Merge tag 'driver-core-3.13-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 / sysfs update for 3.13-rc1.

  There's lots of dev_groups updates for different subsystems, as they
  all get slowly migrated over to the safe versions of the attribute
  groups (removing userspace races with the creation of the sysfs
  files.) Also in here are some kobject updates, devres expansions, and
  the first round of Tejun's sysfs reworking to enable it to be used by
  other subsystems as a backend for an in-kernel filesystem.

  All of these have been in linux-next for a while with no reported
  issues"

* tag 'driver-core-3.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (83 commits)
  sysfs: rename sysfs_assoc_lock and explain what it's about
  sysfs: use generic_file_llseek() for sysfs_file_operations
  sysfs: return correct error code on unimplemented mmap()
  mdio_bus: convert bus code to use dev_groups
  device: Make dev_WARN/dev_WARN_ONCE print device as well as driver name
  sysfs: separate out dup filename warning into a separate function
  sysfs: move sysfs_hash_and_remove() to fs/sysfs/dir.c
  sysfs: remove unused sysfs_get_dentry() prototype
  sysfs: honor bin_attr.attr.ignore_lockdep
  sysfs: merge sysfs_elem_bin_attr into sysfs_elem_attr
  devres: restore zeroing behavior of devres_alloc()
  sysfs: fix sysfs_write_file for bin file
  input: gameport: convert bus code to use dev_groups
  input: serio: remove bus usage of dev_attrs
  input: serio: use DEVICE_ATTR_RO()
  i2o: convert bus code to use dev_groups
  memstick: convert bus code to use dev_groups
  tifm: convert bus code to use dev_groups
  virtio: convert bus code to use dev_groups
  ipack: convert bus code to use dev_groups
  ...

1 files changed, 239 insertions, 185 deletions

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 4d83ced..08c6696 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -26,21 +26,21 @@
 #include "sysfs.h"
 
 DEFINE_MUTEX(sysfs_mutex);
-DEFINE_SPINLOCK(sysfs_assoc_lock);
+DEFINE_SPINLOCK(sysfs_symlink_target_lock);
 
-#define to_sysfs_dirent(X) rb_entry((X), struct sysfs_dirent, s_rb);
+#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
- *	@ns:   Namespace tag to 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 void *ns, const char *name)
+static unsigned int sysfs_name_hash(const char *name, const void *ns)
 {
 	unsigned long hash = init_name_hash();
 	unsigned int len = strlen(name);
@@ -56,8 +56,8 @@ static unsigned int sysfs_name_hash(const void *ns, const char *name)
 	return hash;
 }
 
-static int sysfs_name_compare(unsigned int hash, const void *ns,
-	const char *name, const struct sysfs_dirent *sd)
+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;
@@ -69,7 +69,7 @@ static int sysfs_name_compare(unsigned int hash, const void *ns,
 static int sysfs_sd_compare(const struct sysfs_dirent *left,
 			    const struct sysfs_dirent *right)
 {
-	return sysfs_name_compare(left->s_hash, left->s_ns, left->s_name,
+	return sysfs_name_compare(left->s_hash, left->s_name, left->s_ns,
 				  right);
 }
 
@@ -111,6 +111,11 @@ static int sysfs_link_sibling(struct sysfs_dirent *sd)
 	/* 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);
+
+	/* if @sd has ns tag, mark the parent to enable ns filtering */
+	if (sd->s_ns)
+		sd->s_parent->s_flags |= SYSFS_FLAG_HAS_NS;
+
 	return 0;
 }
 
@@ -130,26 +135,15 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
 		sd->s_parent->s_dir.subdirs--;
 
 	rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children);
-}
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 
-/* Test for attributes that want to ignore lockdep for read-locking */
-static bool ignore_lockdep(struct sysfs_dirent *sd)
-{
-	return sysfs_type(sd) == SYSFS_KOBJ_ATTR &&
-			sd->s_attr.attr->ignore_lockdep;
-}
-
-#else
-
-static inline bool ignore_lockdep(struct sysfs_dirent *sd)
-{
-	return true;
+	/*
+	 * Either all or none of the children have tags.  Clearing HAS_NS
+	 * when there's no child left is enough to keep the flag synced.
+	 */
+	if (RB_EMPTY_ROOT(&sd->s_parent->s_dir.children))
+		sd->s_parent->s_flags &= ~SYSFS_FLAG_HAS_NS;
 }
 
-#endif
-
 /**
  *	sysfs_get_active - get an active reference to sysfs_dirent
  *	@sd: sysfs_dirent to get an active reference to
@@ -168,7 +162,7 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
 	if (!atomic_inc_unless_negative(&sd->s_active))
 		return NULL;
 
-	if (likely(!ignore_lockdep(sd)))
+	if (likely(!sysfs_ignore_lockdep(sd)))
 		rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
 	return sd;
 }
@@ -187,7 +181,7 @@ void sysfs_put_active(struct sysfs_dirent *sd)
 	if (unlikely(!sd))
 		return;
 
-	if (likely(!ignore_lockdep(sd)))
+	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))
@@ -297,7 +291,6 @@ static int sysfs_dentry_delete(const struct dentry *dentry)
 static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct sysfs_dirent *sd;
-	int type;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -318,13 +311,8 @@ static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
 		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;
-	}
+	if (sd->s_ns && sd->s_ns != sysfs_info(dentry->d_sb)->ns)
+		goto out_bad;
 
 	mutex_unlock(&sysfs_mutex);
 out_valid:
@@ -400,22 +388,19 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
 /**
  *	sysfs_addrm_start - prepare for sysfs_dirent add/remove
  *	@acxt: pointer to sysfs_addrm_cxt to be used
- *	@parent_sd: parent sysfs_dirent
  *
- *	This function is called when the caller is about to add or
- *	remove sysfs_dirent under @parent_sd.  This function acquires
- *	sysfs_mutex.  @acxt is used to keep and pass context to
- *	other addrm functions.
+ *	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,
-		       struct sysfs_dirent *parent_sd)
+void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt)
+	__acquires(sysfs_mutex)
 {
 	memset(acxt, 0, sizeof(*acxt));
-	acxt->parent_sd = parent_sd;
 
 	mutex_lock(&sysfs_mutex);
 }
@@ -424,10 +409,11 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  *	__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 @acxt->parent_sd and set sd->s_parent to it and increment
- *	nlink of parent inode if @sd is a directory and link into the
- *	children list of the parent.
+ *	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
@@ -440,27 +426,21 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  *	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)
+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(acxt->parent_sd) != !!sd->s_ns) {
-		WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
-			sysfs_ns_type(acxt->parent_sd) ? "required" : "invalid",
-			acxt->parent_sd->s_name, sd->s_name);
-		return -EINVAL;
-	}
-
-	sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
-	sd->s_parent = sysfs_get(acxt->parent_sd);
+	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 = acxt->parent_sd->s_iattr;
+	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;
@@ -490,14 +470,32 @@ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
 	return path;
 }
 
+void sysfs_warn_dup(struct sysfs_dirent *parent, const char *name)
+{
+	char *path;
+
+	path = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (path) {
+		sysfs_pathname(parent, path);
+		strlcat(path, "/", PATH_MAX);
+		strlcat(path, name, PATH_MAX);
+	}
+
+	WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n",
+	     path ? path : 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 @acxt->parent_sd and set sd->s_parent to it and increment
- *	nlink of parent inode if @sd is a directory and link into the
- *	children list of the parent.
+ *	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
@@ -510,23 +508,15 @@ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path)
  *	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)
+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);
-	if (ret == -EEXIST) {
-		char *path = kzalloc(PATH_MAX, GFP_KERNEL);
-		WARN(1, KERN_WARNING
-		     "sysfs: cannot create duplicate filename '%s'\n",
-		     (path == NULL) ? sd->s_name
-				    : (sysfs_pathname(acxt->parent_sd, path),
-				       strlcat(path, "/", PATH_MAX),
-				       strlcat(path, sd->s_name, PATH_MAX),
-				       path));
-		kfree(path);
-	}
+	ret = __sysfs_add_one(acxt, sd, parent_sd);
 
+	if (ret == -EEXIST)
+		sysfs_warn_dup(parent_sd, sd->s_name);
 	return ret;
 }
 
@@ -545,16 +535,22 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
  *	LOCKING:
  *	Determined by sysfs_addrm_start().
  */
-void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+static void sysfs_remove_one(struct sysfs_addrm_cxt *acxt,
+			     struct sysfs_dirent *sd)
 {
 	struct sysfs_inode_attrs *ps_iattr;
 
-	BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
+	/*
+	 * 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 = acxt->parent_sd->s_iattr;
+	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;
@@ -577,6 +573,7 @@ void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
  *	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);
@@ -588,7 +585,7 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
 		acxt->removed = sd->u.removed_list;
 
 		sysfs_deactivate(sd);
-		unmap_bin_file(sd);
+		sysfs_unmap_bin_file(sd);
 		sysfs_put(sd);
 	}
 }
@@ -597,6 +594,7 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
  *	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.
  *
@@ -607,26 +605,19 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
  *	Pointer to sysfs_dirent if found, NULL if not.
  */
 struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
-				       const void *ns,
-				       const unsigned char *name)
+				       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(ns, name);
+	hash = sysfs_name_hash(name, ns);
 	while (node) {
 		struct sysfs_dirent *sd;
 		int result;
 
 		sd = to_sysfs_dirent(node);
-		result = sysfs_name_compare(hash, ns, name, sd);
+		result = sysfs_name_compare(hash, name, ns, sd);
 		if (result < 0)
 			node = node->rb_left;
 		else if (result > 0)
@@ -638,9 +629,10 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
 }
 
 /**
- *	sysfs_get_dirent - find and get sysfs_dirent with the given name
+ *	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.
@@ -651,24 +643,24 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
  *	RETURNS:
  *	Pointer to sysfs_dirent if found, NULL if not.
  */
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name)
+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, ns, name);
+	sd = sysfs_find_dirent(parent_sd, name, ns);
 	sysfs_get(sd);
 	mutex_unlock(&sysfs_mutex);
 
 	return sd;
 }
-EXPORT_SYMBOL_GPL(sysfs_get_dirent);
+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 void *ns, const char *name,
-	struct sysfs_dirent **p_sd)
+		      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;
@@ -680,13 +672,12 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 	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, parent_sd);
-	rc = sysfs_add_one(&acxt, sd);
+	sysfs_addrm_start(&acxt);
+	rc = sysfs_add_one(&acxt, sd, parent_sd);
 	sysfs_addrm_finish(&acxt);
 
 	if (rc == 0)
@@ -700,44 +691,17 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
 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, NULL, name, p_sd);
+	return create_dir(kobj, kobj->sd, 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
+ * sysfs_create_dir_ns - create a directory for an object with a namespace tag
+ * @kobj: object we're creating directory for
+ * @ns: the namespace tag to use
  */
-static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
+int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
-	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 - create a directory for an object.
- *	@kobj:		object we're creating directory for.
- */
-int sysfs_create_dir(struct kobject *kobj)
-{
-	enum kobj_ns_type type;
 	struct sysfs_dirent *parent_sd, *sd;
-	const void *ns = NULL;
 	int error = 0;
 
 	BUG_ON(!kobj);
@@ -750,11 +714,7 @@ int sysfs_create_dir(struct kobject *kobj)
 	if (!parent_sd)
 		return -ENOENT;
 
-	if (sysfs_ns_type(parent_sd))
-		ns = kobj->ktype->namespace(kobj);
-	type = sysfs_read_ns_type(kobj);
-
-	error = create_dir(kobj, parent_sd, type, ns, kobject_name(kobj), &sd);
+	error = create_dir(kobj, parent_sd, kobject_name(kobj), ns, &sd);
 	if (!error)
 		kobj->sd = sd;
 	return error;
@@ -768,15 +728,14 @@ static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct sysfs_dirent *parent_sd = parent->d_fsdata;
 	struct sysfs_dirent *sd;
 	struct inode *inode;
-	enum kobj_ns_type type;
-	const void *ns;
+	const void *ns = NULL;
 
 	mutex_lock(&sysfs_mutex);
 
-	type = sysfs_ns_type(parent_sd);
-	ns = sysfs_info(dir->i_sb)->ns[type];
+	if (parent_sd->s_flags & SYSFS_FLAG_HAS_NS)
+		ns = sysfs_info(dir->i_sb)->ns;
 
-	sd = sysfs_find_dirent(parent_sd, ns, dentry->d_name.name);
+	sd = sysfs_find_dirent(parent_sd, dentry->d_name.name, ns);
 
 	/* no such entry */
 	if (!sd) {
@@ -807,41 +766,128 @@ const struct inode_operations sysfs_dir_inode_operations = {
 	.setxattr	= sysfs_setxattr,
 };
 
-static void remove_dir(struct sysfs_dirent *sd)
+static struct sysfs_dirent *sysfs_leftmost_descendant(struct sysfs_dirent *pos)
 {
-	struct sysfs_addrm_cxt acxt;
+	struct sysfs_dirent *last;
 
-	sysfs_addrm_start(&acxt, sd->s_parent);
-	sysfs_remove_one(&acxt, sd);
-	sysfs_addrm_finish(&acxt);
+	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;
 }
 
-void sysfs_remove_subdir(struct sysfs_dirent *sd)
+/**
+ * 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)
 {
-	remove_dir(sd);
+	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);
+}
 
-static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
+/**
+ * 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;
-	struct rb_node *pos;
 
-	if (!dir_sd)
-		return;
+	sysfs_addrm_start(&acxt);
+	__sysfs_remove(&acxt, sd);
+	sysfs_addrm_finish(&acxt);
+}
 
-	pr_debug("sysfs %s: removing dir\n", dir_sd->s_name);
-	sysfs_addrm_start(&acxt, dir_sd);
-	pos = rb_first(&dir_sd->s_dir.children);
-	while (pos) {
-		struct sysfs_dirent *sd = to_sysfs_dirent(pos);
-		pos = rb_next(pos);
-		if (sysfs_type(sd) != SYSFS_DIR)
-			sysfs_remove_one(&acxt, sd);
+/**
+ * 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;
 	}
+
+	sysfs_addrm_start(&acxt);
+
+	sd = sysfs_find_dirent(dir_sd, name, ns);
+	if (sd)
+		__sysfs_remove(&acxt, sd);
+
 	sysfs_addrm_finish(&acxt);
 
-	remove_dir(dir_sd);
+	if (sd)
+		return 0;
+	else
+		return -ENOENT;
 }
 
 /**
@@ -852,21 +898,34 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
  *	the directory before we remove the directory, and we've inlined
  *	what used to be sysfs_rmdir() below, instead of calling separately.
  */
-
 void sysfs_remove_dir(struct kobject *kobj)
 {
 	struct sysfs_dirent *sd = kobj->sd;
 
-	spin_lock(&sysfs_assoc_lock);
+	/*
+	 * 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.
+	 *
+	 * 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_assoc_lock);
+	spin_unlock(&sysfs_symlink_target_lock);
 
-	__sysfs_remove_dir(sd);
+	if (sd) {
+		WARN_ON_ONCE(sysfs_type(sd) != SYSFS_DIR);
+		sysfs_remove(sd);
+	}
 }
 
-int sysfs_rename(struct sysfs_dirent *sd,
-	struct sysfs_dirent *new_parent_sd, const void *new_ns,
-	const char *new_name)
+int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
+		 const char *new_name, const void *new_ns)
 {
 	int error;
 
@@ -878,7 +937,7 @@ int sysfs_rename(struct sysfs_dirent *sd,
 		goto out;	/* nothing to rename */
 
 	error = -EEXIST;
-	if (sysfs_find_dirent(new_parent_sd, new_ns, new_name))
+	if (sysfs_find_dirent(new_parent_sd, new_name, new_ns))
 		goto out;
 
 	/* rename sysfs_dirent */
@@ -899,7 +958,7 @@ int sysfs_rename(struct sysfs_dirent *sd,
 	sysfs_get(new_parent_sd);
 	sysfs_put(sd->s_parent);
 	sd->s_ns = new_ns;
-	sd->s_hash = sysfs_name_hash(sd->s_ns, sd->s_name);
+	sd->s_hash = sysfs_name_hash(sd->s_name, sd->s_ns);
 	sd->s_parent = new_parent_sd;
 	sysfs_link_sibling(sd);
 
@@ -909,30 +968,25 @@ int sysfs_rename(struct sysfs_dirent *sd,
 	return error;
 }
 
-int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+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;
-	const void *new_ns = NULL;
-
-	if (sysfs_ns_type(parent_sd))
-		new_ns = kobj->ktype->namespace(kobj);
 
-	return sysfs_rename(kobj->sd, parent_sd, new_ns, new_name);
+	return sysfs_rename(kobj->sd, parent_sd, new_name, new_ns);
 }
 
-int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
+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;
-	const void *new_ns = NULL;
 
 	BUG_ON(!sd->s_parent);
-	if (sysfs_ns_type(sd->s_parent))
-		new_ns = kobj->ktype->namespace(kobj);
 	new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
 		new_parent_kobj->sd : &sysfs_root;
 
-	return sysfs_rename(sd, new_parent_sd, new_ns, sd->s_name);
+	return sysfs_rename(sd, new_parent_sd, sd->s_name, new_ns);
 }
 
 /* Relationship between s_mode and the DT_xxx types */
@@ -1002,15 +1056,15 @@ 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];
+	const void *ns = NULL;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 	mutex_lock(&sysfs_mutex);
+
+	if (parent_sd->s_flags & SYSFS_FLAG_HAS_NS)
+		ns = sysfs_info(dentry->d_sb)->ns;
+
 	for (pos = sysfs_dir_pos(ns, parent_sd, ctx->pos, pos);
 	     pos;
 	     pos = sysfs_dir_next_pos(ns, parent_sd, ctx->pos, pos)) {