vfs: add cross-rename

If flags contain RENAME_EXCHANGE then exchange source and destination files.
There's no restriction on the type of the files; e.g. a directory can be
exchanged with a symlink.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>

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/namei.c

@@ -4031,6 +4031,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *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;
@@ -4039,10 +4041,16 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
-	if (!target)
+	if (!target) {
 		error = may_create(new_dir, new_dentry);
-	else
+	} 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;
 
@@ -4056,11 +4064,18 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * If we are going to change the parent - check write permissions,
 	 * we'll need to flip '..'.
 	 */
-	if (is_dir && new_dir != old_dir) {
+	if (new_dir != old_dir) {
+		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,
 				      flags);
@@ -4069,7 +4084,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
 	dget(new_dentry);
-	if (!is_dir)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
 	else if (target)
 		mutex_lock(&target->i_mutex);
@@ -4078,26 +4093,26 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
-	if (is_dir) {
-		unsigned max_links = new_dir->i_sb->s_max_links;
-
+	if (max_links && new_dir != old_dir) {
 		error = -EMLINK;
-		if (max_links && !target && new_dir != old_dir &&
-		    new_dir->i_nlink >= max_links)
+		if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
 			goto out;
-
-		if (target)
+		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);
-	} else {
+	if (!is_dir) {
 		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;
 	}
-	}
 	if (!flags) {
 		error = old_dir->i_op->rename(old_dir, old_dentry,
 					      new_dir, new_dentry);
@@ -4108,22 +4123,31 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	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))
+	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:
-	if (!is_dir)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
 		unlock_two_nondirectories(source, target);
 	else if (target)
 		mutex_unlock(&target->i_mutex);
 	dput(new_dentry);
-	if (!error)
+	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
-			      target, 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;
@@ -4143,7 +4167,10 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	bool should_retry = false;
 	int error;
 
-	if (flags & ~RENAME_NOREPLACE)
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
 		return -EINVAL;
 
 retry:
@@ -4180,6 +4207,7 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
+	if (!(flags & RENAME_EXCHANGE))
 		newnd.flags |= LOOKUP_RENAME_TARGET;
 
 retry_deleg:
@@ -4200,12 +4228,23 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	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_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit5;
-		if (newnd.last.name[newnd.last.len])
+		if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
 			goto exit5;
 	}
 	/* source should not be ancestor of target */
@@ -4213,6 +4252,7 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	if (old_dentry == trap)
 		goto exit5;
 	/* target should not be an ancestor of source */
+	if (!(flags & RENAME_EXCHANGE))
 		error = -ENOTEMPTY;
 	if (new_dentry == trap)
 		goto exit5;

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 */

include/uapi/linux/fs.h

@@ -36,6 +36,7 @@
 #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;

security/security.c

@@ -439,6 +439,14 @@ int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
 	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);
 }
@@ -531,6 +539,14 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
         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);
 }