From: Kairui Song <kasong@tencent.com>

Some useful comments were dropped in commit b56a2d8af914 ('mm: rid
swapoff of quadratic complexity'), add them back.

Signed-off-by: Kairui Song <kasong@tencent.com>
---
 mm/swapfile.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3eec686484ef..f7271504aa0a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1880,6 +1880,17 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				folio = page_folio(page);
 		}
 		if (!folio) {
+			/*
+			 * The entry could have been freed, and will not
+			 * be reused since swapoff() already disabled
+			 * allocation from here, or alloc_page() failed.
+			 *
+			 * We don't hold lock here, so the swap entry could be
+			 * SWAP_MAP_BAD (when the cluster is discarding).
+			 * Instead of fail out, We can just skip the swap
+			 * entry because swapoff will wait for discarding
+			 * finish anyway.
+			 */
 			swp_count = READ_ONCE(si->swap_map[offset]);
 			if (swp_count == 0 || swp_count == SWAP_MAP_BAD)
 				continue;
-- 
2.43.0