* The bindhash mutex for snum's hash chain must be held here.
*/
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
+ struct net *net,
struct inet_bind_hashbucket *head,
const unsigned short snum)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb != NULL) {
+ tb->ib_net = hold_net(net);
tb->port = snum;
tb->fastreuse = 0;
INIT_HLIST_HEAD(&tb->owners);
{
if (hlist_empty(&tb->owners)) {
__hlist_del(&tb->node);
+ release_net(tb->ib_net);
kmem_cache_free(cachep, tb);
}
}
/*
* Get rid of any references to a local port held by the given sock.
*/
-static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_put_port(struct sock *sk)
{
- const int bhash = inet_bhashfn(inet_sk(sk)->num, hashinfo->bhash_size);
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+ const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->num,
+ hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
spin_unlock(&head->lock);
}
-void inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+void inet_put_port(struct sock *sk)
{
local_bh_disable();
- __inet_put_port(hashinfo, sk);
+ __inet_put_port(sk);
local_bh_enable();
}
EXPORT_SYMBOL(inet_put_port);
+void __inet_inherit_port(struct sock *sk, struct sock *child)
+{
+ struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
+ const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->num,
+ table->bhash_size);
+ struct inet_bind_hashbucket *head = &table->bhash[bhash];
+ struct inet_bind_bucket *tb;
+
+ spin_lock(&head->lock);
+ tb = inet_csk(sk)->icsk_bind_hash;
+ sk_add_bind_node(child, &tb->owners);
+ inet_csk(child)->icsk_bind_hash = tb;
+ spin_unlock(&head->lock);
+}
+
+EXPORT_SYMBOL_GPL(__inet_inherit_port);
+
/*
* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it can be very bad on SMP.
* Look, when several writers sleep and reader wakes them up, all but one
}
}
-EXPORT_SYMBOL(inet_listen_wlock);
-
/*
* Don't inline this cruft. Here are some nice properties to exploit here. The
* BSD API does not allow a listening sock to specify the remote port nor the
* remote address for the connection. So always assume those are both
* wildcarded during the search since they can never be otherwise.
*/
-static struct sock *inet_lookup_listener_slow(const struct hlist_head *head,
+static struct sock *inet_lookup_listener_slow(struct net *net,
+ const struct hlist_head *head,
const __be32 daddr,
const unsigned short hnum,
const int dif)
sk_for_each(sk, node, head) {
const struct inet_sock *inet = inet_sk(sk);
- if (inet->num == hnum && !ipv6_only_sock(sk)) {
+ if (net_eq(sock_net(sk), net) && inet->num == hnum &&
+ !ipv6_only_sock(sk)) {
const __be32 rcv_saddr = inet->rcv_saddr;
int score = sk->sk_family == PF_INET ? 1 : 0;
}
/* Optimize the common listener case. */
-struct sock *__inet_lookup_listener(struct inet_hashinfo *hashinfo,
+struct sock *__inet_lookup_listener(struct net *net,
+ struct inet_hashinfo *hashinfo,
const __be32 daddr, const unsigned short hnum,
const int dif)
{
const struct hlist_head *head;
read_lock(&hashinfo->lhash_lock);
- head = &hashinfo->listening_hash[inet_lhashfn(hnum)];
+ head = &hashinfo->listening_hash[inet_lhashfn(net, hnum)];
if (!hlist_empty(head)) {
const struct inet_sock *inet = inet_sk((sk = __sk_head(head)));
if (inet->num == hnum && !sk->sk_node.next &&
(!inet->rcv_saddr || inet->rcv_saddr == daddr) &&
(sk->sk_family == PF_INET || !ipv6_only_sock(sk)) &&
- !sk->sk_bound_dev_if)
+ !sk->sk_bound_dev_if && net_eq(sock_net(sk), net))
goto sherry_cache;
- sk = inet_lookup_listener_slow(head, daddr, hnum, dif);
+ sk = inet_lookup_listener_slow(net, head, daddr, hnum, dif);
}
if (sk) {
sherry_cache:
}
EXPORT_SYMBOL_GPL(__inet_lookup_listener);
-struct sock * __inet_lookup_established(struct inet_hashinfo *hashinfo,
+struct sock * __inet_lookup_established(struct net *net,
+ struct inet_hashinfo *hashinfo,
const __be32 saddr, const __be16 sport,
const __be32 daddr, const u16 hnum,
const int dif)
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
- unsigned int hash = inet_ehashfn(daddr, hnum, saddr, sport);
+ unsigned int hash = inet_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) {
- if (INET_MATCH(sk, hash, acookie, saddr, daddr, ports, dif))
+ if (INET_MATCH(sk, net, hash, acookie,
+ saddr, daddr, ports, dif))
goto hit; /* You sunk my battleship! */
}
/* Must check for a TIME_WAIT'er before going to listener hash. */
sk_for_each(sk, node, &head->twchain) {
- if (INET_TW_MATCH(sk, hash, acookie, saddr, daddr, ports, dif))
+ if (INET_TW_MATCH(sk, net, hash, acookie,
+ saddr, daddr, ports, dif))
goto hit;
}
sk = NULL;
int dif = sk->sk_bound_dev_if;
INET_ADDR_COOKIE(acookie, saddr, daddr)
const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport);
- unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport);
+ struct net *net = sock_net(sk);
+ unsigned int hash = inet_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;
sk_for_each(sk2, node, &head->twchain) {
tw = inet_twsk(sk2);
- if (INET_TW_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif)) {
+ if (INET_TW_MATCH(sk2, net, hash, acookie,
+ saddr, daddr, ports, dif)) {
if (twsk_unique(sk, sk2, twp))
goto unique;
else
/* And established part... */
sk_for_each(sk2, node, &head->chain) {
- if (INET_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif))
+ if (INET_MATCH(sk2, net, hash, acookie,
+ saddr, daddr, ports, dif))
goto not_unique;
}
sk->sk_hash = hash;
BUG_TRAP(sk_unhashed(sk));
__sk_add_node(sk, &head->chain);
- sock_prot_inuse_add(sk->sk_prot, 1);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock(lock);
if (twp) {
*twp = tw;
- NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
+ NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
} else if (tw) {
/* Silly. Should hash-dance instead... */
inet_twsk_deschedule(tw, death_row);
- NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
+ NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
inet_twsk_put(tw);
}
inet->dport);
}
-void __inet_hash_nolisten(struct inet_hashinfo *hashinfo, struct sock *sk)
+void __inet_hash_nolisten(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_head *list;
rwlock_t *lock;
struct inet_ehash_bucket *head;
write_lock(lock);
__sk_add_node(sk, list);
- sock_prot_inuse_add(sk->sk_prot, 1);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock(lock);
}
EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
-void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_hash(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_head *list;
rwlock_t *lock;
if (sk->sk_state != TCP_LISTEN) {
- __inet_hash_nolisten(hashinfo, sk);
+ __inet_hash_nolisten(sk);
return;
}
inet_listen_wlock(hashinfo);
__sk_add_node(sk, list);
- sock_prot_inuse_add(sk->sk_prot, 1);
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock(lock);
wake_up(&hashinfo->lhash_wait);
}
-EXPORT_SYMBOL_GPL(__inet_hash);
+
+void inet_hash(struct sock *sk)
+{
+ if (sk->sk_state != TCP_CLOSE) {
+ local_bh_disable();
+ __inet_hash(sk);
+ local_bh_enable();
+ }
+}
+EXPORT_SYMBOL_GPL(inet_hash);
+
+void inet_unhash(struct sock *sk)
+{
+ rwlock_t *lock;
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+ if (sk_unhashed(sk))
+ goto out;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ local_bh_disable();
+ inet_listen_wlock(hashinfo);
+ lock = &hashinfo->lhash_lock;
+ } else {
+ lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+ write_lock_bh(lock);
+ }
+
+ if (__sk_del_node_init(sk))
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+ write_unlock_bh(lock);
+out:
+ if (sk->sk_state == TCP_LISTEN)
+ wake_up(&hashinfo->lhash_wait);
+}
+EXPORT_SYMBOL_GPL(inet_unhash);
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
- struct sock *sk,
+ struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **),
- void (*hash)(struct inet_hashinfo *, struct sock *))
+ void (*hash)(struct sock *sk))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
const unsigned short snum = inet_sk(sk)->num;
struct inet_bind_hashbucket *head;
struct inet_bind_bucket *tb;
int ret;
+ struct net *net = sock_net(sk);
if (!snum) {
int i, remaining, low, high, port;
static u32 hint;
- u32 offset = hint + inet_sk_port_offset(sk);
+ u32 offset = hint + port_offset;
struct hlist_node *node;
struct inet_timewait_sock *tw = NULL;
local_bh_disable();
for (i = 1; i <= remaining; i++) {
port = low + (i + offset) % remaining;
- head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];
+ head = &hinfo->bhash[inet_bhashfn(net, port,
+ hinfo->bhash_size)];
spin_lock(&head->lock);
/* Does not bother with rcv_saddr checks,
* unique enough.
*/
inet_bind_bucket_for_each(tb, node, &head->chain) {
- if (tb->port == port) {
+ if (tb->ib_net == net && tb->port == port) {
BUG_TRAP(!hlist_empty(&tb->owners));
if (tb->fastreuse >= 0)
goto next_port;
}
}
- tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, head, port);
+ tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
+ net, head, port);
if (!tb) {
spin_unlock(&head->lock);
break;
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->sport = htons(port);
- hash(hinfo, sk);
+ hash(sk);
}
spin_unlock(&head->lock);
goto out;
}
- head = &hinfo->bhash[inet_bhashfn(snum, hinfo->bhash_size)];
+ head = &hinfo->bhash[inet_bhashfn(net, snum, hinfo->bhash_size)];
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- hash(hinfo, sk);
+ hash(sk);
spin_unlock_bh(&head->lock);
return 0;
} else {
return ret;
}
}
-EXPORT_SYMBOL_GPL(__inet_hash_connect);
/*
* Bind a port for a connect operation and hash it.
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- return __inet_hash_connect(death_row, sk,
+ return __inet_hash_connect(death_row, sk, inet_sk_port_offset(sk),
__inet_check_established, __inet_hash_nolisten);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff