Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753297AbdCOLUo (ORCPT ); Wed, 15 Mar 2017 07:20:44 -0400 Received: from foss.arm.com ([217.140.101.70]:45834 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751308AbdCOLU2 (ORCPT ); Wed, 15 Mar 2017 07:20:28 -0400 Date: Wed, 15 Mar 2017 11:20:20 +0000 From: Patrick Bellasi To: "Joel Fernandes (Google)" Cc: Linux Kernel Mailing List , linux-pm@vger.kernel.org, Ingo Molnar , Peter Zijlstra , Tejun Heo , Joel Fernandes Subject: Re: [RFC v3 1/5] sched/core: add capacity constraints to CPU controller Message-ID: <20170315112020.GA18557@e110439-lin> References: <1488292722-19410-1-git-send-email-patrick.bellasi@arm.com> <1488292722-19410-2-git-send-email-patrick.bellasi@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1412 Lines: 39 On 13-Mar 03:46, Joel Fernandes (Google) wrote: > On Tue, Feb 28, 2017 at 6:38 AM, Patrick Bellasi > wrote: > > The CPU CGroup controller allows to assign a specified (maximum) > > bandwidth to tasks within a group, however it does not enforce any > > constraint on how such bandwidth can be consumed. > > With the integration of schedutil, the scheduler has now the proper > > information about a task to select the most suitable frequency to > > satisfy tasks needs. > [..] > > > +static u64 cpu_capacity_min_read_u64(struct cgroup_subsys_state *css, > > + struct cftype *cft) > > +{ > > + struct task_group *tg; > > + u64 min_capacity; > > + > > + rcu_read_lock(); > > + tg = css_tg(css); > > + min_capacity = tg->cap_clamp[CAP_CLAMP_MIN]; > > Shouldn't the cap_clamp be accessed with READ_ONCE (and WRITE_ONCE in > the write path) to avoid load-tearing? tg->cap_clamp is an "unsigned int" and thus I would expect a single memory access to write/read it, isn't it? I mean: I do not expect the compiler "to mess" with these accesses. However, if your concerns are more about overlapping read/write for the same capacity from different threads, then perhaps we should better use a mutex to serialize these two functions... not entirely convinced... > Thanks, > Joel -- #include Patrick Bellasi