diff options
| author | Yuchung Cheng <ycheng@google.com> | 2014-02-28 16:42:26 -0800 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2014-03-03 15:33:02 -0500 |
| commit | c84a57113f59486e6688be1cd443b96e3118efa0 (patch) | |
| tree | 5177aed13e8ff6c94ceed13239d824a92e672f71 /net/ipv4 | |
| parent | de39d7a4f3693c4247135cbce42716bf2a113577 (diff) | |
| download | op-kernel-dev-c84a57113f59486e6688be1cd443b96e3118efa0.zip op-kernel-dev-c84a57113f59486e6688be1cd443b96e3118efa0.tar.gz | |
tcp: fix bogus RTT on special retransmission
RTT may be bogus with tall loss probe (TLP) when a packet
is retransmitted and latter (s)acked without TCPCB_SACKED_RETRANS flag.
For example, TLP calls __tcp_retransmit_skb() instead of
tcp_retransmit_skb(). The skb timestamps are updated but the sacked
flag is not marked with TCPCB_SACKED_RETRANS. As a result we'll
get bogus RTT in tcp_clean_rtx_queue() or in tcp_sacktag_one() on
spurious retransmission.
The fix is to apply the sticky flag TCP_EVER_RETRANS to enforce Karn's
check on RTT sampling. However this will disable F-RTO if timeout occurs
after TLP, by resetting undo_marker in tcp_enter_loss(). We relax this
check to only if any pending retransmists are still in-flight.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
| -rw-r--r-- | net/ipv4/tcp_input.c | 3 | ||||
| -rw-r--r-- | net/ipv4/tcp_output.c | 11 |
2 files changed, 10 insertions, 4 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 227cba7..eeaac39 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1945,8 +1945,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d718482..f0eb4e3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2337,6 +2337,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2400,11 +2401,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + + if (likely(!err)) + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) |
