ipv6.c

linux 内核源代码

	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;

	req = inet6_reqsk_alloc(&dccp6_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;

	ireq6 = inet6_rsk(req);
	ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
	ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
	ireq6->pktopts	= NULL;

	if (ipv6_opt_accepted(sk, skb) ||
	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
		atomic_inc(&skb->users);
		ireq6->pktopts = skb;
	}
	ireq6->iif = sk->sk_bound_dev_if;

	/* So that link locals have meaning */
	if (!sk->sk_bound_dev_if &&
	    ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL)
		ireq6->iif = inet6_iif(skb);

	/*
	 * 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_v6_init_sequence(skb);
	dreq->dreq_service = service;

	if (dccp_v6_send_response(sk, req, NULL))
		goto drop_and_free;

	inet6_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;
}

static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
					      struct sk_buff *skb,
					      struct request_sock *req,
					      struct dst_entry *dst)
{
	struct inet6_request_sock *ireq6 = inet6_rsk(req);
	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
	struct inet_sock *newinet;
	struct dccp_sock *newdp;
	struct dccp6_sock *newdp6;
	struct sock *newsk;
	struct ipv6_txoptions *opt;

	if (skb->protocol == htons(ETH_P_IP)) {
		/*
		 *	v6 mapped
		 */
		newsk = dccp_v4_request_recv_sock(sk, skb, req, dst);
		if (newsk == NULL)
			return NULL;

		newdp6 = (struct dccp6_sock *)newsk;
		newdp = dccp_sk(newsk);
		newinet = inet_sk(newsk);
		newinet->pinet6 = &newdp6->inet6;
		newnp = inet6_sk(newsk);

		memcpy(newnp, np, sizeof(struct ipv6_pinfo));

		ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
			      newinet->daddr);

		ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
			      newinet->saddr);

		ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);

		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
		newnp->pktoptions  = NULL;
		newnp->opt	   = NULL;
		newnp->mcast_oif   = inet6_iif(skb);
		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;

		/*
		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
		 * here, dccp_create_openreq_child now does this for us, see the comment in
		 * that function for the gory details. -acme
		 */

		/* It is tricky place. Until this moment IPv4 tcp
		   worked with IPv6 icsk.icsk_af_ops.
		   Sync it now.
		 */
		dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);

		return newsk;
	}

	opt = np->opt;

	if (sk_acceptq_is_full(sk))
		goto out_overflow;

	if (dst == NULL) {
		struct in6_addr *final_p = NULL, final;
		struct flowi fl;

		memset(&fl, 0, sizeof(fl));
		fl.proto = IPPROTO_DCCP;
		ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr);
		if (opt != NULL && opt->srcrt != NULL) {
			const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt;

			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}
		ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr);
		fl.oif = sk->sk_bound_dev_if;
		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
		fl.fl_ip_sport = inet_sk(sk)->sport;
		security_sk_classify_flow(sk, &fl);

		if (ip6_dst_lookup(sk, &dst, &fl))
			goto out;

		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
			goto out;
	}

	newsk = dccp_create_openreq_child(sk, req, skb);
	if (newsk == NULL)
		goto out;

	/*
	 * No need to charge this sock to the relevant IPv6 refcnt debug socks
	 * count here, dccp_create_openreq_child now does this for us, see the
	 * comment in that function for the gory details. -acme
	 */

	__ip6_dst_store(newsk, dst, NULL, NULL);
	newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
						      NETIF_F_TSO);
	newdp6 = (struct dccp6_sock *)newsk;
	newinet = inet_sk(newsk);
	newinet->pinet6 = &newdp6->inet6;
	newdp = dccp_sk(newsk);
	newnp = inet6_sk(newsk);

	memcpy(newnp, np, sizeof(struct ipv6_pinfo));

	ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr);
	ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr);
	ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr);
	newsk->sk_bound_dev_if = ireq6->iif;

	/* Now IPv6 options...

	   First: no IPv4 options.
	 */
	newinet->opt = NULL;

	/* Clone RX bits */
	newnp->rxopt.all = np->rxopt.all;

	/* Clone pktoptions received with SYN */
	newnp->pktoptions = NULL;
	if (ireq6->pktopts != NULL) {
		newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
		kfree_skb(ireq6->pktopts);
		ireq6->pktopts = NULL;
		if (newnp->pktoptions)
			skb_set_owner_r(newnp->pktoptions, newsk);
	}
	newnp->opt	  = NULL;
	newnp->mcast_oif  = inet6_iif(skb);
	newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;

	/*
	 * Clone native IPv6 options from listening socket (if any)
	 *
	 * Yes, keeping reference count would be much more clever, but we make
	 * one more one thing there: reattach optmem to newsk.
	 */
	if (opt != NULL) {
		newnp->opt = ipv6_dup_options(newsk, opt);
		if (opt != np->opt)
			sock_kfree_s(sk, opt, opt->tot_len);
	}

	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (newnp->opt != NULL)
		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
						     newnp->opt->opt_flen);

	dccp_sync_mss(newsk, dst_mtu(dst));

	newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;

	__inet6_hash(&dccp_hashinfo, newsk);
	inet_inherit_port(&dccp_hashinfo, sk, newsk);

	return newsk;

out_overflow:
	NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
out:
	NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
	if (opt != NULL && opt != np->opt)
		sock_kfree_s(sk, opt, opt->tot_len);
	dst_release(dst);
	return NULL;
}

/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff *opt_skb = NULL;

	/* Imagine: socket is IPv6. IPv4 packet arrives,
	   goes to IPv4 receive handler and backlogged.
	   From backlog it always goes here. Kerboom...
	   Fortunately, dccp_rcv_established and rcv_established
	   handle them correctly, but it is not case with
	   dccp_v6_hnd_req and dccp_v6_ctl_send_reset().   --ANK
	 */

	if (skb->protocol == htons(ETH_P_IP))
		return dccp_v4_do_rcv(sk, skb);

	if (sk_filter(sk, skb))
		goto discard;

	/*
	 * socket locking is here for SMP purposes as backlog rcv is currently
	 * called with bh processing disabled.
	 */

	/* Do Stevens' IPV6_PKTOPTIONS.

	   Yes, guys, it is the only place in our code, where we
	   may make it not affecting IPv4.
	   The rest of code is protocol independent,
	   and I do not like idea to uglify IPv4.

	   Actually, all the idea behind IPV6_PKTOPTIONS
	   looks not very well thought. For now we latch
	   options, received in the last packet, enqueued
	   by tcp. Feel free to propose better solution.
					       --ANK (980728)
	 */
	if (np->rxopt.all)
	/*
	 * FIXME: Add handling of IPV6_PKTOPTIONS skb. See the comments below
	 *        (wrt ipv6_pktopions) and net/ipv6/tcp_ipv6.c for an example.
	 */
		opt_skb = skb_clone(skb, GFP_ATOMIC);

	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
		if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))
			goto reset;
		if (opt_skb) {
			/* XXX This is where we would goto ipv6_pktoptions. */
			__kfree_skb(opt_skb);
		}
		return 0;
	}

	/*
	 *  Step 3: Process LISTEN state
	 *     If S.state == LISTEN,
	 *	 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_v6_hnd_req(sk, skb);

		if (nsk == NULL)
			goto discard;
		/*
		 * Queue it on the new socket if the new socket is active,
		 * otherwise we just shortcircuit this and continue with
		 * the new socket..
		 */
		if (nsk != sk) {
			if (dccp_child_process(sk, nsk, skb))
				goto reset;
			if (opt_skb != NULL)
				__kfree_skb(opt_skb);
			return 0;
		}
	}

	if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len))
		goto reset;
	if (opt_skb) {
		/* XXX This is where we would goto ipv6_pktoptions. */
		__kfree_skb(opt_skb);
	}
	return 0;

reset:
	dccp_v6_ctl_send_reset(sk, skb);
discard:
	if (opt_skb != NULL)
		__kfree_skb(opt_skb);
	kfree_skb(skb);
	return 0;
}

static int dccp_v6_rcv(struct sk_buff *skb)
{
	const struct dccp_hdr *dh;
	struct sock *sk;
	int min_cov;

	/* Step 1: Check header basics */

	if (dccp_invalid_packet(skb))
		goto discard_it;

	/* Step 1: If header checksum is incorrect, drop packet and return. */
	if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr,
				     &ipv6_hdr(skb)->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;

	if (dccp_packet_without_ack(skb))
		DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
	else
		DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);

	/* Step 2:
	 *	Look up flow ID in table and get corresponding socket */
	sk = __inet6_lookup(&dccp_hashinfo, &ipv6_hdr(skb)->saddr,
			    dh->dccph_sport,
			    &ipv6_hdr(skb)->daddr, ntohs(dh->dccph_dport),
			    inet6_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) {