[PATCH v6 7/7] 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 while
the lruvec lock is still held, with the node id, memcg id, the new
max_seq, the anon and file min_seq, and the number of pages in each
generation for both types, as computed by lruvec_gen_size().

The nr_anon/nr_file arrays are ordered by seq rather than by generation
slot: entry i holds the generation max_seq - MAX_NR_GENS + 1 + i, i.e.
they go from the oldest generation to the newest, the same order as the
debugfs lru_gen file, so the output can be read directly without mapping
slots back to seqs. Entries for seqs below the corresponding min_seq are
not in use and normally read as 0. The arrays are printed with
__print_array(), so the output is hex and its length follows
MAX_NR_GENS automatically.

Only the lruvec is passed in; all of the above is collected in
TP_fast_assign(), so inc_max_seq() does no extra work when the event is
disabled. Paired with mm_mglru_scan_folios it makes the full
aging-to-eviction window observable per memcg.

Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/trace_vmscan.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/vmscan.c       |  2 ++
 2 files changed, 48 insertions(+)

diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
index 8148b8224422..40d6d90f1d7a 100644
--- a/mm/trace_vmscan.h
+++ b/mm/trace_vmscan.h
@@ -456,6 +456,52 @@ TRACE_EVENT(mm_mglru_scan_folios,
 		__entry->min_seq)
 );
 
+TRACE_EVENT(mm_mglru_inc_max_seq,
+
+	TP_PROTO(struct lruvec *lruvec),
+
+	TP_ARGS(lruvec),
+
+	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)
+		__field(int, nid)
+	),
+
+	TP_fast_assign(
+		struct lru_gen_folio *lrugen = &lruvec->lrugen;
+		unsigned long max_seq = lrugen->max_seq;
+		int i;
+
+		__entry->memcg_id = mem_cgroup_id(lruvec_memcg(lruvec));
+		__entry->max_seq = max_seq;
+		__entry->anon_min_seq = lrugen->min_seq[LRU_GEN_ANON];
+		__entry->file_min_seq = lrugen->min_seq[LRU_GEN_FILE];
+		/* from the oldest generation to the newest, as debugfs lru_gen does */
+		for (i = 0; i < MAX_NR_GENS; i++) {
+			unsigned long seq = max_seq - MAX_NR_GENS + 1 + i;
+
+			__entry->nr_anon[i] =
+				lruvec_gen_size(lrugen, LRU_GEN_ANON, seq);
+			__entry->nr_file[i] =
+				lruvec_gen_size(lrugen, LRU_GEN_FILE, seq);
+		}
+		__entry->nid = lruvec_pgdat(lruvec)->node_id;
+	),
+
+	TP_printk("nid=%d memcg_id=%llu max_seq=%lu anon_min_seq=%lu file_min_seq=%lu nr_anon=%s nr_file=%s",
+		__entry->nid,
+		__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)))
+);
 #endif /* CONFIG_LRU_GEN */
 
 TRACE_EVENT(mm_vmscan_write_folio,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1581b73aec56..841fefa68d1f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4115,6 +4115,8 @@ 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_mm_mglru_inc_max_seq(lruvec);
 unlock:
 	lruvec_unlock_irq(lruvec);
 
-- 
2.34.1