[PATCH v3 15/15] mm/memory: ignore writable bit in folio_pte_batch()

[David Hildenbrand]

.. and conditionally return to the caller if any PTE except the first one
is writable. fork() has to make sure to properly write-protect in case any
PTE is writable. Other users (e.g., page unmaping) are expected to not
care.

Reviewed-by: Ryan Roberts <ryan.roberts@xxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
 mm/memory.c | 30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index b2ec2b6b54c7..b05fd28dbce1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -968,7 +968,7 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
 		pte = pte_mkclean(pte);
 	if (likely(flags & FPB_IGNORE_SOFT_DIRTY))
 		pte = pte_clear_soft_dirty(pte);
-	return pte_mkold(pte);
+	return pte_wrprotect(pte_mkold(pte));
 }
 
 /*
@@ -976,21 +976,32 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags)
  * pages of the same folio.
  *
  * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN,
- * the accessed bit, dirty bit (with FPB_IGNORE_DIRTY) and soft-dirty bit
- * (with FPB_IGNORE_SOFT_DIRTY).
+ * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and
+ * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY).
+ *
+ * If "any_writable" is set, it will indicate if any other PTE besides the
+ * first (given) PTE is writable.
  */
 static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
-		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags)
+		pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags,
+		bool *any_writable)
 {
 	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
 	const pte_t *end_ptep = start_ptep + max_nr;
 	pte_t expected_pte = __pte_batch_clear_ignored(pte_next_pfn(pte), flags);
 	pte_t *ptep = start_ptep + 1;
+	bool writable;
+
+	if (any_writable)
+		*any_writable = false;
 
 	VM_WARN_ON_FOLIO(!pte_present(pte), folio);
 
 	while (ptep != end_ptep) {
-		pte = __pte_batch_clear_ignored(ptep_get(ptep), flags);
+		pte = ptep_get(ptep);
+		if (any_writable)
+			writable = !!pte_write(pte);
+		pte = __pte_batch_clear_ignored(pte, flags);
 
 		if (!pte_same(pte, expected_pte))
 			break;
@@ -1003,6 +1014,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
 		if (pte_pfn(pte) == folio_end_pfn)
 			break;
 
+		if (any_writable)
+			*any_writable |= writable;
+
 		expected_pte = pte_next_pfn(expected_pte);
 		ptep++;
 	}
@@ -1024,6 +1038,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 {
 	struct page *page;
 	struct folio *folio;
+	bool any_writable;
 	fpb_t flags = 0;
 	int err, nr;
 
@@ -1044,7 +1059,8 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		if (!vma_soft_dirty_enabled(src_vma))
 			flags |= FPB_IGNORE_SOFT_DIRTY;
 
-		nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags);
+		nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags,
+				     &any_writable);
 		folio_ref_add(folio, nr);
 		if (folio_test_anon(folio)) {
 			if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
@@ -1058,6 +1074,8 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 			folio_dup_file_rmap_ptes(folio, page, nr);
 			rss[mm_counter_file(folio)] += nr;
 		}
+		if (any_writable)
+			pte = pte_mkwrite(pte, src_vma);
 		__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte,
 				    addr, nr);
 		return nr;
-- 
2.43.0