[PATCH] configfs: User-driven configuration filesystem

Configfs, a file system for userspace-driven kernel object configuration.
The OCFS2 stack makes extensive use of this for propagation of cluster
configuration information into kernel.

Signed-off-by: Joel Becker <joel.becker@oracle.com>

15 files changed, 3575 insertions, 0 deletions

diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index bcfbab899b37..628f8a7adb85 100644
--- a/Documentation/filesystems/00-INDEX
+++ b/Documentation/filesystems/00-INDEX
@@ -12,6 +12,8 @@ cifs.txt
         - description of the CIFS filesystem
 coda.txt
         - description of the CODA filesystem.
+configfs/
+        - directory containing configfs documentation and example code.
 cramfs.txt
         - info on the cram filesystem for small storage (ROMs etc)
 devfs/
diff --git a/Documentation/filesystems/configfs/configfs.txt b/Documentation/filesystems/configfs/configfs.txt
new file mode 100644
index 000000000000..c4ff96b7c4e0
--- /dev/null
+++ b/Documentation/filesystems/configfs/configfs.txt
@@ -0,0 +1,434 @@
+
+configfs - Userspace-driven kernel object configuation.
+
+Joel Becker <joel.becker@oracle.com>
+
+Updated: 31 March 2005
+
+Copyright (c) 2005 Oracle Corporation,
+        Joel Becker <joel.becker@oracle.com>
+
+
+[What is configfs?]
+
+configfs is a ram-based filesystem that provides the converse of
+sysfs's functionality.  Where sysfs is a filesystem-based view of
+kernel objects, configfs is a filesystem-based manager of kernel
+objects, or config_items.
+
+With sysfs, an object is created in kernel (for example, when a device
+is discovered) and it is registered with sysfs.  Its attributes then
+appear in sysfs, allowing userspace to read the attributes via
+readdir(3)/read(2).  It may allow some attributes to be modified via
+write(2).  The important point is that the object is created and
+destroyed in kernel, the kernel controls the lifecycle of the sysfs
+representation, and sysfs is merely a window on all this.
+
+A configfs config_item is created via an explicit userspace operation:
+mkdir(2).  It is destroyed via rmdir(2).  The attributes appear at
+mkdir(2) time, and can be read or modified via read(2) and write(2).
+As with sysfs, readdir(3) queries the list of items and/or attributes.
+symlink(2) can be used to group items together.  Unlike sysfs, the
+lifetime of the representation is completely driven by userspace.  The
+kernel modules backing the items must respond to this.
+
+Both sysfs and configfs can and should exist together on the same
+system.  One is not a replacement for the other.
+
+[Using configfs]
+
+configfs can be compiled as a module or into the kernel.  You can access
+it by doing
+
+        mount -t configfs none /config
+
+The configfs tree will be empty unless client modules are also loaded.
+These are modules that register their item types with configfs as
+subsystems.  Once a client subsystem is loaded, it will appear as a
+subdirectory (or more than one) under /config.  Like sysfs, the
+configfs tree is always there, whether mounted on /config or not.
+
+An item is created via mkdir(2).  The item's attributes will also
+appear at this time.  readdir(3) can determine what the attributes are,
+read(2) can query their default values, and write(2) can store new
+values.  Like sysfs, attributes should be ASCII text files, preferably
+with only one value per file.  The same efficiency caveats from sysfs
+apply.  Don't mix more than one attribute in one attribute file.
+
+Like sysfs, configfs expects write(2) to store the entire buffer at
+once.  When writing to configfs attributes, userspace processes should
+first read the entire file, modify the portions they wish to change, and
+then write the entire buffer back.  Attribute files have a maximum size
+of one page (PAGE_SIZE, 4096 on i386).
+
+When an item needs to be destroyed, remove it with rmdir(2).  An
+item cannot be destroyed if any other item has a link to it (via
+symlink(2)).  Links can be removed via unlink(2).
+
+[Configuring FakeNBD: an Example]
+
+Imagine there's a Network Block Device (NBD) driver that allows you to
+access remote block devices.  Call it FakeNBD.  FakeNBD uses configfs
+for its configuration.  Obviously, there will be a nice program that
+sysadmins use to configure FakeNBD, but somehow that program has to tell
+the driver about it.  Here's where configfs comes in.
+
+When the FakeNBD driver is loaded, it registers itself with configfs.
+readdir(3) sees this just fine:
+
+        # ls /config
+        fakenbd
+
+A fakenbd connection can be created with mkdir(2).  The name is
+arbitrary, but likely the tool will make some use of the name.  Perhaps
+it is a uuid or a disk name:
+
+        # mkdir /config/fakenbd/disk1
+        # ls /config/fakenbd/disk1
+        target device rw
+
+The target attribute contains the IP address of the server FakeNBD will
+connect to.  The device attribute is the device on the server.
+Predictably, the rw attribute determines whether the connection is
+read-only or read-write.
+
+        # echo 10.0.0.1 > /config/fakenbd/disk1/target
+        # echo /dev/sda1 > /config/fakenbd/disk1/device
+        # echo 1 > /config/fakenbd/disk1/rw
+
+That's it.  That's all there is.  Now the device is configured, via the
+shell no less.
+
+[Coding With configfs]
+
+Every object in configfs is a config_item.  A config_item reflects an
+object in the subsystem.  It has attributes that match values on that
+object.  configfs handles the filesystem representation of that object
+and its attributes, allowing the subsystem to ignore all but the
+basic show/store interaction.
+
+Items are created and destroyed inside a config_group.  A group is a
+collection of items that share the same attributes and operations.
+Items are created by mkdir(2) and removed by rmdir(2), but configfs
+handles that.  The group has a set of operations to perform these tasks
+
+A subsystem is the top level of a client module.  During initialization,
+the client module registers the subsystem with configfs, the subsystem
+appears as a directory at the top of the configfs filesystem.  A
+subsystem is also a config_group, and can do everything a config_group
+can.
+
+[struct config_item]
+
+        struct config_item {
+                char                    *ci_name;
+                char                    ci_namebuf[UOBJ_NAME_LEN];
+                struct kref             ci_kref;
+                struct list_head        ci_entry;
+                struct config_item      *ci_parent;
+                struct config_group     *ci_group;
+                struct config_item_type *ci_type;
+                struct dentry           *ci_dentry;
+        };
+
+        void config_item_init(struct config_item *);
+        void config_item_init_type_name(struct config_item *,
+                                        const char *name,
+                                        struct config_item_type *type);
+        struct config_item *config_item_get(struct config_item *);
+        void config_item_put(struct config_item *);
+
+Generally, struct config_item is embedded in a container structure, a
+structure that actually represents what the subsystem is doing.  The
+config_item portion of that structure is how the object interacts with
+configfs.
+
+Whether statically defined in a source file or created by a parent
+config_group, a config_item must have one of the _init() functions
+called on it.  This initializes the reference count and sets up the
+appropriate fields.
+
+All users of a config_item should have a reference on it via
+config_item_get(), and drop the reference when they are done via
+config_item_put().
+
+By itself, a config_item cannot do much more than appear in configfs.
+Usually a subsystem wants the item to display and/or store attributes,
+among other things.  For that, it needs a type.
+
+[struct config_item_type]
+
+        struct configfs_item_operations {
+                void (*release)(struct config_item *);
+                ssize_t (*show_attribute)(struct config_item *,
+                                          struct configfs_attribute *,
+                                          char *);
+                ssize_t (*store_attribute)(struct config_item *,
+                                           struct configfs_attribute *,
+                                           const char *, size_t);
+                int (*allow_link)(struct config_item *src,
+                                  struct config_item *target);
+                int (*drop_link)(struct config_item *src,
+                                 struct config_item *target);
+        };
+
+        struct config_item_type {
+                struct module                           *ct_owner;
+                struct configfs_item_operations         *ct_item_ops;
+                struct configfs_group_operations        *ct_group_ops;
+                struct configfs_attribute               **ct_attrs;
+        };
+
+The most basic function of a config_item_type is to define what
+operations can be performed on a config_item.  All items that have been
+allocated dynamically will need to provide the ct_item_ops->release()
+method.  This method is called when the config_item's reference count
+reaches zero.  Items that wish to display an attribute need to provide
+the ct_item_ops->show_attribute() method.  Similarly, storing a new
+attribute value uses the store_attribute() method.
+
+[struct configfs_attribute]
+
+        struct configfs_attribute {
+                char                    *ca_name;
+                struct module           *ca_owner;
+                mode_t                  ca_mode;
+        };
+
+When a config_item wants an attribute to appear as a file in the item's
+configfs directory, it must define a configfs_attribute describing it.
+It then adds the attribute to the NULL-terminated array
+config_item_type->ct_attrs.  When the item appears in configfs, the
+attribute file will appear with the configfs_attribute->ca_name
+filename.  configfs_attribute->ca_mode specifies the file permissions.
+
+If an attribute is readable and the config_item provides a
+ct_item_ops->show_attribute() method, that method will be called
+whenever userspace asks for a read(2) on the attribute.  The converse
+will happen for write(2).
+
+[struct config_group]
+
+A config_item cannot live in a vaccum.  The only way one can be created
+is via mkdir(2) on a config_group.  This will trigger creation of a
+child item.
+
+        struct config_group {
+                struct config_item              cg_item;
+                struct list_head                cg_children;
+                struct configfs_subsystem       *cg_subsys;
+                struct config_group             **default_groups;
+        };
+
+        void config_group_init(struct config_group *group);
+        void config_group_init_type_name(struct config_group *group,
+                                         const char *name,
+                                         struct config_item_type *type);
+
+
+The config_group structure contains a config_item.  Properly configuring
+that item means that a group can behave as an item in its own right.
+However, it can do more: it can create child items or groups.  This is
+accomplished via the group operations specified on the group's
+config_item_type.
+
+        struct configfs_group_operations {
+                struct config_item *(*make_item)(struct config_group *group,
+                                                 const char *name);
+                struct config_group *(*make_group)(struct config_group *group,
+                                                   const char *name);
+                int (*commit_item)(struct config_item *item);
+                void (*drop_item)(struct config_group *group,
+                                  struct config_item *item);
+        };
+
+A group creates child items by providing the
+ct_group_ops->make_item() method.  If provided, this method is called from mkdir(2) in the group's directory.  The subsystem allocates a new
+config_item (or more likely, its container structure), initializes it,
+and returns it to configfs.  Configfs will then populate the filesystem
+tree to reflect the new item.
+
+If the subsystem wants the child to be a group itself, the subsystem
+provides ct_group_ops->make_group().  Everything else behaves the same,
+using the group _init() functions on the group.
+
+Finally, when userspace calls rmdir(2) on the item or group,
+ct_group_ops->drop_item() is called.  As a config_group is also a
+config_item, it is not necessary for a seperate drop_group() method.
+The subsystem must config_item_put() the reference that was initialized
+upon item allocation.  If a subsystem has no work to do, it may omit
+the ct_group_ops->drop_item() method, and configfs will call
+config_item_put() on the item on behalf of the subsystem.
+
+IMPORTANT: drop_item() is void, and as such cannot fail.  When rmdir(2)
+is called, configfs WILL remove the item from the filesystem tree
+(assuming that it has no children to keep it busy).  The subsystem is
+responsible for responding to this.  If the subsystem has references to
+the item in other threads, the memory is safe.  It may take some time
+for the item to actually disappear from the subsystem's usage.  But it
+is gone from configfs.
+
+A config_group cannot be removed while it still has child items.  This
+is implemented in the configfs rmdir(2) code.  ->drop_item() will not be
+called, as the item has not been dropped.  rmdir(2) will fail, as the
+directory is not empty.
+
+[struct configfs_subsystem]
+
+A subsystem must register itself, ususally at module_init time.  This
+tells configfs to make the subsystem appear in the file tree.
+
+        struct configfs_subsystem {
+                struct config_group     su_group;
+                struct semaphore        su_sem;
+        };
+
+        int configfs_register_subsystem(struct configfs_subsystem *subsys);
+        void configfs_unregister_subsystem(struct configfs_subsystem *subsys);
+
+        A subsystem consists of a toplevel config_group and a semaphore.
+The group is where child config_items are created.  For a subsystem,
+this group is usually defined statically.  Before calling
+configfs_register_subsystem(), the subsystem must have initialized the
+group via the usual group _init() functions, and it must also have
+initialized the semaphore.
+        When the register call returns, the subsystem is live, and it
+will be visible via configfs.  At that point, mkdir(2) can be called and
+the subsystem must be ready for it.
+
+[An Example]
+
+The best example of these basic concepts is the simple_children
+subsystem/group and the simple_child item in configfs_example.c  It
+shows a trivial object displaying and storing an attribute, and a simple
+group creating and destroying these children.
+
+[Hierarchy Navigation and the Subsystem Semaphore]
+
+There is an extra bonus that configfs provides.  The config_groups and
+config_items are arranged in a hierarchy due to the fact that they
+appear in a filesystem.  A subsystem is NEVER to touch the filesystem
+parts, but the subsystem might be interested in this hierarchy.  For
+this reason, the hierarchy is mirrored via the config_group->cg_children
+and config_item->ci_parent structure members.
+
+A subsystem can navigate the cg_children list and the ci_parent pointer
+to see the tree created by the subsystem.  This can race with configfs'
+management of the hierarchy, so configfs uses the subsystem semaphore to
+protect modifications.  Whenever a subsystem wants to navigate the
+hierarchy, it must do so under the protection of the subsystem
+semaphore.
+
+A subsystem will be prevented from acquiring the semaphore while a newly
+allocated item has not been linked into this hierarchy.   Similarly, it
+will not be able to acquire the semaphore while a dropping item has not
+yet been unlinked.  This means that an item's ci_parent pointer will
+never be NULL while the item is in configfs, and that an item will only
+be in its parent's cg_children list for the same duration.  This allows
+a subsystem to trust ci_parent and cg_children while they hold the
+semaphore.
+
+[Item Aggregation Via symlink(2)]
+
+configfs provides a simple group via the group->item parent/child
+relationship.  Often, however, a larger environment requires aggregation
+outside of the parent/child connection.  This is implemented via
+symlink(2).
+
+A config_item may provide the ct_item_ops->allow_link() and
+ct_item_ops->drop_link() methods.  If the ->allow_link() method exists,
+symlink(2) may be called with the config_item as the source of the link.
+These links are only allowed between configfs config_items.  Any
+symlink(2) attempt outside the configfs filesystem will be denied.
+
+When symlink(2) is called, the source config_item's ->allow_link()
+method is called with itself and a target item.  If the source item
+allows linking to target item, it returns 0.  A source item may wish to
+reject a link if it only wants links to a certain type of object (say,
+in its own subsystem).
+
+When unlink(2) is called on the symbolic link, the source item is
+notified via the ->drop_link() method.  Like the ->drop_item() method,
+this is a void function and cannot return failure.  The subsystem is
+responsible for responding to the change.
+
+A config_item cannot be removed while it links to any other item, nor
+can it be removed while an item links to it.  Dangling symlinks are not
+allowed in configfs.
+
+[Automatically Created Subgroups]
+
+A new config_group may want to have two types of child config_items.
+While this could be codified by magic names in ->make_item(), it is much
+more explicit to have a method whereby userspace sees this divergence.
+
+Rather than have a group where some items behave differently than
+others, configfs provides a method whereby one or many subgroups are
+automatically created inside the parent at its creation.  Thus,
+mkdir("parent) results in "parent", "parent/subgroup1", up through
+"parent/subgroupN".  Items of type 1 can now be created in
+"parent/subgroup1", and items of type N can be created in
+"parent/subgroupN".
+
+These automatic subgroups, or default groups, do not preclude other
+children of the parent group.  If ct_group_ops->make_group() exists,
+other child groups can be created on the parent group directly.
+
+A configfs subsystem specifies default groups by filling in the
+NULL-terminated array default_groups on the config_group structure.
+Each group in that array is populated in the configfs tree at the same
+time as the parent group.  Similarly, they are removed at the same time
+as the parent.  No extra notification is provided.  When a ->drop_item()
+method call notifies the subsystem the parent group is going away, it
+also means every default group child associated with that parent group.
+
+As a consequence of this, default_groups cannot be removed directly via
+rmdir(2).  They also are not considered when rmdir(2) on the parent
+group is checking for children.
+
+[Committable Items]
+
+NOTE: Committable items are currently unimplemented.
+
+Some config_items cannot have a valid initial state.  That is, no
+default values can be specified for the item's attributes such that the
+item can do its work.  Userspace must configure one or more attributes,
+after which the subsystem can start whatever entity this item
+represents.
+
+Consider the FakeNBD device from above.  Without a target address *and*
+a target device, the subsystem has no idea what block device to import.
+The simple example assumes that the subsystem merely waits until all the
+appropriate attributes are configured, and then connects.  This will,
+indeed, work, but now every attribute store must check if the attributes
+are initialized.  Every attribute store must fire off the connection if
+that condition is met.
+
+Far better would be an explicit action notifying the subsystem that the
+config_item is ready to go.  More importantly, an explicit action allows
+the subsystem to provide feedback as to whether the attibutes are
+initialized in a way that makes sense.  configfs provides this as
+committable items.
+
+configfs still uses only normal filesystem operations.  An item is
+committed via rename(2).  The item is moved from a directory where it
+can be modified to a directory where it cannot.
+
+Any group that provides the ct_group_ops->commit_item() method has
+committable items.  When this group appears in configfs, mkdir(2) will
+not work directly in the group.  Instead, the group will have two
+subdirectories: "live" and "pending".  The "live" directory does not
+support mkdir(2) or rmdir(2) either.  It only allows rename(2).  The
+"pending" directory does allow mkdir(2) and rmdir(2).  An item is
+created in the "pending" directory.  Its attributes can be modified at
+will.  Userspace commits the item by renaming it into the "live"
+directory.  At this point, the subsystem recieves the ->commit_item()
+callback.  If all required attributes are filled to satisfaction, the
+method returns zero and the item is moved to the "live" directory.
+
+As rmdir(2) does not work in the "live" directory, an item must be
+shutdown, or "uncommitted".  Again, this is done via rename(2), this
+time from the "live" directory back to the "pending" one.  The subsystem
+is notified by the ct_group_ops->uncommit_object() method.
+
+
diff --git a/Documentation/filesystems/configfs/configfs_example.c b/Documentation/filesystems/configfs/configfs_example.c
new file mode 100644
index 000000000000..f3c6e4946f98
--- /dev/null
+++ b/Documentation/filesystems/configfs/configfs_example.c
@@ -0,0 +1,474 @@
+/*
+ * vim: noexpandtab ts=8 sts=0 sw=8:
+ *
+ * configfs_example.c - This file is a demonstration module containing
+ *      a number of configfs subsystems.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+
+
+/*
+ * 01-childless
+ *
+ * This first example is a childless subsystem.  It cannot create
+ * any config_items.  It just has attributes.
+ *
+ * Note that we are enclosing the configfs_subsystem inside a container.
+ * This is not necessary if a subsystem has no attributes directly
+ * on the subsystem.  See the next example, 02-simple-children, for
+ * such a subsystem.
+ */
+
+struct childless {
+        struct configfs_subsystem subsys;
+        int showme;
+        int storeme;
+};
+
+struct childless_attribute {
+        struct configfs_attribute attr;
+        ssize_t (*show)(struct childless *, char *);
+        ssize_t (*store)(struct childless *, const char *, size_t);
+};
+
+static inline struct childless *to_childless(struct config_item *item)
+{
+        return item ? container_of(to_configfs_subsystem(to_config_group(item)), struct childless, subsys) : NULL;
+}
+
+static ssize_t childless_showme_read(struct childless *childless,
+                                     char *page)
+{
+        ssize_t pos;
+
+        pos = sprintf(page, "%d\n", childless->showme);
+        childless->showme++;
+
+        return pos;
+}
+
+static ssize_t childless_storeme_read(struct childless *childless,
+                                      char *page)
+{
+        return sprintf(page, "%d\n", childless->storeme);
+}
+
+static ssize_t childless_storeme_write(struct childless *childless,
+                                       const char *page,
+                                       size_t count)
+{
+        unsigned long tmp;
+        char *p = (char *) page;
+
+        tmp = simple_strtoul(p, &p, 10);
+        if (!p || (*p && (*p != '\n')))
+                return -EINVAL;
+
+        if (tmp > INT_MAX)
+                return -ERANGE;
+
+        childless->storeme = tmp;
+
+        return count;
+}
+
+static ssize_t childless_description_read(struct childless *childless,
+                                          char *page)
+{
+        return sprintf(page,
+"[01-childless]\n"
+"\n"
+"The childless subsystem is the simplest possible subsystem in\n"
+"configfs.  It does not support the creation of child config_items.\n"
+"It only has a few attributes.  In fact, it isn't much different\n"
+"than a directory in /proc.\n");
+}
+
+static struct childless_attribute childless_attr_showme = {
+        .attr   = { .ca_owner = THIS_MODULE, .ca_name = "showme", .ca_mode = S_IRUGO },
+        .show   = childless_showme_read,
+};
+static struct childless_attribute childless_attr_storeme = {
+        .attr   = { .ca_owner = THIS_MODULE, .ca_name = "storeme", .ca_mode = S_IRUGO | S_IWUSR },
+        .show   = childless_storeme_read,
+        .store  = childless_storeme_write,
+};
+static struct childless_attribute childless_attr_description = {
+        .attr = { .ca_owner = THIS_MODULE, .ca_name = "description", .ca_mode = S_IRUGO },
+        .show = childless_description_read,
+};
+
+static struct configfs_attribute *childless_attrs[] = {
+        &childless_attr_showme.attr,
+        &childless_attr_storeme.attr,
+        &childless_attr_description.attr,
+        NULL,
+};
+
+static ssize_t childless_attr_show(struct config_item *item,
+                                   struct configfs_attribute *attr,
+                                   char *page)
+{
+        struct childless *childless = to_childless(item);
+        struct childless_attribute *childless_attr =
+                container_of(attr, struct childless_attribute, attr);
+        ssize_t ret = 0;
+
+        if (childless_attr->show)
+                ret = childless_attr->show(childless, page);
+        return ret;
+}
+
+static ssize_t childless_attr_store(struct config_item *item,
+                                    struct configfs_attribute *attr,
+                                    const char *page, size_t count)
+{
+        struct childless *childless = to_childless(item);
+        struct childless_attribute *childless_attr =
+                container_of(attr, struct childless_attribute, attr);
+        ssize_t ret = -EINVAL;
+
+        if (childless_attr->store)
+                ret = childless_attr->store(childless, page, count);
+        return ret;
+}
+
+static struct configfs_item_operations childless_item_ops = {
+        .show_attribute         = childless_attr_show,
+        .store_attribute        = childless_attr_store,
+};
+
+static struct config_item_type childless_type = {
+        .ct_item_ops    = &childless_item_ops,
+        .ct_attrs       = childless_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+
+static struct childless childless_subsys = {
+        .subsys = {
+                .su_group = {
+                        .cg_item = {
+                                .ci_namebuf = "01-childless",
+                                .ci_type = &childless_type,
+                        },
+                },
+        },
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 02-simple-children
+ *
+ * This example merely has a simple one-attribute child.  Note that
+ * there is no extra attribute structure, as the child's attribute is
+ * known from the get-go.  Also, there is no container for the
+ * subsystem, as it has no attributes of its own.
+ */
+
+struct simple_child {
+        struct config_item item;
+        int storeme;
+};
+
+static inline struct simple_child *to_simple_child(struct config_item *item)
+{
+        return item ? container_of(item, struct simple_child, item) : NULL;
+}
+
+static struct configfs_attribute simple_child_attr_storeme = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "storeme",
+        .ca_mode = S_IRUGO | S_IWUSR,
+};
+
+static struct configfs_attribute *simple_child_attrs[] = {
+        &simple_child_attr_storeme,
+        NULL,
+};
+
+static ssize_t simple_child_attr_show(struct config_item *item,
+                                      struct configfs_attribute *attr,
+                                      char *page)
+{
+        ssize_t count;
+        struct simple_child *simple_child = to_simple_child(item);
+
+        count = sprintf(page, "%d\n", simple_child->storeme);
+
+        return count;
+}
+
+static ssize_t simple_child_attr_store(struct config_item *item,
+                                       struct configfs_attribute *attr,
+                                       const char *page, size_t count)
+{
+        struct simple_child *simple_child = to_simple_child(item);
+        unsigned long tmp;
+        char *p = (char *) page;
+
+        tmp = simple_strtoul(p, &p, 10);
+        if (!p || (*p && (*p != '\n')))
+                return -EINVAL;
+
+        if (tmp > INT_MAX)
+                return -ERANGE;
+
+        simple_child->storeme = tmp;
+
+        return count;
+}
+
+static void simple_child_release(struct config_item *item)
+{
+        kfree(to_simple_child(item));
+}
+
+static struct configfs_item_operations simple_child_item_ops = {
+        .release                = simple_child_release,
+        .show_attribute         = simple_child_attr_show,
+        .store_attribute        = simple_child_attr_store,
+};
+
+static struct config_item_type simple_child_type = {
+        .ct_item_ops    = &simple_child_item_ops,
+        .ct_attrs       = simple_child_attrs,
+        .ct_owner       = THIS_MODULE,
+};
+
+
+static struct config_item *simple_children_make_item(struct config_group *group, const char *name)
+{
+        struct simple_child *simple_child;
+
+        simple_child = kmalloc(sizeof(struct simple_child), GFP_KERNEL);
+        if (!simple_child)
+                return NULL;
+
+        memset(simple_child, 0, sizeof(struct simple_child));
+
+        config_item_init_type_name(&simple_child->item, name,
+                                   &simple_child_type);
+
+        simple_child->storeme = 0;
+
+        return &simple_child->item;
+}
+
+static struct configfs_attribute simple_children_attr_description = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "description",
+        .ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *simple_children_attrs[] = {
+        &simple_children_attr_description,
+        NULL,
+};
+
+static ssize_t simple_children_attr_show(struct config_item *item,
+                                         struct configfs_attribute *attr,
+                                         char *page)
+{
+        return sprintf(page,
+"[02-simple-children]\n"
+"\n"
+"This subsystem allows the creation of child config_items.  These\n"
+"items have only one attribute that is readable and writeable.\n");
+}
+
+static struct configfs_item_operations simple_children_item_ops = {
+        .show_attribute = simple_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations simple_children_group_ops = {
+        .make_item      = simple_children_make_item,
+};
+
+static struct config_item_type simple_children_type = {
+        .ct_item_ops    = &simple_children_item_ops,
+        .ct_group_ops   = &simple_children_group_ops,
+        .ct_attrs       = simple_children_attrs,
+};
+
+static struct configfs_subsystem simple_children_subsys = {
+        .su_group = {
+                .cg_item = {
+                        .ci_namebuf = "02-simple-children",
+                        .ci_type = &simple_children_type,
+                },
+        },
+};
+
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * 03-group-children
+ *
+ * This example reuses the simple_children group from above.  However,
+ * the simple_children group is not the subsystem itself, it is a
+ * child of the subsystem.  Creation of a group in the subsystem creates
+ * a new simple_children group.  That group can then have simple_child
+ * children of its own.
+ */
+
+struct simple_children {
+        struct config_group group;
+};
+
+static struct config_group *group_children_make_group(struct config_group *group, const char *name)
+{
+        struct simple_children *simple_children;
+
+        simple_children = kmalloc(sizeof(struct simple_children),
+                                  GFP_KERNEL);
+        if (!simple_children)
+                return NULL;
+
+        memset(simple_children, 0, sizeof(struct simple_children));
+
+        config_group_init_type_name(&simple_children->group, name,
+                                    &simple_children_type);
+
+        return &simple_children->group;
+}
+
+static struct configfs_attribute group_children_attr_description = {
+        .ca_owner = THIS_MODULE,
+        .ca_name = "description",
+        .ca_mode = S_IRUGO,
+};
+
+static struct configfs_attribute *group_children_attrs[] = {
+        &group_children_attr_description,
+        NULL,
+};
+
+static ssize_t group_children_attr_show(struct config_item *item,
+                                        struct configfs_attribute *attr,
+                                        char *page)
+{
+        return sprintf(page,
+"[03-group-children]\n"
+"\n"
+"This subsystem allows the creation of child config_groups.  These\n"
+"groups are like the subsystem simple-children.\n");
+}
+
+static struct configfs_item_operations group_children_item_ops = {
+        .show_attribute = group_children_attr_show,
+};
+
+/*
+ * Note that, since no extra work is required on ->drop_item(),
+ * no ->drop_item() is provided.
+ */
+static struct configfs_group_operations group_children_group_ops = {
+        .make_group     = group_children_make_group,
+};
+
+static struct config_item_type group_children_type = {
+        .ct_item_ops    = &group_children_item_ops,
+        .ct_group_ops   = &group_children_group_ops,
+        .ct_attrs       = group_children_attrs,
+};
+
+static struct configfs_subsystem group_children_subsys = {
+        .su_group = {
+                .cg_item = {
+                        .ci_namebuf = "03-group-children",
+                        .ci_type = &group_children_type,
+                },
+        },
+};
+
+/* ----------------------------------------------------------------- */
+
+/*
+ * We're now done with our subsystem definitions.
+ * For convenience in this module, here's a list of them all.  It
+ * allows the init function to easily register them.  Most modules
+ * will only have one subsystem, and will only call register_subsystem
+ * on it directly.
+ */
+static struct configfs_subsystem *example_subsys[] = {
+        &childless_subsys.subsys,
+        &simple_children_subsys,
+        &group_children_subsys,
+        NULL,
+};
+
+static int __init configfs_example_init(void)
+{
+        int ret;
+        int i;
+        struct configfs_subsystem *subsys;
+
+        for (i = 0; example_subsys[i]; i++) {
+                subsys = example_subsys[i];
+
+                config_group_init(&subsys->su_group);
+                init_MUTEX(&subsys->su_sem);
+                ret = configfs_register_subsystem(subsys);
+                if (ret) {
+                        printk(KERN_ERR "Error %d while registering subsystem %s\n",
+                               ret,
+                               subsys->su_group.cg_item.ci_namebuf);
+                        goto out_unregister;
+                }
+        }
+
+        return 0;
+
+out_unregister:
+        for (; i >= 0; i--) {
+                configfs_unregister_subsystem(example_subsys[i]);
+        }
+
+        return ret;
+}
+
+static void __exit configfs_example_exit(void)
+{
+        int i;
+
+        for (i = 0; example_subsys[i]; i++) {
+                configfs_unregister_subsystem(example_subsys[i]);
+        }
+}
+
+module_init(configfs_example_init);
+module_exit(configfs_example_exit);
+MODULE_LICENSE("GPL");
diff --git a/MAINTAINERS b/MAINTAINERS
index 6af683025ae0..86ee06f43794 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -554,6 +554,11 @@ W:	http://us1.samba.org/samba/Linux_CIFS_client.html
 T:      git kernel.org:/pub/scm/linux/kernel/git/sfrench/cifs-2.6.git
 S:      Supported       
 
+CONFIGFS
+P:      Joel Becker
+M:      Joel Becker <joel.becker@oracle.com>
+S:      Supported
+
 CIRRUS LOGIC GENERIC FBDEV DRIVER
 P:      Jeff Garzik
 M:      jgarzik@pobox.com
diff --git a/fs/Kconfig b/fs/Kconfig
index d5255e627b5f..ba1dbe2b2202 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -841,6 +841,20 @@ config RELAYFS_FS
 
           If unsure, say N.
 
+config CONFIGFS_FS
+        tristate "Userspace-driven configuration filesystem (EXPERIMENTAL)"
+        depends on EXPERIMENTAL
+        help
+          configfs is a ram-based filesystem that provides the converse
+          of sysfs's functionality. Where sysfs is a filesystem-based
+          view of kernel objects, configfs is a filesystem-based manager
+          of kernel objects, or config_items.
+
+          Both sysfs and configfs can and should exist together on the
+          same system. One is not a replacement for the other.
+
+          If unsure, say N.
+
 endmenu
 
 menu "Miscellaneous filesystems"
diff --git a/fs/Makefile b/fs/Makefile
index 4c2655759078..ff3d48a744f5 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -101,3 +101,4 @@ obj-$(CONFIG_BEFS_FS)		+= befs/
 obj-$(CONFIG_HOSTFS)            += hostfs/
 obj-$(CONFIG_HPPFS)             += hppfs/
 obj-$(CONFIG_DEBUG_FS)          += debugfs/
+obj-$(CONFIG_CONFIGFS_FS)       += configfs/
diff --git a/fs/configfs/Makefile b/fs/configfs/Makefile
new file mode 100644
index 000000000000..00ffb278e98c
--- /dev/null
+++ b/fs/configfs/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the configfs virtual filesystem
+#
+
+obj-$(CONFIG_CONFIGFS_FS)       += configfs.o
+
+configfs-objs   := inode.o file.o dir.o symlink.o mount.o item.o
diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h
new file mode 100644
index 000000000000..8899d9c5f6bf
--- /dev/null
+++ b/fs/configfs/configfs_internal.h
@@ -0,0 +1,142 @@
+/* -*- mode: c; c-basic-offset:8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * configfs_internal.h - Internal stuff for configfs
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/slab.h>
+#include <linux/list.h>
+
+struct configfs_dirent {
+        atomic_t                s_count;
+        struct list_head        s_sibling;
+        struct list_head        s_children;
+        struct list_head        s_links;
+        void                    * s_element;
+        int                     s_type;
+        umode_t                 s_mode;
+        struct dentry           * s_dentry;
+};
+
+#define CONFIGFS_ROOT           0x0001
+#define CONFIGFS_DIR            0x0002
+#define CONFIGFS_ITEM_ATTR      0x0004
+#define CONFIGFS_ITEM_LINK      0x0020
+#define CONFIGFS_USET_DIR       0x0040
+#define CONFIGFS_USET_DEFAULT   0x0080
+#define CONFIGFS_USET_DROPPING  0x0100
+#define CONFIGFS_NOT_PINNED     (CONFIGFS_ITEM_ATTR)
+
+extern struct vfsmount * configfs_mount;
+
+extern int configfs_is_root(struct config_item *item);
+
+extern struct inode * configfs_new_inode(mode_t mode);
+extern int configfs_create(struct dentry *, int mode, int (*init)(struct inode *));
+
+extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
+extern int configfs_make_dirent(struct configfs_dirent *,
+                                struct dentry *, void *, umode_t, int);
+
+extern int configfs_add_file(struct dentry *, const struct configfs_attribute *, int);
+extern void configfs_hash_and_remove(struct dentry * dir, const char * name);
+
+extern const unsigned char * configfs_get_name(struct configfs_dirent *sd);
+extern void configfs_drop_dentry(struct configfs_dirent *sd, struct dentry *parent);
+
+extern int configfs_pin_fs(void);
+extern void configfs_release_fs(void);
+
+extern struct rw_semaphore configfs_rename_sem;
+extern struct super_block * configfs_sb;
+extern struct file_operations configfs_dir_operations;
+extern struct file_operations configfs_file_operations;
+extern struct file_operations bin_fops;
+extern struct inode_operations configfs_dir_inode_operations;
+extern struct inode_operations configfs_symlink_inode_operations;
+
+extern int configfs_symlink(struct inode *dir, struct dentry *dentry,
+                            const char *symname);
+extern int configfs_unlink(struct inode *dir, struct dentry *dentry);
+
+struct configfs_symlink {
+        struct list_head sl_list;
+        struct config_item *sl_target;
+};
+
+extern int configfs_create_link(struct configfs_symlink *sl,
+                                struct dentry *parent,
+                                struct dentry *dentry);
+
+static inline struct config_item * to_item(struct dentry * dentry)
+{
+        struct configfs_dirent * sd = dentry->d_fsdata;
+        return ((struct config_item *) sd->s_element);
+}
+
+static inline struct configfs_attribute * to_attr(struct dentry * dentry)
+{
+        struct configfs_dirent * sd = dentry->d_fsdata;
+        return ((struct configfs_attribute *) sd->s_element);
+}
+
+static inline struct config_item *configfs_get_config_item(struct dentry *dentry)
+{
+        struct config_item * item = NULL;
+
+        spin_lock(&dcache_lock);
+        if (!d_unhashed(dentry)) {
+                struct configfs_dirent * sd = dentry->d_fsdata;
+                if (sd->s_type & CONFIGFS_ITEM_LINK) {
+                        struct configfs_symlink * sl = sd->s_element;
+                        item = config_item_get(sl->sl_target);
+                } else
+                        item = config_item_get(sd->s_element);
+        }
+        spin_unlock(&dcache_lock);
+
+        return item;
+}
+
+static inline void release_configfs_dirent(struct configfs_dirent * sd)
+{
+        if (!(sd->s_type & CONFIGFS_ROOT))
+                kfree(sd);
+}
+
+static inline struct configfs_dirent * configfs_get(struct configfs_dirent * sd)
+{
+        if (sd) {
+                WARN_ON(!atomic_read(&sd->s_count));
+                atomic_inc(&sd->s_count);
+        }
+        return sd;
+}
+
+static inline void configfs_put(struct configfs_dirent * sd)
+{
+        WARN_ON(!atomic_read(&sd->s_count));
+        if (atomic_dec_and_test(&sd->s_count))
+                release_configfs_dirent(sd);
+}
+
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
new file mode 100644
index 000000000000..e48b539243a1
--- /dev/null
+++ b/fs/configfs/dir.c
@@ -0,0 +1,1102 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * dir.c - Operations for configfs directories.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#undef DEBUG
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+DECLARE_RWSEM(configfs_rename_sem);
+
+static void configfs_d_iput(struct dentry * dentry,
+                            struct inode * inode)
+{
+        struct configfs_dirent * sd = dentry->d_fsdata;
+
+        if (sd) {
+                BUG_ON(sd->s_dentry != dentry);
+                sd->s_dentry = NULL;
+                configfs_put(sd);
+        }
+        iput(inode);
+}
+
+/*
+ * We _must_ delete our dentries on last dput, as the chain-to-parent
+ * behavior is required to clear the parents of default_groups.
+ */
+static int configfs_d_delete(struct dentry *dentry)
+{
+        return 1;
+}
+
+static struct dentry_operations configfs_dentry_ops = {
+        .d_iput         = configfs_d_iput,
+        /* simple_delete_dentry() isn't exported */
+        .d_delete       = configfs_d_delete,
+};
+
+/*
+ * Allocates a new configfs_dirent and links it to the parent configfs_dirent
+ */
+static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent * parent_sd,
+                                                void * element)
+{
+        struct configfs_dirent * sd;
+
+        sd = kmalloc(sizeof(*sd), GFP_KERNEL);
+        if (!sd)
+                return NULL;
+
+        memset(sd, 0, sizeof(*sd));
+        atomic_set(&sd->s_count, 1);
+        INIT_LIST_HEAD(&sd->s_links);
+        INIT_LIST_HEAD(&sd->s_children);
+        list_add(&sd->s_sibling, &parent_sd->s_children);
+        sd->s_element = element;
+
+        return sd;
+}
+
+int configfs_make_dirent(struct configfs_dirent * parent_sd,
+                         struct dentry * dentry, void * element,
+                         umode_t mode, int type)
+{
+        struct configfs_dirent * sd;
+
+        sd = configfs_new_dirent(parent_sd, element);
+        if (!sd)
+                return -ENOMEM;
+
+        sd->s_mode = mode;
+        sd->s_type = type;
+        sd->s_dentry = dentry;
+        if (dentry) {
+                dentry->d_fsdata = configfs_get(sd);
+                dentry->d_op = &configfs_dentry_ops;
+        }
+
+        return 0;
+}
+
+static int init_dir(struct inode * inode)
+{
+        inode->i_op = &configfs_dir_inode_operations;
+        inode->i_fop = &configfs_dir_operations;
+
+        /* directory inodes start off with i_nlink == 2 (for "." entry) */
+        inode->i_nlink++;
+        return 0;
+}
+
+static int init_file(struct inode * inode)
+{
+        inode->i_size = PAGE_SIZE;
+        inode->i_fop = &configfs_file_operations;
+        return 0;
+}
+
+static int init_symlink(struct inode * inode)
+{
+        inode->i_op = &configfs_symlink_inode_operations;
+        return 0;
+}
+
+static int create_dir(struct config_item * k, struct dentry * p,
+                      struct dentry * d)
+{
+        int error;
+        umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
+
+        error = configfs_create(d, mode, init_dir);
+        if (!error) {
+                error = configfs_make_dirent(p->d_fsdata, d, k, mode,
+                                           CONFIGFS_DIR);
+                if (!error) {
+                        p->d_inode->i_nlink++;
+                        (d)->d_op = &configfs_dentry_ops;
+                }
+        }
+        return error;
+}
+
+
+/**
+ *      configfs_create_dir - create a directory for an config_item.
+ *      @item:          config_itemwe're creating directory for.
+ *      @dentry:        config_item's dentry.
+ */
+
+static int configfs_create_dir(struct config_item * item, struct dentry *dentry)
+{
+        struct dentry * parent;
+        int error = 0;
+
+        BUG_ON(!item);
+
+        if (item->ci_parent)
+                parent = item->ci_parent->ci_dentry;
+        else if (configfs_mount && configfs_mount->mnt_sb)
+                parent = configfs_mount->mnt_sb->s_root;
+        else
+                return -EFAULT;
+
+        error = create_dir(item,parent,dentry);
+        if (!error)
+                item->ci_dentry = dentry;
+        return error;
+}
+
+int configfs_create_link(struct configfs_symlink *sl,
+                         struct dentry *parent,
+                         struct dentry *dentry)
+{
+        int err = 0;
+        umode_t mode = S_IFLNK | S_IRWXUGO;
+
+        err = configfs_create(dentry, mode, init_symlink);
+        if (!err) {
+                err = configfs_make_dirent(parent->d_fsdata, dentry, sl,
+                                         mode, CONFIGFS_ITEM_LINK);
+                if (!err)
+                        dentry->d_op = &configfs_dentry_ops;
+        }
+        return err;
+}
+
+static void remove_dir(struct dentry * d)
+{
+        struct dentry * parent = dget(d->d_parent);
+        struct configfs_dirent * sd;
+
+        sd = d->d_fsdata;
+        list_del_init(&sd->s_sibling);
+        configfs_put(sd);
+        if (d->d_inode)
+                simple_rmdir(parent->d_inode,d);
+
+        pr_debug(" o %s removing done (%d)\n",d->d_name.name,
+                 atomic_read(&d->d_count));
+
+        dput(parent);
+}
+
+/**
+ * configfs_remove_dir - remove an config_item's directory.
+ * @item:       config_item we're removing.
+ *
+ * The only thing special about this is that we remove any files in
+ * the directory before we remove the directory, and we've inlined
+ * what used to be configfs_rmdir() below, instead of calling separately.
+ */
+
+static void configfs_remove_dir(struct config_item * item)
+{
+        struct dentry * dentry = dget(item->ci_dentry);
+
+        if (!dentry)
+                return;
+
+        remove_dir(dentry);
+        /**
+         * Drop reference from dget() on entrance.
+         */
+        dput(dentry);
+}
+
+
+/* attaches attribute's configfs_dirent to the dentry corresponding to the
+ * attribute file
+ */
+static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * dentry)
+{
+        struct configfs_attribute * attr = sd->s_element;
+        int error;
+
+        error = configfs_create(dentry, (attr->ca_mode & S_IALLUGO) | S_IFREG, init_file);
+        if (error)
+                return error;
+
+        dentry->d_op = &configfs_dentry_ops;
+        dentry->d_fsdata = configfs_get(sd);
+        sd->s_dentry = dentry;
+        d_rehash(dentry);
+
+        return 0;
+}
+
+static struct dentry * configfs_lookup(struct inode *dir,
+                                       struct dentry *dentry,
+                                       struct nameidata *nd)
+{
+        struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
+        struct configfs_dirent * sd;
+        int found = 0;
+        int err = 0;
+
+        list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
+                if (sd->s_type & CONFIGFS_NOT_PINNED) {
+                        const unsigned char * name = configfs_get_name(sd);
+
+                        if (strcmp(name, dentry->d_name.name))
+                                continue;
+
+                        found = 1;
+                        err = configfs_attach_attr(sd, dentry);
+                        break;
+                }
+        }
+
+        if (!found) {
+                /*
+                 * If it doesn't exist and it isn't a NOT_PINNED item,
+                 * it must be negative.
+                 */
+                return simple_lookup(dir, dentry, nd);
+        }
+
+        return ERR_PTR(err);
+}
+
+/*
+ * Only subdirectories count here.  Files (CONFIGFS_NOT_PINNED) are
+ * attributes and are removed by rmdir().  We recurse, taking i_sem
+ * on all children that are candidates for default detach.  If the
+ * result is clean, then configfs_detach_group() will handle dropping
+ * i_sem.  If there is an error, the caller will clean up the i_sem
+ * holders via configfs_detach_rollback().
+ */
+static int configfs_detach_prep(struct dentry *dentry)
+{
+        struct configfs_dirent *parent_sd = dentry->d_fsdata;
+        struct configfs_dirent *sd;
+        int ret;
+
+        ret = -EBUSY;
+        if (!list_empty(&parent_sd->s_links))
+                goto out;
+
+        ret = 0;
+        list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
+                if (sd->s_type & CONFIGFS_NOT_PINNED)
+                        continue;
+                if (sd->s_type & CONFIGFS_USET_DEFAULT) {
+                        down(&sd->s_dentry->d_inode->i_sem);
+                        /* Mark that we've taken i_sem */
+                        sd->s_type |= CONFIGFS_USET_DROPPING;
+
+                        ret = configfs_detach_prep(sd->s_dentry);
+                        if (!ret)
+                                continue;
+                } else
+                        ret = -ENOTEMPTY;
+
+                break;
+        }
+
+out:
+        return ret;
+}
+
+/*
+ * Walk the tree, dropping i_sem wherever CONFIGFS_USET_DROPPING is
+ * set.
+ */
+static void configfs_detach_rollback(struct dentry *dentry)
+{
+        struct configfs_dirent *parent_sd = dentry->d_fsdata;
+        struct configfs_dirent *sd;
+
+        list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
+                if (sd->s_type & CONFIGFS_USET_DEFAULT) {
+                        configfs_detach_rollback(sd->s_dentry);
+
+                        if (sd->s_type & CONFIGFS_USET_DROPPING) {
+                                sd->s_type &= ~CONFIGFS_USET_DROPPING;
+                                up(&sd->s_dentry->d_inode->i_sem);
+                        }
+                }
+        }
+}
+
+static void detach_attrs(struct config_item * item)
+{
+        struct dentry * dentry = dget(item->ci_dentry);
+        struct configfs_dirent * parent_sd;
+        struct configfs_dirent * sd, * tmp;
+
+        if (!dentry)
+                return;
+
+        pr_debug("configfs %s: dropping attrs for  dir\n",
+                 dentry->d_name.name);
+
+        parent_sd = dentry->d_fsdata;
+        list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) {
+                if (!sd->s_element || !(sd->s_type & CONFIGFS_NOT_PINNED))
+                        continue;
+                list_del_init(&sd->s_sibling);
+                configfs_drop_dentry(sd, dentry);
+                configfs_put(sd);
+        }
+
+        /**
+         * Drop reference from dget() on entrance.
+         */
+        dput(dentry);
+}
+
+static int populate_attrs(struct config_item *item)
+{
+        struct config_item_type *t = item->ci_type;
+        struct configfs_attribute *attr;
+        int error = 0;
+        int i;
+
+        if (!t)
+                return -EINVAL;
+        if (t->ct_attrs) {
+                for (i = 0; (attr = t->ct_attrs[i]) != NULL; i++) {
+                        if ((error = configfs_create_file(item, attr)))
+                                break;
+                }
+        }
+
+        if (error)
+                detach_attrs(item);
+
+        return error;
+}
+
+static int configfs_attach_group(struct config_item *parent_item,
+                                 struct config_item *item,
+                                 struct dentry *dentry);
+static void configfs_detach_group(struct config_item *item);
+
+static void detach_groups(struct config_group *group)
+{
+        struct dentry * dentry = dget(group->cg_item.ci_dentry);
+        struct dentry *child;
+        struct configfs_dirent *parent_sd;
+        struct configfs_dirent *sd, *tmp;
+
+        if (!dentry)
+                return;
+
+        parent_sd = dentry->d_fsdata;
+        list_for_each_entry_safe(sd, tmp, &parent_sd->s_children, s_sibling) {
+                if (!sd->s_element ||
+                    !(sd->s_type & CONFIGFS_USET_DEFAULT))
+                        continue;
+
+                child = sd->s_dentry;
+
+                configfs_detach_group(sd->s_element);
+                child->d_inode->i_flags |= S_DEAD;
+
+                /*
+                 * From rmdir/unregister, a configfs_detach_prep() pass
+                 * has taken our i_sem for us.  Drop it.
+                 * From mkdir/register cleanup, there is no sem held.
+                 */
+                if (sd->s_type & CONFIGFS_USET_DROPPING)
+                        up(&child->d_inode->i_sem);
+
+                d_delete(child);
+                dput(child);
+        }
+
+        /**
+         * Drop reference from dget() on entrance.
+         */
+        dput(dentry);
+}
+
+/*
+ * This fakes mkdir(2) on a default_groups[] entry.  It
+ * creates a dentry, attachs it, and then does fixup
+ * on the sd->s_type.
+ *
+ * We could, perhaps, tweak our parent's ->mkdir for a minute and
+ * try using vfs_mkdir.  Just a thought.
+ */
+static int create_default_group(struct config_group *parent_group,
+                                struct config_group *group)
+{
+        int ret;
+        struct qstr name;
+        struct configfs_dirent *sd;
+        /* We trust the caller holds a reference to parent */
+        struct dentry *child, *parent = parent_group->cg_item.ci_dentry;
+
+        if (!group->cg_item.ci_name)
+                group->cg_item.ci_name = group->cg_item.ci_namebuf;
+        name.name = group->cg_item.ci_name;
+        name.len = strlen(name.name);
+        name.hash = full_name_hash(name.name, name.len);
+
+        ret = -ENOMEM;
+        child = d_alloc(parent, &name);
+        if (child) {
+                d_add(child, NULL);
+
+                ret = configfs_attach_group(&parent_group->cg_item,
+                                            &group->cg_item, child);
+                if (!ret) {
+                        sd = child->d_fsdata;
+                        sd->s_type |= CONFIGFS_USET_DEFAULT;
+                } else {
+                        d_delete(child);
+                        dput(child);
+                }
+        }
+
+        return ret;
+}
+
+static int populate_groups(struct config_group *group)
+{
+        struct config_group *new_group;
+        struct dentry *dentry = group->cg_item.ci_dentry;
+        int ret = 0;
+        int i;
+
+        if (group && group->default_groups) {
+                /* FYI, we're faking mkdir here
+                 * I'm not sure we need this semaphore, as we're called
+                 * from our parent's mkdir.  That holds our parent's
+                 * i_sem, so afaik lookup cannot continue through our
+                 * parent to find us, let alone mess with our tree.
+                 * That said, taking our i_sem is closer to mkdir
+                 * emulation, and shouldn't hurt. */
+                down(&dentry->d_inode->i_sem);
+
+                for (i = 0; group->default_groups[i]; i++) {
+                        new_group = group->default_groups[i];
+
+                        ret = create_default_group(group, new_group);
+                        if (ret)
+                                break;
+                }
+
+                up(&dentry->d_inode->i_sem);
+        }
+
+        if (ret)
+                detach_groups(group);
+
+        return ret;
+}
+
+/*
+ * All of link_obj/unlink_obj/link_group/unlink_group require that
+ * subsys->su_sem is held.
+ */
+
+static void unlink_obj(struct config_item *item)
+{
+        struct config_group *group;
+
+        group = item->ci_group;
+        if (group) {
+                list_del_init(&item->ci_entry);
+
+                item->ci_group = NULL;
+                item->ci_parent = NULL;
+                config_item_put(item);
+
+                config_group_put(group);
+        }
+}
+
+static void link_obj(struct config_item *parent_item, struct config_item *item)
+{
+        /* Parent seems redundant with group, but it makes certain
+         * traversals much nicer. */
+        item->ci_parent = parent_item;
+        item->ci_group = config_group_get(to_config_group(parent_item));
+        list_add_tail(&item->ci_entry, &item->ci_group->cg_children);
+
+        config_item_get(item);
+}
+
+static void unlink_group(struct config_group *group)
+{
+        int i;
+        struct config_group *new_group;
+
+        if (group->default_groups) {
+                for (i = 0; group->default_groups[i]; i++) {
+                        new_group = group->default_groups[i];
+                        unlink_group(new_group);
+                }
+        }
+
+        group->cg_subsys = NULL;
+        unlink_obj(&group->cg_item);
+}
+
+static void link_group(struct config_group *parent_group, struct config_group *group)
+{
+        int i;
+        struct config_group *new_group;
+        struct configfs_subsystem *subsys = NULL; /* gcc is a turd */
+
+        link_obj(&parent_group->cg_item, &group->cg_item);
+
+        if (parent_group->cg_subsys)
+                subsys = parent_group->cg_subsys;
+        else if (configfs_is_root(&parent_group->cg_item))
+                subsys = to_configfs_subsystem(group);
+        else
+                BUG();
+        group->cg_subsys = subsys;
+
+        if (group->default_groups) {
+                for (i = 0; group->default_groups[i]; i++) {
+                        new_group = group->default_groups[i];
+                        link_group(group, new_group);
+                }
+        }
+}
+
+/*
+ * The goal is that configfs_attach_item() (and
+ * configfs_attach_group()) can be called from either the VFS or this
+ * module.  That is, they assume that the items have been created,
+ * the dentry allocated, and the dcache is all ready to go.
+ *
+ * If they fail, they must clean up after themselves as if they
+ * had never been called.  The caller (VFS or local function) will
+ * handle cleaning up the dcache bits.
+ *
+ * configfs_detach_group() and configfs_detach_item() behave similarly on
+ * the way out.  They assume that the proper semaphores are held, they
+ * clean up the configfs items, and they expect their callers will
+ * handle the dcache bits.
+ */
+static int configfs_attach_item(struct config_item *parent_item,
+                                struct config_item *item,
+                                struct dentry *dentry)
+{
+        int ret;
+
+        ret = configfs_create_dir(item, dentry);
+        if (!ret) {
+                ret = populate_attrs(item);
+                if (ret) {
+                        configfs_remove_dir(item);
+                        d_delete(dentry);
+                }
+        }
+
+        return ret;
+}
+
+static void configfs_detach_item(struct config_item *item)
+{
+        detach_attrs(item);
+        configfs_remove_dir(item);
+}
+
+static int configfs_attach_group(struct config_item *parent_item,
+                                 struct config_item *item,
+                                 struct dentry *dentry)
+{
+        int ret;
+        struct configfs_dirent *sd;
+
+        ret = configfs_attach_item(parent_item, item, dentry);
+        if (!ret) {
+                sd = dentry->d_fsdata;
+                sd->s_type |= CONFIGFS_USET_DIR;
+
+                ret = populate_groups(to_config_group(item));
+                if (ret) {
+                        configfs_detach_item(item);
+                        d_delete(dentry);
+                }
+        }
+
+        return ret;
+}
+
+static void configfs_detach_group(struct config_item *item)
+{
+        detach_groups(to_config_group(item));
+        configfs_detach_item(item);
+}
+
+/*
+ * Drop the initial reference from make_item()/make_group()
+ * This function assumes that reference is held on item
+ * and that item holds a valid reference to the parent.  Also, it
+ * assumes the caller has validated ci_type.
+ */
+static void client_drop_item(struct config_item *parent_item,
+                             struct config_item *item)
+{
+        struct config_item_type *type;
+
+        type = parent_item->ci_type;
+        BUG_ON(!type);
+
+        if (type->ct_group_ops && type->ct_group_ops->drop_item)
+                type->ct_group_ops->drop_item(to_config_group(parent_item),
+                                                item);
+        else
+                config_item_put(item);
+}
+
+
+static int configfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+        int ret;
+        struct config_group *group;
+        struct config_item *item;
+        struct config_item *parent_item;
+        struct configfs_subsystem *subsys;
+        struct configfs_dirent *sd;
+        struct config_item_type *type;
+        struct module *owner;
+        char *name;
+
+        if (dentry->d_parent == configfs_sb->s_root)
+                return -EPERM;
+
+        sd = dentry->d_parent->d_fsdata;
+        if (!(sd->s_type & CONFIGFS_USET_DIR))
+                return -EPERM;
+
+        parent_item = configfs_get_config_item(dentry->d_parent);
+        type = parent_item->ci_type;
+        subsys = to_config_group(parent_item)->cg_subsys;
+        BUG_ON(!subsys);
+
+        if (!type || !type->ct_group_ops ||
+            (!type->ct_group_ops->make_group &&
+             !type->ct_group_ops->make_item)) {
+                config_item_put(parent_item);
+                return -EPERM;  /* What lack-of-mkdir returns */
+        }
+
+        name = kmalloc(dentry->d_name.len + 1, GFP_KERNEL);
+        if (!name) {
+                config_item_put(parent_item);
+                return -ENOMEM;
+        }
+        snprintf(name, dentry->d_name.len + 1, "%s", dentry->d_name.name);
+
+        down(&subsys->su_sem);
+        group = NULL;
+        item = NULL;
+        if (type->ct_group_ops->make_group) {
+                group = type->ct_group_ops->make_group(to_config_group(parent_item), name);
+                if (group) {
+                        link_group(to_config_group(parent_item), group);
+                        item = &group->cg_item;
+                }
+        } else {
+                item = type->ct_group_ops->make_item(to_config_group(parent_item), name);
+                if (item)
+                        link_obj(parent_item, item);
+        }
+        up(&subsys->su_sem);
+
+        kfree(name);
+        if (!item) {
+                config_item_put(parent_item);
+                return -ENOMEM;
+        }
+
+        ret = -EINVAL;
+        type = item->ci_type;
+        if (type) {
+                owner = type->ct_owner;
+                if (try_module_get(owner)) {
+                        if (group) {
+                                ret = configfs_attach_group(parent_item,
+                                                            item,
+                                                            dentry);
+                        } else {
+                                ret = configfs_attach_item(parent_item,
+                                                           item,
+                                                           dentry);
+                        }
+
+                        if (ret) {
+                                down(&subsys->su_sem);
+                                if (group)
+                                        unlink_group(group);
+                                else
+                                        unlink_obj(item);
+                                client_drop_item(parent_item, item);
+                                up(&subsys->su_sem);
+
+                                config_item_put(parent_item);
+                                module_put(owner);
+                        }
+                }
+        }
+
+        return ret;
+}
+
+static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+        struct config_item *parent_item;
+        struct config_item *item;
+        struct configfs_subsystem *subsys;
+        struct configfs_dirent *sd;
+        struct module *owner = NULL;
+        int ret;
+
+        if (dentry->d_parent == configfs_sb->s_root)
+                return -EPERM;
+
+        sd = dentry->d_fsdata;
+        if (sd->s_type & CONFIGFS_USET_DEFAULT)
+                return -EPERM;
+
+        parent_item = configfs_get_config_item(dentry->d_parent);
+        subsys = to_config_group(parent_item)->cg_subsys;
+        BUG_ON(!subsys);
+
+        if (!parent_item->ci_type) {
+                config_item_put(parent_item);
+                return -EINVAL;
+        }
+
+        ret = configfs_detach_prep(dentry);
+        if (ret) {
+                configfs_detach_rollback(dentry);
+                config_item_put(parent_item);
+                return ret;
+        }
+
+        item = configfs_get_config_item(dentry);
+
+        /* Drop reference from above, item already holds one. */
+        config_item_put(parent_item);
+
+        if (item->ci_type)
+                owner = item->ci_type->ct_owner;
+
+        if (sd->s_type & CONFIGFS_USET_DIR) {
+                configfs_detach_group(item);
+
+                down(&subsys->su_sem);
+                unlink_group(to_config_group(item));
+        } else {
+                configfs_detach_item(item);
+
+                down(&subsys->su_sem);
+                unlink_obj(item);
+        }
+
+        client_drop_item(parent_item, item);
+        up(&subsys->su_sem);
+
+        /* Drop our reference from above */
+        config_item_put(item);
+
+        module_put(owner);
+
+        return 0;
+}
+
+struct inode_operations configfs_dir_inode_operations = {
+        .mkdir          = configfs_mkdir,
+        .rmdir          = configfs_rmdir,
+        .symlink        = configfs_symlink,
+        .unlink         = configfs_unlink,
+        .lookup         = configfs_lookup,
+};
+
+#if 0
+int configfs_rename_dir(struct config_item * item, const char *new_name)
+{
+        int error = 0;
+        struct dentry * new_dentry, * parent;
+
+        if (!strcmp(config_item_name(item), new_name))
+                return -EINVAL;
+
+        if (!item->parent)
+                return -EINVAL;
+
+        down_write(&configfs_rename_sem);
+        parent = item->parent->dentry;
+
+        down(&parent->d_inode->i_sem);
+
+        new_dentry = lookup_one_len(new_name, parent, strlen(new_name));
+        if (!IS_ERR(new_dentry)) {
+                if (!new_dentry->d_inode) {
+                        error = config_item_set_name(item, "%s", new_name);
+                        if (!error) {
+                                d_add(new_dentry, NULL);
+                                d_move(item->dentry, new_dentry);
+                        }
+                        else
+                                d_delete(new_dentry);
+                } else
+                        error = -EEXIST;
+                dput(new_dentry);
+        }
+        up(&parent->d_inode->i_sem);
+        up_write(&configfs_rename_sem);
+
+        return error;
+}
+#endif
+
+static int configfs_dir_open(struct inode *inode, struct file *file)
+{
+        struct dentry * dentry = file->f_dentry;
+        struct configfs_dirent * parent_sd = dentry->d_fsdata;
+
+        down(&dentry->d_inode->i_sem);
+        file->private_data = configfs_new_dirent(parent_sd, NULL);
+        up(&dentry->d_inode->i_sem);
+
+        return file->private_data ? 0 : -ENOMEM;
+
+}
+
+static int configfs_dir_close(struct inode *inode, struct file *file)
+{
+        struct dentry * dentry = file->f_dentry;
+        struct configfs_dirent * cursor = file->private_data;
+
+        down(&dentry->d_inode->i_sem);
+        list_del_init(&cursor->s_sibling);
+        up(&dentry->d_inode->i_sem);
+
+        release_configfs_dirent(cursor);
+
+        return 0;
+}
+
+/* Relationship between s_mode and the DT_xxx types */
+static inline unsigned char dt_type(struct configfs_dirent *sd)
+{
+        return (sd->s_mode >> 12) & 15;
+}
+
+static int configfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
+{
+        struct dentry *dentry = filp->f_dentry;
+        struct configfs_dirent * parent_sd = dentry->d_fsdata;
+        struct configfs_dirent *cursor = filp->private_data;
+        struct list_head *p, *q = &cursor->s_sibling;
+        ino_t ino;
+        int i = filp->f_pos;
+
+        switch (i) {
+                case 0:
+                        ino = dentry->d_inode->i_ino;
+                        if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
+                                break;
+                        filp->f_pos++;
+                        i++;
+                        /* fallthrough */
+                case 1:
+                        ino = parent_ino(dentry);
+                        if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
+                                break;
+                        filp->f_pos++;
+                        i++;
+                        /* fallthrough */
+                default:
+                        if (filp->f_pos == 2) {
+                                list_del(q);
+                                list_add(q, &parent_sd->s_children);
+                        }
+                        for (p=q->next; p!= &parent_sd->s_children; p=p->next) {
+                                struct configfs_dirent *next;
+                                const char * name;
+                                int len;
+
+                                next = list_entry(p, struct configfs_dirent,
+                                                   s_sibling);
+                                if (!next->s_element)
+                                        continue;
+
+                                name = configfs_get_name(next);
+                                len = strlen(name);
+                                if (next->s_dentry)
+                                        ino = next->s_dentry->d_inode->i_ino;
+                                else
+                                        ino = iunique(configfs_sb, 2);
+
+                                if (filldir(dirent, name, len, filp->f_pos, ino,
+                                                 dt_type(next)) < 0)
+                                        return 0;
+
+                                list_del(q);
+                                list_add(q, p);
+                                p = q;
+                                filp->f_pos++;
+                        }
+        }
+        return 0;
+}
+
+static loff_t configfs_dir_lseek(struct file * file, loff_t offset, int origin)
+{
+        struct dentry * dentry = file->f_dentry;
+
+        down(&dentry->d_inode->i_sem);
+        switch (origin) {
+                case 1:
+                        offset += file->f_pos;
+                case 0:
+                        if (offset >= 0)
+                                break;
+                default:
+                        up(&file->f_dentry->d_inode->i_sem);
+                        return -EINVAL;
+        }
+        if (offset != file->f_pos) {
+                file->f_pos = offset;
+                if (file->f_pos >= 2) {
+                        struct configfs_dirent *sd = dentry->d_fsdata;
+                        struct configfs_dirent *cursor = file->private_data;
+                        struct list_head *p;
+                        loff_t n = file->f_pos - 2;
+
+                        list_del(&cursor->s_sibling);
+                        p = sd->s_children.next;
+                        while (n && p != &sd->s_children) {
+                                struct configfs_dirent *next;
+                                next = list_entry(p, struct configfs_dirent,
+                                                   s_sibling);
+                                if (next->s_element)
+                                        n--;
+                                p = p->next;
+                        }
+                        list_add_tail(&cursor->s_sibling, p);
+                }
+        }
+        up(&dentry->d_inode->i_sem);
+        return offset;
+}
+
+struct file_operations configfs_dir_operations = {
+        .open           = configfs_dir_open,
+        .release        = configfs_dir_close,
+        .llseek         = configfs_dir_lseek,
+        .read           = generic_read_dir,
+        .readdir        = configfs_readdir,
+};
+
+int configfs_register_subsystem(struct configfs_subsystem *subsys)
+{
+        int err;
+        struct config_group *group = &subsys->su_group;
+        struct qstr name;
+        struct dentry *dentry;
+        struct configfs_dirent *sd;
+
+        err = configfs_pin_fs();
+        if (err)
+                return err;
+
+        if (!group->cg_item.ci_name)
+                group->cg_item.ci_name = group->cg_item.ci_namebuf;
+
+        sd = configfs_sb->s_root->d_fsdata;
+        link_group(to_config_group(sd->s_element), group);
+
+        down(&configfs_sb->s_root->d_inode->i_sem);
+
+        name.name = group->cg_item.ci_name;
+        name.len = strlen(name.name);
+        name.hash = full_name_hash(name.name, name.len);
+
+        err = -ENOMEM;
+        dentry = d_alloc(configfs_sb->s_root, &name);
+        if (!dentry)
+                goto out_release;
+
+        d_add(dentry, NULL);
+
+        err = configfs_attach_group(sd->s_element, &group->cg_item,
+                                    dentry);
+        if (!err)
+                dentry = NULL;
+        else
+                d_delete(dentry);
+
+        up(&configfs_sb->s_root->d_inode->i_sem);
+
+        if (dentry) {
+            dput(dentry);
+out_release:
+            unlink_group(group);
+            configfs_release_fs();
+        }
+
+        return err;
+}
+
+void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
+{
+        struct config_group *group = &subsys->su_group;
+        struct dentry *dentry = group->cg_item.ci_dentry;
+
+        if (dentry->d_parent != configfs_sb->s_root) {
+                printk(KERN_ERR "configfs: Tried to unregister non-subsystem!\n");
+                return;
+        }
+
+        down(&configfs_sb->s_root->d_inode->i_sem);
+        down(&dentry->d_inode->i_sem);
+        if (configfs_detach_prep(dentry)) {
+                printk(KERN_ERR "configfs: Tried to unregister non-empty subsystem!\n");
+        }
+        configfs_detach_group(&group->cg_item);
+        dentry->d_inode->i_flags |= S_DEAD;
+        up(&dentry->d_inode->i_sem);
+
+        d_delete(dentry);
+
+        up(&configfs_sb->s_root->d_inode->i_sem);
+
+        dput(dentry);
+
+        unlink_group(group);
+        configfs_release_fs();
+}
+
+EXPORT_SYMBOL(configfs_register_subsystem);
+EXPORT_SYMBOL(configfs_unregister_subsystem);
diff --git a/fs/configfs/file.c b/fs/configfs/file.c
new file mode 100644
index 000000000000..af1ffc9a15c0
--- /dev/null
+++ b/fs/configfs/file.c
@@ -0,0 +1,360 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * file.c - operations for regular (text) files.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/dnotify.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include <asm/semaphore.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+
+struct configfs_buffer {
+        size_t                  count;
+        loff_t                  pos;
+        char                    * page;
+        struct configfs_item_operations * ops;
+        struct semaphore        sem;
+        int                     needs_read_fill;
+};
+
+
+/**
+ *      fill_read_buffer - allocate and fill buffer from item.
+ *      @dentry:        dentry pointer.
+ *      @buffer:        data buffer for file.
+ *
+ *      Allocate @buffer->page, if it hasn't been already, then call the
+ *      config_item's show() method to fill the buffer with this attribute's
+ *      data.
+ *      This is called only once, on the file's first read.
+ */
+static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buffer)
+{
+        struct configfs_attribute * attr = to_attr(dentry);
+        struct config_item * item = to_item(dentry->d_parent);
+        struct configfs_item_operations * ops = buffer->ops;
+        int ret = 0;
+        ssize_t count;
+
+        if (!buffer->page)
+                buffer->page = (char *) get_zeroed_page(GFP_KERNEL);
+        if (!buffer->page)
+                return -ENOMEM;
+
+        count = ops->show_attribute(item,attr,buffer->page);
+        buffer->needs_read_fill = 0;
+        BUG_ON(count > (ssize_t)PAGE_SIZE);
+        if (count >= 0)
+                buffer->count = count;
+        else
+                ret = count;
+        return ret;
+}
+
+
+/**
+ *      flush_read_buffer - push buffer to userspace.
+ *      @buffer:        data buffer for file.
+ *      @userbuf:       user-passed buffer.
+ *      @count:         number of bytes requested.
+ *      @ppos:          file position.
+ *
+ *      Copy the buffer we filled in fill_read_buffer() to userspace.
+ *      This is done at the reader's leisure, copying and advancing
+ *      the amount they specify each time.
+ *      This may be called continuously until the buffer is empty.
+ */
+static int flush_read_buffer(struct configfs_buffer * buffer, char __user * buf,
+                             size_t count, loff_t * ppos)
+{
+        int error;
+
+        if (*ppos > buffer->count)
+                return 0;
+
+        if (count > (buffer->count - *ppos))
+                count = buffer->count - *ppos;
+
+        error = copy_to_user(buf,buffer->page + *ppos,count);
+        if (!error)
+                *ppos += count;
+        return error ? -EFAULT : count;
+}
+
+/**
+ *      configfs_read_file - read an attribute.
+ *      @file:  file pointer.
+ *      @buf:   buffer to fill.
+ *      @count: number of bytes to read.
+ *      @ppos:  starting offset in file.
+ *
+ *      Userspace wants to read an attribute file. The attribute descriptor
+ *      is in the file's ->d_fsdata. The target item is in the directory's
+ *      ->d_fsdata.
+ *
+ *      We call fill_read_buffer() to allocate and fill the buffer from the
+ *      item's show() method exactly once (if the read is happening from
+ *      the beginning of the file). That should fill the entire buffer with
+ *      all the data the item has to offer for that attribute.
+ *      We then call flush_read_buffer() to copy the buffer to userspace
+ *      in the increments specified.
+ */
+
+static ssize_t
+configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+        struct configfs_buffer * buffer = file->private_data;
+        ssize_t retval = 0;
+
+        down(&buffer->sem);
+        if (buffer->needs_read_fill) {
+                if ((retval = fill_read_buffer(file->f_dentry,buffer)))
+                        goto out;
+        }
+        pr_debug("%s: count = %d, ppos = %lld, buf = %s\n",
+                 __FUNCTION__,count,*ppos,buffer->page);
+        retval = flush_read_buffer(buffer,buf,count,ppos);
+out:
+        up(&buffer->sem);
+        return retval;
+}
+
+
+/**
+ *      fill_write_buffer - copy buffer from userspace.
+ *      @buffer:        data buffer for file.
+ *      @userbuf:       data from user.
+ *      @count:         number of bytes in @userbuf.
+ *
+ *      Allocate @buffer->page if it hasn't been already, then
+ *      copy the user-supplied buffer into it.
+ */
+
+static int
+fill_write_buffer(struct configfs_buffer * buffer, const char __user * buf, size_t count)
+{
+        int error;
+
+        if (!buffer->page)
+                buffer->page = (char *)get_zeroed_page(GFP_KERNEL);
+        if (!buffer->page)
+                return -ENOMEM;
+
+        if (count > PAGE_SIZE)
+                count = PAGE_SIZE;
+        error = copy_from_user(buffer->page,buf,count);
+        buffer->needs_read_fill = 1;
+        return error ? -EFAULT : count;
+}
+
+
+/**
+ *      flush_write_buffer - push buffer to config_item.
+ *      @file:          file pointer.
+ *      @buffer:        data buffer for file.
+ *
+ *      Get the correct pointers for the config_item and the attribute we're
+ *      dealing with, then call the store() method for the attribute,
+ *      passing the buffer that we acquired in fill_write_buffer().
+ */
+
+static int
+flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size_t count)
+{
+        struct configfs_attribute * attr = to_attr(dentry);
+        struct config_item * item = to_item(dentry->d_parent);
+        struct configfs_item_operations * ops = buffer->ops;
+
+        return ops->store_attribute(item,attr,buffer->page,count);
+}
+
+
+/**
+ *      configfs_write_file - write an attribute.
+ *      @file:  file pointer
+ *      @buf:   data to write
+ *      @count: number of bytes
+ *      @ppos:  starting offset
+ *
+ *      Similar to configfs_read_file(), though working in the opposite direction.
+ *      We allocate and fill the data from the user in fill_write_buffer(),
+ *      then push it to the config_item in flush_write_buffer().
+ *      There is no easy way for us to know if userspace is only doing a partial
+ *      write, so we don't support them. We expect the entire buffer to come
+ *      on the first write.
+ *      Hint: if you're writing a value, first read the file, modify only the
+ *      the value you're changing, then write entire buffer back.
+ */
+
+static ssize_t
+configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+        struct configfs_buffer * buffer = file->private_data;
+
+        down(&buffer->sem);
+        count = fill_write_buffer(buffer,buf,count);
+        if (count > 0)
+                count = flush_write_buffer(file->f_dentry,buffer,count);
+        if (count > 0)
+                *ppos += count;
+        up(&buffer->sem);
+        return count;
+}
+
+static int check_perm(struct inode * inode, struct file * file)
+{
+        struct config_item *item = configfs_get_config_item(file->f_dentry->d_parent);
+        struct configfs_attribute * attr = to_attr(file->f_dentry);
+        struct configfs_buffer * buffer;
+        struct configfs_item_operations * ops = NULL;
+        int error = 0;
+
+        if (!item || !attr)
+                goto Einval;
+
+        /* Grab the module reference for this attribute if we have one */
+        if (!try_module_get(attr->ca_owner)) {
+                error = -ENODEV;
+                goto Done;
+        }
+
+        if (item->ci_type)
+                ops = item->ci_type->ct_item_ops;
+        else
+                goto Eaccess;
+
+        /* File needs write support.
+         * The inode's perms must say it's ok,
+         * and we must have a store method.
+         */
+        if (file->f_mode & FMODE_WRITE) {
+
+                if (!(inode->i_mode & S_IWUGO) || !ops->store_attribute)
+                        goto Eaccess;
+
+        }
+
+        /* File needs read support.
+         * The inode's perms must say it's ok, and we there
+         * must be a show method for it.
+         */
+        if (file->f_mode & FMODE_READ) {
+                if (!(inode->i_mode & S_IRUGO) || !ops->show_attribute)
+                        goto Eaccess;
+        }
+
+        /* No error? Great, allocate a buffer for the file, and store it
+         * it in file->private_data for easy access.
+         */
+        buffer = kmalloc(sizeof(struct configfs_buffer),GFP_KERNEL);
+        if (buffer) {
+                memset(buffer,0,sizeof(struct configfs_buffer));
+                init_MUTEX(&buffer->sem);
+                buffer->needs_read_fill = 1;
+                buffer->ops = ops;
+                file->private_data = buffer;
+        } else
+                error = -ENOMEM;
+        goto Done;
+
+ Einval:
+        error = -EINVAL;
+        goto Done;
+ Eaccess:
+        error = -EACCES;
+        module_put(attr->ca_owner);
+ Done:
+        if (error && item)
+                config_item_put(item);
+        return error;
+}
+
+static int configfs_open_file(struct inode * inode, struct file * filp)
+{
+        return check_perm(inode,filp);
+}
+
+static int configfs_release(struct inode * inode, struct file * filp)
+{
+        struct config_item * item = to_item(filp->f_dentry->d_parent);
+        struct configfs_attribute * attr = to_attr(filp->f_dentry);
+        struct module * owner = attr->ca_owner;
+        struct configfs_buffer * buffer = filp->private_data;
+
+        if (item)
+                config_item_put(item);
+        /* After this point, attr should not be accessed. */
+        module_put(owner);
+
+        if (buffer) {
+                if (buffer->page)
+                        free_page((unsigned long)buffer->page);
+                kfree(buffer);
+        }
+        return 0;
+}
+
+struct file_operations configfs_file_operations = {
+        .read           = configfs_read_file,
+        .write          = configfs_write_file,
+        .llseek         = generic_file_llseek,
+        .open           = configfs_open_file,
+        .release        = configfs_release,
+};
+
+
+int configfs_add_file(struct dentry * dir, const struct configfs_attribute * attr, int type)
+{
+        struct configfs_dirent * parent_sd = dir->d_fsdata;
+        umode_t mode = (attr->ca_mode & S_IALLUGO) | S_IFREG;
+        int error = 0;
+
+        down(&dir->d_inode->i_sem);
+        error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode, type);
+        up(&dir->d_inode->i_sem);
+
+        return error;
+}
+
+
+/**
+ *      configfs_create_file - create an attribute file for an item.
+ *      @item:  item we're creating for.
+ *      @attr:  atrribute descriptor.
+ */
+
+int configfs_create_file(struct config_item * item, const struct configfs_attribute * attr)
+{
+        BUG_ON(!item || !item->ci_dentry || !attr);
+
+        return configfs_add_file(item->ci_dentry, attr,
+                                 CONFIGFS_ITEM_ATTR);
+}
+
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
new file mode 100644
index 000000000000..6b274c6d428f
--- /dev/null
+++ b/fs/configfs/inode.c
@@ -0,0 +1,162 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * inode.c - basic inode and dentry operations.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ *
+ * Please see Documentation/filesystems/configfs.txt for more information.
+ */
+
+#undef DEBUG
+
+#include <linux/pagemap.h>
+#include <linux/namei.h>
+#include <linux/backing-dev.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+extern struct super_block * configfs_sb;
+
+static struct address_space_operations configfs_aops = {
+        .readpage       = simple_readpage,
+        .prepare_write  = simple_prepare_write,
+        .commit_write   = simple_commit_write
+};
+
+static struct backing_dev_info configfs_backing_dev_info = {
+        .ra_pages       = 0,    /* No readahead */
+        .capabilities   = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
+};
+
+struct inode * configfs_new_inode(mode_t mode)
+{
+        struct inode * inode = new_inode(configfs_sb);
+        if (inode) {
+                inode->i_mode = mode;
+                inode->i_uid = 0;
+                inode->i_gid = 0;
+                inode->i_blksize = PAGE_CACHE_SIZE;
+                inode->i_blocks = 0;
+                inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+                inode->i_mapping->a_ops = &configfs_aops;
+                inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
+        }
+        return inode;
+}
+
+int configfs_create(struct dentry * dentry, int mode, int (*init)(struct inode *))
+{
+        int error = 0;
+        struct inode * inode = NULL;
+        if (dentry) {
+                if (!dentry->d_inode) {
+                        if ((inode = configfs_new_inode(mode))) {
+                                if (dentry->d_parent && dentry->d_parent->d_inode) {
+                                        struct inode *p_inode = dentry->d_parent->d_inode;
+                                        p_inode->i_mtime = p_inode->i_ctime = CURRENT_TIME;
+                                }
+                                goto Proceed;
+                        }
+                        else
+                                error = -ENOMEM;
+                } else
+                        error = -EEXIST;
+        } else
+                error = -ENOENT;
+        goto Done;
+
+ Proceed:
+        if (init)
+                error = init(inode);
+        if (!error) {
+                d_instantiate(dentry, inode);
+                if (S_ISDIR(mode) || S_ISLNK(mode))
+                        dget(dentry);  /* pin link and directory dentries in core */
+        } else
+                iput(inode);
+ Done:
+        return error;
+}
+
+/*
+ * Get the name for corresponding element represented by the given configfs_dirent
+ */
+const unsigned char * configfs_get_name(struct configfs_dirent *sd)
+{
+        struct attribute * attr;
+
+        if (!sd || !sd->s_element)
+                BUG();
+
+        /* These always have a dentry, so use that */
+        if (sd->s_type & (CONFIGFS_DIR | CONFIGFS_ITEM_LINK))
+                return sd->s_dentry->d_name.name;
+
+        if (sd->s_type & CONFIGFS_ITEM_ATTR) {
+                attr = sd->s_element;
+                return attr->name;
+        }
+        return NULL;
+}
+
+
+/*
+ * Unhashes the dentry corresponding to given configfs_dirent
+ * Called with parent inode's i_sem held.
+ */
+void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
+{
+        struct dentry * dentry = sd->s_dentry;
+
+        if (dentry) {
+                spin_lock(&dcache_lock);
+                if (!(d_unhashed(dentry) && dentry->d_inode)) {
+                        dget_locked(dentry);
+                        __d_drop(dentry);
+                        spin_unlock(&dcache_lock);
+                        simple_unlink(parent->d_inode, dentry);
+                } else
+                        spin_unlock(&dcache_lock);
+        }
+}
+
+void configfs_hash_and_remove(struct dentry * dir, const char * name)
+{
+        struct configfs_dirent * sd;
+        struct configfs_dirent * parent_sd = dir->d_fsdata;
+
+        down(&dir->d_inode->i_sem);
+        list_for_each_entry(sd, &parent_sd->s_children, s_sibling) {
+                if (!sd->s_element)
+                        continue;
+                if (!strcmp(configfs_get_name(sd), name)) {
+                        list_del_init(&sd->s_sibling);
+                        configfs_drop_dentry(sd, dir);
+                        configfs_put(sd);
+                        break;
+                }
+        }
+        up(&dir->d_inode->i_sem);
+}
+
+
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
new file mode 100644
index 000000000000..e07485ac50ad
--- /dev/null
+++ b/fs/configfs/item.c
@@ -0,0 +1,227 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * item.c - library routines for handling generic config items
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on kobject:
+ *      kobject is Copyright (c) 2002-2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ *
+ * Please see the file Documentation/filesystems/configfs.txt for
+ * critical information about using the config_item interface.
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+
+#include <linux/configfs.h>
+
+
+static inline struct config_item * to_item(struct list_head * entry)
+{
+        return container_of(entry,struct config_item,ci_entry);
+}
+
+/* Evil kernel */
+static void config_item_release(struct kref *kref);
+
+/**
+ *      config_item_init - initialize item.
+ *      @item:  item in question.
+ */
+void config_item_init(struct config_item * item)
+{
+        kref_init(&item->ci_kref);
+        INIT_LIST_HEAD(&item->ci_entry);
+}
+
+/**
+ *      config_item_set_name - Set the name of an item
+ *      @item:  item.
+ *      @name:  name.
+ *
+ *      If strlen(name) >= CONFIGFS_ITEM_NAME_LEN, then use a
+ *      dynamically allocated string that @item->ci_name points to.
+ *      Otherwise, use the static @item->ci_namebuf array.
+ */
+
+int config_item_set_name(struct config_item * item, const char * fmt, ...)
+{
+        int error = 0;
+        int limit = CONFIGFS_ITEM_NAME_LEN;
+        int need;
+        va_list args;
+        char * name;
+
+        /*
+         * First, try the static array
+         */
+        va_start(args,fmt);
+        need = vsnprintf(item->ci_namebuf,limit,fmt,args);
+        va_end(args);
+        if (need < limit)
+                name = item->ci_namebuf;
+        else {
+                /*
+                 * Need more space? Allocate it and try again
+                 */
+                limit = need + 1;
+                name = kmalloc(limit,GFP_KERNEL);
+                if (!name) {
+                        error = -ENOMEM;
+                        goto Done;
+                }
+                va_start(args,fmt);
+                need = vsnprintf(name,limit,fmt,args);
+                va_end(args);
+
+                /* Still? Give up. */
+                if (need >= limit) {
+                        kfree(name);
+                        error = -EFAULT;
+                        goto Done;
+                }
+        }
+
+        /* Free the old name, if necessary. */
+        if (item->ci_name && item->ci_name != item->ci_namebuf)
+                kfree(item->ci_name);
+
+        /* Now, set the new name */
+        item->ci_name = name;
+ Done:
+        return error;
+}
+
+EXPORT_SYMBOL(config_item_set_name);
+
+void config_item_init_type_name(struct config_item *item,
+                                const char *name,
+                                struct config_item_type *type)
+{
+        config_item_set_name(item, name);
+        item->ci_type = type;
+        config_item_init(item);
+}
+EXPORT_SYMBOL(config_item_init_type_name);
+
+void config_group_init_type_name(struct config_group *group, const char *name,
+                         struct config_item_type *type)
+{
+        config_item_set_name(&group->cg_item, name);
+        group->cg_item.ci_type = type;
+        config_group_init(group);
+}
+EXPORT_SYMBOL(config_group_init_type_name);
+
+struct config_item * config_item_get(struct config_item * item)
+{
+        if (item)
+                kref_get(&item->ci_kref);
+        return item;
+}
+
+/**
+ *      config_item_cleanup - free config_item resources.
+ *      @item:  item.
+ */
+
+void config_item_cleanup(struct config_item * item)
+{
+        struct config_item_type * t = item->ci_type;
+        struct config_group * s = item->ci_group;
+        struct config_item * parent = item->ci_parent;
+
+        pr_debug("config_item %s: cleaning up\n",config_item_name(item));
+        if (item->ci_name != item->ci_namebuf)
+                kfree(item->ci_name);
+        item->ci_name = NULL;
+        if (t && t->ct_item_ops && t->ct_item_ops->release)
+                t->ct_item_ops->release(item);
+        if (s)
+                config_group_put(s);
+        if (parent)
+                config_item_put(parent);
+}
+
+static void config_item_release(struct kref *kref)
+{
+        config_item_cleanup(container_of(kref, struct config_item, ci_kref));
+}
+
+/**
+ *      config_item_put - decrement refcount for item.
+ *      @item:  item.
+ *
+ *      Decrement the refcount, and if 0, call config_item_cleanup().
+ */
+void config_item_put(struct config_item * item)
+{
+        if (item)
+                kref_put(&item->ci_kref, config_item_release);
+}
+
+
+/**
+ *      config_group_init - initialize a group for use
+ *      @k:     group
+ */
+
+void config_group_init(struct config_group *group)
+{
+        config_item_init(&group->cg_item);
+        INIT_LIST_HEAD(&group->cg_children);
+}
+
+
+/**
+ *      config_group_find_obj - search for item in group.
+ *      @group: group we're looking in.
+ *      @name:  item's name.
+ *
+ *      Lock group via @group->cg_subsys, and iterate over @group->cg_list,
+ *      looking for a matching config_item. If matching item is found
+ *      take a reference and return the item.
+ */
+
+struct config_item * config_group_find_obj(struct config_group * group, const char * name)
+{
+        struct list_head * entry;
+        struct config_item * ret = NULL;
+
+        /* XXX LOCKING! */
+        list_for_each(entry,&group->cg_children) {
+                struct config_item * item = to_item(entry);
+                if (config_item_name(item) &&
+                    !strcmp(config_item_name(item), name)) {
+                        ret = config_item_get(item);
+                        break;
+                }
+        }
+        return ret;
+}
+
+
+EXPORT_SYMBOL(config_item_init);
+EXPORT_SYMBOL(config_group_init);
+EXPORT_SYMBOL(config_item_get);
+EXPORT_SYMBOL(config_item_put);
+
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
new file mode 100644
index 000000000000..1a2f6f6a4d91
--- /dev/null
+++ b/fs/configfs/mount.c
@@ -0,0 +1,159 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * mount.c - operations for initializing and mounting configfs.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+/* Random magic number */
+#define CONFIGFS_MAGIC 0x62656570
+
+struct vfsmount * configfs_mount = NULL;
+struct super_block * configfs_sb = NULL;
+static int configfs_mnt_count = 0;
+
+static struct super_operations configfs_ops = {
+        .statfs         = simple_statfs,
+        .drop_inode     = generic_delete_inode,
+};
+
+static struct config_group configfs_root_group = {
+        .cg_item = {
+                .ci_namebuf     = "root",
+                .ci_name        = configfs_root_group.cg_item.ci_namebuf,
+        },
+};
+
+int configfs_is_root(struct config_item *item)
+{
+        return item == &configfs_root_group.cg_item;
+}
+
+static struct configfs_dirent configfs_root = {
+        .s_sibling      = LIST_HEAD_INIT(configfs_root.s_sibling),
+        .s_children     = LIST_HEAD_INIT(configfs_root.s_children),
+        .s_element      = &configfs_root_group.cg_item,
+        .s_type         = CONFIGFS_ROOT,
+};
+
+static int configfs_fill_super(struct super_block *sb, void *data, int silent)
+{
+        struct inode *inode;
+        struct dentry *root;
+
+        sb->s_blocksize = PAGE_CACHE_SIZE;
+        sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+        sb->s_magic = CONFIGFS_MAGIC;
+        sb->s_op = &configfs_ops;
+        configfs_sb = sb;
+
+        inode = configfs_new_inode(S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
+        if (inode) {
+                inode->i_op = &configfs_dir_inode_operations;
+                inode->i_fop = &configfs_dir_operations;
+                /* directory inodes start off with i_nlink == 2 (for "." entry) */
+                inode->i_nlink++;
+        } else {
+                pr_debug("configfs: could not get root inode\n");
+                return -ENOMEM;
+        }
+
+        root = d_alloc_root(inode);
+        if (!root) {
+                pr_debug("%s: could not get root dentry!\n",__FUNCTION__);
+                iput(inode);
+                return -ENOMEM;
+        }
+        config_group_init(&configfs_root_group);
+        configfs_root_group.cg_item.ci_dentry = root;
+        root->d_fsdata = &configfs_root;
+        sb->s_root = root;
+        return 0;
+}
+
+static struct super_block *configfs_get_sb(struct file_system_type *fs_type,
+        int flags, const char *dev_name, void *data)
+{
+        return get_sb_single(fs_type, flags, data, configfs_fill_super);
+}
+
+static struct file_system_type configfs_fs_type = {
+        .owner          = THIS_MODULE,
+        .name           = "configfs",
+        .get_sb         = configfs_get_sb,
+        .kill_sb        = kill_litter_super,
+};
+
+int configfs_pin_fs(void)
+{
+        return simple_pin_fs("configfs", &configfs_mount,
+                             &configfs_mnt_count);
+}
+
+void configfs_release_fs(void)
+{
+        simple_release_fs(&configfs_mount, &configfs_mnt_count);
+}
+
+
+static decl_subsys(config, NULL, NULL);
+
+static int __init configfs_init(void)
+{
+        int err;
+
+        kset_set_kset_s(&config_subsys, kernel_subsys);
+        err = subsystem_register(&config_subsys);
+        if (err)
+                return err;
+
+        err = register_filesystem(&configfs_fs_type);
+        if (err) {
+                printk(KERN_ERR "configfs: Unable to register filesystem!\n");
+                subsystem_unregister(&config_subsys);
+        }
+
+        return err;
+}
+
+static void __exit configfs_exit(void)
+{
+        unregister_filesystem(&configfs_fs_type);
+        subsystem_unregister(&config_subsys);
+}
+
+MODULE_AUTHOR("Oracle");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("0.0.1");
+MODULE_DESCRIPTION("Simple RAM filesystem for user driven kernel subsystem configuration.");
+
+module_init(configfs_init);
+module_exit(configfs_exit);
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
new file mode 100644
index 000000000000..50f5840521a9
--- /dev/null
+++ b/fs/configfs/symlink.c
@@ -0,0 +1,281 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * symlink.c - operations for configfs symlinks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/namei.h>
+
+#include <linux/configfs.h>
+#include "configfs_internal.h"
+
+static int item_depth(struct config_item * item)
+{
+        struct config_item * p = item;
+        int depth = 0;
+        do { depth++; } while ((p = p->ci_parent) && !configfs_is_root(p));
+        return depth;
+}
+
+static int item_path_length(struct config_item * item)
+{
+        struct config_item * p = item;
+        int length = 1;
+        do {
+                length += strlen(config_item_name(p)) + 1;
+                p = p->ci_parent;
+        } while (p && !configfs_is_root(p));
+        return length;
+}
+
+static void fill_item_path(struct config_item * item, char * buffer, int length)
+{
+        struct config_item * p;
+
+        --length;
+        for (p = item; p && !configfs_is_root(p); p = p->ci_parent) {
+                int cur = strlen(config_item_name(p));
+
+                /* back up enough to print this bus id with '/' */
+                length -= cur;
+                strncpy(buffer + length,config_item_name(p),cur);
+                *(buffer + --length) = '/';
+        }
+}
+
+static int create_link(struct config_item *parent_item,
+                       struct config_item *item,
+                       struct dentry *dentry)
+{
+        struct configfs_dirent *target_sd = item->ci_dentry->d_fsdata;
+        struct configfs_symlink *sl;
+        int ret;
+
+        ret = -ENOMEM;
+        sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
+        if (sl) {
+                sl->sl_target = config_item_get(item);
+                /* FIXME: needs a lock, I'd bet */
+                list_add(&sl->sl_list, &target_sd->s_links);
+                ret = configfs_create_link(sl, parent_item->ci_dentry,
+                                           dentry);
+                if (ret) {
+                        list_del_init(&sl->sl_list);
+                        config_item_put(item);
+                        kfree(sl);
+                }
+        }
+
+        return ret;
+}
+
+
+static int get_target(const char *symname, struct nameidata *nd,
+                      struct config_item **target)
+{
+        int ret;
+
+        ret = path_lookup(symname, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, nd);
+        if (!ret) {
+                if (nd->dentry->d_sb == configfs_sb) {
+                        *target = configfs_get_config_item(nd->dentry);
+                        if (!*target) {
+                                ret = -ENOENT;
+                                path_release(nd);
+                        }
+                } else
+                        ret = -EPERM;
+        }
+
+        return ret;
+}
+
+
+int configfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+{
+        int ret;
+        struct nameidata nd;
+        struct config_item *parent_item;
+        struct config_item *target_item;
+        struct config_item_type *type;
+
+        ret = -EPERM;  /* What lack-of-symlink returns */
+        if (dentry->d_parent == configfs_sb->s_root)
+                goto out;
+
+        parent_item = configfs_get_config_item(dentry->d_parent);
+        type = parent_item->ci_type;
+
+        if (!type || !type->ct_item_ops ||
+            !type->ct_item_ops->allow_link)
+                goto out_put;
+
+        ret = get_target(symname, &nd, &target_item);
+        if (ret)
+                goto out_put;
+
+        ret = type->ct_item_ops->allow_link(parent_item, target_item);
+        if (!ret)
+                ret = create_link(parent_item, target_item, dentry);
+
+        config_item_put(target_item);
+        path_release(&nd);
+
+out_put:
+        config_item_put(parent_item);
+
+out:
+        return ret;
+}
+
+int configfs_unlink(struct inode *dir, struct dentry *dentry)
+{
+        struct configfs_dirent *sd = dentry->d_fsdata;
+        struct configfs_symlink *sl;
+        struct config_item *parent_item;
+        struct config_item_type *type;
+        int ret;
+
+        ret = -EPERM;  /* What lack-of-symlink returns */
+        if (!(sd->s_type & CONFIGFS_ITEM_LINK))
+                goto out;
+
+        if (dentry->d_parent == configfs_sb->s_root)
+                BUG();
+
+        sl = sd->s_element;
+
+        parent_item = configfs_get_config_item(dentry->d_parent);
+        type = parent_item->ci_type;
+
+        list_del_init(&sd->s_sibling);
+        configfs_drop_dentry(sd, dentry->d_parent);
+        dput(dentry);
+        configfs_put(sd);
+
+        /*
+         * drop_link() must be called before
+         * list_del_init(&sl->sl_list), so that the order of
+         * drop_link(this, target) and drop_item(target) is preserved.
+         */
+        if (type && type->ct_item_ops &&
+            type->ct_item_ops->drop_link)
+                type->ct_item_ops->drop_link(parent_item,
+                                               sl->sl_target);
+
+        /* FIXME: Needs lock */
+        list_del_init(&sl->sl_list);
+
+        /* Put reference from create_link() */
+        config_item_put(sl->sl_target);
+        kfree(sl);
+
+        config_item_put(parent_item);
+
+        ret = 0;
+
+out:
+        return ret;
+}
+
+static int configfs_get_target_path(struct config_item * item, struct config_item * target,
+                                   char *path)
+{
+        char * s;
+        int depth, size;
+
+        depth = item_depth(item);
+        size = item_path_length(target) + depth * 3 - 1;
+        if (size > PATH_MAX)
+                return -ENAMETOOLONG;
+
+        pr_debug("%s: depth = %d, size = %d\n", __FUNCTION__, depth, size);
+
+        for (s = path; depth--; s += 3)
+                strcpy(s,"../");
+
+        fill_item_path(target, path, size);
+        pr_debug("%s: path = '%s'\n", __FUNCTION__, path);
+
+        return 0;
+}
+
+static int configfs_getlink(struct dentry *dentry, char * path)
+{
+        struct config_item *item, *target_item;
+        int error = 0;
+
+        item = configfs_get_config_item(dentry->d_parent);
+        if (!item)
+                return -EINVAL;
+
+        target_item = configfs_get_config_item(dentry);
+        if (!target_item) {
+                config_item_put(item);
+                return -EINVAL;
+        }
+
+        down_read(&configfs_rename_sem);
+        error = configfs_get_target_path(item, target_item, path);
+        up_read(&configfs_rename_sem);
+
+        config_item_put(item);
+        config_item_put(target_item);
+        return error;
+
+}
+
+static void *configfs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+        int error = -ENOMEM;
+        unsigned long page = get_zeroed_page(GFP_KERNEL);
+
+        if (page) {
+                error = configfs_getlink(dentry, (char *)page);
+                if (!error) {
+                        nd_set_link(nd, (char *)page);
+                        return (void *)page;
+                }
+        }
+
+        nd_set_link(nd, ERR_PTR(error));
+        return NULL;
+}
+
+static void configfs_put_link(struct dentry *dentry, struct nameidata *nd,
+                              void *cookie)
+{
+        if (cookie) {
+                unsigned long page = (unsigned long)cookie;
+                free_page(page);
+        }
+}
+
+struct inode_operations configfs_symlink_inode_operations = {
+        .follow_link = configfs_follow_link,
+        .readlink = generic_readlink,
+        .put_link = configfs_put_link,
+};
+
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
new file mode 100644
index 000000000000..acffb8c9073a
--- /dev/null
+++ b/include/linux/configfs.h
@@ -0,0 +1,205 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * configfs.h - definitions for the device driver filesystem
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ *
+ * Based on sysfs:
+ *      sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel
+ *
+ * Based on kobject.h:
+ *      Copyright (c) 2002-2003 Patrick Mochel
+ *      Copyright (c) 2002-2003 Open Source Development Labs
+ *
+ * configfs Copyright (C) 2005 Oracle.  All rights reserved.
+ *
+ * Please read Documentation/filesystems/configfs.txt before using the
+ * configfs interface, ESPECIALLY the parts about reference counts and
+ * item destructors.
+ */
+
+#ifndef _CONFIGFS_H_
+#define _CONFIGFS_H_
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/kref.h>
+
+#include <asm/atomic.h>
+#include <asm/semaphore.h>
+
+#define CONFIGFS_ITEM_NAME_LEN  20
+
+struct module;
+
+struct configfs_item_operations;
+struct configfs_group_operations;
+struct configfs_attribute;
+struct configfs_subsystem;
+
+struct config_item {
+        char                    *ci_name;
+        char                    ci_namebuf[CONFIGFS_ITEM_NAME_LEN];
+        struct kref             ci_kref;
+        struct list_head        ci_entry;
+        struct config_item      *ci_parent;
+        struct config_group     *ci_group;
+        struct config_item_type *ci_type;
+        struct dentry           *ci_dentry;
+};
+
+extern int config_item_set_name(struct config_item *, const char *, ...);
+
+static inline char *config_item_name(struct config_item * item)
+{
+        return item->ci_name;
+}
+
+extern void config_item_init(struct config_item *);
+extern void config_item_init_type_name(struct config_item *item,
+                                       const char *name,
+                                       struct config_item_type *type);
+extern void config_item_cleanup(struct config_item *);
+
+extern struct config_item * config_item_get(struct config_item *);
+extern void config_item_put(struct config_item *);
+
+struct config_item_type {
+        struct module                           *ct_owner;
+        struct configfs_item_operations         *ct_item_ops;
+        struct configfs_group_operations        *ct_group_ops;
+        struct configfs_attribute               **ct_attrs;
+};
+
+
+/**
+ *      group - a group of config_items of a specific type, belonging
+ *      to a specific subsystem.
+ */
+
+struct config_group {
+        struct config_item              cg_item;
+        struct list_head                cg_children;
+        struct configfs_subsystem       *cg_subsys;
+        struct config_group             **default_groups;
+};
+
+
+extern void config_group_init(struct config_group *group);
+extern void config_group_init_type_name(struct config_group *group,
+                                        const char *name,
+                                        struct config_item_type *type);
+
+
+static inline struct config_group *to_config_group(struct config_item *item)
+{
+        return item ? container_of(item,struct config_group,cg_item) : NULL;
+}
+
+static inline struct config_group *config_group_get(struct config_group *group)
+{
+        return group ? to_config_group(config_item_get(&group->cg_item)) : NULL;
+}
+
+static inline void config_group_put(struct config_group *group)
+{
+        config_item_put(&group->cg_item);
+}
+
+extern struct config_item *config_group_find_obj(struct config_group *, const char *);
+
+
+struct configfs_attribute {
+        char                    *ca_name;
+        struct module           *ca_owner;
+        mode_t                  ca_mode;
+};
+
+
+/*
+ * If allow_link() exists, the item can symlink(2) out to other
+ * items.  If the item is a group, it may support mkdir(2).
+ * Groups supply one of make_group() and make_item().  If the
+ * group supports make_group(), one can create group children.  If it
+ * supports make_item(), one can create config_item children.  If it has
+ * default_groups on group->default_groups, it has automatically created
+ * group children.  default_groups may coexist alongsize make_group() or
+ * make_item(), but if the group wishes to have only default_groups
+ * children (disallowing mkdir(2)), it need not provide either function.
+ * If the group has commit(), it supports pending and commited (active)
+ * items.
+ */
+struct configfs_item_operations {
+        void (*release)(struct config_item *);
+        ssize_t (*show_attribute)(struct config_item *, struct configfs_attribute *,char *);
+        ssize_t (*store_attribute)(struct config_item *,struct configfs_attribute *,const char *, size_t);
+        int (*allow_link)(struct config_item *src, struct config_item *target);
+        int (*drop_link)(struct config_item *src, struct config_item *target);
+};
+
+struct configfs_group_operations {
+        struct config_item *(*make_item)(struct config_group *group, const char *name);
+        struct config_group *(*make_group)(struct config_group *group, const char *name);
+        int (*commit_item)(struct config_item *item);
+        void (*drop_item)(struct config_group *group, struct config_item *item);
+};
+
+
+
+/**
+ * Use these macros to make defining attributes easier. See include/linux/device.h
+ * for examples..
+ */
+
+#if 0
+#define __ATTR(_name,_mode,_show,_store) { \
+        .attr = {.ca_name = __stringify(_name), .ca_mode = _mode, .ca_owner = THIS_MODULE },    \
+        .show   = _show,                                        \
+        .store  = _store,                                       \
+}
+
+#define __ATTR_RO(_name) { \
+        .attr   = { .ca_name = __stringify(_name), .ca_mode = 0444, .ca_owner = THIS_MODULE },  \
+        .show   = _name##_show, \
+}
+
+#define __ATTR_NULL { .attr = { .name = NULL } }
+
+#define attr_name(_attr) (_attr).attr.name
+#endif
+
+
+struct configfs_subsystem {
+        struct config_group     su_group;
+        struct semaphore        su_sem;
+};
+
+static inline struct configfs_subsystem *to_configfs_subsystem(struct config_group *group)
+{
+        return group ?
+                container_of(group, struct configfs_subsystem, su_group) :
+                NULL;
+}
+
+int configfs_register_subsystem(struct configfs_subsystem *subsys);
+void configfs_unregister_subsystem(struct configfs_subsystem *subsys);
+
+#endif  /* __KERNEL__ */
+
+#endif /* _CONFIGFS_H_ */