path: root/net/ipv4/ipvs/ip_vs_conn.c

/*
 * 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.
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              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/interrupt.h>
#include <linux/in.h>
#include <linux/net.h>
#include <linux/kernel.h>
#include <linux/module.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/net_namespace.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 struct kmem_cache *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, __be32 addr, __be16 port)
{
	return jhash_3words((__force u32)addr, (__force u32)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, __be32 s_addr, __be16 s_port,