vfs: add renameat2 syscall

Add new renameat2 syscall, which is the same as renameat with an added
flags argument.

Pass flags to vfs_rename() and to i_op->rename() as well.

Signed-off-by: Miklos Szeredi <[e-mail]>
Reviewed-by: J. Bruce Fields <[e-mail]>

Documentation/filesystems/Locking

···
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
···
 unlink:		yes (both)
 rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
+rename2:	yes (all)	(see below)
 readlink:	no
 follow_link:	no
 put_link:	no
···
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
-	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+	cross-directory ->rename() and rename2() has (per-superblock)
+->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.

Documentation/filesystems/vfs.txt

···
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
···
 
   rename: called by the rename(2) system call to rename the object to
 	have the parent and name given by the second inode and dentry.
+
+  rename2: this has an additional flags argument compared to rename.
+	If no flags are supported by the filesystem then this method
+	need not be implemented.  If some flags are supported then the
+	filesystem must return -EINVAL for any unsupported or unknown
+	flags.  Currently the following flags are implemented:
+	(1) RENAME_NOREPLACE: this flag indicates that if the target
+	of the rename exists the rename should fail with -EEXIST
+	instead of replacing the target.  The VFS already checks for
+	existence, so for local filesystems the RENAME_NOREPLACE
+	implementation is equivalent to plain rename.
+	(2) RENAME_EXCHANGE: exchange source and target.  Both must
+	exist; this is checked by the VFS.  Unlike plain rename,
+	source and target may be of different type.
 
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links

arch/x86/syscalls/syscall_64.tbl

···
 313	common	finit_module		sys_finit_module
 314	common	sched_setattr		sys_sched_setattr
 315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

drivers/staging/lustre/lustre/include/linux/lustre_compat25.h

···
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
-		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
+#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \
+		vfs_rename(old, old_dir, new, new_dir, NULL, 0)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))

drivers/staging/lustre/lustre/lvfs/lvfs_linux.c

···
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt, NULL);
+			    dir->d_inode, dchild_new, mnt);
 
 	dput(dchild_new);
 put_old:

fs/cachefiles/namei.c

···
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave, NULL);
+				 cache->graveyard->d_inode, grave, NULL, 0);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);

fs/ecryptfs/inode.c

···
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry,
-			NULL);
+			NULL, 0);
 	if (rc)
 		goto out_lock;
 	if (target_inode)

fs/namei.c

···
  * @new_dir:	parent of destination
  * @new_dentry:	destination
  * @delegated_inode: returns an inode needing a delegation break
+ * @flags:	rename flags
  *
  * The caller must hold multiple mutexes--see lock_rename()).
  *
···
  */
 int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	       struct inode *new_dir, struct dentry *new_dentry,
-	       struct inode **delegated_inode)
+	       struct inode **delegated_inode, unsigned int flags)
 {
 	int error;
 	bool is_dir = d_is_dir(old_dentry);
···
 
 	if (!old_dir->i_op->rename)
 		return -EPERM;
+
+	if (flags && !old_dir->i_op->rename2)
+		return -EINVAL;
 
 	/*
 	 * If we are going to change the parent - check write permissions,
···
 				goto out;
 		}
 	}
-	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (!flags) {
+		error = old_dir->i_op->rename(old_dir, old_dentry,
+					      new_dir, new_dentry);
+	} else {
+		error = old_dir->i_op->rename2(old_dir, old_dentry,
+					       new_dir, new_dentry, flags);
+	}
 	if (error)
 		goto out;
 
···
 	return error;
 }
 
-SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
-		int, newdfd, const char __user *, newname)
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, unsigned int, flags)
 {
 	struct dentry *old_dir, *new_dir;
 	struct dentry *old_dentry, *new_dentry;
···
 	unsigned int lookup_flags = 0;
 	bool should_retry = false;
 	int error;
+
+	if (flags)
+		return -EINVAL;
+
 retry:
 	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
 	if (IS_ERR(from)) {
···
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry,
-				   &delegated_inode);
+			   new_dir->d_inode, new_dentry,
+			   &delegated_inode, flags);
 exit5:
 	dput(new_dentry);
 exit4:
···
 	return error;
 }
 
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
+	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)

fs/nfsd/vfs.c

···
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)

include/linux/fs.h

···
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 
 /*
  * VFS dentry helper functions.
···
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);