ip_queue.c

linux 内核源代码

	}
	if (!skb_make_writable(e->skb, v->data_len))
		return -ENOMEM;
	skb_copy_to_linear_data(e->skb, v->payload, v->data_len);
	e->skb->ip_summed = CHECKSUM_NONE;

	return 0;
}

static inline int
id_cmp(struct ipq_queue_entry *e, unsigned long id)
{
	return (id == (unsigned long )e);
}

static int
ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
{
	struct ipq_queue_entry *entry;

	if (vmsg->value > NF_MAX_VERDICT)
		return -EINVAL;

	entry = ipq_find_dequeue_entry(id_cmp, vmsg->id);
	if (entry == NULL)
		return -ENOENT;
	else {
		int verdict = vmsg->value;

		if (vmsg->data_len && vmsg->data_len == len)
			if (ipq_mangle_ipv4(vmsg, entry) < 0)
				verdict = NF_DROP;

		ipq_issue_verdict(entry, verdict);
		return 0;
	}
}

static int
ipq_set_mode(unsigned char mode, unsigned int range)
{
	int status;

	write_lock_bh(&queue_lock);
	status = __ipq_set_mode(mode, range);
	write_unlock_bh(&queue_lock);
	return status;
}

static int
ipq_receive_peer(struct ipq_peer_msg *pmsg,
		 unsigned char type, unsigned int len)
{
	int status = 0;

	if (len < sizeof(*pmsg))
		return -EINVAL;

	switch (type) {
	case IPQM_MODE:
		status = ipq_set_mode(pmsg->msg.mode.value,
				      pmsg->msg.mode.range);
		break;

	case IPQM_VERDICT:
		if (pmsg->msg.verdict.value > NF_MAX_VERDICT)
			status = -EINVAL;
		else
			status = ipq_set_verdict(&pmsg->msg.verdict,
						 len - sizeof(*pmsg));
			break;
	default:
		status = -EINVAL;
	}
	return status;
}

static int
dev_cmp(struct ipq_queue_entry *entry, unsigned long ifindex)
{
	if (entry->info->indev)
		if (entry->info->indev->ifindex == ifindex)
			return 1;
	if (entry->info->outdev)
		if (entry->info->outdev->ifindex == ifindex)
			return 1;
#ifdef CONFIG_BRIDGE_NETFILTER
	if (entry->skb->nf_bridge) {
		if (entry->skb->nf_bridge->physindev &&
		    entry->skb->nf_bridge->physindev->ifindex == ifindex)
			return 1;
		if (entry->skb->nf_bridge->physoutdev &&
		    entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
			return 1;
	}
#endif
	return 0;
}

static void
ipq_dev_drop(int ifindex)
{
	struct ipq_queue_entry *entry;

	while ((entry = ipq_find_dequeue_entry(dev_cmp, ifindex)) != NULL)
		ipq_issue_verdict(entry, NF_DROP);
}

#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)

static inline void
__ipq_rcv_skb(struct sk_buff *skb)
{
	int status, type, pid, flags, nlmsglen, skblen;
	struct nlmsghdr *nlh;

	skblen = skb->len;
	if (skblen < sizeof(*nlh))
		return;

	nlh = nlmsg_hdr(skb);
	nlmsglen = nlh->nlmsg_len;
	if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen)
		return;

	pid = nlh->nlmsg_pid;
	flags = nlh->nlmsg_flags;

	if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI)
		RCV_SKB_FAIL(-EINVAL);

	if (flags & MSG_TRUNC)
		RCV_SKB_FAIL(-ECOMM);

	type = nlh->nlmsg_type;
	if (type < NLMSG_NOOP || type >= IPQM_MAX)
		RCV_SKB_FAIL(-EINVAL);

	if (type <= IPQM_BASE)
		return;

	if (security_netlink_recv(skb, CAP_NET_ADMIN))
		RCV_SKB_FAIL(-EPERM);

	write_lock_bh(&queue_lock);

	if (peer_pid) {
		if (peer_pid != pid) {
			write_unlock_bh(&queue_lock);
			RCV_SKB_FAIL(-EBUSY);
		}
	} else {
		net_enable_timestamp();
		peer_pid = pid;
	}

	write_unlock_bh(&queue_lock);

	status = ipq_receive_peer(NLMSG_DATA(nlh), type,
				  nlmsglen - NLMSG_LENGTH(0));
	if (status < 0)
		RCV_SKB_FAIL(status);

	if (flags & NLM_F_ACK)
		netlink_ack(skb, nlh, 0);
	return;
}

static void
ipq_rcv_skb(struct sk_buff *skb)
{
	mutex_lock(&ipqnl_mutex);
	__ipq_rcv_skb(skb);
	mutex_unlock(&ipqnl_mutex);
}

static int
ipq_rcv_dev_event(struct notifier_block *this,
		  unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;

	if (dev->nd_net != &init_net)
		return NOTIFY_DONE;

	/* Drop any packets associated with the downed device */
	if (event == NETDEV_DOWN)
		ipq_dev_drop(dev->ifindex);
	return NOTIFY_DONE;
}

static struct notifier_block ipq_dev_notifier = {
	.notifier_call	= ipq_rcv_dev_event,
};

static int
ipq_rcv_nl_event(struct notifier_block *this,
		 unsigned long event, void *ptr)
{
	struct netlink_notify *n = ptr;

	if (event == NETLINK_URELEASE &&
	    n->protocol == NETLINK_FIREWALL && n->pid) {
		write_lock_bh(&queue_lock);
		if ((n->net == &init_net) && (n->pid == peer_pid))
			__ipq_reset();
		write_unlock_bh(&queue_lock);
	}
	return NOTIFY_DONE;
}

static struct notifier_block ipq_nl_notifier = {
	.notifier_call	= ipq_rcv_nl_event,
};

static struct ctl_table_header *ipq_sysctl_header;

static ctl_table ipq_table[] = {
	{
		.ctl_name	= NET_IPQ_QMAX,
		.procname	= NET_IPQ_QMAX_NAME,
		.data		= &queue_maxlen,
		.maxlen		= sizeof(queue_maxlen),
		.mode		= 0644,
		.proc_handler	= proc_dointvec
	},
	{ .ctl_name = 0 }
};

static ctl_table ipq_dir_table[] = {
	{
		.ctl_name	= NET_IPV4,
		.procname	= "ipv4",
		.mode		= 0555,
		.child		= ipq_table
	},
	{ .ctl_name = 0 }
};

static ctl_table ipq_root_table[] = {
	{
		.ctl_name	= CTL_NET,
		.procname	= "net",
		.mode		= 0555,
		.child		= ipq_dir_table
	},
	{ .ctl_name = 0 }
};

static int ip_queue_show(struct seq_file *m, void *v)
{
	read_lock_bh(&queue_lock);

	seq_printf(m,
		      "Peer PID          : %d\n"
		      "Copy mode         : %hu\n"
		      "Copy range        : %u\n"
		      "Queue length      : %u\n"
		      "Queue max. length : %u\n"
		      "Queue dropped     : %u\n"
		      "Netlink dropped   : %u\n",
		      peer_pid,
		      copy_mode,
		      copy_range,
		      queue_total,
		      queue_maxlen,
		      queue_dropped,
		      queue_user_dropped);

	read_unlock_bh(&queue_lock);
	return 0;
}

static int ip_queue_open(struct inode *inode, struct file *file)
{
	return single_open(file, ip_queue_show, NULL);
}

static const struct file_operations ip_queue_proc_fops = {
	.open		= ip_queue_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
	.owner		= THIS_MODULE,
};

static struct nf_queue_handler nfqh = {
	.name	= "ip_queue",
	.outfn	= &ipq_enqueue_packet,
};

static int __init ip_queue_init(void)
{
	int status = -ENOMEM;
	struct proc_dir_entry *proc;

	netlink_register_notifier(&ipq_nl_notifier);
	ipqnl = netlink_kernel_create(&init_net, NETLINK_FIREWALL, 0,
				      ipq_rcv_skb, NULL, THIS_MODULE);
	if (ipqnl == NULL) {
		printk(KERN_ERR "ip_queue: failed to create netlink socket\n");
		goto cleanup_netlink_notifier;
	}

	proc = create_proc_entry(IPQ_PROC_FS_NAME, 0, init_net.proc_net);
	if (proc) {
		proc->owner = THIS_MODULE;
		proc->proc_fops = &ip_queue_proc_fops;
	} else {
		printk(KERN_ERR "ip_queue: failed to create proc entry\n");
		goto cleanup_ipqnl;
	}

	register_netdevice_notifier(&ipq_dev_notifier);
	ipq_sysctl_header = register_sysctl_table(ipq_root_table);

	status = nf_register_queue_handler(PF_INET, &nfqh);
	if (status < 0) {
		printk(KERN_ERR "ip_queue: failed to register queue handler\n");
		goto cleanup_sysctl;
	}
	return status;

cleanup_sysctl:
	unregister_sysctl_table(ipq_sysctl_header);
	unregister_netdevice_notifier(&ipq_dev_notifier);
	proc_net_remove(&init_net, IPQ_PROC_FS_NAME);
cleanup_ipqnl:
	sock_release(ipqnl->sk_socket);
	mutex_lock(&ipqnl_mutex);
	mutex_unlock(&ipqnl_mutex);

cleanup_netlink_notifier:
	netlink_unregister_notifier(&ipq_nl_notifier);
	return status;
}

static void __exit ip_queue_fini(void)
{
	nf_unregister_queue_handlers(&nfqh);
	synchronize_net();
	ipq_flush(NF_DROP);

	unregister_sysctl_table(ipq_sysctl_header);
	unregister_netdevice_notifier(&ipq_dev_notifier);
	proc_net_remove(&init_net, IPQ_PROC_FS_NAME);

	sock_release(ipqnl->sk_socket);
	mutex_lock(&ipqnl_mutex);
	mutex_unlock(&ipqnl_mutex);

	netlink_unregister_notifier(&ipq_nl_notifier);
}

MODULE_DESCRIPTION("IPv4 packet queue handler");
MODULE_AUTHOR("James Morris <[e-mail]>");
MODULE_LICENSE("GPL");

module_init(ip_queue_init);
module_exit(ip_queue_fini);