Re: [PATCH v2 4/4] mm: thp: reparent the split queue during memcg offline

[Zi Yan <ziy@nvidia.com>]

On 23 Sep 2025, at 5:16, Qi Zheng wrote:

> 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.
>
> 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@bytedance.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;

Should ds_queue still be marked as dying even if it is empty?
Otherwise, new folios still can be added to it, based on my
understanding of the changes to folio_split_queue_lock*().

> +
> +	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));
> +
> +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);
>  	wb_memcg_offline(memcg);
>  	lru_gen_offline_memcg(memcg);
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index 3db2dea7db4c5..cbda5c2ee3241 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -1387,6 +1387,7 @@ static void pgdat_init_split_queue(struct pglist_data *pgdat)
>  	spin_lock_init(&ds_queue->split_queue_lock);
>  	INIT_LIST_HEAD(&ds_queue->split_queue);
>  	ds_queue->split_queue_len = 0;
> +	ds_queue->is_dying = false;
>  }
>  #else
>  static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
> -- 
> 2.20.1


Best Regards,
Yan, Zi