summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
authorNeal Cardwell <ncardwell@google.com>2017-07-14 17:49:24 -0400
committerDavid S. Miller <davem@davemloft.net>2017-07-15 14:43:29 -0700
commit1d3648eb5d1fe9ed3d095ed8fa19ad11ca4c8bc0 (patch)
tree1383cf659bf210514b73ce560294e2a1fe8ee1c2 /net/ipv4
parent79135b89b8af304456bd67916b80116ddf03d7b6 (diff)
downloadlinux-1d3648eb5d1fe9ed3d095ed8fa19ad11ca4c8bc0.tar.bz2
tcp_bbr: remove sk_pacing_rate=0 transient during init
Fix a corner case noticed by Eric Dumazet, where BBR's setting sk->sk_pacing_rate to 0 during initialization could theoretically cause packets in the sending host to hang if there were packets "in flight" in the pacing infrastructure at the time the BBR congestion control state is initialized. This could occur if the pacing infrastructure happened to race with bbr_init() in a way such that the pacer read the 0 rather than the immediately following non-zero pacing rate. Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control") Reported-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_bbr.c1
1 files changed, 0 insertions, 1 deletions
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 3276140c2506..42e0017f2ebc 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -837,7 +837,6 @@ static void bbr_init(struct sock *sk)
minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */
- sk->sk_pacing_rate = 0; /* force an update of sk_pacing_rate */
bbr_init_pacing_rate_from_rtt(sk);
bbr->restore_cwnd = 0;