#ifndef _INET_HASHTABLES_H
#define _INET_HASHTABLES_H
+#include <linux/config.h>
+
#include <linux/interrupt.h>
-#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/list.h>
#include <linux/slab.h>
+#include <linux/socket.h>
#include <linux/spinlock.h>
#include <linux/types.h>
+#include <linux/wait.h>
+#include <net/inet_connection_sock.h>
+#include <net/route.h>
#include <net/sock.h>
+#include <net/tcp_states.h>
+
+#include <asm/atomic.h>
+#include <asm/byteorder.h>
/* This is for all connections with a full identity, no wildcards.
* New scheme, half the table is for TIME_WAIT, the other half is
struct inet_ehash_bucket {
rwlock_t lock;
struct hlist_head chain;
-} __attribute__((__aligned__(8)));
+};
/* There are a few simple rules, which allow for local port reuse by
* an application. In essence:
struct inet_bind_hashbucket *bhash;
int bhash_size;
- int ehash_size;
+ unsigned int ehash_size;
/* All sockets in TCP_LISTEN state will be in here. This is the only
* table where wildcard'd TCP sockets can exist. Hash function here
wait_queue_head_t lhash_wait;
spinlock_t portalloc_lock;
kmem_cache_t *bind_bucket_cachep;
+ int port_rover;
};
-static inline int inet_ehashfn(const __u32 laddr, const __u16 lport,
- const __u32 faddr, const __u16 fport,
- const int ehash_size)
+static inline unsigned int inet_ehashfn(const __u32 laddr, const __u16 lport,
+ const __u32 faddr, const __u16 fport)
{
- int h = (laddr ^ lport) ^ (faddr ^ fport);
+ unsigned int h = (laddr ^ lport) ^ (faddr ^ fport);
h ^= h >> 16;
h ^= h >> 8;
- return h & (ehash_size - 1);
+ return h;
}
-static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size)
+static inline int inet_sk_ehashfn(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const __u32 laddr = inet->rcv_saddr;
const __u32 faddr = inet->daddr;
const __u16 fport = inet->dport;
- return inet_ehashfn(laddr, lport, faddr, fport, ehash_size);
+ return inet_ehashfn(laddr, lport, faddr, fport);
+}
+
+static inline struct inet_ehash_bucket *inet_ehash_bucket(
+ struct inet_hashinfo *hashinfo,
+ unsigned int hash)
+{
+ return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)];
}
extern struct inet_bind_bucket *
struct inet_bind_bucket *tb;
spin_lock(&head->lock);
- tb = inet_sk(sk)->bind_hash;
+ tb = inet_csk(sk)->icsk_bind_hash;
sk_add_bind_node(child, &tb->owners);
- inet_sk(child)->bind_hash = tb;
+ inet_csk(child)->icsk_bind_hash = tb;
spin_unlock(&head->lock);
}
extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk);
+extern void inet_listen_wlock(struct inet_hashinfo *hashinfo);
+
+/*
+ * - We may sleep inside this lock.
+ * - If sleeping is not required (or called from BH),
+ * use plain read_(un)lock(&inet_hashinfo.lhash_lock).
+ */
+static inline void inet_listen_lock(struct inet_hashinfo *hashinfo)
+{
+ /* read_lock synchronizes to candidates to writers */
+ read_lock(&hashinfo->lhash_lock);
+ atomic_inc(&hashinfo->lhash_users);
+ read_unlock(&hashinfo->lhash_lock);
+}
+
+static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo)
+{
+ if (atomic_dec_and_test(&hashinfo->lhash_users))
+ wake_up(&hashinfo->lhash_wait);
+}
+
+static inline void __inet_hash(struct inet_hashinfo *hashinfo,
+ struct sock *sk, const int listen_possible)
+{
+ struct hlist_head *list;
+ rwlock_t *lock;
+
+ BUG_TRAP(sk_unhashed(sk));
+ if (listen_possible && sk->sk_state == TCP_LISTEN) {
+ list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+ lock = &hashinfo->lhash_lock;
+ inet_listen_wlock(hashinfo);
+ } else {
+ struct inet_ehash_bucket *head;
+ sk->sk_hash = inet_sk_ehashfn(sk);
+ head = inet_ehash_bucket(hashinfo, sk->sk_hash);
+ list = &head->chain;
+ lock = &head->lock;
+ write_lock(lock);
+ }
+ __sk_add_node(sk, list);
+ sock_prot_inc_use(sk->sk_prot);
+ write_unlock(lock);
+ if (listen_possible && sk->sk_state == TCP_LISTEN)
+ wake_up(&hashinfo->lhash_wait);
+}
+
+static inline void inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
+{
+ if (sk->sk_state != TCP_CLOSE) {
+ local_bh_disable();
+ __inet_hash(hashinfo, sk, 1);
+ local_bh_enable();
+ }
+}
+
+static inline void inet_unhash(struct inet_hashinfo *hashinfo, struct sock *sk)
+{
+ rwlock_t *lock;
+
+ 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_bucket(hashinfo, sk->sk_hash)->lock;
+ write_lock_bh(lock);
+ }
+
+ if (__sk_del_node_init(sk))
+ sock_prot_dec_use(sk->sk_prot);
+ write_unlock_bh(lock);
+out:
+ if (sk->sk_state == TCP_LISTEN)
+ wake_up(&hashinfo->lhash_wait);
+}
+
+static inline int inet_iif(const struct sk_buff *skb)
+{
+ return ((struct rtable *)skb->dst)->rt_iif;
+}
+
+extern struct sock *__inet_lookup_listener(const struct hlist_head *head,
+ const u32 daddr,
+ const unsigned short hnum,
+ const int dif);
+
+/* Optimize the common listener case. */
+static inline struct sock *
+ inet_lookup_listener(struct inet_hashinfo *hashinfo,
+ const u32 daddr,
+ const unsigned short hnum, const int dif)
+{
+ struct sock *sk = NULL;
+ const struct hlist_head *head;
+
+ read_lock(&hashinfo->lhash_lock);
+ head = &hashinfo->listening_hash[inet_lhashfn(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)
+ goto sherry_cache;
+ sk = __inet_lookup_listener(head, daddr, hnum, dif);
+ }
+ if (sk) {
+sherry_cache:
+ sock_hold(sk);
+ }
+ read_unlock(&hashinfo->lhash_lock);
+ return sk;
+}
+
+/* Socket demux engine toys. */
+#ifdef __BIG_ENDIAN
+#define INET_COMBINED_PORTS(__sport, __dport) \
+ (((__u32)(__sport) << 16) | (__u32)(__dport))
+#else /* __LITTLE_ENDIAN */
+#define INET_COMBINED_PORTS(__sport, __dport) \
+ (((__u32)(__dport) << 16) | (__u32)(__sport))
+#endif
+
+#if (BITS_PER_LONG == 64)
+#ifdef __BIG_ENDIAN
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+ const __u64 __name = (((__u64)(__saddr)) << 32) | ((__u64)(__daddr));
+#else /* __LITTLE_ENDIAN */
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+ const __u64 __name = (((__u64)(__daddr)) << 32) | ((__u64)(__saddr));
+#endif /* __BIG_ENDIAN */
+#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
+ (((__sk)->sk_hash == (__hash)) && \
+ ((*((__u64 *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \
+ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \
+ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_TW_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
+ (((__sk)->sk_hash == (__hash)) && \
+ ((*((__u64 *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) && \
+ ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \
+ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#else /* 32-bit arch */
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr)
+#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif) \
+ (((__sk)->sk_hash == (__hash)) && \
+ (inet_sk(__sk)->daddr == (__saddr)) && \
+ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \
+ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \
+ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#define INET_TW_MATCH(__sk, __hash,__cookie, __saddr, __daddr, __ports, __dif) \
+ (((__sk)->sk_hash == (__hash)) && \
+ (inet_twsk(__sk)->tw_daddr == (__saddr)) && \
+ (inet_twsk(__sk)->tw_rcv_saddr == (__daddr)) && \
+ ((*((__u32 *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \
+ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
+#endif /* 64-bit arch */
+
+/*
+ * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need
+ * not check it for lookups anymore, thanks Alexey. -DaveM
+ *
+ * Local BH must be disabled here.
+ */
+static inline struct sock *
+ __inet_lookup_established(struct inet_hashinfo *hashinfo,
+ const u32 saddr, const u16 sport,
+ const u32 daddr, const u16 hnum,
+ const int dif)
+{
+ INET_ADDR_COOKIE(acookie, saddr, daddr)
+ const __u32 ports = INET_COMBINED_PORTS(sport, hnum);
+ struct sock *sk;
+ const struct hlist_node *node;
+ /* Optimize here for direct hit, only listening connections can
+ * have wildcards anyways.
+ */
+ unsigned int hash = inet_ehashfn(daddr, hnum, saddr, sport);
+ struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
+
+ prefetch(head->chain.first);
+ read_lock(&head->lock);
+ sk_for_each(sk, node, &head->chain) {
+ if (INET_MATCH(sk, 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 + hashinfo->ehash_size)->chain) {
+ if (INET_TW_MATCH(sk, hash, acookie, saddr, daddr, ports, dif))
+ goto hit;
+ }
+ sk = NULL;
+out:
+ read_unlock(&head->lock);
+ return sk;
+hit:
+ sock_hold(sk);
+ goto out;
+}
+
+static inline struct sock *__inet_lookup(struct inet_hashinfo *hashinfo,
+ const u32 saddr, const u16 sport,
+ const u32 daddr, const u16 hnum,
+ const int dif)
+{
+ struct sock *sk = __inet_lookup_established(hashinfo, saddr, sport, daddr,
+ hnum, dif);
+ return sk ? : inet_lookup_listener(hashinfo, daddr, hnum, dif);
+}
+
+static inline struct sock *inet_lookup(struct inet_hashinfo *hashinfo,
+ const u32 saddr, const u16 sport,
+ const u32 daddr, const u16 dport,
+ const int dif)
+{
+ struct sock *sk;
+
+ local_bh_disable();
+ sk = __inet_lookup(hashinfo, saddr, sport, daddr, ntohs(dport), dif);
+ local_bh_enable();
+
+ return sk;
+}
#endif /* _INET_HASHTABLES_H */