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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 80DB6CF6497 for ; Mon, 30 Sep 2024 09:34:00 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 0536280021; Mon, 30 Sep 2024 05:34:00 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id F20AF80017; Mon, 30 Sep 2024 05:33:59 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id CADA280021; Mon, 30 Sep 2024 05:33:59 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id A53FE80017 for ; Mon, 30 Sep 2024 05:33:59 -0400 (EDT) Received: from smtpin03.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay10.hostedemail.com (Postfix) with ESMTP id 5500FC1D01 for ; Mon, 30 Sep 2024 09:33:59 +0000 (UTC) X-FDA: 82620892998.03.A5D9938 Received: from frasgout12.his.huawei.com (frasgout12.his.huawei.com [14.137.139.154]) by imf24.hostedemail.com (Postfix) with ESMTP id 23B74180007 for ; Mon, 30 Sep 2024 09:33:54 +0000 (UTC) Authentication-Results: imf24.hostedemail.com; dkim=none; dmarc=none; spf=pass (imf24.hostedemail.com: domain of jonas.oberhauser@huaweicloud.com designates 14.137.139.154 as permitted sender) smtp.mailfrom=jonas.oberhauser@huaweicloud.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1727688817; a=rsa-sha256; cv=none; b=0B/5m0tjqXGsvT2yP3hXhJAL59KuR/eSX747E8Z1qQ0X182kQI8vobZft2pkUQ+9rtFiQv PB6vyW2dLA3XUfKA6u2cNYaE11hivWdbYjJCSMtuaGnviTRBfO8d6IXXyBJn99TuOIy5Pw x9kWqFxxzOvzwKuX/op4FiAV9mwih1Q= ARC-Authentication-Results: i=1; imf24.hostedemail.com; dkim=none; dmarc=none; spf=pass (imf24.hostedemail.com: domain of jonas.oberhauser@huaweicloud.com designates 14.137.139.154 as permitted sender) smtp.mailfrom=jonas.oberhauser@huaweicloud.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1727688817; 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:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=pQbokL3YncC83I153hgWdk1tMyJ3oLTqaSsG01GI54k=; b=xuE8JGUFhI3frDOLb0JaqPakI8kj2eAseTnzRl5KeECakaNEyJbPt3SS5uhNEbPCZLW9OL P3hRaZkMyxw2QaNSVoZq5XOLEYj3n/UWP0HAyzC0KKppK2qOggICWixrLq6xPkjdk/GW21 MnQIxhYkybNOhfiUId9IqMQfvAto234= Received: from mail.maildlp.com (unknown [172.18.186.29]) by frasgout12.his.huawei.com (SkyGuard) with ESMTP id 4XHFbV1mm7z9v7JM for ; Mon, 30 Sep 2024 17:08:06 +0800 (CST) Received: from mail02.huawei.com (unknown [7.182.16.27]) by mail.maildlp.com (Postfix) with ESMTP id 73F861404C6 for ; Mon, 30 Sep 2024 17:33:45 +0800 (CST) Received: from [10.81.211.60] (unknown [10.81.211.60]) by APP2 (Coremail) with SMTP id GxC2BwD3psdocPpmCvLwAQ--.5053S2; Mon, 30 Sep 2024 10:33:44 +0100 (CET) Message-ID: Date: Mon, 30 Sep 2024 11:33:26 +0200 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH 1/2] compiler.h: Introduce ptr_eq() to preserve address dependency To: Alan Huang Cc: Mathieu Desnoyers , Alan Stern , Linus Torvalds , LKML , Greg Kroah-Hartman , Sebastian Andrzej Siewior , "Paul E. McKenney" , Will Deacon , Peter Zijlstra , Boqun Feng , John Stultz , Neeraj upadhyay , Frederic Weisbecker , Joel Fernandes , Josh Triplett , "Uladzislau Rezki (Sony)" , Steven Rostedt , Lai Jiangshan , Zqiang , Ingo Molnar , Waiman Long , Mark Rutland , Thomas Gleixner , Vlastimil Babka , maged.michael@gmail.com, Mateusz Guzik , Gary Guo , RCU , linux-mm@kvack.org, lkmm@lists.linux.dev References: <20240928135128.991110-1-mathieu.desnoyers@efficios.com> <20240928135128.991110-2-mathieu.desnoyers@efficios.com> <02c63e79-ec8c-4d6a-9fcf-75f0e67ea242@rowland.harvard.edu> <2091628c-2d96-4492-99d9-0f6a61b08d1d@efficios.com> <8d20cf79-9fa5-4ced-aa91-232ccd545b59@huaweicloud.com> From: Jonas Oberhauser In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-CM-TRANSID:GxC2BwD3psdocPpmCvLwAQ--.5053S2 X-Coremail-Antispam: 1UD129KBjvJXoWxJr1kKw48GFyUtrWxCFy3Jwb_yoW8Ar1Dpr W7Kay7KFn7XF4YyFWUtw18Cw1jqFZaqa90v3Z5Ar1xCFZ0k3WfCr4xtryUCa43u397J340 vrWY934Ig3W5AaUanT9S1TB71UUUUU7qnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDU0xBIdaVrnRJUUUvjb4IE77IF4wAFF20E14v26rWj6s0DM7CY07I20VC2zVCF04k2 6cxKx2IYs7xG6rWj6s0DM7CIcVAFz4kK6r1j6r18M28lY4IEw2IIxxk0rwA2F7IY1VAKz4 vEj48ve4kI8wA2z4x0Y4vE2Ix0cI8IcVAFwI0_Jr0_JF4l84ACjcxK6xIIjxv20xvEc7Cj xVAFwI0_Gr0_Cr1l84ACjcxK6I8E87Iv67AKxVW8JVWxJwA2z4x0Y4vEx4A2jsIEc7CjxV AFwI0_Gr0_Gr1UM2AIxVAIcxkEcVAq07x20xvEncxIr21l5I8CrVACY4xI64kE6c02F40E x7xfMcIj6xIIjxv20xvE14v26r1j6r18McIj6I8E87Iv67AKxVWUJVW8JwAm72CE4IkC6x 0Yz7v_Jr0_Gr1lF7xvr2IY64vIr41lFIxGxcIEc7CjxVA2Y2ka0xkIwI1lc7CjxVAaw2AF wI0_GFv_Wryl42xK82IYc2Ij64vIr41l4I8I3I0E4IkC6x0Yz7v_Jr0_Gr1lx2IqxVAqx4 xG67AKxVWUJVWUGwC20s026x8GjcxK67AKxVWUGVWUWwC2zVAF1VAY17CE14v26r4a6rW5 MIIYrxkI7VAKI48JMIIF0xvE2Ix0cI8IcVAFwI0_Jr0_JF4lIxAIcVC0I7IYx2IY6xkF7I 0E14v26r4j6F4UMIIF0xvE42xK8VAvwI8IcIk0rVWUJVWUCwCI42IY6I8E87Iv67AKxVWU JVW8JwCI42IY6I8E87Iv6xkF7I0E14v26r4j6r4UJbIYCTnIWIevJa73UjIFyTuYvjxUIF 4iUUUUU X-CM-SenderInfo: 5mrqt2oorev25kdx2v3u6k3tpzhluzxrxghudrp/ X-Rspam-User: X-Stat-Signature: t3w8qpoyio3ipnja5nynpzamy1k1xqui X-Rspamd-Queue-Id: 23B74180007 X-Rspamd-Server: rspam02 X-HE-Tag: 1727688834-934231 X-HE-Meta: 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 DEggi22T +lZ9QNkP9r7EctRPV+JlDaijTiQFn6Er+rOu4vGMedO24bxwi/j02ttlL0UJsDLr/X+Gkxm3lXlDQ2o8DKkIXFzB1JjaHcsHmrNsoER1v9SAfE8mSSCxMid7h1qh+FQo8+hAYPsMBVFNH381eBGi7s3l+qTVf6V/9cb1v3gt0dF03GIHaH0BU6+B4K3vsumef+Oi83x7cbheXf7zTj3IkqBkWSwgtZcyv4MP+EK2YGXylFWDAP+bXQ+phG0Y33b9F93DOnNcwNM22Njvj5ej7jRpDyAT4WZnkKF620rGHKw4IXzBcOaartugqnQRgzGC6NBXwXf63aSrnZ4Eh9imfKgssJU/Tgs0gkh6ssSKyvUBDNmDnK7YpPpXKxccfzCimmTZZK3ULv/Ao3Af3IzbEigm+cRDaDvhACYv/ 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: Am 9/30/2024 um 11:27 AM schrieb Alan Huang: > 2024年9月30日 17:15，Alan Huang 写道： >> >> 2024年9月30日 16:57，Jonas Oberhauser 写道： >>> >>> >>> >>> Am 9/29/2024 um 12:26 AM schrieb Alan Huang: >>>> 2024年9月28日 23:55，Mathieu Desnoyers wrote： >>>>> >>>>> The motivation for introducing ptr_eq() is indeed because the >>>>> compiler barrier is not sufficient to prevent the compiler from >>>>> using one pointer instead of the other. >>>> barrier_data(&b) prevents that. >>> >>> I don't think one barrier_data can garantuee preventing this, because right after doing the comparison, the compiler still could do b=a. >>> >>> In that case you would be guaranteed to use the value in b, but that value is not the value loaded into b originally but rather the value loaded into a, and hence your address dependency goes to the wrong load still. >> >> After barrier_data(&b), *b will be loaded from memory, you mean even if *b is loaded from memory, the address dependency goes to the wrong load still? > > Sorry, *b should b. That's exactly what I meant to say. In my understanding, it can happen like this: a = READ_ONCE(*p); ... b = READ_ONCE(*p); if (a == b) { b = a; // inserted by compiler barrier_data(&b); foo(*b); // compiler definitely use the current value in b } In the end, the address dependency is from the first load, and the CPU can speculatively (with register renaming, forwarding etc) execute a = READ_ONCE(*p); b2 = a; // speculatively tmp = load *b2 // speculatively b1 = READ_ONCE(*p); if (a == b1) { // confirmed foo(tmp); } best wishes, jonas