socket.c

	af = sctp_sk(sk)->pf->af;

	port = htons(inet_sk(sk)->num);
	af->inaddr_any(&autoaddr, port);

	return sctp_do_bind(sk, &autoaddr, af->sockaddr_len);
}

/* Parse out IPPROTO_SCTP CMSG headers.  Perform only minimal validation.
 *
 * From RFC 2292
 * 4.2 The cmsghdr Structure *
 *
 * When ancillary data is sent or received, any number of ancillary data
 * objects can be specified by the msg_control and msg_controllen members of
 * the msghdr structure, because each object is preceded by
 * a cmsghdr structure defining the object's length (the cmsg_len member).
 * Historically Berkeley-derived implementations have passed only one object
 * at a time, but this API allows multiple objects to be
 * passed in a single call to sendmsg() or recvmsg(). The following example
 * shows two ancillary data objects in a control buffer.
 *
 *   |<--------------------------- msg_controllen -------------------------->|
 *   |                                                                       |
 *
 *   |<----- ancillary data object ----->|<----- ancillary data object ----->|
 *
 *   |<---------- CMSG_SPACE() --------->|<---------- CMSG_SPACE() --------->|
 *   |                                   |                                   |
 *
 *   |<---------- cmsg_len ---------->|  |<--------- cmsg_len ----------->|  |
 *
 *   |<--------- CMSG_LEN() --------->|  |<-------- CMSG_LEN() ---------->|  |
 *   |                                |  |                                |  |
 *
 *   +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+
 *   |cmsg_|cmsg_|cmsg_|XX|           |XX|cmsg_|cmsg_|cmsg_|XX|           |XX|
 *
 *   |len  |level|type |XX|cmsg_data[]|XX|len  |level|type |XX|cmsg_data[]|XX|
 *
 *   +-----+-----+-----+--+-----------+--+-----+-----+-----+--+-----------+--+
 *    ^
 *    |
 *
 * msg_control
 * points here
 */
SCTP_STATIC int sctp_msghdr_parse(const struct msghdr *msg,
				  sctp_cmsgs_t *cmsgs)
{
	struct cmsghdr *cmsg;

	for (cmsg = CMSG_FIRSTHDR(msg);
	     cmsg != NULL;
	     cmsg = CMSG_NXTHDR((struct msghdr*)msg, cmsg)) {
		if (!CMSG_OK(msg, cmsg))
			return -EINVAL;

		/* Should we parse this header or ignore?  */
		if (cmsg->cmsg_level != IPPROTO_SCTP)
			continue;

		/* Strictly check lengths following example in SCM code.  */
		switch (cmsg->cmsg_type) {
		case SCTP_INIT:
			/* SCTP Socket API Extension
			 * 5.2.1 SCTP Initiation Structure (SCTP_INIT)
			 *
			 * This cmsghdr structure provides information for
			 * initializing new SCTP associations with sendmsg().
			 * The SCTP_INITMSG socket option uses this same data
			 * structure.  This structure is not used for
			 * recvmsg().
			 *
			 * cmsg_level    cmsg_type      cmsg_data[]
			 * ------------  ------------   ----------------------
			 * IPPROTO_SCTP  SCTP_INIT      struct sctp_initmsg
			 */
			if (cmsg->cmsg_len !=
			    CMSG_LEN(sizeof(struct sctp_initmsg)))
				return -EINVAL;
			cmsgs->init = (struct sctp_initmsg *)CMSG_DATA(cmsg);
			break;

		case SCTP_SNDRCV:
			/* SCTP Socket API Extension
			 * 5.2.2 SCTP Header Information Structure(SCTP_SNDRCV)
			 *
			 * This cmsghdr structure specifies SCTP options for
			 * sendmsg() and describes SCTP header information
			 * about a received message through recvmsg().
			 *
			 * cmsg_level    cmsg_type      cmsg_data[]
			 * ------------  ------------   ----------------------
			 * IPPROTO_SCTP  SCTP_SNDRCV    struct sctp_sndrcvinfo
			 */
			if (cmsg->cmsg_len !=
			    CMSG_LEN(sizeof(struct sctp_sndrcvinfo)))
				return -EINVAL;

			cmsgs->info =
				(struct sctp_sndrcvinfo *)CMSG_DATA(cmsg);

			/* Minimally, validate the sinfo_flags. */
			if (cmsgs->info->sinfo_flags &
			    ~(SCTP_UNORDERED | SCTP_ADDR_OVER |
			      SCTP_ABORT | SCTP_EOF))
				return -EINVAL;
			break;

		default:
			return -EINVAL;
		};
	}
	return 0;
}

/*
 * Wait for a packet..
 * Note: This function is the same function as in core/datagram.c
 * with a few modifications to make lksctp work.
 */
static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p)
{
	int error;
	DEFINE_WAIT(wait);

	prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

	/* Socket errors? */
	error = sock_error(sk);
	if (error)
		goto out;

	if (!skb_queue_empty(&sk->sk_receive_queue))
		goto ready;

	/* Socket shut down?  */
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		goto out;

	/* Sequenced packets can come disconnected.  If so we report the
	 * problem.
	 */
	error = -ENOTCONN;

	/* Is there a good reason to think that we may receive some data?  */
	if (list_empty(&sctp_sk(sk)->ep->asocs) && !sctp_sstate(sk, LISTENING))
		goto out;

	/* Handle signals.  */
	if (signal_pending(current))
		goto interrupted;

	/* Let another process have a go.  Since we are going to sleep
	 * anyway.  Note: This may cause odd behaviors if the message
	 * does not fit in the user's buffer, but this seems to be the
	 * only way to honor MSG_DONTWAIT realistically.
	 */
	sctp_release_sock(sk);
	*timeo_p = schedule_timeout(*timeo_p);
	sctp_lock_sock(sk);

ready:
	finish_wait(sk->sk_sleep, &wait);
	return 0;

interrupted:
	error = sock_intr_errno(*timeo_p);

out:
	finish_wait(sk->sk_sleep, &wait);
	*err = error;
	return error;
}

/* Receive a datagram.
 * Note: This is pretty much the same routine as in core/datagram.c
 * with a few changes to make lksctp work.
 */
static struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
					      int noblock, int *err)
{
	int error;
	struct sk_buff *skb;
	long timeo;

	timeo = sock_rcvtimeo(sk, noblock);

	SCTP_DEBUG_PRINTK("Timeout: timeo: %ld, MAX: %ld.\n",
			  timeo, MAX_SCHEDULE_TIMEOUT);

	do {
		/* Again only user level code calls this function,
		 * so nothing interrupt level
		 * will suddenly eat the receive_queue.
		 *
		 *  Look at current nfs client by the way...
		 *  However, this function was corrent in any case. 8)
		 */
		if (flags & MSG_PEEK) {
			spin_lock_bh(&sk->sk_receive_queue.lock);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb)
				atomic_inc(&skb->users);
			spin_unlock_bh(&sk->sk_receive_queue.lock);
		} else {
			skb = skb_dequeue(&sk->sk_receive_queue);
		}

		if (skb)
			return skb;

		/* Caller is allowed not to check sk->sk_err before calling. */
		error = sock_error(sk);
		if (error)
			goto no_packet;

		if (sk->sk_shutdown & RCV_SHUTDOWN)
			break;

		/* User doesn't want to wait.  */
		error = -EAGAIN;
		if (!timeo)
			goto no_packet;
	} while (sctp_wait_for_packet(sk, err, &timeo) == 0);

	return NULL;

no_packet:
	*err = error;
	return NULL;
}

/* If sndbuf has changed, wake up per association sndbuf waiters.  */
static void __sctp_write_space(struct sctp_association *asoc)
{
	struct sock *sk = asoc->base.sk;
	struct socket *sock = sk->sk_socket;

	if ((sctp_wspace(asoc) > 0) && sock) {
		if (waitqueue_active(&asoc->wait))
			wake_up_interruptible(&asoc->wait);

		if (sctp_writeable(sk)) {
			if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
				wake_up_interruptible(sk->sk_sleep);

			/* Note that we try to include the Async I/O support
			 * here by modeling from the current TCP/UDP code.
			 * We have not tested with it yet.
			 */
			if (sock->fasync_list &&
			    !(sk->sk_shutdown & SEND_SHUTDOWN))
				sock_wake_async(sock, 2, POLL_OUT);
		}
	}
}

/* Do accounting for the sndbuf space.
 * Decrement the used sndbuf space of the corresponding association by the
 * data size which was just transmitted(freed).
 */
static void sctp_wfree(struct sk_buff *skb)
{
	struct sctp_association *asoc;
	struct sctp_chunk *chunk;
	struct sock *sk;

	/* Get the saved chunk pointer.  */
	chunk = *((struct sctp_chunk **)(skb->cb));
	asoc = chunk->asoc;
	sk = asoc->base.sk;
	asoc->sndbuf_used -= SCTP_DATA_SNDSIZE(chunk) +
				sizeof(struct sk_buff) +
				sizeof(struct sctp_chunk);

	atomic_sub(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);

	sock_wfree(skb);
	__sctp_write_space(asoc);

	sctp_association_put(asoc);
}

/* Helper function to wait for space in the sndbuf.  */
static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
				size_t msg_len)
{
	struct sock *sk = asoc->base.sk;
	int err = 0;
	long current_timeo = *timeo_p;
	DEFINE_WAIT(wait);

	SCTP_DEBUG_PRINTK("wait_for_sndbuf: asoc=%p, timeo=%ld, msg_len=%zu\n",
	                  asoc, (long)(*timeo_p), msg_len);

	/* Increment the association's refcnt.  */
	sctp_association_hold(asoc);

	/* Wait on the association specific sndbuf space. */
	for (;;) {
		prepare_to_wait_exclusive(&asoc->wait, &wait,
					  TASK_INTERRUPTIBLE);
		if (!*timeo_p)
			goto do_nonblock;
		if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING ||
		    asoc->base.dead)
			goto do_error;
		if (signal_pending(current))
			goto do_interrupted;
		if (msg_len <= sctp_wspace(asoc))
			break;

		/* Let another process have a go.  Since we are going
		 * to sleep anyway.
		 */
		sctp_release_sock(sk);
		current_timeo = schedule_timeout(current_timeo);
		sctp_lock_sock(sk);

		*timeo_p = current_timeo;
	}

out:
	finish_wait(&asoc->wait, &wait);

	/* Release the association's refcnt.  */
	sctp_association_put(asoc);

	return err;

do_error:
	err = -EPIPE;
	goto out;

do_interrupted:
	err = sock_intr_errno(*timeo_p);
	goto out;

do_nonblock:
	err = -EAGAIN;
	goto out;
}

/* If socket sndbuf has changed, wake up all per association waiters.  */
void sctp_write_space(struct sock *sk)
{
	struct sctp_association *asoc;
	struct list_head *pos;

	/* Wake up the tasks in each wait queue.  */
	list_for_each(pos, &((sctp_sk(sk))->ep->asocs)) {
		asoc = list_entry(pos, struct sctp_association, asocs);
		__sctp_write_space(asoc);
	}
}

/* Is there any sndbuf space available on the socket?
 *
 * Note that sk_wmem_alloc is the sum of the send buffers on all of the
 * associations on the same socket.  For a UDP-style socket with
 * multiple associations, it is possible for it to be "unwriteable"
 * prematurely.  I assume that this is acceptable because
 * a premature "unwriteable" is better than an accidental "writeable" which
 * would cause an unwanted block under certain circumstances.  For the 1-1
 * UDP-style sockets or TCP-style sockets, this code should work.
 *  - Daisy
 */
static int sctp_writeable(struct sock *sk)
{
	int amt = 0;

	amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
	if (amt < 0)
		amt = 0;
	return amt;
}

/* Wait for an association to go into ESTABLISHED state. If timeout is 0,
 * returns immediately with EINPROGRESS.
 */
static int sctp_wait_for_connect(struct sctp_association *asoc, long *timeo_p)
{
	struct sock *sk = asoc->base.sk;
	int err = 0;
	long current_timeo = *timeo_p;
	DEFINE_WAIT(wait);

	SCTP_DEBUG_PRINTK("%s: asoc=%p, timeo=%ld\n", __FUNCTION__, asoc,
			  (long)(*timeo_p));

	/* Increment the association's refcnt.  */
	sctp_association_hold(asoc);

	for (;;) {
		prepare_to_wait_exclusive(&asoc->wait, &wait,
					  TASK_INTERRUPTIBLE);
		if (!*timeo_p)
			goto do_nonblock;
		if (sk->sk_shutdown & RCV_SHUTDOWN)
			break;
		if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING ||
		    asoc->base.dead)
			goto do_error;
		if (signal_pending(current))
			goto do_interrupted;

		if (sctp_state(asoc, ESTABLISHED))
			break;

		/* Let another process have a go.  Since we are going
		 * to sleep anyway.
		 */
		sctp_release_sock(sk);
		current_timeo = schedule_timeout(current_timeo);
		sctp_lock_sock(sk);

		*timeo_p = current_timeo;
	}

out:
	finish_wait(&asoc->wait, &wait);

	/* Release the association's refcnt.  */
	sctp_association_put(asoc);

	return err;

do_error:
	if (asoc->init_err_counter + 1 > asoc->max_init_attempts)
		err = -ETIMEDOUT;
	else
		err = -ECONNREFUSED;
	goto out;

do_interrupted:
	err = sock_intr_errno(*timeo_p);
	goto out;

do_nonblock:
	err = -EINPROGRESS;
	goto out;
}

static int sctp_wait_for_accept(struct sock *sk, long timeo)
{
	struct sctp_endpoint *ep;
	int err = 0;
	DEFINE_WAIT(wait);

	ep = sctp_sk(sk)->ep;


	for (;;) {
		prepare_to_wait_exclusive(sk->sk_sleep, &wait,
					  TASK_INTERRUPTIBLE);

		if (list_empty(&ep->asocs)) {
			sctp_release_sock(sk);
			timeo = schedule_timeout(timeo);
			sctp_lock_sock(sk);
		}

		err = -EINVAL;
		if (!sctp_sstate(sk, LISTENING))
			break;

		err = 0;
		if (!list_empty(&ep->asocs))
			break;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;

		err = -EAGAIN;
		if (!timeo)
			break;
	}

	finish_wait(sk->sk_sleep, &wait);

	return err;
}

void sctp_wait_for_close(struct sock *sk, long timeout)
{
	DEFINE_WAIT(wait);

	do {
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
		if (list_empty(&sctp_sk(sk)->ep->asocs))
			break;
		sctp_release_sock(sk);
		timeout = schedule_timeout(timeout);
		sctp_lock_sock(sk);
	} while (!signal_pending(current) && timeout);

	finish_wait(sk->sk_sleep, &wait);
}

/* Populate the fields of the newsk from the oldsk and migrate the assoc
 * and its messages to the newsk.
 */
static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
			      struct sctp_association *assoc,
			      sctp_socket_type_t type)
{
	struct sctp_sock *oldsp = sctp_sk(oldsk);
	struct sctp_sock *newsp = sctp_sk(newsk);
	struct sctp_bind_bucket *pp; /* hash list port iterator */
	struct sctp_endpoint *newep = newsp->ep;
	struct sk_buff *skb, *tmp;
	struct sctp_ulpevent *event;
	int flags = 0;

	/* Migrate socket buffer sizes and all the socket level options to the
	 * new socket.
	 */
	newsk->sk_sndbuf = oldsk->sk_sndbuf;
	newsk->sk_rcvbuf = oldsk->sk_rcvbuf;
	/* Brute force copy old sctp opt. */
	inet_sk_copy_descendant(newsk, oldsk);

	/* Restore the ep value that was overwritten with the above structure
	 * copy.
	 */
	newsp->ep = newep;
	newsp->hmac = NULL;

	/* Hook this new socket in to the bind_hash list. */
	pp = sctp_sk(oldsk)->bind_hash;
	sk_add_bind_node(newsk, &pp->owner);
	sctp_sk(newsk)->bind_hash = pp;
	inet_sk(newsk)->num = inet_sk(oldsk)->num;

	/* Copy the bind_addr list from the original endpoint to the new
	 * endpoint so that we can handle restarts properly
	 */
	if (assoc->peer.ipv4_address)
		flags |= SCTP_ADDR4_PEERSUPP;
	if (assoc->peer.ipv6_address)
		flags |= SCTP_ADDR6_PEERSUPP;
	sctp_bind_addr_copy(&newsp->ep->base.bind_addr,
			     &oldsp->ep->base.bind_addr,
			     SCTP_SCOPE_GLOBAL, GFP_KERNEL, flags);

	/* Move any messages in the old socket's receive queue that are for the
	 * peeled off association to the new socket's receive queue.
	 */
	sctp_skb_for_each(skb, &oldsk->sk_receive_queue, tmp) {
		event = sctp_skb2event(skb);
		if (event->asoc == assoc) {
			sock_rfree(skb);
			__skb_unlink(skb, &oldsk->sk_receive_queue);
			__skb_queue_tail(&newsk->sk_receive_queue, skb);
			skb_set_owner_r(skb, newsk);
		}
	}

	/* Clean up any messages pending delivery due to partial
	 * delivery.   Three cases:
	 * 1) No partial deliver;  no work.
	 * 2) Peeling off partial delivery; keep pd_lobby in new pd_lobby.
	 * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue.
	 */
	skb_queue_head_init(&newsp->pd_lobby);
	sctp_sk(newsk)->pd_mode = assoc->ulpq.pd_mode;

	if (sctp_sk(oldsk)->pd_mode) {
		struct sk_buff_head *queue;

		/* Decide which queue to move pd_lobby skbs to. */
		if (assoc->ulpq.pd_mode) {
			queue = &newsp->pd_lobby;
		} else
			queue = &newsk->sk_receive_queue;

		/* Walk through the pd_lobby, looking for skbs that
		 * need moved to the new socket.
		 */
		sctp_skb_for_each(skb, &oldsp->pd_lobby, tmp) {
			event = sctp_skb2event(skb);
			if (event->asoc == assoc) {
				sock_rfree(skb);
				__skb_unlink(skb, &oldsp->pd_lobby);
				__skb_queue_tail(queue, skb);
				skb_set_owner_r(skb, newsk);
			}
		}

		/* Clear up any skbs waiting for the partial
		 * delivery to finish.
		 */
		if (assoc->ulpq.pd_mode)
			sctp_clear_pd(oldsk);

	}

	/* Set the type of socket to indicate that it is peeled off from the
	 * original UDP-style socket or created with the accept() call on a
	 * TCP-style socket..
	 */
	newsp->type = type;

	spin_lock_bh(&oldsk->sk_lock.slock);
	/* Migrate the backlog from oldsk to newsk. */
	sctp_backlog_migrate(assoc, oldsk, newsk);
	/* Migrate the association to the new socket. */
	sctp_assoc_migrate(assoc, newsk);
	spin_unlock_bh(&oldsk->sk_lock.slock);

	/* If the association on the newsk is already closed before accept()
	 * is called, set RCV_SHUTDOWN flag.
	 */
	if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP))
		newsk->sk_shutdown |= RCV_SHUTDOWN;

	newsk->sk_state = SCTP_SS_ESTABLISHED;
}

/* This proto struct describes the ULP interface for SCTP.  */
struct proto sctp_prot = {
	.name        =	"SCTP",
	.owner       =	THIS_MODULE,
	.close       =	sctp_close,
	.connect     =	sctp_connect,
	.disconnect  =	sctp_disconnect,
	.accept      =	sctp_accept,
	.ioctl       =	sctp_ioctl,
	.init        =	sctp_init_sock,
	.destroy     =	sctp_destroy_sock,
	.shutdown    =	sctp_shutdown,
	.setsockopt  =	sctp_setsockopt,
	.getsockopt  =	sctp_getsockopt,
	.sendmsg     =	sctp_sendmsg,
	.recvmsg     =	sctp_recvmsg,
	.bind        =	sctp_bind,
	.backlog_rcv =	sctp_backlog_rcv,
	.hash        =	sctp_hash,
	.unhash      =	sctp_unhash,
	.get_port    =	sctp_get_port,
	.obj_size    =  sizeof(struct sctp_sock),
};

#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
struct proto sctpv6_prot = {
	.name		= "SCTPv6",
	.owner		= THIS_MODULE,
	.close		= sctp_close,
	.connect	= sctp_connect,
	.disconnect	= sctp_disconnect,
	.accept		= sctp_accept,
	.ioctl		= sctp_ioctl,
	.init		= sctp_init_sock,
	.destroy	= sctp_destroy_sock,
	.shutdown	= sctp_shutdown,
	.setsockopt	= sctp_setsockopt,
	.getsockopt	= sctp_getsockopt,
	.sendmsg	= sctp_sendmsg,
	.recvmsg	= sctp_recvmsg,
	.bind		= sctp_bind,
	.backlog_rcv	= sctp_backlog_rcv,
	.hash		= sctp_hash,
	.unhash		= sctp_unhash,
	.get_port	= sctp_get_port,
	.obj_size	= sizeof(struct sctp6_sock),
};
#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */