From fafaeceb89a5e2e856ff04c2cacb6cae4a2ecb67 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 27 May 2026 16:45:16 -0400 Subject: mm: switch deferred split shrinker to list_lru The deferred split queue handles cgroups in a suboptimal fashion. The queue is per-NUMA node or per-cgroup, not the intersection. That means on a cgrouped system, a node-restricted allocation entering reclaim can end up splitting large pages on other nodes: alloc/unmap deferred_split_folio() list_add_tail(memcg->split_queue) set_shrinker_bit(memcg, node, deferred_shrinker_id) for_each_zone_zonelist_nodemask(restricted_nodes) mem_cgroup_iter() shrink_slab(node, memcg) shrink_slab_memcg(node, memcg) if test_shrinker_bit(memcg, node, deferred_shrinker_id) deferred_split_scan() walks memcg->split_queue The shrinker bit adds an imperfect guard rail. As soon as the cgroup has a single large page on the node of interest, all large pages owned by that memcg, including those on other nodes, will be split. list_lru properly sets up per-node, per-cgroup lists. As a bonus, it streamlines a lot of the list operations and reclaim walks. It's used widely by other major shrinkers already. Convert the deferred split queue as well. The list_lru per-memcg heads are instantiated on demand when the first object of interest is allocated for a cgroup, by calling folio_memcg_alloc_deferred(). Add calls to where splittable pages are created: anon faults, swapin faults, khugepaged collapse. These calls create all possible node heads for the cgroup at once, so the migration code (between nodes) doesn't need any special care. [akpm@linux-foundation.org: fix build with CONFIG_TRANSPARENT_HUGEPAGE=n] Link: https://lore.kernel.org/202605281620.lc3rtkBm-lkp@intel.com [hannes@cmpxchg.org: fix cgroup.memory=nokmem handling] Link: https://lore.kernel.org/ah9PGv12mqai84ES@cmpxchg.org Link: https://lore.kernel.org/20260527204757.2544958-10-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Mikhail Zaslonko Tested-by: Mikhail Zaslonko Acked-by: Shakeel Butt Reviewed-by: Lorenzo Stoakes (Oracle) Acked-by: Usama Arif Reviewed-by: Kairui Song Cc: Baolin Wang Cc: Barry Song Cc: Dave Chinner Cc: David Hildenbrand (Arm) Cc: Dev Jain Cc: Lance Yang Cc: Liam R. Howlett Cc: Michal Hocko Cc: Muchun Song Cc: Nico Pache Cc: Roman Gushchin Cc: Ryan Roberts Cc: Vasily Gorbik Cc: Vlastimil Babka Cc: Zi Yan Cc: kernel test robot Signed-off-by: Andrew Morton --- include/linux/huge_mm.h | 17 ++++++++++++----- include/linux/memcontrol.h | 4 ---- include/linux/mmzone.h | 12 ------------ 3 files changed, 12 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 58382e97a66d..c0d223d0c556 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -439,10 +439,10 @@ static inline int split_huge_page(struct page *page) { return split_huge_page_to_list_to_order(page, NULL, 0); } + +int folio_memcg_alloc_deferred(struct folio *folio); + void deferred_split_folio(struct folio *folio, bool partially_mapped); -#ifdef CONFIG_MEMCG -void reparent_deferred_split_queue(struct mem_cgroup *memcg); -#endif void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze); @@ -679,8 +679,15 @@ static inline int try_folio_split_to_order(struct folio *folio, return -EINVAL; } -static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {} -static inline void reparent_deferred_split_queue(struct mem_cgroup *memcg) {} +static inline int folio_memcg_alloc_deferred(struct folio *folio) +{ + return 0; +} + +static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) +{ +} + #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8f2662db166b..e1f46a0016fc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -278,10 +278,6 @@ struct mem_cgroup { struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - struct deferred_split deferred_split_queue; -#endif - #ifdef CONFIG_LRU_GEN_WALKS_MMU /* per-memcg mm_struct list */ struct lru_gen_mm_list mm_list; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1331a7b93f33..8e449f524f26 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1431,14 +1431,6 @@ struct zonelist { */ extern struct page *mem_map; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -struct deferred_split { - spinlock_t split_queue_lock; - struct list_head split_queue; - unsigned long split_queue_len; -}; -#endif - #ifdef CONFIG_MEMORY_FAILURE /* * Per NUMA node memory failure handling statistics. @@ -1564,10 +1556,6 @@ typedef struct pglist_data { unsigned long first_deferred_pfn; #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - struct deferred_split deferred_split_queue; -#endif - #ifdef CONFIG_NUMA_BALANCING /* start time in ms of current promote rate limit period */ unsigned int nbp_rl_start; -- cgit v1.2.3