diff mbox series

[net-next,2/8] tcp: disable RFC6675 loss detection

Message ID 20180516234017.172775-3-ycheng@google.com
State Accepted, archived
Delegated to: David Miller
Headers show
Series tcp: default RACK loss recovery | expand

Commit Message

Yuchung Cheng May 16, 2018, 11:40 p.m. UTC 
This patch disables RFC6675 loss detection and make sysctl
net.ipv4.tcp_recovery = 1 controls a binary choice between RACK
(1) or RFC6675 (0).

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Priyaranjan Jha <priyarjha@google.com>
---
 Documentation/networking/ip-sysctl.txt |  3 ++-
 net/ipv4/tcp_input.c                   | 12 ++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 13bbac50dc8b..ea304a23c8d7 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -449,7 +449,8 @@  tcp_recovery - INTEGER
 	features.
 
 	RACK: 0x1 enables the RACK loss detection for fast detection of lost
-	      retransmissions and tail drops.
+	      retransmissions and tail drops. It also subsumes and disables
+	      RFC6675 recovery for SACK connections.
 	RACK: 0x2 makes RACK's reordering window static (min_rtt/4).
 	RACK: 0x4 disables RACK's DUPACK threshold heuristic
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b188e0d75edd..ccbe04f80040 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2035,6 +2035,11 @@  static inline int tcp_dupack_heuristics(const struct tcp_sock *tp)
 	return tp->sacked_out + 1;
 }
 
+static bool tcp_is_rack(const struct sock *sk)
+{
+	return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+}
+
 /* Linux NewReno/SACK/ECN state machine.
  * --------------------------------------
  *
@@ -2141,7 +2146,7 @@  static bool tcp_time_to_recover(struct sock *sk, int flag)
 		return true;
 
 	/* Not-A-Trick#2 : Classic rule... */
-	if (tcp_dupack_heuristics(tp) > tp->reordering)
+	if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
 		return true;
 
 	return false;
@@ -2722,8 +2727,7 @@  static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Use RACK to detect loss */
-	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+	if (tcp_is_rack(sk)) {
 		u32 prior_retrans = tp->retrans_out;
 
 		tcp_rack_mark_lost(sk);
@@ -2862,7 +2866,7 @@  static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		fast_rexmit = 1;
 	}
 
-	if (do_lost)
+	if (!tcp_is_rack(sk) && do_lost)
 		tcp_update_scoreboard(sk, fast_rexmit);
 	*rexmit = REXMIT_LOST;
 }