From: Muchun Song <songmuchun@bytedance.com>

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 mglru.

This serves as a preparatory measure for the reparenting of the
LRU pages.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 mm/vmscan.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 354b19f7365d4..814498a2c1bd6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3444,8 +3444,10 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
 	if (folio_nid(folio) != pgdat->node_id)
 		return NULL;
 
+	rcu_read_lock();
 	if (folio_memcg(folio) != memcg)
-		return NULL;
+		folio = NULL;
+	rcu_read_unlock();
 
 	return folio;
 }
@@ -4202,12 +4204,12 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
 	struct folio *folio = pfn_folio(pvmw->pfn);
-	struct mem_cgroup *memcg = folio_memcg(folio);
+	struct mem_cgroup *memcg;
 	struct pglist_data *pgdat = folio_pgdat(folio);
-	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
-	DEFINE_MAX_SEQ(lruvec);
-	int gen = lru_gen_from_seq(max_seq);
+	struct lruvec *lruvec;
+	struct lru_gen_mm_state *mm_state;
+	unsigned long max_seq;
+	int gen;
 
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
@@ -4242,6 +4244,13 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		}
 	}
 
+	rcu_read_lock();
+	memcg = folio_memcg(folio);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
+	gen = lru_gen_from_seq(max_seq);
+	mm_state = get_mm_state(lruvec);
+
 	arch_enter_lazy_mmu_mode();
 
 	pte -= (addr - start) / PAGE_SIZE;
@@ -4282,6 +4291,8 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	if (mm_state && suitable_to_scan(i, young))
 		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
 
+	rcu_read_unlock();
+
 	return true;
 }
 
-- 
2.20.1

On Wed, Dec 17, 2025 at 03:27:38PM +0800, Qi Zheng wrote:
> @@ -4242,6 +4244,13 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
>  		}
>  	}
>  
> +	rcu_read_lock();
> +	memcg = folio_memcg(folio);
> +	lruvec = mem_cgroup_lruvec(memcg, pgdat);
> +	max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
> +	gen = lru_gen_from_seq(max_seq);
> +	mm_state = get_mm_state(lruvec);
> +
>  	arch_enter_lazy_mmu_mode();
>  
>  	pte -= (addr - start) / PAGE_SIZE;
> @@ -4282,6 +4291,8 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
>  	if (mm_state && suitable_to_scan(i, young))
>  		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
>  
> +	rcu_read_unlock();
> +
>  	return true;

This seems a bit long to be holding the rcu lock. Maybe do a get and a
put instead?

On 12/18/25 6:18 AM, Johannes Weiner wrote:
> On Wed, Dec 17, 2025 at 03:27:38PM +0800, Qi Zheng wrote:
>> @@ -4242,6 +4244,13 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
>>   		}
>>   	}
>>   
>> +	rcu_read_lock();
>> +	memcg = folio_memcg(folio);
>> +	lruvec = mem_cgroup_lruvec(memcg, pgdat);
>> +	max_seq = READ_ONCE((lruvec)->lrugen.max_seq);
>> +	gen = lru_gen_from_seq(max_seq);
>> +	mm_state = get_mm_state(lruvec);
>> +
>>   	arch_enter_lazy_mmu_mode();
>>   
>>   	pte -= (addr - start) / PAGE_SIZE;
>> @@ -4282,6 +4291,8 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
>>   	if (mm_state && suitable_to_scan(i, young))
>>   		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
>>   
>> +	rcu_read_unlock();
>> +
>>   	return true;
> 
> This seems a bit long to be holding the rcu lock. 

Indeed.

> Maybe do a get and a
> put instead?

OK, will use get_mem_cgroup_from_folio(folio) to do this.

This way, #8 doesn't need to be folded into #27.