[PATCH] mm/khugepaged: Fix race with folio splitting in hpage_collapse_scan_file()

[Shivank Garg <shivankg@amd.com>]

folio_mapcount() checks folio_test_large() before proceeding to
folio_large_mapcount(), but there exists a race window where a folio
could be split between these checks which triggered the
VM_WARN_ON_FOLIO(!folio_test_large(folio), folio) in
folio_large_mapcount().

Take a temporary folio reference in hpage_collapse_scan_file() to prevent
races with concurrent folio splitting/freeing. This prevent potential
incorrect large folio detection.

Reported-by: syzbot+2b99589e33edbe9475ca@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6828470d.a70a0220.38f255.000c.GAE@google.com
Fixes: 05c5323b2a34 ("mm: track mapcount of large folios in single value")
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Shivank Garg <shivankg@amd.com>
---
 mm/khugepaged.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index cc945c6ab3bd..6e8902f9d88c 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2295,6 +2295,17 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			continue;
 		}
 
+		if (!folio_try_get(folio)) {
+			xas_reset(&xas);
+			continue;
+		}
+
+		if (unlikely(folio != xas_reload(&xas))) {
+			folio_put(folio);
+			xas_reset(&xas);
+			continue;
+		}
+
 		if (folio_order(folio) == HPAGE_PMD_ORDER &&
 		    folio->index == start) {
 			/* Maybe PMD-mapped */
@@ -2305,23 +2316,27 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 			 * it's safe to skip LRU and refcount checks before
 			 * returning.
 			 */
+			folio_put(folio);
 			break;
 		}
 
 		node = folio_nid(folio);
 		if (hpage_collapse_scan_abort(node, cc)) {
 			result = SCAN_SCAN_ABORT;
+			folio_put(folio);
 			break;
 		}
 		cc->node_load[node]++;
 
 		if (!folio_test_lru(folio)) {
 			result = SCAN_PAGE_LRU;
+			folio_put(folio);
 			break;
 		}
 
 		if (!is_refcount_suitable(folio)) {
 			result = SCAN_PAGE_COUNT;
+			folio_put(folio);
 			break;
 		}
 
@@ -2333,6 +2348,7 @@ static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr,
 		 */
 
 		present += folio_nr_pages(folio);
+		folio_put(folio);
 
 		if (need_resched()) {
 			xas_pause(&xas);
-- 
2.34.1