tmp_suning_uos_patched/net/ipv6/inet6_hashtables.c
Eric Dumazet c25eb3bfb9 net: Convert TCP/DCCP listening hash tables to use RCU
This is the last step to be able to perform full RCU lookups
in __inet_lookup() : After established/timewait tables, we
add RCU lookups to listening hash table.

The only trick here is that a socket of a given type (TCP ipv4,
TCP ipv6, ...) can now flight between two different tables
(established and listening) during a RCU grace period, so we
must use different 'nulls' end-of-chain values for two tables.

We define a large value :

#define LISTENING_NULLS_BASE (1U << 29)

So that slots in listening table are guaranteed to have different
end-of-chain values than slots in established table. A reader can
still detect it finished its lookup in the right chain.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-23 17:22:55 -08:00

293 lines
7.8 KiB
C

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Generic INET6 transport hashtables
*
* Authors: Lotsa people, from code originally in tcp, generalised here
* by Arnaldo Carvalho de Melo <acme@mandriva.com>
*
* 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.
*/
#include <linux/module.h>
#include <linux/random.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/ip.h>
void __inet6_hash(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
WARN_ON(!sk_unhashed(sk));
if (sk->sk_state == TCP_LISTEN) {
struct inet_listen_hashbucket *ilb;
ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
spin_lock(&ilb->lock);
__sk_nulls_add_node_rcu(sk, &ilb->head);
spin_unlock(&ilb->lock);
} else {
unsigned int hash;
struct hlist_nulls_head *list;
spinlock_t *lock;
sk->sk_hash = hash = inet6_sk_ehashfn(sk);
list = &inet_ehash_bucket(hashinfo, hash)->chain;
lock = inet_ehash_lockp(hashinfo, hash);
spin_lock(lock);
__sk_nulls_add_node_rcu(sk, list);
spin_unlock(lock);
}
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
}
EXPORT_SYMBOL(__inet6_hash);
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
* we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
*
* The sockhash lock must be held as a reader here.
*/
struct sock *__inet6_lookup_established(struct net *net,
struct inet_hashinfo *hashinfo,
const struct in6_addr *saddr,
const __be16 sport,
const struct in6_addr *daddr,
const u16 hnum,
const int dif)
{
struct sock *sk;
const struct hlist_nulls_node *node;
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
unsigned int slot = hash & (hashinfo->ehash_size - 1);
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
rcu_read_lock();
begin:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
/* For IPV6 do the cheaper port and family tests first. */
if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt)))
goto begintw;
if (!INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
sock_put(sk);
goto begin;
}
goto out;
}
}
if (get_nulls_value(node) != slot)
goto begin;
begintw:
/* Must check for a TIME_WAIT'er before going to listener hash. */
sk_nulls_for_each_rcu(sk, node, &head->twchain) {
if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) {
sk = NULL;
goto out;
}
if (!INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) {
sock_put(sk);
goto begintw;
}
goto out;
}
}
if (get_nulls_value(node) != slot)
goto begintw;
sk = NULL;
out:
rcu_read_unlock();
return sk;
}
EXPORT_SYMBOL(__inet6_lookup_established);
static int inline compute_score(struct sock *sk, struct net *net,
const unsigned short hnum,
const struct in6_addr *daddr,
const int dif)
{
int score = -1;
if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum &&
sk->sk_family == PF_INET6) {
const struct ipv6_pinfo *np = inet6_sk(sk);
score = 1;
if (!ipv6_addr_any(&np->rcv_saddr)) {
if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
return -1;
score++;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
return -1;
score++;
}
}
return score;
}
struct sock *inet6_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo, const struct in6_addr *daddr,
const unsigned short hnum, const int dif)
{
struct sock *sk;
const struct hlist_nulls_node *node;
struct sock *result;
int score, hiscore;
unsigned int hash = inet_lhashfn(net, hnum);
struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash];
rcu_read_lock();
begin:
result = NULL;
hiscore = -1;
sk_nulls_for_each(sk, node, &ilb->head) {
score = compute_score(sk, net, hnum, daddr, dif);
if (score > hiscore) {
hiscore = score;
result = sk;
}
}
/*
* if the nulls value we got at the end of this lookup is
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE)
goto begin;
if (result) {
if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
result = NULL;
else if (unlikely(compute_score(result, net, hnum, daddr,
dif) < hiscore)) {
sock_put(result);
goto begin;
}
}
rcu_read_unlock();
return result;
}
EXPORT_SYMBOL_GPL(inet6_lookup_listener);
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
const int dif)
{
struct sock *sk;
local_bh_disable();
sk = __inet6_lookup(net, hashinfo, saddr, sport, daddr, ntohs(dport), dif);
local_bh_enable();
return sk;
}
EXPORT_SYMBOL_GPL(inet6_lookup);
static int __inet6_check_established(struct inet_timewait_death_row *death_row,
struct sock *sk, const __u16 lport,
struct inet_timewait_sock **twp)
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
struct inet_sock *inet = inet_sk(sk);
const struct ipv6_pinfo *np = inet6_sk(sk);
const struct in6_addr *daddr = &np->rcv_saddr;
const struct in6_addr *saddr = &np->daddr;
const int dif = sk->sk_bound_dev_if;
const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport);
struct net *net = sock_net(sk);
const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
inet->dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_nulls_node *node;
struct inet_timewait_sock *tw;
spin_lock(lock);
/* Check TIME-WAIT sockets first. */
sk_nulls_for_each(sk2, node, &head->twchain) {
tw = inet_twsk(sk2);
if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) {
if (twsk_unique(sk, sk2, twp))
goto unique;
else
goto not_unique;
}
}
tw = NULL;
/* And established part... */
sk_nulls_for_each(sk2, node, &head->chain) {
if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif))
goto not_unique;
}
unique:
/* Must record num and sport now. Otherwise we will see
* in hash table socket with a funny identity. */
inet->num = lport;
inet->sport = htons(lport);
WARN_ON(!sk_unhashed(sk));
__sk_nulls_add_node_rcu(sk, &head->chain);
sk->sk_hash = hash;
spin_unlock(lock);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
if (twp != NULL) {
*twp = tw;
NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
} else if (tw != NULL) {
/* Silly. Should hash-dance instead... */
inet_twsk_deschedule(tw, death_row);
NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
inet_twsk_put(tw);
}
return 0;
not_unique:
spin_unlock(lock);
return -EADDRNOTAVAIL;
}
static inline u32 inet6_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ipv6_pinfo *np = inet6_sk(sk);
return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32,
np->daddr.s6_addr32,
inet->dport);
}
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
return __inet_hash_connect(death_row, sk, inet6_sk_port_offset(sk),
__inet6_check_established, __inet6_hash);
}
EXPORT_SYMBOL_GPL(inet6_hash_connect);