[PATCHv4 5/8] khugepaged: Allow to collapse a page shared across fork

["Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>]

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

Logic to check the refcount is moved to a separate function.
For pages in swap cache, add compound_nr(page) to the expected refcount,
in order to handle the compound page case. This is in preparation for
the following patch.

VM_BUG_ON_PAGE() was removed from __collapse_huge_page_copy() as the
invariant it checks is no longer valid: the source can be mapped
multiple times now.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-and-Tested-by: Zi Yan <ziy@nvidia.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
---
 mm/khugepaged.c | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index adc686f13447..c3eb9d0d53f8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -526,6 +526,24 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte)
 	}
 }
 
+static bool is_refcount_suitable(struct page *page)
+{
+	int expected_refcount, refcount;
+
+	refcount = page_count(page);
+	expected_refcount = total_mapcount(page);
+	if (PageSwapCache(page))
+		expected_refcount += compound_nr(page);
+
+	if (IS_ENABLED(CONFIG_DEBUG_VM) && expected_refcount > refcount) {
+		pr_err("expected_refcount (%d) > refcount (%d)\n",
+				expected_refcount, refcount);
+		dump_page(page, "Unexpected refcount");
+	}
+
+	return page_count(page) == expected_refcount;
+}
+
 static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 					unsigned long address,
 					pte_t *pte)
@@ -578,11 +596,17 @@ 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
+		 * an additinal pin on the page.
+		 *
+		 * New pins can come later if the page is shared across fork,
+		 * but not from this process. The other process cannot write to
+		 * the page, only trigger CoW.
 		 */
-		if (page_count(page) != 1 + PageSwapCache(page)) {
+		if (!is_refcount_suitable(page)) {
 			unlock_page(page);
 			result = SCAN_PAGE_COUNT;
 			goto out;
@@ -669,7 +693,6 @@ 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
@@ -1220,12 +1243,8 @@ 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 (!is_refcount_suitable(page)) {
 			result = SCAN_PAGE_COUNT;
 			goto out_unmap;
 		}
-- 
2.26.1