1 files changed, 215 insertions, 182 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 4919423cce76..b3e5e384e330 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -130,7 +130,11 @@ static inline unsigned char swap_count(unsigned char ent)
 /* Reclaim the swap entry if swap is getting full*/
 #define TTRS_FULL		0x4
 
-/* returns 1 if swap entry is freed */
+/*
+ * returns number of pages in the folio that backs the swap entry. If positive,
+ * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no
+ * folio was associated with the swap entry.
+ */
 static int __try_to_reclaim_swap(struct swap_info_struct *si,
 				 unsigned long offset, unsigned long flags)
 {
@@ -155,6 +159,7 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 			ret = folio_free_swap(folio);
 		folio_unlock(folio);
 	}
+	ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio);
 	folio_put(folio);
 	return ret;
 }
@@ -273,15 +278,15 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #ifdef CONFIG_THP_SWAP
 #define SWAPFILE_CLUSTER	HPAGE_PMD_NR
 
-#define swap_entry_size(size)	(size)
+#define swap_entry_order(order)	(order)
 #else
 #define SWAPFILE_CLUSTER	256
 
 /*
- * Define swap_entry_size() as constant to let compiler to optimize
+ * Define swap_entry_order() as constant to let compiler to optimize
  * out some code if !CONFIG_THP_SWAP
  */
-#define swap_entry_size(size)	1
+#define swap_entry_order(order)	0
 #endif
 #define LATENCY_LIMIT		256
 
@@ -343,18 +348,6 @@ static inline void cluster_set_null(struct swap_cluster_info *info)
 	info->data = 0;
 }
 
-static inline bool cluster_is_huge(struct swap_cluster_info *info)
-{
-	if (IS_ENABLED(CONFIG_THP_SWAP))
-		return info->flags & CLUSTER_FLAG_HUGE;
-	return false;
-}
-
-static inline void cluster_clear_huge(struct swap_cluster_info *info)
-{
-	info->flags &= ~CLUSTER_FLAG_HUGE;
-}
-
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
 						     unsigned long offset)
 {
@@ -558,10 +551,12 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
 
 /*
  * The cluster corresponding to page_nr will be used. The cluster will be
- * removed from free cluster list and its usage counter will be increased.
+ * removed from free cluster list and its usage counter will be increased by
+ * count.
  */
-static void inc_cluster_info_page(struct swap_info_struct *p,
-	struct swap_cluster_info *cluster_info, unsigned long page_nr)
+static void add_cluster_info_page(struct swap_info_struct *p,
+	struct swap_cluster_info *cluster_info, unsigned long page_nr,
+	unsigned long count)
 {
 	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
 
@@ -570,9 +565,19 @@ static void inc_cluster_info_page(struct swap_info_struct *p,
 	if (cluster_is_free(&cluster_info[idx]))
 		alloc_cluster(p, idx);
 
-	VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER);
+	VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
 	cluster_set_count(&cluster_info[idx],
-		cluster_count(&cluster_info[idx]) + 1);
+		cluster_count(&cluster_info[idx]) + count);
+}
+
+/*
+ * The cluster corresponding to page_nr will be used. The cluster will be
+ * removed from free cluster list and its usage counter will be increased by 1.
+ */
+static void inc_cluster_info_page(struct swap_info_struct *p,
+	struct swap_cluster_info *cluster_info, unsigned long page_nr)
+{
+	add_cluster_info_page(p, cluster_info, page_nr, 1);
 }
 
 /*
@@ -602,7 +607,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p,
  */
 static bool
 scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
-	unsigned long offset)
+	unsigned long offset, int order)
 {
 	struct percpu_cluster *percpu_cluster;
 	bool conflict;
@@ -616,27 +621,42 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
 		return false;
 
 	percpu_cluster = this_cpu_ptr(si->percpu_cluster);
-	cluster_set_null(&percpu_cluster->index);
+	percpu_cluster->next[order] = SWAP_NEXT_INVALID;
+	return true;
+}
+
+static inline bool swap_range_empty(char *swap_map, unsigned int start,
+				    unsigned int nr_pages)
+{
+	unsigned int i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (swap_map[start + i])
+			return false;
+	}
+
 	return true;
 }
 
 /*
- * Try to get a swap entry from current cpu's swap entry pool (a cluster). This
- * might involve allocating a new cluster for current CPU too.
+ * Try to get swap entries with specified order from current cpu's swap entry
+ * pool (a cluster). This might involve allocating a new cluster for current CPU
+ * too.
  */
 static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si,
-	unsigned long *offset, unsigned long *scan_base)
+	unsigned long *offset, unsigned long *scan_base, int order)
 {
+	unsigned int nr_pages = 1 << order;
 	struct percpu_cluster *cluster;
 	struct swap_cluster_info *ci;
-	unsigned long tmp, max;
+	unsigned int tmp, max;
 
 new_cluster:
 	cluster = this_cpu_ptr(si->percpu_cluster);
-	if (cluster_is_null(&cluster->index)) {
+	tmp = cluster->next[order];
+	if (tmp == SWAP_NEXT_INVALID) {
 		if (!cluster_list_empty(&si->free_clusters)) {
-			cluster->index = si->free_clusters.head;
-			cluster->next = cluster_next(&cluster->index) *
+			tmp = cluster_next(&si->free_clusters.head) *
 					SWAPFILE_CLUSTER;
 		} else if (!cluster_list_empty(&si->discard_clusters)) {
 			/*
@@ -654,27 +674,27 @@ new_cluster:
 
 	/*
 	 * Other CPUs can use our cluster if they can't find a free cluster,
-	 * check if there is still free entry in the cluster
+	 * check if there is still free entry in the cluster, maintaining
+	 * natural alignment.
 	 */
-	tmp = cluster->next;
-	max = min_t(unsigned long, si->max,
-		    (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER);
+	max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
 	if (tmp < max) {
 		ci = lock_cluster(si, tmp);
 		while (tmp < max) {
-			if (!si->swap_map[tmp])
+			if (swap_range_empty(si->swap_map, tmp, nr_pages))
 				break;
-			tmp++;
+			tmp += nr_pages;
 		}
 		unlock_cluster(ci);
 	}
 	if (tmp >= max) {
-		cluster_set_null(&cluster->index);
+		cluster->next[order] = SWAP_NEXT_INVALID;
 		goto new_cluster;
 	}
-	cluster->next = tmp + 1;
 	*offset = tmp;
 	*scan_base = tmp;
+	tmp += nr_pages;
+	cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
 	return true;
 }
 
@@ -804,13 +824,14 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si,
 
 static int scan_swap_map_slots(struct swap_info_struct *si,
 			       unsigned char usage, int nr,
-			       swp_entry_t slots[])
+			       swp_entry_t slots[], int order)
 {
 	struct swap_cluster_info *ci;
 	unsigned long offset;
 	unsigned long scan_base;
 	unsigned long last_in_cluster = 0;
 	int latency_ration = LATENCY_LIMIT;
+	unsigned int nr_pages = 1 << order;
 	int n_ret = 0;
 	bool scanned_many = false;
 
@@ -825,6 +846,25 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 	 * And we let swap pages go all over an SSD partition.  Hugh
 	 */
 
+	if (order > 0) {
+		/*
+		 * Should not even be attempting large allocations when huge
+		 * page swap is disabled.  Warn and fail the allocation.
+		 */
+		if (!IS_ENABLED(CONFIG_THP_SWAP) ||
+		    nr_pages > SWAPFILE_CLUSTER) {
+			VM_WARN_ON_ONCE(1);
+			return 0;
+		}
+
+		/*
+		 * Swapfile is not block device or not using clusters so unable
+		 * to allocate large entries.
+		 */
+		if (!(si->flags & SWP_BLKDEV) || !si->cluster_info)
+			return 0;
+	}
+
 	si->flags += SWP_SCANNING;
 	/*
 	 * Use percpu scan base for SSD to reduce lock contention on
@@ -839,8 +879,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 
 	/* SSD algorithm */
 	if (si->cluster_info) {
-		if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+		if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order)) {
+			if (order > 0)
+				goto no_page;
 			goto scan;
+		}
 	} else if (unlikely(!si->cluster_nr--)) {
 		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
 			si->cluster_nr = SWAPFILE_CLUSTER - 1;
@@ -859,7 +902,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
 
 		/* Locate the first empty (unaligned) cluster */
-		for (; last_in_cluster <= si->highest_bit; offset++) {
+		for (; last_in_cluster <= READ_ONCE(si->highest_bit); offset++) {
 			if (si->swap_map[offset])
 				last_in_cluster = offset + SWAPFILE_CLUSTER;
 			else if (offset == last_in_cluster) {
@@ -882,13 +925,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 
 checks:
 	if (si->cluster_info) {
-		while (scan_swap_map_ssd_cluster_conflict(si, offset)) {
+		while (scan_swap_map_ssd_cluster_conflict(si, offset, order)) {
 		/* take a break if we already got some slots */
 			if (n_ret)
 				goto done;
 			if (!scan_swap_map_try_ssd_cluster(si, &offset,
-							&scan_base))
+							&scan_base, order)) {
+				if (order > 0)
+					goto no_page;
 				goto scan;
+			}
 		}
 	}
 	if (!(si->flags & SWP_WRITEOK))
@@ -907,7 +953,7 @@ checks:
 		swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
 		spin_lock(&si->lock);
 		/* entry was freed successfully, try to use this again */
-		if (swap_was_freed)
+		if (swap_was_freed > 0)
 			goto checks;
 		goto scan; /* check next one */
 	}
@@ -919,11 +965,11 @@ checks:
 		else
 			goto done;
 	}
-	WRITE_ONCE(si->swap_map[offset], usage);
-	inc_cluster_info_page(si, si->cluster_info, offset);
+	memset(si->swap_map + offset, usage, nr_pages);
+	add_cluster_info_page(si, si->cluster_info, offset, nr_pages);
 	unlock_cluster(ci);
 
-	swap_range_alloc(si, offset, 1);
+	swap_range_alloc(si, offset, nr_pages);
 	slots[n_ret++] = swp_entry(si->type, offset);
 
 	/* got enough slots or reach max slots? */
@@ -944,8 +990,10 @@ checks:
 
 	/* try to get more slots in cluster */
 	if (si->cluster_info) {
-		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base))
+		if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base, order))
 			goto checks;
+		if (order > 0)
+			goto done;
 	} else if (si->cluster_nr && !si->swap_map[++offset]) {
 		/* non-ssd case, still more slots in cluster? */
 		--si->cluster_nr;
@@ -972,11 +1020,13 @@ checks:
 	}
 
 done:
-	set_cluster_next(si, offset + 1);
+	if (order == 0)
+		set_cluster_next(si, offset + 1);
 	si->flags -= SWP_SCANNING;
 	return n_ret;
 
 scan:
+	VM_WARN_ON(order > 0);
 	spin_unlock(&si->lock);
 	while (++offset <= READ_ONCE(si->highest_bit)) {
 		if (unlikely(--latency_ration < 0)) {
@@ -1005,38 +1055,6 @@ no_page:
 	return n_ret;
 }
 
-static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot)
-{
-	unsigned long idx;
-	struct swap_cluster_info *ci;
-	unsigned long offset;
-
-	/*
-	 * Should not even be attempting cluster allocations when huge
-	 * page swap is disabled.  Warn and fail the allocation.
-	 */
-	if (!IS_ENABLED(CONFIG_THP_SWAP)) {
-		VM_WARN_ON_ONCE(1);
-		return 0;
-	}
-
-	if (cluster_list_empty(&si->free_clusters))
-		return 0;
-
-	idx = cluster_list_first(&si->free_clusters);
-	offset = idx * SWAPFILE_CLUSTER;
-	ci = lock_cluster(si, offset);
-	alloc_cluster(si, idx);
-	cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE);
-
-	memset(si->swap_map + offset, SWAP_HAS_CACHE, SWAPFILE_CLUSTER);
-	unlock_cluster(ci);
-	swap_range_alloc(si, offset, SWAPFILE_CLUSTER);
-	*slot = swp_entry(si->type, offset);
-
-	return 1;
-}
-
 static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
 {
 	unsigned long offset = idx * SWAPFILE_CLUSTER;
@@ -1050,17 +1068,15 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
 	swap_range_free(si, offset, SWAPFILE_CLUSTER);
 }
 
-int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size)
+int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_order)
 {
-	unsigned long size = swap_entry_size(entry_size);
+	int order = swap_entry_order(entry_order);
+	unsigned long size = 1 << order;
 	struct swap_info_struct *si, *next;
 	long avail_pgs;
 	int n_ret = 0;
 	int node;
 
-	/* Only single cluster request supported */
-	WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER);
-
 	spin_lock(&swap_avail_lock);
 
 	avail_pgs = atomic_long_read(&nr_swap_pages) / size;
@@ -1096,14 +1112,10 @@ start_over:
 			spin_unlock(&si->lock);
 			goto nextsi;
 		}
-		if (size == SWAPFILE_CLUSTER) {
-			if (si->flags & SWP_BLKDEV)
-				n_ret = swap_alloc_cluster(si, swp_entries);
-		} else
-			n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
-						    n_goal, swp_entries);
+		n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE,
+					    n_goal, swp_entries, order);
 		spin_unlock(&si->lock);
-		if (n_ret || size == SWAPFILE_CLUSTER)
+		if (n_ret || size > 1)
 			goto check_out;
 		cond_resched();
 
@@ -1226,16 +1238,15 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p,
 
 /*
  * When we get a swap entry, if there aren't some other ways to
- * prevent swapoff, such as the folio in swap cache is locked, page
- * table lock is held, etc., the swap entry may become invalid because
- * of swapoff.  Then, we need to enclose all swap related functions
- * with get_swap_device() and put_swap_device(), unless the swap
- * functions call get/put_swap_device() by themselves.
+ * prevent swapoff, such as the folio in swap cache is locked, RCU
+ * reader side is locked, etc., the swap entry may become invalid
+ * because of swapoff.  Then, we need to enclose all swap related
+ * functions with get_swap_device() and put_swap_device(), unless the
+ * swap functions call get/put_swap_device() by themselves.
  *
- * Note that when only holding the PTL, swapoff might succeed immediately
- * after freeing a swap entry. Therefore, immediately after
- * __swap_entry_free(), the swap info might become stale and should not
- * be touched without a prior get_swap_device().
+ * RCU reader side lock (including any spinlock) is sufficient to
+ * prevent swapoff, because synchronize_rcu() is called in swapoff()
+ * before freeing data structures.
  *
  * Check whether swap entry is valid in the swap device.  If so,
  * return pointer to swap_info_struct, and keep the swap entry valid
@@ -1357,7 +1368,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 	unsigned char *map;
 	unsigned int i, free_entries = 0;
 	unsigned char val;
-	int size = swap_entry_size(folio_nr_pages(folio));
+	int size = 1 << swap_entry_order(folio_order(folio));
 
 	si = _swap_info_get(entry);
 	if (!si)
@@ -1365,7 +1376,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 
 	ci = lock_cluster_or_swap_info(si, offset);
 	if (size == SWAPFILE_CLUSTER) {
-		VM_BUG_ON(!cluster_is_huge(ci));
 		map = si->swap_map + offset;
 		for (i = 0; i < SWAPFILE_CLUSTER; i++) {
 			val = map[i];
@@ -1373,7 +1383,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 			if (val == SWAP_HAS_CACHE)
 				free_entries++;
 		}
-		cluster_clear_huge(ci);
 		if (free_entries == SWAPFILE_CLUSTER) {
 			unlock_cluster_or_swap_info(si, ci);
 			spin_lock(&si->lock);
@@ -1395,23 +1404,6 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 	unlock_cluster_or_swap_info(si, ci);
 }
 
-#ifdef CONFIG_THP_SWAP
-int split_swap_cluster(swp_entry_t entry)
-{
-	struct swap_info_struct *si;
-	struct swap_cluster_info *ci;
-	unsigned long offset = swp_offset(entry);
-
-	si = _swap_info_get(entry);
-	if (!si)
-		return -EBUSY;
-	ci = lock_cluster(si, offset);
-	cluster_clear_huge(ci);
-	unlock_cluster(ci);
-	return 0;
-}
-#endif
-
 static int swp_entry_cmp(const void *ent1, const void *ent2)
 {
 	const swp_entry_t *e1 = ent1, *e2 = ent2;
@@ -1519,22 +1511,23 @@ out:
 }
 
 static bool swap_page_trans_huge_swapped(struct swap_info_struct *si,
-					 swp_entry_t entry)
+					 swp_entry_t entry, int order)
 {
 	struct swap_cluster_info *ci;
 	unsigned char *map = si->swap_map;
+	unsigned int nr_pages = 1 << order;
 	unsigned long roffset = swp_offset(entry);
-	unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER);
+	unsigned long offset = round_down(roffset, nr_pages);
 	int i;
 	bool ret = false;
 
 	ci = lock_cluster_or_swap_info(si, offset);
-	if (!ci || !cluster_is_huge(ci)) {
+	if (!ci || nr_pages == 1) {
 		if (swap_count(map[roffset]))
 			ret = true;
 		goto unlock_out;
 	}
-	for (i = 0; i < SWAPFILE_CLUSTER; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		if (swap_count(map[offset + i])) {
 			ret = true;
 			break;
@@ -1556,7 +1549,7 @@ static bool folio_swapped(struct folio *folio)
 	if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio)))
 		return swap_swapcount(si, entry) != 0;
 
-	return swap_page_trans_huge_swapped(si, entry);
+	return swap_page_trans_huge_swapped(si, entry, folio_order(folio));
 }
 
 /**
@@ -1602,33 +1595,88 @@ bool folio_free_swap(struct folio *folio)
 	return true;
 }
 
-/*
- * Free the swap entry like above, but also try to
- * free the page cache entry if it is the last user.
+/**
+ * free_swap_and_cache_nr() - Release reference on range of swap entries and
+ *                            reclaim their cache if no more references remain.
+ * @entry: First entry of range.
+ * @nr: Number of entries in range.
+ *
+ * For each swap entry in the contiguous range, release a reference. If any swap
+ * entries become free, try to reclaim their underlying folios, if present. The
+ * offset range is defined by [entry.offset, entry.offset + nr).
  */
-int free_swap_and_cache(swp_entry_t entry)
+void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 {
-	struct swap_info_struct *p;
+	const unsigned long start_offset = swp_offset(entry);
+	const unsigned long end_offset = start_offset + nr;
+	unsigned int type = swp_type(entry);
+	struct swap_info_struct *si;
+	bool any_only_cache = false;
+	unsigned long offset;
 	unsigned char count;
 
 	if (non_swap_entry(entry))
-		return 1;
+		return;
 
-	p = get_swap_device(entry);
-	if (p) {
-		if (WARN_ON(data_race(!p->swap_map[swp_offset(entry)]))) {
-			put_swap_device(p);
-			return 0;
+	si = get_swap_device(entry);
+	if (!si)
+		return;
+
+	if (WARN_ON(end_offset > si->max))
+		goto out;
+
+	/*
+	 * First free all entries in the range.
+	 */
+	for (offset = start_offset; offset < end_offset; offset++) {
+		if (data_race(si->swap_map[offset])) {
+			count = __swap_entry_free(si, swp_entry(type, offset));
+			if (count == SWAP_HAS_CACHE)
+				any_only_cache = true;
+		} else {
+			WARN_ON_ONCE(1);
 		}
+	}
+
+	/*
+	 * Short-circuit the below loop if none of the entries had their
+	 * reference drop to zero.
+	 */
+	if (!any_only_cache)
+		goto out;
 
-		count = __swap_entry_free(p, entry);
-		if (count == SWAP_HAS_CACHE &&
-		    !swap_page_trans_huge_swapped(p, entry))
-			__try_to_reclaim_swap(p, swp_offset(entry),
+	/*
+	 * 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_free() 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.
+	 */
+	for (offset = start_offset; offset < end_offset; offset += nr) {
+		nr = 1;
+		if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) {
+			/*
+			 * Folios are always naturally aligned in swap so
+			 * advance forward to the next boundary. Zero means no
+			 * folio was found for the swap entry, so advance by 1
+			 * in this case. Negative value means folio was found
+			 * but could not be reclaimed. Here we can still advance
+			 * to the next boundary.
+			 */
+			nr = __try_to_reclaim_swap(si, offset,
 					      TTRS_UNMAPPED | TTRS_FULL);
-		put_swap_device(p);
+			if (nr == 0)
+				nr = 1;
+			else if (nr < 0)
+				nr = -nr;
+			nr = ALIGN(offset + 1, nr) - offset;
+		}
 	}
-	return p != NULL;
+
+out:
+	put_swap_device(si);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1643,7 +1691,7 @@ swp_entry_t get_swap_page_of_type(int type)
 
 	/* This is called for allocating swap entry, not cache */
 	spin_lock(&si->lock);
-	if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry))
+	if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry, 0))
 		atomic_long_dec(&nr_swap_pages);
 	spin_unlock(&si->lock);
 fail:
@@ -1806,7 +1854,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	 * when reading from swap. This metadata may be indexed by swap entry
 	 * so this must be called before swap_free().
 	 */
-	arch_swap_restore(entry, folio);
+	arch_swap_restore(folio_swap(entry, folio), folio);
 
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
@@ -2396,13 +2444,17 @@ static void reinsert_swap_info(struct swap_info_struct *p)
 	spin_unlock(&swap_lock);
 }
 
+static bool __has_usable_swap(void)
+{
+	return !plist_head_empty(&swap_active_head);
+}
+
 bool has_usable_swap(void)
 {
-	bool ret = true;
+	bool ret;
 
 	spin_lock(&swap_lock);
-	if (plist_head_empty(&swap_active_head))
-		ret = false;
+	ret = __has_usable_swap();
 	spin_unlock(&swap_lock);
 	return ret;
 }
@@ -2417,7 +2469,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct inode *inode;
 	struct filename *pathname;
 	int err, found = 0;
-	unsigned int old_block_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -2495,10 +2546,11 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	/*
 	 * Wait for swap operations protected by get/put_swap_device()
-	 * to complete.
-	 *
-	 * We need synchronize_rcu() here to protect the accessing to
-	 * the swap cache data structure.
+	 * to complete.  Because of synchronize_rcu() here, all swap
+	 * operations protected by RCU reader side lock (including any
+	 * spinlock) will be waited too.  This makes it easy to
+	 * prevent folio_test_swapcache() and the following swap cache
+	 * operations from racing with swapoff.
 	 */
 	percpu_ref_kill(&p->users);
 	synchronize_rcu();
@@ -2529,7 +2581,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	}
 
 	swap_file = p->swap_file;
-	old_block_size = p->old_block_size;
 	p->swap_file = NULL;
 	p->max = 0;
 	swap_map = p->swap_map;
@@ -2552,11 +2603,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	exit_swap_address_space(p->type);
 
 	inode = mapping->host;
-	if (p->bdev_file) {
-		set_blocksize(p->bdev, old_block_size);
-		fput(p->bdev_file);
-		p->bdev_file = NULL;
-	}
 
 	inode_lock(inode);
 	inode->i_flags &= ~S_SWAPFILE;
@@ -2782,21 +2828,8 @@ static struct swap_info_struct *alloc_swap_info(void)
 
 static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 {
-	int error;
-
 	if (S_ISBLK(inode->i_mode)) {
-		p->bdev_file = bdev_file_open_by_dev(inode->i_rdev,
-				BLK_OPEN_READ | BLK_OPEN_WRITE, p, NULL);
-		if (IS_ERR(p->bdev_file)) {
-			error = PTR_ERR(p->bdev_file);
-			p->bdev_file = NULL;
-			return error;
-		}
-		p->bdev = file_bdev(p->bdev_file);
-		p->old_block_size = block_size(p->bdev);
-		error = set_blocksize(p->bdev, PAGE_SIZE);
-		if (error < 0)
-			return error;
+		p->bdev = I_BDEV(inode);
 		/*
 		 * Zoned block devices contain zones that have a sequential
 		 * write only restriction.  Hence zoned block devices are not
@@ -3037,7 +3070,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		name = NULL;
 		goto bad_swap;
 	}
-	swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0);
+	swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0);
 	if (IS_ERR(swap_file)) {
 		error = PTR_ERR(swap_file);
 		swap_file = NULL;
@@ -3097,7 +3130,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
 	if (p->bdev && bdev_nonrot(p->bdev)) {
-		int cpu;
+		int cpu, i;
 		unsigned long ci, nr_cluster;
 
 		p->flags |= SWP_SOLIDSTATE;
@@ -3133,8 +3166,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		}
 		for_each_possible_cpu(cpu) {
 			struct percpu_cluster *cluster;
+
 			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
-			cluster_set_null(&cluster->index);
+			for (i = 0; i < SWAP_NR_ORDERS; i++)
+				cluster->next[i] = SWAP_NEXT_INVALID;
 		}
 	} else {
 		atomic_inc(&nr_rotate_swap);
@@ -3234,11 +3269,6 @@ bad_swap:
 	p->percpu_cluster = NULL;
 	free_percpu(p->cluster_next_cpu);
 	p->cluster_next_cpu = NULL;
-	if (p->bdev_file) {
-		set_blocksize(p->bdev, p->old_block_size);
-		fput(p->bdev_file);
-		p->bdev_file = NULL;
-	}
 	inode = NULL;
 	destroy_swap_extents(p);
 	swap_cgroup_swapoff(p->type);
@@ -3659,6 +3689,9 @@ void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
 	if (!(gfp & __GFP_IO))
 		return;
 
+	if (!__has_usable_swap())
+		return;
+
 	if (!blk_cgroup_congested())
 		return;