From 3976535af0cb9fe34a55f2ffb8d7e6b39a2f8188 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 28 Nov 2018 16:06:43 -0800 Subject: [PATCH 1/3] tcp: fix off-by-one bug on aborting window-probing socket Previously there is an off-by-one bug on determining when to abort a stalled window-probing socket. This patch fixes that so it is consistent with tcp_write_timeout(). Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 091c53925e4d..25efdae4368a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -378,7 +378,7 @@ static void tcp_probe_timer(struct sock *sk) return; } - if (icsk->icsk_probes_out > max_probes) { + if (icsk->icsk_probes_out >= max_probes) { abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ From ec641b39457e17774313b66697a8a1dc070257bd Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 28 Nov 2018 16:06:44 -0800 Subject: [PATCH 2/3] tcp: fix SNMP under-estimation on failed retransmission Previously the SNMP counter LINUX_MIB_TCPRETRANSFAIL is not counting the TSO/GSO properly on failed retransmission. This patch fixes that. Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3f510cad0b3e..68b5326f7321 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2920,7 +2920,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } return err; } From e1561fe2dd69dc5dddd69bd73aa65355bdfb048b Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 28 Nov 2018 16:06:45 -0800 Subject: [PATCH 3/3] tcp: fix SNMP TCP timeout under-estimation Previously the SNMP TCPTIMEOUTS counter has inconsistent accounting: 1. It counts all SYN and SYN-ACK timeouts 2. It counts timeouts in other states except recurring timeouts and timeouts after fast recovery or disorder state. Such selective accounting makes analysis difficult and complicated. For example the monitoring system needs to collect many other SNMP counters to infer the total amount of timeout events. This patch makes TCPTIMEOUTS counter simply counts all the retransmit timeout (SYN or data or FIN). Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 25efdae4368a..f87dbc78b6bc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -484,11 +484,12 @@ void tcp_retransmit_timer(struct sock *sk) goto out_reset_timer; } + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { - int mib_idx; + int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) @@ -503,10 +504,9 @@ void tcp_retransmit_timer(struct sock *sk) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else { - mib_idx = LINUX_MIB_TCPTIMEOUTS; } - __NET_INC_STATS(sock_net(sk), mib_idx); + if (mib_idx) + __NET_INC_STATS(sock_net(sk), mib_idx); } tcp_enter_loss(sk);