forked from Minki/linux
08abdffa1c
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> |
||
---|---|---|
.. | ||
netfilter | ||
af_inet.c | ||
ah4.c | ||
arp.c | ||
cipso_ipv4.c | ||
datagram.c | ||
devinet.c | ||
esp4.c | ||
fib_frontend.c | ||
fib_lookup.h | ||
fib_rules.c | ||
fib_semantics.c | ||
fib_trie.c | ||
fou.c | ||
geneve.c | ||
gre_demux.c | ||
gre_offload.c | ||
icmp.c | ||
igmp.c | ||
inet_connection_sock.c | ||
inet_diag.c | ||
inet_fragment.c | ||
inet_hashtables.c | ||
inet_lro.c | ||
inet_timewait_sock.c | ||
inetpeer.c | ||
ip_forward.c | ||
ip_fragment.c | ||
ip_gre.c | ||
ip_input.c | ||
ip_options.c | ||
ip_output.c | ||
ip_sockglue.c | ||
ip_tunnel_core.c | ||
ip_tunnel.c | ||
ip_vti.c | ||
ipcomp.c | ||
ipconfig.c | ||
ipip.c | ||
ipmr.c | ||
Kconfig | ||
Makefile | ||
netfilter.c | ||
ping.c | ||
proc.c | ||
protocol.c | ||
raw.c | ||
route.c | ||
syncookies.c | ||
sysctl_net_ipv4.c | ||
tcp_bic.c | ||
tcp_cong.c | ||
tcp_cubic.c | ||
tcp_dctcp.c | ||
tcp_diag.c | ||
tcp_fastopen.c | ||
tcp_highspeed.c | ||
tcp_htcp.c | ||
tcp_hybla.c | ||
tcp_illinois.c | ||
tcp_input.c | ||
tcp_ipv4.c | ||
tcp_lp.c | ||
tcp_memcontrol.c | ||
tcp_metrics.c | ||
tcp_minisocks.c | ||
tcp_offload.c | ||
tcp_output.c | ||
tcp_probe.c | ||
tcp_scalable.c | ||
tcp_timer.c | ||
tcp_vegas.c | ||
tcp_vegas.h | ||
tcp_veno.c | ||
tcp_westwood.c | ||
tcp_yeah.c | ||
tcp.c | ||
tunnel4.c | ||
udp_diag.c | ||
udp_impl.h | ||
udp_offload.c | ||
udp_tunnel.c | ||
udp.c | ||
udplite.c | ||
xfrm4_input.c | ||
xfrm4_mode_beet.c | ||
xfrm4_mode_transport.c | ||
xfrm4_mode_tunnel.c | ||
xfrm4_output.c | ||
xfrm4_policy.c | ||
xfrm4_protocol.c | ||
xfrm4_state.c | ||
xfrm4_tunnel.c |