[PATCH AUTOSEL 4.18 23/56] tcp_bbr: in restart from idle, see if we should exit PROBE_RTT

From: Sasha Levin
Date: Wed Sep 19 2018 - 22:48:01 EST


From: Kevin Yang <yyd@xxxxxxxxxx>

[ Upstream commit 5490b32dce6932ea7ee8e3b2f76db2957c92af6e ]

This patch fix the case where BBR does not exit PROBE_RTT mode when
it restarts from idle. When BBR restarts from idle and if BBR is in
PROBE_RTT mode, BBR should check if it's time to exit PROBE_RTT. If
yes, then BBR should exit PROBE_RTT mode and restore the cwnd to its
full value.

Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Kevin Yang <yyd@xxxxxxxxxx>
Signed-off-by: Neal Cardwell <ncardwell@xxxxxxxxxx>
Reviewed-by: Yuchung Cheng <ycheng@xxxxxxxxxx>
Reviewed-by: Soheil Hassas Yeganeh <soheil@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
---
net/ipv4/tcp_bbr.c | 4 ++++
1 file changed, 4 insertions(+)

diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 5880015dee36..e99d6afb70ef 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -174,6 +174,8 @@ static const u32 bbr_lt_bw_diff = 4000 / 8;
/* If we estimate we're policed, use lt_bw for this many round trips: */
static const u32 bbr_lt_bw_max_rtts = 48;

+static void bbr_check_probe_rtt_done(struct sock *sk);
+
/* Do we estimate that STARTUP filled the pipe? */
static bool bbr_full_bw_reached(const struct sock *sk)
{
@@ -304,6 +306,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
*/
if (bbr->mode == BBR_PROBE_BW)
bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT);
+ else if (bbr->mode == BBR_PROBE_RTT)
+ bbr_check_probe_rtt_done(sk);
}
}

--
2.17.1