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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 11F95E810DA for ; Wed, 27 Sep 2023 13:26:19 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231921AbjI0N0R (ORCPT ); Wed, 27 Sep 2023 09:26:17 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:54692 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231954AbjI0N0L (ORCPT ); Wed, 27 Sep 2023 09:26:11 -0400 Received: from wxsgout04.xfusion.com (wxsgout03.xfusion.com [36.139.52.80]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 79BBA10A; Wed, 27 Sep 2023 06:26:08 -0700 (PDT) Received: from wuxshcsitd00600.xfusion.com (unknown [10.32.133.213]) by wxsgout04.xfusion.com (SkyGuard) with ESMTPS id 4Rwcky6sGqzB0JRS; Wed, 27 Sep 2023 21:23:54 +0800 (CST) Received: from localhost (10.82.147.3) by wuxshcsitd00600.xfusion.com (10.32.133.213) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.23; Wed, 27 Sep 2023 21:25:55 +0800 Date: Wed, 27 Sep 2023 21:25:54 +0800 From: Wang Jinchao To: Steffen Klassert , Daniel Jordan , , CC: Subject: Issue: Can padata avoid dealing with CPU-related operations? Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline X-Originating-IP: [10.82.147.3] X-ClientProxiedBy: wuxshcsitd00601.xfusion.com (10.32.135.241) To wuxshcsitd00600.xfusion.com (10.32.133.213) Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org Hello, I have a few questions about the padata code I've been studying recently: - Why does padata use the WQ_UNBOUND attribute of the workqueue? Because I've noticed a significant maintenance cost related to CPUs. Are there any specific benefits? - In what scenarios is it necessary to specify a CPU for serial execution, or is ensuring the order sufficient? In fact, the two questions can be summarized into one: Is it possible to avoid handling CPU-related operations to simplify the code logic? Thanks.