[PATCH v2 06/13] mm: thp: introduce split_queue_lock/unlock{_irqsave}()

[Muchun Song]

We should make thp deferred split queue lock safe when LRU pages
reparented. Similar to lock_page_lruvec{_irqsave, _irq}(), we
introduce split_queue_lock/unlock{_irqsave}() to make the deferred
split queue lock easier to be reparented.

And in the next patch, we can use a similar approach (just like
lruvec lock did) to make thp deferred split queue lock safe when
the LRU pages reparented.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 mm/huge_memory.c | 90 +++++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 67 insertions(+), 23 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5e9ef0fc261e..9d8dfa82991a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -499,25 +499,70 @@ 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 page *page)
+static inline struct mem_cgroup *split_queue_memcg(struct deferred_split *queue)
 {
-	struct mem_cgroup *memcg = page_memcg(compound_head(page));
-	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+	if (mem_cgroup_disabled())
+		return NULL;
+	return container_of(queue, struct mem_cgroup, deferred_split_queue);
+}
 
-	if (memcg)
-		return &memcg->deferred_split_queue;
-	else
-		return &pgdat->deferred_split_queue;
+static inline struct deferred_split *page_memcg_split_queue(struct page *head)
+{
+	struct mem_cgroup *memcg = page_memcg(head);
+
+	return memcg ? &memcg->deferred_split_queue : NULL;
 }
 #else
-static inline struct deferred_split *get_deferred_split_queue(struct page *page)
++static inline struct mem_cgroup *split_queue_memcg(struct deferred_split *queue)
 {
-	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+	return NULL;
+}
 
-	return &pgdat->deferred_split_queue;
+static inline struct deferred_split *page_memcg_split_queue(struct page *head)
+{
+	return NULL;
 }
 #endif
 
+static struct deferred_split *page_split_queue(struct page *head)
+{
+	struct deferred_split *queue = page_memcg_split_queue(head);
+
+	return queue ? : &NODE_DATA(page_to_nid(head))->deferred_split_queue;
+}
+
+static struct deferred_split *split_queue_lock(struct page *head)
+{
+	struct deferred_split *queue;
+
+	queue = page_split_queue(head);
+	spin_lock(&queue->split_queue_lock);
+
+	return queue;
+}
+
+static struct deferred_split *
+split_queue_lock_irqsave(struct page *head, unsigned long *flags)
+{
+	struct deferred_split *queue;
+
+	queue = page_split_queue(head);
+	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);
+}
+
 void prep_transhuge_page(struct page *page)
 {
 	/*
@@ -2610,7 +2655,7 @@ bool can_split_huge_page(struct page *page, int *pextra_pins)
 int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
-	struct deferred_split *ds_queue = get_deferred_split_queue(head);
+	struct deferred_split *ds_queue;
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
 	int extra_pins, ret;
@@ -2690,13 +2735,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
-	spin_lock(&ds_queue->split_queue_lock);
+	ds_queue = split_queue_lock(head);
 	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
-		spin_unlock(&ds_queue->split_queue_lock);
+		split_queue_unlock(ds_queue);
 		if (mapping) {
 			int nr = thp_nr_pages(head);
 
@@ -2711,7 +2756,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		__split_huge_page(page, list, end);
 		ret = 0;
 	} else {
-		spin_unlock(&ds_queue->split_queue_lock);
+		split_queue_unlock(ds_queue);
 fail:
 		if (mapping)
 			xa_unlock(&mapping->i_pages);
@@ -2734,24 +2779,22 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 void free_transhuge_page(struct page *page)
 {
-	struct deferred_split *ds_queue = get_deferred_split_queue(page);
+	struct deferred_split *ds_queue;
 	unsigned long flags;
 
-	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+	ds_queue = split_queue_lock_irqsave(page, &flags);
 	if (!list_empty(page_deferred_list(page))) {
 		ds_queue->split_queue_len--;
 		list_del(page_deferred_list(page));
 	}
-	spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
+	split_queue_unlock_irqrestore(ds_queue, flags);
 	free_compound_page(page);
 }
 
 void deferred_split_huge_page(struct page *page)
 {
-	struct deferred_split *ds_queue = get_deferred_split_queue(page);
-#ifdef CONFIG_MEMCG
-	struct mem_cgroup *memcg = page_memcg(compound_head(page));
-#endif
+	struct deferred_split *ds_queue;
+	struct mem_cgroup __maybe_unused *memcg;
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
@@ -2769,7 +2812,8 @@ void deferred_split_huge_page(struct page *page)
 	if (PageSwapCache(page))
 		return;
 
-	spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+	ds_queue = split_queue_lock_irqsave(page, &flags);
+	memcg = split_queue_memcg(ds_queue);
 	if (list_empty(page_deferred_list(page))) {
 		count_vm_event(THP_DEFERRED_SPLIT_PAGE);
 		list_add_tail(page_deferred_list(page), &ds_queue->split_queue);
@@ -2780,7 +2824,7 @@ void deferred_split_huge_page(struct page *page)
 					 deferred_split_shrinker.id);
 #endif
 	}
-	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,
-- 
2.11.0