[RFC v2 3/3] mm/lru_gen: expose oldest-generation page counts in memory.stat

[Zicheng Wang]

Add nr_oldest_anon and nr_oldest_file to memory.stat: pages in the
oldest generation (min_seq) of each type, aggregated over the cgroup
subtree and all N_MEMORY nodes.  This is the observation half of the
proactive-aging loop - it shows a policy how much anon/file memory the
next reclaim can evict directly, so it can decide whether aging is
needed.

Computed on demand from lrugen->nr_pages; no per-page maintenance, no
hot-path cost.  Paired with the AGING counter and workingset_refault_*
to confirm an aging pass took effect and was not too aggressive.

Gated by CONFIG_LRU_GEN; reported in pages, matching the lru_gen dump.

Signed-off-by: Zicheng Wang <wangzicheng@xxxxxxxxx>
---
 Documentation/admin-guide/cgroup-v2.rst | 18 ++++++++++++++++
 mm/internal.h                           |  2 ++
 mm/memcontrol.c                         | 24 +++++++++++++++++++++
 mm/vmscan.c                             | 28 +++++++++++++++++++++++++
 4 files changed, 72 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index f42ac6dddbf6..a071175d11be 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1658,6 +1658,24 @@ The following nested keys are defined.
 		the value for the foo counter, since the foo counter is type-based, not
 		list-based.
 
+	  nr_oldest_anon, nr_oldest_file
+		Number of pages in the oldest generation of the anonymous and
+		file types. Only present when CONFIG_LRU_GEN is enabled.
+
+		With MGLRU, page reclaim starts from the oldest generation
+		(min_seq) of each type, so these counts show how much anonymous
+		and file memory the next reclaim pass (or a proactive
+		memory.reclaim) can directly evict. They are aggregated across
+		this cgroup's subtree and all NUMA nodes, and are reported in
+		pages, matching the per-generation breakdown in the ``lru_gen``
+		debugfs file.
+
+		Proactive-aging policy can use them together with the ``aging``
+		counter and ``workingset_refault_*``: a large ``nr_oldest_file``
+		with near-zero ``nr_oldest_anon`` indicates file cache piling up
+		in the oldest generation while anonymous pages stay young, which
+		is the condition ``memory.aging`` is meant to rebalance.
+
 	  slab_reclaimable
 		Part of "slab" that might be reclaimed, such as
 		dentries and inodes.
diff --git a/mm/internal.h b/mm/internal.h
index 96add6cd4627..959d376c02a6 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -636,6 +636,8 @@ int user_proactive_reclaim(char *buf,
 
 #ifdef CONFIG_LRU_GEN
 int lru_gen_age_memcg(struct mem_cgroup *memcg, unsigned long nr_gens);
+void lru_gen_nr_oldest_pages(struct lruvec *lruvec,
+			     unsigned long *nr_anon, unsigned long *nr_file);
 #endif
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c6a969b56878..016194cabd60 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1733,6 +1733,30 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 		}
 	}
 
+#ifdef CONFIG_LRU_GEN
+	/* Oldest-generation (min_seq) anon/file pages over this cgroup's
+	 * subtree and all N_MEMORY nodes; see lru_gen_nr_oldest_pages().
+	 */
+	{
+		struct mem_cgroup *mi;
+		int nid;
+		unsigned long oldest_anon = 0, oldest_file = 0;
+
+		for_each_mem_cgroup_tree(mi, memcg) {
+			for_each_node_state(nid, N_MEMORY) {
+				unsigned long nr_anon, nr_file;
+				struct lruvec *lruvec = mem_cgroup_lruvec(mi, NODE_DATA(nid));
+
+				lru_gen_nr_oldest_pages(lruvec, &nr_anon, &nr_file);
+				oldest_anon += nr_anon;
+				oldest_file += nr_file;
+			}
+		}
+		seq_buf_printf(s, "nr_oldest_anon %lu\n", oldest_anon);
+		seq_buf_printf(s, "nr_oldest_file %lu\n", oldest_file);
+	}
+#endif
+
 	/* Accumulated memory events */
 	seq_buf_printf(s, "pgscan %lu\n",
 		       memcg_page_state(memcg, PGSCAN_KSWAPD) +
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 805e29c499c8..3800f0c4f1f5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5935,6 +5935,34 @@ int lru_gen_age_memcg(struct mem_cgroup *memcg, unsigned long nr_gens)
 	return ret;
 }
 
+/**
+ * lru_gen_nr_oldest_pages - pages in the oldest generation of a lruvec
+ * @lruvec: target lruvec
+ * @nr_anon: filled with oldest-generation anonymous page count
+ * @nr_file: filled with oldest-generation file page count
+ *
+ * Reclaim starts from the oldest generation (min_seq) of each type, so these
+ * count what the next reclaim can evict directly.  Computed from
+ * lrugen->nr_pages[min_seq type][zone]; eventually consistent, clamped to 0.
+ */
+void lru_gen_nr_oldest_pages(struct lruvec *lruvec,
+			     unsigned long *nr_anon, unsigned long *nr_file)
+{
+	int type, zone;
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+	unsigned long size[ANON_AND_FILE] = {};
+
+	for (type = 0; type < ANON_AND_FILE; type++) {
+		int gen = lru_gen_from_seq(READ_ONCE(lrugen->min_seq[type]));
+
+		for (zone = 0; zone < MAX_NR_ZONES; zone++)
+			size[type] += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+	}
+
+	*nr_anon = size[LRU_GEN_ANON];
+	*nr_file = size[LRU_GEN_FILE];
+}
+
 #else /* !CONFIG_LRU_GEN */
 
 static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
-- 
2.25.1