From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from PH0PR06CU001.outbound.protection.outlook.com (mail-westus3azon11011011.outbound.protection.outlook.com [40.107.208.11]) (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 BB19F23E334; Sun, 20 Sep 2026 06:07:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=40.107.208.11 ARC-Seal:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789884467; cv=fail; b=XNXj6fb0oorG/hqtgE4G41ixew725Ssc+IWt62JJBj+22++E45yNoDu1QFKaAj9LnD+4GzOXQ8b6WqoLIgCSls/LpBbZUv1x7ld7SsA+fRnAk+nq/FkncmwsAhZIRNZQr4SpSwefJcrDHK1d5A7ucy9Vv0w+CeSsATG2FjW7PEY= ARC-Message-Signature:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789884467; c=relaxed/simple; bh=nEF5LJW+S1FzHuqfBZuEAPLGt2rA7gRhgBQ500D7IoA=; h=Date:From:To:Cc:Subject:Message-ID:References:Content-Type: Content-Disposition:In-Reply-To:MIME-Version; b=isTMpWPTuZYTQoZbdrYCWavDZZtXFqPcwJCTkSteSxUGUdGAlffgGDoetOU/Lf561QYI4nIK1FnR5QM7/B/Wtqj5MddTXSMJhCcZ9OxPip2giEYQ0YIn+3ygTNp8V+Ay32/G79Skhhp1BKW+nTPlC6mWBDHCgQQSGq5+CKl7E6U= 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=pQs5iYoR; arc=fail smtp.client-ip=40.107.208.11 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="pQs5iYoR" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=GlVkvCx8Mmv0rxZpyVicy55vcXDJwqnAU6QuDRH7IXN52A7AVCkt8BdbiHYsQTg4yUKDSOOZUbTT+NLQuK0hM+w/YupicD0ZfQgRttIFcDaW3MC1nak8d77pPR3NIMosv00PpCJskHjL0EI5XRWgLXG0qpS6YnAW6forl7YfOEn55/3Z5ZzUmwnke8FeG8kl/+Mh24r61KnsoHuagcSzWppDd6jJjqW4rOQutT2JtHaW6KwG72UT3xq7Y3tQvp7SMIE2pbZ0GqiZkRF2xbKmD0GhiKi7S0tBbqtBMPE7qjSR8D27xfR1T03ycgNoI32Lb+Rs/LFpR9LPGPRs36NZCw== 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=thVBHdCBSZ0P47TkNTx0eWBs8bK5Njkz3aFiAoJypyg=; b=LKyMbUVnZDCbAwDOOHlILl1TAfyb1xhethlcuzEIvLwKXbUoluj6ZGLeZYDwRUW1lkdLrsJVn0x98jL+2nLfXS8QBdXLFUZocvFhoUG5/TcCVfYXXmRy8cdKSZHqUQEJ03uaFKA7TkHhnk48/6F5hZ19N2ibbLndFkLHrBSi5B6CFRlwC9b5pNhuKXUOr4sQUvX98hTpEbu0HDCq+R7lBS+NO8/fGVyCmAHMrygmRAtr6XXspihhiUqoOFMMT3WNN6ZMYnSbTjBkYZ/b1KbANeY9+0sOI+jfORGu5mE+jGhGWYdNFyjFWeixXUicQvrZf0EyLQFX5hX5juLXw1D36w== 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=thVBHdCBSZ0P47TkNTx0eWBs8bK5Njkz3aFiAoJypyg=; b=pQs5iYoRgaVT6CiQCWqzU7rjIShF+4ejaHko/Qmpc9uwsNDzazQ4yX4knXCAVZ/aKWG8l++MuLJgMNYBaRHrgPv951CTsqoV95dTshtTqh4ZirALirelgXQivkA/hfF0QqDGI/V3x20YN169T5biBV44kgzj3A9azHfAZZbstVFafwwSuLxAWRCDWPihRvLqngJWy+0Hxeyvy4AuU3PJnhL388GfCnJC2HcJ7iQNkESUKDwanzICvYh3ffPv7BR79eTwe8M4R/XOj9mWZlACNSpVNzh8SgAad5oB17tWNxtmzRoIxT4xSupUBbXv9+JY+G3koDDygWgGAgy9Cp16Fg== Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=nvidia.com; Received: from DM6PR12MB4827.namprd12.prod.outlook.com (2603:10b6:5:1d6::14) by PH7PR12MB7794.namprd12.prod.outlook.com (2603:10b6:510:276::15) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.21.428.13; Sun, 20 Sep 2026 06:07:42 +0000 Received: from DM6PR12MB4827.namprd12.prod.outlook.com ([fe80::6261:3040:864b:159c]) by DM6PR12MB4827.namprd12.prod.outlook.com ([fe80::6261:3040:864b:159c%7]) with mapi id 15.21.0428.014; Sun, 20 Sep 2026 06:07:42 +0000 Date: Sun, 20 Sep 2026 08:07:30 +0200 From: Andrea Righi To: Alexei Starovoitov Cc: Daniel Borkmann , Andrii Nakryiko , Eduard Zingerman , Kumar Kartikeya Dwivedi , Martin KaFai Lau , Song Liu , Emil Tsalapatis , Ihor Solodrai , bpf@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] bpf: arena: Flush stale TLB entries before reusing ranges Message-ID: References: <20260919224616.3123513-1-arighi@nvidia.com> Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-ClientProxiedBy: MI0P293CA0004.ITAP293.PROD.OUTLOOK.COM (2603:10a6:290:44::15) To DM6PR12MB4827.namprd12.prod.outlook.com (2603:10b6:5:1d6::14) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: DM6PR12MB4827:EE_|PH7PR12MB7794:EE_ X-MS-Office365-Filtering-Correlation-Id: 993c4a5c-d7be-41ce-24a6-08df16dd7af4 X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|7416014|376014|1800799024|366016|23010399003|18002099003|22082099003|56012099006|11063799006|4143699003|10067099003; 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:DM6PR12MB4827.namprd12.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230040)(7416014)(376014)(1800799024)(366016)(23010399003)(18002099003)(22082099003)(56012099006)(11063799006)(4143699003)(10067099003);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?4b41NSJfxbtkVQb8InaHoQu4rA7edmssad+TAE5PR/5ddoEeEcxfnKStLk6Y?= =?us-ascii?Q?CAgVIyYWw79d0jAvdOXgHnpJ1svPzI7dKeHPnNOgPkaHcVrDjbeXRySMsTHv?= =?us-ascii?Q?hj4akWXW9L3xkeflSpNh6Hpf1WGDMNzzKjppoaX/KS+LROyZhN8VpWaVFjeh?= =?us-ascii?Q?LCk2mSqe/fvYqzMS4YFQsI+z0DsbnTAv0wCvwn3atgh6txFpmyHXvg6kvmr0?= =?us-ascii?Q?p4P3HvbcQg0EgxkfAWxZxcnNpeu0K5VNe0yjtbW7//93z5vTOP3QUtqolRKx?= =?us-ascii?Q?4S7P91WR1YkOIZlzhjCCEwrp2Y0E3ErgJP5uQqAKug9snetNfP8MjaWgDqci?= =?us-ascii?Q?/pP2nT8892KulQlArQPg8PyuOD67D8pA7LvOuaPDjeV7Jos6cecYP814RLxS?= =?us-ascii?Q?xvi92hoAUmC99QW4m3rb0QO5Z2atvPPu3QNP4+5ysvvo5+Za1bVkRVtjU4lo?= =?us-ascii?Q?4goCh+cve1fslkImoOy1c7wEZujap3YOvhqEFuxmobhzWWCnGtuAwM1DC6Qd?= =?us-ascii?Q?xHEXnDtm8hqGLfmAzHhS1/pbufhGLhvI7TCL4jTNBOLxaMrtkBP47MQ57rAt?= =?us-ascii?Q?SmYCqx9gSMyHiBYXgBH3EkxAHfCOXKM/HUS/JipwindDcyOEq6RSVgCCZSW8?= =?us-ascii?Q?HO2BHsAwLe8TnrILSI/8GMmVjGEaWhlZSx7DtxJC1fxSccSWvTmOGNaacuRW?= =?us-ascii?Q?5PIRXIsKZOKWxdHjmvdmkES/p6ERxnIaDI9umLTZdIT6V+2wOyDxsaba48rG?= =?us-ascii?Q?kYXDYqWxy7YK+zUa4aWM524s1CCkWm9czlDveHUFXMz0z7AyouCOVLgdbFwl?= =?us-ascii?Q?QS7baSlG3MiteF3JUIObmsaqAfK7M1evyHkPFazzscm7HMjNs7Ch0uFyY4Hd?= =?us-ascii?Q?2QFi5e5BcnjeatWxz+C1WLsJh6w4Oo8uXLm/SvL4GAnvZdMoYj2NElqFzomY?= =?us-ascii?Q?rJb7zReWt0IFrq5OtwYeg+xejawY4aqZRudtj/vJCaTOU6DCk5HkOy7RvLPD?= =?us-ascii?Q?xPqtkTO21fh5wRepzHP9q9lqu5TAkuOI1Q0bzWx1m6xiEHx5xnN07dEzBGhl?= =?us-ascii?Q?WQasYClyN79O+oY53HO5QnjE/ETmWG+ccIZifPg8UmO2ozOVj1GnVZe2dfxv?= =?us-ascii?Q?25g8Y2brQS78ae9eKB9rlx3gW72ayfUXQM54GoB8vUX7F82djNkuqGMqVBbY?= =?us-ascii?Q?Fevt4X9iXpdsTb5t4Glln3HPWuIosbY1LVfbIXPeoi//imrpDfKK7z1go+oz?= =?us-ascii?Q?TsesAGzg2Ov6zwNnMyASoH3ws+hWX3hSs1PRVKvzPmtDltOP0k/phaAZGovE?= =?us-ascii?Q?v3WpkknT1N3Vr6z4TjghT0ZoKEcv8N9pE6VgsyxkI1r83oz1splEEEhwc6BR?= =?us-ascii?Q?oX8ZytJqMm5Ai57n175LB8nkEjCKpHnpNi1oJp5UNcFU8HBDljr7xHUN9fBq?= =?us-ascii?Q?uLmjFMBn3bEf2DOQ+YMgl/aSfaO9WcnAcpa1C/5Hq8fw9KoUMk7ZK5LYVigr?= =?us-ascii?Q?uHMliJV+QQdaSD2SUJkzm0i8ctPpHQXdinR/0VQc7J/JW94nunSeMongZU6n?= =?us-ascii?Q?VBQREQAI4Zed1hPYXyeZJq4dk+8uiXifPuwGc1vEoz+mm9Z2+2bHyqHMaHIO?= =?us-ascii?Q?5TV1I+YbPHiYOmZBWukZhYpkDt/YiqaGiX6vjq/+IZ0eqareA0FM3IEptRmp?= =?us-ascii?Q?v878LJhzg0cJ90qdatLpRBsF8SXtGwXNacZTUL2N2YLdPHl6Tpb3CWwqlzuN?= =?us-ascii?Q?IVCyxkoI6Q=3D=3D?= X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-Network-Message-Id: 993c4a5c-d7be-41ce-24a6-08df16dd7af4 X-MS-Exchange-CrossTenant-AuthSource: DM6PR12MB4827.namprd12.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 20 Sep 2026 06:07:42.0180 (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: FzyFTnLhEQgraVWCmEOT808PkS9YO0IynH6MQWq0eLH0ZmQaXZae9PFQ5g6fi/7aiOvYU6phJOTV6K2yKgm8nw== X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH7PR12MB7794 Hi Alexei, On Sat, Sep 19, 2026 at 11:21:43PM +0000, Alexei Starovoitov wrote: > On Sun, Sep 20, 2026 at 12:46 AM Andrea Righi wrote: > > @@ -911,11 +910,17 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt, > > zap_pages(arena, full_uaddr, 1); > > __free_page(page); > > } > > + > > + ret = raw_res_spin_lock_irqsave(&arena->spinlock, flags); > > + if (ret) > > + goto defer_publish; > > + range_tree_set(&arena->rt, pgoff, page_cnt); > > + raw_res_spin_unlock_irqrestore(&arena->spinlock, flags); > > Now the ptes are cleared in one locked section and the range is set in > another, and arena_vm_fault() can get in between. It doesn't look at > the range tree to decide. It does vmalloc_to_page(), sees no page, > range_tree_clear() of an already clear range returns 0, so it allocates > a page and installs it into the kernel pte. Then the code above marks > that range free. The next bpf_arena_alloc_pages() that picks it hits > WARN_ON_ONCE(pte_page(old) != d->arena->scratch_page) > in apply_range_set_cb(), returns NULL, puts t > he range back into the > tree, and the next call does the same. All it takes is user space > touching the page while the prog frees it. You're right, I missed that range_tree_clear() succeeds even when the range is already clear, so arena_vm_fault() populates the range during the teardown-to-publish window, leaving the range marked free with a valid PTE installed. > > iirc Emil has patches that address this issue differently. Thanks for catching this! I'll sync with Emil. -Andrea