Re: [PATCH 1/2] Optimize generic spinlock code and use C11 like atomic macros.

[Stefan Liebler <stli at linux dot vnet dot ibm dot com>]

On 04/09/2017 03:51 PM, Torvald Riegel wrote:
> On Fri, 2017-04-07 at 18:22 +0200, Stefan Liebler wrote:
> > On 04/06/2017 04:00 PM, Torvald Riegel wrote:
> > > Otherwise, this patch looks good to me.
> > Thanks for review. Here is an updated patch. I've changed the comments
> > and added the POSIX requirement in pthread_spin_trylock.
>
> I assume that this means that you have taken care of all the review
> comments I have and changed nothing else; thus, I won't review this in
> detail again.  (If there have been other changes, please let me know so
> that I can look at them specifically.)
Yes, I have taken care of all the review comments and changed nothing else.

> > @architecture maintainers:
> > I've added defines of ATOMIC_EXCHANGE_USES_CAS in the architecture
> > specific atomic-machine.h files.
> > See comment in include/atomic.h:
> > /* ATOMIC_EXCHANGE_USES_CAS is equal to 1 if atomic_exchange operations
> >     are implemented based on a CAS loop; otherwise, this is 0 and we assume
> >     that the atomic_exchange operations could provide better performance
> >     than a CAS loop.  */
> >
> > Can review the definition to 0 or 1 in the atomic-machine.h file of your
> > architecture, please?
>
> I think we primarily need feedback from the maintainers of the
> architectures where we're not quite sure.  Let's see how responsive
> everyone is and then decide whether we need to continue pinging some of
> them potentially or whether we have enough information to be able to
> commit the patch.
Okay.

Chris has already replied directly to me.
On 04/07/2017 06:50 PM, Chris Metcalf wrote:
> Thanks, looks good for tilegx/tilepro.

Bye
Stefan