From e21db6f69a95b846ff04e31fe0a86004cbd000d7 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 17 Apr 2018 23:18:48 -0700 Subject: [PATCH] tcp: track total bytes delivered with ECN CE marks Introduce a new delivered_ce stat in tcp socket to estimate number of packets being marked with CE bits. The estimation is done via ACKs with ECE bit. Depending on the actual receiver behavior, the estimation could have biases. Since the TCP sender can't really see the CE bit in the data path, so the sender is technically counting packets marked delivered with the "ECE / ECN-Echo" flag set. With RFC3168 ECN, because the ECE bit is sticky, this count can drastically overestimate the nummber of CE-marked data packets With DCTCP-style ECN this should be reasonably precise unless there is loss in the ACK path, in which case it's not precise. With AccECN proposal this can be made still more precise, even in the case some degree of ACK loss. However this is sender's best estimate of CE information. Signed-off-by: Yuchung Cheng Reviewed-by: Neal Cardwell Reviewed-by: Soheil Hassas Yeganeh Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + net/ipv4/tcp.c | 1 + net/ipv4/tcp_input.c | 2 ++ 3 files changed, 4 insertions(+) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8f4c54986f97..20585d5c4e1c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -281,6 +281,7 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 delivered_ce; /* Like the above but only ECE marked packets */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ u64 first_tx_mstamp; /* start of window send phase */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 438fbca96cd3..5a5ce6da4792 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2559,6 +2559,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered_ce = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 01cce28f90ca..b3bff9c20606 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3503,6 +3503,8 @@ static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag) u32 delivered; delivered = tp->delivered - prior_delivered; + if (flag & FLAG_ECE) + tp->delivered_ce += delivered; return delivered; }