Re: [PATCH] eal: add notes to SMP memory barrier APIs

[Thomas Monjalon <thomas@monjalon.net>]

25/06/2023 10:45, Ruifeng Wang:
> From: Tyler Retzlaff <roretzla@linux.microsoft.com>
> > On Thu, Jun 22, 2023 at 08:19:30PM +0200, Mattias R�nnblom wrote:
> > > On 2023-06-21 08:44, Ruifeng Wang wrote:
> > > >+ *  This function is deprecated. It adds complexity to the memory
> > > >+ model
> > > >+ *  used by this project. C11 memory model should always be used.
> > > >+ *  rte_atomic_thread_fence() should be used instead.
> > >
> > > It's somewhat confusing to learn I should use the C11 memory model,
> > > and then in the next sentence that I should call a function which is
> > > not in C11.
> > 
> > i wonder if we can just do without the comments until we begin to adopt changes for 23.11
> > release because the guidance will be short lived.
> > 
> > in 23.07 we want to say that only gcc builtins that align with the standard C++ memory
> > model should be used.
> > 
> > in 23.11 we want to say that only standard C11 atomics should be used.
> 
> Good point. The memory order parameter will change in 23.11.
> 
> > 
> > my suggestion i guess is just adapt the patch to be appropriate for
> > 23.11 and only merge it after 23.07 release? might be easier to manage.
> 
> Agree to only merge it after 23.07. 
> I will update the comment for standard C11 atomics.

I would prefer having each step documented
so it will be clearer what is new in 23.11.