proto.c

linux 内核源代码

		slen = sl->dccpsl_nr * sizeof(u32);
		total_len += slen;
	}

	err = -EINVAL;
	if (total_len > len)
		goto out;

	err = 0;
	if (put_user(total_len, optlen) ||
	    put_user(dp->dccps_service, optval) ||
	    (sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen)))
		err = -EFAULT;
out:
	release_sock(sk);
	return err;
}

static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	struct dccp_sock *dp;
	int val, len;

	if (get_user(len, optlen))
		return -EFAULT;

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

	dp = dccp_sk(sk);

	switch (optname) {
	case DCCP_SOCKOPT_PACKET_SIZE:
		DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
		return 0;
	case DCCP_SOCKOPT_SERVICE:
		return dccp_getsockopt_service(sk, len,
					       (__be32 __user *)optval, optlen);
	case DCCP_SOCKOPT_GET_CUR_MPS:
		val = dp->dccps_mss_cache;
		len = sizeof(val);
		break;
	case DCCP_SOCKOPT_SEND_CSCOV:
		val = dp->dccps_pcslen;
		len = sizeof(val);
		break;
	case DCCP_SOCKOPT_RECV_CSCOV:
		val = dp->dccps_pcrlen;
		len = sizeof(val);
		break;
	case 128 ... 191:
		return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
					     len, (u32 __user *)optval, optlen);
	case 192 ... 255:
		return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
					     len, (u32 __user *)optval, optlen);
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen) || copy_to_user(optval, &val, len))
		return -EFAULT;

	return 0;
}

int dccp_getsockopt(struct sock *sk, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	if (level != SOL_DCCP)
		return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
							     optname, optval,
							     optlen);
	return do_dccp_getsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL_GPL(dccp_getsockopt);

#ifdef CONFIG_COMPAT
int compat_dccp_getsockopt(struct sock *sk, int level, int optname,
			   char __user *optval, int __user *optlen)
{
	if (level != SOL_DCCP)
		return inet_csk_compat_getsockopt(sk, level, optname,
						  optval, optlen);
	return do_dccp_getsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL_GPL(compat_dccp_getsockopt);
#endif

int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		 size_t len)
{
	const struct dccp_sock *dp = dccp_sk(sk);
	const int flags = msg->msg_flags;
	const int noblock = flags & MSG_DONTWAIT;
	struct sk_buff *skb;
	int rc, size;
	long timeo;

	if (len > dp->dccps_mss_cache)
		return -EMSGSIZE;

	lock_sock(sk);

	if (sysctl_dccp_tx_qlen &&
	    (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) {
		rc = -EAGAIN;
		goto out_release;
	}

	timeo = sock_sndtimeo(sk, noblock);

	/*
	 * We have to use sk_stream_wait_connect here to set sk_write_pending,
	 * so that the trick in dccp_rcv_request_sent_state_process.
	 */
	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
		if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_release;

	size = sk->sk_prot->max_header + len;
	release_sock(sk);
	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
	lock_sock(sk);
	if (skb == NULL)
		goto out_release;

	skb_reserve(skb, sk->sk_prot->max_header);
	rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
	if (rc != 0)
		goto out_discard;

	skb_queue_tail(&sk->sk_write_queue, skb);
	dccp_write_xmit(sk,0);
out_release:
	release_sock(sk);
	return rc ? : len;
out_discard:
	kfree_skb(skb);
	goto out_release;
}

EXPORT_SYMBOL_GPL(dccp_sendmsg);

int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		 size_t len, int nonblock, int flags, int *addr_len)
{
	const struct dccp_hdr *dh;
	long timeo;

	lock_sock(sk);

	if (sk->sk_state == DCCP_LISTEN) {
		len = -ENOTCONN;
		goto out;
	}

	timeo = sock_rcvtimeo(sk, nonblock);

	do {
		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);

		if (skb == NULL)
			goto verify_sock_status;

		dh = dccp_hdr(skb);

		if (dh->dccph_type == DCCP_PKT_DATA ||
		    dh->dccph_type == DCCP_PKT_DATAACK)
			goto found_ok_skb;

		if (dh->dccph_type == DCCP_PKT_RESET ||
		    dh->dccph_type == DCCP_PKT_CLOSE) {
			dccp_pr_debug("found fin ok!\n");
			len = 0;
			goto found_fin_ok;
		}
		dccp_pr_debug("packet_type=%s\n",
			      dccp_packet_name(dh->dccph_type));
		sk_eat_skb(sk, skb, 0);
verify_sock_status:
		if (sock_flag(sk, SOCK_DONE)) {
			len = 0;
			break;
		}

		if (sk->sk_err) {
			len = sock_error(sk);
			break;
		}

		if (sk->sk_shutdown & RCV_SHUTDOWN) {
			len = 0;
			break;
		}

		if (sk->sk_state == DCCP_CLOSED) {
			if (!sock_flag(sk, SOCK_DONE)) {
				/* This occurs when user tries to read
				 * from never connected socket.
				 */
				len = -ENOTCONN;
				break;
			}
			len = 0;
			break;
		}

		if (!timeo) {
			len = -EAGAIN;
			break;
		}

		if (signal_pending(current)) {
			len = sock_intr_errno(timeo);
			break;
		}

		sk_wait_data(sk, &timeo);
		continue;
	found_ok_skb:
		if (len > skb->len)
			len = skb->len;
		else if (len < skb->len)
			msg->msg_flags |= MSG_TRUNC;

		if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len)) {
			/* Exception. Bailout! */
			len = -EFAULT;
			break;
		}
	found_fin_ok:
		if (!(flags & MSG_PEEK))
			sk_eat_skb(sk, skb, 0);
		break;
	} while (1);
out:
	release_sock(sk);
	return len;
}

EXPORT_SYMBOL_GPL(dccp_recvmsg);

int inet_dccp_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	unsigned char old_state;
	int err;

	lock_sock(sk);

	err = -EINVAL;
	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP)
		goto out;

	old_state = sk->sk_state;
	if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
		goto out;

	/* Really, if the socket is already in listen state
	 * we can only allow the backlog to be adjusted.
	 */
	if (old_state != DCCP_LISTEN) {
		/*
		 * FIXME: here it probably should be sk->sk_prot->listen_start
		 * see tcp_listen_start
		 */
		err = dccp_listen_start(sk, backlog);
		if (err)
			goto out;
	}
	sk->sk_max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}

EXPORT_SYMBOL_GPL(inet_dccp_listen);

static const unsigned char dccp_new_state[] = {
	/* current state:   new state:      action:	*/
	[0]		  = DCCP_CLOSED,
	[DCCP_OPEN]	  = DCCP_CLOSING | DCCP_ACTION_FIN,
	[DCCP_REQUESTING] = DCCP_CLOSED,
	[DCCP_PARTOPEN]	  = DCCP_CLOSING | DCCP_ACTION_FIN,
	[DCCP_LISTEN]	  = DCCP_CLOSED,
	[DCCP_RESPOND]	  = DCCP_CLOSED,
	[DCCP_CLOSING]	  = DCCP_CLOSED,
	[DCCP_TIME_WAIT]  = DCCP_CLOSED,
	[DCCP_CLOSED]	  = DCCP_CLOSED,
};

static int dccp_close_state(struct sock *sk)
{
	const int next = dccp_new_state[sk->sk_state];
	const int ns = next & DCCP_STATE_MASK;

	if (ns != sk->sk_state)
		dccp_set_state(sk, ns);

	return next & DCCP_ACTION_FIN;
}

void dccp_close(struct sock *sk, long timeout)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;
	int state;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	sk_stop_timer(sk, &dp->dccps_xmit_timer);

	/*
	 * We need to flush the recv. buffs.  We do this only on the
	 * descriptor close, not protocol-sourced closes, because the
	  *reader process may not have drained the data yet!
	 */
	/* FIXME: check for unread data */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		__kfree_skb(skb);
	}

	if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
	} else if (dccp_close_state(sk)) {
		dccp_send_close(sk, 1);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);
	atomic_inc(sk->sk_prot->orphan_count);

	/*
	 * It is the last release_sock in its life. It will remove backlog.
	 */
	release_sock(sk);
	/*
	 * Now socket is owned by kernel and we acquire BH lock
	 * to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	BUG_TRAP(!sock_owned_by_user(sk));

	/* Have we already been destroyed by a softirq or backlog? */
	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
		goto out;

	/*
	 * The last release_sock may have processed the CLOSE or RESET
	 * packet moving sock to CLOSED state, if not we have to fire
	 * the CLOSE/CLOSEREQ retransmission timer, see "8.3. Termination"
	 * in draft-ietf-dccp-spec-11. -acme
	 */
	if (sk->sk_state == DCCP_CLOSING) {
		/* FIXME: should start at 2 * RTT */
		/* Timer for repeating the CLOSE/CLOSEREQ until an answer. */
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  inet_csk(sk)->icsk_rto,
					  DCCP_RTO_MAX);
#if 0
		/* Yeah, we should use sk->sk_prot->orphan_count, etc */
		dccp_set_state(sk, DCCP_CLOSED);
#endif
	}

	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}

EXPORT_SYMBOL_GPL(dccp_close);

void dccp_shutdown(struct sock *sk, int how)
{
	dccp_pr_debug("entry\n");
}

EXPORT_SYMBOL_GPL(dccp_shutdown);

static int __init dccp_mib_init(void)
{
	int rc = -ENOMEM;

	dccp_statistics[0] = alloc_percpu(struct dccp_mib);
	if (dccp_statistics[0] == NULL)
		goto out;

	dccp_statistics[1] = alloc_percpu(struct dccp_mib);
	if (dccp_statistics[1] == NULL)
		goto out_free_one;

	rc = 0;
out:
	return rc;
out_free_one:
	free_percpu(dccp_statistics[0]);
	dccp_statistics[0] = NULL;
	goto out;

}

static void dccp_mib_exit(void)
{
	free_percpu(dccp_statistics[0]);
	free_percpu(dccp_statistics[1]);
	dccp_statistics[0] = dccp_statistics[1] = NULL;
}

static int thash_entries;
module_param(thash_entries, int, 0444);
MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");

#ifdef CONFIG_IP_DCCP_DEBUG
int dccp_debug;
module_param(dccp_debug, bool, 0444);
MODULE_PARM_DESC(dccp_debug, "Enable debug messages");

EXPORT_SYMBOL_GPL(dccp_debug);
#endif

static int __init dccp_init(void)
{
	unsigned long goal;
	int ehash_order, bhash_order, i;
	int rc = -ENOBUFS;

	dccp_hashinfo.bind_bucket_cachep =
		kmem_cache_create("dccp_bind_bucket",
				  sizeof(struct inet_bind_bucket), 0,
				  SLAB_HWCACHE_ALIGN, NULL);
	if (!dccp_hashinfo.bind_bucket_cachep)
		goto out;

	/*
	 * Size and allocate the main established and bind bucket
	 * hash tables.
	 *
	 * The methodology is similar to that of the buffer cache.
	 */
	if (num_physpages >= (128 * 1024))
		goal = num_physpages >> (21 - PAGE_SHIFT);
	else
		goal = num_physpages >> (23 - PAGE_SHIFT);

	if (thash_entries)
		goal = (thash_entries *
			sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT;
	for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++)
		;
	do {
		dccp_hashinfo.ehash_size = (1UL << ehash_order) * PAGE_SIZE /
					sizeof(struct inet_ehash_bucket);
		while (dccp_hashinfo.ehash_size &
		       (dccp_hashinfo.ehash_size - 1))
			dccp_hashinfo.ehash_size--;
		dccp_hashinfo.ehash = (struct inet_ehash_bucket *)
			__get_free_pages(GFP_ATOMIC, ehash_order);
	} while (!dccp_hashinfo.ehash && --ehash_order > 0);

	if (!dccp_hashinfo.ehash) {
		DCCP_CRIT("Failed to allocate DCCP established hash table");
		goto out_free_bind_bucket_cachep;
	}

	for (i = 0; i < dccp_hashinfo.ehash_size; i++) {
		INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain);
		INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain);
	}

	if (inet_ehash_locks_alloc(&dccp_hashinfo))
			goto out_free_dccp_ehash;

	bhash_order = ehash_order;

	do {
		dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE /
					sizeof(struct inet_bind_hashbucket);
		if ((dccp_hashinfo.bhash_size > (64 * 1024)) &&
		    bhash_order > 0)
			continue;
		dccp_hashinfo.bhash = (struct inet_bind_hashbucket *)
			__get_free_pages(GFP_ATOMIC, bhash_order);
	} while (!dccp_hashinfo.bhash && --bhash_order >= 0);

	if (!dccp_hashinfo.bhash) {
		DCCP_CRIT("Failed to allocate DCCP bind hash table");
		goto out_free_dccp_locks;
	}

	for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
		spin_lock_init(&dccp_hashinfo.bhash[i].lock);
		INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
	}

	rc = dccp_mib_init();
	if (rc)
		goto out_free_dccp_bhash;

	rc = dccp_ackvec_init();
	if (rc)
		goto out_free_dccp_mib;

	rc = dccp_sysctl_init();
	if (rc)
		goto out_ackvec_exit;

	dccp_timestamping_init();
out:
	return rc;
out_ackvec_exit:
	dccp_ackvec_exit();
out_free_dccp_mib:
	dccp_mib_exit();
out_free_dccp_bhash:
	free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
	dccp_hashinfo.bhash = NULL;
out_free_dccp_locks:
	inet_ehash_locks_free(&dccp_hashinfo);
out_free_dccp_ehash:
	free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
	dccp_hashinfo.ehash = NULL;
out_free_bind_bucket_cachep:
	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
	dccp_hashinfo.bind_bucket_cachep = NULL;
	goto out;
}

static void __exit dccp_fini(void)
{
	dccp_mib_exit();
	free_pages((unsigned long)dccp_hashinfo.bhash,
		   get_order(dccp_hashinfo.bhash_size *
			     sizeof(struct inet_bind_hashbucket)));
	free_pages((unsigned long)dccp_hashinfo.ehash,
		   get_order(dccp_hashinfo.ehash_size *
			     sizeof(struct inet_ehash_bucket)));
	inet_ehash_locks_free(&dccp_hashinfo);
	kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
	dccp_ackvec_exit();
	dccp_sysctl_exit();
}

module_init(dccp_init);
module_exit(dccp_fini);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <[e-mail]>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");