[PATCH v6 05/23] mm/shmem: Take care of UFFDIO_COPY_MODE_WP

[Peter Xu]

Pass wp_copy into shmem_mfill_atomic_pte() through the stack, then apply the
UFFD_WP bit properly when the UFFDIO_COPY on shmem is with UFFDIO_COPY_MODE_WP.
wp_copy lands mfill_atomic_install_pte() finally.

Note: we must do pte_wrprotect() if !writable in mfill_atomic_install_pte(), as
mk_pte() could return a writable pte (e.g., when VM_SHARED on a shmem file).

Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
 include/linux/shmem_fs.h |  4 ++--
 mm/shmem.c               |  4 ++--
 mm/userfaultfd.c         | 30 +++++++++++++++++++++---------
 3 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 166158b6e917..0ee0f437b14f 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -145,11 +145,11 @@ extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 				  struct vm_area_struct *dst_vma,
 				  unsigned long dst_addr,
 				  unsigned long src_addr,
-				  bool zeropage,
+				  bool zeropage, bool wp_copy,
 				  struct page **pagep);
 #else /* !CONFIG_SHMEM */
 #define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \
-			       src_addr, zeropage, pagep)       ({ BUG(); 0; })
+			       src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; })
 #endif /* CONFIG_SHMEM */
 #endif /* CONFIG_USERFAULTFD */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index dc038ce78700..167a46e6a1ff 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2344,7 +2344,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 			   struct vm_area_struct *dst_vma,
 			   unsigned long dst_addr,
 			   unsigned long src_addr,
-			   bool zeropage,
+			   bool zeropage, bool wp_copy,
 			   struct page **pagep)
 {
 	struct inode *inode = file_inode(dst_vma->vm_file);
@@ -2415,7 +2415,7 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 		goto out_release;
 
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
-				       page, true, false);
+				       page, true, wp_copy);
 	if (ret)
 		goto out_delete_from_cache;
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index ac6f036298cd..95e5a9ba3196 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -70,14 +70,22 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 
 	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
 	_dst_pte = pte_mkdirty(_dst_pte);
-	if (page_in_cache && !vm_shared)
+	/* Don't write if uffd-wp wr-protected */
+	if (wp_copy) {
+		_dst_pte = pte_mkuffd_wp(_dst_pte);
 		writable = false;
-	if (writable) {
-		if (wp_copy)
-			_dst_pte = pte_mkuffd_wp(_dst_pte);
-		else
-			_dst_pte = pte_mkwrite(_dst_pte);
 	}
+	/* Don't write if page cache privately mapped */
+	if (page_in_cache && !vm_shared)
+		writable = false;
+	if (writable)
+		_dst_pte = pte_mkwrite(_dst_pte);
+	else
+		/*
+		 * We need this to make sure write bit removed; as mk_pte()
+		 * could return a pte with write bit set.
+		 */
+		_dst_pte = pte_wrprotect(_dst_pte);
 
 	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
 
@@ -92,7 +100,12 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
 	}
 
 	ret = -EEXIST;
-	if (!pte_none(*dst_pte))
+	/*
+	 * We allow to overwrite a pte marker: consider when both MISSING|WP
+	 * registered, we firstly wr-protect a none pte which has no page cache
+	 * page backing it, then access the page.
+	 */
+	if (!pte_none_mostly(*dst_pte))
 		goto out_unlock;
 
 	if (page_in_cache)
@@ -467,11 +480,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
 			err = mfill_zeropage_pte(dst_mm, dst_pmd,
 						 dst_vma, dst_addr);
 	} else {
-		VM_WARN_ON_ONCE(wp_copy);
 		err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma,
 					     dst_addr, src_addr,
 					     mode != MCOPY_ATOMIC_NORMAL,
-					     page);
+					     wp_copy, page);
 	}
 
 	return err;
-- 
2.32.0