[PATCH 1/4] mm/mglru: add MM_WALK_EMPTY stats and tracepoint for cross-node measurement

Add infrastructure to quantify cross-node empty page table walks in the
MGLRU aging path. These are walks that traverse an mm's page tables but
find no folio belonging to the current lruvec (node+memcg) - pure waste
caused by lru_gen_use_mm() setting mm->lru_gen.bitmap to -1 (all nodes)
at context switch.

New per-walk counters (accumulated in mm_state->stats[]):

  MM_LEAF_ELIGIBLE    - folios belonging to this lruvec
  MM_WALK_TOTAL       - page-table walks completed
  MM_WALK_EMPTY       - walks that found no eligible folio
  MM_LEAF_TOTAL_EMPTY - leaf entries scanned by empty walks

A new tracepoint, mm_vmscan_lru_gen_walk(nid, seq, leaf_total,
leaf_eligible, empty), fires after each walk for live monitoring. The
debugfs lru_gen output format is updated ("TYFA" -> "TYFALWEE") to
display the new fields.

This series uses these counters to quantify the cross-node empty walk
cost and to validate the suppression implemented by the follow-up
patches.

Signed-off-by: Baoquan He <[email protected]>
---
 include/linux/mmzone.h        |  4 ++++
 include/trace/events/vmscan.h | 28 ++++++++++++++++++++++++++++
 mm/vmscan.c                   | 30 ++++++++++++++++++++++++++----
 3 files changed, 58 insertions(+), 4 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a26c8b855222..34938d4f8e23 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -595,6 +595,10 @@ enum {
 	MM_LEAF_YOUNG,		/* young leaf entries */
 	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
 	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
+	MM_LEAF_ELIGIBLE,	/* folios belonging to this lruvec (node+memcg) */
+	MM_WALK_TOTAL,		/* page-table walks completed */
+	MM_WALK_EMPTY,		/* walks that found no eligible folio */
+	MM_LEAF_TOTAL_EMPTY,	/* leaf entries scanned by empty walks */
 	NR_MM_STATS
 };
 
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index b4bf7b8def1f..c7c2034715b6 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -659,6 +659,34 @@ TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless,
 		__entry->nid,
 		__print_symbolic(__entry->reason, kswapd_clear_hopeless_reason_ops))
 );
+TRACE_EVENT(mm_vmscan_lru_gen_walk,
+
+	TP_PROTO(int nid, unsigned long seq, int leaf_total,
+		 int leaf_eligible, bool empty),
+
+	TP_ARGS(nid, seq, leaf_total, leaf_eligible, empty),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(unsigned long, seq)
+		__field(int, leaf_total)
+		__field(int, leaf_eligible)
+		__field(bool, empty)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->seq = seq;
+		__entry->leaf_total = leaf_total;
+		__entry->leaf_eligible = leaf_eligible;
+		__entry->empty = empty;
+	),
+
+	TP_printk("nid=%d seq=%lu leaf_total=%d leaf_eligible=%d empty=%d",
+		__entry->nid, __entry->seq, __entry->leaf_total,
+		__entry->leaf_eligible, __entry->empty)
+);
+
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 17d2b793cbfc..83de2b147919 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3587,6 +3587,8 @@ static bool walk_pte_range(pmd_t *pmd, unsigned long start, unsigned long end,
 		if (!folio)
 			continue;
 
+		walk->mm_stats[MM_LEAF_ELIGIBLE]++;
+
 		if (folio_test_large(folio)) {
 			const unsigned int max_nr = (end - addr) >> PAGE_SHIFT;
 
@@ -3687,6 +3689,8 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		if (!folio)
 			goto next;
 
+		walk->mm_stats[MM_LEAF_ELIGIBLE]++;
+
 		if (!pmdp_test_and_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
@@ -4108,8 +4112,26 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 
 	do {
 		success = iterate_mm_list(walk, &mm);
-		if (mm)
+		if (mm) {
+			bool empty = false;
+
 			walk_mm(mm, walk);
+			/* A walk that traversed page tables but found no folio
+			 * belonging to this lruvec (node+memcg) is pure waste. */
+			if (walk->mm_stats[MM_LEAF_TOTAL]) {
+				walk->mm_stats[MM_WALK_TOTAL]++;
+				if (walk->mm_stats[MM_LEAF_ELIGIBLE] == 0) {
+					walk->mm_stats[MM_WALK_EMPTY]++;
+					walk->mm_stats[MM_LEAF_TOTAL_EMPTY] +=
+						walk->mm_stats[MM_LEAF_TOTAL];
+					empty = true;
+				}
+			}
+			trace_mm_vmscan_lru_gen_walk(
+					lruvec_pgdat(lruvec)->node_id, walk->seq,
+					walk->mm_stats[MM_LEAF_TOTAL],
+					walk->mm_stats[MM_LEAF_ELIGIBLE], empty);
+		}
 	} while (mm);
 done:
 	if (success) {
@@ -5588,14 +5610,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 
 	seq_puts(m, "                      ");
 	for (i = 0; i < NR_MM_STATS; i++) {
-		const char *s = "xxxx";
+		const char *s = "xxxxxxxx";
 		unsigned long n = 0;
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
-			s = "TYFA";
+			s = "TYFALWEE";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
-			s = "tyfa";
+			s = "tyfalwee";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
-- 
2.54.0