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 S934067Ab3ECRsG (ORCPT <rfc822;w@1wt.eu>);
	Fri, 3 May 2013 13:48:06 -0400
Received: from ja.ssi.bg ([178.16.129.10]:38215 "EHLO ja.ssi.bg"
	rhost-flags-OK-FAIL-OK-FAIL) by vger.kernel.org with ESMTP
	id S933812Ab3ECRsE (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Fri, 3 May 2013 13:48:04 -0400
Date: Fri, 3 May 2013 20:47:32 +0300 (EEST)
From: Julian Anastasov <ja@ssi.bg>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
cc: Peter Zijlstra <peterz@infradead.org>, Simon Horman <horms@verge.net.au>,
        Eric Dumazet <eric.dumazet@gmail.com>, Ingo Molnar <mingo@redhat.com>,
        lvs-devel@vger.kernel.org, netdev@vger.kernel.org,
        netfilter-devel@vger.kernel.org, linux-kernel@vger.kernel.org,
        Pablo Neira Ayuso <pablo@netfilter.org>,
        Dipankar Sarma <dipankar@in.ibm.com>
Subject: Re: [PATCH v2 1/2] sched: Add cond_resched_rcu_lock() helper
In-Reply-To: <20130503163045.GE3780@linux.vnet.ibm.com>
Message-ID: <alpine.LFD.2.00.1305031953440.1657@ja.ssi.bg>
References: <20130501155501.GB7521@dyad.programming.kicks-ass.net> <alpine.LFD.2.00.1305012004360.3397@ja.ssi.bg> <20130502072623.GE7521@dyad.programming.kicks-ass.net> <alpine.LFD.2.00.1305021848450.31548@ja.ssi.bg> <20130502173257.GX3780@linux.vnet.ibm.com>
 <alpine.LFD.2.00.1305022140020.31548@ja.ssi.bg> <20130502193409.GA3780@linux.vnet.ibm.com> <alpine.LFD.2.00.1305022249010.25417@ja.ssi.bg> <20130502223107.GB3780@linux.vnet.ibm.com> <alpine.LFD.2.00.1305031024080.1657@ja.ssi.bg>
 <20130503163045.GE3780@linux.vnet.ibm.com>
User-Agent: Alpine 2.00 (LFD 1167 2008-08-23)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


	Hello,

On Fri, 3 May 2013, Paul E. McKenney wrote:

> OK, after getting some sleep, I might have located the root cause of
> my confusion yesterday.
> 
> The key point is that I don't understand why we cannot get the effect
> we are looking for with the following in sched.h (or wherever):
> 
> static inline int cond_resched_rcu(void)
> {
> #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
> 	rcu_read_unlock();
> 	cond_resched();
> 	rcu_read_lock();
> #endif
> }
> 
> This adds absolutely no overhead in non-debug builds of CONFIG_PREEMPT_RCU,
> does the checking in debug builds, and allows voluntary preemption in
> !CONFIG_PREEMPT_RCU builds.  CONFIG_PROVE_RCU builds will check for an
> (illegal) outer rcu_read_lock() in CONFIG_PREEMPT_RCU builds, and you
> will get "scheduling while atomic" in response to an outer rcu_read_lock()
> in !CONFIG_PREEMPT_RCU builds.
> 
> It also seems to me a lot simpler.
> 
> Does this work, or am I still missing something?

	It should work. It is a better version of
the 2nd variant I mentioned here:

http://marc.info/?l=linux-netdev&m=136741839021257&w=2

	I'll stick to this version, hope Peter Zijlstra
agrees. Playing with PREEMPT_ACTIVE or another bit makes
the things more complex.

	To summarize:

- CONFIG_PREEMPT_RCU:
	- no empty functions called
	- CONFIG_DEBUG_ATOMIC_SLEEP can catch errors even
	for this case

- non-CONFIG_PREEMPT_RCU:
	- rcu_read_lock and rcu_read_unlock are barrier(),
	so it expands just to cond_resched()

	I'll repeat the tests tomorrow and if there are
no problems will post official version after the merge window.

Regards

--
Julian Anastasov <ja@ssi.bg>