Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Muchun Song <songmuchun@bytedance.com>
To:     guro@fb.com, hannes@cmpxchg.org, mhocko@kernel.org,
        akpm@linux-foundation.org, shakeelb@google.com,
        vdavydov.dev@gmail.com
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        duanxiongchun@bytedance.com, fam.zheng@bytedance.com,
        bsingharora@gmail.com, shy828301@gmail.com,
        alex.shi@linux.alibaba.com, Muchun Song <songmuchun@bytedance.com>
Subject: [RFC PATCH v2 12/18] mm: thp: make deferred split queue lock safe when the LRU pages reparented
Date:   Fri,  9 Apr 2021 20:29:53 +0800
Message-Id: <20210409122959.82264-13-songmuchun@bytedance.com>
In-Reply-To: <20210409122959.82264-1-songmuchun@bytedance.com>
References: <20210409122959.82264-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Similar to lruvec lock, we use the same approach to make the lock safe
when the LRU pages reparented.

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

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 275dbfc8b2ae..aa5d7b72d5fc 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -497,6 +497,8 @@ static struct deferred_split *lock_split_queue(struct page *page)
 	struct deferred_split *queue;
 	struct mem_cgroup *memcg;
 
+	rcu_read_lock();
+retry:
 	memcg = page_memcg(compound_head(page));
 	if (memcg)
 		queue = &memcg->deferred_split_queue;
@@ -504,6 +506,17 @@ static struct deferred_split *lock_split_queue(struct page *page)
 		queue = &NODE_DATA(page_to_nid(page))->deferred_split_queue;
 	spin_lock(&queue->split_queue_lock);
 
+	if (unlikely(memcg != page_memcg(page))) {
+		spin_unlock(&queue->split_queue_lock);
+		goto retry;
+	}
+
+	/*
+	 * Preemption is disabled in the internal of spin_lock, which can serve
+	 * as RCU read-side critical sections.
+	 */
+	rcu_read_unlock();
+
 	return queue;
 }
 
@@ -513,6 +526,8 @@ static struct deferred_split *lock_split_queue_irqsave(struct page *page,
 	struct deferred_split *queue;
 	struct mem_cgroup *memcg;
 
+	rcu_read_lock();
+retry:
 	memcg = page_memcg(compound_head(page));
 	if (memcg)
 		queue = &memcg->deferred_split_queue;
@@ -520,6 +535,14 @@ static struct deferred_split *lock_split_queue_irqsave(struct page *page,
 		queue = &NODE_DATA(page_to_nid(page))->deferred_split_queue;
 	spin_lock_irqsave(&queue->split_queue_lock, *flags);
 
+	if (unlikely(memcg != page_memcg(page))) {
+		spin_unlock_irqrestore(&queue->split_queue_lock, *flags);
+		goto retry;
+	}
+
+	/* See the comments in lock_split_queue(). */
+	rcu_read_unlock();
+
 	return queue;
 }
 #else
-- 
2.11.0