Merge branch 'cross-rename' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull renameat2 system call from Miklos Szeredi:
 "This adds a new syscall, renameat2(), which is the same as renameat()
  but with a flags argument.

  The purpose of extending rename is to add cross-rename, a symmetric
  variant of rename, which exchanges the two files.  This allows
  interesting things, which were not possible before, for example
  atomically replacing a directory tree with a symlink, etc...  This
  also allows overlayfs and friends to operate on whiteouts atomically.

  Andy Lutomirski also suggested a "noreplace" flag, which disables the
  overwriting behavior of rename.

  These two flags, RENAME_EXCHANGE and RENAME_NOREPLACE are only
  implemented for ext4 as an example and for testing"

* 'cross-rename' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ext4: add cross rename support
  ext4: rename: split out helper functions
  ext4: rename: move EMLINK check up
  ext4: rename: create ext4_renament structure for local vars
  vfs: add cross-rename
  vfs: lock_two_nondirectories: allow directory args
  security: add flags to rename hooks
  vfs: add RENAME_NOREPLACE flag
  vfs: add renameat2 syscall
  vfs: rename: use common code for dir and non-dir
  vfs: rename: move d_move() up
  vfs: add d_is_dir()

Documentation/filesystems/Locking

@@ -47,6 +47,8 @@ prototypes:
 	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 *);
@@ -78,6 +80,7 @@ mkdir:		yes
 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
@@ -96,7 +99,8 @@ tmpfile:	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

@@ -347,6 +347,8 @@ struct inode_operations {
 	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 *);
@@ -414,6 +416,20 @@ otherwise noted.
   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

@@ -322,6 +322,7 @@
 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

@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #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

@@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		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

@@ -391,12 +391,12 @@ try_again:
 	path.dentry = dir;
 	path_to_graveyard.mnt = cache->mnt;
 	path_to_graveyard.dentry = cache->graveyard;
-	ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
+	ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
 	if (ret < 0) {
 		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/dcache.c

@@ -2483,12 +2483,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			dentry->d_name.name = dentry->d_iname;
 		} else {
 			/*
-			 * Both are internal.  Just copy target to dentry
+			 * Both are internal.
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
-			dentry->d_name.len = target->d_name.len;
-			return;
+			unsigned int i;
+			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
+				swap(((long *) &dentry->d_iname)[i],
+				     ((long *) &target->d_iname)[i]);
+			}
 		}
 	}
 	swap(dentry->d_name.len, target->d_name.len);
@@ -2545,13 +2547,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * __d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
+ * @exchange: exchange the two dentries
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way. Caller must hold
  * rename_lock, the i_mutex of the source and target directories,
  * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
-static void __d_move(struct dentry * dentry, struct dentry * target)
+static void __d_move(struct dentry *dentry, struct dentry *target,
+		     bool exchange)
 {
 	if (!dentry->d_inode)
 		printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2573,8 +2577,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	__d_drop(dentry);
 	__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
-	/* Unhash the target: dput() will then get rid of it */
+	/*
+	 * Unhash the target (d_delete() is not usable here).  If exchanging
+	 * the two dentries, then rehash onto the other's hash queue.
+	 */
 	__d_drop(target);
+	if (exchange) {
+		__d_rehash(target,
+			   d_hash(dentry->d_parent, dentry->d_name.hash));
+	}
 
 	list_del(&dentry->d_u.d_child);
 	list_del(&target->d_u.d_child);
@@ -2601,6 +2612,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	write_seqcount_end(&dentry->d_seq);
 
 	dentry_unlock_parents_for_move(dentry, target);
+	if (exchange)
+		fsnotify_d_move(target);
 	spin_unlock(&target->d_lock);
 	fsnotify_d_move(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -2618,11 +2631,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 void d_move(struct dentry *dentry, struct dentry *target)
 {
 	write_seqlock(&rename_lock);
-	__d_move(dentry, target);
+	__d_move(dentry, target, false);
 	write_sequnlock(&rename_lock);
 }
 EXPORT_SYMBOL(d_move);
 
+/*
+ * d_exchange - exchange two dentries
+ * @dentry1: first dentry
+ * @dentry2: second dentry
+ */
+void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+{
+	write_seqlock(&rename_lock);
+
+	WARN_ON(!dentry1->d_inode);
+	WARN_ON(!dentry2->d_inode);
+	WARN_ON(IS_ROOT(dentry1));
+	WARN_ON(IS_ROOT(dentry2));
+
+	__d_move(dentry1, dentry2, true);
+
+	write_sequnlock(&rename_lock);
+}
+
 /**
  * d_ancestor - search for an ancestor
  * @p1: ancestor dentry
@@ -2670,7 +2702,7 @@ static struct dentry *__d_unalias(struct inode *inode,
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
 	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry);
+		__d_move(alias, dentry, false);
 		ret = alias;
 	}
 out_err:

fs/ecryptfs/inode.c

@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	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/ext4/namei.c

@@ -3000,6 +3000,154 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
 	return ext4_get_first_inline_block(inode, parent_de, retval);
 }
 
+struct ext4_renament {
+	struct inode *dir;
+	struct dentry *dentry;
+	struct inode *inode;
+	bool is_dir;
+	int dir_nlink_delta;
+
+	/* entry for "dentry" */
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
+	int inlined;
+
+	/* entry for ".." in inode if it's a directory */
+	struct buffer_head *dir_bh;
+	struct ext4_dir_entry_2 *parent_de;
+	int dir_inlined;
+};
+
+static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
+{
+	int retval;
+
+	ent->dir_bh = ext4_get_first_dir_block(handle, ent->inode,
+					      &retval, &ent->parent_de,
+					      &ent->dir_inlined);
+	if (!ent->dir_bh)
+		return retval;
+	if (le32_to_cpu(ent->parent_de->inode) != ent->dir->i_ino)
+		return -EIO;
+	BUFFER_TRACE(ent->dir_bh, "get_write_access");
+	return ext4_journal_get_write_access(handle, ent->dir_bh);
+}
+
+static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
+				  unsigned dir_ino)
+{
+	int retval;
+
+	ent->parent_de->inode = cpu_to_le32(dir_ino);
+	BUFFER_TRACE(ent->dir_bh, "call ext4_handle_dirty_metadata");
+	if (!ent->dir_inlined) {
+		if (is_dx(ent->inode)) {
+			retval = ext4_handle_dirty_dx_node(handle,
+							   ent->inode,
+							   ent->dir_bh);
+		} else {
+			retval = ext4_handle_dirty_dirent_node(handle,
+							       ent->inode,
+							       ent->dir_bh);
+		}
+	} else {
+		retval = ext4_mark_inode_dirty(handle, ent->inode);
+	}
+	if (retval) {
+		ext4_std_error(ent->dir->i_sb, retval);
+		return retval;
+	}
+	return 0;
+}
+
+static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
+		       unsigned ino, unsigned file_type)
+{
+	int retval;
+
+	BUFFER_TRACE(ent->bh, "get write access");
+	retval = ext4_journal_get_write_access(handle, ent->bh);
+	if (retval)
+		return retval;
+	ent->de->inode = cpu_to_le32(ino);
+	if (EXT4_HAS_INCOMPAT_FEATURE(ent->dir->i_sb,
+				      EXT4_FEATURE_INCOMPAT_FILETYPE))
+		ent->de->file_type = file_type;
+	ent->dir->i_version++;
+	ent->dir->i_ctime = ent->dir->i_mtime =
+		ext4_current_time(ent->dir);
+	ext4_mark_inode_dirty(handle, ent->dir);
+	BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
+	if (!ent->inlined) {
+		retval = ext4_handle_dirty_dirent_node(handle,
+						       ent->dir, ent->bh);
+		if (unlikely(retval)) {
+			ext4_std_error(ent->dir->i_sb, retval);
+			return retval;
+		}
+	}
+	brelse(ent->bh);
+	ent->bh = NULL;
+
+	return 0;
+}
+
+static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
+				  const struct qstr *d_name)
+{
+	int retval = -ENOENT;
+	struct buffer_head *bh;
+	struct ext4_dir_entry_2 *de;
+
+	bh = ext4_find_entry(dir, d_name, &de, NULL);
+	if (bh) {
+		retval = ext4_delete_entry(handle, dir, de, bh);
+		brelse(bh);
+	}
+	return retval;
+}
+
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
+{
+	int retval;
+	/*
+	 * ent->de could have moved from under us during htree split, so make
+	 * sure that we are deleting the right entry.  We might also be pointing
+	 * to a stale entry in the unused part of ent->bh so just checking inum
+	 * and the name isn't enough.
+	 */
+	if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
+	    ent->de->name_len != ent->dentry->d_name.len ||
+	    strncmp(ent->de->name, ent->dentry->d_name.name,
+		    ent->de->name_len)) {
+		retval = ext4_find_delete_entry(handle, ent->dir,
+						&ent->dentry->d_name);
+	} else {
+		retval = ext4_delete_entry(handle, ent->dir, ent->de, ent->bh);
+		if (retval == -ENOENT) {
+			retval = ext4_find_delete_entry(handle, ent->dir,
+							&ent->dentry->d_name);
+		}
+	}
+
+	if (retval) {
+		ext4_warning(ent->dir->i_sb,
+				"Deleting old file (%lu), %d, error=%d",
+				ent->dir->i_ino, ent->dir->i_nlink, retval);
+	}
+}
+
+static void ext4_update_dir_count(handle_t *handle, struct ext4_renament *ent)
+{
+	if (ent->dir_nlink_delta) {
+		if (ent->dir_nlink_delta == -1)
+			ext4_dec_count(handle, ent->dir);
+		else
+			ext4_inc_count(handle, ent->dir);
+		ext4_mark_inode_dirty(handle, ent->dir);
+	}
+}
+
 /*
  * Anybody can rename anything with this: the permission checks are left to the
  * higher-level routines.
@@ -3012,198 +3160,267 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		       struct inode *new_dir, struct dentry *new_dentry)
 {
 	handle_t *handle = NULL;
-	struct inode *old_inode, *new_inode;
-	struct buffer_head *old_bh, *new_bh, *dir_bh;
-	struct ext4_dir_entry_2 *old_de, *new_de;
+	struct ext4_renament old = {
+		.dir = old_dir,
+		.dentry = old_dentry,
+		.inode = old_dentry->d_inode,
+	};
+	struct ext4_renament new = {
+		.dir = new_dir,
+		.dentry = new_dentry,
+		.inode = new_dentry->d_inode,
+	};
 	int retval;
-	int inlined = 0, new_inlined = 0;
-	struct ext4_dir_entry_2 *parent_de;
 
-	dquot_initialize(old_dir);
-	dquot_initialize(new_dir);
-
-	old_bh = new_bh = dir_bh = NULL;
+	dquot_initialize(old.dir);
+	dquot_initialize(new.dir);
 
 	/* Initialize quotas before so that eventual writes go
 	 * in separate transaction */
-	if (new_dentry->d_inode)
-		dquot_initialize(new_dentry->d_inode);
+	if (new.inode)
+		dquot_initialize(new.inode);
 
-	old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL);
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
 	 *  and merrily kill the link to whatever was created under the
 	 *  same name. Goodbye sticky bit ;-<
 	 */
-	old_inode = old_dentry->d_inode;
 	retval = -ENOENT;
-	if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
+	if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
 		goto end_rename;
 
-	new_inode = new_dentry->d_inode;
-	new_bh = ext4_find_entry(new_dir, &new_dentry->d_name,
-				 &new_de, &new_inlined);
-	if (new_bh) {
-		if (!new_inode) {
-			brelse(new_bh);
-			new_bh = NULL;
+	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+				 &new.de, &new.inlined);
+	if (new.bh) {
+		if (!new.inode) {
+			brelse(new.bh);
+			new.bh = NULL;
 		}
 	}
-	if (new_inode && !test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
-		ext4_alloc_da_blocks(old_inode);
+	if (new.inode && !test_opt(new.dir->i_sb, NO_AUTO_DA_ALLOC))
+		ext4_alloc_da_blocks(old.inode);
 
-	handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
-		(2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+	handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
+		(2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
 		 EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
 		ext4_handle_sync(handle);
 
-	if (S_ISDIR(old_inode->i_mode)) {
-		if (new_inode) {
+	if (S_ISDIR(old.inode->i_mode)) {
+		if (new.inode) {
 			retval = -ENOTEMPTY;
-			if (!empty_dir(new_inode))
+			if (!empty_dir(new.inode))
+				goto end_rename;
+		} else {
+			retval = -EMLINK;
+			if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
 				goto end_rename;
 		}
-		retval = -EIO;
-		dir_bh = ext4_get_first_dir_block(handle, old_inode,
-						  &retval, &parent_de,
-						  &inlined);
-		if (!dir_bh)
-			goto end_rename;
-		if (le32_to_cpu(parent_de->inode) != old_dir->i_ino)
-			goto end_rename;
-		retval = -EMLINK;
-		if (!new_inode && new_dir != old_dir &&
-		    EXT4_DIR_LINK_MAX(new_dir))
-			goto end_rename;
-		BUFFER_TRACE(dir_bh, "get_write_access");
-		retval = ext4_journal_get_write_access(handle, dir_bh);
+		retval = ext4_rename_dir_prepare(handle, &old);
 		if (retval)
 			goto end_rename;
 	}
-	if (!new_bh) {
-		retval = ext4_add_entry(handle, new_dentry, old_inode);
+	if (!new.bh) {
+		retval = ext4_add_entry(handle, new.dentry, old.inode);
 		if (retval)
 			goto end_rename;
 	} else {
-		BUFFER_TRACE(new_bh, "get write access");
-		retval = ext4_journal_get_write_access(handle, new_bh);
+		retval = ext4_setent(handle, &new,
+				     old.inode->i_ino, old.de->file_type);
 		if (retval)
 			goto end_rename;
-		new_de->inode = cpu_to_le32(old_inode->i_ino);
-		if (EXT4_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
-					      EXT4_FEATURE_INCOMPAT_FILETYPE))
-			new_de->file_type = old_de->file_type;
-		new_dir->i_version++;
-		new_dir->i_ctime = new_dir->i_mtime =
-					ext4_current_time(new_dir);
-		ext4_mark_inode_dirty(handle, new_dir);
-		BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata");
-		if (!new_inlined) {
-			retval = ext4_handle_dirty_dirent_node(handle,
-							       new_dir, new_bh);
-			if (unlikely(retval)) {
-				ext4_std_error(new_dir->i_sb, retval);
-				goto end_rename;
-			}
-		}
-		brelse(new_bh);
-		new_bh = NULL;
 	}
 
 	/*
 	 * Like most other Unix systems, set the ctime for inodes on a
 	 * rename.
 	 */
-	old_inode->i_ctime = ext4_current_time(old_inode);
-	ext4_mark_inode_dirty(handle, old_inode);
+	old.inode->i_ctime = ext4_current_time(old.inode);
+	ext4_mark_inode_dirty(handle, old.inode);
 
 	/*
 	 * ok, that's it
 	 */
-	if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
-	    old_de->name_len != old_dentry->d_name.len ||
-	    strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
-	    (retval = ext4_delete_entry(handle, old_dir,
-					old_de, old_bh)) == -ENOENT) {
-		/* old_de could have moved from under us during htree split, so
-		 * make sure that we are deleting the right entry.  We might
-		 * also be pointing to a stale entry in the unused part of
-		 * old_bh so just checking inum and the name isn't enough. */
-		struct buffer_head *old_bh2;
-		struct ext4_dir_entry_2 *old_de2;
-
-		old_bh2 = ext4_find_entry(old_dir, &old_dentry->d_name,
-					  &old_de2, NULL);
-		if (old_bh2) {
-			retval = ext4_delete_entry(handle, old_dir,
-						   old_de2, old_bh2);
-			brelse(old_bh2);
-		}
+	ext4_rename_delete(handle, &old);
+
+	if (new.inode) {
+		ext4_dec_count(handle, new.inode);
+		new.inode->i_ctime = ext4_current_time(new.inode);
 	}
-	if (retval) {
-		ext4_warning(old_dir->i_sb,
-				"Deleting old file (%lu), %d, error=%d",
-				old_dir->i_ino, old_dir->i_nlink, retval);
-	}
-
-	if (new_inode) {
-		ext4_dec_count(handle, new_inode);
-		new_inode->i_ctime = ext4_current_time(new_inode);
-	}
-	old_dir->i_ctime = old_dir->i_mtime = ext4_current_time(old_dir);
-	ext4_update_dx_flag(old_dir);
-	if (dir_bh) {
-		parent_de->inode = cpu_to_le32(new_dir->i_ino);
-		BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
-		if (!inlined) {
-			if (is_dx(old_inode)) {
-				retval = ext4_handle_dirty_dx_node(handle,
-								   old_inode,
-								   dir_bh);
-			} else {
-				retval = ext4_handle_dirty_dirent_node(handle,
-							old_inode, dir_bh);
-			}
-		} else {
-			retval = ext4_mark_inode_dirty(handle, old_inode);
-		}
-		if (retval) {
-			ext4_std_error(old_dir->i_sb, retval);
+	old.dir->i_ctime = old.dir->i_mtime = ext4_current_time(old.dir);
+	ext4_update_dx_flag(old.dir);
+	if (old.dir_bh) {
+		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+		if (retval)
 			goto end_rename;
-		}
-		ext4_dec_count(handle, old_dir);
-		if (new_inode) {
+
+		ext4_dec_count(handle, old.dir);
+		if (new.inode) {
 			/* checked empty_dir above, can't have another parent,
 			 * ext4_dec_count() won't work for many-linked dirs */
-			clear_nlink(new_inode);
+			clear_nlink(new.inode);
 		} else {
-			ext4_inc_count(handle, new_dir);
-			ext4_update_dx_flag(new_dir);
-			ext4_mark_inode_dirty(handle, new_dir);
+			ext4_inc_count(handle, new.dir);
+			ext4_update_dx_flag(new.dir);
+			ext4_mark_inode_dirty(handle, new.dir);
 		}
 	}
-	ext4_mark_inode_dirty(handle, old_dir);
-	if (new_inode) {
-		ext4_mark_inode_dirty(handle, new_inode);
-		if (!new_inode->i_nlink)
-			ext4_orphan_add(handle, new_inode);
+	ext4_mark_inode_dirty(handle, old.dir);
+	if (new.inode) {
+		ext4_mark_inode_dirty(handle, new.inode);
+		if (!new.inode->i_nlink)
+			ext4_orphan_add(handle, new.inode);
 	}
 	retval = 0;
 
 end_rename:
-	brelse(dir_bh);
-	brelse(old_bh);
-	brelse(new_bh);
+	brelse(old.dir_bh);
+	brelse(old.bh);
+	brelse(new.bh);
 	if (handle)
 		ext4_journal_stop(handle);
 	return retval;
 }
 
+static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry)
+{
+	handle_t *handle = NULL;
+	struct ext4_renament old = {
+		.dir = old_dir,
+		.dentry = old_dentry,
+		.inode = old_dentry->d_inode,
+	};
+	struct ext4_renament new = {
+		.dir = new_dir,
+		.dentry = new_dentry,
+		.inode = new_dentry->d_inode,
+	};
+	u8 new_file_type;
+	int retval;
+
+	dquot_initialize(old.dir);
+	dquot_initialize(new.dir);
+
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name,
+				 &old.de, &old.inlined);
+	/*
+	 *  Check for inode number is _not_ due to possible IO errors.
+	 *  We might rmdir the source, keep it as pwd of some process
+	 *  and merrily kill the link to whatever was created under the
+	 *  same name. Goodbye sticky bit ;-<
+	 */
+	retval = -ENOENT;
+	if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
+		goto end_rename;
+
+	new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
+				 &new.de, &new.inlined);
+
+	/* RENAME_EXCHANGE case: old *and* new must both exist */
+	if (!new.bh || le32_to_cpu(new.de->inode) != new.inode->i_ino)
+		goto end_rename;
+
+	handle = ext4_journal_start(old.dir, EXT4_HT_DIR,
+		(2 * EXT4_DATA_TRANS_BLOCKS(old.dir->i_sb) +
+		 2 * EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+
+	if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
+		ext4_handle_sync(handle);
+
+	if (S_ISDIR(old.inode->i_mode)) {
+		old.is_dir = true;
+		retval = ext4_rename_dir_prepare(handle, &old);
+		if (retval)
+			goto end_rename;
+	}
+	if (S_ISDIR(new.inode->i_mode)) {
+		new.is_dir = true;
+		retval = ext4_rename_dir_prepare(handle, &new);
+		if (retval)
+			goto end_rename;
+	}
+
+	/*
+	 * Other than the special case of overwriting a directory, parents'
+	 * nlink only needs to be modified if this is a cross directory rename.
+	 */
+	if (old.dir != new.dir && old.is_dir != new.is_dir) {
+		old.dir_nlink_delta = old.is_dir ? -1 : 1;
+		new.dir_nlink_delta = -old.dir_nlink_delta;
+		retval = -EMLINK;
+		if ((old.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(old.dir)) ||
+		    (new.dir_nlink_delta > 0 && EXT4_DIR_LINK_MAX(new.dir)))
+			goto end_rename;
+	}
+
+	new_file_type = new.de->file_type;
+	retval = ext4_setent(handle, &new, old.inode->i_ino, old.de->file_type);
+	if (retval)
+		goto end_rename;
+
+	retval = ext4_setent(handle, &old, new.inode->i_ino, new_file_type);
+	if (retval)
+		goto end_rename;
+
+	/*
+	 * Like most other Unix systems, set the ctime for inodes on a
+	 * rename.
+	 */
+	old.inode->i_ctime = ext4_current_time(old.inode);
+	new.inode->i_ctime = ext4_current_time(new.inode);
+	ext4_mark_inode_dirty(handle, old.inode);
+	ext4_mark_inode_dirty(handle, new.inode);
+
+	if (old.dir_bh) {
+		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
+		if (retval)
+			goto end_rename;
+	}
+	if (new.dir_bh) {
+		retval = ext4_rename_dir_finish(handle, &new, old.dir->i_ino);
+		if (retval)
+			goto end_rename;
+	}
+	ext4_update_dir_count(handle, &old);
+	ext4_update_dir_count(handle, &new);
+	retval = 0;
+
+end_rename:
+	brelse(old.dir_bh);
+	brelse(new.dir_bh);
+	brelse(old.bh);
+	brelse(new.bh);
+	if (handle)
+		ext4_journal_stop(handle);
+	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 | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	if (flags & RENAME_EXCHANGE) {
+		return ext4_cross_rename(old_dir, old_dentry,
+					 new_dir, new_dentry);
+	}
+	/*
+	 * Existence checking was done by the VFS, otherwise "RENAME_NOREPLACE"
+	 * is equivalent to regular rename.
+	 */
+	return ext4_rename(old_dir, old_dentry, new_dir, new_dentry);
+}
+
 /*
  * directories can handle most operations...
  */
@@ -3218,6 +3435,7 @@ 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,

fs/inode.c

@@ -944,24 +944,22 @@ EXPORT_SYMBOL(unlock_new_inode);
 
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ *
+ * Lock any non-NULL argument that is not a directory.
+ * Zero, one or two objects may be locked by this function.
+ *
  * @inode1: first inode to lock
  * @inode2: second inode to lock
  */
 void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-	WARN_ON_ONCE(S_ISDIR(inode1->i_mode));
-	if (inode1 == inode2 || !inode2) {
-		mutex_lock(&inode1->i_mutex);
-		return;
-	}
-	WARN_ON_ONCE(S_ISDIR(inode2->i_mode));
-	if (inode1 < inode2) {
+	if (inode1 > inode2)
+		swap(inode1, inode2);
+
+	if (inode1 && !S_ISDIR(inode1->i_mode))
 		mutex_lock(&inode1->i_mutex);
+	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
 		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
-	} else {
-		mutex_lock(&inode2->i_mutex);
-		mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
-	}
 }
 EXPORT_SYMBOL(lock_two_nondirectories);
 
@@ -972,8 +970,9 @@ EXPORT_SYMBOL(lock_two_nondirectories);
  */
 void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
 {
-	mutex_unlock(&inode1->i_mutex);
-	if (inode2 && inode2 != inode1)
+	if (inode1 && !S_ISDIR(inode1->i_mode))
+		mutex_unlock(&inode1->i_mutex);
+	if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1)
 		mutex_unlock(&inode2->i_mutex);
 }
 EXPORT_SYMBOL(unlock_two_nondirectories);

fs/namei.c

@@ -1796,7 +1796,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			err = -ENOTDIR; 
 			break;
 		}
@@ -1817,7 +1817,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*name) {
-			if (!d_is_directory(root))
+			if (!d_can_lookup(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1873,7 +1873,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!d_is_directory(dentry)) {
+			if (!d_can_lookup(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
@@ -1955,7 +1955,7 @@ static int path_lookupat(int dfd, const char *name,
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			path_put(&nd->path);
 			err = -ENOTDIR;
 		}
@@ -2414,11 +2414,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
-		if (!d_is_directory(victim) && !d_is_autodir(victim))
+		if (!d_is_dir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (d_is_directory(victim) || d_is_autodir(victim))
+	} else if (d_is_dir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
@@ -3016,11 +3016,10 @@ finish_open:
 	}
 	audit_inode(name, nd->path.dentry, 0);
 	error = -EISDIR;
-	if ((open_flag & O_CREAT) &&
-	    (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
+	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
 	error = -ENOTDIR;
-	if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
 		goto out;
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -3744,7 +3743,7 @@ exit1:
 slashes:
 	if (d_is_negative(dentry))
 		error = -ENOENT;
-	else if (d_is_directory(dentry) || d_is_autodir(dentry))
+	else if (d_is_dir(dentry))
 		error = -EISDIR;
 	else
 		error = -ENOTDIR;
@@ -3974,7 +3973,28 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
 	return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
-/*
+/**
+ * vfs_rename - rename a filesystem object
+ * @old_dir:	parent of source
+ * @old_dentry:	source
+ * @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()).
+ *
+ * If vfs_rename discovers a delegation in need of breaking at either
+ * the source or destination, it will return -EWOULDBLOCK and return a
+ * reference to the inode in delegated_inode.  The caller should then
+ * break the delegation and retry.  Because breaking a delegation may
+ * take a long time, the caller should drop all locks before doing
+ * so.
+ *
+ * Alternatively, a caller may pass NULL for delegated_inode.  This may
+ * be appropriate for callers that expect the underlying filesystem not
+ * to be NFS exported.
+ *
  * The worst of all namespace operations - renaming directory. "Perverted"
  * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
  * Problems:
@@ -4002,163 +4022,139 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   ->i_mutex on parents, which works but leads to some truly excessive
  *	   locking].
  */
-static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
-			  struct inode *new_dir, struct dentry *new_dentry)
+int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
+	       struct inode *new_dir, struct dentry *new_dentry,
+	       struct inode **delegated_inode, unsigned int flags)
 {
-	int error = 0;
+	int error;
+	bool is_dir = d_is_dir(old_dentry);
+	const unsigned char *old_name;
+	struct inode *source = old_dentry->d_inode;
 	struct inode *target = new_dentry->d_inode;
+	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
 
+	if (source == target)
+		return 0;
+
+	error = may_delete(old_dir, old_dentry, is_dir);
+	if (error)
+		return error;
+
+	if (!target) {
+		error = may_create(new_dir, new_dentry);
+	} else {
+		new_is_dir = d_is_dir(new_dentry);
+
+		if (!(flags & RENAME_EXCHANGE))
+			error = may_delete(new_dir, new_dentry, is_dir);
+		else
+			error = may_delete(new_dir, new_dentry, new_is_dir);
+	}
+	if (error)
+		return error;
+
+	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,
 	 * we'll need to flip '..'.
 	 */
 	if (new_dir != old_dir) {
-		error = inode_permission(old_dentry->d_inode, MAY_WRITE);
-		if (error)
-			return error;
+		if (is_dir) {
+			error = inode_permission(source, MAY_WRITE);
+			if (error)
+				return error;
+		}
+		if ((flags & RENAME_EXCHANGE) && new_is_dir) {
+			error = inode_permission(target, MAY_WRITE);
+			if (error)
+				return error;
+		}
 	}
 
-	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
+	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
+				      flags);
 	if (error)
 		return error;
 
+	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
 	dget(new_dentry);
-	if (target)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		lock_two_nondirectories(source, target);
+	else if (target)
 		mutex_lock(&target->i_mutex);
 
 	error = -EBUSY;
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
-	error = -EMLINK;
-	if (max_links && !target && new_dir != old_dir &&
-	    new_dir->i_nlink >= max_links)
-		goto out;
-
-	if (target)
+	if (max_links && new_dir != old_dir) {
+		error = -EMLINK;
+		if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
+			goto out;
+		if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
+		    old_dir->i_nlink >= max_links)
+			goto out;
+	}
+	if (is_dir && !(flags & RENAME_EXCHANGE) && target)
 		shrink_dcache_parent(new_dentry);
-	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
-	if (error)
-		goto out;
-
-	if (target) {
-		target->i_flags |= S_DEAD;
-		dont_mount(new_dentry);
+	if (!is_dir) {
+		error = try_break_deleg(source, delegated_inode);
+		if (error)
+			goto out;
 	}
-out:
-	if (target)
-		mutex_unlock(&target->i_mutex);
-	dput(new_dentry);
-	if (!error)
-		if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-			d_move(old_dentry,new_dentry);
-	return error;
-}
-
-static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
-			    struct inode *new_dir, struct dentry *new_dentry,
-			    struct inode **delegated_inode)
-{
-	struct inode *target = new_dentry->d_inode;
-	struct inode *source = old_dentry->d_inode;
-	int error;
-
-	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
-	if (error)
-		return error;
-
-	dget(new_dentry);
-	lock_two_nondirectories(source, target);
-
-	error = -EBUSY;
-	if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
-		goto out;
-
-	error = try_break_deleg(source, delegated_inode);
-	if (error)
-		goto out;
-	if (target) {
+	if (target && !new_is_dir) {
 		error = try_break_deleg(target, delegated_inode);
 		if (error)
 			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;
 
-	if (target)
+	if (!(flags & RENAME_EXCHANGE) && target) {
+		if (is_dir)
+			target->i_flags |= S_DEAD;
 		dont_mount(new_dentry);
-	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-		d_move(old_dentry, new_dentry);
+	}
+	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
+		if (!(flags & RENAME_EXCHANGE))
+			d_move(old_dentry, new_dentry);
+		else
+			d_exchange(old_dentry, new_dentry);
+	}
 out:
-	unlock_two_nondirectories(source, target);
+	if (!is_dir || (flags & RENAME_EXCHANGE))
+		unlock_two_nondirectories(source, target);
+	else if (target)
+		mutex_unlock(&target->i_mutex);
 	dput(new_dentry);
-	return error;
-}
-
-/**
- * vfs_rename - rename a filesystem object
- * @old_dir:	parent of source
- * @old_dentry:	source
- * @new_dir:	parent of destination
- * @new_dentry:	destination
- * @delegated_inode: returns an inode needing a delegation break
- *
- * The caller must hold multiple mutexes--see lock_rename()).
- *
- * If vfs_rename discovers a delegation in need of breaking at either
- * the source or destination, it will return -EWOULDBLOCK and return a
- * reference to the inode in delegated_inode.  The caller should then
- * break the delegation and retry.  Because breaking a delegation may
- * take a long time, the caller should drop all locks before doing
- * so.
- *
- * Alternatively, a caller may pass NULL for delegated_inode.  This may
- * be appropriate for callers that expect the underlying filesystem not
- * to be NFS exported.
- */
-int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
-	       struct inode *new_dir, struct dentry *new_dentry,
-	       struct inode **delegated_inode)
-{
-	int error;
-	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
-	const unsigned char *old_name;
-
-	if (old_dentry->d_inode == new_dentry->d_inode)
- 		return 0;
- 
-	error = may_delete(old_dir, old_dentry, is_dir);
-	if (error)
-		return error;
-
-	if (!new_dentry->d_inode)
-		error = may_create(new_dir, new_dentry);
-	else
-		error = may_delete(new_dir, new_dentry, is_dir);
-	if (error)
-		return error;
-
-	if (!old_dir->i_op->rename)
-		return -EPERM;
-
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
-
-	if (is_dir)
-		error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
-	else
-		error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode);
-	if (!error)
+	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
-			      new_dentry->d_inode, old_dentry);
+			      !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
+		if (flags & RENAME_EXCHANGE) {
+			fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
+				      new_is_dir, NULL, new_dentry);
+		}
+	}
 	fsnotify_oldname_free(old_name);
 
 	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;
@@ -4170,6 +4166,13 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	unsigned int lookup_flags = 0;
 	bool should_retry = false;
 	int error;
+
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
+		return -EINVAL;
+
 retry:
 	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
 	if (IS_ERR(from)) {
@@ -4193,6 +4196,8 @@ retry:
 		goto exit2;
 
 	new_dir = newnd.path.dentry;
+	if (flags & RENAME_NOREPLACE)
+		error = -EEXIST;
 	if (newnd.last_type != LAST_NORM)
 		goto exit2;
 
@@ -4202,7 +4207,8 @@ retry:
 
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
-	newnd.flags |= LOOKUP_RENAME_TARGET;
+	if (!(flags & RENAME_EXCHANGE))
+		newnd.flags |= LOOKUP_RENAME_TARGET;
 
 retry_deleg:
 	trap = lock_rename(new_dir, old_dir);
@@ -4215,34 +4221,49 @@ 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;
+	if (flags & RENAME_EXCHANGE) {
+		error = -ENOENT;
+		if (d_is_negative(new_dentry))
+			goto exit5;
+
+		if (!d_is_dir(new_dentry)) {
+			error = -ENOTDIR;
+			if (newnd.last.name[newnd.last.len])
+				goto exit5;
+		}
+	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
+	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
-			goto exit4;
-		if (newnd.last.name[newnd.last.len])
-			goto exit4;
+			goto exit5;
+		if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
+			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 (!(flags & RENAME_EXCHANGE))
+		error = -ENOTEMPTY;
 	if (new_dentry == trap)
 		goto exit5;
 
 	error = security_path_rename(&oldnd.path, old_dentry,
-				     &newnd.path, new_dentry);
+				     &newnd.path, new_dentry, flags);
 	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:
@@ -4272,9 +4293,15 @@ exit:
 	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

@@ -1694,7 +1694,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	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/dcache.h

@@ -308,6 +308,7 @@ extern void dentry_update_name_case(struct dentry *, struct qstr *);
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
@@ -429,7 +430,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_ENTRY_TYPE;
 }
 
-static inline bool d_is_directory(const struct dentry *dentry)
+static inline bool d_can_lookup(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
 }
@@ -439,6 +440,11 @@ static inline bool d_is_autodir(const struct dentry *dentry)
 	return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
 }
 
+static inline bool d_is_dir(const struct dentry *dentry)
+{
+	return d_can_lookup(dentry) || d_is_autodir(dentry);
+}
+
 static inline bool d_is_symlink(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;

include/linux/fs.h

@@ -1461,7 +1461,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 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.
@@ -1572,6 +1572,8 @@ struct inode_operations {
 	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);

include/linux/security.h

@@ -1793,7 +1793,8 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry);
 int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev);
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			  struct inode *new_dir, struct dentry *new_dentry);
+			  struct inode *new_dir, struct dentry *new_dentry,
+			  unsigned int flags);
 int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask);
@@ -2161,7 +2162,8 @@ static inline int security_inode_mknod(struct inode *dir,
 static inline int security_inode_rename(struct inode *old_dir,
 					 struct dentry *old_dentry,
 					 struct inode *new_dir,
-					 struct dentry *new_dentry)
+					 struct dentry *new_dentry,
+					 unsigned int flags)
 {
 	return 0;
 }
@@ -2955,7 +2957,8 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
 int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 		       struct dentry *new_dentry);
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry);
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags);
 int security_path_chmod(struct path *path, umode_t mode);
 int security_path_chown(struct path *path, kuid_t uid, kgid_t gid);
 int security_path_chroot(struct path *path);
@@ -3003,7 +3006,8 @@ static inline int security_path_link(struct dentry *old_dentry,
 static inline int security_path_rename(struct path *old_dir,
 				       struct dentry *old_dentry,
 				       struct path *new_dir,
-				       struct dentry *new_dentry)
+				       struct dentry *new_dentry,
+				       unsigned int flags)
 {
 	return 0;
 }

include/uapi/linux/fs.h

@@ -35,6 +35,9 @@
 #define SEEK_HOLE	4	/* seek to the next hole */
 #define SEEK_MAX	SEEK_HOLE
 
+#define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
+
 struct fstrim_range {
 	__u64 start;
 	__u64 len;

security/security.c

@@ -433,11 +433,20 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 }
 
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry)
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags)
 {
 	if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
 		     (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->path_rename(new_dir, new_dentry,
+						    old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->path_rename(old_dir, old_dentry, new_dir,
 					 new_dentry);
 }
@@ -524,11 +533,20 @@ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			   struct inode *new_dir, struct dentry *new_dentry)
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
 {
         if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
             (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->inode_rename(new_dir, new_dentry,
+						     old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->inode_rename(old_dir, old_dentry,
 					   new_dir, new_dentry);
 }