Re: [PATCH 2/4] mm: thp: introduce folio_split_queue_lock and its variants

[Zi Yan <ziy@nvidia.com>]

On 18 Sep 2025, at 23:46, Qi Zheng wrote:

> From: Muchun Song <songmuchun@bytedance.com>
>
> In future memcg removal, the binding between a folio and a memcg may
> change, making the split lock within the memcg unstable when held.
>
> A new approach is required to reparent the split queue to its parent. This
> patch starts introducing a unified way to acquire the split lock for
> future work.
>
> It's a code-only refactoring with no functional changes.
>
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
> ---
>  include/linux/memcontrol.h | 10 +++++
>  mm/huge_memory.c           | 89 ++++++++++++++++++++++++++------------
>  2 files changed, 71 insertions(+), 28 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 16fe0306e50ea..99876af13c315 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -1662,6 +1662,11 @@ int alloc_shrinker_info(struct mem_cgroup *memcg);
>  void free_shrinker_info(struct mem_cgroup *memcg);
>  void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
>  void reparent_shrinker_deferred(struct mem_cgroup *memcg);
> +
> +static inline int shrinker_id(struct shrinker *shrinker)
> +{
> +	return shrinker->id;
> +}
>  #else
>  #define mem_cgroup_sockets_enabled 0
>
> @@ -1693,6 +1698,11 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg,
>  				    int nid, int shrinker_id)
>  {
>  }
> +
> +static inline int shrinker_id(struct shrinker *shrinker)
> +{
> +	return -1;
> +}
>  #endif
>
>  #ifdef CONFIG_MEMCG
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 582628ddf3f33..d34516a22f5bb 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1078,26 +1078,62 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
>
>  #ifdef CONFIG_MEMCG
>  static inline
> -struct deferred_split *get_deferred_split_queue(struct folio *folio)
> +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
> +					   struct deferred_split *queue)
>  {
> -	struct mem_cgroup *memcg = folio_memcg(folio);
> -	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
> -
> -	if (memcg)
> -		return &memcg->deferred_split_queue;
> -	else
> -		return &pgdat->deferred_split_queue;
> +	if (mem_cgroup_disabled())
> +		return NULL;
> +	if (&NODE_DATA(folio_nid(folio))->deferred_split_queue == queue)
> +		return NULL;
> +	return container_of(queue, struct mem_cgroup, deferred_split_queue);
>  }
>  #else
>  static inline
> -struct deferred_split *get_deferred_split_queue(struct folio *folio)
> +struct mem_cgroup *folio_split_queue_memcg(struct folio *folio,
> +					   struct deferred_split *queue)
>  {
> -	struct pglist_data *pgdat = NODE_DATA(folio_nid(folio));
> -
> -	return &pgdat->deferred_split_queue;
> +	return NULL;
>  }
>  #endif
>
> +static struct deferred_split *folio_split_queue_lock(struct folio *folio)
> +{
> +	struct mem_cgroup *memcg;
> +	struct deferred_split *queue;
> +
> +	memcg = folio_memcg(folio);
> +	queue = memcg ? &memcg->deferred_split_queue :
> +			&NODE_DATA(folio_nid(folio))->deferred_split_queue;
> +	spin_lock(&queue->split_queue_lock);
> +
> +	return queue;
> +}
> +
> +static struct deferred_split *
> +folio_split_queue_lock_irqsave(struct folio *folio, unsigned long *flags)
> +{
> +	struct mem_cgroup *memcg;
> +	struct deferred_split *queue;
> +
> +	memcg = folio_memcg(folio);
> +	queue = memcg ? &memcg->deferred_split_queue :
> +			&NODE_DATA(folio_nid(folio))->deferred_split_queue;
> +	spin_lock_irqsave(&queue->split_queue_lock, *flags);
> +
> +	return queue;
> +}

A helper function to get queue from a folio would get rid of duplicated
code in the two functions above. Hmm, that is the deleted
get_deferred_split_queue(). So probably retain it.

Otherwise, LGTM. Reviewed-by: Zi Yan <ziy@nvidia.com>

Best Regards,
Yan, Zi