tcp: revert F-RTO extension to detect more spurious timeouts
authorYuchung Cheng <ycheng@google.com>
Tue, 27 Feb 2018 22:15:02 +0000 (14:15 -0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Fri, 9 Mar 2018 06:41:14 +0000 (22:41 -0800)
commit0ab87ec99e9998b908281e92234b87d3d2e27e49
treef2c3f69c47cfe0e6464f3c4016f76160748445b7
parentcc8dadb8c0f45ab5397d956487a8b0dad6c70a67
tcp: revert F-RTO extension to detect more spurious timeouts

[ Upstream commit fc68e171d376c322e6777a3d7ac2f0278b68b17f ]

This reverts commit 89fe18e44f7ee5ab1c90d0dff5835acee7751427.

While the patch could detect more spurious timeouts, it could cause
poor TCP performance on broken middle-boxes that modifies TCP packets
(e.g. receive window, SACK options). Since the performance gain is
much smaller compared to the potential loss. The best solution is
to fully revert the change.

Fixes: 89fe18e44f7e ("tcp: extend F-RTO to catch more spurious timeouts")
Reported-by: Teodor Milkov <tm@del.bg>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@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