socket.c

一种在UDP协议中实现了拥赛控制和重传机制的协议

		default_sinfo.sinfo_ppid = asoc->default_ppid;
		default_sinfo.sinfo_context = asoc->default_context;
		default_sinfo.sinfo_timetolive = asoc->default_timetolive;
		default_sinfo.sinfo_assoc_id = sctp_assoc2id(asoc);
		sinfo = &default_sinfo;
	}

	/* API 7.1.7, the sndbuf size per association bounds the
	 * maximum size of data that can be sent in a single send call.
	 */
	if (msg_len > sk->sk_sndbuf) {
		err = -EMSGSIZE;
		goto out_free;
	}

	/* If fragmentation is disabled and the message length exceeds the
	 * association fragmentation point, return EMSGSIZE.  The I-D
	 * does not specify what this error is, but this looks like
	 * a great fit.
	 */
	if (sctp_sk(sk)->disable_fragments && (msg_len > asoc->frag_point)) {
		err = -EMSGSIZE;
		goto out_free;
	}

	if (sinfo) {
		/* Check for invalid stream. */
		if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) {
			err = -EINVAL;
			goto out_free;
		}
	}

	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
	if (!sctp_wspace(asoc)) {
		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);
		if (err)
			goto out_free;
	}

	/* If an address is passed with the sendto/sendmsg call, it is used
	 * to override the primary destination address in the TCP model, or
	 * when MSG_ADDR_OVER flag is set in the UDP model.
	 */
	if ((sctp_style(sk, TCP) && msg_name) ||
	    (sinfo_flags & MSG_ADDR_OVER)) {
		chunk_tp = sctp_assoc_lookup_paddr(asoc, &to);
		if (!chunk_tp) {
			err = -EINVAL;
			goto out_free;
		}
	} else
		chunk_tp = NULL;

	/* Auto-connect, if we aren't connected already. */
	if (sctp_state(asoc, CLOSED)) {
		err = sctp_primitive_ASSOCIATE(asoc, NULL);
		if (err < 0)
			goto out_free;
		SCTP_DEBUG_PRINTK("We associated primitively.\n");
	}

	/* Break the message into multiple chunks of maximum size. */
	datamsg = sctp_datamsg_from_user(asoc, sinfo, msg, msg_len);
	if (!datamsg) {
		err = -ENOMEM;
		goto out_free;
	}

	/* Now send the (possibly) fragmented message. */
	list_for_each(pos, &datamsg->chunks) {
		chunk = list_entry(pos, struct sctp_chunk, frag_list);
		sctp_datamsg_track(chunk);

		/* Do accounting for the write space.  */
		sctp_set_owner_w(chunk);

		chunk->transport = chunk_tp;

		/* Send it to the lower layers.  Note:  all chunks
		 * must either fail or succeed.   The lower layer
		 * works that way today.  Keep it that way or this
		 * breaks.
		 */
		err = sctp_primitive_SEND(asoc, chunk);
		/* Did the lower layer accept the chunk? */
		if (err)
			sctp_chunk_free(chunk);
		SCTP_DEBUG_PRINTK("We sent primitively.\n");
	}

	sctp_datamsg_free(datamsg);
	if (err)
		goto out_free;
	else
		err = msg_len;

	/* If we are already past ASSOCIATE, the lower
	 * layers are responsible for association cleanup.
	 */
	goto out_unlock;

out_free:
	if (new_asoc)
		sctp_association_free(asoc);
out_unlock:
	sctp_release_sock(sk);

out_nounlock:
	return sctp_error(sk, msg_flags, err);

#if 0
do_sock_err:
	if (msg_len)
		err = msg_len;
	else
		err = sock_error(sk);
	goto out;

do_interrupted:
	if (msg_len)
		err = msg_len;
	goto out;
#endif /* 0 */
}

/* This is an extended version of skb_pull() that removes the data from the
 * start of a skb even when data is spread across the list of skb's in the
 * frag_list. len specifies the total amount of data that needs to be removed.
 * when 'len' bytes could be removed from the skb, it returns 0.
 * If 'len' exceeds the total skb length,  it returns the no. of bytes that
 * could not be removed.
 */
static int sctp_skb_pull(struct sk_buff *skb, int len)
{
	struct sk_buff *list;
	int skb_len = skb_headlen(skb);
	int rlen;

	if (len <= skb_len) {
		__skb_pull(skb, len);
		return 0;
	}
	len -= skb_len;
	__skb_pull(skb, skb_len);

	for (list = skb_shinfo(skb)->frag_list; list; list = list->next) {
		rlen = sctp_skb_pull(list, len);
		skb->len -= (len-rlen);
		skb->data_len -= (len-rlen);

		if (!rlen)
			return 0;

		len = rlen;
	}

	return len;
}

/* API 3.1.3  recvmsg() - UDP Style Syntax
 *
 *  ssize_t recvmsg(int socket, struct msghdr *message,
 *                    int flags);
 *
 *  socket  - the socket descriptor of the endpoint.
 *  message - pointer to the msghdr structure which contains a single
 *            user message and possibly some ancillary data.
 *
 *            See Section 5 for complete description of the data
 *            structures.
 *
 *  flags   - flags sent or received with the user message, see Section
 *            5 for complete description of the flags.
 */
static struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);

SCTP_STATIC int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
			     struct msghdr *msg, size_t len, int noblock,
			     int flags, int *addr_len)
{
	struct sctp_ulpevent *event = NULL;
	struct sctp_sock *sp = sctp_sk(sk);
	struct sk_buff *skb;
	int copied;
	int err = 0;
	int skb_len;

	SCTP_DEBUG_PRINTK("sctp_recvmsg(%s: %p, %s: %p, %s: %zd, %s: %d, %s: "
			  "0x%x, %s: %p)\n", "sk", sk, "msghdr", msg,
			  "len", len, "knoblauch", noblock,
			  "flags", flags, "addr_len", addr_len);

	sctp_lock_sock(sk);

	if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED)) {
		err = -ENOTCONN;
		goto out;
	}

	skb = sctp_skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

	/* Get the total length of the skb including any skb's in the
	 * frag_list.
	 */
	skb_len = skb->len;

	copied = skb_len;
	if (copied > len)
		copied = len;

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);

	event = sctp_skb2event(skb);

	if (err)
		goto out_free;

	sock_recv_timestamp(msg, sk, skb);
	if (sctp_ulpevent_is_notification(event)) {
		msg->msg_flags |= MSG_NOTIFICATION;
		sp->pf->event_msgname(event, msg->msg_name, addr_len);
	} else {
		sp->pf->skb_msgname(skb, msg->msg_name, addr_len);
	}

	/* Check if we allow SCTP_SNDRCVINFO. */
	if (sp->subscribe.sctp_data_io_event)
		sctp_ulpevent_read_sndrcvinfo(event, msg);
#if 0
	/* FIXME: we should be calling IP/IPv6 layers.  */
	if (sk->sk_protinfo.af_inet.cmsg_flags)
		ip_cmsg_recv(msg, skb);
#endif

	err = copied;

	/* If skb's length exceeds the user's buffer, update the skb and
	 * push it back to the receive_queue so that the next call to
	 * recvmsg() will return the remaining data. Don't set MSG_EOR.
	 */
	if (skb_len > copied) {
		msg->msg_flags &= ~MSG_EOR;
		if (flags & MSG_PEEK)
			goto out_free;
		sctp_skb_pull(skb, copied);
		skb_queue_head(&sk->sk_receive_queue, skb);

		/* When only partial message is copied to the user, increase
		 * rwnd by that amount. If all the data in the skb is read,
		 * rwnd is updated when the event is freed.
		 */
		sctp_assoc_rwnd_increase(event->asoc, copied);
		goto out;
	} else if ((event->msg_flags & MSG_NOTIFICATION) ||
		   (event->msg_flags & MSG_EOR))
		msg->msg_flags |= MSG_EOR;
	else
		msg->msg_flags &= ~MSG_EOR;

out_free:
	if (flags & MSG_PEEK) {
		/* Release the skb reference acquired after peeking the skb in
		 * sctp_skb_recv_datagram().
		 */
		kfree_skb(skb);
	} else {
		/* Free the event which includes releasing the reference to
		 * the owner of the skb, freeing the skb and updating the
		 * rwnd.
		 */
		sctp_ulpevent_free(event);
	}
out:
	sctp_release_sock(sk);
	return err;
}

/* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS)
 *
 * This option is a on/off flag.  If enabled no SCTP message
 * fragmentation will be performed.  Instead if a message being sent
 * exceeds the current PMTU size, the message will NOT be sent and
 * instead a error will be indicated to the user.
 */
static int sctp_setsockopt_disable_fragments(struct sock *sk,
					    char __user *optval, int optlen)
{
	int val;

	if (optlen < sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	sctp_sk(sk)->disable_fragments = (val == 0) ? 0 : 1;

	return 0;
}

static int sctp_setsockopt_events(struct sock *sk, char __user *optval,
					int optlen)
{
	if (optlen != sizeof(struct sctp_event_subscribe))
		return -EINVAL;
	if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen))
		return -EFAULT;
	return 0;
}

/* 7.1.8 Automatic Close of associations (SCTP_AUTOCLOSE)
 *
 * This socket option is applicable to the UDP-style socket only.  When
 * set it will cause associations that are idle for more than the
 * specified number of seconds to automatically close.  An association
 * being idle is defined an association that has NOT sent or received
 * user data.  The special value of '0' indicates that no automatic
 * close of any associations should be performed.  The option expects an
 * integer defining the number of seconds of idle time before an
 * association is closed.
 */
static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
					    int optlen)
{
	struct sctp_sock *sp = sctp_sk(sk);

	/* Applicable to UDP-style socket only */
	if (sctp_style(sk, TCP))
		return -EOPNOTSUPP;
	if (optlen != sizeof(int))
		return -EINVAL;
	if (copy_from_user(&sp->autoclose, optval, optlen))
		return -EFAULT;

	sp->ep->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;
	return 0;
}

/* 7.1.13 Peer Address Parameters (SCTP_PEER_ADDR_PARAMS)
 *
 * Applications can enable or disable heartbeats for any peer address of
 * an association, modify an address's heartbeat interval, force a
 * heartbeat to be sent immediately, and adjust the address's maximum
 * number of retransmissions sent before an address is considered
 * unreachable.  The following structure is used to access and modify an
 * address's parameters:
 *
 *  struct sctp_paddrparams {
 *      sctp_assoc_t            spp_assoc_id;
 *      struct sockaddr_storage spp_address;
 *      uint32_t                spp_hbinterval;
 *      uint16_t                spp_pathmaxrxt;
 *  };
 *
 *   spp_assoc_id    - (UDP style socket) This is filled in the application,
 *                     and identifies the association for this query.
 *   spp_address     - This specifies which address is of interest.
 *   spp_hbinterval  - This contains the value of the heartbeat interval,
 *                     in milliseconds.  A value of 0, when modifying the
 *                     parameter, specifies that the heartbeat on this
 *                     address should be disabled. A value of UINT32_MAX
 *                     (4294967295), when modifying the parameter,
 *                     specifies that a heartbeat should be sent
 *                     immediately to the peer address, and the current
 *                     interval should remain unchanged.
 *   spp_pathmaxrxt  - This contains the maximum number of
 *                     retransmissions before this address shall be
 *                     considered unreachable.
 */
static int sctp_setsockopt_peer_addr_params(struct sock *sk,
					    char __user *optval, int optlen)
{
	struct sctp_paddrparams params;
	struct sctp_transport *trans;
	int error;

	if (optlen != sizeof(struct sctp_paddrparams))
		return -EINVAL;
	if (copy_from_user(&params, optval, optlen))
		return -EFAULT;

	/*
	 * API 7. Socket Options (setting the default value for the endpoint)
	 * All options that support specific settings on an association by
	 * filling in either an association id variable or a sockaddr_storage
	 * SHOULD also support setting of the same value for the entire endpoint
	 * (i.e. future associations). To accomplish this the following logic is
	 * used when setting one of these options:

	 * c) If neither the sockaddr_storage or association identification is
	 *    set i.e. the sockaddr_storage is set to all 0's (INADDR_ANY) and
	 *    the association identification is 0, the settings are a default
	 *    and to be applied to the endpoint (all future associations).
	 */

	/* update default value for endpoint (all future associations) */
	if (!params.spp_assoc_id && 
	    sctp_is_any(( union sctp_addr *)&params.spp_address)) {
		/* Manual heartbeat on an endpoint is invalid. */
		if (0xffffffff == params.spp_hbinterval)
			return -EINVAL;
		else if (params.spp_hbinterval)
			sctp_sk(sk)->paddrparam.spp_hbinterval =
						params.spp_hbinterval;
		if (params.spp_pathmaxrxt)
			sctp_sk(sk)->paddrparam.spp_pathmaxrxt =
						params.spp_pathmaxrxt;
		return 0;
	}

	trans = sctp_addr_id2transport(sk, &params.spp_address,
				       params.spp_assoc_id);
	if (!trans)
		return -EINVAL;

	/* Applications can enable or disable heartbeats for any peer address
	 * of an association, modify an address's heartbeat interval, force a
	 * heartbeat to be sent immediately, and adjust the address's maximum
	 * number of retransmissions sent before an address is considered
	 * unreachable.
	 *
	 * The value of the heartbeat interval, in milliseconds. A value of
	 * UINT32_MAX (4294967295), when modifying the parameter, specifies
	 * that a heartbeat should be sent immediately to the peer address,
	 * and the current interval should remain unchanged.
	 */
	if (0xffffffff == params.spp_hbinterval) {
		error = sctp_primitive_REQUESTHEARTBEAT (trans->asoc, trans);
		if (error)
			return error;
	} else {
	/* The value of the heartbeat interval, in milliseconds. A value of 0,
	 * when modifying the parameter, specifies that the heartbeat on this
	 * address should be disabled.
	 */
		if (params.spp_hbinterval) {
			trans->hb_allowed = 1;
			trans->hb_interval = 
				msecs_to_jiffies(params.spp_hbinterval);
		} else