Re: [PATCH] refcount: provide same memory ordering guarantees as in atomic_t

From: Michal Hocko
Date: Thu Nov 16 2017 - 08:44:51 EST


On Mon 13-11-17 09:09:57, Reshetova, Elena wrote:
> <snip>
>
> > Note that there's work done on better documents and updates to this one.
> > One document that might be good to read (I have not in fact had time to
> > read it myself yet :-():
> >
> > https://github.com/aparri/memory-
> > model/blob/master/Documentation/explanation.txt
> >
>
> I have just finished reading over this and must say that this is excellent.

I fully second this. The main problem with
Documentation/memory-barriers.txt is that it jumps from "easy to follow"
to "blow your head" parts is just too quick. On the other hand the above
explanation builds the picture from basics and piles up new layers on
top of previous. So I found it much more easier to grasp. I cannot
really speak for the correctness in all aspects but it certainly makes a
lot of sense to me. If you are really interested then feel free to add.
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
--
Michal Hocko
SUSE Labs