tcp_input.c

 * "Disorder"   In all the respects it is "Open",
 *		but requires a bit more attention. It is entered when
 *		we see some SACKs or dupacks. It is split of "Open"
 *		mainly to move some processing from fast path to slow one.
 * "CWR"	CWND was reduced due to some Congestion Notification event.
 *		It can be ECN, ICMP source quench, local device congestion.
 * "Recovery"	CWND was reduced, we are fast-retransmitting.
 * "Loss"	CWND was reduced due to RTO timeout or SACK reneging.
 *
 * tcp_fastretrans_alert() is entered:
 * - each incoming ACK, if state is not "Open"
 * - when arrived ACK is unusual, namely:
 *	* SACK
 *	* Duplicate ACK.
 *	* ECN ECE.
 *
 * Counting packets in flight is pretty simple.
 *
 *	in_flight = packets_out - left_out + retrans_out
 *
 *	packets_out is SND.NXT-SND.UNA counted in packets.
 *
 *	retrans_out is number of retransmitted segments.
 *
 *	left_out is number of segments left network, but not ACKed yet.
 *
 *		left_out = sacked_out + lost_out
 *
 *     sacked_out: Packets, which arrived to receiver out of order
 *		   and hence not ACKed. With SACKs this number is simply
 *		   amount of SACKed data. Even without SACKs
 *		   it is easy to give pretty reliable estimate of this number,
 *		   counting duplicate ACKs.
 *
 *       lost_out: Packets lost by network. TCP has no explicit
 *		   "loss notification" feedback from network (for now).
 *		   It means that this number can be only _guessed_.
 *		   Actually, it is the heuristics to predict lossage that
 *		   distinguishes different algorithms.
 *
 *	F.e. after RTO, when all the queue is considered as lost,
 *	lost_out = packets_out and in_flight = retrans_out.
 *
 *		Essentially, we have now two algorithms counting
 *		lost packets.
 *
 *		FACK: It is the simplest heuristics. As soon as we decided
 *		that something is lost, we decide that _all_ not SACKed
 *		packets until the most forward SACK are lost. I.e.
 *		lost_out = fackets_out - sacked_out and left_out = fackets_out.
 *		It is absolutely correct estimate, if network does not reorder
 *		packets. And it loses any connection to reality when reordering
 *		takes place. We use FACK by default until reordering
 *		is suspected on the path to this destination.
 *
 *		NewReno: when Recovery is entered, we assume that one segment
 *		is lost (classic Reno). While we are in Recovery and
 *		a partial ACK arrives, we assume that one more packet
 *		is lost (NewReno). This heuristics are the same in NewReno
 *		and SACK.
 *
 *  Imagine, that's all! Forget about all this shamanism about CWND inflation
 *  deflation etc. CWND is real congestion window, never inflated, changes
 *  only according to classic VJ rules.
 *
 * Really tricky (and requiring careful tuning) part of algorithm
 * is hidden in functions tcp_time_to_recover() and tcp_xmit_retransmit_queue().
 * The first determines the moment _when_ we should reduce CWND and,
 * hence, slow down forward transmission. In fact, it determines the moment
 * when we decide that hole is caused by loss, rather than by a reorder.
 *
 * tcp_xmit_retransmit_queue() decides, _what_ we should retransmit to fill
 * holes, caused by lost packets.
 *
 * And the most logically complicated part of algorithm is undo
 * heuristics. We detect false retransmits due to both too early
 * fast retransmit (reordering) and underestimated RTO, analyzing
 * timestamps and D-SACKs. When we detect that some segments were
 * retransmitted by mistake and CWND reduction was wrong, we undo
 * window reduction and abort recovery phase. This logic is hidden
 * inside several functions named tcp_try_undo_<something>.
 */

/* This function decides, when we should leave Disordered state
 * and enter Recovery phase, reducing congestion window.
 *
 * Main question: may we further continue forward transmission
 * with the same cwnd?
 */
static bool tcp_time_to_recover(struct sock *sk, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);
	__u32 packets_out;

	/* Trick#1: The loss is proven. */
	if (tp->lost_out)
		return true;

	/* Not-A-Trick#2 : Classic rule... */
	if (tcp_dupack_heuristics(tp) > tp->reordering)
		return true;

	/* Trick#4: It is still not OK... But will it be useful to delay
	 * recovery more?
	 */
	packets_out = tp->packets_out;
	if (packets_out <= tp->reordering &&
	    tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
	    !tcp_may_send_now(sk)) {
		/* We have nothing to send. This connection is limited
		 * either by receiver window or by application.
		 */
		return true;
	}

	/* If a thin stream is detected, retransmit after first
	 * received dupack. Employ only if SACK is supported in order
	 * to avoid possible corner-case series of spurious retransmissions
	 * Use only if there are no unsent data.
	 */
	if ((tp->thin_dupack || sysctl_tcp_thin_dupack) &&
	    tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 &&
	    tcp_is_sack(tp) && !tcp_send_head(sk))
		return true;

	/* Trick#6: TCP early retransmit, per RFC5827.  To avoid spurious
	 * retransmissions due to small network reorderings, we implement
	 * Mitigation A.3 in the RFC and delay the retransmission for a short
	 * interval if appropriate.
	 */
	if (tp->do_early_retrans && !tp->retrans_out && tp->sacked_out &&
	    (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) &&
	    !tcp_may_send_now(sk))
		return !tcp_pause_early_retransmit(sk, flag);

	return false;
}

/* Detect loss in event "A" above by marking head of queue up as lost.
 * For FACK or non-SACK(Reno) senders, the first "packets" number of segments
 * are considered lost. For RFC3517 SACK, a segment is considered lost if it
 * has at least tp->reordering SACKed seqments above it; "packets" refers to
 * the maximum SACKed segments to pass before reaching this limit.
 */
static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int cnt, oldcnt;
	int err;
	unsigned int mss;
	/* Use SACK to deduce losses of new sequences sent during recovery */
	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;

	WARN_ON(packets > tp->packets_out);
	if (tp->lost_skb_hint) {
		skb = tp->lost_skb_hint;
		cnt = tp->lost_cnt_hint;
		/* Head already handled? */
		if (mark_head && skb != tcp_write_queue_head(sk))
			return;
	} else {
		skb = tcp_write_queue_head(sk);
		cnt = 0;
	}

	tcp_for_write_queue_from(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		/* TODO: do this better */
		/* this is not the most efficient way to do this... */
		tp->lost_skb_hint = skb;
		tp->lost_cnt_hint = cnt;

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

		oldcnt = cnt;
		if (tcp_is_fack(tp) || tcp_is_reno(tp) ||
		    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
			cnt += tcp_skb_pcount(skb);

		if (cnt > packets) {
			if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) ||
			    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
			    (oldcnt >= packets))
				break;

			mss = skb_shinfo(skb)->gso_size;
			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, mss);
			if (err < 0)
				break;
			cnt = packets;
		}

		tcp_skb_mark_lost(tp, skb);

		if (mark_head)
			break;
	}
	tcp_verify_left_out(tp);
}

/* Account newly detected lost packet(s) */

static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_is_reno(tp)) {
		tcp_mark_head_lost(sk, 1, 1);
	} else if (tcp_is_fack(tp)) {
		int lost = tp->fackets_out - tp->reordering;
		if (lost <= 0)
			lost = 1;
		tcp_mark_head_lost(sk, lost, 0);
	} else {
		int sacked_upto = tp->sacked_out - tp->reordering;
		if (sacked_upto >= 0)
			tcp_mark_head_lost(sk, sacked_upto, 0);
		else if (fast_rexmit)
			tcp_mark_head_lost(sk, 1, 1);
	}
}

/* CWND moderation, preventing bursts due to too big ACKs
 * in dubious situations.
 */
static inline void tcp_moderate_cwnd(struct tcp_sock *tp)
{
	tp->snd_cwnd = min(tp->snd_cwnd,
			   tcp_packets_in_flight(tp) + tcp_max_burst(tp));
	tp->snd_cwnd_stamp = tcp_time_stamp;
}

/* Nothing was retransmitted or returned timestamp is less
 * than timestamp of the first retransmission.
 */
static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
	return !tp->retrans_stamp ||
		(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
		 before(tp->rx_opt.rcv_tsecr, tp->retrans_stamp));
}

/* Undo procedures. */

#if FASTRETRANS_DEBUG > 1
static void DBGUNDO(struct sock *sk, const char *msg)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);

	if (sk->sk_family == AF_INET) {
		pr_debug("Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n",
			 msg,
			 &inet->inet_daddr, ntohs(inet->inet_dport),
			 tp->snd_cwnd, tcp_left_out(tp),
			 tp->snd_ssthresh, tp->prior_ssthresh,
			 tp->packets_out);
	}
#if IS_ENABLED(CONFIG_IPV6)
	else if (sk->sk_family == AF_INET6) {
		struct ipv6_pinfo *np = inet6_sk(sk);
		pr_debug("Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
			 msg,
			 &np->daddr, ntohs(inet->inet_dport),
			 tp->snd_cwnd, tcp_left_out(tp),
			 tp->snd_ssthresh, tp->prior_ssthresh,
			 tp->packets_out);
	}
#endif
}
#else
#define DBGUNDO(x...) do { } while (0)
#endif

static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (unmark_loss) {
		struct sk_buff *skb;

		tcp_for_write_queue(skb, sk) {
			if (skb == tcp_send_head(sk))
				break;
			TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
		}
		tp->lost_out = 0;
		tcp_clear_all_retrans_hints(tp);
	}

	if (tp->prior_ssthresh) {
		const struct inet_connection_sock *icsk = inet_csk(sk);

		if (icsk->icsk_ca_ops->undo_cwnd)
			tp->snd_cwnd = icsk->icsk_ca_ops->undo_cwnd(sk);
		else
			tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);

		if (tp->prior_ssthresh > tp->snd_ssthresh) {
			tp->snd_ssthresh = tp->prior_ssthresh;
			TCP_ECN_withdraw_cwr(tp);
		}
	} else {
		tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
	}
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tp->undo_marker = 0;
}

static inline bool tcp_may_undo(const struct tcp_sock *tp)
{
	return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
}

/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tcp_may_undo(tp)) {
		int mib_idx;

		/* Happy end! We did not retransmit anything
		 * or our original transmission succeeded.
		 */
		DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
		tcp_undo_cwnd_reduction(sk, false);
		if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
			mib_idx = LINUX_MIB_TCPLOSSUNDO;
		else
			mib_idx = LINUX_MIB_TCPFULLUNDO;

		NET_INC_STATS_BH(sock_net(sk), mib_idx);
	}
	if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
		/* Hold old state until something *above* high_seq
		 * is ACKed. For Reno it is MUST to prevent false
		 * fast retransmits (RFC2582). SACK TCP is safe. */
		tcp_moderate_cwnd(tp);
		return true;
	}
	tcp_set_ca_state(sk, TCP_CA_Open);
	return false;
}

/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
static bool tcp_try_undo_dsack(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->undo_marker && !tp->undo_retrans) {
		DBGUNDO(sk, "D-SACK");
		tcp_undo_cwnd_reduction(sk, false);
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
		return true;
	}
	return false;
}

/* We can clear retrans_stamp when there are no retransmissions in the
 * window. It would seem that it is trivially available for us in
 * tp->retrans_out, however, that kind of assumptions doesn't consider
 * what will happen if errors occur when sending retransmission for the
 * second time. ...It could the that such segment has only
 * TCPCB_EVER_RETRANS set at the present time. It seems that checking
 * the head skb is enough except for some reneging corner cases that
 * are not worth the effort.
 *
 * Main reason for all this complexity is the fact that connection dying
 * time now depends on the validity of the retrans_stamp, in particular,
 * that successive retransmissions of a segment must not advance
 * retrans_stamp under any conditions.
 */
static bool tcp_any_retrans_done(const struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;

	if (tp->retrans_out)
		return true;

	skb = tcp_write_queue_head(sk);
	if (unlikely(skb && TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS))
		return true;

	return false;
}

/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (frto_undo || tcp_may_undo(tp)) {
		tcp_undo_cwnd_reduction(sk, true);

		DBGUNDO(sk, "partial loss");
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
		if (frto_undo)
			NET_INC_STATS_BH(sock_net(sk),
					 LINUX_MIB_TCPSPURIOUSRTOS);
		inet_csk(sk)->icsk_retransmits = 0;
		if (frto_undo || tcp_is_sack(tp))
			tcp_set_ca_state(sk, TCP_CA_Open);
		return true;
	}
	return false;
}

/* The cwnd reduction in CWR and Recovery use the PRR algorithm
 * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/
 * It computes the number of packets to send (sndcnt) based on packets newly
 * delivered:
 *   1) If the packets in flight is larger than ssthresh, PRR spreads the
 *	cwnd reductions across a full RTT.
 *   2) If packets in flight is lower than ssthresh (such as due to excess
 *	losses and/or application stalls), do not perform any further cwnd
 *	reductions, but instead slow start up to ssthresh.
 */
static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tp->high_seq = tp->snd_nxt;
	tp->tlp_high_seq = 0;
	tp->snd_cwnd_cnt = 0;
	tp->prior_cwnd = tp->snd_cwnd;
	tp->prr_delivered = 0;
	tp->prr_out = 0;
	if (set_ssthresh)
		tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk);
	TCP_ECN_queue_cwr(tp);
}

static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
			       int fast_rexmit)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int sndcnt = 0;
	int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
	int newly_acked_sacked = prior_unsacked -
				 (tp->packets_out - tp->sacked_out);

	tp->prr_delivered += newly_acked_sacked;
	if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) {
		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
			       tp->prior_cwnd - 1;
		sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
	} else {
		sndcnt = min_t(int, delta,
			       max_t(int, tp->prr_delivered - tp->prr_out,
				     newly_acked_sacked) + 1);
	}

	sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0));
	tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt;
}

static inline void tcp_end_cwnd_reduction(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
	if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR ||
	    (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) {
		tp->snd_cwnd = tp->snd_ssthresh;
		tp->snd_cwnd_stamp = tcp_time_stamp;
	}
	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}

/* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */
void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tp->prior_ssthresh = 0;
	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
		tp->undo_marker = 0;
		tcp_init_cwnd_reduction(sk, set_ssthresh);
		tcp_set_ca_state(sk, TCP_CA_CWR);
	}
}

static void tcp_try_keep_open(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int state = TCP_CA_Open;

	if (tcp_left_out(tp) || tcp_any_retrans_done(sk))
		state = TCP_CA_Disorder;

	if (inet_csk(sk)->icsk_ca_state != state) {
		tcp_set_ca_state(sk, state);
		tp->high_seq = tp->snd_nxt;
	}
}

static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_verify_left_out(tp);

	if (!tcp_any_retrans_done(sk))
		tp->retrans_stamp = 0;

	if (flag & FLAG_ECE)
		tcp_enter_cwr(sk, 1);

	if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
		tcp_try_keep_open(sk);
	} else {
		tcp_cwnd_reduction(sk, prior_unsacked, 0);
	}
}

static void tcp_mtup_probe_failed(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1;
	icsk->icsk_mtup.probe_size = 0;
}

static void tcp_mtup_probe_success(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	/* FIXME: breaks with very large cwnd */
	tp->prior_ssthresh = tcp_current_ssthresh(sk);
	tp->snd_cwnd = tp->snd_cwnd *
		       tcp_mss_to_mtu(sk, tp->mss_cache) /
		       icsk->icsk_mtup.probe_size;
	tp->snd_cwnd_cnt = 0;
	tp->snd_cwnd_stamp = tcp_time_stamp;
	tp->snd_ssthresh = tcp_current_ssthresh(sk);

	icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size;
	icsk->icsk_mtup.probe_size = 0;
	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
}

/* Do a simple retransmit without using the backoff mechanisms in
 * tcp_timer. This is used for path mtu discovery.
 * The socket is already locked here.
 */
void tcp_simple_retransmit(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int mss = tcp_current_mss(sk);
	u32 prior_lost = tp->lost_out;

	tcp_for_write_queue(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		if (tcp_skb_seglen(skb) > mss &&
		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);
			}
			tcp_skb_mark_lost_uncond_verify(tp, skb);
		}
	}

	tcp_clear_retrans_hints_partial(tp);

	if (prior_lost == tp->lost_out)
		return;

	if (tcp_is_reno(tp))
		tcp_limit_reno_sacked(tp);

	tcp_verify_left_out(tp);

	/* Don't muck with the congestion window here.
	 * Reason is that we do not increase amount of _data_
	 * in network, but units changed and effective
	 * cwnd/ssthresh really reduced now.
	 */
	if (icsk->icsk_ca_state != TCP_CA_Loss) {
		tp->high_seq = tp->snd_nxt;
		tp->snd_ssthresh = tcp_current_ssthresh(sk);
		tp->prior_ssthresh = 0;
		tp->undo_marker = 0;
		tcp_set_ca_state(sk, TCP_CA_Loss);
	}
	tcp_xmit_retransmit_queue(sk);
}
EXPORT_SYMBOL(tcp_simple_retransmit);

static void tcp_enter_recovery(struct sock *sk, bool ece_ack)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int mib_idx;

	if (tcp_is_reno(tp))
		mib_idx = LINUX_MIB_TCPRENORECOVERY;
	else
		mib_idx = LINUX_MIB_TCPSACKRECOVERY;

	NET_INC_STATS_BH(sock_net(sk), mib_idx);

	tp->prior_ssthresh = 0;
	tp->undo_marker = tp->snd_una;
	tp->undo_retrans = tp->retrans_out;

	if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
		if (!ece_ack)
			tp->prior_ssthresh = tcp_current_ssthresh(sk);
		tcp_init_cwnd_reduction(sk, true);
	}
	tcp_set_ca_state(sk, TCP_CA_Recovery);
}

/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
 * recovered or spurious. Otherwise retransmits more on partial ACKs.
 */
static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	bool recovered = !before(tp->snd_una, tp->high_seq);

	if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */
		if (flag & FLAG_ORIG_SACK_ACKED) {
			/* Step 3.b. A timeout is spurious if not all data are
			 * lost, i.e., never-retransmitted data are (s)acked.
			 */
			tcp_try_undo_loss(sk, true);
			return;
		}
		if (after(tp->snd_nxt, tp->high_seq) &&
		    (flag & FLAG_DATA_SACKED || is_dupack)) {
			tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
		} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
			tp->high_seq = tp->snd_nxt;
			__tcp_push_pending_frames(sk, tcp_current_mss(sk),
						  TCP_NAGLE_OFF);
			if (after(tp->snd_nxt, tp->high_seq))
				return; /* Step 2.b */
			tp->frto = 0;
		}
	}

	if (recovered) {
		/* F-RTO RFC5682 sec 3.1 step 2.a and 1st part of step 3.a */
		icsk->icsk_retransmits = 0;
		tcp_try_undo_recovery(sk);
		return;
	}
	if (flag & FLAG_DATA_ACKED)
		icsk->icsk_retransmits = 0;
	if (tcp_is_reno(tp)) {
		/* A Reno DUPACK means new data in F-RTO step 2.b above are
		 * delivered. Lower inflight to clock out (re)tranmissions.
		 */
		if (after(tp->snd_nxt, tp->high_seq) && is_dupack)
			tcp_add_reno_sack(sk);
		else if (flag & FLAG_SND_UNA_ADVANCED)
			tcp_reset_reno_sack(tp);
	}
	if (tcp_try_undo_loss(sk, false))
		return;
	tcp_xmit_retransmit_queue(sk);
}

/* Undo during fast recovery after partial ACK. */
static bool tcp_try_undo_partial(struct sock *sk, const int acked,
				 const int prior_unsacked)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (tp->undo_marker && tcp_packet_delayed(tp)) {
		/* Plain luck! Hole if filled with delayed
		 * packet, rather than with a retransmit.
		 */
		tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);

		/* We are getting evidence that the reordering degree is higher
		 * than we realized. If there are no retransmits out then we
		 * can undo. Otherwise we clock out new packets but do not
		 * mark more packets lost or retransmit more.
		 */
		if (tp->retrans_out) {
			tcp_cwnd_reduction(sk, prior_unsacked, 0);
			return true;
		}

		if (!tcp_any_retrans_done(sk))
			tp->retrans_stamp = 0;

		DBGUNDO(sk, "partial recovery");
		tcp_undo_cwnd_reduction(sk, true);
		NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
		tcp_try_keep_open(sk);
		return true;
	}
	return false;
}

/* Process an event, which can update packets-in-flight not trivially.
 * Main goal of this function is to calculate new estimate for left_out,
 * taking into account both packets sitting in receiver's buffer and
 * packets lost by network.
 *
 * Besides that it does CWND reduction, when packet loss is detected
 * and changes state of machine.
 *
 * It does _not_ decide what to send, it is made in function
 * tcp_xmit_retransmit_queue().
 */
static void tcp_fastretrans_alert(struct sock *sk, const int acked,
				  const int prior_unsacked,
				  bool is_dupack, int flag)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
				    (tcp_fackets_out(tp) > tp->reordering));
	int fast_rexmit = 0;

	if (WARN_ON(!tp->packets_out && tp->sacked_out))
		tp->sacked_out = 0;
	if (WARN_ON(!tp->sacked_out && tp->fackets_out))
		tp->fackets_out = 0;

	/* Now state machine starts.
	 * A. ECE, hence prohibit cwnd undoing, the reduction is required. */
	if (flag & FLAG_ECE)
		tp->prior_ssthresh = 0;

	/* B. In all the states check for reneging SACKs. */
	if (tcp_check_sack_reneging(sk, flag))
		return;

	/* C. Check consistency of the current state. */
	tcp_verify_left_out(tp);

	/* D. Check state exit conditions. State can be terminated
	 *    when high_seq is ACKed. */
	if (icsk->icsk_ca_state == TCP_CA_Open) {
		WARN_ON(tp->retrans_out != 0);
		tp->retrans_stamp = 0;
	} else if (!before(tp->snd_una, tp->high_seq)) {
		switch (icsk->icsk_ca_state) {
		case TCP_CA_CWR:
			/* CWR is to be held something *above* high_seq
			 * is ACKed for CWR bit to reach receiver. */
			if (tp->snd_una != tp->high_seq) {
				tcp_end_cwnd_reduction(sk);
				tcp_set_ca_state(sk, TCP_CA_Open);
			}
			break;

		case TCP_CA_Recovery:
			if (tcp_is_reno(tp))
				tcp_reset_reno_sack(tp);
			if (tcp_try_undo_recovery(sk))
				return;
			tcp_end_cwnd_reduction(sk);
			break;
		}
	}

	/* E. Process state. */
	switch (icsk->icsk_ca_state) {
	case TCP_CA_Recovery:
		if (!(flag & FLAG_SND_UNA_ADVANCED)) {
			if (tcp_is_reno(tp) && is_dupack)
				tcp_add_reno_sack(sk);
		} else {
			if (tcp_try_undo_partial(sk, acked, prior_unsacked))
				return;
			/* Partial ACK arrived. Force fast retransmit. */
			do_lost = tcp_is_reno(tp) ||
				  tcp_fackets_out(tp) > tp->reordering;
		}
		if (tcp_try_undo_dsack(sk)) {
			tcp_try_keep_open(sk);
			return;
		}
		break;
	case TCP_CA_Loss:
		tcp_process_loss(sk, flag, is_dupack);
		if (icsk->icsk_ca_state != TCP_CA_Open)
			return;
		/* Fall through to processing in Open state. */
	default:
		if (tcp_is_reno(tp)) {
			if (flag & FLAG_SND_UNA_ADVANCED)
				tcp_reset_reno_sack(tp);
			if (is_dupack)
				tcp_add_reno_sack(sk);
		}

		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
			tcp_try_undo_dsack(sk);

		if (!tcp_time_to_recover(sk, flag)) {
			tcp_try_to_open(sk, flag, prior_unsacked);
			return;
		}

		/* MTU probe failure: don't reduce cwnd */
		if (icsk->icsk_ca_state < TCP_CA_CWR &&
		    icsk->icsk_mtup.probe_size &&
		    tp->snd_una == tp->mtu_probe.probe_seq_start) {
			tcp_mtup_probe_failed(sk);
			/* Restores the reduction we did in tcp_mtup_probe() */
			tp->snd_cwnd++;
			tcp_simple_retransmit(sk);
			return;
		}

		/* Otherwise enter Recovery state */
		tcp_enter_recovery(sk, (flag & FLAG_ECE));
		fast_rexmit = 1;
	}

	if (do_lost)
		tcp_update_scoreboard(sk, fast_rexmit);
	tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit);
	tcp_xmit_retransmit_queue(sk);
}

static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
				      s32 seq_rtt, s32 sack_rtt)
{
	const struct tcp_sock *tp = tcp_sk(sk);

	/* Prefer RTT measured from ACK's timing to TS-ECR. This is because
	 * broken middle-boxes or peers may corrupt TS-ECR fields. But
	 * Karn's algorithm forbids taking RTT if some retransmitted data
	 * is acked (RFC6298).
	 */
	if (flag & FLAG_RETRANS_DATA_ACKED)
		seq_rtt = -1;

	if (seq_rtt < 0)
		seq_rtt = sack_rtt;

	/* RTTM Rule: A TSecr value received in a segment is used to
	 * update the averaged RTT measurement only if the segment
	 * acknowledges some new data, i.e., only if it advances the
	 * left edge of the send window.
	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
	 */
	if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
		seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;

	if (seq_rtt < 0)
		return false;

	tcp_rtt_estimator(sk, seq_rtt);
	tcp_set_rto(sk);

	/* RFC6298: only reset backoff on valid RTT measurement. */
	inet_csk(sk)->icsk_backoff = 0;
	return true;
}

/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
{
	struct tcp_sock *tp = tcp_sk(sk);
	s32 seq_rtt = -1;

	if (tp->lsndtime && !tp->total_retrans)
		seq_rtt = tcp_time_stamp - tp->lsndtime;
	tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
}

static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight);
	tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}

/* Restart timer after forward progress on connection.
 * RFC2988 recommends to restart timer to now+rto.
 */
void tcp_rearm_rto(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	/* If the retrans timer is currently being used by Fast Open
	 * for SYN-ACK retrans purpose, stay put.
	 */
	if (tp->fastopen_rsk)
		return;

	if (!tp->packets_out) {
		inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
	} else {
		u32 rto = inet_csk(sk)->icsk_rto;
		/* Offset the time elapsed after installing regular RTO */
		if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
		    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
			struct sk_buff *skb = tcp_write_queue_head(sk);
			const u32 rto_time_stamp = TCP_SKB_CB(skb)->when + rto;
			s32 delta = (s32)(rto_time_stamp - tcp_time_stamp);
			/* delta may not be positive if the socket is locked
			 * when the retrans timer fires and is rescheduled.
			 */
			if (delta > 0)
				rto = delta;
		}
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
					  TCP_RTO_MAX);
	}
}

/* This function is called when the delayed ER timer fires. TCP enters
 * fast recovery and performs fast-retransmit.
 */
void tcp_resume_early_retransmit(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_rearm_rto(sk);

	/* Stop if ER is disabled after the delayed ER timer is scheduled */
	if (!tp->do_early_retrans)
		return;

	tcp_enter_recovery(sk, false);
	tcp_update_scoreboard(sk, 1);
	tcp_xmit_retransmit_queue(sk);
}

/* If we get here, the whole TSO packet has not been acked. */
static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 packets_acked;

	BUG_ON(!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una));

	packets_acked = tcp_skb_pcount(skb);
	if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
		return 0;
	packets_acked -= tcp_skb_pcount(skb);

	if (packets_acked) {
		BUG_ON(tcp_skb_pcount(skb) == 0);
		BUG_ON(!before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq));
	}

	return packets_acked;
}

/* Remove acknowledged frames from the retransmission queue. If our packet
 * is before the ack sequence we can discard it as it's confirmed to have
 * arrived at the other end.
 */
static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
			       u32 prior_snd_una, s32 sack_rtt)
{
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct sk_buff *skb;
	u32 now = tcp_time_stamp;
	int fully_acked = true;
	int flag = 0;
	u32 pkts_acked = 0;
	u32 reord = tp->packets_out;
	u32 prior_sacked = tp->sacked_out;
	s32 seq_rtt = -1;
	s32 ca_seq_rtt = -1;
	ktime_t last_ackt = net_invalid_timestamp();

	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
		u32 acked_pcount;
		u8 sacked = scb->sacked;

		/* Determine how many packets and what bytes were acked, tso and else */
		if (after(scb->end_seq, tp->snd_una)) {
			if (tcp_skb_pcount(skb) == 1 ||
			    !after(tp->snd_una, scb->seq))
				break;

			acked_pcount = tcp_tso_acked(sk, skb);
			if (!acked_pcount)
				break;

			fully_acked = false;
		} else {
			acked_pcount = tcp_skb_pcount(skb);
		}