sysctl.c

		.data		= &vm_dirty_ratio,
		.maxlen		= sizeof(vm_dirty_ratio),
		.mode		= 0644,
		.proc_handler	= dirty_ratio_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "dirty_bytes",
		.data		= &vm_dirty_bytes,
		.maxlen		= sizeof(vm_dirty_bytes),
		.mode		= 0644,
		.proc_handler	= dirty_bytes_handler,
		.extra1		= &dirty_bytes_min,
	},
	{
		.procname	= "dirty_writeback_centisecs",
		.data		= &dirty_writeback_interval,
		.maxlen		= sizeof(dirty_writeback_interval),
		.mode		= 0644,
		.proc_handler	= dirty_writeback_centisecs_handler,
	},
	{
		.procname	= "dirty_expire_centisecs",
		.data		= &dirty_expire_interval,
		.maxlen		= sizeof(dirty_expire_interval),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "nr_pdflush_threads",
		.data		= &nr_pdflush_threads,
		.maxlen		= sizeof nr_pdflush_threads,
		.mode		= 0444 /* read-only*/,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "swappiness",
		.data		= &vm_swappiness,
		.maxlen		= sizeof(vm_swappiness),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
#ifdef CONFIG_HUGETLB_PAGE
	{
		.procname	= "nr_hugepages",
		.data		= NULL,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= hugetlb_sysctl_handler,
		.extra1		= (void *)&hugetlb_zero,
		.extra2		= (void *)&hugetlb_infinity,
	},
#ifdef CONFIG_NUMA
	{
		.procname       = "nr_hugepages_mempolicy",
		.data           = NULL,
		.maxlen         = sizeof(unsigned long),
		.mode           = 0644,
		.proc_handler   = &hugetlb_mempolicy_sysctl_handler,
		.extra1		= (void *)&hugetlb_zero,
		.extra2		= (void *)&hugetlb_infinity,
	},
#endif
	 {
		.procname	= "hugetlb_shm_group",
		.data		= &sysctl_hugetlb_shm_group,
		.maxlen		= sizeof(gid_t),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	 },
	 {
		.procname	= "hugepages_treat_as_movable",
		.data		= &hugepages_treat_as_movable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= hugetlb_treat_movable_handler,
	},
	{
		.procname	= "nr_overcommit_hugepages",
		.data		= NULL,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= hugetlb_overcommit_handler,
		.extra1		= (void *)&hugetlb_zero,
		.extra2		= (void *)&hugetlb_infinity,
	},
#endif
	{
		.procname	= "lowmem_reserve_ratio",
		.data		= &sysctl_lowmem_reserve_ratio,
		.maxlen		= sizeof(sysctl_lowmem_reserve_ratio),
		.mode		= 0644,
		.proc_handler	= lowmem_reserve_ratio_sysctl_handler,
	},
	{
		.procname	= "drop_caches",
		.data		= &sysctl_drop_caches,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= drop_caches_sysctl_handler,
	},
	{
		.procname	= "min_free_kbytes",
		.data		= &min_free_kbytes,
		.maxlen		= sizeof(min_free_kbytes),
		.mode		= 0644,
		.proc_handler	= min_free_kbytes_sysctl_handler,
		.extra1		= &zero,
	},
	{
		.procname	= "percpu_pagelist_fraction",
		.data		= &percpu_pagelist_fraction,
		.maxlen		= sizeof(percpu_pagelist_fraction),
		.mode		= 0644,
		.proc_handler	= percpu_pagelist_fraction_sysctl_handler,
		.extra1		= &min_percpu_pagelist_fract,
	},
#ifdef CONFIG_MMU
	{
		.procname	= "max_map_count",
		.data		= &sysctl_max_map_count,
		.maxlen		= sizeof(sysctl_max_map_count),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
#else
	{
		.procname	= "nr_trim_pages",
		.data		= &sysctl_nr_trim_pages,
		.maxlen		= sizeof(sysctl_nr_trim_pages),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
	},
#endif
	{
		.procname	= "laptop_mode",
		.data		= &laptop_mode,
		.maxlen		= sizeof(laptop_mode),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "block_dump",
		.data		= &block_dump,
		.maxlen		= sizeof(block_dump),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
	{
		.procname	= "vfs_cache_pressure",
		.data		= &sysctl_vfs_cache_pressure,
		.maxlen		= sizeof(sysctl_vfs_cache_pressure),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT
	{
		.procname	= "legacy_va_layout",
		.data		= &sysctl_legacy_va_layout,
		.maxlen		= sizeof(sysctl_legacy_va_layout),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#endif
#ifdef CONFIG_NUMA
	{
		.procname	= "zone_reclaim_mode",
		.data		= &zone_reclaim_mode,
		.maxlen		= sizeof(zone_reclaim_mode),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
	{
		.procname	= "min_unmapped_ratio",
		.data		= &sysctl_min_unmapped_ratio,
		.maxlen		= sizeof(sysctl_min_unmapped_ratio),
		.mode		= 0644,
		.proc_handler	= sysctl_min_unmapped_ratio_sysctl_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.procname	= "min_slab_ratio",
		.data		= &sysctl_min_slab_ratio,
		.maxlen		= sizeof(sysctl_min_slab_ratio),
		.mode		= 0644,
		.proc_handler	= sysctl_min_slab_ratio_sysctl_handler,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
#endif
#ifdef CONFIG_SMP
	{
		.procname	= "stat_interval",
		.data		= &sysctl_stat_interval,
		.maxlen		= sizeof(sysctl_stat_interval),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
#endif
#ifdef CONFIG_MMU
	{
		.procname	= "mmap_min_addr",
		.data		= &dac_mmap_min_addr,
		.maxlen		= sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= mmap_min_addr_handler,
	},
#endif
#ifdef CONFIG_NUMA
	{
		.procname	= "numa_zonelist_order",
		.data		= &numa_zonelist_order,
		.maxlen		= NUMA_ZONELIST_ORDER_LEN,
		.mode		= 0644,
		.proc_handler	= numa_zonelist_order_handler,
	},
#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
   (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
	{
		.procname	= "vdso_enabled",
		.data		= &vdso_enabled,
		.maxlen		= sizeof(vdso_enabled),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
		.extra1		= &zero,
	},
#endif
#ifdef CONFIG_HIGHMEM
	{
		.procname	= "highmem_is_dirtyable",
		.data		= &vm_highmem_is_dirtyable,
		.maxlen		= sizeof(vm_highmem_is_dirtyable),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
	{
		.procname	= "scan_unevictable_pages",
		.data		= &scan_unevictable_pages,
		.maxlen		= sizeof(scan_unevictable_pages),
		.mode		= 0644,
		.proc_handler	= scan_unevictable_handler,
	},
#ifdef CONFIG_MEMORY_FAILURE
	{
		.procname	= "memory_failure_early_kill",
		.data		= &sysctl_memory_failure_early_kill,
		.maxlen		= sizeof(sysctl_memory_failure_early_kill),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
	{
		.procname	= "memory_failure_recovery",
		.data		= &sysctl_memory_failure_recovery,
		.maxlen		= sizeof(sysctl_memory_failure_recovery),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif

/*
 * NOTE: do not add new entries to this table unless you have read
 * Documentation/sysctl/ctl_unnumbered.txt
 */
	{ }
};

#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
static struct ctl_table binfmt_misc_table[] = {
	{ }
};
#endif

static struct ctl_table fs_table[] = {
	{
		.procname	= "inode-nr",
		.data		= &inodes_stat,
		.maxlen		= 2*sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "inode-state",
		.data		= &inodes_stat,
		.maxlen		= 7*sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "file-nr",
		.data		= &files_stat,
		.maxlen		= 3*sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_nr_files,
	},
	{
		.procname	= "file-max",
		.data		= &files_stat.max_files,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "nr_open",
		.data		= &sysctl_nr_open,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &sysctl_nr_open_min,
		.extra2		= &sysctl_nr_open_max,
	},
	{
		.procname	= "dentry-state",
		.data		= &dentry_stat,
		.maxlen		= 6*sizeof(int),
		.mode		= 0444,
		.proc_handler	= proc_dointvec,
	},
	{
		.procname	= "overflowuid",
		.data		= &fs_overflowuid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
	{
		.procname	= "overflowgid",
		.data		= &fs_overflowgid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
#ifdef CONFIG_FILE_LOCKING
	{
		.procname	= "leases-enable",
		.data		= &leases_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_DNOTIFY
	{
		.procname	= "dir-notify-enable",
		.data		= &dir_notify_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_MMU
#ifdef CONFIG_FILE_LOCKING
	{
		.procname	= "lease-break-time",
		.data		= &lease_break_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
#endif
#ifdef CONFIG_AIO
	{
		.procname	= "aio-nr",
		.data		= &aio_nr,
		.maxlen		= sizeof(aio_nr),
		.mode		= 0444,
		.proc_handler	= proc_doulongvec_minmax,
	},
	{
		.procname	= "aio-max-nr",
		.data		= &aio_max_nr,
		.maxlen		= sizeof(aio_max_nr),
		.mode		= 0644,
		.proc_handler	= proc_doulongvec_minmax,
	},
#endif /* CONFIG_AIO */
#ifdef CONFIG_INOTIFY_USER
	{
		.procname	= "inotify",
		.mode		= 0555,
		.child		= inotify_table,
	},
#endif	
#ifdef CONFIG_EPOLL
	{
		.procname	= "epoll",
		.mode		= 0555,
		.child		= epoll_table,
	},
#endif
#endif
	{
		.procname	= "suid_dumpable",
		.data		= &suid_dumpable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1		= &zero,
		.extra2		= &two,
	},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
	{
		.procname	= "binfmt_misc",
		.mode		= 0555,
		.child		= binfmt_misc_table,
	},
#endif
/*
 * NOTE: do not add new entries to this table unless you have read
 * Documentation/sysctl/ctl_unnumbered.txt
 */
	{ }
};

static struct ctl_table debug_table[] = {
#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC)
	{
		.procname	= "exception-trace",
		.data		= &show_unhandled_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
#endif
#if defined(CONFIG_OPTPROBES)
	{
		.procname	= "kprobes-optimization",
		.data		= &sysctl_kprobes_optimization,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_kprobes_optimization_handler,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
	{ }
};

static struct ctl_table dev_table[] = {
	{ }
};

static DEFINE_SPINLOCK(sysctl_lock);

/* 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.
	 */
	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(head);
	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 error;
	int mode;

	error = security_sysctl(table, op & (MAY_READ | MAY_WRITE | MAY_EXEC));
	if (error)
		return error;

	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
	{
		int err;
		err = sysctl_check_table(current->nsproxy, root_table);
	}
#endif
	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(header->parent);
	}
	if (!--header->count)
		kfree(header);
	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 */

/*
 * /proc/sys support
 */

#ifdef CONFIG_PROC_SYSCTL

static int _proc_do_string(void* data, int maxlen, int write,
			   void __user *buffer,
			   size_t *lenp, loff_t *ppos)
{
	size_t len;
	char __user *p;
	char c;

	if (!data || !maxlen || !*lenp) {
		*lenp = 0;
		return 0;
	}

	if (write) {
		len = 0;
		p = buffer;
		while (len < *lenp) {
			if (get_user(c, p++))
				return -EFAULT;
			if (c == 0 || c == '\n')
				break;
			len++;
		}
		if (len >= maxlen)
			len = maxlen-1;
		if(copy_from_user(data, buffer, len))
			return -EFAULT;
		((char *) data)[len] = 0;
		*ppos += *lenp;
	} else {
		len = strlen(data);
		if (len > maxlen)
			len = maxlen;

		if (*ppos > len) {
			*lenp = 0;
			return 0;