[linux.git] / net / ipv4 / tcp_input.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).
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[email protected]>
 *		Mark Evans, <[email protected]>
 *		Corey Minyard <[email protected]>
 *		Florian La Roche, <[email protected]>
 *		Charles Hedrick, <[email protected]>
 *		Linus Torvalds, <[email protected]>
 *		Alan Cox, <[email protected]>
 *		Matthew Dillon, <[email protected]>
 *		Arnt Gulbrandsen, <[email protected]>
 *		Jorge Cwik, <[email protected]>
 */

/*
 * Changes:
 *		Pedro Roque	:	Fast Retransmit/Recovery.
 *					Two receive queues.
 *					Retransmit queue handled by TCP.
 *					Better retransmit timer handling.
 *					New congestion avoidance.
 *					Header prediction.
 *					Variable renaming.
 *
 *		Eric		:	Fast Retransmit.
 *		Randy Scott	:	MSS option defines.
 *		Eric Schenk	:	Fixes to slow start algorithm.
 *		Eric Schenk	:	Yet another double ACK bug.
 *		Eric Schenk	:	Delayed ACK bug fixes.
 *		Eric Schenk	:	Floyd style fast retrans war avoidance.
 *		David S. Miller	:	Don't allow zero congestion window.
 *		Eric Schenk	:	Fix retransmitter so that it sends
 *					next packet on ack of previous packet.
 *		Andi Kleen	:	Moved open_request checking here
 *					and process RSTs for open_requests.
 *		Andi Kleen	:	Better prune_queue, and other fixes.
 *		Andrey Savochkin:	Fix RTT measurements in the presence of
 *					timestamps.
 *		Andrey Savochkin:	Check sequence numbers correctly when
 *					removing SACKs due to in sequence incoming
 *					data segments.
 *		Andi Kleen:		Make sure we never ack data there is not
 *					enough room for. Also make this condition
 *					a fatal error if it might still happen.
 *		Andi Kleen:		Add tcp_measure_rcv_mss to make
 *					connections with MSS<min(MTU,ann. MSS)
 *					work without delayed acks.
 *		Andi Kleen:		Process packets with PSH set in the
 *					fast path.
 *		J Hadi Salim:		ECN support
 *	 	Andrei Gurtov,
 *		Pasi Sarolahti,
 *		Panu Kuhlberg:		Experimental audit of TCP (re)transmission
 *					engine. Lots of bugs are found.
 *		Pasi Sarolahti:		F-RTO for dealing with spurious RTOs
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/kernel.h>
#include <net/dst.h>
#include <net/tcp.h>
#include <net/inet_common.h>
#include <linux/ipsec.h>
#include <asm/unaligned.h>
#include <net/netdma.h>

int sysctl_tcp_timestamps __read_mostly = 1;
int sysctl_tcp_window_scaling __read_mostly = 1;
int sysctl_tcp_sack __read_mostly = 1;
int sysctl_tcp_fack __read_mostly = 1;
int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
int sysctl_tcp_ecn __read_mostly = 2;
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 2;

int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
int sysctl_tcp_frto __read_mostly = 2;
int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_nometrics_save __read_mostly;

int sysctl_tcp_thin_dupack __read_mostly;

int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_abc __read_mostly;

#define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
#define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
#define FLAG_DATA_ACKED		0x04 /* This ACK acknowledged new data.		*/
#define FLAG_RETRANS_DATA_ACKED	0x08 /* "" "" some of which was retransmitted.	*/
#define FLAG_SYN_ACKED		0x10 /* This ACK acknowledged SYN.		*/
#define FLAG_DATA_SACKED	0x20 /* New SACK.				*/
#define FLAG_ECE		0x40 /* ECE in this ACK				*/
#define FLAG_DATA_LOST		0x80 /* SACK detected data lossage.		*/
#define FLAG_SLOWPATH		0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED	0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_SND_UNA_ADVANCED	0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
#define FLAG_DSACKING_ACK	0x800 /* SACK blocks contained D-SACK info */
#define FLAG_NONHEAD_RETRANS_ACKED	0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_SACK_RENEGING	0x2000 /* snd_una advanced to a sacked seq */

#define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
#define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
#define FLAG_CA_ALERT		(FLAG_DATA_SACKED|FLAG_ECE)
#define FLAG_FORWARD_PROGRESS	(FLAG_ACKED|FLAG_DATA_SACKED)
#define FLAG_ANY_PROGRESS	(FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)

#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))

/* Adapt the MSS value used to make delayed ack decision to the
 * real world.
 */
static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	const unsigned int lss = icsk->icsk_ack.last_seg_size;
	unsigned int len;

	icsk->icsk_ack.last_seg_size = 0;

	/* skb->len may jitter because of SACKs, even if peer
	 * sends good full-sized frames.
	 */
	len = skb_shinfo(skb)->gso_size ? : skb->len;
	if (len >= icsk->icsk_ack.rcv_mss) {
		icsk->icsk_ack.rcv_mss = len;
	} else {
		/* Otherwise, we make more careful check taking into account,
		 * that SACKs block is variable.
		 *
		 * "len" is invariant segment length, including TCP header.
		 */
		len += skb->data - skb_transport_header(skb);
		if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) ||
		    /* If PSH is not set, packet should be
		     * full sized, provided peer TCP is not badly broken.
		     * This observation (if it is correct 8)) allows
		     * to handle super-low mtu links fairly.
		     */
		    (len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
		     !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
			/* Subtract also invariant (if peer is RFC compliant),
			 * tcp header plus fixed timestamp option length.
			 * Resulting "len" is MSS free of SACK jitter.
			 */
			len -= tcp_sk(sk)->tcp_header_len;
			icsk->icsk_ack.last_seg_size = len;
			if (len == lss) {
				icsk->icsk_ack.rcv_mss = len;
				return;
			}
		}
		if (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)
			icsk->icsk_ack.pending |= ICSK_ACK_PUSHED2;
		icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
	}
}

static void tcp_incr_quickack(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	unsigned quickacks = tcp_sk(sk)->rcv_wnd / (2 * icsk->icsk_ack.rcv_mss);

	if (quickacks == 0)
		quickacks = 2;
	if (quickacks > icsk->icsk_ack.quick)
		icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
}

void tcp_enter_quickack_mode(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	tcp_incr_quickack(sk);
	icsk->icsk_ack.pingpong = 0;
	icsk->icsk_ack.ato = TCP_ATO_MIN;
}

/* Send ACKs quickly, if "quick" count is not exhausted
 * and the session is not interactive.
 */

static inline int tcp_in_quickack_mode(const struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong;
}

static inline void TCP_ECN_queue_cwr(struct tcp_sock *tp)
{
	if (tp->ecn_flags & TCP_ECN_OK)
		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
}

static inline void TCP_ECN_accept_cwr(struct tcp_sock *tp, struct sk_buff *skb)
{
	if (tcp_hdr(skb)->cwr)
		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}

static inline void TCP_ECN_withdraw_cwr(struct tcp_sock *tp)
{
	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}

static inline void TCP_ECN_check_ce(struct tcp_sock *tp, struct sk_buff *skb)
{
	if (tp->ecn_flags & TCP_ECN_OK) {
		if (INET_ECN_is_ce(TCP_SKB_CB(skb)->flags))
			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
		/* Funny extension: if ECT is not set on a segment,
		 * it is surely retransmit. It is not in ECN RFC,
		 * but Linux follows this rule. */
		else if (INET_ECN_is_not_ect((TCP_SKB_CB(skb)->flags)))
			tcp_enter_quickack_mode((struct sock *)tp);
	}
}

static inline void TCP_ECN_rcv_synack(struct tcp_sock *tp, struct tcphdr *th)
{
	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr))
		tp->ecn_flags &= ~TCP_ECN_OK;
}

static inline void TCP_ECN_rcv_syn(struct tcp_sock *tp, struct tcphdr *th)
{
	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr))
		tp->ecn_flags &= ~TCP_ECN_OK;
}

static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th)
{
	if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK))
		return 1;
	return 0;
}

/* Buffer size and advertised window tuning.
 *
 * 1. Tuning sk->sk_sndbuf, when connection enters established state.
 */

static void tcp_fixup_sndbuf(struct sock *sk)
{
	int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 +
		     sizeof(struct sk_buff);

	if (sk->sk_sndbuf < 3 * sndmem)
		sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]);
}

/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
 *
 * All tcp_full_space() is split to two parts: "network" buffer, allocated
 * forward and advertised in receiver window (tp->rcv_wnd) and
 * "application buffer", required to isolate scheduling/application
 * latencies from network.
 * window_clamp is maximal advertised window. It can be less than
 * tcp_full_space(), in this case tcp_full_space() - window_clamp
 * is reserved for "application" buffer. The less window_clamp is
 * the smoother our behaviour from viewpoint of network, but the lower
 * throughput and the higher sensitivity of the connection to losses. 8)
 *
 * rcv_ssthresh is more strict window_clamp used at "slow start"
 * phase to predict further behaviour of this connection.
 * It is used for two goals:
 * - to enforce header prediction at sender, even when application
 *   requires some significant "application buffer". It is check #1.
 * - to prevent pruning of receive queue because of misprediction
 *   of receiver window. Check #2.
 *
 * The scheme does not work when sender sends good segments opening
 * window and then starts to feed us spaghetti. But it should work
 * in common situations. Otherwise, we have to rely on queue collapsing.
 */

/* Slow part of check#2. */
static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	/* Optimize this! */
	int truesize = tcp_win_from_space(skb->truesize) >> 1;
	int window = tcp_win_from_space(sysctl_tcp_rmem[2]) >> 1;

	while (tp->rcv_ssthresh <= window) {
		if (truesize <= skb->len)
			return 2 * inet_csk(sk)->icsk_ack.rcv_mss;

		truesize >>= 1;
		window >>= 1;
	}
	return 0;
}

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

	/* Check #1 */
	if (tp->rcv_ssthresh < tp->window_clamp &&
	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
	    !tcp_memory_pressure) {
		int incr;

		/* Check #2. Increase window, if skb with such overhead
		 * will fit to rcvbuf in future.
		 */
		if (tcp_win_from_space(skb->truesize) <= skb->len)
			incr = 2 * tp->advmss;
		else
			incr = __tcp_grow_window(sk, skb);

		if (incr) {
			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
					       tp->window_clamp);
			inet_csk(sk)->icsk_ack.quick |= 1;
		}
	}
}

/* 3. Tuning rcvbuf, when connection enters established state. */

static void tcp_fixup_rcvbuf(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int rcvmem = tp->advmss + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff);

	/* Try to select rcvbuf so that 4 mss-sized segments
	 * will fit to window and corresponding skbs will fit to our rcvbuf.
	 * (was 3; 4 is minimum to allow fast retransmit to work.)
	 */
	while (tcp_win_from_space(rcvmem) < tp->advmss)
		rcvmem += 128;
	if (sk->sk_rcvbuf < 4 * rcvmem)
		sk->sk_rcvbuf = min(4 * rcvmem, sysctl_tcp_rmem[2]);
}

/* 4. Try to fixup all. It is made immediately after connection enters
 *    established state.
 */
static void tcp_init_buffer_space(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int maxwin;

	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
		tcp_fixup_rcvbuf(sk);
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
		tcp_fixup_sndbuf(sk);

	tp->rcvq_space.space = tp->rcv_wnd;

	maxwin = tcp_full_space(sk);

	if (tp->window_clamp >= maxwin) {
		tp->window_clamp = maxwin;

		if (sysctl_tcp_app_win && maxwin > 4 * tp->advmss)
			tp->window_clamp = max(maxwin -
					       (maxwin >> sysctl_tcp_app_win),
					       4 * tp->advmss);
	}

	/* Force reservation of one segment. */
	if (sysctl_tcp_app_win &&
	    tp->window_clamp > 2 * tp->advmss &&
	    tp->window_clamp + tp->advmss > maxwin)
		tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss);

	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

/* 5. Recalculate window clamp after socket hit its memory bounds. */
static void tcp_clamp_window(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_ack.quick = 0;

	if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
	    !tcp_memory_pressure &&
	    atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
				    sysctl_tcp_rmem[2]);
	}
	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
}

/* Initialize RCV_MSS value.
 * RCV_MSS is an our guess about MSS used by the peer.
 * We haven't any direct information about the MSS.
 * It's better to underestimate the RCV_MSS rather than overestimate.
 * Overestimations make us ACKing less frequently than needed.
 * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
 */
void tcp_initialize_rcv_mss(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);

	hint = min(hint, tp->rcv_wnd / 2);
	hint = min(hint, TCP_MSS_DEFAULT);
	hint = max(hint, TCP_MIN_MSS);

	inet_csk(sk)->icsk_ack.rcv_mss = hint;
}

/* Receiver "autotuning" code.
 *
 * The algorithm for RTT estimation w/o timestamps is based on
 * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
 * <http://www.lanl.gov/radiant/website/pubs/drs/lacsi2001.ps>
 *
 * More detail on this code can be found at
 * <http://www.psc.edu/~jheffner/senior_thesis.ps>,
 * though this reference is out of date.  A new paper
 * is pending.
 */
static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
	u32 new_sample = tp->rcv_rtt_est.rtt;
	long m = sample;

	if (m == 0)
		m = 1;

	if (new_sample != 0) {
		/* If we sample in larger samples in the non-timestamp
		 * case, we could grossly overestimate the RTT especially
		 * with chatty applications or bulk transfer apps which
		 * are stalled on filesystem I/O.
		 *
		 * Also, since we are only going for a minimum in the
		 * non-timestamp case, we do not smooth things out
		 * else with timestamps disabled convergence takes too
		 * long.
		 */
		if (!win_dep) {
			m -= (new_sample >> 3);
			new_sample += m;
		} else if (m < new_sample)
			new_sample = m << 3;
	} else {
		/* No previous measure. */
		new_sample = m << 3;
	}

	if (tp->rcv_rtt_est.rtt != new_sample)
		tp->rcv_rtt_est.rtt = new_sample;
}

static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
{
	if (tp->rcv_rtt_est.time == 0)
		goto new_measure;
	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
		return;
	tcp_rcv_rtt_update(tp, jiffies - tp->rcv_rtt_est.time, 1);

new_measure:
	tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
	tp->rcv_rtt_est.time = tcp_time_stamp;
}

static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
					  const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	if (tp->rx_opt.rcv_tsecr &&
	    (TCP_SKB_CB(skb)->end_seq -
	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
		tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
}

/*
 * This function should be called every time data is copied to user space.
 * It calculates the appropriate TCP receive buffer space.
 */
void tcp_rcv_space_adjust(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int time;
	int space;

	if (tp->rcvq_space.time == 0)
		goto new_measure;

	time = tcp_time_stamp - tp->rcvq_space.time;
	if (time < (tp->rcv_rtt_est.rtt >> 3) || tp->rcv_rtt_est.rtt == 0)
		return;

	space = 2 * (tp->copied_seq - tp->rcvq_space.seq);

	space = max(tp->rcvq_space.space, space);

	if (tp->rcvq_space.space != space) {
		int rcvmem;

		tp->rcvq_space.space = space;

		if (sysctl_tcp_moderate_rcvbuf &&
		    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
			int new_clamp = space;

			/* Receive space grows, normalize in order to
			 * take into account packet headers and sk_buff
			 * structure overhead.
			 */
			space /= tp->advmss;
			if (!space)
				space = 1;
			rcvmem = (tp->advmss + MAX_TCP_HEADER +
				  16 + sizeof(struct sk_buff));
			while (tcp_win_from_space(rcvmem) < tp->advmss)
				rcvmem += 128;
			space *= rcvmem;
			space = min(space, sysctl_tcp_rmem[2]);
			if (space > sk->sk_rcvbuf) {
				sk->sk_rcvbuf = space;

				/* Make the window clamp follow along.  */
				tp->window_clamp = new_clamp;
			}
		}
	}

new_measure:
	tp->rcvq_space.seq = tp->copied_seq;
	tp->rcvq_space.time = tcp_time_stamp;
}

/* There is something which you must keep in mind when you analyze the
 * behavior of the tp->ato delayed ack timeout interval.  When a
 * connection starts up, we want to ack as quickly as possible.  The
 * problem is that "good" TCP's do slow start at the beginning of data
 * transmission.  The means that until we send the first few ACK's the
 * sender will sit on his end and only queue most of his data, because
 * he can only send snd_cwnd unacked packets at any given time.  For
 * each ACK we send, he increments snd_cwnd and transmits more of his
 * queue.  -DaveM
 */
static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	u32 now;

	inet_csk_schedule_ack(sk);

	tcp_measure_rcv_mss(sk, skb);

	tcp_rcv_rtt_measure(tp);

	now = tcp_time_stamp;

	if (!icsk->icsk_ack.ato) {
		/* The _first_ data packet received, initialize
		 * delayed ACK engine.
		 */
		tcp_incr_quickack(sk);
		icsk->icsk_ack.ato = TCP_ATO_MIN;
	} else {
		int m = now - icsk->icsk_ack.lrcvtime;

		if (m <= TCP_ATO_MIN / 2) {
			/* The fastest case is the first. */
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2;
		} else if (m < icsk->icsk_ack.ato) {
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m;
			if (icsk->icsk_ack.ato > icsk->icsk_rto)
				icsk->icsk_ack.ato = icsk->icsk_rto;
		} else if (m > icsk->icsk_rto) {
			/* Too long gap. Apparently sender failed to
			 * restart window, so that we send ACKs quickly.
			 */
			tcp_incr_quickack(sk);
			sk_mem_reclaim(sk);
		}
	}
	icsk->icsk_ack.lrcvtime = now;

	TCP_ECN_check_ce(tp, skb);

	if (skb->len >= 128)
		tcp_grow_window(sk, skb);
}

/* Called to compute a smoothed rtt estimate. The data fed to this
 * routine either comes from timestamps, or from segments that were
 * known _not_ to have been retransmitted [see Karn/Partridge
 * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
 * piece by Van Jacobson.
 * NOTE: the next three routines used to be one big routine.
 * To save cycles in the RFC 1323 implementation it was better to break
 * it up into three procedures. -- erics
 */
static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
{
	struct tcp_sock *tp = tcp_sk(sk);
	long m = mrtt; /* RTT */

	/*	The following amusing code comes from Jacobson's
	 *	article in SIGCOMM '88.  Note that rtt and mdev
	 *	are scaled versions of rtt and mean deviation.
	 *	This is designed to be as fast as possible
	 *	m stands for "measurement".
	 *
	 *	On a 1990 paper the rto value is changed to:
	 *	RTO = rtt + 4 * mdev
	 *
	 * Funny. This algorithm seems to be very broken.
	 * These formulae increase RTO, when it should be decreased, increase
	 * too slowly, when it should be increased quickly, decrease too quickly
	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
	 * does not matter how to _calculate_ it. Seems, it was trap
	 * that VJ failed to avoid. 8)
	 */
	if (m == 0)
		m = 1;
	if (tp->srtt != 0) {
		m -= (tp->srtt >> 3);	/* m is now error in rtt est */
		tp->srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
		if (m < 0) {
			m = -m;		/* m is now abs(error) */
			m -= (tp->mdev >> 2);   /* similar update on mdev */
			/* This is similar to one of Eifel findings.
			 * Eifel blocks mdev updates when rtt decreases.
			 * This solution is a bit different: we use finer gain
			 * for mdev in this case (alpha*beta).
			 * Like Eifel it also prevents growth of rto,
			 * but also it limits too fast rto decreases,
			 * happening in pure Eifel.
			 */
			if (m > 0)
				m >>= 3;
		} else {
			m -= (tp->mdev >> 2);   /* similar update on mdev */
		}
		tp->mdev += m;	    	/* mdev = 3/4 mdev + 1/4 new */
		if (tp->mdev > tp->mdev_max) {
			tp->mdev_max = tp->mdev;
			if (tp->mdev_max > tp->rttvar)
				tp->rttvar = tp->mdev_max;
		}
		if (after(tp->snd_una, tp->rtt_seq)) {
			if (tp->mdev_max < tp->rttvar)
				tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2;
			tp->rtt_seq = tp->snd_nxt;
			tp->mdev_max = tcp_rto_min(sk);
		}
	} else {
		/* no previous measure. */
		tp->srtt = m << 3;	/* take the measured time to be rtt */
		tp->mdev = m << 1;	/* make sure rto = 3*rtt */
		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
		tp->rtt_seq = tp->snd_nxt;
	}
}

/* Calculate rto without backoff.  This is the second half of Van Jacobson's
 * routine referred to above.
 */
static inline void tcp_set_rto(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	/* Old crap is replaced with new one. 8)
	 *
	 * More seriously:
	 * 1. If rtt variance happened to be less 50msec, it is hallucination.
	 *    It cannot be less due to utterly erratic ACK generation made
	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
	 *    to do with delayed acks, because at cwnd>2 true delack timeout
	 *    is invisible. Actually, Linux-2.4 also generates erratic
	 *    ACKs in some circumstances.
	 */
	inet_csk(sk)->icsk_rto = __tcp_set_rto(tp);

	/* 2. Fixups made earlier cannot be right.
	 *    If we do not estimate RTO correctly without them,
	 *    all the algo is pure shit and should be replaced
	 *    with correct one. It is exactly, which we pretend to do.
	 */

	/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
	 * guarantees that rto is higher.
	 */
	tcp_bound_rto(sk);
}

/* Save metrics learned by this TCP session.
   This function is called only, when TCP finishes successfully
   i.e. when it enters TIME-WAIT or goes from LAST-ACK to CLOSE.
 */
void tcp_update_metrics(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);

	if (sysctl_tcp_nometrics_save)
		return;

	dst_confirm(dst);

	if (dst && (dst->flags & DST_HOST)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		int m;
		unsigned long rtt;

		if (icsk->icsk_backoff || !tp->srtt) {
			/* This session failed to estimate rtt. Why?
			 * Probably, no packets returned in time.
			 * Reset our results.
			 */
			if (!(dst_metric_locked(dst, RTAX_RTT)))
				dst->metrics[RTAX_RTT - 1] = 0;
			return;
		}

		rtt = dst_metric_rtt(dst, RTAX_RTT);
		m = rtt - tp->srtt;

		/* If newly calculated rtt larger than stored one,
		 * store new one. Otherwise, use EWMA. Remember,
		 * rtt overestimation is always better than underestimation.
		 */
		if (!(dst_metric_locked(dst, RTAX_RTT))) {
			if (m <= 0)
				set_dst_metric_rtt(dst, RTAX_RTT, tp->srtt);
			else
				set_dst_metric_rtt(dst, RTAX_RTT, rtt - (m >> 3));
		}

		if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
			unsigned long var;
			if (m < 0)
				m = -m;

			/* Scale deviation to rttvar fixed point */
			m >>= 1;
			if (m < tp->mdev)
				m = tp->mdev;

			var = dst_metric_rtt(dst, RTAX_RTTVAR);
			if (m >= var)
				var = m;
			else
				var -= (var - m) >> 2;

			set_dst_metric_rtt(dst, RTAX_RTTVAR, var);
		}

		if (tcp_in_initial_slowstart(tp)) {
			/* Slow start still did not finish. */
			if (dst_metric(dst, RTAX_SSTHRESH) &&
			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
			    (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
				dst->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1;
			if (!dst_metric_locked(dst, RTAX_CWND) &&
			    tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND - 1] = tp->snd_cwnd;
		} else if (tp->snd_cwnd > tp->snd_ssthresh &&
			   icsk->icsk_ca_state == TCP_CA_Open) {
			/* Cong. avoidance phase, cwnd is reliable. */
			if (!dst_metric_locked(dst, RTAX_SSTHRESH))
				dst->metrics[RTAX_SSTHRESH-1] =
					max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
			if (!dst_metric_locked(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1;
		} else {
			/* Else slow start did not finish, cwnd is non-sense,
			   ssthresh may be also invalid.
			 */
			if (!dst_metric_locked(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1;
			if (dst_metric(dst, RTAX_SSTHRESH) &&
			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
			    tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
				dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
		}

		if (!dst_metric_locked(dst, RTAX_REORDERING)) {
			if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
			    tp->reordering != sysctl_tcp_reordering)
				dst->metrics[RTAX_REORDERING-1] = tp->reordering;
		}
	}
}

/* Numbers are taken from RFC3390.
 *
 * John Heffner states:
 *
 *	The RFC specifies a window of no more than 4380 bytes
 *	unless 2*MSS > 4380.  Reading the pseudocode in the RFC
 *	is a bit misleading because they use a clamp at 4380 bytes
 *	rather than use a multiplier in the relevant range.
 */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
{
	__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);

	if (!cwnd) {
		if (tp->mss_cache > 1460)
			cwnd = 2;
		else
			cwnd = (tp->mss_cache > 1095) ? 3 : 4;
	}
	return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}

/* Set slow start threshold and cwnd not falling to slow start */
void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);

	tp->prior_ssthresh = 0;
	tp->bytes_acked = 0;
	if (icsk->icsk_ca_state < TCP_CA_CWR) {
		tp->undo_marker = 0;
		if (set_ssthresh)
			tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
		tp->snd_cwnd = min(tp->snd_cwnd,
				   tcp_packets_in_flight(tp) + 1U);
		tp->snd_cwnd_cnt = 0;
		tp->high_seq = tp->snd_nxt;
		tp->snd_cwnd_stamp = tcp_time_stamp;
		TCP_ECN_queue_cwr(tp);

		tcp_set_ca_state(sk, TCP_CA_CWR);
	}
}

/*
 * Packet counting of FACK is based on in-order assumptions, therefore TCP
 * disables it when reordering is detected
 */
static void tcp_disable_fack(struct tcp_sock *tp)
{
	/* RFC3517 uses different metric in lost marker => reset on change */
	if (tcp_is_fack(tp))
		tp->lost_skb_hint = NULL;
	tp->rx_opt.sack_ok &= ~2;
}

/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
	tp->rx_opt.sack_ok |= 4;
}

/* Initialize metrics on socket. */

static void tcp_init_metrics(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);

	if (dst == NULL)
		goto reset;

	dst_confirm(dst);

	if (dst_metric_locked(dst, RTAX_CWND))
		tp->snd_cwnd_clamp = dst_metric(dst, RTAX_CWND);
	if (dst_metric(dst, RTAX_SSTHRESH)) {
		tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH);
		if (tp->snd_ssthresh > tp->snd_cwnd_clamp)
			tp->snd_ssthresh = tp->snd_cwnd_clamp;
	}
	if (dst_metric(dst, RTAX_REORDERING) &&
	    tp->reordering != dst_metric(dst, RTAX_REORDERING)) {
		tcp_disable_fack(tp);
		tp->reordering = dst_metric(dst, RTAX_REORDERING);
	}

	if (dst_metric(dst, RTAX_RTT) == 0)
		goto reset;

	if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3))
		goto reset;

	/* Initial rtt is determined from SYN,SYN-ACK.
	 * The segment is small and rtt may appear much
	 * less than real one. Use per-dst memory
	 * to make it more realistic.
	 *
	 * A bit of theory. RTT is time passed after "normal" sized packet
	 * is sent until it is ACKed. In normal circumstances sending small
	 * packets force peer to delay ACKs and calculation is correct too.
	 * The algorithm is adaptive and, provided we follow specs, it
	 * NEVER underestimate RTT. BUT! If peer tries to make some clever
	 * tricks sort of "quick acks" for time long enough to decrease RTT
	 * to low value, and then abruptly stops to do it and starts to delay
	 * ACKs, wait for troubles.
	 */
	if (dst_metric_rtt(dst, RTAX_RTT) > tp->srtt) {
		tp->srtt = dst_metric_rtt(dst, RTAX_RTT);
		tp->rtt_seq = tp->snd_nxt;
	}
	if (dst_metric_rtt(dst, RTAX_RTTVAR) > tp->mdev) {
		tp->mdev = dst_metric_rtt(dst, RTAX_RTTVAR);
		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
	}
	tcp_set_rto(sk);
	if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp)
		goto reset;

cwnd:
	tp->snd_cwnd = tcp_init_cwnd(tp, dst);
	tp->snd_cwnd_stamp = tcp_time_stamp;
	return;

reset:
	/* Play conservative. If timestamps are not
	 * supported, TCP will fail to recalculate correct
	 * rtt, if initial rto is too small. FORGET ALL AND RESET!
	 */
	if (!tp->rx_opt.saw_tstamp && tp->srtt) {
		tp->srtt = 0;
		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT;
		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
	}
	goto cwnd;
}

static void tcp_update_reordering(struct sock *sk, const int metric,
				  const int ts)
{
	struct tcp_sock *tp = tcp_sk(sk);
	if (metric > tp->reordering) {
		int mib_idx;

		tp->reordering = min(TCP_MAX_REORDERING, metric);

		/* This exciting event is worth to be remembered. 8) */
		if (ts)
			mib_idx = LINUX_MIB_TCPTSREORDER;
		else if (tcp_is_reno(tp))
			mib_idx = LINUX_MIB_TCPRENOREORDER;
		else if (tcp_is_fack(tp))
			mib_idx = LINUX_MIB_TCPFACKREORDER;
		else
			mib_idx = LINUX_MIB_TCPSACKREORDER;

		NET_INC_STATS_BH(sock_net(sk), mib_idx);
#if FASTRETRANS_DEBUG > 1
		printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n",
		       tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
		       tp->reordering,
		       tp->fackets_out,
		       tp->sacked_out,
		       tp->undo_marker ? tp->undo_retrans : 0);
#endif
		tcp_disable_fack(tp);
	}
}

/* This must be called before lost_out is incremented */
static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
{
	if ((tp->retransmit_skb_hint == NULL) ||
	    before(TCP_SKB_CB(skb)->seq,
		   TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
		tp->retransmit_skb_hint = skb;

	if (!tp->lost_out ||
	    after(TCP_SKB_CB(skb)->end_seq, tp->retransmit_high))
		tp->retransmit_high = TCP_SKB_CB(skb)->end_seq;
}

static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
{
	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
		tcp_verify_retransmit_hint(tp, skb);

		tp->lost_out += tcp_skb_pcount(skb);
		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
	}
}

static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp,
					    struct sk_buff *skb)
{
	tcp_verify_retransmit_hint(tp, skb);

	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
		tp->lost_out += tcp_skb_pcount(skb);
		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
	}
}

/* This procedure tags the retransmission queue when SACKs arrive.
 *
 * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
 * Packets in queue with these bits set are counted in variables
 * sacked_out, retrans_out and lost_out, correspondingly.
 *
 * Valid combinations are:
 * Tag  InFlight	Description
 * 0	1		- orig segment is in flight.
 * S	0		- nothing flies, orig reached receiver.
 * L	0		- nothing flies, orig lost by net.
 * R	2		- both orig and retransmit are in flight.
 * L|R	1		- orig is lost, retransmit is in flight.
 * S|R  1		- orig reached receiver, retrans is still in flight.
 * (L|S|R is logically valid, it could occur when L|R is sacked,
 *  but it is equivalent to plain S and code short-curcuits it to S.
 *  L|S is logically invalid, it would mean -1 packet in flight 8))
 *
 * These 6 states form finite state machine, controlled by the following events:
 * 1. New ACK (+SACK) arrives. (tcp_sacktag_write_queue())
 * 2. Retransmission. (tcp_retransmit_skb(), tcp_xmit_retransmit_queue())
 * 3. Loss detection event of one of three flavors:
 *	A. Scoreboard estimator decided the packet is lost.
 *	   A'. Reno "three dupacks" marks head of queue lost.
 *	   A''. Its FACK modfication, head until snd.fack is lost.
 *	B. SACK arrives sacking data transmitted after never retransmitted
 *	   hole was sent out.
 *	C. SACK arrives sacking SND.NXT at the moment, when the
 *	   segment was retransmitted.
 * 4. D-SACK added new rule: D-SACK changes any tag to S.
 *
 * It is pleasant to note, that state diagram turns out to be commutative,
 * so that we are allowed not to be bothered by order of our actions,
 * when multiple events arrive simultaneously. (see the function below).
 *
 * Reordering detection.
 * --------------------
 * Reordering metric is maximal distance, which a packet can be displaced
 * in packet stream. With SACKs we can estimate it:
 *
 * 1. SACK fills old hole and the corresponding segment was not
 *    ever retransmitted -> reordering. Alas, we cannot use it
 *    when segment was retransmitted.
 * 2. The last flaw is solved with D-SACK. D-SACK arrives
 *    for retransmitted and already SACKed segment -> reordering..
 * Both of these heuristics are not used in Loss state, when we cannot
 * account for retransmits accurately.
 *
 * SACK block validation.
 * ----------------------
 *
 * SACK block range validation checks that the received SACK block fits to
 * the expected sequence limits, i.e., it is between SND.UNA and SND.NXT.
 * Note that SND.UNA is not included to the range though being valid because
 * it means that the receiver is rather inconsistent with itself reporting
 * SACK reneging when it should advance SND.UNA. Such SACK block this is
 * perfectly valid, however, in light of RFC2018 which explicitly states
 * that "SACK block MUST reflect the newest segment.  Even if the newest
 * segment is going to be discarded ...", not that it looks very clever
 * in case of head skb. Due to potentional receiver driven attacks, we
 * choose to avoid immediate execution of a walk in write queue due to
 * reneging and defer head skb's loss recovery to standard loss recovery
 * procedure that will eventually trigger (nothing forbids us doing this).
 *
 * Implements also blockage to start_seq wrap-around. Problem lies in the
 * fact that though start_seq (s) is before end_seq (i.e., not reversed),
 * there's no guarantee that it will be before snd_nxt (n). The problem
 * happens when start_seq resides between end_seq wrap (e_w) and snd_nxt
 * wrap (s_w):
 *
 *         <- outs wnd ->                          <- wrapzone ->
 *         u     e      n                         u_w   e_w  s n_w
 *         |     |      |                          |     |   |  |
 * |<------------+------+----- TCP seqno space --------------+---------->|
 * ...-- <2^31 ->|                                           |<--------...
 * ...---- >2^31 ------>|                                    |<--------...
 *
 * Current code wouldn't be vulnerable but it's better still to discard such
 * crazy SACK blocks. Doing this check for start_seq alone closes somewhat
 * similar case (end_seq after snd_nxt wrap) as earlier reversed check in
 * snd_nxt wrap -> snd_una region will then become "well defined", i.e.,
 * equal to the ideal case (infinite seqno space without wrap caused issues).
 *
 * With D-SACK the lower bound is extended to cover sequence space below
 * SND.UNA down to undo_marker, which is the last point of interest. Yet
 * again, D-SACK block must not to go across snd_una (for the same reason as
 * for the normal SACK blocks, explained above). But there all simplicity
 * ends, TCP might receive valid D-SACKs below that. As long as they reside
 * fully below undo_marker they do not affect behavior in anyway and can
 * therefore be safely ignored. In rare cases (which are more or less
 * theoretical ones), the D-SACK will nicely cross that boundary due to skb
 * fragmentation and packet reordering past skb's retransmission. To consider
 * them correctly, the acceptable range must be extended even more though
 * the exact amount is rather hard to quantify. However, tp->max_window can
 * be used as an exaggerated estimate.
 */
static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
				  u32 start_seq, u32 end_seq)
{
	/* Too far in future, or reversed (interpretation is ambiguous) */
	if (after(end_seq, tp->snd_nxt) || !before(start_seq, end_seq))
		return 0;

	/* Nasty start_seq wrap-around check (see comments above) */
	if (!before(start_seq, tp->snd_nxt))
		return 0;

	/* In outstanding window? ...This is valid exit for D-SACKs too.
	 * start_seq == snd_una is non-sensical (see comments above)
	 */
	if (after(start_seq, tp->snd_una))
		return 1;

	if (!is_dsack || !tp->undo_marker)
		return 0;

	/* ...Then it's D-SACK, and must reside below snd_una completely */
	if (!after(end_seq, tp->snd_una))
		return 0;

	if (!before(start_seq, tp->undo_marker))
		return 1;

	/* Too old */
	if (!after(end_seq, tp->undo_marker))
		return 0;

	/* Undo_marker boundary crossing (overestimates a lot). Known already:
	 *   start_seq < undo_marker and end_seq >= undo_marker.
	 */
	return !before(start_seq, end_seq - tp->max_window);
}

/* Check for lost retransmit. This superb idea is borrowed from "ratehalving".
 * Event "C". Later note: FACK people cheated me again 8), we have to account
 * for reordering! Ugly, but should help.
 *
 * Search retransmitted skbs from write_queue that were sent when snd_nxt was
 * less than what is now known to be received by the other end (derived from
 * highest SACK block). Also calculate the lowest snd_nxt among the remaining
 * retransmitted skbs to avoid some costly processing per ACKs.
 */
static void tcp_mark_lost_retrans(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int cnt = 0;
	u32 new_low_seq = tp->snd_nxt;
	u32 received_upto = tcp_highest_sack_seq(tp);

	if (!tcp_is_fack(tp) || !tp->retrans_out ||
	    !after(received_upto, tp->lost_retrans_low) ||
	    icsk->icsk_ca_state != TCP_CA_Recovery)
		return;

	tcp_for_write_queue(skb, sk) {
		u32 ack_seq = TCP_SKB_CB(skb)->ack_seq;

		if (skb == tcp_send_head(sk))
			break;
		if (cnt == tp->retrans_out)
			break;
		if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
			continue;

		if (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS))
			continue;

		/* TODO: We would like to get rid of tcp_is_fack(tp) only
		 * constraint here (see above) but figuring out that at
		 * least tp->reordering SACK blocks reside between ack_seq
		 * and received_upto is not easy task to do cheaply with
		 * the available datastructures.
		 *
		 * Whether FACK should check here for tp->reordering segs
		 * in-between one could argue for either way (it would be
		 * rather simple to implement as we could count fack_count
		 * during the walk and do tp->fackets_out - fack_count).
		 */
		if (after(received_upto, ack_seq)) {
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
			tp->retrans_out -= tcp_skb_pcount(skb);

			tcp_skb_mark_lost_uncond_verify(tp, skb);
			NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
		} else {
			if (before(ack_seq, new_low_seq))
				new_low_seq = ack_seq;
			cnt += tcp_skb_pcount(skb);
		}
	}

	if (tp->retrans_out)
		tp->lost_retrans_low = new_low_seq;
}

static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb,
			   struct tcp_sack_block_wire *sp, int num_sacks,
			   u32 prior_snd_una)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
	u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
	int dup_sack = 0;

	if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
		dup_sack = 1;
		tcp_dsack_seen(tp);
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKRECV);
	} else if (num_sacks > 1) {
		u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
		u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);

		if (!after(end_seq_0, end_seq_1) &&
		    !before(start_seq_0, start_seq_1)) {
			dup_sack = 1;
			tcp_dsack_seen(tp);
			NET_INC_STATS_BH(sock_net(sk),
					LINUX_MIB_TCPDSACKOFORECV);
		}
	}

	/* D-SACK for already forgotten data... Do dumb counting. */
	if (dup_sack &&
	    !after(end_seq_0, prior_snd_una) &&
	    after(end_seq_0, tp->undo_marker))
		tp->undo_retrans--;

	return dup_sack;
}

struct tcp_sacktag_state {
	int reord;
	int fack_count;
	int flag;
};

/* Check if skb is fully within the SACK block. In presence of GSO skbs,
 * the incoming SACK may not exactly match but we can find smaller MSS
 * aligned portion of it that matches. Therefore we might need to fragment
 * which may fail and creates some hassle (caller must handle error case
 * returns).
 *
 * FIXME: this could be merged to shift decision code
 */
static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
				 u32 start_seq, u32 end_seq)
{
	int in_sack, err;
	unsigned int pkt_len;
	unsigned int mss;

	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
		  !before(end_seq, TCP_SKB_CB(skb)->end_seq);

	if (tcp_skb_pcount(skb) > 1 && !in_sack &&
	    after(TCP_SKB_CB(skb)->end_seq, start_seq)) {
		mss = tcp_skb_mss(skb);
		in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);

		if (!in_sack) {
			pkt_len = start_seq - TCP_SKB_CB(skb)->seq;
			if (pkt_len < mss)
				pkt_len = mss;
		} else {
			pkt_len = end_seq - TCP_SKB_CB(skb)->seq;
			if (pkt_len < mss)
				return -EINVAL;
		}

		/* Round if necessary so that SACKs cover only full MSSes
		 * and/or the remaining small portion (if present)
		 */
		if (pkt_len > mss) {
			unsigned int new_len = (pkt_len / mss) * mss;
			if (!in_sack && new_len < pkt_len) {
				new_len += mss;
				if (new_len > skb->len)
					return 0;
			}
			pkt_len = new_len;
		}
		err = tcp_fragment(sk, skb, pkt_len, mss);
		if (err < 0)
			return err;
	}

	return in_sack;
}

static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
			  struct tcp_sacktag_state *state,
			  int dup_sack, int pcount)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u8 sacked = TCP_SKB_CB(skb)->sacked;
	int fack_count = state->fack_count;

	/* Account D-SACK for retransmitted packet. */
	if (dup_sack && (sacked & TCPCB_RETRANS)) {
		if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
			tp->undo_retrans--;
		if (sacked & TCPCB_SACKED_ACKED)
			state->reord = min(fack_count, state->reord);
	}

	/* Nothing to do; acked frame is about to be dropped (was ACKed). */
	if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
		return sacked;

	if (!(sacked & TCPCB_SACKED_ACKED)) {
		if (sacked & TCPCB_SACKED_RETRANS) {
			/* If the segment is not tagged as lost,
			 * we do not clear RETRANS, believing
			 * that retransmission is still in flight.
			 */
			if (sacked & TCPCB_LOST) {
				sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS);
				tp->lost_out -= pcount;
				tp->retrans_out -= pcount;
			}
		} else {
			if (!(sacked & TCPCB_RETRANS)) {
				/* New sack for not retransmitted frame,
				 * which was in hole. It is reordering.
				 */
				if (before(TCP_SKB_CB(skb)->seq,
					   tcp_highest_sack_seq(tp)))
					state->reord = min(fack_count,
							   state->reord);

				/* SACK enhanced F-RTO (RFC4138; Appendix B) */
				if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
					state->flag |= FLAG_ONLY_ORIG_SACKED;
			}

			if (sacked & TCPCB_LOST) {
				sacked &= ~TCPCB_LOST;
				tp->lost_out -= pcount;
			}
		}

		sacked |= TCPCB_SACKED_ACKED;
		state->flag |= FLAG_DATA_SACKED;
		tp->sacked_out += pcount;

		fack_count += pcount;

		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
		if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
		    before(TCP_SKB_CB(skb)->seq,
			   TCP_SKB_CB(tp->lost_skb_hint)->seq))
			tp->lost_cnt_hint += pcount;

		if (fack_count > tp->fackets_out)
			tp->fackets_out = fack_count;
	}

	/* D-SACK. We can detect redundant retransmission in S|R and plain R
	 * frames and clear it. undo_retrans is decreased above, L|R frames
	 * are accounted above as well.
	 */
	if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) {
		sacked &= ~TCPCB_SACKED_RETRANS;
		tp->retrans_out -= pcount;
	}

	return sacked;
}

static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
			   struct tcp_sacktag_state *state,
			   unsigned int pcount, int shifted, int mss,
			   int dup_sack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);

	BUG_ON(!pcount);

	/* Tweak before seqno plays */
	if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint &&
	    !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq))
		tp->lost_cnt_hint += pcount;

	TCP_SKB_CB(prev)->end_seq += shifted;
	TCP_SKB_CB(skb)->seq += shifted;

	skb_shinfo(prev)->gso_segs += pcount;
	BUG_ON(skb_shinfo(skb)->gso_segs < pcount);
	skb_shinfo(skb)->gso_segs -= pcount;

	/* When we're adding to gso_segs == 1, gso_size will be zero,
	 * in theory this shouldn't be necessary but as long as DSACK
	 * code can come after this skb later on it's better to keep
	 * setting gso_size to something.
	 */
	if (!skb_shinfo(prev)->gso_size) {
		skb_shinfo(prev)->gso_size = mss;
		skb_shinfo(prev)->gso_type = sk->sk_gso_type;
	}

	/* CHECKME: To clear or not to clear? Mimics normal skb currently */
	if (skb_shinfo(skb)->gso_segs <= 1) {
		skb_shinfo(skb)->gso_size = 0;
		skb_shinfo(skb)->gso_type = 0;
	}

	/* We discard results */
	tcp_sacktag_one(skb, sk, state, dup_sack, pcount);

	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);

	if (skb->len > 0) {
		BUG_ON(!tcp_skb_pcount(skb));
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTED);
		return 0;
	}

	/* Whole SKB was eaten :-) */

	if (skb == tp->retransmit_skb_hint)
		tp->retransmit_skb_hint = prev;
	if (skb == tp->scoreboard_skb_hint)
		tp->scoreboard_skb_hint = prev;
	if (skb == tp->lost_skb_hint) {
		tp->lost_skb_hint = prev;
		tp->lost_cnt_hint -= tcp_skb_pcount(prev);
	}

	TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags;
	if (skb == tcp_highest_sack(sk))
		tcp_advance_highest_sack(sk, skb);

	tcp_unlink_write_queue(skb, sk);
	sk_wmem_free_skb(sk, skb);

	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKMERGED);

	return 1;
}

/* I wish gso_size would have a bit more sane initialization than
 * something-or-zero which complicates things
 */
static int tcp_skb_seglen(struct sk_buff *skb)
{
	return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb);
}

/* Shifting pages past head area doesn't work */
static int skb_can_shift(struct sk_buff *skb)
{
	return !skb_headlen(skb) && skb_is_nonlinear(skb);
}

/* Try collapsing SACK blocks spanning across multiple skbs to a single
 * skb.
 */
static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
					  struct tcp_sacktag_state *state,
					  u32 start_seq, u32 end_seq,
					  int dup_sack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *prev;
	int mss;
	int pcount = 0;
	int len;
	int in_sack;

	if (!sk_can_gso(sk))
		goto fallback;

	/* Normally R but no L won't result in plain S */
	if (!dup_sack &&
	    (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS)
		goto fallback;
	if (!skb_can_shift(skb))
		goto fallback;
	/* This frame is about to be dropped (was ACKed). */
	if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
		goto fallback;

	/* Can only happen with delayed DSACK + discard craziness */
	if (unlikely(skb == tcp_write_queue_head(sk)))
		goto fallback;
	prev = tcp_write_queue_prev(sk, skb);

	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
		goto fallback;

	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
		  !before(end_seq, TCP_SKB_CB(skb)->end_seq);

	if (in_sack) {
		len = skb->len;
		pcount = tcp_skb_pcount(skb);
		mss = tcp_skb_seglen(skb);

		/* TODO: Fix DSACKs to not fragment already SACKed and we can
		 * drop this restriction as unnecessary
		 */
		if (mss != tcp_skb_seglen(prev))
			goto fallback;
	} else {
		if (!after(TCP_SKB_CB(skb)->end_seq, start_seq))
			goto noop;
		/* CHECKME: This is non-MSS split case only?, this will
		 * cause skipped skbs due to advancing loop btw, original
		 * has that feature too
		 */
		if (tcp_skb_pcount(skb) <= 1)
			goto noop;

		in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq);
		if (!in_sack) {
			/* TODO: head merge to next could be attempted here
			 * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)),
			 * though it might not be worth of the additional hassle
			 *
			 * ...we can probably just fallback to what was done
			 * previously. We could try merging non-SACKed ones
			 * as well but it probably isn't going to buy off
			 * because later SACKs might again split them, and
			 * it would make skb timestamp tracking considerably
			 * harder problem.
			 */
			goto fallback;
		}

		len = end_seq - TCP_SKB_CB(skb)->seq;
		BUG_ON(len < 0);
		BUG_ON(len > skb->len);

		/* MSS boundaries should be honoured or else pcount will
		 * severely break even though it makes things bit trickier.
		 * Optimize common case to avoid most of the divides
		 */
		mss = tcp_skb_mss(skb);

		/* TODO: Fix DSACKs to not fragment already SACKed and we can
		 * drop this restriction as unnecessary
		 */
		if (mss != tcp_skb_seglen(prev))
			goto fallback;

		if (len == mss) {
			pcount = 1;
		} else if (len < mss) {
			goto noop;
		} else {
			pcount = len / mss;
			len = pcount * mss;
		}
	}

	if (!skb_shift(prev, skb, len))
		goto fallback;
	if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss, dup_sack))
		goto out;

	/* Hole filled allows collapsing with the next as well, this is very
	 * useful when hole on every nth skb pattern happens
	 */
	if (prev == tcp_write_queue_tail(sk))
		goto out;
	skb = tcp_write_queue_next(sk, prev);

	if (!skb_can_shift(skb) ||
	    (skb == tcp_send_head(sk)) ||
	    ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) ||
	    (mss != tcp_skb_seglen(skb)))
		goto out;

	len = skb->len;
	if (skb_shift(prev, skb, len)) {
		pcount += tcp_skb_pcount(skb);
		tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss, 0);
	}

out:
	state->fack_count += pcount;
	return prev;

noop:
	return skb;

fallback:
	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK);
	return NULL;
}

static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
					struct tcp_sack_block *next_dup,
					struct tcp_sacktag_state *state,
					u32 start_seq, u32 end_seq,
					int dup_sack_in)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *tmp;

	tcp_for_write_queue_from(skb, sk) {
		int in_sack = 0;
		int dup_sack = dup_sack_in;

		if (skb == tcp_send_head(sk))
			break;

		/* queue is in-order => we can short-circuit the walk early */
		if (!before(TCP_SKB_CB(skb)->seq, end_seq))
			break;

		if ((next_dup != NULL) &&
		    before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) {
			in_sack = tcp_match_skb_to_sack(sk, skb,
							next_dup->start_seq,
							next_dup->end_seq);
			if (in_sack > 0)
				dup_sack = 1;
		}

		/* skb reference here is a bit tricky to get right, since
		 * shifting can eat and free both this skb and the next,
		 * so not even _safe variant of the loop is enough.
		 */
		if (in_sack <= 0) {
			tmp = tcp_shift_skb_data(sk, skb, state,
						 start_seq, end_seq, dup_sack);
			if (tmp != NULL) {
				if (tmp != skb) {
					skb = tmp;
					continue;
				}

				in_sack = 0;
			} else {
				in_sack = tcp_match_skb_to_sack(sk, skb,
								start_seq,
								end_seq);
			}
		}

		if (unlikely(in_sack < 0))
			break;

		if (in_sack) {
			TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk,
								  state,
								  dup_sack,
								  tcp_skb_pcount(skb));

			if (!before(TCP_SKB_CB(skb)->seq,
				    tcp_highest_sack_seq(tp)))
				tcp_advance_highest_sack(sk, skb);
		}

		state->fack_count += tcp_skb_pcount(skb);
	}
	return skb;
}

/* Avoid all extra work that is being done by sacktag while walking in
 * a normal way
 */
static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk,
					struct tcp_sacktag_state *state,
					u32 skip_to_seq)
{
	tcp_for_write_queue_from(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;

		if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq))
			break;

		state->fack_count += tcp_skb_pcount(skb);
	}
	return skb;
}

static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb,
						struct sock *sk,
						struct tcp_sack_block *next_dup,
						struct tcp_sacktag_state *state,
						u32 skip_to_seq)
{
	if (next_dup == NULL)
		return skb;

	if (before(next_dup->start_seq, skip_to_seq)) {
		skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq);
		skb = tcp_sacktag_walk(skb, sk, NULL, state,
				       next_dup->start_seq, next_dup->end_seq,
				       1);
	}

	return skb;
}

static int tcp_sack_cache_ok(struct tcp_sock *tp, struct tcp_sack_block *cache)
{
	return cache < tp->recv_sack_cache + ARRAY_SIZE(tp->recv_sack_cache);
}

static int
tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb,
			u32 prior_snd_una)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	unsigned char *ptr = (skb_transport_header(ack_skb) +
			      TCP_SKB_CB(ack_skb)->sacked);
	struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2);
	struct tcp_sack_block sp[TCP_NUM_SACKS];
	struct tcp_sack_block *cache;
	struct tcp_sacktag_state state;
	struct sk_buff *skb;
	int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3);
	int used_sacks;
	int found_dup_sack = 0;
	int i, j;
	int first_sack_index;

	state.flag = 0;
	state.reord = tp->packets_out;

	if (!tp->sacked_out) {
		if (WARN_ON(tp->fackets_out))
			tp->fackets_out = 0;
		tcp_highest_sack_reset(sk);
	}

	found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
					 num_sacks, prior_snd_una);
	if (found_dup_sack)
		state.flag |= FLAG_DSACKING_ACK;

	/* Eliminate too old ACKs, but take into
	 * account more or less fresh ones, they can
	 * contain valid SACK info.
	 */
	if (before(TCP_SKB_CB(ack_skb)->ack_seq, prior_snd_una - tp->max_window))
		return 0;