From: Zhaoyang Huang <zhaoyang.huang@unisoc.com>

This submission addresses an issue where the memcg MGLRU's min_seq is
pinned by an orphan page—a page that resides in the page cache but
lacks a corresponding reference count, while the number of GENs has not
yet met the criteria of aging. I believe such pages should be detected
and handled elsewhere rather than affecting the LRU in this way(legacy
LRU could move forward by bringing this kind of folio along with).
Therefore, I propose moving these folios to the next generation when
isolation makes no progress at all.

Signed-off-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
---
 include/linux/mmzone.h |  6 ++++++
 mm/vmscan.c            | 45 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9adb2ad21da5..b063c56ea30c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -434,6 +434,12 @@ enum lruvec_flags {
 	 */
 	LRUVEC_CGROUP_CONGESTED,
 	LRUVEC_NODE_CONGESTED,
+	/*
+	 * MGLRU: eviction failed to isolate from the oldest generation once
+	 * while the window was at MAX_NR_GENS. A second consecutive failure
+	 * forces aging so residual folios cannot pin min_seq indefinitely.
+	 */
+	LRUVEC_MGLRU_ISOLATE_FAILED,
 };
 
 #endif /* !__GENERATING_BOUNDS_H */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd1b1aa12581..c18db08c5e10 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -175,6 +175,8 @@ struct scan_control {
 		unsigned int immediate;
 		unsigned int file_taken;
 		unsigned int taken;
+		/* folios isolated by MGLRU eviction in the current lruvec pass */
+		unsigned int isolated;
 	} nr;
 
 	/* for recording the reclaimed slab by now */
@@ -4748,6 +4750,7 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, scan_batch,
 				scanned, skipped, isolated,
 				type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
+	sc->nr.isolated += isolated;
 	if (type == LRU_GEN_FILE)
 		sc->nr.file_taken += isolated;
 	/*
@@ -4998,6 +5001,11 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	long nr_to_scan;
 	unsigned long scanned = 0;
 	int swappiness = get_swappiness(lruvec, sc);
+	bool attempted = false;
+	bool rotated = false;
+
+	/* per-lruvec pass; sc is shared across lruvecs during reclaim */
+	sc->nr.isolated = 0;
 
 	while (true) {
 		int delta;
@@ -5006,6 +5014,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		if (nr_to_scan <= 0)
 			break;
 
+		attempted = true;
 		delta = evict_folios(nr_to_scan, lruvec, sc, swappiness);
 		if (!delta)
 			break;
@@ -5020,6 +5029,40 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		cond_resched();
 	}
 
+	/*
+	 * Eviction isolated nothing while the sliding window is already at
+	 * MAX_NR_GENS. In that state should_run_aging() is false, so
+	 * get_nr_to_scan() never calls try_to_inc_max_seq(). Residual folios
+	 * that fail isolate_folio() can pin min_seq and hide reclaimable
+	 * folios in younger generations.
+	 *
+	 * Require two consecutive isolate failures on this lruvec before
+	 * forcing aging, so a single no-progress batch does not rotate the
+	 * window. Successful isolation clears the sticky bit.
+	 *
+	 * Key off sc->nr.isolated, not nr_reclaimed: folios isolated but
+	 * rejected by shrink_folio_list() are put back with PG_active and do
+	 * not pin the oldest generation.
+	 */
+	if (attempted && !sc->nr.isolated) {
+		DEFINE_MAX_SEQ(lruvec);
+		DEFINE_MIN_SEQ(lruvec);
+
+		if (evictable_min_seq(min_seq, swappiness) + MIN_NR_GENS < max_seq) {
+			if (test_and_set_bit(LRUVEC_MGLRU_ISOLATE_FAILED,
+					     &lruvec->flags)) {
+				rotated = try_to_inc_max_seq(lruvec, max_seq,
+							     swappiness, false);
+				clear_bit(LRUVEC_MGLRU_ISOLATE_FAILED,
+					  &lruvec->flags);
+			}
+		} else {
+			clear_bit(LRUVEC_MGLRU_ISOLATE_FAILED, &lruvec->flags);
+		}
+	} else if (sc->nr.isolated) {
+		clear_bit(LRUVEC_MGLRU_ISOLATE_FAILED, &lruvec->flags);
+	}
+
 	/*
 	 * If too many file cache in the coldest generation can't be evicted
 	 * due to being dirty, wake up the flusher.
@@ -5043,7 +5086,7 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 	}
 
 	/* whether this lruvec should be rotated */
-	return nr_to_scan < 0;
+	return nr_to_scan < 0 || rotated;
 }
 
 static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
-- 
2.25.1