mm: thp: reparent the split queue during memcg offline

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.

Link: https://lkml.kernel.org/r/8703f907c4d1f7e8a2ef2bfed3036a84fa53028b.1762762324.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 60 insertions, 0 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 525624c285a6..e2e91aa1a042 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -415,6 +415,9 @@ static inline int split_huge_page(struct page *page)
 	return split_huge_page_to_list_to_order(page, NULL, 0);
 }
 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);
@@ -647,6 +650,7 @@ static inline int try_folio_split_to_order(struct folio *folio,
 }
 
 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/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b0c6a4635c67..cc6db20d7dca 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1775,6 +1775,12 @@ static inline void count_objcg_events(struct obj_cgroup *objcg,
 bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid);
 
 void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg);
+
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return memcg ? css_is_dying(&memcg->css) : false;
+}
+
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1845,6 +1851,11 @@ static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
 static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg)
 {
 }
+
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return false;
+}
 #endif /* CONFIG_MEMCG */
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 13684e5376e8..d17d3810a882 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1118,8 +1118,19 @@ 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;
 }
@@ -1129,8 +1140,14 @@ 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;
 }
@@ -4389,6 +4406,33 @@ next:
 	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 bfc986da3289..623446821b00 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3920,6 +3920,7 @@ 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);