sysctl.c

Kernel code of linux kernel

#ifdef CONFIG_NUMA
	{
		.ctl_name	= VM_ZONE_RECLAIM_MODE,
		.procname	= "zone_reclaim_mode",
		.data		= &zone_reclaim_mode,
		.maxlen		= sizeof(zone_reclaim_mode),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
	},
	{
		.ctl_name	= VM_MIN_UNMAPPED,
		.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,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
	{
		.ctl_name	= VM_MIN_SLAB,
		.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,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
		.extra2		= &one_hundred,
	},
#endif
#ifdef CONFIG_SMP
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "stat_interval",
		.data		= &sysctl_stat_interval,
		.maxlen		= sizeof(sysctl_stat_interval),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
#endif
#ifdef CONFIG_SECURITY
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "mmap_min_addr",
		.data		= &mmap_min_addr,
		.maxlen         = sizeof(unsigned long),
		.mode		= 0644,
		.proc_handler	= &proc_doulongvec_minmax,
	},
#endif
#ifdef CONFIG_NUMA
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "numa_zonelist_order",
		.data		= &numa_zonelist_order,
		.maxlen		= NUMA_ZONELIST_ORDER_LEN,
		.mode		= 0644,
		.proc_handler	= &numa_zonelist_order_handler,
		.strategy	= &sysctl_string,
	},
#endif
#if (defined(CONFIG_X86_32) && !defined(CONFIG_UML))|| \
   (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL))
	{
		.ctl_name	= VM_VDSO_ENABLED,
		.procname	= "vdso_enabled",
		.data		= &vdso_enabled,
		.maxlen		= sizeof(vdso_enabled),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
	},
#endif
#ifdef CONFIG_HIGHMEM
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "highmem_is_dirtyable",
		.data		= &vm_highmem_is_dirtyable,
		.maxlen		= sizeof(vm_highmem_is_dirtyable),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
		.extra2		= &one,
	},
#endif
/*
 * NOTE: do not add new entries to this table unless you have read
 * Documentation/sysctl/ctl_unnumbered.txt
 */
	{ .ctl_name = 0 }
};

#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
static struct ctl_table binfmt_misc_table[] = {
	{ .ctl_name = 0 }
};
#endif

static struct ctl_table fs_table[] = {
	{
		.ctl_name	= FS_NRINODE,
		.procname	= "inode-nr",
		.data		= &inodes_stat,
		.maxlen		= 2*sizeof(int),
		.mode		= 0444,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= FS_STATINODE,
		.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,
	},
	{
		.ctl_name	= FS_MAXFILE,
		.procname	= "file-max",
		.data		= &files_stat.max_files,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= CTL_UNNUMBERED,
		.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,
	},
	{
		.ctl_name	= FS_DENTRY,
		.procname	= "dentry-state",
		.data		= &dentry_stat,
		.maxlen		= 6*sizeof(int),
		.mode		= 0444,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= FS_OVERFLOWUID,
		.procname	= "overflowuid",
		.data		= &fs_overflowuid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
	{
		.ctl_name	= FS_OVERFLOWGID,
		.procname	= "overflowgid",
		.data		= &fs_overflowgid,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &minolduid,
		.extra2		= &maxolduid,
	},
	{
		.ctl_name	= FS_LEASES,
		.procname	= "leases-enable",
		.data		= &leases_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#ifdef CONFIG_DNOTIFY
	{
		.ctl_name	= FS_DIR_NOTIFY,
		.procname	= "dir-notify-enable",
		.data		= &dir_notify_enable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
#ifdef CONFIG_MMU
	{
		.ctl_name	= FS_LEASE_TIME,
		.procname	= "lease-break-time",
		.data		= &lease_break_time,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
		.extra2		= &two,
	},
	{
		.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,
	},
#ifdef CONFIG_INOTIFY_USER
	{
		.ctl_name	= FS_INOTIFY,
		.procname	= "inotify",
		.mode		= 0555,
		.child		= inotify_table,
	},
#endif	
#endif
	{
		.ctl_name	= KERN_SETUID_DUMPABLE,
		.procname	= "suid_dumpable",
		.data		= &suid_dumpable,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
	{
		.ctl_name	= CTL_UNNUMBERED,
		.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
 */
	{ .ctl_name = 0 }
};

static struct ctl_table debug_table[] = {
#if defined(CONFIG_X86) || defined(CONFIG_PPC)
	{
		.ctl_name	= CTL_UNNUMBERED,
		.procname	= "exception-trace",
		.data		= &show_unhandled_signals,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
#endif
	{ .ctl_name = 0 }
};

static struct ctl_table dev_table[] = {
	{ .ctl_name = 0 }
};

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);
}

#ifdef CONFIG_SYSCTL_SYSCALL
/* Perform the actual read/write of a sysctl table entry. */
static int do_sysctl_strategy(struct ctl_table_root *root,
			struct ctl_table *table,
			int __user *name, int nlen,
			void __user *oldval, size_t __user *oldlenp,
			void __user *newval, size_t newlen)
{
	int op = 0, rc;

	if (oldval)
		op |= MAY_READ;
	if (newval)
		op |= MAY_WRITE;
	if (sysctl_perm(root, table, op))
		return -EPERM;

	if (table->strategy) {
		rc = table->strategy(table, name, nlen, oldval, oldlenp,
				     newval, newlen);
		if (rc < 0)
			return rc;
		if (rc > 0)
			return 0;
	}

	/* If there is no strategy routine, or if the strategy returns
	 * zero, proceed with automatic r/w */
	if (table->data && table->maxlen) {
		rc = sysctl_data(table, name, nlen, oldval, oldlenp,
				 newval, newlen);
		if (rc < 0)
			return rc;
	}
	return 0;
}

static int parse_table(int __user *name, int nlen,
		       void __user *oldval, size_t __user *oldlenp,
		       void __user *newval, size_t newlen,
		       struct ctl_table_root *root,
		       struct ctl_table *table)
{
	int n;
repeat:
	if (!nlen)
		return -ENOTDIR;
	if (get_user(n, name))
		return -EFAULT;
	for ( ; table->ctl_name || table->procname; table++) {
		if (!table->ctl_name)
			continue;
		if (n == table->ctl_name) {
			int error;
			if (table->child) {
				if (sysctl_perm(root, table, MAY_EXEC))
					return -EPERM;
				name++;
				nlen--;
				table = table->child;
				goto repeat;
			}
			error = do_sysctl_strategy(root, table, name, nlen,
						   oldval, oldlenp,
						   newval, newlen);
			return error;
		}
	}
	return -ENOTDIR;
}

int do_sysctl(int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp,
	       void __user *newval, size_t newlen)
{
	struct ctl_table_header *head;
	int error = -ENOTDIR;

	if (nlen <= 0 || nlen >= CTL_MAXNAME)
		return -ENOTDIR;
	if (oldval) {
		int old_len;
		if (!oldlenp || get_user(old_len, oldlenp))
			return -EFAULT;
	}

	for (head = sysctl_head_next(NULL); head;
			head = sysctl_head_next(head)) {
		error = parse_table(name, nlen, oldval, oldlenp, 
					newval, newlen,
					head->root, head->ctl_table);
		if (error != -ENOTDIR) {
			sysctl_head_finish(head);
			break;
		}
	}
	return error;
}

asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
{
	struct __sysctl_args tmp;
	int error;

	if (copy_from_user(&tmp, args, sizeof(tmp)))
		return -EFAULT;

	error = deprecated_sysctl_warning(&tmp);
	if (error)
		goto out;

	lock_kernel();
	error = do_sysctl(tmp.name, tmp.nlen, tmp.oldval, tmp.oldlenp,
			  tmp.newval, tmp.newlen);
	unlock_kernel();
out:
	return error;
}
#endif /* CONFIG_SYSCTL_SYSCALL */

/*
 * sysctl_perm does NOT grant the superuser all rights automatically, because