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);
}

static int proc_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	int err;
	struct super_block *sb;
	struct pid_namespace *ns;
	struct proc_inode *ei;
	char *options;

	if (proc_mnt) {
		/* Seed the root directory with a pid so it doesn't need
		 * to be special in base.c.  I would do this earlier but
		 * the only task alive when /proc is mounted the first time
		 * is the init_task and it doesn't have any pids.
		 */
		ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
		if (!ei->pid)
			ei->pid = find_get_pid(1);
	}

	if (flags & MS_KERNMOUNT) {
		ns = (struct pid_namespace *)data;
		options = NULL;
	} else {
		ns = task_active_pid_ns(current);
		options = data;
	}

	sb = sget(fs_type, proc_test_super, proc_set_super, ns);
	if (IS_ERR(sb))
		return PTR_ERR(sb);

	if (!sb->s_root) {
		sb->s_flags = flags;
		if (!proc_parse_options(options, ns)) {
			deactivate_locked_super(sb);
			return -EINVAL;
		}
		err = proc_fill_super(sb);
		if (err) {
			deactivate_locked_super(sb);
			return err;
		}

		ei = PROC_I(sb->s_root->d_inode);
		if (!ei->pid) {
			rcu_read_lock();
			ei->pid = get_pid(find_pid_ns(1, ns));
			rcu_read_unlock();
		}

		sb->s_flags |= MS_ACTIVE;
		ns->proc_mnt = mnt;
	}

	simple_set_mnt(mnt, sb);
	return 0;
}

static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
{
	struct inode *inode;
	struct proc_inode *ei;

	inode = new_inode(sb);
	if (!inode)
		goto out;

	inode->i_ino = get_next_ino();

	sysctl_head_get(head);
	ei = PROC_I(inode);
	ei->sysctl = head;
	ei->sysctl_entry = table;

	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_mode = table->mode;
	if (!table->child) {
		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;
	}
out:
	return inode;
}

static struct dentry *
proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
			struct task_struct *task, const void *ptr)
{
	struct dentry *error = ERR_PTR(-ENOENT);
	unsigned fd = (unsigned long)ptr;
	struct proc_inode *ei;
	struct inode *inode;

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	ei = PROC_I(inode);
	ei->fd = fd;

	inode->i_mode = S_IFREG | S_IRUSR;
	inode->i_fop = &proc_fdinfo_file_operations;

	d_set_d_op(dentry, &tid_fd_dentry_operations);
	d_add(dentry, inode);

	/* Close the race of the process dying before we return the dentry */
	if (tid_fd_revalidate(dentry, 0))
		error = NULL;
 out:
	return error;
}

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 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)) {
		filp->private_data = proc_sys_poll_event(table->poll);
		ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
	}

out:
	sysctl_head_finish(head);

	return ret;
}

static struct inode *proc_sys_make_inode(struct super_block *sb,
		struct ctl_table_header *head, struct ctl_table *table)
{
	struct inode *inode;
	struct proc_inode *ei;

	inode = new_inode(sb);
	if (!inode)
		goto out;

	sysctl_head_get(head);
	ei = PROC_I(inode);
	ei->sysctl = head;
	ei->sysctl_entry = table;

	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
	inode->i_mode = table->mode;
	if (!table->child) {
		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;
		inode->i_nlink = 0;
		inode->i_op = &proc_sys_dir_operations;
		inode->i_fop = &proc_sys_dir_file_operations;
	}
out:
	return inode;
}

static int
proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
		    struct task_struct *task, const void *ptr)
{
	unsigned fd = (unsigned long)ptr;
	struct proc_inode *ei;
	struct inode *inode;

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	ei = PROC_I(inode);
	ei->fd = fd;

	inode->i_mode = S_IFLNK;
	inode->i_op = &proc_pid_link_inode_operations;
	inode->i_size = 64;

	ei->op.proc_get_link = proc_fd_link;

	d_set_d_op(dentry, &tid_fd_dentry_operations);
	d_add(dentry, inode);

	/* Close the race of the process dying before we return the dentry */
	if (tid_fd_revalidate(dentry, 0))
		return 0;
 out:
	return -ENOENT;
}

static struct dentry *proc_ns_instantiate(struct inode *dir,
	struct dentry *dentry, struct task_struct *task, const void *ptr)
{
	const struct proc_ns_operations *ns_ops = ptr;
	struct inode *inode;
	struct proc_inode *ei;
	struct dentry *error = ERR_PTR(-ENOENT);
	void *ns;

	inode = proc_pid_make_inode(dir->i_sb, task);
	if (!inode)
		goto out;

	ns = ns_ops->get(task);
	if (!ns)
		goto out_iput;

	ei = PROC_I(inode);
	inode->i_mode = S_IFREG|S_IRUSR;
	inode->i_fop  = &ns_file_operations;
	ei->ns_ops    = ns_ops;
	ei->ns	      = ns;

	d_set_d_op(dentry, &pid_dentry_operations);
	d_add(dentry, inode);
	/* Close the race of the process dying before we return the dentry */
	if (pid_revalidate(dentry, 0))
		error = NULL;
out:
	return error;
out_iput:
	iput(inode);
	goto out;
}

static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
		size_t count, loff_t *ppos, int write)
{
	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;
	ssize_t error;
	size_t res;

	if (IS_ERR(head))
		return PTR_ERR(head);

	/*
	 * At this point we know that the sysctl was not unregistered
	 * and won't be until we finish.
	 */
	error = -EPERM;
	if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
		goto out;

	/* if that can happen at all, it should be -EINVAL, not -EISDIR */
	error = -EINVAL;
	if (!table->proc_handler)
		goto out;

	/* careful: calling conventions are nasty here */
	res = count;
	error = table->proc_handler(table, write, buf, &res, ppos);
	if (!error)
		error = res;
out:
	sysctl_head_finish(head);

	return error;
}

static int proc_sys_permission(struct inode *inode, int mask)
{
	/*
	 * sysctl entries that are not writeable,
	 * are _NOT_ writeable, capabilities or not.
	 */
	struct ctl_table_header *head;
	struct ctl_table *table;
	int error;

	/* Executable files are not allowed under /proc/sys/ */
	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
		return -EACCES;

	head = grab_header(inode);
	if (IS_ERR(head))
		return PTR_ERR(head);

	table = PROC_I(inode)->sysctl_entry;
	if (!table) /* global root - r-xr-xr-x */
		error = mask & MAY_WRITE ? -EACCES : 0;
	else /* Use the permissions on the sysctl table entry */
		error = sysctl_perm(head->root, table, mask & ~MAY_NOT_BLOCK);

	sysctl_head_finish(head);
	return error;
}

static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
	struct inode *inode = dentry->d_inode;
	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns.ns_ops;

	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
		ns_ops->name, inode->i_ino);
}

/*
 * Decrement the use count of the proc_dir_entry.
 */
static void proc_delete_inode(struct inode *inode)
{
	struct proc_dir_entry *de;

	truncate_inode_pages(&inode->i_data, 0);

	/* Stop tracking associated processes */
	put_pid(PROC_I(inode)->pid);

	/* Let go of any associated proc directory entry */
	de = PROC_I(inode)->pde;
	if (de) {
		if (de->owner)
			module_put(de->owner);
		de_put(de);
	}
	clear_inode(inode);
}

static int proc_sys_open(struct inode *inode, struct file *filp)
{
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	if (table->poll)
		filp->private_data = proc_sys_poll_event(table->poll);

	return 0;
}

/*
 * Decrement the use count of the proc_dir_entry.
 */
static void proc_delete_inode(struct inode *inode)
{
	struct proc_dir_entry *de;
	struct task_struct *tsk;

	/* Let go of any associated process */
	tsk = PROC_I(inode)->task;
	if (tsk)
		put_task_struct(tsk);

	/* Let go of any associated proc directory entry */
	de = PROC_I(inode)->pde;
	if (de) {
		if (de->owner)
			module_put(de->owner);
		de_put(de);
	}
	clear_inode(inode);
}

static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
			    struct qstr *name)
{
	struct dentry *dentry = container_of(qstr, struct dentry, d_name);
	if (qstr->len != name->len)
		return 1;
	if (memcmp(qstr->name, name->name, name->len))
		return 1;
	return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
}

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;
	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;

	ret = 0;
	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
	if (filp->f_pos == 0) {
		if (filldir(dirent, ".", 1, filp->f_pos,
				inode->i_ino, DT_DIR) < 0)
			goto out;
		filp->f_pos++;
	}
	if (filp->f_pos == 1) {
		if (filldir(dirent, "..", 2, filp->f_pos,
				parent_ino(dentry), DT_DIR) < 0)
			goto out;
		filp->f_pos++;
	}
	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);
		if (ret) {
			sysctl_head_finish(h);
			break;
		}
	}
	ret = 1;
out:
	sysctl_head_finish(head);
	return ret;
}

static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	struct ctl_table_header *head = grab_header(inode);
	struct ctl_table *table = PROC_I(inode)->sysctl_entry;

	if (IS_ERR(head))
		return PTR_ERR(head);

	generic_fillattr(inode, stat);
	if (table)
		stat->mode = (stat->mode & S_IFMT) | table->mode;

	sysctl_head_finish(head);
	return 0;
}

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 int proc_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	if (proc_mnt) {
		/* Seed the root directory with a pid so it doesn't need
		 * to be special in base.c.  I would do this earlier but
		 * the only task alive when /proc is mounted the first time
		 * is the init_task and it doesn't have any pids.
		 */
		struct proc_inode *ei;
		ei = PROC_I(proc_mnt->mnt_sb->s_root->d_inode);
		if (!ei->pid)
			ei->pid = find_get_pid(1);
	}
	return get_sb_single(fs_type, flags, data, proc_fill_super, mnt);
}

static struct dentry *proc_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	int err;
	struct super_block *sb;
	struct pid_namespace *ns;
	struct proc_inode *ei;
	char *options;

	if (flags & MS_KERNMOUNT) {
		ns = (struct pid_namespace *)data;
		options = NULL;
	} else {
		ns = current->nsproxy->pid_ns;
		options = data;
	}

	sb = sget(fs_type, proc_test_super, proc_set_super, ns);
	if (IS_ERR(sb))
		return ERR_CAST(sb);

	if (!proc_parse_options(options, ns)) {
		deactivate_locked_super(sb);
		return ERR_PTR(-EINVAL);
	}

	if (!sb->s_root) {
		sb->s_flags = flags;
		err = proc_fill_super(sb);
		if (err) {
			deactivate_locked_super(sb);
			return ERR_PTR(err);
		}

		sb->s_flags |= MS_ACTIVE;
	}

	ei = PROC_I(sb->s_root->d_inode);
	if (!ei->pid) {
		rcu_read_lock();
		ei->pid = get_pid(find_pid_ns(1, ns));
		rcu_read_unlock();
	}

	return dget(sb->s_root);
}