[PATCH] mm: eliminate function call overhead during copy_page_range()

[Hao Lee <haolee.swjtu@xxxxxxxxx>]

vm_normal_page() is called so many times that its overhead is very high.
After changing this call site to an inline function, copy_page_range()
runs 3~5 times faster than before.

Signed-off-by: Hao Lee <haolee.swjtu@xxxxxxxxx>
---
 mm/memory.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 7a04a1130ec1..2084bb7aff85 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -562,7 +562,7 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
  * PFNMAP mappings in order to support COWable mappings.
  *
  */
-struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+static inline struct page *__vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			    pte_t pte)
 {
 	unsigned long pfn = pte_pfn(pte);
@@ -625,6 +625,12 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 	return pfn_to_page(pfn);
 }
 
+struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+			    pte_t pte)
+{
+	return __vm_normal_page(vma, addr, pte);
+}
+
 struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
 			    pte_t pte)
 {
@@ -908,7 +914,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	struct page *page;
 	struct folio *folio;
 
-	page = vm_normal_page(src_vma, addr, pte);
+	page = __vm_normal_page(src_vma, addr, pte);
 	if (page)
 		folio = page_folio(page);
 	if (page && folio_test_anon(folio)) {
-- 
2.37.3