udp_table用于存放udp socket,其定义如下:
struct udp_table {
struct udp_hslot *hash; //hash table, sockets are hashed on (local port)
struct udp_hslot *hash2;//hash table, sockets are hashed on (local port, local address)
unsigned int mask;//number of slots in hash tables, minus 1
unsigned int log;//log2(number of slots in hash table)
};
extern struct udp_table udp_table;
udp_table的初始化:
inet_init
udp_init
udp_table_init(&udp_table, "UDP");
{
unsigned int i;
table->hash = alloc_large_system_hash(name,
2 * sizeof(struct udp_hslot),
uhash_entries,
21, /* one slot per 2 MB */
0,
&table->log,
&table->mask,
UDP_HTABLE_SIZE_MIN,
64 * 1024);
table->hash2 = table->hash + (table->mask + 1);
for (i = 0; i <= table->mask; i++) {
INIT_HLIST_HEAD(&table->hash[i].head);
table->hash[i].count = 0;
spin_lock_init(&table->hash[i].lock);
}
for (i = 0; i <= table->mask; i++) {
INIT_HLIST_HEAD(&table->hash2[i].head);
table->hash2[i].count = 0;
spin_lock_init(&table->hash2[i].lock);
}
}
调用bind()及sendto()时,UDP socket会被插入到udp_table中,而这是在udp_v4_get_port()中进行的。
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
这个函数先计算两个特殊的hash值,然后调用udp_lib_get_port处理:
udp_lib_get_port(sk, snum, hash2_nulladdr)
{
struct udp_hslot *hslot, *hslot2;
struct udp_table *udptable = sk->sk_prot->h.udp_table;
int error = 1;
struct net *net = sock_net(sk);
if (!snum) {
int low, high, remaining;
unsigned int rand;
unsigned short first, last;
DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
rand = prandom_u32();
first = reciprocal_scale(rand, remaining) + low;
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
rand = (rand | 1) * (udptable->mask + 1);
last = first + udptable->mask + 1;
do {
hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
udptable->log);
snum = first;
/*
* Iterate on all possible values of snum for this hash.
* Using steps of an odd multiple of UDP_HTABLE_SIZE
* give us randomization and full range coverage.
*/
do {
if (low <= snum && snum <= high &&
!test_bit(snum >> udptable->log, bitmap) &&
!inet_is_local_reserved_port(net, snum))
goto found;
snum += rand;
} while (snum != first);
spin_unlock_bh(&hslot->lock);
cond_resched();
} while (++first != last);
goto fail;
} else {
hslot = udp_hashslot(udptable, net, snum);
spin_lock_bh(&hslot->lock);
if (hslot->count > 10) {
int exist;
unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
slot2 &= udptable->mask;
hash2_nulladdr &= udptable->mask;
hslot2 = udp_hashslot2(udptable, slot2);
if (hslot->count < hslot2->count)
goto scan_primary_hash;
exist = udp_lib_lport_inuse2(net, snum, hslot2, sk);
if (!exist && (hash2_nulladdr != slot2)) {
hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
exist = udp_lib_lport_inuse2(net, snum, hslot2,
sk);
}
if (exist)
goto fail_unlock;
else
goto found;
}
scan_primary_hash:
if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0))
goto fail_unlock;
}
found:
inet_sk(sk)->inet_num = snum;
udp_sk(sk)->udp_port_hash = snum;
udp_sk(sk)->udp_portaddr_hash ^= snum;
if (sk_unhashed(sk)) {
if (sk->sk_reuseport &&
udp_reuseport_add_sock(sk, hslot)) {
inet_sk(sk)->inet_num = 0;
udp_sk(sk)->udp_port_hash = 0;
udp_sk(sk)->udp_portaddr_hash ^= snum;
goto fail_unlock;
}
sk_add_node_rcu(sk, &hslot->head);
hslot->count++;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock(&hslot2->lock);
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
else
hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
hslot2->count++;
spin_unlock(&hslot2->lock);
}
sock_set_flag(sk, SOCK_RCU_FREE);
error = 0;
fail_unlock:
spin_unlock_bh(&hslot->lock);
fail:
return error;
}
根椐参数snum的值分为两种情况:
1.如果snum为0,则为socket分配一个没有在使用的端口号,然后将socket插入到udp_table,更新socket部分成员。
2.如果snum不为0,则snum就是要bind的端口,先查udp_table,看这个端口号是否已在用,如果没有在用,那么当前socket就使用这个端口号,并将socket插入udp_table,更新socket成员