tcp: don't over-send F-RTO probes

After sending the new data packets to probe (step 2), F-RTO may
incorrectly send more probes if the next ACK advances SND_UNA and
does not sack new packet. However F-RTO RFC 5682 probes at most
once. This bug may cause sender to always send new data instead of
repairing holes, inducing longer HoL blocking on the receiver for
the application.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@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 9faf775a8c4aee2a9ac0f2db450eca88c9230e1a..243d674b3ef5aa0417544b63edad59890141bafb 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2710,9 +2710,9 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
                    tcp_try_undo_loss(sk, true))
                        return;
 
-               if (after(tp->snd_nxt, tp->high_seq) &&
-                   (flag & FLAG_DATA_SACKED || is_dupack)) {
-                       tp->frto = 0; /* Loss was real: 2nd part of step 3.a */
+               if (after(tp->snd_nxt, tp->high_seq)) {
+                       if (flag & FLAG_DATA_SACKED || is_dupack)
+                               tp->frto = 0; /* Step 3.a. loss was real */
                } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
                        tp->high_seq = tp->snd_nxt;
                        __tcp_push_pending_frames(sk, tcp_current_mss(sk),