ip_vs_conn.c

linux-2.6.15.6

/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the Netfilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Version:     $Id: ip_vs_conn.c,v 1.31 2003/04/18 09:03:16 wensong Exp $
 *
 * Authors:     Wensong Zhang <[e-mail]>
 *              Peter Kese <[e-mail]>
 *              Julian Anastasov <[e-mail]>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese,
 * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms
 * and others. Many code here is taken from IP MASQ code of kernel 2.2.
 *
 * Changes:
 *
 */

#include <linux/kernel.h>
#include <linux/vmalloc.h>
#include <linux/proc_fs.h>		/* for proc_net_* */
#include <linux/seq_file.h>
#include <linux/jhash.h>
#include <linux/random.h>

#include <net/ip_vs.h>


/*
 *  Connection hash table: for input and output packets lookups of IPVS
 */
static struct list_head *ip_vs_conn_tab;

/*  SLAB cache for IPVS connections */
static kmem_cache_t *ip_vs_conn_cachep __read_mostly;

/*  counter for current IPVS connections */
static atomic_t ip_vs_conn_count = ATOMIC_INIT(0);

/*  counter for no client port connections */
static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0);

/* random value for IPVS connection hash */
static unsigned int ip_vs_conn_rnd;

/*
 *  Fine locking granularity for big connection hash table
 */
#define CT_LOCKARRAY_BITS  4
#define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
#define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)

struct ip_vs_aligned_lock
{
	rwlock_t	l;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));

/* lock array for conn table */
static struct ip_vs_aligned_lock
__ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned;

static inline void ct_read_lock(unsigned key)
{
	read_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_read_unlock(unsigned key)
{
	read_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_write_lock(unsigned key)
{
	write_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_write_unlock(unsigned key)
{
	write_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_read_lock_bh(unsigned key)
{
	read_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_read_unlock_bh(unsigned key)
{
	read_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_write_lock_bh(unsigned key)
{
	write_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

static inline void ct_write_unlock_bh(unsigned key)
{
	write_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}


/*
 *	Returns hash value for IPVS connection entry
 */
static unsigned int ip_vs_conn_hashkey(unsigned proto, __u32 addr, __u16 port)
{
	return jhash_3words(addr, port, proto, ip_vs_conn_rnd)
		& IP_VS_CONN_TAB_MASK;
}


/*
 *	Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port.
 *	returns bool success.
 */
static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
{
	unsigned hash;
	int ret;

	/* Hash by protocol, client address and port */
	hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport);

	ct_write_lock(hash);

	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
		list_add(&cp->c_list, &ip_vs_conn_tab[hash]);
		cp->flags |= IP_VS_CONN_F_HASHED;
		atomic_inc(&cp->refcnt);
		ret = 1;
	} else {
		IP_VS_ERR("ip_vs_conn_hash(): request for already hashed, "
			  "called from %p\n", __builtin_return_address(0));
		ret = 0;
	}

	ct_write_unlock(hash);

	return ret;
}


/*
 *	UNhashes ip_vs_conn from ip_vs_conn_tab.
 *	returns bool success.
 */
static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
{
	unsigned hash;
	int ret;

	/* unhash it and decrease its reference counter */
	hash = ip_vs_conn_hashkey(cp->protocol, cp->caddr, cp->cport);

	ct_write_lock(hash);

	if (cp->flags & IP_VS_CONN_F_HASHED) {
		list_del(&cp->c_list);
		cp->flags &= ~IP_VS_CONN_F_HASHED;
		atomic_dec(&cp->refcnt);
		ret = 1;
	} else
		ret = 0;

	ct_write_unlock(hash);

	return ret;
}


/*
 *  Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
 *  Called for pkts coming from OUTside-to-INside.
 *	s_addr, s_port: pkt source address (foreign host)
 *	d_addr, d_port: pkt dest address (load balancer)
 */
static inline struct ip_vs_conn *__ip_vs_conn_in_get
(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port)
{
	unsigned hash;
	struct ip_vs_conn *cp;

	hash = ip_vs_conn_hashkey(protocol, s_addr, s_port);

	ct_read_lock(hash);

	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
		if (s_addr==cp->caddr && s_port==cp->cport &&
		    d_port==cp->vport && d_addr==cp->vaddr &&
		    ((!s_port) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
		    protocol==cp->protocol) {
			/* HIT */
			atomic_inc(&cp->refcnt);
			ct_read_unlock(hash);
			return cp;
		}
	}

	ct_read_unlock(hash);

	return NULL;
}

struct ip_vs_conn *ip_vs_conn_in_get
(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port)
{
	struct ip_vs_conn *cp;

	cp = __ip_vs_conn_in_get(protocol, s_addr, s_port, d_addr, d_port);
	if (!cp && atomic_read(&ip_vs_conn_no_cport_cnt))
		cp = __ip_vs_conn_in_get(protocol, s_addr, 0, d_addr, d_port);

	IP_VS_DBG(7, "lookup/in %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n",
		  ip_vs_proto_name(protocol),
		  NIPQUAD(s_addr), ntohs(s_port),
		  NIPQUAD(d_addr), ntohs(d_port),
		  cp?"hit":"not hit");

	return cp;
}

/* Get reference to connection template */
struct ip_vs_conn *ip_vs_ct_in_get
(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port)
{
	unsigned hash;
	struct ip_vs_conn *cp;

	hash = ip_vs_conn_hashkey(protocol, s_addr, s_port);

	ct_read_lock(hash);

	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
		if (s_addr==cp->caddr && s_port==cp->cport &&
		    d_port==cp->vport && d_addr==cp->vaddr &&
		    cp->flags & IP_VS_CONN_F_TEMPLATE &&
		    protocol==cp->protocol) {
			/* HIT */
			atomic_inc(&cp->refcnt);
			goto out;
		}
	}
	cp = NULL;

  out:
	ct_read_unlock(hash);

	IP_VS_DBG(7, "template lookup/in %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n",
		  ip_vs_proto_name(protocol),
		  NIPQUAD(s_addr), ntohs(s_port),
		  NIPQUAD(d_addr), ntohs(d_port),
		  cp?"hit":"not hit");

	return cp;
}

/*
 *  Gets ip_vs_conn associated with supplied parameters in the ip_vs_conn_tab.
 *  Called for pkts coming from inside-to-OUTside.
 *	s_addr, s_port: pkt source address (inside host)
 *	d_addr, d_port: pkt dest address (foreign host)
 */
struct ip_vs_conn *ip_vs_conn_out_get
(int protocol, __u32 s_addr, __u16 s_port, __u32 d_addr, __u16 d_port)
{
	unsigned hash;
	struct ip_vs_conn *cp, *ret=NULL;

	/*
	 *	Check for "full" addressed entries
	 */
	hash = ip_vs_conn_hashkey(protocol, d_addr, d_port);

	ct_read_lock(hash);

	list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
		if (d_addr == cp->caddr && d_port == cp->cport &&
		    s_port == cp->dport && s_addr == cp->daddr &&
		    protocol == cp->protocol) {
			/* HIT */
			atomic_inc(&cp->refcnt);
			ret = cp;
			break;
		}
	}

	ct_read_unlock(hash);

	IP_VS_DBG(7, "lookup/out %s %u.%u.%u.%u:%d->%u.%u.%u.%u:%d %s\n",
		  ip_vs_proto_name(protocol),
		  NIPQUAD(s_addr), ntohs(s_port),
		  NIPQUAD(d_addr), ntohs(d_port),
		  ret?"hit":"not hit");

	return ret;
}


/*
 *      Put back the conn and restart its timer with its timeout
 */
void ip_vs_conn_put(struct ip_vs_conn *cp)
{
	/* reset it expire in its timeout */
	mod_timer(&cp->timer, jiffies+cp->timeout);

	__ip_vs_conn_put(cp);
}


/*
 *	Fill a no_client_port connection with a client port number
 */
void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __u16 cport)
{
	if (ip_vs_conn_unhash(cp)) {
		spin_lock(&cp->lock);
		if (cp->flags & IP_VS_CONN_F_NO_CPORT) {
			atomic_dec(&ip_vs_conn_no_cport_cnt);
			cp->flags &= ~IP_VS_CONN_F_NO_CPORT;
			cp->cport = cport;
		}
		spin_unlock(&cp->lock);

		/* hash on new dport */
		ip_vs_conn_hash(cp);
	}
}


/*
 *	Bind a connection entry with the corresponding packet_xmit.
 *	Called by ip_vs_conn_new.
 */
static inline void ip_vs_bind_xmit(struct ip_vs_conn *cp)
{
	switch (IP_VS_FWD_METHOD(cp)) {
	case IP_VS_CONN_F_MASQ:
		cp->packet_xmit = ip_vs_nat_xmit;
		break;

	case IP_VS_CONN_F_TUNNEL:
		cp->packet_xmit = ip_vs_tunnel_xmit;
		break;

	case IP_VS_CONN_F_DROUTE:
		cp->packet_xmit = ip_vs_dr_xmit;
		break;

	case IP_VS_CONN_F_LOCALNODE:
		cp->packet_xmit = ip_vs_null_xmit;
		break;

	case IP_VS_CONN_F_BYPASS:
		cp->packet_xmit = ip_vs_bypass_xmit;
		break;
	}
}


static inline int ip_vs_dest_totalconns(struct ip_vs_dest *dest)
{
	return atomic_read(&dest->activeconns)
		+ atomic_read(&dest->inactconns);
}

/*
 *	Bind a connection entry with a virtual service destination
 *	Called just after a new connection entry is created.
 */
static inline void
ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
{
	/* if dest is NULL, then return directly */
	if (!dest)
		return;

	/* Increase the refcnt counter of the dest */
	atomic_inc(&dest->refcnt);

	/* Bind with the destination and its corresponding transmitter */
	cp->flags |= atomic_read(&dest->conn_flags);
	cp->dest = dest;

	IP_VS_DBG(9, "Bind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
		  "d:%u.%u.%u.%u:%d fwd:%c s:%u flg:%X cnt:%d destcnt:%d\n",
		  ip_vs_proto_name(cp->protocol),
		  NIPQUAD(cp->caddr), ntohs(cp->cport),
		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
		  NIPQUAD(cp->daddr), ntohs(cp->dport),
		  ip_vs_fwd_tag(cp), cp->state,
		  cp->flags, atomic_read(&cp->refcnt),
		  atomic_read(&dest->refcnt));

	/* Update the connection counters */
	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
		/* It is a normal connection, so increase the inactive
		   connection counter because it is in TCP SYNRECV
		   state (inactive) or other protocol inacive state */
		atomic_inc(&dest->inactconns);
	} else {
		/* It is a persistent connection/template, so increase
		   the peristent connection counter */
		atomic_inc(&dest->persistconns);
	}

	if (dest->u_threshold != 0 &&
	    ip_vs_dest_totalconns(dest) >= dest->u_threshold)
		dest->flags |= IP_VS_DEST_F_OVERLOAD;
}


/*
 *	Unbind a connection entry with its VS destination
 *	Called by the ip_vs_conn_expire function.
 */
static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
{
	struct ip_vs_dest *dest = cp->dest;

	if (!dest)
		return;

	IP_VS_DBG(9, "Unbind-dest %s c:%u.%u.%u.%u:%d v:%u.%u.%u.%u:%d "
		  "d:%u.%u.%u.%u:%d fwd:%c s:%u flg:%X cnt:%d destcnt:%d\n",
		  ip_vs_proto_name(cp->protocol),
		  NIPQUAD(cp->caddr), ntohs(cp->cport),
		  NIPQUAD(cp->vaddr), ntohs(cp->vport),
		  NIPQUAD(cp->daddr), ntohs(cp->dport),
		  ip_vs_fwd_tag(cp), cp->state,
		  cp->flags, atomic_read(&cp->refcnt),
		  atomic_read(&dest->refcnt));

	/* Update the connection counters */
	if (!(cp->flags & IP_VS_CONN_F_TEMPLATE)) {
		/* It is a normal connection, so decrease the inactconns
		   or activeconns counter */
		if (cp->flags & IP_VS_CONN_F_INACTIVE) {
			atomic_dec(&dest->inactconns);
		} else {
			atomic_dec(&dest->activeconns);
		}
	} else {
		/* It is a persistent connection/template, so decrease
		   the peristent connection counter */
		atomic_dec(&dest->persistconns);
	}

	if (dest->l_threshold != 0) {
		if (ip_vs_dest_totalconns(dest) < dest->l_threshold)
			dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
	} else if (dest->u_threshold != 0) {
		if (ip_vs_dest_totalconns(dest) * 4 < dest->u_threshold * 3)
			dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
	} else {
		if (dest->flags & IP_VS_DEST_F_OVERLOAD)
			dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
	}

	/*
	 * Simply decrease the refcnt of the dest, because the