mm/mglru: respect min_ttl_ms with memcgs

While investigating kswapd "consuming 100% CPU" [1] (also see "mm/mglru:
try to stop at high watermarks"), it was discovered that the memcg LRU can
breach the thrashing protection imposed by min_ttl_ms.

Before the memcg LRU:
  kswapd()
    shrink_node_memcgs()
      mem_cgroup_iter()
        inc_max_seq()  // always hit a different memcg
    lru_gen_age_node()
      mem_cgroup_iter()
        check the timestamp of the oldest generation

After the memcg LRU:
  kswapd()
    shrink_many()
      restart:
        iterate the memcg LRU:
          inc_max_seq()  // occasionally hit the same memcg
          if raced with lru_gen_rotate_memcg():
            goto restart
    lru_gen_age_node()
      mem_cgroup_iter()
        check the timestamp of the oldest generation

Specifically, when the restart happens in shrink_many(), it needs to stick
with the (memcg LRU) generation it began with.  In other words, it should
neither re-read memcg_lru->seq nor age an lruvec of a different
generation.  Otherwise it can hit the same memcg multiple times without
giving lru_gen_age_node() a chance to check the timestamp of that memcg's
oldest generation (against min_ttl_ms).

[1] https://lore.kernel.org/CAK8fFZ4DY+GtBA40Pm7Nn5xCHy+51w3sfxPqkqpqakSXYyX+Wg@mail.gmail.com/

Link: https://lkml.kernel.org/r/20231208061407.2125867-3-yuzhao@google.com
Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Tested-by: T.J. Mercier <tjmercier@google.com>
Cc: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jaroslav Pulchart <jaroslav.pulchart@gooddata.com>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 16 insertions, 14 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bb7dacd8f753..e5fe4a94345f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4089,6 +4089,9 @@ 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)
@@ -4099,9 +4102,6 @@ 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);
 
@@ -4124,11 +4124,11 @@ 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);
 	}
 }
@@ -4635,7 +4635,7 @@ 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;
@@ -4710,7 +4710,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		cond_resched();
 	}
 
-	/* whether try_to_inc_max_seq() was successful */
+	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
 
@@ -4764,13 +4764,13 @@ 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;
+	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();
 
@@ -4781,6 +4781,10 @@ 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);
@@ -4865,16 +4869,14 @@ 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);