lowcomms.c

linux 内核源代码

				queue_work(recv_workqueue, &new_con->rwork);
		}
		break;

		case SCTP_COMM_LOST:
		case SCTP_SHUTDOWN_COMP:
		{
			con = assoc2con(sn->sn_assoc_change.sac_assoc_id);
			if (con) {
				con->sctp_assoc = 0;
			}
		}
		break;

		/* We don't know which INIT failed, so clear the PENDING flags
		 * on them all.  if assoc_id is zero then it will then try
		 * again */

		case SCTP_CANT_STR_ASSOC:
		{
			log_print("Can't start SCTP association - retrying");
			sctp_init_failed();
		}
		break;

		default:
			log_print("unexpected SCTP assoc change id=%d state=%d",
				  (int)sn->sn_assoc_change.sac_assoc_id,
				  sn->sn_assoc_change.sac_state);
		}
	}
}

/* Data received from remote end */
static int receive_from_sock(struct connection *con)
{
	int ret = 0;
	struct msghdr msg = {};
	struct kvec iov[2];
	unsigned len;
	int r;
	int call_again_soon = 0;
	int nvec;
	char incmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];

	mutex_lock(&con->sock_mutex);

	if (con->sock == NULL) {
		ret = -EAGAIN;
		goto out_close;
	}

	if (con->rx_page == NULL) {
		/*
		 * This doesn't need to be atomic, but I think it should
		 * improve performance if it is.
		 */
		con->rx_page = alloc_page(GFP_ATOMIC);
		if (con->rx_page == NULL)
			goto out_resched;
		cbuf_init(&con->cb, PAGE_CACHE_SIZE);
	}

	/* Only SCTP needs these really */
	memset(&incmsg, 0, sizeof(incmsg));
	msg.msg_control = incmsg;
	msg.msg_controllen = sizeof(incmsg);

	/*
	 * iov[0] is the bit of the circular buffer between the current end
	 * point (cb.base + cb.len) and the end of the buffer.
	 */
	iov[0].iov_len = con->cb.base - cbuf_data(&con->cb);
	iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb);
	iov[1].iov_len = 0;
	nvec = 1;

	/*
	 * iov[1] is the bit of the circular buffer between the start of the
	 * buffer and the start of the currently used section (cb.base)
	 */
	if (cbuf_data(&con->cb) >= con->cb.base) {
		iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb);
		iov[1].iov_len = con->cb.base;
		iov[1].iov_base = page_address(con->rx_page);
		nvec = 2;
	}
	len = iov[0].iov_len + iov[1].iov_len;

	r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len,
			       MSG_DONTWAIT | MSG_NOSIGNAL);
	if (ret <= 0)
		goto out_close;

	/* Process SCTP notifications */
	if (msg.msg_flags & MSG_NOTIFICATION) {
		msg.msg_control = incmsg;
		msg.msg_controllen = sizeof(incmsg);

		process_sctp_notification(con, &msg,
				page_address(con->rx_page) + con->cb.base);
		mutex_unlock(&con->sock_mutex);
		return 0;
	}
	BUG_ON(con->nodeid == 0);

	if (ret == len)
		call_again_soon = 1;
	cbuf_add(&con->cb, ret);
	ret = dlm_process_incoming_buffer(con->nodeid,
					  page_address(con->rx_page),
					  con->cb.base, con->cb.len,
					  PAGE_CACHE_SIZE);
	if (ret == -EBADMSG) {
		log_print("lowcomms: addr=%p, base=%u, len=%u, "
			  "iov_len=%u, iov_base[0]=%p, read=%d",
			  page_address(con->rx_page), con->cb.base, con->cb.len,
			  len, iov[0].iov_base, r);
	}
	if (ret < 0)
		goto out_close;
	cbuf_eat(&con->cb, ret);

	if (cbuf_empty(&con->cb) && !call_again_soon) {
		__free_page(con->rx_page);
		con->rx_page = NULL;
	}

	if (call_again_soon)
		goto out_resched;
	mutex_unlock(&con->sock_mutex);
	return 0;

out_resched:
	if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
		queue_work(recv_workqueue, &con->rwork);
	mutex_unlock(&con->sock_mutex);
	return -EAGAIN;

out_close:
	mutex_unlock(&con->sock_mutex);
	if (ret != -EAGAIN) {
		close_connection(con, false);
		/* Reconnect when there is something to send */
	}
	/* Don't return success if we really got EOF */
	if (ret == 0)
		ret = -EAGAIN;

	return ret;
}

/* Listening socket is busy, accept a connection */
static int tcp_accept_from_sock(struct connection *con)
{
	int result;
	struct sockaddr_storage peeraddr;
	struct socket *newsock;
	int len;
	int nodeid;
	struct connection *newcon;
	struct connection *addcon;

	memset(&peeraddr, 0, sizeof(peeraddr));
	result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
				  IPPROTO_TCP, &newsock);
	if (result < 0)
		return -ENOMEM;

	mutex_lock_nested(&con->sock_mutex, 0);

	result = -ENOTCONN;
	if (con->sock == NULL)
		goto accept_err;

	newsock->type = con->sock->type;
	newsock->ops = con->sock->ops;

	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
	if (result < 0)
		goto accept_err;

	/* Get the connected socket's peer */
	memset(&peeraddr, 0, sizeof(peeraddr));
	if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr,
				  &len, 2)) {
		result = -ECONNABORTED;
		goto accept_err;
	}

	/* Get the new node's NODEID */
	make_sockaddr(&peeraddr, 0, &len);
	if (dlm_addr_to_nodeid(&peeraddr, &nodeid)) {
		log_print("connect from non cluster node");
		sock_release(newsock);
		mutex_unlock(&con->sock_mutex);
		return -1;
	}

	log_print("got connection from %d", nodeid);

	/*  Check to see if we already have a connection to this node. This
	 *  could happen if the two nodes initiate a connection at roughly
	 *  the same time and the connections cross on the wire.
	 *  In this case we store the incoming one in "othercon"
	 */
	newcon = nodeid2con(nodeid, GFP_KERNEL);
	if (!newcon) {
		result = -ENOMEM;
		goto accept_err;
	}
	mutex_lock_nested(&newcon->sock_mutex, 1);
	if (newcon->sock) {
		struct connection *othercon = newcon->othercon;

		if (!othercon) {
			othercon = kmem_cache_zalloc(con_cache, GFP_KERNEL);
			if (!othercon) {
				log_print("failed to allocate incoming socket");
				mutex_unlock(&newcon->sock_mutex);
				result = -ENOMEM;
				goto accept_err;
			}
			othercon->nodeid = nodeid;
			othercon->rx_action = receive_from_sock;
			mutex_init(&othercon->sock_mutex);
			INIT_WORK(&othercon->swork, process_send_sockets);
			INIT_WORK(&othercon->rwork, process_recv_sockets);
			set_bit(CF_IS_OTHERCON, &othercon->flags);
		}
		if (!othercon->sock) {
			newcon->othercon = othercon;
			othercon->sock = newsock;
			newsock->sk->sk_user_data = othercon;
			add_sock(newsock, othercon);
			addcon = othercon;
		}
		else {
			printk("Extra connection from node %d attempted\n", nodeid);
			result = -EAGAIN;
			mutex_unlock(&newcon->sock_mutex);
			goto accept_err;
		}
	}
	else {
		newsock->sk->sk_user_data = newcon;
		newcon->rx_action = receive_from_sock;
		add_sock(newsock, newcon);
		addcon = newcon;
	}

	mutex_unlock(&newcon->sock_mutex);

	/*
	 * Add it to the active queue in case we got data
	 * beween processing the accept adding the socket
	 * to the read_sockets list
	 */
	if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
		queue_work(recv_workqueue, &addcon->rwork);
	mutex_unlock(&con->sock_mutex);

	return 0;

accept_err:
	mutex_unlock(&con->sock_mutex);
	sock_release(newsock);

	if (result != -EAGAIN)
		log_print("error accepting connection from node: %d", result);
	return result;
}

static void free_entry(struct writequeue_entry *e)
{
	__free_page(e->page);
	kfree(e);
}

/* Initiate an SCTP association.
   This is a special case of send_to_sock() in that we don't yet have a
   peeled-off socket for this association, so we use the listening socket
   and add the primary IP address of the remote node.
 */
static void sctp_init_assoc(struct connection *con)
{
	struct sockaddr_storage rem_addr;
	char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
	struct msghdr outmessage;
	struct cmsghdr *cmsg;
	struct sctp_sndrcvinfo *sinfo;
	struct connection *base_con;
	struct writequeue_entry *e;
	int len, offset;
	int ret;
	int addrlen;
	struct kvec iov[1];

	if (test_and_set_bit(CF_INIT_PENDING, &con->flags))
		return;

	if (con->retries++ > MAX_CONNECT_RETRIES)
		return;

	log_print("Initiating association with node %d", con->nodeid);

	if (nodeid_to_addr(con->nodeid, (struct sockaddr *)&rem_addr)) {
		log_print("no address for nodeid %d", con->nodeid);
		return;
	}
	base_con = nodeid2con(0, 0);
	BUG_ON(base_con == NULL);

	make_sockaddr(&rem_addr, dlm_config.ci_tcp_port, &addrlen);

	outmessage.msg_name = &rem_addr;
	outmessage.msg_namelen = addrlen;
	outmessage.msg_control = outcmsg;
	outmessage.msg_controllen = sizeof(outcmsg);
	outmessage.msg_flags = MSG_EOR;

	spin_lock(&con->writequeue_lock);
	e = list_entry(con->writequeue.next, struct writequeue_entry,
		       list);

	BUG_ON((struct list_head *) e == &con->writequeue);

	len = e->len;
	offset = e->offset;
	spin_unlock(&con->writequeue_lock);
	kmap(e->page);

	/* Send the first block off the write queue */
	iov[0].iov_base = page_address(e->page)+offset;
	iov[0].iov_len = len;

	cmsg = CMSG_FIRSTHDR(&outmessage);
	cmsg->cmsg_level = IPPROTO_SCTP;
	cmsg->cmsg_type = SCTP_SNDRCV;
	cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
	sinfo = CMSG_DATA(cmsg);
	memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
	sinfo->sinfo_ppid = cpu_to_le32(dlm_our_nodeid());
	outmessage.msg_controllen = cmsg->cmsg_len;

	ret = kernel_sendmsg(base_con->sock, &outmessage, iov, 1, len);
	if (ret < 0) {
		log_print("Send first packet to node %d failed: %d",
			  con->nodeid, ret);

		/* Try again later */
		clear_bit(CF_CONNECT_PENDING, &con->flags);
		clear_bit(CF_INIT_PENDING, &con->flags);
	}
	else {
		spin_lock(&con->writequeue_lock);
		e->offset += ret;
		e->len -= ret;

		if (e->len == 0 && e->users == 0) {
			list_del(&e->list);
			kunmap(e->page);
			free_entry(e);
		}
		spin_unlock(&con->writequeue_lock);
	}
}

/* Connect a new socket to its peer */
static void tcp_connect_to_sock(struct connection *con)
{
	int result = -EHOSTUNREACH;
	struct sockaddr_storage saddr;
	int addr_len;
	struct socket *sock;

	if (con->nodeid == 0) {
		log_print("attempt to connect sock 0 foiled");
		return;
	}

	mutex_lock(&con->sock_mutex);
	if (con->retries++ > MAX_CONNECT_RETRIES)
		goto out;

	/* Some odd races can cause double-connects, ignore them */
	if (con->sock) {
		result = 0;
		goto out;
	}

	/* Create a socket to communicate with */
	result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
				  IPPROTO_TCP, &sock);
	if (result < 0)
		goto out_err;

	memset(&saddr, 0, sizeof(saddr));
	if (dlm_nodeid_to_addr(con->nodeid, &saddr))
		goto out_err;

	sock->sk->sk_user_data = con;
	con->rx_action = receive_from_sock;
	con->connect_action = tcp_connect_to_sock;
	add_sock(sock, con);

	make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);

	log_print("connecting to %d", con->nodeid);
	result =
		sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
				   O_NONBLOCK);
	if (result == -EINPROGRESS)
		result = 0;
	if (result == 0)
		goto out;

out_err:
	if (con->sock) {
		sock_release(con->sock);
		con->sock = NULL;
	}
	/*
	 * Some errors are fatal and this list might need adjusting. For other
	 * errors we try again until the max number of retries is reached.
	 */
	if (result != -EHOSTUNREACH && result != -ENETUNREACH &&
	    result != -ENETDOWN && result != EINVAL
	    && result != -EPROTONOSUPPORT) {
		lowcomms_connect_sock(con);
		result = 0;
	}
out:
	mutex_unlock(&con->sock_mutex);
	return;
}

static struct socket *tcp_create_listen_sock(struct connection *con,
					     struct sockaddr_storage *saddr)
{
	struct socket *sock = NULL;
	int result = 0;
	int one = 1;
	int addr_len;

	if (dlm_local_addr[0]->ss_family == AF_INET)
		addr_len = sizeof(struct sockaddr_in);
	else
		addr_len = sizeof(struct sockaddr_in6);

	/* Create a socket to communicate with */
	result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
				  IPPROTO_TCP, &sock);
	if (result < 0) {
		log_print("Can't create listening comms socket");
		goto create_out;
	}

	result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
				   (char *)&one, sizeof(one));

	if (result < 0) {
		log_print("Failed to set SO_REUSEADDR on socket: %d", result);
	}
	sock->sk->sk_user_data = con;
	con->rx_action = tcp_accept_from_sock;
	con->connect_action = tcp_connect_to_sock;
	con->sock = sock;

	/* Bind to our port */
	make_sockaddr(saddr, dlm_config.ci_tcp_port, &addr_len);
	result = sock->ops->bind(sock, (struct sockaddr *) saddr, addr_len);
	if (result < 0) {
		log_print("Can't bind to port %d", dlm_config.ci_tcp_port);
		sock_release(sock);
		sock = NULL;
		con->sock = NULL;
		goto create_out;
	}
	result = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
				 (char *)&one, sizeof(one));
	if (result < 0) {
		log_print("Set keepalive failed: %d", result);
	}

	result = sock->ops->listen(sock, 5);
	if (result < 0) {
		log_print("Can't listen on port %d", dlm_config.ci_tcp_port);
		sock_release(sock);
		sock = NULL;
		goto create_out;
	}

create_out: