From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] rcu: fix a race in hlist_nulls_for_each_entry_rcu macro Date: Tue, 21 May 2013 08:38:13 -0700 Message-ID: <1369150693.3301.233.camel@edumazet-glaptop> References: <519B38EC.90401@yandex-team.ru> <20130521120906.GD3578@linux.vnet.ibm.com> <1369143885.3301.221.camel@edumazet-glaptop> <519B8908.9080007@yandex-team.ru> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: paulmck@linux.vnet.ibm.com, Dipankar Sarma , zhmurov@yandex-team.ru, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, "David S. Miller" , Alexey Kuznetsov , James Morris , Hideaki YOSHIFUJI , Patrick McHardy To: Roman Gushchin Return-path: Received: from mail-da0-f46.google.com ([209.85.210.46]:36581 "EHLO mail-da0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754478Ab3EUPiQ (ORCPT ); Tue, 21 May 2013 11:38:16 -0400 In-Reply-To: <519B8908.9080007@yandex-team.ru> Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 2013-05-21 at 18:47 +0400, Roman Gushchin wrote: > This code has the same mistake: it is rcu_dereference_raw(head->first), > so there is nothing that prevents gcc to store the (head->first) value > in a register. If other rcu accessors have the same problem, a more complete patch is needed. Thanks