path: root/fs/dlm/lowcomms-sctp.c

/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2006 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 it's
 * 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.
 *
 * I don't see any problem with the recv thread executing the locking
 * code on behalf of remote processes as the locking code is
 * short, efficient and never (well, hardly ever) waits.
 *
 */

#include <asm/ioctls.h>
#include <net/sock.h>
#include <net/tcp.h>
#include <net/sctp/user.h>
#include <linux/pagemap.h>
#include <linux/socket.h>
#include <linux/idr.h>

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

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

/* One of these per connected node */

#define NI_INIT_PENDING 1
#define NI_WRITE_PENDING 2

struct nodeinfo {
	spinlock_t		lock;
	sctp_assoc_t		assoc_id;
	unsigned long		flags;
	struct list_head	write_list; /* nodes with pending writes */
	struct list_head	writequeue; /* outgoing writequeue_entries */
	spinlock_t		writequeue_lock;
	int			nodeid;
	struct work_struct      swork; /* Send workqueue */
	struct work_struct      lwork; /* Locking workqueue */
};

static DEFINE_IDR(nodeinfo_idr);
static DECLARE_RWSEM(nodeinfo_lock);
static int max_nodeid;

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

/* Just the one of these, now. But this struct keeps
   the connection-specific variables together */

#define CF_READ_PENDING 1

struct connection {
	struct socket           *sock;
	unsigned long		flags;
	struct page             *rx_page;
	atomic_t		waiting_requests;
	struct cbuf		cb;
	int                     eagain_flag;
	struct work_struct      work; /* Send workqueue */
};

/* 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 nodeinfo         *ni;
};

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;
}

/* List of nodes which have writes pending */
static LIST_HEAD(