From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-ed1-f45.google.com (mail-ed1-f45.google.com [209.85.208.45]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 10A922BD5BC for ; Thu, 18 Dec 2025 22:02:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.208.45 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766095367; cv=none; b=czmBZ08MltL8ZPvmQqK5iTJyzCZIDc3Nj2WDd9zV9roH/hH3TiW2RSN8neeMa/VpJ2MYWEU33fD/NO7aPG1r5c8re8FVNWE+U64LCLcdkivmH2YTTZB31yw09e79GVvU9yoP3NmAIYeabP64yraqSvIO6wxhU7nEVcrvP8sM2WY= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766095367; c=relaxed/simple; bh=Bf2KYbMziPki3rnasos5YRzsDzuBX5KJfPRFOQinxlk=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=NL+KScPnij7UoLPCJ5sdRqol5qdQBNhJVu5FnrhWzb48icVPNxRBPEAC/zA2wp+ih2ZyKycuCEV3u2Yr1u9SmeUCsWg1JoyjQcTzvWEyWHRdZkw9oN4HHrcr5gEwokGkhi2PixpOY+3zxwR5zv4p2M6rrafdkVa5Gaptp/dYn0I= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=LBSFaUOd; arc=none smtp.client-ip=209.85.208.45 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="LBSFaUOd" Received: by mail-ed1-f45.google.com with SMTP id 4fb4d7f45d1cf-64b4f730a02so1636284a12.0 for ; Thu, 18 Dec 2025 14:02:45 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1766095364; x=1766700164; darn=vger.kernel.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=V3VZdRP8NwaypFlr46kQWQp+Zi4z6sAOUbRUp8gjWS4=; b=LBSFaUOd/uTSPlc1g73TwydENpjtWvY6ukORzKZkklho+cNODOo1QXOjQZ6CckFzv5 VN9+6EI5pCufWDS2TogyBccAQtPgFttIIpfJbhBxGRdx0usDecxTYeC4OqMFcQBmxuz8 LiRiTA0hHR6n4j02SCgV6mcW16i/rXnkU8oMzFaUYj9pI4beIL6U5XuX0LFm2zVHM4O+ QNmI9wLvIALz6qgr2OZ8S/0znilMgHmLNCUDwsk5Pr6ySTTSnHn60dqrpcNOOW3yj0mQ Vf4CqXg3lSJliueriAXL1YSWCnjVH8WGzkfreOqH5cXgYec9LFA0BTpCUgv5e6r1zpPC hdsw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1766095364; x=1766700164; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:x-gm-gg:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=V3VZdRP8NwaypFlr46kQWQp+Zi4z6sAOUbRUp8gjWS4=; b=vcjd6FIs2hyI2Xxro1vDjXvT8Xl4+1+Ov4B0ehmzTF39TH5bpQl6sqH6gcQNQzP2ur o4sdOVtQoGLS2JBO72MRHcTKfzk6JG0nKi3v7rkzc7ky1NoUKWFsN8O6LmF0xUPUFgRa MZYzn21xclOmurNdVOkihY1g7tUGzpTnp2ZPdIvgv/HcnFUauccAiwWOKWDtNTCAzP7y YNMH5aZ0VtFcUPJ0LbS/d1tN2RZbcemNBiMNDzwZbG1KdUZ2Iq9I9EzIHCN5vyK2eevr NUnrCBZUAK4Nh1433IB95mzzGmNvyOloZvAdME8CZHMVnfoMbONRbfiLCTqjzd9PGmLZ 52Mg== X-Forwarded-Encrypted: i=1; AJvYcCU4BPHn1eTKtfBaGEDBrwi7Z3ycGktLb5Pq6uTggyv1ZUHrxWnKWiHp9zlj/TYBwtwYnP06kyDJym+v71M=@vger.kernel.org X-Gm-Message-State: AOJu0YwOtPXM0DYugfLngQffLf8fHSK1Oc5HBYjoQqe6mGBnXqeKAGQa oNpWblma2qaVXynsaTFdcNRwAMG/bOuejNZf9T0eC+KziL279j/xIjgb X-Gm-Gg: AY/fxX6eLrj3hBIlDFwJYsGEvqfh5Pm4F0hQAi3lx3jk1p8J0/IobwnkSvWBK9LroCE Gh8nzXwrTDkGG44pvahvQjM0eB01aUdLs67cPn3EM5EvNDuI7K72+PjChIuNr7tL3FK1MoiqaBW +iw0xdt/AcN4uCEYCW3w69FOyjAeq/AkqNrPYmGbA8389Gr2wWmOpG1Sh9p5A7YfNJzjEvNvpB8 sPlp2cu6yn9eHRO/d94fo2aqxbH0by0iPkz1n5ytNfnMWGPGkbngDsJzzZ06ShwSVIh+UQg8rjF C1RR23lbvkuQX/0buuOFuTWztB6tUjFDSuox8LINALS1tfc9ElhmUWZx3crk/z8QkQvj8eKd3Sw NQHfcm3sdjMmklur24/vs/RTcPJXzRoGpNadkNInvQg6435tO3GMQ8HyHQbF3wamTHQCdcNfhSM eC4tNy6YA= X-Google-Smtp-Source: AGHT+IGC8nWpel+ncFSY/d62pIo9n55fFYIVH8WgqZxu82es9cY5UqEa9vD9DhmktlmW69ZmfTB99A== X-Received: by 2002:a17:907:3d42:b0:b73:a0b9:181a with SMTP id a640c23a62f3a-b80371df391mr84490166b.54.1766095363819; Thu, 18 Dec 2025 14:02:43 -0800 (PST) Received: from andrea ([31.189.127.109]) by smtp.gmail.com with ESMTPSA id a640c23a62f3a-b8037f0b7bcsm50069666b.49.2025.12.18.14.02.42 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 18 Dec 2025 14:02:43 -0800 (PST) Date: Thu, 18 Dec 2025 23:02:38 +0100 From: Andrea Parri To: Thomas Haas Cc: Alan Stern , Will Deacon , Peter Zijlstra , Boqun Feng , Nicholas Piggin , David Howells , Jade Alglave , Luc Maranget , "Paul E. McKenney" , Akira Yokosawa , Daniel Lustig , Joel Fernandes , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, lkmm@lists.linux.dev, hernan.poncedeleon@huaweicloud.com, jonas.oberhauser@huaweicloud.com, "r.maseli@tu-bs.de" Subject: Re: [RFC] Potential problem in qspinlock due to mixed-size accesses Message-ID: References: <0f7f3317-7a96-44f2-a3e7-a49f75bcd6aa@tu-bs.de> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <0f7f3317-7a96-44f2-a3e7-a49f75bcd6aa@tu-bs.de> > ARM has recently fixed the issue on their side by strengthening the memory > model (see https://github.com/herd/herdtools7/commit/2b7921a44a61766e23a1234767d28af696b436a0) > > With the updated ARM-MSA model, Dartagnan does no longer find violations in > qspinlock. No patches needed :) Thanks for the heads-up, Thomas. This reminds me: After your post, I wrote some script/files to test MSA against the LKMM by leveraging the MSA support for AArch64 available in herd7 and requiring no changes to herd7 internals. I've put these files in the repository: https://github.com/andrea-parri/lkmm-msa.git in case someone here feels particularly bored during the Christmas holi- days and desire to have a look! ;-) I am hoping to be able to resume this study (and to write a proper README) soonish - but the starting point was to "lift" ARMv8 execution graphs to (corresponding) LKMM graphs, cf. the file cats/lkmm-from-armv8.cat; then the usual "test, model and iterate" process, with unmarked accesses still needing several iterations I'm afraid. Any feedback's welcome. Andrea