[PATCH v2 0/3] mm/mglru: add tracepoints for scan and aging paths

[PATCH v2 0/3] mm/mglru: add tracepoints for scan and aging paths

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

Background
==========

MGLRU currently has no tracepoints of its own. The scan and evict paths
reuse the classic-LRU tracepoints (trace_mm_vmscan_lru_isolate() and
trace_mm_vmscan_lru_shrink_inactive()), which predate MGLRU and carry no
generation, sequence, memcg or swappiness context. A trace of a running
system therefore cannot tell which memcg a given scan belongs to, how far
reclaim has progressed through the generations, or when a new generation
is created - so how MGLRU actually operates is effectively invisible.

Implementation
==============

Patch 1 is a cleanup that factors the per-generation page-count
summation into a helper, lru_gen_seq_nr_pages(), reused by patch 3.

Patch 2 adds mm_mglru_scan_folios on the scan path, and patch 3 adds
mm_mglru_inc_max_seq on the aging path. Both carry the memcg id and the
generation window (min_seq/max_seq), live at MGLRU-specific layers with
no classic-LRU counterpart, and are guarded so the hot paths stay
zero-cost when disabled.

Effect
======

Paired, the two tracepoints make the full aging-to-eviction window
observable per memcg: aging advances max_seq (the leading edge), scanning
consumes the oldest generations, and the min_seq/max_seq pair on each
event shows how the generation window moves over time.

A sample trace, with the classic-LRU tracepoints left enabled to show
how they interleave:

  mm_vmscan_lru_isolate: classzone=4 order=0 nr_requested=36 nr_scanned=31 nr_skipped=0 nr_taken=29 lru=inactive_file
  mm_mglru_scan_folios: memcg_id=73 classzone=4 order=0 nr_requested=36 nr_scanned=31 nr_sorted=2 nr_skipped=0 nr_taken=29 lru=inactive_file max_seq=3 tier=3 min_seq=0
  mm_vmscan_lru_shrink_inactive: nid=0 nr_scanned=31 nr_reclaimed=29 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=0 nr_unmap_fail=0 priority=5 flags=RECLAIM_WB_FILE|RECLAIM_WB_ASYNC
  mm_mglru_inc_max_seq: memcg_id=73 max_seq=4 anon_min_seq=1 file_min_seq=1 nr_anon={0x0,0x0,0x1,0x0} nr_file={0x0,0x427,0x6,0x4a}
  mm_vmscan_lru_isolate: classzone=4 order=0 nr_requested=5 nr_scanned=5 nr_skipped=0 nr_taken=1 lru=inactive_file
  mm_mglru_scan_folios: memcg_id=73 classzone=4 order=0 nr_requested=5 nr_scanned=5 nr_sorted=4 nr_skipped=0 nr_taken=1 lru=inactive_file max_seq=4 tier=3 min_seq=1
  mm_vmscan_lru_shrink_inactive: nid=0 nr_scanned=5 nr_reclaimed=1 nr_dirty=0 nr_writeback=0 nr_congested=0 nr_immediate=0 nr_activate_anon=0 nr_activate_file=0 nr_ref_keep=0 nr_unmap_fail=0 priority=5 flags=RECLAIM_WB_FILE|RECLAIM_WB_ASYNC

The mm_mglru_scan_folios lines carry the memcg id and the generation
window (max_seq/min_seq) that the bare mm_vmscan_lru_isolate lines above
them cannot - those cannot even say which memcg they came from. The
mm_mglru_inc_max_seq line then shows a new generation being created
(max_seq 3 -> 4) with the per-generation page counts for both types.

---
v2: address Sashiko AI review [1] - pass struct lruvec * into the tracepoints
    and do the memcg lookup inside TP_fast_assign.

[1] https://sashiko.dev/#/patchset/20260911072848.2346073-1-ridong.chen@linux.dev?part=2

Ridong Chen (3):
  mm/mglru: factor out lru_gen_seq_nr_pages()
  mm/mglru: add tracepoint for scan_folios()
  mm/mglru: add tracepoint for inc_max_seq()

 include/trace/events/vmscan.h | 101 ++++++++++++++++++++++++++++++++++
 mm/vmscan.c                   |  53 +++++++++++++++---
 2 files changed, 146 insertions(+), 8 deletions(-)

-- 
2.34.1

[PATCH v2 1/3] mm/mglru: factor out lru_gen_seq_nr_pages()

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

Both lruvec_evictable_size() and the debugfs lru_gen_seq_show() compute
the number of pages in a generation the same way: sum lrugen->nr_pages
over all zones for a given (gen, type) and clamp each term to >= 0.

Factor that out into lru_gen_seq_nr_pages() so the open-coded zone loop
lives in one place. No functional change.

A follow-up patch adds a tracepoint that needs the same per-generation
page count, and will reuse this helper instead of open-coding it again.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/vmscan.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 40d3f1b48a74..2554a6513aa8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2813,6 +2813,18 @@ static int get_nr_gens(struct lruvec *lruvec, int type)
 	return lruvec->lrugen.max_seq - lruvec->lrugen.min_seq[type] + 1;
 }
 
+/* the number of pages in a generation, summed over zones and clamped to >= 0 */
+static unsigned long lru_gen_seq_nr_pages(struct lru_gen_folio *lrugen, int gen, int type)
+{
+	int zone;
+	unsigned long size = 0;
+
+	for (zone = 0; zone < MAX_NR_ZONES; zone++)
+		size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+
+	return size;
+}
+
 static bool __maybe_unused seq_is_valid(struct lruvec *lruvec)
 {
 	int type;
@@ -4239,7 +4251,7 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control
 
 static unsigned long lruvec_evictable_size(struct lruvec *lruvec, int swappiness)
 {
-	int gen, type, zone;
+	int gen, type;
 	unsigned long seq, total = 0;
 	struct lru_gen_folio *lrugen = &lruvec->lrugen;
 	DEFINE_MAX_SEQ(lruvec);
@@ -4248,8 +4260,7 @@ static unsigned long lruvec_evictable_size(struct lruvec *lruvec, int swappiness
 	for_each_evictable_type(type, swappiness) {
 		for (seq = min_seq[type]; seq <= max_seq; seq++) {
 			gen = lru_gen_from_seq(seq);
-			for (zone = 0; zone < MAX_NR_ZONES; zone++)
-				total += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
+			total += lru_gen_seq_nr_pages(lrugen, gen, type);
 		}
 	}
 
@@ -5738,19 +5749,16 @@ static int lru_gen_seq_show(struct seq_file *m, void *v)
 		seq = 0;
 
 	for (; seq <= max_seq; seq++) {
-		int type, zone;
+		int type;
 		int gen = lru_gen_from_seq(seq);
 		unsigned long birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
 
 		seq_printf(m, " %10lu %10u", seq, jiffies_to_msecs(jiffies - birth));
 
 		for (type = 0; type < ANON_AND_FILE; type++) {
-			unsigned long size = 0;
+			unsigned long size = lru_gen_seq_nr_pages(lrugen, gen, type);
 			char mark = full && seq < min_seq[type] ? 'x' : ' ';
 
-			for (zone = 0; zone < MAX_NR_ZONES; zone++)
-				size += max(READ_ONCE(lrugen->nr_pages[gen][type][zone]), 0L);
-
 			seq_printf(m, " %10lu%c", size, mark);
 		}
 
-- 
2.34.1

[PATCH v2 2/3] mm/mglru: add tracepoint for scan_folios()

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

MGLRU's scan_folios() emits the classic-LRU tracepoint
trace_mm_vmscan_lru_isolate(), which predates MGLRU. It reports the
scan/isolate counts and the LRU type, but carries no generation or
memcg context, so a trace of an MGLRU run cannot tell which memcg a
given scan belongs to, nor how far reclaim has progressed through the
generations.

Add mm_mglru_scan_folios next to it, reporting the same counters plus
nr_sorted (folios moved to a younger generation by sort_folio()) and
the MGLRU context the classic tracepoint lacks: the memcg id, and the
max_seq, tier and min_seq of the type being scanned.

scan_folios() is the MGLRU-specific layer where folios are actually
scanned, so it has no classic-LRU counterpart. That the classic
trace_mm_vmscan_lru_isolate() has lived here stably shows this is a
long-lived place to hook, and the new tracepoint can be enabled on its
own to observe the MGLRU-specific information. The existing tracepoint
is left unchanged.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 include/trace/events/vmscan.h | 63 +++++++++++++++++++++++++++++++++++
 mm/vmscan.c                   |  6 ++++
 2 files changed, 69 insertions(+)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 8a872990b4be..5defa8f6719c 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -392,6 +392,69 @@ TRACE_EVENT(mm_vmscan_lru_isolate,
 		__print_symbolic(__entry->lru, LRU_NAMES))
 );
 
+TRACE_EVENT(mm_mglru_scan_folios,
+
+	TP_PROTO(struct lruvec *lruvec,
+		int highest_zoneidx,
+		int order,
+		unsigned long nr_requested,
+		unsigned long nr_scanned,
+		unsigned long nr_sorted,
+		unsigned long nr_skipped,
+		unsigned long nr_taken,
+		int lru,
+		unsigned long max_seq,
+		int tier,
+		unsigned long min_seq),
+
+	TP_ARGS(lruvec, highest_zoneidx, order, nr_requested, nr_scanned,
+		nr_sorted, nr_skipped, nr_taken, lru, max_seq, tier, min_seq),
+
+	TP_STRUCT__entry(
+		__field(u64, memcg_id)
+		__field(int, highest_zoneidx)
+		__field(int, order)
+		__field(unsigned long, nr_requested)
+		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_sorted)
+		__field(unsigned long, nr_skipped)
+		__field(unsigned long, nr_taken)
+		__field(int, lru)
+		__field(unsigned long, max_seq)
+		__field(int, tier)
+		__field(unsigned long, min_seq)
+	),
+
+	TP_fast_assign(
+		__entry->memcg_id = mem_cgroup_id(lruvec_memcg(lruvec));
+		__entry->highest_zoneidx = highest_zoneidx;
+		__entry->order = order;
+		__entry->nr_requested = nr_requested;
+		__entry->nr_scanned = nr_scanned;
+		__entry->nr_sorted = nr_sorted;
+		__entry->nr_skipped = nr_skipped;
+		__entry->nr_taken = nr_taken;
+		__entry->lru = lru;
+		__entry->max_seq = max_seq;
+		__entry->tier = tier;
+		__entry->min_seq = min_seq;
+	),
+
+	TP_printk("memcg_id=%llu classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_sorted=%lu nr_skipped=%lu nr_taken=%lu lru=%s max_seq=%lu tier=%d min_seq=%lu",
+		__entry->memcg_id,
+		__entry->highest_zoneidx,
+		__entry->order,
+		__entry->nr_requested,
+		__entry->nr_scanned,
+		__entry->nr_sorted,
+		__entry->nr_skipped,
+		__entry->nr_taken,
+		__print_symbolic(__entry->lru, LRU_NAMES),
+		__entry->max_seq,
+		__entry->tier,
+		__entry->min_seq)
+);
+
 TRACE_EVENT(mm_vmscan_write_folio,
 
 	TP_PROTO(struct folio *folio),
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2554a6513aa8..67f59aa73fb9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4876,6 +4876,12 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec,
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
 				scanned, skipped, isolated,
 				type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
+	trace_mm_mglru_scan_folios(lruvec,
+				   sc->reclaim_idx, sc->order, nr_to_scan,
+				   scanned, sorted, skipped, isolated,
+				   type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON,
+				   lrugen->max_seq, tier,
+				   lrugen->min_seq[type]);
 
 	*isolatedp = isolated;
 	return scanned;
-- 
2.34.1

[PATCH v2 3/3] mm/mglru: add tracepoint for inc_max_seq()

[Ridong Chen]

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                   | 23 +++++++++++++++++++++
 2 files changed, 61 insertions(+)

diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 5defa8f6719c..a20c6b2e062f 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(struct lruvec *lruvec,
+		unsigned long max_seq,
+		unsigned long anon_min_seq,
+		unsigned long file_min_seq,
+		unsigned long *nr_anon,
+		unsigned long *nr_file),
+
+	TP_ARGS(lruvec, 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 = mem_cgroup_id(lruvec_memcg(lruvec));
+		__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 67f59aa73fb9..d1495a7d469d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4100,6 +4100,27 @@ 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;
+
+	if (!trace_mm_mglru_inc_max_seq_enabled())
+		return;
+
+	lrugen = &lruvec->lrugen;
+	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(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 +4180,8 @@ 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