From 15bb7745e94a665caf42bfaabf0ce062845b533b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Mar 2017 08:10:21 -0700 Subject: tcp: initialize icsk_ack.lrcvtime at session start time icsk_ack.lrcvtime has a 0 value at socket creation time. tcpi_last_data_recv can have bogus value if no payload is ever received. This patch initializes icsk_ack.lrcvtime for active sessions in tcp_finish_connect(), and for passive sessions in tcp_create_openreq_child() Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 39c393cc0fd3..c43119726a62 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5541,6 +5541,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) struct inet_connection_sock *icsk = inet_csk(sk); tcp_set_state(sk, TCP_ESTABLISHED); + icsk->icsk_ack.lrcvtime = tcp_time_stamp; if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); @@ -5759,7 +5760,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * to stand against the temptation 8) --ANK */ inet_csk_schedule_ack(sk); - icsk->icsk_ack.lrcvtime = tcp_time_stamp; tcp_enter_quickack_mode(sk); inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); -- cgit v1.2.3 From 0b9aefea860063bb39e36bd7fe6c7087fed0ba87 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Sat, 1 Apr 2017 11:00:21 -0300 Subject: tcp: minimize false-positives on TCP/GRO check Markus Trippelsdorf reported that after commit dcb17d22e1c2 ("tcp: warn on bogus MSS and try to amend it") the kernel started logging the warning for a NIC driver that doesn't even support GRO. It was diagnosed that it was possibly caused on connections that were using TCP Timestamps but some packets lacked the Timestamps option. As we reduce rcv_mss when timestamps are used, the lack of them would cause the packets to be bigger than expected, although this is a valid case. As this warning is more as a hint, getting a clean-cut on the threshold is probably not worth the execution time spent on it. This patch thus alleviates the false-positives with 2 quick checks: by accounting for the entire TCP option space and also checking against the interface MTU if it's available. These changes, specially the MTU one, might mask some real positives, though if they are really happening, it's possible that sooner or later it will be triggered anyway. Reported-by: Markus Trippelsdorf Cc: Eric Dumazet Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c43119726a62..97ac6776e47d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -126,7 +126,8 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ -static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) +static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, + unsigned int len) { static bool __once __read_mostly; @@ -137,8 +138,9 @@ static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb) rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); - pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", - dev ? dev->name : "Unknown driver"); + if (!dev || len >= dev->mtu) + pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n", + dev ? dev->name : "Unknown driver"); rcu_read_unlock(); } } @@ -161,8 +163,10 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) if (len >= icsk->icsk_ack.rcv_mss) { icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); - if (unlikely(icsk->icsk_ack.rcv_mss != len)) - tcp_gro_dev_warn(sk, skb); + /* Account for possibly-removed options */ + if (unlikely(len > icsk->icsk_ack.rcv_mss + + MAX_TCP_OPTION_SPACE)) + tcp_gro_dev_warn(sk, skb, len); } else { /* Otherwise, we make more careful check taking into account, * that SACKs block is variable. -- cgit v1.2.3 From 2d2517ee314ef1de0517f74d06c2825fbf597ba3 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 4 Apr 2017 14:15:40 -0700 Subject: tcp: fix reordering SNMP under-counting Currently the reordering SNMP counters only increase if a connection sees a higher degree then it has previously seen. It ignores if the reordering degree is not greater than the default system threshold. This significantly under-counts the number of reordering events and falsely convey that reordering is rare on the network. This patch properly and faithfully records the number of reordering events detected by the TCP stack, just like the comment says "this exciting event is worth to be remembered". Note that even so TCP still under-estimate the actual reordering events because TCP requires TS options or certain packet sequences to detect reordering (i.e. ACKing never-retransmitted sequence in recovery or disordered state). Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 97ac6776e47d..2c1f59386a7b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -878,22 +878,11 @@ static void tcp_update_reordering(struct sock *sk, const int metric, const int ts) { struct tcp_sock *tp = tcp_sk(sk); - if (metric > tp->reordering) { - int mib_idx; + int mib_idx; + if (metric > tp->reordering) { tp->reordering = min(sysctl_tcp_max_reordering, metric); - /* This exciting event is worth to be remembered. 8) */ - if (ts) - mib_idx = LINUX_MIB_TCPTSREORDER; - else if (tcp_is_reno(tp)) - mib_idx = LINUX_MIB_TCPRENOREORDER; - else if (tcp_is_fack(tp)) - mib_idx = LINUX_MIB_TCPFACKREORDER; - else - mib_idx = LINUX_MIB_TCPSACKREORDER; - - NET_INC_STATS(sock_net(sk), mib_idx); #if FASTRETRANS_DEBUG > 1 pr_debug("Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, @@ -906,6 +895,18 @@ static void tcp_update_reordering(struct sock *sk, const int metric, } tp->rack.reord = 1; + + /* This exciting event is worth to be remembered. 8) */ + if (ts) + mib_idx = LINUX_MIB_TCPTSREORDER; + else if (tcp_is_reno(tp)) + mib_idx = LINUX_MIB_TCPRENOREORDER; + else if (tcp_is_fack(tp)) + mib_idx = LINUX_MIB_TCPFACKREORDER; + else + mib_idx = LINUX_MIB_TCPSACKREORDER; + + NET_INC_STATS(sock_net(sk), mib_idx); } /* This must be called before lost_out is incremented */ -- cgit v1.2.3 From cc663f4d4c97b7297fb45135ab23cfd508b35a77 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 7 Apr 2017 11:42:05 -0700 Subject: tcp: restrict F-RTO to work-around broken middle-boxes The recent extension of F-RTO 89fe18e44 ("tcp: extend F-RTO to catch more spurious timeouts") interacts badly with certain broken middle-boxes. These broken boxes modify and falsely raise the receive window on the ACKs. During a timeout induced recovery, F-RTO would send new data packets to probe if the timeout is false or not. Since the receive window is falsely raised, the receiver would silently drop these F-RTO packets. The recovery would take N (exponentially backoff) timeouts to repair N packet losses. A TCP performance killer. Due to this unfortunate situation, this patch removes this extension to revert F-RTO back to the RFC specification. Fixes: 89fe18e44f7e ("tcp: extend F-RTO to catch more spurious timeouts") Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Soheil Hassas Yeganeh Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2c1f59386a7b..659d1baefb2b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1935,6 +1935,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sk_buff *skb; + bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; bool is_reneg; /* is receiver reneging on SACKs? */ bool mark_lost; @@ -1994,15 +1995,18 @@ void tcp_enter_loss(struct sock *sk) tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); - /* F-RTO RFC5682 sec 3.1 step 1 mandates to disable F-RTO - * if a previous recovery is underway, otherwise it may incorrectly - * call a timeout spurious if some previously retransmitted packets - * are s/acked (sec 3.2). We do not apply that retriction since - * retransmitted skbs are permanently tagged with TCPCB_EVER_RETRANS - * so FLAG_ORIG_SACK_ACKED is always correct. But we do disable F-RTO - * on PTMU discovery to avoid sending new data. + /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous + * loss recovery is underway except recurring timeout(s) on + * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing + * + * In theory F-RTO can be used repeatedly during loss recovery. + * In practice this interacts badly with broken middle-boxes that + * falsely raise the receive window, which results in repeated + * timeouts and stop-and-go behavior. */ - tp->frto = sysctl_tcp_frto && !inet_csk(sk)->icsk_mtup.probe_size; + tp->frto = sysctl_tcp_frto && + (new_recovery || icsk->icsk_retransmits) && + !inet_csk(sk)->icsk_mtup.probe_size; } /* If ACK arrived pointing to a remembered SACK, it means that our -- cgit v1.2.3