[PATCH 1/2] tracing: mm: multigen-lru: fix mglru trace

[Huan Yang]

This patch add two reclaim stat:
nr_promote: nr_pages shrink before promote by folio_update_gen.
nr_demote: nr_pages NUMA demotion passed.

And then, use correct nr_scanned which evict_folios passed into
trace_mm_vmscan_lru_shrink_inactive.

Mistake info like this:
```
kswapd0-89    [000]    64.887613: mm_vmscan_lru_shrink_inactive:
nid=0 nr_scanned=64 nr_reclaimed=0 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=4
flags=RECLAIM_WB_FILE|RECLAIM_WB_ASYNC
```
Correct info like this:
```
 <...>-9041  [006]    43.738481: mm_vmscan_lru_shrink_inactive:
 nid=0 nr_scanned=13 nr_reclaimed=0 nr_dirty=0 nr_writeback=0
 nr_congested=0 nr_immediate=0 nr_activate_anon=9 nr_activate_file=0
 nr_ref_keep=0 nr_unmap_fail=0 nr_promote=4 nr_demote=0 priority=12
 flags=RECLAIM_WB_ANON|RECLAIM_WB_ASYNC
```

Signed-off-by: Huan Yang <link@xxxxxxxx>
---
 include/linux/vmstat.h        |  2 ++
 include/trace/events/vmscan.h |  8 +++++++-
 mm/vmscan.c                   | 26 +++++++++++++++++++++-----
 3 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index fed855bae6d8..ac2dd9168780 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -32,6 +32,8 @@ struct reclaim_stat {
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
 	unsigned nr_lazyfree_fail;
+	unsigned nr_promote;
+	unsigned nr_demote;
 };
 
 enum writeback_stat_item {
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 1a488c30afa5..9b403824a293 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -366,6 +366,8 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		__field(unsigned int, nr_activate1)
 		__field(unsigned long, nr_ref_keep)
 		__field(unsigned long, nr_unmap_fail)
+		__field(unsigned long, nr_promote)
+		__field(unsigned long, nr_demote)
 		__field(int, priority)
 		__field(int, reclaim_flags)
 	),
@@ -382,17 +384,21 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		__entry->nr_activate1 = stat->nr_activate[1];
 		__entry->nr_ref_keep = stat->nr_ref_keep;
 		__entry->nr_unmap_fail = stat->nr_unmap_fail;
+		__entry->nr_promote = stat->nr_promote;
+		__entry->nr_demote = stat->nr_demote;
 		__entry->priority = priority;
 		__entry->reclaim_flags = trace_reclaim_flags(file);
 	),
 
-	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld priority=%d flags=%s",
+	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d"
+	" nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld nr_promote=%ld nr_demote=%ld priority=%d flags=%s",
 		__entry->nid,
 		__entry->nr_scanned, __entry->nr_reclaimed,
 		__entry->nr_dirty, __entry->nr_writeback,
 		__entry->nr_congested, __entry->nr_immediate,
 		__entry->nr_activate0, __entry->nr_activate1,
 		__entry->nr_ref_keep, __entry->nr_unmap_fail,
+		__entry->nr_promote, __entry->nr_demote,
 		__entry->priority,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2cc0cb41fb32..21099b9f21e0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1063,8 +1063,10 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 
 		/* folio_update_gen() tried to promote this page? */
 		if (lru_gen_enabled() && !ignore_references &&
-		    folio_mapped(folio) && folio_test_referenced(folio))
+		    folio_mapped(folio) && folio_test_referenced(folio)) {
+			stat->nr_promote += nr_pages;
 			goto keep_locked;
+		}
 
 		/*
 		 * The number of dirty pages determines if a node is marked
@@ -1193,6 +1195,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 		    (thp_migration_supported() || !folio_test_large(folio))) {
 			list_add(&folio->lru, &demote_folios);
 			folio_unlock(folio);
+			stat->nr_demote += nr_pages;
 			continue;
 		}
 
@@ -4495,6 +4498,8 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 	int type;
 	int scanned;
 	int reclaimed;
+	unsigned long nr_taken = sc->nr_scanned;
+	unsigned int total_reclaimed = 0;
 	LIST_HEAD(list);
 	LIST_HEAD(clean);
 	struct folio *folio;
@@ -4521,10 +4526,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 		return scanned;
 retry:
 	reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
-	sc->nr_reclaimed += reclaimed;
-	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
-			scanned, reclaimed, &stat, sc->priority,
-			type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
+	total_reclaimed += reclaimed;
 
 	list_for_each_entry_safe_reverse(folio, next, &list, lru) {
 		if (!folio_evictable(folio)) {
@@ -4582,6 +4584,20 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 		goto retry;
 	}
 
+	/**
+	 * MGLRU scan_folios return nr_scanned no only contains
+	 * isolated folios. To get actually touched folios in
+	 * shrink_folios_list, we can record last nr_scanned which
+	 * sc saved, and sc nr_scanned will update for each folios
+	 * which we touched. New count sub last can get right nr_taken
+	 */
+	nr_taken = sc->nr_scanned - nr_taken;
+
+	sc->nr_reclaimed += total_reclaimed;
+	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id, nr_taken,
+					     total_reclaimed, &stat,
+					     sc->priority, type);
+
 	return scanned;
 }
 
-- 
2.34.1