From 627f3abeeac1354a4b15eaf0f22b8ffb901029cb Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Mon, 25 Jan 2016 14:01:53 -0800 Subject: tcp: fix tcp_mark_head_lost to check skb len before fragmenting commit d88270eef4b56bd7973841dd1fed387ccfa83709 upstream. This commit fixes a corner case in tcp_mark_head_lost() which was causing the WARN_ON(len > skb->len) in tcp_fragment() to fire. tcp_mark_head_lost() was assuming that if a packet has tcp_skb_pcount(skb) of N, then it's safe to fragment off a prefix of M*mss bytes, for any M < N. But with the tricky way TCP pcounts are maintained, this is not always true. For example, suppose the sender sends 4 1-byte packets and have the last 3 packet sacked. It will merge the last 3 packets in the write queue into an skb with pcount = 3 and len = 3 bytes. If another recovery happens after a sack reneging event, tcp_mark_head_lost() may attempt to split the skb assuming it has more than 2*MSS bytes. This sounds very counterintuitive, but as the commit description for the related commit c0638c247f55 ("tcp: don't fragment SACKed skbs in tcp_mark_head_lost()") notes, this is because tcp_shifted_skb() coalesces adjacent regions of SACKed skbs, and when doing this it preserves the sum of their packet counts in order to reflect the real-world dynamics on the wire. The c0638c247f55 commit tried to avoid problems by not fragmenting SACKed skbs, since SACKed skbs are where the non-proportionality between pcount and skb->len/mss is known to be possible. However, that commit did not handle the case where during a reneging event one of these weird SACKed skbs becomes an un-SACKed skb, which tcp_mark_head_lost() can then try to fragment. The fix is to simply mark the entire skb lost when this happens. This makes the recovery slightly more aggressive in such corner cases before we detect reordering. But once we detect reordering this code path is by-passed because FACK is disabled. Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Cc: Vinson Lee Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 10 +++++----- 1 file changed, 5 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 87791f803627..8f13b2eaabf8 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2165,8 +2165,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int cnt, oldcnt; - int err; + int cnt, oldcnt, lost; unsigned int mss; /* Use SACK to deduce losses of new sequences sent during recovery */ const u32 loss_high = tcp_is_sack(tp) ? tp->snd_nxt : tp->high_seq; @@ -2206,9 +2205,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) break; mss = tcp_skb_mss(skb); - err = tcp_fragment(sk, skb, (packets - oldcnt) * mss, - mss, GFP_ATOMIC); - if (err < 0) + /* If needed, chop off the prefix to mark as lost. */ + lost = (packets - oldcnt) * mss; + if (lost < skb->len && + tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0) break; cnt = packets; } -- cgit v1.2.3 From 025bb7f7e92c2dc3320eefb5676e1813e3c8fa1d Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 1 Aug 2017 13:22:32 -0700 Subject: tcp: avoid setting cwnd to invalid ssthresh after cwnd reduction states [ Upstream commit ed254971edea92c3ac5c67c6a05247a92aa6075e ] If the sender switches the congestion control during ECN-triggered cwnd-reduction state (CA_CWR), upon exiting recovery cwnd is set to the ssthresh value calculated by the previous congestion control. If the previous congestion control is BBR that always keep ssthresh to TCP_INIFINITE_SSTHRESH, cwnd ends up being infinite. The safe step is to avoid assigning invalid ssthresh value when recovery ends. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Acked-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8f13b2eaabf8..f0dabd125c43 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2503,8 +2503,8 @@ static inline void tcp_end_cwnd_reduction(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || - (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH && + (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || tp->undo_marker)) { tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } -- cgit v1.2.3 From 4e39b7409f3b852ae95e580207b4aec93965834c Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Wed, 16 Aug 2017 17:53:36 -0400 Subject: tcp: when rearming RTO, if RTO time is in past then fire RTO ASAP [ Upstream commit cdbeb633ca71a02b7b63bfeb94994bf4e1a0b894 ] In some situations tcp_send_loss_probe() can realize that it's unable to send a loss probe (TLP), and falls back to calling tcp_rearm_rto() to schedule an RTO timer. In such cases, sometimes tcp_rearm_rto() realizes that the RTO was eligible to fire immediately or at some point in the past (delta_us <= 0). Previously in such cases tcp_rearm_rto() was scheduling such "overdue" RTOs to happen at now + icsk_rto, which caused needless delays of hundreds of milliseconds (and non-linear behavior that made reproducible testing difficult). This commit changes the logic to schedule "overdue" RTOs ASAP, rather than at now + icsk_rto. Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)") Suggested-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/ipv4/tcp_input.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f0dabd125c43..c4bbf704ff9c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3028,8 +3028,7 @@ void tcp_rearm_rto(struct sock *sk) /* delta may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ - if (delta > 0) - rto = delta; + rto = max(delta, 1); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); -- cgit v1.2.3