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]) by smtp.lore.kernel.org (Postfix) with ESMTP id 92A5CC369A1 for ; Tue, 8 Apr 2025 18:17:15 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 8FDD528001A; Tue, 8 Apr 2025 14:17:13 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 8ACED280019; Tue, 8 Apr 2025 14:17:13 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 774B428001A; Tue, 8 Apr 2025 14:17:13 -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 5A039280019 for ; Tue, 8 Apr 2025 14:17:13 -0400 (EDT) Received: from smtpin12.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay08.hostedemail.com (Postfix) with ESMTP id BE94D14086A for ; Tue, 8 Apr 2025 18:17:13 +0000 (UTC) X-FDA: 83311683546.12.0D3DD59 Received: from mail-qv1-f49.google.com (mail-qv1-f49.google.com [209.85.219.49]) by imf01.hostedemail.com (Postfix) with ESMTP id A540B40008 for ; Tue, 8 Apr 2025 18:17:11 +0000 (UTC) Authentication-Results: imf01.hostedemail.com; dkim=pass header.d=cmpxchg-org.20230601.gappssmtp.com header.s=20230601 header.b=V+emFKaa; dmarc=pass (policy=none) header.from=cmpxchg.org; spf=pass (imf01.hostedemail.com: domain of hannes@cmpxchg.org designates 209.85.219.49 as permitted sender) smtp.mailfrom=hannes@cmpxchg.org ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1744136231; a=rsa-sha256; cv=none; b=UDvu6CpGv3+682pdQHDWsiHJtZ6yaVNB38Xdzca6NlI601gwKgSO9b7b67lUHSY6RvWVRv +DqppJYPgvpgaPJPqH8melGO8RsEQJWZVo8J2CnpOMJiMs36V3MR6lQMFHV15yW8TJWE1m LXRLWj2umgZNlMIf8Nfg6kvehxdTdJI= ARC-Authentication-Results: i=1; imf01.hostedemail.com; dkim=pass header.d=cmpxchg-org.20230601.gappssmtp.com header.s=20230601 header.b=V+emFKaa; dmarc=pass (policy=none) header.from=cmpxchg.org; spf=pass (imf01.hostedemail.com: domain of hannes@cmpxchg.org designates 209.85.219.49 as permitted sender) smtp.mailfrom=hannes@cmpxchg.org ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1744136231; 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-type:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=BrHRR9y6PG02gx4V+fHyD3RAGrPoiHPM2zS7NCT7idM=; b=Yqy/vJjlueJDicubKwj2Wvg+kPkqydPe+PDaOB27R4nduyBYwHqSL2yP3HJJMQqq4hXln6 ZT2VdVlxXo1YA/AatuV4mcycOoPT/xLUYkJIbug7WiyQE9ppJBjYJwjTVJBFfvVOz9aR0I 2lPzETITAhkH/uYHvY2hmhx7pEGwZyU= Received: by mail-qv1-f49.google.com with SMTP id 6a1803df08f44-6e8fd49b85eso90726946d6.0 for ; Tue, 08 Apr 2025 11:17:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=cmpxchg-org.20230601.gappssmtp.com; s=20230601; t=1744136230; x=1744741030; darn=kvack.org; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:from:to:cc:subject:date:message-id:reply-to; bh=BrHRR9y6PG02gx4V+fHyD3RAGrPoiHPM2zS7NCT7idM=; b=V+emFKaaXwgFCgmtyOaz8hnJhjiAiFTKGaKLq+eUEKjP8MjOXwRfIyVKVtSW6oXN2e pzP8irGQxJCJQcjKeBaaNC+m1xIMvtE5Hslp//SSsjnlZIh/LEDE9UHU2xhDCmxFGetk 3M1K0BUaUD67c2Dlh7rm7EJhviUO8bB0YCw3NCvH7uLYHv0Oz2ooJlRFR7ukOoFBYXED 26HYczsfgEryiDcdqNnaQyKMHWlRM7btnMS211RANwF/OrVhTt7y9KOAsx8fhv6GP6B8 Ri/+P4qQxmaO34VrvCbA5v8X1disAWVNv3V+jLSJnDIQQcqNmLQCcx2KNqg8dYspgqko n4hg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1744136230; x=1744741030; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to; bh=BrHRR9y6PG02gx4V+fHyD3RAGrPoiHPM2zS7NCT7idM=; b=QI+BAIzEQkKHNfn25PoQJURgIAdn0zF3N5VovJ/2qKpZW/VrBq7BoA2juZhhk+kmgN loSdiG47syFDdLn77j918UbEpfYRAiZyRLZRewrq/frR+QOHpzXyjKc4DmD066Cmr4a0 65r+5s71HlWS2rwom6Rj0fP5yktxFBuVi9Mzp6JsCdRQaTPHzTDYRIjWnoLj0mnVruAF vX9quObwYd3L7n68z8+QDju3OlSrQGG8zzxkcHs03cezfLtVDs6FTP82CImhM8SeIcod Ske8j/Oe0c2SWUP1tWMD4Mk06MccpptCc/cxFGfWm1HK/SRykVvB4cl0g5fRwv4XsJRV 8aeA== X-Gm-Message-State: AOJu0YxxVPTIuNrpWFocStdpbCAsZBEbpnhPDJ6dcAssH3IrOENmSmz6 QytM1G5U5ZDklnR7OXn+Z4yNS1P8dv020ospmeuPj0aWttKaz2N0NEd3nuLhSAM= X-Gm-Gg: ASbGncvnuOEHiM1ER6Io0zCiq8ZnPTC8c/GYFJ4jJJDJ7qMNU+dYoOXGaXRtAcTriYd qQKcIvrKdB59p0+OlBCG0togCQY/LIQxX9uJlGfPe8roHhsGQQWGzwODBzxKwKCU5G+l6I8KRyt ay7Ib2jlcMft8o+wvWRn60Y8cNTjF666JciZ4Svd2aS0n+xvgapA51XNWvGCBaXzaUZe6v8yMw/ Q2TcvCPgRs8/t37dwU5ZQgcAPQNKew4EZXkkPisGxRi8c7yVN+s7GCHbHMLx7KAH4bwj6k99W+h n7S/uQ6PpPAmwiIhQkFPUq3i82MMTmX0Jil/J1d1HJ8= X-Google-Smtp-Source: AGHT+IGetL0w8Iqx6ksx4UMXO4UBW+UpVV0Mr2wV49qnLQpAF+xnj3dG0U6YvK047fPnsSyEL3Dviw== X-Received: by 2002:a05:6214:1c46:b0:6ea:face:e33f with SMTP id 6a1803df08f44-6f0dbb80e6bmr4085246d6.3.1744136230650; Tue, 08 Apr 2025 11:17:10 -0700 (PDT) Received: from localhost ([2603:7000:c01:2716:365a:60ff:fe62:ff29]) by smtp.gmail.com with UTF8SMTPSA id 6a1803df08f44-6ef0efc0d42sm77385086d6.13.2025.04.08.11.17.09 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 08 Apr 2025 11:17:09 -0700 (PDT) Date: Tue, 8 Apr 2025 14:17:05 -0400 From: Johannes Weiner To: Gregory Price Cc: linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, kernel-team@meta.com, longman@redhat.com, tj@kernel.org, mkoutny@suse.com, akpm@linux-foundation.org Subject: Re: [RFC PATCH] vmscan,cgroup: apply mems_effective to reclaim Message-ID: <20250408181705.GE816@cmpxchg.org> References: <20250320210919.439964-1-gourry@gourry.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20250320210919.439964-1-gourry@gourry.net> X-Rspam-User: X-Rspamd-Server: rspam03 X-Rspamd-Queue-Id: A540B40008 X-Stat-Signature: r4cpa3ffxd9uipzx9kqtasj3m1bc6cyi X-HE-Tag: 1744136231-864526 X-HE-Meta: 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 SPJKtMrR 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 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: List-Subscribe: List-Unsubscribe: On Thu, Mar 20, 2025 at 05:09:19PM -0400, Gregory Price wrote: > @@ -4296,3 +4296,13 @@ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) > seq_printf(m, "Mems_allowed_list:\t%*pbl\n", > nodemask_pr_args(&task->mems_allowed)); > } > + > +bool memcg_mems_allowed(struct mem_cgroup *memcg, int nid) This should probably be cgroup_mems_allowed(struct cgroup *, int) and then have a mem_cgroup_mems_allowed(struct mem_cgroup *, int) that does the e_css translation, with the necessary dummy functions to work with all CONFIG combinations. > +{ > + struct cgroup_subsys_state *css; > + struct cpuset *cs; > + > + css = cgroup_get_e_css(memcg->css.cgroup, &cpuset_cgrp_subsys); > + cs = css ? container_of(css, struct cpuset, css) : NULL; > + return cs ? node_isset(nid, cs->effective_mems) : true; You need a css_put() to drop the ref from cgroup_get_e_css(), but otherwise accessing css should be safe this way. AFAICS you need callback_lock to query cs->effective_mems. > diff --git a/mm/vmscan.c b/mm/vmscan.c > index 2b2ab386cab5..04152ea1c03d 100644 > --- a/mm/vmscan.c > +++ b/mm/vmscan.c > @@ -342,16 +342,22 @@ static void flush_reclaim_state(struct scan_control *sc) > } > } > > -static bool can_demote(int nid, struct scan_control *sc) > +static bool can_demote(int nid, struct scan_control *sc, > + struct mem_cgroup *memcg) > { > + int demotion_nid; > + > if (!numa_demotion_enabled) > return false; > if (sc && sc->no_demotion) > return false; > - if (next_demotion_node(nid) == NUMA_NO_NODE) > + > + demotion_nid = next_demotion_node(nid); > + if (demotion_nid == NUMA_NO_NODE) > return false; > > - return true; > + /* If demotion node isn't in mems_allowed, fall back */ > + return memcg ? memcg_mems_allowed(memcg, demotion_nid) : true; > } > > static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, > @@ -376,7 +382,7 @@ static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg, > * > * Can it be reclaimed from this node via demotion? > */ > - return can_demote(nid, sc); > + return can_demote(nid, sc, NULL); This has appropriate memcg context from get_scan_count(), use that. > @@ -2654,7 +2662,7 @@ static bool can_age_anon_pages(struct pglist_data *pgdat, > return true; > > /* Also valuable if anon pages can be demoted: */ > - return can_demote(pgdat->node_id, sc); > + return can_demote(pgdat->node_id, sc, NULL); Make this take an lruvec, then pass lruvec_memcg() to can_demote(). shrink_lruvec() already has the lruvec. kswapd_age_node() has to do the test from inside the memcg loop, since demotion and thus aging now very much depends on each cgroup's policy. > } > > #ifdef CONFIG_LRU_GEN > @@ -2732,7 +2740,7 @@ static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc) > if (!sc->may_swap) > return 0; > > - if (!can_demote(pgdat->node_id, sc) && > + if (!can_demote(pgdat->node_id, sc, NULL) && > mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) > return 0; MGLRU, so grain of salt, but that memcg looks appropriate for passing. > @@ -4695,7 +4703,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap > if (list_empty(&list)) > return scanned; > retry: > - reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false); > + reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false, NULL); This also seems to have appropriate lruvec/memcg context.