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
  ...

9 files changed, 934 insertions, 1121 deletions

diff --git a/fs/sysfs/Makefile b/fs/sysfs/Makefile
index 7a1ceb946b80..8876ac183373 100644
--- a/fs/sysfs/Makefile
+++ b/fs/sysfs/Makefile
@@ -2,5 +2,4 @@
 # Makefile for the sysfs virtual filesystem
 #
 
-obj-y		:= inode.o file.o dir.o symlink.o mount.o bin.o \
-		   group.o
+obj-y		:= inode.o file.o dir.o symlink.o mount.o group.o
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
deleted file mode 100644
index c590cabd57bb..000000000000
--- a/fs/sysfs/bin.c
+++ /dev/null
@@ -1,502 +0,0 @@
-/*
- * fs/sysfs/bin.c - sysfs binary file implementation
- *
- * Copyright (c) 2003 Patrick Mochel
- * Copyright (c) 2003 Matthew Wilcox
- * Copyright (c) 2004 Silicon Graphics, Inc.
- * 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/errno.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/kobject.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/mm.h>
-#include <linux/uaccess.h>
-
-#include "sysfs.h"
-
-/*
- * There's one bin_buffer for each open file.
- *
- * filp->private_data points to bin_buffer and
- * sysfs_dirent->s_bin_attr.buffers points to a the bin_buffer s
- * sysfs_dirent->s_bin_attr.buffers is protected by sysfs_bin_lock
- */
-static DEFINE_MUTEX(sysfs_bin_lock);
-
-struct bin_buffer {
-	struct mutex			mutex;
-	void				*buffer;
-	int				mmapped;
-	const struct vm_operations_struct *vm_ops;
-	struct file			*file;
-	struct hlist_node		list;
-};
-
-static int
-fill_read(struct file *file, char *buffer, loff_t off, size_t count)
-{
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	int rc;
-
-	/* need attr_sd for attr, its parent for kobj */
-	if (!sysfs_get_active(attr_sd))
-		return -ENODEV;
-
-	rc = -EIO;
-	if (attr->read)
-		rc = attr->read(file, kobj, attr, buffer, off, count);
-
-	sysfs_put_active(attr_sd);
-
-	return rc;
-}
-
-static ssize_t
-read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
-{
-	struct bin_buffer *bb = file->private_data;
-	int size = file_inode(file)->i_size;
-	loff_t offs = *off;
-	int count = min_t(size_t, bytes, PAGE_SIZE);
-	char *temp;
-
-	if (!bytes)
-		return 0;
-
-	if (size) {
-		if (offs > size)
-			return 0;
-		if (offs + count > size)
-			count = size - offs;
-	}
-
-	temp = kmalloc(count, GFP_KERNEL);
-	if (!temp)
-		return -ENOMEM;
-
-	mutex_lock(&bb->mutex);
-
-	count = fill_read(file, bb->buffer, offs, count);
-	if (count < 0) {
-		mutex_unlock(&bb->mutex);
-		goto out_free;
-	}
-
-	memcpy(temp, bb->buffer, count);
-
-	mutex_unlock(&bb->mutex);
-
-	if (copy_to_user(userbuf, temp, count)) {
-		count = -EFAULT;
-		goto out_free;
-	}
-
-	pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
-
-	*off = offs + count;
-
- out_free:
-	kfree(temp);
-	return count;
-}
-
-static int
-flush_write(struct file *file, char *buffer, loff_t offset, size_t count)
-{
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	int rc;
-
-	/* need attr_sd for attr, its parent for kobj */
-	if (!sysfs_get_active(attr_sd))
-		return -ENODEV;
-
-	rc = -EIO;
-	if (attr->write)
-		rc = attr->write(file, kobj, attr, buffer, offset, count);
-
-	sysfs_put_active(attr_sd);
-
-	return rc;
-}
-
-static ssize_t write(struct file *file, const char __user *userbuf,
-		     size_t bytes, loff_t *off)
-{
-	struct bin_buffer *bb = file->private_data;
-	int size = file_inode(file)->i_size;
-	loff_t offs = *off;
-	int count = min_t(size_t, bytes, PAGE_SIZE);
-	char *temp;
-
-	if (!bytes)
-		return 0;
-
-	if (size) {
-		if (offs > size)
-			return 0;
-		if (offs + count > size)
-			count = size - offs;
-	}
-
-	temp = memdup_user(userbuf, count);
-	if (IS_ERR(temp))
-		return PTR_ERR(temp);
-
-	mutex_lock(&bb->mutex);
-
-	memcpy(bb->buffer, temp, count);
-
-	count = flush_write(file, bb->buffer, offs, count);
-	mutex_unlock(&bb->mutex);
-
-	if (count > 0)
-		*off = offs + count;
-
-	kfree(temp);
-	return count;
-}
-
-static void bin_vma_open(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-
-	if (!bb->vm_ops)
-		return;
-
-	if (!sysfs_get_active(attr_sd))
-		return;
-
-	if (bb->vm_ops->open)
-		bb->vm_ops->open(vma);
-
-	sysfs_put_active(attr_sd);
-}
-
-static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	int ret;
-
-	if (!bb->vm_ops)
-		return VM_FAULT_SIGBUS;
-
-	if (!sysfs_get_active(attr_sd))
-		return VM_FAULT_SIGBUS;
-
-	ret = VM_FAULT_SIGBUS;
-	if (bb->vm_ops->fault)
-		ret = bb->vm_ops->fault(vma, vmf);
-
-	sysfs_put_active(attr_sd);
-	return ret;
-}
-
-static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	int ret;
-
-	if (!bb->vm_ops)
-		return VM_FAULT_SIGBUS;
-
-	if (!sysfs_get_active(attr_sd))
-		return VM_FAULT_SIGBUS;
-
-	ret = 0;
-	if (bb->vm_ops->page_mkwrite)
-		ret = bb->vm_ops->page_mkwrite(vma, vmf);
-	else
-		file_update_time(file);
-
-	sysfs_put_active(attr_sd);
-	return ret;
-}
-
-static int bin_access(struct vm_area_struct *vma, unsigned long addr,
-		  void *buf, int len, int write)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	int ret;
-
-	if (!bb->vm_ops)
-		return -EINVAL;
-
-	if (!sysfs_get_active(attr_sd))
-		return -EINVAL;
-
-	ret = -EINVAL;
-	if (bb->vm_ops->access)
-		ret = bb->vm_ops->access(vma, addr, buf, len, write);
-
-	sysfs_put_active(attr_sd);
-	return ret;
-}
-
-#ifdef CONFIG_NUMA
-static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	int ret;
-
-	if (!bb->vm_ops)
-		return 0;
-
-	if (!sysfs_get_active(attr_sd))
-		return -EINVAL;
-
-	ret = 0;
-	if (bb->vm_ops->set_policy)
-		ret = bb->vm_ops->set_policy(vma, new);
-
-	sysfs_put_active(attr_sd);
-	return ret;
-}
-
-static struct mempolicy *bin_get_policy(struct vm_area_struct *vma,
-					unsigned long addr)
-{
-	struct file *file = vma->vm_file;
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct mempolicy *pol;
-
-	if (!bb->vm_ops)
-		return vma->vm_policy;
-
-	if (!sysfs_get_active(attr_sd))
-		return vma->vm_policy;
-
-	pol = vma->vm_policy;
-	if (bb->vm_ops->get_policy)
-		pol = bb->vm_ops->get_policy(vma, addr);
-
-	sysfs_put_active(attr_sd);
-	return pol;
-}
-
-static int 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 bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	int ret;
-
-	if (!bb->vm_ops)
-		return 0;
-
-	if (!sysfs_get_active(attr_sd))
-		return 0;
-
-	ret = 0;
-	if (bb->vm_ops->migrate)
-		ret = bb->vm_ops->migrate(vma, from, to, flags);
-
-	sysfs_put_active(attr_sd);
-	return ret;
-}
-#endif
-
-static const struct vm_operations_struct bin_vm_ops = {
-	.open		= bin_vma_open,
-	.fault		= bin_fault,
-	.page_mkwrite	= bin_page_mkwrite,
-	.access		= bin_access,
-#ifdef CONFIG_NUMA
-	.set_policy	= bin_set_policy,
-	.get_policy	= bin_get_policy,
-	.migrate	= bin_migrate,
-#endif
-};
-
-static int mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct bin_buffer *bb = file->private_data;
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	int rc;
-
-	mutex_lock(&bb->mutex);
-
-	/* need attr_sd for attr, its parent for kobj */
-	rc = -ENODEV;
-	if (!sysfs_get_active(attr_sd))
-		goto out_unlock;
-
-	rc = -EINVAL;
-	if (!attr->mmap)
-		goto out_put;
-
-	rc = attr->mmap(file, kobj, attr, 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 (bb->mmapped && bb->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;
-	bb->mmapped = 1;
-	bb->vm_ops = vma->vm_ops;
-	vma->vm_ops = &bin_vm_ops;
-out_put:
-	sysfs_put_active(attr_sd);
-out_unlock:
-	mutex_unlock(&bb->mutex);
-
-	return rc;
-}
-
-static int open(struct inode *inode, struct file *file)
-{
-	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
-	struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
-	struct bin_buffer *bb = NULL;
-	int error;
-
-	/* binary file operations requires both @sd and its parent */
-	if (!sysfs_get_active(attr_sd))
-		return -ENODEV;
-
-	error = -EACCES;
-	if ((file->f_mode & FMODE_WRITE) && !(attr->write || attr->mmap))
-		goto err_out;
-	if ((file->f_mode & FMODE_READ) && !(attr->read || attr->mmap))
-		goto err_out;
-
-	error = -ENOMEM;
-	bb = kzalloc(sizeof(*bb), GFP_KERNEL);
-	if (!bb)
-		goto err_out;
-
-	bb->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!bb->buffer)
-		goto err_out;
-
-	mutex_init(&bb->mutex);
-	bb->file = file;
-	file->private_data = bb;
-
-	mutex_lock(&sysfs_bin_lock);
-	hlist_add_head(&bb->list, &attr_sd->s_bin_attr.buffers);
-	mutex_unlock(&sysfs_bin_lock);
-
-	/* open succeeded, put active references */
-	sysfs_put_active(attr_sd);
-	return 0;
-
- err_out:
-	sysfs_put_active(attr_sd);
-	kfree(bb);
-	return error;
-}
-
-static int release(struct inode *inode, struct file *file)
-{
-	struct bin_buffer *bb = file->private_data;
-
-	mutex_lock(&sysfs_bin_lock);
-	hlist_del(&bb->list);
-	mutex_unlock(&sysfs_bin_lock);
-
-	kfree(bb->buffer);
-	kfree(bb);
-	return 0;
-}
-
-const struct file_operations bin_fops = {
-	.read		= read,
-	.write		= write,
-	.mmap		= mmap,
-	.llseek		= generic_file_llseek,
-	.open		= open,
-	.release	= release,
-};
-
-
-void unmap_bin_file(struct sysfs_dirent *attr_sd)
-{
-	struct bin_buffer *bb;
-
-	if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR)
-		return;
-
-	mutex_lock(&sysfs_bin_lock);
-
-	hlist_for_each_entry(bb, &attr_sd->s_bin_attr.buffers, list) {
-		struct inode *inode = file_inode(bb->file);
-
-		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
-	}
-
-	mutex_unlock(&sysfs_bin_lock);
-}
-
-/**
- *	sysfs_create_bin_file - create binary file for object.
- *	@kobj:	object.
- *	@attr:	attribute descriptor.
- */
-int sysfs_create_bin_file(struct kobject *kobj,
-			  const struct bin_attribute *attr)
-{
-	BUG_ON(!kobj || !kobj->sd || !attr);
-
-	return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
-}
-EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
-
-/**
- *	sysfs_remove_bin_file - remove binary file for object.
- *	@kobj:	object.
- *	@attr:	attribute descriptor.
- */
-void sysfs_remove_bin_file(struct kobject *kobj,
-			   const struct bin_attribute *attr)
-{
-	sysfs_hash_and_remove(kobj->sd, NULL, attr->attr.name);
-}
-EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 4d83cedb9fcb..08c66969d52a 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)) {
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 15ef5eb13663..79b5da2acbe1 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -21,70 +21,114 @@
 #include <linux/mutex.h>
 #include <linux/limits.h>
 #include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/mm.h>
 
 #include "sysfs.h"
 
 /*
- * There's one sysfs_buffer for each open file and one
- * sysfs_open_dirent for each sysfs_dirent with one or more open
- * files.
+ * 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.
  *
- * filp->private_data points to sysfs_buffer and
- * sysfs_dirent->s_attr.open points to sysfs_open_dirent.  s_attr.open
- * is protected by sysfs_open_dirent_lock.
+ * 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	buffers; /* goes through sysfs_buffer.list */
+	struct list_head	files; /* goes through sysfs_open_file.list */
 };
 
-struct sysfs_buffer {
-	size_t			count;
-	loff_t			pos;
-	char			*page;
-	const struct sysfs_ops	*ops;
+struct sysfs_open_file {
+	struct sysfs_dirent	*sd;
+	struct file		*file;
 	struct mutex		mutex;
-	int			needs_read_fill;
 	int			event;
 	struct list_head	list;
+
+	bool			mmapped;
+	const struct vm_operations_struct *vm_ops;
 };
 
-/**
- *	fill_read_buffer - allocate and fill buffer from object.
- *	@dentry:	dentry pointer.
- *	@buffer:	data buffer for file.
- *
- *	Allocate @buffer->page, if it hasn't been already, then call the
- *	kobject's show() method to fill the buffer with this attribute's
- *	data.
- *	This is called only once, on the file's first read unless an error
- *	is returned.
+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
+ * must be called while holding an active reference.
  */
-static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer)
+static const struct sysfs_ops *sysfs_file_ops(struct sysfs_dirent *sd)
 {
-	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	const struct sysfs_ops *ops = buffer->ops;
-	int ret = 0;
+	struct kobject *kobj = sd->s_parent->s_dir.kobj;
+
+	if (!sysfs_ignore_lockdep(sd))
+		lockdep_assert_held(sd);
+	return kobj->ktype ? kobj->ktype->sysfs_ops : NULL;
+}
+
+/*
+ * Reads on sysfs are handled through seq_file, which takes care of hairy
+ * 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)
+{
+	struct sysfs_open_file *of = sf->private;
+	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+	const struct sysfs_ops *ops;
+	char *buf;
 	ssize_t count;
 
-	if (!buffer->page)
-		buffer->page = (char *) get_zeroed_page(GFP_KERNEL);
-	if (!buffer->page)
-		return -ENOMEM;
+	/* acquire buffer and ensure that it's >= PAGE_SIZE */
+	count = seq_get_buf(sf, &buf);
+	if (count < PAGE_SIZE) {
+		seq_commit(sf, -1);
+		return 0;
+	}
 
-	/* need attr_sd for attr and ops, its parent for kobj */
-	if (!sysfs_get_active(attr_sd))
+	/*
+	 * 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;
+	}
 
-	buffer->event = atomic_read(&attr_sd->s_attr.open->event);
-	count = ops->show(kobj, attr_sd->s_attr.attr, buffer->page);
+	of->event = atomic_read(&of->sd->s_attr.open->event);
 
-	sysfs_put_active(attr_sd);
+	/*
+	 * 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
@@ -96,155 +140,389 @@ static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer)
 		/* Try to struggle along */
 		count = PAGE_SIZE - 1;
 	}
-	if (count >= 0) {
-		buffer->needs_read_fill = 0;
-		buffer->count = count;
-	} else {
-		ret = count;
-	}
-	return ret;
+	seq_commit(sf, count);
+	return 0;
 }
 
-/**
- *	sysfs_read_file - read an attribute.
- *	@file:	file pointer.
- *	@buf:	buffer to fill.
- *	@count:	number of bytes to read.
- *	@ppos:	starting offset in file.
- *
- *	Userspace wants to read an attribute file. The attribute descriptor
- *	is in the file's ->d_fsdata. The target object is in the directory's
- *	->d_fsdata.
- *
- *	We call fill_read_buffer() to allocate and fill the buffer from the
- *	object's show() method exactly once (if the read is happening from
- *	the beginning of the file). That should fill the entire buffer with
- *	all the data the object has to offer for that attribute.
- *	We then call flush_read_buffer() to copy the buffer to userspace
- *	in the increments specified.
+/*
+ * 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_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+static ssize_t sysfs_bin_read(struct file *file, char __user *userbuf,
+			      size_t bytes, loff_t *off)
 {
-	struct sysfs_buffer *buffer = file->private_data;
-	ssize_t retval = 0;
+	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;
+
+	if (!bytes)
+		return 0;
 
-	mutex_lock(&buffer->mutex);
-	if (buffer->needs_read_fill || *ppos == 0) {
-		retval = fill_read_buffer(file->f_path.dentry, buffer);
-		if (retval)
-			goto out;
+	if (size) {
+		if (offs > size)
+			return 0;
+		if (offs + count > size)
+			count = size - offs;
 	}
-	pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
-		 __func__, count, *ppos, buffer->page);
-	retval = simple_read_from_buffer(buf, count, ppos, buffer->page,
-					 buffer->count);
-out:
-	mutex_unlock(&buffer->mutex);
-	return retval;
-}
 
-/**
- *	fill_write_buffer - copy buffer from userspace.
- *	@buffer:	data buffer for file.
- *	@buf:		data from user.
- *	@count:		number of bytes in @userbuf.
- *
- *	Allocate @buffer->page if it hasn't been already, then
- *	copy the user-supplied buffer into it.
- */
-static int fill_write_buffer(struct sysfs_buffer *buffer,
-			     const char __user *buf, size_t count)
-{
-	int error;
-
-	if (!buffer->page)
-		buffer->page = (char *)get_zeroed_page(GFP_KERNEL);
-	if (!buffer->page)
+	buf = kmalloc(count, GFP_KERNEL);
+	if (!buf)
 		return -ENOMEM;
 
-	if (count >= PAGE_SIZE)
-		count = PAGE_SIZE - 1;
-	error = copy_from_user(buffer->page, buf, count);
-	buffer->needs_read_fill = 1;
-	/* if buf is assumed to contain a string, terminate it by \0,
-	   so e.g. sscanf() can scan the string easily */
-	buffer->page[count] = 0;
-	return error ? -EFAULT : count;
-}
+	/* 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;
+	}
+
+	pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
+
+	*off = offs + count;
+
+ out_free:
+	kfree(buf);
+	return count;
+}
 
 /**
- *	flush_write_buffer - push buffer to kobject.
- *	@dentry:	dentry to the attribute
- *	@buffer:	data buffer for file.
- *	@count:		number of bytes
+ * 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 the attribute,
- *	passing the buffer that we acquired in fill_write_buffer().
+ * 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 dentry *dentry,
-			      struct sysfs_buffer *buffer, size_t count)
+static int flush_write_buffer(struct sysfs_open_file *of, char *buf, loff_t off,
+			      size_t count)
 {
-	struct sysfs_dirent *attr_sd = dentry->d_fsdata;
-	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	const struct sysfs_ops *ops = buffer->ops;
-	int rc;
+	struct kobject *kobj = of->sd->s_parent->s_dir.kobj;
+	int rc = 0;
 
-	/* need attr_sd for attr and ops, its parent for kobj */
-	if (!sysfs_get_active(attr_sd))
+	/*
+	 * 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;
+	}
 
-	rc = ops->store(kobj, attr_sd->s_attr.attr, buffer->page, count);
+	if (sysfs_is_bin(of->sd)) {
+		struct bin_attribute *battr = of->sd->s_attr.bin_attr;
 
-	sysfs_put_active(attr_sd);
+		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);
 
 	return rc;
 }
 
-
 /**
- *	sysfs_write_file - write an attribute.
- *	@file:	file pointer
- *	@buf:	data to write
- *	@count:	number of bytes
- *	@ppos:	starting offset
+ * 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().
  *
- *	Similar to sysfs_read_file(), though working in the opposite direction.
- *	We allocate and fill the data from the user in fill_write_buffer(),
- *	then push it to the kobject in flush_write_buffer().
- *	There is no easy way for us to know if userspace is only doing a partial
- *	write, so we don't support them. We expect the entire buffer to come
- *	on the first write.
- *	Hint: if you're writing a value, first read the file, modify only the
- *	the value you're changing, then write entire buffer back.
+ * 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 *buf,
+static ssize_t sysfs_write_file(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
-	struct sysfs_buffer *buffer = file->private_data;
-	ssize_t len;
+	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;
+
+	if (sysfs_is_bin(of->sd) && size) {
+		if (size <= *ppos)
+			return 0;
+		len = min_t(ssize_t, len, size - *ppos);
+	}
 
-	mutex_lock(&buffer->mutex);
-	len = fill_write_buffer(buffer, buf, count);
-	if (len > 0)
-		len = flush_write_buffer(file->f_path.dentry, buffer, len);
+	if (!len)
+		return 0;
+
+	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 */
+
+	len = flush_write_buffer(of, buf, *ppos, len);
 	if (len > 0)
 		*ppos += len;
-	mutex_unlock(&buffer->mutex);
+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);
+}
+
+static int sysfs_bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct sysfs_open_file *of = sysfs_of(file);
+	int ret;
+
+	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;
+}
+
+static int sysfs_bin_page_mkwrite(struct vm_area_struct *vma,
+				  struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct sysfs_open_file *of = sysfs_of(file);
+	int ret;
+
+	if (!of->vm_ops)
+		return VM_FAULT_SIGBUS;
+
+	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);
+	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;
+
+	/*
+	 * 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
- *	@buffer: sysfs_buffer for this instance of open
+ *	@of: sysfs_open_file for this instance of open
  *
  *	If @sd->s_attr.open exists, increment its reference count;
- *	otherwise, create one.  @buffer is chained to the buffers
- *	list.
+ *	otherwise, create one.  @of is chained to the files list.
  *
  *	LOCKING:
  *	Kernel thread context (may sleep).
@@ -253,11 +531,12 @@ static ssize_t sysfs_write_file(struct file *file, const char __user *buf,
  *	0 on success, -errno on failure.
  */
 static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
-				 struct sysfs_buffer *buffer)
+				 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) {
@@ -268,10 +547,11 @@ static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
 	od = sd->s_attr.open;
 	if (od) {
 		atomic_inc(&od->refcnt);
-		list_add_tail(&buffer->list, &od->buffers);
+		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);
@@ -286,36 +566,40 @@ static int sysfs_get_open_dirent(struct sysfs_dirent *sd,
 	atomic_set(&new_od->refcnt, 0);
 	atomic_set(&new_od->event, 1);
 	init_waitqueue_head(&new_od->poll);
-	INIT_LIST_HEAD(&new_od->buffers);
+	INIT_LIST_HEAD(&new_od->files);
 	goto retry;
 }
 
 /**
  *	sysfs_put_open_dirent - put sysfs_open_dirent
  *	@sd: target sysfs_dirent
- *	@buffer: associated sysfs_buffer
+ *	@of: associated sysfs_open_file
  *
- *	Put @sd->s_attr.open and unlink @buffer from the buffers list.
- *	If reference count reaches zero, disassociate and free it.
+ *	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_buffer *buffer)
+				  struct sysfs_open_file *of)
 {
 	struct sysfs_open_dirent *od = sd->s_attr.open;
 	unsigned long flags;
 
+	mutex_lock(&sysfs_open_file_mutex);
 	spin_lock_irqsave(&sysfs_open_dirent_lock, flags);
 
-	list_del(&buffer->list);
+	if (of)
+		list_del(&of->list);
+
 	if (atomic_dec_and_test(&od->refcnt))
 		sd->s_attr.open = NULL;
 	else
 		od = NULL;
 
 	spin_unlock_irqrestore(&sysfs_open_dirent_lock, flags);
+	mutex_unlock(&sysfs_open_file_mutex);
 
 	kfree(od);
 }
@@ -324,67 +608,81 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 {
 	struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
 	struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
-	struct sysfs_buffer *buffer;
-	const struct sysfs_ops *ops;
+	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;
 
-	/* every kobject with an attribute needs a ktype assigned */
-	if (kobj->ktype && kobj->ktype->sysfs_ops)
-		ops = kobj->ktype->sysfs_ops;
-	else {
-		WARN(1, KERN_ERR
-		     "missing sysfs attribute operations for kobject: %s\n",
-		     kobject_name(kobj));
-		goto err_out;
-	}
+	if (sysfs_is_bin(attr_sd)) {
+		struct bin_attribute *battr = attr_sd->s_attr.bin_attr;
 
-	/* File needs write support.
-	 * The inode's perms must say it's ok,
-	 * and we must have a store method.
-	 */
-	if (file->f_mode & FMODE_WRITE) {
-		if (!(inode->i_mode & S_IWUGO) || !ops->store)
-			goto err_out;
-	}
+		has_read = battr->read || battr->mmap;
+		has_write = battr->write || battr->mmap;
+	} else {
+		const struct sysfs_ops *ops = sysfs_file_ops(attr_sd);
 
-	/* File needs read support.
-	 * The inode's perms must say it's ok, and we there
-	 * must be a show method for it.
-	 */
-	if (file->f_mode & FMODE_READ) {
-		if (!(inode->i_mode & S_IRUGO) || !ops->show)
+		/* every kobject with an attribute needs a ktype assigned */
+		if (WARN(!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;
 	}
 
-	/* No error? Great, allocate a buffer for the file, and store it
-	 * it in file->private_data for easy access.
-	 */
+	/* 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;
-	buffer = kzalloc(sizeof(struct sysfs_buffer), GFP_KERNEL);
-	if (!buffer)
+	of = kzalloc(sizeof(struct sysfs_open_file), GFP_KERNEL);
+	if (!of)
 		goto err_out;
 
-	mutex_init(&buffer->mutex);
-	buffer->needs_read_fill = 1;
-	buffer->ops = ops;
-	file->private_data = buffer;
+	mutex_init(&of->mutex);
+	of->sd = attr_sd;
+	of->file = file;
 
-	/* make sure we have open dirent struct */
-	error = sysfs_get_open_dirent(attr_sd, buffer);
+	/*
+	 * 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_free:
-	kfree(buffer);
- err_out:
+err_close:
+	single_release(inode, file);
+err_free:
+	kfree(of);
+err_out:
 	sysfs_put_active(attr_sd);
 	return error;
 }
@@ -392,17 +690,41 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
 static int sysfs_release(struct inode *inode, struct file *filp)
 {
 	struct sysfs_dirent *sd = filp->f_path.dentry->d_fsdata;
-	struct sysfs_buffer *buffer = filp->private_data;
+	struct sysfs_open_file *of = sysfs_of(filp);
 
-	sysfs_put_open_dirent(sd, buffer);
-
-	if (buffer->page)
-		free_page((unsigned long)buffer->page);
-	kfree(buffer);
+	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);
+	}
+	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
@@ -418,7 +740,7 @@ static int sysfs_release(struct inode *inode, struct file *filp)
  */
 static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
 {
-	struct sysfs_buffer *buffer = filp->private_data;
+	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;
 
@@ -430,13 +752,12 @@ static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
 
 	sysfs_put_active(attr_sd);
 
-	if (buffer->event != atomic_read(&od->event))
+	if (of->event != atomic_read(&od->event))
 		goto trigger;
 
 	return DEFAULT_POLLMASK;
 
  trigger:
-	buffer->needs_read_fill = 1;
 	return DEFAULT_POLLMASK|POLLERR|POLLPRI;
 }
 
@@ -466,9 +787,9 @@ void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
 	mutex_lock(&sysfs_mutex);
 
 	if (sd && dir)
-		sd = sysfs_find_dirent(sd, NULL, dir);
+		sd = sysfs_find_dirent(sd, dir, NULL);
 	if (sd && attr)
-		sd = sysfs_find_dirent(sd, NULL, attr);
+		sd = sysfs_find_dirent(sd, attr, NULL);
 	if (sd)
 		sysfs_notify_dirent(sd);
 
@@ -477,7 +798,7 @@ void sysfs_notify(struct kobject *k, const char *dir, const char *attr)
 EXPORT_SYMBOL_GPL(sysfs_notify);
 
 const struct file_operations sysfs_file_operations = {
-	.read		= sysfs_read_file,
+	.read		= seq_read,
 	.write		= sysfs_write_file,
 	.llseek		= generic_file_llseek,
 	.open		= sysfs_open_file,
@@ -485,58 +806,25 @@ const struct file_operations sysfs_file_operations = {
 	.poll		= sysfs_poll,
 };
 
-static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr,
-			 const void **pns)
-{
-	struct sysfs_dirent *dir_sd = kobj->sd;
-	const struct sysfs_ops *ops;
-	const void *ns = NULL;
-	int err;
-
-	if (!dir_sd) {
-		WARN(1, KERN_ERR "sysfs: kobject %s without dirent\n",
-			kobject_name(kobj));
-		return -ENOENT;
-	}
-
-	err = 0;
-	if (!sysfs_ns_type(dir_sd))
-		goto out;
-
-	err = -EINVAL;
-	if (!kobj->ktype)
-		goto out;
-	ops = kobj->ktype->sysfs_ops;
-	if (!ops)
-		goto out;
-	if (!ops->namespace)
-		goto out;
-
-	err = 0;
-	ns = ops->namespace(kobj, attr);
-out:
-	if (err) {
-		WARN(1, KERN_ERR
-		     "missing sysfs namespace attribute operation for kobject: %s\n",
-		     kobject_name(kobj));
-	}
-	*pns = ns;
-	return err;
-}
+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(struct sysfs_dirent *dir_sd,
-			const struct attribute *attr, int type, umode_t amode)
+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;
-	const void *ns;
 	int rc;
 
-	rc = sysfs_attr_ns(dir_sd->s_dir.kobj, attr, &ns);
-	if (rc)
-		return rc;
-
 	sd = sysfs_new_dirent(attr->name, mode, type);
 	if (!sd)
 		return -ENOMEM;
@@ -545,8 +833,8 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
 	sd->s_attr.attr = (void *)attr;
 	sysfs_dirent_init_lockdep(sd);
 
-	sysfs_addrm_start(&acxt, dir_sd);
-	rc = sysfs_add_one(&acxt, sd);
+	sysfs_addrm_start(&acxt);
+	rc = sysfs_add_one(&acxt, sd, dir_sd);
 	sysfs_addrm_finish(&acxt);
 
 	if (rc)
@@ -559,23 +847,25 @@ int sysfs_add_file_mode(struct sysfs_dirent *dir_sd,
 int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
 		   int type)
 {
-	return sysfs_add_file_mode(dir_sd, attr, type, attr->mode);
+	return sysfs_add_file_mode_ns(dir_sd, attr, type, attr->mode, NULL);
 }
 
-
 /**
- *	sysfs_create_file - create an attribute file for an object.
- *	@kobj:	object we're creating for.
- *	@attr:	attribute descriptor.
+ * sysfs_create_file_ns - create an attribute file for an object with custom ns
+ * @kobj: object we're creating for
+ * @attr: attribute descriptor
+ * @ns: namespace the new file should belong to
  */
-int sysfs_create_file(struct kobject *kobj, const struct attribute *attr)
+int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
+			 const void *ns)
 {
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR);
+	return sysfs_add_file_mode_ns(kobj->sd, attr, SYSFS_KOBJ_ATTR,
+				      attr->mode, ns);
 
 }
-EXPORT_SYMBOL_GPL(sysfs_create_file);
+EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
 
 int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
 {
@@ -604,7 +894,7 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 	int error;
 
 	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, NULL, group);
+		dir_sd = sysfs_get_dirent(kobj->sd, group);
 	else
 		dir_sd = sysfs_get(kobj->sd);
 
@@ -630,17 +920,12 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 {
 	struct sysfs_dirent *sd;
 	struct iattr newattrs;
-	const void *ns;
 	int rc;
 
-	rc = sysfs_attr_ns(kobj, attr, &ns);
-	if (rc)
-		return rc;
-
 	mutex_lock(&sysfs_mutex);
 
 	rc = -ENOENT;
-	sd = sysfs_find_dirent(kobj->sd, ns, attr->name);
+	sd = sysfs_find_dirent(kobj->sd, attr->name, NULL);
 	if (!sd)
 		goto out;
 
@@ -655,22 +940,21 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 EXPORT_SYMBOL_GPL(sysfs_chmod_file);
 
 /**
- *	sysfs_remove_file - remove an object attribute.
- *	@kobj:	object we're acting for.
- *	@attr:	attribute descriptor.
+ * sysfs_remove_file_ns - remove an object attribute with a custom ns tag
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ * @ns: namespace tag of the file to remove
  *
- *	Hash the attribute name and kill the victim.
+ * Hash the attribute name and namespace tag and kill the victim.
  */
-void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr)
+void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
+			  const void *ns)
 {
-	const void *ns;
-
-	if (sysfs_attr_ns(kobj, attr, &ns))
-		return;
+	struct sysfs_dirent *dir_sd = kobj->sd;
 
-	sysfs_hash_and_remove(kobj->sd, ns, attr->name);
+	sysfs_hash_and_remove(dir_sd, attr->name, ns);
 }
-EXPORT_SYMBOL_GPL(sysfs_remove_file);
+EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
 {
@@ -692,16 +976,42 @@ void sysfs_remove_file_from_group(struct kobject *kobj,
 	struct sysfs_dirent *dir_sd;
 
 	if (group)
-		dir_sd = sysfs_get_dirent(kobj->sd, NULL, 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, NULL, attr->name);
+		sysfs_hash_and_remove(dir_sd, attr->name, NULL);
 		sysfs_put(dir_sd);
 	}
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);
 
+/**
+ *	sysfs_create_bin_file - create binary file for object.
+ *	@kobj:	object.
+ *	@attr:	attribute descriptor.
+ */
+int sysfs_create_bin_file(struct kobject *kobj,
+			  const struct bin_attribute *attr)
+{
+	BUG_ON(!kobj || !kobj->sd || !attr);
+
+	return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
+}
+EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
+
+/**
+ *	sysfs_remove_bin_file - remove binary file for object.
+ *	@kobj:	object.
+ *	@attr:	attribute descriptor.
+ */
+void sysfs_remove_bin_file(struct kobject *kobj,
+			   const struct bin_attribute *attr)
+{
+	sysfs_hash_and_remove(kobj->sd, attr->attr.name, NULL);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
+
 struct sysfs_schedule_callback_struct {
 	struct list_head	workq_list;
 	struct kobject		*kobj;
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 5f92cd2f61c1..1898a10e38ce 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -26,7 +26,7 @@ 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, NULL, (*attr)->name);
+			sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
 	if (grp->bin_attrs)
 		for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++)
 			sysfs_remove_bin_file(kobj, *bin_attr);
@@ -49,16 +49,17 @@ 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, NULL,
-						      (*attr)->name);
+				sysfs_hash_and_remove(dir_sd, (*attr)->name,
+						      NULL);
 			if (grp->is_visible) {
 				mode = grp->is_visible(kobj, *attr, i);
 				if (!mode)
 					continue;
 			}
-			error = sysfs_add_file_mode(dir_sd, *attr,
-						    SYSFS_KOBJ_ATTR,
-						    (*attr)->mode | mode);
+			error = sysfs_add_file_mode_ns(dir_sd, *attr,
+						       SYSFS_KOBJ_ATTR,
+						       (*attr)->mode | mode,
+						       NULL);
 			if (unlikely(error))
 				break;
 		}
@@ -110,7 +111,7 @@ static int internal_create_group(struct kobject *kobj, int update,
 	error = create_files(sd, kobj, grp, update);
 	if (error) {
 		if (grp->name)
-			sysfs_remove_subdir(sd);
+			sysfs_remove(sd);
 	}
 	sysfs_put(sd);
 	return error;
@@ -206,7 +207,7 @@ void sysfs_remove_group(struct kobject *kobj,
 	struct sysfs_dirent *sd;
 
 	if (grp->name) {
-		sd = sysfs_get_dirent(dir_sd, NULL, grp->name);
+		sd = sysfs_get_dirent(dir_sd, grp->name);
 		if (!sd) {
 			WARN(!sd, KERN_WARNING
 			     "sysfs group %p not found for kobject '%s'\n",
@@ -218,7 +219,7 @@ void sysfs_remove_group(struct kobject *kobj,
 
 	remove_files(sd, kobj, grp);
 	if (grp->name)
-		sysfs_remove_subdir(sd);
+		sysfs_remove(sd);
 
 	sysfs_put(sd);
 }
@@ -261,7 +262,7 @@ int sysfs_merge_group(struct kobject *kobj,
 	struct attribute *const *attr;
 	int i;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
 	if (!dir_sd)
 		return -ENOENT;
 
@@ -269,7 +270,7 @@ int sysfs_merge_group(struct kobject *kobj,
 		error = sysfs_add_file(dir_sd, *attr, SYSFS_KOBJ_ATTR);
 	if (error) {
 		while (--i >= 0)
-			sysfs_hash_and_remove(dir_sd, NULL, (*--attr)->name);
+			sysfs_hash_and_remove(dir_sd, (*--attr)->name, NULL);
 	}
 	sysfs_put(dir_sd);
 
@@ -288,10 +289,10 @@ void sysfs_unmerge_group(struct kobject *kobj,
 	struct sysfs_dirent *dir_sd;
 	struct attribute *const *attr;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, grp->name);
+	dir_sd = sysfs_get_dirent(kobj->sd, grp->name);
 	if (dir_sd) {
 		for (attr = grp->attrs; *attr; ++attr)
-			sysfs_hash_and_remove(dir_sd, NULL, (*attr)->name);
+			sysfs_hash_and_remove(dir_sd, (*attr)->name, NULL);
 		sysfs_put(dir_sd);
 	}
 }
@@ -310,7 +311,7 @@ int sysfs_add_link_to_group(struct kobject *kobj, const char *group_name,
 	struct sysfs_dirent *dir_sd;
 	int error = 0;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
 	if (!dir_sd)
 		return -ENOENT;
 
@@ -332,9 +333,9 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
 {
 	struct sysfs_dirent *dir_sd;
 
-	dir_sd = sysfs_get_dirent(kobj->sd, NULL, group_name);
+	dir_sd = sysfs_get_dirent(kobj->sd, group_name);
 	if (dir_sd) {
-		sysfs_hash_and_remove(dir_sd, NULL, link_name);
+		sysfs_hash_and_remove(dir_sd, link_name, NULL);
 		sysfs_put(dir_sd);
 	}
 }
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 963f910c8034..1750f790af3b 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -258,9 +258,9 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
 		inode->i_fop = &sysfs_file_operations;
 		break;
 	case SYSFS_KOBJ_BIN_ATTR:
-		bin_attr = sd->s_bin_attr.bin_attr;
+		bin_attr = sd->s_attr.bin_attr;
 		inode->i_size = bin_attr->size;
-		inode->i_fop = &bin_fops;
+		inode->i_fop = &sysfs_bin_operations;
 		break;
 	case SYSFS_KOBJ_LINK:
 		inode->i_op = &sysfs_symlink_inode_operations;
@@ -314,32 +314,6 @@ void sysfs_evict_inode(struct inode *inode)
 	sysfs_put(sd);
 }
 
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
-			  const char *name)
-{
-	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, dir_sd);
-
-	sd = sysfs_find_dirent(dir_sd, ns, name);
-	if (sd)
-		sysfs_remove_one(&acxt, sd);
-
-	sysfs_addrm_finish(&acxt);
-
-	if (sd)
-		return 0;
-	else
-		return -ENOENT;
-}
-
 int sysfs_permission(struct inode *inode, int mask)
 {
 	struct sysfs_dirent *sd;
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 834ec2cdb7a3..8c24bce2f4ae 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -36,7 +36,7 @@ static const struct super_operations sysfs_ops = {
 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_flags	= SYSFS_DIR,
 	.s_mode		= S_IFDIR | S_IRUGO | S_IXUGO,
 	.s_ino		= 1,
 };
@@ -77,14 +77,8 @@ 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;
+	return sb_info->ns == info->ns;
 }
 
 static int sysfs_set_super(struct super_block *sb, void *data)
@@ -98,9 +92,7 @@ static int sysfs_set_super(struct super_block *sb, void *data)
 
 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]);
+	kobj_ns_drop(KOBJ_NS_TYPE_NET, info->ns);
 	kfree(info);
 }
 
@@ -108,7 +100,6 @@ 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;
 
@@ -116,18 +107,15 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 		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);
-		}
+		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
+			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);
+	info->ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
 
 	sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info);
 	if (IS_ERR(sb) || sb->s_fs_info != info)
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 2dd4507d9edd..1a23681b8179 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -28,18 +28,19 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
 	struct sysfs_dirent *target_sd = NULL;
 	struct sysfs_dirent *sd = NULL;
 	struct sysfs_addrm_cxt acxt;
-	enum kobj_ns_type ns_type;
 	int error;
 
 	BUG_ON(!name || !parent_sd);
 
-	/* target->sd can go away beneath us but is protected with
-	 * sysfs_assoc_lock.  Fetch target_sd from it.
+	/*
+	 * We don't own @target and it may be removed at any time.
+	 * Synchronize using sysfs_symlink_target_lock.  See
+	 * sysfs_remove_dir() for details.
 	 */
-	spin_lock(&sysfs_assoc_lock);
+	spin_lock(&sysfs_symlink_target_lock);
 	if (target->sd)
 		target_sd = sysfs_get(target->sd);
-	spin_unlock(&sysfs_assoc_lock);
+	spin_unlock(&sysfs_symlink_target_lock);
 
 	error = -ENOENT;
 	if (!target_sd)
@@ -50,29 +51,15 @@ static int sysfs_do_create_link_sd(struct sysfs_dirent *parent_sd,
 	if (!sd)
 		goto out_put;
 
-	ns_type = sysfs_ns_type(parent_sd);
-	if (ns_type)
-		sd->s_ns = target->ktype->namespace(target);
+	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, parent_sd);
-	/* 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);
-		else
-			error = __sysfs_add_one(&acxt, 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_start(&acxt);
+	if (warn)
+		error = sysfs_add_one(&acxt, sd, parent_sd);
+	else
+		error = __sysfs_add_one(&acxt, sd, parent_sd);
 	sysfs_addrm_finish(&acxt);
 
 	if (error)
@@ -155,11 +142,17 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
 			const char *name)
 {
 	const void *ns = NULL;
-	spin_lock(&sysfs_assoc_lock);
-	if (targ->sd && sysfs_ns_type(kobj->sd))
+
+	/*
+	 * We don't own @target 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 (targ->sd)
 		ns = targ->sd->s_ns;
-	spin_unlock(&sysfs_assoc_lock);
-	sysfs_hash_and_remove(kobj->sd, ns, name);
+	spin_unlock(&sysfs_symlink_target_lock);
+	sysfs_hash_and_remove(kobj->sd, name, ns);
 }
 
 /**
@@ -176,24 +169,25 @@ void sysfs_remove_link(struct kobject *kobj, const char *name)
 	else
 		parent_sd = kobj->sd;
 
-	sysfs_hash_and_remove(parent_sd, NULL, name);
+	sysfs_hash_and_remove(parent_sd, name, NULL);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_link);
 
 /**
- *	sysfs_rename_link - rename symlink in object's directory.
+ *	sysfs_rename_link_ns - rename symlink in object's directory.
  *	@kobj:	object we're acting for.
  *	@targ:	object we're pointing to.
  *	@old:	previous name of the symlink.
  *	@new:	new name of the symlink.
+ *	@new_ns: new namespace of the symlink.
  *
  *	A helper function for the common rename symlink idiom.
  */
-int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
-			const char *old, const char *new)
+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;
-	const void *old_ns = NULL, *new_ns = NULL;
+	const void *old_ns = NULL;
 	int result;
 
 	if (!kobj)
@@ -205,7 +199,7 @@ int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
 		old_ns = targ->sd->s_ns;
 
 	result = -ENOENT;
-	sd = sysfs_get_dirent(parent_sd, old_ns, old);
+	sd = sysfs_get_dirent_ns(parent_sd, old, old_ns);
 	if (!sd)
 		goto out;
 
@@ -215,16 +209,13 @@ int sysfs_rename_link(struct kobject *kobj, struct kobject *targ,
 	if (sd->s_symlink.target_sd->s_dir.kobj != targ)
 		goto out;
 
-	if (sysfs_ns_type(parent_sd))
-		new_ns = targ->ktype->namespace(targ);
-
-	result = sysfs_rename(sd, parent_sd, new_ns, new);
+	result = sysfs_rename(sd, parent_sd, new, new_ns);
 
 out:
 	sysfs_put(sd);
 	return result;
 }
-EXPORT_SYMBOL_GPL(sysfs_rename_link);
+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)
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index b6deca3e301d..e3aea92ebfa3 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -29,15 +29,13 @@ struct sysfs_elem_symlink {
 };
 
 struct sysfs_elem_attr {
-	struct attribute	*attr;
+	union {
+		struct attribute	*attr;
+		struct bin_attribute	*bin_attr;
+	};
 	struct sysfs_open_dirent *open;
 };
 
-struct sysfs_elem_bin_attr {
-	struct bin_attribute	*bin_attr;
-	struct hlist_head	buffers;
-};
-
 struct sysfs_inode_attrs {
 	struct iattr	ia_iattr;
 	void		*ia_secdata;
@@ -74,7 +72,6 @@ struct sysfs_dirent {
 		struct sysfs_elem_dir		s_dir;
 		struct sysfs_elem_symlink	s_symlink;
 		struct sysfs_elem_attr		s_attr;
-		struct sysfs_elem_bin_attr	s_bin_attr;
 	};
 
 	unsigned short		s_flags;
@@ -93,11 +90,8 @@ struct sysfs_dirent {
 #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_MASK			~SYSFS_TYPE_MASK
+#define SYSFS_FLAG_HAS_NS		0x01000
 #define SYSFS_FLAG_REMOVED		0x02000
 
 static inline unsigned int sysfs_type(struct sysfs_dirent *sd)
@@ -105,16 +99,8 @@ 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;		\
@@ -124,15 +110,31 @@ do {								\
 								\
 	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	*parent_sd;
 	struct sysfs_dirent	*removed;
 };
 
@@ -141,12 +143,13 @@ struct sysfs_addrm_cxt {
  */
 
 /*
- * Each sb is associated with a set of namespace tags (i.e.
- * the network namespace of the task which mounted this sysfs
- * instance).
+ * Each sb is associated with one namespace tag, currently the network
+ * namespace of the task which mounted this sysfs instance.  If multiple
+ * tags become necessary, make the following an array and compare
+ * sysfs_dirent tag against every entry.
  */
 struct sysfs_super_info {
-	void *ns[KOBJ_NS_TYPES];
+	void *ns;
 };
 #define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info))
 extern struct sysfs_dirent sysfs_root;
@@ -156,38 +159,37 @@ extern struct kmem_cache *sysfs_dir_cachep;
  * dir.c
  */
 extern struct mutex sysfs_mutex;
-extern spinlock_t sysfs_assoc_lock;
+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 dentry *sysfs_get_dentry(struct sysfs_dirent *sd);
 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,
-		       struct sysfs_dirent *parent_sd);
-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);
-void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, 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 void *ns,
-				       const unsigned char *name);
-struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
-				      const void *ns,
-				      const unsigned char *name);
+				       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);
-void sysfs_remove_subdir(struct sysfs_dirent *sd);
 
 int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
-		 const void *ns, const char *new_name);
+		 const char *new_name, const void *new_ns);
 
 static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd)
 {
@@ -218,25 +220,21 @@ 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_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
-			  const char *name);
 int sysfs_inode_init(void);
 
 /*
  * 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(struct sysfs_dirent *dir_sd,
-			const struct attribute *attr, int type, umode_t amode);
-/*
- * bin.c
- */
-extern const struct file_operations bin_fops;
-void unmap_bin_file(struct sysfs_dirent *attr_sd);
+int sysfs_add_file_mode_ns(struct sysfs_dirent *dir_sd,
+			   const struct attribute *attr, int type,
+			   umode_t amode, const void *ns);
+void sysfs_unmap_bin_file(struct sysfs_dirent *sd);
 
 /*
  * symlink.c