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 <hannes@cmpxchg.org>
Reported-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Tested-by: Mikhail Zaslonko <zaslonko@linux.ibm.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Acked-by: Usama Arif <usama.arif@linux.dev>
Reviewed-by: Kairui Song <kasong@tencent.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nico Pache <npache@redhat.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 12 insertions, 21 deletions

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;