ipv4.c

linux 内核源代码

	if (dst == NULL)
		return;

	skb = dccp_ctl_make_reset(dccp_v4_ctl_socket, rxskb);
	if (skb == NULL)
		goto out;

	rxiph = ip_hdr(rxskb);
	dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr,
								 rxiph->daddr);
	skb->dst = dst_clone(dst);

	bh_lock_sock(dccp_v4_ctl_socket->sk);
	err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk,
				    rxiph->daddr, rxiph->saddr, NULL);
	bh_unlock_sock(dccp_v4_ctl_socket->sk);

	if (net_xmit_eval(err) == 0) {
		DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
		DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
	}
out:
	 dst_release(dst);
}

static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
	kfree(inet_rsk(req)->opt);
}

static struct request_sock_ops dccp_request_sock_ops __read_mostly = {
	.family		= PF_INET,
	.obj_size	= sizeof(struct dccp_request_sock),
	.rtx_syn_ack	= dccp_v4_send_response,
	.send_ack	= dccp_reqsk_send_ack,
	.destructor	= dccp_v4_reqsk_destructor,
	.send_reset	= dccp_v4_ctl_send_reset,
};

int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct inet_request_sock *ireq;
	struct request_sock *req;
	struct dccp_request_sock *dreq;
	const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
	struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);

	/* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */
	if (((struct rtable *)skb->dst)->rt_flags &
	    (RTCF_BROADCAST | RTCF_MULTICAST))
		return 0;	/* discard, don't send a reset here */

	if (dccp_bad_service_code(sk, service)) {
		dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
		goto drop;
	}
	/*
	 * TW buckets are converted to open requests without
	 * limitations, they conserve resources and peer is
	 * evidently real one.
	 */
	dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
	if (inet_csk_reqsk_queue_is_full(sk))
		goto drop;

	/*
	 * Accept backlog is full. If we have already queued enough
	 * of warm entries in syn queue, drop request. It is better than
	 * clogging syn queue with openreqs with exponentially increasing
	 * timeout.
	 */
	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;

	req = reqsk_alloc(&dccp_request_sock_ops);
	if (req == NULL)
		goto drop;

	if (dccp_parse_options(sk, skb))
		goto drop_and_free;

	dccp_reqsk_init(req, skb);

	if (security_inet_conn_request(sk, skb, req))
		goto drop_and_free;

	ireq = inet_rsk(req);
	ireq->loc_addr = ip_hdr(skb)->daddr;
	ireq->rmt_addr = ip_hdr(skb)->saddr;
	ireq->opt	= NULL;

	/*
	 * Step 3: Process LISTEN state
	 *
	 * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
	 *
	 * In fact we defer setting S.GSR, S.SWL, S.SWH to
	 * dccp_create_openreq_child.
	 */
	dreq = dccp_rsk(req);
	dreq->dreq_isr	   = dcb->dccpd_seq;
	dreq->dreq_iss	   = dccp_v4_init_sequence(skb);
	dreq->dreq_service = service;

	if (dccp_v4_send_response(sk, req, NULL))
		goto drop_and_free;

	inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
	return 0;

drop_and_free:
	reqsk_free(req);
drop:
	DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
	return -1;
}

EXPORT_SYMBOL_GPL(dccp_v4_conn_request);

int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_hdr *dh = dccp_hdr(skb);

	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
		if (dccp_rcv_established(sk, skb, dh, skb->len))
			goto reset;
		return 0;
	}

	/*
	 *  Step 3: Process LISTEN state
	 *	 If P.type == Request or P contains a valid Init Cookie option,
	 *	      (* Must scan the packet's options to check for Init
	 *		 Cookies.  Only Init Cookies are processed here,
	 *		 however; other options are processed in Step 8.  This
	 *		 scan need only be performed if the endpoint uses Init
	 *		 Cookies *)
	 *	      (* Generate a new socket and switch to that socket *)
	 *	      Set S := new socket for this port pair
	 *	      S.state = RESPOND
	 *	      Choose S.ISS (initial seqno) or set from Init Cookies
	 *	      Initialize S.GAR := S.ISS
	 *	      Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
	 *	      Continue with S.state == RESPOND
	 *	      (* A Response packet will be generated in Step 11 *)
	 *	 Otherwise,
	 *	      Generate Reset(No Connection) unless P.type == Reset
	 *	      Drop packet and return
	 *
	 * NOTE: the check for the packet types is done in
	 *	 dccp_rcv_state_process
	 */
	if (sk->sk_state == DCCP_LISTEN) {
		struct sock *nsk = dccp_v4_hnd_req(sk, skb);

		if (nsk == NULL)
			goto discard;

		if (nsk != sk) {
			if (dccp_child_process(sk, nsk, skb))
				goto reset;
			return 0;
		}
	}

	if (dccp_rcv_state_process(sk, skb, dh, skb->len))
		goto reset;
	return 0;

reset:
	dccp_v4_ctl_send_reset(sk, skb);
discard:
	kfree_skb(skb);
	return 0;
}

EXPORT_SYMBOL_GPL(dccp_v4_do_rcv);

/**
 *	dccp_invalid_packet  -  check for malformed packets
 *	Implements RFC 4340, 8.5:  Step 1: Check header basics
 *	Packets that fail these checks are ignored and do not receive Resets.
 */
int dccp_invalid_packet(struct sk_buff *skb)
{
	const struct dccp_hdr *dh;
	unsigned int cscov;

	if (skb->pkt_type != PACKET_HOST)
		return 1;

	/* If the packet is shorter than 12 bytes, drop packet and return */
	if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) {
		DCCP_WARN("pskb_may_pull failed\n");
		return 1;
	}

	dh = dccp_hdr(skb);

	/* If P.type is not understood, drop packet and return */
	if (dh->dccph_type >= DCCP_PKT_INVALID) {
		DCCP_WARN("invalid packet type\n");
		return 1;
	}

	/*
	 * If P.Data Offset is too small for packet type, drop packet and return
	 */
	if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
		DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff);
		return 1;
	}
	/*
	 * If P.Data Offset is too too large for packet, drop packet and return
	 */
	if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) {
		DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff);
		return 1;
	}

	/*
	 * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
	 * has short sequence numbers), drop packet and return
	 */
	if (dh->dccph_type >= DCCP_PKT_DATA    &&
	    dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0)  {
		DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
			  dccp_packet_name(dh->dccph_type));
		return 1;
	}

	/*
	 * If P.CsCov is too large for the packet size, drop packet and return.
	 * This must come _before_ checksumming (not as RFC 4340 suggests).
	 */
	cscov = dccp_csum_coverage(skb);
	if (cscov > skb->len) {
		DCCP_WARN("P.CsCov %u exceeds packet length %d\n",
			  dh->dccph_cscov, skb->len);
		return 1;
	}

	/* If header checksum is incorrect, drop packet and return.
	 * (This step is completed in the AF-dependent functions.) */
	skb->csum = skb_checksum(skb, 0, cscov, 0);

	return 0;
}

EXPORT_SYMBOL_GPL(dccp_invalid_packet);

/* this is called when real data arrives */
static int dccp_v4_rcv(struct sk_buff *skb)
{
	const struct dccp_hdr *dh;
	const struct iphdr *iph;
	struct sock *sk;
	int min_cov;

	/* Step 1: Check header basics */

	if (dccp_invalid_packet(skb))
		goto discard_it;

	iph = ip_hdr(skb);
	/* Step 1: If header checksum is incorrect, drop packet and return */
	if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) {
		DCCP_WARN("dropped packet with invalid checksum\n");
		goto discard_it;
	}

	dh = dccp_hdr(skb);

	DCCP_SKB_CB(skb)->dccpd_seq  = dccp_hdr_seq(dh);
	DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type;

	dccp_pr_debug("%8.8s "
		      "src=%u.%u.%u.%u@%-5d "
		      "dst=%u.%u.%u.%u@%-5d seq=%llu",
		      dccp_packet_name(dh->dccph_type),
		      NIPQUAD(iph->saddr), ntohs(dh->dccph_sport),
		      NIPQUAD(iph->daddr), ntohs(dh->dccph_dport),
		      (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq);

	if (dccp_packet_without_ack(skb)) {
		DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
		dccp_pr_debug_cat("\n");
	} else {
		DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
		dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long)
				  DCCP_SKB_CB(skb)->dccpd_ack_seq);
	}

	/* Step 2:
	 *	Look up flow ID in table and get corresponding socket */
	sk = __inet_lookup(&dccp_hashinfo,
			   iph->saddr, dh->dccph_sport,
			   iph->daddr, dh->dccph_dport, inet_iif(skb));
	/*
	 * Step 2:
	 *	If no socket ...
	 */
	if (sk == NULL) {
		dccp_pr_debug("failed to look up flow ID in table and "
			      "get corresponding socket\n");
		goto no_dccp_socket;
	}

	/*
	 * Step 2:
	 *	... or S.state == TIMEWAIT,
	 *		Generate Reset(No Connection) unless P.type == Reset
	 *		Drop packet and return
	 */
	if (sk->sk_state == DCCP_TIME_WAIT) {
		dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
		inet_twsk_put(inet_twsk(sk));
		goto no_dccp_socket;
	}

	/*
	 * RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
	 *	o if MinCsCov = 0, only packets with CsCov = 0 are accepted
	 *	o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
	 */
	min_cov = dccp_sk(sk)->dccps_pcrlen;
	if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov))  {
		dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
			      dh->dccph_cscov, min_cov);
		/* FIXME: "Such packets SHOULD be reported using Data Dropped
		 *         options (Section 11.7) with Drop Code 0, Protocol
		 *         Constraints."                                     */
		goto discard_and_relse;
	}

	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;
	nf_reset(skb);

	return sk_receive_skb(sk, skb, 1);

no_dccp_socket:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;
	/*
	 * Step 2:
	 *	If no socket ...
	 *		Generate Reset(No Connection) unless P.type == Reset
	 *		Drop packet and return
	 */
	if (dh->dccph_type != DCCP_PKT_RESET) {
		DCCP_SKB_CB(skb)->dccpd_reset_code =
					DCCP_RESET_CODE_NO_CONNECTION;
		dccp_v4_ctl_send_reset(sk, skb);
	}

discard_it:
	kfree_skb(skb);
	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;
}

static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
	.queue_xmit	   = ip_queue_xmit,
	.send_check	   = dccp_v4_send_check,
	.rebuild_header	   = inet_sk_rebuild_header,
	.conn_request	   = dccp_v4_conn_request,
	.syn_recv_sock	   = dccp_v4_request_recv_sock,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
};

static int dccp_v4_init_sock(struct sock *sk)
{
	static __u8 dccp_v4_ctl_sock_initialized;
	int err = dccp_init_sock(sk, dccp_v4_ctl_sock_initialized);

	if (err == 0) {
		if (unlikely(!dccp_v4_ctl_sock_initialized))
			dccp_v4_ctl_sock_initialized = 1;
		inet_csk(sk)->icsk_af_ops = &dccp_ipv4_af_ops;
	}

	return err;
}

static struct timewait_sock_ops dccp_timewait_sock_ops = {
	.twsk_obj_size	= sizeof(struct inet_timewait_sock),
};

DEFINE_PROTO_INUSE(dccp_v4)

static struct proto dccp_v4_prot = {
	.name			= "DCCP",
	.owner			= THIS_MODULE,
	.close			= dccp_close,
	.connect		= dccp_v4_connect,
	.disconnect		= dccp_disconnect,
	.ioctl			= dccp_ioctl,
	.init			= dccp_v4_init_sock,
	.setsockopt		= dccp_setsockopt,
	.getsockopt		= dccp_getsockopt,
	.sendmsg		= dccp_sendmsg,
	.recvmsg		= dccp_recvmsg,
	.backlog_rcv		= dccp_v4_do_rcv,
	.hash			= dccp_hash,
	.unhash			= dccp_unhash,
	.accept			= inet_csk_accept,
	.get_port		= dccp_v4_get_port,
	.shutdown		= dccp_shutdown,
	.destroy		= dccp_destroy_sock,
	.orphan_count		= &dccp_orphan_count,
	.max_header		= MAX_DCCP_HEADER,
	.obj_size		= sizeof(struct dccp_sock),
	.rsk_prot		= &dccp_request_sock_ops,
	.twsk_prot		= &dccp_timewait_sock_ops,
#ifdef CONFIG_COMPAT
	.compat_setsockopt	= compat_dccp_setsockopt,
	.compat_getsockopt	= compat_dccp_getsockopt,
#endif
	REF_PROTO_INUSE(dccp_v4)
};

static struct net_protocol dccp_v4_protocol = {
	.handler	= dccp_v4_rcv,
	.err_handler	= dccp_v4_err,
	.no_policy	= 1,
};

static const struct proto_ops inet_dccp_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,
	/* FIXME: work on tcp_poll to rename it to inet_csk_poll */
	.poll		   = dccp_poll,
	.ioctl		   = inet_ioctl,
	/* FIXME: work on inet_listen to rename it to sock_common_listen */
	.listen		   = inet_dccp_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = sock_no_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

static struct inet_protosw dccp_v4_protosw = {
	.type		= SOCK_DCCP,
	.protocol	= IPPROTO_DCCP,
	.prot		= &dccp_v4_prot,
	.ops		= &inet_dccp_ops,
	.capability	= -1,
	.no_check	= 0,
	.flags		= INET_PROTOSW_ICSK,
};

static int __init dccp_v4_init(void)
{
	int err = proto_register(&dccp_v4_prot, 1);

	if (err != 0)
		goto out;

	err = inet_add_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
	if (err != 0)
		goto out_proto_unregister;

	inet_register_protosw(&dccp_v4_protosw);

	err = inet_csk_ctl_sock_create(&dccp_v4_ctl_socket, PF_INET,
				       SOCK_DCCP, IPPROTO_DCCP);
	if (err)
		goto out_unregister_protosw;
out:
	return err;
out_unregister_protosw:
	inet_unregister_protosw(&dccp_v4_protosw);
	inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
out_proto_unregister:
	proto_unregister(&dccp_v4_prot);
	goto out;
}

static void __exit dccp_v4_exit(void)
{
	inet_unregister_protosw(&dccp_v4_protosw);
	inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP);
	proto_unregister(&dccp_v4_prot);
}

module_init(dccp_v4_init);
module_exit(dccp_v4_exit);

/*
 * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33)
 * values directly, Also cover the case where the protocol is not specified,
 * i.e. net-pf-PF_INET-proto-0-type-SOCK_DCCP
 */
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 33, 6);
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 0, 6);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <[e-mail]>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");