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 3AB77CA1012 for ; Sat, 6 Sep 2025 06:36:14 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 74A018E0006; Sat, 6 Sep 2025 02:36:13 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 721A18E0003; Sat, 6 Sep 2025 02:36:13 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 65E938E0006; Sat, 6 Sep 2025 02:36:13 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0012.hostedemail.com [216.40.44.12]) by kanga.kvack.org (Postfix) with ESMTP id 4D2E18E0003 for ; Sat, 6 Sep 2025 02:36:13 -0400 (EDT) Received: from smtpin05.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay08.hostedemail.com (Postfix) with ESMTP id 02AD7140232 for ; Sat, 6 Sep 2025 06:36:12 +0000 (UTC) X-FDA: 83857865826.05.50092EC Received: from out-181.mta0.migadu.com (out-181.mta0.migadu.com [91.218.175.181]) by imf06.hostedemail.com (Postfix) with ESMTP id 9C78F180003 for ; Sat, 6 Sep 2025 06:36:10 +0000 (UTC) Authentication-Results: imf06.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=MGbr7vuP; spf=pass (imf06.hostedemail.com: domain of lance.yang@linux.dev designates 91.218.175.181 as permitted sender) smtp.mailfrom=lance.yang@linux.dev; dmarc=pass (policy=none) header.from=linux.dev ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1757140571; 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:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=hZI+7xxBYSUjf2DkYRpNjguP0eowa/Qcb8yf8x4bp6o=; b=jnwDO7Fwktj4SkTxq0cle2GgJOaCBtCfs4l9EIiYax5tu0KZdxdFVqX9n5czM9vaw//Jwj GKhtqnnqet08rf2P4ZewGQYl0+DvadnwBOWu6ElJR1u7ramBjLuri5eAYOQOh1jpRR/IfZ zyQuljbxY2nUKG6sydap1JF54bTzX7U= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1757140571; a=rsa-sha256; cv=none; b=fTTR6PkrBcATJyr1Cw+4xiiKHDu57j56btM2op11EpTIfOdfvzvegBkOtFCvlhlx6hy/tl 2ZRwaBnLWpxBqBPS1Qo1Msjp2zs5axk3Xvm3LQ2jEQlujgtRaWXtuZNldIW8/v94YWHMMW qelca93SJVOwfYWwV3yh9vVNPj7ticA= ARC-Authentication-Results: i=1; imf06.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=MGbr7vuP; spf=pass (imf06.hostedemail.com: domain of lance.yang@linux.dev designates 91.218.175.181 as permitted sender) smtp.mailfrom=lance.yang@linux.dev; dmarc=pass (policy=none) header.from=linux.dev X-Forwarded-Encrypted: i=1; AJvYcCXMPNKismehuD4MvPJs/rGd6MsfCKuKXnhINbPDIjW0Fl3fxw/ZbFVYuzQ63WzM5gXtQgTrvukS4g==@kvack.org DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1757140568; h=from:from: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:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=hZI+7xxBYSUjf2DkYRpNjguP0eowa/Qcb8yf8x4bp6o=; b=MGbr7vuPvLbBEG7xfZrVys+nQblKZ+RbeJznQLP7LibZmJ+2DF4t9UA35xoA1dcla/NaB/ aEU2y3HNYDPUv2aRQO5GlMmRpoKCUen8pl8VFSSjsxmL+TW6dmd9sW6oJSY0f6SYg1HFJ+ mv6ESF5qQ95Q1Cgtr9PAYocX4kCzPgk= X-Gm-Message-State: AOJu0Yy8zXZQD5iTg8412c6Ieo2viiea+JgS7lz7IzGdnT3fVfo9tOLF 6EucxAguhhlrBdAu0t8ovsaOlsd/hRDcWqVbKZzARNtha92fUVZQThuEGw3IV3Yb3XjJ7XvLfXy VeZ0sP1N4XSlQa3OAWAcG9pdhE9PAboU= X-Google-Smtp-Source: AGHT+IGNxstH+GnVHJBOvOkXVFQ94aleFh61ynH/0fgSb7qxhJXuopaMmAthk78PTShzywiIxlJt1lhTtSRXJ8mx3gI= X-Received: by 2002:a05:6214:2302:b0:712:9051:c001 with SMTP id 6a1803df08f44-73922f67c33mr15297266d6.12.1757140556079; Fri, 05 Sep 2025 23:35:56 -0700 (PDT) MIME-Version: 1.0 References: <20250905141137.3529867-1-david@redhat.com> <7B0B1E09-5083-449F-851D-FD63D32D2B3D@nvidia.com> <2f4141b3-bd66-415d-b2ff-00544b03b908@redhat.com> In-Reply-To: <2f4141b3-bd66-415d-b2ff-00544b03b908@redhat.com> X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: Lance Yang Date: Sat, 6 Sep 2025 14:35:18 +0800 X-Gmail-Original-Message-ID: X-Gm-Features: Ac12FXwZXUX6523e25WuhUjfg2Wk6VLSjA3TWPpSs5qJfKafZ8u7MZFwTj20LIg Message-ID: Subject: Re: [PATCH v1] mm/huge_memory: fix shrinking of all-zero THPs with max_ptes_none default To: David Hildenbrand Cc: Zi Yan , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Andrew Morton , Lorenzo Stoakes , Baolin Wang , "Liam R. Howlett" , Nico Pache , Ryan Roberts , Dev Jain , Barry Song , Usama Arif Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT X-Rspamd-Server: rspam10 X-Rspamd-Queue-Id: 9C78F180003 X-Stat-Signature: qwem7d58fcseezmxgqwuqoznhane4sws X-Rspam-User: X-HE-Tag: 1757140570-66868 X-HE-Meta: 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 TgxAXCTk 8LLB3rJoQ5tnXpTi56mvdX0xjS9RssnOmIYiZTcG3eLCAa1Rj2XlsDtMoEwvJuu27N2aPIJgR1TfcsRb+9161xGQx/VjpnIi4CBuW9kgUMqOkK9G1M3g6eZOiab5bSi6EEqU6c7UgVBwoQ+laeI2F/mQvVeLLt0hILOBmHcahre5x8zfj7hjObTWSS3tXIrrTaUF/vTZKahRKcl4sMRM0FnruabTqAehycNfUFPIf8Yw7U+FgyE20c3K2iRp5hDA+ysHkPvYWPIWK4blwTYfwfSBi6+nRCk1DVIqCG2M1Az7ruFhO07af++4nJBVS2p2c1DkrE88IhE+t8Y2n4qtgYj6oCKI2J32RTJwvClBUW5sh+zfwPRzfWFoC63y8os5vQXBQc6HeF0VHadEYCU8yW7U6cDPCaLBDn+qi5L4CDfZnjf1iD7L8ScAY8bJzYHb50vtlthsFNS65TAjeB1vy8/YFJaFULtrxMtZZ 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 Fri, Sep 5, 2025 at 11:17=E2=80=AFPM David Hildenbrand wrote: > > On 05.09.25 16:37, Zi Yan wrote: > > On 5 Sep 2025, at 10:11, David Hildenbrand wrote: > > > >> We added an early exit in thp_underused(), probably to avoid scanning > >> pages when there is no chance for success. > >> > >> However, assume we have max_ptes_none =3D 511 (default). > >> > >> Nothing should stop us from freeing all pages part of a THP that > >> is completely zero (512) and khugepaged will for sure not try to > >> instantiate a THP in that case (512 shared zeropages). > >> > >> This can just trivially happen if someone writes a single 0 byte into = a > >> PMD area, or of course, when data ends up being zero later. > >> > >> So let's remove that early exit. > >> > >> Do we want to CC stable? Hm, not sure. Probably not urgent. > >> > >> Note that, as default, the THP shrinker is active > >> (/sys/kernel/mm/transparent_hugepage/shrink_underused =3D 1), and all > >> THPs are added to the deferred split lists. However, with the > >> max_ptes_none default we would never scan them. We would not do that. = If > >> that's not desirable, we should just disable the shrinker as default, > >> also not adding all THPs to the deferred split lists. > >> > >> Easy to reproduce: > >> > >> 1) Allocate some THPs filled with 0s > >> > >> > >> #include > >> #include > >> #include > >> #include > >> #include > >> > >> const size_t size =3D 1024*1024*1024; > >> > >> int main(void) > >> { > >> size_t offs; > >> char *area; > >> > >> area =3D mmap(0, size, PROT_READ | PROT_WRITE, > >> MAP_ANON | MAP_PRIVATE, -1, 0); > >> if (area =3D=3D MAP_FAILED) { > >> printf("mmap failed\n"); > >> exit(-1); > >> } > >> madvise(area, size, MADV_HUGEPAGE); > >> > >> for (offs =3D 0; offs < size; offs +=3D getpagesize()) > >> area[offs] =3D 0; > >> pause(); > >> } > >> <\prog.c> > >> > >> 2) Trigger the shrinker > >> > >> E.g., memory pressure through memhog > >> > >> 3) Observe that THPs are not getting reclaimed > >> > >> $ cat /proc/`pgrep prog`/smaps_rollup > >> > >> Would list ~1GiB of AnonHugePages. With this fix, they would get > >> reclaimed as expected. > >> > >> Fixes: dafff3f4c850 ("mm: split underused THPs") > >> Cc: Andrew Morton > >> Cc: Lorenzo Stoakes > >> Cc: Zi Yan > >> Cc: Baolin Wang > >> Cc: "Liam R. Howlett" > >> Cc: Nico Pache > >> Cc: Ryan Roberts > >> Cc: Dev Jain > >> Cc: Barry Song > >> Cc: Usama Arif > >> Signed-off-by: David Hildenbrand > >> --- > >> mm/huge_memory.c | 3 --- > >> 1 file changed, 3 deletions(-) > >> > > LGTM. Acked-by: Zi Yan > > > > I also notice that thp_underused() checks num_zero_pages directly > > against khugepaged_max_ptes_none. This means mTHPs will never be regard= ed > > as underused. A similar issue you are discussing in Nico=E2=80=99s khug= epaged > > mTHP support. Maybe checks against these khugepaged_max* variables > > should be calculated based on nr_pages of a large folio, like > > making these variables a ratio in other discussion. > > Yeah, factoring that out and cleaning it up is my next step. > > But note that mTHPs are not a candidate for the shrinker right now. (see > my explanation in reply to Nicos patch) Right. IIUC, the logic in deferred_split_scan() is gated by !folio_test_partially_mapped(folio). This creates two paths: 1) Splits for mTHPs that are partially mapped. These set the flag and corectly bypass thp_underused(). 2) Optional shrinker splits for new or collapsed THPs. These don't set the flag and must go through thp_underused(). So, thp_underused() is only for whole, PMD-sized THPs right now. Please correct me if my understanding is wrong here ;) Cheers, Lance