#ifndef _INET_HASHTABLES_H
#define _INET_HASHTABLES_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/tcp.h> /* only for TCP_LISTEN, damn :-( */
#include <linux/types.h>
#include <linux/wait.h>
+#include <linux/vmalloc.h>
+#include <net/inet_connection_sock.h>
+#include <net/inet_sock.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
- * for the rest. I'll experiment with dynamic table growth later.
+ * One chain is dedicated to TIME_WAIT sockets.
+ * I'll experiment with dynamic table growth later.
*/
struct inet_ehash_bucket {
- rwlock_t lock;
struct hlist_head chain;
-} __attribute__((__aligned__(8)));
+ struct hlist_head twchain;
+};
/* There are a few simple rules, which allow for local port reuse by
* an application. In essence:
*
* TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
*
- * First half of the table is for sockets not in TIME_WAIT, second half
- * is for TIME_WAIT sockets only.
+ * TIME_WAIT sockets use a separate chain (twchain).
*/
struct inet_ehash_bucket *ehash;
+ rwlock_t *ehash_locks;
+ unsigned int ehash_size;
+ unsigned int ehash_locks_mask;
/* Ok, let's try this, I give up, we do need a local binding
* TCP hash as well as the others for fast bind/connect.
*/
struct inet_bind_hashbucket *bhash;
- int bhash_size;
- int ehash_size;
+ unsigned int bhash_size;
+ /* Note : 4 bytes padding on 64 bit arches */
/* 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
rwlock_t lhash_lock ____cacheline_aligned;
atomic_t lhash_users;
wait_queue_head_t lhash_wait;
- spinlock_t portalloc_lock;
- kmem_cache_t *bind_bucket_cachep;
- int port_rover;
+ struct kmem_cache *bind_bucket_cachep;
};
-static inline int inet_ehashfn(const __u32 laddr, const __u16 lport,
- const __u32 faddr, const __u16 fport,
- const int ehash_size)
+static inline struct inet_ehash_bucket *inet_ehash_bucket(
+ struct inet_hashinfo *hashinfo,
+ unsigned int hash)
{
- int h = (laddr ^ lport) ^ (faddr ^ fport);
- h ^= h >> 16;
- h ^= h >> 8;
- return h & (ehash_size - 1);
+ return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)];
}
-static inline int inet_sk_ehashfn(const struct sock *sk, const int ehash_size)
+static inline rwlock_t *inet_ehash_lockp(
+ struct inet_hashinfo *hashinfo,
+ unsigned int hash)
{
- const struct inet_sock *inet = inet_sk(sk);
- const __u32 laddr = inet->rcv_saddr;
- const __u16 lport = inet->num;
- const __u32 faddr = inet->daddr;
- const __u16 fport = inet->dport;
+ return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask];
+}
+
+static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
+{
+ unsigned int i, size = 256;
+#if defined(CONFIG_PROVE_LOCKING)
+ unsigned int nr_pcpus = 2;
+#else
+ unsigned int nr_pcpus = num_possible_cpus();
+#endif
+ if (nr_pcpus >= 4)
+ size = 512;
+ if (nr_pcpus >= 8)
+ size = 1024;
+ if (nr_pcpus >= 16)
+ size = 2048;
+ if (nr_pcpus >= 32)
+ size = 4096;
+ if (sizeof(rwlock_t) != 0) {
+#ifdef CONFIG_NUMA
+ if (size * sizeof(rwlock_t) > PAGE_SIZE)
+ hashinfo->ehash_locks = vmalloc(size * sizeof(rwlock_t));
+ else
+#endif
+ hashinfo->ehash_locks = kmalloc(size * sizeof(rwlock_t),
+ GFP_KERNEL);
+ if (!hashinfo->ehash_locks)
+ return ENOMEM;
+ for (i = 0; i < size; i++)
+ rwlock_init(&hashinfo->ehash_locks[i]);
+ }
+ hashinfo->ehash_locks_mask = size - 1;
+ return 0;
+}
- return inet_ehashfn(laddr, lport, faddr, fport, ehash_size);
+static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
+{
+ if (hashinfo->ehash_locks) {
+#ifdef CONFIG_NUMA
+ unsigned int size = (hashinfo->ehash_locks_mask + 1) *
+ sizeof(rwlock_t);
+ if (size > PAGE_SIZE)
+ vfree(hashinfo->ehash_locks);
+ else
+#endif
+ kfree(hashinfo->ehash_locks);
+ hashinfo->ehash_locks = NULL;
+ }
}
extern struct inet_bind_bucket *
- inet_bind_bucket_create(kmem_cache_t *cachep,
+ inet_bind_bucket_create(struct kmem_cache *cachep,
struct inet_bind_hashbucket *head,
const unsigned short snum);
-extern void inet_bind_bucket_destroy(kmem_cache_t *cachep,
+extern void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
static inline int inet_bhashfn(const __u16 lport, const int bhash_size)
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);
}
lock = &hashinfo->lhash_lock;
inet_listen_wlock(hashinfo);
} else {
- sk->sk_hashent = inet_sk_ehashfn(sk, hashinfo->ehash_size);
- list = &hashinfo->ehash[sk->sk_hashent].chain;
- lock = &hashinfo->ehash[sk->sk_hashent].lock;
+ struct inet_ehash_bucket *head;
+ sk->sk_hash = inet_sk_ehashfn(sk);
+ head = inet_ehash_bucket(hashinfo, sk->sk_hash);
+ list = &head->chain;
+ lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
write_lock(lock);
}
__sk_add_node(sk, list);
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_lockp(hashinfo, sk->sk_hash);
+ 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);
+}
+
+extern struct sock *__inet_lookup_listener(struct inet_hashinfo *hashinfo,
+ const __be32 daddr,
+ const unsigned short hnum,
+ const int dif);
+
+static inline struct sock *inet_lookup_listener(struct inet_hashinfo *hashinfo,
+ __be32 daddr, __be16 dport, int dif)
+{
+ return __inet_lookup_listener(hashinfo, daddr, ntohs(dport), dif);
+}
+
+/* Socket demux engine toys. */
+/* What happens here is ugly; there's a pair of adjacent fields in
+ struct inet_sock; __be16 dport followed by __u16 num. We want to
+ search by pair, so we combine the keys into a single 32bit value
+ and compare with 32bit value read from &...->dport. Let's at least
+ make sure that it's not mixed with anything else...
+ On 64bit targets we combine comparisons with pair of adjacent __be32
+ fields in the same way.
+*/
+typedef __u32 __bitwise __portpair;
+#ifdef __BIG_ENDIAN
+#define INET_COMBINED_PORTS(__sport, __dport) \
+ ((__force __portpair)(((__force __u32)(__be16)(__sport) << 16) | (__u32)(__dport)))
+#else /* __LITTLE_ENDIAN */
+#define INET_COMBINED_PORTS(__sport, __dport) \
+ ((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport)))
+#endif
+
+#if (BITS_PER_LONG == 64)
+typedef __u64 __bitwise __addrpair;
+#ifdef __BIG_ENDIAN
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+ const __addrpair __name = (__force __addrpair) ( \
+ (((__force __u64)(__be32)(__saddr)) << 32) | \
+ ((__force __u64)(__be32)(__daddr)));
+#else /* __LITTLE_ENDIAN */
+#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
+ const __addrpair __name = (__force __addrpair) ( \
+ (((__force __u64)(__be32)(__daddr)) << 32) | \
+ ((__force __u64)(__be32)(__saddr)));
+#endif /* __BIG_ENDIAN */
+#define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
+ (((__sk)->sk_hash == (__hash)) && \
+ ((*((__addrpair *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \
+ ((*((__portpair *)&(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)) && \
+ ((*((__addrpair *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) && \
+ ((*((__portpair *)&(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)) && \
+ ((*((__portpair *)&(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)) && \
+ ((*((__portpair *)&(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 __be32 saddr, const __be16 sport,
+ const __be32 daddr, const u16 hnum,
+ const int dif)
+{
+ INET_ADDR_COOKIE(acookie, saddr, daddr)
+ const __portpair 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);
+ 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))
+ 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))
+ goto hit;
+ }
+ sk = NULL;
+out:
+ read_unlock(lock);
+ return sk;
+hit:
+ sock_hold(sk);
+ goto out;
+}
+
+static inline struct sock *
+ inet_lookup_established(struct inet_hashinfo *hashinfo,
+ const __be32 saddr, const __be16 sport,
+ const __be32 daddr, const __be16 dport,
+ const int dif)
+{
+ return __inet_lookup_established(hashinfo, saddr, sport, daddr,
+ ntohs(dport), dif);
+}
+
+static inline struct sock *__inet_lookup(struct inet_hashinfo *hashinfo,
+ const __be32 saddr, const __be16 sport,
+ const __be32 daddr, const __be16 dport,
+ const int dif)
+{
+ u16 hnum = ntohs(dport);
+ 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 __be32 saddr, const __be16 sport,
+ const __be32 daddr, const __be16 dport,
+ const int dif)
+{
+ struct sock *sk;
+
+ local_bh_disable();
+ sk = __inet_lookup(hashinfo, saddr, sport, daddr, dport, dif);
+ local_bh_enable();
+
+ return sk;
+}
+
+extern int inet_hash_connect(struct inet_timewait_death_row *death_row,
+ struct sock *sk);
#endif /* _INET_HASHTABLES_H */