As we grow the code, the compiler might make stupid decisions and
unnecessarily degrade fork() performance. Let's make sure to always inline
functions that operate on a single PTE so the compiler will always
optimize out the loop and avoid a function call.
This is a preparation for maintining a total mapcount for large folios.
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
include/linux/rmap.h | 17 +++++++++++++----
1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 9bf9324214fc..9549d78928bb 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -347,8 +347,12 @@ static inline void folio_dup_file_rmap_ptes(struct folio *folio,
{
__folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE);
}
-#define folio_dup_file_rmap_pte(folio, page) \
- folio_dup_file_rmap_ptes(folio, page, 1)
+
+static __always_inline void folio_dup_file_rmap_pte(struct folio *folio,
+ struct page *page)
+{
+ __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE);
+}
/**
* folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio
@@ -448,8 +452,13 @@ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio,
return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma,
RMAP_LEVEL_PTE);
}
-#define folio_try_dup_anon_rmap_pte(folio, page, vma) \
- folio_try_dup_anon_rmap_ptes(folio, page, 1, vma)
+
+static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio,
+ struct page *page, struct vm_area_struct *src_vma)
+{
+ return __folio_try_dup_anon_rmap(folio, page, 1, src_vma,
+ RMAP_LEVEL_PTE);
+}
/**
* folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range
--
2.44.0
