diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index f6fcd45a30e9..c9cb85defac0 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -77,23 +77,27 @@
 #define LAST_CPUPID_SHIFT 0
 #endif
 
-#ifdef CONFIG_KASAN_SW_TAGS
-#define KASAN_TAG_WIDTH 8
-#else
-#define KASAN_TAG_WIDTH 0
-#endif
-
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_WIDTH+LRU_GEN_WIDTH+LRU_REFS_WIDTH+ \
-	KASAN_TAG_WIDTH + LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_WIDTH+LAST_CPUPID_SHIFT+ \
+	LRU_GEN_WIDTH+LRU_REFS_WIDTH <= BITS_PER_LONG - NR_PAGEFLAGS
 #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
 #else
 #define LAST_CPUPID_WIDTH 0
 #endif
 
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_WIDTH+LRU_GEN_WIDTH+LRU_REFS_WIDTH+ \
-	KASAN_TAG_WIDTH + LAST_CPUPID_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
+#ifdef CONFIG_KASAN_SW_TAGS
+#define KASAN_TAG_WIDTH 8
+#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \
+	> BITS_PER_LONG - NR_PAGEFLAGS
 #error "KASAN: not enough bits in page flags for tag"
 #endif
+#else
+#define KASAN_TAG_WIDTH 0
+#endif
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH+ \
+	LRU_GEN_WIDTH+LRU_REFS_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
+#error "Not enough bits in page flags"
+#endif
 
 /*
  * We are going to use the flags for the page to node mapping if its in
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index beeafcf33c60..2f9e7699f6c8 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -35,6 +35,15 @@ enum vm_event_item { PGPGIN, PGPGOUT, PGPGOUTCLEAN, PSWPIN, PSWPOUT,
 		PGSCAN_KSWAPD,
 		PGSCAN_DIRECT,
 		PGSCAN_DIRECT_THROTTLE,
+		LRU_KSWAPD_NO_PROGRESS,
+		LRU_KSWAPD_ANON,
+		LRU_KSWAPD_FILE,
+		LRU_DIRECT_ANON,
+		LRU_DIRECT_FILE,
+		LRU_KSWAPD_SWAP_FULL,
+		LRU_DIRECT_SWAP_FULL,
+		LRU_NO_GFP_IO,
+		LRU_NO_WRITEPAGE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
diff --git a/mm/swap.c b/mm/swap.c
index 49c9e2062058..5e7539467894 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -501,9 +501,10 @@ void __lru_cache_add_active_or_unevictable(struct page *page,
 {
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 
-	if (likely((vma_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
-		SetPageActive(page);
-	else if (!TestSetPageMlocked(page)) {
+	if (likely((vma_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) {
+		if (!lru_gen_enabled())
+			SetPageActive(page);
+	} else if (!TestSetPageMlocked(page)) {
 		/*
 		 * We use the irq-unsafe __mod_zone_page_stat because this
 		 * counter is not modified from interrupt context, and the pte
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4aecda263c4d..af81bef23682 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2630,8 +2630,11 @@ static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
 {
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 
-	if (mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
+	if (mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH) {
+		count_vm_event(current_is_kswapd() ? LRU_KSWAPD_SWAP_FULL:
+						     LRU_DIRECT_SWAP_FULL);
 		return 0;
+	}
 
 	return mem_cgroup_swappiness(memcg);
 }
@@ -3857,9 +3860,9 @@ static long get_nr_evictable(struct lruvec *lruvec, unsigned long max_seq,
 	 * from the producer's POV, the aging only cares about the upper bound
 	 * of hot pages, i.e., 1/MIN_NR_GENS.
 	 */
-	if (min_seq[LRU_GEN_FILE] + MIN_NR_GENS > max_seq)
+	if (min_seq[!can_swap] + MIN_NR_GENS > max_seq)
 		*need_aging = true;
-	else if (min_seq[LRU_GEN_FILE] + MIN_NR_GENS < max_seq)
+	else if (min_seq[!can_swap] + MIN_NR_GENS < max_seq)
 		*need_aging = false;
 	else if (young * MIN_NR_GENS > total)
 		*need_aging = true;
@@ -3954,10 +3957,9 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
 	 * younger than min_ttl. However, another theoretical possibility is all
 	 * memcgs are either below min or empty.
 	 */
-	if (!success && mutex_trylock(&oom_lock)) {
+	if (!success && !sc->order && mutex_trylock(&oom_lock)) {
 		struct oom_control oc = {
 			.gfp_mask = sc->gfp_mask,
-			.order = sc->order,
 		};
 
 		out_of_memory(&oc);
@@ -3997,7 +3999,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		return;
 
 	start = max(pvmw->address & PMD_MASK, pvmw->vma->vm_start);
-	end = pmd_addr_end(pvmw->address, pvmw->vma->vm_end);
+	end = min(pvmw->address | ~PMD_MASK, pvmw->vma->vm_end - 1) + 1;
 
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (pvmw->address - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
@@ -4169,8 +4171,13 @@ static bool isolate_page(struct lruvec *lruvec, struct page *page, struct scan_c
 		return false;
 
 	if (!(sc->may_writepage && (sc->gfp_mask & __GFP_IO)) &&
-	    (PageDirty(page) || (PageAnon(page) && !PageSwapCache(page))))
+	    (PageDirty(page) || (PageAnon(page) && !PageSwapCache(page)))) {
+		if (!sc->may_writepage)
+			__count_vm_event(LRU_NO_WRITEPAGE);
+		if (!(sc->gfp_mask & __GFP_IO))
+			__count_vm_event(LRU_NO_GFP_IO);
 		return false;
+	}
 
 	if (!get_page_unless_zero(page))
 		return false;
@@ -4372,7 +4379,7 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
 	if (try_to_inc_min_seq(lruvec, swappiness))
 		scanned++;
 
-	if (get_nr_gens(lruvec, LRU_GEN_FILE) == MIN_NR_GENS)
+	if (get_nr_gens(lruvec, !swappiness) == MIN_NR_GENS)
 		scanned = 0;
 
 	spin_unlock_irq(&pgdat->lru_lock);
@@ -4415,6 +4422,10 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
 	free_unref_page_list(&list);
 
 	sc->nr_reclaimed += reclaimed;
+	if (!reclaimed) {
+		item = current_is_kswapd() ? LRU_KSWAPD_ANON : LRU_DIRECT_ANON;
+		count_vm_event(item + type);
+	}
 
 	if (type == LRU_GEN_ANON && swapped)
 		*swapped = true;
@@ -4422,15 +4433,15 @@ static int evict_pages(struct lruvec *lruvec, struct scan_control *sc, int swapp
 	return scanned;
 }
 
-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, bool can_swap,
+			   bool *need_aging)
 {
-	bool need_aging;
 	long nr_to_scan;
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	DEFINE_MAX_SEQ(lruvec);
 	DEFINE_MIN_SEQ(lruvec);
 
-	nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, can_swap, &need_aging);
+	nr_to_scan = get_nr_evictable(lruvec, max_seq, min_seq, can_swap, need_aging);
 	if (!nr_to_scan)
 		return 0;
 
@@ -4443,27 +4454,29 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	if (!nr_to_scan)
 		return 0;
 
-	if (!need_aging) {
-		sc->memcgs_need_aging = false;
+	if (!*need_aging)
 		return nr_to_scan;
-	}
 
 	/* leave the work to lru_gen_age_node() */
 	if (current_is_kswapd())
 		return 0;
 
+	/* try other memcgs before going to the aging path */
+	if (sc->priority == DEF_PRIORITY)
+		return 0;
+
 	if (try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false))
 		return nr_to_scan;
 
-	return min_seq[LRU_GEN_FILE] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
+	return min_seq[!can_swap] + MIN_NR_GENS <= max_seq ? nr_to_scan : 0;
 }
 
 static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	struct blk_plug plug;
 	long scanned = 0;
+	bool need_aging = false;
 	bool swapped = false;
-	unsigned long reclaimed = sc->nr_reclaimed;
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
 	lru_add_drain();
@@ -4485,27 +4498,29 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
 		else
 			swappiness = 0;
 
-		nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness);
+		nr_to_scan = get_nr_to_scan(lruvec, sc, swappiness, &need_aging);
 		if (!nr_to_scan)
-			break;
+			goto done;
 
 		delta = evict_pages(lruvec, sc, swappiness, &swapped);
 		if (!delta)
-			break;
+			goto done;
 
 		if (sc->memcgs_avoid_swapping && swappiness < 200 && swapped)
 			break;
 
 		scanned += delta;
-		if (scanned >= nr_to_scan) {
-			if (!swapped && sc->nr_reclaimed - reclaimed >= MIN_LRU_BATCH)
-				sc->memcgs_need_swapping = false;
+		if (scanned >= nr_to_scan)
 			break;
-		}
 
 		cond_resched();
 	}
 
+	if (!need_aging)
+		sc->memcgs_need_aging = false;
+	if (!swapped)
+		sc->memcgs_need_swapping = false;
+done:
 	if (current_is_kswapd())
 		current->reclaim_state->mm_walk = NULL;
 
@@ -6414,8 +6429,11 @@ restart:
 			sc.priority--;
 	} while (sc.priority >= 1);
 
-	if (!sc.nr_reclaimed)
-		pgdat->kswapd_failures++;
+	if (!sc.nr_reclaimed) {
+		count_vm_event(LRU_KSWAPD_NO_PROGRESS);
+		if (!lru_gen_enabled())
+			pgdat->kswapd_failures++;
+	}
 
 out:
 	/* If reclaim was boosted, account for the reclaim done in this pass */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6c202df93035..5df342d5f3f7 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1203,6 +1203,15 @@ const char * const vmstat_text[] = {
 	"pgscan_kswapd",
 	"pgscan_direct",
 	"pgscan_direct_throttle",
+	"lru_kswapd_no_progress",
+	"lru_kswapd_anon",
+	"lru_kswapd_file",
+	"lru_direct_anon",
+	"lru_direct_file",
+	"lru_kswapd_swap_full",
+	"lru_direct_swap_full",
+	"lru_no_gfp_io",
+	"lru_no_writepage",
 
 #ifdef CONFIG_NUMA
 	"zone_reclaim_failed",