vfs: add RENAME_NOREPLACE flag

If this flag is specified and the target of the rename exists then the
rename syscall fails with EEXIST.

The VFS does the existence checking, so it is trivial to enable for most
local filesystems.  This patch only enables it in ext4.

For network filesystems the VFS check is not enough as there may be a race
between a remote create and the rename, so these filesystems need to handle
this flag in their ->rename() implementations to ensure atomicity.

Andy writes about why this is useful:

"The trivial answer: to eliminate the race condition from 'mv -i'.

Another answer: there's a common pattern to atomically create a file
with contents: open a temporary file, write to it, optionally fsync
it, close it, then link(2) it to the final name, then unlink the
temporary file.

The reason to use link(2) is because it won't silently clobber the destination.

This is annoying:
 - It requires an extra system call that shouldn't be necessary.
 - It doesn't work on (IMO sensible) filesystems that don't support
hard links (e.g. vfat).
 - It's not atomic -- there's an intermediate state where both files exist.
 - It's ugly.

The new rename flag will make this totally sensible.

To be fair, on new enough kernels, you can also use O_TMPFILE and
linkat to achieve the same thing even more cleanly."

Suggested-by: Andy Lutomirski <luto@amacapital.net> 
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>

3 files changed, 26 insertions, 8 deletions

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index d050e043e88..5f19171b3e1 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3204,6 +3204,16 @@ end_rename:
 	return retval;
 }
 
+static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry,
+			unsigned int flags)
+{
+	if (flags & ~RENAME_NOREPLACE)
+		return -EINVAL;
+
+	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
+}
+
 /*
  * directories can handle most operations...
  */
@@ -3218,6 +3228,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.mknod		= ext4_mknod,
 	.tmpfile	= ext4_tmpfile,
 	.rename		= ext4_rename,
+	.rename2	= ext4_rename2,
 	.setattr	= ext4_setattr,
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
diff --git a/fs/namei.c b/fs/namei.c
index ab4e48c4a80..0e9d186b7f7 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4142,7 +4142,7 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	bool should_retry = false;
 	int error;
 
-	if (flags)
+	if (flags & ~RENAME_NOREPLACE)
 		return -EINVAL;
 
 retry:
@@ -4168,6 +4168,8 @@ retry:
 		goto exit2;
 
 	new_dir = newnd.path.dentry;
+	if (flags & RENAME_NOREPLACE)
+		error = -EEXIST;
 	if (newnd.last_type != LAST_NORM)
 		goto exit2;
 
@@ -4190,22 +4192,25 @@ retry_deleg:
 	error = -ENOENT;
 	if (d_is_negative(old_dentry))
 		goto exit4;
+	new_dentry = lookup_hash(&newnd);
+	error = PTR_ERR(new_dentry);
+	if (IS_ERR(new_dentry))
+		goto exit4;
+	error = -EEXIST;
+	if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
+		goto exit5;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
 	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
-			goto exit4;
+			goto exit5;
 		if (newnd.last.name[newnd.last.len])
-			goto exit4;
+			goto exit5;
 	}
 	/* source should not be ancestor of target */
 	error = -EINVAL;
 	if (old_dentry == trap)
-		goto exit4;
-	new_dentry = lookup_hash(&newnd);
-	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry))
-		goto exit4;
+		goto exit5;
 	/* target should not be an ancestor of source */
 	error = -ENOTEMPTY;
 	if (new_dentry == trap)
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 6c28b61bb69..9250f4dd7d9 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -35,6 +35,8 @@
 #define SEEK_HOLE	4	/* seek to the next hole */
 #define SEEK_MAX	SEEK_HOLE
 
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+
 struct fstrim_range {
 	__u64 start;
 	__u64 len;