socket.c

			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_sleep(sk), &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_sleep(sk), &wait);
	return 0;

interrupted:
	error = sock_intr_errno(*timeo_p);

out:
	finish_wait(sk_sleep(sk), &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 correct 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)) {
			wait_queue_head_t *wq = sk_sleep(sk);

			if (wq && waitqueue_active(wq))
				wake_up_interruptible(wq);

			/* 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 (!(sk->sk_shutdown & SEND_SHUTDOWN))
				sock_wake_async(sock,
						SOCK_WAKE_SPACE, 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);

	/*
	 * This undoes what is done via sctp_set_owner_w and sk_mem_charge
	 */
	sk->sk_wmem_queued   -= skb->truesize;
	sk_mem_uncharge(sk, skb->truesize);

	sock_wfree(skb);
	__sctp_write_space(asoc);

	sctp_association_put(asoc);
}

/* Do accounting for the receive space on the socket.
 * Accounting for the association is done in ulpevent.c
 * We set this as a destructor for the cloned data skbs so that
 * accounting is done at the correct time.
 */
void sctp_sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	struct sctp_ulpevent *event = sctp_skb2event(skb);

	atomic_sub(event->rmem_len, &sk->sk_rmem_alloc);

	/*
	 * Mimic the behavior of sock_rfree
	 */
	sk_mem_uncharge(sk, event->rmem_len);
}


/* 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);
		BUG_ON(sk != asoc->base.sk);
		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;
}

void sctp_data_ready(struct sock *sk, int len)
{
	struct socket_wq *wq;

	rcu_read_lock();
	wq = rcu_dereference(sk->sk_wq);
	if (wq_has_sleeper(wq))
		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
						POLLRDNORM | POLLRDBAND);
	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
	rcu_read_unlock();
}

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

	/* Wake up the tasks in each wait queue.  */
	list_for_each_entry(asoc, &((sctp_sk(sk))->ep->asocs), 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 - sk_wmem_alloc_get(sk);
	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", __func__, 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_sleep(sk), &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_sleep(sk), &wait);

	return err;
}

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

	do {
		prepare_to_wait(sk_sleep(sk), &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_sleep(sk), &wait);
}

static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk)
{
	struct sk_buff *frag;

	if (!skb->data_len)
		goto done;

	/* Don't forget the fragments. */
	skb_walk_frags(skb, frag)
		sctp_skb_set_owner_r_frag(frag, sk);

done:
	sctp_skb_set_owner_r(skb, sk);
}

void sctp_copy_sock(struct sock *newsk, struct sock *sk,
		    struct sctp_association *asoc)
{
	struct inet_sock *inet = inet_sk(sk);
	struct inet_sock *newinet;

	newsk->sk_type = sk->sk_type;
	newsk->sk_bound_dev_if = sk->sk_bound_dev_if;
	newsk->sk_flags = sk->sk_flags;
	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 = sk->sk_family;
	newsk->sk_protocol = IPPROTO_SCTP;
	newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
	newsk->sk_sndbuf = sk->sk_sndbuf;
	newsk->sk_rcvbuf = sk->sk_rcvbuf;
	newsk->sk_lingertime = sk->sk_lingertime;
	newsk->sk_rcvtimeo = sk->sk_rcvtimeo;
	newsk->sk_sndtimeo = sk->sk_sndtimeo;

	newinet = inet_sk(newsk);

	/* Initialize sk's sport, dport, rcv_saddr and daddr for
	 * getsockname() and getpeername()
	 */
	newinet->inet_sport = inet->inet_sport;
	newinet->inet_saddr = inet->inet_saddr;
	newinet->inet_rcv_saddr = inet->inet_rcv_saddr;
	newinet->inet_dport = htons(asoc->peer.port);
	newinet->pmtudisc = inet->pmtudisc;
	newinet->inet_id = asoc->next_tsn ^ jiffies;

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

/* 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;
	struct sctp_bind_hashbucket *head;

	/* 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. */
	head = &sctp_port_hashtable[sctp_phashfn(inet_sk(oldsk)->inet_num)];
	sctp_local_bh_disable();
	sctp_spin_lock(&head->lock);
	pp = sctp_sk(oldsk)->bind_hash;
	sk_add_bind_node(newsk, &pp->owner);
	sctp_sk(newsk)->bind_hash = pp;
	inet_sk(newsk)->inet_num = inet_sk(oldsk)->inet_num;
	sctp_spin_unlock(&head->lock);
	sctp_local_bh_enable();

	/* Copy the bind_addr list from the original endpoint to the new
	 * endpoint so that we can handle restarts properly
	 */
	sctp_bind_addr_dup(&newsp->ep->base.bind_addr,
				&oldsp->ep->base.bind_addr, GFP_KERNEL);

	/* 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) {
			__skb_unlink(skb, &oldsk->sk_receive_queue);
			__skb_queue_tail(&newsk->sk_receive_queue, skb);
			sctp_skb_set_owner_r_frag(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);
	atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode);

	if (atomic_read(&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) {
				__skb_unlink(skb, &oldsp->pd_lobby);
				__skb_queue_tail(queue, skb);
				sctp_skb_set_owner_r_frag(skb, newsk);
			}
		}

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

	}

	sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp)
		sctp_skb_set_owner_r_frag(skb, newsk);

	sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp)
		sctp_skb_set_owner_r_frag(skb, newsk);

	/* 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;

	/* Mark the new socket "in-use" by the user so that any packets
	 * that may arrive on the association after we've moved it are
	 * queued to the backlog.  This prevents a potential race between
	 * backlog processing on the old socket and new-packet processing
	 * on the new socket.
	 *
	 * The caller has just allocated newsk so we can guarantee that other
	 * paths won't try to lock it and then oldsk.
	 */
	lock_sock_nested(newsk, SINGLE_DEPTH_NESTING);
	sctp_assoc_migrate(assoc, newsk);

	/* 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;
	sctp_release_sock(newsk);
}


/* 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),
	.sysctl_mem  =  sysctl_sctp_mem,
	.sysctl_rmem =  sysctl_sctp_rmem,
	.sysctl_wmem =  sysctl_sctp_wmem,
	.memory_pressure = &sctp_memory_pressure,
	.enter_memory_pressure = sctp_enter_memory_pressure,
	.memory_allocated = &sctp_memory_allocated,
	.sockets_allocated = &sctp_sockets_allocated,
};

#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),
	.sysctl_mem	= sysctl_sctp_mem,
	.sysctl_rmem	= sysctl_sctp_rmem,
	.sysctl_wmem	= sysctl_sctp_wmem,
	.memory_pressure = &sctp_memory_pressure,
	.enter_memory_pressure = sctp_enter_memory_pressure,
	.memory_allocated = &sctp_memory_allocated,
	.sockets_allocated = &sctp_sockets_allocated,
};
#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */