From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from out-189.mta0.migadu.com (out-189.mta0.migadu.com [91.218.175.189]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 549714582CB for ; Tue, 11 Aug 2026 20:32:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=91.218.175.189 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786480363; cv=none; b=MJz3FPa73n4Ptn9k4paK/y4A/nbT1S6DKM/Hvh8pH/y57B9eRkVFQtxxGRBqeLnUJVlhZAtQ5SbD/FpbbB4btcsHzZtP/VVtPLIZ9HzZGHrybaUcyFPMMxzs/eoOMXC8HbZAD1DBo9QrN7ZxsrGkdaH27SRYBOrGQj69MR1yTs4= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786480363; c=relaxed/simple; bh=YqMU9RNZUNzFsU+YziNRY+pkIuQVvc6LRzjzYDGTFVA=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=i6EA/ld5Vb3tcCpegNfZv4yqPW8rj4ndiSqSiowcmG/dDjMNYdkaKjtLLKJ1oJYDTdbMRmkK8hSu6WpZTQKjKfz5ZD9f3mF7EmeNcoVMrUbwYoWwGJgTuuHK78EFvax+a12UMpobEeB+lz+Qpr9/NNCRzuvfu0+agRy9odr8MO8= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=uN9AUmp6; arc=none smtp.client-ip=91.218.175.189 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="uN9AUmp6" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1786480358; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=mfoSEEh1wmZsAndftJOLrD9wrMxUb9iE4ebdJd4337w=; b=uN9AUmp6oVwQ9Y1xltyPWBsey4c26TsO6lpQJe3mzugLda498cXA4sDAqL0xIPmFpYHhrF baUc0Yc7yojMKFA+kP4oF9WjOnBtnr74qoSCWjFglB9iVM+arTO+dlCqlzityWDxbV9BFX Hc+5lXXRt8MPFJZqpySkmpMUr20fD6U= From: Shakeel Butt To: Andrew Morton Cc: Michal Hocko , Johannes Weiner , Roman Gushchin , Muchun Song , David Hildenbrand , Lorenzo Stoakes , Kairui Song , Qi Zheng , Barry Song , Axel Rasmussen , Meta kernel team , linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH 5/9] memcg: remove the soft limit rbtree Date: Tue, 11 Aug 2026 13:31:59 -0700 Message-ID: <20260811203203.3456029-6-shakeel.butt@linux.dev> In-Reply-To: <20260811203203.3456029-1-shakeel.butt@linux.dev> References: <20260811203203.3456029-1-shakeel.butt@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Migadu-Flow: FLOW_OUT With soft limit reclaim gone, the per-node rbtree of cgroups in excess has no readers left. Remove the tree, the helpers maintaining it, and the subsys_initcall that existed only to allocate it. memcg1_check_events() no longer needs to feed it, which also drops the last caller of lru_gen_soft_reclaim(). Signed-off-by: Shakeel Butt --- mm/memcontrol-v1.c | 176 +-------------------------------------------- mm/memcontrol-v1.h | 2 - mm/memcontrol.c | 1 - 3 files changed, 2 insertions(+), 177 deletions(-) diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index b38b8d0f7f51..475f998b7643 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -17,23 +17,6 @@ #include "swap_table.h" #include "memcontrol-v1.h" -/* - * Cgroups above their limits are maintained in a RB-Tree, independent of - * their hierarchy representation - */ - -struct mem_cgroup_tree_per_node { - struct rb_root rb_root; - struct rb_node *rb_rightmost; - spinlock_t lock; -}; - -struct mem_cgroup_tree { - struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; -}; - -static struct mem_cgroup_tree soft_limit_tree __read_mostly; - /* for OOM */ struct mem_cgroup_eventfd_list { struct list_head list; @@ -99,133 +82,6 @@ static struct lockdep_map memcg_oom_lock_dep_map = { DEFINE_SPINLOCK(memcg_oom_lock); -static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz, - unsigned long new_usage_in_excess) -{ - struct rb_node **p = &mctz->rb_root.rb_node; - struct rb_node *parent = NULL; - struct mem_cgroup_per_node *mz_node; - bool rightmost = true; - - if (mz->on_tree) - return; - - mz->usage_in_excess = new_usage_in_excess; - if (!mz->usage_in_excess) - return; - while (*p) { - parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_node, - tree_node); - if (mz->usage_in_excess < mz_node->usage_in_excess) { - p = &(*p)->rb_left; - rightmost = false; - } else { - p = &(*p)->rb_right; - } - } - - if (rightmost) - mctz->rb_rightmost = &mz->tree_node; - - rb_link_node(&mz->tree_node, parent, p); - rb_insert_color(&mz->tree_node, &mctz->rb_root); - mz->on_tree = true; -} - -static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz) -{ - if (!mz->on_tree) - return; - - if (&mz->tree_node == mctz->rb_rightmost) - mctz->rb_rightmost = rb_prev(&mz->tree_node); - - rb_erase(&mz->tree_node, &mctz->rb_root); - mz->on_tree = false; -} - -static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz, - struct mem_cgroup_tree_per_node *mctz) -{ - unsigned long flags; - - spin_lock_irqsave(&mctz->lock, flags); - __mem_cgroup_remove_exceeded(mz, mctz); - spin_unlock_irqrestore(&mctz->lock, flags); -} - -static unsigned long soft_limit_excess(struct mem_cgroup *memcg) -{ - unsigned long nr_pages = page_counter_read(&memcg->memory); - unsigned long soft_limit = READ_ONCE(memcg->soft_limit); - unsigned long excess = 0; - - if (nr_pages > soft_limit) - excess = nr_pages - soft_limit; - - return excess; -} - -static void memcg1_update_tree(struct mem_cgroup *memcg, int nid) -{ - unsigned long excess; - struct mem_cgroup_per_node *mz; - struct mem_cgroup_tree_per_node *mctz; - - if (lru_gen_enabled()) { - if (soft_limit_excess(memcg)) - lru_gen_soft_reclaim(memcg, nid); - return; - } - - mctz = soft_limit_tree.rb_tree_per_node[nid]; - if (!mctz) - return; - /* - * Necessary to update all ancestors when hierarchy is used. - * because their event counter is not touched. - */ - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = memcg->nodeinfo[nid]; - excess = soft_limit_excess(memcg); - /* - * We have to update the tree if mz is on RB-tree or - * mem is over its softlimit. - */ - if (excess || mz->on_tree) { - unsigned long flags; - - spin_lock_irqsave(&mctz->lock, flags); - /* if on-tree, remove it */ - if (mz->on_tree) - __mem_cgroup_remove_exceeded(mz, mctz); - /* - * Insert again. mz->usage_in_excess will be updated. - * If excess is 0, no tree ops. - */ - __mem_cgroup_insert_exceeded(mz, mctz, excess); - spin_unlock_irqrestore(&mctz->lock, flags); - } - } -} - -void memcg1_remove_from_trees(struct mem_cgroup *memcg) -{ - struct mem_cgroup_tree_per_node *mctz; - struct mem_cgroup_per_node *mz; - int nid; - - for_each_node(nid) { - mz = memcg->nodeinfo[nid]; - mctz = soft_limit_tree.rb_tree_per_node[nid]; - if (mctz) - mem_cgroup_remove_exceeded(mz, mctz); - } -} - static u64 mem_cgroup_move_charge_read(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -336,7 +192,7 @@ static void mem_cgroup_threshold(struct mem_cgroup *memcg) } } -/* Cgroup1: threshold notifications & softlimit tree updates */ +/* Cgroup1: threshold notifications */ /* * Per memcg event counter is incremented at every pagein/pageout. With THP, @@ -405,17 +261,8 @@ static void memcg1_check_events(struct mem_cgroup *memcg, int nid) if (IS_ENABLED(CONFIG_PREEMPT_RT)) return; - /* threshold event is triggered in finer grain than soft limit */ - if (unlikely(memcg1_event_ratelimit(memcg, - MEM_CGROUP_TARGET_THRESH))) { - bool do_softlimit; - - do_softlimit = memcg1_event_ratelimit(memcg, - MEM_CGROUP_TARGET_SOFTLIMIT); + if (unlikely(memcg1_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) mem_cgroup_threshold(memcg); - if (unlikely(do_softlimit)) - memcg1_update_tree(memcg, nid); - } } void memcg1_commit_charge(struct folio *folio, struct mem_cgroup *memcg) @@ -2391,22 +2238,3 @@ void memcg1_free_events(struct mem_cgroup *memcg) { free_percpu(memcg->events_percpu); } - -static int __init memcg1_init(void) -{ - int node; - - for_each_node(node) { - struct mem_cgroup_tree_per_node *rtpn; - - rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, node); - - rtpn->rb_root = RB_ROOT; - rtpn->rb_rightmost = NULL; - spin_lock_init(&rtpn->lock); - soft_limit_tree.rb_tree_per_node[node] = rtpn; - } - - return 0; -} -subsys_initcall(memcg1_init); diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h index 1e394269c613..fd611e66859a 100644 --- a/mm/memcontrol-v1.h +++ b/mm/memcontrol-v1.h @@ -41,7 +41,6 @@ bool memcg1_alloc_events(struct mem_cgroup *memcg); void memcg1_free_events(struct mem_cgroup *memcg); void memcg1_memcg_init(struct mem_cgroup *memcg); -void memcg1_remove_from_trees(struct mem_cgroup *memcg); static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) { @@ -98,7 +97,6 @@ static inline bool memcg1_alloc_events(struct mem_cgroup *memcg) { return true; static inline void memcg1_free_events(struct mem_cgroup *memcg) {} static inline void memcg1_memcg_init(struct mem_cgroup *memcg) {} -static inline void memcg1_remove_from_trees(struct mem_cgroup *memcg) {} static inline void memcg1_soft_limit_reset(struct mem_cgroup *memcg) {} static inline void memcg1_css_offline(struct mem_cgroup *memcg) {} diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1d3339520809..b68f1f16ae54 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4394,7 +4394,6 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) vmpressure_cleanup(&memcg->vmpressure); cancel_work_sync(&memcg->high_work); - memcg1_remove_from_trees(memcg); free_shrinker_info(memcg); mem_cgroup_free(memcg); } -- 2.53.0-Meta