From: Huang Ying <[email protected]>

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 <[email protected]>
Signed-off-by: "Huang, Ying" <[email protected]>
---
 mm/vmscan.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index a5355022dc2f..f7e949ac9756 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1125,10 +1125,19 @@ static unsigned long shrink_page_list(struct list_head 
*page_list,
                    !PageSwapCache(page)) {
                        if (!(sc->gfp_mask & __GFP_IO))
                                goto keep_locked;
-                       /* cannot split THP, skip it */
-                       if (PageTransHuge(page) &&
-                           !can_split_huge_page(page, NULL))
-                               goto activate_locked;
+                       if (PageTransHuge(page)) {
+                               /* cannot split THP, skip it */
+                               if (!can_split_huge_page(page, NULL))
+                                       goto activate_locked;
+                               /*
+                                * 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, page_list))
+                                       goto activate_locked;
+                       }
                        if (!add_to_swap(page)) {
                                if (!PageTransHuge(page))
                                        goto activate_locked;
-- 
2.11.0

Reply via email to