Re: [PATCH v2 6/7] mm/mglru: move folios from oldest gen to second-oldest gen from head to tail

[Lian Wang]

On Fri, 28 Aug 2026 07:47:03 +0800 "Barry Song (Xiaomi)" <baohua@xxxxxxxxxx> wrote:

> For reclamation, it makes sense to reclaim folios from tail to
> head, as folios near the head are relatively hot. However, when
> moving folios from the oldest generation to the second-oldest
> generation, using the tail-to-head order would effectively cause
> a cold/hot inversion.
>
> Signed-off-by: Barry Song (Xiaomi) <baohua@xxxxxxxxxx>
> Reviewed-by: Baoquan He <baoquan.he@xxxxxxxxx>
> Tested-by: Xueyuan Chen <xueyuan.chen21@xxxxxxxxx>
> ---
>  mm/vmscan.c | 23 +++++++++++++++++++++--
>  1 file changed, 21 insertions(+), 2 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 81f95a968447..17524e96fe64 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -192,11 +192,27 @@ static inline void prefetchw_prev_lru_folio(struct folio *folio,
>  		prefetchw(&prev->flags);
>  	}
>  }
> +
> +static inline void prefetchw_next_lru_folio(struct folio *folio,
> +		struct list_head *base)
> +{
> +	if (folio->lru.next != base) {
> +		struct folio *next;
> +
> +		next = list_entry(folio->lru.next, struct folio, lru);
> +		prefetchw(&next->flags);
> +	}
> +}
>  #else
>  static inline void prefetchw_prev_lru_folio(struct folio *folio,
>  		struct list_head *base)
>  {
>  }
> +
> +static inline void prefetchw_next_lru_folio(struct folio *folio,
> +		struct list_head *base)
> +{
> +}
>  #endif
>
>  /*
> @@ -3938,10 +3954,11 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
>  	/* prevent cold/hot inversion if the type is evictable */
>  	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
>  		struct list_head *head = &lrugen->folios[old_gen][type][zone];
> +		struct list_head *pos = head->next;
>  		long delta = 0;
>
> -		while (!list_empty(head)) {
> -			struct folio *folio = lru_to_folio(head);
> +		while (pos != head) {
> +			struct folio *folio = list_entry(pos, struct folio, lru);
>  			long nr_pages = folio_nr_pages(folio);
>  			int refs = folio_lru_refs(folio);
>  			bool workingset = folio_test_workingset(folio);
> @@ -3952,6 +3969,8 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
>  			VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
>  			VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
>
> +			prefetchw_next_lru_folio(folio, head);
> +			pos = pos->next;

Saving `pos->next` before moving the current folio keeps the forward iterator
valid. Across partial-batch restarts, processing from head to tail and appending
to the target tail preserves the relative hot-to-cold order of these folios.

>  			new_gen = __folio_inc_gen(folio, old_gen, &gen_increased);
>  			if (gen_increased) {
>  				delta += nr_pages;
> --
> 2.34.1

Looks good to me.

Reviewed-by: Lian Wang <lianux.mm@xxxxxxxxx>