Re: [PATCH v2 1/2] mm/mglru: fix cgroup OOM during MGLRU state switching

[Leno Hou]

On 3/12/26 2:02 PM, Barry Song wrote:
[...]
>> This effectively eliminates the race window that previously triggered OOMs
>> under high memory pressure.
>
> I don't think this eliminates the race window, but it does reduce it.
> There is nothing preventing the draining state from changing while
> you are shrinking.
>
Hi Barry，

You raise a valid point about the race window.

While the window exists, I believe the impact is effectively mitigated by
The reclaim retry mechanism: Even if the reclaimer makes a suboptimal path
 decision due to the race,  the kernel's reclaim loop (in do_try_to_free_pages)
provides multiple retries. If the first pass fails to reclaim  memory
due to the
race or an inconsistent state, the subsequent retry will observe the updated
draining state and correctly direct the scan to the appropriate LRU lists.

Anyway，thanks correct me and i'll updating the commit message.

>>
>> The issue was consistently reproduced on v6.1.157 and v6.18.3 using
>> a high-pressure memory cgroup (v1) environment.
>>
>> To: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
>> To: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
>> To: Yuanchu Xie <yuanchu@xxxxxxxxxx>
>> To: Wei Xu <weixugc@xxxxxxxxxx>
>> To: Barry Song <21cnbao@xxxxxxxxx>
>> To: Jialing Wang <wjl.linux@xxxxxxxxx>
>> To: Yafang Shao <laoar.shao@xxxxxxxxx>
>> To: Yu Zhao <yuzhao@xxxxxxxxxx>
>> To: Kairui Song <ryncsn@xxxxxxxxx>
>> To: Bingfang Guo <bfguo@xxxxxxxxxx>
>> Cc: linux-mm@xxxxxxxxx
>> Cc: linux-kernel@xxxxxxxxxxxxxxx
>> Signed-off-by: Leno Hou <lenohou@xxxxxxxxx>
>> ---
>>   include/linux/mm_inline.h |  5 +++++
>>   mm/rmap.c                 |  2 +-
>>   mm/swap.c                 | 14 ++++++++------
>>   mm/vmscan.c               | 49 ++++++++++++++++++++++++++++++++++++++---------
>>   4 files changed, 54 insertions(+), 16 deletions(-)
>>
>> diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
>> index fa2d6ba811b5..e6443e22bf67 100644
>> --- a/include/linux/mm_inline.h
>> +++ b/include/linux/mm_inline.h
>> @@ -321,6 +321,11 @@ static inline bool lru_gen_in_fault(void)
>>          return false;
>>   }
>>
>> +static inline int folio_lru_gen(const struct folio *folio)
>> +{
>> +       return -1;
>> +}
>> +
>>   static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
>>   {
>>          return false;
>> diff --git a/mm/rmap.c b/mm/rmap.c
>> index 0f00570d1b9e..488bcdca65ed 100644
>> --- a/mm/rmap.c
>> +++ b/mm/rmap.c
>> @@ -958,7 +958,7 @@ static bool folio_referenced_one(struct folio *folio,
>>                          return false;
>>                  }
>>
>> -               if (lru_gen_enabled() && pvmw.pte) {
>> +               if ((folio_lru_gen(folio) != -1) && pvmw.pte) {
>
> I am not quite sure if a folio's gen is set to -1 when it is isolated
> from MGLRU for reclamation. If so, I don't think this would work.
>

Thanks for your feedback. You are absolutely right—relying solely on
folio_lru_gen(folio) != -1 is insufficient because the generation tag
is cleared during isolation in lru_gen_del_folio().

In the current implementation, once a page is isolated, its generation
information is lost, causing the logic to fall back to the traditional LRU
path prematurely.

To address this, I am changing the logic to:
```c
@@ -966,7 +966,7 @@ static bool folio_referenced_one(struct folio *folio,
                        nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr);
                }

-               if (lru_gen_enabled() && pvmw.pte) {
+               if (lru_gen_enabled() && !lru_gen_draining() && pvmw.pte) {
                        if (lru_gen_look_around(&pvmw, nr))
                                referenced++;
                } else if (pvmw.pte) {
```
The rationale is that lru_gen_look_around() is an MGLRU-specific optimization
that promotes pages based on generation aging. During the draining
transition, we should strictly rely on traditional RMAP-based reference
auditing to ensure that pages are correctly migrated to traditional LRU
lists without being spuriously promoted by MGLRU logic. This avoids
mixing MGLRU's generation-based promotion with traditional LRU's 'active'
status, preventing potential reclaim state inconsistencies during the
transition period."


---
Thanks

Leno Hou