1 files changed, 220 insertions, 248 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 500a09a48dfd..4fc322f7111a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -45,33 +45,29 @@
 
 /* How many pages do we try to swap or page in/out together? As a power of 2 */
 int page_cluster;
-const int page_cluster_max = 31;
+static const int page_cluster_max = 31;
 
-/* Protecting only lru_rotate.fbatch which requires disabling interrupts */
-struct lru_rotate {
-	local_lock_t lock;
-	struct folio_batch fbatch;
-};
-static DEFINE_PER_CPU(struct lru_rotate, lru_rotate) = {
-	.lock = INIT_LOCAL_LOCK(lock),
-};
-
-/*
- * The following folio batches are grouped together because they are protected
- * by disabling preemption (and interrupts remain enabled).
- */
 struct cpu_fbatches {
+	/*
+	 * The following folio batches are grouped together because they are protected
+	 * by disabling preemption (and interrupts remain enabled).
+	 */
 	local_lock_t lock;
 	struct folio_batch lru_add;
 	struct folio_batch lru_deactivate_file;
 	struct folio_batch lru_deactivate;
 	struct folio_batch lru_lazyfree;
 #ifdef CONFIG_SMP
-	struct folio_batch activate;
+	struct folio_batch lru_activate;
 #endif
+	/* Protecting the following batches which require disabling interrupts */
+	local_lock_t lock_irq;
+	struct folio_batch lru_move_tail;
 };
+
 static DEFINE_PER_CPU(struct cpu_fbatches, cpu_fbatches) = {
 	.lock = INIT_LOCAL_LOCK(lock),
+	.lock_irq = INIT_LOCAL_LOCK(lock_irq),
 };
 
 static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
@@ -82,20 +78,6 @@ static void __page_cache_release(struct folio *folio, struct lruvec **lruvecp,
 		lruvec_del_folio(*lruvecp, folio);
 		__folio_clear_lru_flags(folio);
 	}
-
-	/*
-	 * In rare cases, when truncation or holepunching raced with
-	 * munlock after VM_LOCKED was cleared, Mlocked may still be
-	 * found set here.  This does not indicate a problem, unless
-	 * "unevictable_pgs_cleared" appears worryingly large.
-	 */
-	if (unlikely(folio_test_mlocked(folio))) {
-		long nr_pages = folio_nr_pages(folio);
-
-		__folio_clear_mlocked(folio);
-		zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
-		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
-	}
 }
 
 /*
@@ -112,71 +94,28 @@ static void page_cache_release(struct folio *folio)
 		unlock_page_lruvec_irqrestore(lruvec, flags);
 }
 
-static void __folio_put_small(struct folio *folio)
-{
-	page_cache_release(folio);
-	mem_cgroup_uncharge(folio);
-	free_unref_page(&folio->page, 0);
-}
-
-static void __folio_put_large(struct folio *folio)
-{
-	/*
-	 * __page_cache_release() is supposed to be called for thp, not for
-	 * hugetlb. This is because hugetlb page does never have PageLRU set
-	 * (it's never listed to any LRU lists) and no memcg routines should
-	 * be called for hugetlb (it has a separate hugetlb_cgroup.)
-	 */
-	if (!folio_test_hugetlb(folio))
-		page_cache_release(folio);
-	destroy_large_folio(folio);
-}
-
 void __folio_put(struct folio *folio)
 {
-	if (unlikely(folio_is_zone_device(folio)))
-		free_zone_device_page(&folio->page);
-	else if (unlikely(folio_test_large(folio)))
-		__folio_put_large(folio);
-	else
-		__folio_put_small(folio);
-}
-EXPORT_SYMBOL(__folio_put);
-
-/**
- * put_pages_list() - release a list of pages
- * @pages: list of pages threaded on page->lru
- *
- * Release a list of pages which are strung together on page.lru.
- */
-void put_pages_list(struct list_head *pages)
-{
-	struct folio_batch fbatch;
-	struct folio *folio, *next;
+	if (unlikely(folio_is_zone_device(folio))) {
+		free_zone_device_folio(folio);
+		return;
+	}
 
-	folio_batch_init(&fbatch);
-	list_for_each_entry_safe(folio, next, pages, lru) {
-		if (!folio_put_testzero(folio))
-			continue;
-		if (folio_test_large(folio)) {
-			__folio_put_large(folio);
-			continue;
-		}
-		/* LRU flag must be clear because it's passed using the lru */
-		if (folio_batch_add(&fbatch, folio) > 0)
-			continue;
-		free_unref_folios(&fbatch);
+	if (folio_test_hugetlb(folio)) {
+		free_huge_folio(folio);
+		return;
 	}
 
-	if (fbatch.nr)
-		free_unref_folios(&fbatch);
-	INIT_LIST_HEAD(pages);
+	page_cache_release(folio);
+	folio_unqueue_deferred_split(folio);
+	mem_cgroup_uncharge(folio);
+	free_frozen_pages(&folio->page, folio_order(folio));
 }
-EXPORT_SYMBOL(put_pages_list);
+EXPORT_SYMBOL(__folio_put);
 
 typedef void (*move_fn_t)(struct lruvec *lruvec, struct folio *folio);
 
-static void lru_add_fn(struct lruvec *lruvec, struct folio *folio)
+static void lru_add(struct lruvec *lruvec, struct folio *folio)
 {
 	int was_unevictable = folio_test_clear_unevictable(folio);
 	long nr_pages = folio_nr_pages(folio);
@@ -225,10 +164,6 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 	for (i = 0; i < folio_batch_count(fbatch); i++) {
 		struct folio *folio = fbatch->folios[i];
 
-		/* block memcg migration while the folio moves between lru */
-		if (move_fn != lru_add_fn && !folio_test_clear_lru(folio))
-			continue;
-
 		folio_lruvec_relock_irqsave(folio, &lruvec, &flags);
 		move_fn(lruvec, folio);
 
@@ -240,23 +175,50 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 	folios_put(fbatch);
 }
 
-static void folio_batch_add_and_move(struct folio_batch *fbatch,
-		struct folio *folio, move_fn_t move_fn)
+static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
+		struct folio *folio, move_fn_t move_fn,
+		bool on_lru, bool disable_irq)
 {
-	if (folio_batch_add(fbatch, folio) && !folio_test_large(folio) &&
-	    !lru_cache_disabled())
+	unsigned long flags;
+
+	if (on_lru && !folio_test_clear_lru(folio))
 		return;
-	folio_batch_move_lru(fbatch, move_fn);
+
+	folio_get(folio);
+
+	if (disable_irq)
+		local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
+	else
+		local_lock(&cpu_fbatches.lock);
+
+	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) ||
+	    lru_cache_disabled())
+		folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
+
+	if (disable_irq)
+		local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
+	else
+		local_unlock(&cpu_fbatches.lock);
 }
 
-static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio)
+#define folio_batch_add_and_move(folio, op, on_lru)						\
+	__folio_batch_add_and_move(								\
+		&cpu_fbatches.op,								\
+		folio,										\
+		op,										\
+		on_lru,										\
+		offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq)	\
+	)
+
+static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
 {
-	if (!folio_test_unevictable(folio)) {
-		lruvec_del_folio(lruvec, folio);
-		folio_clear_active(folio);
-		lruvec_add_folio_tail(lruvec, folio);
-		__count_vm_events(PGROTATED, folio_nr_pages(folio));
-	}
+	if (folio_test_unevictable(folio))
+		return;
+
+	lruvec_del_folio(lruvec, folio);
+	folio_clear_active(folio);
+	lruvec_add_folio_tail(lruvec, folio);
+	__count_vm_events(PGROTATED, folio_nr_pages(folio));
 }
 
 /*
@@ -268,17 +230,11 @@ static void lru_move_tail_fn(struct lruvec *lruvec, struct folio *folio)
  */
 void folio_rotate_reclaimable(struct folio *folio)
 {
-	if (!folio_test_locked(folio) && !folio_test_dirty(folio) &&
-	    !folio_test_unevictable(folio) && folio_test_lru(folio)) {
-		struct folio_batch *fbatch;
-		unsigned long flags;
+	if (folio_test_locked(folio) || folio_test_dirty(folio) ||
+	    folio_test_unevictable(folio))
+		return;
 
-		folio_get(folio);
-		local_lock_irqsave(&lru_rotate.lock, flags);
-		fbatch = this_cpu_ptr(&lru_rotate.fbatch);
-		folio_batch_add_and_move(fbatch, folio, lru_move_tail_fn);
-		local_unlock_irqrestore(&lru_rotate.lock, flags);
-	}
+	folio_batch_add_and_move(folio, lru_move_tail, true);
 }
 
 void lru_note_cost(struct lruvec *lruvec, bool file,
@@ -339,43 +295,38 @@ void lru_note_cost_refault(struct folio *folio)
 		      folio_nr_pages(folio), 0);
 }
 
-static void folio_activate_fn(struct lruvec *lruvec, struct folio *folio)
+static void lru_activate(struct lruvec *lruvec, struct folio *folio)
 {
-	if (!folio_test_active(folio) && !folio_test_unevictable(folio)) {
-		long nr_pages = folio_nr_pages(folio);
+	long nr_pages = folio_nr_pages(folio);
 
-		lruvec_del_folio(lruvec, folio);
-		folio_set_active(folio);
-		lruvec_add_folio(lruvec, folio);
-		trace_mm_lru_activate(folio);
+	if (folio_test_active(folio) || folio_test_unevictable(folio))
+		return;
 
-		__count_vm_events(PGACTIVATE, nr_pages);
-		__count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE,
-				     nr_pages);
-	}
+
+	lruvec_del_folio(lruvec, folio);
+	folio_set_active(folio);
+	lruvec_add_folio(lruvec, folio);
+	trace_mm_lru_activate(folio);
+
+	__count_vm_events(PGACTIVATE, nr_pages);
+	count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages);
 }
 
 #ifdef CONFIG_SMP
 static void folio_activate_drain(int cpu)
 {
-	struct folio_batch *fbatch = &per_cpu(cpu_fbatches.activate, cpu);
+	struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu);
 
 	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, folio_activate_fn);
+		folio_batch_move_lru(fbatch, lru_activate);
 }
 
 void folio_activate(struct folio *folio)
 {
-	if (folio_test_lru(folio) && !folio_test_active(folio) &&
-	    !folio_test_unevictable(folio)) {
-		struct folio_batch *fbatch;
+	if (folio_test_active(folio) || folio_test_unevictable(folio))
+		return;
 
-		folio_get(folio);
-		local_lock(&cpu_fbatches.lock);
-		fbatch = this_cpu_ptr(&cpu_fbatches.activate);
-		folio_batch_add_and_move(fbatch, folio, folio_activate_fn);
-		local_unlock(&cpu_fbatches.lock);
-	}
+	folio_batch_add_and_move(folio, lru_activate, true);
 }
 
 #else
@@ -387,12 +338,13 @@ void folio_activate(struct folio *folio)
 {
 	struct lruvec *lruvec;
 
-	if (folio_test_clear_lru(folio)) {
-		lruvec = folio_lruvec_lock_irq(folio);
-		folio_activate_fn(lruvec, folio);
-		unlock_page_lruvec_irq(lruvec);
-		folio_set_lru(folio);
-	}
+	if (!folio_test_clear_lru(folio))
+		return;
+
+	lruvec = folio_lruvec_lock_irq(folio);
+	lru_activate(lruvec, folio);
+	unlock_page_lruvec_irq(lruvec);
+	folio_set_lru(folio);
 }
 #endif
 
@@ -427,53 +379,79 @@ static void __lru_cache_activate_folio(struct folio *folio)
 }
 
 #ifdef CONFIG_LRU_GEN
-static void folio_inc_refs(struct folio *folio)
+
+static void lru_gen_inc_refs(struct folio *folio)
 {
 	unsigned long new_flags, old_flags = READ_ONCE(folio->flags);
 
 	if (folio_test_unevictable(folio))
 		return;
 
+	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio)) {
-		folio_set_referenced(folio);
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
 		return;
 	}
 
-	if (!folio_test_workingset(folio)) {
-		folio_set_workingset(folio);
-		return;
-	}
-
-	/* see the comment on MAX_NR_TIERS */
 	do {
-		new_flags = old_flags & LRU_REFS_MASK;
-		if (new_flags == LRU_REFS_MASK)
-			break;
+		if ((old_flags & LRU_REFS_MASK) == LRU_REFS_MASK) {
+			if (!folio_test_workingset(folio))
+				folio_set_workingset(folio);
+			return;
+		}
 
-		new_flags += BIT(LRU_REFS_PGOFF);
-		new_flags |= old_flags & ~LRU_REFS_MASK;
+		new_flags = old_flags + BIT(LRU_REFS_PGOFF);
 	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
 }
-#else
-static void folio_inc_refs(struct folio *folio)
+
+static bool lru_gen_clear_refs(struct folio *folio)
 {
+	struct lru_gen_folio *lrugen;
+	int gen = folio_lru_gen(folio);
+	int type = folio_is_file_lru(folio);
+
+	if (gen < 0)
+		return true;
+
+	set_mask_bits(&folio->flags, LRU_REFS_FLAGS | BIT(PG_workingset), 0);
+
+	lrugen = &folio_lruvec(folio)->lrugen;
+	/* whether can do without shuffling under the LRU lock */
+	return gen == lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type]));
 }
+
+#else /* !CONFIG_LRU_GEN */
+
+static void lru_gen_inc_refs(struct folio *folio)
+{
+}
+
+static bool lru_gen_clear_refs(struct folio *folio)
+{
+	return false;
+}
+
 #endif /* CONFIG_LRU_GEN */
 
-/*
- * Mark a page as having seen activity.
+/**
+ * folio_mark_accessed - Mark a folio as having seen activity.
+ * @folio: The folio to mark.
+ *
+ * This function will perform one of the following transitions:
  *
- * inactive,unreferenced	->	inactive,referenced
- * inactive,referenced		->	active,unreferenced
- * active,unreferenced		->	active,referenced
+ * * inactive,unreferenced	->	inactive,referenced
+ * * inactive,referenced	->	active,unreferenced
+ * * active,unreferenced	->	active,referenced
  *
- * When a newly allocated page is not yet visible, so safe for non-atomic ops,
- * __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
+ * When a newly allocated folio is not yet visible, so safe for non-atomic ops,
+ * __folio_set_referenced() may be substituted for folio_mark_accessed().
  */
 void folio_mark_accessed(struct folio *folio)
 {
+	if (folio_test_dropbehind(folio))
+		return;
 	if (lru_gen_enabled()) {
-		folio_inc_refs(folio);
+		lru_gen_inc_refs(folio);
 		return;
 	}
 
@@ -488,7 +466,7 @@ void folio_mark_accessed(struct folio *folio)
 	} else if (!folio_test_active(folio)) {
 		/*
 		 * If the folio is on the LRU, queue it for activation via
-		 * cpu_fbatches.activate. Otherwise, assume the folio is in a
+		 * cpu_fbatches.lru_activate. Otherwise, assume the folio is in a
 		 * folio_batch, mark it active and it'll be moved to the active
 		 * LRU on the next drain.
 		 */
@@ -515,22 +493,16 @@ EXPORT_SYMBOL(folio_mark_accessed);
  */
 void folio_add_lru(struct folio *folio)
 {
-	struct folio_batch *fbatch;
-
 	VM_BUG_ON_FOLIO(folio_test_active(folio) &&
 			folio_test_unevictable(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
 
-	/* see the comment in lru_gen_add_folio() */
+	/* see the comment in lru_gen_folio_seq() */
 	if (lru_gen_enabled() && !folio_test_unevictable(folio) &&
 	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
 		folio_set_active(folio);
 
-	folio_get(folio);
-	local_lock(&cpu_fbatches.lock);
-	fbatch = this_cpu_ptr(&cpu_fbatches.lru_add);
-	folio_batch_add_and_move(fbatch, folio, lru_add_fn);
-	local_unlock(&cpu_fbatches.lock);
+	folio_batch_add_and_move(folio, lru_add, false);
 }
 EXPORT_SYMBOL(folio_add_lru);
 
@@ -573,9 +545,9 @@ void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma)
  * written out by flusher threads as this is much more efficient
  * than the single-page writeout from reclaim.
  */
-static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio)
+static void lru_deactivate_file(struct lruvec *lruvec, struct folio *folio)
 {
-	bool active = folio_test_active(folio);
+	bool active = folio_test_active(folio) || lru_gen_enabled();
 	long nr_pages = folio_nr_pages(folio);
 
 	if (folio_test_unevictable(folio))
@@ -609,48 +581,51 @@ static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio)
 
 	if (active) {
 		__count_vm_events(PGDEACTIVATE, nr_pages);
-		__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
+		count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
 				     nr_pages);
 	}
 }
 
-static void lru_deactivate_fn(struct lruvec *lruvec, struct folio *folio)
+static void lru_deactivate(struct lruvec *lruvec, struct folio *folio)
 {
-	if (!folio_test_unevictable(folio) && (folio_test_active(folio) || lru_gen_enabled())) {
-		long nr_pages = folio_nr_pages(folio);
+	long nr_pages = folio_nr_pages(folio);
 
-		lruvec_del_folio(lruvec, folio);
-		folio_clear_active(folio);
-		folio_clear_referenced(folio);
-		lruvec_add_folio(lruvec, folio);
+	if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled()))
+		return;
 
-		__count_vm_events(PGDEACTIVATE, nr_pages);
-		__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
-				     nr_pages);
-	}
+	lruvec_del_folio(lruvec, folio);
+	folio_clear_active(folio);
+	folio_clear_referenced(folio);
+	lruvec_add_folio(lruvec, folio);
+
+	__count_vm_events(PGDEACTIVATE, nr_pages);
+	count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_pages);
 }
 
-static void lru_lazyfree_fn(struct lruvec *lruvec, struct folio *folio)
+static void lru_lazyfree(struct lruvec *lruvec, struct folio *folio)
 {
-	if (folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-	    !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) {
-		long nr_pages = folio_nr_pages(folio);
+	long nr_pages = folio_nr_pages(folio);
 
-		lruvec_del_folio(lruvec, folio);
-		folio_clear_active(folio);
+	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
+		return;
+
+	lruvec_del_folio(lruvec, folio);
+	folio_clear_active(folio);
+	if (lru_gen_enabled())
+		lru_gen_clear_refs(folio);
+	else
 		folio_clear_referenced(folio);
-		/*
-		 * Lazyfree folios are clean anonymous folios.  They have
-		 * the swapbacked flag cleared, to distinguish them from normal
-		 * anonymous folios
-		 */
-		folio_clear_swapbacked(folio);
-		lruvec_add_folio(lruvec, folio);
+	/*
+	 * Lazyfree folios are clean anonymous folios.  They have
+	 * the swapbacked flag cleared, to distinguish them from normal
+	 * anonymous folios
+	 */
+	folio_clear_swapbacked(folio);
+	lruvec_add_folio(lruvec, folio);
 
-		__count_vm_events(PGLAZYFREE, nr_pages);
-		__count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE,
-				     nr_pages);
-	}
+	__count_vm_events(PGLAZYFREE, nr_pages);
+	count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
 }
 
 /*
@@ -664,30 +639,30 @@ void lru_add_drain_cpu(int cpu)
 	struct folio_batch *fbatch = &fbatches->lru_add;
 
 	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, lru_add_fn);
+		folio_batch_move_lru(fbatch, lru_add);
 
-	fbatch = &per_cpu(lru_rotate.fbatch, cpu);
+	fbatch = &fbatches->lru_move_tail;
 	/* Disabling interrupts below acts as a compiler barrier. */
 	if (data_race(folio_batch_count(fbatch))) {
 		unsigned long flags;
 
 		/* No harm done if a racing interrupt already did this */
-		local_lock_irqsave(&lru_rotate.lock, flags);
-		folio_batch_move_lru(fbatch, lru_move_tail_fn);
-		local_unlock_irqrestore(&lru_rotate.lock, flags);
+		local_lock_irqsave(&cpu_fbatches.lock_irq, flags);
+		folio_batch_move_lru(fbatch, lru_move_tail);
+		local_unlock_irqrestore(&cpu_fbatches.lock_irq, flags);
 	}
 
 	fbatch = &fbatches->lru_deactivate_file;
 	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, lru_deactivate_file_fn);
+		folio_batch_move_lru(fbatch, lru_deactivate_file);
 
 	fbatch = &fbatches->lru_deactivate;
 	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, lru_deactivate_fn);
+		folio_batch_move_lru(fbatch, lru_deactivate);
 
 	fbatch = &fbatches->lru_lazyfree;
 	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, lru_lazyfree_fn);
+		folio_batch_move_lru(fbatch, lru_lazyfree);
 
 	folio_activate_drain(cpu);
 }
@@ -704,17 +679,14 @@ void lru_add_drain_cpu(int cpu)
  */
 void deactivate_file_folio(struct folio *folio)
 {
-	struct folio_batch *fbatch;
-
 	/* Deactivating an unevictable folio will not accelerate reclaim */
 	if (folio_test_unevictable(folio))
 		return;
 
-	folio_get(folio);
-	local_lock(&cpu_fbatches.lock);
-	fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate_file);
-	folio_batch_add_and_move(fbatch, folio, lru_deactivate_file_fn);
-	local_unlock(&cpu_fbatches.lock);
+	if (lru_gen_enabled() && lru_gen_clear_refs(folio))
+		return;
+
+	folio_batch_add_and_move(folio, lru_deactivate_file, true);
 }
 
 /*
@@ -727,16 +699,13 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (folio_test_lru(folio) && !folio_test_unevictable(folio) &&
-	    (folio_test_active(folio) || lru_gen_enabled())) {
-		struct folio_batch *fbatch;
+	if (folio_test_unevictable(folio))
+		return;
 
-		folio_get(folio);
-		local_lock(&cpu_fbatches.lock);
-		fbatch = this_cpu_ptr(&cpu_fbatches.lru_deactivate);
-		folio_batch_add_and_move(fbatch, folio, lru_deactivate_fn);
-		local_unlock(&cpu_fbatches.lock);
-	}
+	if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
+		return;
+
+	folio_batch_add_and_move(folio, lru_deactivate, true);
 }
 
 /**
@@ -748,17 +717,11 @@ void folio_deactivate(struct folio *folio)
  */
 void folio_mark_lazyfree(struct folio *folio)
 {
-	if (folio_test_lru(folio) && folio_test_anon(folio) &&
-	    folio_test_swapbacked(folio) && !folio_test_swapcache(folio) &&
-	    !folio_test_unevictable(folio)) {
-		struct folio_batch *fbatch;
+	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
+		return;
 
-		folio_get(folio);
-		local_lock(&cpu_fbatches.lock);
-		fbatch = this_cpu_ptr(&cpu_fbatches.lru_lazyfree);
-		folio_batch_add_and_move(fbatch, folio, lru_lazyfree_fn);
-		local_unlock(&cpu_fbatches.lock);
-	}
+	folio_batch_add_and_move(folio, lru_lazyfree, true);
 }
 
 void lru_add_drain(void)
@@ -808,11 +771,11 @@ static bool cpu_needs_drain(unsigned int cpu)
 
 	/* Check these in order of likelihood that they're not zero */
 	return folio_batch_count(&fbatches->lru_add) ||
-		data_race(folio_batch_count(&per_cpu(lru_rotate.fbatch, cpu))) ||
+		folio_batch_count(&fbatches->lru_move_tail) ||
 		folio_batch_count(&fbatches->lru_deactivate_file) ||
 		folio_batch_count(&fbatches->lru_deactivate) ||
 		folio_batch_count(&fbatches->lru_lazyfree) ||
-		folio_batch_count(&fbatches->activate) ||
+		folio_batch_count(&fbatches->lru_activate) ||
 		need_mlock_drain(cpu) ||
 		has_bh_in_lru(cpu, NULL);
 }
@@ -930,8 +893,8 @@ atomic_t lru_disable_count = ATOMIC_INIT(0);
 
 /*
  * lru_cache_disable() needs to be called before we start compiling
- * a list of pages to be migrated using isolate_lru_page().
- * It drains pages on LRU cache and then disable on all cpus until
+ * a list of folios to be migrated using folio_isolate_lru().
+ * It drains folios on LRU cache and then disable on all cpus until
  * lru_cache_enable is called.
  *
  * Must be paired with a call to lru_cache_enable().
@@ -985,7 +948,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs)
 		struct folio *folio = folios->folios[i];
 		unsigned int nr_refs = refs ? refs[i] : 1;
 
-		if (is_huge_zero_page(&folio->page))
+		if (is_huge_zero_folio(folio))
 			continue;
 
 		if (folio_is_zone_device(folio)) {
@@ -993,10 +956,8 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs)
 				unlock_page_lruvec_irqrestore(lruvec, flags);
 				lruvec = NULL;
 			}
-			if (put_devmap_managed_page_refs(&folio->page, nr_refs))
-				continue;
 			if (folio_ref_sub_and_test(folio, nr_refs))
-				free_zone_device_page(&folio->page);
+				free_zone_device_folio(folio);
 			continue;
 		}
 
@@ -1012,10 +973,7 @@ void folios_put_refs(struct folio_batch *folios, unsigned int *refs)
 			free_huge_folio(folio);
 			continue;
 		}
-		if (folio_test_large(folio) &&
-		    folio_test_large_rmappable(folio))
-			folio_undo_large_rmappable(folio);
-
+		folio_unqueue_deferred_split(folio);
 		__page_cache_release(folio, &lruvec, &flags);
 
 		if (j != i)
@@ -1116,6 +1074,18 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
 	fbatch->nr = j;
 }
 
+static const struct ctl_table swap_sysctl_table[] = {
+	{
+		.procname	= "page-cluster",
+		.data		= &page_cluster,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= (void *)&page_cluster_max,
+	}
+};
+
 /*
  * Perform any setup for the swap system
  */
@@ -1132,4 +1102,6 @@ void __init swap_setup(void)
 	 * Right now other parts of the system means that we
 	 * _really_ don't want to cluster much more
 	 */
+
+	register_sysctl_init("vm", swap_sysctl_table);
 }