[PATCH 6.18.y 4/6] mm/huge_memory: replace can_split_folio() with direct refcount calculation

[Sasha Levin <sashal@kernel.org>]

From: Zi Yan <ziy@nvidia.com>

[ Upstream commit 5842bcbfc316738cbfcbdb4def5a7592aa03ebf2 ]

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_ref_count() to calculate it.
Also replace folio_expected_ref_count() with folio_cache_ref_count() used
by folio_ref_unfreeze(), since they are returning the same values when a
folio is frozen and folio_cache_ref_count() does not have unnecessary
folio_mapcount() in its implementation.

Link: https://lkml.kernel.org/r/20251126210618.1971206-3-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Suggested-by: David Hildenbrand (Red Hat) <david@kernel.org>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Acked-by: David Hildenbrand (Red Hat) <david@kernel.org>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: c299a2285d9d ("mm/huge_memory: use folio's memcg inside __folio_split()")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/huge_mm.h |  1 -
 mm/huge_memory.c        | 35 ++++++++++++-----------------------
 mm/vmscan.c             |  3 ++-
 3 files changed, 14 insertions(+), 25 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9bafcdb4d66ac..b55a4a342f578 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -364,7 +364,6 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 		unsigned long len, unsigned long pgoff, unsigned long flags,
 		vm_flags_t vm_flags);
 
-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 min_order_for_split(struct folio *folio);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index dc53a92308513..7df0a1380738c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3326,23 +3326,6 @@ 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--)
@@ -3715,7 +3698,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	struct anon_vma *anon_vma = NULL;
 	int old_order = folio_order(folio);
 	struct folio *new_folio, *next;
-	int extra_pins;
 	int nr_shmem_dropped = 0;
 	enum ttu_flags ttu_flags = 0;
 	pgoff_t end = 0;
@@ -3803,7 +3785,7 @@ 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;
 	}
@@ -3827,7 +3809,10 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	ds_queue = folio_split_queue_lock(folio);
-	if (folio_ref_freeze(folio, 1 + extra_pins)) {
+	if (folio_ref_freeze(folio,
+			     (folio_test_anon(folio) &&
+			      !folio_test_swapcache(folio) ?
+			      0 : folio_nr_pages(folio)) + 1)) {
 		struct swap_cluster_info *ci = NULL;
 		struct lruvec *lruvec;
 		int expected_refs;
@@ -3896,7 +3881,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 
 			next = folio_next(new_folio);
 
-			expected_refs = folio_expected_ref_count(new_folio) + 1;
+			expected_refs = (folio_test_anon(new_folio) &&
+					 !folio_test_swapcache(new_folio) ?
+					 0 : folio_nr_pages(new_folio)) + 1;
 			folio_ref_unfreeze(new_folio, expected_refs);
 
 			lru_add_split_folio(folio, new_folio, lruvec, list);
@@ -3936,7 +3923,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		 * Otherwise, a parallel folio_try_get() can grab @folio
 		 * and its caller can see stale page cache entries.
 		 */
-		expected_refs = folio_expected_ref_count(folio) + 1;
+		expected_refs = (folio_test_anon(folio) &&
+				 !folio_test_swapcache(folio) ?
+				 0 : folio_nr_pages(folio)) + 1;
 		folio_ref_unfreeze(folio, expected_refs);
 
 		unlock_page_lruvec(lruvec);
@@ -4465,7 +4454,7 @@ 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 95b1179a14e78..6d563563cecfd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1317,7 +1317,8 @@ 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.
-- 
2.53.0