From e5947d23edd897ffe068564e91fd186adb95ee6d Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Wed, 30 Jun 2021 18:51:07 -0700 Subject: [PATCH] mm: mempolicy: don't have to split pmd for huge zero page When trying to migrate pages to obey mempolicy, the huge zero page is split by inserting base zero pfn to all PTEs, then the page table walk fallback to PTE level and just skips zero page. Skipping zero page for mempolicy has been the behavior of kernel since v2.6.16 due to commit f4598c8b3678 ("[PATCH] migration: make sure there is no attempt to migrate reserved pages."). So it seems pointless to split huge zero page, it could be just skipped like base zero page. Set ACTION_CONTINUE to prevent the walk_page_range() split the pmd for this case. Link: https://lkml.kernel.org/r/20210609172146.3594-1-shy828301@gmail.com Link: https://lkml.kernel.org/r/20210604203513.240709-1-shy828301@gmail.com Signed-off-by: Yang Shi Reviewed-by: Zi Yan Acked-by: Michal Hocko Cc: Naoya Horiguchi Cc: Kirill A. Shutemov Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 89721501b22c..8739bfd967e5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -437,7 +437,8 @@ static inline bool queue_pages_required(struct page *page, /* * queue_pages_pmd() has four possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. huge zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. @@ -461,8 +462,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); - __split_huge_pmd(walk->vma, pmd, addr, false, NULL); - ret = 2; + walk->action = ACTION_CONTINUE; goto out; } if (!queue_pages_required(page, qp)) @@ -489,7 +489,8 @@ out: * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already