最近一直在读内核网络协议栈源码，这里以ipv4/tcp为例对socket相关系统调用的流程做一个简要整理，这些相关系统调用的内部细节虽然各有不同，但其调用流程则基本一致；
调用流程：
(1)系统调用 –> (2)查找socket –> (3)执行socket的对应操作函数 –> (4)执行传输层协议的对应操作函数；
中间核心数据结构为inetws_array[]，位于af_inet.c，以第一个元素type=SOCK_STREAM，protocol=IPPROTO_TCP为例，该类型适用与tcp协议，当创建tcp socket时，其操作socket->ops赋值为&inet_stream_ops，对应的传输控制块操作sock->sk_prot赋值为&tcp_prot；
/* 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,
.flags = INET_PROTOSW_PERMANENT |
INET_PROTOSW_ICSK,
}, {
.type = SOCK_DGRAM,
.protocol = IPPROTO_UDP,
.prot = &udp_prot,
.ops = &inet_dgram_ops,
.flags = INET_PROTOSW_PERMANENT,
}, {
.type = SOCK_DGRAM,
.protocol = IPPROTO_ICMP,
.prot = &ping_prot,
.ops = &inet_sockraw_ops,
.flags = INET_PROTOSW_REUSE,
}, {
.type = SOCK_RAW,
.protocol = IPPROTO_IP, /* wild card */
.prot = &raw_prot,
.ops = &inet_sockraw_ops,
.flags = INET_PROTOSW_REUSE,
}
};
查看inet_stream_ops结构会发现，其中包含了各种socket系统调用的对应的处理函数；
const struct proto_ops inet_stream_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
.release = inet_release,
.bind = inet_bind,
.connect = inet_stream_connect,
.socketpair = sock_no_socketpair,
.accept = inet_accept,
.getname = inet_getname,
.poll = tcp_poll,
.ioctl = inet_ioctl,
.listen = inet_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,
.splice_read = tcp_splice_read,
.read_sock = tcp_read_sock,
.peek_len = tcp_peek_len,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_sock_common_setsockopt,
.compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
};
具体实例，以tcp bind系统调用为例：
SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen)
{
struct socket *sock;
struct sockaddr_storage address;
int err, fput_needed; /* 获取socket ，fput_need标识是否需要减少文件引用计数*/
sock = sockfd_lookup_light(fd, &err, &fput_needed);
if (sock) {
/* 将用户空间地址复制到内核空间 */
err = move_addr_to_kernel(umyaddr, addrlen, &address);
if (err >= ) {
/* 安全模块的bind检查 */
err = security_socket_bind(sock,
(struct sockaddr *)&address,
addrlen);
if (!err)
/* 调用socket的bind操作 */
err = sock->ops->bind(sock,
(struct sockaddr *)
&address, addrlen);
} /* 根据fput_needed决定是否减少引用计数 */
fput_light(sock->file, fput_needed);
}
return err;
}
上面的sock->ops->bind操作实际是调用了inet_stream_ops.bind
/* 地址绑定 */
int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
/* 省略无关代码 */
/* If the socket has its own bind function then use it. (RAW) */
/*
如果传输控制块有自己的bind操作则调用，
目前只有raw实现了自己的bind
*/
if (sk->sk_prot->bind) {
err = sk->sk_prot->bind(sk, uaddr, addr_len);
goto out;
} /* 省略无关代码 */ /*
端口不为0，或者端口为0允许绑定
则使用协议的具体获取端口函数绑定端口
*/
if ((snum || !inet->bind_address_no_port) &&
sk->sk_prot->get_port(sk, snum)) { /* 绑定失败 */
inet->inet_saddr = inet->inet_rcv_saddr = ; /* 端口在使用中 */
err = -EADDRINUSE;
goto out_release_sock;
} /* 省略无关代码 */
out_release_sock:
release_sock(sk);
out:
return err;
}
上面的sk->sk_prot->bind以及sk->sk_prot->get_port为具体传输层实现的对应操作函数，其中只有raw socket实现了bind操作，我们不关注，而以tcp的get_port操作为例，实际上也就是调用了tcp_prot.get_port，具体tcp实现为inet_csk_get_port；（该函数尚未分析，后续补充）
/* Obtain a reference to a local port for the given sock,
* if snum is zero it means select any available local port.
* We try to allocate an odd port (and leave even ports for connect())
*/
int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
int ret = , port = snum;
struct inet_bind_hashbucket *head;
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
kuid_t uid = sock_i_uid(sk); if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
if (!head)
return ret;
if (!tb)
goto tb_not_found;
goto success;
}
head = &hinfo->bhash[inet_bhashfn(net, port,
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
if (net_eq(ib_net(tb), net) && tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
net, head, port);
if (!tb)
goto fail_unlock;
tb_found:
if (!hlist_empty(&tb->owners)) {
if (sk->sk_reuse == SK_FORCE_REUSE)
goto success; if ((tb->fastreuse > && reuse) ||
sk_reuseport_match(tb, sk))
goto success;
if (inet_csk_bind_conflict(sk, tb, true, true))
goto fail_unlock;
}
success:
if (!hlist_empty(&tb->owners)) {
tb->fastreuse = reuse;
if (sk->sk_reuseport) {
tb->fastreuseport = FASTREUSEPORT_ANY;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
} else {
tb->fastreuseport = ;
}
} else {
if (!reuse)
tb->fastreuse = ;
if (sk->sk_reuseport) {
/* We didn't match or we don't have fastreuseport set on
* the tb, but we have sk_reuseport set on this socket
* and we know that there are no bind conflicts with
* this socket in this tb, so reset our tb's reuseport
* settings so that any subsequent sockets that match
* our current socket will be put on the fast path.
*
* If we reset we need to set FASTREUSEPORT_STRICT so we
* do extra checking for all subsequent sk_reuseport
* socks.
*/
if (!sk_reuseport_match(tb, sk)) {
tb->fastreuseport = FASTREUSEPORT_STRICT;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
}
} else {
tb->fastreuseport = ;
}
}
if (!inet_csk(sk)->icsk_bind_hash)
inet_bind_hash(sk, tb, port);
WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
ret = ; fail_unlock:
spin_unlock_bh(&head->lock);
return ret;
}