khugepaged: skip collapse if uffd-wp detected

Don't collapse the huge PMD if there is any userfault write protected
small PTEs.  The problem is that the write protection is in small page
granularity and there's no way to keep all these write protection
information if the small pages are going to be merged into a huge PMD.

The same thing needs to be considered for swap entries and migration
entries.  So do the check as well disregarding khugepaged_max_ptes_swap.

Signed-off-by: Peter Xu <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Reviewed-by: Jerome Glisse <[email protected]>
Reviewed-by: Mike Rapoport <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Bobby Powers <[email protected]>
Cc: Brian Geffon <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Denis Plotnikov <[email protected]>
Cc: "Dr . David Alan Gilbert" <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: "Kirill A . Shutemov" <[email protected]>
Cc: Martin Cracauer <[email protected]>
Cc: Marty McFadden <[email protected]>
Cc: Maya Gokhale <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Mike Kravetz <[email protected]>
Cc: Pavel Emelyanov <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Shaohua Li <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 24 insertions, 0 deletions

diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index d82a0f4e824d..70e32ff096ec 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -13,6 +13,7 @@
 	EM( SCAN_PMD_NULL,		"pmd_null")			\
 	EM( SCAN_EXCEED_NONE_PTE,	"exceed_none_pte")		\
 	EM( SCAN_PTE_NON_PRESENT,	"pte_non_present")		\
+	EM( SCAN_PTE_UFFD_WP,		"pte_uffd_wp")			\
 	EM( SCAN_PAGE_RO,		"no_writable_page")		\
 	EM( SCAN_LACK_REFERENCED_PAGE,	"lack_referenced_page")		\
 	EM( SCAN_PAGE_NULL,		"page_null")			\
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 3afc1e2d7a55..99d77ffb79c2 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -29,6 +29,7 @@ enum scan_result {
 	SCAN_PMD_NULL,
 	SCAN_EXCEED_NONE_PTE,
 	SCAN_PTE_NON_PRESENT,
+	SCAN_PTE_UFFD_WP,
 	SCAN_PAGE_RO,
 	SCAN_LACK_REFERENCED_PAGE,
 	SCAN_PAGE_NULL,
@@ -1137,6 +1138,15 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		pte_t pteval = *_pte;
 		if (is_swap_pte(pteval)) {
 			if (++unmapped <= khugepaged_max_ptes_swap) {
+				/*
+				 * Always be strict with uffd-wp
+				 * enabled swap entries.  Please see
+				 * comment below for pte_uffd_wp().
+				 */
+				if (pte_swp_uffd_wp(pteval)) {
+					result = SCAN_PTE_UFFD_WP;
+					goto out_unmap;
+				}
 				continue;
 			} else {
 				result = SCAN_EXCEED_SWAP_PTE;
@@ -1156,6 +1166,19 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 			result = SCAN_PTE_NON_PRESENT;
 			goto out_unmap;
 		}
+		if (pte_uffd_wp(pteval)) {
+			/*
+			 * Don't collapse the page if any of the small
+			 * PTEs are armed with uffd write protection.
+			 * Here we can also mark the new huge pmd as
+			 * write protected if any of the small ones is
+			 * marked but that could bring uknown
+			 * userfault messages that falls outside of
+			 * the registered range.  So, just be simple.
+			 */
+			result = SCAN_PTE_UFFD_WP;
+			goto out_unmap;
+		}
 		if (pte_write(pteval))
 			writable = true;