Linux内核网络协议栈8—socket监听
几个问题
了解以下几个问题的同学可以直接忽略下文：
listen( server_sockfd, 5) ; ?
asmlinkage long sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; int somaxconn; // 根据文件描述符取得内核中的socket sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { // 根据系统中的设置调整参数backlog somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn; if ((unsigned)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); // 调用相应协议簇的listen函数 if (!err) err = sock->ops->listen(sock, backlog); fput_light(sock->file, fput_needed); } return err; }?
int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; int err; lock_sock(sk); err = -EINVAL; // 1 这里首先检查socket的状态和类型，如果状态或类型不正确，返回出错信息 if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto out; old_state = sk->sk_state; // 2 这里检查sock的状态是否是TCP_CLOSE或TCP_LISTEN，如果不是，返回出错信息 if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) goto out; /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ // 3 当sock的状态不是TCP_LISTEN时，做监听相关的初始化 if (old_state != TCP_LISTEN) { err = inet_csk_listen_start(sk, backlog); if (err) goto out; } // 4 设置sock的最大并发连接请求数 sk->sk_max_ack_backlog = backlog; err = 0; out: release_sock(sk); return err; }?
int inet_csk_listen_start(struct sock *sk, const int nr_table_entries){ struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); // 初始化连接等待队列 int rc = reqsk_queue_alloc(&icsk->icsk_accept_queue, nr_table_entries); if (rc != 0) return rc; sk->sk_max_ack_backlog = 0; sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); // 设置sock的状态为TCP_LISTEN sk->sk_state = TCP_LISTEN; if (!sk->sk_prot->get_port(sk, inet->num)) { inet->sport = htons(inet->num); sk_dst_reset(sk); sk->sk_prot->hash(sk); return 0; } sk->sk_state = TCP_CLOSE; __reqsk_queue_destroy(&icsk->icsk_accept_queue); return -EADDRINUSE;}?
struct request_sock { struct request_sock *dl_next; /* Must be first */ u16 mss; u8 retrans; u8 cookie_ts; /* syncookie: encode tcpopts in timestamp */ /* The following two fields can be easily recomputed I think -AK */ u32 window_clamp; /* window clamp at creation time */ u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; unsigned long expires; const struct request_sock_ops *rsk_ops; struct sock *sk; u32 secid; u32 peer_secid; };?
struct listen_sock { u8 max_qlen_log; /* 3 bytes hole, try to use */ int qlen; int qlen_young; int clock_hand; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; };?
struct request_sock_queue { struct request_sock *rskq_accept_head; struct request_sock *rskq_accept_tail; rwlock_t syn_wait_lock; u16 rskq_defer_accept; /* 2 bytes hole, try to pack */ struct listen_sock *listen_opt; };?
int reqsk_queue_alloc(struct request_sock_queue *queue, unsigned int nr_table_entries) { size_t lopt_size = sizeof(struct listen_sock); struct listen_sock *lopt; // 1 控制nr_table_entries在8~ sysctl_max_syn_backlog之间 nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog); nr_table_entries = max_t(u32, nr_table_entries, 8); // 2 向上取2的幂 nr_table_entries = roundup_pow_of_two(nr_table_entries + 1); // 3 申请等待队列空间 lopt_size += nr_table_entries * sizeof(struct request_sock *); if (lopt_size > PAGE_SIZE) lopt = __vmalloc(lopt_size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); else lopt = kzalloc(lopt_size, GFP_KERNEL); if (lopt == NULL) return -ENOMEM; // 4 设置listen_sock的成员max_qlen_log最小为3，最大为nr_table_entries的对数 for (lopt->max_qlen_log = 3; (1 << lopt->max_qlen_log) < nr_table_entries; lopt->max_qlen_log++); // 5 相关字段赋值 get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); rwlock_init(&queue->syn_wait_lock); queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; write_lock_bh(&queue->syn_wait_lock); queue->listen_opt = lopt; write_unlock_bh(&queue->syn_wait_lock); return 0; }?
if (!sk->sk_prot->get_port(sk, inet->num)) { // 这里再次判断端口是否被占用 inet->sport = htons(inet->num); sk_dst_reset(sk); // 将当前socket哈希到inet_hashinfo中 sk->sk_prot->hash(sk); return 0; }?
void inet_hash(struct sock *sk) { if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); __inet_hash(sk); local_bh_enable(); } } static void __inet_hash(struct sock *sk) { // 取得inet_hashinfo结构 struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_head *list; rwlock_t *lock; // 状态检查 if (sk->sk_state != TCP_LISTEN) { __inet_hash_nolisten(sk); return; } BUG_TRAP(sk_unhashed(sk)); // 计算hash值，取得链表 list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; lock = &hashinfo->lhash_lock; inet_listen_wlock(hashinfo); // 将sock添加到链表中 __sk_add_node(sk, list); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); write_unlock(lock); wake_up(&hashinfo->lhash_wait); }?
了解到这里，回答文初提出的3个问题，应该没什么问题了吧 :)
