[PATCH RFC] mm: count zeromap read and set for swapout and swapin

[Barry Song]

From: Barry Song <v-songbaohua@xxxxxxxx>

When the proportion of folios from the zero map is small, missing their
accounting may not significantly impact profiling. However, it’s easy
to construct a scenario where this becomes an issue—for example,
allocating 1 GB of memory, writing zeros from userspace, followed by
MADV_PAGEOUT, and then swapping it back in. In this case, the swap-out
and swap-in counts seem to vanish into a black hole, potentially
causing semantic ambiguity.

We have two ways to address this:

1. Add a separate counter specifically for the zero map.
2. Continue using the current accounting, treating the zero map like
a normal backend. (This aligns with the current behavior of zRAM
when supporting same-page fills at the device level.)

This patch adopts option 2. I'm curious if others have different
opinions, so I'm marking it as RFC.

Fixes: 0ca0c24e3211 ("mm: store zero pages to be swapped out in a bitmap")
Cc: Usama Arif <usamaarif642@xxxxxxxxx>
Cc: Chengming Zhou <chengming.zhou@xxxxxxxxx>
Cc: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
Cc: Nhat Pham <nphamcs@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Cc: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Cc: Chris Li <chrisl@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Kairui Song <kasong@xxxxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
---
 mm/page_io.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/mm/page_io.c b/mm/page_io.c
index 5d9b6e6cf96c..90c5ea870038 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -226,6 +226,19 @@ static void swap_zeromap_folio_clear(struct folio *folio)
 	}
 }
 
+static inline void count_swpout_vm_event(struct folio *folio)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (unlikely(folio_test_pmd_mappable(folio))) {
+		count_memcg_folio_events(folio, THP_SWPOUT, 1);
+		count_vm_event(THP_SWPOUT);
+	}
+#endif
+	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
+	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
+	count_vm_events(PSWPOUT, folio_nr_pages(folio));
+}
+
 /*
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
@@ -258,6 +271,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 	 */
 	if (is_folio_zero_filled(folio)) {
 		swap_zeromap_folio_set(folio);
+		count_swpout_vm_event(folio);
 		folio_unlock(folio);
 		return 0;
 	} else {
@@ -282,19 +296,6 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 	return 0;
 }
 
-static inline void count_swpout_vm_event(struct folio *folio)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (unlikely(folio_test_pmd_mappable(folio))) {
-		count_memcg_folio_events(folio, THP_SWPOUT, 1);
-		count_vm_event(THP_SWPOUT);
-	}
-#endif
-	count_mthp_stat(folio_order(folio), MTHP_STAT_SWPOUT);
-	count_memcg_folio_events(folio, PSWPOUT, folio_nr_pages(folio));
-	count_vm_events(PSWPOUT, folio_nr_pages(folio));
-}
-
 #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
 static void bio_associate_blkg_from_page(struct bio *bio, struct folio *folio)
 {
@@ -621,6 +622,9 @@ void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
 	delayacct_swapin_start();
 
 	if (swap_read_folio_zeromap(folio)) {
+		count_mthp_stat(folio_order(folio), MTHP_STAT_SWPIN);
+		count_memcg_folio_events(folio, PSWPIN, folio_nr_pages(folio));
+		count_vm_events(PSWPIN, folio_nr_pages(folio));
 		folio_unlock(folio);
 		goto finish;
 	} else if (zswap_load(folio)) {
-- 
2.39.3 (Apple Git-146)