2004-04-29 19:36:40

by Rafał J. Wysocki

[permalink] [raw]
Subject: 2.6.6-rc3 broken on dual Opteron

Hi,

I've got this on a dual-Opteron box w/ SuSE 9.0 (AMD64) + 2.6.6-rc3:

kjournald starting. Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
VFS: Mounted root (ext3 filesystem) readonly.
Freeing unused kernel memory: 176k freed
general protection fault: 0000 [1] SMP
CPU 1
Pid: 1, comm: init Not tainted 2.6.6-rc3
RIP: 0010:[<ffffffff8010cf66>] <ffffffff8010cf66>{__switch_to+86}
RSP: 0000:000001000171be70 EFLAGS: 00010002
RAX: 000001003ff96000 RBX: 000001000171ecc8 RCX: 0000000000000100
RDX: 0000000000000001 RSI: 000001000171e848 RDI: 000001000171f058
RBP: 000001000171f4d8 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000001 R11: ffffffff8049c4c0 R12: 000001002073c400
R13: 000001000171e848 R14: 000001000171f058 R15: ffffffff80468580
FS: 0000000000000000(0000) GS:ffffffff8046c6c0(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004112e0 CR3: 000000003ff95000 CR4: 00000000000006e0
Process init (pid: 1, stackpage=10001720058)
Stack: 0000000001000881 000001000171e848 000001000171e848 000001002073c400
000001002070f5e0 000001003fd1f610 0000000378d45554 ffffffff80308f50
000001000171bf40 0000000000000046
Call Trace:<ffffffff80308f50>{thread_return+0}
<ffffffff8010c5d0>{default_idle+0}
<ffffffff8010d572>{cpu_idle+50}

Code: 0f ae 87 00 05 00 00 db e2 83 60 14 fe 0f 20 c0 48 83 c8 08
RIP <ffffffff8010cf66>{__switch_to+86} RSP <000001000171be70>
<0>Kernel panic: Attempted to kill init!
NMI Watchdog detected LOCKUP on CPU1, registers:
CPU 1
Pid: 1, comm: init Not tainted 2.6.6-rc3
RIP: 0010:[<ffffffff80132058>] <ffffffff80132058>{.text.lock.sched+170}
RSP: 0000:000001000171ba68 EFLAGS: 00000082
RAX: 0000000000000080 RBX: 000001001fd7d158 RCX: 000001003fe2bef0
RDX: ffffffff8049c4c0 RSI: 0000000000000007 RDI: 0000000000000000
RBP: 000001000171ba98 R08: 0000000000000000 R09: 0000000000000000
R10: 000001000171bac8 R11: 0000000000000140 R12: 000001002070f5e0
R13: 000001000171ba70 R14: 000001000171f058 R15: ffffffff80468580
FS: 0000000000000000(0000) GS:ffffffff8046c6c0(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004112e0 CR3: 000000003ff95000 CR4: 00000000000006e0
Process init (pid: 1, stackpage=10001720058)
Stack: 00000000000003e8 0000000000000002 0000000000000000 000001000171f058
000000000000000b 000001000171f058 000000008010e8f7 ffffffff80158bb1
0000000000000001 0000000000000286
Call Trace:<ffffffff80158bb1>{pdflush_operation+145}
<ffffffff8015854f>{wakeup_bdflush+47}
<ffffffff8017388b>{do_sync+11} <ffffffff801738fe>{sys_sync+14}
<ffffffff801348b6>{panic+262} <ffffffff8013711d>{do_exit+93}
<ffffffff8010f8e3>{oops_end+35} <ffffffff801101e5>{die+69}
<ffffffff801102f7>{do_general_protection+263}
<ffffffff8010ec81>{error_exit+0}
<ffffffff8010cf66>{__switch_to+86} <ffffffff80308f50>{thread_return+0}
<ffffffff8010c5d0>{default_idle+0} <ffffffff8010d572>{cpu_idle+50}


Code: 41 80 3c 24 00 7e f7 e9 fe dd ff ff f3 90 80 3b 00 7e f9 e9
console shuts up ...
NMI Watchdog detected LOCKUP on CPU0, registers:
CPU 0

and then silence ...

Also, there are some (un)interesting messages from the gcc:

CC arch/x86_64/ia32/ia32_binfmt.o
In file included from arch/x86_64/ia32/ia32_binfmt.c:306:
fs/binfmt_elf.c: In function `load_elf_interp':
fs/binfmt_elf.c:369: warning: comparison is always false due to limited range
of data type
fs/binfmt_elf.c: In function `load_elf32_binary':
fs/binfmt_elf.c:781: warning: comparison is always false due to limited range
of data type
CC arch/x86_64/ia32/fpu32.o

Attached is the .config.

Yours,
RJW

--
Rafael J. Wysocki,
SiSK
[tel. (+48) 605 053 693]
----------------------------
For a successful technology, reality must take precedence over public
relations, for nature cannot be fooled.
-- Richard P. Feynman


Attachments:
(No filename) (3.83 kB)
2.6.6-rc3-config (26.29 kB)
Download all attachments