[PATCH v4 4/4] mm: thp: reparent the split queue during memcg offline

[Qi Zheng <qi.zheng@linux.dev>]

From: Qi Zheng <zhengqi.arch@bytedance.com>

Similar to list_lru, the split queue is relatively independent and does
not need to be reparented along with objcg and LRU folios (holding
objcg lock and lru lock). So let's apply the similar mechanism as list_lru
to reparent the split queue separately when memcg is offine.

This is also a preparation for reparenting LRU folios.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 include/linux/huge_mm.h |  4 +++
 mm/huge_memory.c        | 54 +++++++++++++++++++++++++++++++++++++++++
 mm/memcontrol.c         |  1 +
 3 files changed, 59 insertions(+)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f327d62fc9852..0c211dcbb0ec1 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -417,6 +417,9 @@ static inline int split_huge_page(struct page *page)
 	return split_huge_page_to_list_to_order(page, NULL, ret);
 }
 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);
@@ -611,6 +614,7 @@ static inline int try_folio_split(struct folio *folio, struct page *page,
 }
 
 static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {}
+static inline void reparent_deferred_split_queue(struct mem_cgroup *memcg) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 59ddebc9f3232..b5eea2091cdf6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1099,6 +1099,11 @@ static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memc
 {
 	return memcg ? &memcg->deferred_split_queue : split_queue_node(nid);
 }
+
+static bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return memcg ? css_is_dying(&memcg->css) : false;
+}
 #else
 static inline
 struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
@@ -1111,14 +1116,30 @@ static struct deferred_split *memcg_split_queue(int nid, struct mem_cgroup *memc
 {
 	return split_queue_node(nid);
 }
+
+static bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return false;
+}
 #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;
 }
@@ -1128,8 +1149,14 @@ 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;
 }
@@ -4271,6 +4298,33 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 	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)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4deda33625f41..2acb53fd7f71e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3888,6 +3888,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	zswap_memcg_offline_cleanup(memcg);
 
 	memcg_offline_kmem(memcg);
+	reparent_deferred_split_queue(memcg);
 	reparent_shrinker_deferred(memcg);
 	wb_memcg_offline(memcg);
 	lru_gen_offline_memcg(memcg);
-- 
2.20.1