Merge git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/sysctl

Pull sysctl updates from Eric Biederman:

- Rewrite of sysctl for speed and clarity.

Insert/remove/Lookup in sysctl are all now O(NlogN) operations, and
are no longer bottlenecks in the process of adding and removing
network devices.

sysctl is now focused on being a filesystem instead of system call
and the code can all be found in fs/proc/proc_sysctl.c. Hopefully
this means the code is now approachable.

Much thanks is owed to Lucian Grinjincu for keeping at this until
something was found that was usable.

- The recent proc_sys_poll oops found by the fuzzer during hibernation
is fixed.

* git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/sysctl: (36 commits)
sysctl: protect poll() in entries that may go away
sysctl: Don't call sysctl_follow_link unless we are a link.
sysctl: Comments to make the code clearer.
sysctl: Correct error return from get_subdir
sysctl: An easier to read version of find_subdir
sysctl: fix memset parameters in setup_sysctl_set()
sysctl: remove an unused variable
sysctl: Add register_sysctl for normal sysctl users
sysctl: Index sysctl directories with rbtrees.
sysctl: Make the header lists per directory.
sysctl: Move sysctl_check_dups into insert_header
sysctl: Modify __register_sysctl_paths to take a set instead of a root and an nsproxy
sysctl: Replace root_list with links between sysctl_table_sets.
sysctl: Add sysctl_print_dir and use it in get_subdir
sysctl: Stop requiring explicit management of sysctl directories
sysctl: Add a root pointer to ctl_table_set
sysctl: Rewrite proc_sys_readdir in terms of first_entry and next_entry
sysctl: Rewrite proc_sys_lookup introducing find_entry and lookup_entry.
sysctl: Normalize the root_table data structure.
sysctl: Factor out insert_header and erase_header
...

fs/proc/internal.h

···
  */
 
 #include <linux/proc_fs.h>
+struct  ctl_table_header;
 
 extern struct proc_dir_entry proc_root;
 #ifdef CONFIG_PROC_SYSCTL
 extern int proc_sys_init(void);
+extern void sysctl_head_put(struct ctl_table_header *head);
 #else
 static inline void proc_sys_init(void) { }
+static inline void sysctl_head_put(struct ctl_table_header *head) { }
 #endif
 #ifdef CONFIG_NET
 extern int proc_net_init(void);

fs/proc/proc_sysctl.c

···
 #include <linux/sched.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/module.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
···
 
 	atomic_inc(&poll->event);
 	wake_up_interruptible(&poll->wait);
+}
+
+static struct ctl_table root_table[] = {
+	{
+		.procname = "",
+		.mode = S_IFDIR|S_IRUGO|S_IXUGO,
+	},
+	{ }
+};
+static struct ctl_table_root sysctl_table_root = {
+	.default_set.dir.header = {
+		{{.count = 1,
+		  .nreg = 1,
+		  .ctl_table = root_table }},
+		.ctl_table_arg = root_table,
+		.root = &sysctl_table_root,
+		.set = &sysctl_table_root.default_set,
+	},
+};
+
+static DEFINE_SPINLOCK(sysctl_lock);
+
+static void drop_sysctl_table(struct ctl_table_header *header);
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces);
+static int insert_links(struct ctl_table_header *head);
+static void put_links(struct ctl_table_header *header);
+
+static void sysctl_print_dir(struct ctl_dir *dir)
+{
+	if (dir->header.parent)
+		sysctl_print_dir(dir->header.parent);
+	printk(KERN_CONT "%s/", dir->header.ctl_table[0].procname);
+}
+
+static int namecmp(const char *name1, int len1, const char *name2, int len2)
+{
+	int minlen;
+	int cmp;
+
+	minlen = len1;
+	if (minlen > len2)
+		minlen = len2;
+
+	cmp = memcmp(name1, name2, minlen);
+	if (cmp == 0)
+		cmp = len1 - len2;
+	return cmp;
+}
+
+/* Called under sysctl_lock */
+static struct ctl_table *find_entry(struct ctl_table_header **phead,
+	struct ctl_dir *dir, const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+	struct rb_node *node = dir->root.rb_node;
+
+	while (node)
+	{
+		struct ctl_node *ctl_node;
+		const char *procname;
+		int cmp;
+
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+		procname = entry->procname;
+
+		cmp = namecmp(name, namelen, procname, strlen(procname));
+		if (cmp < 0)
+			node = node->rb_left;
+		else if (cmp > 0)
+			node = node->rb_right;
+		else {
+			*phead = head;
+			return entry;
+		}
+	}
+	return NULL;
+}
+
+static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+	struct rb_node **p = &head->parent->root.rb_node;
+	struct rb_node *parent = NULL;
+	const char *name = entry->procname;
+	int namelen = strlen(name);
+
+	while (*p) {
+		struct ctl_table_header *parent_head;
+		struct ctl_table *parent_entry;
+		struct ctl_node *parent_node;
+		const char *parent_name;
+		int cmp;
+
+		parent = *p;
+		parent_node = rb_entry(parent, struct ctl_node, node);
+		parent_head = parent_node->header;
+		parent_entry = &parent_head->ctl_table[parent_node - parent_head->node];
+		parent_name = parent_entry->procname;
+
+		cmp = namecmp(name, namelen, parent_name, strlen(parent_name));
+		if (cmp < 0)
+			p = &(*p)->rb_left;
+		else if (cmp > 0)
+			p = &(*p)->rb_right;
+		else {
+			printk(KERN_ERR "sysctl duplicate entry: ");
+			sysctl_print_dir(head->parent);
+			printk(KERN_CONT "/%s\n", entry->procname);
+			return -EEXIST;
+		}
+	}
+
+	rb_link_node(node, parent, p);
+	return 0;
+}
+
+static void erase_entry(struct ctl_table_header *head, struct ctl_table *entry)
+{
+	struct rb_node *node = &head->node[entry - head->ctl_table].node;
+
+	rb_erase(node, &head->parent->root);
+}
+
+static void init_header(struct ctl_table_header *head,
+	struct ctl_table_root *root, struct ctl_table_set *set,
+	struct ctl_node *node, struct ctl_table *table)
+{
+	head->ctl_table = table;
+	head->ctl_table_arg = table;
+	head->used = 0;
+	head->count = 1;
+	head->nreg = 1;
+	head->unregistering = NULL;
+	head->root = root;
+	head->set = set;
+	head->parent = NULL;
+	head->node = node;
+	if (node) {
+		struct ctl_table *entry;
+		for (entry = table; entry->procname; entry++, node++) {
+			rb_init_node(&node->node);
+			node->header = head;
+		}
+	}
+}
+
+static void erase_header(struct ctl_table_header *head)
+{
+	struct ctl_table *entry;
+	for (entry = head->ctl_table; entry->procname; entry++)
+		erase_entry(head, entry);
+}
+
+static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
+{
+	struct ctl_table *entry;
+	int err;
+
+	dir->header.nreg++;
+	header->parent = dir;
+	err = insert_links(header);
+	if (err)
+		goto fail_links;
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		err = insert_entry(header, entry);
+		if (err)
+			goto fail;
+	}
+	return 0;
+fail:
+	erase_header(header);
+	put_links(header);
+fail_links:
+	header->parent = NULL;
+	drop_sysctl_table(&dir->header);
+	return err;
+}
+
+/* called under sysctl_lock */
+static int use_table(struct ctl_table_header *p)
+{
+	if (unlikely(p->unregistering))
+		return 0;
+	p->used++;
+	return 1;
+}
+
+/* called under sysctl_lock */
+static void unuse_table(struct ctl_table_header *p)
+{
+	if (!--p->used)
+		if (unlikely(p->unregistering))
+			complete(p->unregistering);
+}
+
+/* called under sysctl_lock, will reacquire if has to wait */
+static void start_unregistering(struct ctl_table_header *p)
+{
+	/*
+	 * if p->used is 0, nobody will ever touch that entry again;
+	 * we'll eliminate all paths to it before dropping sysctl_lock
+	 */
+	if (unlikely(p->used)) {
+		struct completion wait;
+		init_completion(&wait);
+		p->unregistering = &wait;
+		spin_unlock(&sysctl_lock);
+		wait_for_completion(&wait);
+		spin_lock(&sysctl_lock);
+	} else {
+		/* anything non-NULL; we'll never dereference it */
+		p->unregistering = ERR_PTR(-EINVAL);
+	}
+	/*
+	 * do not remove from the list until nobody holds it; walking the
+	 * list in do_sysctl() relies on that.
+	 */
+	erase_header(p);
+}
+
+static void sysctl_head_get(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	head->count++;
+	spin_unlock(&sysctl_lock);
+}
+
+void sysctl_head_put(struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	if (!--head->count)
+		kfree_rcu(head, rcu);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
+{
+	if (!head)
+		BUG();
+	spin_lock(&sysctl_lock);
+	if (!use_table(head))
+		head = ERR_PTR(-ENOENT);
+	spin_unlock(&sysctl_lock);
+	return head;
+}
+
+static void sysctl_head_finish(struct ctl_table_header *head)
+{
+	if (!head)
+		return;
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+	spin_unlock(&sysctl_lock);
+}
+
+static struct ctl_table_set *
+lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
+{
+	struct ctl_table_set *set = &root->default_set;
+	if (root->lookup)
+		set = root->lookup(root, namespaces);
+	return set;
+}
+
+static struct ctl_table *lookup_entry(struct ctl_table_header **phead,
+				      struct ctl_dir *dir,
+				      const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	spin_lock(&sysctl_lock);
+	entry = find_entry(&head, dir, name, namelen);
+	if (entry && use_table(head))
+		*phead = head;
+	else
+		entry = NULL;
+	spin_unlock(&sysctl_lock);
+	return entry;
+}
+
+static struct ctl_node *first_usable_entry(struct rb_node *node)
+{
+	struct ctl_node *ctl_node;
+
+	for (;node; node = rb_next(node)) {
+		ctl_node = rb_entry(node, struct ctl_node, node);
+		if (use_table(ctl_node->header))
+			return ctl_node;
+	}
+	return NULL;
+}
+
+static void first_entry(struct ctl_dir *dir,
+	struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = NULL;
+	struct ctl_table *entry = NULL;
+	struct ctl_node *ctl_node;
+
+	spin_lock(&sysctl_lock);
+	ctl_node = first_usable_entry(rb_first(&dir->root));
+	spin_unlock(&sysctl_lock);
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentry)
+{
+	struct ctl_table_header *head = *phead;
+	struct ctl_table *entry = *pentry;
+	struct ctl_node *ctl_node = &head->node[entry - head->ctl_table];
+
+	spin_lock(&sysctl_lock);
+	unuse_table(head);
+
+	ctl_node = first_usable_entry(rb_next(&ctl_node->node));
+	spin_unlock(&sysctl_lock);
+	head = NULL;
+	if (ctl_node) {
+		head = ctl_node->header;
+		entry = &head->ctl_table[ctl_node - head->node];
+	}
+	*phead = head;
+	*pentry = entry;
+}
+
+void register_sysctl_root(struct ctl_table_root *root)
+{
+}
+
+/*
+ * sysctl_perm does NOT grant the superuser all rights automatically, because
+ * some sysctl variables are readonly even to root.
+ */
+
+static int test_perm(int mode, int op)
+{
+	if (!current_euid())
+		mode >>= 6;
+	else if (in_egroup_p(0))
+		mode >>= 3;
+	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
+		return 0;
+	return -EACCES;
+}
+
+static int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
+{
+	int mode;
+
+	if (root->permissions)
+		mode = root->permissions(root, current->nsproxy, table);
+	else
+		mode = table->mode;
+
+	return test_perm(mode, op);
 }
 
 static struct inode *proc_sys_make_inode(struct super_block *sb,
···
 
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_mode = table->mode;
-	if (!table->child) {
+	if (!S_ISDIR(table->mode)) {
 		inode->i_mode |= S_IFREG;
 		inode->i_op = &proc_sys_inode_operations;
 		inode->i_fop = &proc_sys_file_operations;
 	} else {
 		inode->i_mode |= S_IFDIR;
-		clear_nlink(inode);
 		inode->i_op = &proc_sys_dir_operations;
 		inode->i_fop = &proc_sys_dir_file_operations;
 	}
···
 	return inode;
 }
 
-static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
-{
-	int len;
-	for ( ; p->procname; p++) {
-
-		if (!p->procname)
-			continue;
-
-		len = strlen(p->procname);
-		if (len != name->len)
-			continue;
-
-		if (memcmp(p->procname, name->name, len) != 0)
-			continue;
-
-		/* I have a match */
-		return p;
-	}
-	return NULL;
-}
-
 static struct ctl_table_header *grab_header(struct inode *inode)
 {
-	if (PROC_I(inode)->sysctl)
-		return sysctl_head_grab(PROC_I(inode)->sysctl);
-	else
-		return sysctl_head_next(NULL);
+	struct ctl_table_header *head = PROC_I(inode)->sysctl;
+	if (!head)
+		head = &sysctl_table_root.default_set.dir.header;
+	return sysctl_head_grab(head);
 }
 
 static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
 					struct nameidata *nd)
 {
 	struct ctl_table_header *head = grab_header(dir);
-	struct ctl_table *table = PROC_I(dir)->sysctl_entry;
 	struct ctl_table_header *h = NULL;
 	struct qstr *name = &dentry->d_name;
 	struct ctl_table *p;
 	struct inode *inode;
 	struct dentry *err = ERR_PTR(-ENOENT);
+	struct ctl_dir *ctl_dir;
+	int ret;
 
 	if (IS_ERR(head))
 		return ERR_CAST(head);
 
-	if (table && !table->child) {
-		WARN_ON(1);
-		goto out;
-	}
+	ctl_dir = container_of(head, struct ctl_dir, header);
 
-	table = table ? table->child : head->ctl_table;
-
-	p = find_in_table(table, name);
-	if (!p) {
-		for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
-			if (h->attached_to != table)
-				continue;
-			p = find_in_table(h->attached_by, name);
-			if (p)
-				break;
-		}
-	}
-
+	p = lookup_entry(&h, ctl_dir, name->name, name->len);
 	if (!p)
 		goto out;
+
+	if (S_ISLNK(p->mode)) {
+		ret = sysctl_follow_link(&h, &p, current->nsproxy);
+		err = ERR_PTR(ret);
+		if (ret)
+			goto out;
+	}
 
 	err = ERR_PTR(-ENOMEM);
 	inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
···
 
 static int proc_sys_open(struct inode *inode, struct file *filp)
 {
+	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return PTR_ERR(head);
 
 	if (table->poll)
 		filp->private_data = proc_sys_poll_event(table->poll);
+
+	sysctl_head_finish(head);
 
 	return 0;
 }
···
 static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
 {
 	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
-	unsigned long event = (unsigned long)filp->private_data;
 	unsigned int ret = DEFAULT_POLLMASK;
+	unsigned long event;
+
+	/* sysctl was unregistered */
+	if (IS_ERR(head))
+		return POLLERR | POLLHUP;
 
 	if (!table->proc_handler)
 		goto out;
···
 	if (!table->poll)
 		goto out;
 
+	event = (unsigned long)filp->private_data;
 	poll_wait(filp, &table->poll->wait, wait);
 
 	if (event != atomic_read(&table->poll->event)) {
···
 	}
 
 out:
+	sysctl_head_finish(head);
+
 	return ret;
 }
 
···
 	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
 }
 
+static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
+				    filldir_t filldir,
+				    struct ctl_table_header *head,
+				    struct ctl_table *table)
+{
+	int err, ret = 0;
+	head = sysctl_head_grab(head);
+
+	if (S_ISLNK(table->mode)) {
+		/* It is not an error if we can not follow the link ignore it */
+		err = sysctl_follow_link(&head, &table, current->nsproxy);
+		if (err)
+			goto out;
+	}
+
+	ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
+out:
+	sysctl_head_finish(head);
+	return ret;
+}
+
 static int scan(struct ctl_table_header *head, ctl_table *table,
 		unsigned long *pos, struct file *file,
 		void *dirent, filldir_t filldir)
 {
+	int res;
 
-	for (; table->procname; table++, (*pos)++) {
-		int res;
+	if ((*pos)++ < file->f_pos)
+		return 0;
 
-		/* Can't do anything without a proc name */
-		if (!table->procname)
-			continue;
-
-		if (*pos < file->f_pos)
-			continue;
-
+	if (unlikely(S_ISLNK(table->mode)))
+		res = proc_sys_link_fill_cache(file, dirent, filldir, head, table);
+	else
 		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
-		if (res)
-			return res;
 
-		file->f_pos = *pos + 1;
-	}
-	return 0;
+	if (res == 0)
+		file->f_pos = *pos;
+
+	return res;
 }
 
 static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
···
 	struct dentry *dentry = filp->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	struct ctl_table_header *head = grab_header(inode);
-	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 	struct ctl_table_header *h = NULL;
+	struct ctl_table *entry;
+	struct ctl_dir *ctl_dir;
 	unsigned long pos;
 	int ret = -EINVAL;
 
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
-	if (table && !table->child) {
-		WARN_ON(1);
-		goto out;
-	}
-
-	table = table ? table->child : head->ctl_table;
+	ctl_dir = container_of(head, struct ctl_dir, header);
 
 	ret = 0;
 	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
···
 	}
 	pos = 2;
 
-	ret = scan(head, table, &pos, filp, dirent, filldir);
-	if (ret)
-		goto out;
-
-	for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
-		if (h->attached_to != table)
-			continue;
-		ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
+		ret = scan(h, entry, &pos, filp, dirent, filldir);
 		if (ret) {
 			sysctl_head_finish(h);
 			break;
···
 	return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
 }
 
+static int sysctl_is_seen(struct ctl_table_header *p)
+{
+	struct ctl_table_set *set = p->set;
+	int res;
+	spin_lock(&sysctl_lock);
+	if (p->unregistering)
+		res = 0;
+	else if (!set->is_seen)
+		res = 1;
+	else
+		res = set->is_seen(set);
+	spin_unlock(&sysctl_lock);
+	return res;
+}
+
 static int proc_sys_compare(const struct dentry *parent,
 		const struct inode *pinode,
 		const struct dentry *dentry, const struct inode *inode,
···
 	.d_compare	= proc_sys_compare,
 };
 
+static struct ctl_dir *find_subdir(struct ctl_dir *dir,
+				   const char *name, int namelen)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry;
+
+	entry = find_entry(&head, dir, name, namelen);
+	if (!entry)
+		return ERR_PTR(-ENOENT);
+	if (!S_ISDIR(entry->mode))
+		return ERR_PTR(-ENOTDIR);
+	return container_of(head, struct ctl_dir, header);
+}
+
+static struct ctl_dir *new_dir(struct ctl_table_set *set,
+			       const char *name, int namelen)
+{
+	struct ctl_table *table;
+	struct ctl_dir *new;
+	struct ctl_node *node;
+	char *new_name;
+
+	new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
+		      sizeof(struct ctl_table)*2 +  namelen + 1,
+		      GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	node = (struct ctl_node *)(new + 1);
+	table = (struct ctl_table *)(node + 1);
+	new_name = (char *)(table + 2);
+	memcpy(new_name, name, namelen);
+	new_name[namelen] = '\0';
+	table[0].procname = new_name;
+	table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
+	init_header(&new->header, set->dir.header.root, set, node, table);
+
+	return new;
+}
+
+/**
+ * get_subdir - find or create a subdir with the specified name.
+ * @dir:  Directory to create the subdirectory in
+ * @name: The name of the subdirectory to find or create
+ * @namelen: The length of name
+ *
+ * Takes a directory with an elevated reference count so we know that
+ * if we drop the lock the directory will not go away.  Upon success
+ * the reference is moved from @dir to the returned subdirectory.
+ * Upon error an error code is returned and the reference on @dir is
+ * simply dropped.
+ */
+static struct ctl_dir *get_subdir(struct ctl_dir *dir,
+				  const char *name, int namelen)
+{
+	struct ctl_table_set *set = dir->header.set;
+	struct ctl_dir *subdir, *new = NULL;
+	int err;
+
+	spin_lock(&sysctl_lock);
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	spin_unlock(&sysctl_lock);
+	new = new_dir(set, name, namelen);
+	spin_lock(&sysctl_lock);
+	subdir = ERR_PTR(-ENOMEM);
+	if (!new)
+		goto failed;
+
+	/* Was the subdir added while we dropped the lock? */
+	subdir = find_subdir(dir, name, namelen);
+	if (!IS_ERR(subdir))
+		goto found;
+	if (PTR_ERR(subdir) != -ENOENT)
+		goto failed;
+
+	/* Nope.  Use the our freshly made directory entry. */
+	err = insert_header(dir, &new->header);
+	subdir = ERR_PTR(err);
+	if (err)
+		goto failed;
+	subdir = new;
+found:
+	subdir->header.nreg++;
+failed:
+	if (unlikely(IS_ERR(subdir))) {
+		printk(KERN_ERR "sysctl could not get directory: ");
+		sysctl_print_dir(dir);
+		printk(KERN_CONT "/%*.*s %ld\n",
+			namelen, namelen, name, PTR_ERR(subdir));
+	}
+	drop_sysctl_table(&dir->header);
+	if (new)
+		drop_sysctl_table(&new->header);
+	spin_unlock(&sysctl_lock);
+	return subdir;
+}
+
+static struct ctl_dir *xlate_dir(struct ctl_table_set *set, struct ctl_dir *dir)
+{
+	struct ctl_dir *parent;
+	const char *procname;
+	if (!dir->header.parent)
+		return &set->dir;
+	parent = xlate_dir(set, dir->header.parent);
+	if (IS_ERR(parent))
+		return parent;
+	procname = dir->header.ctl_table[0].procname;
+	return find_subdir(parent, procname, strlen(procname));
+}
+
+static int sysctl_follow_link(struct ctl_table_header **phead,
+	struct ctl_table **pentry, struct nsproxy *namespaces)
+{
+	struct ctl_table_header *head;
+	struct ctl_table_root *root;
+	struct ctl_table_set *set;
+	struct ctl_table *entry;
+	struct ctl_dir *dir;
+	int ret;
+
+	ret = 0;
+	spin_lock(&sysctl_lock);
+	root = (*pentry)->data;
+	set = lookup_header_set(root, namespaces);
+	dir = xlate_dir(set, (*phead)->parent);
+	if (IS_ERR(dir))
+		ret = PTR_ERR(dir);
+	else {
+		const char *procname = (*pentry)->procname;
+		head = NULL;
+		entry = find_entry(&head, dir, procname, strlen(procname));
+		ret = -ENOENT;
+		if (entry && use_table(head)) {
+			unuse_table(*phead);
+			*phead = head;
+			*pentry = entry;
+			ret = 0;
+		}
+	}
+
+	spin_unlock(&sysctl_lock);
+	return ret;
+}
+
+static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	printk(KERN_ERR "sysctl table check failed: %s/%s %pV\n",
+		path, table->procname, &vaf);
+
+	va_end(args);
+	return -EINVAL;
+}
+
+static int sysctl_check_table(const char *path, struct ctl_table *table)
+{
+	int err = 0;
+	for (; table->procname; table++) {
+		if (table->child)
+			err = sysctl_err(path, table, "Not a file");
+
+		if ((table->proc_handler == proc_dostring) ||
+		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_dointvec_minmax) ||
+		    (table->proc_handler == proc_dointvec_jiffies) ||
+		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
+		    (table->proc_handler == proc_dointvec_ms_jiffies) ||
+		    (table->proc_handler == proc_doulongvec_minmax) ||
+		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
+			if (!table->data)
+				err = sysctl_err(path, table, "No data");
+			if (!table->maxlen)
+				err = sysctl_err(path, table, "No maxlen");
+		}
+		if (!table->proc_handler)
+			err = sysctl_err(path, table, "No proc_handler");
+
+		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
+			err = sysctl_err(path, table, "bogus .mode 0%o",
+				table->mode);
+	}
+	return err;
+}
+
+static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table *table,
+	struct ctl_table_root *link_root)
+{
+	struct ctl_table *link_table, *entry, *link;
+	struct ctl_table_header *links;
+	struct ctl_node *node;
+	char *link_name;
+	int nr_entries, name_bytes;
+
+	name_bytes = 0;
+	nr_entries = 0;
+	for (entry = table; entry->procname; entry++) {
+		nr_entries++;
+		name_bytes += strlen(entry->procname) + 1;
+	}
+
+	links = kzalloc(sizeof(struct ctl_table_header) +
+			sizeof(struct ctl_node)*nr_entries +
+			sizeof(struct ctl_table)*(nr_entries + 1) +
+			name_bytes,
+			GFP_KERNEL);
+
+	if (!links)
+		return NULL;
+
+	node = (struct ctl_node *)(links + 1);
+	link_table = (struct ctl_table *)(node + nr_entries);
+	link_name = (char *)&link_table[nr_entries + 1];
+
+	for (link = link_table, entry = table; entry->procname; link++, entry++) {
+		int len = strlen(entry->procname) + 1;
+		memcpy(link_name, entry->procname, len);
+		link->procname = link_name;
+		link->mode = S_IFLNK|S_IRWXUGO;
+		link->data = link_root;
+		link_name += len;
+	}
+	init_header(links, dir->header.root, dir->header.set, node, link_table);
+	links->nreg = nr_entries;
+
+	return links;
+}
+
+static bool get_links(struct ctl_dir *dir,
+	struct ctl_table *table, struct ctl_table_root *link_root)
+{
+	struct ctl_table_header *head;
+	struct ctl_table *entry, *link;
+
+	/* Are there links available for every entry in table? */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		if (!link)
+			return false;
+		if (S_ISDIR(link->mode) && S_ISDIR(entry->mode))
+			continue;
+		if (S_ISLNK(link->mode) && (link->data == link_root))
+			continue;
+		return false;
+	}
+
+	/* The checks passed.  Increase the registration count on the links */
+	for (entry = table; entry->procname; entry++) {
+		const char *procname = entry->procname;
+		link = find_entry(&head, dir, procname, strlen(procname));
+		head->nreg++;
+	}
+	return true;
+}
+
+static int insert_links(struct ctl_table_header *head)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_dir *core_parent = NULL;
+	struct ctl_table_header *links;
+	int err;
+
+	if (head->set == root_set)
+		return 0;
+
+	core_parent = xlate_dir(root_set, head->parent);
+	if (IS_ERR(core_parent))
+		return 0;
+
+	if (get_links(core_parent, head->ctl_table, head->root))
+		return 0;
+
+	core_parent->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	links = new_links(core_parent, head->ctl_table, head->root);
+
+	spin_lock(&sysctl_lock);
+	err = -ENOMEM;
+	if (!links)
+		goto out;
+
+	err = 0;
+	if (get_links(core_parent, head->ctl_table, head->root)) {
+		kfree(links);
+		goto out;
+	}
+
+	err = insert_header(core_parent, links);
+	if (err)
+		kfree(links);
+out:
+	drop_sysctl_table(&core_parent->header);
+	return err;
+}
+
+/**
+ * __register_sysctl_table - register a leaf sysctl table
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * The members of the &struct ctl_table structure are used as follows:
+ *
+ * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
+ *            enter a sysctl file
+ *
+ * data - a pointer to data for use by proc_handler
+ *
+ * maxlen - the maximum size in bytes of the data
+ *
+ * mode - the file permissions for the /proc/sys file
+ *
+ * child - must be %NULL.
+ *
+ * proc_handler - the text handler routine (described below)
+ *
+ * extra1, extra2 - extra pointers usable by the proc handler routines
+ *
+ * Leaf nodes in the sysctl tree will be represented by a single file
+ * under /proc; non-leaf nodes will be represented by directories.
+ *
+ * There must be a proc_handler routine for any terminal nodes.
+ * Several default handlers are available to cover common cases -
+ *
+ * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
+ * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(),
+ * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
+ *
+ * It is the handler's job to read the input buffer from user memory
+ * and process it. The handler should return 0 on success.
+ *
+ * This routine returns %NULL on a failure to register, and a pointer
+ * to the table header on success.
+ */
+struct ctl_table_header *__register_sysctl_table(
+	struct ctl_table_set *set,
+	const char *path, struct ctl_table *table)
+{
+	struct ctl_table_root *root = set->dir.header.root;
+	struct ctl_table_header *header;
+	const char *name, *nextname;
+	struct ctl_dir *dir;
+	struct ctl_table *entry;
+	struct ctl_node *node;
+	int nr_entries = 0;
+
+	for (entry = table; entry->procname; entry++)
+		nr_entries++;
+
+	header = kzalloc(sizeof(struct ctl_table_header) +
+			 sizeof(struct ctl_node)*nr_entries, GFP_KERNEL);
+	if (!header)
+		return NULL;
+
+	node = (struct ctl_node *)(header + 1);
+	init_header(header, root, set, node, table);
+	if (sysctl_check_table(path, table))
+		goto fail;
+
+	spin_lock(&sysctl_lock);
+	dir = &set->dir;
+	/* Reference moved down the diretory tree get_subdir */
+	dir->header.nreg++;
+	spin_unlock(&sysctl_lock);
+
+	/* Find the directory for the ctl_table */
+	for (name = path; name; name = nextname) {
+		int namelen;
+		nextname = strchr(name, '/');
+		if (nextname) {
+			namelen = nextname - name;
+			nextname++;
+		} else {
+			namelen = strlen(name);
+		}
+		if (namelen == 0)
+			continue;
+
+		dir = get_subdir(dir, name, namelen);
+		if (IS_ERR(dir))
+			goto fail;
+	}
+
+	spin_lock(&sysctl_lock);
+	if (insert_header(dir, header))
+		goto fail_put_dir_locked;
+
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+
+	return header;
+
+fail_put_dir_locked:
+	drop_sysctl_table(&dir->header);
+	spin_unlock(&sysctl_lock);
+fail:
+	kfree(header);
+	dump_stack();
+	return NULL;
+}
+
+/**
+ * register_sysctl - register a sysctl table
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the table structure
+ *
+ * Register a sysctl table. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table)
+{
+	return __register_sysctl_table(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl);
+
+static char *append_path(const char *path, char *pos, const char *name)
+{
+	int namelen;
+	namelen = strlen(name);
+	if (((pos - path) + namelen + 2) >= PATH_MAX)
+		return NULL;
+	memcpy(pos, name, namelen);
+	pos[namelen] = '/';
+	pos[namelen + 1] = '\0';
+	pos += namelen + 1;
+	return pos;
+}
+
+static int count_subheaders(struct ctl_table *table)
+{
+	int has_files = 0;
+	int nr_subheaders = 0;
+	struct ctl_table *entry;
+
+	/* special case: no directory and empty directory */
+	if (!table || !table->procname)
+		return 1;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_subheaders += count_subheaders(entry->child);
+		else
+			has_files = 1;
+	}
+	return nr_subheaders + has_files;
+}
+
+static int register_leaf_sysctl_tables(const char *path, char *pos,
+	struct ctl_table_header ***subheader, struct ctl_table_set *set,
+	struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = NULL;
+	struct ctl_table *entry, *files;
+	int nr_files = 0;
+	int nr_dirs = 0;
+	int err = -ENOMEM;
+
+	for (entry = table; entry->procname; entry++) {
+		if (entry->child)
+			nr_dirs++;
+		else
+			nr_files++;
+	}
+
+	files = table;
+	/* If there are mixed files and directories we need a new table */
+	if (nr_dirs && nr_files) {
+		struct ctl_table *new;
+		files = kzalloc(sizeof(struct ctl_table) * (nr_files + 1),
+				GFP_KERNEL);
+		if (!files)
+			goto out;
+
+		ctl_table_arg = files;
+		for (new = files, entry = table; entry->procname; entry++) {
+			if (entry->child)
+				continue;
+			*new = *entry;
+			new++;
+		}
+	}
+
+	/* Register everything except a directory full of subdirectories */
+	if (nr_files || !nr_dirs) {
+		struct ctl_table_header *header;
+		header = __register_sysctl_table(set, path, files);
+		if (!header) {
+			kfree(ctl_table_arg);
+			goto out;
+		}
+
+		/* Remember if we need to free the file table */
+		header->ctl_table_arg = ctl_table_arg;
+		**subheader = header;
+		(*subheader)++;
+	}
+
+	/* Recurse into the subdirectories. */
+	for (entry = table; entry->procname; entry++) {
+		char *child_pos;
+
+		if (!entry->child)
+			continue;
+
+		err = -ENAMETOOLONG;
+		child_pos = append_path(path, pos, entry->procname);
+		if (!child_pos)
+			goto out;
+
+		err = register_leaf_sysctl_tables(path, child_pos, subheader,
+						  set, entry->child);
+		pos[0] = '\0';
+		if (err)
+			goto out;
+	}
+	err = 0;
+out:
+	/* On failure our caller will unregister all registered subheaders */
+	return err;
+}
+
+/**
+ * __register_sysctl_paths - register a sysctl table hierarchy
+ * @set: Sysctl tree to register on
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_table for more details.
+ */
+struct ctl_table_header *__register_sysctl_paths(
+	struct ctl_table_set *set,
+	const struct ctl_path *path, struct ctl_table *table)
+{
+	struct ctl_table *ctl_table_arg = table;
+	int nr_subheaders = count_subheaders(table);
+	struct ctl_table_header *header = NULL, **subheaders, **subheader;
+	const struct ctl_path *component;
+	char *new_path, *pos;
+
+	pos = new_path = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!new_path)
+		return NULL;
+
+	pos[0] = '\0';
+	for (component = path; component->procname; component++) {
+		pos = append_path(new_path, pos, component->procname);
+		if (!pos)
+			goto out;
+	}
+	while (table->procname && table->child && !table[1].procname) {
+		pos = append_path(new_path, pos, table->procname);
+		if (!pos)
+			goto out;
+		table = table->child;
+	}
+	if (nr_subheaders == 1) {
+		header = __register_sysctl_table(set, new_path, table);
+		if (header)
+			header->ctl_table_arg = ctl_table_arg;
+	} else {
+		header = kzalloc(sizeof(*header) +
+				 sizeof(*subheaders)*nr_subheaders, GFP_KERNEL);
+		if (!header)
+			goto out;
+
+		subheaders = (struct ctl_table_header **) (header + 1);
+		subheader = subheaders;
+		header->ctl_table_arg = ctl_table_arg;
+
+		if (register_leaf_sysctl_tables(new_path, pos, &subheader,
+						set, table))
+			goto err_register_leaves;
+	}
+
+out:
+	kfree(new_path);
+	return header;
+
+err_register_leaves:
+	while (subheader > subheaders) {
+		struct ctl_table_header *subh = *(--subheader);
+		struct ctl_table *table = subh->ctl_table_arg;
+		unregister_sysctl_table(subh);
+		kfree(table);
+	}
+	kfree(header);
+	header = NULL;
+	goto out;
+}
+
+/**
+ * register_sysctl_table_path - register a sysctl table hierarchy
+ * @path: The path to the directory the sysctl table is in.
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See __register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
+						struct ctl_table *table)
+{
+	return __register_sysctl_paths(&sysctl_table_root.default_set,
+					path, table);
+}
+EXPORT_SYMBOL(register_sysctl_paths);
+
+/**
+ * register_sysctl_table - register a sysctl table hierarchy
+ * @table: the top-level table structure
+ *
+ * Register a sysctl table hierarchy. @table should be a filled in ctl_table
+ * array. A completely 0 filled entry terminates the table.
+ *
+ * See register_sysctl_paths for more details.
+ */
+struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
+{
+	static const struct ctl_path null_path[] = { {} };
+
+	return register_sysctl_paths(null_path, table);
+}
+EXPORT_SYMBOL(register_sysctl_table);
+
+static void put_links(struct ctl_table_header *header)
+{
+	struct ctl_table_set *root_set = &sysctl_table_root.default_set;
+	struct ctl_table_root *root = header->root;
+	struct ctl_dir *parent = header->parent;
+	struct ctl_dir *core_parent;
+	struct ctl_table *entry;
+
+	if (header->set == root_set)
+		return;
+
+	core_parent = xlate_dir(root_set, parent);
+	if (IS_ERR(core_parent))
+		return;
+
+	for (entry = header->ctl_table; entry->procname; entry++) {
+		struct ctl_table_header *link_head;
+		struct ctl_table *link;
+		const char *name = entry->procname;
+
+		link = find_entry(&link_head, core_parent, name, strlen(name));
+		if (link &&
+		    ((S_ISDIR(link->mode) && S_ISDIR(entry->mode)) ||
+		     (S_ISLNK(link->mode) && (link->data == root)))) {
+			drop_sysctl_table(link_head);
+		}
+		else {
+			printk(KERN_ERR "sysctl link missing during unregister: ");
+			sysctl_print_dir(parent);
+			printk(KERN_CONT "/%s\n", name);
+		}
+	}
+}
+
+static void drop_sysctl_table(struct ctl_table_header *header)
+{
+	struct ctl_dir *parent = header->parent;
+
+	if (--header->nreg)
+		return;
+
+	put_links(header);
+	start_unregistering(header);
+	if (!--header->count)
+		kfree_rcu(header, rcu);
+
+	if (parent)
+		drop_sysctl_table(&parent->header);
+}
+
+/**
+ * unregister_sysctl_table - unregister a sysctl table hierarchy
+ * @header: the header returned from register_sysctl_table
+ *
+ * Unregisters the sysctl table and all children. proc entries may not
+ * actually be removed until they are no longer used by anyone.
+ */
+void unregister_sysctl_table(struct ctl_table_header * header)
+{
+	int nr_subheaders;
+	might_sleep();
+
+	if (header == NULL)
+		return;
+
+	nr_subheaders = count_subheaders(header->ctl_table_arg);
+	if (unlikely(nr_subheaders > 1)) {
+		struct ctl_table_header **subheaders;
+		int i;
+
+		subheaders = (struct ctl_table_header **)(header + 1);
+		for (i = nr_subheaders -1; i >= 0; i--) {
+			struct ctl_table_header *subh = subheaders[i];
+			struct ctl_table *table = subh->ctl_table_arg;
+			unregister_sysctl_table(subh);
+			kfree(table);
+		}
+		kfree(header);
+		return;
+	}
+
+	spin_lock(&sysctl_lock);
+	drop_sysctl_table(header);
+	spin_unlock(&sysctl_lock);
+}
+EXPORT_SYMBOL(unregister_sysctl_table);
+
+void setup_sysctl_set(struct ctl_table_set *set,
+	struct ctl_table_root *root,
+	int (*is_seen)(struct ctl_table_set *))
+{
+	memset(set, 0, sizeof(*set));
+	set->is_seen = is_seen;
+	init_header(&set->dir.header, root, set, NULL, root_table);
+}
+
+void retire_sysctl_set(struct ctl_table_set *set)
+{
+	WARN_ON(!RB_EMPTY_ROOT(&set->dir.root));
+}
+
 int __init proc_sys_init(void)
 {
 	struct proc_dir_entry *proc_sys_root;
···
 	proc_sys_root->proc_iops = &proc_sys_dir_operations;
 	proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
 	proc_sys_root->nlink = 0;
-	return 0;
+
+	return sysctl_init();
 }

include/linux/sysctl.h

···
 #include <linux/list.h>
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
+#include <linux/rbtree.h>
 
 /* For the /proc/sys support */
 struct ctl_table;
 struct nsproxy;
 struct ctl_table_root;
-
-struct ctl_table_set {
-	struct list_head list;
-	struct ctl_table_set *parent;
-	int (*is_seen)(struct ctl_table_set *);
-};
-
-extern void setup_sysctl_set(struct ctl_table_set *p,
-	struct ctl_table_set *parent,
-	int (*is_seen)(struct ctl_table_set *));
-
 struct ctl_table_header;
-
-extern void sysctl_head_get(struct ctl_table_header *);
-extern void sysctl_head_put(struct ctl_table_header *);
-extern int sysctl_is_seen(struct ctl_table_header *);
-extern struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *);
-extern struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev);
-extern struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
-						struct ctl_table_header *prev);
-extern void sysctl_head_finish(struct ctl_table_header *prev);
-extern int sysctl_perm(struct ctl_table_root *root,
-		struct ctl_table *table, int op);
+struct ctl_dir;
 
 typedef struct ctl_table ctl_table;
 
···
 	return (void *)(unsigned long)atomic_read(&poll->event);
 }
 
-void proc_sys_poll_notify(struct ctl_table_poll *poll);
-
 #define __CTL_TABLE_POLL_INITIALIZER(name) {				\
 	.event = ATOMIC_INIT(0),					\
 	.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait) }
···
 	void *data;
 	int maxlen;
 	umode_t mode;
-	struct ctl_table *child;
-	struct ctl_table *parent;	/* Automatically set */
+	struct ctl_table *child;	/* Deprecated */
 	proc_handler *proc_handler;	/* Callback for text formatting */
 	struct ctl_table_poll *poll;
 	void *extra1;
 	void *extra2;
 };
 
-struct ctl_table_root {
-	struct list_head root_list;
-	struct ctl_table_set default_set;
-	struct ctl_table_set *(*lookup)(struct ctl_table_root *root,
-					   struct nsproxy *namespaces);
-	int (*permissions)(struct ctl_table_root *root,
-			struct nsproxy *namespaces, struct ctl_table *table);
+struct ctl_node {
+	struct rb_node node;
+	struct ctl_table_header *header;
 };
 
 /* struct ctl_table_header is used to maintain dynamic lists of
···
 	union {
 		struct {
 			struct ctl_table *ctl_table;
-			struct list_head ctl_entry;
 			int used;
 			int count;
+			int nreg;
 		};
 		struct rcu_head rcu;
 	};
···
 	struct ctl_table *ctl_table_arg;
 	struct ctl_table_root *root;
 	struct ctl_table_set *set;
-	struct ctl_table *attached_by;
-	struct ctl_table *attached_to;
-	struct ctl_table_header *parent;
+	struct ctl_dir *parent;
+	struct ctl_node *node;
+};
+
+struct ctl_dir {
+	/* Header must be at the start of ctl_dir */
+	struct ctl_table_header header;
+	struct rb_root root;
+};
+
+struct ctl_table_set {
+	int (*is_seen)(struct ctl_table_set *);
+	struct ctl_dir dir;
+};
+
+struct ctl_table_root {
+	struct ctl_table_set default_set;
+	struct ctl_table_set *(*lookup)(struct ctl_table_root *root,
+					   struct nsproxy *namespaces);
+	int (*permissions)(struct ctl_table_root *root,
+			struct nsproxy *namespaces, struct ctl_table *table);
 };
 
 /* struct ctl_path describes where in the hierarchy a table is added */
···
 	const char *procname;
 };
 
+#ifdef CONFIG_SYSCTL
+
+void proc_sys_poll_notify(struct ctl_table_poll *poll);
+
+extern void setup_sysctl_set(struct ctl_table_set *p,
+	struct ctl_table_root *root,
+	int (*is_seen)(struct ctl_table_set *));
+extern void retire_sysctl_set(struct ctl_table_set *set);
+
 void register_sysctl_root(struct ctl_table_root *root);
+struct ctl_table_header *__register_sysctl_table(
+	struct ctl_table_set *set,
+	const char *path, struct ctl_table *table);
 struct ctl_table_header *__register_sysctl_paths(
-	struct ctl_table_root *root, struct nsproxy *namespaces,
+	struct ctl_table_set *set,
 	const struct ctl_path *path, struct ctl_table *table);
+struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *table);
 struct ctl_table_header *register_sysctl_table(struct ctl_table * table);
 struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
 						struct ctl_table *table);
 
 void unregister_sysctl_table(struct ctl_table_header * table);
-int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table);
+
+extern int sysctl_init(void);
+#else /* CONFIG_SYSCTL */
+static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
+{
+	return NULL;
+}
+
+static inline struct ctl_table_header *register_sysctl_paths(
+			const struct ctl_path *path, struct ctl_table *table)
+{
+	return NULL;
+}
+
+static inline void unregister_sysctl_table(struct ctl_table_header * table)
+{
+}
+
+static inline void setup_sysctl_set(struct ctl_table_set *p,
+	struct ctl_table_root *root,
+	int (*is_seen)(struct ctl_table_set *))
+{
+}
+
+#endif /* CONFIG_SYSCTL */
 
 #endif /* __KERNEL__ */
 

kernel/Makefile

···
 
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
-obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o

kernel/sysctl.c

···
 
 #endif
 
-static struct ctl_table root_table[];
-static struct ctl_table_root sysctl_table_root;
-static struct ctl_table_header root_table_header = {
-	{{.count = 1,
-	.ctl_table = root_table,
-	.ctl_entry = LIST_HEAD_INIT(sysctl_table_root.default_set.list),}},
-	.root = &sysctl_table_root,
-	.set = &sysctl_table_root.default_set,
-};
-static struct ctl_table_root sysctl_table_root = {
-	.root_list = LIST_HEAD_INIT(sysctl_table_root.root_list),
-	.default_set.list = LIST_HEAD_INIT(root_table_header.ctl_entry),
-};
-
 static struct ctl_table kern_table[];
 static struct ctl_table vm_table[];
 static struct ctl_table fs_table[];
···
 
 /* The default sysctl tables: */
 
-static struct ctl_table root_table[] = {
+static struct ctl_table sysctl_base_table[] = {
 	{
 		.procname	= "kernel",
 		.mode		= 0555,
···
 	{ }
 };
 
-static DEFINE_SPINLOCK(sysctl_lock);
-
-/* called under sysctl_lock */
-static int use_table(struct ctl_table_header *p)
+int __init sysctl_init(void)
 {
-	if (unlikely(p->unregistering))
-		return 0;
-	p->used++;
-	return 1;
-}
-
-/* called under sysctl_lock */
-static void unuse_table(struct ctl_table_header *p)
-{
-	if (!--p->used)
-		if (unlikely(p->unregistering))
-			complete(p->unregistering);
-}
-
-/* called under sysctl_lock, will reacquire if has to wait */
-static void start_unregistering(struct ctl_table_header *p)
-{
-	/*
-	 * if p->used is 0, nobody will ever touch that entry again;
-	 * we'll eliminate all paths to it before dropping sysctl_lock
-	 */
-	if (unlikely(p->used)) {
-		struct completion wait;
-		init_completion(&wait);
-		p->unregistering = &wait;
-		spin_unlock(&sysctl_lock);
-		wait_for_completion(&wait);
-		spin_lock(&sysctl_lock);
-	} else {
-		/* anything non-NULL; we'll never dereference it */
-		p->unregistering = ERR_PTR(-EINVAL);
-	}
-	/*
-	 * do not remove from the list until nobody holds it; walking the
-	 * list in do_sysctl() relies on that.
-	 */
-	list_del_init(&p->ctl_entry);
-}
-
-void sysctl_head_get(struct ctl_table_header *head)
-{
-	spin_lock(&sysctl_lock);
-	head->count++;
-	spin_unlock(&sysctl_lock);
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
-	spin_lock(&sysctl_lock);
-	if (!--head->count)
-		kfree_rcu(head, rcu);
-	spin_unlock(&sysctl_lock);
-}
-
-struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
-{
-	if (!head)
-		BUG();
-	spin_lock(&sysctl_lock);
-	if (!use_table(head))
-		head = ERR_PTR(-ENOENT);
-	spin_unlock(&sysctl_lock);
-	return head;
-}
-
-void sysctl_head_finish(struct ctl_table_header *head)
-{
-	if (!head)
-		return;
-	spin_lock(&sysctl_lock);
-	unuse_table(head);
-	spin_unlock(&sysctl_lock);
-}
-
-static struct ctl_table_set *
-lookup_header_set(struct ctl_table_root *root, struct nsproxy *namespaces)
-{
-	struct ctl_table_set *set = &root->default_set;
-	if (root->lookup)
-		set = root->lookup(root, namespaces);
-	return set;
-}
-
-static struct list_head *
-lookup_header_list(struct ctl_table_root *root, struct nsproxy *namespaces)
-{
-	struct ctl_table_set *set = lookup_header_set(root, namespaces);
-	return &set->list;
-}
-
-struct ctl_table_header *__sysctl_head_next(struct nsproxy *namespaces,
-					    struct ctl_table_header *prev)
-{
-	struct ctl_table_root *root;
-	struct list_head *header_list;
-	struct ctl_table_header *head;
-	struct list_head *tmp;
-
-	spin_lock(&sysctl_lock);
-	if (prev) {
-		head = prev;
-		tmp = &prev->ctl_entry;
-		unuse_table(prev);
-		goto next;
-	}
-	tmp = &root_table_header.ctl_entry;
-	for (;;) {
-		head = list_entry(tmp, struct ctl_table_header, ctl_entry);
-
-		if (!use_table(head))
-			goto next;
-		spin_unlock(&sysctl_lock);
-		return head;
-	next:
-		root = head->root;
-		tmp = tmp->next;
-		header_list = lookup_header_list(root, namespaces);
-		if (tmp != header_list)
-			continue;
-
-		do {
-			root = list_entry(root->root_list.next,
-					struct ctl_table_root, root_list);
-			if (root == &sysctl_table_root)
-				goto out;
-			header_list = lookup_header_list(root, namespaces);
-		} while (list_empty(header_list));
-		tmp = header_list->next;
-	}
-out:
-	spin_unlock(&sysctl_lock);
-	return NULL;
-}
-
-struct ctl_table_header *sysctl_head_next(struct ctl_table_header *prev)
-{
-	return __sysctl_head_next(current->nsproxy, prev);
-}
-
-void register_sysctl_root(struct ctl_table_root *root)
-{
-	spin_lock(&sysctl_lock);
-	list_add_tail(&root->root_list, &sysctl_table_root.root_list);
-	spin_unlock(&sysctl_lock);
-}
-
-/*
- * sysctl_perm does NOT grant the superuser all rights automatically, because
- * some sysctl variables are readonly even to root.
- */
-
-static int test_perm(int mode, int op)
-{
-	if (!current_euid())
-		mode >>= 6;
-	else if (in_egroup_p(0))
-		mode >>= 3;
-	if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0)
-		return 0;
-	return -EACCES;
-}
-
-int sysctl_perm(struct ctl_table_root *root, struct ctl_table *table, int op)
-{
-	int mode;
-
-	if (root->permissions)
-		mode = root->permissions(root, current->nsproxy, table);
-	else
-		mode = table->mode;
-
-	return test_perm(mode, op);
-}
-
-static void sysctl_set_parent(struct ctl_table *parent, struct ctl_table *table)
-{
-	for (; table->procname; table++) {
-		table->parent = parent;
-		if (table->child)
-			sysctl_set_parent(table, table->child);
-	}
-}
-
-static __init int sysctl_init(void)
-{
-	sysctl_set_parent(NULL, root_table);
-#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
-	sysctl_check_table(current->nsproxy, root_table);
-#endif
+	register_sysctl_table(sysctl_base_table);
 	return 0;
-}
-
-core_initcall(sysctl_init);
-
-static struct ctl_table *is_branch_in(struct ctl_table *branch,
-				      struct ctl_table *table)
-{
-	struct ctl_table *p;
-	const char *s = branch->procname;
-
-	/* branch should have named subdirectory as its first element */
-	if (!s || !branch->child)
-		return NULL;
-
-	/* ... and nothing else */
-	if (branch[1].procname)
-		return NULL;
-
-	/* table should contain subdirectory with the same name */
-	for (p = table; p->procname; p++) {
-		if (!p->child)
-			continue;
-		if (p->procname && strcmp(p->procname, s) == 0)
-			return p;
-	}
-	return NULL;
-}
-
-/* see if attaching q to p would be an improvement */
-static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
-{
-	struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
-	struct ctl_table *next;
-	int is_better = 0;
-	int not_in_parent = !p->attached_by;
-
-	while ((next = is_branch_in(by, to)) != NULL) {
-		if (by == q->attached_by)
-			is_better = 1;
-		if (to == p->attached_by)
-			not_in_parent = 1;
-		by = by->child;
-		to = next->child;
-	}
-
-	if (is_better && not_in_parent) {
-		q->attached_by = by;
-		q->attached_to = to;
-		q->parent = p;
-	}
-}
-
-/**
- * __register_sysctl_paths - register a sysctl hierarchy
- * @root: List of sysctl headers to register on
- * @namespaces: Data to compute which lists of sysctl entries are visible
- * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * The members of the &struct ctl_table structure are used as follows:
- *
- * procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
- *            enter a sysctl file
- *
- * data - a pointer to data for use by proc_handler
- *
- * maxlen - the maximum size in bytes of the data
- *
- * mode - the file permissions for the /proc/sys file, and for sysctl(2)
- *
- * child - a pointer to the child sysctl table if this entry is a directory, or
- *         %NULL.
- *
- * proc_handler - the text handler routine (described below)
- *
- * de - for internal use by the sysctl routines
- *
- * extra1, extra2 - extra pointers usable by the proc handler routines
- *
- * Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes will be represented by directories.
- *
- * sysctl(2) can automatically manage read and write requests through
- * the sysctl table.  The data and maxlen fields of the ctl_table
- * struct enable minimal validation of the values being written to be
- * performed, and the mode field allows minimal authentication.
- *
- * There must be a proc_handler routine for any terminal nodes
- * mirrored under /proc/sys (non-terminals are handled by a built-in
- * directory handler).  Several default handlers are available to
- * cover common cases -
- *
- * proc_dostring(), proc_dointvec(), proc_dointvec_jiffies(),
- * proc_dointvec_userhz_jiffies(), proc_dointvec_minmax(), 
- * proc_doulongvec_ms_jiffies_minmax(), proc_doulongvec_minmax()
- *
- * It is the handler's job to read the input buffer from user memory
- * and process it. The handler should return 0 on success.
- *
- * This routine returns %NULL on a failure to register, and a pointer
- * to the table header on success.
- */
-struct ctl_table_header *__register_sysctl_paths(
-	struct ctl_table_root *root,
-	struct nsproxy *namespaces,
-	const struct ctl_path *path, struct ctl_table *table)
-{
-	struct ctl_table_header *header;
-	struct ctl_table *new, **prevp;
-	unsigned int n, npath;
-	struct ctl_table_set *set;
-
-	/* Count the path components */
-	for (npath = 0; path[npath].procname; ++npath)
-		;
-
-	/*
-	 * For each path component, allocate a 2-element ctl_table array.
-	 * The first array element will be filled with the sysctl entry
-	 * for this, the second will be the sentinel (procname == 0).
-	 *
-	 * We allocate everything in one go so that we don't have to
-	 * worry about freeing additional memory in unregister_sysctl_table.
-	 */
-	header = kzalloc(sizeof(struct ctl_table_header) +
-			 (2 * npath * sizeof(struct ctl_table)), GFP_KERNEL);
-	if (!header)
-		return NULL;
-
-	new = (struct ctl_table *) (header + 1);
-
-	/* Now connect the dots */
-	prevp = &header->ctl_table;
-	for (n = 0; n < npath; ++n, ++path) {
-		/* Copy the procname */
-		new->procname = path->procname;
-		new->mode     = 0555;
-
-		*prevp = new;
-		prevp = &new->child;
-
-		new += 2;
-	}
-	*prevp = table;
-	header->ctl_table_arg = table;
-
-	INIT_LIST_HEAD(&header->ctl_entry);
-	header->used = 0;
-	header->unregistering = NULL;
-	header->root = root;
-	sysctl_set_parent(NULL, header->ctl_table);
-	header->count = 1;
-#ifdef CONFIG_SYSCTL_SYSCALL_CHECK
-	if (sysctl_check_table(namespaces, header->ctl_table)) {
-		kfree(header);
-		return NULL;
-	}
-#endif
-	spin_lock(&sysctl_lock);
-	header->set = lookup_header_set(root, namespaces);
-	header->attached_by = header->ctl_table;
-	header->attached_to = root_table;
-	header->parent = &root_table_header;
-	for (set = header->set; set; set = set->parent) {
-		struct ctl_table_header *p;
-		list_for_each_entry(p, &set->list, ctl_entry) {
-			if (p->unregistering)
-				continue;
-			try_attach(p, header);
-		}
-	}
-	header->parent->count++;
-	list_add_tail(&header->ctl_entry, &header->set->list);
-	spin_unlock(&sysctl_lock);
-
-	return header;
-}
-
-/**
- * register_sysctl_table_path - register a sysctl table hierarchy
- * @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * See __register_sysctl_paths for more details.
- */
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
-						struct ctl_table *table)
-{
-	return __register_sysctl_paths(&sysctl_table_root, current->nsproxy,
-					path, table);
-}
-
-/**
- * register_sysctl_table - register a sysctl table hierarchy
- * @table: the top-level table structure
- *
- * Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
- *
- * See register_sysctl_paths for more details.
- */
-struct ctl_table_header *register_sysctl_table(struct ctl_table *table)
-{
-	static const struct ctl_path null_path[] = { {} };
-
-	return register_sysctl_paths(null_path, table);
-}
-
-/**
- * unregister_sysctl_table - unregister a sysctl table hierarchy
- * @header: the header returned from register_sysctl_table
- *
- * Unregisters the sysctl table and all children. proc entries may not
- * actually be removed until they are no longer used by anyone.
- */
-void unregister_sysctl_table(struct ctl_table_header * header)
-{
-	might_sleep();
-
-	if (header == NULL)
-		return;
-
-	spin_lock(&sysctl_lock);
-	start_unregistering(header);
-	if (!--header->parent->count) {
-		WARN_ON(1);
-		kfree_rcu(header->parent, rcu);
-	}
-	if (!--header->count)
-		kfree_rcu(header, rcu);
-	spin_unlock(&sysctl_lock);
-}
-
-int sysctl_is_seen(struct ctl_table_header *p)
-{
-	struct ctl_table_set *set = p->set;
-	int res;
-	spin_lock(&sysctl_lock);
-	if (p->unregistering)
-		res = 0;
-	else if (!set->is_seen)
-		res = 1;
-	else
-		res = set->is_seen(set);
-	spin_unlock(&sysctl_lock);
-	return res;
-}
-
-void setup_sysctl_set(struct ctl_table_set *p,
-	struct ctl_table_set *parent,
-	int (*is_seen)(struct ctl_table_set *))
-{
-	INIT_LIST_HEAD(&p->list);
-	p->parent = parent ? parent : &sysctl_table_root.default_set;
-	p->is_seen = is_seen;
-}
-
-#else /* !CONFIG_SYSCTL */
-struct ctl_table_header *register_sysctl_table(struct ctl_table * table)
-{
-	return NULL;
-}
-
-struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path,
-						    struct ctl_table *table)
-{
-	return NULL;
-}
-
-void unregister_sysctl_table(struct ctl_table_header * table)
-{
-}
-
-void setup_sysctl_set(struct ctl_table_set *p,
-	struct ctl_table_set *parent,
-	int (*is_seen)(struct ctl_table_set *))
-{
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
 }
 
 #endif /* CONFIG_SYSCTL */
···
 EXPORT_SYMBOL(proc_dostring);
 EXPORT_SYMBOL(proc_doulongvec_minmax);
 EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
-EXPORT_SYMBOL(register_sysctl_table);
-EXPORT_SYMBOL(register_sysctl_paths);
-EXPORT_SYMBOL(unregister_sysctl_table);

kernel/sysctl_check.c

···
-#include <linux/stat.h>
-#include <linux/sysctl.h>
-#include "../fs/xfs/xfs_sysctl.h"
-#include <linux/sunrpc/debug.h>
-#include <linux/string.h>
-#include <net/ip_vs.h>
-
-
-static int sysctl_depth(struct ctl_table *table)
-{
-	struct ctl_table *tmp;
-	int depth;
-
-	depth = 0;
-	for (tmp = table; tmp->parent; tmp = tmp->parent)
-		depth++;
-
-	return depth;
-}
-
-static struct ctl_table *sysctl_parent(struct ctl_table *table, int n)
-{
-	int i;
-
-	for (i = 0; table && i < n; i++)
-		table = table->parent;
-
-	return table;
-}
-
-
-static void sysctl_print_path(struct ctl_table *table)
-{
-	struct ctl_table *tmp;
-	int depth, i;
-	depth = sysctl_depth(table);
-	if (table->procname) {
-		for (i = depth; i >= 0; i--) {
-			tmp = sysctl_parent(table, i);
-			printk("/%s", tmp->procname?tmp->procname:"");
-		}
-	}
-	printk(" ");
-}
-
-static struct ctl_table *sysctl_check_lookup(struct nsproxy *namespaces,
-						struct ctl_table *table)
-{
-	struct ctl_table_header *head;
-	struct ctl_table *ref, *test;
-	int depth, cur_depth;
-
-	depth = sysctl_depth(table);
-
-	for (head = __sysctl_head_next(namespaces, NULL); head;
-	     head = __sysctl_head_next(namespaces, head)) {
-		cur_depth = depth;
-		ref = head->ctl_table;
-repeat:
-		test = sysctl_parent(table, cur_depth);
-		for (; ref->procname; ref++) {
-			int match = 0;
-			if (cur_depth && !ref->child)
-				continue;
-
-			if (test->procname && ref->procname &&
-			    (strcmp(test->procname, ref->procname) == 0))
-					match++;
-
-			if (match) {
-				if (cur_depth != 0) {
-					cur_depth--;
-					ref = ref->child;
-					goto repeat;
-				}
-				goto out;
-			}
-		}
-	}
-	ref = NULL;
-out:
-	sysctl_head_finish(head);
-	return ref;
-}
-
-static void set_fail(const char **fail, struct ctl_table *table, const char *str)
-{
-	if (*fail) {
-		printk(KERN_ERR "sysctl table check failed: ");
-		sysctl_print_path(table);
-		printk(" %s\n", *fail);
-		dump_stack();
-	}
-	*fail = str;
-}
-
-static void sysctl_check_leaf(struct nsproxy *namespaces,
-				struct ctl_table *table, const char **fail)
-{
-	struct ctl_table *ref;
-
-	ref = sysctl_check_lookup(namespaces, table);
-	if (ref && (ref != table))
-		set_fail(fail, table, "Sysctl already exists");
-}
-
-int sysctl_check_table(struct nsproxy *namespaces, struct ctl_table *table)
-{
-	int error = 0;
-	for (; table->procname; table++) {
-		const char *fail = NULL;
-
-		if (table->parent) {
-			if (!table->parent->procname)
-				set_fail(&fail, table, "Parent without procname");
-		}
-		if (table->child) {
-			if (table->data)
-				set_fail(&fail, table, "Directory with data?");
-			if (table->maxlen)
-				set_fail(&fail, table, "Directory with maxlen?");
-			if ((table->mode & (S_IRUGO|S_IXUGO)) != table->mode)
-				set_fail(&fail, table, "Writable sysctl directory");
-			if (table->proc_handler)
-				set_fail(&fail, table, "Directory with proc_handler");
-			if (table->extra1)
-				set_fail(&fail, table, "Directory with extra1");
-			if (table->extra2)
-				set_fail(&fail, table, "Directory with extra2");
-		} else {
-			if ((table->proc_handler == proc_dostring) ||
-			    (table->proc_handler == proc_dointvec) ||
-			    (table->proc_handler == proc_dointvec_minmax) ||
-			    (table->proc_handler == proc_dointvec_jiffies) ||
-			    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
-			    (table->proc_handler == proc_dointvec_ms_jiffies) ||
-			    (table->proc_handler == proc_doulongvec_minmax) ||
-			    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
-				if (!table->data)
-					set_fail(&fail, table, "No data");
-				if (!table->maxlen)
-					set_fail(&fail, table, "No maxlen");
-			}
-#ifdef CONFIG_PROC_SYSCTL
-			if (!table->proc_handler)
-				set_fail(&fail, table, "No proc_handler");
-#endif
-			sysctl_check_leaf(namespaces, table, &fail);
-		}
-		if (table->mode > 0777)
-			set_fail(&fail, table, "bogus .mode");
-		if (fail) {
-			set_fail(&fail, table, NULL);
-			error = -EINVAL;
-		}
-		if (table->child)
-			error |= sysctl_check_table(namespaces, table->child);
-	}
-	return error;
-}

lib/Kconfig.debug

···
 	  Enable this option if you want to use the LatencyTOP tool
 	  to find out which userspace is blocking on what kernel operations.
 
-config SYSCTL_SYSCALL_CHECK
-	bool "Sysctl checks"
-	depends on SYSCTL
-	---help---
-	  sys_sysctl uses binary paths that have been found challenging
-	  to properly maintain and use. This enables checks that help
-	  you to keep things correct.
-
 source mm/Kconfig.debug
 source kernel/trace/Kconfig
 

net/sysctl_net.c

···
 
 static int __net_init sysctl_net_init(struct net *net)
 {
-	setup_sysctl_set(&net->sysctls,
-			 &net_sysctl_ro_root.default_set,
-			 is_seen);
+	setup_sysctl_set(&net->sysctls, &net_sysctl_root, is_seen);
 	return 0;
 }
 
 static void __net_exit sysctl_net_exit(struct net *net)
 {
-	WARN_ON(!list_empty(&net->sysctls.list));
+	retire_sysctl_set(&net->sysctls);
 }
 
 static struct pernet_operations sysctl_pernet_ops = {
···
 	.exit = sysctl_net_exit,
 };
 
-static __init int sysctl_init(void)
+static __init int net_sysctl_init(void)
 {
 	int ret;
 	ret = register_pernet_subsys(&sysctl_pernet_ops);
 	if (ret)
 		goto out;
-	register_sysctl_root(&net_sysctl_root);
-	setup_sysctl_set(&net_sysctl_ro_root.default_set, NULL, NULL);
+	setup_sysctl_set(&net_sysctl_ro_root.default_set, &net_sysctl_ro_root, NULL);
 	register_sysctl_root(&net_sysctl_ro_root);
+	register_sysctl_root(&net_sysctl_root);
 out:
 	return ret;
 }
-subsys_initcall(sysctl_init);
+subsys_initcall(net_sysctl_init);
 
 struct ctl_table_header *register_net_sysctl_table(struct net *net,
 	const struct ctl_path *path, struct ctl_table *table)
 {
-	struct nsproxy namespaces;
-	namespaces = *current->nsproxy;
-	namespaces.net_ns = net;
-	return __register_sysctl_paths(&net_sysctl_root,
-					&namespaces, path, table);
+	return __register_sysctl_paths(&net->sysctls, path, table);
 }
 EXPORT_SYMBOL_GPL(register_net_sysctl_table);
 
 struct ctl_table_header *register_net_sysctl_rotable(const
 		struct ctl_path *path, struct ctl_table *table)
 {
-	return __register_sysctl_paths(&net_sysctl_ro_root,
-			&init_nsproxy, path, table);
+	return __register_sysctl_paths(&net_sysctl_ro_root.default_set,
+					path, table);
 }
 EXPORT_SYMBOL_GPL(register_net_sysctl_rotable);