[PATCH v4 4/8] hugetlb: perform vmemmap restoration on a list of pages

[Mike Kravetz <mike.kravetz@oracle.com>]

The routine update_and_free_pages_bulk already performs vmemmap
restoration on the list of hugetlb pages in a separate step.  In
preparation for more functionality to be added in this step, create a
new routine hugetlb_vmemmap_restore_folios() that will restore
vmemmap for a list of folios.

This new routine must provide sufficient feedback about errors and
actual restoration performed so that update_and_free_pages_bulk can
perform optimally.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 mm/hugetlb.c         | 36 ++++++++++++++++++------------------
 mm/hugetlb_vmemmap.c | 37 +++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h | 11 +++++++++++
 3 files changed, 66 insertions(+), 18 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d6f3db3c1313..814bb1982274 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1836,36 +1836,36 @@ static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio,
 
 static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list)
 {
+	int ret;
+	unsigned long restored;
 	struct folio *folio, *t_folio;
-	bool clear_dtor = false;
 
 	/*
-	 * First allocate required vmemmmap (if necessary) for all folios on
-	 * list.  If vmemmap can not be allocated, we can not free folio to
-	 * lower level allocator, so add back as hugetlb surplus page.
-	 * add_hugetlb_folio() removes the page from THIS list.
-	 * Use clear_dtor to note if vmemmap was successfully allocated for
-	 * ANY page on the list.
+	 * First allocate required vmemmmap (if necessary) for all folios.
 	 */
-	list_for_each_entry_safe(folio, t_folio, list, lru) {
-		if (folio_test_hugetlb_vmemmap_optimized(folio)) {
-			if (hugetlb_vmemmap_restore(h, &folio->page)) {
-				spin_lock_irq(&hugetlb_lock);
+	ret = hugetlb_vmemmap_restore_folios(h, list, &restored);
+
+	/*
+	 * If there was an error restoring vmemmap for ANY folios on the list,
+	 * add them back as surplus hugetlb pages.  add_hugetlb_folio() removes
+	 * the folio from THIS list.
+	 */
+	if (ret < 0) {
+		spin_lock_irq(&hugetlb_lock);
+		list_for_each_entry_safe(folio, t_folio, list, lru)
+			if (folio_test_hugetlb_vmemmap_optimized(folio))
 				add_hugetlb_folio(h, folio, true);
-				spin_unlock_irq(&hugetlb_lock);
-			} else
-				clear_dtor = true;
-		}
+		spin_unlock_irq(&hugetlb_lock);
 	}
 
 	/*
-	 * If vmemmmap allocation was performed on any folio above, take lock
-	 * to clear destructor of all folios on list.  This avoids the need to
+	 * If vmemmmap allocation was performed on ANY folio , take lock to
+	 * clear destructor of all folios on list.  This avoids the need to
 	 * lock/unlock for each individual folio.
 	 * The assumption is vmemmap allocation was performed on all or none
 	 * of the folios on the list.  This is true expect in VERY rare cases.
 	 */
-	if (clear_dtor) {
+	if (restored) {
 		spin_lock_irq(&hugetlb_lock);
 		list_for_each_entry(folio, list, lru)
 			__clear_hugetlb_destructor(h, folio);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 4558b814ffab..463a4037ec6e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -480,6 +480,43 @@ int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head)
 	return ret;
 }
 
+/**
+ * hugetlb_vmemmap_restore_folios - restore vmemmap for every folio on the list.
+ * @h:		struct hstate.
+ * @folio_list:	list of folios.
+ * @restored:	Set to number of folios for which vmemmap was restored
+ *		successfully if caller passes a non-NULL pointer.
+ *
+ * Return: %0 if vmemmap exists for all folios on the list.  If an error is
+ *		encountered restoring vmemmap for ANY folio, an error code
+ *		will be returned to the caller.  It is then the responsibility
+ *		of the caller to check the hugetlb vmemmap optimized flag of
+ *		each folio to determine if vmemmap was actually restored.
+ */
+int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+					struct list_head *folio_list,
+					unsigned long *restored)
+{
+	unsigned long num_restored;
+	struct folio *folio;
+	int ret = 0, t_ret;
+
+	num_restored = 0;
+	list_for_each_entry(folio, folio_list, lru) {
+		if (folio_test_hugetlb_vmemmap_optimized(folio)) {
+			t_ret = hugetlb_vmemmap_restore(h, &folio->page);
+			if (t_ret)
+				ret = t_ret;
+			else
+				num_restored++;
+		}
+	}
+
+	if (*restored)
+		*restored = num_restored;
+	return ret;
+}
+
 /* Return true iff a HugeTLB whose vmemmap should and can be optimized. */
 static bool vmemmap_should_optimize(const struct hstate *h, const struct page *head)
 {
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index c512e388dbb4..bb58453c3cc0 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -19,6 +19,8 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
 int hugetlb_vmemmap_restore(const struct hstate *h, struct page *head);
+int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+			struct list_head *folio_list, unsigned long *restored);
 void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head);
 void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_list);
 
@@ -45,6 +47,15 @@ static inline int hugetlb_vmemmap_restore(const struct hstate *h, struct page *h
 	return 0;
 }
 
+static inline int hugetlb_vmemmap_restore_folios(const struct hstate *h,
+					struct list_head *folio_list,
+					unsigned long *restored)
+{
+	if (restored)
+		*restored = 0;
+	return 0;
+}
+
 static inline void hugetlb_vmemmap_optimize(const struct hstate *h, struct page *head)
 {
 }
-- 
2.41.0