memfd: fix F_SEAL_WRITE after shmem huge page allocated

[Hugh Dickins <hughd@xxxxxxxxxx>]

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>
---
 mm/memfd.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -34,26 +34,35 @@ static void memfd_tag_pins(struct address_space *mapping)
 	void __rcu **slot;
 	pgoff_t start;
 	struct page *page;
-	unsigned int tagged = 0;
+	int latency = 0;
+	int cache_count;
 
 	lru_add_drain();
 	start = 0;
 
 	xa_lock_irq(&mapping->i_pages);
 	radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
+		cache_count = 1;
 		page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-		if (!page || radix_tree_exception(page)) {
+		if (!page || radix_tree_exception(page) || PageTail(page)) {
 			if (radix_tree_deref_retry(page)) {
 				slot = radix_tree_iter_retry(&iter);
 				continue;
 			}
-		} else if (page_count(page) - page_mapcount(page) > 1) {
-			radix_tree_tag_set(&mapping->i_pages, iter.index,
-					   MEMFD_TAG_PINNED);
+		} else {
+			if (PageTransHuge(page) && !PageHuge(page))
+				cache_count = HPAGE_PMD_NR;
+			if (cache_count !=
+			    page_count(page) - total_mapcount(page)) {
+				radix_tree_tag_set(&mapping->i_pages,
+						iter.index, MEMFD_TAG_PINNED);
+			}
 		}
 
-		if (++tagged % 1024)
+		latency += cache_count;
+		if (latency < 1024)
 			continue;
+		latency = 0;
 
 		slot = radix_tree_iter_resume(slot, &iter);
 		xa_unlock_irq(&mapping->i_pages);
@@ -79,6 +88,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
 	pgoff_t start;
 	struct page *page;
 	int error, scan;
+	int cache_count;
 
 	memfd_tag_pins(mapping);
 
@@ -107,8 +117,12 @@ static int memfd_wait_for_pins(struct address_space *mapping)
 				page = NULL;
 			}
 
-			if (page &&
-			    page_count(page) - page_mapcount(page) != 1) {
+			cache_count = 1;
+			if (page && PageTransHuge(page) && !PageHuge(page))
+				cache_count = HPAGE_PMD_NR;
+
+			if (page && cache_count !=
+			    page_count(page) - total_mapcount(page)) {
 				if (scan < LAST_SCAN)
 					goto continue_resched;