tcp.c

		sk->sk_backlog_rcv(sk, skb);
	local_bh_enable();

	/* Clear memory counter. */
	tp->ucopy.memory = 0;
}

static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
	struct sk_buff *skb;
	u32 offset;

	skb_queue_walk(&sk->sk_receive_queue, skb) {
		offset = seq - TCP_SKB_CB(skb)->seq;
		if (skb->h.th->syn)
			offset--;
		if (offset < skb->len || skb->h.th->fin) {
			*off = offset;
			return skb;
		}
	}
	return NULL;
}

/*
 * This routine provides an alternative to tcp_recvmsg() for routines
 * that would like to handle copying from skbuffs directly in 'sendfile'
 * fashion.
 * Note:
 *	- It is assumed that the socket was locked by the caller.
 *	- The routine does not block.
 *	- At present, there is no support for reading OOB data
 *	  or for 'peeking' the socket using this routine
 *	  (although both would be easy to implement).
 */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);
	u32 seq = tp->copied_seq;
	u32 offset;
	int copied = 0;

	if (sk->sk_state == TCP_LISTEN)
		return -ENOTCONN;
	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
		if (offset < skb->len) {
			size_t used, len;

			len = skb->len - offset;
			/* Stop reading if we hit a patch of urgent data */
			if (tp->urg_data) {
				u32 urg_offset = tp->urg_seq - seq;
				if (urg_offset < len)
					len = urg_offset;
				if (!len)
					break;
			}
			used = recv_actor(desc, skb, offset, len);
			if (used <= len) {
				seq += used;
				copied += used;
				offset += used;
			}
			if (offset != skb->len)
				break;
		}
		if (skb->h.th->fin) {
			sk_eat_skb(sk, skb, 0);
			++seq;
			break;
		}
		sk_eat_skb(sk, skb, 0);
		if (!desc->count)
			break;
	}
	tp->copied_seq = seq;

	tcp_rcv_space_adjust(sk);

	/* Clean up data we have read: This will do ACK frames. */
	if (copied)
		tcp_cleanup_rbuf(sk, copied);
	return copied;
}

/*
 *	This routine copies from a sock struct into the user buffer.
 *
 *	Technical note: in 2.3 we work on _locked_ socket, so that
 *	tricks with *seq access order and skb->users are not required.
 *	Probably, code can be easily improved even more.
 */

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct task_struct *user_recv = NULL;
	int copied_early = 0;

	lock_sock(sk);

	TCP_CHECK_TIMER(sk);

	err = -ENOTCONN;
	if (sk->sk_state == TCP_LISTEN)
		goto out;

	timeo = sock_rcvtimeo(sk, nonblock);

	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;

	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

#ifdef CONFIG_NET_DMA
	tp->ucopy.dma_chan = NULL;
	preempt_disable();
	if ((len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
	    !sysctl_tcp_low_latency && __get_cpu_var(softnet_data.net_dma)) {
		preempt_enable_no_resched();
		tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len);
	} else
		preempt_enable_no_resched();
#endif

	do {
		struct sk_buff *skb;
		u32 offset;

		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		if (tp->urg_data && tp->urg_seq == *seq) {
			if (copied)
				break;
			if (signal_pending(current)) {
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}

		/* Next get a buffer. */

		skb = skb_peek(&sk->sk_receive_queue);
		do {
			if (!skb)
				break;

			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (before(*seq, TCP_SKB_CB(skb)->seq)) {
				printk(KERN_INFO "recvmsg bug: copied %X "
				       "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
				break;
			}
			offset = *seq - TCP_SKB_CB(skb)->seq;
			if (skb->h.th->syn)
				offset--;
			if (offset < skb->len)
				goto found_ok_skb;
			if (skb->h.th->fin)
				goto found_fin_ok;
			BUG_TRAP(flags & MSG_PEEK);
			skb = skb->next;
		} while (skb != (struct sk_buff *)&sk->sk_receive_queue);

		/* Well, if we have backlog, try to process it now yet. */

		if (copied >= target && !sk->sk_backlog.tail)
			break;

		if (copied) {
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current) ||
			    (flags & MSG_PEEK))
				break;
		} else {
			if (sock_flag(sk, SOCK_DONE))
				break;

			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;

			if (sk->sk_state == TCP_CLOSE) {
				if (!sock_flag(sk, SOCK_DONE)) {
					/* This occurs when user tries to read
					 * from never connected socket.
					 */
					copied = -ENOTCONN;
					break;
				}
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

		tcp_cleanup_rbuf(sk, copied);

		if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
			/* Install new reader */
			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
				user_recv = current;
				tp->ucopy.task = user_recv;
				tp->ucopy.iov = msg->msg_iov;
			}

			tp->ucopy.len = len;

			BUG_TRAP(tp->copied_seq == tp->rcv_nxt ||
				 (flags & (MSG_PEEK | MSG_TRUNC)));

			/* Ugly... If prequeue is not empty, we have to
			 * process it before releasing socket, otherwise
			 * order will be broken at second iteration.
			 * More elegant solution is required!!!
			 *
			 * Look: we have the following (pseudo)queues:
			 *
			 * 1. packets in flight
			 * 2. backlog
			 * 3. prequeue
			 * 4. receive_queue
			 *
			 * Each queue can be processed only if the next ones
			 * are empty. At this point we have empty receive_queue.
			 * But prequeue _can_ be not empty after 2nd iteration,
			 * when we jumped to start of loop because backlog
			 * processing added something to receive_queue.
			 * We cannot release_sock(), because backlog contains
			 * packets arrived _after_ prequeued ones.
			 *
			 * Shortly, algorithm is clear --- to process all
			 * the queues in order. We could make it more directly,
			 * requeueing packets from backlog to prequeue, if
			 * is not empty. It is more elegant, but eats cycles,
			 * unfortunately.
			 */
			if (!skb_queue_empty(&tp->ucopy.prequeue))
				goto do_prequeue;

			/* __ Set realtime policy in scheduler __ */
		}

		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			release_sock(sk);
			lock_sock(sk);
		} else
			sk_wait_data(sk, &timeo);

#ifdef CONFIG_NET_DMA
		tp->ucopy.wakeup = 0;
#endif

		if (user_recv) {
			int chunk;

			/* __ Restore normal policy in scheduler __ */

			if ((chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
				len -= chunk;
				copied += chunk;
			}

			if (tp->rcv_nxt == tp->copied_seq &&
			    !skb_queue_empty(&tp->ucopy.prequeue)) {
do_prequeue:
				tcp_prequeue_process(sk);

				if ((chunk = len - tp->ucopy.len) != 0) {
					NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
					len -= chunk;
					copied += chunk;
				}
			}
		}
		if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
			if (net_ratelimit())
				printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
				       current->comm, current->pid);
			peek_seq = tp->copied_seq;
		}
		continue;

	found_ok_skb:
		/* Ok so how much can we use? */
		used = skb->len - offset;
		if (len < used)
			used = len;

		/* Do we have urgent data here? */
		if (tp->urg_data) {
			u32 urg_offset = tp->urg_seq - *seq;
			if (urg_offset < used) {
				if (!urg_offset) {
					if (!sock_flag(sk, SOCK_URGINLINE)) {
						++*seq;
						offset++;
						used--;
						if (!used)
							goto skip_copy;
					}
				} else
					used = urg_offset;
			}
		}

		if (!(flags & MSG_TRUNC)) {
#ifdef CONFIG_NET_DMA
			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
				tp->ucopy.dma_chan = get_softnet_dma();

			if (tp->ucopy.dma_chan) {
				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
					tp->ucopy.dma_chan, skb, offset,
					msg->msg_iov, used,
					tp->ucopy.pinned_list);

				if (tp->ucopy.dma_cookie < 0) {

					printk(KERN_ALERT "dma_cookie < 0\n");

					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}
				if ((offset + used) == skb->len)
					copied_early = 1;

			} else
#endif
			{
				err = skb_copy_datagram_iovec(skb, offset,
						msg->msg_iov, used);
				if (err) {
					/* Exception. Bailout! */
					if (!copied)
						copied = -EFAULT;
					break;
				}
			}
		}

		*seq += used;
		copied += used;
		len -= used;

		tcp_rcv_space_adjust(sk);

skip_copy:
		if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
			tp->urg_data = 0;
			tcp_fast_path_check(sk, tp);
		}
		if (used + offset < skb->len)
			continue;

		if (skb->h.th->fin)
			goto found_fin_ok;
		if (!(flags & MSG_PEEK)) {
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		continue;

	found_fin_ok:
		/* Process the FIN. */
		++*seq;
		if (!(flags & MSG_PEEK)) {
			sk_eat_skb(sk, skb, copied_early);
			copied_early = 0;
		}
		break;
	} while (len > 0);

	if (user_recv) {
		if (!skb_queue_empty(&tp->ucopy.prequeue)) {
			int chunk;

			tp->ucopy.len = copied > 0 ? len : 0;

			tcp_prequeue_process(sk);

			if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
				len -= chunk;
				copied += chunk;
			}
		}

		tp->ucopy.task = NULL;
		tp->ucopy.len = 0;
	}

#ifdef CONFIG_NET_DMA
	if (tp->ucopy.dma_chan) {
		struct sk_buff *skb;
		dma_cookie_t done, used;

		dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);

		while (dma_async_memcpy_complete(tp->ucopy.dma_chan,
		                                 tp->ucopy.dma_cookie, &done,
		                                 &used) == DMA_IN_PROGRESS) {
			/* do partial cleanup of sk_async_wait_queue */
			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
			       (dma_async_is_complete(skb->dma_cookie, done,
			                              used) == DMA_SUCCESS)) {
				__skb_dequeue(&sk->sk_async_wait_queue);
				kfree_skb(skb);
			}
		}

		/* Safe to free early-copied skbs now */
		__skb_queue_purge(&sk->sk_async_wait_queue);
		dma_chan_put(tp->ucopy.dma_chan);
		tp->ucopy.dma_chan = NULL;
	}
	if (tp->ucopy.pinned_list) {
		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
		tp->ucopy.pinned_list = NULL;
	}
#endif

	/* According to UNIX98, msg_name/msg_namelen are ignored
	 * on connected socket. I was just happy when found this 8) --ANK
	 */

	/* Clean up data we have read: This will do ACK frames. */
	tcp_cleanup_rbuf(sk, copied);

	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return copied;

out:
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return err;

recv_urg:
	err = tcp_recv_urg(sk, timeo, msg, len, flags, addr_len);
	goto out;
}

/*
 *	State processing on a close. This implements the state shift for
 *	sending our FIN frame. Note that we only send a FIN for some
 *	states. A shutdown() may have already sent the FIN, or we may be
 *	closed.
 */

static const unsigned char new_state[16] = {
  /* current state:        new state:      action:	*/
  /* (Invalid)		*/ TCP_CLOSE,
  /* TCP_ESTABLISHED	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_SYN_SENT	*/ TCP_CLOSE,
  /* TCP_SYN_RECV	*/ TCP_FIN_WAIT1 | TCP_ACTION_FIN,
  /* TCP_FIN_WAIT1	*/ TCP_FIN_WAIT1,
  /* TCP_FIN_WAIT2	*/ TCP_FIN_WAIT2,
  /* TCP_TIME_WAIT	*/ TCP_CLOSE,
  /* TCP_CLOSE		*/ TCP_CLOSE,
  /* TCP_CLOSE_WAIT	*/ TCP_LAST_ACK  | TCP_ACTION_FIN,
  /* TCP_LAST_ACK	*/ TCP_LAST_ACK,
  /* TCP_LISTEN		*/ TCP_CLOSE,
  /* TCP_CLOSING	*/ TCP_CLOSING,
};

static int tcp_close_state(struct sock *sk)
{
	int next = (int)new_state[sk->sk_state];
	int ns = next & TCP_STATE_MASK;

	tcp_set_state(sk, ns);

	return next & TCP_ACTION_FIN;
}

/*
 *	Shutdown the sending side of a connection. Much like close except
 *	that we don't receive shut down or set_sock_flag(sk, SOCK_DEAD).
 */

void tcp_shutdown(struct sock *sk, int how)
{
	/*	We need to grab some memory, and put together a FIN,
	 *	and then put it into the queue to be sent.
	 *		Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92.
	 */
	if (!(how & SEND_SHUTDOWN))
		return;

	/* If we've already sent a FIN, or it's a closed state, skip this. */
	if ((1 << sk->sk_state) &
	    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
	     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) {
		/* Clear out any half completed packets.  FIN if needed. */
		if (tcp_close_state(sk))
			tcp_send_fin(sk);
	}
}

void tcp_close(struct sock *sk, long timeout)
{
	struct sk_buff *skb;
	int data_was_unread = 0;
	int state;

	lock_sock(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == TCP_LISTEN) {
		tcp_set_state(sk, TCP_CLOSE);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	/*  We need to flush the recv. buffs.  We do this only on the
	 *  descriptor close, not protocol-sourced closes, because the
	 *  reader process may not have drained the data yet!
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
			  skb->h.th->fin;
		data_was_unread += len;
		__kfree_skb(skb);
	}

	sk_stream_mem_reclaim(sk);

	/* As outlined in draft-ietf-tcpimpl-prob-03.txt, section
	 * 3.10, we send a RST here because data was lost.  To
	 * witness the awful effects of the old behavior of always
	 * doing a FIN, run an older 2.1.x kernel or 2.0.x, start
	 * a bulk GET in an FTP client, suspend the process, wait
	 * for the client to advertise a zero window, then kill -9
	 * the FTP client, wheee...  Note: timeout is always zero
	 * in such a case.
	 */
	if (data_was_unread) {
		/* Unread data was tossed, zap the connection. */
		NET_INC_STATS_USER(LINUX_MIB_TCPABORTONCLOSE);
		tcp_set_state(sk, TCP_CLOSE);
		tcp_send_active_reset(sk, GFP_KERNEL);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
		NET_INC_STATS_USER(LINUX_MIB_TCPABORTONDATA);
	} else if (tcp_close_state(sk)) {
		/* We FIN if the application ate all the data before
		 * zapping the connection.
		 */

		/* RED-PEN. Formally speaking, we have broken TCP state
		 * machine. State transitions:
		 *
		 * TCP_ESTABLISHED -> TCP_FIN_WAIT1
		 * TCP_SYN_RECV	-> TCP_FIN_WAIT1 (forget it, it's impossible)
		 * TCP_CLOSE_WAIT -> TCP_LAST_ACK
		 *
		 * are legal only when FIN has been sent (i.e. in window),
		 * rather than queued out of window. Purists blame.
		 *
		 * F.e. "RFC state" is ESTABLISHED,
		 * if Linux state is FIN-WAIT-1, but FIN is still not sent.
		 *
		 * The visible declinations are that sometimes
		 * we enter time-wait state, when it is not required really
		 * (harmless), do not send active resets, when they are
		 * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when
		 * they look as CLOSING or LAST_ACK for Linux)
		 * Probably, I missed some more holelets.
		 * 						--ANK
		 */
		tcp_send_fin(sk);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);
	atomic_inc(sk->sk_prot->orphan_count);

	/* It is the last release_sock in its life. It will remove backlog. */
	release_sock(sk);


	/* Now socket is owned by kernel and we acquire BH lock
	   to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	BUG_TRAP(!sock_owned_by_user(sk));

	/* Have we already been destroyed by a softirq or backlog? */
	if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
		goto out;

	/*	This is a (useful) BSD violating of the RFC. There is a
	 *	problem with TCP as specified in that the other end could
	 *	keep a socket open forever with no application left this end.
	 *	We use a 3 minute timeout (about the same as BSD) then kill
	 *	our end. If they send after that then tough - BUT: long enough
	 *	that we won't make the old 4*rto = almost no time - whoops
	 *	reset mistake.
	 *
	 *	Nope, it was not mistake. It is really desired behaviour
	 *	f.e. on http servers, when such sockets are useless, but
	 *	consume significant resources. Let's do it with special
	 *	linger2	option.					--ANK
	 */

	if (sk->sk_state == TCP_FIN_WAIT2) {
		struct tcp_sock *tp = tcp_sk(sk);
		if (tp->linger2 < 0) {
			tcp_set_state(sk, TCP_CLOSE);
			tcp_send_active_reset(sk, GFP_ATOMIC);
			NET_INC_STATS_BH(LINUX_MIB_TCPABORTONLINGER);
		} else {
			const int tmo = tcp_fin_time(sk);

			if (tmo > TCP_TIMEWAIT_LEN) {
				inet_csk_reset_keepalive_timer(sk, tcp_fin_time(sk));
			} else {
				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
				goto out;
			}
		}
	}
	if (sk->sk_state != TCP_CLOSE) {
		sk_stream_mem_reclaim(sk);
		if (atomic_read(sk->sk_prot->orphan_count) > sysctl_tcp_max_orphans ||
		    (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
		     atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
			if (net_ratelimit())
				printk(KERN_INFO "TCP: too many of orphaned "
				       "sockets\n");
			tcp_set_state(sk, TCP_CLOSE);
			tcp_send_active_reset(sk, GFP_ATOMIC);
			NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
		}
	}

	if (sk->sk_state == TCP_CLOSE)
		inet_csk_destroy_sock(sk);
	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}

/* These states need RST on ABORT according to RFC793 */

static inline int tcp_need_reset(int state)
{
	return (1 << state) &
	       (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 |
		TCPF_FIN_WAIT2 | TCPF_SYN_RECV);
}

int tcp_disconnect(struct sock *sk, int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int err = 0;
	int old_state = sk->sk_state;

	if (old_state != TCP_CLOSE)
		tcp_set_state(sk, TCP_CLOSE);

	/* ABORT function of RFC793 */
	if (old_state == TCP_LISTEN) {
		inet_csk_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 discrepancy of Linux wrt. RFC
		 * states
		 */
		tcp_send_active_reset(sk, gfp_any());
		sk->sk_err = ECONNRESET;
	} else if (old_state == TCP_SYN_SENT)
		sk->sk_err = ECONNRESET;

	tcp_clear_xmit_timers(sk);
	__skb_queue_purge(&sk->sk_receive_queue);
	sk_stream_writequeue_purge(sk);
	__skb_queue_purge(&tp->out_of_order_queue);
#ifdef CONFIG_NET_DMA
	__skb_queue_purge(&sk->sk_async_wait_queue);
#endif

	inet->dport = 0;

	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	sk->sk_shutdown = 0;
	sock_reset_flag(sk, SOCK_DONE);
	tp->srtt = 0;
	if ((tp->write_seq += tp->max_window + 2) == 0)
		tp->write_seq = 1;
	icsk->icsk_backoff = 0;
	tp->snd_cwnd = 2;
	icsk->icsk_probes_out = 0;
	tp->packets_out = 0;
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_cnt = 0;
	tp->bytes_acked = 0;
	tcp_set_ca_state(sk, TCP_CA_Open);
	tcp_clear_retrans(tp);
	inet_csk_delack_init(sk);
	sk->sk_send_head = NULL;
	tp->rx_opt.saw_tstamp = 0;
	tcp_sack_reset(&tp->rx_opt);
	__sk_dst_reset(sk);

	BUG_TRAP(!inet->num || icsk->icsk_bind_hash);

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

/*
 *	Socket option code for TCP.
 */
static int do_tcp_setsockopt(struct sock *sk, int level,
		int optname, char __user *optval, int optlen)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	int val;
	int err = 0;

	/* This is a string value all the others are int's */
	if (optname == TCP_CONGESTION) {
		char name[TCP_CA_NAME_MAX];

		if (optlen < 1)
			return -EINVAL;

		val = strncpy_from_user(name, optval,
					min(TCP_CA_NAME_MAX-1, optlen));
		if (val < 0)
			return -EFAULT;
		name[val] = 0;

		lock_sock(sk);
		err = tcp_set_congestion_control(sk, name);
		release_sock(sk);
		return err;
	}

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

	if (get_user(val, (int __user *)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->rx_opt.user_mss = val;
		break;

	case TCP_NODELAY:
		if (val) {
			/* TCP_NODELAY is weaker than TCP_CORK, so that
			 * this option on corked socket is remembered, but
			 * it is not activated until cork is cleared.
			 *
			 * However, when TCP_NODELAY is set we make
			 * an explicit push, which overrides even TCP_CORK
			 * for currently queued segments.
			 */
			tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
			tcp_push_pending_frames(sk, tp);
		} else {
			tp->nonagle &= ~TCP_NAGLE_OFF;
		}
		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.
		 *
		 * TCP_CORK can be set together with TCP_NODELAY and it is
		 * stronger than TCP_NODELAY.
		 */
		if (val) {
			tp->nonagle |= TCP_NAGLE_CORK;
		} else {
			tp->nonagle &= ~TCP_NAGLE_CORK;
			if (tp->nonagle&TCP_NAGLE_OFF)
				tp->nonagle |= TCP_NAGLE_PUSH;
			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 (sock_flag(sk, SOCK_KEEPOPEN) &&
			    !((1 << sk->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;
				inet_csk_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
			icsk->icsk_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:
		icsk->icsk_accept_queue.rskq_defer_accept = 0;
		if (val > 0) {
			/* Translate value in seconds to number of
			 * retransmits */
			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
			       val > ((TCP_TIMEOUT_INIT / HZ) <<
				       icsk->icsk_accept_queue.rskq_defer_accept))
				icsk->icsk_accept_queue.rskq_defer_accept++;
			icsk->icsk_accept_queue.rskq_defer_accept++;
		}
		break;

	case TCP_WINDOW_CLAMP:
		if (!val) {
			if (sk->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) {
			icsk->icsk_ack.pingpong = 1;
		} else {
			icsk->icsk_ack.pingpong = 0;
			if ((1 << sk->sk_state) &
			    (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
			    inet_csk_ack_scheduled(sk)) {
				icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
				tcp_cleanup_rbuf(sk, 1);
				if (!(val & 1))
					icsk->icsk_ack.pingpong = 1;
			}
		}
		break;

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

int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
		   int optlen)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (level != SOL_TCP)
		return icsk->icsk_af_ops->setsockopt(sk, level, optname,
						     optval, optlen);
	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	if (level != SOL_TCP)
		return inet_csk_compat_setsockopt(sk, level, optname,
						  optval, optlen);
	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif

/* Return information about state of tcp endpoint in API format. */
void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	u32 now = tcp_time_stamp;

	memset(info, 0, sizeof(*info));

	info->tcpi_state = sk->sk_state;
	info->tcpi_ca_state = icsk->icsk_ca_state;
	info->tcpi_retransmits = icsk->icsk_retransmits;
	info->tcpi_probes = icsk->icsk_probes_out;
	info->tcpi_backoff = icsk->icsk_backoff;

	if (tp->rx_opt.tstamp_ok)
		info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
	if (tp->rx_opt.sack_ok)
		info->tcpi_options |= TCPI_OPT_SACK;
	if (tp->rx_opt.wscale_ok) {
		info->tcpi_options |= TCPI_OPT_WSCALE;
		info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
	} 

	if (tp->ecn_flags&TCP_ECN_OK)
		info->tcpi_options |= TCPI_OPT_ECN;