1 files changed, 133 insertions, 165 deletions

diff --git a/mm/swap.c b/mm/swap.c
index 9caf6b017cf0..835bdf324b76 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -47,31 +47,27 @@
 int page_cluster;
 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,
@@ -117,7 +113,9 @@ void __folio_put(struct folio *folio)
 	if (unlikely(folio_is_zone_device(folio))) {
 		free_zone_device_folio(folio);
 		return;
-	} else if (folio_test_hugetlb(folio)) {
+	}
+
+	if (folio_test_hugetlb(folio)) {
 		free_huge_folio(folio);
 		return;
 	}
@@ -162,7 +160,7 @@ EXPORT_SYMBOL(put_pages_list);
 
 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);
@@ -222,23 +220,50 @@ 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));
 }
 
 /*
@@ -250,22 +275,11 @@ 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)) {
-		struct folio_batch *fbatch;
-		unsigned long flags;
-
-		folio_get(folio);
-		if (!folio_test_clear_lru(folio)) {
-			folio_put(folio);
-			return;
-		}
+	if (folio_test_locked(folio) || folio_test_dirty(folio) ||
+	    folio_test_unevictable(folio))
+		return;
 
-		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,
@@ -326,47 +340,38 @@ 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_active(folio) && !folio_test_unevictable(folio)) {
-		struct folio_batch *fbatch;
-
-		folio_get(folio);
-		if (!folio_test_clear_lru(folio)) {
-			folio_put(folio);
-			return;
-		}
+	if (folio_test_active(folio) || folio_test_unevictable(folio))
+		return;
 
-		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
@@ -378,12 +383,13 @@ 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
 
@@ -482,7 +488,7 @@ 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.
 		 */
@@ -509,8 +515,6 @@ 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);
@@ -520,11 +524,7 @@ void folio_add_lru(struct folio *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);
 
@@ -567,7 +567,7 @@ 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);
 	long nr_pages = folio_nr_pages(folio);
@@ -608,43 +608,43 @@ static void lru_deactivate_file_fn(struct lruvec *lruvec, struct folio *folio)
 	}
 }
 
-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);
-		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);
+	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
+		return;
 
-		__count_vm_events(PGLAZYFREE, nr_pages);
-		__count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE,
-				     nr_pages);
-	}
+	lruvec_del_folio(lruvec, folio);
+	folio_clear_active(folio);
+	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);
+
+	__count_vm_events(PGLAZYFREE, nr_pages);
+	__count_memcg_events(lruvec_memcg(lruvec), PGLAZYFREE, nr_pages);
 }
 
 /*
@@ -658,30 +658,30 @@ 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);
 }
@@ -698,22 +698,11 @@ 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);
-	if (!folio_test_clear_lru(folio)) {
-		folio_put(folio);
-		return;
-	}
-
-	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);
+	folio_batch_add_and_move(folio, lru_deactivate_file, true);
 }
 
 /*
@@ -726,21 +715,10 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (!folio_test_unevictable(folio) && (folio_test_active(folio) ||
-	    lru_gen_enabled())) {
-		struct folio_batch *fbatch;
-
-		folio_get(folio);
-		if (!folio_test_clear_lru(folio)) {
-			folio_put(folio);
-			return;
-		}
+	if (folio_test_unevictable(folio) || !(folio_test_active(folio) || lru_gen_enabled()))
+		return;
 
-		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);
-	}
+	folio_batch_add_and_move(folio, lru_deactivate, true);
 }
 
 /**
@@ -752,21 +730,11 @@ void folio_deactivate(struct folio *folio)
  */
 void folio_mark_lazyfree(struct folio *folio)
 {
-	if (folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-	    !folio_test_swapcache(folio) && !folio_test_unevictable(folio)) {
-		struct folio_batch *fbatch;
-
-		folio_get(folio);
-		if (!folio_test_clear_lru(folio)) {
-			folio_put(folio);
-			return;
-		}
+	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
+		return;
 
-		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)
@@ -816,11 +784,11 @@ 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);
 }
@@ -938,8 +906,8 @@ 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().