lowcomms.c

/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2009 Red Hat, Inc.  All rights reserved.
**
**  This copyrighted material is made available to anyone wishing to use,
**  modify, copy, or redistribute it subject to the terms and conditions
**  of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/

/*
 * lowcomms.c
 *
 * This is the "low-level" comms layer.
 *
 * It is responsible for sending/receiving messages
 * from other nodes in the cluster.
 *
 * Cluster nodes are referred to by their nodeids. nodeids are
 * simply 32 bit numbers to the locking module - if they need to
 * be expanded for the cluster infrastructure then that is its
 * responsibility. It is this layer's
 * responsibility to resolve these into IP address or
 * whatever it needs for inter-node communication.
 *
 * The comms level is two kernel threads that deal mainly with
 * the receiving of messages from other nodes and passing them
 * up to the mid-level comms layer (which understands the
 * message format) for execution by the locking core, and
 * a send thread which does all the setting up of connections
 * to remote nodes and the sending of data. Threads are not allowed
 * to send their own data because it may cause them to wait in times
 * of high load. Also, this way, the sending thread can collect together
 * messages bound for one node and send them in one block.
 *
 * lowcomms will choose to use either TCP or SCTP as its transport layer
 * depending on the configuration variable 'protocol'. This should be set
 * to 0 (default) for TCP or 1 for SCTP. It should be configured using a
 * cluster-wide mechanism as it must be the same on all nodes of the cluster
 * for the DLM to function.
 *
 */

#include <asm/ioctls.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mutex.h>
#include <linux/sctp.h>
#include <linux/slab.h>
#include <net/sctp/sctp.h>
#include <net/ipv6.h>

#include "dlm_internal.h"
#include "lowcomms.h"
#include "midcomms.h"
#include "config.h"

#define NEEDED_RMEM (4*1024*1024)
#define CONN_HASH_SIZE 32

/* Number of messages to send before rescheduling */
#define MAX_SEND_MSG_COUNT 25

struct cbuf {
	unsigned int base;
	unsigned int len;
	unsigned int mask;
};

static void cbuf_add(struct cbuf *cb, int n)
{
	cb->len += n;
}

static int cbuf_data(struct cbuf *cb)
{
	return ((cb->base + cb->len) & cb->mask);
}

static void cbuf_init(struct cbuf *cb, int size)
{
	cb->base = cb->len = 0;
	cb->mask = size-1;
}

static void cbuf_eat(struct cbuf *cb, int n)
{
	cb->len  -= n;
	cb->base += n;
	cb->base &= cb->mask;
}

static bool cbuf_empty(struct cbuf *cb)
{
	return cb->len == 0;
}

struct connection {
	struct socket *sock;	/* NULL if not connected */
	uint32_t nodeid;	/* So we know who we are in the list */
	struct mutex sock_mutex;
	unsigned long flags;
#define CF_READ_PENDING 1
#define CF_WRITE_PENDING 2
#define CF_CONNECT_PENDING 3
#define CF_INIT_PENDING 4
#define CF_IS_OTHERCON 5
#define CF_CLOSE 6
#define CF_APP_LIMITED 7
	struct list_head writequeue;  /* List of outgoing writequeue_entries */
	spinlock_t writequeue_lock;
	int (*rx_action) (struct connection *);	/* What to do when active */
	void (*connect_action) (struct connection *);	/* What to do to connect */
	struct page *rx_page;
	struct cbuf cb;
	int retries;
#define MAX_CONNECT_RETRIES 3
	int sctp_assoc;
	struct hlist_node list;
	struct connection *othercon;
	struct work_struct rwork; /* Receive workqueue */
	struct work_struct swork; /* Send workqueue */
	bool try_new_addr;
};
#define sock2con(x) ((struct connection *)(x)->sk_user_data)

/* An entry waiting to be sent */
struct writequeue_entry {
	struct list_head list;
	struct page *page;
	int offset;
	int len;
	int end;
	int users;
	struct connection *con;
};

struct dlm_node_addr {
	struct list_head list;
	int nodeid;
	int addr_count;
	int curr_addr_index;
	struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
};

static LIST_HEAD(dlm_node_addrs);
static DEFINE_SPINLOCK(dlm_node_addrs_spin);

static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
static int dlm_local_count;
static int dlm_allow_conn;

/* Work queues */
static struct workqueue_struct *recv_workqueue;
static struct workqueue_struct *send_workqueue;

static struct hlist_head connection_hash[CONN_HASH_SIZE];
static DEFINE_MUTEX(connections_lock);
static struct kmem_cache *con_cache;

static void process_recv_sockets(struct work_struct *work);
static void process_send_sockets(struct work_struct *work);


/* This is deliberately very simple because most clusters have simple
   sequential nodeids, so we should be able to go straight to a connection
   struct in the array */
static inline int nodeid_hash(int nodeid)
{
	return nodeid & (CONN_HASH_SIZE-1);
}

static struct connection *__find_con(int nodeid)
{
	int r;
	struct connection *con;

	r = nodeid_hash(nodeid);

	hlist_for_each_entry(con, &connection_hash[r], list) {
		if (con->nodeid == nodeid)
			return con;
	}
	return NULL;
}

/*
 * If 'allocation' is zero then we don't attempt to create a new
 * connection structure for this node.
 */
static struct connection *__nodeid2con(int nodeid, gfp_t alloc)
{
	struct connection *con = NULL;
	int r;

	con = __find_con(nodeid);
	if (con || !alloc)
		return con;

	con = kmem_cache_zalloc(con_cache, alloc);
	if (!con)
		return NULL;

	r = nodeid_hash(nodeid);
	hlist_add_head(&con->list, &connection_hash[r]);

	con->nodeid = nodeid;
	mutex_init(&con->sock_mutex);
	INIT_LIST_HEAD(&con->writequeue);
	spin_lock_init(&con->writequeue_lock);
	INIT_WORK(&con->swork, process_send_sockets);
	INIT_WORK(&con->rwork, process_recv_sockets);

	/* Setup action pointers for child sockets */
	if (con->nodeid) {
		struct connection *zerocon = __find_con(0);

		con->connect_action = zerocon->connect_action;
		if (!con->rx_action)
			con->rx_action = zerocon->rx_action;
	}

	return con;
}

/* Loop round all connections */
static void foreach_conn(void (*conn_func)(struct connection *c))
{
	int i;
	struct hlist_node *n;
	struct connection *con;

	for (i = 0; i < CONN_HASH_SIZE; i++) {
		hlist_for_each_entry_safe(con, n, &connection_hash[i], list)
			conn_func(con);
	}
}

static struct connection *nodeid2con(int nodeid, gfp_t allocation)
{
	struct connection *con;

	mutex_lock(&connections_lock);
	con = __nodeid2con(nodeid, allocation);
	mutex_unlock(&connections_lock);

	return con;
}

/* This is a bit drastic, but only called when things go wrong */
static struct connection *assoc2con(int assoc_id)
{
	int i;
	struct connection *con;

	mutex_lock(&connections_lock);

	for (i = 0 ; i < CONN_HASH_SIZE; i++) {
		hlist_for_each_entry(con, &connection_hash[i], list) {
			if (con->sctp_assoc == assoc_id) {
				mutex_unlock(&connections_lock);
				return con;
			}
		}
	}
	mutex_unlock(&connections_lock);
	return NULL;
}

static struct dlm_node_addr *find_node_addr(int nodeid)
{
	struct dlm_node_addr *na;

	list_for_each_entry(na, &dlm_node_addrs, list) {
		if (na->nodeid == nodeid)
			return na;
	}
	return NULL;
}

static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
{
	switch (x->ss_family) {
	case AF_INET: {
		struct sockaddr_in *sinx = (struct sockaddr_in *)x;
		struct sockaddr_in *siny = (struct sockaddr_in *)y;
		if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
			return 0;
		if (sinx->sin_port != siny->sin_port)
			return 0;
		break;
	}
	case AF_INET6: {
		struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
		struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
		if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
			return 0;
		if (sinx->sin6_port != siny->sin6_port)
			return 0;
		break;
	}
	default:
		return 0;
	}
	return 1;
}

static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
			  struct sockaddr *sa_out, bool try_new_addr)
{
	struct sockaddr_storage sas;
	struct dlm_node_addr *na;

	if (!dlm_local_count)
		return -1;

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (na && na->addr_count) {
		if (try_new_addr) {
			na->curr_addr_index++;
			if (na->curr_addr_index == na->addr_count)
				na->curr_addr_index = 0;
		}

		memcpy(&sas, na->addr[na->curr_addr_index ],
			sizeof(struct sockaddr_storage));
	}
	spin_unlock(&dlm_node_addrs_spin);

	if (!na)
		return -EEXIST;

	if (!na->addr_count)
		return -ENOENT;

	if (sas_out)
		memcpy(sas_out, &sas, sizeof(struct sockaddr_storage));

	if (!sa_out)
		return 0;

	if (dlm_local_addr[0]->ss_family == AF_INET) {
		struct sockaddr_in *in4  = (struct sockaddr_in *) &sas;
		struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out;
		ret4->sin_addr.s_addr = in4->sin_addr.s_addr;
	} else {
		struct sockaddr_in6 *in6  = (struct sockaddr_in6 *) &sas;
		struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) sa_out;
		ret6->sin6_addr = in6->sin6_addr;
	}

	return 0;
}

static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
{
	struct dlm_node_addr *na;
	int rv = -EEXIST;
	int addr_i;

	spin_lock(&dlm_node_addrs_spin);
	list_for_each_entry(na, &dlm_node_addrs, list) {
		if (!na->addr_count)
			continue;

		for (addr_i = 0; addr_i < na->addr_count; addr_i++) {
			if (addr_compare(na->addr[addr_i], addr)) {
				*nodeid = na->nodeid;
				rv = 0;
				goto unlock;
			}
		}
	}
unlock:
	spin_unlock(&dlm_node_addrs_spin);
	return rv;
}

int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
{
	struct sockaddr_storage *new_addr;
	struct dlm_node_addr *new_node, *na;

	new_node = kzalloc(sizeof(struct dlm_node_addr), GFP_NOFS);
	if (!new_node)
		return -ENOMEM;

	new_addr = kzalloc(sizeof(struct sockaddr_storage), GFP_NOFS);
	if (!new_addr) {
		kfree(new_node);
		return -ENOMEM;
	}

	memcpy(new_addr, addr, len);

	spin_lock(&dlm_node_addrs_spin);
	na = find_node_addr(nodeid);
	if (!na) {
		new_node->nodeid = nodeid;
		new_node->addr[0] = new_addr;
		new_node->addr_count = 1;
		list_add(&new_node->list, &dlm_node_addrs);
		spin_unlock(&dlm_node_addrs_spin);
		return 0;
	}

	if (na->addr_count >= DLM_MAX_ADDR_COUNT) {
		spin_unlock(&dlm_node_addrs_spin);
		kfree(new_addr);
		kfree(new_node);
		return -ENOSPC;
	}

	na->addr[na->addr_count++] = new_addr;
	spin_unlock(&dlm_node_addrs_spin);
	kfree(new_node);
	return 0;
}

/* Data available on socket or listen socket received a connect */
static void lowcomms_data_ready(struct sock *sk)
{
	struct connection *con = sock2con(sk);
	if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags))
		queue_work(recv_workqueue, &con->rwork);
}

static void lowcomms_write_space(struct sock *sk)
{
	struct connection *con = sock2con(sk);

	if (!con)
		return;

	clear_bit(SOCK_NOSPACE, &con->sock->flags);

	if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
		con->sock->sk->sk_write_pending--;
		clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
	}

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

static inline void lowcomms_connect_sock(struct connection *con)
{
	if (test_bit(CF_CLOSE, &con->flags))
		return;
	if (!test_and_set_bit(CF_CONNECT_PENDING, &con->flags))
		queue_work(send_workqueue, &con->swork);
}

static void lowcomms_state_change(struct sock *sk)
{
	if (sk->sk_state == TCP_ESTABLISHED)
		lowcomms_write_space(sk);
}

int dlm_lowcomms_connect_node(int nodeid)
{
	struct connection *con;

	/* with sctp there's no connecting without sending */
	if (dlm_config.ci_protocol != 0)
		return 0;

	if (nodeid == dlm_our_nodeid())
		return 0;

	con = nodeid2con(nodeid, GFP_NOFS);
	if (!con)
		return -ENOMEM;
	lowcomms_connect_sock(con);
	return 0;
}

/* Make a socket active */
static void add_sock(struct socket *sock, struct connection *con)
{
	con->sock = sock;

	/* Install a data_ready callback */
	con->sock->sk->sk_data_ready = lowcomms_data_ready;
	con->sock->sk->sk_write_space = lowcomms_write_space;
	con->sock->sk->sk_state_change = lowcomms_state_change;
	con->sock->sk->sk_user_data = con;
	con->sock->sk->sk_allocation = GFP_NOFS;
}

/* Add the port number to an IPv6 or 4 sockaddr and return the address
   length */
static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
			  int *addr_len)
{
	saddr->ss_family =  dlm_local_addr[0]->ss_family;
	if (saddr->ss_family == AF_INET) {
		struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
		in4_addr->sin_port = cpu_to_be16(port);
		*addr_len = sizeof(struct sockaddr_in);
		memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero));
	} else {
		struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
		in6_addr->sin6_port = cpu_to_be16(port);
		*addr_len = sizeof(struct sockaddr_in6);
	}
	memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len);
}

/* Close a remote connection and tidy up */
static void close_connection(struct connection *con, bool and_other)
{
	mutex_lock(&con->sock_mutex);

	if (con->sock) {
		sock_release(con->sock);
		con->sock = NULL;
	}
	if (con->othercon && and_other) {
		/* Will only re-enter once. */
		close_connection(con->othercon, false);
	}
	if (con->rx_page) {
		__free_page(con->rx_page);
		con->rx_page = NULL;
	}

	con->retries = 0;
	mutex_unlock(&con->sock_mutex);
}

/* We only send shutdown messages to nodes that are not part of the cluster */
static void sctp_send_shutdown(sctp_assoc_t associd)
{
	static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
	struct msghdr outmessage;
	struct cmsghdr *cmsg;
	struct sctp_sndrcvinfo *sinfo;
	int ret;
	struct connection *con;

	con = nodeid2con(0,0);
	BUG_ON(con == NULL);

	outmessage.msg_name = NULL;
	outmessage.msg_namelen = 0;
	outmessage.msg_control = outcmsg;
	outmessage.msg_controllen = sizeof(outcmsg);
	outmessage.msg_flags = MSG_EOR;

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

	sinfo->sinfo_flags |= MSG_EOF;
	sinfo->sinfo_assoc_id = associd;

	ret = kernel_sendmsg(con->sock, &outmessage, NULL, 0, 0);

	if (ret != 0)
		log_print("send EOF to node failed: %d", ret);
}

static void sctp_init_failed_foreach(struct connection *con)
{

	/*
	 * Don't try to recover base con and handle race where the
	 * other node's assoc init creates a assoc and we get that
	 * notification, then we get a notification that our attempt
	 * failed due. This happens when we are still trying the primary
	 * address, but the other node has already tried secondary addrs
	 * and found one that worked.
	 */
	if (!con->nodeid || con->sctp_assoc)
		return;

	log_print("Retrying SCTP association init for node %d\n", con->nodeid);

	con->try_new_addr = true;
	con->sctp_assoc = 0;
	if (test_and_clear_bit(CF_INIT_PENDING, &con->flags)) {
		if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
			queue_work(send_workqueue, &con->swork);
	}
}

/* INIT failed but we don't know which node...
   restart INIT on all pending nodes */
static void sctp_init_failed(void)
{
	mutex_lock(&connections_lock);

	foreach_conn(sctp_init_failed_foreach);

	mutex_unlock(&connections_lock);
}

static void retry_failed_sctp_send(struct connection *recv_con,
				   struct sctp_send_failed *sn_send_failed,
				   char *buf)
{
	int len = sn_send_failed->ssf_length - sizeof(struct sctp_send_failed);
	struct dlm_mhandle *mh;
	struct connection *con;
	char *retry_buf;
	int nodeid = sn_send_failed->ssf_info.sinfo_ppid;

	log_print("Retry sending %d bytes to node id %d", len, nodeid);

	con = nodeid2con(nodeid, 0);
	if (!con) {
		log_print("Could not look up con for nodeid %d\n",
			  nodeid);
		return;
	}

	mh = dlm_lowcomms_get_buffer(nodeid, len, GFP_NOFS, &retry_buf);
	if (!mh) {
		log_print("Could not allocate buf for retry.");
		return;
	}
	memcpy(retry_buf, buf + sizeof(struct sctp_send_failed), len);
	dlm_lowcomms_commit_buffer(mh);

	/*
	 * If we got a assoc changed event before the send failed event then
	 * we only need to retry the send.
	 */
	if (con->sctp_assoc) {
		if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
			queue_work(send_workqueue, &con->swork);
	} else
		sctp_init_failed_foreach(con);
}

/* Something happened to an association */
static void process_sctp_notification(struct connection *con,
				      struct msghdr *msg, char *buf)
{
	union sctp_notification *sn = (union sctp_notification *)buf;
	struct linger linger;

	switch (sn->sn_header.sn_type) {
	case SCTP_SEND_FAILED:
		retry_failed_sctp_send(con, &sn->sn_send_failed, buf);
		break;
	case SCTP_ASSOC_CHANGE:
		switch (sn->sn_assoc_change.sac_state) {
		case SCTP_COMM_UP:
		case SCTP_RESTART:
		{
			/* Check that the new node is in the lockspace */
			struct sctp_prim prim;
			int nodeid;
			int prim_len, ret;
			int addr_len;
			struct connection *new_con;

			/*
			 * We get this before any data for an association.
			 * We verify that the node is in the cluster and
			 * then peel off a socket for it.
			 */
			if ((int)sn->sn_assoc_change.sac_assoc_id <= 0) {
				log_print("COMM_UP for invalid assoc ID %d",
					 (int)sn->sn_assoc_change.sac_assoc_id);
				sctp_init_failed();
				return;
			}
			memset(&prim, 0, sizeof(struct sctp_prim));
			prim_len = sizeof(struct sctp_prim);
			prim.ssp_assoc_id = sn->sn_assoc_change.sac_assoc_id;

			ret = kernel_getsockopt(con->sock,
						IPPROTO_SCTP,
						SCTP_PRIMARY_ADDR,
						(char*)&prim,
						&prim_len);
			if (ret < 0) {
				log_print("getsockopt/sctp_primary_addr on "
					  "new assoc %d failed : %d",
					  (int)sn->sn_assoc_change.sac_assoc_id,
					  ret);

				/* Retry INIT later */
				new_con = assoc2con(sn->sn_assoc_change.sac_assoc_id);
				if (new_con)
					clear_bit(CF_CONNECT_PENDING, &con->flags);
				return;
			}
			make_sockaddr(&prim.ssp_addr, 0, &addr_len);
			if (addr_to_nodeid(&prim.ssp_addr, &nodeid)) {
				unsigned char *b=(unsigned char *)&prim.ssp_addr;
				log_print("reject connect from unknown addr");
				print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, 
						     b, sizeof(struct sockaddr_storage));
				sctp_send_shutdown(prim.ssp_assoc_id);
				return;
			}

			new_con = nodeid2con(nodeid, GFP_NOFS);
			if (!new_con)
				return;

			/* Peel off a new sock */
			lock_sock(con->sock->sk);
			ret = sctp_do_peeloff(con->sock->sk,
				sn->sn_assoc_change.sac_assoc_id,
				&new_con->sock);
			release_sock(con->sock->sk);
			if (ret < 0) {
				log_print("Can't peel off a socket for "
					  "connection %d to node %d: err=%d",
					  (int)sn->sn_assoc_change.sac_assoc_id,
					  nodeid, ret);
				return;
			}
			add_sock(new_con->sock, new_con);

			linger.l_onoff = 1;
			linger.l_linger = 0;
			ret = kernel_setsockopt(new_con->sock, SOL_SOCKET, SO_LINGER,
						(char *)&linger, sizeof(linger));
			if (ret < 0)
				log_print("set socket option SO_LINGER failed");

			log_print("connecting to %d sctp association %d",
				 nodeid, (int)sn->sn_assoc_change.sac_assoc_id);

			new_con->sctp_assoc = sn->sn_assoc_change.sac_assoc_id;
			new_con->try_new_addr = false;
			/* Send any pending writes */
			clear_bit(CF_CONNECT_PENDING, &new_con->flags);
			clear_bit(CF_INIT_PENDING, &new_con->flags);
			if (!test_and_set_bit(CF_WRITE_PENDING, &new_con->flags)) {
				queue_work(send_workqueue, &new_con->swork);
			}
			if (!test_and_set_bit(CF_READ_PENDING, &new_con->flags))
				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;

		case SCTP_CANT_STR_ASSOC:
		{
			/* Will retry init when we get the send failed notification */
			log_print("Can't start SCTP association - retrying");
		}
		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);
		}
	default:
		; /* fall through */
	}
}

/* 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;

	mutex_lock(&connections_lock);
	if (!dlm_allow_conn) {
		mutex_unlock(&connections_lock);
		return -1;
	}
	mutex_unlock(&connections_lock);

	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 (addr_to_nodeid(&peeraddr, &nodeid)) {
		unsigned char *b=(unsigned char *)&peeraddr;
		log_print("connect from non cluster node");
		print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, 
				     b, sizeof(struct sockaddr_storage));
		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_NOFS);
	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_NOFS);
			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;
		}