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

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * 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>
 *
 * 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:
 */

#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/interrupt.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/net.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>		/* for proc_net_* */
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <linux/rcupdate_wait.h>

#include <net/net_namespace.h>
#include <net/ip_vs.h>


#ifndef CONFIG_IP_VS_TAB_BITS
#define CONFIG_IP_VS_TAB_BITS	12
#endif

/*
 * Connection hash size. Default is what was selected at compile time.
*/
static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444);
MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size");

/* size and mask values */
int ip_vs_conn_tab_size __read_mostly;
static int ip_vs_conn_tab_mask __read_mostly;

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

/*  SLAB cache for IPVS connections */
static struct kmem_cache *ip_vs_conn_cachep __read_mostly;

/*  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 __read_mostly;

/*
 *  Fine locking granularity for big connection hash table
 */
#define CT_LOCKARRAY_BITS  5
#define CT_LOCKARRAY_SIZE  (1<<CT_LOCKARRAY_BITS)
#define CT_LOCKARRAY_MASK  (CT_LOCKARRAY_SIZE-1)

/* We need an addrstrlen that works with or without v6 */
#ifdef CONFIG_IP_VS_IPV6
#define IP_VS_ADDRSTRLEN INET6_ADDRSTRLEN
#else
#define IP_VS_ADDRSTRLEN (8+1)
#endif

struct ip_vs_aligned_lock
{
	spinlock_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_write_lock_bh(unsigned int key)
{
	spin_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}

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

static void ip_vs_conn_expire(struct timer_list *t);

/*
 *	Returns hash value for IPVS connection entry
 */
static unsigned int ip_vs_conn_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto,
				       const union nf_inet_addr *addr,
				       __be16 port)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd),
				    (__force u32)port, proto, ip_vs_conn_rnd) ^
			((size_t)ipvs>>8)) & ip_vs_conn_tab_mask;
#endif
	return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto,
			    ip_vs_conn_rnd) ^
		((size_t)ipvs>>8)) & ip_vs_conn_tab_mask;
}

static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p,
					     bool inverse)
{
	const union nf_inet_addr *addr;
	__be16 port;

	if (p->pe_data && p->pe->hashkey_raw)
		return p->pe->hashkey_raw(p, ip_vs_conn_rnd, inverse) &
			ip_vs_conn_tab_mask;

	if (likely(!inverse)) {
		addr = p->caddr;
		port = p->cport;
	} else {
		addr = p->vaddr;
		port = p->vport;
	}

	return ip_vs_conn_hashkey(p->ipvs, p->af, p->protocol, addr, port);
}

static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp)
{
	struct ip_vs_conn_param p;

	ip_vs_conn_fill_param(cp->ipvs, cp->af, cp->protocol,
			      &cp->caddr, cp->cport, NULL, 0, &p);

	if (cp->pe) {
		p.pe = cp->pe;
		p.pe_data = cp->pe_data;
		p.pe_data_len = cp->pe_data_len;
	}

	return ip_vs_conn_hashkey_param(&p, false);
}

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

	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
		return 0;

	/* Hash by protocol, client address and port */
	hash = ip_vs_conn_hashkey_conn(cp);

	ct_write_lock_bh(hash);
	spin_lock(&cp->lock);

	if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
		cp->flags |= IP_VS_CONN_F_HASHED;
		refcount_inc(&cp->refcnt);
		hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]);
		ret = 1;
	} else {
		pr_err("%s(): request for already hashed, called from %pS\n",
		       __func__, __builtin_return_address(0));
		ret = 0;
	}

	spin_unlock(&cp->lock);
	ct_write_unlock_bh(hash);

	return ret;
}


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

	/* unhash it and decrease its reference counter */
	hash = ip_vs_conn_hashkey_conn(cp);

	ct_write_lock_bh(hash);
	spin_lock(&cp->lock);

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

	spin_unlock(&cp->lock);
	ct_write_unlock_bh(hash);

	return ret;
}

/* Try to unlink ip_vs_conn from ip_vs_conn_tab.
 * returns bool success.
 */
static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
{
	unsigned int hash;
	bool ret = false;

	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
		return refcount_dec_if_one(&cp->refcnt);

	hash = ip_vs_conn_hashkey_conn(cp);

	ct_write_lock_bh(hash);
	spin_lock(&cp->lock);

	if (cp->flags & IP_VS_CONN_F_HASHED) {
		/* Decrease refcnt and unlink conn only if we are last user */
		if (refcount_dec_if_one(&cp->refcnt)) {
			hlist_del_rcu(&cp->c_list);
			cp->flags &= ~IP_VS_CONN_F_HASHED;
			ret = true;
		}
	}

	spin_unlock(&cp->lock);
	ct_write_unlock_bh(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.
 *	p->caddr, p->cport: pkt source address (foreign host)
 *	p->vaddr, p->vport: pkt dest address (load balancer)
 */
static inline struct ip_vs_conn *
__ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
{
	unsigned int hash;
	struct ip_vs_conn *cp;

	hash = ip_vs_conn_hashkey_param(p, false);

	rcu_read_lock();

	hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
		if (p->cport == cp->cport && p->vport == cp->vport &&
		    cp->af == p->af &&
		    ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
		    ip_vs