From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from verein.lst.de ([213.95.11.211]:38641 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726224AbeHBKpK (ORCPT ); Thu, 2 Aug 2018 06:45:10 -0400 Date: Thu, 2 Aug 2018 10:59:38 +0200 From: Christoph Hellwig To: Al Viro Cc: Christoph Hellwig , Avi Kivity , linux-aio@kvack.org, linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH 2/4] aio: add a iocb refcount Message-ID: <20180802085938.GA13473@lst.de> References: <20180730071544.23998-1-hch@lst.de> <20180730071544.23998-3-hch@lst.de> <20180801231956.GS30522@ZenIV.linux.org.uk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180801231956.GS30522@ZenIV.linux.org.uk> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: On Thu, Aug 02, 2018 at 12:19:56AM +0100, Al Viro wrote: > On Mon, Jul 30, 2018 at 09:15:42AM +0200, Christoph Hellwig wrote: > > This is needed to prevent races caused by the way the ->poll API works. > > To avoid introducing overhead for other users of the iocbs we initialize > > it to zero and only do refcount operations if it is non-zero in the > > completion path. > > refcount_t looks like a bad match - you, AFAICS, have count 0 for everything > except poll, while for poll you start with 2. That looks like > if (iocb->shared && test_and_clear_bit(0, &iocb->shared)) > return; > kill the sucker > in your iocb_put() and initializing it to 1 in poll. No? For non-poll we don't need the recount, so we can ignore that. For poll we have two reference - submitting and wakee context. We could replace the refcount_t with an atomic bitops - but it would a) make the code harder to read than plain old refcounting b) make the iocb bigger - at least for now as there is nothing else we can share that unsigned long with. Your call - I can respin it either way.