[PATCH v4 10/17] mm/huge_memory: move the racy refcount check into unmap_folio()

[Kairui Song via B4 Relay]

From: Kairui Song <kasong@xxxxxxxxxxx>

The check only exists to avoid the expensive PMD-splitting unmap of a
folio that cannot be split anyway.  Move it from __folio_split() into
unmap_folio(), right before the PMD split, so both the anon and file
split helpers get the early check without repeating it.

unmap_folio() now returns -EAGAIN if the check fails and the split
helpers propagate the error.  folio_split_unmapped() drops its own
copy of the check: it works on already unmapped folios and the
definitive folio_ref_freeze() in __folio_freeze_split_anon() still
catches unexpected references.

Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
---
 mm/huge_memory.c | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c5279c0d0e59..17bd2c053210 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3538,13 +3538,17 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 		split_huge_pmd_if_needed(next, end);
 }
 
-static void unmap_folio(struct folio *folio)
+static int unmap_folio(struct folio *folio)
 {
 	enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC |
 		TTU_BATCH_FLUSH;
 
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
+	/* Racy check if we can split the page, before we split PMDs */
+	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1)
+		return -EAGAIN;
+
 	if (folio_test_pmd_mappable(folio))
 		ttu_flags |= TTU_SPLIT_HUGE_PMD;
 
@@ -3559,6 +3563,8 @@ static void unmap_folio(struct folio *folio)
 		try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK);
 
 	try_to_unmap_flush();
+
+	return 0;
 }
 
 static bool __discard_anon_folio_pmd_locked(struct vm_area_struct *vma,
@@ -4006,7 +4012,9 @@ static int __folio_freeze_split_anon(struct folio *folio,
 
 	if (folio_mapped(folio)) {
 		need_remap = true;
-		unmap_folio(folio);
+		ret = unmap_folio(folio);
+		if (ret)
+			return ret;
 	}
 
 	local_irq_disable();
@@ -4104,7 +4112,9 @@ static int __folio_freeze_split_file(struct folio *folio,
 	if (shmem_mapping(mapping))
 		end = shmem_fallocend(mapping->host, end);
 
-	unmap_folio(folio);
+	ret = unmap_folio(folio);
+	if (ret)
+		return ret;
 
 	xas_lock_irq(xas);
 
@@ -4312,15 +4322,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		i_mmap_lock_read(mapping);
 	}
 
-	/*
-	 * Racy check if we can split the page, before unmap_folio() will
-	 * split PMDs
-	 */
-	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) {
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-
 	if (is_anon)
 		ret = __folio_freeze_split_anon(folio, new_order, split_at,
 						true, list, split_type);
@@ -4359,7 +4360,6 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 		free_folio_and_swap_cache(new_folio);
 	}
 
-out_unlock:
 	if (anon_vma) {
 		anon_vma_unlock_write(anon_vma);
 		put_anon_vma(anon_vma);
@@ -4407,9 +4407,6 @@ int folio_split_unmapped(struct folio *folio, unsigned int new_order)
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio);
 	VM_WARN_ON_ONCE_FOLIO(!folio_test_anon(folio), folio);
 
-	if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1)
-		return -EAGAIN;
-
 	return __folio_freeze_split_anon(folio, new_order, &folio->page,
 					 false, NULL, SPLIT_TYPE_UNIFORM);
 }

-- 
2.55.0