diff --git a/include/linux/swap.h b/include/linux/swap.h
index bea0c0f1f640552e399ae08e48da79046e413176..33396153afc0a38413105e8b571a3ca806d74503 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -255,22 +255,24 @@ enum {
  * free clusters are organized into a list. We fetch an entry from the list to
  * get a free cluster.
  *
- * The data field stores next cluster if the cluster is free or cluster usage
- * counter otherwise. The flags field determines if a cluster is free. This is
- * protected by swap_info_struct.lock.
+ * The flags field determines if a cluster is free. This is
+ * protected by cluster lock.
  */
 struct swap_cluster_info {
 	spinlock_t lock;	/*
 				 * Protect swap_cluster_info fields
-				 * and swap_info_struct->swap_map
-				 * elements correspond to the swap
-				 * cluster
+				 * other than list, and swap_info_struct->swap_map
+				 * elements corresponding to the swap cluster.
 				 */
-	unsigned int data:24;
-	unsigned int flags:8;
+	u16 count;
+	u8 flags;
+	u8 order;
+	struct list_head list;
 };
 #define CLUSTER_FLAG_FREE 1 /* This cluster is free */
-#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
+#define CLUSTER_FLAG_NONFULL 2 /* This cluster is on nonfull list */
+#define CLUSTER_FLAG_FRAG 4 /* This cluster is on nonfull list */
+#define CLUSTER_FLAG_FULL 8 /* This cluster is on full list */
 
 /*
  * The first page in the swap file is the swap header, which is always marked
@@ -295,11 +297,6 @@ struct percpu_cluster {
 	unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */
 };
 
-struct swap_cluster_list {
-	struct swap_cluster_info head;
-	struct swap_cluster_info tail;
-};
-
 /*
  * The in-memory structure used to track swap areas.
  */
@@ -312,7 +309,13 @@ struct swap_info_struct {
 	unsigned int	max;		/* extent of the swap_map */
 	unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
 	struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
-	struct swap_cluster_list free_clusters; /* free clusters list */
+	struct list_head free_clusters; /* free clusters list */
+	struct list_head full_clusters; /* full clusters list */
+	struct list_head nonfull_clusters[SWAP_NR_ORDERS];
+					/* list of cluster that contains at least one free slot */
+	struct list_head frag_clusters[SWAP_NR_ORDERS];
+					/* list of cluster that are fragmented or contented */
+	unsigned int frag_cluster_nr[SWAP_NR_ORDERS];
 	unsigned int lowest_bit;	/* index of first free in swap_map */
 	unsigned int highest_bit;	/* index of last free in swap_map */
 	unsigned int pages;		/* total of usable pages of swap */
@@ -345,7 +348,8 @@ struct swap_info_struct {
 					 * list.
 					 */
 	struct work_struct discard_work; /* discard worker */
-	struct swap_cluster_list discard_clusters; /* discard clusters list */
+	struct work_struct reclaim_work; /* reclaim worker */
+	struct list_head discard_clusters; /* discard clusters list */
 	KABI_RESERVE(1)
 	KABI_RESERVE(2)
 	KABI_RESERVE(3)
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 2a60ce39cfde19ac90cebb9b16aaba8b6a99c4ab..a13d2d2d91311659d18a4fbbeaaf7ca45bdf32b9 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -12,7 +12,7 @@ extern atomic_t zswap_stored_pages;
 
 bool zswap_store(struct folio *folio);
 bool zswap_load(struct folio *folio);
-void zswap_invalidate(int type, pgoff_t offset);
+void zswap_invalidate(swp_entry_t swp);
 void zswap_swapon(int type);
 void zswap_swapoff(int type);
 
@@ -28,7 +28,7 @@ static inline bool zswap_load(struct folio *folio)
 	return false;
 }
 
-static inline void zswap_invalidate(int type, pgoff_t offset) {}
+static inline void zswap_invalidate(swp_entry_t swp) {}
 static inline void zswap_swapon(int type) {}
 static inline void zswap_swapoff(int type) {}
 
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index 7af3b93d4c8c8a15bcfbf3adce5270830c2ab9d9..5579eed7065f8353df89b6c6b1f48b563b998700 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -34,6 +34,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mutex.h>
 #include <linux/mm.h>
+#include <linux/zswap.h>
 
 static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots);
 #ifdef CONFIG_MEMCG_SWAP_QOS
@@ -394,6 +395,9 @@ void free_swap_slot(swp_entry_t entry)
 {
 	struct swap_slots_cache *cache;
 
+	/* Large folio swap slot is not covered. */
+	zswap_invalidate(entry);
+
 	cache = raw_cpu_ptr(&swp_slots);
 	if (likely(use_swap_slot_cache && cache->slots_ret)) {
 		spin_lock_irq(&cache->free_lock);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3af5b6ebb2412735e386f293eae789188a0350e6..3b48159820f2a1f7237ba5e6f4a56c8ea1266df8 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -52,6 +52,15 @@
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
 static void free_swap_count_continuations(struct swap_info_struct *);
+static void swap_entry_range_free(struct swap_info_struct *si, swp_entry_t entry,
+				  unsigned int nr_pages);
+static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
+			     unsigned int nr_entries);
+static bool folio_swapcache_freeable(struct folio *folio);
+static struct swap_cluster_info *lock_cluster_or_swap_info(
+		struct swap_info_struct *si, unsigned long offset);
+static void unlock_cluster_or_swap_info(struct swap_info_struct *si,
+					struct swap_cluster_info *ci);
 
 static DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
@@ -126,8 +135,25 @@ static inline unsigned char swap_count(unsigned char ent)
  * corresponding page
  */
 #define TTRS_UNMAPPED		0x2
-/* Reclaim the swap entry if swap is getting full*/
+/* Reclaim the swap entry if swap is getting full */
 #define TTRS_FULL		0x4
+/* Reclaim directly, bypass the slot cache and don't touch device lock */
+#define TTRS_DIRECT		0x8
+
+static bool swap_is_has_cache(struct swap_info_struct *si,
+			      unsigned long offset, int nr_pages)
+{
+	unsigned char *map = si->swap_map + offset;
+	unsigned char *map_end = map + nr_pages;
+
+	do {
+		VM_BUG_ON(!(*map & SWAP_HAS_CACHE));
+		if (*map != SWAP_HAS_CACHE)
+			return false;
+	} while (++map < map_end);
+
+	return true;
+}
 
 /*
  * returns number of pages in the folio that backs the swap entry. If positive,
@@ -138,12 +164,19 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 				 unsigned long offset, unsigned long flags)
 {
 	swp_entry_t entry = swp_entry(si->type, offset);
+	struct address_space *address_space = swap_address_space(entry);
+	struct swap_cluster_info *ci;
 	struct folio *folio;
-	int ret = 0;
+	int ret, nr_pages;
+	bool need_reclaim;
 
-	folio = filemap_get_folio(swap_address_space(entry), offset);
+	folio = filemap_get_folio(address_space, offset);
 	if (IS_ERR(folio))
 		return 0;
+
+	nr_pages = folio_nr_pages(folio);
+	ret = -nr_pages;
+
 	/*
 	 * When this function is called from scan_swap_map_slots() and it's
 	 * called by vmscan.c at reclaiming folios. So we hold a folio lock
@@ -151,14 +184,54 @@ static int __try_to_reclaim_swap(struct swap_info_struct *si,
 	 * case and you should use folio_free_swap() with explicit folio_lock()
 	 * in usual operations.
 	 */
-	if (folio_trylock(folio)) {
-		if ((flags & TTRS_ANYWAY) ||
-		    ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) ||
-		    ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio)))
-			ret = folio_free_swap(folio);
-		folio_unlock(folio);
+	if (!folio_trylock(folio))
+		goto out;
+
+	/* offset could point to the middle of a large folio */
+	entry = folio->swap;
+	offset = swp_offset(entry);
+
+	need_reclaim = ((flags & TTRS_ANYWAY) ||
+			((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) ||
+			((flags & TTRS_FULL) && mem_cgroup_swap_full(folio)));
+	if (!need_reclaim || !folio_swapcache_freeable(folio))
+		goto out_unlock;
+
+	/*
+	 * It's safe to delete the folio from swap cache only if the folio's
+	 * swap_map is HAS_CACHE only, which means the slots have no page table
+	 * reference or pending writeback, and can't be allocated to others.
+	 */
+	ci = lock_cluster_or_swap_info(si, offset);
+	need_reclaim = swap_is_has_cache(si, offset, nr_pages);
+	unlock_cluster_or_swap_info(si, ci);
+	if (!need_reclaim)
+		goto out_unlock;
+
+	if (!(flags & TTRS_DIRECT)) {
+		/* Free through slot cache */
+		delete_from_swap_cache(folio);
+		folio_set_dirty(folio);
+		ret = nr_pages;
+		goto out_unlock;
 	}
-	ret = ret ? folio_nr_pages(folio) : -folio_nr_pages(folio);
+
+	xa_lock_irq(&address_space->i_pages);
+	__delete_from_swap_cache(folio, entry, NULL);
+	xa_unlock_irq(&address_space->i_pages);
+	folio_ref_sub(folio, nr_pages);
+	folio_set_dirty(folio);
+
+	spin_lock(&si->lock);
+	/* Only sinple page folio can be backed by zswap */
+	if (nr_pages == 1)
+		zswap_invalidate(entry);
+	swap_entry_range_free(si, entry, nr_pages);
+	spin_unlock(&si->lock);
+	ret = nr_pages;
+out_unlock:
+	folio_unlock(folio);
+out:
 	folio_put(folio);
 	return ret;
 }
@@ -289,62 +362,21 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 #endif
 #define LATENCY_LIMIT		256
 
-static inline void cluster_set_flag(struct swap_cluster_info *info,
-	unsigned int flag)
-{
-	info->flags = flag;
-}
-
-static inline unsigned int cluster_count(struct swap_cluster_info *info)
-{
-	return info->data;
-}
-
-static inline void cluster_set_count(struct swap_cluster_info *info,
-				     unsigned int c)
-{
-	info->data = c;
-}
-
-static inline void cluster_set_count_flag(struct swap_cluster_info *info,
-					 unsigned int c, unsigned int f)
-{
-	info->flags = f;
-	info->data = c;
-}
-
-static inline unsigned int cluster_next(struct swap_cluster_info *info)
-{
-	return info->data;
-}
-
-static inline void cluster_set_next(struct swap_cluster_info *info,
-				    unsigned int n)
-{
-	info->data = n;
-}
-
-static inline void cluster_set_next_flag(struct swap_cluster_info *info,
-					 unsigned int n, unsigned int f)
-{
-	info->flags = f;
-	info->data = n;
-}
-
 static inline bool cluster_is_free(struct swap_cluster_info *info)
 {
 	return info->flags & CLUSTER_FLAG_FREE;
 }
 
-static inline bool cluster_is_null(struct swap_cluster_info *info)
+static inline unsigned int cluster_index(struct swap_info_struct *si,
+					 struct swap_cluster_info *ci)
 {
-	return info->flags & CLUSTER_FLAG_NEXT_NULL;
+	return ci - si->cluster_info;
 }
 
-static inline void cluster_set_null(struct swap_cluster_info *info)
+static inline unsigned int cluster_offset(struct swap_info_struct *si,
+					  struct swap_cluster_info *ci)
 {
-	info->flags = CLUSTER_FLAG_NEXT_NULL;
-	info->data = 0;
+	return cluster_index(si, ci) * SWAPFILE_CLUSTER;
 }
 
 static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si,
@@ -393,65 +425,11 @@ static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si,
 		spin_unlock(&si->lock);
 }
 
-static inline bool cluster_list_empty(struct swap_cluster_list *list)
-{
-	return cluster_is_null(&list->head);
-}
-
-static inline unsigned int cluster_list_first(struct swap_cluster_list *list)
-{
-	return cluster_next(&list->head);
-}
-
-static void cluster_list_init(struct swap_cluster_list *list)
-{
-	cluster_set_null(&list->head);
-	cluster_set_null(&list->tail);
-}
-
-static void cluster_list_add_tail(struct swap_cluster_list *list,
-				  struct swap_cluster_info *ci,
-				  unsigned int idx)
-{
-	if (cluster_list_empty(list)) {
-		cluster_set_next_flag(&list->head, idx, 0);
-		cluster_set_next_flag(&list->tail, idx, 0);
-	} else {
-		struct swap_cluster_info *ci_tail;
-		unsigned int tail = cluster_next(&list->tail);
-
-		/*
-		 * Nested cluster lock, but both cluster locks are
-		 * only acquired when we held swap_info_struct->lock
-		 */
-		ci_tail = ci + tail;
-		spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING);
-		cluster_set_next(ci_tail, idx);
-		spin_unlock(&ci_tail->lock);
-		cluster_set_next_flag(&list->tail, idx, 0);
-	}
-}
-
-static unsigned int cluster_list_del_first(struct swap_cluster_list *list,
-					   struct swap_cluster_info *ci)
-{
-	unsigned int idx;
-
-	idx = cluster_next(&list->head);
-	if (cluster_next(&list->tail) == idx) {
-		cluster_set_null(&list->head);
-		cluster_set_null(&list->tail);
-	} else
-		cluster_set_next_flag(&list->head,
-				      cluster_next(&ci[idx]), 0);
-
-	return idx;
-}
-
 /* Add a cluster to discard list and schedule it to do discard */
 static void swap_cluster_schedule_discard(struct swap_info_struct *si,
-		unsigned int idx)
+		struct swap_cluster_info *ci)
 {
+	unsigned int idx = cluster_index(si, ci);
 	/*
 	 * If scan_swap_map_slots() can't find a free cluster, it will check
 	 * si->swap_map directly. To make sure the discarding cluster isn't
@@ -461,17 +439,23 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si,
 	memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 			SWAP_MAP_BAD, SWAPFILE_CLUSTER);
 
-	cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx);
-
+	VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
+	list_move_tail(&ci->list, &si->discard_clusters);
+	ci->flags = 0;
 	schedule_work(&si->discard_work);
 }
 
-static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
+static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-	struct swap_cluster_info *ci = si->cluster_info;
+	lockdep_assert_held(&si->lock);
+	lockdep_assert_held(&ci->lock);
 
-	cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE);
-	cluster_list_add_tail(&si->free_clusters, ci, idx);
+	if (ci->flags)
+		list_move_tail(&ci->list, &si->free_clusters);
+	else
+		list_add_tail(&ci->list, &si->free_clusters);
+	ci->flags = CLUSTER_FLAG_FREE;
+	ci->order = 0;
 }
 
 /*
@@ -480,24 +464,24 @@ static void __free_cluster(struct swap_info_struct *si, unsigned long idx)
 */
 static void swap_do_scheduled_discard(struct swap_info_struct *si)
 {
-	struct swap_cluster_info *info, *ci;
+	struct swap_cluster_info *ci;
 	unsigned int idx;
 
-	info = si->cluster_info;
-
-	while (!cluster_list_empty(&si->discard_clusters)) {
-		idx = cluster_list_del_first(&si->discard_clusters, info);
+	while (!list_empty(&si->discard_clusters)) {
+		ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list);
+		list_del(&ci->list);
+		idx = cluster_index(si, ci);
 		spin_unlock(&si->lock);
 
 		discard_swap_cluster(si, idx * SWAPFILE_CLUSTER,
 				SWAPFILE_CLUSTER);
 
 		spin_lock(&si->lock);
-		ci = lock_cluster(si, idx * SWAPFILE_CLUSTER);
-		__free_cluster(si, idx);
+		spin_lock(&ci->lock);
+		__free_cluster(si, ci);
 		memset(si->swap_map + idx * SWAPFILE_CLUSTER,
 				0, SWAPFILE_CLUSTER);
-		unlock_cluster(ci);
+		spin_unlock(&ci->lock);
 	}
 }
 
@@ -520,20 +504,15 @@ static void swap_users_ref_free(struct percpu_ref *ref)
 	complete(&si->comp);
 }
 
-static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
+static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci)
 {
-	struct swap_cluster_info *ci = si->cluster_info;
+	VM_BUG_ON(ci->count != 0);
+	lockdep_assert_held(&si->lock);
+	lockdep_assert_held(&ci->lock);
 
-	VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx);
-	cluster_list_del_first(&si->free_clusters, ci);
-	cluster_set_count_flag(ci + idx, 0, 0);
-}
-
-static void free_cluster(struct swap_info_struct *si, unsigned long idx)
-{
-	struct swap_cluster_info *ci = si->cluster_info + idx;
+	if (ci->flags & CLUSTER_FLAG_FRAG)
+		si->frag_cluster_nr[ci->order]--;
 
-	VM_BUG_ON(cluster_count(ci) != 0);
 	/*
 	 * If the swap is discardable, prepare discard the cluster
 	 * instead of free it immediately. The cluster will be freed
@@ -541,160 +520,374 @@ static void free_cluster(struct swap_info_struct *si, unsigned long idx)
 	 */
 	if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) ==
 	    (SWP_WRITEOK | SWP_PAGE_DISCARD)) {
-		swap_cluster_schedule_discard(si, idx);
+		swap_cluster_schedule_discard(si, ci);
 		return;
 	}
 
-	__free_cluster(si, idx);
+	__free_cluster(si, ci);
 }
 
 /*
- * 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
- * count.
+ * The cluster corresponding to page_nr will be used. The cluster will not be
+ * added to free cluster list and its usage counter will be increased by 1.
+ * Only used for initialization.
  */
-static void add_cluster_info_page(struct swap_info_struct *p,
-	struct swap_cluster_info *cluster_info, unsigned long page_nr,
-	unsigned long count)
+static void inc_cluster_info_page(struct swap_info_struct *p,
+	struct swap_cluster_info *cluster_info, unsigned long page_nr)
 {
 	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
+	struct swap_cluster_info *ci;
 
 	if (!cluster_info)
 		return;
-	if (cluster_is_free(&cluster_info[idx]))
-		alloc_cluster(p, idx);
 
-	VM_BUG_ON(cluster_count(&cluster_info[idx]) + count > SWAPFILE_CLUSTER);
-	cluster_set_count(&cluster_info[idx],
-		cluster_count(&cluster_info[idx]) + count);
-}
+	ci = cluster_info + idx;
+	ci->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);
+	VM_BUG_ON(ci->count > SWAPFILE_CLUSTER);
+	VM_BUG_ON(ci->flags);
 }
 
 /*
- * The cluster corresponding to page_nr decreases one usage. If the usage
- * counter becomes 0, which means no page in the cluster is in using, we can
- * optionally discard the cluster and add it to free cluster list.
+ * The cluster ci decreases @nr_pages usage. If the usage counter becomes 0,
+ * which means no page in the cluster is in use, we can optionally discard
+ * the cluster and add it to free cluster list.
  */
 static void dec_cluster_info_page(struct swap_info_struct *p,
-	struct swap_cluster_info *cluster_info, unsigned long page_nr)
+				  struct swap_cluster_info *ci, int nr_pages)
 {
-	unsigned long idx = page_nr / SWAPFILE_CLUSTER;
-
-	if (!cluster_info)
+	if (!p->cluster_info)
 		return;
 
-	VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0);
-	cluster_set_count(&cluster_info[idx],
-		cluster_count(&cluster_info[idx]) - 1);
+	VM_BUG_ON(ci->count < nr_pages);
+	VM_BUG_ON(cluster_is_free(ci));
+	lockdep_assert_held(&p->lock);
+	lockdep_assert_held(&ci->lock);
+	ci->count -= nr_pages;
+
+	if (!ci->count) {
+		free_cluster(p, ci);
+		return;
+	}
 
-	if (cluster_count(&cluster_info[idx]) == 0)
-		free_cluster(p, idx);
+	if (!(ci->flags & CLUSTER_FLAG_NONFULL)) {
+		VM_BUG_ON(ci->flags & CLUSTER_FLAG_FREE);
+		if (ci->flags & CLUSTER_FLAG_FRAG)
+			p->frag_cluster_nr[ci->order]--;
+		list_move_tail(&ci->list, &p->nonfull_clusters[ci->order]);
+		ci->flags = CLUSTER_FLAG_NONFULL;
+	}
 }
 
-/*
- * It's possible scan_swap_map_slots() uses a free cluster in the middle of free
- * cluster list. Avoiding such abuse to avoid list corruption.
- */
-static bool
-scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si,
-	unsigned long offset, int order)
+static bool cluster_reclaim_range(struct swap_info_struct *si,
+				  struct swap_cluster_info *ci,
+				  unsigned long start, unsigned long end)
 {
-	struct percpu_cluster *percpu_cluster;
-	bool conflict;
+	unsigned char *map = si->swap_map;
+	unsigned long offset;
 
-	offset /= SWAPFILE_CLUSTER;
-	conflict = !cluster_list_empty(&si->free_clusters) &&
-		offset != cluster_list_first(&si->free_clusters) &&
-		cluster_is_free(&si->cluster_info[offset]);
+	spin_unlock(&ci->lock);
+	spin_unlock(&si->lock);
 
-	if (!conflict)
-		return false;
+	for (offset = start; offset < end; offset++) {
+		switch (READ_ONCE(map[offset])) {
+		case 0:
+			continue;
+		case SWAP_HAS_CACHE:
+			if (__try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT) > 0)
+				continue;
+			goto out;
+		default:
+			goto out;
+		}
+	}
+out:
+	spin_lock(&si->lock);
+	spin_lock(&ci->lock);
+
+	/*
+	 * Recheck the range no matter reclaim succeeded or not, the slot
+	 * could have been be freed while we are not holding the lock.
+	 */
+	for (offset = start; offset < end; offset++)
+		if (READ_ONCE(map[offset]))
+			return false;
 
-	percpu_cluster = this_cpu_ptr(si->percpu_cluster);
-	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)
+static bool cluster_scan_range(struct swap_info_struct *si,
+			       struct swap_cluster_info *ci,
+			       unsigned long start, unsigned int nr_pages)
 {
-	unsigned int i;
+	unsigned long offset, end = start + nr_pages;
+	unsigned char *map = si->swap_map;
+	bool need_reclaim = false;
 
-	for (i = 0; i < nr_pages; i++) {
-		if (swap_map[start + i])
+	for (offset = start; offset < end; offset++) {
+		switch (READ_ONCE(map[offset])) {
+		case 0:
+			continue;
+		case SWAP_HAS_CACHE:
+			if (!vm_swap_full())
+				return false;
+			need_reclaim = true;
+			continue;
+		default:
 			return false;
+		}
 	}
 
+	if (need_reclaim)
+		return cluster_reclaim_range(si, ci, start, end);
+
 	return true;
 }
 
+static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci,
+				unsigned int start, unsigned char usage,
+				unsigned int order)
+{
+	unsigned int nr_pages = 1 << order;
+
+	if (!(si->flags & SWP_WRITEOK))
+		return false;
+
+	if (cluster_is_free(ci)) {
+		if (nr_pages < SWAPFILE_CLUSTER) {
+			list_move_tail(&ci->list, &si->nonfull_clusters[order]);
+			ci->flags = CLUSTER_FLAG_NONFULL;
+		}
+		ci->order = order;
+	}
+
+	memset(si->swap_map + start, usage, nr_pages);
+	swap_range_alloc(si, start, nr_pages);
+	ci->count += nr_pages;
+
+	if (ci->count == SWAPFILE_CLUSTER) {
+		VM_BUG_ON(!(ci->flags &
+			  (CLUSTER_FLAG_FREE | CLUSTER_FLAG_NONFULL | CLUSTER_FLAG_FRAG)));
+		if (ci->flags & CLUSTER_FLAG_FRAG)
+			si->frag_cluster_nr[ci->order]--;
+		list_move_tail(&ci->list, &si->full_clusters);
+		ci->flags = CLUSTER_FLAG_FULL;
+	}
+
+	return true;
+}
+
+static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, unsigned long offset,
+					    unsigned int *foundp, unsigned int order,
+					    unsigned char usage)
+{
+	unsigned long start = offset & ~(SWAPFILE_CLUSTER - 1);
+	unsigned long end = min(start + SWAPFILE_CLUSTER, si->max);
+	unsigned int nr_pages = 1 << order;
+	struct swap_cluster_info *ci;
+
+	if (end < nr_pages)
+		return SWAP_NEXT_INVALID;
+	end -= nr_pages;
+
+	ci = lock_cluster(si, offset);
+	if (ci->count + nr_pages > SWAPFILE_CLUSTER) {
+		offset = SWAP_NEXT_INVALID;
+		goto done;
+	}
+
+	while (offset <= end) {
+		if (cluster_scan_range(si, ci, offset, nr_pages)) {
+			if (!cluster_alloc_range(si, ci, offset, usage, order)) {
+				offset = SWAP_NEXT_INVALID;
+				goto done;
+			}
+			*foundp = offset;
+			if (ci->count == SWAPFILE_CLUSTER) {
+				offset = SWAP_NEXT_INVALID;
+				goto done;
+			}
+			offset += nr_pages;
+			break;
+		}
+		offset += nr_pages;
+	}
+	if (offset > end)
+		offset = SWAP_NEXT_INVALID;
+done:
+	unlock_cluster(ci);
+	return offset;
+}
+
+/* Return true if reclaimed a whole cluster */
+static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
+{
+	long to_scan = 1;
+	unsigned long offset, end;
+	struct swap_cluster_info *ci;
+	unsigned char *map = si->swap_map;
+	int nr_reclaim;
+
+	if (force)
+		to_scan = si->inuse_pages / SWAPFILE_CLUSTER;
+
+	while (!list_empty(&si->full_clusters)) {
+		ci = list_first_entry(&si->full_clusters, struct swap_cluster_info, list);
+		list_move_tail(&ci->list, &si->full_clusters);
+		offset = cluster_offset(si, ci);
+		end = min(si->max, offset + SWAPFILE_CLUSTER);
+		to_scan--;
+
+		spin_unlock(&si->lock);
+		while (offset < end) {
+			if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
+				nr_reclaim = __try_to_reclaim_swap(si, offset,
+								   TTRS_ANYWAY | TTRS_DIRECT);
+				if (nr_reclaim) {
+					offset += abs(nr_reclaim);
+					continue;
+				}
+			}
+			offset++;
+		}
+		spin_lock(&si->lock);
+
+		if (to_scan <= 0)
+			break;
+	}
+}
+
+static void swap_reclaim_work(struct work_struct *work)
+{
+	struct swap_info_struct *si;
+
+	si = container_of(work, struct swap_info_struct, reclaim_work);
+
+	spin_lock(&si->lock);
+	swap_reclaim_full_clusters(si, true);
+	spin_unlock(&si->lock);
+}
+
 /*
  * 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, int order)
+static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order,
+					      unsigned char usage)
 {
-	unsigned int nr_pages = 1 << order;
 	struct percpu_cluster *cluster;
 	struct swap_cluster_info *ci;
-	unsigned int tmp, max;
+	unsigned int offset, found = 0;
 
 new_cluster:
+	lockdep_assert_held(&si->lock);
 	cluster = this_cpu_ptr(si->percpu_cluster);
-	tmp = cluster->next[order];
-	if (tmp == SWAP_NEXT_INVALID) {
-		if (!cluster_list_empty(&si->free_clusters)) {
-			tmp = cluster_next(&si->free_clusters.head) *
-					SWAPFILE_CLUSTER;
-		} else if (!cluster_list_empty(&si->discard_clusters)) {
-			/*
-			 * we don't have free cluster but have some clusters in
-			 * discarding, do discard now and reclaim them, then
-			 * reread cluster_next_cpu since we dropped si->lock
-			 */
-			swap_do_scheduled_discard(si);
-			*scan_base = this_cpu_read(*si->cluster_next_cpu);
-			*offset = *scan_base;
-			goto new_cluster;
-		} else
-			return false;
+	offset = cluster->next[order];
+	if (offset) {
+		offset = alloc_swap_scan_cluster(si, offset, &found, order, usage);
+		if (found)
+			goto done;
 	}
 
-	/*
-	 * Other CPUs can use our cluster if they can't find a free cluster,
-	 * check if there is still free entry in the cluster, maintaining
-	 * natural alignment.
-	 */
-	max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER));
-	if (tmp < max) {
-		ci = lock_cluster(si, tmp);
-		while (tmp < max) {
-			if (swap_range_empty(si->swap_map, tmp, nr_pages))
+	if (!list_empty(&si->free_clusters)) {
+		ci = list_first_entry(&si->free_clusters, struct swap_cluster_info, list);
+		offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci), &found, order, usage);
+		/*
+		 * Either we didn't touch the cluster due to swapoff,
+		 * or the allocation must success.
+		 */
+		VM_BUG_ON((si->flags & SWP_WRITEOK) && !found);
+		goto done;
+	}
+
+	/* Try reclaim from full clusters if free clusters list is drained */
+	if (vm_swap_full())
+		swap_reclaim_full_clusters(si, false);
+
+	if (order < PMD_ORDER) {
+		unsigned int frags = 0;
+
+		while (!list_empty(&si->nonfull_clusters[order])) {
+			ci = list_first_entry(&si->nonfull_clusters[order],
+					      struct swap_cluster_info, list);
+			list_move_tail(&ci->list, &si->frag_clusters[order]);
+			ci->flags = CLUSTER_FLAG_FRAG;
+			si->frag_cluster_nr[order]++;
+			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+							 &found, order, usage);
+			frags++;
+			if (found)
 				break;
-			tmp += nr_pages;
 		}
-		unlock_cluster(ci);
+
+		if (!found) {
+			/*
+			 * Nonfull clusters are moved to frag tail if we reached
+			 * here, count them too, don't over scan the frag list.
+			 */
+			while (frags < si->frag_cluster_nr[order]) {
+				ci = list_first_entry(&si->frag_clusters[order],
+						      struct swap_cluster_info, list);
+				/*
+				 * Rotate the frag list to iterate, they were all failing
+				 * high order allocation or moved here due to per-CPU usage,
+				 * this help keeping usable cluster ahead.
+				 */
+				list_move_tail(&ci->list, &si->frag_clusters[order]);
+				offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+								 &found, order, usage);
+				frags++;
+				if (found)
+					break;
+			}
+		}
 	}
-	if (tmp >= max) {
-		cluster->next[order] = SWAP_NEXT_INVALID;
+
+	if (found)
+		goto done;
+
+	if (!list_empty(&si->discard_clusters)) {
+		/*
+		 * we don't have free cluster but have some clusters in
+		 * discarding, do discard now and reclaim them, then
+		 * reread cluster_next_cpu since we dropped si->lock
+		 */
+		swap_do_scheduled_discard(si);
 		goto new_cluster;
 	}
-	*offset = tmp;
-	*scan_base = tmp;
-	tmp += nr_pages;
-	cluster->next[order] = tmp < max ? tmp : SWAP_NEXT_INVALID;
-	return true;
+
+	if (order)
+		goto done;
+
+	/* Order 0 stealing from higher order */
+	for (int o = 1; o < SWAP_NR_ORDERS; o++) {
+		/*
+		 * Clusters here have at least one usable slots and can't fail order 0
+		 * allocation, but reclaim may drop si->lock and race with another user.
+		 */
+		while (!list_empty(&si->frag_clusters[o])) {
+			ci = list_first_entry(&si->frag_clusters[o],
+					      struct swap_cluster_info, list);
+			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+							 &found, 0, usage);
+			if (found)
+				goto done;
+		}
+
+		while (!list_empty(&si->nonfull_clusters[o])) {
+			ci = list_first_entry(&si->nonfull_clusters[o],
+					      struct swap_cluster_info, list);
+			offset = alloc_swap_scan_cluster(si, cluster_offset(si, ci),
+							 &found, 0, usage);
+			if (found)
+				goto done;
+		}
+	}
+
+done:
+	cluster->next[order] = offset;
+	return found;
 }
 
 static void __del_from_avail_list(struct swap_info_struct *p)
@@ -727,6 +920,9 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
 		del_from_avail_list(si);
+
+		if (si->cluster_info && vm_swap_full())
+			schedule_work(&si->reclaim_work);
 	}
 }
 
@@ -765,7 +961,6 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 		swap_slot_free_notify = NULL;
 	while (offset <= end) {
 		arch_swap_invalidate_page(si->type, offset);
-		zswap_invalidate(si->type, offset);
 		if (swap_slot_free_notify)
 			swap_slot_free_notify(si->bdev, offset);
 		offset++;
@@ -816,11 +1011,33 @@ static bool swap_offset_available_and_locked(struct swap_info_struct *si,
 	return false;
 }
 
+static int cluster_alloc_swap(struct swap_info_struct *si,
+			     unsigned char usage, int nr,
+			     swp_entry_t slots[], int order)
+{
+	int n_ret = 0;
+
+	VM_BUG_ON(!si->cluster_info);
+
+	si->flags += SWP_SCANNING;
+
+	while (n_ret < nr) {
+		unsigned long offset = cluster_alloc_swap_entry(si, order, usage);
+
+		if (!offset)
+			break;
+		slots[n_ret++] = swp_entry(si->type, offset);
+	}
+
+	si->flags -= SWP_SCANNING;
+
+	return n_ret;
+}
+
 static int scan_swap_map_slots(struct swap_info_struct *si,
 			       unsigned char usage, int nr,
 			       swp_entry_t slots[], int order)
 {
-	struct swap_cluster_info *ci;
 	unsigned long offset;
 	unsigned long scan_base;
 	unsigned long last_in_cluster = 0;
@@ -859,26 +1076,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 			return 0;
 	}
 
+	if (si->cluster_info)
+		return cluster_alloc_swap(si, usage, nr, slots, order);
+
 	si->flags += SWP_SCANNING;
-	/*
-	 * Use percpu scan base for SSD to reduce lock contention on
-	 * cluster and swap cache.  For HDD, sequential access is more
-	 * important.
-	 */
-	if (si->flags & SWP_SOLIDSTATE)
-		scan_base = this_cpu_read(*si->cluster_next_cpu);
-	else
-		scan_base = si->cluster_next;
+
+	/* For HDD, sequential access is more important. */
+	scan_base = si->cluster_next;
 	offset = scan_base;
 
-	/* SSD algorithm */
-	if (si->cluster_info) {
-		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 (unlikely(!si->cluster_nr--)) {
 		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
 			si->cluster_nr = SWAPFILE_CLUSTER - 1;
 			goto checks;
@@ -889,8 +1096,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 		/*
 		 * If seek is expensive, start searching for new cluster from
 		 * start of partition, to minimize the span of allocated swap.
-		 * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info
-		 * case, just handled by scan_swap_map_try_ssd_cluster() above.
 		 */
 		scan_base = offset = si->lowest_bit;
 		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
@@ -918,19 +1123,6 @@ 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, 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, order)) {
-				if (order > 0)
-					goto no_page;
-				goto scan;
-			}
-		}
-	}
 	if (!(si->flags & SWP_WRITEOK))
 		goto no_page;
 	if (!si->highest_bit)
@@ -938,13 +1130,11 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 	if (offset > si->highest_bit)
 		scan_base = offset = si->lowest_bit;
 
-	ci = lock_cluster(si, offset);
 	/* reuse swap entry of cache-only swap if not busy. */
 	if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
 		int swap_was_freed;
-		unlock_cluster(ci);
 		spin_unlock(&si->lock);
-		swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY);
+		swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY | TTRS_DIRECT);
 		spin_lock(&si->lock);
 		/* entry was freed successfully, try to use this again */
 		if (swap_was_freed > 0)
@@ -953,15 +1143,12 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 	}
 
 	if (si->swap_map[offset]) {
-		unlock_cluster(ci);
 		if (!n_ret)
 			goto scan;
 		else
 			goto done;
 	}
 	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, nr_pages);
 	slots[n_ret++] = swp_entry(si->type, offset);
@@ -982,13 +1169,7 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 		latency_ration = LATENCY_LIMIT;
 	}
 
-	/* try to get more slots in cluster */
-	if (si->cluster_info) {
-		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]) {
+	if (si->cluster_nr && !si->swap_map[++offset]) {
 		/* non-ssd case, still more slots in cluster? */
 		--si->cluster_nr;
 		goto checks;
@@ -1049,19 +1230,6 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
 	return n_ret;
 }
 
-static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx)
-{
-	unsigned long offset = idx * SWAPFILE_CLUSTER;
-	struct swap_cluster_info *ci;
-
-	ci = lock_cluster(si, offset);
-	memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER);
-	cluster_set_count_flag(ci, 0, 0);
-	free_cluster(si, idx);
-	unlock_cluster(ci);
-	swap_range_free(si, offset, SWAPFILE_CLUSTER);
-}
-
 #ifdef CONFIG_MEMCG_SWAP_QOS
 int write_swapfile_for_memcg(struct address_space *mapping, int *swap_type)
 {
@@ -1409,21 +1577,28 @@ static unsigned char __swap_entry_free(struct swap_info_struct *p,
 	return usage;
 }
 
-static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry)
+/*
+ * Drop the last HAS_CACHE flag of swap entries, caller have to
+ * ensure all entries belong to the same cgroup.
+ */
+static void swap_entry_range_free(struct swap_info_struct *p, swp_entry_t entry,
+				  unsigned int nr_pages)
 {
-	struct swap_cluster_info *ci;
 	unsigned long offset = swp_offset(entry);
-	unsigned char count;
+	unsigned char *map = p->swap_map + offset;
+	unsigned char *map_end = map + nr_pages;
+	struct swap_cluster_info *ci;
 
 	ci = lock_cluster(p, offset);
-	count = p->swap_map[offset];
-	VM_BUG_ON(count != SWAP_HAS_CACHE);
-	p->swap_map[offset] = 0;
-	dec_cluster_info_page(p, p->cluster_info, offset);
+	do {
+		VM_BUG_ON(*map != SWAP_HAS_CACHE);
+		*map = 0;
+	} while (++map < map_end);
+	dec_cluster_info_page(p, ci, nr_pages);
 	unlock_cluster(ci);
 
-	mem_cgroup_uncharge_swap(entry, 1);
-	swap_range_free(p, offset, 1);
+	mem_cgroup_uncharge_swap(entry, nr_pages);
+	swap_range_free(p, offset, nr_pages);
 }
 
 static void cluster_swap_free_nr(struct swap_info_struct *sis,
@@ -1484,12 +1659,8 @@ void swap_free_nr(swp_entry_t entry, int nr_pages)
 void put_swap_folio(struct folio *folio, swp_entry_t entry)
 {
 	unsigned long offset = swp_offset(entry);
-	unsigned long idx = offset / SWAPFILE_CLUSTER;
 	struct swap_cluster_info *ci;
 	struct swap_info_struct *si;
-	unsigned char *map;
-	unsigned int i, free_entries = 0;
-	unsigned char val;
 	int size = 1 << swap_entry_order(folio_order(folio));
 
 	si = _swap_info_get(entry);
@@ -1497,24 +1668,14 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 		return;
 
 	ci = lock_cluster_or_swap_info(si, offset);
-	if (size == SWAPFILE_CLUSTER) {
-		map = si->swap_map + offset;
-		for (i = 0; i < SWAPFILE_CLUSTER; i++) {
-			val = map[i];
-			VM_BUG_ON(!(val & SWAP_HAS_CACHE));
-			if (val == SWAP_HAS_CACHE)
-				free_entries++;
-		}
-		if (free_entries == SWAPFILE_CLUSTER) {
-			unlock_cluster_or_swap_info(si, ci);
-			spin_lock(&si->lock);
-			mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER);
-			swap_free_cluster(si, idx);
-			spin_unlock(&si->lock);
-			return;
-		}
+	if (size > 1 && swap_is_has_cache(si, offset, size)) {
+		unlock_cluster_or_swap_info(si, ci);
+		spin_lock(&si->lock);
+		swap_entry_range_free(si, entry, size);
+		spin_unlock(&si->lock);
+		return;
 	}
-	for (i = 0; i < size; i++, entry.val++) {
+	for (int i = 0; i < size; i++, entry.val++) {
 		if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) {
 			unlock_cluster_or_swap_info(si, ci);
 			free_swap_slot(entry);
@@ -1554,7 +1715,7 @@ void swapcache_free_entries(swp_entry_t *entries, int n)
 	for (i = 0; i < n; ++i) {
 		p = swap_info_get_cont(entries[i], prev);
 		if (p)
-			swap_entry_free(p, entries[i]);
+			swap_entry_range_free(p, entries[i], 1);
 		prev = p;
 	}
 	if (p)
@@ -1674,16 +1835,7 @@ static bool folio_swapped(struct folio *folio)
 	return swap_page_trans_huge_swapped(si, entry, folio_order(folio));
 }
 
-/**
- * folio_free_swap() - Free the swap space used for this folio.
- * @folio: The folio to remove.
- *
- * If swap is getting full, or if there are no more mappings of this folio,
- * then call folio_free_swap to free its swap space.
- *
- * Return: true if we were able to release the swap space.
- */
-bool folio_free_swap(struct folio *folio)
+static bool folio_swapcache_freeable(struct folio *folio)
 {
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
@@ -1691,8 +1843,6 @@ bool folio_free_swap(struct folio *folio)
 		return false;
 	if (folio_test_writeback(folio))
 		return false;
-	if (folio_swapped(folio))
-		return false;
 
 	/*
 	 * Once hibernation has begun to create its image of memory,
@@ -1712,6 +1862,25 @@ bool folio_free_swap(struct folio *folio)
 	if (pm_suspended_storage())
 		return false;
 
+	return true;
+}
+
+/**
+ * folio_free_swap() - Free the swap space used for this folio.
+ * @folio: The folio to remove.
+ *
+ * If swap is getting full, or if there are no more mappings of this folio,
+ * then call folio_free_swap to free its swap space.
+ *
+ * Return: true if we were able to release the swap space.
+ */
+bool folio_free_swap(struct folio *folio)
+{
+	if (!folio_swapcache_freeable(folio))
+		return false;
+	if (folio_swapped(folio))
+		return false;
+
 	delete_from_swap_cache(folio);
 	folio_set_dirty(folio);
 	return true;
@@ -1788,7 +1957,7 @@ void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 			 * to the next boundary.
 			 */
 			nr = __try_to_reclaim_swap(si, offset,
-					      TTRS_UNMAPPED | TTRS_FULL);
+						   TTRS_UNMAPPED | TTRS_FULL);
 			if (nr == 0)
 				nr = 1;
 			else if (nr < 0)
@@ -2686,6 +2855,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	wait_for_completion(&p->comp);
 
 	flush_work(&p->discard_work);
+	flush_work(&p->reclaim_work);
 
 	destroy_swap_extents(p);
 	if (p->flags & SWP_CONTINUED)
@@ -3114,8 +3284,15 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 
 	nr_good_pages = maxpages - 1;	/* omit header page */
 
-	cluster_list_init(&p->free_clusters);
-	cluster_list_init(&p->discard_clusters);
+	INIT_LIST_HEAD(&p->free_clusters);
+	INIT_LIST_HEAD(&p->full_clusters);
+	INIT_LIST_HEAD(&p->discard_clusters);
+
+	for (i = 0; i < SWAP_NR_ORDERS; i++) {
+		INIT_LIST_HEAD(&p->nonfull_clusters[i]);
+		INIT_LIST_HEAD(&p->frag_clusters[i]);
+		p->frag_cluster_nr[i] = 0;
+	}
 
 	for (i = 0; i < swap_header->info.nr_badpages; i++) {
 		unsigned int page_nr = swap_header->info.badpages[i];
@@ -3158,7 +3335,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	if (!cluster_info)
 		return nr_extents;
 
-
 	/*
 	 * Reduce false cache line sharing between cluster_info and
 	 * sharing same address space.
@@ -3166,14 +3342,18 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	for (k = 0; k < SWAP_CLUSTER_COLS; k++) {
 		j = (k + col) % SWAP_CLUSTER_COLS;
 		for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) {
+			struct swap_cluster_info *ci;
 			idx = i * SWAP_CLUSTER_COLS + j;
+			ci = cluster_info + idx;
 			if (idx >= nr_clusters)
 				continue;
-			if (cluster_count(&cluster_info[idx]))
+			if (ci->count) {
+				ci->flags = CLUSTER_FLAG_NONFULL;
+				list_add_tail(&ci->list, &p->nonfull_clusters[0]);
 				continue;
-			cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE);
-			cluster_list_add_tail(&p->free_clusters, cluster_info,
-					      idx);
+			}
+			ci->flags = CLUSTER_FLAG_FREE;
+			list_add_tail(&ci->list, &p->free_clusters);
 		}
 	}
 	return nr_extents;
@@ -3212,6 +3392,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		return PTR_ERR(p);
 
 	INIT_WORK(&p->discard_work, swap_discard_work);
+	INIT_WORK(&p->reclaim_work, swap_reclaim_work);
 
 	name = getname(specialfile);
 	if (IS_ERR(name)) {
diff --git a/mm/zswap.c b/mm/zswap.c
index 69681b9173fdcbf9f90967e21b5159760a16c601..5acda5b906bc43bcdc993dcdb9702e48307da0fa 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1482,9 +1482,10 @@ bool zswap_load(struct folio *folio)
 	return ret;
 }
 
-void zswap_invalidate(int type, pgoff_t offset)
+void zswap_invalidate(swp_entry_t swp)
 {
-	struct zswap_tree *tree = zswap_trees[type];
+	pgoff_t offset = swp_offset(swp);
+	struct zswap_tree *tree = zswap_trees[swp_type(swp)];
 	struct zswap_entry *entry;
 
 	/* find */