From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from SN4PR0501CU005.outbound.protection.outlook.com (mail-southcentralusazon11011029.outbound.protection.outlook.com [40.93.194.29]) (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 36EF4311954; Sat, 18 Apr 2026 02:44:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=40.93.194.29 ARC-Seal:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1776480288; cv=fail; b=Xk6ktPIYfbEX4rilsEEZHCWMRGl59B9OfmCjrf3fosMagLLwBHkg5Ua1EhI/Qlvh+CCSwh+/CuAwIrUru3CJoboLmp6hmk6zbka2I+iDtsxO9zVds9oX3tzOd+GH6/QBreEwt8jR/4s3um3ZTgFfPzU5kWXSWayHsGXu9nTYEk0= ARC-Message-Signature:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1776480288; c=relaxed/simple; bh=KwvU3CkDLMIbwaGq6g8nElcDzk8ki4Vy8v+L7MBmMRs=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: Content-Type:MIME-Version; b=KVonnlimFGbqr3lJQD8rv+AzLX7H7Lv/xw0joVHYO+bEeETb6G9K9OH0e2NAUH2tD1I+/Fr0sOu1N8i7oDQdlbIwnLTj9qLpP0qBo9edwz3ytOIXgF9gKFxMeIYfq+lk1eZEWYkyrwsLPbNQnbBbI4sAZ1JTnUOdiIHs2WljLnM= ARC-Authentication-Results:i=2; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com; spf=fail smtp.mailfrom=nvidia.com; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b=tJuEcytl; arc=fail smtp.client-ip=40.93.194.29 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=nvidia.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b="tJuEcytl" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=UBGJfGPDum3m6776KlxZ2JidZX7AL4NxFvKcdnVoSJULx5OTr5A6KCeGdcNnwWWab7LvtRFT+qcFz7bHyyDuJhdkuwwhXrBKQa3kp/SKPMbqlXDRtuzQVyyeCyIEfbrcSaoMzi9fV+JRiu78iFgR5vj3Ra/+L7o02JTtjYo/ViNhnxJ12H8ophYUetzU3L9bC3rVTzDG2v0HgLOeIcFpm8gRmJiVYKuw9IHlJso3gD53X64wGNb0ocjYAF9RlLzi7fcrSkL4PI0H2tBCrOSbgDlCx+C2HPiQ5DTjrA0c6ZJM/3fiGYiieQBQUP0o8XFfwnOFKcLfIRMh3QwhO1AmCw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=HO8ICQiUFQkzLBg9SgSYwDDAN3DeRitz+/rI4C14BQ4=; b=uU9nfYqAt2UIzJQJ3N/197u5MMEcFAJKqmuFCm9veTVtzOHy3IcjqTMM0+xdj80jnnQFtlb0v0CE4+Rb20uaGmVdM1qyrMN6hHHWlGVlO3vQQ77RWJSNwAw1tXYaqk7DEiCCGEg/1qBipp5P4qd2NJgjrAQ0hO6SaKSxzLgYyFNYShrK50b3rs1HbdMON4nTCj5181IgJ6OpG87+nKbAK4OP/KpTqeJ0Mfq9BF2M2TAH3gcWxT+dfAy1l9JeC+4Zl1ZB7LPECZrLzodIW6HScbyBknkoAFK2o4Jw0e2ty/c6kbsrk+w53RULtOG2uq0vIZFmDvmftfRI6VPXXDLkUw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=nvidia.com; dmarc=pass action=none header.from=nvidia.com; dkim=pass header.d=nvidia.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=HO8ICQiUFQkzLBg9SgSYwDDAN3DeRitz+/rI4C14BQ4=; b=tJuEcytlxNL6IZZYgcDeNBOzXUP1sLsJ8NnSNV8KfxAwUdlUn1f060IJv5/yuSGBiTRLzpAfviTSBDdcCkl2s9fEf7DL3EP47DK5XQkPYeYZmeXZ5UM4j49XVFNtDGUluRC2SN7Vc/sP03h+PeocGS1hjcHWWbyqooG12o8Fw9pEVUjyaf0kqk813pPKvOhz0AUVFWe/wMZ5negBR8dIq29kzAckqxXlbt6J121KzRfueoVBqzwGGRR14o4BYeAV6JOa+FVrRYxwouB59hEHj1iw7VgT0cKxrSZMf23/JrUntxY9YJDgQjoTbNwLyEeIlEhkQ4xQYr7gdh4299ZhZA== Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=nvidia.com; Received: from DS7PR12MB9473.namprd12.prod.outlook.com (2603:10b6:8:252::5) by IA1PR12MB6650.namprd12.prod.outlook.com (2603:10b6:208:3a1::18) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.9818.20; Sat, 18 Apr 2026 02:44:40 +0000 Received: from DS7PR12MB9473.namprd12.prod.outlook.com ([fe80::f01d:73d2:2dda:c7b2]) by DS7PR12MB9473.namprd12.prod.outlook.com ([fe80::f01d:73d2:2dda:c7b2%4]) with mapi id 15.20.9818.017; Sat, 18 Apr 2026 02:44:39 +0000 From: Zi Yan To: "Matthew Wilcox (Oracle)" , Song Liu Cc: Chris Mason , David Sterba , Alexander Viro , Christian Brauner , Jan Kara , Andrew Morton , David Hildenbrand , Lorenzo Stoakes , Zi Yan , Baolin Wang , "Liam R. Howlett" , Nico Pache , Ryan Roberts , Dev Jain , Barry Song , Lance Yang , Vlastimil Babka , Mike Rapoport , Suren Baghdasaryan , Michal Hocko , Shuah Khan , linux-btrfs@vger.kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kselftest@vger.kernel.org Subject: [PATCH 7.2 v3 02/12] mm/khugepaged: add folio dirty check after try_to_unmap() Date: Fri, 17 Apr 2026 22:44:19 -0400 Message-ID: <20260418024429.4055056-3-ziy@nvidia.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20260418024429.4055056-1-ziy@nvidia.com> References: <20260418024429.4055056-1-ziy@nvidia.com> Content-Transfer-Encoding: 8bit Content-Type: text/plain X-ClientProxiedBy: BL1PR13CA0155.namprd13.prod.outlook.com (2603:10b6:208:2bd::10) To DS7PR12MB9473.namprd12.prod.outlook.com (2603:10b6:8:252::5) Precedence: bulk X-Mailing-List: linux-kselftest@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: DS7PR12MB9473:EE_|IA1PR12MB6650:EE_ X-MS-Office365-Filtering-Correlation-Id: fa97c46f-016c-493b-35db-08de9cf46d48 X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|376014|7416014|366016|1800799024|22082099003|18002099003|56012099003; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:DS7PR12MB9473.namprd12.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230040)(376014)(7416014)(366016)(1800799024)(22082099003)(18002099003)(56012099003);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?nHu2isgWdNSGnHPl9Ml3MddaMjyiSmDBsm0luWhLJFR9hXW6+QkGjkJoq75r?= =?us-ascii?Q?9AKCJu+Q3pddHkvZHuTJkjJ6b46AWh0l7uDC3r8eWx3o5Q2tDOelELh6lFsT?= =?us-ascii?Q?ojzj/cej6bhAB4ZKWrqJPV2JdbQ1zbngx0z8XtbaSSSsRgcNbxpQd5uoxSvp?= =?us-ascii?Q?FOQshvMnZBcGseJiYlyvTIZW0OxLjjfyspzq5f1OnrdsdnHe6c0Gp0rxDsYd?= =?us-ascii?Q?cSKR+rIPm3a6NSg7QBg5QwWKSJSUjAd+sUu8aUj9+ttriwlxtoD8fDFx991Z?= =?us-ascii?Q?gQp6vxpmsOtTjQWIOw7qMswTdqaP1JhRexlEMP067d1Ej+ueizo4MotvCdd5?= =?us-ascii?Q?YKoofaYH8ap6yk9l1+grnwLdslEiZtr9cTSOII/jqctYYLlQArzJ4jPOmJdv?= =?us-ascii?Q?xCEGkFhugcKDRZzV1GoSHZJ/OodFoaellKMKSwJ6PqmOuWYYPjx+lBMHg+ji?= =?us-ascii?Q?cqCQ60TYW2GO3qwA7UiNmNEK7DcqbOX1TvILCkM45WHLj/tVl8X92bXI6Zxw?= =?us-ascii?Q?7BY8m2csuUgoZG+URtkOixX1PCTaALnd3+D7kasqS17wX3r1p0DqURTttDp+?= =?us-ascii?Q?BVuPkSIcmbvoLbU88jWFd4F4hi/Xv+xLdTvIqtH4ZskMEAjVxtp73fNRRe+V?= =?us-ascii?Q?mHMea8eB4AL4h8hvyOqabqKPpBTZxZI2YZBH9eYhCE7cGdSRTGUjv2DJCjSh?= =?us-ascii?Q?EG8jH7tWCXa3+iNMtmrQjJa1CsBf9W2OwVQ8hPFiJbyfFsprcwne2PfXbOIv?= =?us-ascii?Q?qgDZQMP4vTv7giD+7uMUm4Iv5FstRqcym9ndX9u7NlATSqzT6t5XUII12/sa?= =?us-ascii?Q?ITiM59IMx1BRr8Zuq8JlJKZ5p0yeFDtvlR8qGy8GzcTHmSIq9sNg0JPIwt+s?= =?us-ascii?Q?Sx6RNRIF84jeZI4wxqC/nsCJ9RblS6yDOdJRx6DNY+UCU4LtoyClMVcSYjRz?= =?us-ascii?Q?ikA0orDDZYydn1Fs9YiSGuvjNeqHi7GwivSxvhHTA5LVizouS6EWZOYRbed9?= =?us-ascii?Q?H983+EeQodcdhf0UMCe0iqA6kLM/tXx8YgxQMwxv//ekb5mM+GAqh73EkcJS?= =?us-ascii?Q?z2f0uPjWyPJ+jugI1tWh7Js+peIGf6TAxPDAxro4NTMMxWcKbifHXZFaDrsf?= =?us-ascii?Q?q6e/MsCTIr9Os+0YdbeQOHWiDFLthxy6Ff0TvQHTLbFePh/gXdmj93st8Hf3?= =?us-ascii?Q?Y6e6UZ30pU64KTZl4YqPiThDrN9r2xNEbf3d0ayKWvC66X2YlRcF0E0PghBM?= =?us-ascii?Q?N9aIivZRcaiqa2CjYGVa78EuQKGrZCCWaLgrd8vUfnwupvIAORdt1//sW+iS?= =?us-ascii?Q?H1uN9khIfN1ko8YU5+mc6h7KQC0c/TQXy80VzJJw81td798YyozwZidXyuu0?= =?us-ascii?Q?F9sv6gh3x0v5/wiiB31/mS//N3cgM/rRSfzGahmVgE8bBo4qAxkh5wAEekIa?= =?us-ascii?Q?QSunqrkskZYXi98hhSeqoLfu/4bmMK/Xjaz6z6RDr+CRNFavZMrp9761qxYA?= =?us-ascii?Q?+SJ9jKk1gKZSm5txL5nDTKY0lwIMgZhrzthVDoVJ+7+6W5xYPad4+IhV+F+i?= =?us-ascii?Q?LPk819b8nYk5vMwH0kvRnlfmp+Si9S3gxl6JRYuex3nJr+GKBf5KkjRSRkQj?= =?us-ascii?Q?L7F6qJLTofvvFjm3s0VQh/+ZGZuCpU9RM/X1Lco1evLHxFhED/Kfet0HAU/L?= =?us-ascii?Q?0ne/bKppJ4NuzTC+LeWGMXClUS0kr4A/AxfiNE2j1h1YNj1T?= X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-Network-Message-Id: fa97c46f-016c-493b-35db-08de9cf46d48 X-MS-Exchange-CrossTenant-AuthSource: DS7PR12MB9473.namprd12.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 18 Apr 2026 02:44:35.3538 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: 4Z6MpALSbSDkphoW6j38eMRjhS921+njYGxhtEPBkYTqOkJLTJ06KNozWwfAlPvL X-MS-Exchange-Transport-CrossTenantHeadersStamped: IA1PR12MB6650 This check ensures the correctness of collapse read-only THPs for FSes after READ_ONLY_THP_FOR_FS is enabled by default for all FSes supporting PMD THP pagecache. READ_ONLY_THP_FOR_FS only supports read-only fd and uses mapping->nr_thps and inode->i_writecount to prevent any write to read-only to-be-collapsed folios. In upcoming commits, READ_ONLY_THP_FOR_FS will be removed and the aforementioned mechanism will go away too. To ensure khugepaged functions as expected after the changes, skip if any folio is dirty after try_to_unmap(), since a dirty folio means this read-only folio got some writes via mmap can happen between try_to_unmap() and try_to_unmap_flush() via cached TLB entries and khugepaged does not support writable pagecache folio collapse yet. Signed-off-by: Zi Yan --- mm/khugepaged.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 3eb5d982d3d3..1c0fdc81d276 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1979,8 +1979,7 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, } } else if (folio_test_dirty(folio)) { /* - * khugepaged only works on read-only fd, - * so this page is dirty because it hasn't + * This page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * @@ -2038,8 +2037,8 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* - * khugepaged only works on read-only fd, so this - * folio is dirty because it hasn't been flushed + * khugepaged only works on clean file-backed folios, + * so this folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_PAGE_DIRTY_OR_WRITEBACK; @@ -2083,6 +2082,24 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } + /* + * At this point, the folio is locked, unmapped. Make sure the + * folio is clean, so that no one else is able to write to it, + * since that would require taking the folio lock first. + * Otherwise that means the folio was pointed by a dirty PTE and + * some CPU might have a valid TLB entry with dirty bit set + * still pointing to this folio and writes can happen without + * causing a page table walk and folio lock acquisition before + * the try_to_unmap_flush() below is done. After the collapse, + * file-backed folio is not set as dirty and can be discarded + * before any new write marks the folio dirty, causing data + * corruption. + */ + if (!is_shmem && folio_test_dirty(folio)) { + result = SCAN_PAGE_DIRTY_OR_WRITEBACK; + goto out_unlock; + } + /* * Accumulate the folios that are being collapsed. */ -- 2.43.0