From: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
Subject: mm: thp: don't need to drain lru cache when splitting and mlocking THP
Since commit 8f182270dfec ("mm/swap.c: flush lru pvecs on compound page
arrival") THP would not stay in pagevec anymore. So the optimization made
by commit d965432234db ("thp: increase split_huge_page() success rate")
doesn't make sense anymore, which tries to unpin munlocked THPs from
pagevec by draining pagevec.
Draining lru cache before isolating THP in mlock path is also unnecessary.
b676b293fb48 ("mm, thp: fix mapped pages avoiding unevictable list on
mlock") added it and 9a73f61bdb8a ("thp, mlock: do not mlock PTE-mapped
file huge pages") accidentally carried it over after the above
optimization went in.
Link: http://lkml.kernel.org/r/1585946493-7531-1-git-send-email-yang.shi@xxxxxxxxxxxxxxxxx
Signed-off-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx>
Reviewed-by: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 7 -------
1 file changed, 7 deletions(-)
--- a/mm/huge_memory.c~mm-thp-dont-need-drain-lru-cache-when-splitting-and-mlocking-thp
+++ a/mm/huge_memory.c
@@ -1378,7 +1378,6 @@ struct page *follow_trans_huge_pmd(struc
goto skip_mlock;
if (!trylock_page(page))
goto skip_mlock;
- lru_add_drain();
if (page->mapping && !PageDoubleMap(page))
mlock_vma_page(page);
unlock_page(page);
@@ -2582,7 +2581,6 @@ int split_huge_page_to_list(struct page
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
int count, mapcount, extra_pins, ret;
- bool mlocked;
unsigned long flags;
pgoff_t end;
@@ -2641,14 +2639,9 @@ int split_huge_page_to_list(struct page
goto out_unlock;
}
- mlocked = PageMlocked(head);
unmap_page(head);
VM_BUG_ON_PAGE(compound_mapcount(head), head);
- /* Make sure the page is not on per-CPU pagevec as it takes pin */
- if (mlocked)
- lru_add_drain();
-
/* prevent PageLRU to go away from under us, and freeze lru stats */
spin_lock_irqsave(&pgdata->lru_lock, flags);
_
