mm/migrate: correct nr_failed in migrate_pages_sync()

nr_failed was missing the large folio splits from migrate_pages_batch()
and can cause a mismatch between migrate_pages() return value and the
number of not migrated pages, i.e., when the return value of
migrate_pages() is 0, there are still pages left in the from page list. 
It will happen when a non-PMD THP large folio fails to migrate due to
-ENOMEM and is split successfully but not all the split pages are not
migrated, migrate_pages_batch() would return non-zero, but
astats.nr_thp_split = 0.  nr_failed would be 0 and returned to the caller
of migrate_pages(), but the not migrated pages are left in the from page
list without being added back to LRU lists.

Fix it by adding a new nr_split counter for large folio splits and adding
it to nr_failed in migrate_page_sync() after migrate_pages_batch() is
done.

Link: https://lkml.kernel.org/r/20231017163129.2025214-1-zi.yan@sent.com
Fixes: 2ef7dbb26990 ("migrate_pages: try migrate in batch asynchronously firstly")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: Huang Ying <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 13 insertions, 3 deletions

diff --git a/mm/migrate.c b/mm/migrate.c
index 71fc5064cec6..53244d283c3e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1495,6 +1495,7 @@ struct migrate_pages_stats {
 	int nr_thp_succeeded;	/* THP migrated successfully */
 	int nr_thp_failed;	/* THP failed to be migrated */
 	int nr_thp_split;	/* THP split before migrating */
+	int nr_split;	/* Large folio (include THP) split before migrating */
 };
 
 /*
@@ -1614,6 +1615,7 @@ static int migrate_pages_batch(struct list_head *from,
 	int nr_retry_pages = 0;
 	int pass = 0;
 	bool is_thp = false;
+	bool is_large = false;
 	struct folio *folio, *folio2, *dst = NULL, *dst2;
 	int rc, rc_saved = 0, nr_pages;
 	LIST_HEAD(unmap_folios);
@@ -1629,7 +1631,8 @@ static int migrate_pages_batch(struct list_head *from,
 		nr_retry_pages = 0;
 
 		list_for_each_entry_safe(folio, folio2, from, lru) {
-			is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio);
+			is_large = folio_test_large(folio);
+			is_thp = is_large && folio_test_pmd_mappable(folio);
 			nr_pages = folio_nr_pages(folio);
 
 			cond_resched();
@@ -1649,6 +1652,7 @@ static int migrate_pages_batch(struct list_head *from,
 				stats->nr_thp_failed++;
 				if (!try_split_folio(folio, split_folios)) {
 					stats->nr_thp_split++;
+					stats->nr_split++;
 					continue;
 				}
 				stats->nr_failed_pages += nr_pages;
@@ -1677,11 +1681,12 @@ static int migrate_pages_batch(struct list_head *from,
 				nr_failed++;
 				stats->nr_thp_failed += is_thp;
 				/* Large folio NUMA faulting doesn't split to retry. */
-				if (folio_test_large(folio) && !nosplit) {
+				if (is_large && !nosplit) {
 					int ret = try_split_folio(folio, split_folios);
 
 					if (!ret) {
 						stats->nr_thp_split += is_thp;
+						stats->nr_split += is_large;
 						break;
 					} else if (reason == MR_LONGTERM_PIN &&
 						   ret == -EAGAIN) {
@@ -1827,6 +1832,7 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
 	stats->nr_succeeded += astats.nr_succeeded;
 	stats->nr_thp_succeeded += astats.nr_thp_succeeded;
 	stats->nr_thp_split += astats.nr_thp_split;
+	stats->nr_split += astats.nr_split;
 	if (rc < 0) {
 		stats->nr_failed_pages += astats.nr_failed_pages;
 		stats->nr_thp_failed += astats.nr_thp_failed;
@@ -1834,7 +1840,11 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
 		return rc;
 	}
 	stats->nr_thp_failed += astats.nr_thp_split;
-	nr_failed += astats.nr_thp_split;
+	/*
+	 * Do not count rc, as pages will be retried below.
+	 * Count nr_split only, since it includes nr_thp_split.
+	 */
+	nr_failed += astats.nr_split;
 	/*
 	 * Fall back to migrate all failed folios one by one synchronously. All
 	 * failed folios except split THPs will be retried, so their failure