[PATCH 3/3] mm/mglru: add tracepoint for inc_max_seq()

[Ridong Chen <ridong.chen@linux.dev>]

From: Ridong Chen <chenridong@xiaomi.com>

Aging in MGLRU advances max_seq via inc_max_seq(), creating a new
youngest generation. There is currently no tracepoint on this path, so
the moment a new generation is created, and how the min_seq of each type
trails behind it, cannot be observed as it happens.

Add mm_mglru_inc_max_seq, emitted right after max_seq is bumped, with
the memcg id, the new max_seq, the anon and file min_seq, and the number
of pages in each generation for both types, summed over zones the same
way the debugfs lru_gen file reports them. The nr_anon/nr_file arrays are
indexed by generation slot, so the emitted max_seq/min_seq say which slot
holds which seq. They are printed with __print_array(), so the output is
hex and its length follows MAX_NR_GENS automatically. Paired with the
mm_mglru_scan_folios tracepoint it makes the full aging-to-eviction
window observable per memcg.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 include/trace/events/vmscan.h | 38 +++++++++++++++++++++++++++++++++++
 mm/vmscan.c                   | 22 ++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index c39dfacef033..9cf3f4564afb 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -455,6 +455,44 @@ TRACE_EVENT(mm_mglru_scan_folios,
 		__entry->min_seq)
 );
 
+TRACE_EVENT(mm_mglru_inc_max_seq,
+
+	TP_PROTO(u64 memcg_id,
+		unsigned long max_seq,
+		unsigned long anon_min_seq,
+		unsigned long file_min_seq,
+		unsigned long *nr_anon,
+		unsigned long *nr_file),
+
+	TP_ARGS(memcg_id, max_seq, anon_min_seq, file_min_seq, nr_anon, nr_file),
+
+	TP_STRUCT__entry(
+		__field(u64, memcg_id)
+		__field(unsigned long, max_seq)
+		__field(unsigned long, anon_min_seq)
+		__field(unsigned long, file_min_seq)
+		__array(unsigned long, nr_anon, MAX_NR_GENS)
+		__array(unsigned long, nr_file, MAX_NR_GENS)
+	),
+
+	TP_fast_assign(
+		__entry->memcg_id = memcg_id;
+		__entry->max_seq = max_seq;
+		__entry->anon_min_seq = anon_min_seq;
+		__entry->file_min_seq = file_min_seq;
+		memcpy(__entry->nr_anon, nr_anon, sizeof(__entry->nr_anon));
+		memcpy(__entry->nr_file, nr_file, sizeof(__entry->nr_file));
+	),
+
+	TP_printk("memcg_id=%llu max_seq=%lu anon_min_seq=%lu file_min_seq=%lu nr_anon=%s nr_file=%s",
+		__entry->memcg_id,
+		__entry->max_seq,
+		__entry->anon_min_seq,
+		__entry->file_min_seq,
+		__print_array(__entry->nr_anon, MAX_NR_GENS, sizeof(unsigned long)),
+		__print_array(__entry->nr_file, MAX_NR_GENS, sizeof(unsigned long)))
+);
+
 TRACE_EVENT(mm_vmscan_write_folio,
 
 	TP_PROTO(struct folio *folio),
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd1b9ecf2e84..d0e59baf5d5c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4100,6 +4100,26 @@ static void try_to_inc_min_seq(struct lruvec *lruvec, int swappiness)
 	}
 }
 
+static void trace_inc_max_seq(struct lruvec *lruvec)
+{
+	int type, gen;
+	unsigned long nr[ANON_AND_FILE][MAX_NR_GENS];
+	struct lru_gen_folio *lrugen = &lruvec->lrugen;
+
+	if (!trace_mm_mglru_inc_max_seq_enabled())
+		return;
+
+	for (type = 0; type < ANON_AND_FILE; type++)
+		for (gen = 0; gen < MAX_NR_GENS; gen++)
+			nr[type][gen] = lru_gen_seq_nr_pages(lrugen, gen, type);
+
+	trace_mm_mglru_inc_max_seq(mem_cgroup_id(lruvec_memcg(lruvec)),
+				   lrugen->max_seq,
+				   lrugen->min_seq[LRU_GEN_ANON],
+				   lrugen->min_seq[LRU_GEN_FILE],
+				   nr[LRU_GEN_ANON], nr[LRU_GEN_FILE]);
+}
+
 static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness)
 {
 	bool success;
@@ -4159,6 +4179,8 @@ static bool inc_max_seq(struct lruvec *lruvec, unsigned long seq, int swappiness
 	WRITE_ONCE(lrugen->timestamps[next], jiffies);
 	/* make sure preceding modifications appear */
 	smp_store_release(&lrugen->max_seq, lrugen->max_seq + 1);
+
+	trace_inc_max_seq(lruvec);
 unlock:
 	lruvec_unlock_irq(lruvec);
 
-- 
2.34.1