Re: [PATCH 6/6] percpu-refcount: implement percpu_ref_reinit() and percpu_ref_is_zero()

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Wed, Jun 18, 2014 at 10:07:27PM -0400, Tejun Heo wrote:
> On Thu, Jun 19, 2014 at 09:58:16AM +0800, Lai Jiangshan wrote:
> > On 06/18/2014 11:32 PM, Tejun Heo wrote:
> > > On Wed, Jun 18, 2014 at 11:37:35AM +0800, Lai Jiangshan wrote:
> > >>> @@ -97,7 +98,10 @@ static inline void percpu_ref_kill(struct percpu_ref *ref)
> > >>>  static inline bool __pcpu_ref_alive(struct percpu_ref *ref,
> > >>>  				    unsigned __percpu **pcpu_countp)
> > >>>  {
> > >>> -	unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr);
> > >>> +	unsigned long pcpu_ptr;
> > >>> +
> > >>> +	/* paired with smp_store_release() in percpu_ref_reinit() */
> > >>> +	pcpu_ptr = smp_load_acquire(&ref->pcpu_count_ptr);
> > >>
> > >>
> > >> Does "smp_load_acquire()" hurts the performance of percpu_ref_get/put()
> > >> in non-x86 system?
> > > 
> > > It's equivalent to data dependency barrier.  The only arch which needs
> > > something more than barrier() is alpha.  It isn't an issue.
> > 
> > But I searched from the source, smp_load_acquire() is just barrier() in
> > x86, arm64, ia64, s390, sparc, but it includes memory barrier 
> > instruction in other archs.
> 
> Hmmm, right, it's a stronger guarantee than the data dependency
> barrier.  This should probably use smp_wmb() and
> smp_read_barrier_depends().  That's all it needs anyway.

Yep, smp_load_acquire() orders its load against later loads and stores,
so it really does need a memory barrier on weakly ordered systems.

This is the "publish" operation for dynamically allocated per-CPU
references?  If so, agreed, you should be able to rely on dependency
ordering.  Make sure to comment the smp_read_barrier_depends().  ;-)

							Thanx, Paul

> Thanks.
> 
> -- 
> tejun
>