diff mbox series

[net,1/5] tcp: feed correct number of pkts acked to cc modules also in recovery

Message ID 1520427569-14365-2-git-send-email-ilpo.jarvinen@helsinki.fi
State Changes Requested, archived
Delegated to: David Miller
Headers show
Series tcp: fixes to non-SACK TCP | expand

Commit Message

Ilpo Järvinen March 7, 2018, 12:59 p.m. UTC
The pkts_acked is clearly not the correct value for slow start
after RTO as it may include segments that were not lost and
therefore did not need retransmissions in the slow start following
the RTO. Then tcp_slow_start will add the excess into cwnd bloating
it and triggering a burst.

Instead, we want to pass only the number of retransmitted segments
that were covered by the cumulative ACK (and potentially newly sent
data segments too if the cumulative ACK covers that far).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
---
 net/ipv4/tcp_input.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9a1b3c1..0305f6d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3027,6 +3027,8 @@  static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 	long seq_rtt_us = -1L;
 	long ca_rtt_us = -1L;
 	u32 pkts_acked = 0;
+	u32 rexmit_acked = 0;
+	u32 newdata_acked = 0;
 	u32 last_in_flight = 0;
 	bool rtt_update;
 	int flag = 0;
@@ -3056,8 +3058,10 @@  static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 		}
 
 		if (unlikely(sacked & TCPCB_RETRANS)) {
-			if (sacked & TCPCB_SACKED_RETRANS)
+			if (sacked & TCPCB_SACKED_RETRANS) {
 				tp->retrans_out -= acked_pcount;
+				rexmit_acked += acked_pcount;
+			}
 			flag |= FLAG_RETRANS_DATA_ACKED;
 		} else if (!(sacked & TCPCB_SACKED_ACKED)) {
 			last_ackt = skb->skb_mstamp;
@@ -3068,8 +3072,11 @@  static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 			last_in_flight = TCP_SKB_CB(skb)->tx.in_flight;
 			if (before(start_seq, reord))
 				reord = start_seq;
-			if (!after(scb->end_seq, tp->high_seq))
+			if (!after(scb->end_seq, tp->high_seq)) {
 				flag |= FLAG_ORIG_SACK_ACKED;
+			} else {
+				newdata_acked += acked_pcount;
+			}
 		}
 
 		if (sacked & TCPCB_SACKED_ACKED) {
@@ -3151,6 +3158,14 @@  static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 		}
 
 		if (tcp_is_reno(tp)) {
+			/* Due to discontinuity on RTO in the artificial
+			 * sacked_out calculations, TCP must restrict
+			 * pkts_acked without SACK to rexmits and new data
+			 * segments
+			 */
+			if (icsk->icsk_ca_state == TCP_CA_Loss)
+				pkts_acked = rexmit_acked + newdata_acked;
+
 			tcp_remove_reno_sacks(sk, pkts_acked);
 		} else {
 			int delta;