From patchwork Sun Oct 27 19:59:34 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hugh Dickins X-Patchwork-Id: 13852728 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 0D6C3D1357E for ; Sun, 27 Oct 2024 19:59:54 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 927DF6B0095; Sun, 27 Oct 2024 15:59:53 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 8D7736B0096; Sun, 27 Oct 2024 15:59:53 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 777FA6B0099; Sun, 27 Oct 2024 15:59:53 -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 552B76B0095 for ; Sun, 27 Oct 2024 15:59:53 -0400 (EDT) Received: from smtpin07.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay06.hostedemail.com (Postfix) with ESMTP id 70B21AAC79 for ; Sun, 27 Oct 2024 19:59:09 +0000 (UTC) X-FDA: 82720446732.07.24B88DE Received: from mail-pg1-f175.google.com (mail-pg1-f175.google.com [209.85.215.175]) by imf28.hostedemail.com (Postfix) with ESMTP id 5E97BC0006 for ; Sun, 27 Oct 2024 19:59:28 +0000 (UTC) Authentication-Results: imf28.hostedemail.com; dkim=pass header.d=google.com header.s=20230601 header.b=NmZ2EzFY; spf=pass (imf28.hostedemail.com: domain of hughd@google.com designates 209.85.215.175 as permitted sender) smtp.mailfrom=hughd@google.com; dmarc=pass (policy=reject) header.from=google.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1730059033; 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: references:dkim-signature; bh=2K0ZF9zx/iXF4BSeP4voI6OccaK4WNY3EiJpX9l6QVQ=; b=yv+cdgHQLIn2KgMSOF86ZY6qnKOXKnuzCslSsuRjDKp1hAHKevNtoyHINhB5dd9PIdzeEo 44w5cCpObWiP04QJfCNCiq94R1U9n6yBey/Vz9BScHsHv9KF6oEdrIjt+4W1IyRoQMeuZw OOyyBeX3NV/KUlzAqRyKW61Qmo1Bahc= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1730059033; a=rsa-sha256; cv=none; b=AqSgF8nY0pFAlmhOXctG849JUR9kV9M8t5U1pdOeZI3SRWt7SSeRwdyWspignmn238+5Cr 4AQVLRm9giKc0bdaow4o/K7LBD7NvMegNNYzZbMeSFPIubSBB/9WC0DtKAEX1H4YD3D6uw bhs5JKlSlovD6QRMVg9e05J4rFXSgSs= ARC-Authentication-Results: i=1; imf28.hostedemail.com; dkim=pass header.d=google.com header.s=20230601 header.b=NmZ2EzFY; spf=pass (imf28.hostedemail.com: domain of hughd@google.com designates 209.85.215.175 as permitted sender) smtp.mailfrom=hughd@google.com; dmarc=pass (policy=reject) header.from=google.com Received: by mail-pg1-f175.google.com with SMTP id 41be03b00d2f7-7db238d07b3so2673003a12.2 for ; Sun, 27 Oct 2024 12:59:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1730059190; x=1730663990; darn=kvack.org; h=mime-version:message-id:subject:cc:to:from:date:from:to:cc:subject :date:message-id:reply-to; bh=2K0ZF9zx/iXF4BSeP4voI6OccaK4WNY3EiJpX9l6QVQ=; b=NmZ2EzFYuFDMpuykWbifXT9dH67wXGaB9pdXtQ9CZO3uxox082rXx41Cd+SmUT5smo MsXs7nUuDVttSAkZrfWd3dIw7QJ1kGZ+wuPh9umTeJWoV2I0Mr7Gy3gO86FKDsoIHzDy rkJtC7lYOL7ojCtk+sr8hou9udPVXiTZkRYtPvJ0HM1749eKp7Z92/2yJGj9Kl56xgvp No47yRzC/xKE/PNdoBHsjC28wlB4066IcRkk3lHXyHrWB6oTltlbdD5ZKEUMekxQAfXU FQaNxJGyK0WZi0kxKaKW0X4HN1EcROMn0QDV1oF7yg7cv7OOgnWX/7NwDMTKgytwopjJ v7pg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730059190; x=1730663990; h=mime-version:message-id:subject:cc:to:from:date:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=2K0ZF9zx/iXF4BSeP4voI6OccaK4WNY3EiJpX9l6QVQ=; b=kRdvQuONLxFRfzgVM1uD0f0DB4P95f8n7fCmxlnPkEtIrcYcqop+f2gzXA1wUAScE9 FFMP4nKssri8a1QZdJDIz0KxJ7lQb08WQXwxEJHEY5E2RcOMJp/S0iFUyV4hGBpyzFlu 95e84MEPAFfaD/8a4aX9TXYoUguQX1C5co2WaIxtrLiMWEnitH9zJcxPvbi1T0nLD8ux H3cADp1he19KjK4HdKboIeKmzoz71YvgShvvQH88sw6d82e3iu4bLe1PqGAbUleEJvjJ jNNT0BF5sn8GPE0t70ziCvYKFkC8rwZl4HaC5fFeIUgzw6MCZqhByxZWhXY/cH5/J05/ 52MA== X-Forwarded-Encrypted: i=1; AJvYcCVWnfiFByRsc5xxnB1HFD65aaIfuSGdmVXV35jSfzBjb8MgWO22K0nYnCtx5ik3dDQ5kzeh8zdwug==@kvack.org X-Gm-Message-State: AOJu0Yx/KuwjelAC0eRAkxctfozorjwfKO+P6Hh8xS4Mq4L5Z292DrRh pluvgbKKgB41WR/KpaIJNGVCNGRxp9Np5xJZiDkQal+LqbxBa+9q2u8Y1L083w== X-Google-Smtp-Source: AGHT+IEzH36YOXESM9Up0rNVkNIoEgpliyHU+RcGa54EOHpi5Nqa7gJZnKWl/7+xW3c5Q/LPMwj5Xw== X-Received: by 2002:a05:6a20:9f95:b0:1d7:ca7:bfce with SMTP id adf61e73a8af0-1d9a850a3c8mr9259258637.42.1730059189495; Sun, 27 Oct 2024 12:59:49 -0700 (PDT) Received: from darker.attlocal.net (172-10-233-147.lightspeed.sntcca.sbcglobal.net. [172.10.233.147]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-72057a2493bsm4476650b3a.179.2024.10.27.12.59.47 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 27 Oct 2024 12:59:48 -0700 (PDT) Date: Sun, 27 Oct 2024 12:59:34 -0700 (PDT) From: Hugh Dickins To: Andrew Morton cc: Usama Arif , Yang Shi , Wei Yang , "Kirill A. Shutemov" , Matthew Wilcox , David Hildenbrand , Johannes Weiner , Baolin Wang , Barry Song , Kefeng Wang , Ryan Roberts , Nhat Pham , Zi Yan , Chris Li , Shakeel Butt , linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH hotfix v2 1/2] mm/thp: fix deferred split queue not partially_mapped Message-ID: <81e34a8b-113a-0701-740e-2135c97eb1d7@google.com> MIME-Version: 1.0 X-Rspam-User: X-Rspamd-Server: rspam04 X-Rspamd-Queue-Id: 5E97BC0006 X-Stat-Signature: ntahmq3rdp5cw9h7riursd17zx6fcgfu X-HE-Tag: 1730059168-816469 X-HE-Meta: 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 tf/gN4vJ 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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: Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. The new unlocked list_del_init() in deferred_split_scan() is buggy. I gave bad advice, it looks plausible since that's a local on-stack list, but the fact is that it can race with a third party freeing or migrating the preceding folio (properly unqueueing it with refcount 0 while holding split_queue_lock), thereby corrupting the list linkage. The obvious answer would be to take split_queue_lock there: but it has a long history of contention, so I'm reluctant to add to that. Instead, make sure that there is always one safe (raised refcount) folio before, by delaying its folio_put(). (And of course I was wrong to suggest updating split_queue_len without the lock: leave that until the splice.) And remove two over-eager partially_mapped checks, restoring those tests to how they were before: if uncharge_folio() or free_tail_page_prepare() finds _deferred_list non-empty, it's in trouble whether or not that folio is partially_mapped (and the flag was already cleared in the latter case). Fixes: dafff3f4c850 ("mm: split underused THPs") Signed-off-by: Hugh Dickins Acked-by: Usama Arif Reviewed-by: David Hildenbrand Reviewed-by: Baolin Wang Acked-by: Zi Yan --- Based on 6.12-rc4 v2: added ack and reviewed-bys mm/huge_memory.c | 21 +++++++++++++++++---- mm/memcontrol.c | 3 +-- mm/page_alloc.c | 5 ++--- 3 files changed, 20 insertions(+), 9 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fb328880b50..a1d345f1680c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3718,8 +3718,8 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); - struct folio *folio, *next; - int split = 0; + struct folio *folio, *next, *prev = NULL; + int split = 0, removed = 0; #ifdef CONFIG_MEMCG if (sc->memcg) @@ -3775,15 +3775,28 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, */ if (!did_split && !folio_test_partially_mapped(folio)) { list_del_init(&folio->_deferred_list); - ds_queue->split_queue_len--; + removed++; + } else { + /* + * That unlocked list_del_init() above would be unsafe, + * unless its folio is separated from any earlier folios + * left on the list (which may be concurrently unqueued) + * by one safe folio with refcount still raised. + */ + swap(folio, prev); } - folio_put(folio); + if (folio) + folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); + ds_queue->split_queue_len -= removed; spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + if (prev) + folio_put(prev); + /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7845c64a2c57..2703227cce88 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4631,8 +4631,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); VM_BUG_ON_FOLIO(folio_order(folio) > 1 && !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio), folio); + !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8afab64814dc..4b21a368b4e2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -961,9 +961,8 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) break; case 2: /* the second tail page: deferred_list overlaps ->mapping */ - if (unlikely(!list_empty(&folio->_deferred_list) && - folio_test_partially_mapped(folio))) { - bad_page(page, "partially mapped folio on deferred list"); + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); goto out; } break; From patchwork Sun Oct 27 20:02:13 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hugh Dickins X-Patchwork-Id: 13852729 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 807D7D13580 for ; Sun, 27 Oct 2024 20:02:21 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id B99206B009D; Sun, 27 Oct 2024 16:02:20 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id B49666B009E; Sun, 27 Oct 2024 16:02:20 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 9C1C66B00A0; Sun, 27 Oct 2024 16:02:20 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0011.hostedemail.com [216.40.44.11]) by kanga.kvack.org (Postfix) with ESMTP id 779C16B009D for ; Sun, 27 Oct 2024 16:02:20 -0400 (EDT) Received: from smtpin26.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id 1820EA1BDC for ; Sun, 27 Oct 2024 20:01:40 +0000 (UTC) X-FDA: 82720453326.26.0DD0117 Received: from mail-pl1-f170.google.com (mail-pl1-f170.google.com [209.85.214.170]) by imf18.hostedemail.com (Postfix) with ESMTP id 4A84D1C002C for ; Sun, 27 Oct 2024 20:02:08 +0000 (UTC) Authentication-Results: imf18.hostedemail.com; dkim=pass header.d=google.com header.s=20230601 header.b="V/XX2M1d"; dmarc=pass (policy=reject) header.from=google.com; spf=pass (imf18.hostedemail.com: domain of hughd@google.com designates 209.85.214.170 as permitted sender) smtp.mailfrom=hughd@google.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1730059165; 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=U5xhn7RSTWM2lUg8fS/XXmeMk68KKIj9kU8T8Vkq0vE=; b=KFSEirgpXZJc8M0Uxm4A1A+EAIWc5mToMwb75t/fau7FwxsVElnMQEM9GlHMEh8fZJRP9V syZq1b7aB9mX07M/UzfUNetcC1n06ImxYqvQwOJdp2touBnubXdEf+OZbvsRaN94Oo+AVz klADcPA21FVbKTyzINZzsaDIYP1fC2k= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1730059165; a=rsa-sha256; cv=none; b=Tq+hq+FbdF+Pp0q/s3zJDFrVXq7mk7HGIT7hwumgtC18Xl6a1+KGoSx/27/7JpFLIuY/a1 nWPh9LG72DXVTteyTh/Raq6KOEXzbisue1IbTTwc/tuelJBknaRtWEkzbSOx6u//iy1ayk 6H86OhgHrP0e56RZp6W+LmyxuyuxFr4= ARC-Authentication-Results: i=1; imf18.hostedemail.com; dkim=pass header.d=google.com header.s=20230601 header.b="V/XX2M1d"; dmarc=pass (policy=reject) header.from=google.com; spf=pass (imf18.hostedemail.com: domain of hughd@google.com designates 209.85.214.170 as permitted sender) smtp.mailfrom=hughd@google.com Received: by mail-pl1-f170.google.com with SMTP id d9443c01a7336-20cb47387ceso30810915ad.1 for ; Sun, 27 Oct 2024 13:02:17 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1730059337; x=1730664137; darn=kvack.org; h=mime-version:references:message-id:in-reply-to:subject:cc:to:from :date:from:to:cc:subject:date:message-id:reply-to; bh=U5xhn7RSTWM2lUg8fS/XXmeMk68KKIj9kU8T8Vkq0vE=; b=V/XX2M1dSbPkWsPpTWe+XEF92fgeHhMivSRQK5KP3k9KTi4lj1lyHA8kI8cBKNE3Zu MzaLrlE/+4GYnUsf+/tmMn75aUMyqgkDt6aNXwSUDrzFvqjynMnufkBOqCHY76vYr4cV 9dQSW0qBfmdT0OoNZETGDktZa+uFpyt1fc+JLPYrN3vQSNp19r98jYcmsMsA+a6ZhRJa qJnVdOjGfZ1CGOO77RpHjLo7Uj4tTq1VTfnN139d7aki71SjKF7OajtwYS0/qIYWVFpZ Z6+ddjpul8i42tj36Zku4bIDGPAyIIH5RGAAvIWIVsu0y6bWmEVa2/FT+tRylXTuxDw/ LOQw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1730059337; x=1730664137; h=mime-version:references:message-id:in-reply-to:subject:cc:to:from :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=U5xhn7RSTWM2lUg8fS/XXmeMk68KKIj9kU8T8Vkq0vE=; b=W+ix/ESIbFJ1o0xpaLx9v0u7nImawSjTLgI0SJXSW4wpFchp3DqD0vmqBvQY8inXTO Y1qNZO2a1KWQRsj7qFaCumbuhoFjPZbnTZXlIKnALhwGSeWIlJAtm07dOhLed2v9kALz YgIcPKec3R7RrWGJilkCmINla+chbdCQAqSE5uEaC4bi6QyvQrjh3ttHgOwRNGtqsrGl u8rSSUCkbXmxJnkbr+j1s/IB+8PaXQAPJb4g/mFKOF0WySl8elNp/G3xEq+DJbkcJ1kY mznCpHx8axRG79QXaG+oC5HqJCdCw1V0deVj6CwRGgdLEMlTDVrztI6tACgm9atN5xIS 8nRg== X-Forwarded-Encrypted: i=1; AJvYcCVh0sztHX0jCAKEXT3gQOVpPvMJBq5wWSttVJ0+upZZ2sGvqt0JckfqG92NsnrA9q6xuZ5k98ORYg==@kvack.org X-Gm-Message-State: AOJu0YzduTT3dhsBGKpinjqhhfvKyX4mYHBPo4a2DgOXkjqIM0VzlzFz IfIJM0Hsh4HPkf9Dl6CkcERebrIzE0QglEEJ6zKdAg2sUlet1b/Tggg6pSlXdg== X-Google-Smtp-Source: AGHT+IFXtBky9M44SnX3mQY4FJdgBxzvChjhDvJFPpQvhFVYc7LnC9xewMls9dbjbG2N/cnCVIf+Sg== X-Received: by 2002:a17:90a:b111:b0:2e2:d16e:8769 with SMTP id 98e67ed59e1d1-2e8f106926emr7546123a91.15.1730059336486; Sun, 27 Oct 2024 13:02:16 -0700 (PDT) Received: from darker.attlocal.net (172-10-233-147.lightspeed.sntcca.sbcglobal.net. [172.10.233.147]) by smtp.gmail.com with ESMTPSA id 98e67ed59e1d1-2e8e3555b67sm5611114a91.9.2024.10.27.13.02.13 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sun, 27 Oct 2024 13:02:14 -0700 (PDT) Date: Sun, 27 Oct 2024 13:02:13 -0700 (PDT) From: Hugh Dickins To: Andrew Morton cc: Usama Arif , Yang Shi , Wei Yang , "Kirill A. Shutemov" , Matthew Wilcox , David Hildenbrand , Johannes Weiner , Baolin Wang , Barry Song , Kefeng Wang , Ryan Roberts , Nhat Pham , Zi Yan , Chris Li , Shakeel Butt , linux-kernel@vger.kernel.org, linux-mm@kvack.org Subject: [PATCH hotfix v2 2/2] mm/thp: fix deferred split unqueue naming and locking In-Reply-To: <81e34a8b-113a-0701-740e-2135c97eb1d7@google.com> Message-ID: <8dc111ae-f6db-2da7-b25c-7a20b1effe3b@google.com> References: <81e34a8b-113a-0701-740e-2135c97eb1d7@google.com> MIME-Version: 1.0 X-Rspamd-Server: rspam07 X-Rspamd-Queue-Id: 4A84D1C002C X-Stat-Signature: zibdzbqeo9yowq435t79y41a5p31enpd X-Rspam-User: X-HE-Tag: 1730059328-593947 X-HE-Meta: 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 txZoHeHC mpUOvilZx3KkzYDnx/RwZk4UHXH4xWWfqA9dKdD+FwcuJeNk6IxXxqe8/ra9yPcR3mcrgyBilrx3ytE7zhW9IZQWzQjPmvQvhhBD1LersPIY67tfTarRAHmIX8d4bQhtB141AbojXz0ftJi5TPCz6ozZKQmPHbnN27C17fVlLs5boXai3vwlofFIfgK/E4PgMTyD1F35P6mVVuBaNn2TLAFJBRsQF0WqzcnV/v7CNhqZX/srWt7+Lwch+59zYXZNWC7B7haLO5yQk9XWLXcU1Odeb6jd3taQwmo40UbYT4Qt87KpY6s+VFVknwseOyLG6tMtqV5S5lLN+NkWN9JLOjRSJE8gxYMnfDTS4c4mfvhoPViOnjwLQ1yaCWJt+Lsfb9gXFfTcuAOnqOkr3MPGWbrY86A7TbnyLv6Ar4PxWgd+ePtzku0dOgNhUKtc5vQmHZzoH 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: Recent changes are putting more pressure on THP deferred split queues: under load revealing long-standing races, causing list_del corruptions, "Bad page state"s and worse (I keep BUGs in both of those, so usually don't get to see how badly they end up without). The relevant recent changes being 6.8's mTHP, 6.10's mTHP swapout, and 6.12's mTHP swapin, improved swap allocation, and underused THP splitting. Before fixing locking: rename misleading folio_undo_large_rmappable(), which does not undo large_rmappable, to folio_unqueue_deferred_split(), which is what it does. But that and its out-of-line __callee are mm internals of very limited usability: add comment and WARN_ON_ONCEs to check usage; and return a bool to say if a deferred split was unqueued, which can then be used in WARN_ON_ONCEs around safety checks (sparing callers the arcane conditionals in __folio_unqueue_deferred_split()). Just omit the folio_unqueue_deferred_split() from free_unref_folios(), all of whose callers now call it beforehand (and if any forget then bad_page() will tell) - except for its caller put_pages_list(), which itself no longer has any callers (and will be deleted separately). Swapout: mem_cgroup_swapout() has been resetting folio->memcg_data 0 without checking and unqueueing a THP folio from deferred split list; which is unfortunate, since the split_queue_lock depends on the memcg (when memcg is enabled); so swapout has been unqueueing such THPs later, when freeing the folio, using the pgdat's lock instead: potentially corrupting the memcg's list. __remove_mapping() has frozen refcount to 0 here, so no problem with calling folio_unqueue_deferred_split() before resetting memcg_data. That goes back to 5.4 commit 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware"): which included a check on swapcache before adding to deferred queue, but no check on deferred queue before adding THP to swapcache. That worked fine with the usual sequence of events in reclaim (though there were a couple of rare ways in which a THP on deferred queue could have been swapped out), but 6.12 commit dafff3f4c850 ("mm: split underused THPs") avoids splitting underused THPs in reclaim, which makes swapcache THPs on deferred queue commonplace. Keep the check on swapcache before adding to deferred queue? Yes: it is no longer essential, but preserves the existing behaviour, and is likely to be a worthwhile optimization (vmstat showed much more traffic on the queue under swapping load if the check was removed); update its comment. Memcg-v1 move (deprecated): mem_cgroup_move_account() has been changing folio->memcg_data without checking and unqueueing a THP folio from the deferred list, sometimes corrupting "from" memcg's list, like swapout. Refcount is non-zero here, so folio_unqueue_deferred_split() can only be used in a WARN_ON_ONCE to validate the fix, which must be done earlier: mem_cgroup_move_charge_pte_range() first try to split the THP (splitting of course unqueues), or skip it if that fails. Not ideal, but moving charge has been requested, and khugepaged should repair the THP later: nobody wants new custom unqueueing code just for this deprecated case. The 87eaceb3faa5 commit did have the code to move from one deferred list to another (but was not conscious of its unsafety while refcount non-0); but that was removed by 5.6 commit fac0516b5534 ("mm: thp: don't need care deferred split queue in memcg charge move path"), which argued that the existence of a PMD mapping guarantees that the THP cannot be on a deferred list. As above, false in rare cases, and now commonly false. Backport to 6.11 should be straightforward. Earlier backports must take care that other _deferred_list fixes and dependencies are included. There is not a strong case for backports, but they can fix cornercases. Fixes: 87eaceb3faa5 ("mm: thp: make deferred split shrinker memcg aware") Fixes: dafff3f4c850 ("mm: split underused THPs") Signed-off-by: Hugh Dickins Cc: Acked-by: David Hildenbrand Reviewed-by: Yang Shi --- Based on 6.12-rc4 v2: adjusted commit message following info from Yang and David reinstated deferred_split_folio swapcache check, adjusting comment omitted (mem_cgroup_disabled) unqueue from free_unref_folios mm/huge_memory.c | 35 ++++++++++++++++++++++++++--------- mm/internal.h | 10 +++++----- mm/memcontrol-v1.c | 25 +++++++++++++++++++++++++ mm/memcontrol.c | 8 +++++--- mm/migrate.c | 4 ++-- mm/page_alloc.c | 1 - mm/swap.c | 4 ++-- mm/vmscan.c | 4 ++-- 8 files changed, 67 insertions(+), 24 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a1d345f1680c..03fd4bc39ea1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3588,10 +3588,27 @@ int split_folio_to_list(struct folio *folio, struct list_head *list) return split_huge_page_to_list_to_order(&folio->page, list, ret); } -void __folio_undo_large_rmappable(struct folio *folio) +/* + * __folio_unqueue_deferred_split() is not to be called directly: + * the folio_unqueue_deferred_split() inline wrapper in mm/internal.h + * limits its calls to those folios which may have a _deferred_list for + * queueing THP splits, and that list is (racily observed to be) non-empty. + * + * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is + * zero: because even when split_queue_lock is held, a non-empty _deferred_list + * might be in use on deferred_split_scan()'s unlocked on-stack list. + * + * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is + * therefore important to unqueue deferred split before changing folio memcg. + */ +bool __folio_unqueue_deferred_split(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; + bool unqueued = false; + + WARN_ON_ONCE(folio_ref_count(folio)); + WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg(folio)); ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); @@ -3603,8 +3620,11 @@ void __folio_undo_large_rmappable(struct folio *folio) MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } list_del_init(&folio->_deferred_list); + unqueued = true; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); + + return unqueued; /* useful for debug warnings */ } /* partially_mapped=false won't clear PG_partially_mapped folio flag */ @@ -3627,14 +3647,11 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) return; /* - * The try_to_unmap() in page reclaim path might reach here too, - * this may cause a race condition to corrupt deferred split queue. - * And, if page reclaim is already handling the same folio, it is - * unnecessary to handle it again in shrinker. - * - * Check the swapcache flag to determine if the folio is being - * handled by page reclaim since THP swap would add the folio into - * swap cache before calling try_to_unmap(). + * Exclude swapcache: originally to avoid a corrupt deferred split + * queue. Nowadays that is fully prevented by mem_cgroup_swapout(); + * but if page reclaim is already handling the same folio, it is + * unnecessary to handle it again in the shrinker, so excluding + * swapcache here may still be a useful optimization. */ if (folio_test_swapcache(folio)) return; diff --git a/mm/internal.h b/mm/internal.h index 93083bbeeefa..16c1f3cd599e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -639,11 +639,11 @@ static inline void folio_set_order(struct folio *folio, unsigned int order) #endif } -void __folio_undo_large_rmappable(struct folio *folio); -static inline void folio_undo_large_rmappable(struct folio *folio) +bool __folio_unqueue_deferred_split(struct folio *folio); +static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) - return; + return false; /* * At this point, there is no one trying to add the folio to @@ -651,9 +651,9 @@ static inline void folio_undo_large_rmappable(struct folio *folio) * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) - return; + return false; - __folio_undo_large_rmappable(folio); + return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c index 81d8819f13cd..f8744f5630bb 100644 --- a/mm/memcontrol-v1.c +++ b/mm/memcontrol-v1.c @@ -848,6 +848,8 @@ static int mem_cgroup_move_account(struct folio *folio, css_get(&to->css); css_put(&from->css); + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = (unsigned long)to; __folio_memcg_unlock(from); @@ -1217,7 +1219,9 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, enum mc_target_type target_type; union mc_target target; struct folio *folio; + bool tried_split_before = false; +retry_pmd: ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { if (mc.precharge < HPAGE_PMD_NR) { @@ -1227,6 +1231,27 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); if (target_type == MC_TARGET_PAGE) { folio = target.folio; + /* + * Deferred split queue locking depends on memcg, + * and unqueue is unsafe unless folio refcount is 0: + * split or skip if on the queue? first try to split. + */ + if (!list_empty(&folio->_deferred_list)) { + spin_unlock(ptl); + if (!tried_split_before) + split_folio(folio); + folio_unlock(folio); + folio_put(folio); + if (tried_split_before) + return 0; + tried_split_before = true; + goto retry_pmd; + } + /* + * So long as that pmd lock is held, the folio cannot + * be racily added to the _deferred_list, because + * __folio_remove_rmap() will find !partially_mapped. + */ if (folio_isolate_lru(folio)) { if (!mem_cgroup_move_account(folio, true, mc.from, mc.to)) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2703227cce88..06df2af97415 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4629,9 +4629,6 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON_FOLIO(folio_order(folio) > 1 && - !folio_test_hugetlb(folio) && - !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at @@ -4678,6 +4675,7 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) ug->nr_memory += nr_pages; ug->pgpgout++; + WARN_ON_ONCE(folio_unqueue_deferred_split(folio)); folio->memcg_data = 0; } @@ -4789,6 +4787,9 @@ void mem_cgroup_migrate(struct folio *old, struct folio *new) /* Transfer the charge and the css ref */ commit_charge(new, memcg); + + /* Warning should never happen, so don't worry about refcount non-0 */ + WARN_ON_ONCE(folio_unqueue_deferred_split(old)); old->memcg_data = 0; } @@ -4975,6 +4976,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) VM_BUG_ON_FOLIO(oldid, folio); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); + folio_unqueue_deferred_split(folio); folio->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) diff --git a/mm/migrate.c b/mm/migrate.c index df91248755e4..691f25ee2489 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -489,7 +489,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, folio_test_large_rmappable(folio)) { if (!folio_ref_freeze(folio, expected_count)) return -EAGAIN; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); folio_ref_unfreeze(folio, expected_count); } @@ -514,7 +514,7 @@ static int __folio_migrate_mapping(struct address_space *mapping, } /* Take off deferred split queue while frozen and memcg set */ - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); /* * Now we know that no one else is looking at the folio: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4b21a368b4e2..815100a45b25 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2681,7 +2681,6 @@ void free_unref_folios(struct folio_batch *folios) unsigned long pfn = folio_pfn(folio); unsigned int order = folio_order(folio); - folio_undo_large_rmappable(folio); if (!free_pages_prepare(&folio->page, order)) continue; /* diff --git a/mm/swap.c b/mm/swap.c index 835bdf324b76..b8e3259ea2c4 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -121,7 +121,7 @@ void __folio_put(struct folio *folio) } page_cache_release(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); mem_cgroup_uncharge(folio); free_unref_page(&folio->page, folio_order(folio)); } @@ -988,7 +988,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs) free_huge_folio(folio); continue; } - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); __page_cache_release(folio, &lruvec, &flags); if (j != i) diff --git a/mm/vmscan.c b/mm/vmscan.c index eb4e8440c507..635d45745b73 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1475,7 +1475,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, */ nr_reclaimed += nr_pages; - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { mem_cgroup_uncharge_folios(&free_folios); try_to_unmap_flush(); @@ -1863,7 +1863,7 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec, if (unlikely(folio_put_testzero(folio))) { __folio_clear_lru_flags(folio); - folio_undo_large_rmappable(folio); + folio_unqueue_deferred_split(folio); if (folio_batch_add(&free_folios, folio) == 0) { spin_unlock_irq(&lruvec->lru_lock); mem_cgroup_uncharge_folios(&free_folios);