0b8nMhE6xrpO/ELa46BQh5q9vL1eXjJcEUSSRYmQwbmPfNDlTEHNnLAoECx0oUMpTGLUdE15FAt7K+FGNCJhzD9e4YJ7QZD1IIopqA6InWuf/qLdSD1ikkCyY/r8wn2Pxn4Wr9y28sNJCat+mBOF+jYd9PWrimVf1FFG70p8LSO3rwPwotzFGVaZIZV3Gq6xOg5SZw9gurjPTDR1Nkt5qHdA== Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: When kmem is disabled, memcg slab shrink only call non-slab shrinkers, so just allocates shrinker info for non-slab shrinkers to non-root memcgs. Therefore, if memcg_kmem_online is true, all things keep same as before. Otherwise, root memcg allocates id from shrinker_idr to identify each shrinker and non-root memcgs use nonslab_id to identify non-slab shrinkers. The size of shrinkers_info in non-root memcgs can be very low because the number of shrinkers marked as SHRINKER_NONSLAB | SHRINKER_MEMCG_AWARE is few. Also, the time spending in expand_shrinker_info() can reduce a lot. When setting shrinker bit or updating nr_deferred, use nonslab_id for non-root memcgs if the shrinker is marked as SHRINKER_NONSLAB. Signed-off-by: Haifeng Xu --- include/linux/memcontrol.h | 8 ++- include/linux/shrinker.h | 3 + mm/shrinker.c | 116 +++++++++++++++++++++++++++++++++---- 3 files changed, 114 insertions(+), 13 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ce7b5101bc02..3edd6211aed2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1804,7 +1804,13 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg); static inline int shrinker_id(struct mem_cgroup *memcg, struct shrinker *shrinker) { - return shrinker->id; + int id = shrinker->id; + + if (!memcg_kmem_online() && (shrinker->flags & SHRINKER_NONSLAB) && + memcg != root_mem_cgroup) + id = shrinker->nonslab_id; + + return id; } #else #define mem_cgroup_sockets_enabled 0 diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 1a00be90d93a..df53008ed8b5 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -107,6 +107,9 @@ struct shrinker { #ifdef CONFIG_MEMCG /* ID in shrinker_idr */ int id; + + /* ID in shrinker_nonslab_idr */ + int nonslab_id; #endif #ifdef CONFIG_SHRINKER_DEBUG int debugfs_id; diff --git a/mm/shrinker.c b/mm/shrinker.c index 61dbb6afae52..68ea2d49495c 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -12,6 +12,7 @@ DEFINE_MUTEX(shrinker_mutex); #ifdef CONFIG_MEMCG static int shrinker_nr_max; +static int shrinker_nonslab_nr_max; static inline int shrinker_unit_size(int nr_items) { @@ -78,15 +79,25 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) { int nid, ret = 0; int array_size = 0; + int alloc_nr_max; + + if (memcg_kmem_online()) { + alloc_nr_max = shrinker_nr_max; + } else { + if (memcg == root_mem_cgroup) + alloc_nr_max = shrinker_nr_max; + else + alloc_nr_max = shrinker_nonslab_nr_max; + } mutex_lock(&shrinker_mutex); - array_size = shrinker_unit_size(shrinker_nr_max); + array_size = shrinker_unit_size(alloc_nr_max); for_each_node(nid) { struct shrinker_info *info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); if (!info) goto err; - info->map_nr_max = shrinker_nr_max; + info->map_nr_max = alloc_nr_max; if (shrinker_unit_alloc(info, NULL, nid)) { kvfree(info); goto err; @@ -147,33 +158,47 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, return 0; } -static int expand_shrinker_info(int new_id) +static int expand_shrinker_info(int new_id, bool full, bool root) { int ret = 0; int new_nr_max = round_up(new_id + 1, SHRINKER_UNIT_BITS); int new_size, old_size = 0; struct mem_cgroup *memcg; + struct mem_cgroup *start = NULL; + int old_nr_max = shrinker_nr_max; if (!root_mem_cgroup) goto out; lockdep_assert_held(&shrinker_mutex); + if (!full && !root) { + start = root_mem_cgroup; + old_nr_max = shrinker_nonslab_nr_max; + } + new_size = shrinker_unit_size(new_nr_max); - old_size = shrinker_unit_size(shrinker_nr_max); + old_size = shrinker_unit_size(old_nr_max); + + memcg = mem_cgroup_iter(NULL, start, NULL); + if (!memcg) + goto out; - memcg = mem_cgroup_iter(NULL, NULL, NULL); do { ret = expand_one_shrinker_info(memcg, new_size, old_size, new_nr_max); - if (ret) { + if (ret || (root && memcg == root_mem_cgroup)) { 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; + if (!ret) { + if (!full && !root) + shrinker_nonslab_nr_max = new_nr_max; + else + shrinker_nr_max = new_nr_max; + } return ret; } @@ -212,25 +237,58 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) } static DEFINE_IDR(shrinker_idr); +static DEFINE_IDR(shrinker_nonslab_idr); static int shrinker_memcg_alloc(struct shrinker *shrinker) { int id, ret = -ENOMEM; + bool kmem_online; if (mem_cgroup_disabled()) return -ENOSYS; + kmem_online = memcg_kmem_online(); 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)) { + /* If memcg_kmem_online() returns true, expand shrinker + * info for all memcgs, otherwise, expand shrinker info + * for root memcg only + */ + if (expand_shrinker_info(id, kmem_online, !kmem_online)) { + idr_remove(&shrinker_idr, id); + goto unlock; + } + } + + shrinker->nonslab_id = -1; + /* + * If cgroup_memory_nokmem is set, record shrinkers with SHRINKER_NONSLAB + * because memcg slab shrink only call non-slab shrinkers. + */ + if (!kmem_online && shrinker->flags & SHRINKER_NONSLAB) { + int nonslab_id; + + nonslab_id = idr_alloc(&shrinker_nonslab_idr, shrinker, 0, 0, GFP_KERNEL); + if (nonslab_id < 0) { idr_remove(&shrinker_idr, id); goto unlock; } + + if (nonslab_id >= shrinker_nonslab_nr_max) { + /* expand shrinker info for non-root memcgs */ + if (expand_shrinker_info(nonslab_id, false, false)) { + idr_remove(&shrinker_idr, id); + idr_remove(&shrinker_nonslab_idr, nonslab_id); + goto unlock; + } + } + shrinker->nonslab_id = nonslab_id; } + shrinker->id = id; ret = 0; unlock: @@ -247,6 +305,12 @@ static void shrinker_memcg_remove(struct shrinker *shrinker) lockdep_assert_held(&shrinker_mutex); idr_remove(&shrinker_idr, id); + + if (shrinker->flags & SHRINKER_NONSLAB) { + id = shrinker->nonslab_id; + if (id >= 0) + idr_remove(&shrinker_nonslab_idr, id); + } } static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker, @@ -305,10 +369,33 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent_info = shrinker_info_protected(parent, nid); for (index = 0; index < shrinker_id_to_index(child_info->map_nr_max); index++) { child_unit = child_info->unit[index]; - parent_unit = parent_info->unit[index]; for (offset = 0; offset < SHRINKER_UNIT_BITS; offset++) { nr = atomic_long_read(&child_unit->nr_deferred[offset]); - atomic_long_add(nr, &parent_unit->nr_deferred[offset]); + + /* + * If memcg_kmem_online() is false, the non-root memcgs use + * nonslab_id but root memory cgroup use id. When reparenting + * shrinker info to it, must convert the nonslab_id to id. + */ + if (!memcg_kmem_online() && parent == root_mem_cgroup) { + int id, p_index, p_off; + struct shrinker *shrinker; + + id = calc_shrinker_id(index, offset); + shrinker = idr_find(&shrinker_nonslab_idr, id); + if (shrinker) { + id = shrinker->id; + p_index = shrinker_id_to_index(id); + p_off = shrinker_id_to_offset(id); + + parent_unit = parent_info->unit[p_index]; + atomic_long_add(nr, + &parent_unit->nr_deferred[p_off]); + } + } else { + parent_unit = parent_info->unit[index]; + atomic_long_add(nr, &parent_unit->nr_deferred[offset]); + } } } } @@ -538,7 +625,12 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, int shrinker_id = calc_shrinker_id(index, offset); rcu_read_lock(); - shrinker = idr_find(&shrinker_idr, shrinker_id); + + if (memcg_kmem_online()) + shrinker = idr_find(&shrinker_idr, shrinker_id); + else + shrinker = idr_find(&shrinker_nonslab_idr, shrinker_id); + if (unlikely(!shrinker || !shrinker_try_get(shrinker))) { clear_bit(offset, unit->map); rcu_read_unlock(); -- 2.43.0