| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <72d23e4d-6c59-4adf-86ba-aa3ae8566bde@bytedance.com>
Date: Wed, 24 Sep 2025 18:06:14 +0800
From: Qi Zheng <zhengqi.arch@...edance.com>
To: Roman Gushchin <roman.gushchin@...ux.dev>
Cc: hannes@...xchg.org, hughd@...gle.com, mhocko@...e.com,
shakeel.butt@...ux.dev, muchun.song@...ux.dev, david@...hat.com,
lorenzo.stoakes@...cle.com, ziy@...dia.com, harry.yoo@...cle.com,
baolin.wang@...ux.alibaba.com, Liam.Howlett@...cle.com, npache@...hat.com,
ryan.roberts@....com, dev.jain@....com, baohua@...nel.org,
lance.yang@...ux.dev, akpm@...ux-foundation.org, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, cgroups@...r.kernel.org
Subject: Re: [PATCH v2 4/4] mm: thp: reparent the split queue during memcg
offline
Hi Roman,
On 9/24/25 5:23 PM, Roman Gushchin wrote:
> Qi Zheng <zhengqi.arch@...edance.com> writes:
>
>> In the future, we will reparent LRU folios during memcg offline to
>> eliminate dying memory cgroups, which requires reparenting the split queue
>> to its parent.
>
> Nit: commit logs should really focus on the actual change, not the future
> plans.
Got it.
>
>>
>> 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 same mechanism as list_lru
>> to reparent the split queue separately when memcg is offine.
>>
>> Signed-off-by: Qi Zheng <zhengqi.arch@...edance.com>
>> ---
>> include/linux/huge_mm.h | 2 ++
>> include/linux/mmzone.h | 1 +
>> mm/huge_memory.c | 39 +++++++++++++++++++++++++++++++++++++++
>> mm/memcontrol.c | 1 +
>> mm/mm_init.c | 1 +
>> 5 files changed, 44 insertions(+)
>>
>> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
>> index f327d62fc9852..a0d4b751974d2 100644
>> --- a/include/linux/huge_mm.h
>> +++ b/include/linux/huge_mm.h
>> @@ -417,6 +417,7 @@ static inline int split_huge_page(struct page *page)
>> return split_huge_page_to_list_to_order(page, NULL, ret);
>> }
>> void deferred_split_folio(struct folio *folio, bool partially_mapped);
>> +void reparent_deferred_split_queue(struct mem_cgroup *memcg);
>>
>> void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
>> unsigned long address, bool freeze);
>> @@ -611,6 +612,7 @@ static inline int try_folio_split(struct folio *folio, struct page *page,
>> }
>>
>> 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/mmzone.h b/include/linux/mmzone.h
>> index 7fb7331c57250..f3eb81fee056a 100644
>> --- a/include/linux/mmzone.h
>> +++ b/include/linux/mmzone.h
>> @@ -1346,6 +1346,7 @@ struct deferred_split {
>> spinlock_t split_queue_lock;
>> struct list_head split_queue;
>> unsigned long split_queue_len;
>> + bool is_dying;
>> };
>> #endif
>>
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index 48b51e6230a67..de7806f759cba 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -1094,9 +1094,15 @@ static struct deferred_split *folio_split_queue_lock(struct folio *folio)
>> struct deferred_split *queue;
>>
>> memcg = folio_memcg(folio);
>> +retry:
>> queue = memcg ? &memcg->deferred_split_queue :
>> &NODE_DATA(folio_nid(folio))->deferred_split_queue;
>> spin_lock(&queue->split_queue_lock);
>> + if (unlikely(queue->is_dying == true)) {
>> + spin_unlock(&queue->split_queue_lock);
>> + memcg = parent_mem_cgroup(memcg);
>> + goto retry;
>> + }
>>
>> return queue;
>> }
>> @@ -1108,9 +1114,15 @@ folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags)
>> struct deferred_split *queue;
>>
>> memcg = folio_memcg(folio);
>> +retry:
>> queue = memcg ? &memcg->deferred_split_queue :
>> &NODE_DATA(folio_nid(folio))->deferred_split_queue;
>> spin_lock_irqsave(&queue->split_queue_lock, *flags);
>> + if (unlikely(queue->is_dying == true)) {
>> + spin_unlock_irqrestore(&queue->split_queue_lock, *flags);
>> + memcg = parent_mem_cgroup(memcg);
>> + goto retry;
>> + }
>>
>> return queue;
>> }
>> @@ -4284,6 +4296,33 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
>> return split;
>> }
>>
>> +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;
>> + /* Mark the ds_queue dead */
>> + ds_queue->is_dying = true;
>> +
>> + for_each_node(nid)
>> + set_shrinker_bit(parent, nid, shrinker_id(deferred_split_shrinker));
>
> Does this loop need to be under locks?
I think it is not necessary, but the loop overhead should not be high.
>
>> +
>> +unlock:
>> + spin_unlock(&parent_ds_queue->split_queue_lock);
>> + spin_unlock_irq(&ds_queue->split_queue_lock);
>> +}
>> +
>> #ifdef CONFIG_DEBUG_FS
>> static void split_huge_pages_all(void)
>> {
>> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
>> index e090f29eb03bd..d03da72e7585d 100644
>> --- a/mm/memcontrol.c
>> +++ b/mm/memcontrol.c
>> @@ -3887,6 +3887,7 @@ 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);
>
> I guess the naming can be a bit more consistent here :)
Do you mean to change them all to:
memcg_offline_xxx()
or
reparent_xxx() ?
Thanks,
Qi
>
> Thanks!
Powered by blists - more mailing lists