#include <linux/interrupt.h>
+#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <net/inet_connection_sock.h>
#include <net/inet_sock.h>
#include <net/sock.h>
+#include <net/route.h>
#include <net/tcp_states.h>
+#include <net/netns/hash.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
* I'll experiment with dynamic table growth later.
*/
struct inet_ehash_bucket {
- struct hlist_head chain;
- struct hlist_head twchain;
+ struct hlist_nulls_head chain;
+ struct hlist_nulls_head twchain;
};
/* There are a few simple rules, which allow for local port reuse by
* ports are created in O(1) time? I thought so. ;-) -DaveM
*/
struct inet_bind_bucket {
+#ifdef CONFIG_NET_NS
struct net *ib_net;
+#endif
unsigned short port;
signed short fastreuse;
+ int num_owners;
struct hlist_node node;
struct hlist_head owners;
};
+static inline struct net *ib_net(struct inet_bind_bucket *ib)
+{
+ return read_pnet(&ib->ib_net);
+}
+
#define inet_bind_bucket_for_each(tb, node, head) \
hlist_for_each_entry(tb, node, head, node)
struct hlist_head chain;
};
+/*
+ * Sockets can be hashed in established or listening table
+ * We must use different 'nulls' end-of-chain value for listening
+ * hash table, or we might find a socket that was closed and
+ * reallocated/inserted into established hash table
+ */
+#define LISTENING_NULLS_BASE (1U << 29)
+struct inet_listen_hashbucket {
+ spinlock_t lock;
+ struct hlist_nulls_head head;
+};
+
/* This is for listening sockets, thus all sockets which possess wildcards. */
#define INET_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */
* TIME_WAIT sockets use a separate chain (twchain).
*/
struct inet_ehash_bucket *ehash;
- rwlock_t *ehash_locks;
+ spinlock_t *ehash_locks;
unsigned int ehash_size;
unsigned int ehash_locks_mask;
struct inet_bind_hashbucket *bhash;
unsigned int bhash_size;
- /* Note : 4 bytes padding on 64 bit arches */
+ /* 4 bytes hole on 64 bit */
- /* 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
- * is just local port number.
- */
- struct hlist_head listening_hash[INET_LHTABLE_SIZE];
+ struct kmem_cache *bind_bucket_cachep;
/* All the above members are written once at bootup and
* never written again _or_ are predominantly read-access.
*
* Now align to a new cache line as all the following members
- * are often dirty.
+ * might be often dirty.
*/
- rwlock_t lhash_lock ____cacheline_aligned;
- atomic_t lhash_users;
- wait_queue_head_t lhash_wait;
- struct kmem_cache *bind_bucket_cachep;
+ /* 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
+ * is just local port number.
+ */
+ struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE]
+ ____cacheline_aligned_in_smp;
+
+ atomic_t bsockets;
};
static inline struct inet_ehash_bucket *inet_ehash_bucket(
return &hashinfo->ehash[hash & (hashinfo->ehash_size - 1)];
}
-static inline rwlock_t *inet_ehash_lockp(
+static inline spinlock_t *inet_ehash_lockp(
struct inet_hashinfo *hashinfo,
unsigned int hash)
{
size = 2048;
if (nr_pcpus >= 32)
size = 4096;
- if (sizeof(rwlock_t) != 0) {
+ if (sizeof(spinlock_t) != 0) {
#ifdef CONFIG_NUMA
- if (size * sizeof(rwlock_t) > PAGE_SIZE)
- hashinfo->ehash_locks = vmalloc(size * sizeof(rwlock_t));
+ if (size * sizeof(spinlock_t) > PAGE_SIZE)
+ hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t));
else
#endif
- hashinfo->ehash_locks = kmalloc(size * sizeof(rwlock_t),
+ hashinfo->ehash_locks = kmalloc(size * sizeof(spinlock_t),
GFP_KERNEL);
if (!hashinfo->ehash_locks)
return ENOMEM;
for (i = 0; i < size; i++)
- rwlock_init(&hashinfo->ehash_locks[i]);
+ spin_lock_init(&hashinfo->ehash_locks[i]);
}
hashinfo->ehash_locks_mask = size - 1;
return 0;
if (hashinfo->ehash_locks) {
#ifdef CONFIG_NUMA
unsigned int size = (hashinfo->ehash_locks_mask + 1) *
- sizeof(rwlock_t);
+ sizeof(spinlock_t);
if (size > PAGE_SIZE)
vfree(hashinfo->ehash_locks);
else
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)
+static inline int inet_bhashfn(struct net *net,
+ const __u16 lport, const int bhash_size)
{
- return lport & (bhash_size - 1);
+ return (lport + net_hash_mix(net)) & (bhash_size - 1);
}
extern void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
const unsigned short snum);
/* These can have wildcards, don't try too hard. */
-static inline int inet_lhashfn(const unsigned short num)
+static inline int inet_lhashfn(struct net *net, const unsigned short num)
{
- return num & (INET_LHTABLE_SIZE - 1);
+ return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1);
}
static inline int inet_sk_listen_hashfn(const struct sock *sk)
{
- return inet_lhashfn(inet_sk(sk)->num);
+ return inet_lhashfn(sock_net(sk), inet_sk(sk)->num);
}
/* Caller must disable local BH processing. */
-static inline void __inet_inherit_port(struct sock *sk, struct sock *child)
-{
- struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
- const int bhash = inet_bhashfn(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);
-}
-
-static inline void inet_inherit_port(struct sock *sk, struct sock *child)
-{
- local_bh_disable();
- __inet_inherit_port(sk, child);
- local_bh_enable();
-}
+extern void __inet_inherit_port(struct sock *sk, struct sock *child);
extern void inet_put_port(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);
-}
+void inet_hashinfo_init(struct inet_hashinfo *h);
extern void __inet_hash_nolisten(struct sock *sk);
extern void inet_hash(struct sock *sk);
((__force __u64)(__be32)(__saddr)));
#endif /* __BIG_ENDIAN */
#define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
- (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \
+ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \
((*((__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, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\
- (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \
+ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \
((*((__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, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif) \
- (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \
+ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \
(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, __net, __hash,__cookie, __saddr, __daddr, __ports, __dif) \
- (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \
+ (((__sk)->sk_hash == (__hash)) && net_eq(sock_net(__sk), (__net)) && \
(inet_twsk(__sk)->tw_daddr == (__saddr)) && \
(inet_twsk(__sk)->tw_rcv_saddr == (__daddr)) && \
((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \
return sk;
}
+static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb,
+ const __be16 sport,
+ const __be16 dport)
+{
+ struct sock *sk;
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __inet_lookup(dev_net(skb->dst->dev), hashinfo,
+ iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb));
+}
+
extern int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff