[openib-general] Re: ib_uat kernel panic without async callback

[Hal Rosenstock]

Hi Arlin,

On Mon, 2005-07-11 at 18:37, Davis, Arlin R wrote:
> I was attempting to call ib_at_route_by_ip() in sync mode and get the
> following oops:  
> 
> You can change the att.c (line 193) example as follow to duplicate:
> 
>   r = ib_at_route_by_ip(0x1400a8c0, 0, 0, 0,
>                                       att_rt + i, NULL, NULL);
> 
> I will go back to async mode for now.
> 
> Thanks,
> 
> -arlin
> 
> Jul 11 15:01:17 iclust-20 kernel: Unable to handle kernel NULL pointer
> dereference at 0000000000000000 RIP:
> Jul 11 15:01:17 iclust-20 kernel:
> <ffffffff880a449c>{:ib_uat:ib_uat_route_by_ip+204}
> Jul 11 15:01:17 iclust-20 kernel: PGD 38fa3067 PUD 2e7c7067 PMD 0
> Jul 11 15:01:17 iclust-20 kernel: Oops: 0000 [1] SMP
> Jul 11 15:01:17 iclust-20 kernel: CPU 0
> Jul 11 15:01:17 iclust-20 kernel: Modules linked in: ib_att ib_uat
> ib_at ib_ucm ib_cm ib_umad ib_uverbs ib_ipoib ib_sa ib_mthca ib_mad
> ib_core dm_snapshot dm_zero dm_mirror ext3 jbd dm_mod
> Jul 11 15:01:17 iclust-20 kernel: Pid: 6320, comm: dtestib Tainted:
> P      2.6.11
> Jul 11 15:01:17 iclust-20 kernel: RIP: 0010:[<ffffffff880a449c>]
> <ffffffff880a449c>{:ib_uat:ib_uat_route_by_ip+204}
> Jul 11 15:01:17 iclust-20 kernel: RSP: 0018:ffff810030c9be78  EFLAGS:
> 00010282
> Jul 11 15:01:17 iclust-20 kernel: RAX: 0000000000000000 RBX:
> 00000000fffffff4 RCX: 0000000000040000
> Jul 11 15:01:17 iclust-20 kernel: RDX: 00000000ffffff01 RSI:
> 0000000000000292 RDI: ffffffff80453f80
> Jul 11 15:01:17 iclust-20 kernel: RBP: ffff81002f342380 R08:
> ffff810038d54d80 R09: ffff81003e498c80
> Jul 11 15:01:17 iclust-20 kernel: R10: 00000000ffffffff R11:
> 0000000000000000 R12: ffff81003e498c80
> Jul 11 15:01:17 iclust-20 kernel: R13: ffff810038d54d80 R14:
> ffff810030c9bf50 R15: 00007ffffffff7c0
> Jul 11 15:01:17 iclust-20 kernel: FS:  00002aaaaabc53e0(0000)
> GS:ffffffff80580280(0000) knlGS:0000000000000000
> Jul 11 15:01:17 iclust-20 kernel: CS:  0010 DS: 0000 ES: 0000 CR0:
> 000000008005003b
> Jul 11 15:01:17 iclust-20 kernel: CR2: 0000000000000000 CR3:
> 0000000033975000 CR4: 00000000000006e0
> Jul 11 15:01:17 iclust-20 kernel: Process dtestib (pid: 6320,
> threadinfo ffff810030c9a000, task ffff810038a88b00)
> Jul 11 15:01:17 iclust-20 kernel: Stack: ffff81003e890940
> ffff810030c9bf70 2ca2070a1300a8c0 0000000000000000
> Jul 11 15:01:17 iclust-20 kernel:        0000000000518cb8
> 0000000000000000 00007ffffffff210 ffffffff88099b82
> Jul 11 15:01:17 iclust-20 kernel:        ffff810039167820
> 0000000000000030
> Jul 11 15:01:17 iclust-20 kernel: Call
> Trace:<ffffffff88099b82>{:ib_ucm:ib_ucm_create_id+130}
> <ffffffff880a4eed>{:ib_uat:ib_uat_write+157}
> Jul 11 15:01:17 iclust-20 kernel:       
> <ffffffff8017aca4>{vfs_write+196} <ffffffff8017ae03>{sys_write+83}
> Jul 11 15:01:17 iclust-20 kernel:       
> <ffffffff8010e30a>{system_call+126}
> Jul 11 15:01:17 iclust-20 kernel:
> Jul 11 15:01:17 iclust-20 kernel: Code: 48 8b 00 48 89 45 78 48 8b 44
> 24 28 48 8b 40 08 48 89 85 80
> Jul 11 15:01:17 iclust-20 kernel: RIP
> <ffffffff880a449c>{:ib_uat:ib_uat_route_by_ip+204} RSP
> <ffff810030c9be78>
> Jul 11 15:01:17 iclust-20 kernel: CR2: 0000000000000000

How was IPoIB configured ? Was ib0 on the 192.168.0.x subnet ?

What do you mean by "back to async mode" ? Did you use async mode before
?

-- Hal