From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Date: Thu, 17 Nov 2016 08:02:11 -0800
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        Lai Jiangshan <jiangshanlai@gmail.com>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        Josh Triplett <josh@joshtriplett.org>,
        stable <stable@vger.kernel.org>
Subject: Re: [PATCH] Fix: disable sys_membarrier when nohz_full is enabled
Reply-To: paulmck@linux.vnet.ibm.com
References: <1478190568-5829-1-git-send-email-mathieu.desnoyers@efficios.com>
 <CAJhGHyC1WB7vp4JgAbp+fS4NXP+jmwUWYXeivQU7-OznjqE_fg@mail.gmail.com>
 <604945667.4957.1479383194368.JavaMail.zimbra@efficios.com>
 <20161117134015.GT3612@linux.vnet.ibm.com>
 <11301812.5114.1479390867218.JavaMail.zimbra@efficios.com>
 <20161117095011.1857bca5@gandalf.local.home>
 <1466810760.5394.1479394938124.JavaMail.zimbra@efficios.com>
 <20161117101725.3abcb413@gandalf.local.home>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161117101725.3abcb413@gandalf.local.home>
Message-Id: <20161117160211.GB3612@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <stable.vger.kernel.org>

On Thu, Nov 17, 2016 at 10:17:25AM -0500, Steven Rostedt wrote:
> On Thu, 17 Nov 2016 15:02:18 +0000 (UTC)
> Mathieu Desnoyers <mathieu.desnoyers@efficios.com> wrote:
> 
> 
> > That's an interesting approach. I would be tempted to give it a
> > per-thread (rather than per-process) scope.
> 
> Sure, per thread, but have it inherit to child processes.
> 
> > 
> > E.g., a thread could do the following to ask to be
> > interrupted by IPIs:
> > 
> > membarrier(MEMBARRIER_CMD_REGISTER_EXPEDITED, 0)
> > 
> > and could unregister with:
> > 
> > membarrier(MEMBARRIER_CMD_UNREGISTER_EXPEDITED, 0)
> 
> Sure why not ;-)

Makes a lot of sense to me!

> > We can then keep a per-thread refcount internally.
> > (not sure the "EXPEDITED" is the right word there...
> > do we want it to be "NOHZ_FULL" instead ?)
> 
> No, it shouldn't mention NOHZ_FULL. Perhaps have all tasks do this
> regardless, even though it will only affect nohz full ones. But in the
> future it may be other tasks as well.
> 
> > 
> > Then in membarrier(MEMBARRIER_CMD_SHARED, 0), for each
> > nohz_full cpu, we grab the rq lock, and only send an IPI
> > if the running thread is registered as "expedited".
> 
> Yeah, something like that. That way it wont interrupt tasks that are
> running in no-hz-full and don't care about this syscall.

And this as well!

							Thanx, Paul