On 25/08/2023 14:59, Matthew Wilcox (Oracle) wrote:
> The few folios which can't be moved to the LRU list (because their
> refcount dropped to zero) used to be returned to the caller to dispose
> of. Make this simpler to call by freeing the folios directly through
> free_unref_folios().
>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
> ---
> mm/vmscan.c | 31 ++++++++++++-------------------
> 1 file changed, 12 insertions(+), 19 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 965c429847fd..d5080510608e 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -2489,8 +2489,9 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
> struct list_head *list)
The comment for this function is now stale:
/*
* move_folios_to_lru() moves folios from private @list to appropriate LRU list.
* On return, @list is reused as a list of folios to be freed by the caller.
*
* Returns the number of pages moved to the given lruvec.
*/
I think the "On return" bit is no longer true.
> {
> int nr_pages, nr_moved = 0;
> - LIST_HEAD(folios_to_free);
> + struct folio_batch free_folios;
>
> + folio_batch_init(&free_folios);
> while (!list_empty(list)) {
> struct folio *folio = lru_to_folio(list);
>
> @@ -2519,12 +2520,12 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
> if (unlikely(folio_put_testzero(folio))) {
> __folio_clear_lru_flags(folio);
>
> - if (unlikely(folio_test_large(folio))) {
> + if (folio_batch_add(&free_folios, folio) == 0) {
> spin_unlock_irq(&lruvec->lru_lock);
> - destroy_large_folio(folio);
> + mem_cgroup_uncharge_folios(&free_folios);
> + free_unref_folios(&free_folios);
> spin_lock_irq(&lruvec->lru_lock);
> - } else
> - list_add(&folio->lru, &folios_to_free);
> + }
>
> continue;
> }
> @@ -2541,10 +2542,12 @@ static unsigned int move_folios_to_lru(struct lruvec *lruvec,
> workingset_age_nonresident(lruvec, nr_pages);
> }
>
> - /*
> - * To save our caller's stack, now use input list for pages to free.
> - */
> - list_splice(&folios_to_free, list);
> + if (free_folios.nr) {
> + spin_unlock_irq(&lruvec->lru_lock);
> + mem_cgroup_uncharge_folios(&free_folios);
> + free_unref_folios(&free_folios);
> + spin_lock_irq(&lruvec->lru_lock);
> + }
>
> return nr_moved;
> }
> @@ -2623,8 +2626,6 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
> spin_unlock_irq(&lruvec->lru_lock);
>
> lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed);
> - mem_cgroup_uncharge_list(&folio_list);
> - free_unref_page_list(&folio_list);
>
> /*
> * If dirty folios are scanned that are not queued for IO, it
> @@ -2765,8 +2766,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
>
> nr_activate = move_folios_to_lru(lruvec, &l_active);
> nr_deactivate = move_folios_to_lru(lruvec, &l_inactive);
> - /* Keep all free folios in l_active list */
> - list_splice(&l_inactive, &l_active);
>
> __count_vm_events(PGDEACTIVATE, nr_deactivate);
> __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
> @@ -2776,8 +2775,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
>
> if (nr_rotated)
> lru_note_cost(lruvec, file, 0, nr_rotated);
> - mem_cgroup_uncharge_list(&l_active);
> - free_unref_page_list(&l_active);
> trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
> nr_deactivate, nr_rotated, sc->priority, file);
> }
> @@ -5238,10 +5235,6 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
>
> spin_unlock_irq(&lruvec->lru_lock);
>
> - mem_cgroup_uncharge_list(&list);
> - free_unref_page_list(&list);
> -
> - INIT_LIST_HEAD(&list);
> list_splice_init(&clean, &list);
>
> if (!list_empty(&list)) {
