From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1754478AbbJ1FDg (ORCPT <rfc822;w@1wt.eu>);
	Wed, 28 Oct 2015 01:03:36 -0400
Received: from bombadil.infradead.org ([198.137.202.9]:47482 "EHLO
	bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750964AbbJ1FDe (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Wed, 28 Oct 2015 01:03:34 -0400
Date: Wed, 28 Oct 2015 06:03:14 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Paul Turner <commonly@gmail.com>
Cc: Andrew Hunter <ahh@google.com>, Andy Lutomirski <luto@amacapital.net>,
        Andi Kleen <andi@firstfloor.org>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        Dave Watson <davejwatson@fb.com>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        linux-api@vger.kernel.org, linux-kernel@vger.kernel.org,
        Josh Triplett <josh@joshtriplett.org>, Ingo Molnar <mingo@redhat.com>,
        Chris Lameter <cl@linux.com>,
        Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [RFC PATCH v2 2/3] restartable sequences: x86 ABI
Message-ID: <20151028050314.GC11242@worktop.amr.corp.intel.com>
References: <20151027235635.16059.11630.stgit@pjt-glaptop.roam.corp.google.com>
 <20151027235705.16059.63268.stgit@pjt-glaptop.roam.corp.google.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20151027235705.16059.63268.stgit@pjt-glaptop.roam.corp.google.com>
User-Agent: Mutt/1.5.22.1 (2013-10-16)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Tue, Oct 27, 2015 at 04:57:05PM -0700, Paul Turner wrote:
> +static void rseq_sched_out(struct preempt_notifier *pn,
> +			   struct task_struct *next)
> +{
> +	set_thread_flag(TIF_NOTIFY_RESUME);
> +}
>  
>  static __read_mostly struct preempt_ops rseq_preempt_ops = {
>  	.sched_in = rseq_sched_in_nop,
> -	.sched_out = rseq_sched_out_nop,
> +	.sched_out = rseq_sched_out,
>  };

Since we're unconditionally setting this TIF flag for these tasks, can't
we introduce something similar to the (contested) TIF_NOHZ_FULL thing
which is kept on the task indefinitely.

That avoids having the preempt notifiers and this atomic op in the
schedule path.