内核中的UDP socket流程（5）——inet_create
作者：gfree.wind@gmail.com
进入函数inet_create
static int inet_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct sock *sk;
struct inet_protosw *answer;
struct inet_sock *inet;
struct proto *answer_prot;
unsigned char answer_flags;
char answer_no_check;
int try_loading_module = 0;
int err;
if (unlikely(!inet_ehash_secret))
if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM)
build_ehash_secret(); |
当socket为UDP时，sock->type = SOCK_DGRAM。所以这里不会调用到huild_ehash_secret()————其实这个函数是为了产生一个随机的数赋给inet_ehash_secret————暂时还不知道这个变量的确切用途。
通过sock->type和protocol在inetsw链表中找到对应的proto；
/* Look for the requested type/protocol pair. */
lookup_protocol:
err = -ESOCKTNOSUPPORT;
rcu_read_lock();
list_for_each_entry_rcu(answer, &inetsw[sock->type], list) {
err = 0;
/* Check the non-wild match. */
if (protocol == answer->protocol) {
if (protocol != IPPROTO_IP)
break;
} else {
/* Check for the two wild cases. */
if (IPPROTO_IP == protocol) {
protocol = answer->protocol;
break;
}
if (IPPROTO_IP == answer->protocol)
break;
}
err = -EPROTONOSUPPORT;
}
|
从以上代码可以看出，IPPROTO_IP是作为一个wild protocol使用的。首先是尽量寻找与参数protocol完全匹配的协议，如果找不到完全匹配的，如果参数是IPPROTO_IP，那么任一protocol都可以使用，如果找到PPROTO_IP协议的话，就使用该协议。
inetsw是一个static的全局变量
static struct list_head inetsw[SOCK_MAX]; |
该全局变量在函数inet_init中初始化
| static int __init inet_init(void)
{
/* Skip some codes */ /* Register the socket-side information for inet_create. */
for (r = &inetsw[0]; r &inetsw[SOCK_MAX]; ++r)
INIT_LIST_HEAD(r);
for (q = inetsw_array; q &inetsw_array[INETSW_ARRAY_LEN]; ++q)
inet_register_protosw(q);
|
通过inetsw_array来初始化inetsw，那么在inetsw中保存的协议顺序就与inetsw相同。
/* Upon startup we insert all the elements in inetsw_array[] into
* the linked list inetsw.
*/
static struct inet_protosw inetsw_array[] =
{
{
.type = SOCK_STREAM,
.protocol = IPPROTO_TCP,
.prot = &tcp_prot,
.ops = &inet_stream_ops,
.no_check = 0,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
},
{
.type = SOCK_DGRAM,
.protocol = IPPROTO_UDP,
.prot = &udp_prot,
.ops = &inet_dgram_ops,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_PERMANENT,
},
{
.type = SOCK_RAW,
.protocol = IPPROTO_IP, /* wild card */
.prot = &raw_prot,
.ops = &inet_sockraw_ops,
.no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
}
};
|
那么对于UDP来说，再找到对应的UDP protocol后，answer就指向inetsw_array[1]。
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
answer_flags = answer->flags;
rcu_read_unlock(); |
对于UDP来说，sock->ops就指向inet_dgram_ops，answer_prot就是udp_prot，answer_no_check为UDP_CSUM_DEFAULT，answer_flags为INET_PROTOSW_PERMANENT。
下面是inet_dgram_ops的定义
const struct proto_ops inet_dgram_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_dgram_connect,
.socketpair = sock_no_socketpair,
.accept = sock_no_accept,
.getname = inet_getname,
.poll = udp_poll,
.ioctl = inet_ioctl,
.listen = sock_no_listen,
.shutdown = inet_shutdown,
.setsockopt = sock_common_setsockopt,
.getsockopt = sock_common_getsockopt,
.sendmsg = inet_sendmsg,
.recvmsg = inet_recvmsg,
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};
|
answer_prot的定义是
struct proto udp_prot = {
.name = "UDP",
.owner = THIS_MODULE,
.close = udp_lib_close,
.connect = ip4_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.destroy = udp_destroy_sock,
.setsockopt = udp_setsockopt,
.getsockopt = udp_getsockopt,
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
.backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.rehash = udp_v4_rehash,
.get_port = udp_v4_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp_sock),
.slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
.compat_getsockopt = compat_udp_getsockopt,
#endif
}; |
继续后面的代码
err = -ENOBUFS;
sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
err = 0;
sk->sk_no_check = answer_no_check;
if (INET_PROTOSW_REUSE & answer_flags)
sk->sk_reuse = 1; |
首先申请一个struct sock的内存，然后sk->sk_no_check用于表示是否检查checksum，1为不检查，0为检查。通过与INET_PROTOSW_REUSE的位与操作——该宏表示这个协议是自动重用socket。
inet = inet_sk(sk);
inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
inet->nodefrag = 0; |
首先，将通用sock结构用函数inet_sk转为inet_sock——UDP的域是AF_INET，然后与宏INET_PROTOSW_ICSK相与来确定是否是基于连接——查看inetsw_array，只有TCP是有这个标志的。inet->nodefrag设为0，是允许分片。
if (SOCK_RAW == sock->type) {
inet->inet_num = protocol;
if (IPPROTO_RAW == protocol)
inet->hdrincl = 1;
} |
如果创建的是RAW socket，那么就以protocol协议号作为本地端口。如果protocol是IPPROTO_RAW，那么就给inet->hdincl置1，表示由用户来创建IP头，而不再由内核添加IP头。
if (ipv4_config.no_pmtu_disc)
inet->pmtudisc = IP_PMTUDISC_DONT;
else
inet->pmtudisc = IP_PMTUDISC_WANT;
inet->inet_id = 0; |
设置MTU的策略——这里说策略不太合适,IP_PMTUDISC_DONT表示不对frame帧分片，IP_PMTUDISC_WANT表示通过route转发过来的包来确定最小的MTU。然后初始化inet_id.
sock_init_data(sock, sk);
sk->sk_destruct = inet_sock_destruct;
sk->sk_protocol = protocol;
sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
初始化sk的结构体。
inet->uc_ttl = -1;
inet->mc_loop = 1;
inet->mc_ttl = 1;
inet->mc_all = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
sk_refcnt_debug_inc(sk);
|
初始化剩余的inet的成员变量，这些变量的含义可以直接看inet_sock结构体的注释，很清晰。uc_ttl表示单播ttl，mc_loop表示回环是否有效，mc_ttl表示组播ttl，mc_all是为了支持新的socket option IP_MULTICAST_ALL，如果设置了这个标志，表示所有发往端口的组播都会传给这个socket，如果没有设置，那么只有加入了的组的组播才会传给socket。
if (inet->inet_num) {
/* It assumes that any protocol which allows
* the user to assign a number at socket
* creation time automatically
* shares.
*/
inet->inet_sport = htons(inet->inet_num);
/* Add to protocol hash chains. */
sk->sk_prot->hash(sk);
}
if (sk->sk_prot->init) {
err = sk->sk_prot->init(sk);
if (err)
sk_common_release(sk);
} |
当inet->inet_num不为0时，设置inet的source port，并把sk加到hash表中——对于UDP，不会执行这个。如果该协议有init函数，就调用init。通过inetsw_array可知，udp是没有init函数的，而tcp和ip，raw的init函数分别为tcp_v4_init_sock，raw_init。
到此，UDP的socket已经建立成功了。
