tcp_output.c

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Version:	$Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *		Linus Torvalds, <torvalds@cs.helsinki.fi>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Matthew Dillon, <dillon@apollo.west.oic.com>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Jorge Cwik, <jorge@laser.satlink.net>
 */

/*
 * Changes:	Pedro Roque	:	Retransmit queue handled by TCP.
 *				:	Fragmentation on mtu decrease
 *				:	Segment collapse on retransmit
 *				:	AF independence
 *
 *		Linus Torvalds	:	send_delayed_ack
 *		David S. Miller	:	Charge memory using the right skb
 *					during syn/ack processing.
 *		David S. Miller :	Output engine completely rewritten.
 *		Andrea Arcangeli:	SYNACK carry ts_recent in tsecr.
 *		Cacophonix Gaul :	draft-minshall-nagle-01
 *		J Hadi Salim	:	ECN support
 *
 */

#include <net/tcp.h>

#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/smp_lock.h>

/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_retrans_collapse = 1;

/* This limits the percentage of the congestion window which we
 * will allow a single TSO frame to consume.  Building TSO frames
 * which are too large can cause TCP streams to be bursty.
 */
int sysctl_tcp_tso_win_divisor = 3;

static void update_send_head(struct sock *sk, struct tcp_sock *tp,
			     struct sk_buff *skb)
{
	sk->sk_send_head = skb->next;
	if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
		sk->sk_send_head = NULL;
	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
	tcp_packets_out_inc(sk, tp, skb);
}

/* SND.NXT, if window was not shrunk.
 * If window has been shrunk, what should we make? It is not clear at all.
 * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-(
 * Anything in between SND.UNA...SND.UNA+SND.WND also can be already
 * invalid. OK, let's make this for now:
 */
static inline __u32 tcp_acceptable_seq(struct sock *sk, struct tcp_sock *tp)
{
	if (!before(tp->snd_una+tp->snd_wnd, tp->snd_nxt))
		return tp->snd_nxt;
	else
		return tp->snd_una+tp->snd_wnd;
}

/* Calculate mss to advertise in SYN segment.
 * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that:
 *
 * 1. It is independent of path mtu.
 * 2. Ideally, it is maximal possible segment size i.e. 65535-40.
 * 3. For IPv4 it is reasonable to calculate it from maximal MTU of
 *    attached devices, because some buggy hosts are confused by
 *    large MSS.
 * 4. We do not make 3, we advertise MSS, calculated from first
 *    hop device mtu, but allow to raise it to ip_rt_min_advmss.
 *    This may be overridden via information stored in routing table.
 * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible,
 *    probably even Jumbo".
 */
static __u16 tcp_advertise_mss(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);
	int mss = tp->advmss;

	if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
		mss = dst_metric(dst, RTAX_ADVMSS);
		tp->advmss = mss;
	}

	return (__u16)mss;
}

/* RFC2861. Reset CWND after idle period longer RTO to "restart window".
 * This is the first part of cwnd validation mechanism. */
static void tcp_cwnd_restart(struct sock *sk, struct dst_entry *dst)
{
	struct tcp_sock *tp = tcp_sk(sk);
	s32 delta = tcp_time_stamp - tp->lsndtime;
	u32 restart_cwnd = tcp_init_cwnd(tp, dst);
	u32 cwnd = tp->snd_cwnd;

	tcp_ca_event(sk, CA_EVENT_CWND_RESTART);

	tp->snd_ssthresh = tcp_current_ssthresh(sk);
	restart_cwnd = min(restart_cwnd, cwnd);

	while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd)
		cwnd >>= 1;
	tp->snd_cwnd = max(cwnd, restart_cwnd);
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tp->snd_cwnd_used = 0;
}

static void tcp_event_data_sent(struct tcp_sock *tp,
				struct sk_buff *skb, struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	const u32 now = tcp_time_stamp;

	if (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)
		tcp_cwnd_restart(sk, __sk_dst_get(sk));

	tp->lsndtime = now;

	/* If it is a reply for ato after last received
	 * packet, enter pingpong mode.
	 */
	if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
		icsk->icsk_ack.pingpong = 1;
}

static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
	tcp_dec_quickack_mode(sk, pkts);
	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}

/* Determine a window scaling and initial window to offer.
 * Based on the assumption that the given amount of space
 * will be offered. Store the results in the tp structure.
 * NOTE: for smooth operation initial space offering should
 * be a multiple of mss if possible. We assume here that mss >= 1.
 * This MUST be enforced by all callers.
 */
void tcp_select_initial_window(int __space, __u32 mss,
			       __u32 *rcv_wnd, __u32 *window_clamp,
			       int wscale_ok, __u8 *rcv_wscale)
{
	unsigned int space = (__space < 0 ? 0 : __space);

	/* If no clamp set the clamp to the max possible scaled window */
	if (*window_clamp == 0)
		(*window_clamp) = (65535 << 14);
	space = min(*window_clamp, space);

	/* Quantize space offering to a multiple of mss if possible. */
	if (space > mss)
		space = (space / mss) * mss;

	/* NOTE: offering an initial window larger than 32767
	 * will break some buggy TCP stacks. We try to be nice.
	 * If we are not window scaling, then this truncates
	 * our initial window offering to 32k. There should also
	 * be a sysctl option to stop being nice.
	 */
	(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
	(*rcv_wscale) = 0;
	if (wscale_ok) {
		/* Set window scaling on max possible window
		 * See RFC1323 for an explanation of the limit to 14 
		 */
		space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
		while (space > 65535 && (*rcv_wscale) < 14) {
			space >>= 1;
			(*rcv_wscale)++;
		}
	}

	/* Set initial window to value enough for senders,
	 * following RFC2414. Senders, not following this RFC,
	 * will be satisfied with 2.
	 */
	if (mss > (1<<*rcv_wscale)) {
		int init_cwnd = 4;
		if (mss > 1460*3)
			init_cwnd = 2;
		else if (mss > 1460)
			init_cwnd = 3;
		if (*rcv_wnd > init_cwnd*mss)
			*rcv_wnd = init_cwnd*mss;
	}

	/* Set the clamp no higher than max representable value */
	(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
}

/* Chose a new window to advertise, update state in tcp_sock for the
 * socket, and return result with RFC1323 scaling applied.  The return
 * value can be stuffed directly into th->window for an outgoing
 * frame.
 */
static u16 tcp_select_window(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 cur_win = tcp_receive_window(tp);
	u32 new_win = __tcp_select_window(sk);

	/* Never shrink the offered window */
	if(new_win < cur_win) {
		/* Danger Will Robinson!
		 * Don't update rcv_wup/rcv_wnd here or else
		 * we will not be able to advertise a zero
		 * window in time.  --DaveM
		 *
		 * Relax Will Robinson.
		 */
		new_win = cur_win;
	}
	tp->rcv_wnd = new_win;
	tp->rcv_wup = tp->rcv_nxt;

	/* Make sure we do not exceed the maximum possible
	 * scaled window.
	 */
	if (!tp->rx_opt.rcv_wscale)
		new_win = min(new_win, MAX_TCP_WINDOW);
	else
		new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));

	/* RFC1323 scaling applied */
	new_win >>= tp->rx_opt.rcv_wscale;

	/* If we advertise zero window, disable fast path. */
	if (new_win == 0)
		tp->pred_flags = 0;

	return new_win;
}

static void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp,
					 __u32 tstamp)
{
	if (tp->rx_opt.tstamp_ok) {
		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
					  (TCPOPT_NOP << 16) |
					  (TCPOPT_TIMESTAMP << 8) |
					  TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tstamp);
		*ptr++ = htonl(tp->rx_opt.ts_recent);
	}
	if (tp->rx_opt.eff_sacks) {
		struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
		int this_sack;

		*ptr++ = htonl((TCPOPT_NOP  << 24) |
			       (TCPOPT_NOP  << 16) |
			       (TCPOPT_SACK <<  8) |
			       (TCPOLEN_SACK_BASE + (tp->rx_opt.eff_sacks *
						     TCPOLEN_SACK_PERBLOCK)));
		for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
			*ptr++ = htonl(sp[this_sack].start_seq);
			*ptr++ = htonl(sp[this_sack].end_seq);
		}
		if (tp->rx_opt.dsack) {
			tp->rx_opt.dsack = 0;
			tp->rx_opt.eff_sacks--;
		}
	}
}

/* Construct a tcp options header for a SYN or SYN_ACK packet.
 * If this is every changed make sure to change the definition of
 * MAX_SYN_SIZE to match the new maximum number of options that you
 * can generate.
 */
static void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack,
				  int offer_wscale, int wscale, __u32 tstamp,
				  __u32 ts_recent)
{
	/* We always get an MSS option.
	 * The option bytes which will be seen in normal data
	 * packets should timestamps be used, must be in the MSS
	 * advertised.  But we subtract them from tp->mss_cache so
	 * that calculations in tcp_sendmsg are simpler etc.
	 * So account for this fact here if necessary.  If we
	 * don't do this correctly, as a receiver we won't
	 * recognize data packets as being full sized when we
	 * should, and thus we won't abide by the delayed ACK
	 * rules correctly.
	 * SACKs don't matter, we never delay an ACK when we
	 * have any of those going out.
	 */
	*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
	if (ts) {
		if(sack)
			*ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
						  (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
		else
			*ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
						  (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tstamp);		/* TSVAL */
		*ptr++ = htonl(ts_recent);	/* TSECR */
	} else if(sack)
		*ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
					  (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
	if (offer_wscale)
		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
}

/* This routine actually transmits TCP packets queued in by
 * tcp_do_sendmsg().  This is used by both the initial
 * transmission and possible later retransmissions.
 * All SKB's seen here are completely headerless.  It is our
 * job to build the TCP header, and pass the packet down to
 * IP so it can do the same plus pass the packet off to the
 * device.
 *
 * We are working here with either a clone of the original
 * SKB, or a fresh unique copy made by the retransmit engine.
 */
static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet;
	struct tcp_sock *tp;
	struct tcp_skb_cb *tcb;
	int tcp_header_size;
	struct tcphdr *th;
	int sysctl_flags;
	int err;

	BUG_ON(!skb || !tcp_skb_pcount(skb));

	/* If congestion control is doing timestamping, we must
	 * take such a timestamp before we potentially clone/copy.
	 */
	if (icsk->icsk_ca_ops->rtt_sample)
		__net_timestamp(skb);

	if (likely(clone_it)) {
		if (unlikely(skb_cloned(skb)))
			skb = pskb_copy(skb, gfp_mask);
		else
			skb = skb_clone(skb, gfp_mask);
		if (unlikely(!skb))
			return -ENOBUFS;
	}

	inet = inet_sk(sk);
	tp = tcp_sk(sk);
	tcb = TCP_SKB_CB(skb);
	tcp_header_size = tp->tcp_header_len;

#define SYSCTL_FLAG_TSTAMPS	0x1
#define SYSCTL_FLAG_WSCALE	0x2
#define SYSCTL_FLAG_SACK	0x4

	sysctl_flags = 0;
	if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
		tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
		if(sysctl_tcp_timestamps) {
			tcp_header_size += TCPOLEN_TSTAMP_ALIGNED;
			sysctl_flags |= SYSCTL_FLAG_TSTAMPS;
		}
		if (sysctl_tcp_window_scaling) {
			tcp_header_size += TCPOLEN_WSCALE_ALIGNED;
			sysctl_flags |= SYSCTL_FLAG_WSCALE;
		}
		if (sysctl_tcp_sack) {
			sysctl_flags |= SYSCTL_FLAG_SACK;
			if (!(sysctl_flags & SYSCTL_FLAG_TSTAMPS))
				tcp_header_size += TCPOLEN_SACKPERM_ALIGNED;
		}
	} else if (unlikely(tp->rx_opt.eff_sacks)) {
		/* A SACK is 2 pad bytes, a 2 byte header, plus
		 * 2 32-bit sequence numbers for each SACK block.
		 */
		tcp_header_size += (TCPOLEN_SACK_BASE_ALIGNED +
				    (tp->rx_opt.eff_sacks *
				     TCPOLEN_SACK_PERBLOCK));
	}
		
	if (tcp_packets_in_flight(tp) == 0)
		tcp_ca_event(sk, CA_EVENT_TX_START);

	th = (struct tcphdr *) skb_push(skb, tcp_header_size);
	skb->h.th = th;
	skb_set_owner_w(skb, sk);

	/* Build TCP header and checksum it. */
	th->source		= inet->sport;
	th->dest		= inet->dport;
	th->seq			= htonl(tcb->seq);
	th->ack_seq		= htonl(tp->rcv_nxt);
	*(((__u16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
					tcb->flags);

	if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
		/* RFC1323: The window in SYN & SYN/ACK segments
		 * is never scaled.
		 */
		th->window	= htons(tp->rcv_wnd);
	} else {
		th->window	= htons(tcp_select_window(sk));
	}
	th->check		= 0;
	th->urg_ptr		= 0;

	if (unlikely(tp->urg_mode &&
		     between(tp->snd_up, tcb->seq+1, tcb->seq+0xFFFF))) {
		th->urg_ptr		= htons(tp->snd_up-tcb->seq);
		th->urg			= 1;
	}

	if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
		tcp_syn_build_options((__u32 *)(th + 1),
				      tcp_advertise_mss(sk),
				      (sysctl_flags & SYSCTL_FLAG_TSTAMPS),
				      (sysctl_flags & SYSCTL_FLAG_SACK),
				      (sysctl_flags & SYSCTL_FLAG_WSCALE),
				      tp->rx_opt.rcv_wscale,
				      tcb->when,
				      tp->rx_opt.ts_recent);
	} else {
		tcp_build_and_update_options((__u32 *)(th + 1),
					     tp, tcb->when);
		TCP_ECN_send(sk, tp, skb, tcp_header_size);
	}

	icsk->icsk_af_ops->send_check(sk, skb->len, skb);

	if (likely(tcb->flags & TCPCB_FLAG_ACK))
		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));

	if (skb->len != tcp_header_size)
		tcp_event_data_sent(tp, skb, sk);

	TCP_INC_STATS(TCP_MIB_OUTSEGS);

	err = icsk->icsk_af_ops->queue_xmit(skb, 0);
	if (unlikely(err <= 0))
		return err;

	tcp_enter_cwr(sk);

	/* NET_XMIT_CN is special. It does not guarantee,
	 * that this packet is lost. It tells that device
	 * is about to start to drop packets or already
	 * drops some packets of the same priority and
	 * invokes us to send less aggressively.
	 */
	return err == NET_XMIT_CN ? 0 : err;

#undef SYSCTL_FLAG_TSTAMPS
#undef SYSCTL_FLAG_WSCALE
#undef SYSCTL_FLAG_SACK
}


/* This routine just queue's the buffer 
 *
 * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
 * otherwise socket can stall.
 */
static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Advance write_seq and place onto the write_queue. */
	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
	skb_header_release(skb);
	__skb_queue_tail(&sk->sk_write_queue, skb);
	sk_charge_skb(sk, skb);

	/* Queue it, remembering where we must start sending. */
	if (sk->sk_send_head == NULL)
		sk->sk_send_head = skb;
}

static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
	if (skb->len <= mss_now ||
	    !(sk->sk_route_caps & NETIF_F_TSO)) {
		/* Avoid the costly divide in the normal
		 * non-TSO case.
		 */
		skb_shinfo(skb)->tso_segs = 1;
		skb_shinfo(skb)->tso_size = 0;
	} else {
		unsigned int factor;

		factor = skb->len + (mss_now - 1);
		factor /= mss_now;
		skb_shinfo(skb)->tso_segs = factor;
		skb_shinfo(skb)->tso_size = mss_now;
	}
}

/* Function to create two new TCP segments.  Shrinks the given segment
 * to the specified size and appends a new segment with the rest of the
 * packet to the list.  This won't be called frequently, I hope. 
 * Remember, these are still headerless SKBs at this point.
 */
int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *buff;
	int nsize, old_factor;
	u16 flags;

	BUG_ON(len > skb->len);

 	clear_all_retrans_hints(tp);
	nsize = skb_headlen(skb) - len;
	if (nsize < 0)
		nsize = 0;

	if (skb_cloned(skb) &&
	    skb_is_nonlinear(skb) &&
	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
		return -ENOMEM;

	/* Get a new skb... force flag on. */
	buff = sk_stream_alloc_skb(sk, nsize, GFP_ATOMIC);
	if (buff == NULL)
		return -ENOMEM; /* We'll just try again later. */
	sk_charge_skb(sk, buff);

	/* Correct the sequence numbers. */
	TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;

	/* PSH and FIN should only be set in the second packet. */
	flags = TCP_SKB_CB(skb)->flags;
	TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
	TCP_SKB_CB(buff)->flags = flags;
	TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
	TCP_SKB_CB(skb)->sacked &= ~TCPCB_AT_TAIL;

	if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_HW) {
		/* Copy and checksum data tail into the new buffer. */
		buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize),
						       nsize, 0);

		skb_trim(skb, len);

		skb->csum = csum_block_sub(skb->csum, buff->csum, len);
	} else {
		skb->ip_summed = CHECKSUM_HW;
		skb_split(skb, buff, len);
	}

	buff->ip_summed = skb->ip_summed;

	/* Looks stupid, but our code really uses when of
	 * skbs, which it never sent before. --ANK
	 */
	TCP_SKB_CB(buff)->when = TCP_SKB_CB(skb)->when;
	buff->tstamp = skb->tstamp;

	old_factor = tcp_skb_pcount(skb);

	/* Fix up tso_factor for both original and new SKB.  */
	tcp_set_skb_tso_segs(sk, skb, mss_now);
	tcp_set_skb_tso_segs(sk, buff, mss_now);

	/* If this packet has been sent out already, we must
	 * adjust the various packet counters.
	 */
	if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
		int diff = old_factor - tcp_skb_pcount(skb) -
			tcp_skb_pcount(buff);

		tp->packets_out -= diff;

		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
			tp->sacked_out -= diff;
		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
			tp->retrans_out -= diff;

		if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
			tp->lost_out -= diff;
			tp->left_out -= diff;
		}

		if (diff > 0) {
			/* Adjust Reno SACK estimate. */
			if (!tp->rx_opt.sack_ok) {
				tp->sacked_out -= diff;
				if ((int)tp->sacked_out < 0)
					tp->sacked_out = 0;
				tcp_sync_left_out(tp);
			}

			tp->fackets_out -= diff;
			if ((int)tp->fackets_out < 0)
				tp->fackets_out = 0;
		}
	}

	/* Link BUFF into the send queue. */
	skb_header_release(buff);
	__skb_append(skb, buff, &sk->sk_write_queue);

	return 0;
}

/* This is similar to __pskb_pull_head() (it will go to core/skbuff.c
 * eventually). The difference is that pulled data not copied, but
 * immediately discarded.
 */
static unsigned char *__pskb_trim_head(struct sk_buff *skb, int len)
{
	int i, k, eat;

	eat = len;
	k = 0;
	for (i=0; i<skb_shinfo(skb)->nr_frags; i++) {
		if (skb_shinfo(skb)->frags[i].size <= eat) {
			put_page(skb_shinfo(skb)->frags[i].page);
			eat -= skb_shinfo(skb)->frags[i].size;
		} else {
			skb_shinfo(skb)->frags[k] = skb_shinfo(skb)->frags[i];
			if (eat) {
				skb_shinfo(skb)->frags[k].page_offset += eat;
				skb_shinfo(skb)->frags[k].size -= eat;
				eat = 0;
			}
			k++;
		}
	}
	skb_shinfo(skb)->nr_frags = k;

	skb->tail = skb->data;
	skb->data_len -= len;
	skb->len = skb->data_len;
	return skb->tail;
}

int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
	if (skb_cloned(skb) &&
	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
		return -ENOMEM;

	if (len <= skb_headlen(skb)) {
		__skb_pull(skb, len);
	} else {
		if (__pskb_trim_head(skb, len-skb_headlen(skb)) == NULL)
			return -ENOMEM;
	}

	TCP_SKB_CB(skb)->seq += len;
	skb->ip_summed = CHECKSUM_HW;

	skb->truesize	     -= len;
	sk->sk_wmem_queued   -= len;
	sk->sk_forward_alloc += len;
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);

	/* Any change of skb->len requires recalculation of tso
	 * factor and mss.
	 */
	if (tcp_skb_pcount(skb) > 1)
		tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));

	return 0;
}

/* This function synchronize snd mss to current pmtu/exthdr set.

   tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
   for TCP options, but includes only bare TCP header.

   tp->rx_opt.mss_clamp is mss negotiated at connection setup.
   It is minimum of user_mss and mss received with SYN.
   It also does not include TCP options.

   inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function.

   tp->mss_cache is current effective sending mss, including
   all tcp options except for SACKs. It is evaluated,
   taking into account current pmtu, but never exceeds
   tp->rx_opt.mss_clamp.

   NOTE1. rfc1122 clearly states that advertised MSS
   DOES NOT include either tcp or ip options.

   NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache
   are READ ONLY outside this function.		--ANK (980731)
 */

unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	/* Calculate base mss without TCP options:
	   It is MMS_S - sizeof(tcphdr) of rfc1122
	 */
	int mss_now = (pmtu - icsk->icsk_af_ops->net_header_len -
		       sizeof(struct tcphdr));

	/* Clamp it (mss_clamp does not include tcp options) */
	if (mss_now > tp->rx_opt.mss_clamp)
		mss_now = tp->rx_opt.mss_clamp;

	/* Now subtract optional transport overhead */
	mss_now -= icsk->icsk_ext_hdr_len;

	/* Then reserve room for full set of TCP options and 8 bytes of data */
	if (mss_now < 48)
		mss_now = 48;

	/* Now subtract TCP options size, not including SACKs */
	mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);

	/* Bound mss with half of window */
	if (tp->max_window && mss_now > (tp->max_window>>1))
		mss_now = max((tp->max_window>>1), 68U - tp->tcp_header_len);

	/* And store cached results */
	icsk->icsk_pmtu_cookie = pmtu;
	tp->mss_cache = mss_now;

	return mss_now;
}

/* Compute the current effective MSS, taking SACKs and IP options,
 * and even PMTU discovery events into account.
 *
 * LARGESEND note: !urg_mode is overkill, only frames up to snd_up
 * cannot be large. However, taking into account rare use of URG, this
 * is not a big flaw.
 */
unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);
	u32 mss_now;
	u16 xmit_size_goal;
	int doing_tso = 0;

	mss_now = tp->mss_cache;

	if (large_allowed &&
	    (sk->sk_route_caps & NETIF_F_TSO) &&
	    !tp->urg_mode)
		doing_tso = 1;

	if (dst) {
		u32 mtu = dst_mtu(dst);
		if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
			mss_now = tcp_sync_mss(sk, mtu);
	}

	if (tp->rx_opt.eff_sacks)
		mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
			    (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));

	xmit_size_goal = mss_now;

	if (doing_tso) {
		xmit_size_goal = (65535 -
				  inet_csk(sk)->icsk_af_ops->net_header_len -
				  inet_csk(sk)->icsk_ext_hdr_len -
				  tp->tcp_header_len);

		if (tp->max_window &&
		    (xmit_size_goal > (tp->max_window >> 1)))
			xmit_size_goal = max((tp->max_window >> 1),
					     68U - tp->tcp_header_len);

		xmit_size_goal -= (xmit_size_goal % mss_now);
	}
	tp->xmit_size_goal = xmit_size_goal;

	return mss_now;
}

/* Congestion window validation. (RFC2861) */

static void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
{
	__u32 packets_out = tp->packets_out;

	if (packets_out >= tp->snd_cwnd) {
		/* Network is feed fully. */
		tp->snd_cwnd_used = 0;
		tp->snd_cwnd_stamp = tcp_time_stamp;
	} else {
		/* Network starves. */
		if (tp->packets_out > tp->snd_cwnd_used)
			tp->snd_cwnd_used = tp->packets_out;

		if ((s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
			tcp_cwnd_application_limited(sk);
	}
}

static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd)
{
	u32 window, cwnd_len;

	window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq);
	cwnd_len = mss_now * cwnd;
	return min(window, cwnd_len);
}

/* Can at least one segment of SKB be sent right now, according to the
 * congestion window rules?  If so, return how many segments are allowed.
 */
static inline unsigned int tcp_cwnd_test(struct tcp_sock *tp, struct sk_buff *skb)
{
	u32 in_flight, cwnd;

	/* Don't be strict about the congestion window for the final FIN.  */
	if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
		return 1;

	in_flight = tcp_packets_in_flight(tp);
	cwnd = tp->snd_cwnd;
	if (in_flight < cwnd)
		return (cwnd - in_flight);

	return 0;
}

/* This must be invoked the first time we consider transmitting
 * SKB onto the wire.
 */
static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
{
	int tso_segs = tcp_skb_pcount(skb);

	if (!tso_segs ||
	    (tso_segs > 1 &&
	     skb_shinfo(skb)->tso_size != mss_now)) {
		tcp_set_skb_tso_segs(sk, skb, mss_now);
		tso_segs = tcp_skb_pcount(skb);
	}
	return tso_segs;
}

static inline int tcp_minshall_check(const struct tcp_sock *tp)
{
	return after(tp->snd_sml,tp->snd_una) &&
		!after(tp->snd_sml, tp->snd_nxt);
}

/* Return 0, if packet can be sent now without violation Nagle's rules:
 * 1. It is full sized.
 * 2. Or it contains FIN. (already checked by caller)
 * 3. Or TCP_NODELAY was set.
 * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
 *    With Minshall's modification: all sent small packets are ACKed.
 */

static inline int tcp_nagle_check(const struct tcp_sock *tp,
				  const struct sk_buff *skb, 
				  unsigned mss_now, int nonagle)
{
	return (skb->len < mss_now &&
		((nonagle&TCP_NAGLE_CORK) ||
		 (!nonagle &&
		  tp->packets_out &&
		  tcp_minshall_check(tp))));
}

/* Return non-zero if the Nagle test allows this packet to be
 * sent now.
 */
static inline int tcp_nagle_test(struct tcp_sock *tp, struct sk_buff *skb,
				 unsigned int cur_mss, int nonagle)
{
	/* Nagle rule does not apply to frames, which sit in the middle of the
	 * write_queue (they have no chances to get new data).
	 *
	 * This is implemented in the callers, where they modify the 'nonagle'
	 * argument based upon the location of SKB in the send queue.
	 */
	if (nonagle & TCP_NAGLE_PUSH)
		return 1;

	/* Don't use the nagle rule for urgent data (or for the final FIN).  */
	if (tp->urg_mode ||
	    (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
		return 1;

	if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
		return 1;

	return 0;
}

/* Does at least the first segment of SKB fit into the send window? */
static inline int tcp_snd_wnd_test(struct tcp_sock *tp, struct sk_buff *skb, unsigned int cur_mss)
{
	u32 end_seq = TCP_SKB_CB(skb)->end_seq;

	if (skb->len > cur_mss)
		end_seq = TCP_SKB_CB(skb)->seq + cur_mss;

	return !after(end_seq, tp->snd_una + tp->snd_wnd);
}

/* This checks if the data bearing packet SKB (usually sk->sk_send_head)
 * should be put on the wire right now.  If so, it returns the number of
 * packets allowed by the congestion window.
 */
static unsigned int tcp_snd_test(struct sock *sk, struct sk_buff *skb,
				 unsigned int cur_mss, int nonagle)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int cwnd_quota;

	tcp_init_tso_segs(sk, skb, cur_mss);

	if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
		return 0;

	cwnd_quota = tcp_cwnd_test(tp, skb);
	if (cwnd_quota &&
	    !tcp_snd_wnd_test(tp, skb, cur_mss))
		cwnd_quota = 0;

	return cwnd_quota;
}

static inline int tcp_skb_is_last(const struct sock *sk, 
				  const struct sk_buff *skb)
{
	return skb->next == (struct sk_buff *)&sk->sk_write_queue;
}

int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
{
	struct sk_buff *skb = sk->sk_send_head;

	return (skb &&
		tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
			     (tcp_skb_is_last(sk, skb) ?
			      TCP_NAGLE_PUSH :
			      tp->nonagle)));
}

/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
 * which is put after SKB on the list.  It is very much like
 * tcp_fragment() except that it may make several kinds of assumptions
 * in order to speed up the splitting operation.  In particular, we
 * know that all the data is in scatter-gather pages, and that the
 * packet has never been sent out before (and thus is not cloned).
 */
static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now)
{
	struct sk_buff *buff;
	int nlen = skb->len - len;
	u16 flags;

	/* All of a TSO frame must be composed of paged data.  */
	if (skb->len != skb->data_len)
		return tcp_fragment(sk, skb, len, mss_now);

	buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC);
	if (unlikely(buff == NULL))
		return -ENOMEM;

	buff->truesize = nlen;
	skb->truesize -= nlen;

	/* Correct the sequence numbers. */
	TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len;
	TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq;
	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq;

	/* PSH and FIN should only be set in the second packet. */
	flags = TCP_SKB_CB(skb)->flags;
	TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
	TCP_SKB_CB(buff)->flags = flags;

	/* This packet was never sent out yet, so no SACK bits. */
	TCP_SKB_CB(buff)->sacked = 0;

	buff->ip_summed = skb->ip_summed = CHECKSUM_HW;
	skb_split(skb, buff, len);

	/* Fix up tso_factor for both original and new SKB.  */