From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754321AbbKYQhf (ORCPT ); Wed, 25 Nov 2015 11:37:35 -0500 Received: from shards.monkeyblade.net ([149.20.54.216]:33759 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754104AbbKYQhb (ORCPT ); Wed, 25 Nov 2015 11:37:31 -0500 Date: Wed, 25 Nov 2015 11:37:29 -0500 (EST) Message-Id: <20151125.113729.987827630302526646.davem@davemloft.net> To: peterz@infradead.org Cc: herbert@gondor.apana.org.au, tatsu@ab.jp.nec.com, mingo@redhat.com, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, jolsa@redhat.com, eric.dumazet@gmail.com Subject: Re: net: Generalise wq_has_sleeper helper From: David Miller In-Reply-To: <20151125091533.GX17308@twins.programming.kicks-ass.net> References: <20151111094829.GA23202@gondor.apana.org.au> <20151124055423.GA31611@gondor.apana.org.au> <20151125091533.GX17308@twins.programming.kicks-ass.net> X-Mailer: Mew version 6.7 on Emacs 24.5 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.5.12 (shards.monkeyblade.net [149.20.54.216]); Wed, 25 Nov 2015 08:37:31 -0800 (PST) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Peter Zijlstra Date: Wed, 25 Nov 2015 10:15:33 +0100 > On Tue, Nov 24, 2015 at 01:54:23PM +0800, Herbert Xu wrote: >> + * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay >> + * in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 >> + * could then endup calling schedule and sleep forever if there are no more >> + * data on the socket. >> + * > > Would be easier to refer to the comment that now adorns > waitqueue_active(). Yeah, that might be a good idea. Herbert can you adjust this? >> + */ >> +static inline bool wq_has_sleeper(wait_queue_head_t *wq) >> +{ >> + /* We need to be sure we are in sync with the > > broken comment style. This is how we do it in the networking, so that's why it's formatted this way, but yes he will need to fix it up.