If no free hugepage folios are available, there is no need to perform
any replacement operations. Additionally, gigantic folios should not
be replaced under any circumstances. Therefore, we only check for the
presence of non-gigantic folios.

To ensure that gigantic folios are not mistakenly replaced, we utilize
the function `isolate_or_dissolve_huge_folio()`.

Lastly, to optimize performance, we skip unnecessary iterations over pfn
for compound pages, including THP and non-compound high-order buddy pages.
This helps save processing time.

A simple test on machine with 114G free memory, allocate 120 * 1G
HugeTLB folios(104 successfully returned),

  time echo 120 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

Before: 0m0.602s
After:  0m0.431s

Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
---
 mm/hugetlb.c | 53 ++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 12 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8c197307db0c..a80cef879f61 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2806,26 +2806,55 @@ int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list)
  */
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 {
-	struct folio *folio;
-	int ret = 0;
+	unsigned long nr = 0;
+	struct page *page;
+	struct hstate *h;
+	LIST_HEAD(list);
 
-	LIST_HEAD(isolate_list);
+	/* Avoid pfn iterations if no free non-gigantic huge pages */
+	for_each_hstate(h) {
+		if (hstate_is_gigantic(h))
+			continue;
+
+		nr += h->free_huge_pages;
+		if (nr)
+			break;
+	}
+
+	if (!nr)
+		return 0;
 
 	while (start_pfn < end_pfn) {
-		folio = pfn_folio(start_pfn);
+		page = pfn_to_page(start_pfn);
+		nr = 1;
 
-		/* Not to disrupt normal path by vainly holding hugetlb_lock */
-		if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) {
-			ret = alloc_and_dissolve_hugetlb_folio(folio, &isolate_list);
-			if (ret)
-				break;
+		if (PageHuge(page) || PageCompound(page)) {
+			struct folio *folio = page_folio(page);
+
+			nr = folio_nr_pages(folio) - folio_page_idx(folio, page);
+
+			if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) {
+				if (isolate_or_dissolve_huge_folio(folio, &list))
+					return -ENOMEM;
 
-			putback_movable_pages(&isolate_list);
+				putback_movable_pages(&list);
+			}
+		} else if (PageBuddy(page)) {
+			/*
+			 * Buddy order check without zone lock is unsafe and
+			 * the order is maybe invalid, but race should be
+			 * small, and the worst thing is skipping free hugetlb.
+			 */
+			const unsigned int order = buddy_order_unsafe(page);
+
+			if (order <= MAX_PAGE_ORDER)
+				nr = 1UL << order;
 		}
-		start_pfn++;
+
+		start_pfn += nr;
 	}
 
-	return ret;
+	return 0;
 }
 
 void wait_for_freed_hugetlb_folios(void)
-- 
2.27.0