From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-yb1-f194.google.com ([209.85.219.194]:44231 "EHLO mail-yb1-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726800AbeIKVaj (ORCPT ); Tue, 11 Sep 2018 17:30:39 -0400 Date: Tue, 11 Sep 2018 09:30:32 -0700 From: Tejun Heo To: Ming Lei Cc: linux-kernel@vger.kernel.org, Jianchao Wang , Kent Overstreet , linux-block@vger.kernel.org Subject: Re: [PATCH] percpu-refcount: relax limit on percpu_ref_reinit() Message-ID: <20180911163032.GA2966370@devbig004.ftw2.facebook.com> References: <20180909125824.9150-1-ming.lei@redhat.com> <20180910164920.GE1100574@devbig004.ftw2.facebook.com> <20180911000049.GB30977@ming.t460p> <20180911134836.GG1100574@devbig004.ftw2.facebook.com> <20180911154540.GA10082@ming.t460p> <20180911154959.GI1100574@devbig004.ftw2.facebook.com> <20180911160532.GB10082@ming.t460p> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20180911160532.GB10082@ming.t460p> Sender: linux-block-owner@vger.kernel.org List-Id: linux-block@vger.kernel.org On Wed, Sep 12, 2018 at 12:05:33AM +0800, Ming Lei wrote: > On Tue, Sep 11, 2018 at 08:49:59AM -0700, Tejun Heo wrote: > > On Tue, Sep 11, 2018 at 11:45:41PM +0800, Ming Lei wrote: > > > > So, this part seems wrong. The function is called percpu_ref_reinit() > > > > - the refcnt is expected to be in its initial state with just the base > > > > ref once this function returns. If you're removing the restriction on > > > > > > But the comment says that 'Re-initialize @ref so that it's in the same > > > state as when it finished', and this invariant isn't changed with this > > > patch. > > > > The comment goes "when perpcu_ref_init() finished". The function is > > called re _init_. It should put the ref in the initial state, right? > > OK, I am fine to keep the behaviour for this API, will introduce a new helper > for NVMe. Why aren't switch_to_atomic/percpu enough? > However, it is doable to switch to percpu mode from atomic mode when it > doesn't drop to zero, looks like sort of perpcu_ref_reinit(inherit_old_refcount). Isn't that way more contorted than just switching operating modes? Thanks. -- tejun