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;