Re: [PATCH 1/3] slab: decouple pointer to barn from kmem_cache_node

[Vlastimil Babka (SUSE)]

On 3/13/26 12:48, Harry Yoo wrote:
> On Fri, Mar 13, 2026 at 10:46:15AM +0100, Vlastimil Babka (SUSE) wrote:
>> On 3/13/26 10:27, Harry Yoo wrote:
>> > On Wed, Mar 11, 2026 at 09:25:55AM +0100, Vlastimil Babka (SUSE) wrote:
>> >> diff --git a/mm/slub.c b/mm/slub.c
>> >> index 20cb4f3b636d..609a183f8533 100644
>> >> --- a/mm/slub.c
>> >> +++ b/mm/slub.c
>> >> @@ -436,26 +436,24 @@ struct kmem_cache_node {
>> >>  /*
>> >> - * Get the barn of the current cpu's closest memory node. It may not exist on
>> >> - * systems with memoryless nodes but without CONFIG_HAVE_MEMORYLESS_NODES
>> >> + * Get the barn of the current cpu's memory node. It may be a memoryless node.
>> >>   */
>> >>  static inline struct node_barn *get_barn(struct kmem_cache *s)
>> >>  {
>> >> -	struct kmem_cache_node *n = get_node(s, numa_mem_id());
>> >> -
>> >> -	if (!n)
>> >> -		return NULL;
>> >> -
>> >> -	return n->barn;
>> >> +	return get_barn_node(s, numa_node_id());
>> >>  }
>> > 
>> > Previously, memoryless nodes on architectures w/ CONFIG_HAVE_MEMORYLESS_NODES
>> > shared the barn of the nearest NUMA node with memory.
>> > 
>> > But now memoryless nodes will have their own barns (after patch 2)
>> > regardless of CONFIG_HAVE_MEMORYLESS_NODES, and that's intentional, right?
>> 
>> Yeah it improves their caching capacity, but good point, will mention it in
>> the changelog.
> 
> Thanks! just wanted to check that it was intentional.

I wanted to update the changelog as promised. But realized that the change
from numa_node_id() to numa_node_id() in get_barn() should actually be done
only in patch 2, so I will move it there. In patch 1 that would mean no
barns with CONFIG_HAVE_MEMORYLESS_NODES and thus a performance bisection hazard.

> with that, please feel free to add:
> Reviewed-by: Harry Yoo <harry.yoo@xxxxxxxxxx>

Thanks!