[PATCHv2 5/8] khugepaged: Allow to callapse a page shared across fork

From: Kirill A. Shutemov
Date: Fri Apr 03 2020 - 07:29:50 EST


The page can be included into collapse as long as it doesn't have extra
pins (from GUP or otherwise).

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
mm/khugepaged.c | 25 ++++++++++++++-----------
1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 57ff287caf6b..1e7e6543ebca 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -581,11 +581,18 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
}

/*
- * cannot use mapcount: can't collapse if there's a gup pin.
- * The page must only be referenced by the scanned process
- * and page swap cache.
+ * Check if the page has any GUP (or other external) pins.
+ *
+ * The page table that maps the page has been already unlinked
+ * from the page table tree and this process cannot get
+ * additinal pin on the page.
+ *
+ * New pins can come later if the page is shared across fork,
+ * but not for the this process. It is fine. The other process
+ * cannot write to the page, only trigger CoW.
*/
- if (page_count(page) != 1 + PageSwapCache(page)) {
+ if (total_mapcount(page) + PageSwapCache(page) !=
+ page_count(page)) {
unlock_page(page);
result = SCAN_PAGE_COUNT;
goto out;
@@ -672,7 +679,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
} else {
src_page = pte_page(pteval);
copy_user_highpage(page, src_page, address, vma);
- VM_BUG_ON_PAGE(page_mapcount(src_page) != 1, src_page);
release_pte_page(src_page);
/*
* ptl mostly unnecessary, but preempt has to
@@ -1206,12 +1212,9 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
goto out_unmap;
}

- /*
- * cannot use mapcount: can't collapse if there's a gup pin.
- * The page must only be referenced by the scanned process
- * and page swap cache.
- */
- if (page_count(page) != 1 + PageSwapCache(page)) {
+ /* Check if the page has any GUP (or other external) pins */
+ if (total_mapcount(page) + PageSwapCache(page) !=
+ page_count(page)) {
result = SCAN_PAGE_COUNT;
goto out_unmap;
}
--
2.26.0