tcp: fix TLP timer not set when CA_STATE changes from DISORDER to OPEN

Upon receiving a cumulative ACK that changes the congestion state from
Disorder to Open, the TLP timer is not set. If the sender is app-limited,
it can only wait for the RTO timer to expire and retransmit.

The reason for this is that the TLP timer is set before the congestion
state changes in tcp_ack(), so we delay the time point of calling
tcp_set_xmit_timer() until after tcp_fastretrans_alert() returns and
remove the FLAG_SET_XMIT_TIMER from ack_flag when the RACK reorder timer
is set.

This commit has two additional benefits:
1) Make sure to reset RTO according to RFC6298 when receiving ACK, to
avoid spurious RTO caused by RTO timer early expires.
2) Reduce the xmit timer reschedule once per ACK when the RACK reorder
timer is set.

Fixes: df92c8394e6e ("tcp: fix xmit timer to only be reset if data ACKed/SACKed")
Link: https://lore.kernel.org/netdev/1611311242-6675-1-git-send-email-yangpc@wangsu.com
Signed-off-by: Pengcheng Yang <yangpc@wangsu.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/1611464834-23030-1-git-send-email-yangpc@wangsu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index ca7e2c6cc663ee96dabc1ee01a69182ab770da22..25bbada379c46add16fb7239733bd6571f10f680 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2061,7 +2061,7 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb);
 void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced);
 extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb,
                                u32 reo_wnd);
-extern void tcp_rack_mark_lost(struct sock *sk);
+extern bool tcp_rack_mark_lost(struct sock *sk);
 extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq,
                             u64 xmit_time);
 extern void tcp_rack_reo_timeout(struct sock *sk);

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 55c6fd6b5d139e0b3808ea4b44d45d6a36cbdbd7..9b44caa4b956221a8d911fa8d0d8a6c51bad5829 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2859,7 +2859,8 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
        } else if (tcp_is_rack(sk)) {
                u32 prior_retrans = tp->retrans_out;
 
-               tcp_rack_mark_lost(sk);
+               if (tcp_rack_mark_lost(sk))
+                       *ack_flag &= ~FLAG_SET_XMIT_TIMER;
                if (prior_retrans > tp->retrans_out)
                        *ack_flag |= FLAG_LOST_RETRANS;
        }
@@ -3816,9 +3817,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
        if (tp->tlp_high_seq)
                tcp_process_tlp_ack(sk, ack, flag);
-       /* If needed, reset TLP/RTO timer; RACK may later override this. */
-       if (flag & FLAG_SET_XMIT_TIMER)
-               tcp_set_xmit_timer(sk);
 
        if (tcp_ack_is_dubious(sk, flag)) {
                if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
@@ -3831,6 +3829,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
                                      &rexmit);
        }
 
+       /* If needed, reset TLP/RTO timer when RACK doesn't set. */
+       if (flag & FLAG_SET_XMIT_TIMER)
+               tcp_set_xmit_timer(sk);
+
        if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
                sk_dst_confirm(sk);
 

diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 177307a3081f9583e5e488e1a1d73035fb4bc3fd..6f1b4ac7fe99c4b256d45e23f7b96509dd597e77 100644 (file)
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -96,13 +96,13 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
        }
 }
 
-void tcp_rack_mark_lost(struct sock *sk)
+bool tcp_rack_mark_lost(struct sock *sk)
 {
        struct tcp_sock *tp = tcp_sk(sk);
        u32 timeout;
 
        if (!tp->rack.advanced)
-               return;
+               return false;
 
        /* Reset the advanced flag to avoid unnecessary queue scanning */
        tp->rack.advanced = 0;
@@ -112,6 +112,7 @@ void tcp_rack_mark_lost(struct sock *sk)
                inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
                                          timeout, inet_csk(sk)->icsk_rto);
        }
+       return !!timeout;
 }
 
 /* Record the most recently (re)sent time among the (s)acked packets