tcp_input.c

	u32 ack = TCP_SKB_CB(skb)->ack_seq;

	return (/* 1. Pure ACK with correct sequence number. */
		(th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) &&

		/* 2. ... and duplicate ACK. */
		ack == tp->snd_una &&

		/* 3. ... and does not update window. */
		!tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) &&

		/* 4. ... and sits in replay window. */
		(s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= (inet_csk(sk)->icsk_rto * 1024) / HZ);
}

static inline int tcp_paws_discard(const struct sock *sk, const struct sk_buff *skb)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	return ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > TCP_PAWS_WINDOW &&
		get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
		!tcp_disordered_ack(sk, skb));
}

/* Check segment sequence number for validity.
 *
 * Segment controls are considered valid, if the segment
 * fits to the window after truncation to the window. Acceptability
 * of data (and SYN, FIN, of course) is checked separately.
 * See tcp_data_queue(), for example.
 *
 * Also, controls (RST is main one) are accepted using RCV.WUP instead
 * of RCV.NXT. Peer still did not advance his SND.UNA when we
 * delayed ACK, so that hisSND.UNA<=ourRCV.WUP.
 * (borrowed from freebsd)
 */

static inline int tcp_sequence(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	return	!before(end_seq, tp->rcv_wup) &&
		!after(seq, tp->rcv_nxt + tcp_receive_window(tp));
}

/* When we get a reset we do this. */
static void tcp_reset(struct sock *sk)
{
	/* We want the right error as BSD sees it (and indeed as we do). */
	switch (sk->sk_state) {
		case TCP_SYN_SENT:
			sk->sk_err = ECONNREFUSED;
			break;
		case TCP_CLOSE_WAIT:
			sk->sk_err = EPIPE;
			break;
		case TCP_CLOSE:
			return;
		default:
			sk->sk_err = ECONNRESET;
	}

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_error_report(sk);

	tcp_done(sk);
}

/*
 * 	Process the FIN bit. This now behaves as it is supposed to work
 *	and the FIN takes effect when it is validly part of sequence
 *	space. Not before when we get holes.
 *
 *	If we are ESTABLISHED, a received fin moves us to CLOSE-WAIT
 *	(and thence onto LAST-ACK and finally, CLOSE, we never enter
 *	TIME-WAIT)
 *
 *	If we are in FINWAIT-1, a received FIN indicates simultaneous
 *	close and we go into CLOSING (and later onto TIME-WAIT)
 *
 *	If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
 */
static void tcp_fin(struct sk_buff *skb, struct sock *sk, struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);

	inet_csk_schedule_ack(sk);

	sk->sk_shutdown |= RCV_SHUTDOWN;
	sock_set_flag(sk, SOCK_DONE);

	switch (sk->sk_state) {
		case TCP_SYN_RECV:
		case TCP_ESTABLISHED:
			/* Move to CLOSE_WAIT */
			tcp_set_state(sk, TCP_CLOSE_WAIT);
			inet_csk(sk)->icsk_ack.pingpong = 1;
			break;

		case TCP_CLOSE_WAIT:
		case TCP_CLOSING:
			/* Received a retransmission of the FIN, do
			 * nothing.
			 */
			break;
		case TCP_LAST_ACK:
			/* RFC793: Remain in the LAST-ACK state. */
			break;

		case TCP_FIN_WAIT1:
			/* This case occurs when a simultaneous close
			 * happens, we must ack the received FIN and
			 * enter the CLOSING state.
			 */
			tcp_send_ack(sk);
			tcp_set_state(sk, TCP_CLOSING);
			break;
		case TCP_FIN_WAIT2:
			/* Received a FIN -- send ACK and enter TIME_WAIT. */
			tcp_send_ack(sk);
			tcp_time_wait(sk, TCP_TIME_WAIT, 0);
			break;
		default:
			/* Only TCP_LISTEN and TCP_CLOSE are left, in these
			 * cases we should never reach this piece of code.
			 */
			printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
			       __FUNCTION__, sk->sk_state);
			break;
	};

	/* It _is_ possible, that we have something out-of-order _after_ FIN.
	 * Probably, we should reset in this case. For now drop them.
	 */
	__skb_queue_purge(&tp->out_of_order_queue);
	if (tp->rx_opt.sack_ok)
		tcp_sack_reset(&tp->rx_opt);
	sk_stream_mem_reclaim(sk);

	if (!sock_flag(sk, SOCK_DEAD)) {
		sk->sk_state_change(sk);

		/* Do not send POLL_HUP for half duplex close. */
		if (sk->sk_shutdown == SHUTDOWN_MASK ||
		    sk->sk_state == TCP_CLOSE)
			sk_wake_async(sk, 1, POLL_HUP);
		else
			sk_wake_async(sk, 1, POLL_IN);
	}
}

static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, u32 end_seq)
{
	if (!after(seq, sp->end_seq) && !after(sp->start_seq, end_seq)) {
		if (before(seq, sp->start_seq))
			sp->start_seq = seq;
		if (after(end_seq, sp->end_seq))
			sp->end_seq = end_seq;
		return 1;
	}
	return 0;
}

static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
		if (before(seq, tp->rcv_nxt))
			NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT);
		else
			NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFOSENT);

		tp->rx_opt.dsack = 1;
		tp->duplicate_sack[0].start_seq = seq;
		tp->duplicate_sack[0].end_seq = end_seq;
		tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + 1, 4 - tp->rx_opt.tstamp_ok);
	}
}

static void tcp_dsack_extend(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
	if (!tp->rx_opt.dsack)
		tcp_dsack_set(tp, seq, end_seq);
	else
		tcp_sack_extend(tp->duplicate_sack, seq, end_seq);
}

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

	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
	    before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOST);
		tcp_enter_quickack_mode(sk);

		if (tp->rx_opt.sack_ok && sysctl_tcp_dsack) {
			u32 end_seq = TCP_SKB_CB(skb)->end_seq;

			if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
				end_seq = tp->rcv_nxt;
			tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, end_seq);
		}
	}

	tcp_send_ack(sk);
}

/* These routines update the SACK block as out-of-order packets arrive or
 * in-order packets close up the sequence space.
 */
static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
{
	int this_sack;
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	struct tcp_sack_block *swalk = sp+1;

	/* See if the recent change to the first SACK eats into
	 * or hits the sequence space of other SACK blocks, if so coalesce.
	 */
	for (this_sack = 1; this_sack < tp->rx_opt.num_sacks; ) {
		if (tcp_sack_extend(sp, swalk->start_seq, swalk->end_seq)) {
			int i;

			/* Zap SWALK, by moving every further SACK up by one slot.
			 * Decrease num_sacks.
			 */
			tp->rx_opt.num_sacks--;
			tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
			for(i=this_sack; i < tp->rx_opt.num_sacks; i++)
				sp[i] = sp[i+1];
			continue;
		}
		this_sack++, swalk++;
	}
}

static inline void tcp_sack_swap(struct tcp_sack_block *sack1, struct tcp_sack_block *sack2)
{
	__u32 tmp;

	tmp = sack1->start_seq;
	sack1->start_seq = sack2->start_seq;
	sack2->start_seq = tmp;

	tmp = sack1->end_seq;
	sack1->end_seq = sack2->end_seq;
	sack2->end_seq = tmp;
}

static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int cur_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	if (!cur_sacks)
		goto new_sack;

	for (this_sack=0; this_sack<cur_sacks; this_sack++, sp++) {
		if (tcp_sack_extend(sp, seq, end_seq)) {
			/* Rotate this_sack to the first one. */
			for (; this_sack>0; this_sack--, sp--)
				tcp_sack_swap(sp, sp-1);
			if (cur_sacks > 1)
				tcp_sack_maybe_coalesce(tp);
			return;
		}
	}

	/* Could not find an adjacent existing SACK, build a new one,
	 * put it at the front, and shift everyone else down.  We
	 * always know there is at least one SACK present already here.
	 *
	 * If the sack array is full, forget about the last one.
	 */
	if (this_sack >= 4) {
		this_sack--;
		tp->rx_opt.num_sacks--;
		sp--;
	}
	for(; this_sack > 0; this_sack--, sp--)
		*sp = *(sp-1);

new_sack:
	/* Build the new head SACK, and we're done. */
	sp->start_seq = seq;
	sp->end_seq = end_seq;
	tp->rx_opt.num_sacks++;
	tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
}

/* RCV.NXT advances, some SACKs should be eaten. */

static void tcp_sack_remove(struct tcp_sock *tp)
{
	struct tcp_sack_block *sp = &tp->selective_acks[0];
	int num_sacks = tp->rx_opt.num_sacks;
	int this_sack;

	/* Empty ofo queue, hence, all the SACKs are eaten. Clear. */
	if (skb_queue_empty(&tp->out_of_order_queue)) {
		tp->rx_opt.num_sacks = 0;
		tp->rx_opt.eff_sacks = tp->rx_opt.dsack;
		return;
	}

	for(this_sack = 0; this_sack < num_sacks; ) {
		/* Check if the start of the sack is covered by RCV.NXT. */
		if (!before(tp->rcv_nxt, sp->start_seq)) {
			int i;

			/* RCV.NXT must cover all the block! */
			BUG_TRAP(!before(tp->rcv_nxt, sp->end_seq));

			/* Zap this SACK, by moving forward any other SACKS. */
			for (i=this_sack+1; i < num_sacks; i++)
				tp->selective_acks[i-1] = tp->selective_acks[i];
			num_sacks--;
			continue;
		}
		this_sack++;
		sp++;
	}
	if (num_sacks != tp->rx_opt.num_sacks) {
		tp->rx_opt.num_sacks = num_sacks;
		tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
	}
}

/* This one checks to see if we can put data from the
 * out_of_order queue into the receive_queue.
 */
static void tcp_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	__u32 dsack_high = tp->rcv_nxt;
	struct sk_buff *skb;

	while ((skb = skb_peek(&tp->out_of_order_queue)) != NULL) {
		if (after(TCP_SKB_CB(skb)->seq, tp->rcv_nxt))
			break;

		if (before(TCP_SKB_CB(skb)->seq, dsack_high)) {
			__u32 dsack = dsack_high;
			if (before(TCP_SKB_CB(skb)->end_seq, dsack_high))
				dsack_high = TCP_SKB_CB(skb)->end_seq;
			tcp_dsack_extend(tp, TCP_SKB_CB(skb)->seq, dsack);
		}

		if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
			SOCK_DEBUG(sk, "ofo packet was already received \n");
			__skb_unlink(skb, &tp->out_of_order_queue);
			__kfree_skb(skb);
			continue;
		}
		SOCK_DEBUG(sk, "ofo requeuing : rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		__skb_unlink(skb, &tp->out_of_order_queue);
		__skb_queue_tail(&sk->sk_receive_queue, skb);
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		if(skb->h.th->fin)
			tcp_fin(skb, sk, skb->h.th);
	}
}

static int tcp_prune_queue(struct sock *sk);

static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th;
	struct tcp_sock *tp = tcp_sk(sk);
	int eaten = -1;

	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
		goto drop;

	__skb_pull(skb, th->doff*4);

	TCP_ECN_accept_cwr(tp, skb);

	if (tp->rx_opt.dsack) {
		tp->rx_opt.dsack = 0;
		tp->rx_opt.eff_sacks = min_t(unsigned int, tp->rx_opt.num_sacks,
						    4 - tp->rx_opt.tstamp_ok);
	}

	/*  Queue data for delivery to the user.
	 *  Packets in sequence go to the receive queue.
	 *  Out of sequence packets to the out_of_order_queue.
	 */
	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
		if (tcp_receive_window(tp) == 0)
			goto out_of_window;

		/* Ok. In sequence. In window. */
		if (tp->ucopy.task == current &&
		    tp->copied_seq == tp->rcv_nxt && tp->ucopy.len &&
		    sock_owned_by_user(sk) && !tp->urg_data) {
			int chunk = min_t(unsigned int, skb->len,
							tp->ucopy.len);

			__set_current_state(TASK_RUNNING);

			local_bh_enable();
			if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) {
				tp->ucopy.len -= chunk;
				tp->copied_seq += chunk;
				eaten = (chunk == skb->len && !th->fin);
				tcp_rcv_space_adjust(sk);
			}
			local_bh_disable();
		}

		if (eaten <= 0) {
queue_and_out:
			if (eaten < 0 &&
			    (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
			     !sk_stream_rmem_schedule(sk, skb))) {
				if (tcp_prune_queue(sk) < 0 ||
				    !sk_stream_rmem_schedule(sk, skb))
					goto drop;
			}
			sk_stream_set_owner_r(skb, sk);
			__skb_queue_tail(&sk->sk_receive_queue, skb);
		}
		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
		if(skb->len)
			tcp_event_data_recv(sk, tp, skb);
		if(th->fin)
			tcp_fin(skb, sk, th);

		if (!skb_queue_empty(&tp->out_of_order_queue)) {
			tcp_ofo_queue(sk);

			/* RFC2581. 4.2. SHOULD send immediate ACK, when
			 * gap in queue is filled.
			 */
			if (skb_queue_empty(&tp->out_of_order_queue))
				inet_csk(sk)->icsk_ack.pingpong = 0;
		}

		if (tp->rx_opt.num_sacks)
			tcp_sack_remove(tp);

		tcp_fast_path_check(sk, tp);

		if (eaten > 0)
			__kfree_skb(skb);
		else if (!sock_flag(sk, SOCK_DEAD))
			sk->sk_data_ready(sk, 0);
		return;
	}

	if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
		/* A retransmit, 2nd most common case.  Force an immediate ack. */
		NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOST);
		tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);

out_of_window:
		tcp_enter_quickack_mode(sk);
		inet_csk_schedule_ack(sk);
drop:
		__kfree_skb(skb);
		return;
	}

	/* Out of window. F.e. zero window probe. */
	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
		goto out_of_window;

	tcp_enter_quickack_mode(sk);

	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
		/* Partial packet, seq < rcv_next < end_seq */
		SOCK_DEBUG(sk, "partial packet: rcv_next %X seq %X - %X\n",
			   tp->rcv_nxt, TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(skb)->end_seq);

		tcp_dsack_set(tp, TCP_SKB_CB(skb)->seq, tp->rcv_nxt);

		/* If window is closed, drop tail of packet. But after
		 * remembering D-SACK for its head made in previous line.
		 */
		if (!tcp_receive_window(tp))
			goto out_of_window;
		goto queue_and_out;
	}

	TCP_ECN_check_ce(tp, skb);

	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
	    !sk_stream_rmem_schedule(sk, skb)) {
		if (tcp_prune_queue(sk) < 0 ||
		    !sk_stream_rmem_schedule(sk, skb))
			goto drop;
	}

	/* Disable header prediction. */
	tp->pred_flags = 0;
	inet_csk_schedule_ack(sk);

	SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
		   tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);

	sk_stream_set_owner_r(skb, sk);

	if (!skb_peek(&tp->out_of_order_queue)) {
		/* Initial out of order segment, build 1 SACK. */
		if (tp->rx_opt.sack_ok) {
			tp->rx_opt.num_sacks = 1;
			tp->rx_opt.dsack     = 0;
			tp->rx_opt.eff_sacks = 1;
			tp->selective_acks[0].start_seq = TCP_SKB_CB(skb)->seq;
			tp->selective_acks[0].end_seq =
						TCP_SKB_CB(skb)->end_seq;
		}
		__skb_queue_head(&tp->out_of_order_queue,skb);
	} else {
		struct sk_buff *skb1 = tp->out_of_order_queue.prev;
		u32 seq = TCP_SKB_CB(skb)->seq;
		u32 end_seq = TCP_SKB_CB(skb)->end_seq;

		if (seq == TCP_SKB_CB(skb1)->end_seq) {
			__skb_append(skb1, skb, &tp->out_of_order_queue);

			if (!tp->rx_opt.num_sacks ||
			    tp->selective_acks[0].end_seq != seq)
				goto add_sack;

			/* Common case: data arrive in order after hole. */
			tp->selective_acks[0].end_seq = end_seq;
			return;
		}

		/* Find place to insert this segment. */
		do {
			if (!after(TCP_SKB_CB(skb1)->seq, seq))
				break;
		} while ((skb1 = skb1->prev) !=
			 (struct sk_buff*)&tp->out_of_order_queue);

		/* Do skb overlap to previous one? */
		if (skb1 != (struct sk_buff*)&tp->out_of_order_queue &&
		    before(seq, TCP_SKB_CB(skb1)->end_seq)) {
			if (!after(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
				/* All the bits are present. Drop. */
				__kfree_skb(skb);
				tcp_dsack_set(tp, seq, end_seq);
				goto add_sack;
			}
			if (after(seq, TCP_SKB_CB(skb1)->seq)) {
				/* Partial overlap. */
				tcp_dsack_set(tp, seq, TCP_SKB_CB(skb1)->end_seq);
			} else {
				skb1 = skb1->prev;
			}
		}
		__skb_insert(skb, skb1, skb1->next, &tp->out_of_order_queue);

		/* And clean segments covered by new one as whole. */
		while ((skb1 = skb->next) !=
		       (struct sk_buff*)&tp->out_of_order_queue &&
		       after(end_seq, TCP_SKB_CB(skb1)->seq)) {
		       if (before(end_seq, TCP_SKB_CB(skb1)->end_seq)) {
			       tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, end_seq);
			       break;
		       }
		       __skb_unlink(skb1, &tp->out_of_order_queue);
		       tcp_dsack_extend(tp, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq);
		       __kfree_skb(skb1);
		}

add_sack:
		if (tp->rx_opt.sack_ok)
			tcp_sack_new_ofo_skb(sk, seq, end_seq);
	}
}

/* Collapse contiguous sequence of skbs head..tail with
 * sequence numbers start..end.
 * Segments with FIN/SYN are not collapsed (only because this
 * simplifies code)
 */
static void
tcp_collapse(struct sock *sk, struct sk_buff_head *list,
	     struct sk_buff *head, struct sk_buff *tail,
	     u32 start, u32 end)
{
	struct sk_buff *skb;

	/* First, check that queue is collapsible and find
	 * the point where collapsing can be useful. */
	for (skb = head; skb != tail; ) {
		/* No new bits? It is possible on ofo queue. */
		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
			struct sk_buff *next = skb->next;
			__skb_unlink(skb, list);
			__kfree_skb(skb);
			NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
			skb = next;
			continue;
		}

		/* The first skb to collapse is:
		 * - not SYN/FIN and
		 * - bloated or contains data before "start" or
		 *   overlaps to the next one.
		 */
		if (!skb->h.th->syn && !skb->h.th->fin &&
		    (tcp_win_from_space(skb->truesize) > skb->len ||
		     before(TCP_SKB_CB(skb)->seq, start) ||
		     (skb->next != tail &&
		      TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb->next)->seq)))
			break;

		/* Decided to skip this, advance start seq. */
		start = TCP_SKB_CB(skb)->end_seq;
		skb = skb->next;
	}
	if (skb == tail || skb->h.th->syn || skb->h.th->fin)
		return;

	while (before(start, end)) {
		struct sk_buff *nskb;
		int header = skb_headroom(skb);
		int copy = SKB_MAX_ORDER(header, 0);

		/* Too big header? This can happen with IPv6. */
		if (copy < 0)
			return;
		if (end-start < copy)
			copy = end-start;
		nskb = alloc_skb(copy+header, GFP_ATOMIC);
		if (!nskb)
			return;
		skb_reserve(nskb, header);
		memcpy(nskb->head, skb->head, header);
		nskb->nh.raw = nskb->head + (skb->nh.raw-skb->head);
		nskb->h.raw = nskb->head + (skb->h.raw-skb->head);
		nskb->mac.raw = nskb->head + (skb->mac.raw-skb->head);
		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
		__skb_insert(nskb, skb->prev, skb, list);
		sk_stream_set_owner_r(nskb, sk);

		/* Copy data, releasing collapsed skbs. */
		while (copy > 0) {
			int offset = start - TCP_SKB_CB(skb)->seq;
			int size = TCP_SKB_CB(skb)->end_seq - start;

			BUG_ON(offset < 0);
			if (size > 0) {
				size = min(copy, size);
				if (skb_copy_bits(skb, offset, skb_put(nskb, size), size))
					BUG();
				TCP_SKB_CB(nskb)->end_seq += size;
				copy -= size;
				start += size;
			}
			if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
				struct sk_buff *next = skb->next;
				__skb_unlink(skb, list);
				__kfree_skb(skb);
				NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
				skb = next;
				if (skb == tail || skb->h.th->syn || skb->h.th->fin)
					return;
			}
		}
	}
}

/* Collapse ofo queue. Algorithm: select contiguous sequence of skbs
 * and tcp_collapse() them until all the queue is collapsed.
 */
static void tcp_collapse_ofo_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = skb_peek(&tp->out_of_order_queue);
	struct sk_buff *head;
	u32 start, end;

	if (skb == NULL)
		return;

	start = TCP_SKB_CB(skb)->seq;
	end = TCP_SKB_CB(skb)->end_seq;
	head = skb;

	for (;;) {
		skb = skb->next;

		/* Segment is terminated when we see gap or when
		 * we are at the end of all the queue. */
		if (skb == (struct sk_buff *)&tp->out_of_order_queue ||
		    after(TCP_SKB_CB(skb)->seq, end) ||
		    before(TCP_SKB_CB(skb)->end_seq, start)) {
			tcp_collapse(sk, &tp->out_of_order_queue,
				     head, skb, start, end);
			head = skb;
			if (skb == (struct sk_buff *)&tp->out_of_order_queue)
				break;
			/* Start new segment */
			start = TCP_SKB_CB(skb)->seq;
			end = TCP_SKB_CB(skb)->end_seq;
		} else {
			if (before(TCP_SKB_CB(skb)->seq, start))
				start = TCP_SKB_CB(skb)->seq;
			if (after(TCP_SKB_CB(skb)->end_seq, end))
				end = TCP_SKB_CB(skb)->end_seq;
		}
	}
}

/* Reduce allocated memory if we can, trying to get
 * the socket within its memory limits again.
 *
 * Return less than zero if we should start dropping frames
 * until the socket owning process reads some of the data
 * to stabilize the situation.
 */
static int tcp_prune_queue(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	SOCK_DEBUG(sk, "prune_queue: c=%x\n", tp->copied_seq);

	NET_INC_STATS_BH(LINUX_MIB_PRUNECALLED);

	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
		tcp_clamp_window(sk, tp);
	else if (tcp_memory_pressure)
		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);

	tcp_collapse_ofo_queue(sk);
	tcp_collapse(sk, &sk->sk_receive_queue,
		     sk->sk_receive_queue.next,
		     (struct sk_buff*)&sk->sk_receive_queue,
		     tp->copied_seq, tp->rcv_nxt);
	sk_stream_mem_reclaim(sk);

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;

	/* Collapsing did not help, destructive actions follow.
	 * This must not ever occur. */

	/* First, purge the out_of_order queue. */
	if (!skb_queue_empty(&tp->out_of_order_queue)) {
		NET_INC_STATS_BH(LINUX_MIB_OFOPRUNED);
		__skb_queue_purge(&tp->out_of_order_queue);

		/* Reset SACK state.  A conforming SACK implementation will
		 * do the same at a timeout based retransmit.  When a connection
		 * is in a sad state like this, we care only about integrity
		 * of the connection not performance.
		 */
		if (tp->rx_opt.sack_ok)
			tcp_sack_reset(&tp->rx_opt);
		sk_stream_mem_reclaim(sk);
	}

	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
		return 0;

	/* If we are really being abused, tell the caller to silently
	 * drop receive data on the floor.  It will get retransmitted
	 * and hopefully then we'll have sufficient space.
	 */
	NET_INC_STATS_BH(LINUX_MIB_RCVPRUNED);

	/* Massive buffer overcommit. */
	tp->pred_flags = 0;
	return -1;
}


/* RFC2861, slow part. Adjust cwnd, after it was not full during one rto.
 * As additional protections, we do not touch cwnd in retransmission phases,
 * and if application hit its sndbuf limit recently.
 */
void tcp_cwnd_application_limited(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
	    sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
		/* Limited by application or receiver window. */
		u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk));
		u32 win_used = max(tp->snd_cwnd_used, init_win);
		if (win_used < tp->snd_cwnd) {
			tp->snd_ssthresh = tcp_current_ssthresh(sk);
			tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1;
		}
		tp->snd_cwnd_used = 0;
	}
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

static int tcp_should_expand_sndbuf(struct sock *sk, struct tcp_sock *tp)
{
	/* If the user specified a specific send buffer setting, do
	 * not modify it.
	 */
	if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
		return 0;

	/* If we are under global TCP memory pressure, do not expand.  */
	if (tcp_memory_pressure)
		return 0;

	/* If we are under soft global TCP memory pressure, do not expand.  */
	if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
		return 0;

	/* If we filled the congestion window, do not expand.  */
	if (tp->packets_out >= tp->snd_cwnd)
		return 0;

	return 1;
}

/* When incoming ACK allowed to free some skb from write_queue,
 * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
 * on the exit from tcp input handler.
 *
 * PROBLEM: sndbuf expansion does not work well with largesend.
 */
static void tcp_new_space(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_should_expand_sndbuf(sk, tp)) {
		int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
			MAX_TCP_HEADER + 16 + sizeof(struct sk_buff),
		    demanded = max_t(unsigned int, tp->snd_cwnd,
						   tp->reordering + 1);
		sndmem *= 2*demanded;
		if (sndmem > sk->sk_sndbuf)
			sk->sk_sndbuf = min(sndmem, sysctl_tcp_wmem[2]);
		tp->snd_cwnd_stamp = tcp_time_stamp;
	}

	sk->sk_write_space(sk);
}

static void tcp_check_space(struct sock *sk)
{
	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
		if (sk->sk_socket &&
		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
			tcp_new_space(sk);
	}
}

static inline void tcp_data_snd_check(struct sock *sk, struct tcp_sock *tp)
{
	tcp_push_pending_frames(sk, tp);
	tcp_check_space(sk);
}

/*
 * Check if sending an ack is needed.
 */
static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
{
	struct tcp_sock *tp = tcp_sk(sk);

	    /* More than one full frame received... */
	if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss
	     /* ... and right edge of window advances far enough.
	      * (tcp_recvmsg() will send ACK otherwise). Or...
	      */
	     && __tcp_select_window(sk) >= tp->rcv_wnd) ||
	    /* We ACK each frame or... */
	    tcp_in_quickack_mode(sk) ||
	    /* We have out of order data. */
	    (ofo_possible &&
	     skb_peek(&tp->out_of_order_queue))) {
		/* Then ack it now */
		tcp_send_ack(sk);
	} else {
		/* Else, send delayed ack. */
		tcp_send_delayed_ack(sk);
	}
}

static inline void tcp_ack_snd_check(struct sock *sk)
{
	if (!inet_csk_ack_scheduled(sk)) {
		/* We sent a data segment already. */
		return;
	}
	__tcp_ack_snd_check(sk, 1);
}

/*
 *	This routine is only called when we have urgent data
 *	signaled. Its the 'slow' part of tcp_urg. It could be
 *	moved inline now as tcp_urg is only called from one
 *	place. We handle URGent data wrong. We have to - as
 *	BSD still doesn't use the correction from RFC961.
 *	For 1003.1g we should support a new option TCP_STDURG to permit
 *	either form (or just set the sysctl tcp_stdurg).
 */

static void tcp_check_urg(struct sock * sk, struct tcphdr * th)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 ptr = ntohs(th->urg_ptr);

	if (ptr && !sysctl_tcp_stdurg)
		ptr--;
	ptr += ntohl(th->seq);

	/* Ignore urgent data that we've already seen and read. */
	if (after(tp->copied_seq, ptr))
		return;

	/* Do not replay urg ptr.
	 *
	 * NOTE: interesting situation not covered by specs.
	 * Misbehaving sender may send urg ptr, pointing to segment,
	 * which we already have in ofo queue. We are not able to fetch
	 * such data and will stay in TCP_URG_NOTYET until will be eaten
	 * by recvmsg(). Seems, we are not obliged to handle such wicked
	 * situations. But it is worth to think about possibility of some
	 * DoSes using some hypothetical application level deadlock.
	 */
	if (before(ptr, tp->rcv_nxt))
		return;

	/* Do we already have a newer (or duplicate) urgent pointer? */
	if (tp->urg_data && !after(ptr, tp->urg_seq))
		return;

	/* Tell the world about our new urgent pointer. */
	sk_send_sigurg(sk);

	/* We may be adding urgent data when the last byte read was
	 * urgent. To do this requires some care. We cannot just ignore
	 * tp->copied_seq since we would read the last urgent byte again
	 * as data, nor can we alter copied_seq until this data arrives
	 * or we break the semantics of SIOCATMARK (and thus sockatmark())
	 *
	 * NOTE. Double Dutch. Rendering to plain English: author of comment
	 * above did something sort of 	send("A", MSG_OOB); send("B", MSG_OOB);
	 * and expect that both A and B disappear from stream. This is _wrong_.
	 * Though this happens in BSD with high probability, this is occasional.
	 * Any application relying on this is buggy. Note also, that fix "works"
	 * only in this artificial test. Insert some normal data between A and B and we will
	 * decline of BSD again. Verdict: it is better to remove to trap
	 * buggy users.
	 */
	if (tp->urg_seq == tp->copied_seq && tp->urg_data &&
	    !sock_flag(sk, SOCK_URGINLINE) &&
	    tp->copied_seq != tp->rcv_nxt) {
		struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
		tp->copied_seq++;
		if (skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq)) {
			__skb_unlink(skb, &sk->sk_receive_queue);
			__kfree_skb(skb);
		}
	}

	tp->urg_data   = TCP_URG_NOTYET;
	tp->urg_seq    = ptr;

	/* Disable header prediction. */
	tp->pred_flags = 0;
}

/* This is the 'fast' part of urgent handling. */
static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Check if we get a new urgent pointer - normally not. */
	if (th->urg)
		tcp_check_urg(sk,th);

	/* Do we wait for any urgent data? - normally not... */
	if (tp->urg_data == TCP_URG_NOTYET) {
		u32 ptr = tp->urg_seq - ntohl(th->seq) + (th->doff * 4) -
			  th->syn;

		/* Is the urgent pointer pointing into this packet? */
		if (ptr < skb->len) {
			u8 tmp;
			if (skb_copy_bits(skb, ptr, &tmp, 1))
				BUG();
			tp->urg_data = TCP_URG_VALID | tmp;
			if (!sock_flag(sk, SOCK_DEAD))
				sk->sk_data_ready(sk, 0);
		}
	}
}

static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen)