1 files changed, 158 insertions, 20 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8ac08557321..8e7742f0b5d 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);
 }
 
@@ -314,7 +316,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->ecn_flags = 0;
-	if (sysctl_tcp_ecn == 1) {
+	if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
 		tp->ecn_flags = TCP_ECN_OK;
 	}
@@ -622,7 +624,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 
 	if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = TCP_SKB_CB(skb)->when;
+		opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -806,7 +808,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 
 	if (likely(tp->rx_opt.tstamp_ok)) {
 		opts->options |= OPTION_TS;
-		opts->tsval = tcb ? tcb->when : 0;
+		opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
 		opts->tsecr = tp->rx_opt.ts_recent;
 		size += TCPOLEN_TSTAMP_ALIGNED;
 	}
@@ -1331,7 +1333,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 /* Remove acked data from a packet in the transmit queue. */
 int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 {
-	if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
 	__pskb_trim_head(skb, len);
@@ -1351,8 +1353,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	return 0;
 }
 
-/* Calculate MSS. Not accounting for SACKs here.  */
-int tcp_mtu_to_mss(struct sock *sk, int pmtu)
+/* Calculate MSS not accounting any TCP options.  */
+static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1381,13 +1383,17 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
 	if (mss_now < 48)
 		mss_now = 48;
-
-	/* Now subtract TCP options size, not including SACKs */
-	mss_now -= tp->tcp_header_len - sizeof(struct tcphdr);
-
 	return mss_now;
 }
 
+/* Calculate MSS. Not accounting for SACKs here.  */
+int tcp_mtu_to_mss(struct sock *sk, int pmtu)
+{
+	/* Subtract TCP options size, not including SACKs */
+	return __tcp_mtu_to_mss(sk, pmtu) -
+	       (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
+}
+
 /* Inverse of above */
 int tcp_mss_to_mtu(struct sock *sk, int mss)
 {
@@ -1955,6 +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.
  */
@@ -1990,8 +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;
@@ -2045,10 +2059,129 @@ repair:
 	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 tcp_sock *tp = tcp_sk(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;
+	}
+
+	/* At most one outstanding TLP retransmission. */
+	if (tp->tlp_high_seq)
+		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);
+
+	/* Record snd_nxt for loss detection. */
+	if (likely(!err))
+		tp->tlp_high_seq = tp->snd_nxt;
+
+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
@@ -2309,12 +2442,11 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
  * state updates are done by the caller.  Returns non-zero if an
  * error occurred which prevented the send.
  */
-int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned int cur_mss;
-	int err;
 
 	/* Inconslusive MTU probe */
 	if (icsk->icsk_mtup.probe_size) {
@@ -2387,11 +2519,17 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
 		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
 						   GFP_ATOMIC);
-		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-			     -ENOBUFS;
+		return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			      -ENOBUFS;
 	} else {
-		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+		return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
+}
+
+int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	int err = __tcp_retransmit_skb(sk, skb);
 
 	if (err == 0) {
 		/* Update global TCP statistics. */
@@ -2925,7 +3063,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
 	 */
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
 		tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
-	space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+	space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
 		MAX_TCP_OPTION_SPACE;
 
 	syn_data = skb_copy_expand(syn, skb_headroom(syn), space,