tcp.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

	       	(TCPF_ESTABLISHED|TCPF_CLOSE_WAIT|TCPF_FIN_WAIT1|
		 TCPF_FIN_WAIT2|TCPF_SYN_RECV));
}

int tcp_disconnect(struct sock *sk, int flags)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;
	int old_state;
	int err = 0;

	old_state = sk->state;
	if (old_state != TCP_CLOSE)
		tcp_set_state(sk, TCP_CLOSE);

	/* ABORT function of RFC793 */
	if (old_state == TCP_LISTEN) {
		tcp_listen_stop(sk);
	} else if (tcp_need_reset(old_state) ||
		   (tp->snd_nxt != tp->write_seq &&
		    (1<<old_state)&(TCPF_CLOSING|TCPF_LAST_ACK))) {
		/* The last check adjusts for discrepance of Linux wrt. RFC
		 * states
		 */
		tcp_send_active_reset(sk, gfp_any());
		sk->err = ECONNRESET;
	} else if (old_state == TCP_SYN_SENT)
		sk->err = ECONNRESET;

	tcp_clear_xmit_timers(sk);
	__skb_queue_purge(&sk->receive_queue);
  	tcp_writequeue_purge(sk);
  	__skb_queue_purge(&tp->out_of_order_queue);

	sk->dport = 0;

	if (!(sk->userlocks&SOCK_BINDADDR_LOCK)) {
		sk->rcv_saddr = 0;
		sk->saddr = 0;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
		memset(&sk->net_pinfo.af_inet6.saddr, 0, 16);
		memset(&sk->net_pinfo.af_inet6.rcv_saddr, 0, 16);
#endif
	}

	sk->shutdown = 0;
	sk->done = 0;
	tp->srtt = 0;
	if ((tp->write_seq += tp->max_window+2) == 0)
		tp->write_seq = 1;
	tp->backoff = 0;
	tp->snd_cwnd = 2;
	tp->probes_out = 0;
	tp->packets_out = 0;
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_cnt = 0;
	tp->ca_state = TCP_CA_Open;
	tcp_clear_retrans(tp);
	tcp_delack_init(tp);
	tp->send_head = NULL;
	tp->saw_tstamp = 0;
	tcp_sack_reset(tp);
	__sk_dst_reset(sk);

	BUG_TRAP(!sk->num || sk->prev);

	sk->error_report(sk);
	return err;
}

/*
 *	Wait for an incoming connection, avoid race
 *	conditions. This must be called with the socket locked.
 */
static int wait_for_connect(struct sock * sk, long timeo)
{
	DECLARE_WAITQUEUE(wait, current);
	int err;

	/*
	 * True wake-one mechanism for incoming connections: only
	 * one process gets woken up, not the 'whole herd'.
	 * Since we do not 'race & poll' for established sockets
	 * anymore, the common case will execute the loop only once.
	 *
	 * Subtle issue: "add_wait_queue_exclusive()" will be added
	 * after any current non-exclusive waiters, and we know that
	 * it will always _stay_ after any new non-exclusive waiters
	 * because all non-exclusive waiters are added at the
	 * beginning of the wait-queue. As such, it's ok to "drop"
	 * our exclusiveness temporarily when we get woken up without
	 * having to remove and re-insert us on the wait queue.
	 */
	add_wait_queue_exclusive(sk->sleep, &wait);
	for (;;) {
		current->state = TASK_INTERRUPTIBLE;
		release_sock(sk);
		if (sk->tp_pinfo.af_tcp.accept_queue == NULL)
			timeo = schedule_timeout(timeo);
		lock_sock(sk);
		err = 0;
		if (sk->tp_pinfo.af_tcp.accept_queue)
			break;
		err = -EINVAL;
		if (sk->state != TCP_LISTEN)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
	}
	current->state = TASK_RUNNING;
	remove_wait_queue(sk->sleep, &wait);
	return err;
}

/*
 *	This will accept the next outstanding connection.
 */

struct sock *tcp_accept(struct sock *sk, int flags, int *err)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;
	struct open_request *req;
	struct sock *newsk;
	int error;

	lock_sock(sk); 

	/* We need to make sure that this socket is listening,
	 * and that it has something pending.
	 */
	error = -EINVAL;
	if (sk->state != TCP_LISTEN)
		goto out;

	/* Find already established connection */
	if (!tp->accept_queue) {
		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);

		/* If this is a non blocking socket don't sleep */
		error = -EAGAIN;
		if (!timeo)
			goto out;

		error = wait_for_connect(sk, timeo);
		if (error)
			goto out;
	}

	req = tp->accept_queue;
	if ((tp->accept_queue = req->dl_next) == NULL)
		tp->accept_queue_tail = NULL;

 	newsk = req->sk;
	tcp_acceptq_removed(sk);
	tcp_openreq_fastfree(req);
	BUG_TRAP(newsk->state != TCP_SYN_RECV);
	release_sock(sk);
	return newsk;

out:
	release_sock(sk);
	*err = error; 
	return NULL;
}

/*
 *	Socket option code for TCP. 
 */
  
int tcp_setsockopt(struct sock *sk, int level, int optname, char *optval, 
		   int optlen)
{
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);
	int val;
	int err = 0;

	if (level != SOL_TCP)
		return tp->af_specific->setsockopt(sk, level, optname, 
						   optval, optlen);

	if(optlen<sizeof(int))
		return -EINVAL;

	if (get_user(val, (int *)optval))
		return -EFAULT;

	lock_sock(sk);

	switch(optname) {
	case TCP_MAXSEG:
		/* values greater than interface MTU won't take effect.  however at
		 * the point when this call is done we typically don't yet know
		 * which interface is going to be used
		 */
		if(val < 8 || val > MAX_TCP_WINDOW) {
			err = -EINVAL;
			break;
		}
		tp->user_mss = val;
		break;

	case TCP_NODELAY:
		/* You cannot try to use this and TCP_CORK in
		 * tandem, so let the user know.
		 */
		if (tp->nonagle == 2) {
			err = -EINVAL;
			break;
		}
		tp->nonagle = (val == 0) ? 0 : 1;
		if (val)
			tcp_push_pending_frames(sk, tp);
		break;

	case TCP_CORK:
		/* When set indicates to always queue non-full frames.
		 * Later the user clears this option and we transmit
		 * any pending partial frames in the queue.  This is
		 * meant to be used alongside sendfile() to get properly
		 * filled frames when the user (for example) must write
		 * out headers with a write() call first and then use
		 * sendfile to send out the data parts.
		 *
		 * You cannot try to use TCP_NODELAY and this mechanism
		 * at the same time, so let the user know.
		 */
		if (tp->nonagle == 1) {
			err = -EINVAL;
			break;
		}
		if (val != 0) {
			tp->nonagle = 2;
		} else {
			tp->nonagle = 0;

			tcp_push_pending_frames(sk, tp);
		}
		break;
		
	case TCP_KEEPIDLE:
		if (val < 1 || val > MAX_TCP_KEEPIDLE)
			err = -EINVAL;
		else {
			tp->keepalive_time = val * HZ;
			if (sk->keepopen && !((1<<sk->state)&(TCPF_CLOSE|TCPF_LISTEN))) {
				__u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
				if (tp->keepalive_time > elapsed)
					elapsed = tp->keepalive_time - elapsed;
				else
					elapsed = 0;
				tcp_reset_keepalive_timer(sk, elapsed);
			}
		}
		break;
	case TCP_KEEPINTVL:
		if (val < 1 || val > MAX_TCP_KEEPINTVL)
			err = -EINVAL;
		else
			tp->keepalive_intvl = val * HZ;
		break;
	case TCP_KEEPCNT:
		if (val < 1 || val > MAX_TCP_KEEPCNT)
			err = -EINVAL;
		else
			tp->keepalive_probes = val;
		break;
	case TCP_SYNCNT:
		if (val < 1 || val > MAX_TCP_SYNCNT)
			err = -EINVAL;
		else
			tp->syn_retries = val;
		break;

	case TCP_LINGER2:
		if (val < 0)
			tp->linger2 = -1;
		else if (val > sysctl_tcp_fin_timeout/HZ)
			tp->linger2 = 0;
		else
			tp->linger2 = val*HZ;
		break;

	case TCP_DEFER_ACCEPT:
		tp->defer_accept = 0;
		if (val > 0) {
			/* Translate value in seconds to number of retransmits */
			while (tp->defer_accept < 32 && val > ((TCP_TIMEOUT_INIT/HZ)<<tp->defer_accept))
				tp->defer_accept++;
			tp->defer_accept++;
		}
		break;

	case TCP_WINDOW_CLAMP:
		if (val==0) {
			if (sk->state != TCP_CLOSE) {
				err = -EINVAL;
				break;
			}
			tp->window_clamp = 0;
		} else {
			tp->window_clamp = val<SOCK_MIN_RCVBUF/2 ?
				SOCK_MIN_RCVBUF/2 : val;
		}
		break;

	case TCP_QUICKACK:
		if (!val) {
			tp->ack.pingpong = 1;
		} else {
			tp->ack.pingpong = 0;
			if ((1<<sk->state)&(TCPF_ESTABLISHED|TCPF_CLOSE_WAIT) &&
			    tcp_ack_scheduled(tp)) {
				tp->ack.pending |= TCP_ACK_PUSHED;
				cleanup_rbuf(sk, 1);
				if (!(val & 1))
					tp->ack.pingpong = 1;
			}
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};
	release_sock(sk);
	return err;
}

int tcp_getsockopt(struct sock *sk, int level, int optname, char *optval,
		   int *optlen)
{
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);
	int val, len;

	if(level != SOL_TCP)
		return tp->af_specific->getsockopt(sk, level, optname,
						   optval, optlen);

	if(get_user(len,optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));
	
	if(len < 0)
		return -EINVAL;

	switch(optname) {
	case TCP_MAXSEG:
		val = tp->mss_cache;
		if (val == 0 && ((1<<sk->state)&(TCPF_CLOSE|TCPF_LISTEN)))
			val = tp->user_mss;
		break;
	case TCP_NODELAY:
		val = (tp->nonagle == 1);
		break;
	case TCP_CORK:
		val = (tp->nonagle == 2);
		break;
	case TCP_KEEPIDLE:
		val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time)/HZ;
		break;
	case TCP_KEEPINTVL:
		val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl)/HZ;
		break;
	case TCP_KEEPCNT:
		val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
		break;
	case TCP_SYNCNT:
		val = tp->syn_retries ? : sysctl_tcp_syn_retries;
		break;
	case TCP_LINGER2:
		val = tp->linger2;
		if (val >= 0)
			val = (val ? : sysctl_tcp_fin_timeout)/HZ;
		break;
	case TCP_DEFER_ACCEPT:
		val = tp->defer_accept == 0 ? 0 : ((TCP_TIMEOUT_INIT/HZ)<<(tp->defer_accept-1));
		break;
	case TCP_WINDOW_CLAMP:
		val = tp->window_clamp;
		break;
	case TCP_INFO:
	{
		struct tcp_info info;
		u32 now = tcp_time_stamp;

		if(get_user(len,optlen))
			return -EFAULT;
		info.tcpi_state = sk->state;
		info.tcpi_ca_state = tp->ca_state;
		info.tcpi_retransmits = tp->retransmits;
		info.tcpi_probes = tp->probes_out;
		info.tcpi_backoff = tp->backoff;
		info.tcpi_options = 0;
		if (tp->tstamp_ok)
			info.tcpi_options |= TCPI_OPT_TIMESTAMPS;
		if (tp->sack_ok)
			info.tcpi_options |= TCPI_OPT_SACK;
		if (tp->wscale_ok) {
			info.tcpi_options |= TCPI_OPT_WSCALE;
			info.tcpi_snd_wscale = tp->snd_wscale;
			info.tcpi_rcv_wscale = tp->rcv_wscale;
		} else {
			info.tcpi_snd_wscale = 0;
			info.tcpi_rcv_wscale = 0;
		}
		if (tp->ecn_flags&TCP_ECN_OK)
			info.tcpi_options |= TCPI_OPT_ECN;

		info.tcpi_rto = (1000000*tp->rto)/HZ;
		info.tcpi_ato = (1000000*tp->ack.ato)/HZ;
		info.tcpi_snd_mss = tp->mss_cache;
		info.tcpi_rcv_mss = tp->ack.rcv_mss;

		info.tcpi_unacked = tp->packets_out;
		info.tcpi_sacked = tp->sacked_out;
		info.tcpi_lost = tp->lost_out;
		info.tcpi_retrans = tp->retrans_out;
		info.tcpi_fackets = tp->fackets_out;

		info.tcpi_last_data_sent = ((now - tp->lsndtime)*1000)/HZ;
		info.tcpi_last_ack_sent = 0;
		info.tcpi_last_data_recv = ((now - tp->ack.lrcvtime)*1000)/HZ;
		info.tcpi_last_ack_recv = ((now - tp->rcv_tstamp)*1000)/HZ;

		info.tcpi_pmtu = tp->pmtu_cookie;
		info.tcpi_rcv_ssthresh = tp->rcv_ssthresh;
		info.tcpi_rtt = ((1000000*tp->srtt)/HZ)>>3;
		info.tcpi_rttvar = ((1000000*tp->mdev)/HZ)>>2;
		info.tcpi_snd_ssthresh = tp->snd_ssthresh;
		info.tcpi_snd_cwnd = tp->snd_cwnd;
		info.tcpi_advmss = tp->advmss;
		info.tcpi_reordering = tp->reordering;

		len = min_t(unsigned int, len, sizeof(info));
		if(put_user(len, optlen))
			return -EFAULT;
		if(copy_to_user(optval, &info,len))
			return -EFAULT;
		return 0;
	}
	case TCP_QUICKACK:
		val = !tp->ack.pingpong;
		break;
	default:
		return -ENOPROTOOPT;
	};

  	if(put_user(len, optlen))
  		return -EFAULT;
	if(copy_to_user(optval, &val,len))
		return -EFAULT;
  	return 0;
}


extern void __skb_cb_too_small_for_tcp(int, int);
extern void tcpdiag_init(void);

void __init tcp_init(void)
{
	struct sk_buff *skb = NULL;
	unsigned long goal;
	int order, i;

	if(sizeof(struct tcp_skb_cb) > sizeof(skb->cb))
		__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
					   sizeof(skb->cb));

	tcp_openreq_cachep = kmem_cache_create("tcp_open_request",
						   sizeof(struct open_request),
					       0, SLAB_HWCACHE_ALIGN,
					       NULL, NULL);
	if(!tcp_openreq_cachep)
		panic("tcp_init: Cannot alloc open_request cache.");

	tcp_bucket_cachep = kmem_cache_create("tcp_bind_bucket",
					      sizeof(struct tcp_bind_bucket),
					      0, SLAB_HWCACHE_ALIGN,
					      NULL, NULL);
	if(!tcp_bucket_cachep)
		panic("tcp_init: Cannot alloc tcp_bind_bucket cache.");

	tcp_timewait_cachep = kmem_cache_create("tcp_tw_bucket",
						sizeof(struct tcp_tw_bucket),
						0, SLAB_HWCACHE_ALIGN,
						NULL, NULL);
	if(!tcp_timewait_cachep)
		panic("tcp_init: Cannot alloc tcp_