1 files changed, 280 insertions, 260 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 76378bc257e3..c767d71c43d7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
 	if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
 		nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
 			zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
-
+	/*
+	 * If there are no reclaimable file-backed or anonymous pages,
+	 * ensure zones with sufficient free pages are not skipped.
+	 * This prevents zones like DMA32 from being ignored in reclaim
+	 * scenarios where they can still help alleviate memory pressure.
+	 */
+	if (nr == 0)
+		nr = zone_page_state_snapshot(zone, NR_FREE_PAGES);
 	return nr;
 }
 
@@ -855,6 +862,31 @@ enum folio_references {
 	FOLIOREF_ACTIVATE,
 };
 
+#ifdef CONFIG_LRU_GEN
+/*
+ * Only used on a mapped folio in the eviction (rmap walk) path, where promotion
+ * needs to be done by taking the folio off the LRU list and then adding it back
+ * with PG_active set. In contrast, the aging (page table walk) path uses
+ * folio_update_gen().
+ */
+static bool lru_gen_set_refs(struct folio *folio)
+{
+	/* see the comment on LRU_REFS_FLAGS */
+	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		return false;
+	}
+
+	set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_workingset));
+	return true;
+}
+#else
+static bool lru_gen_set_refs(struct folio *folio)
+{
+	return false;
+}
+#endif /* CONFIG_LRU_GEN */
+
 static enum folio_references folio_check_references(struct folio *folio,
 						  struct scan_control *sc)
 {
@@ -863,7 +895,6 @@ static enum folio_references folio_check_references(struct folio *folio,
 
 	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
 					   &vm_flags);
-	referenced_folio = folio_test_clear_referenced(folio);
 
 	/*
 	 * The supposedly reclaimable folio was found to be in a VM_LOCKED vma.
@@ -881,6 +912,15 @@ static enum folio_references folio_check_references(struct folio *folio,
 	if (referenced_ptes == -1)
 		return FOLIOREF_KEEP;
 
+	if (lru_gen_enabled()) {
+		if (!referenced_ptes)
+			return FOLIOREF_RECLAIM;
+
+		return lru_gen_set_refs(folio) ? FOLIOREF_ACTIVATE : FOLIOREF_KEEP;
+	}
+
+	referenced_folio = folio_test_clear_referenced(folio);
+
 	if (referenced_ptes) {
 		/*
 		 * All mapped folios start out with page table
@@ -1046,7 +1086,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 	struct folio_batch free_folios;
 	LIST_HEAD(ret_folios);
 	LIST_HEAD(demote_folios);
-	unsigned int nr_reclaimed = 0;
+	unsigned int nr_reclaimed = 0, nr_demoted = 0;
 	unsigned int pgactivate = 0;
 	bool do_demote_pass;
 	struct swap_iocb *plug = NULL;
@@ -1085,11 +1125,6 @@ retry:
 		if (!sc->may_unmap && folio_mapped(folio))
 			goto keep_locked;
 
-		/* folio_update_gen() tried to promote this page? */
-		if (lru_gen_enabled() && !ignore_references &&
-		    folio_mapped(folio) && folio_test_referenced(folio))
-			goto keep_locked;
-
 		/*
 		 * The number of dirty pages determines if a node is marked
 		 * reclaim_congested. kswapd will stall and start writing
@@ -1515,8 +1550,9 @@ keep:
 	/* 'folio_list' is always empty here */
 
 	/* Migrate folios selected for demotion */
-	stat->nr_demoted = demote_folio_list(&demote_folios, pgdat);
-	nr_reclaimed += stat->nr_demoted;
+	nr_demoted = demote_folio_list(&demote_folios, pgdat);
+	nr_reclaimed += nr_demoted;
+	stat->nr_demoted += nr_demoted;
 	/* Folios that could not be demoted are still in @demote_folios */
 	if (!list_empty(&demote_folios)) {
 		/* Folios which weren't demoted go back on @folio_list */
@@ -1657,6 +1693,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
 	unsigned long scan, total_scan, nr_pages;
+	unsigned long max_nr_skipped = 0;
 	LIST_HEAD(folios_skipped);
 
 	total_scan = 0;
@@ -1671,9 +1708,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
 		nr_pages = folio_nr_pages(folio);
 		total_scan += nr_pages;
 
-		if (folio_zonenum(folio) > sc->reclaim_idx) {
+		/* Using max_nr_skipped to prevent hard LOCKUP*/
+		if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED &&
+		    (folio_zonenum(folio) > sc->reclaim_idx)) {
 			nr_skipped[folio_zonenum(folio)] += nr_pages;
 			move_to = &folios_skipped;
+			max_nr_skipped++;
 			goto move;
 		}
 
@@ -2612,11 +2652,17 @@ static bool should_clear_pmd_young(void)
 		READ_ONCE((lruvec)->lrugen.min_seq[LRU_GEN_FILE]),	\
 	}
 
+#define evictable_min_seq(min_seq, swappiness)				\
+	min((min_seq)[!(swappiness)], (min_seq)[(swappiness) <= MAX_SWAPPINESS])
+
 #define for_each_gen_type_zone(gen, type, zone)				\
 	for ((gen) = 0; (gen) < MAX_NR_GENS; (gen)++)			\
 		for ((type) = 0; (type) < ANON_AND_FILE; (type)++)	\
 			for ((zone) = 0; (zone) < MAX_NR_ZONES; (zone)++)
 
+#define for_each_evictable_type(type, swappiness)			\
+	for ((type) = !(swappiness); (type) <= ((swappiness) <= MAX_SWAPPINESS); (type)++)
+
 #define get_memcg_gen(seq)	((seq) % MEMCG_NR_GENS)
 #define get_memcg_bin(bin)	((bin) % MEMCG_NR_BINS)
 
@@ -2662,10 +2708,16 @@ static int get_nr_gens(struct lruvec *lruvec, int type)
 
 static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
 {
-	/* see the comment on lru_gen_folio */
-	return get_nr_gens(lruvec, LRU_GEN_FILE) >= MIN_NR_GENS &&
-	       get_nr_gens(lruvec, LRU_GEN_FILE) <= get_nr_gens(lruvec, LRU_GEN_ANON) &&
-	       get_nr_gens(lruvec, LRU_GEN_ANON) <= MAX_NR_GENS;
+	int type;
+
+	for (type = 0; type < ANON_AND_FILE; type++) {
+		int n = get_nr_gens(lruvec, type);
+
+		if (n < MIN_NR_GENS || n > MAX_NR_GENS)
+			return false;
+	}
+
+	return true;
 }
 
 /******************************************************************************
@@ -3066,16 +3118,20 @@ struct ctrl_pos {
 static void read_ctrl_pos(struct lruvec *lruvec, int type, int tier, int gain,
 			  struct ctrl_pos *pos)
 {
+	int i;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
-	pos->refaulted = lrugen->avg_refaulted[type][tier] +
-			 atomic_long_read(&lrugen->refaulted[hist][type][tier]);
-	pos->total = lrugen->avg_total[type][tier] +
-		     atomic_long_read(&lrugen->evicted[hist][type][tier]);
-	if (tier)
-		pos->total += lrugen->protected[hist][type][tier - 1];
 	pos->gain = gain;
+	pos->refaulted = pos->total = 0;
+
+	for (i = tier % MAX_NR_TIERS; i <= min(tier, MAX_NR_TIERS - 1); i++) {
+		pos->refaulted += lrugen->avg_refaulted[type][i] +
+				  atomic_long_read(&lrugen->refaulted[hist][type][i]);
+		pos->total += lrugen->avg_total[type][i] +
+			      lrugen->protected[hist][type][i] +
+			      atomic_long_read(&lrugen->evicted[hist][type][i]);
+	}
 }
 
 static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
@@ -3101,17 +3157,15 @@ static void reset_ctrl_pos(struct lruvec *lruvec, int type, bool carryover)
 			WRITE_ONCE(lrugen->avg_refaulted[type][tier], sum / 2);
 
 			sum = lrugen->avg_total[type][tier] +
+			      lrugen->protected[hist][type][tier] +
 			      atomic_long_read(&lrugen->evicted[hist][type][tier]);
-			if (tier)
-				sum += lrugen->protected[hist][type][tier - 1];
 			WRITE_ONCE(lrugen->avg_total[type][tier], sum / 2);
 		}
 
 		if (clear) {
 			atomic_long_set(&lrugen->refaulted[hist][type][tier], 0);
 			atomic_long_set(&lrugen->evicted[hist][type][tier], 0);
-			if (tier)
-				WRITE_ONCE(lrugen->protected[hist][type][tier - 1], 0);
+			WRITE_ONCE(lrugen->protected[hist][type][tier], 0);
 		}
 	}
 }
@@ -3138,16 +3192,19 @@ static int folio_update_gen(struct folio *folio, int gen)
 
 	VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);
 
+	/* see the comment on LRU_REFS_FLAGS */
+	if (!folio_test_referenced(folio) && !folio_test_workingset(folio)) {
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, BIT(PG_referenced));
+		return -1;
+	}
+
 	do {
 		/* lru_gen_del_folio() has isolated this page? */
-		if (!(old_flags & LRU_GEN_MASK)) {
-			/* for shrink_folio_list() */
-			new_flags = old_flags | BIT(PG_referenced);
-			continue;
-		}
+		if (!(old_flags & LRU_GEN_MASK))
+			return -1;
 
-		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
-		new_flags |= (gen + 1UL) << LRU_GEN_PGOFF;
+		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
+		new_flags |= ((gen + 1UL) << LRU_GEN_PGOFF) | BIT(PG_workingset);
 	} while (!try_cmpxchg(&folio->flags, &old_flags, new_flags));
 
 	return ((old_flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
@@ -3171,7 +3228,7 @@ static int folio_inc_gen(struct lruvec *lruvec, struct folio *folio, bool reclai
 
 		new_gen = (old_gen + 1) % MAX_NR_GENS;
 
-		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_MASK | LRU_REFS_FLAGS);
+		new_flags = old_flags & ~(LRU_GEN_MASK | LRU_REFS_FLAGS);
 		new_flags |= (new_gen + 1UL) << LRU_GEN_PGOFF;
 		/* for folio_end_writeback() */
 		if (reclaiming)
@@ -3246,7 +3303,7 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
 		return true;
 
 	if (vma_is_anonymous(vma))
-		return !walk->can_swap;
+		return !walk->swappiness;
 
 	if (WARN_ON_ONCE(!vma->vm_file || !vma->vm_file->f_mapping))
 		return true;
@@ -3256,7 +3313,10 @@ static int should_skip_vma(unsigned long start, unsigned long end, struct mm_wal
 		return true;
 
 	if (shmem_mapping(mapping))
-		return !walk->can_swap;
+		return !walk->swappiness;
+
+	if (walk->swappiness > MAX_SWAPPINESS)
+		return true;
 
 	/* to exclude special mappings like dax, etc. */
 	return !mapping->a_ops->read_folio;
@@ -3344,19 +3404,17 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 }
 
 static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
-				   struct pglist_data *pgdat, bool can_swap)
+				   struct pglist_data *pgdat)
 {
-	struct folio *folio;
+	struct folio *folio = pfn_folio(pfn);
 
-	folio = pfn_folio(pfn);
-	if (folio_nid(folio) != pgdat->node_id)
+	if (folio_lru_gen(folio) < 0)
 		return NULL;
 
-	if (folio_memcg(folio) != memcg)
+	if (folio_nid(folio) != pgdat->node_id)
 		return NULL;
 
-	/* file VMAs can contain anon pages from COW */
-	if (!folio_is_file_lru(folio) && !can_swap)
+	if (folio_memcg(folio) != memcg)
 		return NULL;
 
 	return folio;
@@ -3370,29 +3428,55 @@ static bool suitable_to_scan(int total, int young)
 	return young * n >= total;
 }
 
+static void walk_update_folio(struct lru_gen_mm_walk *walk, struct folio *folio,
+			      int new_gen, bool dirty)
+{
+	int old_gen;
+
+	if (!folio)
+		return;
+
+	if (dirty && !folio_test_dirty(folio) &&
+	    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
+	      !folio_test_swapcache(folio)))
+		folio_mark_dirty(folio);
+
+	if (walk) {
+		old_gen = folio_update_gen(folio, new_gen);
+		if (old_gen >= 0 && old_gen != new_gen)
+			update_batch_size(walk, folio, old_gen, new_gen);
+	} else if (lru_gen_set_refs(folio)) {
+		old_gen = folio_lru_gen(folio);
+		if (old_gen >= 0 && old_gen != new_gen)
+			folio_activate(folio);
+	}
+}
+
 static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 			   struct mm_walk *args)
 {
 	int i;
+	bool dirty;
 	pte_t *pte;
 	spinlock_t *ptl;
 	unsigned long addr;
 	int total = 0;
 	int young = 0;
+	struct folio *last = NULL;
 	struct lru_gen_mm_walk *walk = args->private;
 	struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
 	DEFINE_MAX_SEQ(walk->lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 	pmd_t pmdval;
 
-	pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval,
-				       &ptl);
+	pte = pte_offset_map_rw_nolock(args->mm, pmd, start & PMD_MASK, &pmdval, &ptl);
 	if (!pte)
 		return false;
+
 	if (!spin_trylock(ptl)) {
 		pte_unmap(pte);
-		return false;
+		return true;
 	}
 
 	if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
@@ -3414,26 +3498,30 @@ restart:
 		if (pfn == -1)
 			continue;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			continue;
 
 		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
 			continue;
 
-		young++;
-		walk->mm_stats[MM_LEAF_YOUNG]++;
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
 
-		if (pte_dirty(ptent) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
+			last = folio;
+			dirty = false;
+		}
 
-		old_gen = folio_update_gen(folio, new_gen);
-		if (old_gen >= 0 && old_gen != new_gen)
-			update_batch_size(walk, folio, old_gen, new_gen);
+		if (pte_dirty(ptent))
+			dirty = true;
+
+		young++;
+		walk->mm_stats[MM_LEAF_YOUNG]++;
 	}
 
+	walk_update_folio(walk, last, gen, dirty);
+	last = NULL;
+
 	if (i < PTRS_PER_PTE && get_next_vma(PMD_MASK, PAGE_SIZE, args, &start, &end))
 		goto restart;
 
@@ -3447,13 +3535,15 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 				  struct mm_walk *args, unsigned long *bitmap, unsigned long *first)
 {
 	int i;
+	bool dirty;
 	pmd_t *pmd;
 	spinlock_t *ptl;
+	struct folio *last = NULL;
 	struct lru_gen_mm_walk *walk = args->private;
 	struct mem_cgroup *memcg = lruvec_memcg(walk->lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
 	DEFINE_MAX_SEQ(walk->lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 
 	VM_WARN_ON_ONCE(pud_leaf(*pud));
 
@@ -3499,27 +3589,30 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		if (pfn == -1)
 			goto next;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			goto next;
 
 		if (!pmdp_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
-		walk->mm_stats[MM_LEAF_YOUNG]++;
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
 
-		if (pmd_dirty(pmd[i]) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
+			last = folio;
+			dirty = false;
+		}
 
-		old_gen = folio_update_gen(folio, new_gen);
-		if (old_gen >= 0 && old_gen != new_gen)
-			update_batch_size(walk, folio, old_gen, new_gen);
+		if (pmd_dirty(pmd[i]))
+			dirty = true;
+
+		walk->mm_stats[MM_LEAF_YOUNG]++;
 next:
 		i = i > MIN_LRU_BATCH ? 0 : find_next_bit(bitmap, MIN_LRU_BATCH, i) + 1;
 	} while (i <= MIN_LRU_BATCH);
 
+	walk_update_folio(walk, last, gen, dirty);
+
 	arch_leave_lazy_mmu_mode();
 	spin_unlock(ptl);
 done:
@@ -3711,22 +3804,25 @@ static void clear_mm_walk(void)
 		kfree(walk);
 }
 
-static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
+static bool inc_min_seq(struct lruvec *lruvec, int type, int swappiness)
 {
 	int zone;
 	int remaining = MAX_LRU_BATCH;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 	int new_gen, old_gen = lru_gen_from_seq(lrugen->min_seq[type]);
 
-	if (type == LRU_GEN_ANON && !can_swap)
+	if (type ? swappiness > MAX_SWAPPINESS : !swappiness)
 		goto done;
 
-	/* prevent cold/hot inversion if force_scan is true */
+	/* prevent cold/hot inversion if the type is evictable */
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		struct list_head *head = &lrugen->folios[old_gen][type][zone];
 
 		while (!list_empty(head)) {
 			struct folio *folio = lru_to_folio(head);
+			int refs = folio_lru_refs(folio);
+			bool workingset = folio_test_workingset(folio);
 
 			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
 			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
@@ -3736,6 +3832,15 @@ static bool inc_min_seq(struct lruvec *lruvec, int type, bool can_swap)
 			new_gen = folio_inc_gen(lruvec, folio, false);
 			list_move_tail(&folio->lru, &lrugen->folios[new_gen][type][zone]);
 
+			/* don't count the workingset being lazily promoted */
+			if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) {
+				int tier = lru_tier_from_refs(refs, workingset);
+				int delta = folio_nr_pages(folio);
+
+				WRITE_ONCE(lrugen->protected[hist][type][tier],
+					   lrugen->protected[hist][type][tier] + delta);
+			}
+
 			if (!--remaining)
 				return false;
 		}
@@ -3747,7 +3852,7 @@ done:
 	return true;
 }
 
-static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
+static bool try_to_inc_min_seq(struct lruvec *lruvec, int swappiness)
 {
 	int gen, type, zone;
 	bool success = false;
@@ -3757,7 +3862,7 @@ static bool try_to_inc_min_seq(struct lruvec *lruvec, bool can_swap)
 	VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
 
 	/* find the oldest populated generation */
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		while (min_seq[type] + MIN_NR_GENS <= lrugen->max_seq) {
 			gen = lru_gen_from_seq(min_seq[type]);
 
@@ -3773,13 +3878,17 @@ next:
 	}
 
 	/* see the comment on lru_gen_folio */
-	if (can_swap) {
-		min_seq[LRU_GEN_ANON] = min(min_seq[LRU_GEN_ANON], min_seq[LRU_GEN_FILE]);
-		min_seq[LRU_GEN_FILE] = max(min_seq[LRU_GEN_ANON], lrugen->min_seq[LRU_GEN_FILE]);
+	if (swappiness && swappiness <= MAX_SWAPPINESS) {
+		unsigned long seq = lrugen->max_seq - MIN_NR_GENS;
+
+		if (min_seq[LRU_GEN_ANON] > seq && min_seq[LRU_GEN_FILE] < seq)
+			min_seq[LRU_GEN_ANON] = seq;
+		else if (min_seq[LRU_GEN_FILE] > seq && min_seq[LRU_GEN_ANON] < seq)
+			min_seq[LRU_GEN_FILE] = seq;
 	}
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
-		if (min_seq[type] == lrugen->min_seq[type])
+	for_each_evictable_type(type, swappiness) {
+		if (min_seq[type] <= lrugen->min_seq[type])
 			continue;
 
 		reset_ctrl_pos(lruvec, type, true);
@@ -3790,8 +3899,7 @@ next:
 	return success;
 }
 
-static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq,
-			bool can_swap, bool force_scan)
+static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness)
 {
 	bool success;
 	int prev, next;
@@ -3809,13 +3917,11 @@ restart:
 	if (!success)
 		goto unlock;
 
-	for (type = ANON_AND_FILE - 1; type >= 0; type--) {
+	for (type = 0; type < ANON_AND_FILE; type++) {
 		if (get_nr_gens(lruvec, type) != MAX_NR_GENS)
 			continue;
 
-		VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap));
-
-		if (inc_min_seq(lruvec, type, can_swap))
+		if (inc_min_seq(lruvec, type, swappiness))
 			continue;
 
 		spin_unlock_irq(&lruvec->lru_lock);
@@ -3859,7 +3965,7 @@ unlock:
 }
 
 static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
-			       bool can_swap, bool force_scan)
+			       int swappiness, bool force_scan)
 {
 	bool success;
 	struct lru_gen_mm_walk *walk;
@@ -3870,7 +3976,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 	VM_WARN_ON_ONCE(seq > READ_ONCE(lrugen->max_seq));
 
 	if (!mm_state)
-		return inc_max_seq(lruvec, seq, can_swap, force_scan);
+		return inc_max_seq(lruvec, seq, swappiness);
 
 	/* see the comment in iterate_mm_list() */
 	if (seq <= READ_ONCE(mm_state->seq))
@@ -3895,7 +4001,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 
 	walk->lruvec = lruvec;
 	walk->seq = seq;
-	walk->can_swap = can_swap;
+	walk->swappiness = swappiness;
 	walk->force_scan = force_scan;
 
 	do {
@@ -3905,7 +4011,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 	} while (mm);
 done:
 	if (success) {
-		success = inc_max_seq(lruvec, seq, can_swap, force_scan);
+		success = inc_max_seq(lruvec, seq, swappiness);
 		WARN_ON_ONCE(!success);
 	}
 
@@ -3946,13 +4052,13 @@ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
 {
 	int gen, type, zone;
 	unsigned long total = 0;
-	bool can_swap = get_swappiness(lruvec, sc);
+	int swappiness = get_swappiness(lruvec, sc);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		unsigned long seq;
 
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
@@ -3972,6 +4078,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
 {
 	int gen;
 	unsigned long birth;
+	int swappiness = get_swappiness(lruvec, sc);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
@@ -3981,8 +4088,7 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
 	if (!lruvec_is_sizable(lruvec, sc))
 		return false;
 
-	/* see the comment on lru_gen_folio */
-	gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
+	gen = lru_gen_from_seq(evictable_min_seq(min_seq, swappiness));
 	birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
 
 	return time_is_before_jiffies(birth + min_ttl);
@@ -4041,21 +4147,22 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 	int i;
+	bool dirty;
 	unsigned long start;
 	unsigned long end;
 	struct lru_gen_mm_walk *walk;
+	struct folio *last = NULL;
 	int young = 1;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
 	struct folio *folio = pfn_folio(pvmw->pfn);
-	bool can_swap = !folio_is_file_lru(folio);
 	struct mem_cgroup *memcg = folio_memcg(folio);
 	struct pglist_data *pgdat = folio_pgdat(folio);
 	struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	struct lru_gen_mm_state *mm_state = get_mm_state(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
-	int old_gen, new_gen = lru_gen_from_seq(max_seq);
+	int gen = lru_gen_from_seq(max_seq);
 
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
@@ -4102,37 +4209,28 @@ bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		if (pfn == -1)
 			continue;
 
-		folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
+		folio = get_pfn_folio(pfn, memcg, pgdat);
 		if (!folio)
 			continue;
 
 		if (!ptep_clear_young_notify(vma, addr, pte + i))
 			continue;
 
-		young++;
-
-		if (pte_dirty(ptent) && !folio_test_dirty(folio) &&
-		    !(folio_test_anon(folio) && folio_test_swapbacked(folio) &&
-		      !folio_test_swapcache(folio)))
-			folio_mark_dirty(folio);
-
-		if (walk) {
-			old_gen = folio_update_gen(folio, new_gen);
-			if (old_gen >= 0 && old_gen != new_gen)
-				update_batch_size(walk, folio, old_gen, new_gen);
+		if (last != folio) {
+			walk_update_folio(walk, last, gen, dirty);
 
-			continue;
+			last = folio;
+			dirty = false;
 		}
 
-		old_gen = folio_lru_gen(folio);
-		if (old_gen < 0)
-			folio_set_referenced(folio);
-		else if (old_gen != new_gen) {
-			folio_clear_lru_refs(folio);
-			folio_activate(folio);
-		}
+		if (pte_dirty(ptent))
+			dirty = true;
+
+		young++;
 	}
 
+	walk_update_folio(walk, last, gen, dirty);
+
 	arch_leave_lazy_mmu_mode();
 
 	/* feedback from rmap walkers to page table walkers */
@@ -4290,7 +4388,8 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	int zone = folio_zonenum(folio);
 	int delta = folio_nr_pages(folio);
 	int refs = folio_lru_refs(folio);
-	int tier = lru_tier_from_refs(refs);
+	bool workingset = folio_test_workingset(folio);
+	int tier = lru_tier_from_refs(refs, workingset);
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 
 	VM_WARN_ON_ONCE_FOLIO(gen >= MAX_NR_GENS, folio);
@@ -4312,14 +4411,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
-		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
-
+	if (tier > tier_idx || refs + workingset == BIT(LRU_REFS_WIDTH) + 1) {
 		gen = folio_inc_gen(lruvec, folio, false);
-		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
+		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
+
+		/* don't count the workingset being lazily promoted */
+		if (refs + workingset != BIT(LRU_REFS_WIDTH) + 1) {
+			int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
-		WRITE_ONCE(lrugen->protected[hist][type][tier - 1],
-			   lrugen->protected[hist][type][tier - 1] + delta);
+			WRITE_ONCE(lrugen->protected[hist][type][tier],
+				   lrugen->protected[hist][type][tier] + delta);
+		}
 		return true;
 	}
 
@@ -4339,8 +4441,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* waiting for writeback */
-	if (folio_test_locked(folio) || writeback ||
-	    (type == LRU_GEN_FILE && dirty)) {
+	if (writeback || (type == LRU_GEN_FILE && dirty)) {
 		gen = folio_inc_gen(lruvec, folio, true);
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;
@@ -4369,13 +4470,12 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 		return false;
 	}
 
-	/* see the comment on MAX_NR_TIERS */
+	/* see the comment on LRU_REFS_FLAGS */
 	if (!folio_test_referenced(folio))
-		folio_clear_lru_refs(folio);
+		set_mask_bits(&folio->flags, LRU_REFS_MASK, 0);
 
 	/* for shrink_folio_list() */
 	folio_clear_reclaim(folio);
-	folio_clear_referenced(folio);
 
 	success = lru_gen_del_folio(lruvec, folio, true);
 	VM_WARN_ON_ONCE_FOLIO(!success, folio);
@@ -4471,13 +4571,13 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
 	struct ctrl_pos sp, pv;
 
 	/*
-	 * To leave a margin for fluctuations, use a larger gain factor (1:2).
+	 * To leave a margin for fluctuations, use a larger gain factor (2:3).
 	 * This value is chosen because any other tier would have at least twice
 	 * as many refaults as the first tier.
 	 */
-	read_ctrl_pos(lruvec, type, 0, 1, &sp);
+	read_ctrl_pos(lruvec, type, 0, 2, &sp);
 	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-		read_ctrl_pos(lruvec, type, tier, 2, &pv);
+		read_ctrl_pos(lruvec, type, tier, 3, &pv);
 		if (!positive_ctrl_err(&sp, &pv))
 			break;
 	}
@@ -4485,79 +4585,45 @@ static int get_tier_idx(struct lruvec *lruvec, int type)
 	return tier - 1;
 }
 
-static int get_type_to_scan(struct lruvec *lruvec, int swappiness, int *tier_idx)
+static int get_type_to_scan(struct lruvec *lruvec, int swappiness)
 {
-	int type, tier;
 	struct ctrl_pos sp, pv;
-	int gain[ANON_AND_FILE] = { swappiness, MAX_SWAPPINESS - swappiness };
 
+	if (swappiness <= MIN_SWAPPINESS + 1)
+		return LRU_GEN_FILE;
+
+	if (swappiness >= MAX_SWAPPINESS)
+		return LRU_GEN_ANON;
 	/*
-	 * Compare the first tier of anon with that of file to determine which
-	 * type to scan. Also need to compare other tiers of the selected type
-	 * with the first tier of the other type to determine the last tier (of
-	 * the selected type) to evict.
+	 * Compare the sum of all tiers of anon with that of file to determine
+	 * which type to scan.
 	 */
-	read_ctrl_pos(lruvec, LRU_GEN_ANON, 0, gain[LRU_GEN_ANON], &sp);
-	read_ctrl_pos(lruvec, LRU_GEN_FILE, 0, gain[LRU_GEN_FILE], &pv);
-	type = positive_ctrl_err(&sp, &pv);
+	read_ctrl_pos(lruvec, LRU_GEN_ANON, MAX_NR_TIERS, swappiness, &sp);
+	read_ctrl_pos(lruvec, LRU_GEN_FILE, MAX_NR_TIERS, MAX_SWAPPINESS - swappiness, &pv);
 
-	read_ctrl_pos(lruvec, !type, 0, gain[!type], &sp);
-	for (tier = 1; tier < MAX_NR_TIERS; tier++) {
-		read_ctrl_pos(lruvec, type, tier, gain[type], &pv);
-		if (!positive_ctrl_err(&sp, &pv))
-			break;
-	}
-
-	*tier_idx = tier - 1;
-
-	return type;
+	return positive_ctrl_err(&sp, &pv);
 }
 
 static int isolate_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
 			  int *type_scanned, struct list_head *list)
 {
 	int i;
-	int type;
-	int scanned;
-	int tier = -1;
-	DEFINE_MIN_SEQ(lruvec);
+	int type = get_type_to_scan(lruvec, swappiness);
 
-	/*
-	 * Try to make the obvious choice first, and if anon and file are both
-	 * available from the same generation,
-	 * 1. Interpret swappiness 1 as file first and MAX_SWAPPINESS as anon
-	 *    first.
-	 * 2. If !__GFP_IO, file first since clean pagecache is more likely to
-	 *    exist than clean swapcache.
-	 */
-	if (!swappiness)
-		type = LRU_GEN_FILE;
-	else if (min_seq[LRU_GEN_ANON] < min_seq[LRU_GEN_FILE])
-		type = LRU_GEN_ANON;
-	else if (swappiness == 1)
-		type = LRU_GEN_FILE;
-	else if (swappiness == MAX_SWAPPINESS)
-		type = LRU_GEN_ANON;
-	else if (!(sc->gfp_mask & __GFP_IO))
-		type = LRU_GEN_FILE;
-	else
-		type = get_type_to_scan(lruvec, swappiness, &tier);
+	for_each_evictable_type(i, swappiness) {
+		int scanned;
+		int tier = get_tier_idx(lruvec, type);
 
-	for (i = !swappiness; i < ANON_AND_FILE; i++) {
-		if (tier < 0)
-			tier = get_tier_idx(lruvec, type);
+		*type_scanned = type;
 
 		scanned = scan_folios(lruvec, sc, type, tier, list);
 		if (scanned)
-			break;
+			return scanned;
 
 		type = !type;
-		tier = -1;
 	}
 
-	*type_scanned = type;
-
-	return scanned;
+	return 0;
 }
 
 static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
@@ -4573,6 +4639,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	struct reclaim_stat stat;
 	struct lru_gen_mm_walk *walk;
 	bool skip_retry = false;
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
@@ -4582,7 +4649,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 
 	scanned += try_to_inc_min_seq(lruvec, swappiness);
 
-	if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
+	if (evictable_min_seq(lrugen->min_seq, swappiness) + MIN_NR_GENS > lrugen->max_seq)
 		scanned = 0;
 
 	spin_unlock_irq(&lruvec->lru_lock);
@@ -4598,31 +4665,24 @@ retry:
 			type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
 
 	list_for_each_entry_safe_reverse(folio, next, &list, lru) {
+		DEFINE_MIN_SEQ(lruvec);
+
 		if (!folio_evictable(folio)) {
 			list_del(&folio->lru);
 			folio_putback_lru(folio);
 			continue;
 		}
 
-		if (folio_test_reclaim(folio) &&
-		    (folio_test_dirty(folio) || folio_test_writeback(folio))) {
-			/* restore LRU_REFS_FLAGS cleared by isolate_folio() */
-			if (folio_test_workingset(folio))
-				folio_set_referenced(folio);
-			continue;
-		}
-
-		if (skip_retry || folio_test_active(folio) || folio_test_referenced(folio) ||
-		    folio_mapped(folio) || folio_test_locked(folio) ||
-		    folio_test_dirty(folio) || folio_test_writeback(folio)) {
-			/* don't add rejected folios to the oldest generation */
-			set_mask_bits(&folio->flags, LRU_REFS_MASK | LRU_REFS_FLAGS,
-				      BIT(PG_active));
+		/* retry folios that may have missed folio_rotate_reclaimable() */
+		if (!skip_retry && !folio_test_active(folio) && !folio_mapped(folio) &&
+		    !folio_test_dirty(folio) && !folio_test_writeback(folio)) {
+			list_move(&folio->lru, &clean);
 			continue;
 		}
 
-		/* retry folios that may have missed folio_rotate_reclaimable() */
-		list_move(&folio->lru, &clean);
+		/* don't add rejected folios to the oldest generation */
+		if (lru_gen_folio_seq(lruvec, folio, false) == min_seq[type])
+			set_mask_bits(&folio->flags, LRU_REFS_FLAGS, BIT(PG_active));
 	}
 
 	spin_lock_irq(&lruvec->lru_lock);
@@ -4635,6 +4695,9 @@ retry:
 		reset_batch_size(walk);
 	}
 
+	__mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(),
+					stat.nr_demoted);
+
 	item = PGSTEAL_KSWAPD + reclaimer_offset();
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, reclaimed);
@@ -4654,63 +4717,32 @@ retry:
 }
 
 static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
-			     bool can_swap, unsigned long *nr_to_scan)
+			     int swappiness, unsigned long *nr_to_scan)
 {
 	int gen, type, zone;
-	unsigned long old = 0;
-	unsigned long young = 0;
-	unsigned long total = 0;
+	unsigned long size = 0;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	DEFINE_MIN_SEQ(lruvec);
 
-	/* whether this lruvec is completely out of cold folios */
-	if (min_seq[!can_swap] + MIN_NR_GENS > max_seq) {
-		*nr_to_scan = 0;
+	*nr_to_scan = 0;
+	/* have to run aging, since eviction is not possible anymore */
+	if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS > max_seq)
 		return true;
-	}
 
-	for (type = !can_swap; type < ANON_AND_FILE; type++) {
+	for_each_evictable_type(type, swappiness) {
 		unsigned long seq;
 
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
-			unsigned long size = 0;
-
 			gen = lru_gen_from_seq(seq);
 
 			for (zone = 0; zone < MAX_NR_ZONES; zone++)
 				size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
-
-			total += size;
-			if (seq == max_seq)
-				young += size;
-			else if (seq + MIN_NR_GENS == max_seq)
-				old += size;
 		}
 	}
 
-	*nr_to_scan = total;
-
-	/*
-	 * The aging tries to be lazy to reduce the overhead, while the eviction
-	 * stalls when the number of generations reaches MIN_NR_GENS. Hence, the
-	 * ideal number of generations is MIN_NR_GENS+1.
-	 */
-	if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
-		return false;
-
-	/*
-	 * It's also ideal to spread pages out evenly, i.e., 1/(MIN_NR_GENS+1)
-	 * of the total number of pages for each generation. A reasonable range
-	 * for this average portion is [1/MIN_NR_GENS, 1/(MIN_NR_GENS+2)]. The
-	 * aging cares about the upper bound of hot pages, while the eviction
-	 * cares about the lower bound of cold pages.
-	 */
-	if (young * MIN_NR_GENS > total)
-		return true;
-	if (old * (MIN_NR_GENS + 2) < total)
-		return true;
-
-	return false;
+	*nr_to_scan = size;
+	/* better to run aging even though eviction is still possible */
+	return evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS == max_seq;
 }
 
 /*
@@ -4718,7 +4750,7 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
  * 1. Defer try_to_inc_max_seq() to workqueues to reduce latency for memcg
  *    reclaim.
  */
-static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool can_swap)
+static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, int swappiness)
 {
 	bool success;
 	unsigned long nr_to_scan;
@@ -4728,7 +4760,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
 		return -1;
 
-	success = should_run_aging(lruvec, max_seq, can_swap, &nr_to_scan);
+	success = should_run_aging(lruvec, max_seq, swappiness, &nr_to_scan);
 
 	/* try to scrape all its memory if this memcg was deleted */
 	if (nr_to_scan && !mem_cgroup_online(memcg))
@@ -4739,7 +4771,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 		return nr_to_scan >> sc->priority;
 
 	/* stop scanning this lruvec as it's low on cold folios */
-	return try_to_inc_max_seq(lruvec, max_seq, can_swap, false) ? -1 : 0;
+	return try_to_inc_max_seq(lruvec, max_seq, swappiness, false) ? -1 : 0;
 }
 
 static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
@@ -5283,8 +5315,7 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 				s = "rep";
 				n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
 				n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
-				if (tier)
-					n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
+				n[2] = READ_ONCE(lrugen->protected[hist][type][tier]);
 			}
 
 			for (i = 0; i < 3; i++)
@@ -5339,7 +5370,7 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
 	seq_printf(m, " node %5d\n", nid);
 
 	if (!full)
-		seq = min_seq[LRU_GEN_ANON];
+		seq = evictable_min_seq(min_seq, MAX_SWAPPINESS / 2);
 	else if (max_seq >= MAX_NR_GENS)
 		seq = max_seq - MAX_NR_GENS + 1;
 	else
@@ -5379,23 +5410,14 @@ static const struct seq_operations lru_gen_seq_ops = {
 };
 
 static int run_aging(struct lruvec *lruvec, unsigned long seq,
-		     bool can_swap, bool force_scan)
+		     int swappiness, bool force_scan)
 {
 	DEFINE_MAX_SEQ(lruvec);
-	DEFINE_MIN_SEQ(lruvec);
-
-	if (seq < max_seq)
-		return 0;
 
 	if (seq > max_seq)
 		return -EINVAL;
 
-	if (!force_scan && min_seq[!can_swap] + MAX_NR_GENS - 1 <= max_seq)
-		return -ERANGE;
-
-	try_to_inc_max_seq(lruvec, max_seq, can_swap, force_scan);
-
-	return 0;
+	return try_to_inc_max_seq(lruvec, max_seq, swappiness, force_scan) ? 0 : -EEXIST;
 }
 
 static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_control *sc,
@@ -5411,7 +5433,7 @@ static int run_eviction(struct lruvec *lruvec, unsigned long seq, struct scan_co
 	while (!signal_pending(current)) {
 		DEFINE_MIN_SEQ(lruvec);
 
-		if (seq < min_seq[!swappiness])
+		if (seq < evictable_min_seq(min_seq, swappiness))
 			return 0;
 
 		if (sc->nr_reclaimed >= nr_to_reclaim)
@@ -5456,7 +5478,7 @@ static int run_cmd(char cmd, int memcg_id, int nid, unsigned long seq,
 
 	if (swappiness < MIN_SWAPPINESS)
 		swappiness = get_swappiness(lruvec, sc);
-	else if (swappiness > MAX_SWAPPINESS)
+	else if (swappiness > MAX_SWAPPINESS + 1)
 		goto done;
 
 	switch (cmd) {
@@ -7182,10 +7204,6 @@ static int kswapd(void *p)
 	unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
 	pg_data_t *pgdat = (pg_data_t *)p;
 	struct task_struct *tsk = current;
-	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
-
-	if (!cpumask_empty(cpumask))
-		set_cpus_allowed_ptr(tsk, cpumask);
 
 	/*
 	 * Tell the memory management that we're a "memory allocator",
@@ -7354,13 +7372,15 @@ void __meminit kswapd_run(int nid)
 
 	pgdat_kswapd_lock(pgdat);
 	if (!pgdat->kswapd) {
-		pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+		pgdat->kswapd = kthread_create_on_node(kswapd, pgdat, nid, "kswapd%d", nid);
 		if (IS_ERR(pgdat->kswapd)) {
 			/* failure at boot is fatal */
 			pr_err("Failed to start kswapd on node %d，ret=%ld\n",
 				   nid, PTR_ERR(pgdat->kswapd));
 			BUG_ON(system_state < SYSTEM_RUNNING);
 			pgdat->kswapd = NULL;
+		} else {
+			wake_up_process(pgdat->kswapd);
 		}
 	}
 	pgdat_kswapd_unlock(pgdat);