diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2008-12-28 12:49:40 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2008-12-28 12:49:40 -0800 |
commit | 0191b625ca5a46206d2fb862bb08f36f2fcb3b31 (patch) | |
tree | 454d1842b1833d976da62abcbd5c47521ebe9bd7 /net/ipv6/inet6_hashtables.c | |
parent | 54a696bd07c14d3b1192d03ce7269bc59b45209a (diff) | |
parent | eb56092fc168bf5af199d47af50c0d84a96db898 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1429 commits)
net: Allow dependancies of FDDI & Tokenring to be modular.
igb: Fix build warning when DCA is disabled.
net: Fix warning fallout from recent NAPI interface changes.
gro: Fix potential use after free
sfc: If AN is enabled, always read speed/duplex from the AN advertising bits
sfc: When disabling the NIC, close the device rather than unregistering it
sfc: SFT9001: Add cable diagnostics
sfc: Add support for multiple PHY self-tests
sfc: Merge top-level functions for self-tests
sfc: Clean up PHY mode management in loopback self-test
sfc: Fix unreliable link detection in some loopback modes
sfc: Generate unique names for per-NIC workqueues
802.3ad: use standard ethhdr instead of ad_header
802.3ad: generalize out mac address initializer
802.3ad: initialize ports LACPDU from const initializer
802.3ad: remove typedef around ad_system
802.3ad: turn ports is_individual into a bool
802.3ad: turn ports is_enabled into a bool
802.3ad: make ntt bool
ixgbe: Fix set_ringparam in ixgbe to use the same memory pools.
...
Fixed trivial IPv4/6 address printing conflicts in fs/cifs/connect.c due
to the conversion to %pI (in this networking merge) and the addition of
doing IPv6 addresses (from the earlier merge of CIFS).
Diffstat (limited to 'net/ipv6/inet6_hashtables.c')
-rw-r--r-- | net/ipv6/inet6_hashtables.c | 182 |
1 files changed, 115 insertions, 67 deletions
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1646a565825..8fe267feb81 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -25,26 +25,30 @@ 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); + 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); - write_lock(lock); + spin_lock(lock); + __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); } - __sk_add_node(sk, list); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); } EXPORT_SYMBOL(__inet6_hash); @@ -63,77 +67,122 @@ struct sock *__inet6_lookup_established(struct net *net, const int dif) { struct sock *sk; - const struct hlist_node *node; + 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); - struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hashinfo, hash); + unsigned int slot = hash & (hashinfo->ehash_size - 1); + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - prefetch(head->chain.first); - read_lock(lock); - sk_for_each(sk, node, &head->chain) { + + 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)) - goto hit; /* You sunk my battleship! */ + 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_for_each(sk, node, &head->twchain) { - if (INET6_TW_MATCH(sk, net, hash, saddr, daddr, ports, dif)) - goto hit; + 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; + } } - read_unlock(lock); - return NULL; - -hit: - sock_hold(sk); - read_unlock(lock); + 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_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; - } + 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; } } - if (result) - sock_hold(result); - read_unlock(&hashinfo->lhash_lock); + rcu_read_unlock(); return result; } @@ -170,16 +219,15 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, 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); + spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; - const struct hlist_node *node; + const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; - prefetch(head->chain.first); - write_lock(lock); + spin_lock(lock); /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &head->twchain) { + sk_nulls_for_each(sk2, node, &head->twchain) { tw = inet_twsk(sk2); if (INET6_TW_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) { @@ -192,7 +240,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, tw = NULL; /* And established part... */ - sk_for_each(sk2, node, &head->chain) { + sk_nulls_for_each(sk2, node, &head->chain) { if (INET6_MATCH(sk2, net, hash, saddr, daddr, ports, dif)) goto not_unique; } @@ -203,10 +251,10 @@ unique: inet->num = lport; inet->sport = htons(lport); WARN_ON(!sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); + __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); - write_unlock(lock); if (twp != NULL) { *twp = tw; @@ -221,7 +269,7 @@ unique: return 0; not_unique: - write_unlock(lock); + spin_unlock(lock); return -EADDRNOTAVAIL; } |