diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index dc2dc87d2557b4fdf7537b9e8f4185965c3dd1ce..1cae6c383e1b781cc6a6e2b424d973ccecb811e6 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -190,7 +190,9 @@ tcp_early_retrans - INTEGER
 	Enable Early Retransmit (ER), per RFC 5827. ER lowers the threshold
 	for triggering fast retransmit when the amount of outstanding data is
 	small and when no previously unsent data can be transmitted (such
-	that limited transmit could be used).
+	that limited transmit could be used). Also controls the use of
+	Tail loss probe (TLP) that converts RTOs occuring due to tail
+	losses into fast recovery (draft-dukkipati-tcpm-tcp-loss-probe-01).
 	Possible values:
 		0 disables ER
 		1 enables ER
@@ -198,7 +200,9 @@ tcp_early_retrans - INTEGER
 		  by a fourth of RTT. This mitigates connection falsely
 		  recovers when network has a small degree of reordering
 		  (less than 3 packets).
-	Default: 2
+		3 enables delayed ER and TLP.
+		4 enables TLP only.
+	Default: 3
 
 tcp_ecn - INTEGER
 	Control use of Explicit Congestion Notification (ECN) by TCP.
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 515c3746b6754b8a5e1b0baa125264fdfbe3e583..01860d74555cfe747e3e00baf9e70f4e2bd1739f 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -201,7 +201,6 @@ struct tcp_sock {
 		unused      : 1;
 	u8	repair_queue;
 	u8	do_early_retrans:1,/* Enable RFC5827 early-retransmit  */
-		early_retrans_delayed:1, /* Delayed ER timer installed */
 		syn_data:1,	/* SYN includes data */
 		syn_fastopen:1,	/* SYN includes Fast Open option */
 		syn_data_acked:1;/* data in SYN is acked by SYN-ACK */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 183292722f6e587eee72bf3ff5c201dfe25afbaf..de2c78529afaf81f00abff62bb29708f7f6941a2 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -133,6 +133,8 @@ struct inet_connection_sock {
 #define ICSK_TIME_RETRANS	1	/* Retransmit timer */
 #define ICSK_TIME_DACK		2	/* Delayed ack timer */
 #define ICSK_TIME_PROBE0	3	/* Zero window probe timer */
+#define ICSK_TIME_EARLY_RETRANS 4	/* Early retransmit timer */
+#define ICSK_TIME_LOSS_PROBE	5	/* Tail loss probe timer */
 
 static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
 {
@@ -222,7 +224,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 		when = max_when;
 	}
 
-	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
+	if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
+	    what == ICSK_TIME_EARLY_RETRANS || what ==  ICSK_TIME_LOSS_PROBE) {
 		icsk->icsk_pending = what;
 		icsk->icsk_timeout = jiffies + when;
 		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a2baa5e4ba3159fa87760800a219538eb19a54e0..ab9f947b118bf85ef0bbb6d87616fd2e830222ca 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -543,6 +543,8 @@ extern bool tcp_syn_flood_action(struct sock *sk,
 extern void tcp_push_one(struct sock *, unsigned int mss_now);
 extern void tcp_send_ack(struct sock *sk);
 extern void tcp_send_delayed_ack(struct sock *sk);
+extern void tcp_send_loss_probe(struct sock *sk);
+extern bool tcp_schedule_loss_probe(struct sock *sk);
 
 /* tcp_input.c */
 extern void tcp_cwnd_application_limited(struct sock *sk);
@@ -873,8 +875,8 @@ static inline void tcp_enable_fack(struct tcp_sock *tp)
 static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
 {
 	tp->do_early_retrans = sysctl_tcp_early_retrans &&
-		!sysctl_tcp_thin_dupack && sysctl_tcp_reordering == 3;
-	tp->early_retrans_delayed = 0;
+		sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
+		sysctl_tcp_reordering == 3;
 }
 
 static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index b49eab89c9fd4461c155ec1b60083aeab1234e44..290bed6b085f149c2dea0af92f8f991f7cd32b1a 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -202,6 +202,7 @@ enum
 	LINUX_MIB_TCPFORWARDRETRANS,		/* TCPForwardRetrans */
 	LINUX_MIB_TCPSLOWSTARTRETRANS,		/* TCPSlowStartRetrans */
 	LINUX_MIB_TCPTIMEOUTS,			/* TCPTimeouts */
+	LINUX_MIB_TCPLOSSPROBES,		/* TCPLossProbes */
 	LINUX_MIB_TCPRENORECOVERYFAIL,		/* TCPRenoRecoveryFail */
 	LINUX_MIB_TCPSACKRECOVERYFAIL,		/* TCPSackRecoveryFail */
 	LINUX_MIB_TCPSCHEDULERFAILED,		/* TCPSchedulerFailed */
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7afa2c3c788f184457e45899a7065a9786d26df7..8620408af5744cc785c01fad9c6bb0f1f4870c8c 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -158,7 +158,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 #define EXPIRES_IN_MS(tmo)  DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		r->idiag_timer = 1;
 		r->idiag_retrans = icsk->icsk_retransmits;
 		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 32030a24e77624c2df45b87d9ae759a9ed8de454..4c35911d935fc6c3aee485a4033f3895acd3580e 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -224,6 +224,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPForwardRetrans", LINUX_MIB_TCPFORWARDRETRANS),
 	SNMP_MIB_ITEM("TCPSlowStartRetrans", LINUX_MIB_TCPSLOWSTARTRETRANS),
 	SNMP_MIB_ITEM("TCPTimeouts", LINUX_MIB_TCPTIMEOUTS),
+	SNMP_MIB_ITEM("TCPLossProbes", LINUX_MIB_TCPLOSSPROBES),
 	SNMP_MIB_ITEM("TCPRenoRecoveryFail", LINUX_MIB_TCPRENORECOVERYFAIL),
 	SNMP_MIB_ITEM("TCPSackRecoveryFail", LINUX_MIB_TCPSACKRECOVERYFAIL),
 	SNMP_MIB_ITEM("TCPSchedulerFailed", LINUX_MIB_TCPSCHEDULERFAILED),
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 960fd29d9b8e067e12f89a6dfdcb3fa7873ea468..cca4550f4082fddc005a77c129ae89bfd8f69955 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -28,7 +28,7 @@
 
 static int zero;
 static int one = 1;
-static int two = 2;
+static int four = 4;
 static int tcp_retr1_max = 255;
 static int ip_local_port_range_min[] = { 1, 1 };
 static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -760,7 +760,7 @@ static struct ctl_table ipv4_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
-		.extra2		= &two,
+		.extra2		= &four,
 	},
 	{
 		.procname	= "udp_mem",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0d9bdacce99f46a77982d89c86a7764fe9ef15f8..b794f89ac1f2ec5824fcee4dc5d0f3fb474e354e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -98,7 +98,7 @@ int sysctl_tcp_frto_response __read_mostly;
 int sysctl_tcp_thin_dupack __read_mostly;
 
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_early_retrans __read_mostly = 2;
+int sysctl_tcp_early_retrans __read_mostly = 3;
 
 #define FLAG_DATA		0x01 /* Incoming frame contained data.		*/
 #define FLAG_WIN_UPDATE		0x02 /* Incoming ACK was a window update.	*/
@@ -2150,15 +2150,16 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
 	 * max(RTT/4, 2msec) unless ack has ECE mark, no RTT samples
 	 * available, or RTO is scheduled to fire first.
 	 */
-	if (sysctl_tcp_early_retrans < 2 || (flag & FLAG_ECE) || !tp->srtt)
+	if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
+	    (flag & FLAG_ECE) || !tp->srtt)
 		return false;
 
 	delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2));
 	if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
 		return false;
 
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX);
-	tp->early_retrans_delayed = 1;
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_EARLY_RETRANS, delay,
+				  TCP_RTO_MAX);
 	return true;
 }
 
@@ -2321,7 +2322,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 	 * 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) &&
+	    (tp->packets_out >= (tp->sacked_out + 1) && tp->packets_out < 4) &&
 	    !tcp_may_send_now(sk))
 		return !tcp_pause_early_retransmit(sk, flag);
 
@@ -3081,6 +3082,7 @@ static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
  */
 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
@@ -3094,12 +3096,13 @@ void tcp_rearm_rto(struct sock *sk)
 	} else {
 		u32 rto = inet_csk(sk)->icsk_rto;
 		/* Offset the time elapsed after installing regular RTO */
-		if (tp->early_retrans_delayed) {
+		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 delayed ER timer fires and is rescheduled.
+			 * when the retrans timer fires and is rescheduled.
 			 */
 			if (delta > 0)
 				rto = delta;
@@ -3107,7 +3110,6 @@ void tcp_rearm_rto(struct sock *sk)
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
 					  TCP_RTO_MAX);
 	}
-	tp->early_retrans_delayed = 0;
 }
 
 /* This function is called when the delayed ER timer fires. TCP enters
@@ -3601,7 +3603,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	if (after(ack, tp->snd_nxt))
 		goto invalid_ack;
 
-	if (tp->early_retrans_delayed)
+	if (icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 
 	if (after(ack, prior_snd_una))
@@ -3678,6 +3681,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		if (dst)
 			dst_confirm(dst);
 	}
+
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
+		tcp_schedule_loss_probe(sk);
 	return 1;
 
 no_queue:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8cdee120a50c5729cd1898eb09caf256efb41d4d..b7ab868c8284ff202d2dc228e7ffe9682ed3cc0c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2703,7 +2703,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
 	__u16 srcp = ntohs(inet->inet_sport);
 	int rx_queue;
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
+	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e2b4461074dab715af9c328fd1767f4a5caf8c97..beb63dbc85f53284ed3e66141ed9675ac3551922 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -74,6 +74,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 /* Account for new data that has been sent to the network. */
 static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 {
+	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
@@ -85,7 +86,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 		tp->frto_counter = 3;
 
 	tp->packets_out += tcp_skb_pcount(skb);
-	if (!prior_packets || tp->early_retrans_delayed)
+	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
+	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
 }
 
@@ -1959,6 +1961,9 @@ static int tcp_mtu_probe(struct sock *sk)
  * snd_up-64k-mss .. snd_up cannot be large. However, taking into
  * account rare use of URG, this is not a big flaw.
  *
+ * Send at most one packet when push_one > 0. Temporarily ignore
+ * cwnd limit to force at most one packet out when push_one == 2.
+
  * Returns true, if no segments are in flight and we have queued segments,
  * but cannot send anything now because of SWS or another problem.
  */
@@ -1994,8 +1999,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 			goto repair; /* Skip network transmission */
 
 		cwnd_quota = tcp_cwnd_test(tp, skb);
-		if (!cwnd_quota)
-			break;
+		if (!cwnd_quota) {
+			if (push_one == 2)
+				/* Force out a loss probe pkt. */
+				cwnd_quota = 1;
+			else
+				break;
+		}
 
 		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
 			break;
@@ -2049,10 +2059,120 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
 	if (likely(sent_pkts)) {
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += sent_pkts;
+
+		/* Send one loss probe per tail loss episode. */
+		if (push_one != 2)
+			tcp_schedule_loss_probe(sk);
 		tcp_cwnd_validate(sk);
 		return false;
 	}
-	return !tp->packets_out && tcp_send_head(sk);
+	return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk));
+}
+
+bool tcp_schedule_loss_probe(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 timeout, tlp_time_stamp, rto_time_stamp;
+	u32 rtt = tp->srtt >> 3;
+
+	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
+		return false;
+	/* No consecutive loss probes. */
+	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
+		tcp_rearm_rto(sk);
+		return false;
+	}
+	/* Don't do any loss probe on a Fast Open connection before 3WHS
+	 * finishes.
+	 */
+	if (sk->sk_state == TCP_SYN_RECV)
+		return false;
+
+	/* TLP is only scheduled when next timer event is RTO. */
+	if (icsk->icsk_pending != ICSK_TIME_RETRANS)
+		return false;
+
+	/* Schedule a loss probe in 2*RTT for SACK capable connections
+	 * in Open state, that are either limited by cwnd or application.
+	 */
+	if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out ||
+	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+		return false;
+
+	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
+	     tcp_send_head(sk))
+		return false;
+
+	/* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account
+	 * for delayed ack when there's one outstanding packet.
+	 */
+	timeout = rtt << 1;
+	if (tp->packets_out == 1)
+		timeout = max_t(u32, timeout,
+				(rtt + (rtt >> 1) + TCP_DELACK_MAX));
+	timeout = max_t(u32, timeout, msecs_to_jiffies(10));
+
+	/* If RTO is shorter, just schedule TLP in its place. */
+	tlp_time_stamp = tcp_time_stamp + timeout;
+	rto_time_stamp = (u32)inet_csk(sk)->icsk_timeout;
+	if ((s32)(tlp_time_stamp - rto_time_stamp) > 0) {
+		s32 delta = rto_time_stamp - tcp_time_stamp;
+		if (delta > 0)
+			timeout = delta;
+	}
+
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
+				  TCP_RTO_MAX);
+	return true;
+}
+
+/* When probe timeout (PTO) fires, send a new segment if one exists, else
+ * retransmit the last segment.
+ */
+void tcp_send_loss_probe(struct sock *sk)
+{
+	struct sk_buff *skb;
+	int pcount;
+	int mss = tcp_current_mss(sk);
+	int err = -1;
+
+	if (tcp_send_head(sk) != NULL) {
+		err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC);
+		goto rearm_timer;
+	}
+
+	/* Retransmit last segment. */
+	skb = tcp_write_queue_tail(sk);
+	if (WARN_ON(!skb))
+		goto rearm_timer;
+
+	pcount = tcp_skb_pcount(skb);
+	if (WARN_ON(!pcount))
+		goto rearm_timer;
+
+	if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) {
+		if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss)))
+			goto rearm_timer;
+		skb = tcp_write_queue_tail(sk);
+	}
+
+	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
+		goto rearm_timer;
+
+	/* Probe with zero data doesn't trigger fast recovery. */
+	if (skb->len > 0)
+		err = __tcp_retransmit_skb(sk, skb);
+
+rearm_timer:
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+				  inet_csk(sk)->icsk_rto,
+				  TCP_RTO_MAX);
+
+	if (likely(!err))
+		NET_INC_STATS_BH(sock_net(sk),
+				 LINUX_MIB_TCPLOSSPROBES);
+	return;
 }
 
 /* Push out any pending frames which were held back due to
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b78aac30c4986dc78fcd8dae03a527326baa32a3..ecd61d54147f1cf1f665b5f8ded32691e40de60f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -342,10 +342,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (tp->early_retrans_delayed) {
-		tcp_resume_early_retransmit(sk);
-		return;
-	}
 	if (tp->fastopen_rsk) {
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 			     sk->sk_state != TCP_FIN_WAIT1);
@@ -495,13 +491,20 @@ void tcp_write_timer_handler(struct sock *sk)
 	}
 
 	event = icsk->icsk_pending;
-	icsk->icsk_pending = 0;
 
 	switch (event) {
+	case ICSK_TIME_EARLY_RETRANS:
+		tcp_resume_early_retransmit(sk);
+		break;
+	case ICSK_TIME_LOSS_PROBE:
+		tcp_send_loss_probe(sk);
+		break;
 	case ICSK_TIME_RETRANS:
+		icsk->icsk_pending = 0;
 		tcp_retransmit_timer(sk);
 		break;
 	case ICSK_TIME_PROBE0:
+		icsk->icsk_pending = 0;
 		tcp_probe_timer(sk);
 		break;
 	}