1 files changed, 38 insertions, 51 deletions

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index f87dbc78b6bc..f0c86398e6a7 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,28 +22,14 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-static u32 tcp_retransmit_stamp(const struct sock *sk)
-{
-	u32 start_ts = tcp_sk(sk)->retrans_stamp;
-
-	if (unlikely(!start_ts)) {
-		struct sk_buff *head = tcp_rtx_queue_head(sk);
-
-		if (!head)
-			return 0;
-		start_ts = tcp_skb_timestamp(head);
-	}
-	return start_ts;
-}
-
 static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 elapsed, start_ts;
 	s32 remaining;
 
-	start_ts = tcp_retransmit_stamp(sk);
-	if (!icsk->icsk_user_timeout || !start_ts)
+	start_ts = tcp_sk(sk)->retrans_stamp;
+	if (!icsk->icsk_user_timeout)
 		return icsk->icsk_rto;
 	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
 	remaining = icsk->icsk_user_timeout - elapsed;
@@ -173,7 +159,20 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
 }
 
-
+static unsigned int tcp_model_timeout(struct sock *sk,
+				      unsigned int boundary,
+				      unsigned int rto_base)
+{
+	unsigned int linear_backoff_thresh, timeout;
+
+	linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base);
+	if (boundary <= linear_backoff_thresh)
+		timeout = ((2 << boundary) - 1) * rto_base;
+	else
+		timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
+			(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+	return jiffies_to_msecs(timeout);
+}
 /**
  *  retransmits_timed_out() - returns true if this connection has timed out
  *  @sk:       The current socket
@@ -191,26 +190,15 @@ static bool retransmits_timed_out(struct sock *sk,
 				  unsigned int boundary,
 				  unsigned int timeout)
 {
-	const unsigned int rto_base = TCP_RTO_MIN;
-	unsigned int linear_backoff_thresh, start_ts;
+	unsigned int start_ts;
 
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
-	start_ts = tcp_retransmit_stamp(sk);
-	if (!start_ts)
-		return false;
-
-	if (likely(timeout == 0)) {
-		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
+	start_ts = tcp_sk(sk)->retrans_stamp;
+	if (likely(timeout == 0))
+		timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN);
 
-		if (boundary <= linear_backoff_thresh)
-			timeout = ((2 << boundary) - 1) * rto_base;
-		else
-			timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
-				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
-		timeout = jiffies_to_msecs(timeout);
-	}
 	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
 
@@ -226,7 +214,7 @@ static int tcp_write_timeout(struct sock *sk)
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits) {
 			dst_negative_advice(sk);
-		} else if (!tp->syn_data && !tp->syn_fastopen) {
+		} else {
 			sk_rethink_txhash(sk);
 		}
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
@@ -289,14 +277,14 @@ void tcp_delack_timer_handler(struct sock *sk)
 	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;
 
 	if (inet_csk_ack_scheduled(sk)) {
-		if (!icsk->icsk_ack.pingpong) {
+		if (!inet_csk_in_pingpong_mode(sk)) {
 			/* Delayed ACK missed: inflate ATO. */
 			icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto);
 		} else {
 			/* Delayed ACK missed: leave pingpong mode and
 			 * deflate ATO.
 			 */
-			icsk->icsk_ack.pingpong = 0;
+			inet_csk_exit_pingpong_mode(sk);
 			icsk->icsk_ack.ato      = TCP_ATO_MIN;
 		}
 		tcp_mstamp_refresh(tcp_sk(sk));
@@ -345,7 +333,6 @@ static void tcp_probe_timer(struct sock *sk)
 	struct sk_buff *skb = tcp_send_head(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int max_probes;
-	u32 start_ts;
 
 	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
@@ -360,12 +347,13 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	start_ts = tcp_skb_timestamp(skb);
-	if (!start_ts)
-		skb->skb_mstamp_ns = tp->tcp_clock_cache;
-	else if (icsk->icsk_user_timeout &&
-		 (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout)
-		goto abort;
+	if (icsk->icsk_user_timeout) {
+		u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out,
+						tcp_probe0_base(sk));
+
+		if (elapsed >= icsk->icsk_user_timeout)
+			goto abort;
+	}
 
 	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
@@ -395,6 +383,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int max_retries = icsk->icsk_syn_retries ? :
 	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct request_sock *req;
 
 	req = tcp_sk(sk)->fastopen_rsk;
@@ -412,6 +401,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk)
 	inet_rtx_syn_ack(sk, req);
 	req->num_timeout++;
 	icsk->icsk_retransmits++;
+	if (!tp->retrans_stamp)
+		tp->retrans_stamp = tcp_time_stamp(tp);
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 			  TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
 }
@@ -443,10 +434,8 @@ void tcp_retransmit_timer(struct sock *sk)
 		 */
 		return;
 	}
-	if (!tp->packets_out)
-		goto out;
-
-	WARN_ON(tcp_rtx_queue_empty(sk));
+	if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk)))
+		return;
 
 	tp->tlp_high_seq = 0;
 
@@ -511,14 +500,13 @@ void tcp_retransmit_timer(struct sock *sk)
 
 	tcp_enter_loss(sk);
 
+	icsk->icsk_retransmits++;
 	if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) {
 		/* Retransmission failed because of local congestion,
-		 * do not backoff.
+		 * Let senders fight for local resources conservatively.
 		 */
-		if (!icsk->icsk_retransmits)
-			icsk->icsk_retransmits = 1;
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL),
+					  TCP_RESOURCE_PROBE_INTERVAL,
 					  TCP_RTO_MAX);
 		goto out;
 	}
@@ -539,7 +527,6 @@ void tcp_retransmit_timer(struct sock *sk)
 	 * the 120 second clamps though!
 	 */
 	icsk->icsk_backoff++;
-	icsk->icsk_retransmits++;
 
 out_reset_timer:
 	/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is