summaryrefslogtreecommitdiffstats
path: root/include/net/tcp.h
diff options
context:
space:
mode:
authorEric Dumazet2015-08-21 21:30:00 +0200
committerDavid S. Miller2015-08-25 20:22:50 +0200
commit6f021c62d64f38092bc2a0c5fe7b81d5e5b21a00 (patch)
treed5029a2d5f2e4cd9df5f7b11d43cd72da0f520c0 /include/net/tcp.h
parentMerge branch 'fjes' (diff)
downloadkernel-qcow2-linux-6f021c62d64f38092bc2a0c5fe7b81d5e5b21a00.tar.gz
kernel-qcow2-linux-6f021c62d64f38092bc2a0c5fe7b81d5e5b21a00.tar.xz
kernel-qcow2-linux-6f021c62d64f38092bc2a0c5fe7b81d5e5b21a00.zip
tcp: fix slow start after idle vs TSO/GSO
slow start after idle might reduce cwnd, but we perform this after first packet was cooked and sent. With TSO/GSO, it means that we might send a full TSO packet even if cwnd should have been reduced to IW10. Moving the SSAI check in skb_entail() makes sense, because we slightly reduce number of times this check is done, especially for large send() and TCP Small queue callbacks from softirq context. As Neal pointed out, we also need to perform the check if/when receive window opens. Tested: Following packetdrill test demonstrates the problem // Test of slow start after idle `sysctl -q net.ipv4.tcp_slow_start_after_idle=1` 0.000 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 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7> +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6> +.100 < . 1:1(0) ack 1 win 511 +0 accept(3, ..., ...) = 4 +0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0 +0 write(4, ..., 26000) = 26000 +0 > . 1:5001(5000) ack 1 +0 > . 5001:10001(5000) ack 1 +0 %{ assert tcpi_snd_cwnd == 10 }% +.100 < . 1:1(0) ack 10001 win 511 +0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }% +0 > . 10001:20001(10000) ack 1 +0 > P. 20001:26001(6000) ack 1 +.100 < . 1:1(0) ack 26001 win 511 +0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }% +4 write(4, ..., 20000) = 20000 // If slow start after idle works properly, we should send 5 MSS here (cwnd/2) +0 > . 26001:31001(5000) ack 1 +0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }% +0 > . 31001:36001(5000) ack 1 Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net/tcp.h')
-rw-r--r--include/net/tcp.h13
1 files changed, 13 insertions, 0 deletions
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 364426a2be5a..309801f7eb82 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1165,6 +1165,19 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
}
u32 tcp_default_init_rwnd(u32 mss);
+void tcp_cwnd_restart(struct sock *sk, s32 delta);
+
+static inline void tcp_slow_start_after_idle_check(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ s32 delta;
+
+ if (!sysctl_tcp_slow_start_after_idle || tp->packets_out)
+ return;
+ delta = tcp_time_stamp - tp->lsndtime;
+ if (delta > inet_csk(sk)->icsk_rto)
+ tcp_cwnd_restart(sk, delta);
+}
/* Determine a window scaling and initial window to offer. */
void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd,