From e3e12028315749b7fa2edbc37328e5847be9ede9 Mon Sep 17 00:00:00 2001 From: Andrew Vagin Date: Tue, 27 Aug 2013 12:21:55 +0400 Subject: tcp: don't apply tsoffset if rcv_tsecr is zero The zero value means that tsecr is not valid, so it's a special case. tsoffset is used to customize tcp_time_stamp for one socket. tsoffset is usually zero, it's used when a socket was moved from one host to another host. Currently this issue affects logic of tcp_rcv_rtt_measure_ts. Due to incorrect value of rcv_tsecr, tcp_rcv_rtt_measure_ts sets rto to TCP_RTO_MAX. Cc: Pavel Emelyanov Cc: Eric Dumazet Cc: "David S. Miller" Cc: Alexey Kuznetsov Cc: James Morris Cc: Hideaki YOSHIFUJI Cc: Patrick McHardy Reported-by: Cyrill Gorcunov Signed-off-by: Andrey Vagin Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 28af45abe06..3ca2139a130 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3535,7 +3535,10 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + if (*ptr) + tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; + else + tp->rx_opt.rcv_tsecr = 0; return true; } return false; @@ -3560,7 +3563,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, } tcp_parse_options(skb, &tp->rx_opt, 1, NULL); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; return true; @@ -5316,7 +5319,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; tcp_parse_options(skb, &tp->rx_opt, 0, &foc); - if (tp->rx_opt.saw_tstamp) + if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { -- cgit v1.2.3-70-g09d2 From 16edfe7ee02dd7fcc13855ea19158333529533b2 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 5 Sep 2013 15:36:09 -0700 Subject: tcp: fix no cwnd growth after timeout In commit 0f7cc9a3 "tcp: increase throughput when reordering is high", it only allows cwnd to increase in Open state. This mistakenly disables slow start after timeout (CA_Loss). Moreover cwnd won't grow if the state moves from Disorder to Open later in tcp_fastretrans_alert(). Therefore the correct logic should be to allow cwnd to grow as long as the data is received in order in Open, Loss, or even Disorder state. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1969e16d936..894bc174f47 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3162,16 +3162,14 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) /* If reordering is high then always grow cwnd whenever data is * delivered regardless of its ordering. Otherwise stay conservative - * and only grow cwnd on in-order delivery in Open state, and retain - * cwnd in Disordered state (RFC5681). A stretched ACK with + * and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/ * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ if (tcp_sk(sk)->reordering > sysctl_tcp_reordering) return flag & FLAG_FORWARD_PROGRESS; - return inet_csk(sk)->icsk_ca_state == TCP_CA_Open && - flag & FLAG_DATA_ACKED; + return flag & FLAG_DATA_ACKED; } /* Check that window update is acceptable. -- cgit v1.2.3-70-g09d2 From 4e4f1fc226816905c937f9b29dabe351075dfe0f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 6 Sep 2013 10:35:58 -0700 Subject: tcp: properly increase rcv_ssthresh for ofo packets TCP receive window handling is multi staged. A socket has a memory budget, static or dynamic, in sk_rcvbuf. Because we do not really know how this memory budget translates to a TCP window (payload), TCP announces a small initial window (about 20 MSS). When a packet is received, we increase TCP rcv_win depending on the payload/truesize ratio of this packet. Good citizen packets give a hint that it's reasonable to have rcv_win = sk_rcvbuf/2 This heuristic takes place in tcp_grow_window() Problem is : We currently call tcp_grow_window() only for in-order packets. This means that reorders or packet losses stop proper grow of rcv_win, and senders are unable to benefit from fast recovery, or proper reordering level detection. Really, a packet being stored in OFO queue is not a bad citizen. It should be part of the game as in-order packets. In our traces, we very often see sender is limited by linux small receive windows, even if linux hosts use autotuning (DRS) and should allow rcv_win to grow to ~3MB. Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 894bc174f47..25a89eaa669 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4139,6 +4139,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (!tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { __skb_queue_after(&tp->out_of_order_queue, skb1, skb); } else { + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; } @@ -4214,8 +4215,10 @@ add_sack: if (tcp_is_sack(tp)) tcp_sack_new_ofo_skb(sk, seq, end_seq); end: - if (skb) + if (skb) { + tcp_grow_window(sk, skb); skb_set_owner_r(skb, sk); + } } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen, -- cgit v1.2.3-70-g09d2