Re: [PATCH 6/6 v2] mm: Drain LRUs upon resume to userspace on nohz_full CPUs

[Michal Hocko]

On Mon 10-02-25 18:50:26, Hillf Danton wrote:
> On Sun,  9 Feb 2025 23:30:04 +0100 Frederic Weisbecker <frederic@xxxxxxxxxx>
> > @@ -769,6 +772,9 @@ static bool cpu_needs_drain(unsigned int cpu)
> >  {
> >  	struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
> >  
> > +	if (!housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE))
> > +		return false;
> > +
> >  	/* Check these in order of likelihood that they're not zero */
> >  	return folio_batch_count(&fbatches->lru_add) ||
> >  		folio_batch_count(&fbatches->lru_move_tail) ||
> > -- 
> > 2.46.0
> 
> Nit, I'd like to add a debug line to test your assumption that
> isolated tasks are pinned to a single nohz_full CPU.

Why? And why would you like to add a trivial VM_BUG_ON vector to the
kernel?

> --- x/mm/swap.c
> +++ y/mm/swap.c
> @@ -767,9 +767,10 @@ static void lru_add_drain_per_cpu(struct
>  static bool cpu_needs_drain(unsigned int cpu)
>  {
>  	struct cpu_fbatches *fbatches = &per_cpu(cpu_fbatches, cpu);
> +	bool yes;
>  
>  	/* Check these in order of likelihood that they're not zero */
> -	return folio_batch_count(&fbatches->lru_add) ||
> +	yes = folio_batch_count(&fbatches->lru_add) ||
>  		folio_batch_count(&fbatches->lru_move_tail) ||
>  		folio_batch_count(&fbatches->lru_deactivate_file) ||
>  		folio_batch_count(&fbatches->lru_deactivate) ||
> @@ -777,6 +778,12 @@ static bool cpu_needs_drain(unsigned int
>  		folio_batch_count(&fbatches->lru_activate) ||
>  		need_mlock_drain(cpu) ||
>  		has_bh_in_lru(cpu, NULL);
> +
> +	if (!housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) {
> +		VM_BUG_ON(yes);
> +		return false;
> +	}
> +	return yes;
>  }
>  
>  /*

-- 
Michal Hocko
SUSE Labs