Commit 16b475d2ac3c ("mm/mglru: avoid reclaim type fall back when
isolation makes no progress") uses scanned == 0 to determine
whether scan_folios() has exhausted a reclaim type. However,
this is not always sufficient. It is possible for scanned > 0,
while the oldest reclaimable generation is exhausted after the
first scan_folios() call.

We detect early_stop in scan_folios(). If we stop early for any reason,
it means the current reclaim type is not exhausted yet. If early_stop is
never reached, it means we have exhausted the current oldest generation
without hitting any scanning limit.

Another issue is that if the lruvec has 4 generations, we might have
exhausted the oldest generation while the second oldest generation is
still reclaimable. In that case, this type is not exhausted yet.

Add an exhausted output argument to scan_folios() so it can
explicitly report whether the reclaimable lists for the current
type have been exhausted.

Signed-off-by: Barry Song (Xiaomi) <baohua@kernel.org>
---
 mm/vmscan.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index ea058692b9a5..0670a25d3a7e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4727,7 +4727,8 @@ static bool isolate_folio(struct lruvec *lruvec, struct folio *folio, struct sca
 
 static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 		       struct scan_control *sc, int type, int tier,
-		       struct list_head *list, int *isolatedp)
+		       struct list_head *list, int *isolatedp,
+		       bool *exhausted)
 {
 	int i;
 	int gen;
@@ -4738,12 +4739,15 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	int skipped = 0;
 	unsigned long remaining = nr_to_scan;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	bool early_stop = false;
 
 	VM_WARN_ON_ONCE(nr_to_scan > MAX_LRU_BATCH);
 	VM_WARN_ON_ONCE(!list_empty(list));
 
-	if (get_nr_gens(lruvec, type) == MIN_NR_GENS)
+	if (get_nr_gens(lruvec, type) == MIN_NR_GENS) {
+		*exhausted = true;
 		return 0;
+	}
 
 	gen = lru_gen_from_seq(lrugen->min_seq[type]);
 
@@ -4774,8 +4778,10 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 				skipped_zone += delta;
 			}
 
-			if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH)
+			if (!--remaining || max(isolated, skipped_zone) >= MIN_LRU_BATCH) {
+				early_stop = true;
 				break;
+			}
 		}
 
 		if (skipped_zone) {
@@ -4784,8 +4790,10 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 			skipped += skipped_zone;
 		}
 
-		if (!remaining || isolated >= MIN_LRU_BATCH)
+		if (!remaining || isolated >= MIN_LRU_BATCH) {
+			early_stop = true;
 			break;
+		}
 	}
 
 	item = PGSCAN_KSWAPD + reclaimer_offset(sc);
@@ -4796,6 +4804,13 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 				scanned, skipped, isolated,
 				type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
 
+	/*
+	 * If we didn't stop early, all reclaimable folios in the current
+	 * generation have been scanned. We are exhausted if this is the last
+	 * reclaimable generation.
+	 */
+	*exhausted = !early_stop &&
+		     lrugen->min_seq[type] + MIN_NR_GENS == lrugen->max_seq;
 	*isolatedp = isolated;
 	return scanned;
 }
@@ -4853,11 +4868,12 @@ static int isolate_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	bool type_fallback_allowed = !is_single_type_reclaim(swappiness);
 	int type = get_type_to_scan(lruvec, swappiness);
 	int total_scanned = 0, scanned, tier;
+	bool exhausted;
 
 retry:
 	tier = get_tier_idx(lruvec, type);
 	scanned = scan_folios(nr_to_scan, lruvec, sc,
-			      type, tier, list, isolated);
+			      type, tier, list, isolated, &exhausted);
 
 	total_scanned += scanned;
 	if (*isolated) {
@@ -4870,7 +4886,7 @@ static int isolate_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	 * We are running out of the current reclaim type. Fall back to
 	 * the other type if allowed.
 	 */
-	if (!scanned && type_fallback_allowed) {
+	if (exhausted && type_fallback_allowed) {
 		type = !type;
 		type_fallback_allowed = false;
 		goto retry;
-- 
2.34.1