[PATCH v3 17/30] mm: thp: prevent memory cgroup release in folio_split_queue_lock{_irqsave}()

[Qi Zheng]

From: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>

In the near future, a folio will no longer pin its corresponding memory
cgroup. To ensure safety, it will only be appropriate to hold the rcu read
lock or acquire a reference to the memory cgroup returned by
folio_memcg(), thereby preventing it from being released.

In the current patch, the rcu read lock is employed to safeguard against
the release of the memory cgroup in folio_split_queue_lock{_irqsave}().

Signed-off-by: Qi Zheng <zhengqi.arch@xxxxxxxxxxxxx>
Reviewed-by: Harry Yoo <harry.yoo@xxxxxxxxxx>
Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Acked-by: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Acked-by: David Hildenbrand (Red Hat) <david@xxxxxxxxxx>
---
 mm/huge_memory.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 99515838faa51..eb611239c1a74 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1154,13 +1154,29 @@ split_queue_lock_irqsave(int nid, struct mem_cgroup *memcg, unsigned long *flags
 
 static struct deferred_split *folio_split_queue_lock(struct folio *folio)
 {
-	return split_queue_lock(folio_nid(folio), folio_memcg(folio));
+	struct deferred_split *queue;
+
+	rcu_read_lock();
+	queue = split_queue_lock(folio_nid(folio), folio_memcg(folio));
+	/*
+	 * The memcg destruction path is acquiring the split queue lock for
+	 * reparenting. Once you have it locked, it's safe to drop the rcu lock.
+	 */
+	rcu_read_unlock();
+
+	return queue;
 }
 
 static struct deferred_split *
 folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags)
 {
-	return split_queue_lock_irqsave(folio_nid(folio), folio_memcg(folio), flags);
+	struct deferred_split *queue;
+
+	rcu_read_lock();
+	queue = split_queue_lock_irqsave(folio_nid(folio), folio_memcg(folio), flags);
+	rcu_read_unlock();
+
+	return queue;
 }
 
 static inline void split_queue_unlock(struct deferred_split *queue)
-- 
2.20.1