[merged mm-stable] mm-switch-deferred-split-shrinker-to-list_lru.patch removed from -mm tree

[merged mm-stable] mm-switch-deferred-split-shrinker-to-list_lru.patch removed from -mm tree

[Andrew Morton]

The quilt patch titled
     Subject: mm: switch deferred split shrinker to list_lru
has been removed from the -mm tree.  Its filename was
     mm-switch-deferred-split-shrinker-to-list_lru.patch

This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Johannes Weiner <hannes@cmpxchg.org>
Subject: mm: switch deferred split shrinker to list_lru
Date: Wed, 27 May 2026 16:45:16 -0400

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>
---

 include/linux/huge_mm.h    |   17 +
 include/linux/memcontrol.h |    4 
 include/linux/mmzone.h     |   12 -
 mm/huge_memory.c           |  367 +++++++++++------------------------
 mm/internal.h              |    2 
 mm/khugepaged.c            |    5 
 mm/memcontrol.c            |   12 -
 mm/memory.c                |    4 
 mm/mm_init.c               |   15 -
 mm/swap_state.c            |   10 
 10 files changed, 160 insertions(+), 288 deletions(-)

--- a/include/linux/huge_mm.h~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/include/linux/huge_mm.h
@@ -439,10 +439,10 @@ static inline int split_huge_page(struct
 {
 	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_ord
 	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)
 
--- a/include/linux/memcontrol.h~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/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;
--- a/include/linux/mmzone.h~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/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;
--- a/mm/huge_memory.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/huge_memory.c
@@ -14,6 +14,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
+#include <linux/list_lru.h>
 #include <linux/shrinker.h>
 #include <linux/mm_inline.h>
 #include <linux/swapops.h>
@@ -67,6 +68,8 @@ unsigned long transparent_hugepage_flags
 	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)|
 	(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG);
 
+static struct lock_class_key deferred_split_key;
+static struct list_lru deferred_split_lru;
 static struct shrinker *deferred_split_shrinker;
 static unsigned long deferred_split_count(struct shrinker *shrink,
 					  struct shrink_control *sc);
@@ -932,15 +935,28 @@ static inline void hugepage_exit_sysfs(s
 }
 #endif /* CONFIG_SYSFS */
 
+int folio_memcg_alloc_deferred(struct folio *folio)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+	return folio_memcg_list_lru_alloc(folio, &deferred_split_lru, GFP_KERNEL);
+}
+
 static int __init thp_shrinker_init(void)
 {
 	deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE |
-						 SHRINKER_MEMCG_AWARE |
-						 SHRINKER_NONSLAB,
+						 SHRINKER_MEMCG_AWARE,
 						 "thp-deferred_split");
 	if (!deferred_split_shrinker)
 		return -ENOMEM;
 
+	if (list_lru_init_memcg_key(&deferred_split_lru,
+				    deferred_split_shrinker,
+				    &deferred_split_key)) {
+		shrinker_free(deferred_split_shrinker);
+		return -ENOMEM;
+	}
+
 	deferred_split_shrinker->count_objects = deferred_split_count;
 	deferred_split_shrinker->scan_objects = deferred_split_scan;
 	shrinker_register(deferred_split_shrinker);
@@ -962,6 +978,7 @@ static int __init thp_shrinker_init(void
 	huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero");
 	if (!huge_zero_folio_shrinker) {
 		shrinker_free(deferred_split_shrinker);
+		list_lru_destroy(&deferred_split_lru);
 		return -ENOMEM;
 	}
 
@@ -976,6 +993,7 @@ static void __init thp_shrinker_exit(voi
 {
 	shrinker_free(huge_zero_folio_shrinker);
 	shrinker_free(deferred_split_shrinker);
+	list_lru_destroy(&deferred_split_lru);
 }
 
 static int __init hugepage_init(void)
@@ -1155,119 +1173,6 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struc
 	return pmd;
 }
 
-static struct deferred_split *split_queue_node(int nid)
-{
-	struct pglist_data *pgdata = NODE_DATA(nid);
-
-	return &pgdata->deferred_split_queue;
-}
-
-#ifdef CONFIG_MEMCG
-static inline
-struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
-					   struct deferred_split *queue)
-{
-	if (mem_cgroup_disabled())
-		return NULL;
-	if (split_queue_node(folio_nid(folio)) == queue)
-		return NULL;
-	return container_of(queue, struct mem_cgroup, deferred_split_queue);
-}
-
-static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memcg)
-{
-	return memcg ? &memcg->deferred_split_queue : split_queue_node(nid);
-}
-#else
-static inline
-struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
-					   struct deferred_split *queue)
-{
-	return NULL;
-}
-
-static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memcg)
-{
-	return split_queue_node(nid);
-}
-#endif
-
-static struct deferred_split *split_queue_lock(int nid, struct mem_cgroup *memcg)
-{
-	struct deferred_split *queue;
-
-retry:
-	queue = memcg_split_queue(nid, memcg);
-	spin_lock(&queue->split_queue_lock);
-	/*
-	 * There is a period between setting memcg to dying and reparenting
-	 * deferred split queue, and during this period the THPs in the deferred
-	 * split queue will be hidden from the shrinker side.
-	 */
-	if (unlikely(memcg_is_dying(memcg))) {
-		spin_unlock(&queue->split_queue_lock);
-		memcg = parent_mem_cgroup(memcg);
-		goto retry;
-	}
-
-	return queue;
-}
-
-static struct deferred_split *
-split_queue_lock_irqsave(int nid, struct mem_cgroup *memcg, unsigned long *flags)
-{
-	struct deferred_split *queue;
-
-retry:
-	queue = memcg_split_queue(nid, memcg);
-	spin_lock_irqsave(&queue->split_queue_lock, *flags);
-	if (unlikely(memcg_is_dying(memcg))) {
-		spin_unlock_irqrestore(&queue->split_queue_lock, *flags);
-		memcg = parent_mem_cgroup(memcg);
-		goto retry;
-	}
-
-	return queue;
-}
-
-static struct deferred_split *folio_split_queue_lock(struct folio *folio)
-{
-	struct deferred_split *queue;
-
-	rcu_read_lock();
-	queue = split_queue_lock(folio_nid(folio), folio_memcg(folio));
-	/*
-	 * The memcg destruction path is acquiring the split queue lock for
-	 * reparenting. Once you have it locked, it's safe to drop the rcu lock.
-	 */
-	rcu_read_unlock();
-
-	return queue;
-}
-
-static struct deferred_split *
-folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags)
-{
-	struct deferred_split *queue;
-
-	rcu_read_lock();
-	queue = split_queue_lock_irqsave(folio_nid(folio), folio_memcg(folio), flags);
-	rcu_read_unlock();
-
-	return queue;
-}
-
-static inline void split_queue_unlock(struct deferred_split *queue)
-{
-	spin_unlock(&queue->split_queue_lock);
-}
-
-static inline void split_queue_unlock_irqrestore(struct deferred_split *queue,
-						 unsigned long flags)
-{
-	spin_unlock_irqrestore(&queue->split_queue_lock, flags);
-}
-
 static inline bool is_transparent_hugepage(const struct folio *folio)
 {
 	if (!folio_test_large(folio))
@@ -1368,6 +1273,14 @@ static struct folio *vma_alloc_anon_foli
 		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
 		return NULL;
 	}
+
+	if (folio_memcg_alloc_deferred(folio)) {
+		folio_put(folio);
+		count_vm_event(THP_FAULT_FALLBACK);
+		count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
+		return NULL;
+	}
+
 	folio_throttle_swaprate(folio, gfp);
 
        /*
@@ -3903,34 +3816,43 @@ static int __folio_freeze_and_split_unma
 	struct folio *end_folio = folio_next(folio);
 	struct folio *new_folio, *next;
 	int old_order = folio_order(folio);
+	struct list_lru_one *lru;
+	bool dequeue_deferred;
 	int ret = 0;
-	struct deferred_split *ds_queue;
 
 	VM_WARN_ON_ONCE(!mapping && end);
-	/* Prevent deferred_split_scan() touching ->_refcount */
-	ds_queue = folio_split_queue_lock(folio);
+	/*
+	 * If this folio can be on the deferred split queue, lock out
+	 * the shrinker before freezing the ref. If the shrinker sees
+	 * a 0-ref folio, it assumes it beat folio_put() to the list
+	 * lock and must clean up the LRU state - the same dequeue we
+	 * will do below as part of the split.
+	 */
+	dequeue_deferred = folio_test_anon(folio) && old_order > 1;
+	if (dequeue_deferred) {
+		struct mem_cgroup *memcg;
+
+		rcu_read_lock();
+		memcg = folio_memcg(folio);
+		lru = list_lru_lock(&deferred_split_lru,
+				    folio_nid(folio), &memcg);
+	}
 	if (folio_ref_freeze(folio, folio_cache_ref_count(folio) + 1)) {
 		struct swap_cluster_info *ci = NULL;
 		struct lruvec *lruvec;
 
-		if (old_order > 1) {
-			if (!list_empty(&folio->_deferred_list)) {
-				ds_queue->split_queue_len--;
-				/*
-				 * Reinitialize page_deferred_list after removing the
-				 * page from the split_queue, otherwise a subsequent
-				 * split will see list corruption when checking the
-				 * page_deferred_list.
-				 */
-				list_del_init(&folio->_deferred_list);
-			}
+		if (dequeue_deferred) {
+			__list_lru_del(&deferred_split_lru, lru,
+				       &folio->_deferred_list, folio_nid(folio));
 			if (folio_test_partially_mapped(folio)) {
 				folio_clear_partially_mapped(folio);
 				mod_mthp_stat(old_order,
 					MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 			}
+			list_lru_unlock(lru);
+			rcu_read_unlock();
 		}
-		split_queue_unlock(ds_queue);
+
 		if (mapping) {
 			int nr = folio_nr_pages(folio);
 
@@ -4031,7 +3953,10 @@ static int __folio_freeze_and_split_unma
 		if (ci)
 			swap_cluster_unlock(ci);
 	} else {
-		split_queue_unlock(ds_queue);
+		if (dequeue_deferred) {
+			list_lru_unlock(lru);
+			rcu_read_unlock();
+		}
 		return -EAGAIN;
 	}
 
@@ -4397,33 +4322,37 @@ int split_folio_to_list(struct folio *fo
  * queueing THP splits, and that list is (racily observed to be) non-empty.
  *
  * It is unsafe to call folio_unqueue_deferred_split() until folio refcount is
- * zero: because even when split_queue_lock is held, a non-empty _deferred_list
- * might be in use on deferred_split_scan()'s unlocked on-stack list.
+ * zero: because even when the list_lru lock is held, a non-empty
+ * _deferred_list might be in use on deferred_split_scan()'s unlocked
+ * on-stack list.
  *
- * If memory cgroups are enabled, split_queue_lock is in the mem_cgroup: it is
- * therefore important to unqueue deferred split before changing folio memcg.
+ * The list_lru sublist is determined by folio's memcg: it is therefore
+ * important to unqueue deferred split before changing folio memcg.
  */
 bool __folio_unqueue_deferred_split(struct folio *folio)
 {
-	struct deferred_split *ds_queue;
+	struct mem_cgroup *memcg;
+	struct list_lru_one *lru;
+	int nid = folio_nid(folio);
 	unsigned long flags;
 	bool unqueued = false;
 
 	WARN_ON_ONCE(folio_ref_count(folio));
 	WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg_charged(folio));
 
-	ds_queue = folio_split_queue_lock_irqsave(folio, &flags);
-	if (!list_empty(&folio->_deferred_list)) {
-		ds_queue->split_queue_len--;
+	rcu_read_lock();
+	memcg = folio_memcg(folio);
+	lru = list_lru_lock_irqsave(&deferred_split_lru, nid, &memcg, &flags);
+	if (__list_lru_del(&deferred_split_lru, lru, &folio->_deferred_list, nid)) {
 		if (folio_test_partially_mapped(folio)) {
 			folio_clear_partially_mapped(folio);
 			mod_mthp_stat(folio_order(folio),
 				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
 		}
-		list_del_init(&folio->_deferred_list);
 		unqueued = true;
 	}
-	split_queue_unlock_irqrestore(ds_queue, flags);
+	list_lru_unlock_irqrestore(lru, &flags);
+	rcu_read_unlock();
 
 	return unqueued;	/* useful for debug warnings */
 }
@@ -4431,7 +4360,9 @@ bool __folio_unqueue_deferred_split(stru
 /* partially_mapped=false won't clear PG_partially_mapped folio flag */
 void deferred_split_folio(struct folio *folio, bool partially_mapped)
 {
-	struct deferred_split *ds_queue;
+	struct list_lru_one *lru;
+	int nid;
+	struct mem_cgroup *memcg;
 	unsigned long flags;
 
 	/*
@@ -4454,7 +4385,11 @@ void deferred_split_folio(struct folio *
 	if (folio_test_swapcache(folio))
 		return;
 
-	ds_queue = folio_split_queue_lock_irqsave(folio, &flags);
+	nid = folio_nid(folio);
+
+	rcu_read_lock();
+	memcg = folio_memcg(folio);
+	lru = list_lru_lock_irqsave(&deferred_split_lru, nid, &memcg, &flags);
 	if (partially_mapped) {
 		if (!folio_test_partially_mapped(folio)) {
 			folio_set_partially_mapped(folio);
@@ -4462,36 +4397,20 @@ void deferred_split_folio(struct folio *
 				count_vm_event(THP_DEFERRED_SPLIT_PAGE);
 			count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
 			mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1);
-
 		}
 	} else {
 		/* partially mapped folios cannot become non-partially mapped */
 		VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
 	}
-	if (list_empty(&folio->_deferred_list)) {
-		struct mem_cgroup *memcg;
-
-		memcg = folio_split_queue_memcg(folio, ds_queue);
-		list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
-		ds_queue->split_queue_len++;
-		if (memcg)
-			set_shrinker_bit(memcg, folio_nid(folio),
-					 shrinker_id(deferred_split_shrinker));
-	}
-	split_queue_unlock_irqrestore(ds_queue, flags);
+	__list_lru_add(&deferred_split_lru, lru, &folio->_deferred_list, nid, memcg);
+	list_lru_unlock_irqrestore(lru, &flags);
+	rcu_read_unlock();
 }
 
 static unsigned long deferred_split_count(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
-	struct pglist_data *pgdata = NODE_DATA(sc->nid);
-	struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
-
-#ifdef CONFIG_MEMCG
-	if (sc->memcg)
-		ds_queue = &sc->memcg->deferred_split_queue;
-#endif
-	return READ_ONCE(ds_queue->split_queue_len);
+	return list_lru_shrink_count(&deferred_split_lru, sc);
 }
 
 static bool thp_underused(struct folio *folio)
@@ -4521,45 +4440,49 @@ static bool thp_underused(struct folio *
 	return false;
 }
 
+static enum lru_status deferred_split_isolate(struct list_head *item,
+					      struct list_lru_one *lru,
+					      void *cb_arg)
+{
+	struct folio *folio = container_of(item, struct folio, _deferred_list);
+	struct list_head *freeable = cb_arg;
+
+	if (folio_try_get(folio)) {
+		list_lru_isolate_move(lru, item, freeable);
+		return LRU_REMOVED;
+	}
+
+	/*
+	 * We lost race with folio_put(). Read folio state before the
+	 * isolate: folio_unqueue_deferred_split() checks list_empty()
+	 * locklessly, so once removed the folio can be freed any time.
+	 */
+	if (folio_test_partially_mapped(folio)) {
+		folio_clear_partially_mapped(folio);
+		mod_mthp_stat(folio_order(folio),
+			      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
+	}
+	list_lru_isolate(lru, item);
+	return LRU_REMOVED;
+}
+
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
-	struct deferred_split *ds_queue;
-	unsigned long flags;
+	LIST_HEAD(dispose);
 	struct folio *folio, *next;
-	int split = 0, i;
-	struct folio_batch fbatch;
-
-	folio_batch_init(&fbatch);
+	int split = 0;
+	unsigned long isolated;
 
-retry:
-	ds_queue = split_queue_lock_irqsave(sc->nid, sc->memcg, &flags);
-	/* Take pin on all head pages to avoid freeing them under us */
-	list_for_each_entry_safe(folio, next, &ds_queue->split_queue,
-							_deferred_list) {
-		if (folio_try_get(folio)) {
-			folio_batch_add(&fbatch, folio);
-		} else if (folio_test_partially_mapped(folio)) {
-			/* We lost race with folio_put() */
-			folio_clear_partially_mapped(folio);
-			mod_mthp_stat(folio_order(folio),
-				      MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
-		}
-		list_del_init(&folio->_deferred_list);
-		ds_queue->split_queue_len--;
-		if (!--sc->nr_to_scan)
-			break;
-		if (!folio_batch_space(&fbatch))
-			break;
-	}
-	split_queue_unlock_irqrestore(ds_queue, flags);
+	isolated = list_lru_shrink_walk_irq(&deferred_split_lru, sc,
+					    deferred_split_isolate, &dispose);
 
-	for (i = 0; i < folio_batch_count(&fbatch); i++) {
+	list_for_each_entry_safe(folio, next, &dispose, _deferred_list) {
 		bool did_split = false;
 		bool underused = false;
-		struct deferred_split *fqueue;
 
-		folio = fbatch.folios[i];
+		list_del_init(&folio->_deferred_list);
+
 		if (!folio_test_partially_mapped(folio)) {
 			/*
 			 * See try_to_map_unused_to_zeropage(): we cannot
@@ -4588,63 +4511,23 @@ next:
 		 * underused, then consider it used and don't add it back to
 		 * split_queue.
 		 */
-		if (did_split || !folio_test_partially_mapped(folio))
-			continue;
+		if (!did_split && folio_test_partially_mapped(folio)) {
 requeue:
-		/*
-		 * Add back partially mapped folios, or underused folios that
-		 * we could not lock this round.
-		 */
-		fqueue = folio_split_queue_lock_irqsave(folio, &flags);
-		if (list_empty(&folio->_deferred_list)) {
-			list_add_tail(&folio->_deferred_list, &fqueue->split_queue);
-			fqueue->split_queue_len++;
+			rcu_read_lock();
+			list_lru_add_irq(&deferred_split_lru,
+					 &folio->_deferred_list,
+					 folio_nid(folio),
+					 folio_memcg(folio));
+			rcu_read_unlock();
 		}
-		split_queue_unlock_irqrestore(fqueue, flags);
-	}
-	folios_put(&fbatch);
-
-	if (sc->nr_to_scan && !list_empty(&ds_queue->split_queue)) {
-		cond_resched();
-		goto retry;
+		folio_put(folio);
 	}
 
-	/*
-	 * Stop shrinker if we didn't split any page, but the queue is empty.
-	 * This can happen if pages were freed under us.
-	 */
-	if (!split && list_empty(&ds_queue->split_queue))
+	if (!split && !isolated)
 		return SHRINK_STOP;
 	return split;
 }
 
-#ifdef CONFIG_MEMCG
-void reparent_deferred_split_queue(struct mem_cgroup *memcg)
-{
-	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
-	struct deferred_split *ds_queue = &memcg->deferred_split_queue;
-	struct deferred_split *parent_ds_queue = &parent->deferred_split_queue;
-	int nid;
-
-	spin_lock_irq(&ds_queue->split_queue_lock);
-	spin_lock_nested(&parent_ds_queue->split_queue_lock, SINGLE_DEPTH_NESTING);
-
-	if (!ds_queue->split_queue_len)
-		goto unlock;
-
-	list_splice_tail_init(&ds_queue->split_queue, &parent_ds_queue->split_queue);
-	parent_ds_queue->split_queue_len += ds_queue->split_queue_len;
-	ds_queue->split_queue_len = 0;
-
-	for_each_node(nid)
-		set_shrinker_bit(parent, nid, shrinker_id(deferred_split_shrinker));
-
-unlock:
-	spin_unlock(&parent_ds_queue->split_queue_lock);
-	spin_unlock_irq(&ds_queue->split_queue_lock);
-}
-#endif
-
 #ifdef CONFIG_DEBUG_FS
 static void split_huge_pages_all(void)
 {
--- a/mm/internal.h~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/internal.h
@@ -852,7 +852,7 @@ static inline bool folio_unqueue_deferre
 	/*
 	 * At this point, there is no one trying to add the folio to
 	 * deferred_list. If folio is not in deferred_list, it's safe
-	 * to check without acquiring the split_queue_lock.
+	 * to check without acquiring the list_lru lock.
 	 */
 	if (data_race(list_empty(&folio->_deferred_list)))
 		return false;
--- a/mm/khugepaged.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/khugepaged.c
@@ -1123,6 +1123,11 @@ static enum scan_result collapse_huge_pa
 	if (result != SCAN_SUCCEED)
 		goto out_nolock;
 
+	if (folio_memcg_alloc_deferred(folio)) {
+		result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+		goto out_nolock;
+	}
+
 	mmap_read_lock(mm);
 	result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
 	if (result != SCAN_SUCCEED) {
--- a/mm/memcontrol.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/memcontrol.c
@@ -4144,11 +4144,6 @@ static struct mem_cgroup *mem_cgroup_all
 		memcg->cgwb_frn[i].done =
 			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
 #endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	spin_lock_init(&memcg->deferred_split_queue.split_queue_lock);
-	INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
-	memcg->deferred_split_queue.split_queue_len = 0;
-#endif
 	lru_gen_init_memcg(memcg);
 	return memcg;
 fail:
@@ -4299,11 +4294,10 @@ static void mem_cgroup_css_offline(struc
 	zswap_memcg_offline_cleanup(memcg);
 
 	memcg_offline_kmem(memcg);
-	reparent_deferred_split_queue(memcg);
 	/*
-	 * The reparenting of objcg must be after the reparenting of the
-	 * list_lru and deferred_split_queue above, which ensures that they will
-	 * not mistakenly get the parent list_lru and deferred_split_queue.
+	 * The reparenting of objcg must be after the reparenting of
+	 * the list_lru in memcg_offline_kmem(), which ensures that
+	 * they will not mistakenly get the parent list_lru.
 	 */
 	memcg_reparent_objcgs(memcg);
 	reparent_shrinker_deferred(memcg);
--- a/mm/memory.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/memory.c
@@ -5222,6 +5222,10 @@ static struct folio *alloc_anon_folio(st
 			folio_put(folio);
 			goto next;
 		}
+		if (order > 1 && folio_memcg_alloc_deferred(folio)) {
+			folio_put(folio);
+			goto fallback;
+		}
 		folio_throttle_swaprate(folio, gfp);
 		/*
 		 * When a folio is not zeroed during allocation
--- a/mm/mm_init.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/mm_init.c
@@ -1373,19 +1373,6 @@ static void __init calculate_node_totalp
 	pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void pgdat_init_split_queue(struct pglist_data *pgdat)
-{
-	struct deferred_split *ds_queue = &pgdat->deferred_split_queue;
-
-	spin_lock_init(&ds_queue->split_queue_lock);
-	INIT_LIST_HEAD(&ds_queue->split_queue);
-	ds_queue->split_queue_len = 0;
-}
-#else
-static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
-#endif
-
 #ifdef CONFIG_COMPACTION
 static void pgdat_init_kcompactd(struct pglist_data *pgdat)
 {
@@ -1401,8 +1388,6 @@ static void __meminit pgdat_init_interna
 
 	pgdat_resize_init(pgdat);
 	pgdat_kswapd_lock_init(pgdat);
-
-	pgdat_init_split_queue(pgdat);
 	pgdat_init_kcompactd(pgdat);
 
 	init_waitqueue_head(&pgdat->kswapd_wait);
--- a/mm/swap_state.c~mm-switch-deferred-split-shrinker-to-list_lru
+++ a/mm/swap_state.c
@@ -465,6 +465,16 @@ static struct folio *__swap_cache_alloc(
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (order > 1 && folio_memcg_alloc_deferred(folio)) {
+		spin_lock(&ci->lock);
+		__swap_cache_do_del_folio(ci, folio, entry, shadow);
+		spin_unlock(&ci->lock);
+		folio_unlock(folio);
+		/* nr_pages refs from swap cache, 1 from allocation */
+		folio_put_refs(folio, nr_pages + 1);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	/* memsw uncharges swap when folio is added to swap cache */
 	memcg1_swapin(folio);
 	if (shadow)
_

Patches currently in -mm which might be from hannes@cmpxchg.org are