詳解linux裡的backlog引數

int listen(int sockfd, int backlog)

struct request_sock_queue {
/*Points to the request_sock accept queue, when after 3 handshake will add the request_sock from syn_table to here*/
    struct request_sock    *rskq_accept_head;
    struct request_sock    *rskq_accept_tail;
    rwlock_t        syn_wait_lock;
    u8            rskq_defer_accept;
    /* 3 bytes hole, try to pack */
    struct listen_sock    *listen_opt;
};
struct listen_sock {
    u8            max_qlen_log; /*2^max_qlen_log is the length of the accpet queue, max of max_qlen_log is 10. (2^10=1024)*/
    /* 3 bytes hole, try to use */
    int            qlen; /* qlen is the current length of the accpet queue*/
    int            qlen_young;
    int            clock_hand;
    u32            hash_rnd;
    u32            nr_table_entries; /*nr_table_entries is the number of the syn_table,max is 512*/
    struct request_sock    *syn_table[0];
};
struct request_sock {
	struct request_sock		*dl_next; /* Must be first member! */
	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 sock{
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
}

const struct inet_connection_sock_af_ops ipv4_specific = {
	.queue_xmit	   = ip_queue_xmit,
	.send_check	   = tcp_v4_send_check,
	.rebuild_header	   = inet_sk_rebuild_header,
	.conn_request	   = tcp_v4_conn_request,
	.syn_recv_sock	   = tcp_v4_syn_recv_sock,
	.remember_stamp	   = tcp_v4_remember_stamp,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
	.bind_conflict	   = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
};

int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
	/* Never answer to SYNs send to broadcast or multicast */
	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		goto drop;

	/* TW buckets are converted to open requests without
	 * limitations, they conserve resources and peer is
	 * evidently real one.
	 */
	if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
#ifdef CONFIG_SYN_COOKIES
		if (sysctl_tcp_syncookies) {
			want_cookie = 1;
		} else
#endif
		goto drop;
	}

	/* Accept backlog is full. If we have already queued enough
	 * of warm entries in syn queue, drop request. It is better than
	 * clogging syn queue with openreqs with exponentially increasing
	 * timeout.
	 */
	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;
....
}

nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog);
nr_table_entries = max_t(u32, nr_table_entries, 8);
nr_table_entries = roundup_pow_of_two(nr_table_entries + 1);
for (lopt->max_qlen_log = 3;
	     (1 << lopt->max_qlen_log) < nr_table_entries;
	     lopt->max_qlen_log++);

SYSCALL_DEFINE2(listen, int, fd, int, backlog)
{
	struct socket *sock;
	int err, fput_needed;
	int somaxconn;
 
	sock = sockfd_lookup_light(fd, &err, &fput_needed);
	if (sock) {
		<span style="color: rgb(255, 102, 102);">somaxconn = sock_net(sock->sk)->core.sysctl_somaxconn;
		if ((unsigned)backlog > somaxconn)
			backlog = somaxconn;</span>
 
		err = security_socket_listen(sock, backlog);
		if (!err)
			err = sock->ops->listen(sock, backlog);
 
		fput_light(sock->file, fput_needed);
	}
	return err;
}

static inline int sk_acceptq_is_full(struct sock *sk)
{
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}
int inet_listen(struct socket *sock, int backlog)
{
    sk->sk_max_ack_backlog = backlog;
}

 if (sk->sk_state == TCP_LISTEN) {
		tcp_synack_timer(sk);
		goto out;
}

static void tcp_synack_timer(struct sock *sk)
{
	inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL,
				   TCP_TIMEOUT_INIT, TCP_RTO_MAX);
}

struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
				  struct request_sock *req,
				  struct dst_entry *dst)
{
	struct inet_request_sock *ireq;
	struct inet_sock *newinet;
	struct tcp_sock *newtp;
	struct sock *newsk;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
#endif
 
	if (sk_acceptq_is_full(sk))
		goto exit_overflow;
 
	if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
		goto exit;
 
	newsk = tcp_create_openreq_child(sk, req, skb);
	if (!newsk)
		goto exit;
 
	newsk->sk_gso_type = SKB_GSO_TCPV4;
	sk_setup_caps(newsk, dst);
 
	newtp		      = tcp_sk(newsk);
	newinet		      = inet_sk(newsk);
	ireq		      = inet_rsk(req);
	newinet->inet_daddr   = ireq->rmt_addr;
	newinet->inet_rcv_saddr = ireq->loc_addr;
	newinet->inet_saddr	      = ireq->loc_addr;
	newinet->opt	      = ireq->opt;
	ireq->opt	      = NULL;
	newinet->mc_index     = inet_iif(skb);
	newinet->mc_ttl	      = ip_hdr(skb)->ttl;
	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (newinet->opt)
		inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen;
	newinet->inet_id = newtp->write_seq ^ jiffies;
 
	tcp_mtup_init(newsk);
	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
	if (tcp_sk(sk)->rx_opt.user_mss &&
	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
 
	tcp_initialize_rcv_mss(newsk);
 
#ifdef CONFIG_TCP_MD5SIG
	/* Copy over the MD5 key from the original socket */
	key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr);
	if (key != NULL) {
		/*
		 * We're using one, so create a matching key
		 * on the newsk structure. If we fail to get
		 * memory, then we end up not copying the key
		 * across. Shucks.
		 */
		char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC);
		if (newkey != NULL)
			tcp_v4_md5_do_add(newsk, newinet->inet_daddr,
					  newkey, key->keylen);
		newsk->sk_route_caps &= ~NETIF_F_GSO_MASK;
	}
#endif
 
	__inet_hash_nolisten(newsk, NULL);
	__inet_inherit_port(sk, newsk);
 
	return newsk;
 
exit_overflow:
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
exit:
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
	dst_release(dst);
	return NULL;
}

case TCP_SYN_RECV:
			if (acceptable) {
				tp->copied_seq = tp->rcv_nxt;
				smp_mb();
				tcp_set_state(sk, TCP_ESTABLISHED);

static void get_openreq4(struct sock *sk, struct request_sock *req,
			 struct seq_file *f, int i, int uid, int *len)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int ttd = req->expires - jiffies;
 
	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n",
		i,
		ireq->loc_addr,
		ntohs(inet_sk(sk)->inet_sport),
		ireq->rmt_addr,
		ntohs(ireq->rmt_port),
		TCP_SYN_RECV,
		0, 0, /* could print option size, but that is af dependent. */
		1,    /* timers active (only the expire timer) */
		jiffies_to_clock_t(ttd),
		req->retrans,
		uid,
		0,  /* non standard timer */
		0, /* open_requests have no inode */
		atomic_read(&sk->sk_refcnt),
		req,
		len);
}