1 files changed, 61 insertions, 31 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5dc581cac225..f0eba9ef3332 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4093,6 +4093,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	else
 		VM_WARN_ON_ONCE(true);
 
+	WRITE_ONCE(lruvec->lrugen.seg, seg);
+	WRITE_ONCE(lruvec->lrugen.gen, new);
+
 	hlist_nulls_del_rcu(&lruvec->lrugen.list);
 
 	if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD)
@@ -4103,9 +4106,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op)
 	pgdat->memcg_lru.nr_memcgs[old]--;
 	pgdat->memcg_lru.nr_memcgs[new]++;
 
-	lruvec->lrugen.gen = new;
-	WRITE_ONCE(lruvec->lrugen.seg, seg);
-
 	if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq))
 		WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1);
 
@@ -4128,11 +4128,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg)
 
 		gen = get_memcg_gen(pgdat->memcg_lru.seq);
 
+		lruvec->lrugen.gen = gen;
+
 		hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]);
 		pgdat->memcg_lru.nr_memcgs[gen]++;
 
-		lruvec->lrugen.gen = gen;
-
 		spin_unlock_irq(&pgdat->memcg_lru.lock);
 	}
 }
@@ -4236,7 +4236,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* protected */
-	if (tier > tier_idx) {
+	if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) {
 		int hist = lru_hist_from_seq(lrugen->min_seq[type]);
 
 		gen = folio_inc_gen(lruvec, folio, false);
@@ -4602,7 +4602,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq,
 	}
 
 	/* try to scrape all its memory if this memcg was deleted */
-	*nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total;
+	if (!mem_cgroup_online(memcg)) {
+		*nr_to_scan = total;
+		return false;
+	}
+
+	*nr_to_scan = total >> sc->priority;
 
 	/*
 	 * The aging tries to be lazy to reduce the overhead, while the eviction
@@ -4639,7 +4644,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	DEFINE_MAX_SEQ(lruvec);
 
 	if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg))
-		return 0;
+		return -1;
 
 	if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan))
 		return nr_to_scan;
@@ -4652,20 +4657,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool
 	return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0;
 }
 
-static unsigned long get_nr_to_reclaim(struct scan_control *sc)
+static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc)
 {
+	int i;
+	enum zone_watermarks mark;
+
 	/* don't abort memcg reclaim to ensure fairness */
 	if (!root_reclaim(sc))
-		return -1;
+		return false;
+
+	if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order)))
+		return true;
+
+	/* check the order to exclude compaction-induced reclaim */
+	if (!current_is_kswapd() || sc->order)
+		return false;
+
+	mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ?
+	       WMARK_PROMO : WMARK_HIGH;
+
+	for (i = 0; i <= sc->reclaim_idx; i++) {
+		struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i;
+		unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH;
+
+		if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0))
+			return false;
+	}
 
-	return max(sc->nr_to_reclaim, compact_gap(sc->order));
+	/* kswapd should abort if all eligible zones are safe */
+	return true;
 }
 
 static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 {
 	long nr_to_scan;
 	unsigned long scanned = 0;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
 	int swappiness = get_swappiness(lruvec, sc);
 
 	/* clean file folios are more likely to exist */
@@ -4687,13 +4713,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		if (scanned >= nr_to_scan)
 			break;
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
@@ -4702,14 +4728,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 	bool success;
 	unsigned long scanned = sc->nr_scanned;
 	unsigned long reclaimed = sc->nr_reclaimed;
-	int seg = lru_gen_memcg_seg(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-	/* see the comment on MEMCG_NR_GENS */
-	if (!lruvec_is_sizable(lruvec, sc))
-		return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
-
 	mem_cgroup_calculate_protection(NULL, memcg);
 
 	if (mem_cgroup_below_min(NULL, memcg))
@@ -4717,7 +4738,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	if (mem_cgroup_below_low(NULL, memcg)) {
 		/* see the comment on MEMCG_NR_GENS */
-		if (seg != MEMCG_LRU_TAIL)
+		if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL)
 			return MEMCG_LRU_TAIL;
 
 		memcg_memory_event(memcg, MEMCG_LOW);
@@ -4733,7 +4754,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 
 	flush_reclaim_state(sc);
 
-	return success ? MEMCG_LRU_YOUNG : 0;
+	if (success && mem_cgroup_online(memcg))
+		return MEMCG_LRU_YOUNG;
+
+	if (!success && lruvec_is_sizable(lruvec, sc))
+		return 0;
+
+	/* one retry if offlined or too small */
+	return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ?
+	       MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG;
 }
 
 #ifdef CONFIG_MEMCG
@@ -4747,14 +4776,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc)
 	struct lruvec *lruvec;
 	struct lru_gen_folio *lrugen;
 	struct mem_cgroup *memcg;
-	const struct hlist_nulls_node *pos;
-	unsigned long nr_to_reclaim = get_nr_to_reclaim(sc);
+	struct hlist_nulls_node *pos;
 
+	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 	bin = first_bin = get_random_u32_below(MEMCG_NR_BINS);
 restart:
 	op = 0;
 	memcg = NULL;
-	gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq));
 
 	rcu_read_lock();
 
@@ -4765,6 +4793,10 @@ restart:
 		}
 
 		mem_cgroup_put(memcg);
+		memcg = NULL;
+
+		if (gen != READ_ONCE(lrugen->gen))
+			continue;
 
 		lruvec = container_of(lrugen, struct lruvec, lrugen);
 		memcg = lruvec_memcg(lruvec);
@@ -4781,7 +4813,7 @@ restart:
 
 		rcu_read_lock();
 
-		if (sc->nr_reclaimed >= nr_to_reclaim)
+		if (should_abort_scan(lruvec, sc))
 			break;
 	}
 
@@ -4792,7 +4824,7 @@ restart:
 
 	mem_cgroup_put(memcg);
 
-	if (sc->nr_reclaimed >= nr_to_reclaim)
+	if (!is_a_nulls(pos))
 		return;
 
 	/* restart if raced with lru_gen_rotate_memcg() */
@@ -4849,16 +4881,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 	if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
 		return;
 	/*
-	 * Determine the initial priority based on ((total / MEMCG_NR_GENS) >>
-	 * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the
-	 * estimated reclaimed_to_scanned_ratio = inactive / total.
+	 * Determine the initial priority based on
+	 * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+	 * where reclaimed_to_scanned_ratio = inactive / total.
 	 */
 	reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
 	if (get_swappiness(lruvec, sc))
 		reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
 
-	reclaimable /= MEMCG_NR_GENS;
-
 	/* round down reclaimable and round up sc->nr_to_reclaim */
 	priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);