protocol.c

在linux环境下的流控制传输协议（sctp）的源代码

	/* If there is no association or if a source address is passed, no
	 * more validation is required.
	 */
	if (!asoc || saddr)
		goto out;

	bp = &asoc->base.bind_addr;

	if (dst) {
		/* Walk through the bind address list and look for a bind
		 * address that matches the source address of the returned dst.
		 */
		rcu_read_lock();
		list_for_each_entry_rcu(laddr, &bp->address_list, list) {
			if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC))
				continue;
			sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port));
			if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a))
				goto out_unlock;
		}
		rcu_read_unlock();

		/* None of the bound addresses match the source address of the
		 * dst. So release it.
		 */
		dst_release(dst);
		dst = NULL;
	}

	/* Walk through the bind address list and try to get a dst that
	 * matches a bind address as the source address.
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(laddr, &bp->address_list, list) {
		if (!laddr->valid)
			continue;
		if ((laddr->state == SCTP_ADDR_SRC) &&
		    (AF_INET == laddr->a.sa.sa_family)) {
			fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
			if (!ip_route_output_key(&init_net, &rt, &fl)) {
				dst = &rt->u.dst;
				goto out_unlock;
			}
		}
	}

out_unlock:
	rcu_read_unlock();
out:
	if (dst)
		SCTP_DEBUG_PRINTK("rt_dst:%u.%u.%u.%u, rt_src:%u.%u.%u.%u\n",
				  NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_src));
	else
		SCTP_DEBUG_PRINTK("NO ROUTE\n");

	return dst;
}

/* For v4, the source address is cached in the route entry(dst). So no need
 * to cache it separately and hence this is an empty routine.
 */
static void sctp_v4_get_saddr(struct sctp_association *asoc,
			      struct dst_entry *dst,
			      union sctp_addr *daddr,
			      union sctp_addr *saddr)
{
	struct rtable *rt = (struct rtable *)dst;

	if (!asoc)
		return;

	if (rt) {
		saddr->v4.sin_family = AF_INET;
		saddr->v4.sin_port = htons(asoc->base.bind_addr.port);
		saddr->v4.sin_addr.s_addr = rt->rt_src;
	}
}

/* What interface did this skb arrive on? */
static int sctp_v4_skb_iif(const struct sk_buff *skb)
{
	return ((struct rtable *)skb->dst)->rt_iif;
}

/* Was this packet marked by Explicit Congestion Notification? */
static int sctp_v4_is_ce(const struct sk_buff *skb)
{
	return INET_ECN_is_ce(ip_hdr(skb)->tos);
}

/* Create and initialize a new sk for the socket returned by accept(). */
static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
					     struct sctp_association *asoc)
{
	struct inet_sock *inet = inet_sk(sk);
	struct inet_sock *newinet;
	struct sock *newsk = sk_alloc(sk->sk_net, PF_INET, GFP_KERNEL,
			sk->sk_prot);

	if (!newsk)
		goto out;

	sock_init_data(NULL, newsk);

	newsk->sk_type = SOCK_STREAM;

	newsk->sk_no_check = sk->sk_no_check;
	newsk->sk_reuse = sk->sk_reuse;
	newsk->sk_shutdown = sk->sk_shutdown;

	newsk->sk_destruct = inet_sock_destruct;
	newsk->sk_family = PF_INET;
	newsk->sk_protocol = IPPROTO_SCTP;
	newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
	sock_reset_flag(newsk, SOCK_ZAPPED);

	newinet = inet_sk(newsk);

	/* Initialize sk's sport, dport, rcv_saddr and daddr for
	 * getsockname() and getpeername()
	 */
	newinet->sport = inet->sport;
	newinet->saddr = inet->saddr;
	newinet->rcv_saddr = inet->rcv_saddr;
	newinet->dport = htons(asoc->peer.port);
	newinet->daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr;
	newinet->pmtudisc = inet->pmtudisc;
	newinet->id = asoc->next_tsn ^ jiffies;

	newinet->uc_ttl = -1;
	newinet->mc_loop = 1;
	newinet->mc_ttl = 1;
	newinet->mc_index = 0;
	newinet->mc_list = NULL;

	sk_refcnt_debug_inc(newsk);

	if (newsk->sk_prot->init(newsk)) {
		sk_common_release(newsk);
		newsk = NULL;
	}

out:
	return newsk;
}

/* Map address, empty for v4 family */
static void sctp_v4_addr_v4map(struct sctp_sock *sp, union sctp_addr *addr)
{
	/* Empty */
}

/* Dump the v4 addr to the seq file. */
static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr)
{
	seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr));
}

/* Event handler for inet address addition/deletion events.
 * The sctp_local_addr_list needs to be protocted by a spin lock since
 * multiple notifiers (say IPv4 and IPv6) may be running at the same
 * time and thus corrupt the list.
 * The reader side is protected with RCU.
 */
static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev,
			       void *ptr)
{
	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
	struct sctp_sockaddr_entry *addr = NULL;
	struct sctp_sockaddr_entry *temp;
	int found = 0;

	switch (ev) {
	case NETDEV_UP:
		addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC);
		if (addr) {
			addr->a.v4.sin_family = AF_INET;
			addr->a.v4.sin_port = 0;
			addr->a.v4.sin_addr.s_addr = ifa->ifa_local;
			addr->valid = 1;
			spin_lock_bh(&sctp_local_addr_lock);
			list_add_tail_rcu(&addr->list, &sctp_local_addr_list);
			spin_unlock_bh(&sctp_local_addr_lock);
		}
		break;
	case NETDEV_DOWN:
		spin_lock_bh(&sctp_local_addr_lock);
		list_for_each_entry_safe(addr, temp,
					&sctp_local_addr_list, list) {
			if (addr->a.sa.sa_family == AF_INET &&
					addr->a.v4.sin_addr.s_addr ==
					ifa->ifa_local) {
				found = 1;
				addr->valid = 0;
				list_del_rcu(&addr->list);
				break;
			}
		}
		spin_unlock_bh(&sctp_local_addr_lock);
		if (found)
			call_rcu(&addr->rcu, sctp_local_addr_free);
		break;
	}

	return NOTIFY_DONE;
}

/*
 * Initialize the control inode/socket with a control endpoint data
 * structure.  This endpoint is reserved exclusively for the OOTB processing.
 */
static int sctp_ctl_sock_init(void)
{
	int err;
	sa_family_t family;

	if (sctp_get_pf_specific(PF_INET6))
		family = PF_INET6;
	else
		family = PF_INET;

	err = sock_create_kern(family, SOCK_SEQPACKET, IPPROTO_SCTP,
			       &sctp_ctl_socket);
	if (err < 0) {
		printk(KERN_ERR
		       "SCTP: Failed to create the SCTP control socket.\n");
		return err;
	}
	sctp_ctl_socket->sk->sk_allocation = GFP_ATOMIC;
	inet_sk(sctp_ctl_socket->sk)->uc_ttl = -1;

	return 0;
}

/* Register address family specific functions. */
int sctp_register_af(struct sctp_af *af)
{
	switch (af->sa_family) {
	case AF_INET:
		if (sctp_af_v4_specific)
			return 0;
		sctp_af_v4_specific = af;
		break;
	case AF_INET6:
		if (sctp_af_v6_specific)
			return 0;
		sctp_af_v6_specific = af;
		break;
	default:
		return 0;
	}

	INIT_LIST_HEAD(&af->list);
	list_add_tail(&af->list, &sctp_address_families);
	return 1;
}

/* Get the table of functions for manipulating a particular address
 * family.
 */
struct sctp_af *sctp_get_af_specific(sa_family_t family)
{
	switch (family) {
	case AF_INET:
		return sctp_af_v4_specific;
	case AF_INET6:
		return sctp_af_v6_specific;
	default:
		return NULL;
	}
}

/* Common code to initialize a AF_INET msg_name. */
static void sctp_inet_msgname(char *msgname, int *addr_len)
{
	struct sockaddr_in *sin;

	sin = (struct sockaddr_in *)msgname;
	*addr_len = sizeof(struct sockaddr_in);
	sin->sin_family = AF_INET;
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
}

/* Copy the primary address of the peer primary address as the msg_name. */
static void sctp_inet_event_msgname(struct sctp_ulpevent *event, char *msgname,
				    int *addr_len)
{
	struct sockaddr_in *sin, *sinfrom;

	if (msgname) {
		struct sctp_association *asoc;

		asoc = event->asoc;
		sctp_inet_msgname(msgname, addr_len);
		sin = (struct sockaddr_in *)msgname;
		sinfrom = &asoc->peer.primary_addr.v4;
		sin->sin_port = htons(asoc->peer.port);
		sin->sin_addr.s_addr = sinfrom->sin_addr.s_addr;
	}
}

/* Initialize and copy out a msgname from an inbound skb. */
static void sctp_inet_skb_msgname(struct sk_buff *skb, char *msgname, int *len)
{
	if (msgname) {
		struct sctphdr *sh = sctp_hdr(skb);
		struct sockaddr_in *sin = (struct sockaddr_in *)msgname;

		sctp_inet_msgname(msgname, len);
		sin->sin_port = sh->source;
		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
	}
}

/* Do we support this AF? */
static int sctp_inet_af_supported(sa_family_t family, struct sctp_sock *sp)
{
	/* PF_INET only supports AF_INET addresses. */
	return (AF_INET == family);
}

/* Address matching with wildcards allowed. */
static int sctp_inet_cmp_addr(const union sctp_addr *addr1,
			      const union sctp_addr *addr2,
			      struct sctp_sock *opt)
{
	/* PF_INET only supports AF_INET addresses. */
	if (addr1->sa.sa_family != addr2->sa.sa_family)
		return 0;
	if (htonl(INADDR_ANY) == addr1->v4.sin_addr.s_addr ||
	    htonl(INADDR_ANY) == addr2->v4.sin_addr.s_addr)
		return 1;
	if (addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr)
		return 1;

	return 0;
}

/* Verify that provided sockaddr looks bindable.  Common verification has
 * already been taken care of.
 */
static int sctp_inet_bind_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
	return sctp_v4_available(addr, opt);
}

/* Verify that sockaddr looks sendable.  Common verification has already
 * been taken care of.
 */
static int sctp_inet_send_verify(struct sctp_sock *opt, union sctp_addr *addr)
{
	return 1;
}

/* Fill in Supported Address Type information for INIT and INIT-ACK
 * chunks.  Returns number of addresses supported.
 */
static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
				     __be16 *types)
{
	types[0] = SCTP_PARAM_IPV4_ADDRESS;
	return 1;
}

/* Wrapper routine that calls the ip transmit routine. */
static inline int sctp_v4_xmit(struct sk_buff *skb,
			       struct sctp_transport *transport, int ipfragok)
{
	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, "
			  "src:%u.%u.%u.%u, dst:%u.%u.%u.%u\n",
			  __FUNCTION__, skb, skb->len,
			  NIPQUAD(((struct rtable *)skb->dst)->rt_src),
			  NIPQUAD(((struct rtable *)skb->dst)->rt_dst));

	SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS);
	return ip_queue_xmit(skb, ipfragok);
}

static struct sctp_af sctp_af_inet;

static struct sctp_pf sctp_pf_inet = {
	.event_msgname = sctp_inet_event_msgname,
	.skb_msgname   = sctp_inet_skb_msgname,
	.af_supported  = sctp_inet_af_supported,
	.cmp_addr      = sctp_inet_cmp_addr,
	.bind_verify   = sctp_inet_bind_verify,
	.send_verify   = sctp_inet_send_verify,
	.supported_addrs = sctp_inet_supported_addrs,
	.create_accept_sk = sctp_v4_create_accept_sk,
	.addr_v4map	= sctp_v4_addr_v4map,
	.af            = &sctp_af_inet
};

/* Notifier for inetaddr addition/deletion events.  */
static struct notifier_block sctp_inetaddr_notifier = {
	.notifier_call = sctp_inetaddr_event,
};

/* Socket operations.  */
static const struct proto_ops inet_seqpacket_ops = {
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,	/* Needs to be wrapped... */
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,	/* Semantics are different.  */
	.poll		   = sctp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sctp_inet_listen,
	.shutdown	   = inet_shutdown,	/* Looks harmless.  */
	.setsockopt	   = sock_common_setsockopt, /* IP_SOL IP_OPTION is a problem */
	.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
};

/* Registration with AF_INET family.  */
static struct inet_protosw sctp_seqpacket_protosw = {
	.type       = SOCK_SEQPACKET,
	.protocol   = IPPROTO_SCTP,
	.prot       = &sctp_prot,
	.ops        = &inet_seqpacket_ops,
	.capability = -1,
	.no_check   = 0,
	.flags      = SCTP_PROTOSW_FLAG
};
static struct inet_protosw sctp_stream_protosw = {
	.type       = SOCK_STREAM,
	.protocol   = IPPROTO_SCTP,
	.prot       = &sctp_prot,
	.ops        = &inet_seqpacket_ops,
	.capability = -1,
	.no_check   = 0,
	.flags      = SCTP_PROTOSW_FLAG
};

/* Register with IP layer.  */
static struct net_protocol sctp_protocol = {
	.handler     = sctp_rcv,
	.err_handler = sctp_v4_err,
	.no_policy   = 1,
};

/* IPv4 address related functions.  */
static struct sctp_af sctp_af_inet = {
	.sa_family	   = AF_INET,
	.sctp_xmit	   = sctp_v4_xmit,
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.get_dst	   = sctp_v4_get_dst,