[PATCH 07/19] mm/fork: Accept huge pfnmap entries

[Peter Xu <peterx@redhat.com>]

Teach the fork code to properly copy pfnmaps for pmd/pud levels.  Pud is
much easier, the write bit needs to be persisted though for writable and
shared pud mappings like PFNMAP ones, otherwise a follow up write in either
parent or child process will trigger a write fault.

Do the same for pmd level.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/huge_memory.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6568586b21ab..015c9468eed5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1375,6 +1375,22 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pgtable_t pgtable = NULL;
 	int ret = -ENOMEM;
 
+	pmd = pmdp_get_lockless(src_pmd);
+	if (unlikely(pmd_special(pmd))) {
+		dst_ptl = pmd_lock(dst_mm, dst_pmd);
+		src_ptl = pmd_lockptr(src_mm, src_pmd);
+		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+		/*
+		 * No need to recheck the pmd, it can't change with write
+		 * mmap lock held here.
+		 */
+		if (is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd)) {
+			pmdp_set_wrprotect(src_mm, addr, src_pmd);
+			pmd = pmd_wrprotect(pmd);
+		}
+		goto set_pmd;
+	}
+
 	/* Skip if can be re-fill on fault */
 	if (!vma_is_anonymous(dst_vma))
 		return 0;
@@ -1456,7 +1472,9 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	pmdp_set_wrprotect(src_mm, addr, src_pmd);
 	if (!userfaultfd_wp(dst_vma))
 		pmd = pmd_clear_uffd_wp(pmd);
-	pmd = pmd_mkold(pmd_wrprotect(pmd));
+	pmd = pmd_wrprotect(pmd);
+set_pmd:
+	pmd = pmd_mkold(pmd);
 	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
 
 	ret = 0;
@@ -1502,8 +1520,11 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * TODO: once we support anonymous pages, use
 	 * folio_try_dup_anon_rmap_*() and split if duplicating fails.
 	 */
-	pudp_set_wrprotect(src_mm, addr, src_pud);
-	pud = pud_mkold(pud_wrprotect(pud));
+	if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) {
+		pudp_set_wrprotect(src_mm, addr, src_pud);
+		pud = pud_wrprotect(pud);
+	}
+	pud = pud_mkold(pud);
 	set_pud_at(dst_mm, addr, dst_pud, pud);
 
 	ret = 0;
-- 
2.45.0