If the first access to a folio is a read that is then followed by a
write, we can save a page fault. s390 implemented this in their
mk_pte() in commit abf09bed3cce ("s390/mm: implement software dirty
bits"), but other architectures can also benefit from this.
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
---
arch/s390/include/asm/pgtable.h | 7 +------
mm/memory.c | 2 ++
2 files changed, 3 insertions(+), 6 deletions(-)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 3ca5af4cfe43..3ee495b5171e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1451,12 +1451,7 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot)
static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
{
- unsigned long physpage = page_to_phys(page);
- pte_t __pte = mk_pte_phys(physpage, pgprot);
-
- if (pte_write(__pte) && PageDirty(page))
- __pte = pte_mkdirty(__pte);
- return __pte;
+ return mk_pte_phys(page_to_phys(page), pgprot);
}
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
diff --git a/mm/memory.c b/mm/memory.c
index 539c0f7c6d54..4330560eee55 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5124,6 +5124,8 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
if (write)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ else if (pte_write(entry) && folio_test_dirty(folio))
+ entry = pte_mkdirty(entry);
if (unlikely(vmf_orig_pte_uffd_wp(vmf)))
entry = pte_mkuffd_wp(entry);
/* copy-on-write page */
--
2.47.2
