On 25/08/2023 14:59, Matthew Wilcox (Oracle) wrote:
> Hugetlb folios still get special treatment, but normal large folios
> can now be freed by free_unref_folios(). This should have a reasonable
> performance impact, TBD.
>
> Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
> ---
> mm/swap.c | 5 +++--
> 1 file changed, 3 insertions(+), 2 deletions(-)
>
> diff --git a/mm/swap.c b/mm/swap.c
> index 21c2df0f7928..8bd15402cd8f 100644
> --- a/mm/swap.c
> +++ b/mm/swap.c
> @@ -1000,12 +1000,13 @@ void folios_put(struct folio_batch *folios)
> if (!folio_put_testzero(folio))
> continue;
>
> - if (folio_test_large(folio)) {
> + /* hugetlb has its own memcg */
> + if (folio_test_hugetlb(folio)) {
Ahh I see, you special case hugetlb here. You can disregard my comment about
hugetlb in the previous patch.
> if (lruvec) {
> unlock_page_lruvec_irqrestore(lruvec, flags);
> lruvec = NULL;
> }
> - __folio_put_large(folio);
> + free_huge_folio(folio);
> continue;
> }
>
