Description

I am using keepalive module to send keepalives to all the destinations registered with an application server which sits behind kamailio.
When Kamailio recieves 200 Ok. I take URI contact from 200 OK and pass it as a param to ka_add_destination function.Most of the time it works fine but sometimes kamailio crashes when it recieves 200 OK of OPTIONS.

Troubleshooting

Reproduction

I am able to reproduce it easily in below scenario :
All the URIs which we are feeding to KA module has this syntax :
sip:2003@10.50.8.11:9090;alias=10.50.8.150601;pb-ip=35.185.177.49;pb-pt=5060;tp=udp

  1. So request will be generate by KA module and it will be send to 10.50.8.11:9090 ( which is another port of same kamailio instance ) via UDP protocol.
  2. On recieving OPTION on 9090 port ,
    - We are calling handle_ruri_alias() function which will set $du =sip:10.50.8.1:5060;transport=udp
    - Modify RURI from sip:2003@10.50.8.11:9090;alias=10.50.8.150601;pb-ip=35.185.177.49;pb-pt=5060;tp=udp to
    sip:2003@35.185.177.49:5060;pb-ip=35.185.177.49;pb-pt=5060;transport=udp
    - and relay to 10.50.8.1
  3. 10.50.8.1 is another instance of Kamailio which will relay OPTION packet to final destination

Debugging Data

[root@SBC-4-2 /]# gdb kamailio core.67771
GNU gdb (GDB) Red Hat Enterprise Linux 7.6.1-110.el7                                                                                                  
Copyright (C) 2013 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.  Type "show copying"
and "show warranty" for details.
This GDB was configured as "x86_64-redhat-linux-gnu".
For bug reporting instructions, please see:
<http://www.gnu.org/software/gdb/bugs/>...
Reading symbols from /usr/local/sbin/kamailio...done.
[New LWP 67771]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
Core was generated by `/usr/local/sbin/kamailio -m 5000 -M 500 -P /run/kamailio/kamailio.pid'.
Program terminated with signal 11, Segmentation fault.
#0  0x00000000abcdefed in ?? ()
Missing separate debuginfos, use: debuginfo-install cyrus-sasl-lib-2.1.26-23.el7.x86_64 glibc-2.17-222.el7.x86_64 keyutils-libs-1.5.8-3.el7.x86_64 krb5-libs-1.15.1-19.el7.x86_64 libcom_err-1.42.9-12.el7_5.x86_64 libcurl-7.29.0-51.el7.x86_64 libevent-2.0.21-4.el7.x86_64 libgcc-4.8.5-36.el7_6.2.x86_64 libidn-1.28-4.el7.x86_64 libselinux-2.5-12.el7.x86_64 libssh2-1.4.3-10.el7_2.1.x86_64 libstdc++-4.8.5-36.el7_6.2.x86_64 libuuid-2.23.2-52.el7_5.1.x86_64 mariadb-libs-5.5.64-1.el7.x86_64 nspr-4.19.0-1.el7_5.x86_64 nss-3.36.0-5.el7_5.x86_64 nss-softokn-freebl-3.36.0-5.el7_5.x86_64 nss-util-3.36.0-1.el7_5.x86_64 openldap-2.4.44-15.el7_5.x86_64 openssl-libs-1.0.2k-16.el7_6.1.x86_64 pcre-8.32-17.el7.x86_64 zlib-1.2.7-18.el7.x86_64
(gdb) bt full
#0  0x00000000abcdefed in ?? ()
No symbol table info available.
#1  0x00007f931dc69c7e in ka_options_callback (t=0x7f91e58f05c0, type=1024, ps=0x7ffda0977bd0) at keepalive_core.c:126
        uri = {
          s = 0x7f91e58f63f0 "sip:2003@10.50.8.11:9090;alias=10.50.8.1~5060~1;pb-ip=35.185.177.49;pb-pt=5060;tp=udp>\r\nFrom: <sip:keepalive@fromsbc>;tag=c7bfd876be500fff196414658218fc27-d6989f6d\r\nCSeq: 10 OPTIONS\r\nCall-ID: 3f2c3c7c"..., len = 85}
        msg = 0x0
        state = 2
        state_routes = {0x7f931dc6f844 "", 0x7f931dc6f93d "keepalive:dst-up", 0x7f931dc6f94e "keepalive:dst-down"}
        ka_dest = 0x7f91e5898988
        __FUNCTION__ = "ka_options_callback"
#2  0x00007f9324bfddd8 in run_trans_callbacks_internal (cb_lst=0x7f91e58f0638, type=1024, trans=0x7f91e58f05c0, params=0x7ffda0977bd0)
    at t_hooks.c:258
        cbp = 0x7f91e58f6590
        backup_from = 0xb2a750 <def_list+16>
        backup_to = 0xb2a758 <def_list+24>
        backup_dom_from = 0xb2a760 <def_list+32>
        backup_dom_to = 0xb2a768 <def_list+40>
        backup_uri_from = 0xb2a740 <def_list>
        backup_uri_to = 0xb2a748 <def_list+8>
        backup_xavps = 0xb29fd0 <_xavp_list_head>
        backup_xavus = 0xb29fd8 <_xavu_list_head>
        backup_xavis = 0xb29fe0 <_xavi_list_head>
        __FUNCTION__ = "run_trans_callbacks_internal"
#3  0x00007f9324bfdf0a in run_trans_callbacks (type=1024, trans=0x7f91e58f05c0, req=0x0, rpl=0xffffffffffffffff, code=408) at t_hooks.c:285
        params = {req = 0x0, rpl = 0xffffffffffffffff, param = 0x7f91e58f65a0, code = 408, flags = 0, branch = 0, t_rbuf = 0x0, dst = 0x0, 
          send_buf = {s = 0x0, len = 0}}
#4  0x00007f9324b943f1 in local_reply (t=0x7f91e58f05c0, p_msg=0xffffffffffffffff, branch=0, msg_status=408, cancel_data=0x7ffda0977d50)
    at t_reply.c:2265
        local_store = 0
        local_winner = 0
        reply_status = RPS_COMPLETED
        winning_msg = 0xffffffffffffffff
        winning_code = 408
        totag_retr = 0
---Type <return> to continue, or q <return> to quit---
        __FUNCTION__ = "local_reply"
#5  0x00007f9324bcc9fd in fake_reply (t=0x7f91e58f05c0, branch=0, code=408) at timer.c:290
        cancel_data = {cancel_bitmap = 0, reason = {cause = 0, u = {text = {s = 0x0, len = -443611712}, e2e_cancel = 0x0, packed_hdrs = {s = 0x0, 
                len = -443611712}}}}
        do_cancel_branch = 0
        reply_status = 67771
#6  0x00007f9324bcce95 in final_response_handler (r_buf=0x7f91e58f0860, t=0x7f91e58f05c0) at timer.c:462
        silent = 0
        branch_ret = 0
        prev_branch = 0
        now = 0
#7  0x00007f9324bccf56 in retr_buf_handler (ticks=112894435, tl=0x7f91e58f0880, p=0xfa0) at timer.c:518
        rbuf = 0x7f91e58f0860
        fr_remainder = 1
        retr_remainder = 32657
        retr_interval = 3847088576
        new_retr_interval_ms = 6989250208
        crt_retr_interval_ms = 140264594074048
        t = 0x7f91e58f05c0
        __FUNCTION__ = "retr_buf_handler"
#8  0x00000000004b7bcd in slow_timer_main () at core/timer.c:1105
        n = 12
        ret = 4294967295
        tl = 0x7f91e58f0880
        i = 700
        __FUNCTION__ = "slow_timer_main"
#9  0x000000000042a4c3 in main_loop () at main.c:1737
        i = 16
        pid = 0
        si = 0x0
        si_desc = "udp receiver child=15 sock=10.50.8.11:9090\000:0:0:11]:5060\000\061:5060)\000\000\000\000\000\000\000\000\000\000F\345\221\177\000\000\000\000\000\000\000\000\000\000\bLv\345\221\177\000\000P\201\227\240\375\177\000\000\210\212K\000\000\000\000\000\260\270A\000\000\000\000\000\b{\017(\223\177\000"
        nrprocs = 16
        woneinit = 1
---Type <return> to continue, or q <return> to quit---
        __FUNCTION__ = "main_loop"
#10 0x0000000000433a66 in main (argc=7, argv=0x7ffda09786b8) at main.c:2856
        cfg_stream = 0x27e7010
        c = -1
        r = 0
        tmp = 0x7ffda0979f26 ""
        tmp_len = 0
        port = 0
        proto = 0
        ahost = 0x0
        aport = 0
        options = 0x7d2498 ":f:cm:M:dVIhEeb:l:L:n:vKrRDTN:W:w:t:u:g:P:G:SQ:O:a:A:x:X:Y:"
        ret = -1
        seed = 791137056
        rfd = 4
        debug_save = 0
        debug_flag = 0
        dont_fork_cnt = 0
        n_lst = 0x7f934718ea00 <intel_02_known>
        p = 0x0
        st = {st_dev = 23, st_ino = 30676, st_nlink = 2, st_mode = 16877, st_uid = 0, st_gid = 5001, __pad0 = 0, st_rdev = 0, st_size = 40, 
          st_blksize = 4096, st_blocks = 0, st_atim = {tv_sec = 1597841333, tv_nsec = 176009291}, st_mtim = {tv_sec = 1597841333, 
            tv_nsec = 166009247}, st_ctim = {tv_sec = 1597841333, tv_nsec = 176009291}, __unused = {0, 0, 0}}
        tbuf = "\377\377\377\377", '\000' <repeats 12 times>, "\340\263\001G\223\177\000\000\310T\320G\223\177", '\000' <repeats 90 times>, "p\342\252\000\000\000\000\000\260\270A\000\000\000\000\000\260\206\227\240\375\177", '\000' <repeats 26 times>, "\036_\260G\223\177\000\000\001", '\000' <repeats 23 times>...
        option_index = 0
        long_options = {{name = 0x7d468f "help", has_arg = 0, flag = 0x0, val = 104}, {name = 0x7cfc94 "version", has_arg = 0, flag = 0x0, 
            val = 118}, {name = 0x7d4694 "alias", has_arg = 1, flag = 0x0, val = 1024}, {name = 0x7d469a "subst", has_arg = 1, flag = 0x0, 
            val = 1025}, {name = 0x7d46a0 "substdef", has_arg = 1, flag = 0x0, val = 1026}, {name = 0x7d46a9 "substdefs", has_arg = 1, flag = 0x0, 
            val = 1027}, {name = 0x7d46b3 "server-id", has_arg = 1, flag = 0x0, val = 1028}, {name = 0x7d46bd "loadmodule", has_arg = 1, flag = 0x0, 
            val = 1029}, {name = 0x7d46c8 "modparam", has_arg = 1, flag = 0x0, val = 1030}, {name = 0x7d46d1 "log-engine", has_arg = 1, flag = 0x0, 
            val = 1031}, {name = 0x7d46dc "debug", has_arg = 1, flag = 0x0, val = 1032}, {name = 0x0, has_arg = 0, flag = 0x0, val = 0}}
        __FUNCTION__ = "main"
(gdb) 

Log Messages

Aug 19 12:58:26 SBC-4-2 /usr/local/sbin/kamailio[67772]: CRITICAL: <core> [core/mem/q_malloc.c:138]: qm_debug_check_frag(): BUG: qm: fragm. 0x7f91e5898950 (address 0x7f91e5898988) end overwritten (c0c0c0c1, abcdefed)! Memory allocator was called from core: core/usr_avp.c:626. Fragment marked by core: core/usr_avp.c:175. Exec from core/mem/q_malloc.c:511.
Aug 19 12:58:38 SBC-4-2 /usr/local/sbin/kamailio[67793]: CRITICAL: <core> [core/pass_fd.c:277]: receive_fd(): EOF on 94

SIP Traffic

(paste your sip traffic here)

Possible Solutions

Additional Information

[root@SBC-4-2 /]# kamailio -v
version: kamailio 5.4.0 (x86_64/linux) 6c4fce                                                                                                         
flags: USE_TCP, USE_TLS, USE_SCTP, TLS_HOOKS, USE_RAW_SOCKS, DISABLE_NAGLE, USE_MCAST, DNS_IP_HACK, SHM_MMAP, PKG_MALLOC, Q_MALLOC, F_MALLOC, TLSF_MALLOC, DBG_SR_MEMORY, USE_FUTEX, FAST_LOCK-ADAPTIVE_WAIT, USE_DNS_CACHE, USE_DNS_FAILOVER, USE_NAPTR, USE_DST_BLACKLIST, HAVE_RESOLV_RES
ADAPTIVE_WAIT_LOOPS 1024, MAX_RECV_BUFFER_SIZE 262144, MAX_URI_SIZE 1024, BUF_SIZE 65535, DEFAULT PKG_SIZE 8MB
poll method support: poll, epoll_lt, epoll_et, sigio_rt, select.
id: 6c4fce 
compiled on 14:16:47 Aug 14 2020 with gcc 4.8.5
[root@SBC-4-2 /]# uname -a
Linux SBC-4-2.netcarrier.net 5.1.0 #1 SMP Mon May 6 13:44:38 GMT 2019 x86_64 x86_64 x86_64 GNU/Linux


You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or unsubscribe.