inet_diag.c

linux 内核源代码

			    !valid_cc(bytecode, bytecode_len, len - op->no))
				return -EINVAL;
			break;
		case INET_DIAG_BC_NOP:
			if (op->yes < 4 || op->yes > len + 4)
				return -EINVAL;
			break;
		default:
			return -EINVAL;
		}
		bc  += op->yes;
		len -= op->yes;
	}
	return len == 0 ? 0 : -EINVAL;
}

static int inet_csk_diag_dump(struct sock *sk,
			      struct sk_buff *skb,
			      struct netlink_callback *cb)
{
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);

	if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
		struct inet_diag_entry entry;
		struct rtattr *bc = (struct rtattr *)(r + 1);
		struct inet_sock *inet = inet_sk(sk);

		entry.family = sk->sk_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		if (entry.family == AF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(sk);

			entry.saddr = np->rcv_saddr.s6_addr32;
			entry.daddr = np->daddr.s6_addr32;
		} else
#endif
		{
			entry.saddr = &inet->rcv_saddr;
			entry.daddr = &inet->daddr;
		}
		entry.sport = inet->num;
		entry.dport = ntohs(inet->dport);
		entry.userlocks = sk->sk_userlocks;

		if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
			return 0;
	}

	return inet_csk_diag_fill(sk, skb, r->idiag_ext,
				  NETLINK_CB(cb->skb).pid,
				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}

static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
			       struct sk_buff *skb,
			       struct netlink_callback *cb)
{
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);

	if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
		struct inet_diag_entry entry;
		struct rtattr *bc = (struct rtattr *)(r + 1);

		entry.family = tw->tw_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		if (tw->tw_family == AF_INET6) {
			struct inet6_timewait_sock *tw6 =
						inet6_twsk((struct sock *)tw);
			entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
			entry.daddr = tw6->tw_v6_daddr.s6_addr32;
		} else
#endif
		{
			entry.saddr = &tw->tw_rcv_saddr;
			entry.daddr = &tw->tw_daddr;
		}
		entry.sport = tw->tw_num;
		entry.dport = ntohs(tw->tw_dport);
		entry.userlocks = 0;

		if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry))
			return 0;
	}

	return inet_twsk_diag_fill(tw, skb, r->idiag_ext,
				   NETLINK_CB(cb->skb).pid,
				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}

static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
			      struct request_sock *req, u32 pid, u32 seq,
			      const struct nlmsghdr *unlh)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct inet_sock *inet = inet_sk(sk);
	unsigned char *b = skb_tail_pointer(skb);
	struct inet_diag_msg *r;
	struct nlmsghdr *nlh;
	long tmo;

	nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
	nlh->nlmsg_flags = NLM_F_MULTI;
	r = NLMSG_DATA(nlh);

	r->idiag_family = sk->sk_family;
	r->idiag_state = TCP_SYN_RECV;
	r->idiag_timer = 1;
	r->idiag_retrans = req->retrans;

	r->id.idiag_if = sk->sk_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)req;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1);

	tmo = req->expires - jiffies;
	if (tmo < 0)
		tmo = 0;

	r->id.idiag_sport = inet->sport;
	r->id.idiag_dport = ireq->rmt_port;
	r->id.idiag_src[0] = ireq->loc_addr;
	r->id.idiag_dst[0] = ireq->rmt_addr;
	r->idiag_expires = jiffies_to_msecs(tmo);
	r->idiag_rqueue = 0;
	r->idiag_wqueue = 0;
	r->idiag_uid = sock_i_uid(sk);
	r->idiag_inode = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (r->idiag_family == AF_INET6) {
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &inet6_rsk(req)->loc_addr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &inet6_rsk(req)->rmt_addr);
	}
#endif
	nlh->nlmsg_len = skb_tail_pointer(skb) - b;

	return skb->len;

nlmsg_failure:
	nlmsg_trim(skb, b);
	return -1;
}

static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
			       struct netlink_callback *cb)
{
	struct inet_diag_entry entry;
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct listen_sock *lopt;
	struct rtattr *bc = NULL;
	struct inet_sock *inet = inet_sk(sk);
	int j, s_j;
	int reqnum, s_reqnum;
	int err = 0;

	s_j = cb->args[3];
	s_reqnum = cb->args[4];

	if (s_j > 0)
		s_j--;

	entry.family = sk->sk_family;

	read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);

	lopt = icsk->icsk_accept_queue.listen_opt;
	if (!lopt || !lopt->qlen)
		goto out;

	if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) {
		bc = (struct rtattr *)(r + 1);
		entry.sport = inet->num;
		entry.userlocks = sk->sk_userlocks;
	}

	for (j = s_j; j < lopt->nr_table_entries; j++) {
		struct request_sock *req, *head = lopt->syn_table[j];

		reqnum = 0;
		for (req = head; req; reqnum++, req = req->dl_next) {
			struct inet_request_sock *ireq = inet_rsk(req);

			if (reqnum < s_reqnum)
				continue;
			if (r->id.idiag_dport != ireq->rmt_port &&
			    r->id.idiag_dport)
				continue;

			if (bc) {
				entry.saddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
					(entry.family == AF_INET6) ?
					inet6_rsk(req)->loc_addr.s6_addr32 :
#endif
					&ireq->loc_addr;
				entry.daddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
					(entry.family == AF_INET6) ?
					inet6_rsk(req)->rmt_addr.s6_addr32 :
#endif
					&ireq->rmt_addr;
				entry.dport = ntohs(ireq->rmt_port);

				if (!inet_diag_bc_run(RTA_DATA(bc),
						    RTA_PAYLOAD(bc), &entry))
					continue;
			}

			err = inet_diag_fill_req(skb, sk, req,
					       NETLINK_CB(cb->skb).pid,
					       cb->nlh->nlmsg_seq, cb->nlh);
			if (err < 0) {
				cb->args[3] = j + 1;
				cb->args[4] = reqnum;
				goto out;
			}
		}

		s_reqnum = 0;
	}

out:
	read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);

	return err;
}

static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	int i, num;
	int s_i, s_num;
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
	const struct inet_diag_handler *handler;
	struct inet_hashinfo *hashinfo;

	handler = inet_diag_lock_handler(cb->nlh->nlmsg_type);
	if (!handler)
		goto no_handler;

	hashinfo = handler->idiag_hashinfo;

	s_i = cb->args[1];
	s_num = num = cb->args[2];

	if (cb->args[0] == 0) {
		if (!(r->idiag_states & (TCPF_LISTEN | TCPF_SYN_RECV)))
			goto skip_listen_ht;

		inet_listen_lock(hashinfo);
		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
			struct sock *sk;
			struct hlist_node *node;

			num = 0;
			sk_for_each(sk, node, &hashinfo->listening_hash[i]) {
				struct inet_sock *inet = inet_sk(sk);

				if (num < s_num) {
					num++;
					continue;
				}

				if (r->id.idiag_sport != inet->sport &&
				    r->id.idiag_sport)
					goto next_listen;

				if (!(r->idiag_states & TCPF_LISTEN) ||
				    r->id.idiag_dport ||
				    cb->args[3] > 0)
					goto syn_recv;

				if (inet_csk_diag_dump(sk, skb, cb) < 0) {
					inet_listen_unlock(hashinfo);
					goto done;
				}

syn_recv:
				if (!(r->idiag_states & TCPF_SYN_RECV))
					goto next_listen;

				if (inet_diag_dump_reqs(skb, sk, cb) < 0) {
					inet_listen_unlock(hashinfo);
					goto done;
				}

next_listen:
				cb->args[3] = 0;
				cb->args[4] = 0;
				++num;
			}

			s_num = 0;
			cb->args[3] = 0;
			cb->args[4] = 0;
		}
		inet_listen_unlock(hashinfo);
skip_listen_ht:
		cb->args[0] = 1;
		s_i = num = s_num = 0;
	}

	if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV)))
		goto unlock;

	for (i = s_i; i < hashinfo->ehash_size; i++) {
		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
		rwlock_t *lock = inet_ehash_lockp(hashinfo, i);
		struct sock *sk;
		struct hlist_node *node;

		if (i > s_i)
			s_num = 0;

		read_lock_bh(lock);
		num = 0;
		sk_for_each(sk, node, &head->chain) {
			struct inet_sock *inet = inet_sk(sk);

			if (num < s_num)
				goto next_normal;
			if (!(r->idiag_states & (1 << sk->sk_state)))
				goto next_normal;
			if (r->id.idiag_sport != inet->sport &&
			    r->id.idiag_sport)
				goto next_normal;
			if (r->id.idiag_dport != inet->dport &&
			    r->id.idiag_dport)
				goto next_normal;
			if (inet_csk_diag_dump(sk, skb, cb) < 0) {
				read_unlock_bh(lock);
				goto done;
			}
next_normal:
			++num;
		}

		if (r->idiag_states & TCPF_TIME_WAIT) {
			struct inet_timewait_sock *tw;

			inet_twsk_for_each(tw, node,
				    &head->twchain) {

				if (num < s_num)
					goto next_dying;
				if (r->id.idiag_sport != tw->tw_sport &&
				    r->id.idiag_sport)
					goto next_dying;
				if (r->id.idiag_dport != tw->tw_dport &&
				    r->id.idiag_dport)
					goto next_dying;
				if (inet_twsk_diag_dump(tw, skb, cb) < 0) {
					read_unlock_bh(lock);
					goto done;
				}
next_dying:
				++num;
			}
		}
		read_unlock_bh(lock);
	}

done:
	cb->args[1] = i;
	cb->args[2] = num;
unlock:
	inet_diag_unlock_handler(handler);
no_handler:
	return skb->len;
}

static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	int hdrlen = sizeof(struct inet_diag_req);

	if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
	    nlmsg_len(nlh) < hdrlen)
		return -EINVAL;

	if (nlh->nlmsg_flags & NLM_F_DUMP) {
		if (nlmsg_attrlen(nlh, hdrlen)) {
			struct nlattr *attr;

			attr = nlmsg_find_attr(nlh, hdrlen,
					       INET_DIAG_REQ_BYTECODE);
			if (attr == NULL ||
			    nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
			    inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
				return -EINVAL;
		}

		return netlink_dump_start(idiagnl, skb, nlh,
					  inet_diag_dump, NULL);
	}

	return inet_diag_get_exact(skb, nlh);
}

static DEFINE_MUTEX(inet_diag_mutex);

static void inet_diag_rcv(struct sk_buff *skb)
{
	mutex_lock(&inet_diag_mutex);
	netlink_rcv_skb(skb, &inet_diag_rcv_msg);
	mutex_unlock(&inet_diag_mutex);
}

int inet_diag_register(const struct inet_diag_handler *h)
{
	const __u16 type = h->idiag_type;
	int err = -EINVAL;

	if (type >= INET_DIAG_GETSOCK_MAX)
		goto out;

	mutex_lock(&inet_diag_table_mutex);
	err = -EEXIST;
	if (inet_diag_table[type] == NULL) {
		inet_diag_table[type] = h;
		err = 0;
	}
	mutex_unlock(&inet_diag_table_mutex);
out:
	return err;
}
EXPORT_SYMBOL_GPL(inet_diag_register);

void inet_diag_unregister(const struct inet_diag_handler *h)
{
	const __u16 type = h->idiag_type;

	if (type >= INET_DIAG_GETSOCK_MAX)
		return;

	mutex_lock(&inet_diag_table_mutex);
	inet_diag_table[type] = NULL;
	mutex_unlock(&inet_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(inet_diag_unregister);

static int __init inet_diag_init(void)
{
	const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX *
					  sizeof(struct inet_diag_handler *));
	int err = -ENOMEM;

	inet_diag_table = kzalloc(inet_diag_table_size, GFP_KERNEL);
	if (!inet_diag_table)
		goto out;

	idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0,
					inet_diag_rcv, NULL, THIS_MODULE);
	if (idiagnl == NULL)
		goto out_free_table;
	err = 0;
out:
	return err;
out_free_table:
	kfree(inet_diag_table);
	goto out;
}

static void __exit inet_diag_exit(void)
{
	sock_release(idiagnl->sk_socket);
	kfree(inet_diag_table);
}

module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG);