Re: [PATCH v3 25/30] mm: vmscan: prepare for reparenting traditional LRU folios

[Muchun Song <muchun.song@linux.dev>]

On 2026/1/14 19:32, Qi Zheng wrote:
> From: Qi Zheng <zhengqi.arch@bytedance.com>
>
> To resolve the dying memcg issue, we need to reparent LRU folios of child
> memcg to its parent memcg. For traditional LRU list, each lruvec of every
> memcg comprises four LRU lists. Due to the symmetry of the LRU lists, it
> is feasible to transfer the LRU lists from a memcg to its parent memcg
> during the reparenting process.
>
> This commit implements the specific function, which will be used during
> the reparenting process.
>
> Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
> Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
> Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Acked-by: Muchun Song <muchun.song@linux.dev>

With one comment below.
> ---
>   include/linux/mmzone.h |  4 ++++
>   include/linux/swap.h   | 19 +++++++++++++++++++
>   mm/swap.c              | 37 +++++++++++++++++++++++++++++++++++++
>   mm/vmscan.c            | 19 -------------------
>   4 files changed, 60 insertions(+), 19 deletions(-)
>
> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
> index 6a7db0fee54a3..1014b5a93c09c 100644
> --- a/include/linux/mmzone.h
> +++ b/include/linux/mmzone.h
> @@ -366,6 +366,10 @@ enum lruvec_flags {
>   	LRUVEC_NODE_CONGESTED,
>   };
>   
> +#ifdef CONFIG_MEMCG
> +void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent);
> +#endif /* CONFIG_MEMCG */

Can we move it to swap.h since it is declared in swap.c?

> +
>   #endif /* !__GENERATING_BOUNDS_H */
>   
>   /*
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index e60f45b48e74d..4449d1f371a56 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -636,5 +636,24 @@ static inline bool mem_cgroup_swap_full(struct folio *folio)
>   }
>   #endif
>   
> +/* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to
> + * and including the specified highidx
> + * @zone: The current zone in the iterator
> + * @pgdat: The pgdat which node_zones are being iterated
> + * @idx: The index variable
> + * @highidx: The index of the highest zone to return
> + *
> + * This macro iterates through all managed zones up to and including the specified highidx.
> + * The zone iterator enters an invalid state after macro call and must be reinitialized
> + * before it can be used again.
> + */
> +#define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx)	\
> +	for ((idx) = 0, (zone) = (pgdat)->node_zones;		\
> +	    (idx) <= (highidx);					\
> +	    (idx)++, (zone)++)					\
> +		if (!managed_zone(zone))			\
> +			continue;				\
> +		else
> +
>   #endif /* __KERNEL__*/
>   #endif /* _LINUX_SWAP_H */
> diff --git a/mm/swap.c b/mm/swap.c
> index 7e53479ca1732..cb40e80da53cd 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -1090,6 +1090,43 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
>   	fbatch->nr = j;
>   }
>   
> +#ifdef CONFIG_MEMCG
> +static void lruvec_reparent_lru(struct lruvec *child_lruvec,
> +				struct lruvec *parent_lruvec,
> +				enum lru_list lru, int nid)
> +{
> +	int zid;
> +	struct zone *zone;
> +
> +	if (lru != LRU_UNEVICTABLE)
> +		list_splice_tail_init(&child_lruvec->lists[lru], &parent_lruvec->lists[lru]);
> +
> +	for_each_managed_zone_pgdat(zone, NODE_DATA(nid), zid, MAX_NR_ZONES - 1) {
> +		unsigned long size = mem_cgroup_get_zone_lru_size(child_lruvec, lru, zid);
> +
> +		mem_cgroup_update_lru_size(parent_lruvec, lru, zid, size);
> +	}
> +}
> +
> +void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent)
> +{
> +	int nid;
> +
> +	for_each_node(nid) {
> +		enum lru_list lru;
> +		struct lruvec *child_lruvec, *parent_lruvec;
> +
> +		child_lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
> +		parent_lruvec = mem_cgroup_lruvec(parent, NODE_DATA(nid));
> +		parent_lruvec->anon_cost += child_lruvec->anon_cost;
> +		parent_lruvec->file_cost += child_lruvec->file_cost;
> +
> +		for_each_lru(lru)
> +			lruvec_reparent_lru(child_lruvec, parent_lruvec, lru, nid);
> +	}
> +}
> +#endif
> +
>   static const struct ctl_table swap_sysctl_table[] = {
>   	{
>   		.procname	= "page-cluster",
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index c48ff6e05e004..e738082874878 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -270,25 +270,6 @@ static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
>   }
>   #endif
>   
> -/* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to
> - * and including the specified highidx
> - * @zone: The current zone in the iterator
> - * @pgdat: The pgdat which node_zones are being iterated
> - * @idx: The index variable
> - * @highidx: The index of the highest zone to return
> - *
> - * This macro iterates through all managed zones up to and including the specified highidx.
> - * The zone iterator enters an invalid state after macro call and must be reinitialized
> - * before it can be used again.
> - */
> -#define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx)	\
> -	for ((idx) = 0, (zone) = (pgdat)->node_zones;		\
> -	    (idx) <= (highidx);					\
> -	    (idx)++, (zone)++)					\
> -		if (!managed_zone(zone))			\
> -			continue;				\
> -		else
> -
>   static void set_task_reclaim_state(struct task_struct *task,
>   				   struct reclaim_state *rs)
>   {