Re: [RESEND][PATCH v2] mm: don't call lru draining in the nested lru_cache_disable

[Michal Hocko <mhocko@suse.com>]

On Fri 21-01-22 13:56:31, Minchan Kim wrote:
> On Fri, Jan 21, 2022 at 10:59:32AM +0100, Michal Hocko wrote:
> > On Thu 20-01-22 13:07:55, Minchan Kim wrote:
> > > On Thu, Jan 20, 2022 at 09:24:22AM +0100, Michal Hocko wrote:
> > > > On Wed 19-01-22 20:25:54, Minchan Kim wrote:
> > > > > On Wed, Jan 19, 2022 at 10:20:22AM +0100, Michal Hocko wrote:
> > > > [...]
> > > > > > What does prevent you from calling lru_cache_{disable,enable} this way
> > > > > > with the existing implementation? AFAICS calls can be nested just fine.
> > > > > > Or am I missing something?
> > > > > 
> > > > > It just increases more IPI calls since we drain the lru cache
> > > > > both upper layer and lower layer. That's I'd like to avoid
> > > > > in this patch. Just disable lru cache one time for entire
> > > > > allocation path.
> > > > 
> > > > I do not follow. Once you call lru_cache_disable at the higher level
> > > > then no new pages are going to be added to the pcp caches. At the same
> > > > time existing caches are flushed so the inner lru_cache_disable will not
> > > > trigger any new IPIs.
> > > 
> > > lru_cache_disable calls __lru_add_drain_all with force_all_cpus
> > > unconditionally so keep calling the IPI.
> > 
> > OK, this is something I have missed. Why cannot we remove the force_all
> > mode for lru_disable_count>0 when there are no pcp caches populated?
> 
> Couldn't gaurantee whether the IPI is finished with only atomic counter.
> 
> CPU 0                               CPU 1
> lru_cache_disable                   lru_cache_disable
>   ret = atomic_inc_return
>                                     
>                                    ret = atomic_inc_return
>   lru_add_drain_all(ret == 1);     lru_add_drain_all(ret == 1)
>     IPI ongoing                    skip IPI
>                                    alloc_contig_range
>                                    fail
>     ..
>     ..
> 
>    IPI done

But __lru_add_drain_all uses a local mutex while the IPI flushing is
done so the racing lru_cache_disable would block until
flush_work(&per_cpu(lru_add_drain_work, cpu)) completes so all IPIs are
handled. Or am I missing something?

-- 
Michal Hocko
SUSE Labs