tcp: update skb->skb_mstamp more carefully

Eric Dumazet · davem330 · commit 8c72c65b426b · 2017-09-15T14:36:28.000-07:00
liujian reported a problem in TCP_USER_TIMEOUT processing with a patch in tcp_probe_timer() : https://www.spinics.net/lists/netdev/msg454496.html After investigations, the root cause of the problem is that we update skb->skb_mstamp of skbs in write queue, even if the attempt to send a clone or copy of it failed. One reason being a routing problem. This patch prevents this, solving liujian issue. It also removes a potential RTT miscalculation, since __tcp_retransmit_skb() is not OR-ing TCP_SKB_CB(skb)->sacked with TCPCB_EVER_RETRANS if a failure happens, but skb->skb_mstamp has been changed. A future ACK would then lead to a very small RTT sample and min_rtt would then be lowered to this too small value. Tested: # cat user_timeout.pkt --local_ip=192.168.102.64 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 +0 `ifconfig tun0 192.168.102.64/16; ip ro add 192.0.2.1 dev tun0` +0 < S 0:0(0) win 0 <mss 1460> +0 > S. 0:0(0) ack 1 <mss 1460> +.1 < . 1:1(0) ack 1 win 65530 +0 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0 +0 write(4, ..., 24) = 24 +0 > P. 1:25(24) ack 1 win 29200 +.1 < . 1:1(0) ack 25 win 65530 //change the ipaddress +1 `ifconfig tun0 192.168.0.10/16` +1 write(4, ..., 24) = 24 +1 write(4, ..., 24) = 24 +1 write(4, ..., 24) = 24 +1 write(4, ..., 24) = 24 +0 `ifconfig tun0 192.168.102.64/16` +0 < . 1:2(1) ack 25 win 65530 +0 `ifconfig tun0 192.168.0.10/16` +3 write(4, ..., 24) = -1 # ./packetdrill user_timeout.pkt Signed-off-by: Eric Dumazet <edumazet@googl.com> Reported-by: liujian <liujian56@huawei.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
@@ -991,26 +991,28 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	struct tcp_skb_cb *tcb;
 	struct tcp_out_options opts;
 	unsigned int tcp_options_size, tcp_header_size;
+	struct sk_buff *oskb = NULL;
 	struct tcp_md5sig_key *md5;
 	struct tcphdr *th;
 	int err;
 
 	BUG_ON(!skb || !tcp_skb_pcount(skb));
 	tp = tcp_sk(sk);
 
-	skb->skb_mstamp = tp->tcp_mstamp;
 	if (clone_it) {
 		TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
 			- tp->snd_una;
 		tcp_rate_skb_sent(sk, skb);
 
+		oskb = skb;
 		if (unlikely(skb_cloned(skb)))
 			skb = pskb_copy(skb, gfp_mask);
 		else
 			skb = skb_clone(skb, gfp_mask);
 		if (unlikely(!skb))
 			return -ENOBUFS;
 	}
+	skb->skb_mstamp = tp->tcp_mstamp;
 
 	inet = inet_sk(sk);
 	tcb = TCP_SKB_CB(skb);
@@ -1122,12 +1124,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 
 	err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl);
 
-	if (likely(err <= 0))
-		return err;
-
-	tcp_enter_cwr(sk);
+	if (unlikely(err > 0)) {
+		tcp_enter_cwr(sk);
+		err = net_xmit_eval(err);
+	}
+	if (!err && oskb)
+		oskb->skb_mstamp = tp->tcp_mstamp;
 
-	return net_xmit_eval(err);
+	return err;
 }
 
 /* This routine just queues the buffer for sending.
@@ -2869,10 +2873,11 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 		     skb_headroom(skb) >= 0xFFFF)) {
 		struct sk_buff *nskb;
 
-		skb->skb_mstamp = tp->tcp_mstamp;
 		nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
 		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
 			     -ENOBUFS;
+		if (!err)
+			skb->skb_mstamp = tp->tcp_mstamp;
 	} else {
 		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
 	}
