Merge tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:
 "This contains two new features:

   - Stack file operations: this allows removal of several hacks from
     the VFS, proper interaction of read-only open files with copy-up,
     possibility to implement fs modifying ioctls properly, and others.

   - Metadata only copy-up: when file is on lower layer and only
     metadata is modified (except size) then only copy up the metadata
     and continue to use the data from the lower file"

* tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: (66 commits)
  ovl: Enable metadata only feature
  ovl: Do not do metacopy only for ioctl modifying file attr
  ovl: Do not do metadata only copy-up for truncate operation
  ovl: add helper to force data copy-up
  ovl: Check redirect on index as well
  ovl: Set redirect on upper inode when it is linked
  ovl: Set redirect on metacopy files upon rename
  ovl: Do not set dentry type ORIGIN for broken hardlinks
  ovl: Add an inode flag OVL_CONST_INO
  ovl: Treat metacopy dentries as type OVL_PATH_MERGE
  ovl: Check redirects for metacopy files
  ovl: Move some dir related ovl_lookup_single() code in else block
  ovl: Do not expose metacopy only dentry from d_real()
  ovl: Open file with data except for the case of fsync
  ovl: Add helper ovl_inode_realdata()
  ovl: Store lower data inode in ovl_inode
  ovl: Fix ovl_getattr() to get number of blocks from lower
  ovl: Add helper ovl_dentry_lowerdata() to get lower data dentry
  ovl: Copy up meta inode data from lowest data inode
  ovl: Modify ovl_lookup() and friends to lookup metacopy dentry
  ...

1 files changed, 53 insertions, 41 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 153f8f690490..39b4a21dd933 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1964,6 +1964,44 @@ out_error:
 }
 EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
 
+int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+			      struct file *dst_file, loff_t dst_pos, u64 len)
+{
+	s64 ret;
+
+	ret = mnt_want_write_file(dst_file);
+	if (ret)
+		return ret;
+
+	ret = clone_verify_area(dst_file, dst_pos, len, true);
+	if (ret < 0)
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!(capable(CAP_SYS_ADMIN) || (dst_file->f_mode & FMODE_WRITE)))
+		goto out_drop_write;
+
+	ret = -EXDEV;
+	if (src_file->f_path.mnt != dst_file->f_path.mnt)
+		goto out_drop_write;
+
+	ret = -EISDIR;
+	if (S_ISDIR(file_inode(dst_file)->i_mode))
+		goto out_drop_write;
+
+	ret = -EINVAL;
+	if (!dst_file->f_op->dedupe_file_range)
+		goto out_drop_write;
+
+	ret = dst_file->f_op->dedupe_file_range(src_file, src_pos,
+						dst_file, dst_pos, len);
+out_drop_write:
+	mnt_drop_write_file(dst_file);
+
+	return ret;
+}
+EXPORT_SYMBOL(vfs_dedupe_file_range_one);
+
 int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 {
 	struct file_dedupe_range_info *info;
@@ -1972,11 +2010,8 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	u64 len;
 	int i;
 	int ret;
-	bool is_admin = capable(CAP_SYS_ADMIN);
 	u16 count = same->dest_count;
-	struct file *dst_file;
-	loff_t dst_off;
-	ssize_t deduped;
+	int deduped;
 
 	if (!(file->f_mode & FMODE_READ))
 		return -EINVAL;
@@ -2003,6 +2038,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	if (off + len > i_size_read(src))
 		return -EINVAL;
 
+	/* Arbitrary 1G limit on a single dedupe request, can be raised. */
+	len = min_t(u64, len, 1 << 30);
+
 	/* pre-format output fields to sane values */
 	for (i = 0; i < count; i++) {
 		same->info[i].bytes_deduped = 0ULL;
@@ -2010,54 +2048,28 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 	}
 
 	for (i = 0, info = same->info; i < count; i++, info++) {
-		struct inode *dst;
 		struct fd dst_fd = fdget(info->dest_fd);
+		struct file *dst_file = dst_fd.file;
 
-		dst_file = dst_fd.file;
 		if (!dst_file) {
 			info->status = -EBADF;
 			goto next_loop;
 		}
-		dst = file_inode(dst_file);
-
-		ret = mnt_want_write_file(dst_file);
-		if (ret) {
-			info->status = ret;
-			goto next_fdput;
-		}
-
-		dst_off = info->dest_offset;
-		ret = clone_verify_area(dst_file, dst_off, len, true);
-		if (ret < 0) {
-			info->status = ret;
-			goto next_file;
-		}
-		ret = 0;
 
 		if (info->reserved) {
 			info->status = -EINVAL;
-		} else if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
-			info->status = -EINVAL;
-		} else if (file->f_path.mnt != dst_file->f_path.mnt) {
-			info->status = -EXDEV;
-		} else if (S_ISDIR(dst->i_mode)) {
-			info->status = -EISDIR;
-		} else if (dst_file->f_op->dedupe_file_range == NULL) {
-			info->status = -EINVAL;
-		} else {
-			deduped = dst_file->f_op->dedupe_file_range(file, off,
-							len, dst_file,
-							info->dest_offset);
-			if (deduped == -EBADE)
-				info->status = FILE_DEDUPE_RANGE_DIFFERS;
-			else if (deduped < 0)
-				info->status = deduped;
-			else
-				info->bytes_deduped += deduped;
+			goto next_fdput;
 		}
 
-next_file:
-		mnt_drop_write_file(dst_file);
+		deduped = vfs_dedupe_file_range_one(file, off, dst_file,
+						    info->dest_offset, len);
+		if (deduped == -EBADE)
+			info->status = FILE_DEDUPE_RANGE_DIFFERS;
+		else if (deduped < 0)
+			info->status = deduped;
+		else
+			info->bytes_deduped = len;
+
 next_fdput:
 		fdput(dst_fd);
 next_loop: