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

[Tejun Heo <tj@kernel.org>]

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.

Thanks.

-- 
tejun