[RFC PATCH 4/5] mm: swap: fall back to order-0 after large swapin races

[fujunjie]

swapin_folio() documents that a large folio insertion race returns NULL
so the caller can fall back to order-0 swapin. do_swap_page() currently
turns that NULL into VM_FAULT_OOM if the PTE is unchanged, which is
harsher than necessary and gets in the way of rejecting large folio
ranges for backend reasons.

Move the synchronous swapin sequence into a helper and retry with an
order-0 folio when a large folio cannot be inserted into the swap cache.
Count the event as an mTHP swapin fallback before dropping the failed
large allocation.

Signed-off-by: fujunjie <fujunjie1@xxxxxx>
---
 mm/memory.c | 50 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 39 insertions(+), 11 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index ea6568571131..84e3b77b8293 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4757,6 +4757,44 @@ static struct folio *alloc_swap_folio(struct vm_fault *vmf)
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static struct folio *swapin_synchronous_folio(swp_entry_t entry,
+					      struct vm_fault *vmf)
+{
+	struct folio *swapcache, *folio;
+	bool large;
+	int order;
+
+	folio = alloc_swap_folio(vmf);
+	if (!folio)
+		return NULL;
+
+	large = folio_test_large(folio);
+	order = folio_order(folio);
+
+	/*
+	 * folio is charged, so swapin can only fail due to raced swapin and
+	 * return NULL.
+	 */
+	swapcache = swapin_folio(entry, folio);
+	if (swapcache == folio)
+		return folio;
+
+	if (!swapcache && large)
+		count_mthp_stat(order, MTHP_STAT_SWPIN_FALLBACK);
+	folio_put(folio);
+	if (swapcache || !large)
+		return swapcache;
+
+	folio = __alloc_swap_folio(vmf);
+	if (!folio)
+		return NULL;
+
+	swapcache = swapin_folio(entry, folio);
+	if (swapcache != folio)
+		folio_put(folio);
+	return swapcache;
+}
+
 /* Sanity check that a folio is fully exclusive */
 static void check_swap_exclusive(struct folio *folio, swp_entry_t entry,
 				 unsigned int nr_pages)
@@ -4860,17 +4898,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		swap_update_readahead(folio, vma, vmf->address);
 	if (!folio) {
 		if (data_race(si->flags & SWP_SYNCHRONOUS_IO)) {
-			folio = alloc_swap_folio(vmf);
-			if (folio) {
-				/*
-				 * folio is charged, so swapin can only fail due
-				 * to raced swapin and return NULL.
-				 */
-				swapcache = swapin_folio(entry, folio);
-				if (swapcache != folio)
-					folio_put(folio);
-				folio = swapcache;
-			}
+			folio = swapin_synchronous_folio(entry, vmf);
 		} else {
 			folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vmf);
 		}
-- 
2.34.1