[ofa-general] [Bug 447] New: ib_ipoib kernel 2.6.9-34 panic when routing to 10G ethernet

bugzilla-daemon at lists.openfabrics.org bugzilla-daemon at lists.openfabrics.org
Mon Mar 12 10:24:55 PDT 2007


https://bugs.openfabrics.org/show_bug.cgi?id=447

           Summary: ib_ipoib kernel 2.6.9-34 panic when routing to 10G
                    ethernet
           Product: OpenFabrics Linux
           Version: 1.1
          Platform: X86-64
        OS/Version: RHEL 4
            Status: NEW
          Severity: blocker
          Priority: P1
         Component: IPoIB
        AssignedTo: bugzilla at openib.org
        ReportedBy: DarylGrunau at gmail.com


We're experiencing kernel panics of the following ilk on our I/O nodes used as
routers between our IB fabric and 10GE network (providing service to a Panasas
filesystem).  The panic can be triggered by simply mounting the Panasas
filesystem via the I/O node - some time later (as soon as 1 minute, and
sometimes overnight/weekend) the node panics.  Using the compute-node-mounted
filesystem accelerates the timetable.

Kernel BUG at dev:1121
invalid operand: 0000 [1] SMP 
CPU 7 
Modules linked in: myri10ge(U) ib_ipoib ib_mthca ib_uverbs ib_umad ib_ucm ib_sa
ib_cm ib_mad ib_core bluesmoke_k8 bluesmoke_mc perfctr ipmi_devintf ipmi_si
ipmi_msghandler bnx2 ext3 jbd nfs lockd nfs_acl sunrpc
Pid: 0, comm: swapper Not tainted 2.6.9-34.ELsmp.lanl
RIP: 0010:[<ffffffff802aafc2>] <ffffffff802aafc2>{__skb_linearize+62}
RSP: 0018:00000102270efcf8  EFLAGS: 00010203
RAX: 0000000000000001 RBX: 000000000000001c RCX: 000001061fef7680
RDX: 00000000ffffffdc RSI: 0000000000000220 RDI: 000001061fef7600
RBP: 000001021fedabc0 R08: 0000000000000000 R09: 000000000000003c
R10: 0000000000000000 R11: 0000000000000000 R12: 000001021f459a80
R13: 0000000000000000 R14: 000001081d741000 R15: 0000000000000000
FS:  0000002a95ac76e0(0000) GS:ffffffff804d8600(0000) knlGS:0000000000000000
CS:  0010 DS: 0018 ES: 0018 CR0: 000000008005003b
CR2: 0000000000429ff0 CR3: 00000000dfcae000 CR4: 00000000000006e0
Process swapper (pid: 0, threadinfo 000001081ff38000, task 0000010220035030)
Stack: 000001081d741000 000001081d741000 00000000fffffff4 000001021f459a80 
       0000000000000000 ffffffff802ab133 000001021fedabc0 000001021f459ac0 
       000001021fedabc0 ffffffff802b01c8 
Call Trace:<IRQ> <ffffffff802ab133>{dev_queue_xmit+93}
<ffffffff802b01c8>{neigh_resolve_output+578} 
       <ffffffff802afdc4>{neigh_update+626}
<ffffffff802e62a7>{arp_process+1257} 
       <ffffffffa01766a6>{:ib_ipoib:ipoib_ib_completion+936} 
       <ffffffff802ab87d>{netif_receive_skb+590}
<ffffffff802ab939>{process_backlog+136} 
       <ffffffff802aba43>{net_rx_action+129}
<ffffffff8013bf38>{__do_softirq+88} 
       <ffffffff8013bfe1>{do_softirq+49} <ffffffff801131a7>{do_IRQ+328} 
       <ffffffff801107bf>{ret_from_intr+0}  <EOI>
<ffffffff8010e749>{default_idle+0} 
       <ffffffff8010e769>{default_idle+32} <ffffffff8010e7dc>{cpu_idle+26} 


Code: 0f 0b 41 ee 31 80 ff ff ff ff 61 04 85 d2 b8 00 00 00 00 0f 
RIP <ffffffff802aafc2>{__skb_linearize+62} RSP <00000102270efcf8>
 <0>Kernel panic - not syncing: Oops

----------------

Our HCA hardware/firmware is:

-bash-3.00# ./ibv_devinfo 
hca_id: mthca0
        fw_ver:                         5.1.937
        node_guid:                      0002:c902:0023:85cc
        sys_image_guid:                 0002:c902:0023:85cf
        vendor_id:                      0x02c9
        vendor_part_id:                 25218
        hw_ver:                         0xA0
        board_id:                       MT_0370110001
        phys_port_cnt:                  2
                port:   1
                        state:                  PORT_ACTIVE (4)
                        max_mtu:                2048 (4)
                        active_mtu:             2048 (4)
                        sm_lid:                 1
                        port_lid:               69
                        port_lmc:               0x00

                port:   2
                        state:                  PORT_DOWN (1)
                        max_mtu:                2048 (4)
                        active_mtu:             512 (2)
                        sm_lid:                 0
                        port_lid:               0
                        port_lmc:               0x00



-bash-3.00# lspci -vvv

[[ snip ]]
41:00.0 InfiniBand: Mellanox Technologies MT25208 InfiniHost III Ex (rev a0)
        Subsystem: Mellanox Technologies MT25208 InfiniHost III Ex
        Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr+
Stepping- SERR- FastB2B-
        Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort-
<MAbort- >SERR- <PERR-
        Latency: 0, Cache Line Size 10
        Interrupt: pin A routed to IRQ 209
        Region 0: Memory at e1700000 (64-bit, non-prefetchable) [size=1M]
        Region 2: Memory at e1800000 (64-bit, prefetchable) [size=8M]
        Capabilities: [40] Power Management version 2
                Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot-,D3cold-)
                Status: D0 PME-Enable- DSel=0 DScale=0 PME-
        Capabilities: [48] Vital Product Data
        Capabilities: [90] Message Signalled Interrupts: 64bit+ Queue=0/5
Enable-
                Address: 0000000000000000  Data: 0000
        Capabilities: [84] MSI-X: Enable- Mask- TabSize=32
                Vector table: BAR=0 offset=00082000
                PBA: BAR=0 offset=00082200
        Capabilities: [60] Express Endpoint IRQ 0
                Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag+
                Device: Latency L0s <64ns, L1 unlimited
                Device: AtnBtn- AtnInd- PwrInd-
                Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
                Device: RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
                Device: MaxPayload 128 bytes, MaxReadReq 4096 bytes
                Link: Supported Speed 2.5Gb/s, Width x8, ASPM L0s, Port 8
                Link: Latency L0s unlimited, L1 unlimited
                Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
                Link: Speed 2.5Gb/s, Width x8

[[ snip ]]

--------------

We are running a patched kernel (perfctr & bluesmoke/EDAC only) from RHEL4
update 3 with IB drivers from Voltaire's GridStack-4.1.5_4: 
   dapl-1.2.0-0.x86_64.rpm
   dapl-devel-1.2.0-0.x86_64.rpm
   ibutils-1.0-0.x86_64.rpm
   kernel-ib-1.1-2.6.9_34.ELsmp.lanl.x86_64.rpm
   kernel-ib-devel-1.1-2.6.9_34.ELsmp.lanl.x86_64.rpm
   libibcm-0.9.0-0.x86_64.rpm
   libibcm-devel-0.9.0-0.x86_64.rpm
   libibcommon-1.0-0.x86_64.rpm
   libibcommon-devel-1.0-0.x86_64.rpm
   libibmad-1.0-0.x86_64.rpm
   libibmad-devel-1.0-0.x86_64.rpm
   libibumad-1.0-0.x86_64.rpm
   libibumad-devel-1.0-0.x86_64.rpm
   libibverbs-1.0.4-0.x86_64.rpm
   libibverbs-devel-1.0.4-0.x86_64.rpm
   libibverbs-utils-1.0.4-0.x86_64.rpm
   libipathverbs-1.0-0.x86_64.rpm
   libipathverbs-devel-1.0-0.x86_64.rpm
   libmthca-1.0.3-0.x86_64.rpm
   libmthca-devel-1.0.3-0.x86_64.rpm
   libopensm-2.0.0-0.x86_64.rpm
   libopensm-devel-2.0.0-0.x86_64.rpm
   libosmcomp-2.0.0-0.x86_64.rpm
   libosmcomp-devel-2.0.0-0.x86_64.rpm
   libosmvendor-2.0.0-0.x86_64.rpm
   libosmvendor-devel-2.0.0-0.x86_64.rpm
   librdmacm-0.9.0-0.x86_64.rpm
   librdmacm-devel-0.9.0-0.x86_64.rpm
   librdmacm-utils-0.9.0-0.x86_64.rpm
   mpitests_openmpi_gcc-2.0-0.x86_64.rpm
   mstflint-1.0-0.x86_64.rpm
   ofed-docs-1.1-0.noarch.rpm
   ofed-scripts-1.1-0.noarch.rpm
   openib-diags-1.1.0-0.x86_64.rpm
   openmpi_gcc-1.1.1-1.x86_64.rpm
   perftest-1.0-0.x86_64.rpm
   tvflash-0.9.0-0.x86_64.rpm

Our kernel module info and interface configs look like this:

-bash-3.00# cat /etc/modprobe.conf
alias eth2 myri10ge
options myri10ge myri10ge_lro=0

-bash-3.00# lsmod
Module                  Size  Used by
myri10ge               53656  0 
ib_ipoib               45641  0 
ib_mthca              129505  1 
ib_uverbs              41841  3 
ib_umad                18929  0 
ib_ucm                 21193  0 
ib_sa                  16213  1 ib_ipoib
ib_cm                  39217  1 ib_ucm
ib_mad                 40169  4 ib_mthca,ib_umad,ib_sa,ib_cm
ib_core                53313  8
ib_ipoib,ib_mthca,ib_uverbs,ib_umad,ib_ucm,ib_sa,ib_cm,ib_mad
bluesmoke_k8           18405  0 
bluesmoke_mc           26377  5 bluesmoke_k8
perfctr                46305  0 
ipmi_devintf           11985  0 
ipmi_si                40033  0 
ipmi_msghandler        33093  2 ipmi_devintf,ipmi_si
bnx2                  147217  0 
ext3                  137809  0 
jbd                    68977  1 ext3
nfs                   243825  1 
lockd                  77809  2 nfs
nfs_acl                 5185  1 nfs
sunrpc                174905  5 nfs,lockd,nfs_acl

-bash-3.00# ifconfig ib0
ib0       Link encap:UNSPEC  HWaddr
00-00-00-00-00-00-00-00-00-00-00-00-00-00-00-00  
          inet addr:10.160.137.141  Bcast:10.160.159.255  Mask:255.255.224.0
          UP BROADCAST RUNNING MULTICAST  MTU:2044  Metric:1
          RX packets:6119 errors:0 dropped:0 overruns:0 frame:0
          TX packets:1856 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:128 
          RX bytes:520392 (508.1 KiB)  TX bytes:157844 (154.1 KiB)

-bash-3.00# ifconfig eth2
eth2      Link encap:Ethernet  HWaddr 00:60:DD:47:B3:10  
          inet addr:10.160.168.74  Bcast:10.160.168.79  Mask:255.255.255.248
          UP BROADCAST RUNNING MULTICAST  MTU:1500  Metric:1
          RX packets:1762 errors:0 dropped:0 overruns:0 frame:0
          TX packets:4416 errors:0 dropped:0 overruns:0 carrier:0
          collisions:0 txqueuelen:1000 
          RX bytes:172374 (168.3 KiB)  TX bytes:486056 (474.6 KiB)
          Interrupt:74 

Note that the Myri10G driver sets eth2 to MTU=9000 by default; here we have it
at MTU=1500 (to baseline).  We are currently implementing jumbo frames to see
if the problem changes.  Any help/information you can provide re: this problem
would be greatly appreciated!

Daryl Grunau


-- 
Configure bugmail: https://bugs.openfabrics.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.




More information about the general mailing list