lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list] 
Date:   Wed, 13 Sep 2017 07:40:47 -0700
From:   Eric Dumazet <eric.dumazet@...il.com>
To:     liujian <liujian56@...wei.com>
Cc:     davem@...emloft.net, kuznet@....inr.ac.ru, yoshfuji@...ux-ipv6.org,
        edumazet@...gle.com, ycheng@...gle.com, hkchu@...gle.com,
        netdev@...r.kernel.org, weiyongjun1@...wei.com,
        wangkefeng 00227729 <wangkefeng.wang@...wei.com>
Subject: Re: [PATCH] tcp: TCP_USER_TIMEOUT can not work in tcp_probe_timer()

On Wed, 2017-09-13 at 15:15 +0800, liujian wrote:
> 
> 在 2017/9/13 14:56, liujian 写道:
> > 
> > 
> > 在 2017/9/12 23:38, Eric Dumazet 写道:
> >> On Tue, 2017-09-12 at 08:05 -0700, Eric Dumazet wrote:
> >>> On Tue, 2017-09-12 at 14:08 +0800, liujian wrote:
> >>>> Hi,
> >>>>
> >>>> In the scenario, tcp server side IP changed, and at that memont,
> >>>> userspace application still send data continuously;
> >>>> tcp_send_head(sk)'s timestamp always be refreshed.
> >>>>
> >>>> Here is the packetdrill script:
> >>>>
> >>>>    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
> >>>>    +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
> >>>>    +0 bind(3, ..., ...) = 0
> >>>>    +0 listen(3, 1) = 0
> >>>>
> >>>>    +0 < S 0:0(0) win 0 <mss 1460,sackOK,nop,nop,nop,wscale 7>
> >>>>    +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
> >>>>
> >>>>   +.1 < . 1:1(0) ack 1 win 65530
> >>>>    +0 accept(3, ..., ...) = 4
> >>>>
> >>>>    +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
> >>>>    +0 write(4, ..., 24) = 24
> >>>>    +0 > P. 1:25(24) ack 1 win 229
> >>>>    +.1 < . 1:1(0) ack 25 win 65530
> >>>>
> >>>> //change the ipaddress
> >>>>    +1 `ifconfig tun0 192.168.0.10/16`
> >>>>
> >>>>    +1 write(4, ..., 24) = 24
> >>>>    +1 write(4, ..., 24) = 24
> >>>>    +1 write(4, ..., 24) = 24
> >>>>    +1 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>    +3 write(4, ..., 24) = 24
> >>>>
> >>>>    +0 `ifconfig tun0 192.168.0.1/16`
> >>>>    +0 < . 1:1(0) ack 1 win 1000
> >>>>    +0 write(4, ..., 24) = -1
> >>>>
> >>>>
> >>>
> >>> This has nothing to do with the code patch you have changed.
> >>>
> >>> How have you tested your patch exactly ?
> >>>
> > I tested the patch, it can work.
> > 
> > [root@...alhost ~]# time ./gtests/net/packetdrill/packetdrill test.pkt
> > test.pkt:24: runtime error in write call: Expected result 24 but got -1 with errno 110 (Connection timed out)
> > 
> > real	0m5.356s
> > user	0m0.026s
> > sys	0m0.104s
> > 
> > [root@...alhost ~]# ss -toenmi src :8080
> > State       Recv-Q Send-Q               Local Address:Port                              Peer Address:Port
> > ESTAB       0      48                     192.168.0.1:8080                                 192.0.2.1:39559               timer:(persist,186ms,2) ino:37178 sk:6 <->
> > 	 skmem:(r0,rb369280,t0,tb87040,f1792,w2304,o0,bl0) sack cubic wscale:7,7 rto:301 backoff:2 rtt:100.253/37.643 mss:1460 cwnd:10 bytes_acked:24 segs_out:5 segs_in:3 send 1.2Mbps lastsnd:976 lastrcv:4082 lastack:3982 pacing_rate 2.3Mbps rcv_space:29200
> > 
> > 
> > if change the TCP_USER_TIMEOUT to 30s, test result as below:
> > 
> > [root@...alhost ~]#   time ./gtests/net/packetdrill/packetdrill test.pkt
> > test.pkt:37: runtime error in write call: Expected result 24 but got -1 with errno 110 (Connection timed out)
> > 
> > real	0m44.362s
> > user	0m0.018s
> > sys	0m0.110s
> > 
> > ESTAB       0      360                         192.168.0.1:8080                                      192.0.2.1:47577     timer:(persist,516ms,6) ino:18806 sk:5 <->
> > 	 skmem:(r0,rb369280,t0,tb87040,f1792,w2304,o0,bl0) sack cubic wscale:7,7 rto:301 backoff:6 rtt:100.228/37.623 mss:10 bytes_acked:24 segs_out:22 segs_in:3 send 1.2Mbps lastsnd:2343 lastrcv:40450 lastack:40350 pacing_rate 2.3Mbps rcv_sp
> > 
> >>
> >> lpaa23:~# ss -toenmi src :8080
> >> State      Recv-Q Send-Q Local Address:Port               Peer
> >> Address:Port              
> >> ESTAB      0      144    192.168.134.161:8080
> >> 192.0.2.1:51165               timer:(persist,8.262ms,5) ino:1
> >> 82083 sk:3 <->
> >> 	 skmem:(r0,rb359040,t0,tb46080,f1792,w2304,o0,bl0,d0) sack cubic
> >> wscale:7,8 rto:301 backoff:5 rtt:100.127/37.576 
> >> mss:1460 rcvmss:536 advmss:1460 cwnd:10 bytes_acked:24 segs_out:12
> >> segs_in:3 data_segs_out:12 send 1.2Mbps lastsnd:1370 l
> >> astrcv:13348 lastack:13248 pacing_rate 2.3Mbps delivery_rate 116.7Kbps
> >> app_limited busy:11346ms rcv_space:29200 notsent:1
> >> 44 minrtt:100.043userspace application still send data continuously
> >>
> >> This is the typical RTO timer, not zero window probe.
> >>
> > with the script, it is not zero window; but the code enter tcp_probe_timer.
> > ->tcp_sendmsg
> > -->tcp_push
> > ---->__tcp_push_pending_frames
> > ------>tcp_write_xmit
> > -------->tcp_transmit_skb (at this function, tcp_send_head(sk)'s timestamp was be refreshed)
> > ---------->ip_queue_xmit (can not find route, return -EHOSTUNREACH)
> > -------->tcp_transmit_skb (send fail, do not advance send head)
> > ------->tcp_check_probe_timer (reset ICSK_TIME_PROBE0 timer)
> sorry, change to
> ->tcp_sendmsg
> -->tcp_push
> ---->__tcp_push_pending_frames
> ------>tcp_write_xmit
> -------->tcp_transmit_skb (at this function, tcp_send_head(sk)'s timestamp was be refreshed)
> ---------->ip_queue_xmit (can not find route, return -EHOSTUNREACH)
> ------>tcp_write_xmit (send fail, do not advance send head)
> ------>tcp_check_probe_timer (reset ICSK_TIME_PROBE0 timer)


OK but :

1) keepalive_time_elapsed() returns jiffies, and you compare it to a ms
value. It will break on kernels with HZ=100


2) keepalive_time_elapsed() is reset every time a packet is received.

With following packetdrill your patch (even if we fix 1)) breaks again


# ./packetdrill --local_ip 192.168.102.64 user_timeout.pkt
# cat user_timeout.pkt 

0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 `ifconfig tun0 192.168.102.64/16; ip ro add 192.0.2.1 dev tun0`

   +0 < S 0:0(0) win 0 <mss 1460,sackOK,nop,nop,nop,wscale 7>
   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>

  +.1 < . 1:1(0) ack 1 win 65530
   +0 accept(3, ..., ...) = 4

   +0 setsockopt(4, SOL_TCP, TCP_USER_TIMEOUT, [3000], 4) = 0
   +0 write(4, ..., 24) = 24
   +0 > P. 1:25(24) ack 1 win 115
   +.1 < . 1:1(0) ack 25 win 65530

//change the ipaddress
   +1 `ifconfig tun0 192.168.0.10/16`

   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24
   +1 write(4, ..., 24) = 24

   +0 `ifconfig tun0 192.168.102.64/16`
   +0 < . 1:2(1) ack 25 win 65530
   +0 `ifconfig tun0 192.168.0.10/16`

   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24
   +3 write(4, ..., 24) = 24

   +0 `ifconfig tun0 192.168.0.1/16`
   +0 < . 1:1(0) ack 1 win 1000
   +0 write(4, ..., 24) = -1


I would instead try to keep a meaningful value in
tcp_send_head(sk)->skb_mstamp if the transmit failed.

Or more exactly change skb->skb_mstamp only on (successfully)
transmitted skb.

I will provide a patch ( fixing net/ipv4/tcp_output.c )

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ