diff options
author | Andrey Vagin <avagin@openvz.org> | 2016-06-27 15:33:56 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-06-30 08:15:31 -0400 |
commit | b1ed4c4fa9a5ccf325184fd90edc50978ef6e33a (patch) | |
tree | eb298a85a5f016c52ad375f351bf171eec99152a /net | |
parent | 641f7e405ed208cfeb6b52145252675b51c43180 (diff) | |
download | linux-b1ed4c4fa9a5ccf325184fd90edc50978ef6e33a.tar.gz linux-b1ed4c4fa9a5ccf325184fd90edc50978ef6e33a.tar.bz2 linux-b1ed4c4fa9a5ccf325184fd90edc50978ef6e33a.zip |
tcp: add an ability to dump and restore window parameters
We found that sometimes a restored tcp socket doesn't work.
A reason of this bug is incorrect window parameters and in this case
tcp_acceptable_seq() returns tcp_wnd_end(tp) instead of tp->snd_nxt. The
other side drops packets with this seq, because seq is less than
tp->rcv_nxt ( tcp_sequence() ).
Data from a send queue is sent only if there is enough space in a
window, so when we restore unacked data, we need to expand a window to
fit this data.
This was in a first version of this patch:
"tcp: extend window to fit all restored unacked data in a send queue"
Then Alexey recommended me to restore window parameters instead of
adjusted them according with data in a sent queue. This sounds resonable.
rcv_wnd has to be restored, because it was reported to another side
and the offered window is never shrunk.
One of reasons why we need to restore snd_wnd was described above.
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: James Morris <jmorris@namei.org>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r-- | net/ipv4/tcp.c | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5c7ed147449c..108ef2a6665c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2277,6 +2277,38 @@ static inline bool tcp_can_repair_sock(const struct sock *sk) ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_ESTABLISHED)); } +static int tcp_repair_set_window(struct tcp_sock *tp, char __user *optbuf, int len) +{ + struct tcp_repair_window opt; + + if (!tp->repair) + return -EPERM; + + if (len != sizeof(opt)) + return -EINVAL; + + if (copy_from_user(&opt, optbuf, sizeof(opt))) + return -EFAULT; + + if (opt.max_window < opt.snd_wnd) + return -EINVAL; + + if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) + return -EINVAL; + + if (after(opt.rcv_wup, tp->rcv_nxt)) + return -EINVAL; + + tp->snd_wl1 = opt.snd_wl1; + tp->snd_wnd = opt.snd_wnd; + tp->max_window = opt.max_window; + + tp->rcv_wnd = opt.rcv_wnd; + tp->rcv_wup = opt.rcv_wup; + + return 0; +} + static int tcp_repair_options_est(struct tcp_sock *tp, struct tcp_repair_opt __user *optbuf, unsigned int len) { @@ -2604,6 +2636,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else tp->tsoffset = val - tcp_time_stamp; break; + case TCP_REPAIR_WINDOW: + err = tcp_repair_set_window(tp, optval, optlen); + break; case TCP_NOTSENT_LOWAT: tp->notsent_lowat = val; sk->sk_write_space(sk); @@ -2860,6 +2895,28 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return -EINVAL; break; + case TCP_REPAIR_WINDOW: { + struct tcp_repair_window opt; + + if (get_user(len, optlen)) + return -EFAULT; + + if (len != sizeof(opt)) + return -EINVAL; + + if (!tp->repair) + return -EPERM; + + opt.snd_wl1 = tp->snd_wl1; + opt.snd_wnd = tp->snd_wnd; + opt.max_window = tp->max_window; + opt.rcv_wnd = tp->rcv_wnd; + opt.rcv_wup = tp->rcv_wup; + + if (copy_to_user(optval, &opt, len)) + return -EFAULT; + return 0; + } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; |