A fix is available
APAR status
Closed as program error.
Error description
Panic is in memmove64 when called from m_cat being called from ip_reass. One such stack is: pvthread+011700 STACK: [0000F4D4]___memmove64+0000D4 () [004F42C4]m_cat+0000E4 (??, ??) [0458AF30]ip_reass+000A30 (??) [0458BD98]ipintr_noqueue_post_fw+0006B8 (F1000A058AA00B18, F10005005C634E00, F1000A001AB47F40) [0458D2A0]ipintr_noqueue+000120 (??, ??, ??) [0458E8BC]in_newstack+000020 () [04587390]in_flip_and_run+000070 (??, ??, ??) [04586728]dogisr+0003C8 (F1000A001993C068, F10005005C634E00, F100050008702000) [04412BD8]eth_std_receive+000378 (??, ??, ??) [04410BA8]eth_receive+0001A8 (??, ??) [043EB230]rx_handler+000790 (??, ??) [043ED8D4]goent_slih+000794 (??) [0026752C]i_poll_soft+00012C (??) [00266E40]i_softmod+000620 () [00141C8C]flih_util+000258 () Many factors need to be involved at the same time. The errctrl for netmalloc.police needs to be detail or higher. There must be some fragments being promoted. In this case, the 2K memory fragment was being promoted to a full page. The network must also be fragmenting the packets for some reason which implies that PMTU is turned off or is somehow not being 100% effective.
Local fix
A number of possible local work around. Turn down the errctrl for netmalloc.police component, turn off page promotion of 2K pages, make sure IP fragmentation does not occur.
Problem summary
System crash with following stack pvthread+011700 STACK: 0000F4D4 ___memmove64+0000D4 () 004F42C4 m_cat+0000E4 (??, ??) 0458AF30 ip_reass+000A30 (??) 0458BD98 ipintr_noqueue_post_fw+0006B8 (F1000A058AA00B18, F10005005C634E00, F1000A001AB47F40) 0458D2A0 ipintr_noqueue+000120 (??, ??, ??) 0458E8BC in_newstack+000020 () 04587390 in_flip_and_run+000070 (??, ??, ??) 04586728 dogisr+0003C8 (F1000A001993C068, F10005005C634E00, F100050008702000) 04412BD8 eth_std_receive+000378 (??, ??, ??) 04410BA8 eth_receive+0001A8 (??, ??) 043EB230 rx_handler+000790 (??, ??) 043ED8D4 goent_slih+000794 (??) 0026752C i_poll_soft+00012C (??) 00266E40 i_softmod+000620 () 00141C8C flih_util+000258 ()
Problem conclusion
Network memory alloc code is mofied to return the exact size of the memory that is allocated. This prevents IP layer from accessing the unallocated memory and also prevents the system from crash
Temporary fix
Comments
APAR Information
APAR number
IV22691
Reported component name
AIX V7.1
Reported component ID
5765H4000
Reported release
710
Status
CLOSED PER
PE
NoPE
HIPER
NoHIPER
Submitted date
2012-06-09
Closed date
2012-06-09
Last modified date
2013-04-10
APAR is sysrouted FROM one or more of the following:
APAR is sysrouted TO one or more of the following:
Fix information
Fixed component name
AIX V7.1
Fixed component ID
5765H4000
Applicable component levels
R710 PSY U847987
UP12/07/17 I 1000
PTF to Fileset Mapping
U847987 bos.mp64 7.1.1.16
[{"Business Unit":{"code":"BU054","label":"Systems w\/TPS"},"Product":{"code":"SSMV87","label":"AIX 6.1 Enterprise Edition"},"Component":"","ARM Category":[],"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"710","Edition":"","Line of Business":{"code":"LOB08","label":"Cognitive Systems"}},{"Business Unit":{"code":"BU058","label":"IBM Infrastructure w\/TPS"},"Product":{"code":"SSMVAX","label":"AIX Express Edition"},"Component":"","ARM Category":[],"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"710","Edition":"","Line of Business":{"code":"LOB08","label":"Cognitive Systems"}},{"Business Unit":{"code":"BU054","label":"Systems w\/TPS"},"Product":{"code":"SG11R","label":"AIX 7.1 HIPERS, APARs and Fixes"},"Component":"","ARM Category":[],"Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"710","Edition":"","Line of Business":{"code":"","label":""}}]
Document Information
Modified date:
10 April 2013