tcp: always timestamp on every skb transmission

Previously TCP skbs are not always timestamped if the transmission
failed due to memory or other local issues. This makes deciding
when to abort a socket tricky and complicated because the first
unacknowledged skb's timestamp may be 0 on TCP timeout.

The straight-forward fix is to always timestamp skb on every
transmission attempt. Also every skb retransmission needs to be
flagged properly to avoid RTT under-estimation. This can happen
upon receiving an ACK for the original packet and the a previous
(spurious) retransmission has failed.

It's worth noting that this reverts to the old time-stamping
style before commit 8c72c65b426b ("tcp: update skb->skb_mstamp more
carefully") which addresses a problem in computing the elapsed time
of a stalled window-probing socket. The problem will be addressed
differently in the next patches with a simpler approach.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 8 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 730bc44dbad9..57a56e205070 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -980,7 +980,6 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb,
 {
         struct tcp_sock *tp = tcp_sk(sk);
 
-        skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
         if (sk->sk_pacing_status != SK_PACING_NONE) {
                 unsigned long rate = sk->sk_pacing_rate;
 
@@ -1028,7 +1027,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 
         BUG_ON(!skb || !tcp_skb_pcount(skb));
         tp = tcp_sk(sk);
-
+        prior_wstamp = tp->tcp_wstamp_ns;
+        tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
+        skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
         if (clone_it) {
                 TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
                         - tp->snd_una;
@@ -1045,11 +1046,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
                         return -ENOBUFS;
         }
 
-        prior_wstamp = tp->tcp_wstamp_ns;
-        tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache);
-
-        skb->skb_mstamp_ns = tp->tcp_wstamp_ns;
-
         inet = inet_sk(sk);
         tcb = TCP_SKB_CB(skb);
         memset(&opts, 0, sizeof(opts));
@@ -2937,12 +2933,16 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
                 err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
         }
 
+        /* To avoid taking spuriously low RTT samples based on a timestamp
+         * for a transmit that never happened, always mark EVER_RETRANS
+         */
+        TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
+
         if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
                 tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
                                   TCP_SKB_CB(skb)->seq, segs, err);
 
         if (likely(!err)) {
-                TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
                 trace_tcp_retransmit_skb(sk, skb);
         } else if (err != -EBUSY) {
                 NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs);