Merge tag 'driver-core-3.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core

Pull driver core / sysfs patches from Greg KH:
 "Here's the big driver core and sysfs patch set for 3.14-rc1.

  There's a lot of work here moving sysfs logic out into a "kernfs" to
  allow other subsystems to also have a virtual filesystem with the same
  attributes of sysfs (handle device disconnect, dynamic creation /
  removal as needed / unneeded, etc)

  This is primarily being done for the cgroups filesystem, but the goal
  is to also move debugfs to it when it is ready, solving all of the
  known issues in that filesystem as well.  The code isn't completed
  yet, but all should be stable now (there is a big section that was
  reverted due to problems found when testing)

  There's also some other smaller fixes, and a driver core addition that
  allows for a "collection" of objects, that the DRM people will be
  using soon (it's in this tree to make merges after -rc1 easier)

  All of this has been in linux-next with no reported issues"

* tag 'driver-core-3.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (113 commits)
  kernfs: associate a new kernfs_node with its parent on creation
  kernfs: add struct dentry declaration in kernfs.h
  kernfs: fix get_active failure handling in kernfs_seq_*()
  Revert "kernfs: fix get_active failure handling in kernfs_seq_*()"
  Revert "kernfs: replace kernfs_node->u.completion with kernfs_root->deactivate_waitq"
  Revert "kernfs: remove KERNFS_ACTIVE_REF and add kernfs_lockdep()"
  Revert "kernfs: remove KERNFS_REMOVED"
  Revert "kernfs: restructure removal path to fix possible premature return"
  Revert "kernfs: invoke kernfs_unmap_bin_file() directly from __kernfs_remove()"
  Revert "kernfs: remove kernfs_addrm_cxt"
  Revert "kernfs: make kernfs_get_active() block if the node is deactivated but not removed"
  Revert "kernfs: implement kernfs_{de|re}activate[_self]()"
  Revert "kernfs, sysfs, driver-core: implement kernfs_remove_self() and its wrappers"
  Revert "pci: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "scsi: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "s390: use device_remove_file_self() instead of device_schedule_callback()"
  Revert "sysfs, driver-core: remove unused {sysfs|device}_schedule_callback_owner()"
  Revert "kernfs: remove unnecessary NULL check in __kernfs_remove()"
  kernfs: remove unnecessary NULL check in __kernfs_remove()
  drivers/base: provide an infrastructure for componentised subsystems
  ...

Documentation/driver-model/design-patterns.txt

@@ -0,0 +1,116 @@
+
+Device Driver Design Patterns
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+This document describes a few common design patterns found in device drivers.
+It is likely that subsystem maintainers will ask driver developers to
+conform to these design patterns.
+
+1. State Container
+2. container_of()
+
+
+1. State Container
+~~~~~~~~~~~~~~~~~~
+
+While the kernel contains a few device drivers that assume that they will
+only be probed() once on a certain system (singletons), it is custom to assume
+that the device the driver binds to will appear in several instances. This
+means that the probe() function and all callbacks need to be reentrant.
+
+The most common way to achieve this is to use the state container design
+pattern. It usually has this form:
+
+struct foo {
+    spinlock_t lock; /* Example member */
+    (...)
+};
+
+static int foo_probe(...)
+{
+    struct foo *foo;
+
+    foo = devm_kzalloc(dev, sizeof(*foo), GFP_KERNEL);
+    if (!foo)
+        return -ENOMEM;
+    spin_lock_init(&foo->lock);
+    (...)
+}
+
+This will create an instance of struct foo in memory every time probe() is
+called. This is our state container for this instance of the device driver.
+Of course it is then necessary to always pass this instance of the
+state around to all functions that need access to the state and its members.
+
+For example, if the driver is registering an interrupt handler, you would
+pass around a pointer to struct foo like this:
+
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+    struct foo *foo = arg;
+    (...)
+}
+
+static int foo_probe(...)
+{
+    struct foo *foo;
+
+    (...)
+    ret = request_irq(irq, foo_handler, 0, "foo", foo);
+}
+
+This way you always get a pointer back to the correct instance of foo in
+your interrupt handler.
+
+
+2. container_of()
+~~~~~~~~~~~~~~~~~
+
+Continuing on the above example we add an offloaded work:
+
+struct foo {
+    spinlock_t lock;
+    struct workqueue_struct *wq;
+    struct work_struct offload;
+    (...)
+};
+
+static void foo_work(struct work_struct *work)
+{
+    struct foo *foo = container_of(work, struct foo, offload);
+
+    (...)
+}
+
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+    struct foo *foo = arg;
+
+    queue_work(foo->wq, &foo->offload);
+    (...)
+}
+
+static int foo_probe(...)
+{
+    struct foo *foo;
+
+    foo->wq = create_singlethread_workqueue("foo-wq");
+    INIT_WORK(&foo->offload, foo_work);
+    (...)
+}
+
+The design pattern is the same for an hrtimer or something similar that will
+return a single argument which is a pointer to a struct member in the
+callback.
+
+container_of() is a macro defined in <linux/kernel.h>
+
+What container_of() does is to obtain a pointer to the containing struct from
+a pointer to a member by a simple subtraction using the offsetof() macro from
+standard C, which allows something similar to object oriented behaviours.
+Notice that the contained member must not be a pointer, but an actual member
+for this to work.
+
+We can see here that we avoid having global pointers to our struct foo *
+instance this way, while still keeping the number of parameters passed to the
+work function to a single pointer.

Documentation/kobject.txt

@@ -342,7 +342,10 @@ kset use:
 
 When you are finished with the kset, call:
   void kset_unregister(struct kset *kset);
-to destroy it.
+to destroy it.  This removes the kset from sysfs and decrements its reference
+count.  When the reference count goes to zero, the kset will be released.
+Because other references to the kset may still exist, the release may happen
+after kset_unregister() returns.
 
 An example of using a kset can be seen in the
 samples/kobject/kset-example.c file in the kernel tree.

arch/x86/kernel/cpu/microcode/amd.c

@@ -433,7 +433,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 	if (c->x86 >= 0x15)
 		snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
 
-	if (request_firmware(&fw, (const char *)fw_name, device)) {
+	if (request_firmware_direct(&fw, (const char *)fw_name, device)) {
 		pr_debug("failed to load file %s\n", fw_name);
 		goto out;
 	}

arch/x86/kernel/cpu/microcode/intel.c

@@ -278,7 +278,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 	sprintf(name, "intel-ucode/%02x-%02x-%02x",
 		c->x86, c->x86_model, c->x86_mask);
 
-	if (request_firmware(&firmware, name, device)) {
+	if (request_firmware_direct(&firmware, name, device)) {
 		pr_debug("data file %s load failed\n", name);
 		return UCODE_NFOUND;
 	}

drivers/base/Makefile

@@ -1,6 +1,6 @@
 # Makefile for the Linux device tree
 
-obj-y			:= core.o bus.o dd.o syscore.o \
+obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \

drivers/base/bus.c

@@ -146,8 +146,19 @@ void bus_remove_file(struct bus_type *bus, struct bus_attribute *attr)
 }
 EXPORT_SYMBOL_GPL(bus_remove_file);
 
+static void bus_release(struct kobject *kobj)
+{
+	struct subsys_private *priv =
+		container_of(kobj, typeof(*priv), subsys.kobj);
+	struct bus_type *bus = priv->bus;
+
+	kfree(priv);
+	bus->p = NULL;
+}
+
 static struct kobj_type bus_ktype = {
 	.sysfs_ops	= &bus_sysfs_ops,
+	.release	= bus_release,
 };
 
 static int bus_uevent_filter(struct kset *kset, struct kobject *kobj)
@@ -953,8 +964,6 @@ void bus_unregister(struct bus_type *bus)
 	kset_unregister(bus->p->devices_kset);
 	bus_remove_file(bus, &bus_attr_uevent);
 	kset_unregister(&bus->p->subsys);
-	kfree(bus->p);
-	bus->p = NULL;
 }
 EXPORT_SYMBOL_GPL(bus_unregister);
 

drivers/base/component.c

@@ -0,0 +1,382 @@
+/*
+ * Componentized device handling.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This is work in progress.  We gather up the component devices into a list,
+ * and bind them when instructed.  At the moment, we're specific to the DRM
+ * subsystem, and only handles one master device, but this doesn't have to be
+ * the case.
+ */
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+struct master {
+	struct list_head node;
+	struct list_head components;
+	bool bound;
+
+	const struct component_master_ops *ops;
+	struct device *dev;
+};
+
+struct component {
+	struct list_head node;
+	struct list_head master_node;
+	struct master *master;
+	bool bound;
+
+	const struct component_ops *ops;
+	struct device *dev;
+};
+
+static DEFINE_MUTEX(component_mutex);
+static LIST_HEAD(component_list);
+static LIST_HEAD(masters);
+
+static struct master *__master_find(struct device *dev,
+	const struct component_master_ops *ops)
+{
+	struct master *m;
+
+	list_for_each_entry(m, &masters, node)
+		if (m->dev == dev && (!ops || m->ops == ops))
+			return m;
+
+	return NULL;
+}
+
+/* Attach an unattached component to a master. */
+static void component_attach_master(struct master *master, struct component *c)
+{
+	c->master = master;
+
+	list_add_tail(&c->master_node, &master->components);
+}
+
+/* Detach a component from a master. */
+static void component_detach_master(struct master *master, struct component *c)
+{
+	list_del(&c->master_node);
+
+	c->master = NULL;
+}
+
+int component_master_add_child(struct master *master,
+	int (*compare)(struct device *, void *), void *compare_data)
+{
+	struct component *c;
+	int ret = -ENXIO;
+
+	list_for_each_entry(c, &component_list, node) {
+		if (c->master)
+			continue;
+
+		if (compare(c->dev, compare_data)) {
+			component_attach_master(master, c);
+			ret = 0;
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(component_master_add_child);
+
+/* Detach all attached components from this master */
+static void master_remove_components(struct master *master)
+{
+	while (!list_empty(&master->components)) {
+		struct component *c = list_first_entry(&master->components,
+					struct component, master_node);
+
+		WARN_ON(c->master != master);
+
+		component_detach_master(master, c);
+	}
+}
+
+/*
+ * Try to bring up a master.  If component is NULL, we're interested in
+ * this master, otherwise it's a component which must be present to try
+ * and bring up the master.
+ *
+ * Returns 1 for successful bringup, 0 if not ready, or -ve errno.
+ */
+static int try_to_bring_up_master(struct master *master,
+	struct component *component)
+{
+	int ret = 0;
+
+	if (!master->bound) {
+		/*
+		 * Search the list of components, looking for components that
+		 * belong to this master, and attach them to the master.
+		 */
+		if (master->ops->add_components(master->dev, master)) {
+			/* Failed to find all components */
+			master_remove_components(master);
+			ret = 0;
+			goto out;
+		}
+
+		if (component && component->master != master) {
+			master_remove_components(master);
+			ret = 0;
+			goto out;
+		}
+
+		/* Found all components */
+		ret = master->ops->bind(master->dev);
+		if (ret < 0) {
+			master_remove_components(master);
+			goto out;
+		}
+
+		master->bound = true;
+		ret = 1;
+	}
+out:
+
+	return ret;
+}
+
+static int try_to_bring_up_masters(struct component *component)
+{
+	struct master *m;
+	int ret = 0;
+
+	list_for_each_entry(m, &masters, node) {
+		ret = try_to_bring_up_master(m, component);
+		if (ret != 0)
+			break;
+	}
+
+	return ret;
+}
+
+static void take_down_master(struct master *master)
+{
+	if (master->bound) {
+		master->ops->unbind(master->dev);
+		master->bound = false;
+	}
+
+	master_remove_components(master);
+}
+
+int component_master_add(struct device *dev,
+	const struct component_master_ops *ops)
+{
+	struct master *master;
+	int ret;
+
+	master = kzalloc(sizeof(*master), GFP_KERNEL);
+	if (!master)
+		return -ENOMEM;
+
+	master->dev = dev;
+	master->ops = ops;
+	INIT_LIST_HEAD(&master->components);
+
+	/* Add to the list of available masters. */
+	mutex_lock(&component_mutex);
+	list_add(&master->node, &masters);
+
+	ret = try_to_bring_up_master(master, NULL);
+
+	if (ret < 0) {
+		/* Delete off the list if we weren't successful */
+		list_del(&master->node);
+		kfree(master);
+	}
+	mutex_unlock(&component_mutex);
+
+	return ret < 0 ? ret : 0;
+}
+EXPORT_SYMBOL_GPL(component_master_add);
+
+void component_master_del(struct device *dev,
+	const struct component_master_ops *ops)
+{
+	struct master *master;
+
+	mutex_lock(&component_mutex);
+	master = __master_find(dev, ops);
+	if (master) {
+		take_down_master(master);
+
+		list_del(&master->node);
+		kfree(master);
+	}
+	mutex_unlock(&component_mutex);
+}
+EXPORT_SYMBOL_GPL(component_master_del);
+
+static void component_unbind(struct component *component,
+	struct master *master, void *data)
+{
+	WARN_ON(!component->bound);
+
+	component->ops->unbind(component->dev, master->dev, data);
+	component->bound = false;
+
+	/* Release all resources claimed in the binding of this component */
+	devres_release_group(component->dev, component);
+}
+
+void component_unbind_all(struct device *master_dev, void *data)
+{
+	struct master *master;
+	struct component *c;
+
+	WARN_ON(!mutex_is_locked(&component_mutex));
+
+	master = __master_find(master_dev, NULL);
+	if (!master)
+		return;
+
+	list_for_each_entry_reverse(c, &master->components, master_node)
+		component_unbind(c, master, data);
+}
+EXPORT_SYMBOL_GPL(component_unbind_all);
+
+static int component_bind(struct component *component, struct master *master,
+	void *data)
+{
+	int ret;
+
+	/*
+	 * Each component initialises inside its own devres group.
+	 * This allows us to roll-back a failed component without
+	 * affecting anything else.
+	 */
+	if (!devres_open_group(master->dev, NULL, GFP_KERNEL))
+		return -ENOMEM;
+
+	/*
+	 * Also open a group for the device itself: this allows us
+	 * to release the resources claimed against the sub-device
+	 * at the appropriate moment.
+	 */
+	if (!devres_open_group(component->dev, component, GFP_KERNEL)) {
+		devres_release_group(master->dev, NULL);
+		return -ENOMEM;
+	}
+
+	dev_dbg(master->dev, "binding %s (ops %ps)\n",
+		dev_name(component->dev), component->ops);
+
+	ret = component->ops->bind(component->dev, master->dev, data);
+	if (!ret) {
+		component->bound = true;
+
+		/*
+		 * Close the component device's group so that resources
+		 * allocated in the binding are encapsulated for removal
+		 * at unbind.  Remove the group on the DRM device as we
+		 * can clean those resources up independently.
+		 */
+		devres_close_group(component->dev, NULL);
+		devres_remove_group(master->dev, NULL);
+
+		dev_info(master->dev, "bound %s (ops %ps)\n",
+			 dev_name(component->dev), component->ops);
+	} else {
+		devres_release_group(component->dev, NULL);
+		devres_release_group(master->dev, NULL);
+
+		dev_err(master->dev, "failed to bind %s (ops %ps): %d\n",
+			dev_name(component->dev), component->ops, ret);
+	}
+
+	return ret;
+}
+
+int component_bind_all(struct device *master_dev, void *data)
+{
+	struct master *master;
+	struct component *c;
+	int ret = 0;
+
+	WARN_ON(!mutex_is_locked(&component_mutex));
+
+	master = __master_find(master_dev, NULL);
+	if (!master)
+		return -EINVAL;
+
+	list_for_each_entry(c, &master->components, master_node) {
+		ret = component_bind(c, master, data);
+		if (ret)
+			break;
+	}
+
+	if (ret != 0) {
+		list_for_each_entry_continue_reverse(c, &master->components,
+						     master_node)
+			component_unbind(c, master, data);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(component_bind_all);
+
+int component_add(struct device *dev, const struct component_ops *ops)
+{
+	struct component *component;
+	int ret;
+
+	component = kzalloc(sizeof(*component), GFP_KERNEL);
+	if (!component)
+		return -ENOMEM;
+
+	component->ops = ops;
+	component->dev = dev;
+
+	dev_dbg(dev, "adding component (ops %ps)\n", ops);
+
+	mutex_lock(&component_mutex);
+	list_add_tail(&component->node, &component_list);
+
+	ret = try_to_bring_up_masters(component);
+	if (ret < 0) {
+		list_del(&component->node);
+
+		kfree(component);
+	}
+	mutex_unlock(&component_mutex);
+
+	return ret < 0 ? ret : 0;
+}
+EXPORT_SYMBOL_GPL(component_add);
+
+void component_del(struct device *dev, const struct component_ops *ops)
+{
+	struct component *c, *component = NULL;
+
+	mutex_lock(&component_mutex);
+	list_for_each_entry(c, &component_list, node)
+		if (c->dev == dev && c->ops == ops) {
+			list_del(&c->node);
+			component = c;
+			break;
+		}
+
+	if (component && component->master)
+		take_down_master(component->master);
+
+	mutex_unlock(&component_mutex);
+
+	WARN_ON(!component);
+	kfree(component);
+}
+EXPORT_SYMBOL_GPL(component_del);
+
+MODULE_LICENSE("GPL v2");

drivers/base/core.c

@@ -491,11 +491,13 @@ static int device_add_attrs(struct device *dev)
 	if (device_supports_offline(dev) && !dev->offline_disabled) {
 		error = device_create_file(dev, &dev_attr_online);
 		if (error)
-			goto err_remove_type_groups;
+			goto err_remove_dev_groups;
 	}
 
 	return 0;
 
+ err_remove_dev_groups:
+	device_remove_groups(dev, dev->groups);
  err_remove_type_groups:
 	if (type)
 		device_remove_groups(dev, type->groups);
@@ -1603,6 +1605,7 @@ device_create_groups_vargs(struct class *class, struct device *parent,
 		goto error;
 	}
 
+	device_initialize(dev);
 	dev->devt = devt;
 	dev->class = class;
 	dev->parent = parent;
@@ -1614,7 +1617,7 @@ device_create_groups_vargs(struct class *class, struct device *parent,
 	if (retval)
 		goto error;
 
-	retval = device_register(dev);
+	retval = device_add(dev);
 	if (retval)
 		goto error;
 

drivers/base/devtmpfs.c

@@ -299,7 +299,7 @@ static int handle_remove(const char *nodename, struct device *dev)
 {
 	struct path parent;
 	struct dentry *dentry;
-	int deleted = 1;
+	int deleted = 0;
 	int err;
 
 	dentry = kern_path_locked(nodename, &parent);

drivers/base/firmware_class.c

@@ -96,6 +96,15 @@ static inline long firmware_loading_timeout(void)
 	return loading_timeout > 0 ? loading_timeout * HZ : MAX_SCHEDULE_TIMEOUT;
 }
 
+/* firmware behavior options */
+#define FW_OPT_UEVENT	(1U << 0)
+#define FW_OPT_NOWAIT	(1U << 1)
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+#define FW_OPT_FALLBACK	(1U << 2)
+#else
+#define FW_OPT_FALLBACK	0
+#endif
+
 struct firmware_cache {
 	/* firmware_buf instance will be added into the below list */
 	spinlock_t lock;
@@ -219,6 +228,7 @@ static int fw_lookup_and_allocate_buf(const char *fw_name,
 }
 
 static void __fw_free_buf(struct kref *ref)
+	__releases(&fwc->lock)
 {
 	struct firmware_buf *buf = to_fwbuf(ref);
 	struct firmware_cache *fwc = buf->fwc;
@@ -270,21 +280,21 @@ module_param_string(path, fw_path_para, sizeof(fw_path_para), 0644);
 MODULE_PARM_DESC(path, "customized firmware image search path with a higher priority than default path");
 
 /* Don't inline this: 'struct kstat' is biggish */
-static noinline_for_stack long fw_file_size(struct file *file)
+static noinline_for_stack int fw_file_size(struct file *file)
 {
 	struct kstat st;
 	if (vfs_getattr(&file->f_path, &st))
 		return -1;
 	if (!S_ISREG(st.mode))
 		return -1;
-	if (st.size != (long)st.size)
+	if (st.size != (int)st.size)
 		return -1;
 	return st.size;
 }
 
 static int fw_read_file_contents(struct file *file, struct firmware_buf *fw_buf)
 {
-	long size;
+	int size;
 	char *buf;
 	int rc;
 
@@ -820,7 +830,7 @@ static void firmware_class_timeout_work(struct work_struct *work)
 
 static struct firmware_priv *
 fw_create_instance(struct firmware *firmware, const char *fw_name,
-		   struct device *device, bool uevent, bool nowait)
+		   struct device *device, unsigned int opt_flags)
 {
 	struct firmware_priv *fw_priv;
 	struct device *f_dev;
@@ -832,7 +842,7 @@ fw_create_instance(struct firmware *firmware, const char *fw_name,
 		goto exit;
 	}
 
-	fw_priv->nowait = nowait;
+	fw_priv->nowait = !!(opt_flags & FW_OPT_NOWAIT);
 	fw_priv->fw = firmware;
 	INIT_DELAYED_WORK(&fw_priv->timeout_work,
 		firmware_class_timeout_work);
@@ -848,8 +858,8 @@ exit:
 }
 
 /* load a firmware via user helper */
-static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
-				  long timeout)
+static int _request_firmware_load(struct firmware_priv *fw_priv,
+				  unsigned int opt_flags, long timeout)
 {
 	int retval = 0;
 	struct device *f_dev = &fw_priv->dev;
@@ -885,7 +895,7 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
 		goto err_del_bin_attr;
 	}
 
-	if (uevent) {
+	if (opt_flags & FW_OPT_UEVENT) {
 		buf->need_uevent = true;
 		dev_set_uevent_suppress(f_dev, false);
 		dev_dbg(f_dev, "firmware: requesting %s\n", buf->fw_id);
@@ -911,16 +921,16 @@ err_put_dev:
 
 static int fw_load_from_user_helper(struct firmware *firmware,
 				    const char *name, struct device *device,
-				    bool uevent, bool nowait, long timeout)
+				    unsigned int opt_flags, long timeout)
 {
 	struct firmware_priv *fw_priv;
 
-	fw_priv = fw_create_instance(firmware, name, device, uevent, nowait);
+	fw_priv = fw_create_instance(firmware, name, device, opt_flags);
 	if (IS_ERR(fw_priv))
 		return PTR_ERR(fw_priv);
 
 	fw_priv->buf = firmware->priv;
-	return _request_firmware_load(fw_priv, uevent, timeout);
+	return _request_firmware_load(fw_priv, opt_flags, timeout);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -942,7 +952,7 @@ static void kill_requests_without_uevent(void)
 #else /* CONFIG_FW_LOADER_USER_HELPER */
 static inline int
 fw_load_from_user_helper(struct firmware *firmware, const char *name,
-			 struct device *device, bool uevent, bool nowait,
+			 struct device *device, unsigned int opt_flags,
 			 long timeout)
 {
 	return -ENOENT;
@@ -1023,7 +1033,7 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name,
 }
 
 static int assign_firmware_buf(struct firmware *fw, struct device *device,
-				bool skip_cache)
+			       unsigned int opt_flags)
 {
 	struct firmware_buf *buf = fw->priv;
 
@@ -1040,7 +1050,8 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
 	 * device may has been deleted already, but the problem
 	 * should be fixed in devres or driver core.
 	 */
-	if (device && !skip_cache)
+	/* don't cache firmware handled without uevent */
+	if (device && (opt_flags & FW_OPT_UEVENT))
 		fw_add_devm_name(device, buf->fw_id);
 
 	/*
@@ -1061,7 +1072,7 @@ static int assign_firmware_buf(struct firmware *fw, struct device *device,
 /* called from request_firmware() and request_firmware_work_func() */
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
-		  struct device *device, bool uevent, bool nowait)
+		  struct device *device, unsigned int opt_flags)
 {
 	struct firmware *fw;
 	long timeout;
@@ -1076,7 +1087,7 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 
 	ret = 0;
 	timeout = firmware_loading_timeout();
-	if (nowait) {
+	if (opt_flags & FW_OPT_NOWAIT) {
 		timeout = usermodehelper_read_lock_wait(timeout);
 		if (!timeout) {
 			dev_dbg(device, "firmware: %s loading timed out\n",
@@ -1095,16 +1106,18 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 
 	ret = fw_get_filesystem_firmware(device, fw->priv);
 	if (ret) {
-		dev_warn(device, "Direct firmware load failed with error %d\n",
-			 ret);
-		dev_warn(device, "Falling back to user helper\n");
-		ret = fw_load_from_user_helper(fw, name, device,
-					       uevent, nowait, timeout);
+		if (opt_flags & FW_OPT_FALLBACK) {
+			dev_warn(device,
+				 "Direct firmware load failed with error %d\n",
+				 ret);
+			dev_warn(device, "Falling back to user helper\n");
+			ret = fw_load_from_user_helper(fw, name, device,
+						       opt_flags, timeout);
+		}
 	}
 
-	/* don't cache firmware handled without uevent */
 	if (!ret)
-		ret = assign_firmware_buf(fw, device, !uevent);
+		ret = assign_firmware_buf(fw, device, opt_flags);
 
 	usermodehelper_read_unlock();
 
@@ -1146,12 +1159,37 @@ request_firmware(const struct firmware **firmware_p, const char *name,
 
 	/* Need to pin this module until return */
 	__module_get(THIS_MODULE);
-	ret = _request_firmware(firmware_p, name, device, true, false);
+	ret = _request_firmware(firmware_p, name, device,
+				FW_OPT_UEVENT | FW_OPT_FALLBACK);
 	module_put(THIS_MODULE);
 	return ret;
 }
 EXPORT_SYMBOL(request_firmware);
 
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+/**
+ * request_firmware: - load firmware directly without usermode helper
+ * @firmware_p: pointer to firmware image
+ * @name: name of firmware file
+ * @device: device for which firmware is being loaded
+ *
+ * This function works pretty much like request_firmware(), but this doesn't
+ * fall back to usermode helper even if the firmware couldn't be loaded
+ * directly from fs.  Hence it's useful for loading optional firmwares, which
+ * aren't always present, without extra long timeouts of udev.
+ **/
+int request_firmware_direct(const struct firmware **firmware_p,
+			    const char *name, struct device *device)
+{
+	int ret;
+	__module_get(THIS_MODULE);
+	ret = _request_firmware(firmware_p, name, device, FW_OPT_UEVENT);
+	module_put(THIS_MODULE);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(request_firmware_direct);
+#endif
+
 /**
  * release_firmware: - release the resource associated with a firmware image
  * @fw: firmware resource to release
@@ -1174,7 +1212,7 @@ struct firmware_work {
 	struct device *device;
 	void *context;
 	void (*cont)(const struct firmware *fw, void *context);
-	bool uevent;
+	unsigned int opt_flags;
 };
 
 static void request_firmware_work_func(struct work_struct *work)
@@ -1185,7 +1223,7 @@ static void request_firmware_work_func(struct work_struct *work)
 	fw_work = container_of(work, struct firmware_work, work);
 
 	_request_firmware(&fw, fw_work->name, fw_work->device,
-			  fw_work->uevent, true);
+			  fw_work->opt_flags);
 	fw_work->cont(fw, fw_work->context);
 	put_device(fw_work->device); /* taken in request_firmware_nowait() */
 
@@ -1233,7 +1271,8 @@ request_firmware_nowait(
 	fw_work->device = device;
 	fw_work->context = context;
 	fw_work->cont = cont;
-	fw_work->uevent = uevent;
+	fw_work->opt_flags = FW_OPT_NOWAIT | FW_OPT_FALLBACK |
+		(uevent ? FW_OPT_UEVENT : 0);
 
 	if (!try_module_get(module)) {
 		kfree(fw_work);

drivers/firmware/dmi-sysfs.c

@@ -553,7 +553,7 @@ static const struct bin_attribute dmi_entry_raw_attr = {
 static void dmi_sysfs_entry_release(struct kobject *kobj)
 {
 	struct dmi_sysfs_entry *entry = to_entry(kobj);
-	sysfs_remove_bin_file(&entry->kobj, &dmi_entry_raw_attr);
+
 	spin_lock(&entry_list_lock);
 	list_del(&entry->list);
 	spin_unlock(&entry_list_lock);
@@ -685,6 +685,7 @@ static void __exit dmi_sysfs_exit(void)
 	pr_debug("dmi-sysfs: unloading.\n");
 	cleanup_entry_list();
 	kset_unregister(dmi_kset);
+	kobject_del(dmi_kobj);
 	kobject_put(dmi_kobj);
 }
 

drivers/gpio/gpiolib.c

@@ -393,7 +393,7 @@ static const DEVICE_ATTR(value, 0644,
 
 static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
 {
-	struct sysfs_dirent	*value_sd = priv;
+	struct kernfs_node	*value_sd = priv;
 
 	sysfs_notify_dirent(value_sd);
 	return IRQ_HANDLED;
@@ -402,7 +402,7 @@ static irqreturn_t gpio_sysfs_irq(int irq, void *priv)
 static int gpio_setup_irq(struct gpio_desc *desc, struct device *dev,
 		unsigned long gpio_flags)
 {
-	struct sysfs_dirent	*value_sd;
+	struct kernfs_node	*value_sd;
 	unsigned long		irq_flags;
 	int			ret, irq, id;
 

drivers/md/bitmap.c

@@ -1635,7 +1635,7 @@ int bitmap_create(struct mddev *mddev)
 	sector_t blocks = mddev->resync_max_sectors;
 	struct file *file = mddev->bitmap_info.file;
 	int err;
-	struct sysfs_dirent *bm = NULL;
+	struct kernfs_node *bm = NULL;
 
 	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);
 

drivers/md/bitmap.h

@@ -225,7 +225,7 @@ struct bitmap {
 	wait_queue_head_t overflow_wait;
 	wait_queue_head_t behind_wait;
 
-	struct sysfs_dirent *sysfs_can_clear;
+	struct kernfs_node *sysfs_can_clear;
 };
 
 /* the bitmap API */

drivers/md/md.h

@@ -106,7 +106,7 @@ struct md_rdev {
 					   */
 	struct work_struct del_work;	/* used for delayed sysfs removal */
 
-	struct sysfs_dirent *sysfs_state; /* handle for 'state'
+	struct kernfs_node *sysfs_state; /* handle for 'state'
 					   * sysfs entry */
 
 	struct badblocks {
@@ -379,10 +379,10 @@ struct mddev {
 	sector_t			resync_max;	/* resync should pause
 							 * when it gets here */
 
-	struct sysfs_dirent		*sysfs_state;	/* handle for 'array_state'
+	struct kernfs_node		*sysfs_state;	/* handle for 'array_state'
 							 * file in sysfs.
 							 */
-	struct sysfs_dirent		*sysfs_action;  /* handle for 'sync_action' */
+	struct kernfs_node		*sysfs_action;  /* handle for 'sync_action' */
 
 	struct work_struct del_work;	/* used for delayed sysfs removal */
 
@@ -501,13 +501,13 @@ struct md_sysfs_entry {
 };
 extern struct attribute_group md_bitmap_group;
 
-static inline struct sysfs_dirent *sysfs_get_dirent_safe(struct sysfs_dirent *sd, char *name)
+static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name)
 {
 	if (sd)
 		return sysfs_get_dirent(sd, name);
 	return sd;
 }
-static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd)
+static inline void sysfs_notify_dirent_safe(struct kernfs_node *sd)
 {
 	if (sd)
 		sysfs_notify_dirent(sd);

drivers/misc/mic/host/mic_device.h

@@ -112,7 +112,7 @@ struct mic_device {
 	struct work_struct shutdown_work;
 	u8 state;
 	u8 shutdown_status;
-	struct sysfs_dirent *state_sysfs;
+	struct kernfs_node *state_sysfs;
 	struct completion reset_wait;
 	void *log_buf_addr;
 	int *log_buf_len;

fs/Makefile

@@ -53,7 +53,7 @@ obj-$(CONFIG_FHANDLE)		+= fhandle.o
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
-obj-$(CONFIG_SYSFS)		+= sysfs/
+obj-$(CONFIG_SYSFS)		+= sysfs/ kernfs/
 obj-$(CONFIG_CONFIGFS_FS)	+= configfs/
 obj-y				+= devpts/
 

fs/kernfs/Makefile

@@ -0,0 +1,5 @@
+#
+# Makefile for the kernfs pseudo filesystem
+#
+
+obj-y		:= mount.o inode.o dir.o file.o symlink.o

fs/kernfs/dir.c

@@ -0,0 +1,1073 @@
+/*
+ * fs/kernfs/dir.c - kernfs directory implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/hash.h>
+
+#include "kernfs-internal.h"
+
+DEFINE_MUTEX(kernfs_mutex);
+
+#define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
+
+/**
+ *	kernfs_name_hash
+ *	@name: Null terminated string to hash
+ *	@ns:   Namespace tag to hash
+ *
+ *	Returns 31 bit hash of ns + name (so it fits in an off_t )
+ */
+static unsigned int kernfs_name_hash(const char *name, const void *ns)
+{
+	unsigned long hash = init_name_hash();
+	unsigned int len = strlen(name);
+	while (len--)
+		hash = partial_name_hash(*name++, hash);
+	hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
+	hash &= 0x7fffffffU;
+	/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
+	if (hash < 1)
+		hash += 2;
+	if (hash >= INT_MAX)
+		hash = INT_MAX - 1;
+	return hash;
+}
+
+static int kernfs_name_compare(unsigned int hash, const char *name,
+			       const void *ns, const struct kernfs_node *kn)
+{
+	if (hash != kn->hash)
+		return hash - kn->hash;
+	if (ns != kn->ns)
+		return ns - kn->ns;
+	return strcmp(name, kn->name);
+}
+
+static int kernfs_sd_compare(const struct kernfs_node *left,
+			     const struct kernfs_node *right)
+{
+	return kernfs_name_compare(left->hash, left->name, left->ns, right);
+}
+
+/**
+ *	kernfs_link_sibling - link kernfs_node into sibling rbtree
+ *	@kn: kernfs_node of interest
+ *
+ *	Link @kn into its sibling rbtree which starts from
+ *	@kn->parent->dir.children.
+ *
+ *	Locking:
+ *	mutex_lock(kernfs_mutex)
+ *
+ *	RETURNS:
+ *	0 on susccess -EEXIST on failure.
+ */
+static int kernfs_link_sibling(struct kernfs_node *kn)
+{
+	struct rb_node **node = &kn->parent->dir.children.rb_node;
+	struct rb_node *parent = NULL;
+
+	if (kernfs_type(kn) == KERNFS_DIR)
+		kn->parent->dir.subdirs++;
+
+	while (*node) {
+		struct kernfs_node *pos;
+		int result;
+
+		pos = rb_to_kn(*node);
+		parent = *node;
+		result = kernfs_sd_compare(kn, pos);
+		if (result < 0)
+			node = &pos->rb.rb_left;
+		else if (result > 0)
+			node = &pos->rb.rb_right;
+		else
+			return -EEXIST;
+	}
+	/* add new node and rebalance the tree */
+	rb_link_node(&kn->rb, parent, node);
+	rb_insert_color(&kn->rb, &kn->parent->dir.children);
+	return 0;
+}
+
+/**
+ *	kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree
+ *	@kn: kernfs_node of interest
+ *
+ *	Unlink @kn from its sibling rbtree which starts from
+ *	kn->parent->dir.children.
+ *
+ *	Locking:
+ *	mutex_lock(kernfs_mutex)
+ */
+static void kernfs_unlink_sibling(struct kernfs_node *kn)
+{
+	if (kernfs_type(kn) == KERNFS_DIR)
+		kn->parent->dir.subdirs--;
+
+	rb_erase(&kn->rb, &kn->parent->dir.children);
+}
+
+/**
+ *	kernfs_get_active - get an active reference to kernfs_node
+ *	@kn: kernfs_node to get an active reference to
+ *
+ *	Get an active reference of @kn.  This function is noop if @kn
+ *	is NULL.
+ *
+ *	RETURNS:
+ *	Pointer to @kn on success, NULL on failure.
+ */
+struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
+{
+	if (unlikely(!kn))
+		return NULL;
+
+	if (!atomic_inc_unless_negative(&kn->active))
+		return NULL;
+
+	if (kn->flags & KERNFS_LOCKDEP)
+		rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
+	return kn;
+}
+
+/**
+ *	kernfs_put_active - put an active reference to kernfs_node
+ *	@kn: kernfs_node to put an active reference to
+ *
+ *	Put an active reference to @kn.  This function is noop if @kn
+ *	is NULL.
+ */
+void kernfs_put_active(struct kernfs_node *kn)
+{
+	int v;
+
+	if (unlikely(!kn))
+		return;
+
+	if (kn->flags & KERNFS_LOCKDEP)
+		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+	v = atomic_dec_return(&kn->active);
+	if (likely(v != KN_DEACTIVATED_BIAS))
+		return;
+
+	/*
+	 * atomic_dec_return() is a mb(), we'll always see the updated
+	 * kn->u.completion.
+	 */
+	complete(kn->u.completion);
+}
+
+/**
+ *	kernfs_deactivate - deactivate kernfs_node
+ *	@kn: kernfs_node to deactivate
+ *
+ *	Deny new active references and drain existing ones.
+ */
+static void kernfs_deactivate(struct kernfs_node *kn)
+{
+	DECLARE_COMPLETION_ONSTACK(wait);
+	int v;
+
+	BUG_ON(!(kn->flags & KERNFS_REMOVED));
+
+	if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
+		return;
+
+	kn->u.completion = (void *)&wait;
+
+	rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
+	/* atomic_add_return() is a mb(), put_active() will always see
+	 * the updated kn->u.completion.
+	 */
+	v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
+
+	if (v != KN_DEACTIVATED_BIAS) {
+		lock_contended(&kn->dep_map, _RET_IP_);
+		wait_for_completion(&wait);
+	}
+
+	lock_acquired(&kn->dep_map, _RET_IP_);
+	rwsem_release(&kn->dep_map, 1, _RET_IP_);
+}
+
+/**
+ * kernfs_get - get a reference count on a kernfs_node
+ * @kn: the target kernfs_node
+ */
+void kernfs_get(struct kernfs_node *kn)
+{
+	if (kn) {
+		WARN_ON(!atomic_read(&kn->count));
+		atomic_inc(&kn->count);
+	}
+}
+EXPORT_SYMBOL_GPL(kernfs_get);
+
+/**
+ * kernfs_put - put a reference count on a kernfs_node
+ * @kn: the target kernfs_node
+ *
+ * Put a reference count of @kn and destroy it if it reached zero.
+ */
+void kernfs_put(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	struct kernfs_root *root;
+
+	if (!kn || !atomic_dec_and_test(&kn->count))
+		return;
+	root = kernfs_root(kn);
+ repeat:
+	/* Moving/renaming is always done while holding reference.
+	 * kn->parent won't change beneath us.
+	 */
+	parent = kn->parent;
+
+	WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n",
+	     parent ? parent->name : "", kn->name);
+
+	if (kernfs_type(kn) == KERNFS_LINK)
+		kernfs_put(kn->symlink.target_kn);
+	if (!(kn->flags & KERNFS_STATIC_NAME))
+		kfree(kn->name);
+	if (kn->iattr) {
+		if (kn->iattr->ia_secdata)
+			security_release_secctx(kn->iattr->ia_secdata,
+						kn->iattr->ia_secdata_len);
+		simple_xattrs_free(&kn->iattr->xattrs);
+	}
+	kfree(kn->iattr);
+	ida_simple_remove(&root->ino_ida, kn->ino);
+	kmem_cache_free(kernfs_node_cache, kn);
+
+	kn = parent;
+	if (kn) {
+		if (atomic_dec_and_test(&kn->count))
+			goto repeat;
+	} else {
+		/* just released the root kn, free @root too */
+		ida_destroy(&root->ino_ida);
+		kfree(root);
+	}
+}
+EXPORT_SYMBOL_GPL(kernfs_put);
+
+static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct kernfs_node *kn;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	/* Always perform fresh lookup for negatives */
+	if (!dentry->d_inode)
+		goto out_bad_unlocked;
+
+	kn = dentry->d_fsdata;
+	mutex_lock(&kernfs_mutex);
+
+	/* The kernfs node has been deleted */
+	if (kn->flags & KERNFS_REMOVED)
+		goto out_bad;
+
+	/* The kernfs node has been moved? */
+	if (dentry->d_parent->d_fsdata != kn->parent)
+		goto out_bad;
+
+	/* The kernfs node has been renamed */
+	if (strcmp(dentry->d_name.name, kn->name) != 0)
+		goto out_bad;
+
+	/* The kernfs node has been moved to a different namespace */
+	if (kn->parent && kernfs_ns_enabled(kn->parent) &&
+	    kernfs_info(dentry->d_sb)->ns != kn->ns)
+		goto out_bad;
+
+	mutex_unlock(&kernfs_mutex);
+out_valid:
+	return 1;
+out_bad:
+	mutex_unlock(&kernfs_mutex);
+out_bad_unlocked:
+	/*
+	 * @dentry doesn't match the underlying kernfs node, drop the
+	 * dentry and force lookup.  If we have submounts we must allow the
+	 * vfs caches to lie about the state of the filesystem to prevent
+	 * leaks and other nasty things, so use check_submounts_and_drop()
+	 * instead of d_drop().
+	 */
+	if (check_submounts_and_drop(dentry) != 0)
+		goto out_valid;
+
+	return 0;
+}
+
+static void kernfs_dop_release(struct dentry *dentry)
+{
+	kernfs_put(dentry->d_fsdata);
+}
+
+const struct dentry_operations kernfs_dops = {
+	.d_revalidate	= kernfs_dop_revalidate,
+	.d_release	= kernfs_dop_release,
+};
+
+static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
+					     const char *name, umode_t mode,
+					     unsigned flags)
+{
+	char *dup_name = NULL;
+	struct kernfs_node *kn;
+	int ret;
+
+	if (!(flags & KERNFS_STATIC_NAME)) {
+		name = dup_name = kstrdup(name, GFP_KERNEL);
+		if (!name)
+			return NULL;
+	}
+
+	kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL);
+	if (!kn)
+		goto err_out1;
+
+	ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
+	if (ret < 0)
+		goto err_out2;
+	kn->ino = ret;
+
+	atomic_set(&kn->count, 1);
+	atomic_set(&kn->active, 0);
+
+	kn->name = name;
+	kn->mode = mode;
+	kn->flags = flags | KERNFS_REMOVED;
+
+	return kn;
+
+ err_out2:
+	kmem_cache_free(kernfs_node_cache, kn);
+ err_out1:
+	kfree(dup_name);
+	return NULL;
+}
+
+struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
+				    const char *name, umode_t mode,
+				    unsigned flags)
+{
+	struct kernfs_node *kn;
+
+	kn = __kernfs_new_node(kernfs_root(parent), name, mode, flags);
+	if (kn) {
+		kernfs_get(parent);
+		kn->parent = parent;
+	}
+	return kn;
+}
+
+/**
+ *	kernfs_addrm_start - prepare for kernfs_node add/remove
+ *	@acxt: pointer to kernfs_addrm_cxt to be used
+ *
+ *	This function is called when the caller is about to add or remove
+ *	kernfs_node.  This function acquires kernfs_mutex.  @acxt is used
+ *	to keep and pass context to other addrm functions.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).  kernfs_mutex is locked on
+ *	return.
+ */
+void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt)
+	__acquires(kernfs_mutex)
+{
+	memset(acxt, 0, sizeof(*acxt));
+
+	mutex_lock(&kernfs_mutex);
+}
+
+/**
+ *	kernfs_add_one - add kernfs_node to parent without warning
+ *	@acxt: addrm context to use
+ *	@kn: kernfs_node to be added
+ *
+ *	The caller must already have initialized @kn->parent.  This
+ *	function increments nlink of the parent's inode if @kn is a
+ *	directory and link into the children list of the parent.
+ *
+ *	This function should be called between calls to
+ *	kernfs_addrm_start() and kernfs_addrm_finish() and should be passed
+ *	the same @acxt as passed to kernfs_addrm_start().
+ *
+ *	LOCKING:
+ *	Determined by kernfs_addrm_start().
+ *
+ *	RETURNS:
+ *	0 on success, -EEXIST if entry with the given name already
+ *	exists.
+ */
+int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
+{
+	struct kernfs_node *parent = kn->parent;
+	bool has_ns = kernfs_ns_enabled(parent);
+	struct kernfs_iattrs *ps_iattr;
+	int ret;
+
+	if (has_ns != (bool)kn->ns) {
+		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+		     has_ns ? "required" : "invalid", parent->name, kn->name);
+		return -EINVAL;
+	}
+
+	if (kernfs_type(parent) != KERNFS_DIR)
+		return -EINVAL;
+
+	if (parent->flags & KERNFS_REMOVED)
+		return -ENOENT;
+
+	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+
+	ret = kernfs_link_sibling(kn);
+	if (ret)
+		return ret;
+
+	/* Update timestamps on the parent */
+	ps_iattr = parent->iattr;
+	if (ps_iattr) {
+		struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+	}
+
+	/* Mark the entry added into directory tree */
+	kn->flags &= ~KERNFS_REMOVED;
+
+	return 0;
+}
+
+/**
+ *	kernfs_remove_one - remove kernfs_node from parent
+ *	@acxt: addrm context to use
+ *	@kn: kernfs_node to be removed
+ *
+ *	Mark @kn removed and drop nlink of parent inode if @kn is a
+ *	directory.  @kn is unlinked from the children list.
+ *
+ *	This function should be called between calls to
+ *	kernfs_addrm_start() and kernfs_addrm_finish() and should be
+ *	passed the same @acxt as passed to kernfs_addrm_start().
+ *
+ *	LOCKING:
+ *	Determined by kernfs_addrm_start().
+ */
+static void kernfs_remove_one(struct kernfs_addrm_cxt *acxt,
+			      struct kernfs_node *kn)
+{
+	struct kernfs_iattrs *ps_iattr;
+
+	/*
+	 * Removal can be called multiple times on the same node.  Only the
+	 * first invocation is effective and puts the base ref.
+	 */
+	if (kn->flags & KERNFS_REMOVED)
+		return;
+
+	if (kn->parent) {
+		kernfs_unlink_sibling(kn);
+
+		/* Update timestamps on the parent */
+		ps_iattr = kn->parent->iattr;
+		if (ps_iattr) {
+			ps_iattr->ia_iattr.ia_ctime = CURRENT_TIME;
+			ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
+		}
+	}
+
+	kn->flags |= KERNFS_REMOVED;
+	kn->u.removed_list = acxt->removed;
+	acxt->removed = kn;
+}
+
+/**
+ *	kernfs_addrm_finish - finish up kernfs_node add/remove
+ *	@acxt: addrm context to finish up
+ *
+ *	Finish up kernfs_node add/remove.  Resources acquired by
+ *	kernfs_addrm_start() are released and removed kernfs_nodes are
+ *	cleaned up.
+ *
+ *	LOCKING:
+ *	kernfs_mutex is released.
+ */
+void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt)
+	__releases(kernfs_mutex)
+{
+	/* release resources acquired by kernfs_addrm_start() */
+	mutex_unlock(&kernfs_mutex);
+
+	/* kill removed kernfs_nodes */
+	while (acxt->removed) {
+		struct kernfs_node *kn = acxt->removed;
+
+		acxt->removed = kn->u.removed_list;
+
+		kernfs_deactivate(kn);
+		kernfs_unmap_bin_file(kn);
+		kernfs_put(kn);
+	}
+}
+
+/**
+ * kernfs_find_ns - find kernfs_node with the given name
+ * @parent: kernfs_node to search under
+ * @name: name to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with name @name under @parent.  Returns pointer to
+ * the found kernfs_node on success, %NULL on failure.
+ */
+static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
+					  const unsigned char *name,
+					  const void *ns)
+{
+	struct rb_node *node = parent->dir.children.rb_node;
+	bool has_ns = kernfs_ns_enabled(parent);
+	unsigned int hash;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	if (has_ns != (bool)ns) {
+		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+		     has_ns ? "required" : "invalid", parent->name, name);
+		return NULL;
+	}
+
+	hash = kernfs_name_hash(name, ns);
+	while (node) {
+		struct kernfs_node *kn;
+		int result;
+
+		kn = rb_to_kn(node);
+		result = kernfs_name_compare(hash, name, ns, kn);
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return kn;
+	}
+	return NULL;
+}
+
+/**
+ * kernfs_find_and_get_ns - find and get kernfs_node with the given name
+ * @parent: kernfs_node to search under
+ * @name: name to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with name @name under @parent and get a reference
+ * if found.  This function may sleep and returns pointer to the found
+ * kernfs_node on success, %NULL on failure.
+ */
+struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
+					   const char *name, const void *ns)
+{
+	struct kernfs_node *kn;
+
+	mutex_lock(&kernfs_mutex);
+	kn = kernfs_find_ns(parent, name, ns);
+	kernfs_get(kn);
+	mutex_unlock(&kernfs_mutex);
+
+	return kn;
+}
+EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
+
+/**
+ * kernfs_create_root - create a new kernfs hierarchy
+ * @kdops: optional directory syscall operations for the hierarchy
+ * @priv: opaque data associated with the new directory
+ *
+ * Returns the root of the new hierarchy on success, ERR_PTR() value on
+ * failure.
+ */
+struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+{
+	struct kernfs_root *root;
+	struct kernfs_node *kn;
+
+	root = kzalloc(sizeof(*root), GFP_KERNEL);
+	if (!root)
+		return ERR_PTR(-ENOMEM);
+
+	ida_init(&root->ino_ida);
+
+	kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
+			       KERNFS_DIR);
+	if (!kn) {
+		ida_destroy(&root->ino_ida);
+		kfree(root);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	kn->flags &= ~KERNFS_REMOVED;
+	kn->priv = priv;
+	kn->dir.root = root;
+
+	root->dir_ops = kdops;
+	root->kn = kn;
+
+	return root;
+}
+
+/**
+ * kernfs_destroy_root - destroy a kernfs hierarchy
+ * @root: root of the hierarchy to destroy
+ *
+ * Destroy the hierarchy anchored at @root by removing all existing
+ * directories and destroying @root.
+ */
+void kernfs_destroy_root(struct kernfs_root *root)
+{
+	kernfs_remove(root->kn);	/* will also free @root */
+}
+
+/**
+ * kernfs_create_dir_ns - create a directory
+ * @parent: parent in which to create a new directory
+ * @name: name of the new directory
+ * @mode: mode of the new directory
+ * @priv: opaque data associated with the new directory
+ * @ns: optional namespace tag of the directory
+ *
+ * Returns the created node on success, ERR_PTR() value on failure.
+ */
+struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
+					 const char *name, umode_t mode,
+					 void *priv, const void *ns)
+{
+	struct kernfs_addrm_cxt acxt;
+	struct kernfs_node *kn;
+	int rc;
+
+	/* allocate */
+	kn = kernfs_new_node(parent, name, mode | S_IFDIR, KERNFS_DIR);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	kn->dir.root = parent->dir.root;
+	kn->ns = ns;
+	kn->priv = priv;
+
+	/* link in */
+	kernfs_addrm_start(&acxt);
+	rc = kernfs_add_one(&acxt, kn);
+	kernfs_addrm_finish(&acxt);
+
+	if (!rc)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(rc);
+}
+
+static struct dentry *kernfs_iop_lookup(struct inode *dir,
+					struct dentry *dentry,
+					unsigned int flags)
+{
+	struct dentry *ret;
+	struct kernfs_node *parent = dentry->d_parent->d_fsdata;
+	struct kernfs_node *kn;
+	struct inode *inode;
+	const void *ns = NULL;
+
+	mutex_lock(&kernfs_mutex);
+
+	if (kernfs_ns_enabled(parent))
+		ns = kernfs_info(dir->i_sb)->ns;
+
+	kn = kernfs_find_ns(parent, dentry->d_name.name, ns);
+
+	/* no such entry */
+	if (!kn) {
+		ret = NULL;
+		goto out_unlock;
+	}
+	kernfs_get(kn);
+	dentry->d_fsdata = kn;
+
+	/* attach dentry and inode */
+	inode = kernfs_get_inode(dir->i_sb, kn);
+	if (!inode) {
+		ret = ERR_PTR(-ENOMEM);
+		goto out_unlock;
+	}
+
+	/* instantiate and hash dentry */
+	ret = d_materialise_unique(dentry, inode);
+ out_unlock:
+	mutex_unlock(&kernfs_mutex);
+	return ret;
+}
+
+static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
+			    umode_t mode)
+{
+	struct kernfs_node *parent = dir->i_private;
+	struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+
+	if (!kdops || !kdops->mkdir)
+		return -EPERM;
+
+	return kdops->mkdir(parent, dentry->d_name.name, mode);
+}
+
+static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	struct kernfs_node *kn  = dentry->d_fsdata;
+	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+
+	if (!kdops || !kdops->rmdir)
+		return -EPERM;
+
+	return kdops->rmdir(kn);
+}
+
+static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry)
+{
+	struct kernfs_node *kn  = old_dentry->d_fsdata;
+	struct kernfs_node *new_parent = new_dir->i_private;
+	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+
+	if (!kdops || !kdops->rename)
+		return -EPERM;
+
+	return kdops->rename(kn, new_parent, new_dentry->d_name.name);
+}
+
+const struct inode_operations kernfs_dir_iops = {
+	.lookup		= kernfs_iop_lookup,
+	.permission	= kernfs_iop_permission,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.setxattr	= kernfs_iop_setxattr,
+	.removexattr	= kernfs_iop_removexattr,
+	.getxattr	= kernfs_iop_getxattr,
+	.listxattr	= kernfs_iop_listxattr,
+
+	.mkdir		= kernfs_iop_mkdir,
+	.rmdir		= kernfs_iop_rmdir,
+	.rename		= kernfs_iop_rename,
+};
+
+static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos)
+{
+	struct kernfs_node *last;
+
+	while (true) {
+		struct rb_node *rbn;
+
+		last = pos;
+
+		if (kernfs_type(pos) != KERNFS_DIR)
+			break;
+
+		rbn = rb_first(&pos->dir.children);
+		if (!rbn)
+			break;
+
+		pos = rb_to_kn(rbn);
+	}
+
+	return last;
+}
+
+/**
+ * kernfs_next_descendant_post - find the next descendant for post-order walk
+ * @pos: the current position (%NULL to initiate traversal)
+ * @root: kernfs_node whose descendants to walk
+ *
+ * Find the next descendant to visit for post-order traversal of @root's
+ * descendants.  @root is included in the iteration and the last node to be
+ * visited.
+ */
+static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
+						       struct kernfs_node *root)
+{
+	struct rb_node *rbn;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	/* if first iteration, visit leftmost descendant which may be root */
+	if (!pos)
+		return kernfs_leftmost_descendant(root);
+
+	/* if we visited @root, we're done */
+	if (pos == root)
+		return NULL;
+
+	/* if there's an unvisited sibling, visit its leftmost descendant */
+	rbn = rb_next(&pos->rb);
+	if (rbn)
+		return kernfs_leftmost_descendant(rb_to_kn(rbn));
+
+	/* no sibling left, visit parent */
+	return pos->parent;
+}
+
+static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
+			    struct kernfs_node *kn)
+{
+	struct kernfs_node *pos, *next;
+
+	if (!kn)
+		return;
+
+	pr_debug("kernfs %s: removing\n", kn->name);
+
+	next = NULL;
+	do {
+		pos = next;
+		next = kernfs_next_descendant_post(pos, kn);
+		if (pos)
+			kernfs_remove_one(acxt, pos);
+	} while (next);
+}
+
+/**
+ * kernfs_remove - remove a kernfs_node recursively
+ * @kn: the kernfs_node to remove
+ *
+ * Remove @kn along with all its subdirectories and files.
+ */
+void kernfs_remove(struct kernfs_node *kn)
+{
+	struct kernfs_addrm_cxt acxt;
+
+	kernfs_addrm_start(&acxt);
+	__kernfs_remove(&acxt, kn);
+	kernfs_addrm_finish(&acxt);
+}
+
+/**
+ * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it
+ * @parent: parent of the target
+ * @name: name of the kernfs_node to remove
+ * @ns: namespace tag of the kernfs_node to remove
+ *
+ * Look for the kernfs_node with @name and @ns under @parent and remove it.
+ * Returns 0 on success, -ENOENT if such entry doesn't exist.
+ */
+int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
+			     const void *ns)
+{
+	struct kernfs_addrm_cxt acxt;
+	struct kernfs_node *kn;
+
+	if (!parent) {
+		WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n",
+			name);
+		return -ENOENT;
+	}
+
+	kernfs_addrm_start(&acxt);
+
+	kn = kernfs_find_ns(parent, name, ns);
+	if (kn)
+		__kernfs_remove(&acxt, kn);
+
+	kernfs_addrm_finish(&acxt);
+
+	if (kn)
+		return 0;
+	else
+		return -ENOENT;
+}
+
+/**
+ * kernfs_rename_ns - move and rename a kernfs_node
+ * @kn: target node
+ * @new_parent: new parent to put @sd under
+ * @new_name: new name
+ * @new_ns: new namespace tag
+ */
+int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		     const char *new_name, const void *new_ns)
+{
+	int error;
+
+	mutex_lock(&kernfs_mutex);
+
+	error = -ENOENT;
+	if ((kn->flags | new_parent->flags) & KERNFS_REMOVED)
+		goto out;
+
+	error = 0;
+	if ((kn->parent == new_parent) && (kn->ns == new_ns) &&
+	    (strcmp(kn->name, new_name) == 0))
+		goto out;	/* nothing to rename */
+
+	error = -EEXIST;
+	if (kernfs_find_ns(new_parent, new_name, new_ns))
+		goto out;
+
+	/* rename kernfs_node */
+	if (strcmp(kn->name, new_name) != 0) {
+		error = -ENOMEM;
+		new_name = kstrdup(new_name, GFP_KERNEL);
+		if (!new_name)
+			goto out;
+
+		if (kn->flags & KERNFS_STATIC_NAME)
+			kn->flags &= ~KERNFS_STATIC_NAME;
+		else
+			kfree(kn->name);
+
+		kn->name = new_name;
+	}
+
+	/*
+	 * Move to the appropriate place in the appropriate directories rbtree.
+	 */
+	kernfs_unlink_sibling(kn);
+	kernfs_get(new_parent);
+	kernfs_put(kn->parent);
+	kn->ns = new_ns;
+	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+	kn->parent = new_parent;
+	kernfs_link_sibling(kn);
+
+	error = 0;
+ out:
+	mutex_unlock(&kernfs_mutex);
+	return error;
+}
+
+/* Relationship between s_mode and the DT_xxx types */
+static inline unsigned char dt_type(struct kernfs_node *kn)
+{
+	return (kn->mode >> 12) & 15;
+}
+
+static int kernfs_dir_fop_release(struct inode *inode, struct file *filp)
+{
+	kernfs_put(filp->private_data);
+	return 0;
+}
+
+static struct kernfs_node *kernfs_dir_pos(const void *ns,
+	struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
+{
+	if (pos) {
+		int valid = !(pos->flags & KERNFS_REMOVED) &&
+			pos->parent == parent && hash == pos->hash;
+		kernfs_put(pos);
+		if (!valid)
+			pos = NULL;
+	}
+	if (!pos && (hash > 1) && (hash < INT_MAX)) {
+		struct rb_node *node = parent->dir.children.rb_node;
+		while (node) {
+			pos = rb_to_kn(node);
+
+			if (hash < pos->hash)
+				node = node->rb_left;
+			else if (hash > pos->hash)
+				node = node->rb_right;
+			else
+				break;
+		}
+	}
+	/* Skip over entries in the wrong namespace */
+	while (pos && pos->ns != ns) {
+		struct rb_node *node = rb_next(&pos->rb);
+		if (!node)
+			pos = NULL;
+		else
+			pos = rb_to_kn(node);
+	}
+	return pos;
+}
+
+static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
+	struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos)
+{
+	pos = kernfs_dir_pos(ns, parent, ino, pos);
+	if (pos)
+		do {
+			struct rb_node *node = rb_next(&pos->rb);
+			if (!node)
+				pos = NULL;
+			else
+				pos = rb_to_kn(node);
+		} while (pos && pos->ns != ns);
+	return pos;
+}
+
+static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct dentry *dentry = file->f_path.dentry;
+	struct kernfs_node *parent = dentry->d_fsdata;
+	struct kernfs_node *pos = file->private_data;
+	const void *ns = NULL;
+
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+	mutex_lock(&kernfs_mutex);
+
+	if (kernfs_ns_enabled(parent))
+		ns = kernfs_info(dentry->d_sb)->ns;
+
+	for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos);
+	     pos;
+	     pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) {
+		const char *name = pos->name;
+		unsigned int type = dt_type(pos);
+		int len = strlen(name);
+		ino_t ino = pos->ino;
+
+		ctx->pos = pos->hash;
+		file->private_data = pos;
+		kernfs_get(pos);
+
+		mutex_unlock(&kernfs_mutex);
+		if (!dir_emit(ctx, name, len, ino, type))
+			return 0;
+		mutex_lock(&kernfs_mutex);
+	}
+	mutex_unlock(&kernfs_mutex);
+	file->private_data = NULL;
+	ctx->pos = INT_MAX;
+	return 0;
+}
+
+static loff_t kernfs_dir_fop_llseek(struct file *file, loff_t offset,
+				    int whence)
+{
+	struct inode *inode = file_inode(file);
+	loff_t ret;
+
+	mutex_lock(&inode->i_mutex);
+	ret = generic_file_llseek(file, offset, whence);
+	mutex_unlock(&inode->i_mutex);
+
+	return ret;
+}
+
+const struct file_operations kernfs_dir_fops = {
+	.read		= generic_read_dir,
+	.iterate	= kernfs_fop_readdir,
+	.release	= kernfs_dir_fop_release,
+	.llseek		= kernfs_dir_fop_llseek,
+};

fs/kernfs/file.c

@@ -0,0 +1,867 @@
+/*
+ * fs/kernfs/file.c - kernfs file implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/pagemap.h>
+#include <linux/sched.h>
+
+#include "kernfs-internal.h"
+
+/*
+ * There's one kernfs_open_file for each open file and one kernfs_open_node
+ * for each kernfs_node with one or more open files.
+ *
+ * kernfs_node->attr.open points to kernfs_open_node.  attr.open is
+ * protected by kernfs_open_node_lock.
+ *
+ * filp->private_data points to seq_file whose ->private points to
+ * kernfs_open_file.  kernfs_open_files are chained at
+ * kernfs_open_node->files, which is protected by kernfs_open_file_mutex.
+ */
+static DEFINE_SPINLOCK(kernfs_open_node_lock);
+static DEFINE_MUTEX(kernfs_open_file_mutex);
+
+struct kernfs_open_node {
+	atomic_t		refcnt;
+	atomic_t		event;
+	wait_queue_head_t	poll;
+	struct list_head	files; /* goes through kernfs_open_file.list */
+};
+
+static struct kernfs_open_file *kernfs_of(struct file *file)
+{
+	return ((struct seq_file *)file->private_data)->private;
+}
+
+/*
+ * Determine the kernfs_ops for the given kernfs_node.  This function must
+ * be called while holding an active reference.
+ */
+static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn)
+{
+	if (kn->flags & KERNFS_LOCKDEP)
+		lockdep_assert_held(kn);
+	return kn->attr.ops;
+}
+
+/*
+ * As kernfs_seq_stop() is also called after kernfs_seq_start() or
+ * kernfs_seq_next() failure, it needs to distinguish whether it's stopping
+ * a seq_file iteration which is fully initialized with an active reference
+ * or an aborted kernfs_seq_start() due to get_active failure.  The
+ * position pointer is the only context for each seq_file iteration and
+ * thus the stop condition should be encoded in it.  As the return value is
+ * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable
+ * choice to indicate get_active failure.
+ *
+ * Unfortunately, this is complicated due to the optional custom seq_file
+ * operations which may return ERR_PTR(-ENODEV) too.  kernfs_seq_stop()
+ * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or
+ * custom seq_file operations and thus can't decide whether put_active
+ * should be performed or not only on ERR_PTR(-ENODEV).
+ *
+ * This is worked around by factoring out the custom seq_stop() and
+ * put_active part into kernfs_seq_stop_active(), skipping it from
+ * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after
+ * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures
+ * that kernfs_seq_stop_active() is skipped only after get_active failure.
+ */
+static void kernfs_seq_stop_active(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+	if (ops->seq_stop)
+		ops->seq_stop(sf, v);
+	kernfs_put_active(of->kn);
+}
+
+static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops;
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn))
+		return ERR_PTR(-ENODEV);
+
+	ops = kernfs_ops(of->kn);
+	if (ops->seq_start) {
+		void *next = ops->seq_start(sf, ppos);
+		/* see the comment above kernfs_seq_stop_active() */
+		if (next == ERR_PTR(-ENODEV))
+			kernfs_seq_stop_active(sf, next);
+		return next;
+	} else {
+		/*
+		 * The same behavior and code as single_open().  Returns
+		 * !NULL if pos is at the beginning; otherwise, NULL.
+		 */
+		return NULL + !*ppos;
+	}
+}
+
+static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos)
+{
+	struct kernfs_open_file *of = sf->private;
+	const struct kernfs_ops *ops = kernfs_ops(of->kn);
+
+	if (ops->seq_next) {
+		void *next = ops->seq_next(sf, v, ppos);
+		/* see the comment above kernfs_seq_stop_active() */
+		if (next == ERR_PTR(-ENODEV))
+			kernfs_seq_stop_active(sf, next);
+		return next;
+	} else {
+		/*
+		 * The same behavior and code as single_open(), always
+		 * terminate after the initial read.
+		 */
+		++*ppos;
+		return NULL;
+	}
+}
+
+static void kernfs_seq_stop(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+
+	if (v != ERR_PTR(-ENODEV))
+		kernfs_seq_stop_active(sf, v);
+	mutex_unlock(&of->mutex);
+}
+
+static int kernfs_seq_show(struct seq_file *sf, void *v)
+{
+	struct kernfs_open_file *of = sf->private;
+
+	of->event = atomic_read(&of->kn->attr.open->event);
+
+	return of->kn->attr.ops->seq_show(sf, v);
+}
+
+static const struct seq_operations kernfs_seq_ops = {
+	.start = kernfs_seq_start,
+	.next = kernfs_seq_next,
+	.stop = kernfs_seq_stop,
+	.show = kernfs_seq_show,
+};
+
+/*
+ * As reading a bin file can have side-effects, the exact offset and bytes
+ * specified in read(2) call should be passed to the read callback making
+ * it difficult to use seq_file.  Implement simplistic custom buffering for
+ * bin files.
+ */
+static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
+				       char __user *user_buf, size_t count,
+				       loff_t *ppos)
+{
+	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+	const struct kernfs_ops *ops;
+	char *buf;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		len = -ENODEV;
+		mutex_unlock(&of->mutex);
+		goto out_free;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->read)
+		len = ops->read(of, buf, len, *ppos);
+	else
+		len = -EINVAL;
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+
+	if (len < 0)
+		goto out_free;
+
+	if (copy_to_user(user_buf, buf, len)) {
+		len = -EFAULT;
+		goto out_free;
+	}
+
+	*ppos += len;
+
+ out_free:
+	kfree(buf);
+	return len;
+}
+
+/**
+ * kernfs_fop_read - kernfs vfs read callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ */
+static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
+			       size_t count, loff_t *ppos)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+
+	if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
+		return seq_read(file, user_buf, count, ppos);
+	else
+		return kernfs_file_direct_read(of, user_buf, count, ppos);
+}
+
+/**
+ * kernfs_fop_write - kernfs vfs write callback
+ * @file: file pointer
+ * @user_buf: data to write
+ * @count: number of bytes
+ * @ppos: starting offset
+ *
+ * Copy data in from userland and pass it to the matching kernfs write
+ * operation.
+ *
+ * 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 kernfs_fop_write(struct file *file, const char __user *user_buf,
+				size_t count, loff_t *ppos)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+	const struct kernfs_ops *ops;
+	char *buf;
+
+	buf = kmalloc(len + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, user_buf, len)) {
+		len = -EFAULT;
+		goto out_free;
+	}
+	buf[len] = '\0';	/* guarantee string termination */
+
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		len = -ENODEV;
+		goto out_free;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->write)
+		len = ops->write(of, buf, len, *ppos);
+	else
+		len = -EINVAL;
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+
+	if (len > 0)
+		*ppos += len;
+out_free:
+	kfree(buf);
+	return len;
+}
+
+static void kernfs_vma_open(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+
+	if (!of->vm_ops)
+		return;
+
+	if (!kernfs_get_active(of->kn))
+		return;
+
+	if (of->vm_ops->open)
+		of->vm_ops->open(vma);
+
+	kernfs_put_active(of->kn);
+}
+
+static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return VM_FAULT_SIGBUS;
+
+	if (!kernfs_get_active(of->kn))
+		return VM_FAULT_SIGBUS;
+
+	ret = VM_FAULT_SIGBUS;
+	if (of->vm_ops->fault)
+		ret = of->vm_ops->fault(vma, vmf);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
+				   struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return VM_FAULT_SIGBUS;
+
+	if (!kernfs_get_active(of->kn))
+		return VM_FAULT_SIGBUS;
+
+	ret = 0;
+	if (of->vm_ops->page_mkwrite)
+		ret = of->vm_ops->page_mkwrite(vma, vmf);
+	else
+		file_update_time(file);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
+			     void *buf, int len, int write)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return -EINVAL;
+
+	if (!kernfs_get_active(of->kn))
+		return -EINVAL;
+
+	ret = -EINVAL;
+	if (of->vm_ops->access)
+		ret = of->vm_ops->access(vma, addr, buf, len, write);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+#ifdef CONFIG_NUMA
+static int kernfs_vma_set_policy(struct vm_area_struct *vma,
+				 struct mempolicy *new)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return 0;
+
+	if (!kernfs_get_active(of->kn))
+		return -EINVAL;
+
+	ret = 0;
+	if (of->vm_ops->set_policy)
+		ret = of->vm_ops->set_policy(vma, new);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+
+static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
+					       unsigned long addr)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	struct mempolicy *pol;
+
+	if (!of->vm_ops)
+		return vma->vm_policy;
+
+	if (!kernfs_get_active(of->kn))
+		return vma->vm_policy;
+
+	pol = vma->vm_policy;
+	if (of->vm_ops->get_policy)
+		pol = of->vm_ops->get_policy(vma, addr);
+
+	kernfs_put_active(of->kn);
+	return pol;
+}
+
+static int kernfs_vma_migrate(struct vm_area_struct *vma,
+			      const nodemask_t *from, const nodemask_t *to,
+			      unsigned long flags)
+{
+	struct file *file = vma->vm_file;
+	struct kernfs_open_file *of = kernfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return 0;
+
+	if (!kernfs_get_active(of->kn))
+		return 0;
+
+	ret = 0;
+	if (of->vm_ops->migrate)
+		ret = of->vm_ops->migrate(vma, from, to, flags);
+
+	kernfs_put_active(of->kn);
+	return ret;
+}
+#endif
+
+static const struct vm_operations_struct kernfs_vm_ops = {
+	.open		= kernfs_vma_open,
+	.fault		= kernfs_vma_fault,
+	.page_mkwrite	= kernfs_vma_page_mkwrite,
+	.access		= kernfs_vma_access,
+#ifdef CONFIG_NUMA
+	.set_policy	= kernfs_vma_set_policy,
+	.get_policy	= kernfs_vma_get_policy,
+	.migrate	= kernfs_vma_migrate,
+#endif
+};
+
+static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	int rc;
+
+	/*
+	 * mmap path and of->mutex are prone to triggering spurious lockdep
+	 * warnings and we don't want to add spurious locking dependency
+	 * between the two.  Check whether mmap is actually implemented
+	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
+	 * comment in kernfs_file_open() for more details.
+	 */
+	if (!(of->kn->flags & KERNFS_HAS_MMAP))
+		return -ENODEV;
+
+	mutex_lock(&of->mutex);
+
+	rc = -ENODEV;
+	if (!kernfs_get_active(of->kn))
+		goto out_unlock;
+
+	ops = kernfs_ops(of->kn);
+	rc = ops->mmap(of, vma);
+
+	/*
+	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
+	 * to satisfy versions of X which crash if the mmap fails: that
+	 * substitutes a new vm_file, and we don't then want bin_vm_ops.
+	 */
+	if (vma->vm_file != file)
+		goto out_put;
+
+	rc = -EINVAL;
+	if (of->mmapped && of->vm_ops != vma->vm_ops)
+		goto out_put;
+
+	/*
+	 * It is not possible to successfully wrap close.
+	 * So error if someone is trying to use close.
+	 */
+	rc = -EINVAL;
+	if (vma->vm_ops && vma->vm_ops->close)
+		goto out_put;
+
+	rc = 0;
+	of->mmapped = 1;
+	of->vm_ops = vma->vm_ops;
+	vma->vm_ops = &kernfs_vm_ops;
+out_put:
+	kernfs_put_active(of->kn);
+out_unlock:
+	mutex_unlock(&of->mutex);
+
+	return rc;
+}
+
+/**
+ *	kernfs_get_open_node - get or create kernfs_open_node
+ *	@kn: target kernfs_node
+ *	@of: kernfs_open_file for this instance of open
+ *
+ *	If @kn->attr.open exists, increment its reference count; otherwise,
+ *	create one.  @of is chained to the files list.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	0 on success, -errno on failure.
+ */
+static int kernfs_get_open_node(struct kernfs_node *kn,
+				struct kernfs_open_file *of)
+{
+	struct kernfs_open_node *on, *new_on = NULL;
+
+ retry:
+	mutex_lock(&kernfs_open_file_mutex);
+	spin_lock_irq(&kernfs_open_node_lock);
+
+	if (!kn->attr.open && new_on) {
+		kn->attr.open = new_on;
+		new_on = NULL;
+	}
+
+	on = kn->attr.open;
+	if (on) {
+		atomic_inc(&on->refcnt);
+		list_add_tail(&of->list, &on->files);
+	}
+
+	spin_unlock_irq(&kernfs_open_node_lock);
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	if (on) {
+		kfree(new_on);
+		return 0;
+	}
+
+	/* not there, initialize a new one and retry */
+	new_on = kmalloc(sizeof(*new_on), GFP_KERNEL);
+	if (!new_on)
+		return -ENOMEM;
+
+	atomic_set(&new_on->refcnt, 0);
+	atomic_set(&new_on->event, 1);
+	init_waitqueue_head(&new_on->poll);
+	INIT_LIST_HEAD(&new_on->files);
+	goto retry;
+}
+
+/**
+ *	kernfs_put_open_node - put kernfs_open_node
+ *	@kn: target kernfs_nodet
+ *	@of: associated kernfs_open_file
+ *
+ *	Put @kn->attr.open and unlink @of from the files list.  If
+ *	reference count reaches zero, disassociate and free it.
+ *
+ *	LOCKING:
+ *	None.
+ */
+static void kernfs_put_open_node(struct kernfs_node *kn,
+				 struct kernfs_open_file *of)
+{
+	struct kernfs_open_node *on = kn->attr.open;
+	unsigned long flags;
+
+	mutex_lock(&kernfs_open_file_mutex);
+	spin_lock_irqsave(&kernfs_open_node_lock, flags);
+
+	if (of)
+		list_del(&of->list);
+
+	if (atomic_dec_and_test(&on->refcnt))
+		kn->attr.open = NULL;
+	else
+		on = NULL;
+
+	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	kfree(on);
+}
+
+static int kernfs_fop_open(struct inode *inode, struct file *file)
+{
+	struct kernfs_node *kn = file->f_path.dentry->d_fsdata;
+	const struct kernfs_ops *ops;
+	struct kernfs_open_file *of;
+	bool has_read, has_write, has_mmap;
+	int error = -EACCES;
+
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	ops = kernfs_ops(kn);
+
+	has_read = ops->seq_show || ops->read || ops->mmap;
+	has_write = ops->write || ops->mmap;
+	has_mmap = ops->mmap;
+
+	/* check perms and supported operations */
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (!(inode->i_mode & S_IWUGO) || !has_write))
+		goto err_out;
+
+	if ((file->f_mode & FMODE_READ) &&
+	    (!(inode->i_mode & S_IRUGO) || !has_read))
+		goto err_out;
+
+	/* allocate a kernfs_open_file for the file */
+	error = -ENOMEM;
+	of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL);
+	if (!of)
+		goto err_out;
+
+	/*
+	 * The following is done to give a different lockdep key to
+	 * @of->mutex for files which implement mmap.  This is a rather
+	 * crude way to avoid false positive lockdep warning around
+	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
+	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
+	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
+	 * open file has a separate mutex, it's okay as long as those don't
+	 * happen on the same file.  At this point, we can't easily give
+	 * each file a separate locking class.  Let's differentiate on
+	 * whether the file has mmap or not for now.
+	 *
+	 * Both paths of the branch look the same.  They're supposed to
+	 * look that way and give @of->mutex different static lockdep keys.
+	 */
+	if (has_mmap)
+		mutex_init(&of->mutex);
+	else
+		mutex_init(&of->mutex);
+
+	of->kn = kn;
+	of->file = file;
+
+	/*
+	 * Always instantiate seq_file even if read access doesn't use
+	 * seq_file or is not requested.  This unifies private data access
+	 * and readable regular files are the vast majority anyway.
+	 */
+	if (ops->seq_show)
+		error = seq_open(file, &kernfs_seq_ops);
+	else
+		error = seq_open(file, NULL);
+	if (error)
+		goto err_free;
+
+	((struct seq_file *)file->private_data)->private = of;
+
+	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
+	if (file->f_mode & FMODE_WRITE)
+		file->f_mode |= FMODE_PWRITE;
+
+	/* make sure we have open node struct */
+	error = kernfs_get_open_node(kn, of);
+	if (error)
+		goto err_close;
+
+	/* open succeeded, put active references */
+	kernfs_put_active(kn);
+	return 0;
+
+err_close:
+	seq_release(inode, file);
+err_free:
+	kfree(of);
+err_out:
+	kernfs_put_active(kn);
+	return error;
+}
+
+static int kernfs_fop_release(struct inode *inode, struct file *filp)
+{
+	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+	struct kernfs_open_file *of = kernfs_of(filp);
+
+	kernfs_put_open_node(kn, of);
+	seq_release(inode, filp);
+	kfree(of);
+
+	return 0;
+}
+
+void kernfs_unmap_bin_file(struct kernfs_node *kn)
+{
+	struct kernfs_open_node *on;
+	struct kernfs_open_file *of;
+
+	if (!(kn->flags & KERNFS_HAS_MMAP))
+		return;
+
+	spin_lock_irq(&kernfs_open_node_lock);
+	on = kn->attr.open;
+	if (on)
+		atomic_inc(&on->refcnt);
+	spin_unlock_irq(&kernfs_open_node_lock);
+	if (!on)
+		return;
+
+	mutex_lock(&kernfs_open_file_mutex);
+	list_for_each_entry(of, &on->files, list) {
+		struct inode *inode = file_inode(of->file);
+		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+	}
+	mutex_unlock(&kernfs_open_file_mutex);
+
+	kernfs_put_open_node(kn, NULL);
+}
+
+/*
+ * Kernfs attribute files are pollable.  The idea is that you read
+ * the content and then you use 'poll' or 'select' to wait for
+ * the content to change.  When the content changes (assuming the
+ * manager for the kobject supports notification), poll will
+ * return POLLERR|POLLPRI, and select will return the fd whether
+ * it is waiting for read, write, or exceptions.
+ * Once poll/select indicates that the value has changed, you
+ * need to close and re-open the file, or seek to 0 and read again.
+ * Reminder: this only works for attributes which actively support
+ * it, and it is not possible to test an attribute from userspace
+ * to see if it supports poll (Neither 'poll' nor 'select' return
+ * an appropriate error code).  When in doubt, set a suitable timeout value.
+ */
+static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
+{
+	struct kernfs_open_file *of = kernfs_of(filp);
+	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+	struct kernfs_open_node *on = kn->attr.open;
+
+	/* need parent for the kobj, grab both */
+	if (!kernfs_get_active(kn))
+		goto trigger;
+
+	poll_wait(filp, &on->poll, wait);
+
+	kernfs_put_active(kn);
+
+	if (of->event != atomic_read(&on->event))
+		goto trigger;
+
+	return DEFAULT_POLLMASK;
+
+ trigger:
+	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
+}
+
+/**
+ * kernfs_notify - notify a kernfs file
+ * @kn: file to notify
+ *
+ * Notify @kn such that poll(2) on @kn wakes up.
+ */
+void kernfs_notify(struct kernfs_node *kn)
+{
+	struct kernfs_open_node *on;
+	unsigned long flags;
+
+	spin_lock_irqsave(&kernfs_open_node_lock, flags);
+
+	if (!WARN_ON(kernfs_type(kn) != KERNFS_FILE)) {
+		on = kn->attr.open;
+		if (on) {
+			atomic_inc(&on->event);
+			wake_up_interruptible(&on->poll);
+		}
+	}
+
+	spin_unlock_irqrestore(&kernfs_open_node_lock, flags);
+}
+EXPORT_SYMBOL_GPL(kernfs_notify);
+
+const struct file_operations kernfs_file_fops = {
+	.read		= kernfs_fop_read,
+	.write		= kernfs_fop_write,
+	.llseek		= generic_file_llseek,
+	.mmap		= kernfs_fop_mmap,
+	.open		= kernfs_fop_open,
+	.release	= kernfs_fop_release,
+	.poll		= kernfs_fop_poll,
+};
+
+/**
+ * __kernfs_create_file - kernfs internal function to create a file
+ * @parent: directory to create the file in
+ * @name: name of the file
+ * @mode: mode of the file
+ * @size: size of the file
+ * @ops: kernfs operations for the file
+ * @priv: private data for the file
+ * @ns: optional namespace tag of the file
+ * @static_name: don't copy file name
+ * @key: lockdep key for the file's active_ref, %NULL to disable lockdep
+ *
+ * Returns the created node on success, ERR_PTR() value on error.
+ */
+struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
+					 const char *name,
+					 umode_t mode, loff_t size,
+					 const struct kernfs_ops *ops,
+					 void *priv, const void *ns,
+					 bool name_is_static,
+					 struct lock_class_key *key)
+{
+	struct kernfs_addrm_cxt acxt;
+	struct kernfs_node *kn;
+	unsigned flags;
+	int rc;
+
+	flags = KERNFS_FILE;
+	if (name_is_static)
+		flags |= KERNFS_STATIC_NAME;
+
+	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	kn->attr.ops = ops;
+	kn->attr.size = size;
+	kn->ns = ns;
+	kn->priv = priv;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (key) {
+		lockdep_init_map(&kn->dep_map, "s_active", key, 0);
+		kn->flags |= KERNFS_LOCKDEP;
+	}
+#endif
+
+	/*
+	 * kn->attr.ops is accesible only while holding active ref.  We
+	 * need to know whether some ops are implemented outside active
+	 * ref.  Cache their existence in flags.
+	 */
+	if (ops->seq_show)
+		kn->flags |= KERNFS_HAS_SEQ_SHOW;
+	if (ops->mmap)
+		kn->flags |= KERNFS_HAS_MMAP;
+
+	kernfs_addrm_start(&acxt);
+	rc = kernfs_add_one(&acxt, kn);
+	kernfs_addrm_finish(&acxt);
+
+	if (rc) {
+		kernfs_put(kn);
+		return ERR_PTR(rc);
+	}
+	return kn;
+}

fs/kernfs/inode.c

@@ -0,0 +1,377 @@
+/*
+ * fs/kernfs/inode.c - kernfs inode implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "kernfs-internal.h"
+
+static const struct address_space_operations kernfs_aops = {
+	.readpage	= simple_readpage,
+	.write_begin	= simple_write_begin,
+	.write_end	= simple_write_end,
+};
+
+static struct backing_dev_info kernfs_bdi = {
+	.name		= "kernfs",
+	.ra_pages	= 0,	/* No readahead */
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+
+static const struct inode_operations kernfs_iops = {
+	.permission	= kernfs_iop_permission,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.setxattr	= kernfs_iop_setxattr,
+	.removexattr	= kernfs_iop_removexattr,
+	.getxattr	= kernfs_iop_getxattr,
+	.listxattr	= kernfs_iop_listxattr,
+};
+
+void __init kernfs_inode_init(void)
+{
+	if (bdi_init(&kernfs_bdi))
+		panic("failed to init kernfs_bdi");
+}
+
+static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
+{
+	struct iattr *iattrs;
+
+	if (kn->iattr)
+		return kn->iattr;
+
+	kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL);
+	if (!kn->iattr)
+		return NULL;
+	iattrs = &kn->iattr->ia_iattr;
+
+	/* assign default attributes */
+	iattrs->ia_mode = kn->mode;
+	iattrs->ia_uid = GLOBAL_ROOT_UID;
+	iattrs->ia_gid = GLOBAL_ROOT_GID;
+	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
+
+	simple_xattrs_init(&kn->iattr->xattrs);
+
+	return kn->iattr;
+}
+
+static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	struct kernfs_iattrs *attrs;
+	struct iattr *iattrs;
+	unsigned int ia_valid = iattr->ia_valid;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	iattrs = &attrs->ia_iattr;
+
+	if (ia_valid & ATTR_UID)
+		iattrs->ia_uid = iattr->ia_uid;
+	if (ia_valid & ATTR_GID)
+		iattrs->ia_gid = iattr->ia_gid;
+	if (ia_valid & ATTR_ATIME)
+		iattrs->ia_atime = iattr->ia_atime;
+	if (ia_valid & ATTR_MTIME)
+		iattrs->ia_mtime = iattr->ia_mtime;
+	if (ia_valid & ATTR_CTIME)
+		iattrs->ia_ctime = iattr->ia_ctime;
+	if (ia_valid & ATTR_MODE) {
+		umode_t mode = iattr->ia_mode;
+		iattrs->ia_mode = kn->mode = mode;
+	}
+	return 0;
+}
+
+/**
+ * kernfs_setattr - set iattr on a node
+ * @kn: target node
+ * @iattr: iattr to set
+ *
+ * Returns 0 on success, -errno on failure.
+ */
+int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+{
+	int ret;
+
+	mutex_lock(&kernfs_mutex);
+	ret = __kernfs_setattr(kn, iattr);
+	mutex_unlock(&kernfs_mutex);
+	return ret;
+}
+
+int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct kernfs_node *kn = dentry->d_fsdata;
+	int error;
+
+	if (!kn)
+		return -EINVAL;
+
+	mutex_lock(&kernfs_mutex);
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		goto out;
+
+	error = __kernfs_setattr(kn, iattr);
+	if (error)
+		goto out;
+
+	/* this ignores size changes */
+	setattr_copy(inode, iattr);
+
+out:
+	mutex_unlock(&kernfs_mutex);
+	return error;
+}
+
+static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata,
+				  u32 *secdata_len)
+{
+	struct kernfs_iattrs *attrs;
+	void *old_secdata;
+	size_t old_secdata_len;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	old_secdata = attrs->ia_secdata;
+	old_secdata_len = attrs->ia_secdata_len;
+
+	attrs->ia_secdata = *secdata;
+	attrs->ia_secdata_len = *secdata_len;
+
+	*secdata = old_secdata;
+	*secdata_len = old_secdata_len;
+	return 0;
+}
+
+int kernfs_iop_setxattr(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+	void *secdata;
+	int error;
+	u32 secdata_len = 0;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
+		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
+		error = security_inode_setsecurity(dentry->d_inode, suffix,
+						value, size, flags);
+		if (error)
+			return error;
+		error = security_inode_getsecctx(dentry->d_inode,
+						&secdata, &secdata_len);
+		if (error)
+			return error;
+
+		mutex_lock(&kernfs_mutex);
+		error = kernfs_node_setsecdata(kn, &secdata, &secdata_len);
+		mutex_unlock(&kernfs_mutex);
+
+		if (secdata)
+			security_release_secctx(secdata, secdata_len);
+		return error;
+	} else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
+		return simple_xattr_set(&attrs->xattrs, name, value, size,
+					flags);
+	}
+
+	return -EINVAL;
+}
+
+int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_remove(&attrs->xattrs, name);
+}
+
+ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
+			    size_t size)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_get(&attrs->xattrs, name, buf, size);
+}
+
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_iattrs *attrs;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	return simple_xattr_list(&attrs->xattrs, buf, size);
+}
+
+static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
+{
+	inode->i_mode = mode;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+}
+
+static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
+{
+	inode->i_uid = iattr->ia_uid;
+	inode->i_gid = iattr->ia_gid;
+	inode->i_atime = iattr->ia_atime;
+	inode->i_mtime = iattr->ia_mtime;
+	inode->i_ctime = iattr->ia_ctime;
+}
+
+static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	struct kernfs_iattrs *attrs = kn->iattr;
+
+	inode->i_mode = kn->mode;
+	if (attrs) {
+		/*
+		 * kernfs_node has non-default attributes get them from
+		 * persistent copy in kernfs_node.
+		 */
+		set_inode_attr(inode, &attrs->ia_iattr);
+		security_inode_notifysecctx(inode, attrs->ia_secdata,
+					    attrs->ia_secdata_len);
+	}
+
+	if (kernfs_type(kn) == KERNFS_DIR)
+		set_nlink(inode, kn->dir.subdirs + 2);
+}
+
+int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		   struct kstat *stat)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct inode *inode = dentry->d_inode;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_refresh_inode(kn, inode);
+	mutex_unlock(&kernfs_mutex);
+
+	generic_fillattr(inode, stat);
+	return 0;
+}
+
+static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
+{
+	kernfs_get(kn);
+	inode->i_private = kn;
+	inode->i_mapping->a_ops = &kernfs_aops;
+	inode->i_mapping->backing_dev_info = &kernfs_bdi;
+	inode->i_op = &kernfs_iops;
+
+	set_default_inode_attr(inode, kn->mode);
+	kernfs_refresh_inode(kn, inode);
+
+	/* initialize inode according to type */
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		inode->i_op = &kernfs_dir_iops;
+		inode->i_fop = &kernfs_dir_fops;
+		break;
+	case KERNFS_FILE:
+		inode->i_size = kn->attr.size;
+		inode->i_fop = &kernfs_file_fops;
+		break;
+	case KERNFS_LINK:
+		inode->i_op = &kernfs_symlink_iops;
+		break;
+	default:
+		BUG();
+	}
+
+	unlock_new_inode(inode);
+}
+
+/**
+ *	kernfs_get_inode - get inode for kernfs_node
+ *	@sb: super block
+ *	@kn: kernfs_node to allocate inode for
+ *
+ *	Get inode for @kn.  If such inode doesn't exist, a new inode is
+ *	allocated and basics are initialized.  New inode is returned
+ *	locked.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep).
+ *
+ *	RETURNS:
+ *	Pointer to allocated inode on success, NULL on failure.
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
+{
+	struct inode *inode;
+
+	inode = iget_locked(sb, kn->ino);
+	if (inode && (inode->i_state & I_NEW))
+		kernfs_init_inode(kn, inode);
+
+	return inode;
+}
+
+/*
+ * The kernfs_node serves as both an inode and a directory entry for
+ * kernfs.  To prevent the kernfs inode numbers from being freed
+ * prematurely we take a reference to kernfs_node from the kernfs inode.  A
+ * super_operations.evict_inode() implementation is needed to drop that
+ * reference upon inode destruction.
+ */
+void kernfs_evict_inode(struct inode *inode)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	truncate_inode_pages(&inode->i_data, 0);
+	clear_inode(inode);
+	kernfs_put(kn);
+}
+
+int kernfs_iop_permission(struct inode *inode, int mask)
+{
+	struct kernfs_node *kn;
+
+	if (mask & MAY_NOT_BLOCK)
+		return -ECHILD;
+
+	kn = inode->i_private;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_refresh_inode(kn, inode);
+	mutex_unlock(&kernfs_mutex);
+
+	return generic_permission(inode, mask);
+}

fs/kernfs/kernfs-internal.h

@@ -0,0 +1,122 @@
+/*
+ * fs/kernfs/kernfs-internal.h - kernfs internal header file
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef __KERNFS_INTERNAL_H
+#define __KERNFS_INTERNAL_H
+
+#include <linux/lockdep.h>
+#include <linux/fs.h>
+#include <linux/mutex.h>
+#include <linux/xattr.h>
+
+#include <linux/kernfs.h>
+
+struct kernfs_iattrs {
+	struct iattr		ia_iattr;
+	void			*ia_secdata;
+	u32			ia_secdata_len;
+
+	struct simple_xattrs	xattrs;
+};
+
+#define KN_DEACTIVATED_BIAS		INT_MIN
+
+/* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
+
+/**
+ * kernfs_root - find out the kernfs_root a kernfs_node belongs to
+ * @kn: kernfs_node of interest
+ *
+ * Return the kernfs_root @kn belongs to.
+ */
+static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
+{
+	/* if parent exists, it's always a dir; otherwise, @sd is a dir */
+	if (kn->parent)
+		kn = kn->parent;
+	return kn->dir.root;
+}
+
+/*
+ * Context structure to be used while adding/removing nodes.
+ */
+struct kernfs_addrm_cxt {
+	struct kernfs_node	*removed;
+};
+
+/*
+ * mount.c
+ */
+struct kernfs_super_info {
+	/*
+	 * The root associated with this super_block.  Each super_block is
+	 * identified by the root and ns it's associated with.
+	 */
+	struct kernfs_root	*root;
+
+	/*
+	 * Each sb is associated with one namespace tag, currently the
+	 * network namespace of the task which mounted this kernfs
+	 * instance.  If multiple tags become necessary, make the following
+	 * an array and compare kernfs_node tag against every entry.
+	 */
+	const void		*ns;
+};
+#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
+
+extern struct kmem_cache *kernfs_node_cache;
+
+/*
+ * inode.c
+ */
+struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn);
+void kernfs_evict_inode(struct inode *inode);
+int kernfs_iop_permission(struct inode *inode, int mask);
+int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
+int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		       struct kstat *stat);
+int kernfs_iop_setxattr(struct dentry *dentry, const char *name, const void *value,
+			size_t size, int flags);
+int kernfs_iop_removexattr(struct dentry *dentry, const char *name);
+ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
+			    size_t size);
+ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
+void kernfs_inode_init(void);
+
+/*
+ * dir.c
+ */
+extern struct mutex kernfs_mutex;
+extern const struct dentry_operations kernfs_dops;
+extern const struct file_operations kernfs_dir_fops;
+extern const struct inode_operations kernfs_dir_iops;
+
+struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
+void kernfs_put_active(struct kernfs_node *kn);
+void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt);
+int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn);
+void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt);
+struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
+				    const char *name, umode_t mode,
+				    unsigned flags);
+
+/*
+ * file.c
+ */
+extern const struct file_operations kernfs_file_fops;
+
+void kernfs_unmap_bin_file(struct kernfs_node *kn);
+
+/*
+ * symlink.c
+ */
+extern const struct inode_operations kernfs_symlink_iops;
+
+#endif	/* __KERNFS_INTERNAL_H */

fs/kernfs/mount.c

@@ -0,0 +1,165 @@
+/*
+ * fs/kernfs/mount.c - kernfs mount implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/init.h>
+#include <linux/magic.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+
+#include "kernfs-internal.h"
+
+struct kmem_cache *kernfs_node_cache;
+
+static const struct super_operations kernfs_sops = {
+	.statfs		= simple_statfs,
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= kernfs_evict_inode,
+};
+
+static int kernfs_fill_super(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct inode *inode;
+	struct dentry *root;
+
+	sb->s_blocksize = PAGE_CACHE_SIZE;
+	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_magic = SYSFS_MAGIC;
+	sb->s_op = &kernfs_sops;
+	sb->s_time_gran = 1;
+
+	/* get root inode, initialize and unlock it */
+	mutex_lock(&kernfs_mutex);
+	inode = kernfs_get_inode(sb, info->root->kn);
+	mutex_unlock(&kernfs_mutex);
+	if (!inode) {
+		pr_debug("kernfs: could not get root inode\n");
+		return -ENOMEM;
+	}
+
+	/* instantiate and link root dentry */
+	root = d_make_root(inode);
+	if (!root) {
+		pr_debug("%s: could not get root dentry!\n", __func__);
+		return -ENOMEM;
+	}
+	kernfs_get(info->root->kn);
+	root->d_fsdata = info->root->kn;
+	sb->s_root = root;
+	sb->s_d_op = &kernfs_dops;
+	return 0;
+}
+
+static int kernfs_test_super(struct super_block *sb, void *data)
+{
+	struct kernfs_super_info *sb_info = kernfs_info(sb);
+	struct kernfs_super_info *info = data;
+
+	return sb_info->root == info->root && sb_info->ns == info->ns;
+}
+
+static int kernfs_set_super(struct super_block *sb, void *data)
+{
+	int error;
+	error = set_anon_super(sb, data);
+	if (!error)
+		sb->s_fs_info = data;
+	return error;
+}
+
+/**
+ * kernfs_super_ns - determine the namespace tag of a kernfs super_block
+ * @sb: super_block of interest
+ *
+ * Return the namespace tag associated with kernfs super_block @sb.
+ */
+const void *kernfs_super_ns(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+
+	return info->ns;
+}
+
+/**
+ * kernfs_mount_ns - kernfs mount helper
+ * @fs_type: file_system_type of the fs being mounted
+ * @flags: mount flags specified for the mount
+ * @root: kernfs_root of the hierarchy being mounted
+ * @ns: optional namespace tag of the mount
+ *
+ * This is to be called from each kernfs user's file_system_type->mount()
+ * implementation, which should pass through the specified @fs_type and
+ * @flags, and specify the hierarchy and namespace tag to mount via @root
+ * and @ns, respectively.
+ *
+ * The return value can be passed to the vfs layer verbatim.
+ */
+struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
+			       struct kernfs_root *root, const void *ns)
+{
+	struct super_block *sb;
+	struct kernfs_super_info *info;
+	int error;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	info->root = root;
+	info->ns = ns;
+
+	sb = sget(fs_type, kernfs_test_super, kernfs_set_super, flags, info);
+	if (IS_ERR(sb) || sb->s_fs_info != info)
+		kfree(info);
+	if (IS_ERR(sb))
+		return ERR_CAST(sb);
+	if (!sb->s_root) {
+		error = kernfs_fill_super(sb);
+		if (error) {
+			deactivate_locked_super(sb);
+			return ERR_PTR(error);
+		}
+		sb->s_flags |= MS_ACTIVE;
+	}
+
+	return dget(sb->s_root);
+}
+
+/**
+ * kernfs_kill_sb - kill_sb for kernfs
+ * @sb: super_block being killed
+ *
+ * This can be used directly for file_system_type->kill_sb().  If a kernfs
+ * user needs extra cleanup, it can implement its own kill_sb() and call
+ * this function at the end.
+ */
+void kernfs_kill_sb(struct super_block *sb)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_node *root_kn = sb->s_root->d_fsdata;
+
+	/*
+	 * Remove the superblock from fs_supers/s_instances
+	 * so we can't find it, before freeing kernfs_super_info.
+	 */
+	kill_anon_super(sb);
+	kfree(info);
+	kernfs_put(root_kn);
+}
+
+void __init kernfs_init(void)
+{
+	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
+					      sizeof(struct kernfs_node),
+					      0, SLAB_PANIC, NULL);
+	kernfs_inode_init();
+}

fs/kernfs/symlink.c

@@ -0,0 +1,151 @@
+/*
+ * fs/kernfs/symlink.c - kernfs symlink implementation
+ *
+ * Copyright (c) 2001-3 Patrick Mochel
+ * Copyright (c) 2007 SUSE Linux Products GmbH
+ * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/namei.h>
+
+#include "kernfs-internal.h"
+
+/**
+ * kernfs_create_link - create a symlink
+ * @parent: directory to create the symlink in
+ * @name: name of the symlink
+ * @target: target node for the symlink to point to
+ *
+ * Returns the created node on success, ERR_PTR() value on error.
+ */
+struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
+				       const char *name,
+				       struct kernfs_node *target)
+{
+	struct kernfs_node *kn;
+	struct kernfs_addrm_cxt acxt;
+	int error;
+
+	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
+	if (!kn)
+		return ERR_PTR(-ENOMEM);
+
+	if (kernfs_ns_enabled(parent))
+		kn->ns = target->ns;
+	kn->symlink.target_kn = target;
+	kernfs_get(target);	/* ref owned by symlink */
+
+	kernfs_addrm_start(&acxt);
+	error = kernfs_add_one(&acxt, kn);
+	kernfs_addrm_finish(&acxt);
+
+	if (!error)
+		return kn;
+
+	kernfs_put(kn);
+	return ERR_PTR(error);
+}
+
+static int kernfs_get_target_path(struct kernfs_node *parent,
+				  struct kernfs_node *target, char *path)
+{
+	struct kernfs_node *base, *kn;
+	char *s = path;
+	int len = 0;
+
+	/* go up to the root, stop at the base */
+	base = parent;
+	while (base->parent) {
+		kn = target->parent;
+		while (kn->parent && base != kn)
+			kn = kn->parent;
+
+		if (base == kn)
+			break;
+
+		strcpy(s, "../");
+		s += 3;
+		base = base->parent;
+	}
+
+	/* determine end of target string for reverse fillup */
+	kn = target;
+	while (kn->parent && kn != base) {
+		len += strlen(kn->name) + 1;
+		kn = kn->parent;
+	}
+
+	/* check limits */
+	if (len < 2)
+		return -EINVAL;
+	len--;
+	if ((s - path) + len > PATH_MAX)
+		return -ENAMETOOLONG;
+
+	/* reverse fillup of target string from target to base */
+	kn = target;
+	while (kn->parent && kn != base) {
+		int slen = strlen(kn->name);
+
+		len -= slen;
+		strncpy(s + len, kn->name, slen);
+		if (len)
+			s[--len] = '/';
+
+		kn = kn->parent;
+	}
+
+	return 0;
+}
+
+static int kernfs_getlink(struct dentry *dentry, char *path)
+{
+	struct kernfs_node *kn = dentry->d_fsdata;
+	struct kernfs_node *parent = kn->parent;
+	struct kernfs_node *target = kn->symlink.target_kn;
+	int error;
+
+	mutex_lock(&kernfs_mutex);
+	error = kernfs_get_target_path(parent, target, path);
+	mutex_unlock(&kernfs_mutex);
+
+	return error;
+}
+
+static void *kernfs_iop_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	int error = -ENOMEM;
+	unsigned long page = get_zeroed_page(GFP_KERNEL);
+	if (page) {
+		error = kernfs_getlink(dentry, (char *) page);
+		if (error < 0)
+			free_page((unsigned long)page);
+	}
+	nd_set_link(nd, error ? ERR_PTR(error) : (char *)page);
+	return NULL;
+}
+
+static void kernfs_iop_put_link(struct dentry *dentry, struct nameidata *nd,
+				void *cookie)
+{
+	char *page = nd_get_link(nd);
+	if (!IS_ERR(page))
+		free_page((unsigned long)page);
+}
+
+const struct inode_operations kernfs_symlink_iops = {
+	.setxattr	= kernfs_iop_setxattr,
+	.removexattr	= kernfs_iop_removexattr,
+	.getxattr	= kernfs_iop_getxattr,
+	.listxattr	= kernfs_iop_listxattr,
+	.readlink	= generic_readlink,
+	.follow_link	= kernfs_iop_follow_link,
+	.put_link	= kernfs_iop_put_link,
+	.setattr	= kernfs_iop_setattr,
+	.getattr	= kernfs_iop_getattr,
+	.permission	= kernfs_iop_permission,
+};

fs/namespace.c

@@ -2790,6 +2790,8 @@ void __init mnt_init(void)
 	for (u = 0; u < HASH_SIZE; u++)
 		INIT_LIST_HEAD(&mountpoint_hashtable[u]);
 
+	kernfs_init();
+
 	err = sysfs_init();
 	if (err)
 		printk(KERN_WARNING "%s: sysfs_init error: %d\n",

fs/sysfs/Makefile

@@ -2,4 +2,4 @@
 # Makefile for the sysfs virtual filesystem
 #
 
-obj-y		:= inode.o file.o dir.o symlink.o mount.o group.o
+obj-y		:= file.o dir.o symlink.o mount.o group.o

fs/sysfs/dir.c

@@ -13,465 +13,31 @@
 #undef DEBUG
 
 #include <linux/fs.h>
-#include <linux/mount.h>
-#include <linux/module.h>
 #include <linux/kobject.h>
-#include <linux/namei.h>
-#include <linux/idr.h>
-#include <linux/completion.h>
-#include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/security.h>
-#include <linux/hash.h>
 #include "sysfs.h"
 
-DEFINE_MUTEX(sysfs_mutex);
 DEFINE_SPINLOCK(sysfs_symlink_target_lock);
 
-#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb)
-
-static DEFINE_SPINLOCK(sysfs_ino_lock);
-static DEFINE_IDA(sysfs_ino_ida);
-
-/**
- *	sysfs_name_hash
- *	@name: Null terminated string to hash
- *	@ns:   Namespace tag to hash
- *
- *	Returns 31 bit hash of ns + name (so it fits in an off_t )
- */
-static unsigned int sysfs_name_hash(const char *name, const void *ns)
-{
-	unsigned long hash = init_name_hash();
-	unsigned int len = strlen(name);
-	while (len--)
-		hash = partial_name_hash(*name++, hash);
-	hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
-	hash &= 0x7fffffffU;
-	/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
-	if (hash < 1)
-		hash += 2;
-	if (hash >= INT_MAX)
-		hash = INT_MAX - 1;
-	return hash;
-}
-
-static int sysfs_name_compare(unsigned int hash, const char *name,
-			      const void *ns, const struct sysfs_dirent *sd)
-{
-	if (hash != sd->s_hash)
-		return hash - sd->s_hash;
-	if (ns != sd->s_ns)
-		return ns - sd->s_ns;
-	return strcmp(name, sd->s_name);
-}
-
-static int sysfs_sd_compare(const struct sysfs_dirent *left,
-			    const struct sysfs_dirent *right)
-{
-	return sysfs_name_compare(left->s_hash, left->s_name, left->s_ns,
-				  right);
-}
-
-/**
- *	sysfs_link_sibling - link sysfs_dirent into sibling rbtree
- *	@sd: sysfs_dirent of interest
- *
- *	Link @sd into its sibling rbtree which starts from
- *	sd->s_parent->s_dir.children.
- *
- *	Locking:
- *	mutex_lock(sysfs_mutex)
- *
- *	RETURNS:
- *	0 on susccess -EEXIST on failure.
- */
-static int sysfs_link_sibling(struct sysfs_dirent *sd)
-{
-	struct rb_node **node = &sd->s_parent->s_dir.children.rb_node;
-	struct rb_node *parent = NULL;
-
-	if (sysfs_type(sd) == SYSFS_DIR)
-		sd->s_parent->s_dir.subdirs++;
-
-	while (*node) {
-		struct sysfs_dirent *pos;
-		int result;
-
-		pos = to_sysfs_dirent(*node);
-		parent = *node;
-		result = sysfs_sd_compare(sd, pos);
-		if (result < 0)
-			node = &pos->s_rb.rb_left;
-		else if (result > 0)
-			node = &pos->s_rb.rb_right;
-		else
-			return -EEXIST;
-	}
-	/* add new node and rebalance the tree */
-	rb_link_node(&sd->s_rb, parent, node);
-	rb_insert_color(&sd->s_rb, &sd->s_parent->s_dir.children);
-	return 0;
-}
-
-/**
- *	sysfs_unlink_sibling - unlink sysfs_dirent from sibling rbtree
- *	@sd: sysfs_dirent of interest
- *
- *	Unlink @sd from its sibling rbtree which starts from
- *	sd->s_parent->s_dir.children.
- *
- *	Locking:
- *	mutex_lock(sysfs_mutex)
- */
-static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
-{
-	if (sysfs_type(sd) == SYSFS_DIR)
-		sd->s_parent->s_dir.subdirs--;
-
-	rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
-}
-
-/**
- *	sysfs_get_active - get an active reference to sysfs_dirent
- *	@sd: sysfs_dirent to get an active reference to
- *
- *	Get an active reference of @sd.  This function is noop if @sd
- *	is NULL.
- *
- *	RETURNS:
- *	Pointer to @sd on success, NULL on failure.
- */
-struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
-{
-	if (unlikely(!sd))
-		return NULL;
-
-	if (!atomic_inc_unless_negative(&sd->s_active))
-		return NULL;
-
-	if (likely(!sysfs_ignore_lockdep(sd)))
-		rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
-	return sd;
-}
-
-/**
- *	sysfs_put_active - put an active reference to sysfs_dirent
- *	@sd: sysfs_dirent to put an active reference to
- *
- *	Put an active reference to @sd.  This function is noop if @sd
- *	is NULL.
- */
-void sysfs_put_active(struct sysfs_dirent *sd)
-{
-	int v;
-
-	if (unlikely(!sd))
-		return;
-
-	if (likely(!sysfs_ignore_lockdep(sd)))
-		rwsem_release(&sd->dep_map, 1, _RET_IP_);
-	v = atomic_dec_return(&sd->s_active);
-	if (likely(v != SD_DEACTIVATED_BIAS))
-		return;
-
-	/* atomic_dec_return() is a mb(), we'll always see the updated
-	 * sd->u.completion.
-	 */
-	complete(sd->u.completion);
-}
-
-/**
- *	sysfs_deactivate - deactivate sysfs_dirent
- *	@sd: sysfs_dirent to deactivate
- *
- *	Deny new active references and drain existing ones.
- */
-static void sysfs_deactivate(struct sysfs_dirent *sd)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int v;
-
-	BUG_ON(!(sd->s_flags & SYSFS_FLAG_REMOVED));
-
-	if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF))
-		return;
-
-	sd->u.completion = (void *)&wait;
-
-	rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_);
-	/* atomic_add_return() is a mb(), put_active() will always see
-	 * the updated sd->u.completion.
-	 */
-	v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);
-
-	if (v != SD_DEACTIVATED_BIAS) {
-		lock_contended(&sd->dep_map, _RET_IP_);
-		wait_for_completion(&wait);
-	}
-
-	lock_acquired(&sd->dep_map, _RET_IP_);
-	rwsem_release(&sd->dep_map, 1, _RET_IP_);
-}
-
-static int sysfs_alloc_ino(unsigned int *pino)
-{
-	int ino, rc;
-
- retry:
-	spin_lock(&sysfs_ino_lock);
-	rc = ida_get_new_above(&sysfs_ino_ida, 2, &ino);
-	spin_unlock(&sysfs_ino_lock);
-
-	if (rc == -EAGAIN) {
-		if (ida_pre_get(&sysfs_ino_ida, GFP_KERNEL))
-			goto retry;
-		rc = -ENOMEM;
-	}
-
-	*pino = ino;
-	return rc;
-}
-
-static void sysfs_free_ino(unsigned int ino)
-{
-	spin_lock(&sysfs_ino_lock);
-	ida_remove(&sysfs_ino_ida, ino);
-	spin_unlock(&sysfs_ino_lock);
-}
-
-void release_sysfs_dirent(struct sysfs_dirent *sd)
-{
-	struct sysfs_dirent *parent_sd;
-
- repeat:
-	/* Moving/renaming is always done while holding reference.
-	 * sd->s_parent won't change beneath us.
-	 */
-	parent_sd = sd->s_parent;
-
-	WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED),
-		"sysfs: free using entry: %s/%s\n",
-		parent_sd ? parent_sd->s_name : "", sd->s_name);
-
-	if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
-		sysfs_put(sd->s_symlink.target_sd);
-	if (sysfs_type(sd) & SYSFS_COPY_NAME)
-		kfree(sd->s_name);
-	if (sd->s_iattr && sd->s_iattr->ia_secdata)
-		security_release_secctx(sd->s_iattr->ia_secdata,
-					sd->s_iattr->ia_secdata_len);
-	kfree(sd->s_iattr);
-	sysfs_free_ino(sd->s_ino);
-	kmem_cache_free(sysfs_dir_cachep, sd);
-
-	sd = parent_sd;
-	if (sd && atomic_dec_and_test(&sd->s_count))
-		goto repeat;
-}
-
-static int sysfs_dentry_delete(const struct dentry *dentry)
-{
-	struct sysfs_dirent *sd = dentry->d_fsdata;
-	return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED));
-}
-
-static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
-{
-	struct sysfs_dirent *sd;
-	int type;
-
-	if (flags & LOOKUP_RCU)
-		return -ECHILD;
-
-	sd = dentry->d_fsdata;
-	mutex_lock(&sysfs_mutex);
-
-	/* The sysfs dirent has been deleted */
-	if (sd->s_flags & SYSFS_FLAG_REMOVED)
-		goto out_bad;
-
-	/* The sysfs dirent has been moved? */
-	if (dentry->d_parent->d_fsdata != sd->s_parent)
-		goto out_bad;
-
-	/* The sysfs dirent has been renamed */
-	if (strcmp(dentry->d_name.name, sd->s_name) != 0)
-		goto out_bad;
-
-	/* The sysfs dirent has been moved to a different namespace */
-	type = KOBJ_NS_TYPE_NONE;
-	if (sd->s_parent) {
-		type = sysfs_ns_type(sd->s_parent);
-		if (type != KOBJ_NS_TYPE_NONE &&
-				sysfs_info(dentry->d_sb)->ns[type] != sd->s_ns)
-			goto out_bad;
-	}
-
-	mutex_unlock(&sysfs_mutex);
-out_valid:
-	return 1;
-out_bad:
-	/* Remove the dentry from the dcache hashes.
-	 * If this is a deleted dentry we use d_drop instead of d_delete
-	 * so sysfs doesn't need to cope with negative dentries.
-	 *
-	 * If this is a dentry that has simply been renamed we
-	 * use d_drop to remove it from the dcache lookup on its
-	 * old parent.  If this dentry persists later when a lookup
-	 * is performed at its new name the dentry will be readded
-	 * to the dcache hashes.
-	 */
-	mutex_unlock(&sysfs_mutex);
-
-	/* If we have submounts we must allow the vfs caches
-	 * to lie about the state of the filesystem to prevent
-	 * leaks and other nasty things.
-	 */
-	if (check_submounts_and_drop(dentry) != 0)
-		goto out_valid;
-
-	return 0;
-}
-
-static void sysfs_dentry_release(struct dentry *dentry)
-{
-	sysfs_put(dentry->d_fsdata);
-}
-
-const struct dentry_operations sysfs_dentry_ops = {
-	.d_revalidate	= sysfs_dentry_revalidate,
-	.d_delete	= sysfs_dentry_delete,
-	.d_release	= sysfs_dentry_release,
-};
-
-struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
-{
-	char *dup_name = NULL;
-	struct sysfs_dirent *sd;
-
-	if (type & SYSFS_COPY_NAME) {
-		name = dup_name = kstrdup(name, GFP_KERNEL);
-		if (!name)
-			return NULL;
-	}
-
-	sd = kmem_cache_zalloc(sysfs_dir_cachep, GFP_KERNEL);
-	if (!sd)
-		goto err_out1;
-
-	if (sysfs_alloc_ino(&sd->s_ino))
-		goto err_out2;
-
-	atomic_set(&sd->s_count, 1);
-	atomic_set(&sd->s_active, 0);
-
-	sd->s_name = name;
-	sd->s_mode = mode;
-	sd->s_flags = type | SYSFS_FLAG_REMOVED;
-
-	return sd;
-
- err_out2:
-	kmem_cache_free(sysfs_dir_cachep, sd);
- err_out1:
-	kfree(dup_name);
-	return NULL;
-}
-
-/**
- *	sysfs_addrm_start - prepare for sysfs_dirent add/remove
- *	@acxt: pointer to sysfs_addrm_cxt to be used
- *
- *	This function is called when the caller is about to add or remove
- *	sysfs_dirent.  This function acquires sysfs_mutex.  @acxt is used
- *	to keep and pass context to other addrm functions.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).  sysfs_mutex is locked on
- *	return.
- */
-void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt)
-	__acquires(sysfs_mutex)
-{
-	memset(acxt, 0, sizeof(*acxt));
-
-	mutex_lock(&sysfs_mutex);
-}
-
-/**
- *	__sysfs_add_one - add sysfs_dirent to parent without warning
- *	@acxt: addrm context to use
- *	@sd: sysfs_dirent to be added
- *	@parent_sd: the parent sysfs_dirent to add @sd to
- *
- *	Get @parent_sd and set @sd->s_parent to it and increment nlink of
- *	the parent inode if @sd is a directory and link into the children
- *	list of the parent.
- *
- *	This function should be called between calls to
- *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
- *	passed the same @acxt as passed to sysfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by sysfs_addrm_start().
- *
- *	RETURNS:
- *	0 on success, -EEXIST if entry with the given name already
- *	exists.
- */
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
-		    struct sysfs_dirent *parent_sd)
-{
-	struct sysfs_inode_attrs *ps_iattr;
-	int ret;
-
-	if (!!sysfs_ns_type(parent_sd) != !!sd->s_ns) {
-		WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
-			sysfs_ns_type(parent_sd) ? "required" : "invalid",
-			parent_sd->s_name, sd->s_name);
-		return -EINVAL;
-	}
-
-	sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
-	sd->s_parent = sysfs_get(parent_sd);
-
-	ret = sysfs_link_sibling(sd);
-	if (ret)
-		return ret;
-
-	/* Update timestamps on the parent */
-	ps_iattr = parent_sd->s_iattr;
-	if (ps_iattr) {
-		struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
-		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
-	}
-
-	/* Mark the entry added into directory tree */
-	sd->s_flags &= ~SYSFS_FLAG_REMOVED;
-
-	return 0;
-}
-
 /**
  *	sysfs_pathname - return full path to sysfs dirent
- *	@sd: sysfs_dirent whose path we want
+ *	@kn: kernfs_node whose path we want
  *	@path: caller allocated buffer of size PATH_MAX
  *
  *	Gives the name "/" to the sysfs_root entry; any path returned
  *	is relative to wherever sysfs is mounted.
  */
-static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
+static char *sysfs_pathname(struct kernfs_node *kn, char *path)
 {
-	if (sd->s_parent) {
-		sysfs_pathname(sd->s_parent, path);
+	if (kn->parent) {
+		sysfs_pathname(kn->parent, path);
 		strlcat(path, "/", PATH_MAX);
 	}
-	strlcat(path, sd->s_name, PATH_MAX);
+	strlcat(path, kn->name, PATH_MAX);
 	return path;
 }
 
-void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name)
+void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
 {
 	char *path;
 
@@ -488,248 +54,6 @@ void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name)
 	kfree(path);
 }
 
-/**
- *	sysfs_add_one - add sysfs_dirent to parent
- *	@acxt: addrm context to use
- *	@sd: sysfs_dirent to be added
- *	@parent_sd: the parent sysfs_dirent to add @sd to
- *
- *	Get @parent_sd and set @sd->s_parent to it and increment nlink of
- *	the parent inode if @sd is a directory and link into the children
- *	list of the parent.
- *
- *	This function should be called between calls to
- *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
- *	passed the same @acxt as passed to sysfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by sysfs_addrm_start().
- *
- *	RETURNS:
- *	0 on success, -EEXIST if entry with the given name already
- *	exists.
- */
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
-		  struct sysfs_dirent *parent_sd)
-{
-	int ret;
-
-	ret = __sysfs_add_one(acxt, sd, parent_sd);
-
-	if (ret == -EEXIST)
-		sysfs_warn_dup(parent_sd, sd->s_name);
-	return ret;
-}
-
-/**
- *	sysfs_remove_one - remove sysfs_dirent from parent
- *	@acxt: addrm context to use
- *	@sd: sysfs_dirent to be removed
- *
- *	Mark @sd removed and drop nlink of parent inode if @sd is a
- *	directory.  @sd is unlinked from the children list.
- *
- *	This function should be called between calls to
- *	sysfs_addrm_start() and sysfs_addrm_finish() and should be
- *	passed the same @acxt as passed to sysfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by sysfs_addrm_start().
- */
-static void sysfs_remove_one(struct sysfs_addrm_cxt *acxt,
-			     struct sysfs_dirent *sd)
-{
-	struct sysfs_inode_attrs *ps_iattr;
-
-	/*
-	 * Removal can be called multiple times on the same node.  Only the
-	 * first invocation is effective and puts the base ref.
-	 */
-	if (sd->s_flags & SYSFS_FLAG_REMOVED)
-		return;
-
-	sysfs_unlink_sibling(sd);
-
-	/* Update timestamps on the parent */
-	ps_iattr = sd->s_parent->s_iattr;
-	if (ps_iattr) {
-		struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
-		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
-	}
-
-	sd->s_flags |= SYSFS_FLAG_REMOVED;
-	sd->u.removed_list = acxt->removed;
-	acxt->removed = sd;
-}
-
-/**
- *	sysfs_addrm_finish - finish up sysfs_dirent add/remove
- *	@acxt: addrm context to finish up
- *
- *	Finish up sysfs_dirent add/remove.  Resources acquired by
- *	sysfs_addrm_start() are released and removed sysfs_dirents are
- *	cleaned up.
- *
- *	LOCKING:
- *	sysfs_mutex is released.
- */
-void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
-	__releases(sysfs_mutex)
-{
-	/* release resources acquired by sysfs_addrm_start() */
-	mutex_unlock(&sysfs_mutex);
-
-	/* kill removed sysfs_dirents */
-	while (acxt->removed) {
-		struct sysfs_dirent *sd = acxt->removed;
-
-		acxt->removed = sd->u.removed_list;
-
-		sysfs_deactivate(sd);
-		sysfs_unmap_bin_file(sd);
-		sysfs_put(sd);
-	}
-}
-
-/**
- *	sysfs_find_dirent - find sysfs_dirent with the given name
- *	@parent_sd: sysfs_dirent to search under
- *	@name: name to look for
- *	@ns: the namespace tag to use
- *
- *	Look for sysfs_dirent with name @name under @parent_sd.
- *
- *	LOCKING:
- *	mutex_lock(sysfs_mutex)
- *
- *	RETURNS:
- *	Pointer to sysfs_dirent if found, NULL if not.
- */
-struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
-				       const unsigned char *name,
-				       const void *ns)
-{
-	struct rb_node *node = parent_sd->s_dir.children.rb_node;
-	unsigned int hash;
-
-	if (!!sysfs_ns_type(parent_sd) != !!ns) {
-		WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
-			sysfs_ns_type(parent_sd) ? "required" : "invalid",
-			parent_sd->s_name, name);
-		return NULL;
-	}
-
-	hash = sysfs_name_hash(name, ns);
-	while (node) {
-		struct sysfs_dirent *sd;
-		int result;
-
-		sd = to_sysfs_dirent(node);
-		result = sysfs_name_compare(hash, name, ns, sd);
-		if (result < 0)
-			node = node->rb_left;
-		else if (result > 0)
-			node = node->rb_right;
-		else
-			return sd;
-	}
-	return NULL;
-}
-
-/**
- *	sysfs_get_dirent_ns - find and get sysfs_dirent with the given name
- *	@parent_sd: sysfs_dirent to search under
- *	@name: name to look for
- *	@ns: the namespace tag to use
- *
- *	Look for sysfs_dirent with name @name under @parent_sd and get
- *	it if found.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).  Grabs sysfs_mutex.
- *
- *	RETURNS:
- *	Pointer to sysfs_dirent if found, NULL if not.
- */
-struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
-					 const unsigned char *name,
-					 const void *ns)
-{
-	struct sysfs_dirent *sd;
-
-	mutex_lock(&sysfs_mutex);
-	sd = sysfs_find_dirent(parent_sd, name, ns);
-	sysfs_get(sd);
-	mutex_unlock(&sysfs_mutex);
-
-	return sd;
-}
-EXPORT_SYMBOL_GPL(sysfs_get_dirent_ns);
-
-static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
-		      enum kobj_ns_type type,
-		      const char *name, const void *ns,
-		      struct sysfs_dirent **p_sd)
-{
-	umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
-	struct sysfs_addrm_cxt acxt;
-	struct sysfs_dirent *sd;
-	int rc;
-
-	/* allocate */
-	sd = sysfs_new_dirent(name, mode, SYSFS_DIR);
-	if (!sd)
-		return -ENOMEM;
-
-	sd->s_flags |= (type << SYSFS_NS_TYPE_SHIFT);
-	sd->s_ns = ns;
-	sd->s_dir.kobj = kobj;
-
-	/* link in */
-	sysfs_addrm_start(&acxt);
-	rc = sysfs_add_one(&acxt, sd, parent_sd);
-	sysfs_addrm_finish(&acxt);
-
-	if (rc == 0)
-		*p_sd = sd;
-	else
-		sysfs_put(sd);
-
-	return rc;
-}
-
-int sysfs_create_subdir(struct kobject *kobj, const char *name,
-			struct sysfs_dirent **p_sd)
-{
-	return create_dir(kobj, kobj->sd,
-			  KOBJ_NS_TYPE_NONE, name, NULL, p_sd);
-}
-
-/**
- *	sysfs_read_ns_type: return associated ns_type
- *	@kobj: the kobject being queried
- *
- *	Each kobject can be tagged with exactly one namespace type
- *	(i.e. network or user).  Return the ns_type associated with
- *	this object if any
- */
-static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
-{
-	const struct kobj_ns_type_operations *ops;
-	enum kobj_ns_type type;
-
-	ops = kobj_child_ns_ops(kobj);
-	if (!ops)
-		return KOBJ_NS_TYPE_NONE;
-
-	type = ops->type;
-	BUG_ON(type <= KOBJ_NS_TYPE_NONE);
-	BUG_ON(type >= KOBJ_NS_TYPES);
-	BUG_ON(!kobj_ns_type_registered(type));
-
-	return type;
-}
-
 /**
  * sysfs_create_dir_ns - create a directory for an object with a namespace tag
  * @kobj: object we're creating directory for
@@ -737,197 +61,28 @@ static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
  */
 int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
-	enum kobj_ns_type type;
-	struct sysfs_dirent *parent_sd, *sd;
-	int error = 0;
+	struct kernfs_node *parent, *kn;
 
 	BUG_ON(!kobj);
 
 	if (kobj->parent)
-		parent_sd = kobj->parent->sd;
+		parent = kobj->parent->sd;
 	else
-		parent_sd = &sysfs_root;
+		parent = sysfs_root_kn;
 
-	if (!parent_sd)
+	if (!parent)
 		return -ENOENT;
 
-	type = sysfs_read_ns_type(kobj);
-
-	error = create_dir(kobj, parent_sd, type, kobject_name(kobj), ns, &sd);
-	if (!error)
-		kobj->sd = sd;
-	return error;
-}
-
-static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry,
-				   unsigned int flags)
-{
-	struct dentry *ret = NULL;
-	struct dentry *parent = dentry->d_parent;
-	struct sysfs_dirent *parent_sd = parent->d_fsdata;
-	struct sysfs_dirent *sd;
-	struct inode *inode;
-	enum kobj_ns_type type;
-	const void *ns;
-
-	mutex_lock(&sysfs_mutex);
-
-	type = sysfs_ns_type(parent_sd);
-	ns = sysfs_info(dir->i_sb)->ns[type];
-
-	sd = sysfs_find_dirent(parent_sd, dentry->d_name.name, ns);
-
-	/* no such entry */
-	if (!sd) {
-		ret = ERR_PTR(-ENOENT);
-		goto out_unlock;
-	}
-	dentry->d_fsdata = sysfs_get(sd);
-
-	/* attach dentry and inode */
-	inode = sysfs_get_inode(dir->i_sb, sd);
-	if (!inode) {
-		ret = ERR_PTR(-ENOMEM);
-		goto out_unlock;
-	}
-
-	/* instantiate and hash dentry */
-	ret = d_materialise_unique(dentry, inode);
- out_unlock:
-	mutex_unlock(&sysfs_mutex);
-	return ret;
-}
-
-const struct inode_operations sysfs_dir_inode_operations = {
-	.lookup		= sysfs_lookup,
-	.permission	= sysfs_permission,
-	.setattr	= sysfs_setattr,
-	.getattr	= sysfs_getattr,
-	.setxattr	= sysfs_setxattr,
-};
-
-static struct sysfs_dirent *sysfs_leftmost_descendant(struct sysfs_dirent *pos)
-{
-	struct sysfs_dirent *last;
-
-	while (true) {
-		struct rb_node *rbn;
-
-		last = pos;
-
-		if (sysfs_type(pos) != SYSFS_DIR)
-			break;
-
-		rbn = rb_first(&pos->s_dir.children);
-		if (!rbn)
-			break;
-
-		pos = to_sysfs_dirent(rbn);
-	}
-
-	return last;
-}
-
-/**
- * sysfs_next_descendant_post - find the next descendant for post-order walk
- * @pos: the current position (%NULL to initiate traversal)
- * @root: sysfs_dirent whose descendants to walk
- *
- * Find the next descendant to visit for post-order traversal of @root's
- * descendants.  @root is included in the iteration and the last node to be
- * visited.
- */
-static struct sysfs_dirent *sysfs_next_descendant_post(struct sysfs_dirent *pos,
-						       struct sysfs_dirent *root)
-{
-	struct rb_node *rbn;
-
-	lockdep_assert_held(&sysfs_mutex);
-
-	/* if first iteration, visit leftmost descendant which may be root */
-	if (!pos)
-		return sysfs_leftmost_descendant(root);
-
-	/* if we visited @root, we're done */
-	if (pos == root)
-		return NULL;
-
-	/* if there's an unvisited sibling, visit its leftmost descendant */
-	rbn = rb_next(&pos->s_rb);
-	if (rbn)
-		return sysfs_leftmost_descendant(to_sysfs_dirent(rbn));
-
-	/* no sibling left, visit parent */
-	return pos->s_parent;
-}
-
-static void __sysfs_remove(struct sysfs_addrm_cxt *acxt,
-			   struct sysfs_dirent *sd)
-{
-	struct sysfs_dirent *pos, *next;
-
-	if (!sd)
-		return;
-
-	pr_debug("sysfs %s: removing\n", sd->s_name);
-
-	next = NULL;
-	do {
-		pos = next;
-		next = sysfs_next_descendant_post(pos, sd);
-		if (pos)
-			sysfs_remove_one(acxt, pos);
-	} while (next);
-}
-
-/**
- * sysfs_remove - remove a sysfs_dirent recursively
- * @sd: the sysfs_dirent to remove
- *
- * Remove @sd along with all its subdirectories and files.
- */
-void sysfs_remove(struct sysfs_dirent *sd)
-{
-	struct sysfs_addrm_cxt acxt;
-
-	sysfs_addrm_start(&acxt);
-	__sysfs_remove(&acxt, sd);
-	sysfs_addrm_finish(&acxt);
-}
-
-/**
- * sysfs_hash_and_remove - find a sysfs_dirent by name and remove it
- * @dir_sd: parent of the target
- * @name: name of the sysfs_dirent to remove
- * @ns: namespace tag of the sysfs_dirent to remove
- *
- * Look for the sysfs_dirent with @name and @ns under @dir_sd and remove
- * it.  Returns 0 on success, -ENOENT if such entry doesn't exist.
- */
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name,
-			  const void *ns)
-{
-	struct sysfs_addrm_cxt acxt;
-	struct sysfs_dirent *sd;
-
-	if (!dir_sd) {
-		WARN(1, KERN_WARNING "sysfs: can not remove '%s', no directory\n",
-			name);
-		return -ENOENT;
+	kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
+				  S_IRWXU | S_IRUGO | S_IXUGO, kobj, ns);
+	if (IS_ERR(kn)) {
+		if (PTR_ERR(kn) == -EEXIST)
+			sysfs_warn_dup(parent, kobject_name(kobj));
+		return PTR_ERR(kn);
 	}
 
-	sysfs_addrm_start(&acxt);
-
-	sd = sysfs_find_dirent(dir_sd, name, ns);
-	if (sd)
-		__sysfs_remove(&acxt, sd);
-
-	sysfs_addrm_finish(&acxt);
-
-	if (sd)
-		return 0;
-	else
-		return -ENOENT;
+	kobj->sd = kn;
+	return 0;
 }
 
 /**
@@ -940,207 +95,47 @@ int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name,
  */
 void sysfs_remove_dir(struct kobject *kobj)
 {
-	struct sysfs_dirent *sd = kobj->sd;
+	struct kernfs_node *kn = kobj->sd;
 
 	/*
 	 * In general, kboject owner is responsible for ensuring removal
 	 * doesn't race with other operations and sysfs doesn't provide any
 	 * protection; however, when @kobj is used as a symlink target, the
 	 * symlinking entity usually doesn't own @kobj and thus has no
-	 * control over removal.  @kobj->sd may be removed anytime and
-	 * symlink code may end up dereferencing an already freed sd.
+	 * control over removal.  @kobj->sd may be removed anytime
+	 * and symlink code may end up dereferencing an already freed node.
 	 *
-	 * sysfs_symlink_target_lock synchronizes @kobj->sd disassociation
-	 * against symlink operations so that symlink code can safely
-	 * dereference @kobj->sd.
+	 * sysfs_symlink_target_lock synchronizes @kobj->sd
+	 * disassociation against symlink operations so that symlink code
+	 * can safely dereference @kobj->sd.
 	 */
 	spin_lock(&sysfs_symlink_target_lock);
 	kobj->sd = NULL;
 	spin_unlock(&sysfs_symlink_target_lock);
 
-	if (sd) {
-		WARN_ON_ONCE(sysfs_type(sd) != SYSFS_DIR);
-		sysfs_remove(sd);
+	if (kn) {
+		WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR);
+		kernfs_remove(kn);
 	}
 }
 
-int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
-		 const char *new_name, const void *new_ns)
-{
-	int error;
-
-	mutex_lock(&sysfs_mutex);
-
-	error = 0;
-	if ((sd->s_parent == new_parent_sd) && (sd->s_ns == new_ns) &&
-	    (strcmp(sd->s_name, new_name) == 0))
-		goto out;	/* nothing to rename */
-
-	error = -EEXIST;
-	if (sysfs_find_dirent(new_parent_sd, new_name, new_ns))
-		goto out;
-
-	/* rename sysfs_dirent */
-	if (strcmp(sd->s_name, new_name) != 0) {
-		error = -ENOMEM;
-		new_name = kstrdup(new_name, GFP_KERNEL);
-		if (!new_name)
-			goto out;
-
-		kfree(sd->s_name);
-		sd->s_name = new_name;
-	}
-
-	/*
-	 * Move to the appropriate place in the appropriate directories rbtree.
-	 */
-	sysfs_unlink_sibling(sd);
-	sysfs_get(new_parent_sd);
-	sysfs_put(sd->s_parent);
-	sd->s_ns = new_ns;
-	sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
-	sd->s_parent = new_parent_sd;
-	sysfs_link_sibling(sd);
-
-	error = 0;
- out:
-	mutex_unlock(&sysfs_mutex);
-	return error;
-}
-
 int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
 			const void *new_ns)
 {
-	struct sysfs_dirent *parent_sd = kobj->sd->s_parent;
+	struct kernfs_node *parent = kobj->sd->parent;
 
-	return sysfs_rename(kobj->sd, parent_sd, new_name, new_ns);
+	return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
 }
 
 int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
 		      const void *new_ns)
 {
-	struct sysfs_dirent *sd = kobj->sd;
-	struct sysfs_dirent *new_parent_sd;
+	struct kernfs_node *kn = kobj->sd;
+	struct kernfs_node *new_parent;
 
-	BUG_ON(!sd->s_parent);
-	new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
-		new_parent_kobj->sd : &sysfs_root;
+	BUG_ON(!kn->parent);
+	new_parent = new_parent_kobj && new_parent_kobj->sd ?
+		new_parent_kobj->sd : sysfs_root_kn;
 
-	return sysfs_rename(sd, new_parent_sd, sd->s_name, new_ns);
+	return kernfs_rename_ns(kn, new_parent, kn->name, new_ns);
 }
-
-/* Relationship between s_mode and the DT_xxx types */
-static inline unsigned char dt_type(struct sysfs_dirent *sd)
-{
-	return (sd->s_mode >> 12) & 15;
-}
-
-static int sysfs_dir_release(struct inode *inode, struct file *filp)
-{
-	sysfs_put(filp->private_data);
-	return 0;
-}
-
-static struct sysfs_dirent *sysfs_dir_pos(const void *ns,
-	struct sysfs_dirent *parent_sd,	loff_t hash, struct sysfs_dirent *pos)
-{
-	if (pos) {
-		int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) &&
-			pos->s_parent == parent_sd &&
-			hash == pos->s_hash;
-		sysfs_put(pos);
-		if (!valid)
-			pos = NULL;
-	}
-	if (!pos && (hash > 1) && (hash < INT_MAX)) {
-		struct rb_node *node = parent_sd->s_dir.children.rb_node;
-		while (node) {
-			pos = to_sysfs_dirent(node);
-
-			if (hash < pos->s_hash)
-				node = node->rb_left;
-			else if (hash > pos->s_hash)
-				node = node->rb_right;
-			else
-				break;
-		}
-	}
-	/* Skip over entries in the wrong namespace */
-	while (pos && pos->s_ns != ns) {
-		struct rb_node *node = rb_next(&pos->s_rb);
-		if (!node)
-			pos = NULL;
-		else
-			pos = to_sysfs_dirent(node);
-	}
-	return pos;
-}
-
-static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns,
-	struct sysfs_dirent *parent_sd,	ino_t ino, struct sysfs_dirent *pos)
-{
-	pos = sysfs_dir_pos(ns, parent_sd, ino, pos);
-	if (pos)
-		do {
-			struct rb_node *node = rb_next(&pos->s_rb);
-			if (!node)
-				pos = NULL;
-			else
-				pos = to_sysfs_dirent(node);
-		} while (pos && pos->s_ns != ns);
-	return pos;
-}
-
-static int sysfs_readdir(struct file *file, struct dir_context *ctx)
-{
-	struct dentry *dentry = file->f_path.dentry;
-	struct sysfs_dirent *parent_sd = dentry->d_fsdata;
-	struct sysfs_dirent *pos = file->private_data;
-	enum kobj_ns_type type;
-	const void *ns;
-
-	type = sysfs_ns_type(parent_sd);
-	ns = sysfs_info(dentry->d_sb)->ns[type];
-
-	if (!dir_emit_dots(file, ctx))
-		return 0;
-	mutex_lock(&sysfs_mutex);
-	for (pos = sysfs_dir_pos(ns, parent_sd, ctx->pos, pos);
-	     pos;
-	     pos = sysfs_dir_next_pos(ns, parent_sd, ctx->pos, pos)) {
-		const char *name = pos->s_name;
-		unsigned int type = dt_type(pos);
-		int len = strlen(name);
-		ino_t ino = pos->s_ino;
-		ctx->pos = pos->s_hash;
-		file->private_data = sysfs_get(pos);
-
-		mutex_unlock(&sysfs_mutex);
-		if (!dir_emit(ctx, name, len, ino, type))
-			return 0;
-		mutex_lock(&sysfs_mutex);
-	}
-	mutex_unlock(&sysfs_mutex);
-	file->private_data = NULL;
-	ctx->pos = INT_MAX;
-	return 0;
-}
-
-static loff_t sysfs_dir_llseek(struct file *file, loff_t offset, int whence)
-{
-	struct inode *inode = file_inode(file);
-	loff_t ret;
-
-	mutex_lock(&inode->i_mutex);
-	ret = generic_file_llseek(file, offset, whence);
-	mutex_unlock(&inode->i_mutex);
-
-	return ret;
-}
-
-const struct file_operations sysfs_dir_operations = {
-	.read		= generic_read_dir,
-	.iterate	= sysfs_readdir,
-	.release	= sysfs_dir_release,
-	.llseek		= sysfs_dir_llseek,
-};

fs/sysfs/file.c

@@ -14,70 +14,23 @@
 #include <linux/kobject.h>
 #include <linux/kallsyms.h>
 #include <linux/slab.h>
-#include <linux/fsnotify.h>
-#include <linux/namei.h>
-#include <linux/poll.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
-#include <linux/limits.h>
-#include <linux/uaccess.h>
 #include <linux/seq_file.h>
-#include <linux/mm.h>
 
 #include "sysfs.h"
+#include "../kernfs/kernfs-internal.h"
 
 /*
- * There's one sysfs_open_file for each open file and one sysfs_open_dirent
- * for each sysfs_dirent with one or more open files.
- *
- * sysfs_dirent->s_attr.open points to sysfs_open_dirent.  s_attr.open is
- * protected by sysfs_open_dirent_lock.
- *
- * filp->private_data points to seq_file whose ->private points to
- * sysfs_open_file.  sysfs_open_files are chained at
- * sysfs_open_dirent->files, which is protected by sysfs_open_file_mutex.
- */
-static DEFINE_SPINLOCK(sysfs_open_dirent_lock);
-static DEFINE_MUTEX(sysfs_open_file_mutex);
-
-struct sysfs_open_dirent {
-	atomic_t		refcnt;
-	atomic_t		event;
-	wait_queue_head_t	poll;
-	struct list_head	files; /* goes through sysfs_open_file.list */
-};
-
-struct sysfs_open_file {
-	struct sysfs_dirent	*sd;
-	struct file		*file;
-	struct mutex		mutex;
-	int			event;
-	struct list_head	list;
-
-	bool			mmapped;
-	const struct vm_operations_struct *vm_ops;
-};
-
-static bool sysfs_is_bin(struct sysfs_dirent *sd)
-{
-	return sysfs_type(sd) == SYSFS_KOBJ_BIN_ATTR;
-}
-
-static struct sysfs_open_file *sysfs_of(struct file *file)
-{
-	return ((struct seq_file *)file->private_data)->private;
-}
-
-/*
- * Determine ktype->sysfs_ops for the given sysfs_dirent.  This function
+ * Determine ktype->sysfs_ops for the given kernfs_node.  This function
  * must be called while holding an active reference.
  */
-static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd)
+static const struct sysfs_ops *sysfs_file_ops(struct kernfs_node *kn)
 {
-	struct kobject *kobj = sd->s_parent->s_dir.kobj;
+	struct kobject *kobj = kn->parent->priv;
 
-	if (!sysfs_ignore_lockdep(sd))
-		lockdep_assert_held(sd);
+	if (kn->flags & KERNFS_LOCKDEP)
+		lockdep_assert_held(kn);
 	return kobj->ktype ? kobj->ktype->sysfs_ops : NULL;
 }
 
@@ -86,13 +39,13 @@ static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd)
  * details like buffering and seeking.  The following function pipes
  * sysfs_ops->show() result through seq_file.
  */
-static int sysfs_seq_show(struct seq_file *sf, void *v)
+static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
 {
-	struct sysfs_open_file *of = sf->private;
-	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
-	const struct sysfs_ops *ops;
-	char *buf;
+	struct kernfs_open_file *of = sf->private;
+	struct kobject *kobj = of->kn->parent->priv;
+	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	ssize_t count;
+	char *buf;
 
 	/* acquire buffer and ensure that it's >= PAGE_SIZE */
 	count = seq_get_buf(sf, &buf);
@@ -102,34 +55,15 @@ static int sysfs_seq_show(struct seq_file *sf, void *v)
 	}
 
 	/*
-	 * Need @of->sd for attr and ops, its parent for kobj.  @of->mutex
-	 * nests outside active ref and is just to ensure that the ops
-	 * aren't called concurrently for the same open file.
+	 * Invoke show().  Control may reach here via seq file lseek even
+	 * if @ops->show() isn't implemented.
 	 */
-	mutex_lock(&of->mutex);
-	if (!sysfs_get_active(of->sd)) {
-		mutex_unlock(&of->mutex);
-		return -ENODEV;
+	if (ops->show) {
+		count = ops->show(kobj, of->kn->priv, buf);
+		if (count < 0)
+			return count;
 	}
 
-	of->event = atomic_read(&of->sd->s_attr.open->event);
-
-	/*
-	 * Lookup @ops and invoke show().  Control may reach here via seq
-	 * file lseek even if @ops->show() isn't implemented.
-	 */
-	ops = sysfs_file_ops(of->sd);
-	if (ops->show)
-		count = ops->show(kobj, of->sd->s_attr.attr, buf);
-	else
-		count = 0;
-
-	sysfs_put_active(of->sd);
-	mutex_unlock(&of->mutex);
-
-	if (count < 0)
-		return count;
-
 	/*
 	 * The code works fine with PAGE_SIZE return but it's likely to
 	 * indicate truncated result or overflow in normal use cases.
@@ -144,726 +78,194 @@ static int sysfs_seq_show(struct seq_file *sf, void *v)
 	return 0;
 }
 
-/*
- * Read method for bin files.  As reading a bin file can have side-effects,
- * the exact offset and bytes specified in read(2) call should be passed to
- * the read callback making it difficult to use seq_file.  Implement
- * simplistic custom buffering for bin files.
- */
-static ssize_t sysfs_bin_read(struct file *file, char __user *userbuf,
-			      size_t bytes, loff_t *off)
+static ssize_t sysfs_kf_bin_read(struct kernfs_open_file *of, char *buf,
+				 size_t count, loff_t pos)
 {
-	struct sysfs_open_file *of = sysfs_of(file);
-	struct bin_attribute *battr = of->sd->s_attr.bin_attr;
-	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
-	loff_t size = file_inode(file)->i_size;
-	int count = min_t(size_t, bytes, PAGE_SIZE);
-	loff_t offs = *off;
-	char *buf;
+	struct bin_attribute *battr = of->kn->priv;
+	struct kobject *kobj = of->kn->parent->priv;
+	loff_t size = file_inode(of->file)->i_size;
 
-	if (!bytes)
+	if (!count)
 		return 0;
 
 	if (size) {
-		if (offs > size)
+		if (pos > size)
 			return 0;
-		if (offs + count > size)
-			count = size - offs;
-	}
-
-	buf = kmalloc(count, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	/* need of->sd for battr, its parent for kobj */
-	mutex_lock(&of->mutex);
-	if (!sysfs_get_active(of->sd)) {
-		count = -ENODEV;
-		mutex_unlock(&of->mutex);
-		goto out_free;
-	}
-
-	if (battr->read)
-		count = battr->read(file, kobj, battr, buf, offs, count);
-	else
-		count = -EIO;
-
-	sysfs_put_active(of->sd);
-	mutex_unlock(&of->mutex);
-
-	if (count < 0)
-		goto out_free;
-
-	if (copy_to_user(userbuf, buf, count)) {
-		count = -EFAULT;
-		goto out_free;
+		if (pos + count > size)
+			count = size - pos;
 	}
 
-	pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
-
-	*off = offs + count;
+	if (!battr->read)
+		return -EIO;
 
- out_free:
-	kfree(buf);
-	return count;
+	return battr->read(of->file, kobj, battr, buf, pos, count);
 }
 
-/**
- * flush_write_buffer - push buffer to kobject
- * @of: open file
- * @buf: data buffer for file
- * @off: file offset to write to
- * @count: number of bytes
- *
- * Get the correct pointers for the kobject and the attribute we're dealing
- * with, then call the store() method for it with @buf.
- */
-static int flush_write_buffer(struct sysfs_open_file *of, char *buf, loff_t off,
-			      size_t count)
+/* kernfs write callback for regular sysfs files */
+static ssize_t sysfs_kf_write(struct kernfs_open_file *of, char *buf,
+			      size_t count, loff_t pos)
 {
-	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
-	int rc = 0;
-
-	/*
-	 * Need @of->sd for attr and ops, its parent for kobj.  @of->mutex
-	 * nests outside active ref and is just to ensure that the ops
-	 * aren't called concurrently for the same open file.
-	 */
-	mutex_lock(&of->mutex);
-	if (!sysfs_get_active(of->sd)) {
-		mutex_unlock(&of->mutex);
-		return -ENODEV;
-	}
+	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
+	struct kobject *kobj = of->kn->parent->priv;
 
-	if (sysfs_is_bin(of->sd)) {
-		struct bin_attribute *battr = of->sd->s_attr.bin_attr;
-
-		rc = -EIO;
-		if (battr->write)
-			rc = battr->write(of->file, kobj, battr, buf, off,
-					  count);
-	} else {
-		const struct sysfs_ops *ops = sysfs_file_ops(of->sd);
-
-		rc = ops->store(kobj, of->sd->s_attr.attr, buf, count);
-	}
-
-	sysfs_put_active(of->sd);
-	mutex_unlock(&of->mutex);
+	if (!count)
+		return 0;
 
-	return rc;
+	return ops->store(kobj, of->kn->priv, buf, count);
 }
 
-/**
- * sysfs_write_file - write an attribute
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- *
- * Copy data in from userland and pass it to the matching
- * sysfs_ops->store() by invoking 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 sysfs_write_file(struct file *file, const char __user *user_buf,
-				size_t count, loff_t *ppos)
+/* kernfs write callback for bin sysfs files */
+static ssize_t sysfs_kf_bin_write(struct kernfs_open_file *of, char *buf,
+				  size_t count, loff_t pos)
 {
-	struct sysfs_open_file *of = sysfs_of(file);
-	ssize_t len = min_t(size_t, count, PAGE_SIZE);
-	loff_t size = file_inode(file)->i_size;
-	char *buf;
+	struct bin_attribute *battr = of->kn->priv;
+	struct kobject *kobj = of->kn->parent->priv;
+	loff_t size = file_inode(of->file)->i_size;
 
-	if (sysfs_is_bin(of->sd) && size) {
-		if (size <= *ppos)
+	if (size) {
+		if (size <= pos)
 			return 0;
-		len = min_t(ssize_t, len, size - *ppos);
+		count = min_t(ssize_t, count, size - pos);
 	}
-
-	if (!len)
+	if (!count)
 		return 0;
 
-	buf = kmalloc(len + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
+	if (!battr->write)
+		return -EIO;
 
-	if (copy_from_user(buf, user_buf, len)) {
-		len = -EFAULT;
-		goto out_free;
-	}
-	buf[len] = '\0';	/* guarantee string termination */
-
-	len = flush_write_buffer(of, buf, *ppos, len);
-	if (len > 0)
-		*ppos += len;
-out_free:
-	kfree(buf);
-	return len;
-}
-
-static void sysfs_bin_vma_open(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-
-	if (!of->vm_ops)
-		return;
-
-	if (!sysfs_get_active(of->sd))
-		return;
-
-	if (of->vm_ops->open)
-		of->vm_ops->open(vma);
-
-	sysfs_put_active(of->sd);
+	return battr->write(of->file, kobj, battr, buf, pos, count);
 }
 
-static int sysfs_bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int sysfs_kf_bin_mmap(struct kernfs_open_file *of,
+			     struct vm_area_struct *vma)
 {
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	int ret;
+	struct bin_attribute *battr = of->kn->priv;
+	struct kobject *kobj = of->kn->parent->priv;
 
-	if (!of->vm_ops)
-		return VM_FAULT_SIGBUS;
-
-	if (!sysfs_get_active(of->sd))
-		return VM_FAULT_SIGBUS;
-
-	ret = VM_FAULT_SIGBUS;
-	if (of->vm_ops->fault)
-		ret = of->vm_ops->fault(vma, vmf);
-
-	sysfs_put_active(of->sd);
-	return ret;
+	return battr->mmap(of->file, kobj, battr, vma);
 }
 
-static int sysfs_bin_page_mkwrite(struct vm_area_struct *vma,
-				  struct vm_fault *vmf)
+void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr)
 {
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return VM_FAULT_SIGBUS;
+	struct kernfs_node *kn = kobj->sd, *tmp;
 
-	if (!sysfs_get_active(of->sd))
-		return VM_FAULT_SIGBUS;
-
-	ret = 0;
-	if (of->vm_ops->page_mkwrite)
-		ret = of->vm_ops->page_mkwrite(vma, vmf);
+	if (kn && dir)
+		kn = kernfs_find_and_get(kn, dir);
 	else
-		file_update_time(file);
-
-	sysfs_put_active(of->sd);
-	return ret;
-}
-
-static int sysfs_bin_access(struct vm_area_struct *vma, unsigned long addr,
-			    void *buf, int len, int write)
-{
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return -EINVAL;
-
-	if (!sysfs_get_active(of->sd))
-		return -EINVAL;
-
-	ret = -EINVAL;
-	if (of->vm_ops->access)
-		ret = of->vm_ops->access(vma, addr, buf, len, write);
-
-	sysfs_put_active(of->sd);
-	return ret;
-}
-
-#ifdef CONFIG_NUMA
-static int sysfs_bin_set_policy(struct vm_area_struct *vma,
-				struct mempolicy *new)
-{
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return 0;
-
-	if (!sysfs_get_active(of->sd))
-		return -EINVAL;
-
-	ret = 0;
-	if (of->vm_ops->set_policy)
-		ret = of->vm_ops->set_policy(vma, new);
-
-	sysfs_put_active(of->sd);
-	return ret;
-}
-
-static struct mempolicy *sysfs_bin_get_policy(struct vm_area_struct *vma,
-					      unsigned long addr)
-{
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	struct mempolicy *pol;
-
-	if (!of->vm_ops)
-		return vma->vm_policy;
-
-	if (!sysfs_get_active(of->sd))
-		return vma->vm_policy;
-
-	pol = vma->vm_policy;
-	if (of->vm_ops->get_policy)
-		pol = of->vm_ops->get_policy(vma, addr);
-
-	sysfs_put_active(of->sd);
-	return pol;
-}
-
-static int sysfs_bin_migrate(struct vm_area_struct *vma, const nodemask_t *from,
-			     const nodemask_t *to, unsigned long flags)
-{
-	struct file *file = vma->vm_file;
-	struct sysfs_open_file *of = sysfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return 0;
-
-	if (!sysfs_get_active(of->sd))
-		return 0;
-
-	ret = 0;
-	if (of->vm_ops->migrate)
-		ret = of->vm_ops->migrate(vma, from, to, flags);
-
-	sysfs_put_active(of->sd);
-	return ret;
-}
-#endif
-
-static const struct vm_operations_struct sysfs_bin_vm_ops = {
-	.open		= sysfs_bin_vma_open,
-	.fault		= sysfs_bin_fault,
-	.page_mkwrite	= sysfs_bin_page_mkwrite,
-	.access		= sysfs_bin_access,
-#ifdef CONFIG_NUMA
-	.set_policy	= sysfs_bin_set_policy,
-	.get_policy	= sysfs_bin_get_policy,
-	.migrate	= sysfs_bin_migrate,
-#endif
-};
-
-static int sysfs_bin_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct sysfs_open_file *of = sysfs_of(file);
-	struct bin_attribute *battr = of->sd->s_attr.bin_attr;
-	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
-	int rc;
-
-	mutex_lock(&of->mutex);
-
-	/* need of->sd for battr, its parent for kobj */
-	rc = -ENODEV;
-	if (!sysfs_get_active(of->sd))
-		goto out_unlock;
-
-	if (!battr->mmap)
-		goto out_put;
-
-	rc = battr->mmap(file, kobj, battr, vma);
-	if (rc)
-		goto out_put;
-
-	/*
-	 * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
-	 * to satisfy versions of X which crash if the mmap fails: that
-	 * substitutes a new vm_file, and we don't then want bin_vm_ops.
-	 */
-	if (vma->vm_file != file)
-		goto out_put;
-
-	rc = -EINVAL;
-	if (of->mmapped && of->vm_ops != vma->vm_ops)
-		goto out_put;
+		kernfs_get(kn);
 
-	/*
-	 * It is not possible to successfully wrap close.
-	 * So error if someone is trying to use close.
-	 */
-	rc = -EINVAL;
-	if (vma->vm_ops && vma->vm_ops->close)
-		goto out_put;
-
-	rc = 0;
-	of->mmapped = 1;
-	of->vm_ops = vma->vm_ops;
-	vma->vm_ops = &sysfs_bin_vm_ops;
-out_put:
-	sysfs_put_active(of->sd);
-out_unlock:
-	mutex_unlock(&of->mutex);
-
-	return rc;
-}
-
-/**
- *	sysfs_get_open_dirent - get or create sysfs_open_dirent
- *	@sd: target sysfs_dirent
- *	@of: sysfs_open_file for this instance of open
- *
- *	If @sd->s_attr.open exists, increment its reference count;
- *	otherwise, create one.  @of is chained to the files list.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).
- *
- *	RETURNS:
- *	0 on success, -errno on failure.
- */
-static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
-				 struct sysfs_open_file *of)
-{
-	struct sysfs_open_dirent *od, *new_od = NULL;
-
- retry:
-	mutex_lock(&sysfs_open_file_mutex);
-	spin_lock_irq(&sysfs_open_dirent_lock);
-
-	if (!sd->s_attr.open && new_od) {
-		sd->s_attr.open = new_od;
-		new_od = NULL;
+	if (kn && attr) {
+		tmp = kernfs_find_and_get(kn, attr);
+		kernfs_put(kn);
+		kn = tmp;
 	}
 
-	od = sd->s_attr.open;
-	if (od) {
-		atomic_inc(&od->refcnt);
-		list_add_tail(&of->list, &od->files);
-	}
-
-	spin_unlock_irq(&sysfs_open_dirent_lock);
-	mutex_unlock(&sysfs_open_file_mutex);
-
-	if (od) {
-		kfree(new_od);
-		return 0;
+	if (kn) {
+		kernfs_notify(kn);
+		kernfs_put(kn);
 	}
+}
+EXPORT_SYMBOL_GPL(sysfs_notify);
 
-	/* not there, initialize a new one and retry */
-	new_od = kmalloc(sizeof(*new_od), GFP_KERNEL);
-	if (!new_od)
-		return -ENOMEM;
+static const struct kernfs_ops sysfs_file_kfops_empty = {
+};
 
-	atomic_set(&new_od->refcnt, 0);
-	atomic_set(&new_od->event, 1);
-	init_waitqueue_head(&new_od->poll);
-	INIT_LIST_HEAD(&new_od->files);
-	goto retry;
-}
+static const struct kernfs_ops sysfs_file_kfops_ro = {
+	.seq_show	= sysfs_kf_seq_show,
+};
 
-/**
- *	sysfs_put_open_dirent - put sysfs_open_dirent
- *	@sd: target sysfs_dirent
- *	@of: associated sysfs_open_file
- *
- *	Put @sd->s_attr.open and unlink @of from the files list.  If
- *	reference count reaches zero, disassociate and free it.
- *
- *	LOCKING:
- *	None.
- */
-static void sysfs_put_open_dirent(struct sysfs_dirent *sd,
-				  struct sysfs_open_file *of)
-{
-	struct sysfs_open_dirent *od = sd->s_attr.open;
-	unsigned long flags;
+static const struct kernfs_ops sysfs_file_kfops_wo = {
+	.write		= sysfs_kf_write,
+};
 
-	mutex_lock(&sysfs_open_file_mutex);
-	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);
+static const struct kernfs_ops sysfs_file_kfops_rw = {
+	.seq_show	= sysfs_kf_seq_show,
+	.write		= sysfs_kf_write,
+};
 
-	if (of)
-		list_del(&of->list);
+static const struct kernfs_ops sysfs_bin_kfops_ro = {
+	.read		= sysfs_kf_bin_read,
+};
 
-	if (atomic_dec_and_test(&od->refcnt))
-		sd->s_attr.open = NULL;
-	else
-		od = NULL;
+static const struct kernfs_ops sysfs_bin_kfops_wo = {
+	.write		= sysfs_kf_bin_write,
+};
 
-	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
-	mutex_unlock(&sysfs_open_file_mutex);
+static const struct kernfs_ops sysfs_bin_kfops_rw = {
+	.read		= sysfs_kf_bin_read,
+	.write		= sysfs_kf_bin_write,
+};
 
-	kfree(od);
-}
+static const struct kernfs_ops sysfs_bin_kfops_mmap = {
+	.read		= sysfs_kf_bin_read,
+	.write		= sysfs_kf_bin_write,
+	.mmap		= sysfs_kf_bin_mmap,
+};
 
-static int sysfs_open_file(struct inode *inode, struct file *file)
+int sysfs_add_file_mode_ns(struct kernfs_node *parent,
+			   const struct attribute *attr, bool is_bin,
+			   umode_t mode, const void *ns)
 {
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	struct sysfs_open_file *of;
-	bool has_read, has_write;
-	int error = -EACCES;
-
-	/* need attr_sd for attr and ops, its parent for kobj */
-	if (!sysfs_get_active(attr_sd))
-		return -ENODEV;
+	struct lock_class_key *key = NULL;
+	const struct kernfs_ops *ops;
+	struct kernfs_node *kn;
+	loff_t size;
 
-	if (sysfs_is_bin(attr_sd)) {
-		struct bin_attribute *battr = attr_sd->s_attr.bin_attr;
-
-		has_read = battr->read || battr->mmap;
-		has_write = battr->write || battr->mmap;
-	} else {
-		const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
+	if (!is_bin) {
+		struct kobject *kobj = parent->priv;
+		const struct sysfs_ops *sysfs_ops = kobj->ktype->sysfs_ops;
 
 		/* every kobject with an attribute needs a ktype assigned */
-		if (WARN(!ops, KERN_ERR
+		if (WARN(!sysfs_ops, KERN_ERR
 			 "missing sysfs attribute operations for kobject: %s\n",
 			 kobject_name(kobj)))
-			goto err_out;
-
-		has_read = ops->show;
-		has_write = ops->store;
-	}
-
-	/* check perms and supported operations */
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (!(inode->i_mode & S_IWUGO) || !has_write))
-		goto err_out;
-
-	if ((file->f_mode & FMODE_READ) &&
-	    (!(inode->i_mode & S_IRUGO) || !has_read))
-		goto err_out;
-
-	/* allocate a sysfs_open_file for the file */
-	error = -ENOMEM;
-	of = kzalloc(sizeof(struct sysfs_open_file), GFP_KERNEL);
-	if (!of)
-		goto err_out;
-
-	/*
-	 * The following is done to give a different lockdep key to
-	 * @of->mutex for files which implement mmap.  This is a rather
-	 * crude way to avoid false positive lockdep warning around
-	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
-	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
-	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
-	 * open file has a separate mutex, it's okay as long as those don't
-	 * happen on the same file.  At this point, we can't easily give
-	 * each file a separate locking class.  Let's differentiate on
-	 * whether the file is bin or not for now.
-	 */
-	if (sysfs_is_bin(attr_sd))
-		mutex_init(&of->mutex);
-	else
-		mutex_init(&of->mutex);
-
-	of->sd = attr_sd;
-	of->file = file;
-
-	/*
-	 * Always instantiate seq_file even if read access doesn't use
-	 * seq_file or is not requested.  This unifies private data access
-	 * and readable regular files are the vast majority anyway.
-	 */
-	if (sysfs_is_bin(attr_sd))
-		error = single_open(file, NULL, of);
-	else
-		error = single_open(file, sysfs_seq_show, of);
-	if (error)
-		goto err_free;
-
-	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
-	if (file->f_mode & FMODE_WRITE)
-		file->f_mode |= FMODE_PWRITE;
-
-	/* make sure we have open dirent struct */
-	error = sysfs_get_open_dirent(attr_sd, of);
-	if (error)
-		goto err_close;
-
-	/* open succeeded, put active references */
-	sysfs_put_active(attr_sd);
-	return 0;
-
-err_close:
-	single_release(inode, file);
-err_free:
-	kfree(of);
-err_out:
-	sysfs_put_active(attr_sd);
-	return error;
-}
-
-static int sysfs_release(struct inode *inode, struct file *filp)
-{
-	struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata;
-	struct sysfs_open_file *of = sysfs_of(filp);
-
-	sysfs_put_open_dirent(sd, of);
-	single_release(inode, filp);
-	kfree(of);
-
-	return 0;
-}
-
-void sysfs_unmap_bin_file(struct sysfs_dirent *sd)
-{
-	struct sysfs_open_dirent *od;
-	struct sysfs_open_file *of;
-
-	if (!sysfs_is_bin(sd))
-		return;
-
-	spin_lock_irq(&sysfs_open_dirent_lock);
-	od = sd->s_attr.open;
-	if (od)
-		atomic_inc(&od->refcnt);
-	spin_unlock_irq(&sysfs_open_dirent_lock);
-	if (!od)
-		return;
-
-	mutex_lock(&sysfs_open_file_mutex);
-	list_for_each_entry(of, &od->files, list) {
-		struct inode *inode = file_inode(of->file);
-		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+			return -EINVAL;
+
+		if (sysfs_ops->show && sysfs_ops->store)
+			ops = &sysfs_file_kfops_rw;
+		else if (sysfs_ops->show)
+			ops = &sysfs_file_kfops_ro;
+		else if (sysfs_ops->store)
+			ops = &sysfs_file_kfops_wo;
+		else
+			ops = &sysfs_file_kfops_empty;
+
+		size = PAGE_SIZE;
+	} else {
+		struct bin_attribute *battr = (void *)attr;
+
+		if (battr->mmap)
+			ops = &sysfs_bin_kfops_mmap;
+		else if (battr->read && battr->write)
+			ops = &sysfs_bin_kfops_rw;
+		else if (battr->read)
+			ops = &sysfs_bin_kfops_ro;
+		else if (battr->write)
+			ops = &sysfs_bin_kfops_wo;
+		else
+			ops = &sysfs_file_kfops_empty;
+
+		size = battr->size;
 	}
-	mutex_unlock(&sysfs_open_file_mutex);
-
-	sysfs_put_open_dirent(sd, NULL);
-}
-
-/* Sysfs attribute files are pollable.  The idea is that you read
- * the content and then you use 'poll' or 'select' to wait for
- * the content to change.  When the content changes (assuming the
- * manager for the kobject supports notification), poll will
- * return POLLERR|POLLPRI, and select will return the fd whether
- * it is waiting for read, write, or exceptions.
- * Once poll/select indicates that the value has changed, you
- * need to close and re-open the file, or seek to 0 and read again.
- * Reminder: this only works for attributes which actively support
- * it, and it is not possible to test an attribute from userspace
- * to see if it supports poll (Neither 'poll' nor 'select' return
- * an appropriate error code).  When in doubt, set a suitable timeout value.
- */
-static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
-{
-	struct sysfs_open_file *of = sysfs_of(filp);
-	struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
-	struct sysfs_open_dirent *od = attr_sd->s_attr.open;
-
-	/* need parent for the kobj, grab both */
-	if (!sysfs_get_active(attr_sd))
-		goto trigger;
-
-	poll_wait(filp, &od->poll, wait);
 
-	sysfs_put_active(attr_sd);
-
-	if (of->event != atomic_read(&od->event))
-		goto trigger;
-
-	return DEFAULT_POLLMASK;
-
- trigger:
-	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
-}
-
-void sysfs_notify_dirent(struct sysfs_dirent *sd)
-{
-	struct sysfs_open_dirent *od;
-	unsigned long flags;
-
-	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);
-
-	if (!WARN_ON(sysfs_type(sd) != SYSFS_KOBJ_ATTR)) {
-		od = sd->s_attr.open;
-		if (od) {
-			atomic_inc(&od->event);
-			wake_up_interruptible(&od->poll);
-		}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	if (!attr->ignore_lockdep)
+		key = attr->key ?: (struct lock_class_key *)&attr->skey;
+#endif
+	kn = __kernfs_create_file(parent, attr->name, mode, size, ops,
+				  (void *)attr, ns, true, key);
+	if (IS_ERR(kn)) {
+		if (PTR_ERR(kn) == -EEXIST)
+			sysfs_warn_dup(parent, attr->name);
+		return PTR_ERR(kn);
 	}
-
-	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
-}
-EXPORT_SYMBOL_GPL(sysfs_notify_dirent);
-
-void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
-{
-	struct sysfs_dirent *sd = k->sd;
-
-	mutex_lock(&sysfs_mutex);
-
-	if (sd && dir)
-		sd = sysfs_find_dirent(sd, dir, NULL);
-	if (sd && attr)
-		sd = sysfs_find_dirent(sd, attr, NULL);
-	if (sd)
-		sysfs_notify_dirent(sd);
-
-	mutex_unlock(&sysfs_mutex);
-}
-EXPORT_SYMBOL_GPL(sysfs_notify);
-
-const struct file_operations sysfs_file_operations = {
-	.read		= seq_read,
-	.write		= sysfs_write_file,
-	.llseek		= generic_file_llseek,
-	.open		= sysfs_open_file,
-	.release	= sysfs_release,
-	.poll		= sysfs_poll,
-};
-
-const struct file_operations sysfs_bin_operations = {
-	.read		= sysfs_bin_read,
-	.write		= sysfs_write_file,
-	.llseek		= generic_file_llseek,
-	.mmap		= sysfs_bin_mmap,
-	.open		= sysfs_open_file,
-	.release	= sysfs_release,
-	.poll		= sysfs_poll,
-};
-
-int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
-			   const struct attribute *attr, int type,
-			   umode_t amode, const void *ns)
-{
-	umode_t mode = (amode & S_IALLUGO) | S_IFREG;
-	struct sysfs_addrm_cxt acxt;
-	struct sysfs_dirent *sd;
-	int rc;
-
-	sd = sysfs_new_dirent(attr->name, mode, type);
-	if (!sd)
-		return -ENOMEM;
-
-	sd->s_ns = ns;
-	sd->s_attr.attr = (void *)attr;
-	sysfs_dirent_init_lockdep(sd);
-
-	sysfs_addrm_start(&acxt);
-	rc = sysfs_add_one(&acxt, sd, dir_sd);
-	sysfs_addrm_finish(&acxt);
-
-	if (rc)
-		sysfs_put(sd);
-
-	return rc;
+	return 0;
 }
 
-
-int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
-		   int type)
+int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr,
+		   bool is_bin)
 {
-	return sysfs_add_file_mode_ns(dir_sd, attr, type, attr->mode, NULL);
+	return sysfs_add_file_mode_ns(parent, attr, is_bin, attr->mode, NULL);
 }
 
 /**
@@ -877,8 +279,7 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
 {
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file_mode_ns(kobj->sd, attr, SYSFS_KOBJ_ATTR,
-				      attr->mode, ns);
+	return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns);
 
 }
 EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
@@ -906,19 +307,21 @@ EXPORT_SYMBOL_GPL(sysfs_create_files);
 int sysfs_add_file_to_group(struct kobject *kobj,
 		const struct attribute *attr, const char *group)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 	int error;
 
-	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, group);
-	else
-		dir_sd = sysfs_get(kobj->sd);
+	if (group) {
+		parent = kernfs_find_and_get(kobj->sd, group);
+	} else {
+		parent = kobj->sd;
+		kernfs_get(parent);
+	}
 
-	if (!dir_sd)
+	if (!parent)
 		return -ENOENT;
 
-	error = sysfs_add_file(dir_sd, attr, SYSFS_KOBJ_ATTR);
-	sysfs_put(dir_sd);
+	error = sysfs_add_file(parent, attr, false);
+	kernfs_put(parent);
 
 	return error;
 }
@@ -934,23 +337,20 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group);
 int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 		     umode_t mode)
 {
-	struct sysfs_dirent *sd;
+	struct kernfs_node *kn;
 	struct iattr newattrs;
 	int rc;
 
-	mutex_lock(&sysfs_mutex);
-
-	rc = -ENOENT;
-	sd = sysfs_find_dirent(kobj->sd, attr->name, NULL);
-	if (!sd)
-		goto out;
+	kn = kernfs_find_and_get(kobj->sd, attr->name);
+	if (!kn)
+		return -ENOENT;
 
-	newattrs.ia_mode = (mode & S_IALLUGO) | (sd->s_mode & ~S_IALLUGO);
+	newattrs.ia_mode = (mode & S_IALLUGO) | (kn->mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE;
-	rc = sysfs_sd_setattr(sd, &newattrs);
 
- out:
-	mutex_unlock(&sysfs_mutex);
+	rc = kernfs_setattr(kn, &newattrs);
+
+	kernfs_put(kn);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(sysfs_chmod_file);
@@ -966,9 +366,9 @@ EXPORT_SYMBOL_GPL(sysfs_chmod_file);
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 			  const void *ns)
 {
-	struct sysfs_dirent *dir_sd = kobj->sd;
+	struct kernfs_node *parent = kobj->sd;
 
-	sysfs_hash_and_remove(dir_sd, attr->name, ns);
+	kernfs_remove_by_name_ns(parent, attr->name, ns);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
@@ -989,15 +389,18 @@ EXPORT_SYMBOL_GPL(sysfs_remove_files);
 void sysfs_remove_file_from_group(struct kobject *kobj,
 		const struct attribute *attr, const char *group)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 
-	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, group);
-	else
-		dir_sd = sysfs_get(kobj->sd);
-	if (dir_sd) {
-		sysfs_hash_and_remove(dir_sd, attr->name, NULL);
-		sysfs_put(dir_sd);
+	if (group) {
+		parent = kernfs_find_and_get(kobj->sd, group);
+	} else {
+		parent = kobj->sd;
+		kernfs_get(parent);
+	}
+
+	if (parent) {
+		kernfs_remove_by_name(parent, attr->name);
+		kernfs_put(parent);
 	}
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);
@@ -1012,7 +415,7 @@ int sysfs_create_bin_file(struct kobject *kobj,
 {
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
+	return sysfs_add_file(kobj->sd, &attr->attr, true);
 }
 EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
 
@@ -1024,7 +427,7 @@ EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
 void sysfs_remove_bin_file(struct kobject *kobj,
 			   const struct bin_attribute *attr)
 {
-	sysfs_hash_and_remove(kobj->sd, attr->attr.name, NULL);
+	kernfs_remove_by_name(kobj->sd, attr->attr.name);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
 

fs/sysfs/group.c

@@ -18,7 +18,7 @@
 #include "sysfs.h"
 
 
-static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
+static void remove_files(struct kernfs_node *parent, struct kobject *kobj,
 			 const struct attribute_group *grp)
 {
 	struct attribute *const *attr;
@@ -26,13 +26,13 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
 
 	if (grp->attrs)
 		for (attr = grp->attrs; *attr; attr++)
-			sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
+			kernfs_remove_by_name(parent, (*attr)->name);
 	if (grp->bin_attrs)
 		for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++)
 			sysfs_remove_bin_file(kobj, *bin_attr);
 }
 
-static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
+static int create_files(struct kernfs_node *parent, struct kobject *kobj,
 			const struct attribute_group *grp, int update)
 {
 	struct attribute *const *attr;
@@ -49,22 +49,20 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
 			 * re-adding (if required) the file.
 			 */
 			if (update)
-				sysfs_hash_and_remove(dir_sd, (*attr)->name,
-						      NULL);
+				kernfs_remove_by_name(parent, (*attr)->name);
 			if (grp->is_visible) {
 				mode = grp->is_visible(kobj, *attr, i);
 				if (!mode)
 					continue;
 			}
-			error = sysfs_add_file_mode_ns(dir_sd, *attr,
-						       SYSFS_KOBJ_ATTR,
+			error = sysfs_add_file_mode_ns(parent, *attr, false,
 						       (*attr)->mode | mode,
 						       NULL);
 			if (unlikely(error))
 				break;
 		}
 		if (error) {
-			remove_files(dir_sd, kobj, grp);
+			remove_files(parent, kobj, grp);
 			goto exit;
 		}
 	}
@@ -78,7 +76,7 @@ static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
 				break;
 		}
 		if (error)
-			remove_files(dir_sd, kobj, grp);
+			remove_files(parent, kobj, grp);
 	}
 exit:
 	return error;
@@ -88,7 +86,7 @@ exit:
 static int internal_create_group(struct kobject *kobj, int update,
 				 const struct attribute_group *grp)
 {
-	struct sysfs_dirent *sd;
+	struct kernfs_node *kn;
 	int error;
 
 	BUG_ON(!kobj || (!update && !kobj->sd));
@@ -102,18 +100,22 @@ static int internal_create_group(struct kobject *kobj, int update,
 		return -EINVAL;
 	}
 	if (grp->name) {
-		error = sysfs_create_subdir(kobj, grp->name, &sd);
-		if (error)
-			return error;
+		kn = kernfs_create_dir(kobj->sd, grp->name,
+				       S_IRWXU | S_IRUGO | S_IXUGO, kobj);
+		if (IS_ERR(kn)) {
+			if (PTR_ERR(kn) == -EEXIST)
+				sysfs_warn_dup(kobj->sd, grp->name);
+			return PTR_ERR(kn);
+		}
 	} else
-		sd = kobj->sd;
-	sysfs_get(sd);
-	error = create_files(sd, kobj, grp, update);
+		kn = kobj->sd;
+	kernfs_get(kn);
+	error = create_files(kn, kobj, grp, update);
 	if (error) {
 		if (grp->name)
-			sysfs_remove(sd);
+			kernfs_remove(kn);
 	}
-	sysfs_put(sd);
+	kernfs_put(kn);
 	return error;
 }
 
@@ -203,25 +205,27 @@ EXPORT_SYMBOL_GPL(sysfs_update_group);
 void sysfs_remove_group(struct kobject *kobj,
 			const struct attribute_group *grp)
 {
-	struct sysfs_dirent *dir_sd = kobj->sd;
-	struct sysfs_dirent *sd;
+	struct kernfs_node *parent = kobj->sd;
+	struct kernfs_node *kn;
 
 	if (grp->name) {
-		sd = sysfs_get_dirent(dir_sd, grp->name);
-		if (!sd) {
-			WARN(!sd, KERN_WARNING
+		kn = kernfs_find_and_get(parent, grp->name);
+		if (!kn) {
+			WARN(!kn, KERN_WARNING
 			     "sysfs group %p not found for kobject '%s'\n",
 			     grp, kobject_name(kobj));
 			return;
 		}
-	} else
-		sd = sysfs_get(dir_sd);
+	} else {
+		kn = parent;
+		kernfs_get(kn);
+	}
 
-	remove_files(sd, kobj, grp);
+	remove_files(kn, kobj, grp);
 	if (grp->name)
-		sysfs_remove(sd);
+		kernfs_remove(kn);
 
-	sysfs_put(sd);
+	kernfs_put(kn);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_group);
 
@@ -257,22 +261,22 @@ EXPORT_SYMBOL_GPL(sysfs_remove_groups);
 int sysfs_merge_group(struct kobject *kobj,
 		       const struct attribute_group *grp)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 	int error = 0;
 	struct attribute *const *attr;
 	int i;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
-	if (!dir_sd)
+	parent = kernfs_find_and_get(kobj->sd, grp->name);
+	if (!parent)
 		return -ENOENT;
 
 	for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr))
-		error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
+		error = sysfs_add_file(parent, *attr, false);
 	if (error) {
 		while (--i >= 0)
-			sysfs_hash_and_remove(dir_sd, (*--attr)->name, NULL);
+			kernfs_remove_by_name(parent, (*--attr)->name);
 	}
-	sysfs_put(dir_sd);
+	kernfs_put(parent);
 
 	return error;
 }
@@ -286,14 +290,14 @@ EXPORT_SYMBOL_GPL(sysfs_merge_group);
 void sysfs_unmerge_group(struct kobject *kobj,
 		       const struct attribute_group *grp)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 	struct attribute *const *attr;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
-	if (dir_sd) {
+	parent = kernfs_find_and_get(kobj->sd, grp->name);
+	if (parent) {
 		for (attr = grp->attrs; *attr; ++attr)
-			sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
-		sysfs_put(dir_sd);
+			kernfs_remove_by_name(parent, (*attr)->name);
+		kernfs_put(parent);
 	}
 }
 EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
@@ -308,15 +312,15 @@ EXPORT_SYMBOL_GPL(sysfs_unmerge_group);
 int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
 			    struct kobject *target, const char *link_name)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 	int error = 0;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
-	if (!dir_sd)
+	parent = kernfs_find_and_get(kobj->sd, group_name);
+	if (!parent)
 		return -ENOENT;
 
-	error = sysfs_create_link_sd(dir_sd, target, link_name);
-	sysfs_put(dir_sd);
+	error = sysfs_create_link_sd(parent, target, link_name);
+	kernfs_put(parent);
 
 	return error;
 }
@@ -331,12 +335,12 @@ EXPORT_SYMBOL_GPL(sysfs_add_link_to_group);
 void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
 				  const char *link_name)
 {
-	struct sysfs_dirent *dir_sd;
+	struct kernfs_node *parent;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
-	if (dir_sd) {
-		sysfs_hash_and_remove(dir_sd, link_name, NULL);
-		sysfs_put(dir_sd);
+	parent = kernfs_find_and_get(kobj->sd, group_name);
+	if (parent) {
+		kernfs_remove_by_name(parent, link_name);
+		kernfs_put(parent);
 	}
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group);

fs/sysfs/inode.c

@@ -1,331 +0,0 @@
-/*
- * fs/sysfs/inode.c - basic sysfs inode and dentry operations
- *
- * Copyright (c) 2001-3 Patrick Mochel
- * Copyright (c) 2007 SUSE Linux Products GmbH
- * Copyright (c) 2007 Tejun Heo <teheo@suse.de>
- *
- * This file is released under the GPLv2.
- *
- * Please see Documentation/filesystems/sysfs.txt for more information.
- */
-
-#undef DEBUG
-
-#include <linux/pagemap.h>
-#include <linux/namei.h>
-#include <linux/backing-dev.h>
-#include <linux/capability.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/sysfs.h>
-#include <linux/xattr.h>
-#include <linux/security.h>
-#include "sysfs.h"
-
-static const struct address_space_operations sysfs_aops = {
-	.readpage	= simple_readpage,
-	.write_begin	= simple_write_begin,
-	.write_end	= simple_write_end,
-};
-
-static struct backing_dev_info sysfs_backing_dev_info = {
-	.name		= "sysfs",
-	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
-static const struct inode_operations sysfs_inode_operations = {
-	.permission	= sysfs_permission,
-	.setattr	= sysfs_setattr,
-	.getattr	= sysfs_getattr,
-	.setxattr	= sysfs_setxattr,
-};
-
-int __init sysfs_inode_init(void)
-{
-	return bdi_init(&sysfs_backing_dev_info);
-}
-
-static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd)
-{
-	struct sysfs_inode_attrs *attrs;
-	struct iattr *iattrs;
-
-	attrs = kzalloc(sizeof(struct sysfs_inode_attrs), GFP_KERNEL);
-	if (!attrs)
-		return NULL;
-	iattrs = &attrs->ia_iattr;
-
-	/* assign default attributes */
-	iattrs->ia_mode = sd->s_mode;
-	iattrs->ia_uid = GLOBAL_ROOT_UID;
-	iattrs->ia_gid = GLOBAL_ROOT_GID;
-	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
-
-	return attrs;
-}
-
-int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr)
-{
-	struct sysfs_inode_attrs *sd_attrs;
-	struct iattr *iattrs;
-	unsigned int ia_valid = iattr->ia_valid;
-
-	sd_attrs = sd->s_iattr;
-
-	if (!sd_attrs) {
-		/* setting attributes for the first time, allocate now */
-		sd_attrs = sysfs_init_inode_attrs(sd);
-		if (!sd_attrs)
-			return -ENOMEM;
-		sd->s_iattr = sd_attrs;
-	}
-	/* attributes were changed at least once in past */
-	iattrs = &sd_attrs->ia_iattr;
-
-	if (ia_valid & ATTR_UID)
-		iattrs->ia_uid = iattr->ia_uid;
-	if (ia_valid & ATTR_GID)
-		iattrs->ia_gid = iattr->ia_gid;
-	if (ia_valid & ATTR_ATIME)
-		iattrs->ia_atime = iattr->ia_atime;
-	if (ia_valid & ATTR_MTIME)
-		iattrs->ia_mtime = iattr->ia_mtime;
-	if (ia_valid & ATTR_CTIME)
-		iattrs->ia_ctime = iattr->ia_ctime;
-	if (ia_valid & ATTR_MODE) {
-		umode_t mode = iattr->ia_mode;
-		iattrs->ia_mode = sd->s_mode = mode;
-	}
-	return 0;
-}
-
-int sysfs_setattr(struct dentry *dentry, struct iattr *iattr)
-{
-	struct inode *inode = dentry->d_inode;
-	struct sysfs_dirent *sd = dentry->d_fsdata;
-	int error;
-
-	if (!sd)
-		return -EINVAL;
-
-	mutex_lock(&sysfs_mutex);
-	error = inode_change_ok(inode, iattr);
-	if (error)
-		goto out;
-
-	error = sysfs_sd_setattr(sd, iattr);
-	if (error)
-		goto out;
-
-	/* this ignores size changes */
-	setattr_copy(inode, iattr);
-
-out:
-	mutex_unlock(&sysfs_mutex);
-	return error;
-}
-
-static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata,
-			       u32 *secdata_len)
-{
-	struct sysfs_inode_attrs *iattrs;
-	void *old_secdata;
-	size_t old_secdata_len;
-
-	if (!sd->s_iattr) {
-		sd->s_iattr = sysfs_init_inode_attrs(sd);
-		if (!sd->s_iattr)
-			return -ENOMEM;
-	}
-
-	iattrs = sd->s_iattr;
-	old_secdata = iattrs->ia_secdata;
-	old_secdata_len = iattrs->ia_secdata_len;
-
-	iattrs->ia_secdata = *secdata;
-	iattrs->ia_secdata_len = *secdata_len;
-
-	*secdata = old_secdata;
-	*secdata_len = old_secdata_len;
-	return 0;
-}
-
-int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		size_t size, int flags)
-{
-	struct sysfs_dirent *sd = dentry->d_fsdata;
-	void *secdata;
-	int error;
-	u32 secdata_len = 0;
-
-	if (!sd)
-		return -EINVAL;
-
-	if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
-		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
-		error = security_inode_setsecurity(dentry->d_inode, suffix,
-						value, size, flags);
-		if (error)
-			goto out;
-		error = security_inode_getsecctx(dentry->d_inode,
-						&secdata, &secdata_len);
-		if (error)
-			goto out;
-
-		mutex_lock(&sysfs_mutex);
-		error = sysfs_sd_setsecdata(sd, &secdata, &secdata_len);
-		mutex_unlock(&sysfs_mutex);
-
-		if (secdata)
-			security_release_secctx(secdata, secdata_len);
-	} else
-		return -EINVAL;
-out:
-	return error;
-}
-
-static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
-{
-	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-}
-
-static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
-{
-	inode->i_uid = iattr->ia_uid;
-	inode->i_gid = iattr->ia_gid;
-	inode->i_atime = iattr->ia_atime;
-	inode->i_mtime = iattr->ia_mtime;
-	inode->i_ctime = iattr->ia_ctime;
-}
-
-static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode)
-{
-	struct sysfs_inode_attrs *iattrs = sd->s_iattr;
-
-	inode->i_mode = sd->s_mode;
-	if (iattrs) {
-		/* sysfs_dirent has non-default attributes
-		 * get them from persistent copy in sysfs_dirent
-		 */
-		set_inode_attr(inode, &iattrs->ia_iattr);
-		security_inode_notifysecctx(inode,
-					    iattrs->ia_secdata,
-					    iattrs->ia_secdata_len);
-	}
-
-	if (sysfs_type(sd) == SYSFS_DIR)
-		set_nlink(inode, sd->s_dir.subdirs + 2);
-}
-
-int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat)
-{
-	struct sysfs_dirent *sd = dentry->d_fsdata;
-	struct inode *inode = dentry->d_inode;
-
-	mutex_lock(&sysfs_mutex);
-	sysfs_refresh_inode(sd, inode);
-	mutex_unlock(&sysfs_mutex);
-
-	generic_fillattr(inode, stat);
-	return 0;
-}
-
-static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
-{
-	struct bin_attribute *bin_attr;
-
-	inode->i_private = sysfs_get(sd);
-	inode->i_mapping->a_ops = &sysfs_aops;
-	inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info;
-	inode->i_op = &sysfs_inode_operations;
-
-	set_default_inode_attr(inode, sd->s_mode);
-	sysfs_refresh_inode(sd, inode);
-
-	/* initialize inode according to type */
-	switch (sysfs_type(sd)) {
-	case SYSFS_DIR:
-		inode->i_op = &sysfs_dir_inode_operations;
-		inode->i_fop = &sysfs_dir_operations;
-		break;
-	case SYSFS_KOBJ_ATTR:
-		inode->i_size = PAGE_SIZE;
-		inode->i_fop = &sysfs_file_operations;
-		break;
-	case SYSFS_KOBJ_BIN_ATTR:
-		bin_attr = sd->s_attr.bin_attr;
-		inode->i_size = bin_attr->size;
-		inode->i_fop = &sysfs_bin_operations;
-		break;
-	case SYSFS_KOBJ_LINK:
-		inode->i_op = &sysfs_symlink_inode_operations;
-		break;
-	default:
-		BUG();
-	}
-
-	unlock_new_inode(inode);
-}
-
-/**
- *	sysfs_get_inode - get inode for sysfs_dirent
- *	@sb: super block
- *	@sd: sysfs_dirent to allocate inode for
- *
- *	Get inode for @sd.  If such inode doesn't exist, a new inode
- *	is allocated and basics are initialized.  New inode is
- *	returned locked.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).
- *
- *	RETURNS:
- *	Pointer to allocated inode on success, NULL on failure.
- */
-struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd)
-{
-	struct inode *inode;
-
-	inode = iget_locked(sb, sd->s_ino);
-	if (inode && (inode->i_state & I_NEW))
-		sysfs_init_inode(sd, inode);
-
-	return inode;
-}
-
-/*
- * The sysfs_dirent serves as both an inode and a directory entry for sysfs.
- * To prevent the sysfs inode numbers from being freed prematurely we take a
- * reference to sysfs_dirent from the sysfs inode.  A
- * super_operations.evict_inode() implementation is needed to drop that
- * reference upon inode destruction.
- */
-void sysfs_evict_inode(struct inode *inode)
-{
-	struct sysfs_dirent *sd  = inode->i_private;
-
-	truncate_inode_pages(&inode->i_data, 0);
-	clear_inode(inode);
-	sysfs_put(sd);
-}
-
-int sysfs_permission(struct inode *inode, int mask)
-{
-	struct sysfs_dirent *sd;
-
-	if (mask & MAY_NOT_BLOCK)
-		return -ECHILD;
-
-	sd = inode->i_private;
-
-	mutex_lock(&sysfs_mutex);
-	sysfs_refresh_inode(sd, inode);
-	mutex_unlock(&sysfs_mutex);
-
-	return generic_permission(inode, mask);
-}

fs/sysfs/mount.c

@@ -14,146 +14,41 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
-#include <linux/pagemap.h>
 #include <linux/init.h>
-#include <linux/module.h>
-#include <linux/magic.h>
-#include <linux/slab.h>
 #include <linux/user_namespace.h>
 
 #include "sysfs.h"
 
-
-static struct vfsmount *sysfs_mnt;
-struct kmem_cache *sysfs_dir_cachep;
-
-static const struct super_operations sysfs_ops = {
-	.statfs		= simple_statfs,
-	.drop_inode	= generic_delete_inode,
-	.evict_inode	= sysfs_evict_inode,
-};
-
-struct sysfs_dirent sysfs_root = {
-	.s_name		= "",
-	.s_count	= ATOMIC_INIT(1),
-	.s_flags	= SYSFS_DIR | (KOBJ_NS_TYPE_NONE << SYSFS_NS_TYPE_SHIFT),
-	.s_mode		= S_IFDIR | S_IRUGO | S_IXUGO,
-	.s_ino		= 1,
-};
-
-static int sysfs_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 = SYSFS_MAGIC;
-	sb->s_op = &sysfs_ops;
-	sb->s_time_gran = 1;
-
-	/* get root inode, initialize and unlock it */
-	mutex_lock(&sysfs_mutex);
-	inode = sysfs_get_inode(sb, &sysfs_root);
-	mutex_unlock(&sysfs_mutex);
-	if (!inode) {
-		pr_debug("sysfs: could not get root inode\n");
-		return -ENOMEM;
-	}
-
-	/* instantiate and link root dentry */
-	root = d_make_root(inode);
-	if (!root) {
-		pr_debug("%s: could not get root dentry!\n", __func__);
-		return -ENOMEM;
-	}
-	root->d_fsdata = &sysfs_root;
-	sb->s_root = root;
-	sb->s_d_op = &sysfs_dentry_ops;
-	return 0;
-}
-
-static int sysfs_test_super(struct super_block *sb, void *data)
-{
-	struct sysfs_super_info *sb_info = sysfs_info(sb);
-	struct sysfs_super_info *info = data;
-	enum kobj_ns_type type;
-	int found = 1;
-
-	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) {
-		if (sb_info->ns[type] != info->ns[type])
-			found = 0;
-	}
-	return found;
-}
-
-static int sysfs_set_super(struct super_block *sb, void *data)
-{
-	int error;
-	error = set_anon_super(sb, data);
-	if (!error)
-		sb->s_fs_info = data;
-	return error;
-}
-
-static void free_sysfs_super_info(struct sysfs_super_info *info)
-{
-	int type;
-	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
-		kobj_ns_drop(type, info->ns[type]);
-	kfree(info);
-}
+static struct kernfs_root *sysfs_root;
+struct kernfs_node *sysfs_root_kn;
 
 static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data)
 {
-	struct sysfs_super_info *info;
-	enum kobj_ns_type type;
-	struct super_block *sb;
-	int error;
+	struct dentry *root;
+	void *ns;
 
 	if (!(flags & MS_KERNMOUNT)) {
 		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
 			return ERR_PTR(-EPERM);
 
-		for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++) {
-			if (!kobj_ns_current_may_mount(type))
-				return ERR_PTR(-EPERM);
-		}
-	}
-
-	info = kzalloc(sizeof(*info), GFP_KERNEL);
-	if (!info)
-		return ERR_PTR(-ENOMEM);
-
-	for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
-		info->ns[type] = kobj_ns_grab_current(type);
-
-	sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info);
-	if (IS_ERR(sb) || sb->s_fs_info != info)
-		free_sysfs_super_info(info);
-	if (IS_ERR(sb))
-		return ERR_CAST(sb);
-	if (!sb->s_root) {
-		error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
-		if (error) {
-			deactivate_locked_super(sb);
-			return ERR_PTR(error);
-		}
-		sb->s_flags |= MS_ACTIVE;
+		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
+			return ERR_PTR(-EPERM);
 	}
 
-	return dget(sb->s_root);
+	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
+	if (IS_ERR(root))
+		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
+	return root;
 }
 
 static void sysfs_kill_sb(struct super_block *sb)
 {
-	struct sysfs_super_info *info = sysfs_info(sb);
-	/* Remove the superblock from fs_supers/s_instances
-	 * so we can't find it, before freeing sysfs_super_info.
-	 */
-	kill_anon_super(sb);
-	free_sysfs_super_info(info);
+	void *ns = (void *)kernfs_super_ns(sb);
+
+	kernfs_kill_sb(sb);
+	kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
 }
 
 static struct file_system_type sysfs_fs_type = {
@@ -165,48 +60,19 @@ static struct file_system_type sysfs_fs_type = {
 
 int __init sysfs_init(void)
 {
-	int err = -ENOMEM;
+	int err;
 
-	sysfs_dir_cachep = kmem_cache_create("sysfs_dir_cache",
-					      sizeof(struct sysfs_dirent),
-					      0, 0, NULL);
-	if (!sysfs_dir_cachep)
-		goto out;
+	sysfs_root = kernfs_create_root(NULL, NULL);
+	if (IS_ERR(sysfs_root))
+		return PTR_ERR(sysfs_root);
 
-	err = sysfs_inode_init();
-	if (err)
-		goto out_err;
+	sysfs_root_kn = sysfs_root->kn;
 
 	err = register_filesystem(&sysfs_fs_type);
-	if (!err) {
-		sysfs_mnt = kern_mount(&sysfs_fs_type);
-		if (IS_ERR(sysfs_mnt)) {
-			printk(KERN_ERR "sysfs: could not mount!\n");
-			err = PTR_ERR(sysfs_mnt);
-			sysfs_mnt = NULL;
-			unregister_filesystem(&sysfs_fs_type);
-			goto out_err;
-		}
-	} else
-		goto out_err;
-out:
-	return err;
-out_err:
-	kmem_cache_destroy(sysfs_dir_cachep);
-	sysfs_dir_cachep = NULL;
-	goto out;
-}
-
-#undef sysfs_get
-struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
-{
-	return __sysfs_get(sd);
-}
-EXPORT_SYMBOL_GPL(sysfs_get);
+	if (err) {
+		kernfs_destroy_root(sysfs_root);
+		return err;
+	}
 
-#undef sysfs_put
-void sysfs_put(struct sysfs_dirent *sd)
-{
-	__sysfs_put(sd);
+	return 0;
 }
-EXPORT_SYMBOL_GPL(sysfs_put);

fs/sysfs/symlink.c

@@ -11,109 +11,73 @@
  */
 
 #include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/kobject.h>
-#include <linux/namei.h>
 #include <linux/mutex.h>
 #include <linux/security.h>
 
 #include "sysfs.h"
 
-static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
-				   struct kobject *target,
+static int sysfs_do_create_link_sd(struct kernfs_node *parent,
+				   struct kobject *target_kobj,
 				   const char *name, int warn)
 {
-	struct sysfs_dirent *target_sd = NULL;
-	struct sysfs_dirent *sd = NULL;
-	struct sysfs_addrm_cxt acxt;
-	enum kobj_ns_type ns_type;
-	int error;
+	struct kernfs_node *kn, *target = NULL;
 
-	BUG_ON(!name || !parent_sd);
+	BUG_ON(!name || !parent);
 
 	/*
-	 * We don't own @target and it may be removed at any time.
+	 * We don't own @target_kobj and it may be removed at any time.
 	 * Synchronize using sysfs_symlink_target_lock.  See
 	 * sysfs_remove_dir() for details.
 	 */
 	spin_lock(&sysfs_symlink_target_lock);
-	if (target->sd)
-		target_sd = sysfs_get(target->sd);
+	if (target_kobj->sd) {
+		target = target_kobj->sd;
+		kernfs_get(target);
+	}
 	spin_unlock(&sysfs_symlink_target_lock);
 
-	error = -ENOENT;
-	if (!target_sd)
-		goto out_put;
-
-	error = -ENOMEM;
-	sd = sysfs_new_dirent(name, S_IFLNK|S_IRWXUGO, SYSFS_KOBJ_LINK);
-	if (!sd)
-		goto out_put;
+	if (!target)
+		return -ENOENT;
 
-	ns_type = sysfs_ns_type(parent_sd);
-	if (ns_type)
-		sd->s_ns = target_sd->s_ns;
-	sd->s_symlink.target_sd = target_sd;
-	target_sd = NULL;	/* reference is now owned by the symlink */
-
-	sysfs_addrm_start(&acxt);
-	/* Symlinks must be between directories with the same ns_type */
-	if (!ns_type ||
-	    (ns_type == sysfs_ns_type(sd->s_symlink.target_sd->s_parent))) {
-		if (warn)
-			error = sysfs_add_one(&acxt, sd, parent_sd);
-		else
-			error = __sysfs_add_one(&acxt, sd, parent_sd);
-	} else {
-		error = -EINVAL;
-		WARN(1, KERN_WARNING
-			"sysfs: symlink across ns_types %s/%s -> %s/%s\n",
-			parent_sd->s_name,
-			sd->s_name,
-			sd->s_symlink.target_sd->s_parent->s_name,
-			sd->s_symlink.target_sd->s_name);
-	}
-	sysfs_addrm_finish(&acxt);
+	kn = kernfs_create_link(parent, name, target);
+	kernfs_put(target);
 
-	if (error)
-		goto out_put;
+	if (!IS_ERR(kn))
+		return 0;
 
-	return 0;
-
- out_put:
-	sysfs_put(target_sd);
-	sysfs_put(sd);
-	return error;
+	if (warn && PTR_ERR(kn) == -EEXIST)
+		sysfs_warn_dup(parent, name);
+	return PTR_ERR(kn);
 }
 
 /**
  *	sysfs_create_link_sd - create symlink to a given object.
- *	@sd:		directory we're creating the link in.
+ *	@kn:		directory we're creating the link in.
  *	@target:	object we're pointing to.
  *	@name:		name of the symlink.
  */
-int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target,
 			 const char *name)
 {
-	return sysfs_do_create_link_sd(sd, target, name, 1);
+	return sysfs_do_create_link_sd(kn, target, name, 1);
 }
 
 static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
 				const char *name, int warn)
 {
-	struct sysfs_dirent *parent_sd = NULL;
+	struct kernfs_node *parent = NULL;
 
 	if (!kobj)
-		parent_sd = &sysfs_root;
+		parent = sysfs_root_kn;
 	else
-		parent_sd = kobj->sd;
+		parent = kobj->sd;
 
-	if (!parent_sd)
+	if (!parent)
 		return -EFAULT;
 
-	return sysfs_do_create_link_sd(parent_sd, target, name, warn);
+	return sysfs_do_create_link_sd(parent, target, name, warn);
 }
 
 /**
@@ -164,10 +128,10 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
 	 * sysfs_remove_dir() for details.
 	 */
 	spin_lock(&sysfs_symlink_target_lock);
-	if (targ->sd && sysfs_ns_type(kobj->sd))
-		ns = targ->sd->s_ns;
+	if (targ->sd && kernfs_ns_enabled(kobj->sd))
+		ns = targ->sd->ns;
 	spin_unlock(&sysfs_symlink_target_lock);
-	sysfs_hash_and_remove(kobj->sd, name, ns);
+	kernfs_remove_by_name_ns(kobj->sd, name, ns);
 }
 
 /**
@@ -177,14 +141,14 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
  */
 void sysfs_remove_link(struct kobject *kobj, const char *name)
 {
-	struct sysfs_dirent *parent_sd = NULL;
+	struct kernfs_node *parent = NULL;
 
 	if (!kobj)
-		parent_sd = &sysfs_root;
+		parent = sysfs_root_kn;
 	else
-		parent_sd = kobj->sd;
+		parent = kobj->sd;
 
-	sysfs_hash_and_remove(parent_sd, name, NULL);
+	kernfs_remove_by_name(parent, name);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_link);
 
@@ -201,130 +165,33 @@ EXPORT_SYMBOL_GPL(sysfs_remove_link);
 int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ,
 			 const char *old, const char *new, const void *new_ns)
 {
-	struct sysfs_dirent *parent_sd, *sd = NULL;
+	struct kernfs_node *parent, *kn = NULL;
 	const void *old_ns = NULL;
 	int result;
 
 	if (!kobj)
-		parent_sd = &sysfs_root;
+		parent = sysfs_root_kn;
 	else
-		parent_sd = kobj->sd;
+		parent = kobj->sd;
 
 	if (targ->sd)
-		old_ns = targ->sd->s_ns;
+		old_ns = targ->sd->ns;
 
 	result = -ENOENT;
-	sd = sysfs_get_dirent_ns(parent_sd, old, old_ns);
-	if (!sd)
+	kn = kernfs_find_and_get_ns(parent, old, old_ns);
+	if (!kn)
 		goto out;
 
 	result = -EINVAL;
-	if (sysfs_type(sd) != SYSFS_KOBJ_LINK)
+	if (kernfs_type(kn) != KERNFS_LINK)
 		goto out;
-	if (sd->s_symlink.target_sd->s_dir.kobj != targ)
+	if (kn->symlink.target_kn->priv != targ)
 		goto out;
 
-	result = sysfs_rename(sd, parent_sd, new, new_ns);
+	result = kernfs_rename_ns(kn, parent, new, new_ns);
 
 out:
-	sysfs_put(sd);
+	kernfs_put(kn);
 	return result;
 }
 EXPORT_SYMBOL_GPL(sysfs_rename_link_ns);
-
-static int sysfs_get_target_path(struct sysfs_dirent *parent_sd,
-				 struct sysfs_dirent *target_sd, char *path)
-{
-	struct sysfs_dirent *base, *sd;
-	char *s = path;
-	int len = 0;
-
-	/* go up to the root, stop at the base */
-	base = parent_sd;
-	while (base->s_parent) {
-		sd = target_sd->s_parent;
-		while (sd->s_parent && base != sd)
-			sd = sd->s_parent;
-
-		if (base == sd)
-			break;
-
-		strcpy(s, "../");
-		s += 3;
-		base = base->s_parent;
-	}
-
-	/* determine end of target string for reverse fillup */
-	sd = target_sd;
-	while (sd->s_parent && sd != base) {
-		len += strlen(sd->s_name) + 1;
-		sd = sd->s_parent;
-	}
-
-	/* check limits */
-	if (len < 2)
-		return -EINVAL;
-	len--;
-	if ((s - path) + len > PATH_MAX)
-		return -ENAMETOOLONG;
-
-	/* reverse fillup of target string from target to base */
-	sd = target_sd;
-	while (sd->s_parent && sd != base) {
-		int slen = strlen(sd->s_name);
-
-		len -= slen;
-		strncpy(s + len, sd->s_name, slen);
-		if (len)
-			s[--len] = '/';
-
-		sd = sd->s_parent;
-	}
-
-	return 0;
-}
-
-static int sysfs_getlink(struct dentry *dentry, char *path)
-{
-	struct sysfs_dirent *sd = dentry->d_fsdata;
-	struct sysfs_dirent *parent_sd = sd->s_parent;
-	struct sysfs_dirent *target_sd = sd->s_symlink.target_sd;
-	int error;
-
-	mutex_lock(&sysfs_mutex);
-	error = sysfs_get_target_path(parent_sd, target_sd, path);
-	mutex_unlock(&sysfs_mutex);
-
-	return error;
-}
-
-static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
-	int error = -ENOMEM;
-	unsigned long page = get_zeroed_page(GFP_KERNEL);
-	if (page) {
-		error = sysfs_getlink(dentry, (char *) page);
-		if (error < 0)
-			free_page((unsigned long)page);
-	}
-	nd_set_link(nd, error ? ERR_PTR(error) : (char *)page);
-	return NULL;
-}
-
-static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd,
-			   void *cookie)
-{
-	char *page = nd_get_link(nd);
-	if (!IS_ERR(page))
-		free_page((unsigned long)page);
-}
-
-const struct inode_operations sysfs_symlink_inode_operations = {
-	.setxattr	= sysfs_setxattr,
-	.readlink	= generic_readlink,
-	.follow_link	= sysfs_follow_link,
-	.put_link	= sysfs_put_link,
-	.setattr	= sysfs_setattr,
-	.getattr	= sysfs_getattr,
-	.permission	= sysfs_permission,
-};

fs/sysfs/sysfs.h

@@ -8,248 +8,36 @@
  * This file is released under the GPLv2.
  */
 
-#include <linux/lockdep.h>
-#include <linux/kobject_ns.h>
-#include <linux/fs.h>
-#include <linux/rbtree.h>
+#ifndef __SYSFS_INTERNAL_H
+#define __SYSFS_INTERNAL_H
 
-struct sysfs_open_dirent;
-
-/* type-specific structures for sysfs_dirent->s_* union members */
-struct sysfs_elem_dir {
-	struct kobject		*kobj;
-
-	unsigned long		subdirs;
-	/* children rbtree starts here and goes through sd->s_rb */
-	struct rb_root		children;
-};
-
-struct sysfs_elem_symlink {
-	struct sysfs_dirent	*target_sd;
-};
-
-struct sysfs_elem_attr {
-	union {
-		struct attribute	*attr;
-		struct bin_attribute	*bin_attr;
-	};
-	struct sysfs_open_dirent *open;
-};
-
-struct sysfs_inode_attrs {
-	struct iattr	ia_iattr;
-	void		*ia_secdata;
-	u32		ia_secdata_len;
-};
-
-/*
- * sysfs_dirent - the building block of sysfs hierarchy.  Each and
- * every sysfs node is represented by single sysfs_dirent.
- *
- * As long as s_count reference is held, the sysfs_dirent itself is
- * accessible.  Dereferencing s_elem or any other outer entity
- * requires s_active reference.
- */
-struct sysfs_dirent {
-	atomic_t		s_count;
-	atomic_t		s_active;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-	struct sysfs_dirent	*s_parent;
-	const char		*s_name;
-
-	struct rb_node		s_rb;
-
-	union {
-		struct completion	*completion;
-		struct sysfs_dirent	*removed_list;
-	} u;
-
-	const void		*s_ns; /* namespace tag */
-	unsigned int		s_hash; /* ns + name hash */
-	union {
-		struct sysfs_elem_dir		s_dir;
-		struct sysfs_elem_symlink	s_symlink;
-		struct sysfs_elem_attr		s_attr;
-	};
-
-	unsigned short		s_flags;
-	umode_t			s_mode;
-	unsigned int		s_ino;
-	struct sysfs_inode_attrs *s_iattr;
-};
-
-#define SD_DEACTIVATED_BIAS		INT_MIN
-
-#define SYSFS_TYPE_MASK			0x00ff
-#define SYSFS_DIR			0x0001
-#define SYSFS_KOBJ_ATTR			0x0002
-#define SYSFS_KOBJ_BIN_ATTR		0x0004
-#define SYSFS_KOBJ_LINK			0x0008
-#define SYSFS_COPY_NAME			(SYSFS_DIR | SYSFS_KOBJ_LINK)
-#define SYSFS_ACTIVE_REF		(SYSFS_KOBJ_ATTR | SYSFS_KOBJ_BIN_ATTR)
-
-/* identify any namespace tag on sysfs_dirents */
-#define SYSFS_NS_TYPE_MASK		0xf00
-#define SYSFS_NS_TYPE_SHIFT		8
-
-#define SYSFS_FLAG_MASK			~(SYSFS_NS_TYPE_MASK|SYSFS_TYPE_MASK)
-#define SYSFS_FLAG_REMOVED		0x02000
-
-static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
-{
-	return sd->s_flags & SYSFS_TYPE_MASK;
-}
-
-/*
- * Return any namespace tags on this dirent.
- * enum kobj_ns_type is defined in linux/kobject.h
- */
-static inline enum kobj_ns_type sysfs_ns_type(struct sysfs_dirent *sd)
-{
-	return (sd->s_flags & SYSFS_NS_TYPE_MASK) >> SYSFS_NS_TYPE_SHIFT;
-}
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-
-#define sysfs_dirent_init_lockdep(sd)				\
-do {								\
-	struct attribute *attr = sd->s_attr.attr;		\
-	struct lock_class_key *key = attr->key;			\
-	if (!key)						\
-		key = &attr->skey;				\
-								\
-	lockdep_init_map(&sd->dep_map, "s_active", key, 0);	\
-} while (0)
-
-/* Test for attributes that want to ignore lockdep for read-locking */
-static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd)
-{
-	int type = sysfs_type(sd);
-
-	return (type == SYSFS_KOBJ_ATTR || type == SYSFS_KOBJ_BIN_ATTR) &&
-		sd->s_attr.attr->ignore_lockdep;
-}
-
-#else
-
-#define sysfs_dirent_init_lockdep(sd) do {} while (0)
-
-static inline bool sysfs_ignore_lockdep(struct sysfs_dirent *sd)
-{
-	return true;
-}
-
-#endif
-
-/*
- * Context structure to be used while adding/removing nodes.
- */
-struct sysfs_addrm_cxt {
-	struct sysfs_dirent	*removed;
-};
+#include <linux/sysfs.h>
 
 /*
  * mount.c
  */
-
-/*
- * Each sb is associated with a set of namespace tags (i.e.
- * the network namespace of the task which mounted this sysfs
- * instance).
- */
-struct sysfs_super_info {
-	void *ns[KOBJ_NS_TYPES];
-};
-#define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info))
-extern struct sysfs_dirent sysfs_root;
-extern struct kmem_cache *sysfs_dir_cachep;
+extern struct kernfs_node *sysfs_root_kn;
 
 /*
  * dir.c
  */
-extern struct mutex sysfs_mutex;
 extern spinlock_t sysfs_symlink_target_lock;
-extern const struct dentry_operations sysfs_dentry_ops;
-
-extern const struct file_operations sysfs_dir_operations;
-extern const struct inode_operations sysfs_dir_inode_operations;
 
-struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd);
-void sysfs_put_active(struct sysfs_dirent *sd);
-void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt);
-void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name);
-int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
-		    struct sysfs_dirent *parent_sd);
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd,
-		  struct sysfs_dirent *parent_sd);
-void sysfs_remove(struct sysfs_dirent *sd);
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name,
-			  const void *ns);
-void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
-
-struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
-				       const unsigned char *name,
-				       const void *ns);
-struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type);
-
-void release_sysfs_dirent(struct sysfs_dirent *sd);
-
-int sysfs_create_subdir(struct kobject *kobj, const char *name,
-			struct sysfs_dirent **p_sd);
-
-int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
-		 const char *new_name, const void *new_ns);
-
-static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd)
-{
-	if (sd) {
-		WARN_ON(!atomic_read(&sd->s_count));
-		atomic_inc(&sd->s_count);
-	}
-	return sd;
-}
-#define sysfs_get(sd) __sysfs_get(sd)
-
-static inline void __sysfs_put(struct sysfs_dirent *sd)
-{
-	if (sd && atomic_dec_and_test(&sd->s_count))
-		release_sysfs_dirent(sd);
-}
-#define sysfs_put(sd) __sysfs_put(sd)
-
-/*
- * inode.c
- */
-struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd);
-void sysfs_evict_inode(struct inode *inode);
-int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr);
-int sysfs_permission(struct inode *inode, int mask);
-int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
-int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat);
-int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		   size_t size, int flags);
-int sysfs_inode_init(void);
+void sysfs_warn_dup(struct kernfs_node *parent, const char *name);
 
 /*
  * file.c
  */
-extern const struct file_operations sysfs_file_operations;
-extern const struct file_operations sysfs_bin_operations;
-
-int sysfs_add_file(struct sysfs_dirent *dir_sd,
-		   const struct attribute *attr, int type);
-
-int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
-			   const struct attribute *attr, int type,
+int sysfs_add_file(struct kernfs_node *parent,
+		   const struct attribute *attr, bool is_bin);
+int sysfs_add_file_mode_ns(struct kernfs_node *parent,
+			   const struct attribute *attr, bool is_bin,
 			   umode_t amode, const void *ns);
-void sysfs_unmap_bin_file(struct sysfs_dirent *sd);
 
 /*
  * symlink.c
  */
-extern const struct inode_operations sysfs_symlink_inode_operations;
-int sysfs_create_link_sd(struct sysfs_dirent *sd, struct kobject *target,
+int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target,
 			 const char *name);
+
+#endif	/* __SYSFS_INTERNAL_H */

include/linux/component.h

@@ -0,0 +1,32 @@
+#ifndef COMPONENT_H
+#define COMPONENT_H
+
+struct device;
+
+struct component_ops {
+	int (*bind)(struct device *, struct device *, void *);
+	void (*unbind)(struct device *, struct device *, void *);
+};
+
+int component_add(struct device *, const struct component_ops *);
+void component_del(struct device *, const struct component_ops *);
+
+int component_bind_all(struct device *, void *);
+void component_unbind_all(struct device *, void *);
+
+struct master;
+
+struct component_master_ops {
+	int (*add_components)(struct device *, struct master *);
+	int (*bind)(struct device *);
+	void (*unbind)(struct device *);
+};
+
+int component_master_add(struct device *, const struct component_master_ops *);
+void component_master_del(struct device *,
+	const struct component_master_ops *);
+
+int component_master_add_child(struct master *master,
+	int (*compare)(struct device *, void *), void *compare_data);
+
+#endif

include/linux/firmware.h

@@ -68,4 +68,11 @@ static inline void release_firmware(const struct firmware *fw)
 
 #endif
 
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+int request_firmware_direct(const struct firmware **fw, const char *name,
+			    struct device *device);
+#else
+#define request_firmware_direct	request_firmware
+#endif
+
 #endif

include/linux/kernfs.h

@@ -0,0 +1,376 @@
+/*
+ * kernfs.h - pseudo filesystem decoupled from vfs locking
+ *
+ * This file is released under the GPLv2.
+ */
+
+#ifndef __LINUX_KERNFS_H
+#define __LINUX_KERNFS_H
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/idr.h>
+#include <linux/lockdep.h>
+#include <linux/rbtree.h>
+#include <linux/atomic.h>
+#include <linux/completion.h>
+
+struct file;
+struct dentry;
+struct iattr;
+struct seq_file;
+struct vm_area_struct;
+struct super_block;
+struct file_system_type;
+
+struct kernfs_open_node;
+struct kernfs_iattrs;
+
+enum kernfs_node_type {
+	KERNFS_DIR		= 0x0001,
+	KERNFS_FILE		= 0x0002,
+	KERNFS_LINK		= 0x0004,
+};
+
+#define KERNFS_TYPE_MASK	0x000f
+#define KERNFS_ACTIVE_REF	KERNFS_FILE
+#define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
+
+enum kernfs_node_flag {
+	KERNFS_REMOVED		= 0x0010,
+	KERNFS_NS		= 0x0020,
+	KERNFS_HAS_SEQ_SHOW	= 0x0040,
+	KERNFS_HAS_MMAP		= 0x0080,
+	KERNFS_LOCKDEP		= 0x0100,
+	KERNFS_STATIC_NAME	= 0x0200,
+};
+
+/* type-specific structures for kernfs_node union members */
+struct kernfs_elem_dir {
+	unsigned long		subdirs;
+	/* children rbtree starts here and goes through kn->rb */
+	struct rb_root		children;
+
+	/*
+	 * The kernfs hierarchy this directory belongs to.  This fits
+	 * better directly in kernfs_node but is here to save space.
+	 */
+	struct kernfs_root	*root;
+};
+
+struct kernfs_elem_symlink {
+	struct kernfs_node	*target_kn;
+};
+
+struct kernfs_elem_attr {
+	const struct kernfs_ops	*ops;
+	struct kernfs_open_node	*open;
+	loff_t			size;
+};
+
+/*
+ * kernfs_node - the building block of kernfs hierarchy.  Each and every
+ * kernfs node is represented by single kernfs_node.  Most fields are
+ * private to kernfs and shouldn't be accessed directly by kernfs users.
+ *
+ * As long as s_count reference is held, the kernfs_node itself is
+ * accessible.  Dereferencing elem or any other outer entity requires
+ * active reference.
+ */
+struct kernfs_node {
+	atomic_t		count;
+	atomic_t		active;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+	/* the following two fields are published */
+	struct kernfs_node	*parent;
+	const char		*name;
+
+	struct rb_node		rb;
+
+	union {
+		struct completion	*completion;
+		struct kernfs_node	*removed_list;
+	} u;
+
+	const void		*ns;	/* namespace tag */
+	unsigned int		hash;	/* ns + name hash */
+	union {
+		struct kernfs_elem_dir		dir;
+		struct kernfs_elem_symlink	symlink;
+		struct kernfs_elem_attr		attr;
+	};
+
+	void			*priv;
+
+	unsigned short		flags;
+	umode_t			mode;
+	unsigned int		ino;
+	struct kernfs_iattrs	*iattr;
+};
+
+/*
+ * kernfs_dir_ops may be specified on kernfs_create_root() to support
+ * directory manipulation syscalls.  These optional callbacks are invoked
+ * on the matching syscalls and can perform any kernfs operations which
+ * don't necessarily have to be the exact operation requested.
+ */
+struct kernfs_dir_ops {
+	int (*mkdir)(struct kernfs_node *parent, const char *name,
+		     umode_t mode);
+	int (*rmdir)(struct kernfs_node *kn);
+	int (*rename)(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		      const char *new_name);
+};
+
+struct kernfs_root {
+	/* published fields */
+	struct kernfs_node	*kn;
+
+	/* private fields, do not use outside kernfs proper */
+	struct ida		ino_ida;
+	struct kernfs_dir_ops	*dir_ops;
+};
+
+struct kernfs_open_file {
+	/* published fields */
+	struct kernfs_node	*kn;
+	struct file		*file;
+
+	/* private fields, do not use outside kernfs proper */
+	struct mutex		mutex;
+	int			event;
+	struct list_head	list;
+
+	bool			mmapped;
+	const struct vm_operations_struct *vm_ops;
+};
+
+struct kernfs_ops {
+	/*
+	 * Read is handled by either seq_file or raw_read().
+	 *
+	 * If seq_show() is present, seq_file path is active.  Other seq
+	 * operations are optional and if not implemented, the behavior is
+	 * equivalent to single_open().  @sf->private points to the
+	 * associated kernfs_open_file.
+	 *
+	 * read() is bounced through kernel buffer and a read larger than
+	 * PAGE_SIZE results in partial operation of PAGE_SIZE.
+	 */
+	int (*seq_show)(struct seq_file *sf, void *v);
+
+	void *(*seq_start)(struct seq_file *sf, loff_t *ppos);
+	void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos);
+	void (*seq_stop)(struct seq_file *sf, void *v);
+
+	ssize_t (*read)(struct kernfs_open_file *of, char *buf, size_t bytes,
+			loff_t off);
+
+	/*
+	 * write() is bounced through kernel buffer and a write larger than
+	 * PAGE_SIZE results in partial operation of PAGE_SIZE.
+	 */
+	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
+			 loff_t off);
+
+	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lock_class_key	lockdep_key;
+#endif
+};
+
+#ifdef CONFIG_SYSFS
+
+static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
+{
+	return kn->flags & KERNFS_TYPE_MASK;
+}
+
+/**
+ * kernfs_enable_ns - enable namespace under a directory
+ * @kn: directory of interest, should be empty
+ *
+ * This is to be called right after @kn is created to enable namespace
+ * under it.  All children of @kn must have non-NULL namespace tags and
+ * only the ones which match the super_block's tag will be visible.
+ */
+static inline void kernfs_enable_ns(struct kernfs_node *kn)
+{
+	WARN_ON_ONCE(kernfs_type(kn) != KERNFS_DIR);
+	WARN_ON_ONCE(!RB_EMPTY_ROOT(&kn->dir.children));
+	kn->flags |= KERNFS_NS;
+}
+
+/**
+ * kernfs_ns_enabled - test whether namespace is enabled
+ * @kn: the node to test
+ *
+ * Test whether namespace filtering is enabled for the children of @ns.
+ */
+static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
+{
+	return kn->flags & KERNFS_NS;
+}
+
+struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
+					   const char *name, const void *ns);
+void kernfs_get(struct kernfs_node *kn);
+void kernfs_put(struct kernfs_node *kn);
+
+struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops,
+				       void *priv);
+void kernfs_destroy_root(struct kernfs_root *root);
+
+struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
+					 const char *name, umode_t mode,
+					 void *priv, const void *ns);
+struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
+					 const char *name,
+					 umode_t mode, loff_t size,
+					 const struct kernfs_ops *ops,
+					 void *priv, const void *ns,
+					 bool name_is_static,
+					 struct lock_class_key *key);
+struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
+				       const char *name,
+				       struct kernfs_node *target);
+void kernfs_remove(struct kernfs_node *kn);
+int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
+			     const void *ns);
+int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		     const char *new_name, const void *new_ns);
+int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
+void kernfs_notify(struct kernfs_node *kn);
+
+const void *kernfs_super_ns(struct super_block *sb);
+struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
+			       struct kernfs_root *root, const void *ns);
+void kernfs_kill_sb(struct super_block *sb);
+
+void kernfs_init(void);
+
+#else	/* CONFIG_SYSFS */
+
+static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
+{ return 0; }	/* whatever */
+
+static inline void kernfs_enable_ns(struct kernfs_node *kn) { }
+
+static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
+{ return false; }
+
+static inline struct kernfs_node *
+kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
+		       const void *ns)
+{ return NULL; }
+
+static inline void kernfs_get(struct kernfs_node *kn) { }
+static inline void kernfs_put(struct kernfs_node *kn) { }
+
+static inline struct kernfs_root *
+kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+{ return ERR_PTR(-ENOSYS); }
+
+static inline void kernfs_destroy_root(struct kernfs_root *root) { }
+
+static inline struct kernfs_node *
+kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
+		     umode_t mode, void *priv, const void *ns)
+{ return ERR_PTR(-ENOSYS); }
+
+static inline struct kernfs_node *
+__kernfs_create_file(struct kernfs_node *parent, const char *name,
+		     umode_t mode, loff_t size, const struct kernfs_ops *ops,
+		     void *priv, const void *ns, bool name_is_static,
+		     struct lock_class_key *key)
+{ return ERR_PTR(-ENOSYS); }
+
+static inline struct kernfs_node *
+kernfs_create_link(struct kernfs_node *parent, const char *name,
+		   struct kernfs_node *target)
+{ return ERR_PTR(-ENOSYS); }
+
+static inline void kernfs_remove(struct kernfs_node *kn) { }
+
+static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn,
+					   const char *name, const void *ns)
+{ return -ENOSYS; }
+
+static inline int kernfs_rename_ns(struct kernfs_node *kn,
+				   struct kernfs_node *new_parent,
+				   const char *new_name, const void *new_ns)
+{ return -ENOSYS; }
+
+static inline int kernfs_setattr(struct kernfs_node *kn,
+				 const struct iattr *iattr)
+{ return -ENOSYS; }
+
+static inline void kernfs_notify(struct kernfs_node *kn) { }
+
+static inline const void *kernfs_super_ns(struct super_block *sb)
+{ return NULL; }
+
+static inline struct dentry *
+kernfs_mount_ns(struct file_system_type *fs_type, int flags,
+		struct kernfs_root *root, const void *ns)
+{ return ERR_PTR(-ENOSYS); }
+
+static inline void kernfs_kill_sb(struct super_block *sb) { }
+
+static inline void kernfs_init(void) { }
+
+#endif	/* CONFIG_SYSFS */
+
+static inline struct kernfs_node *
+kernfs_find_and_get(struct kernfs_node *kn, const char *name)
+{
+	return kernfs_find_and_get_ns(kn, name, NULL);
+}
+
+static inline struct kernfs_node *
+kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
+		  void *priv)
+{
+	return kernfs_create_dir_ns(parent, name, mode, priv, NULL);
+}
+
+static inline struct kernfs_node *
+kernfs_create_file_ns(struct kernfs_node *parent, const char *name,
+		      umode_t mode, loff_t size, const struct kernfs_ops *ops,
+		      void *priv, const void *ns)
+{
+	struct lock_class_key *key = NULL;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	key = (struct lock_class_key *)&ops->lockdep_key;
+#endif
+	return __kernfs_create_file(parent, name, mode, size, ops, priv, ns,
+				    false, key);
+}
+
+static inline struct kernfs_node *
+kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode,
+		   loff_t size, const struct kernfs_ops *ops, void *priv)
+{
+	return kernfs_create_file_ns(parent, name, mode, size, ops, priv, NULL);
+}
+
+static inline int kernfs_remove_by_name(struct kernfs_node *parent,
+					const char *name)
+{
+	return kernfs_remove_by_name_ns(parent, name, NULL);
+}
+
+static inline struct dentry *
+kernfs_mount(struct file_system_type *fs_type, int flags,
+	     struct kernfs_root *root)
+{
+	return kernfs_mount_ns(fs_type, flags, root, NULL);
+}
+
+#endif	/* __LINUX_KERNFS_H */

include/linux/kobj_completion.h

@@ -1,18 +0,0 @@
-#ifndef _KOBJ_COMPLETION_H_
-#define _KOBJ_COMPLETION_H_
-
-#include <linux/kobject.h>
-#include <linux/completion.h>
-
-struct kobj_completion {
-	struct kobject kc_kobj;
-	struct completion kc_unregister;
-};
-
-#define kobj_to_kobj_completion(kobj) \
-	container_of(kobj, struct kobj_completion, kc_kobj)
-
-void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype);
-void kobj_completion_release(struct kobject *kobj);
-void kobj_completion_del_and_wait(struct kobj_completion *kc);
-#endif /* _KOBJ_COMPLETION_H_ */

include/linux/kobject.h

@@ -64,7 +64,7 @@ struct kobject {
 	struct kobject		*parent;
 	struct kset		*kset;
 	struct kobj_type	*ktype;
-	struct sysfs_dirent	*sd;
+	struct kernfs_node	*sd;
 	struct kref		kref;
 #ifdef CONFIG_DEBUG_KOBJECT_RELEASE
 	struct delayed_work	release;

include/linux/memory.h

@@ -35,6 +35,7 @@ struct memory_block {
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
+unsigned long __weak memory_block_size_bytes(void);
 
 /* These states are exposed to userspace as text strings in sysfs */
 #define	MEM_ONLINE		(1<<0) /* exposed to userspace */

include/linux/sysfs.h

@@ -12,6 +12,7 @@
 #ifndef _SYSFS_H_
 #define _SYSFS_H_
 
+#include <linux/kernfs.h>
 #include <linux/compiler.h>
 #include <linux/errno.h>
 #include <linux/list.h>
@@ -175,8 +176,6 @@ struct sysfs_ops {
 	ssize_t	(*store)(struct kobject *, struct attribute *, const char *, size_t);
 };
 
-struct sysfs_dirent;
-
 #ifdef CONFIG_SYSFS
 
 int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
@@ -244,12 +243,6 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
 				  const char *link_name);
 
 void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
-void sysfs_notify_dirent(struct sysfs_dirent *sd);
-struct sysfs_dirent *sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd,
-					 const unsigned char *name,
-					 const void *ns);
-struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd);
-void sysfs_put(struct sysfs_dirent *sd);
 
 int __must_check sysfs_init(void);
 
@@ -419,22 +412,6 @@ static inline void sysfs_notify(struct kobject *kobj, const char *dir,
 				const char *attr)
 {
 }
-static inline void sysfs_notify_dirent(struct sysfs_dirent *sd)
-{
-}
-static inline struct sysfs_dirent *
-sysfs_get_dirent_ns(struct sysfs_dirent *parent_sd, const unsigned char *name,
-		    const void *ns)
-{
-	return NULL;
-}
-static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd)
-{
-	return NULL;
-}
-static inline void sysfs_put(struct sysfs_dirent *sd)
-{
-}
 
 static inline int __must_check sysfs_init(void)
 {
@@ -461,10 +438,26 @@ static inline int sysfs_rename_link(struct kobject *kobj, struct kobject *target
 	return sysfs_rename_link_ns(kobj, target, old_name, new_name, NULL);
 }
 
-static inline struct sysfs_dirent *
-sysfs_get_dirent(struct sysfs_dirent *parent_sd, const unsigned char *name)
+static inline void sysfs_notify_dirent(struct kernfs_node *kn)
+{
+	kernfs_notify(kn);
+}
+
+static inline struct kernfs_node *sysfs_get_dirent(struct kernfs_node *parent,
+						   const unsigned char *name)
+{
+	return kernfs_find_and_get(parent, name);
+}
+
+static inline struct kernfs_node *sysfs_get(struct kernfs_node *kn)
+{
+	kernfs_get(kn);
+	return kn;
+}
+
+static inline void sysfs_put(struct kernfs_node *kn)
 {
-	return sysfs_get_dirent_ns(parent_sd, name, NULL);
+	kernfs_put(kn);
 }
 
 #endif /* _SYSFS_H_ */

lib/kobject.c

@@ -13,11 +13,11 @@
  */
 
 #include <linux/kobject.h>
-#include <linux/kobj_completion.h>
 #include <linux/string.h>
 #include <linux/export.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
+#include <linux/random.h>
 
 /**
  * kobject_namespace - return @kobj's namespace tag
@@ -65,13 +65,17 @@ static int populate_dir(struct kobject *kobj)
 
 static int create_dir(struct kobject *kobj)
 {
+	const struct kobj_ns_type_operations *ops;
 	int error;
 
 	error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj));
-	if (!error) {
-		error = populate_dir(kobj);
-		if (error)
-			sysfs_remove_dir(kobj);
+	if (error)
+		return error;
+
+	error = populate_dir(kobj);
+	if (error) {
+		sysfs_remove_dir(kobj);
+		return error;
 	}
 
 	/*
@@ -80,7 +84,20 @@ static int create_dir(struct kobject *kobj)
 	 */
 	sysfs_get(kobj->sd);
 
-	return error;
+	/*
+	 * If @kobj has ns_ops, its children need to be filtered based on
+	 * their namespace tags.  Enable namespace support on @kobj->sd.
+	 */
+	ops = kobj_child_ns_ops(kobj);
+	if (ops) {
+		BUG_ON(ops->type <= KOBJ_NS_TYPE_NONE);
+		BUG_ON(ops->type >= KOBJ_NS_TYPES);
+		BUG_ON(!kobj_ns_type_registered(ops->type));
+
+		kernfs_enable_ns(kobj->sd);
+	}
+
+	return 0;
 }
 
 static int get_kobj_path_length(struct kobject *kobj)
@@ -247,8 +264,10 @@ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
 		return 0;
 
 	kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs);
-	if (!kobj->name)
+	if (!kobj->name) {
+		kobj->name = old_name;
 		return -ENOMEM;
+	}
 
 	/* ewww... some of these buggers have '/' in the name ... */
 	while ((s = strchr(kobj->name, '/')))
@@ -346,7 +365,7 @@ static int kobject_add_varg(struct kobject *kobj, struct kobject *parent,
  *
  * If @parent is set, then the parent of the @kobj will be set to it.
  * If @parent is NULL, then the parent of the @kobj will be set to the
- * kobject associted with the kset assigned to this kobject.  If no kset
+ * kobject associated with the kset assigned to this kobject.  If no kset
  * is assigned to the kobject, then the kobject will be located in the
  * root of the sysfs tree.
  *
@@ -536,7 +555,7 @@ out:
  */
 void kobject_del(struct kobject *kobj)
 {
-	struct sysfs_dirent *sd;
+	struct kernfs_node *sd;
 
 	if (!kobj)
 		return;
@@ -625,10 +644,12 @@ static void kobject_release(struct kref *kref)
 {
 	struct kobject *kobj = container_of(kref, struct kobject, kref);
 #ifdef CONFIG_DEBUG_KOBJECT_RELEASE
-	pr_info("kobject: '%s' (%p): %s, parent %p (delayed)\n",
-		 kobject_name(kobj), kobj, __func__, kobj->parent);
+	unsigned long delay = HZ + HZ * (get_random_int() & 0x3);
+	pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n",
+		 kobject_name(kobj), kobj, __func__, kobj->parent, delay);
 	INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup);
-	schedule_delayed_work(&kobj->release, HZ);
+
+	schedule_delayed_work(&kobj->release, delay);
 #else
 	kobject_cleanup(kobj);
 #endif
@@ -759,55 +780,6 @@ const struct sysfs_ops kobj_sysfs_ops = {
 	.store	= kobj_attr_store,
 };
 
-/**
- * kobj_completion_init - initialize a kobj_completion object.
- * @kc: kobj_completion
- * @ktype: type of kobject to initialize
- *
- * kobj_completion structures can be embedded within structures with different
- * lifetime rules.  During the release of the enclosing object, we can
- * wait on the release of the kobject so that we don't free it while it's
- * still busy.
- */
-void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype)
-{
-	init_completion(&kc->kc_unregister);
-	kobject_init(&kc->kc_kobj, ktype);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_init);
-
-/**
- * kobj_completion_release - release a kobj_completion object
- * @kobj: kobject embedded in kobj_completion
- *
- * Used with kobject_release to notify waiters that the kobject has been
- * released.
- */
-void kobj_completion_release(struct kobject *kobj)
-{
-	struct kobj_completion *kc = kobj_to_kobj_completion(kobj);
-	complete(&kc->kc_unregister);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_release);
-
-/**
- * kobj_completion_del_and_wait - release the kobject and wait for it
- * @kc: kobj_completion object to release
- *
- * Delete the kobject from sysfs and drop the reference count.  Then wait
- * until any other outstanding references are also dropped.  This routine
- * is only necessary once other references may have been taken on the
- * kobject.  Typically this happens when the kobject has been published
- * to sysfs via kobject_add.
- */
-void kobj_completion_del_and_wait(struct kobj_completion *kc)
-{
-	kobject_del(&kc->kc_kobj);
-	kobject_put(&kc->kc_kobj);
-	wait_for_completion(&kc->kc_unregister);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_del_and_wait);
-
 /**
  * kset_register - initialize and add a kset.
  * @k: kset.
@@ -835,6 +807,7 @@ void kset_unregister(struct kset *k)
 {
 	if (!k)
 		return;
+	kobject_del(&k->kobj);
 	kobject_put(&k->kobj);
 }
 

samples/kobject/kset-example.c

@@ -262,6 +262,7 @@ baz_error:
 bar_error:
 	destroy_foo_obj(foo_obj);
 foo_error:
+	kset_unregister(example_kset);
 	return -EINVAL;
 }