linux/net/ipv6/inet6_hashtables.c

245 lines
6.7 KiB
C
Raw Normal View History

/*
* 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>
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 12:06:04 +00:00
void __inet6_hash(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_head *list;
rwlock_t *lock;
WARN_ON(!sk_unhashed(sk));
if (sk->sk_state == TCP_LISTEN) {
list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
lock = &hashinfo->lhash_lock;
inet_listen_wlock(hashinfo);
} else {
unsigned int hash;
sk->sk_hash = hash = inet6_sk_ehashfn(sk);
list = &inet_ehash_bucket(hashinfo, hash)->chain;
lock = inet_ehash_lockp(hashinfo, hash);
write_lock(lock);
}
__sk_add_node(sk, list);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock(lock);
}
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_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);
struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
rwlock_t *lock = inet_ehash_lockp(hashinfo, hash);
prefetch(head->chain.first);
read_lock(lock);
sk_for_each(sk, node, &head->chain) {
/* For IPV6 do the cheaper port and family tests first. */
if (INET6_MATCH(sk, net, hash, saddr, daddr, ports, dif))
goto hit; /* You sunk my battleship! */
}
/* Must check for a TIME_WAIT'er before going to listener hash. */
[NET]: change layout of ehash table ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 22:16:46 +00:00
sk_for_each(sk, node, &head->twchain) {
if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif))
goto hit;
}
read_unlock(lock);
return NULL;
hit:
sock_hold(sk);
read_unlock(lock);
return sk;
}
EXPORT_SYMBOL(__inet6_lookup_established);
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_node *node;
struct sock *result = NULL;
int score, hiscore = 0;
read_lock(&hashinfo->lhash_lock);
sk_for_each(sk, node,
&hashinfo->listening_hash[inet_lhashfn(net, hnum)]) {
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))
continue;
score++;
}
if (sk->sk_bound_dev_if) {
if (sk->sk_bound_dev_if != dif)
continue;
score++;
}
if (score == 3) {
result = sk;
break;
}
if (score > hiscore) {
hiscore = score;
result = sk;
}
}
}
if (result)
sock_hold(result);
read_unlock(&hashinfo->lhash_lock);
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);
rwlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_node *node;
struct inet_timewait_sock *tw;
prefetch(head->chain.first);
write_lock(lock);
/* Check TIME-WAIT sockets first. */
[NET]: change layout of ehash table ehash table layout is currently this one : First half of this table is used by sockets not in TIME_WAIT state Second half of it is used by sockets in TIME_WAIT state. This is non optimal because of for a given hash or socket, the two chain heads are located in separate cache lines. Moreover the locks of the second half are never used. If instead of this halving, we use two list heads in inet_ehash_bucket instead of only one, we probably can avoid one cache miss, and reduce ram usage, particularly if sizeof(rwlock_t) is big (various CONFIG_DEBUG_SPINLOCK, CONFIG_DEBUG_LOCK_ALLOC settings). So we still halves the table but we keep together related chains to speedup lookups and socket state change. In this patch I did not try to align struct inet_ehash_bucket, but a future patch could try to make this structure have a convenient size (a power of two or a multiple of L1_CACHE_SIZE). I guess rwlock will just vanish as soon as RCU is plugged into ehash :) , so maybe we dont need to scratch our heads to align the bucket... Note : In case struct inet_ehash_bucket is not a power of two, we could probably change alloc_large_system_hash() (in case it use __get_free_pages()) to free the unused space. It currently allocates a big zone, but the last quarter of it could be freed. Again, this should be a temporary 'problem'. Patch tested on ipv4 tcp only, but should be OK for IPV6 and DCCP. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-08 22:16:46 +00:00
sk_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_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_add_node(sk, &head->chain);
sk->sk_hash = hash;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock(lock);
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:
write_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);