Server Crash on 4.1.12-103.6.1.el7uek.x86_64 at "RIP task_numa_find_cpu"

(Doc ID 2359810.1)

Last updated on FEBRUARY 11, 2018

Applies to:

Linux OS - Version Oracle Linux 6.7 with Unbreakable Enterprise Kernel [4.1.12] and later
Linux x86-64

Symptoms

Linux Server with kernel "4.1.12-103.6.1.el7uek.x86_64" crashed, the vmcore file shows below:

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

[2081949.752829] CPU: 54 PID: 39491 Comm: java Not tainted

4.1.12-103.6.1.el7uek.x86_64
[2081949.752942] Hardware name: ABC
[2081949.753062] task: ffff880e1a55e200 ti: ffff880ed6c58000 task.ti:
ffff880ed6c58000
[2081949.753169] RIP: 0010:[<ffffffff810be4d1>] [<ffffffff810be4d1>]
task_numa_find_cpu+0x241/0x770
[2081949.753304] RSP: 0000:ffff880ed6c5bb68 EFLAGS: 00010246
[2081949.753382] RAX: 0000000000000000 RBX: ffff881167b72a00 RCX:
0000000000000000
[2081949.753485] RDX: 0000000000000000 RSI: 0000000000000400 RDI:
ffff88607ea97878
[2081949.753587] RBP: ffff880ed6c5bbd8 R08: 00000000000000af R09:
000000000000000d
[2081949.753689] R10: 0000000000000009 R11: 0000000000000002 R12:
0000000000000107
[2081949.753791] R13: 0000000000000007 R14: 0000000000000335 R15:
ffff880ed6c5bc18
[2081949.753894] FS: 00007f6a459db700(0000) GS:ffff88607ea80000(0000)
knlGS:0000000000000000
[2081949.754010] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[2081949.754094] CR2: 00007f6f74016028 CR3: 0000005fa40bb000 CR4:
00000000003406e0
[2081949.754197] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[2081949.754299] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[2081949.754400] Stack:
[2081949.754435] 000000000000000d 000000000000036e 0000000000000009
00000000000000af
[2081949.754554] ffff880e1a55e200 0000000000000335 000000000000023b
0000000000017800
[2081949.754673] ffff880ed6c5bbd8 ffff880e1a55e200 0000000000000059
ffff880ed6c5bc18
[2081949.754791] Call Trace:
[2081949.754839] [<ffffffff810bec76>] task_numa_migrate+0x276/0x970
[2081949.754930] [<ffffffff810bf3ed>] numa_migrate_preferred+0x7d/0x90
[2081949.755029] [<ffffffff811f7940>] ? numamigrate_isolate_page+0x170/0x170
[2081949.755127] [<ffffffff810c0560>] task_numa_fault+0x800/0xbd0
[2081949.755214] [<ffffffff811f9eb2>] ? migrate_misplaced_page+0xe2/0x150
[2081949.755312] [<ffffffff811c6ac5>] handle_mm_fault+0xa75/0x17c0
[2081949.755401] [<ffffffff81106710>] ? futex_wake+0x80/0x160
[2081949.755484] [<ffffffff811092b2>] ? do_futex+0x122/0x630
[2081949.755567] [<ffffffff8134aa44>] ?
call_rwsem_down_read_failed+0x14/0x30
[2081949.755671] [<ffffffff8106df9c>] __do_page_fault+0x1ac/0x460
[2081949.755759] [<ffffffff81130b16>] ? __audit_syscall_exit+0x1e6/0x280
[2081949.755855] [<ffffffff8106e280>] do_page_fault+0x30/0x90
[2081949.755938] [<ffffffff81028666>] ? syscall_trace_leave+0xc6/0x150
[2081949.756032] [<ffffffff81740228>] page_fault+0x28/0x40
[2081949.756109] Code: f6 cb ff ff 48 8b 55 b0 49 8b 84 24 b8 00 00 00 49 8b
4c 24 70 4c 8b 45 a8 4d 8b 67 20 48 0f af 82 00 01 00 00 48 83 c1 01 31 d2
<48> f7 f1 49 8b 4f 78 49 89 c1 49 29 c4 4d 03 4f 48 4d 39 c6 7e
[2081949.756587] RIP [<ffffffff810be4d1>] task_numa_find_cpu+0x241/0x770
[2081949.760153] RSP <ffff880ed6c5bb68>

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

And the output of 'sys' command is shown below

*************

crash64> sys
KERNEL:
/ABC/4.1.12-103.6.1.el7uek.x86_64/vmlinux
DUMPFILE: vmcore [PARTIAL DUMP]
CPUS: 56
DATE: Sun Oct 29 20:00:43 2017
UPTIME: 6 days, 04:27:58
LOAD AVERAGE: 1.08, 0.99, 1.25
TASKS: 6171
NODENAME: host.demo.com
RELEASE: 4.1.12-103.6.1.el7uek.x86_64
VERSION: #2 SMP Wed Sep 20 12:15:11 PDT 2017
MACHINE: x86_64 (2397 Mhz)
MEMORY: 383.9 GB
PANIC: "divide error: 0000 [#1] SMP "

************

Cause

Sign In with your My Oracle Support account

Don't have a My Oracle Support account? Click to get started

My Oracle Support provides customers with access to over a
Million Knowledge Articles and hundreds of Community platforms