aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_input.c
diff options
context:
space:
mode:
authorSébastien Barré <sebastien.barre@uclouvain.be>2015-01-12 04:30:40 -0500
committerDavid S. Miller <davem@davemloft.net>2015-01-13 14:22:02 -0500
commit08abdffa1c16b9603ee9bb33f3226ff186d98fa1 (patch)
treea9bb57f831715d010b571d758a39d3e6bb86bd4c /net/ipv4/tcp_input.c
parent52e3ad9f011fe72620b2f7050227cd48fd295ad5 (diff)
tcp: avoid reducing cwnd when ACK+DSACK is received
With TLP, the peer may reply to a probe with an ACK+D-SACK, with ack value set to tlp_high_seq. In the current code, such ACK+DSACK will be missed and only at next, higher ack will the TLP episode be considered done. Since the DSACK is not present anymore, this will cost a cwnd reduction. This patch ensures that this scenario does not cause a cwnd reduction, since receiving an ACK+DSACK indicates that both the initial segment and the probe have been received by the peer. The following packetdrill test, from Neal Cardwell, validates this patch: // Establish a connection. 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 < S 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6> +.020 < . 1:1(0) ack 1 win 257 +0 accept(3, ..., ...) = 4 // Send 1 packet. +0 write(4, ..., 1000) = 1000 +0 > P. 1:1001(1000) ack 1 // Loss probe retransmission. // packets_out == 1 => schedule PTO in max(2*RTT, 1.5*RTT + 200ms) // In this case, this means: 1.5*RTT + 200ms = 230ms +.230 > P. 1:1001(1000) ack 1 +0 %{ assert tcpi_snd_cwnd == 10 }% // Receiver ACKs at tlp_high_seq with a DSACK, // indicating they received the original packet and probe. +.020 < . 1:1(0) ack 1001 win 257 <sack 1:1001,nop,nop> +0 %{ assert tcpi_snd_cwnd == 10 }% // Send another packet. +0 write(4, ..., 1000) = 1000 +0 > P. 1001:2001(1000) ack 1 // Receiver ACKs above tlp_high_seq, which should end the TLP episode // if we haven't already. We should not reduce cwnd. +.020 < . 1:1(0) ack 2001 win 257 +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }% Credits: -Gregory helped in finding that tcp_process_tlp_ack was where the cwnd got reduced in our MPTCP tests. -Neal wrote the packetdrill test above -Yuchung reworked the patch to make it more readable. Cc: Gregory Detal <gregory.detal@uclouvain.be> Cc: Nandita Dukkipati <nanditad@google.com> Tested-by: Neal Cardwell <ncardwell@google.com> Reviewed-by: Yuchung Cheng <ycheng@google.com> Reviewed-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Sébastien Barré <sebastien.barre@uclouvain.be> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp_input.c')
-rw-r--r--net/ipv4/tcp_input.c38
1 files changed, 19 insertions, 19 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 075ab4d5af5e..71fb37c70581 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3358,34 +3358,34 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
3358} 3358}
3359 3359
3360/* This routine deals with acks during a TLP episode. 3360/* This routine deals with acks during a TLP episode.
3361 * We mark the end of a TLP episode on receiving TLP dupack or when
3362 * ack is after tlp_high_seq.
3361 * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. 3363 * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe.
3362 */ 3364 */
3363static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) 3365static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
3364{ 3366{
3365 struct tcp_sock *tp = tcp_sk(sk); 3367 struct tcp_sock *tp = tcp_sk(sk);
3366 bool is_tlp_dupack = (ack == tp->tlp_high_seq) &&
3367 !(flag & (FLAG_SND_UNA_ADVANCED |
3368 FLAG_NOT_DUP | FLAG_DATA_SACKED));
3369 3368
3370 /* Mark the end of TLP episode on receiving TLP dupack or when 3369 if (before(ack, tp->tlp_high_seq))
3371 * ack is after tlp_high_seq.
3372 */
3373 if (is_tlp_dupack) {
3374 tp->tlp_high_seq = 0;
3375 return; 3370 return;
3376 }
3377 3371
3378 if (after(ack, tp->tlp_high_seq)) { 3372 if (flag & FLAG_DSACKING_ACK) {
3373 /* This DSACK means original and TLP probe arrived; no loss */
3374 tp->tlp_high_seq = 0;
3375 } else if (after(ack, tp->tlp_high_seq)) {
3376 /* ACK advances: there was a loss, so reduce cwnd. Reset
3377 * tlp_high_seq in tcp_init_cwnd_reduction()
3378 */
3379 tcp_init_cwnd_reduction(sk);
3380 tcp_set_ca_state(sk, TCP_CA_CWR);
3381 tcp_end_cwnd_reduction(sk);
3382 tcp_try_keep_open(sk);
3383 NET_INC_STATS_BH(sock_net(sk),
3384 LINUX_MIB_TCPLOSSPROBERECOVERY);
3385 } else if (!(flag & (FLAG_SND_UNA_ADVANCED |
3386 FLAG_NOT_DUP | FLAG_DATA_SACKED))) {
3387 /* Pure dupack: original and TLP probe arrived; no loss */
3379 tp->tlp_high_seq = 0; 3388 tp->tlp_high_seq = 0;
3380 /* Don't reduce cwnd if DSACK arrives for TLP retrans. */
3381 if (!(flag & FLAG_DSACKING_ACK)) {
3382 tcp_init_cwnd_reduction(sk);
3383 tcp_set_ca_state(sk, TCP_CA_CWR);
3384 tcp_end_cwnd_reduction(sk);
3385 tcp_try_keep_open(sk);
3386 NET_INC_STATS_BH(sock_net(sk),
3387 LINUX_MIB_TCPLOSSPROBERECOVERY);
3388 }
3389 } 3389 }
3390} 3390}
3391 3391