[PATCH 9/9] mm/mglru: count PUD subtrees skipped by the PUD-level filter

Add MM_PUD_EMPTY_SKIPPED, incremented in walk_pud_range() whenever a PUD
subtree is skipped by the filter. Like other counters accumulated
per walk, shown in debugfs lru_gen output (the "S" column of TYFALWEES)
and via the mm_vmscan_lru_gen_walk tracepoint, so the avoided cost
by the filter can be measured directly.

Signed-off-by: Baoquan He <[email protected]>
---
 include/linux/mmzone.h        |  1 +
 include/trace/events/vmscan.h | 10 ++++++----
 mm/vmscan.c                   | 13 ++++++++-----
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 64eb010624b2..a039df84f907 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -599,6 +599,7 @@ enum {
 	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 */
+	MM_PUD_EMPTY_SKIPPED,	/* PUD subtrees skipped by the PUD-level filter */
 	NR_MM_STATS
 };
 
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index c7c2034715b6..923fbdb20de6 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -662,9 +662,9 @@ TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless,
 TRACE_EVENT(mm_vmscan_lru_gen_walk,
 
 	TP_PROTO(int nid, unsigned long seq, int leaf_total,
-		 int leaf_eligible, bool empty),
+		 int leaf_eligible, bool empty, int pud_skipped),
 
-	TP_ARGS(nid, seq, leaf_total, leaf_eligible, empty),
+	TP_ARGS(nid, seq, leaf_total, leaf_eligible, empty, pud_skipped),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
@@ -672,6 +672,7 @@ TRACE_EVENT(mm_vmscan_lru_gen_walk,
 		__field(int, leaf_total)
 		__field(int, leaf_eligible)
 		__field(bool, empty)
+		__field(int, pud_skipped)
 	),
 
 	TP_fast_assign(
@@ -680,11 +681,12 @@ TRACE_EVENT(mm_vmscan_lru_gen_walk,
 		__entry->leaf_total = leaf_total;
 		__entry->leaf_eligible = leaf_eligible;
 		__entry->empty = empty;
+		__entry->pud_skipped = pud_skipped;
 	),
 
-	TP_printk("nid=%d seq=%lu leaf_total=%d leaf_eligible=%d empty=%d",
+	TP_printk("nid=%d seq=%lu leaf_total=%d leaf_eligible=%d empty=%d pud_skipped=%d",
 		__entry->nid, __entry->seq, __entry->leaf_total,
-		__entry->leaf_eligible, __entry->empty)
+		__entry->leaf_eligible, __entry->empty, __entry->pud_skipped)
 );
 
 #endif /* _TRACE_VMSCAN_H */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cc41d3692bd5..fa437b187a05 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3868,8 +3868,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long start, unsigned long end,
 			continue;
 
 		/* Skip a subtree whose 512 PMDs all failed the PMD-level filter last gen */
-		if (!walk->force_scan && !test_pud_bloom_filter(mm_state, walk->seq, pud + i))
+		if (!walk->force_scan && !test_pud_bloom_filter(mm_state, walk->seq, pud + i)) {
+			walk->mm_stats[MM_PUD_EMPTY_SKIPPED]++;
 			continue;
+		}
 
 		if (walk_pmd_range(&val, addr, next, args))
 			update_pud_bloom_filter(mm_state, walk->seq + 1, pud + i);
@@ -4213,7 +4215,8 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
 			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);
+					walk->mm_stats[MM_LEAF_ELIGIBLE], empty,
+					walk->mm_stats[MM_PUD_EMPTY_SKIPPED]);
 		}
 	} while (mm);
 done:
@@ -5698,14 +5701,14 @@ 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 = "xxxxxxxx";
+		const char *s = "xxxxxxxxx";
 		unsigned long n = 0;
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
-			s = "TYFALWEE";
+			s = "TYFALWEES";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
-			s = "tyfalwee";
+			s = "tyfalwees";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
-- 
2.54.0