tcp.c

	err = sk_stream_error(sk, flags, err);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return err;
}

/*
 *	Handle reading urgent data. BSD has very simple semantics for
 *	this, no blocking and very strange errors 8)
 */

static int tcp_recv_urg(struct sock *sk, long timeo,
			struct msghdr *msg, int len, int flags,
			int *addr_len)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* No URG data to read. */
	if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
	    tp->urg_data == TCP_URG_READ)
		return -EINVAL;	/* Yes this is right ! */

	if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
		return -ENOTCONN;

	if (tp->urg_data & TCP_URG_VALID) {
		int err = 0;
		char c = tp->urg_data;

		if (!(flags & MSG_PEEK))
			tp->urg_data = TCP_URG_READ;

		/* Read urgent data. */
		msg->msg_flags |= MSG_OOB;

		if (len > 0) {
			if (!(flags & MSG_TRUNC))
				err = memcpy_toiovec(msg->msg_iov, &c, 1);
			len = 1;
		} else
			msg->msg_flags |= MSG_TRUNC;

		return err ? -EFAULT : len;
	}

	if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
		return 0;

	/* Fixed the recv(..., MSG_OOB) behaviour.  BSD docs and
	 * the available implementations agree in this case:
	 * this call should never block, independent of the
	 * blocking state of the socket.
	 * Mike <pall@rz.uni-karlsruhe.de>
	 */
	return -EAGAIN;
}

/* Clean up the receive buffer for full frames taken by the user,
 * then send an ACK if necessary.  COPIED is the number of bytes
 * tcp_recvmsg has given to the user so far, it speeds up the
 * calculation of whether or not we must ACK for the sake of
 * a window update.
 */
static void cleanup_rbuf(struct sock *sk, int copied)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int time_to_ack = 0;

#if TCP_DEBUG
	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);

	BUG_TRAP(!skb || before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq));
#endif

	if (tcp_ack_scheduled(tp)) {
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
		if (tp->ack.blocked ||
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
		    tp->rcv_nxt - tp->rcv_wup > tp->ack.rcv_mss ||
		    /*
		     * If this read emptied read buffer, we send ACK, if
		     * connection is not bidirectional, user drained
		     * receive buffer and there was a small segment
		     * in queue.
		     */
		    (copied > 0 && (tp->ack.pending & TCP_ACK_PUSHED) &&
		     !tp->ack.pingpong && !atomic_read(&sk->sk_rmem_alloc)))
			time_to_ack = 1;
	}

	/* We send an ACK if we can now advertise a non-zero window
	 * which has been raised "significantly".
	 *
	 * Even if window raised up to infinity, do not send window open ACK
	 * in states, where we will not receive more. It is useless.
	 */
	if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
		__u32 rcv_window_now = tcp_receive_window(tp);

		/* Optimize, __tcp_select_window() is not cheap. */
		if (2*rcv_window_now <= tp->window_clamp) {
			__u32 new_window = __tcp_select_window(sk);

			/* Send ACK now, if this read freed lots of space
			 * in our buffer. Certainly, new_window is new window.
			 * We can advertise it now, if it is not less than current one.
			 * "Lots" means "at least twice" here.
			 */
			if (new_window && new_window >= 2 * rcv_window_now)
				time_to_ack = 1;
		}
	}
	if (time_to_ack)
		tcp_send_ack(sk);
}

static void tcp_prequeue_process(struct sock *sk)
{
	struct sk_buff *skb;
	struct tcp_sock *tp = tcp_sk(sk);

	NET_ADD_STATS_USER(LINUX_MIB_TCPPREQUEUED, skb_queue_len(&tp->ucopy.prequeue));

	/* RX process wants to run with disabled BHs, though it is not
	 * necessary */
	local_bh_disable();
	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
		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);
			++seq;
			break;
		}
		sk_eat_skb(sk, skb);
		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)
		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;

	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);

	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;
			}
		}

		cleanup_rbuf(sk, copied);

		if (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_len(&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);

		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_len(&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)) {
			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);
		continue;

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

	if (user_recv) {
		if (skb_queue_len(&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;
	}

	/* 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. */
	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 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);
	}
}

/*
 * At this point, there should be no process reference to this
 * socket, and thus no user references at all.  Therefore we
 * can assume the socket waitqueue is inactive and nobody will
 * try to jump onto it.
 */
void tcp_destroy_sock(struct sock *sk)
{
	BUG_TRAP(sk->sk_state == TCP_CLOSE);
	BUG_TRAP(sock_flag(sk, SOCK_DEAD));

	/* It cannot be in hash table! */
	BUG_TRAP(sk_unhashed(sk));

	/* If it has not 0 inet_sk(sk)->num, it must be bound */
	BUG_TRAP(!inet_sk(sk)->num || tcp_sk(sk)->bind_hash);

	sk->sk_prot->destroy(sk);

	sk_stream_kill_queues(sk);

	xfrm_sk_free_policy(sk);

#ifdef INET_REFCNT_DEBUG
	if (atomic_read(&sk->sk_refcnt) != 1) {
		printk(KERN_DEBUG "Destruction TCP %p delayed, c=%d\n",
		       sk, atomic_read(&sk->sk_refcnt));
	}
#endif

	atomic_dec(&tcp_orphan_count);
	sock_put(sk);
}

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

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

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

		/* Special case. */
		tcp_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:
	/* 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));

	sock_hold(sk);
	sock_orphan(sk);

	/*	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 {
			int tmo = tcp_fin_time(tp);

			if (tmo > TCP_TIMEWAIT_LEN) {
				tcp_reset_keepalive_timer(sk, tcp_fin_time(tp));
			} else {
				atomic_inc(&tcp_orphan_count);
				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
				goto out;
			}
		}
	}
	if (sk->sk_state != TCP_CLOSE) {
		sk_stream_mem_reclaim(sk);
		if (atomic_read(&tcp_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);
		}
	}
	atomic_inc(&tcp_orphan_count);

	if (sk->sk_state == TCP_CLOSE)
		tcp_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 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) {
		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->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);

	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;
	tp->backoff = 0;
	tp->snd_cwnd = 2;
	tp->probes_out = 0;
	tp->packets_out = 0;
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_cnt = 0;
	tcp_set_ca_state(tp, TCP_CA_Open);
	tcp_clear_retrans(tp);
	tcp_delack_init(tp);
	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 || tp->bind_hash);

	sk->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)
{
	struct tcp_sock *tp = tcp_sk(sk);
	DEFINE_WAIT(wait);
	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.
	 */
	for (;;) {
		prepare_to_wait_exclusive(sk->sk_sleep, &wait,
					  TASK_INTERRUPTIBLE);
		release_sock(sk);
		if (!tp->accept_queue)
			timeo = schedule_timeout(timeo);
		lock_sock(sk);
		err = 0;
		if (tp->accept_queue)
			break;
		err = -EINVAL;
		if (sk->sk_state != TCP_LISTEN)
			break;
		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			break;
		err = -EAGAIN;
		if (!timeo)
			break;
	}
	finish_wait(sk->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_sock *tp = tcp_sk(sk);
	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->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;
	sk_acceptq_removed(sk);
	tcp_openreq_fastfree(req);
	BUG_TRAP(newsk->sk_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 __user *optval,
		   int optlen)
{
	struct tcp_sock *tp = tcp_sk(sk);
	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 __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.