[PATCH 5.10 080/105] memfd: fix F_SEAL_WRITE after shmem huge page allocated

[Greg Kroah-Hartman]

From: Hugh Dickins <hughd@xxxxxxxxxx>

commit f2b277c4d1c63a85127e8aa2588e9cc3bd21cb99 upstream.

Wangyong reports: after enabling tmpfs filesystem to support transparent
hugepage with the following command:

  echo always > /sys/kernel/mm/transparent_hugepage/shmem_enabled

the docker program tries to add F_SEAL_WRITE through the following
command, but it fails unexpectedly with errno EBUSY:

  fcntl(5, F_ADD_SEALS, F_SEAL_WRITE) = -1.

That is because memfd_tag_pins() and memfd_wait_for_pins() were never
updated for shmem huge pages: checking page_mapcount() against
page_count() is hopeless on THP subpages - they need to check
total_mapcount() against page_count() on THP heads only.

Make memfd_tag_pins() (compared > 1) as strict as memfd_wait_for_pins()
(compared != 1): either can be justified, but given the non-atomic
total_mapcount() calculation, it is better now to be strict.  Bear in
mind that total_mapcount() itself scans all of the THP subpages, when
choosing to take an XA_CHECK_SCHED latency break.

Also fix the unlikely xa_is_value() case in memfd_wait_for_pins(): if a
page has been swapped out since memfd_tag_pins(), then its refcount must
have fallen, and so it can safely be untagged.

Link: https://lkml.kernel.org/r/a4f79248-df75-2c8c-3df-ba3317ccb5da@xxxxxxxxxx
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Reported-by: Zeal Robot <zealci@xxxxxxxxxx>
Reported-by: wangyong <wang.yong12@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: CGEL ZTE <cgel.zte@xxxxxxxxx>
Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
Cc: Song Liu <songliubraving@xxxxxx>
Cc: Yang Yang <yang.yang29@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 mm/memfd.c |   40 ++++++++++++++++++++++++++++------------
 1 file changed, 28 insertions(+), 12 deletions(-)

--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -31,20 +31,28 @@
 static void memfd_tag_pins(struct xa_state *xas)
 {
 	struct page *page;
-	unsigned int tagged = 0;
+	int latency = 0;
+	int cache_count;
 
 	lru_add_drain();
 
 	xas_lock_irq(xas);
 	xas_for_each(xas, page, ULONG_MAX) {
-		if (xa_is_value(page))
-			continue;
-		page = find_subpage(page, xas->xa_index);
-		if (page_count(page) - page_mapcount(page) > 1)
+		cache_count = 1;
+		if (!xa_is_value(page) &&
+		    PageTransHuge(page) && !PageHuge(page))
+			cache_count = HPAGE_PMD_NR;
+
+		if (!xa_is_value(page) &&
+		    page_count(page) - total_mapcount(page) != cache_count)
 			xas_set_mark(xas, MEMFD_TAG_PINNED);
+		if (cache_count != 1)
+			xas_set(xas, page->index + cache_count);
 
-		if (++tagged % XA_CHECK_SCHED)
+		latency += cache_count;
+		if (latency < XA_CHECK_SCHED)
 			continue;
+		latency = 0;
 
 		xas_pause(xas);
 		xas_unlock_irq(xas);
@@ -73,7 +81,8 @@ static int memfd_wait_for_pins(struct ad
 
 	error = 0;
 	for (scan = 0; scan <= LAST_SCAN; scan++) {
-		unsigned int tagged = 0;
+		int latency = 0;
+		int cache_count;
 
 		if (!xas_marked(&xas, MEMFD_TAG_PINNED))
 			break;
@@ -87,10 +96,14 @@ static int memfd_wait_for_pins(struct ad
 		xas_lock_irq(&xas);
 		xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) {
 			bool clear = true;
-			if (xa_is_value(page))
-				continue;
-			page = find_subpage(page, xas.xa_index);
-			if (page_count(page) - page_mapcount(page) != 1) {
+
+			cache_count = 1;
+			if (!xa_is_value(page) &&
+			    PageTransHuge(page) && !PageHuge(page))
+				cache_count = HPAGE_PMD_NR;
+
+			if (!xa_is_value(page) && cache_count !=
+			    page_count(page) - total_mapcount(page)) {
 				/*
 				 * On the last scan, we clean up all those tags
 				 * we inserted; but make a note that we still
@@ -103,8 +116,11 @@ static int memfd_wait_for_pins(struct ad
 			}
 			if (clear)
 				xas_clear_mark(&xas, MEMFD_TAG_PINNED);
-			if (++tagged % XA_CHECK_SCHED)
+
+			latency += cache_count;
+			if (latency < XA_CHECK_SCHED)
 				continue;
+			latency = 0;
 
 			xas_pause(&xas);
 			xas_unlock_irq(&xas);