Re: [PATCH v3 2/5] locking/rwsem: Limit # of null owner retries for handoff writer

[Waiman Long]

On 10/25/22 07:48, Peter Zijlstra wrote:
> On Tue, Oct 25, 2022 at 01:22:22PM +0200, Peter Zijlstra wrote:
>
> > Funny, I find the former approach much saner. Disabling preemption
> > around the whole thing fixes the fundamental problem while spin-limiting
> > is a band-aid.
> >
> > Note how rwsem_write_trylock() already does preempt_disable(), having
> > the read-side do something similar only makes sense.
> Something like the completely untested below perhaps...

That is quite a number of changes spread over many different functions. 
That is the kind of changes that may make it harder to backport to 
stable releases.

This patch is just a stop-gap measure for stable releases which I 
essentially revert in a later patch. I have no objection to disable 
preemption in within the rwsem code exception to be backported to a 
stable release. So I can add another patch on top of the series to 
essentially do that.

Cheers,
Longman