Re: [PATCH 2/9] slab: remove synchronous rcu_barrier() call in memcg cache release path

[Tejun Heo]

Hello, Joonsoo.

On Tue, Jan 17, 2017 at 09:07:54AM +0900, Joonsoo Kim wrote:
> Long time no see! :)

Yeah, happy new year!

> IIUC, rcu_barrier() here prevents to destruct the kmem_cache until all
> slab pages in it are freed. These slab pages are freed through call_rcu().

Hmm... why do we need that tho?  SLAB_DESTROY_BY_RCU only needs to
protect the slab pages, not kmem cache struct.  I thought that this
was because kmem cache destruction is allowed to release pages w/o RCU
delaying it.

> Your patch changes it to another call_rcu() and, I think, if sequence of
> executing rcu callbacks is the same with sequence of adding rcu
> callbacks, it would work. However, I'm not sure that it is
> guaranteed by RCU API. Am I missing something?

The call sequence doesn't matter.  Whether you're using call_rcu() or
rcu_barrier(), you're just waiting for a grace period to pass before
continuing.  It doens't give any other ordering guarantees, so the new
code should be equivalent to the old one except for being asynchronous.

Thanks.

-- 
tejun