[PATCH v2 2/4] mm/huge_memory: replace can_split_folio() with direct refcount calculation

[Zi Yan <ziy@nvidia.com>]

can_split_folio() is just a refcount comparison, making sure only the
split caller holds an extra pin. Open code it with
folio_expected_ref_count() != folio_ref_count() - 1. For the extra_pins
used by folio_ref_freeze(), add folio_cache_references() to calculate it.

Suggested-by: David Hildenbrand (Red Hat) <david@kernel.org>
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/huge_mm.h |  1 -
 mm/huge_memory.c        | 43 ++++++++++++++++-------------------------
 mm/vmscan.c             |  3 ++-
 3 files changed, 19 insertions(+), 28 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 97686fb46e30..1ecaeccf39c9 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -369,7 +369,6 @@ enum split_type {
 	SPLIT_TYPE_NON_UNIFORM,
 };
 
-bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
 int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
 int folio_split_unmapped(struct folio *folio, unsigned int new_order);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c1f1055165dd..6c821c1c0ac3 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3455,23 +3455,6 @@ static void lru_add_split_folio(struct folio *folio, struct folio *new_folio,
 	}
 }
 
-/* Racy check whether the huge page can be split */
-bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
-{
-	int extra_pins;
-
-	/* Additional pins from page cache */
-	if (folio_test_anon(folio))
-		extra_pins = folio_test_swapcache(folio) ?
-				folio_nr_pages(folio) : 0;
-	else
-		extra_pins = folio_nr_pages(folio);
-	if (pextra_pins)
-		*pextra_pins = extra_pins;
-	return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins -
-					caller_pins;
-}
-
 static bool page_range_has_hwpoisoned(struct page *page, long nr_pages)
 {
 	for (; nr_pages; page++, nr_pages--)
@@ -3776,17 +3759,26 @@ int folio_check_splittable(struct folio *folio, unsigned int new_order,
 	return 0;
 }
 
+/* Number of folio references from the pagecache or the swapcache. */
+static unsigned int folio_cache_references(const struct folio *folio)
+{
+	if (folio_test_anon(folio) && !folio_test_swapcache(folio))
+		return 0;
+	return folio_nr_pages(folio);
+}
+
 static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int new_order,
 					     struct page *split_at, struct xa_state *xas,
 					     struct address_space *mapping, bool do_lru,
 					     struct list_head *list, enum split_type split_type,
-					     pgoff_t end, int *nr_shmem_dropped, int extra_pins)
+					     pgoff_t end, int *nr_shmem_dropped)
 {
 	struct folio *end_folio = folio_next(folio);
 	struct folio *new_folio, *next;
 	int old_order = folio_order(folio);
 	int ret = 0;
 	struct deferred_split *ds_queue;
+	int extra_pins = folio_cache_references(folio);
 
 	VM_WARN_ON_ONCE(!mapping && end);
 	/* Prevent deferred_split_scan() touching ->_refcount */
@@ -3956,7 +3948,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	struct folio *new_folio, *next;
 	int nr_shmem_dropped = 0;
 	int remap_flags = 0;
-	int extra_pins, ret;
+	int ret;
 	pgoff_t end = 0;
 
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
@@ -4036,7 +4028,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	 * Racy check if we can split the page, before unmap_folio() will
 	 * split PMDs
 	 */
-	if (!can_split_folio(folio, 1, &extra_pins)) {
+	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) {
 		ret = -EAGAIN;
 		goto out_unlock;
 	}
@@ -4059,8 +4051,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	}
 
 	ret = __folio_freeze_and_split_unmapped(folio, new_order, split_at, &xas, mapping,
-						true, list, split_type, end, &nr_shmem_dropped,
-						extra_pins);
+						true, list, split_type, end, &nr_shmem_dropped);
 fail:
 	if (mapping)
 		xas_unlock(&xas);
@@ -4134,20 +4125,20 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
  */
 int folio_split_unmapped(struct folio *folio, unsigned int new_order)
 {
-	int extra_pins, ret = 0;
+	int ret = 0;
 
 	VM_WARN_ON_ONCE_FOLIO(folio_mapped(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_anon(folio), folio);
 
-	if (!can_split_folio(folio, 1, &extra_pins))
+	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1)
 		return -EAGAIN;
 
 	local_irq_disable();
 	ret = __folio_freeze_and_split_unmapped(folio, new_order, &folio->page, NULL,
 						NULL, false, NULL, SPLIT_TYPE_UNIFORM,
-						0, NULL, extra_pins);
+						0, NULL);
 	local_irq_enable();
 	return ret;
 }
@@ -4640,7 +4631,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		 * can be split or not. So skip the check here.
 		 */
 		if (!folio_test_private(folio) &&
-		    !can_split_folio(folio, 0, NULL))
+		    folio_expected_ref_count(folio) != folio_ref_count(folio))
 			goto next;
 
 		if (!folio_trylock(folio))
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 92980b072121..3b85652a42b9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1284,7 +1284,8 @@ static unsigned int shrink_folio_list(struct list_head *folio_list,
 					goto keep_locked;
 				if (folio_test_large(folio)) {
 					/* cannot split folio, skip it */
-					if (!can_split_folio(folio, 1, NULL))
+					if (folio_expected_ref_count(folio) !=
+					    folio_ref_count(folio) - 1)
 						goto activate_locked;
 					/*
 					 * Split partially mapped folios right away.
-- 
2.51.0