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>

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba79fa6b1f490f27a3aaf013070fbf9c8015..eeaac399420de043bb466603fcb03ff83076438a 100644 (file)
--- 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 d718482fd11c1073b42140a8dddfbb26624d6bfd..f0eb4e337ec88fc631a30adc0d168817e5812ced 100644 (file)
--- 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)