ip_vs_conn.c

linux-2.6.15.6

	 * dest will be either in service's destination list
	 * or in the trash.
	 */
	atomic_dec(&dest->refcnt);
}


/*
 *	Checking if the destination of a connection template is available.
 *	If available, return 1, otherwise invalidate this connection
 *	template and return 0.
 */
int ip_vs_check_template(struct ip_vs_conn *ct)
{
	struct ip_vs_dest *dest = ct->dest;

	/*
	 * Checking the dest server status.
	 */
	if ((dest == NULL) ||
	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) || 
	    (sysctl_ip_vs_expire_quiescent_template && 
	     (atomic_read(&dest->weight) == 0))) {
		IP_VS_DBG(9, "check_template: dest not available for "
			  "protocol %s s:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
			  "-> d:%u.%u.%u.%u:%d\n",
			  ip_vs_proto_name(ct->protocol),
			  NIPQUAD(ct->caddr), ntohs(ct->cport),
			  NIPQUAD(ct->vaddr), ntohs(ct->vport),
			  NIPQUAD(ct->daddr), ntohs(ct->dport));

		/*
		 * Invalidate the connection template
		 */
		if (ct->vport != 65535) {
			if (ip_vs_conn_unhash(ct)) {
				ct->dport = 65535;
				ct->vport = 65535;
				ct->cport = 0;
				ip_vs_conn_hash(ct);
			}
		}

		/*
		 * Simply decrease the refcnt of the template,
		 * don't restart its timer.
		 */
		atomic_dec(&ct->refcnt);
		return 0;
	}
	return 1;
}

static void ip_vs_conn_expire(unsigned long data)
{
	struct ip_vs_conn *cp = (struct ip_vs_conn *)data;

	cp->timeout = 60*HZ;

	/*
	 *	hey, I'm using it
	 */
	atomic_inc(&cp->refcnt);

	/*
	 *	do I control anybody?
	 */
	if (atomic_read(&cp->n_control))
		goto expire_later;

	/*
	 *	unhash it if it is hashed in the conn table
	 */
	if (!ip_vs_conn_unhash(cp))
		goto expire_later;

	/*
	 *	refcnt==1 implies I'm the only one referrer
	 */
	if (likely(atomic_read(&cp->refcnt) == 1)) {
		/* delete the timer if it is activated by other users */
		if (timer_pending(&cp->timer))
			del_timer(&cp->timer);

		/* does anybody control me? */
		if (cp->control)
			ip_vs_control_del(cp);

		if (unlikely(cp->app != NULL))
			ip_vs_unbind_app(cp);
		ip_vs_unbind_dest(cp);
		if (cp->flags & IP_VS_CONN_F_NO_CPORT)
			atomic_dec(&ip_vs_conn_no_cport_cnt);
		atomic_dec(&ip_vs_conn_count);

		kmem_cache_free(ip_vs_conn_cachep, cp);
		return;
	}

	/* hash it back to the table */
	ip_vs_conn_hash(cp);

  expire_later:
	IP_VS_DBG(7, "delayed: refcnt-1=%d conn.n_control=%d\n",
		  atomic_read(&cp->refcnt)-1,
		  atomic_read(&cp->n_control));

	ip_vs_conn_put(cp);
}


void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
{
	if (del_timer(&cp->timer))
		mod_timer(&cp->timer, jiffies);
}


/*
 *	Create a new connection entry and hash it into the ip_vs_conn_tab
 */
struct ip_vs_conn *
ip_vs_conn_new(int proto, __u32 caddr, __u16 cport, __u32 vaddr, __u16 vport,
	       __u32 daddr, __u16 dport, unsigned flags,
	       struct ip_vs_dest *dest)
{
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp = ip_vs_proto_get(proto);

	cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC);
	if (cp == NULL) {
		IP_VS_ERR_RL("ip_vs_conn_new: no memory available.\n");
		return NULL;
	}

	memset(cp, 0, sizeof(*cp));
	INIT_LIST_HEAD(&cp->c_list);
	init_timer(&cp->timer);
	cp->timer.data     = (unsigned long)cp;
	cp->timer.function = ip_vs_conn_expire;
	cp->protocol	   = proto;
	cp->caddr	   = caddr;
	cp->cport	   = cport;
	cp->vaddr	   = vaddr;
	cp->vport	   = vport;
	cp->daddr          = daddr;
	cp->dport          = dport;
	cp->flags	   = flags;
	spin_lock_init(&cp->lock);

	/*
	 * Set the entry is referenced by the current thread before hashing
	 * it in the table, so that other thread run ip_vs_random_dropentry
	 * but cannot drop this entry.
	 */
	atomic_set(&cp->refcnt, 1);

	atomic_set(&cp->n_control, 0);
	atomic_set(&cp->in_pkts, 0);

	atomic_inc(&ip_vs_conn_count);
	if (flags & IP_VS_CONN_F_NO_CPORT)
		atomic_inc(&ip_vs_conn_no_cport_cnt);

	/* Bind the connection with a destination server */
	ip_vs_bind_dest(cp, dest);

	/* Set its state and timeout */
	cp->state = 0;
	cp->timeout = 3*HZ;

	/* Bind its packet transmitter */
	ip_vs_bind_xmit(cp);

	if (unlikely(pp && atomic_read(&pp->appcnt)))
		ip_vs_bind_app(cp, pp);

	/* Hash it in the ip_vs_conn_tab finally */
	ip_vs_conn_hash(cp);

	return cp;
}


/*
 *	/proc/net/ip_vs_conn entries
 */
#ifdef CONFIG_PROC_FS

static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
{
	int idx;
	struct ip_vs_conn *cp;
	
	for(idx = 0; idx < IP_VS_CONN_TAB_SIZE; idx++) {
		ct_read_lock_bh(idx);
		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
			if (pos-- == 0) {
				seq->private = &ip_vs_conn_tab[idx];
				return cp;
			}
		}
		ct_read_unlock_bh(idx);
	}

	return NULL;
}

static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
{
	seq->private = NULL;
	return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
}

static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct ip_vs_conn *cp = v;
	struct list_head *e, *l = seq->private;
	int idx;

	++*pos;
	if (v == SEQ_START_TOKEN) 
		return ip_vs_conn_array(seq, 0);

	/* more on same hash chain? */
	if ((e = cp->c_list.next) != l)
		return list_entry(e, struct ip_vs_conn, c_list);

	idx = l - ip_vs_conn_tab;
	ct_read_unlock_bh(idx);

	while (++idx < IP_VS_CONN_TAB_SIZE) {
		ct_read_lock_bh(idx);
		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
			seq->private = &ip_vs_conn_tab[idx];
			return cp;
		}	
		ct_read_unlock_bh(idx);
	}
	seq->private = NULL;
	return NULL;
}

static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
{
	struct list_head *l = seq->private;

	if (l)
		ct_read_unlock_bh(l - ip_vs_conn_tab);
}

static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
{

	if (v == SEQ_START_TOKEN)
		seq_puts(seq,
   "Pro FromIP   FPrt ToIP     TPrt DestIP   DPrt State       Expires\n");
	else {
		const struct ip_vs_conn *cp = v;

		seq_printf(seq,
			"%-3s %08X %04X %08X %04X %08X %04X %-11s %7lu\n",
				ip_vs_proto_name(cp->protocol),
				ntohl(cp->caddr), ntohs(cp->cport),
				ntohl(cp->vaddr), ntohs(cp->vport),
				ntohl(cp->daddr), ntohs(cp->dport),
				ip_vs_state_name(cp->protocol, cp->state),
				(cp->timer.expires-jiffies)/HZ);
	}
	return 0;
}

static struct seq_operations ip_vs_conn_seq_ops = {
	.start = ip_vs_conn_seq_start,
	.next  = ip_vs_conn_seq_next,
	.stop  = ip_vs_conn_seq_stop,
	.show  = ip_vs_conn_seq_show,
};

static int ip_vs_conn_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &ip_vs_conn_seq_ops);
}

static struct file_operations ip_vs_conn_fops = {
	.owner	 = THIS_MODULE,
	.open    = ip_vs_conn_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};
#endif


/*
 *      Randomly drop connection entries before running out of memory
 */
static inline int todrop_entry(struct ip_vs_conn *cp)
{
	/*
	 * The drop rate array needs tuning for real environments.
	 * Called from timer bh only => no locking
	 */
	static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8};
	static char todrop_counter[9] = {0};
	int i;

	/* if the conn entry hasn't lasted for 60 seconds, don't drop it.
	   This will leave enough time for normal connection to get
	   through. */
	if (time_before(cp->timeout + jiffies, cp->timer.expires + 60*HZ))
		return 0;

	/* Don't drop the entry if its number of incoming packets is not
	   located in [0, 8] */
	i = atomic_read(&cp->in_pkts);
	if (i > 8 || i < 0) return 0;

	if (!todrop_rate[i]) return 0;
	if (--todrop_counter[i] > 0) return 0;

	todrop_counter[i] = todrop_rate[i];
	return 1;
}

/* Called from keventd and must protect itself from softirqs */
void ip_vs_random_dropentry(void)
{
	int idx;
	struct ip_vs_conn *cp;

	/*
	 * Randomly scan 1/32 of the whole table every second
	 */
	for (idx = 0; idx < (IP_VS_CONN_TAB_SIZE>>5); idx++) {
		unsigned hash = net_random() & IP_VS_CONN_TAB_MASK;

		/*
		 *  Lock is actually needed in this loop.
		 */
		ct_write_lock_bh(hash);

		list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
			if (cp->flags & IP_VS_CONN_F_TEMPLATE)
				/* connection template */
				continue;

			if (cp->protocol == IPPROTO_TCP) {
				switch(cp->state) {
				case IP_VS_TCP_S_SYN_RECV:
				case IP_VS_TCP_S_SYNACK:
					break;

				case IP_VS_TCP_S_ESTABLISHED:
					if (todrop_entry(cp))
						break;
					continue;

				default:
					continue;
				}
			} else {
				if (!todrop_entry(cp))
					continue;
			}

			IP_VS_DBG(4, "del connection\n");
			ip_vs_conn_expire_now(cp);
			if (cp->control) {
				IP_VS_DBG(4, "del conn template\n");
				ip_vs_conn_expire_now(cp->control);
			}
		}
		ct_write_unlock_bh(hash);
	}
}


/*
 *      Flush all the connection entries in the ip_vs_conn_tab
 */
static void ip_vs_conn_flush(void)
{
	int idx;
	struct ip_vs_conn *cp;

  flush_again:
	for (idx=0; idx<IP_VS_CONN_TAB_SIZE; idx++) {
		/*
		 *  Lock is actually needed in this loop.
		 */
		ct_write_lock_bh(idx);

		list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {

			IP_VS_DBG(4, "del connection\n");
			ip_vs_conn_expire_now(cp);
			if (cp->control) {
				IP_VS_DBG(4, "del conn template\n");
				ip_vs_conn_expire_now(cp->control);
			}
		}
		ct_write_unlock_bh(idx);
	}

	/* the counter may be not NULL, because maybe some conn entries
	   are run by slow timer handler or unhashed but still referred */
	if (atomic_read(&ip_vs_conn_count) != 0) {
		schedule();
		goto flush_again;
	}
}


int ip_vs_conn_init(void)
{
	int idx;

	/*
	 * Allocate the connection hash table and initialize its list heads
	 */
	ip_vs_conn_tab = vmalloc(IP_VS_CONN_TAB_SIZE*sizeof(struct list_head));
	if (!ip_vs_conn_tab)
		return -ENOMEM;

	/* Allocate ip_vs_conn slab cache */
	ip_vs_conn_cachep = kmem_cache_create("ip_vs_conn",
					      sizeof(struct ip_vs_conn), 0,
					      SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!ip_vs_conn_cachep) {
		vfree(ip_vs_conn_tab);
		return -ENOMEM;
	}

	IP_VS_INFO("Connection hash table configured "
		   "(size=%d, memory=%ldKbytes)\n",
		   IP_VS_CONN_TAB_SIZE,
		   (long)(IP_VS_CONN_TAB_SIZE*sizeof(struct list_head))/1024);
	IP_VS_DBG(0, "Each connection entry needs %Zd bytes at least\n",
		  sizeof(struct ip_vs_conn));

	for (idx = 0; idx < IP_VS_CONN_TAB_SIZE; idx++) {
		INIT_LIST_HEAD(&ip_vs_conn_tab[idx]);
	}

	for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++)  {
		rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
	}

	proc_net_fops_create("ip_vs_conn", 0, &ip_vs_conn_fops);

	/* calculate the random value for connection hash */
	get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd));

	return 0;
}


void ip_vs_conn_cleanup(void)
{
	/* flush all the connection entries first */
	ip_vs_conn_flush();

	/* Release the empty cache */
	kmem_cache_destroy(ip_vs_conn_cachep);
	proc_net_remove("ip_vs_conn");
	vfree(ip_vs_conn_tab);
}