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 518F5CD343F for ; Mon, 18 May 2026 22:28:59 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 8B0756B0005; Mon, 18 May 2026 18:28:58 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 861196B0088; Mon, 18 May 2026 18:28:58 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 776776B008C; Mon, 18 May 2026 18:28:58 -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 60CA16B0005 for ; Mon, 18 May 2026 18:28:58 -0400 (EDT) Received: from smtpin18.hostedemail.com (lb01a-stub [10.200.18.249]) by unirelay05.hostedemail.com (Postfix) with ESMTP id CB17540AF4 for ; Mon, 18 May 2026 22:28:57 +0000 (UTC) X-FDA: 84781981914.18.5A34816 Received: from out-171.mta0.migadu.com (out-171.mta0.migadu.com [91.218.175.171]) by imf07.hostedemail.com (Postfix) with ESMTP id E73914000A for ; Mon, 18 May 2026 22:28:55 +0000 (UTC) Authentication-Results: imf07.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=MfDbF6Ay; dmarc=pass (policy=none) header.from=linux.dev; spf=pass (imf07.hostedemail.com: domain of shakeel.butt@linux.dev designates 91.218.175.171 as permitted sender) smtp.mailfrom=shakeel.butt@linux.dev ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1779143336; 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:references:dkim-signature; bh=eNkqK2A55he/AkNTcmEivfEujicKPHNpUvazuTitr7U=; b=gwqCA3TO/N9ZQpdG8fDYGYnBEX69Tl9OdNq+ta9VNIppCl2h/P4AisIxBlumwy++HS6x+U 6LvrKuhC/PF3+eu0niUwLeSjguYGjxrkN3xj9I5XN25Sfwow212cHJFbSk1FNtkFtEkUzJ wvkx5GE5OjY7o+CRf/kZVyJRu7piqA0= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1779143336; a=rsa-sha256; cv=none; b=IjKrN/M7aITY7XWV+TYryr6yznv0OmusF7FhHyn5vse4Nv6bAEXh2FXJXJUrbfGkL7FVWY UOF3C5ZJpcwG8fUzk4BU5lkKdR/MPazY+a30RRGgJ1MFgAxhZLdN+fMgjTtjyHHBEyInGQ SaRpH9Ug9RDXLRmjo2MaawbGmxqbwe8= ARC-Authentication-Results: i=1; imf07.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=MfDbF6Ay; dmarc=pass (policy=none) header.from=linux.dev; spf=pass (imf07.hostedemail.com: domain of shakeel.butt@linux.dev designates 91.218.175.171 as permitted sender) smtp.mailfrom=shakeel.butt@linux.dev 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=1779143333; 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; bh=eNkqK2A55he/AkNTcmEivfEujicKPHNpUvazuTitr7U=; b=MfDbF6AyWkNiedUaGRpVlVBH78K8WfmWXypNTh15kLqzTYdIwlwYP58CInVnc9uPKO+56C nQdhXnWAwVry7m6A1aKupi+6zoMg0mIk9UF0vVnWlvlz7UCJBHPhYJEp5Q0cFxG6krnLjb 0z9m95s//rNavmPx3tyEWbJdtnlOq9c= From: Shakeel Butt To: Andrew Morton Cc: Johannes Weiner , Michal Hocko , Roman Gushchin , Muchun Song , Qi Zheng , Alexandre Ghiti , Joshua Hahn , Meta kernel team , linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, kernel test robot Subject: [PATCH v3] memcg: cache obj_stock by memcg, not by objcg pointer Date: Mon, 18 May 2026 15:28:27 -0700 Message-ID: <20260518222827.110696-1-shakeel.butt@linux.dev> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Migadu-Flow: FLOW_OUT X-Rspamd-Server: rspam11 X-Rspamd-Queue-Id: E73914000A X-Stat-Signature: 6nqbff44wipuo6puco3txcd5an8u4oxz X-Rspam-User: X-HE-Tag: 1779143335-403125 X-HE-Meta: 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 q+0n585z 6ki7lA4mr4mgrnZvtQVTtVIEqezZ4YqIJhqqtnC+3iRO5Rd38EhxHMhCptCfcHYpwYJd1BvWgvUrh3iyz28XOfQ7j/iMiQ+CCa9r2UetjdEVhW/d1ZqLR39K9qErCp/fchz3XbqTDMT5JlHHRcQ/HPMDBQYsFqDKf4iGBYMHtHJWSEotfzN3rhmE/WIptwHd09QBaQUGCcAct6MndSABfznHoyEk4EQcGdnro7wymrz725JQ3Cqnd8XjtbuC+nszAkE7FCUFkfs4TIqwDNywYDsJIcfz4nUiT+MZUm80W5qdplix3BIUptKceZ6IgNTOlC4jsCjhd5pvF0O21V+YzHkYji+EBInED/njtNBUoz2AXwzA= Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: Commit 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg per-node type") split a memcg's single obj_cgroup into one per NUMA node, but the per-CPU obj_stock_pcp still keys cached_objcg by pointer. Cross-NUMA workloads now see a drain on every refill and a miss on every consume that targets a sibling per-node objcg of the same memcg, producing the 67.7% stress-ng switch-mq regression reported by LKP. stock->nr_bytes are fungible across per-node objcgs of one memcg. Treat the cache as keyed by memcg in __consume_obj_stock() and __refill_obj_stock() so siblings share the reserve. Compare via READ_ONCE(objcg->memcg) directly: pointer-compare only, no deref, so the rcu_read_lock contract on obj_cgroup_memcg() does not apply. Sharing the reserve without re-caching means bytes funded by one per-node objcg's slow path can be consumed/freed under a different sibling, leaving sub-page residue on whichever sibling was cached at drain time. The pre-existing obj_cgroup_release() path would WARN and silently drop that residue, leaking up to nr_node_ids * (PAGE_SIZE - 1) bytes per memcg lifecycle from the page_counter. Forward the residue into a per-node objcg of the same (post-reparent) memcg at release time instead, so it can be reconciled later via a refill atomic_xchg or another release; the chain terminates at root_mem_cgroup, whose page_counter has no enforced limit. Please note that this is temporary fix and will be reverted when per-node kmem accounting is introduced. Update the stale invariant comment on __account_obj_stock(). Qi Zheng built a specialized reproducer [1] for the corner case and confirmed the fix. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202605121641.b6a60cb0-lkp@intel.com Fixes: 01b9da291c49 ("mm: memcontrol: convert objcg to be per-memcg per-node type") Link: https://lore.kernel.org/19693be6-7132-446e-b3fc-b7e9f56e5949@linux.dev/ [1] Signed-off-by: Shakeel Butt Debugged-by: Qi Zheng --- Changes since v2: https://lore.kernel.org/20260517194308.952655-1-shakeel.butt@linux.dev/ - Instead of handling sub-page charged residue at refill time, let's handle it at the obj_cgroup_release time. Changes since v1: https://lore.kernel.org/20260515171953.2224503-1-shakeel.butt@linux.dev/ - Fix the rcu warning (Sashiko). - Fix the page counter possible underflow warning (Sashiko). mm/memcontrol.c | 69 ++++++++++++++++++++++++++++++++++++------------- 1 file changed, 51 insertions(+), 18 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index d978e18b9b2d..a547ec7c42d1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -142,14 +142,24 @@ static void obj_cgroup_release(struct percpu_ref *ref) struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); unsigned int nr_bytes; unsigned int nr_pages; + unsigned int sub_bytes; unsigned long flags; /* - * At this point all allocated objects are freed, and - * objcg->nr_charged_bytes can't have an arbitrary byte value. - * However, it can be PAGE_SIZE or (x * PAGE_SIZE). + * At this point all allocated objects are freed, but + * objcg->nr_charged_bytes can still hold either + * - (x * PAGE_SIZE) if a small-alloc/drain race left whole pages + * stranded (see the historical sequence below), or + * - any sub-page residue, now that the stock is keyed by memcg and + * sibling per-node objcgs share its reserve: bytes consumed by + * one sibling can spill into another sibling's nr_charged_bytes + * when the stock is drained. * - * The following sequence can lead to it: + * Uncharge the page-aligned portion from this objcg's (post-reparent) + * memcg, and forward any sub-page residue into a per-node objcg of + * the same memcg so it can be reconciled later instead of being lost. + * + * Historical race producing the (x * PAGE_SIZE) case: * 1) CPU0: objcg == stock->cached_objcg * 2) CPU1: we do a small allocation (e.g. 92 bytes), * PAGE_SIZE bytes are charged @@ -160,23 +170,33 @@ static void obj_cgroup_release(struct percpu_ref *ref) * 92 bytes are added to stock->nr_bytes * 6) CPU0: stock is flushed, * 92 bytes are added to objcg->nr_charged_bytes - * - * In the result, nr_charged_bytes == PAGE_SIZE. - * This page will be uncharged in obj_cgroup_release(). */ nr_bytes = atomic_read(&objcg->nr_charged_bytes); - WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); nr_pages = nr_bytes >> PAGE_SHIFT; + sub_bytes = nr_bytes & (PAGE_SIZE - 1); - if (nr_pages) { + if (nr_pages || sub_bytes) { struct mem_cgroup *memcg; - memcg = get_mem_cgroup_from_objcg(objcg); - mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages); - memcg1_account_kmem(memcg, -nr_pages); - if (!mem_cgroup_is_root(memcg)) - memcg_uncharge(memcg, nr_pages); - mem_cgroup_put(memcg); + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + + if (nr_pages) { + mod_memcg_state(memcg, MEMCG_KMEM, -nr_pages); + memcg1_account_kmem(memcg, -nr_pages); + if (!mem_cgroup_is_root(memcg)) + memcg_uncharge(memcg, nr_pages); + } + + if (sub_bytes && !mem_cgroup_is_root(memcg)) { + struct obj_cgroup *fwd; + + fwd = rcu_dereference( + memcg->nodeinfo[numa_node_id()]->objcg); + if (fwd) + atomic_add(sub_bytes, &fwd->nr_charged_bytes); + } + rcu_read_unlock(); } spin_lock_irqsave(&objcg_lock, flags); @@ -3152,7 +3172,12 @@ static void unlock_stock(struct obj_stock_pcp *stock) local_unlock(&obj_stock.lock); } -/* Call after __refill_obj_stock() to ensure stock->cached_objg == objcg */ +/* + * Call after __consume_obj_stock() / __refill_obj_stock(). The stock may be + * cached for a sibling per-node objcg of the same memcg; in that case the + * vmstat batching slot does not match objcg and we fallthrough to the + * direct path. + */ static void __account_obj_stock(struct obj_cgroup *objcg, struct obj_stock_pcp *stock, int nr, struct pglist_data *pgdat, enum node_stat_item idx) @@ -3210,7 +3235,11 @@ static bool __consume_obj_stock(struct obj_cgroup *objcg, struct obj_stock_pcp *stock, unsigned int nr_bytes) { - if (objcg == READ_ONCE(stock->cached_objcg) && + struct obj_cgroup *cached = READ_ONCE(stock->cached_objcg); + + /* Sibling per-node objcgs share the reserve. */ + if ((cached == objcg || + (cached && READ_ONCE(cached->memcg) == READ_ONCE(objcg->memcg))) && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; return true; @@ -3318,6 +3347,7 @@ static void __refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, bool allow_uncharge) { + struct obj_cgroup *cached; unsigned int nr_pages = 0; if (!stock) { @@ -3327,7 +3357,10 @@ static void __refill_obj_stock(struct obj_cgroup *objcg, goto out; } - if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */ + cached = READ_ONCE(stock->cached_objcg); + /* Direct READ_ONCE due to just pointer comparison. */ + if (cached != objcg && + (!cached || READ_ONCE(cached->memcg) != READ_ONCE(objcg->memcg))) { drain_obj_stock(stock); obj_cgroup_get(objcg); stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) -- 2.53.0-Meta