lowcomms.c

	spin_lock(&con->writequeue_lock);

	if (list_empty(&con->writequeue)) {
		spin_unlock(&con->writequeue_lock);
		log_print("writequeue empty for nodeid %d", con->nodeid);
		return;
	}

	e = list_first_entry(&con->writequeue, struct writequeue_entry, list);
	len = e->len;
	offset = e->offset;
	spin_unlock(&con->writequeue_lock);

	/* 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);
			free_entry(e);
		}
		spin_unlock(&con->writequeue_lock);
	}
}

/* Connect a new socket to its peer */
static void tcp_connect_to_sock(struct connection *con)
{
	struct sockaddr_storage saddr, src_addr;
	int addr_len;
	struct socket *sock = NULL;
	int one = 1;
	int result;

	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)
		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));
	result = nodeid_to_addr(con->nodeid, &saddr, NULL);
	if (result < 0) {
		log_print("no address for nodeid %d", con->nodeid);
		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);

	/* Bind to our cluster-known address connecting to avoid
	   routing problems */
	memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
	make_sockaddr(&src_addr, 0, &addr_len);
	result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
				 addr_len);
	if (result < 0) {
		log_print("could not bind for connect: %d", result);
		/* This *may* not indicate a critical error */
	}

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

	log_print("connecting to %d", con->nodeid);

	/* Turn off Nagle's algorithm */
	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
			  sizeof(one));

	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;
	} else if (sock) {
		sock_release(sock);
	}
	/*
	 * 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) {
		log_print("connect %d try %d error %d", con->nodeid,
			  con->retries, result);
		mutex_unlock(&con->sock_mutex);
		msleep(1000);
		lowcomms_connect_sock(con);
		return;
	}
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;
	}

	/* Turn off Nagle's algorithm */
	kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
			  sizeof(one));

	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);
	}
	con->rx_action = tcp_accept_from_sock;
	con->connect_action = tcp_connect_to_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:
	return sock;
}

/* Get local addresses */
static void init_local(void)
{
	struct sockaddr_storage sas, *addr;
	int i;

	dlm_local_count = 0;
	for (i = 0; i < DLM_MAX_ADDR_COUNT; i++) {
		if (dlm_our_addr(&sas, i))
			break;

		addr = kmalloc(sizeof(*addr), GFP_NOFS);
		if (!addr)
			break;
		memcpy(addr, &sas, sizeof(*addr));
		dlm_local_addr[dlm_local_count++] = addr;
	}
}

/* Bind to an IP address. SCTP allows multiple address so it can do
   multi-homing */
static int add_sctp_bind_addr(struct connection *sctp_con,
			      struct sockaddr_storage *addr,
			      int addr_len, int num)
{
	int result = 0;

	if (num == 1)
		result = kernel_bind(sctp_con->sock,
				     (struct sockaddr *) addr,
				     addr_len);
	else
		result = kernel_setsockopt(sctp_con->sock, SOL_SCTP,
					   SCTP_SOCKOPT_BINDX_ADD,
					   (char *)addr, addr_len);

	if (result < 0)
		log_print("Can't bind to port %d addr number %d",
			  dlm_config.ci_tcp_port, num);

	return result;
}

/* Initialise SCTP socket and bind to all interfaces */
static int sctp_listen_for_all(void)
{
	struct socket *sock = NULL;
	struct sockaddr_storage localaddr;
	struct sctp_event_subscribe subscribe;
	int result = -EINVAL, num = 1, i, addr_len;
	struct connection *con = nodeid2con(0, GFP_NOFS);
	int bufsize = NEEDED_RMEM;

	if (!con)
		return -ENOMEM;

	log_print("Using SCTP for communications");

	result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_SEQPACKET,
				  IPPROTO_SCTP, &sock);
	if (result < 0) {
		log_print("Can't create comms socket, check SCTP is loaded");
		goto out;
	}

	/* Listen for events */
	memset(&subscribe, 0, sizeof(subscribe));
	subscribe.sctp_data_io_event = 1;
	subscribe.sctp_association_event = 1;
	subscribe.sctp_send_failure_event = 1;
	subscribe.sctp_shutdown_event = 1;
	subscribe.sctp_partial_delivery_event = 1;

	result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUFFORCE,
				 (char *)&bufsize, sizeof(bufsize));
	if (result)
		log_print("Error increasing buffer space on socket %d", result);

	result = kernel_setsockopt(sock, SOL_SCTP, SCTP_EVENTS,
				   (char *)&subscribe, sizeof(subscribe));
	if (result < 0) {
		log_print("Failed to set SCTP_EVENTS on socket: result=%d",
			  result);
		goto create_delsock;
	}

	/* Init con struct */
	sock->sk->sk_user_data = con;
	con->sock = sock;
	con->sock->sk->sk_data_ready = lowcomms_data_ready;
	con->rx_action = receive_from_sock;
	con->connect_action = sctp_init_assoc;

	/* Bind to all interfaces. */
	for (i = 0; i < dlm_local_count; i++) {
		memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr));
		make_sockaddr(&localaddr, dlm_config.ci_tcp_port, &addr_len);

		result = add_sctp_bind_addr(con, &localaddr, addr_len, num);
		if (result)
			goto create_delsock;
		++num;
	}

	result = sock->ops->listen(sock, 5);
	if (result < 0) {
		log_print("Can't set socket listening");
		goto create_delsock;
	}

	return 0;

create_delsock:
	sock_release(sock);
	con->sock = NULL;
out:
	return result;
}

static int tcp_listen_for_all(void)
{
	struct socket *sock = NULL;
	struct connection *con = nodeid2con(0, GFP_NOFS);
	int result = -EINVAL;

	if (!con)
		return -ENOMEM;

	/* We don't support multi-homed hosts */
	if (dlm_local_addr[1] != NULL) {
		log_print("TCP protocol can't handle multi-homed hosts, "
			  "try SCTP");
		return -EINVAL;
	}

	log_print("Using TCP for communications");

	sock = tcp_create_listen_sock(con, dlm_local_addr[0]);
	if (sock) {
		add_sock(sock, con);
		result = 0;
	}
	else {
		result = -EADDRINUSE;
	}

	return result;
}



static struct writequeue_entry *new_writequeue_entry(struct connection *con,
						     gfp_t allocation)
{
	struct writequeue_entry *entry;

	entry = kmalloc(sizeof(struct writequeue_entry), allocation);
	if (!entry)
		return NULL;

	entry->page = alloc_page(allocation);
	if (!entry->page) {
		kfree(entry);
		return NULL;
	}

	entry->offset = 0;
	entry->len = 0;
	entry->end = 0;
	entry->users = 0;
	entry->con = con;

	return entry;
}

void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
{
	struct connection *con;
	struct writequeue_entry *e;
	int offset = 0;

	con = nodeid2con(nodeid, allocation);
	if (!con)
		return NULL;

	spin_lock(&con->writequeue_lock);
	e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
	if ((&e->list == &con->writequeue) ||
	    (PAGE_CACHE_SIZE - e->end < len)) {
		e = NULL;
	} else {
		offset = e->end;
		e->end += len;
		e->users++;
	}
	spin_unlock(&con->writequeue_lock);

	if (e) {
	got_one:
		*ppc = page_address(e->page) + offset;
		return e;
	}

	e = new_writequeue_entry(con, allocation);
	if (e) {
		spin_lock(&con->writequeue_lock);
		offset = e->end;
		e->end += len;
		e->users++;
		list_add_tail(&e->list, &con->writequeue);
		spin_unlock(&con->writequeue_lock);
		goto got_one;
	}
	return NULL;
}

void dlm_lowcomms_commit_buffer(void *mh)
{
	struct writequeue_entry *e = (struct writequeue_entry *)mh;
	struct connection *con = e->con;
	int users;

	spin_lock(&con->writequeue_lock);
	users = --e->users;
	if (users)
		goto out;
	e->len = e->end - e->offset;
	spin_unlock(&con->writequeue_lock);

	if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) {
		queue_work(send_workqueue, &con->swork);
	}
	return;

out:
	spin_unlock(&con->writequeue_lock);
	return;
}

/* Send a message */
static void send_to_sock(struct connection *con)
{
	int ret = 0;
	const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
	struct writequeue_entry *e;
	int len, offset;
	int count = 0;

	mutex_lock(&con->sock_mutex);
	if (con->sock == NULL)
		goto out_connect;

	spin_lock(&con->writequeue_lock);
	for (;;) {
		e = list_entry(con->writequeue.next, struct writequeue_entry,
			       list);
		if ((struct list_head *) e == &con->writequeue)
			break;

		len = e->len;
		offset = e->offset;
		BUG_ON(len == 0 && e->users == 0);
		spin_unlock(&con->writequeue_lock);

		ret = 0;
		if (len) {
			ret = kernel_sendpage(con->sock, e->page, offset, len,
					      msg_flags);
			if (ret == -EAGAIN || ret == 0) {
				if (ret == -EAGAIN &&
				    test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
				    !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
					/* Notify TCP that we're limited by the
					 * application window size.
					 */
					set_bit(SOCK_NOSPACE, &con->sock->flags);
					con->sock->sk->sk_write_pending++;
				}
				cond_resched();
				goto out;
			} else if (ret < 0)
				goto send_error;
		}

		/* Don't starve people filling buffers */
		if (++count >= MAX_SEND_MSG_COUNT) {
			cond_resched();
			count = 0;
		}

		spin_lock(&con->writequeue_lock);
		e->offset += ret;
		e->len -= ret;

		if (e->len == 0 && e->users == 0) {
			list_del(&e->list);
			free_entry(e);
		}
	}
	spin_unlock(&con->writequeue_lock);
out:
	mutex_unlock(&con->sock_mutex);
	return;

send_error:
	mutex_unlock(&con->sock_mutex);
	close_connection(con, false);
	lowcomms_connect_sock(con);
	return;

out_connect:
	mutex_unlock(&con->sock_mutex);
	if (!test_bit(CF_INIT_PENDING, &con->flags))
		lowcomms_connect_sock(con);
}

static void clean_one_writequeue(struct connection *con)
{
	struct writequeue_entry *e, *safe;

	spin_lock(&con->writequeue_lock);
	list_for_each_entry_safe(e, safe, &con->writequeue, list) {
		list_del(&e->list);
		free_entry(e);
	}
	spin_unlock(&con->writequeue_lock);
}

/* Called from recovery when it knows that a node has
   left the cluster */
int dlm_lowcomms_close(int nodeid)
{
	struct connection *con;
	struct dlm_node_addr *na;

	log_print("closing connection to node %d", nodeid);
	con = nodeid2con(nodeid, 0);
	if (con) {
		clear_bit(CF_CONNECT_PENDING, &con->flags);
		clear_bit(CF_WRITE_PENDING, &con->flags);
		set_bit(CF_CLOSE, &con->flags);
		if (cancel_work_sync(&con->swork))
			log_print("canceled swork for node %d", nodeid);
		if (cancel_work_sync(&con->rwork))
			log_print("canceled rwork for node %d", nodeid);
		clean_one_writequeue(con);
		close_connection(con, true);
	}

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (na) {
		list_del(&na->list);
		while (na->addr_count--)
			kfree(na->addr[na->addr_count]);
		kfree(na);
	}
	spin_unlock(&dlm_node_addrs_spin);

	return 0;
}

/* Receive workqueue function */
static void process_recv_sockets(struct work_struct *work)
{
	struct connection *con = container_of(work, struct connection, rwork);
	int err;

	clear_bit(CF_READ_PENDING, &con->flags);
	do {
		err = con->rx_action(con);
	} while (!err);
}

/* Send workqueue function */
static void process_send_sockets(struct work_struct *work)
{
	struct connection *con = container_of(work, struct connection, swork);

	if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags)) {
		con->connect_action(con);
		set_bit(CF_WRITE_PENDING, &con->flags);
	}
	if (test_and_clear_bit(CF_WRITE_PENDING, &con->flags))
		send_to_sock(con);
}


/* Discard all entries on the write queues */
static void clean_writequeues(void)
{
	foreach_conn(clean_one_writequeue);
}

static void work_stop(void)
{
	destroy_workqueue(recv_workqueue);
	destroy_workqueue(send_workqueue);
}

static int work_start(void)
{
	recv_workqueue = alloc_workqueue("dlm_recv",
					 WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
	if (!recv_workqueue) {
		log_print("can't start dlm_recv");
		return -ENOMEM;
	}

	send_workqueue = alloc_workqueue("dlm_send",
					 WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
	if (!send_workqueue) {
		log_print("can't start dlm_send");
		destroy_workqueue(recv_workqueue);
		return -ENOMEM;
	}

	return 0;
}

static void stop_conn(struct connection *con)
{
	con->flags |= 0x0F;
	if (con->sock && con->sock->sk)
		con->sock->sk->sk_user_data = NULL;
}

static void free_conn(struct connection *con)
{
	close_connection(con, true);
	if (con->othercon)
		kmem_cache_free(con_cache, con->othercon);
	hlist_del(&con->list);
	kmem_cache_free(con_cache, con);
}

void dlm_lowcomms_stop(void)
{
	/* Set all the flags to prevent any
	   socket activity.
	*/
	mutex_lock(&connections_lock);
	dlm_allow_conn = 0;
	foreach_conn(stop_conn);
	mutex_unlock(&connections_lock);

	work_stop();

	mutex_lock(&connections_lock);
	clean_writequeues();

	foreach_conn(free_conn);

	mutex_unlock(&connections_lock);
	kmem_cache_destroy(con_cache);
}

int dlm_lowcomms_start(void)
{
	int error = -EINVAL;
	struct connection *con;
	int i;

	for (i = 0; i < CONN_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&connection_hash[i]);

	init_local();
	if (!dlm_local_count) {
		error = -ENOTCONN;
		log_print("no local IP address has been set");
		goto fail;
	}

	error = -ENOMEM;
	con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection),
				      __alignof__(struct connection), 0,
				      NULL);
	if (!con_cache)
		goto fail;

	error = work_start();
	if (error)
		goto fail_destroy;

	dlm_allow_conn = 1;

	/* Start listening */
	if (dlm_config.ci_protocol == 0)
		error = tcp_listen_for_all();
	else
		error = sctp_listen_for_all();
	if (error)
		goto fail_unlisten;

	return 0;

fail_unlisten:
	dlm_allow_conn = 0;
	con = nodeid2con(0,0);
	if (con) {
		close_connection(con, false);
		kmem_cache_free(con_cache, con);
	}
fail_destroy:
	kmem_cache_destroy(con_cache);
fail:
	return error;
}

void dlm_lowcomms_exit(void)
{
	struct dlm_node_addr *na, *safe;

	spin_lock(&dlm_node_addrs_spin);
	list_for_each_entry_safe(na, safe, &dlm_node_addrs, list) {
		list_del(&na->list);
		while (na->addr_count--)
			kfree(na->addr[na->addr_count]);
		kfree(na);
	}
	spin_unlock(&dlm_node_addrs_spin);
}