diff --git a/mm/swapfile.c b/mm/swapfile.c
index 668684dc9efa..4f4fc74239d6 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1463,25 +1463,10 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry)
 	return NULL;
 }
 
-static unsigned char swap_entry_put(struct swap_info_struct *si,
-				    swp_entry_t entry)
-{
-	struct swap_cluster_info *ci;
-	unsigned long offset = swp_offset(entry);
-	unsigned char usage;
-
-	ci = lock_cluster(si, offset);
-	usage = swap_entry_put_locked(si, ci, entry, 1);
-	unlock_cluster(ci);
-
-	return usage;
-}
-
-static bool swap_entries_put_nr(struct swap_info_struct *si,
-				swp_entry_t entry, int nr)
+static bool swap_entries_put_map(struct swap_info_struct *si,
+				 swp_entry_t entry, int nr)
 {
 	unsigned long offset = swp_offset(entry);
-	unsigned int type = swp_type(entry);
 	struct swap_cluster_info *ci;
 	bool has_cache = false;
 	unsigned char count;
@@ -1492,14 +1477,10 @@ static bool swap_entries_put_nr(struct swap_info_struct *si,
 	count = swap_count(data_race(si->swap_map[offset]));
 	if (count != 1 && count != SWAP_MAP_SHMEM)
 		goto fallback;
-	/* cross into another cluster */
-	if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER)
-		goto fallback;
 
 	ci = lock_cluster(si, offset);
 	if (!swap_is_last_map(si, offset, nr, &has_cache)) {
-		unlock_cluster(ci);
-		goto fallback;
+		goto locked_fallback;
 	}
 	if (!has_cache)
 		swap_entries_free(si, ci, entry, nr);
@@ -1511,15 +1492,34 @@ static bool swap_entries_put_nr(struct swap_info_struct *si,
 	return has_cache;
 
 fallback:
-	for (i = 0; i < nr; i++) {
-		if (data_race(si->swap_map[offset + i])) {
-			count = swap_entry_put(si, swp_entry(type, offset + i));
-			if (count == SWAP_HAS_CACHE)
-				has_cache = true;
-		} else {
-			WARN_ON_ONCE(1);
-		}
+	ci = lock_cluster(si, offset);
+locked_fallback:
+	for (i = 0; i < nr; i++, entry.val++) {
+		count = swap_entry_put_locked(si, ci, entry, 1);
+		if (count == SWAP_HAS_CACHE)
+			has_cache = true;
 	}
+	unlock_cluster(ci);
+	return has_cache;
+
+}
+
+static bool swap_entries_put_map_nr(struct swap_info_struct *si,
+				    swp_entry_t entry, int nr)
+{
+	int cluster_nr, cluster_rest;
+	unsigned long offset = swp_offset(entry);
+	bool has_cache = false;
+
+	cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER;
+	while (nr) {
+		cluster_nr = min(nr, cluster_rest);
+		has_cache |= swap_entries_put_map(si, entry, cluster_nr);
+		cluster_rest = SWAPFILE_CLUSTER;
+		nr -= cluster_nr;
+		entry.val += cluster_nr;
+	}
+
 	return has_cache;
 }
 
@@ -1818,7 +1818,7 @@ void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 	/*
 	 * First free all entries in the range.
 	 */
-	any_only_cache = swap_entries_put_nr(si, entry, nr);
+	any_only_cache = swap_entries_put_map_nr(si, entry, nr);
 
 	/*
 	 * Short-circuit the below loop if none of the entries had their
@@ -1828,13 +1828,7 @@ void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 		goto out;
 
 	/*
-	 * Now go back over the range trying to reclaim the swap cache. This is
-	 * more efficient for large folios because we will only try to reclaim
-	 * the swap once per folio in the common case. If we do
-	 * swap_entry_put() and __try_to_reclaim_swap() in the same loop, the
-	 * latter will get a reference and lock the folio for every individual
-	 * page but will only succeed once the swap slot for every subpage is
-	 * zero.
+	 * Now go back over the range trying to reclaim the swap cache.
 	 */
 	for (offset = start_offset; offset < end_offset; offset += nr) {
 		nr = 1;