On Tue, Apr 25, 2017 at 08:56:58PM +0800, Huang, Ying wrote:
> From: Huang Ying <ying.hu...@intel.com>
>
> If there is no compound map for a THP (Transparent Huge Page), it is
> possible that the map count of some sub-pages of the THP is 0. So it
> is better to split the THP before swapping out. In this way, the
> sub-pages not mapped will be freed, and we can avoid the unnecessary
> swap out operations for these sub-pages.
>
> Cc: Johannes Weiner <han...@cmpxchg.org>
> Signed-off-by: "Huang, Ying" <ying.hu...@intel.com>
Acked-by: Johannes Weiner <han...@cmpxchg.org>
CC Kirill to double check the reasoning here
> ---
> mm/swap_state.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 006d91d8fc53..13f83c6bb1b4 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -192,9 +192,19 @@ int add_to_swap(struct page *page, struct list_head
> *list)
> VM_BUG_ON_PAGE(!PageLocked(page), page);
> VM_BUG_ON_PAGE(!PageUptodate(page), page);
>
> - /* cannot split, skip it */
> - if (PageTransHuge(page) && !can_split_huge_page(page, NULL))
> - return 0;
> + if (PageTransHuge(page)) {
> + /* cannot split, skip it */
> + if (!can_split_huge_page(page, NULL))
> + return 0;
> + /*
> + * Split pages without a PMD map right away. Chances
> + * are some or all of the tail pages can be freed
> + * without IO.
> + */
> + if (!compound_mapcount(page) &&
> + split_huge_page_to_list(page, list))
> + return 0;
> + }
>
> retry:
> entry = get_swap_page(page);
> --
> 2.11.0
