tcp: frto should not set snd_cwnd to 0
authorEric Dumazet <edumazet@google.com>
Sun, 3 Feb 2013 09:13:05 +0000 (09:13 +0000)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Thu, 14 Feb 2013 18:49:06 +0000 (10:49 -0800)
commit2813296332187d222b96363fe29f10929f7a5228
tree10dfdbd0714285dbb4385bfd38f67ae968b6a4aa
parent42671f1e6fd8922b071bd3fd3e0cfad7226c654d
tcp: frto should not set snd_cwnd to 0

[ Upstream commit 2e5f421211ff76c17130b4597bc06df4eeead24f ]

Commit 9dc274151a548 (tcp: fix ABC in tcp_slow_start())
uncovered a bug in FRTO code :
tcp_process_frto() is setting snd_cwnd to 0 if the number
of in flight packets is 0.

As Neal pointed out, if no packet is in flight we lost our
chance to disambiguate whether a loss timeout was spurious.

We should assume it was a proper loss.

Reported-by: Pasi Kärkkäinen <pasik@iki.fi>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
net/ipv4/tcp_input.c