[PATCH RFC 06/28] mm: thp: introduce folio_split_queue_lock and its variants

[Muchun Song <songmuchun@bytedance.com>]

In future memcg removal, the binding between a folio and a memcg may change,
making the split lock within the memcg unstable when held.

A new approach is required to reparent the split queue to its parent. This
patch starts introducing a unified way to acquire the split lock for future
work.

It's a code-only refactoring with no functional changes.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/memcontrol.h |  10 ++++
 mm/huge_memory.c           | 100 +++++++++++++++++++++++++++----------
 2 files changed, 83 insertions(+), 27 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a045819bcf40..bb4f203733f3 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1639,6 +1639,11 @@ int alloc_shrinker_info(struct mem_cgroup *memcg);
 void free_shrinker_info(struct mem_cgroup *memcg);
 void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
 void reparent_shrinker_deferred(struct mem_cgroup *memcg);
+
+static inline int shrinker_id(struct shrinker *shrinker)
+{
+	return shrinker->id;
+}
 #else
 #define mem_cgroup_sockets_enabled 0
 static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
@@ -1652,6 +1657,11 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg,
 				    int nid, int shrinker_id)
 {
 }
+
+static inline int shrinker_id(struct shrinker *shrinker)
+{
+	return -1;
+}
 #endif
 
 #ifdef CONFIG_MEMCG
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a81e89987ca2..70820fa75c1f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1059,26 +1059,75 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 
 #ifdef CONFIG_MEMCG
 static inline
-struct deferred_split *get_deferred_split_queue(struct folio *folio)
+struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
+					   struct deferred_split *queue)
+{
+	if (mem_cgroup_disabled())
+		return NULL;
+	if (&NODE_DATA(folio_nid(folio))->deferred_split_queue == queue)
+		return NULL;
+	return container_of(queue, struct mem_cgroup, deferred_split_queue);
+}
+
+static inline struct deferred_split *folio_memcg_split_queue(struct folio *folio)
 {
 	struct mem_cgroup *memcg = folio_memcg(folio);
-	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
 
-	if (memcg)
-		return &memcg->deferred_split_queue;
-	else
-		return &pgdat->deferred_split_queue;
+	return memcg ? &memcg->deferred_split_queue : NULL;
 }
 #else
 static inline
-struct deferred_split *get_deferred_split_queue(struct folio *folio)
+struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
+					   struct deferred_split *queue)
 {
-	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
+	return NULL;
+}
 
-	return &pgdat->deferred_split_queue;
+static inline struct deferred_split *folio_memcg_split_queue(struct folio *folio)
+{
+	return NULL;
 }
 #endif
 
+static struct deferred_split *folio_split_queue(struct folio *folio)
+{
+	struct deferred_split *queue = folio_memcg_split_queue(folio);
+
+	return queue ? : &NODE_DATA(folio_nid(folio))->deferred_split_queue;
+}
+
+static struct deferred_split *folio_split_queue_lock(struct folio *folio)
+{
+	struct deferred_split *queue;
+
+	queue = folio_split_queue(folio);
+	spin_lock(&queue->split_queue_lock);
+
+	return queue;
+}
+
+static struct deferred_split *
+folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags)
+{
+	struct deferred_split *queue;
+
+	queue = folio_split_queue(folio);
+	spin_lock_irqsave(&queue->split_queue_lock, *flags);
+
+	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))
@@ -3723,7 +3772,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		struct page *split_at, struct page *lock_at,
 		struct list_head *list, bool uniform_split)
 {
-	struct deferred_split *ds_queue = get_deferred_split_queue(folio);
+	struct deferred_split *ds_queue;
 	XA_STATE(xas, &folio->mapping->i_pages, folio->index);
 	bool is_anon = folio_test_anon(folio);
 	struct address_space *mapping = NULL;
@@ -3857,7 +3906,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	}
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
-	spin_lock(&ds_queue->split_queue_lock);
+	ds_queue = folio_split_queue_lock(folio);
 	if (folio_ref_freeze(folio, 1 + extra_pins)) {
 		if (folio_order(folio) > 1 &&
 		    !list_empty(&folio->_deferred_list)) {
@@ -3875,7 +3924,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 			 */
 			list_del_init(&folio->_deferred_list);
 		}
-		spin_unlock(&ds_queue->split_queue_lock);
+		split_queue_unlock(ds_queue);
 		if (mapping) {
 			int nr = folio_nr_pages(folio);
 
@@ -3896,7 +3945,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 				split_at, lock_at, list, end, &xas, mapping,
 				uniform_split);
 	} else {
-		spin_unlock(&ds_queue->split_queue_lock);
+		split_queue_unlock(ds_queue);
 fail:
 		if (mapping)
 			xas_unlock(&xas);
@@ -4050,8 +4099,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
 	WARN_ON_ONCE(folio_ref_count(folio));
 	WARN_ON_ONCE(!mem_cgroup_disabled() && !folio_memcg_charged(folio));
 
-	ds_queue = get_deferred_split_queue(folio);
-	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+	ds_queue = folio_split_queue_lock_irqsave(folio, &flags);
 	if (!list_empty(&folio->_deferred_list)) {
 		ds_queue->split_queue_len--;
 		if (folio_test_partially_mapped(folio)) {
@@ -4062,7 +4110,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
 		list_del_init(&folio->_deferred_list);
 		unqueued = true;
 	}
-	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+	split_queue_unlock_irqrestore(ds_queue, flags);
 
 	return unqueued;	/* useful for debug warnings */
 }
@@ -4070,10 +4118,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio)
 /* 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 = get_deferred_split_queue(folio);
-#ifdef CONFIG_MEMCG
-	struct mem_cgroup *memcg = folio_memcg(folio);
-#endif
+	struct deferred_split *ds_queue;
 	unsigned long flags;
 
 	/*
@@ -4096,7 +4141,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
 	if (folio_test_swapcache(folio))
 		return;
 
-	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+	ds_queue = folio_split_queue_lock_irqsave(folio, &flags);
 	if (partially_mapped) {
 		if (!folio_test_partially_mapped(folio)) {
 			folio_set_partially_mapped(folio);
@@ -4111,15 +4156,16 @@ void deferred_split_folio(struct folio *folio, bool 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++;
-#ifdef CONFIG_MEMCG
 		if (memcg)
 			set_shrinker_bit(memcg, folio_nid(folio),
-					 deferred_split_shrinker->id);
-#endif
+					 shrinker_id(deferred_split_shrinker));
 	}
-	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+	split_queue_unlock_irqrestore(ds_queue, flags);
 }
 
 static unsigned long deferred_split_count(struct shrinker *shrink,
@@ -4202,7 +4248,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		if (!--sc->nr_to_scan)
 			break;
 	}
-	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+	split_queue_unlock_irqrestore(ds_queue, flags);
 
 	list_for_each_entry_safe(folio, next, &list, _deferred_list) {
 		bool did_split = false;
@@ -4251,7 +4297,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
 	list_splice_tail(&list, &ds_queue->split_queue);
 	ds_queue->split_queue_len -= removed;
-	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+	split_queue_unlock_irqrestore(ds_queue, flags);
 
 	if (prev)
 		folio_put(prev);
-- 
2.20.1