Date: Thu, 19 Jun 2014 09:55:02 -0700
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>, cl@linux-foundation.org,
        kmo@daterainc.com, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 6/6] percpu-refcount: implement percpu_ref_reinit()
 and percpu_ref_is_zero()
Message-ID: <20140619165501.GB4904@linux.vnet.ibm.com>
Reply-To: paulmck@linux.vnet.ibm.com
References: <1403053685-28240-1-git-send-email-tj@kernel.org>
 <1403053685-28240-7-git-send-email-tj@kernel.org>
 <20140619022055.GD20100@mtj.dyndns.org>
 <53A25286.1030003@cn.fujitsu.com>
 <20140619133104.GH11042@htj.dyndns.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20140619133104.GH11042@htj.dyndns.org>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org

On Thu, Jun 19, 2014 at 09:31:04AM -0400, Tejun Heo wrote:
> On Thu, Jun 19, 2014 at 11:01:26AM +0800, Lai Jiangshan wrote:
> > > +	/*
> > > +	 * Restore per-cpu operation.  smp_store_release() is paired with
> > > +	 * smp_load_acquire() in __pcpu_ref_alive() and guarantees that the
> > 
> > s/smp_load_acquire()/smp_read_barrier_depends()/
> 
> Will update.
> 
> > s/smp_store_release()/smp_mb()/  if you accept my next comment.
> >
> > > +	 * zeroing is visible to all percpu accesses which can see the
> > > +	 * following PCPU_REF_DEAD clearing.
> > > +	 */
> > > +	for_each_possible_cpu(cpu)
> > > +		*per_cpu_ptr(pcpu_count, cpu) = 0;
> > > +
> > > +	smp_store_release(&ref->pcpu_count_ptr,
> > > +			  ref->pcpu_count_ptr & ~PCPU_REF_DEAD);
> > 
> > I think it would be better if smp_mb() is used.
> 
> smp_wmb() would be better here.  We don't need the reader side.
> 
> > it is documented that smp_read_barrier_depends() and smp_mb() are paired.
> > Not smp_read_barrier_depends() and smp_store_release().

Well, sounds like the documentation needs an update, then.  ;-)

For example, current rcu_assign_pointer() is a wrapper around
smp_store_release().

> I don't know.  I thought about doing that but the RCU accessors are
> pairing store_release with read_barrier_depends, so I don't think the
> particular paring is problematic and store_release is better at
> documenting what's being barriered.

Which Tejun noted as well.

							Thanx, Paul

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/