Re: [PATCH 1/2] IB/hfi1: Use preempt_{dis,en}able_nort()

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Wed, Oct 11, 2017 at 01:03:55PM +0200, Sebastian Andrzej Siewior escreveu:
> On 2017-10-10 16:02:18 [-0300], Arnaldo Carvalho de Melo wrote:
> > 
> > Right, and so far there were no strong objection for this one to be
> > merged on the -rt tree, Sebastian, can you do it please? Adding Dennis'
> > reviewed-by, one of maintainers for this driver, ok?
> 
> I am still curious about the performance improvement that is with this
> preempt disable section compared to without it compared to !PREEMPT
> kernel..
> If that is important then migrate_disable() would do that on RT.

I can try that

> I guess that there were no splat with CONFIG_DEBUG_PREEMPT ?

I haven't tried that

> If that is all okay, please resend the patch with the explanation why
> this preempt_disable() does not matter and I pick it up.

I can just pick the explanation given by the authors and stash it there,
I guess.
 
> > > tree? Anyway, for this patch:
> > > 
> > > Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
> 
> Sebastian