Gentoo Websites Logo
Go to: Gentoo Home Documentation Forums Lists Bugs Planet Store Wiki Get Gentoo!
Bug 180026 - gentoo-sources-2.6.22-r2 - kernel BUG at include/linux/dcache.h:322
Summary: gentoo-sources-2.6.22-r2 - kernel BUG at include/linux/dcache.h:322
Status: RESOLVED UPSTREAM
Alias: None
Product: Gentoo Linux
Classification: Unclassified
Component: [OLD] Core system (show other bugs)
Hardware: PPC Linux
: High normal (vote)
Assignee: Gentoo Kernel Bug Wranglers and Kernel Maintainers
URL:
Whiteboard: linux-bugzilla-pending
Keywords:
Depends on:
Blocks:
 
Reported: 2007-05-27 16:19 UTC by Florian Steinel
Modified: 2007-10-14 23:44 UTC (History)
0 users

See Also:
Package list:
Runtime testing required: ---


Attachments
.config (.config,38.95 KB, text/plain)
2007-05-27 16:21 UTC, Florian Steinel
Details
.config (.config,40.30 KB, text/plain)
2007-05-29 17:19 UTC, Florian Steinel
Details
gentoo-sources-2.6.21 crash (DSCN0070a.jpg,24.74 KB, image/jpeg)
2007-05-30 20:17 UTC, Florian Steinel
Details
config for vanilla Linux 2.6.23-rc7 (.config,43.62 KB, text/plain)
2007-10-14 11:48 UTC, Florian Steinel
Details
dmesg vanilla Linux 2.6.23_rc7 (dmesg,7.51 KB, text/plain)
2007-10-14 11:51 UTC, Florian Steinel
Details

Note You need to log in before you can comment on or make changes to this bug.
Description Florian Steinel 2007-05-27 16:19:25 UTC
while compiling i get:
kernel BUG at include/linux/dcache.h:316!
Oops: Exception in kernel mode, sig: 5 [#2]

Modules linked in: evbug evdev nfs lockd sunrpc af_packet eth1394 ohci1394 i2c_viapro ieee1394 snd_via82xx snd_ac97_codec ac97_bus s
nd_pcm snd_timer snd_page_alloc snd_mpu401_uart snd_rawmidi snd_seq_device snd soundcore parport_pc parport
NIP: C00A3D14 LR: C00A3C84 CTR: C00A3C48
REGS: d8a69db0 TRAP: 0700   Not tainted  (2.6.20-gentoo-r8)
MSR: 00029032 <EE,ME,IR,DR>  CR: 22004488  XER: 00000000
TASK = c5256050[14875] 'rm' THREAD: d8a68000
GPR00: 00000001 D8A69E60 C5256050 CFBEE740 C525611C D8A69E9C DFFF0400 4659A3FF 
GPR08: 165D6F9D 00000000 0000017A C099B194 00000000 100227E0 00000000 00000000 
GPR16: 00000000 00000001 00000000 3001B678 00000002 7FDF57D0 100A2B88 100A3B88 
GPR24: 00000000 100A2B88 7FDF47C0 D8A69E98 D8A69E9C CFBEE740 00000003 C5256050 
NIP [C00A3D14] proc_fd_link+0xcc/0x114
LR [C00A3C84] proc_fd_link+0x3c/0x114
Call Trace:
[D8A69E60] [C00A3C74] proc_fd_link+0x2c/0x114 (unreliable)
[D8A69E90] [C00A3694] proc_pid_readlink+0x50/0x16c
[D8A69EC0] [C0070824] sys_readlinkat+0xb4/0xdc
[D8A69F40] [C00122E0] ret_from_syscall+0x0/0x38
--- Exception: c01 at 0xff3eba0
    LR = 0xfec1d94
Instruction dump:
38090028 7d400028 314a0001 7d40012d 40a2fff4 913c0000 816b000c 2f8b0000 
419e0024 800b0000 21200000 7c090114 <0f000000> 7c005828 30000001 7c00592d 


Reproducible: Sometimes

Steps to Reproduce:




Portage 2.1.2.7 (default-linux/ppc/ppc32/2007.0/G4/Pegasos, gcc-3.4.4, glibc-2.3.6-r5, 2.6.20-gentoo-r8 ppc)
=================================================================
System uname: 2.6.20-gentoo-r8 ppc 7447/7457, altivec supported
Gentoo Base System release 1.12.9
Timestamp of tree: Sun, 27 May 2007 12:50:01 +0000
dev-lang/python:     2.4.4-r4
dev-python/pycrypto: 2.0.1-r5
sys-apps/sandbox:    1.2.17
sys-devel/autoconf:  2.13, 2.61
sys-devel/automake:  1.4_p6, 1.5, 1.6.3, 1.7.9-r1, 1.8.5-r3, 1.9.6-r2, 1.10
sys-devel/binutils:  2.17
sys-devel/gcc-config: 1.3.16
sys-devel/libtool:   1.5.22
virtual/os-headers:  2.6.17-r2
ACCEPT_KEYWORDS="ppc"
AUTOCLEAN="yes"
CBUILD="powerpc-unknown-linux-gnu"
CFLAGS="-O2 -mcpu=G4 -mtune=G4 -maltivec -mabi=altivec -fno-strict-aliasing -pipe"
CHOST="powerpc-unknown-linux-gnu"
CONFIG_PROTECT="/etc"
CONFIG_PROTECT_MASK="/etc/env.d /etc/gconf /etc/revdep-rebuild /etc/terminfo"
CXXFLAGS="-O2 -mcpu=G4 -mtune=G4 -maltivec -mabi=altivec -fno-strict-aliasing -pipe"
DISTDIR="/usr/portage/distfiles"
FEATURES="distlocks metadata-transfer sandbox sfperms strict"
GENTOO_MIRRORS="http://distfiles.gentoo.org http://distro.ibiblio.org/pub/linux/distributions/gentoo"
LDFLAGS="-Wl,--as-needed"
LINGUAS="de en"
PKGDIR="/usr/portage/packages"
PORTAGE_RSYNC_OPTS="--recursive --links --safe-links --perms --times --compress --force --whole-file --delete --delete-after --stats --timeout=180 --exclude=/distfiles --exclude=/local --exclude=/packages --filter=H_**/files/digest-*"
PORTAGE_TMPDIR="/var/tmp"
PORTDIR="/usr/portage"
SYNC="rsync://rsync.local/gentoo-portage"
USE="acl altivec berkdb bitmap-fonts cli cracklib crypt cups dri fortran gdbm gpm iconv ipv6 isdnlog libg++ midi mudflap ncurses nls nptl nptlonly openmp pam pcre perl ppc pppd python readline reflection session spl ssl tcpd truetype-fonts type1-fonts unicode xorg zlib" ALSA_CARDS="aoa aoa-fabric-layout aoa-onyx aoa-soundbus aoa-soundbus-i2s aoa-tas aoa-toonie powermac usb-audio via82xx" ALSA_PCM_PLUGINS="adpcm alaw asym copy dmix dshare dsnoop empty extplug file hooks iec958 ioplug ladspa lfloat linear meter mulaw multi null plug rate route share shm softvol" ELIBC="glibc" INPUT_DEVICES="keyboard mouse evdev" KERNEL="linux" LCD_DEVICES="bayrad cfontz cfontz633 glk hd44780 lb216 lcdm001 mtxorb ncurses text" LINGUAS="de en" USERLAND="GNU" VIDEO_CARDS="chips dummy fbdev glint imstt mach64 mga nv r128 radeon s3 s3virge savage sisusb tdfx trident v4l voodoo"
Unset:  CTARGET, EMERGE_DEFAULT_OPTS, INSTALL_MASK, LANG, LC_ALL, MAKEOPTS, PORTAGE_COMPRESS, PORTAGE_COMPRESS_FLAGS, PORTAGE_RSYNC_EXTRA_OPTS, PORTDIR_OVERLAY

processor       : 0
cpu     : 7447/7457, altivec supported
clock           : 999.999990MHz
revision        : 0.1 (pvr 8002 0101)
bogomips        : 66.56
timebase        : 33333333
platform        : CHRP
machine         : CHRP Pegasos2
Comment 1 Florian Steinel 2007-05-27 16:21:47 UTC
Created attachment 120456 [details]
.config
Comment 2 ecks 2007-05-28 23:58:31 UTC
Can you reproduce this with the latest kernel version, 2.6.21?
Comment 3 Florian Steinel 2007-05-29 17:19:47 UTC
Created attachment 120628 [details]
.config

.config from gentoo-sources-2.6.21-r2 i'm about to build and test
Comment 4 Florian Steinel 2007-05-29 20:06:45 UTC
I've tried compiling gcc-3.4.6-r2 and 4.1.2 as an stress test.
Before with gentoo-sources-2.6.20-r8:
- gcc-3.4.6-r2: fail in bootstrap
- gcc 4.1.2:    fail in bootstrap?(not sure)
Now with gentoo-sources-2.6.21-r2:
- gcc-3.4.6-r2: successfully emerged
- gcc 4.1.2:
/var/tmp/portage/sys-devel/gcc-4.1.2/work/gcc-4.1.2/gcc/loop.c:6370: internal compiler error: in var_ann, at tree-flow-inline.h:127
Please submit a full bug report,
with preprocessed source if appropriate.
See <URL:http://bugs.gentoo.org/> for instructions.
The bug is not reproducible, so it is likely a hardware or OS problem.
make[2]: *** [loop.o] Error 1
make[2]: Leaving directory `/var/tmp/portage/sys-devel/gcc-4.1.2/work/build/gcc'
make[1]: *** [stage2_build] Error 2
make[1]: Leaving directory `/var/tmp/portage/sys-devel/gcc-4.1.2/work/build/gcc'
make: *** [bootstrap-lean] Error 2

Will rebuild gcc-4.1.2 and report back.
Comment 5 Florian Steinel 2007-05-29 21:58:59 UTC
Now its (gcc-4.1.2):
Bootstrap comparison failure!
./insn-recog.o differs
cp/tree.o differs
fortran/parse.o differs
Comment 6 Daniel Drake (RETIRED) gentoo-dev 2007-05-29 22:33:14 UTC
Do you have any memory testing utilities available? The errors seem random and are very likely to be the result of hardware problems. On x86/amd64 I'd recommend memtest here, but I'm not familiar with ppc.
Comment 7 Florian Steinel 2007-05-30 20:17:04 UTC
Created attachment 120726 [details]
gentoo-sources-2.6.21 crash

last message from kernel
Comment 8 Florian Steinel 2007-05-30 20:18:31 UTC
Messages after restart:
------------[ cut here ]------------
kernel BUG at include/linux/dcache.h:316!
Oops: Exception in kernel mode, sig: 5 [#1]

Modules linked in: nfs lockd sunrpc af_packet eth1394 ohci1394 ieee1394 snd_via82xx snd_ac97_codec ac97_bus snd_pcm snd_timer snd_pa
ge_alloc snd_mpu401_uart snd_rawmidi parport_pc parport i2c_viapro snd_seq_device snd soundcore
NIP: C0075270 LR: C0075188 CTR: C00E86EC
REGS: dcd4bc90 TRAP: 0700   Not tainted  (2.6.21-gentoo-r2)
MSR: 00029032 <EE,ME,IR,DR>  CR: 22042448  XER: 00000000
TASK = cfb533a0[7491] 'powerpc-unknown' THREAD: dcd4a000
GPR00: 00000001 DCD4BD40 CFB533A0 DF621134 00000001 DCD4BE80 DCCBF234 00000000 
GPR08: 0000002F CFC14414 00000000 00002298 00000000 1003A74C 10030000 10030000 
GPR16: 10030000 10030000 10030000 100BEEEC 100360D8 00000000 00000002 00000003 
GPR24: 00000101 DD582039 00000000 DCD4BD60 00000000 CFBE0860 DCD4BE80 00000000 
NIP [C0075270] __link_path_walk+0x250/0xeb0
LR [C0075188] __link_path_walk+0x168/0xeb0
Call Trace:
[DCD4BD40] [C0075188] __link_path_walk+0x168/0xeb0 (unreliable)
[DCD4BDA0] [C0075F50] link_path_walk+0x80/0x13c
[DCD4BE10] [C0076208] do_path_lookup+0x1fc/0x26c
[DCD4BE40] [C0076350] __path_lookup_intent_open+0x58/0xb0
[DCD4BE70] [C0071874] open_exec+0x2c/0xe4
[DCD4BEE0] [C00725E8] do_execve+0x4c/0x248
[DCD4BF10] [C0008758] sys_execve+0x60/0x94
[DCD4BF40] [C0012114] ret_from_syscall+0x0/0x38
--- Exception: c01 at 0xff21884
    LR = 0xff21a0c
Instruction dump:
7f804800 419e00cc 813e0004 80090010 7f830000 41be003c 81230014 2f890000 
419e0024 80090000 21400000 7c0a0114 <0f000000> 7c004828 30000001 7c00492d 

and

------------[ cut here ]------------
kernel BUG at include/linux/dcache.h:316!
Oops: Exception in kernel mode, sig: 5 [#2]

Modules linked in: nfs lockd sunrpc af_packet eth1394 ohci1394 ieee1394 snd_via82xx snd_ac97_codec ac97_bus snd_pcm snd_timer snd_pa
ge_alloc snd_mpu401_uart snd_rawmidi parport_pc parport i2c_viapro snd_seq_device snd soundcore
NIP: C0075270 LR: C0075188 CTR: C00E86EC
REGS: dccefc80 TRAP: 0700   Not tainted  (2.6.21-gentoo-r2)
MSR: 00029032 <EE,ME,IR,DR>  CR: 22022288  XER: 00000000
TASK = df528090[7490] 'cc1' THREAD: dccee000
GPR00: 00000001 DCCEFD30 DF528090 DF621134 00000001 DCCEFE70 DCCBF234 00000000 
GPR08: 0000002F CFC14414 00000000 00002298 00000000 1054D1C4 10030000 10030000 
GPR16: 10030000 10030000 10540000 103E0000 103F0000 103F0000 103F0000 103F0000 
GPR24: 00000001 DD776039 00000000 DCCEFD50 00000000 CFBE08A0 DCCEFE70 00000000 
NIP [C0075270] __link_path_walk+0x250/0xeb0
LR [C0075188] __link_path_walk+0x168/0xeb0
Call Trace:
[DCCEFD30] [C0075188] __link_path_walk+0x168/0xeb0 (unreliable)
[DCCEFD90] [C0075F50] link_path_walk+0x80/0x13c
[DCCEFE00] [C0076208] do_path_lookup+0x1fc/0x26c
[DCCEFE30] [C0076698] __user_walk_fd+0x54/0x78
[DCCEFE60] [C007055C] vfs_stat_fd+0x24/0x60
[DCCEFED0] [C0070E64] sys_stat64+0x20/0x50
[DCCEFF40] [C0012114] ret_from_syscall+0x0/0x38
--- Exception: c01 at 0xff446dc
    LR = 0xff44694
Instruction dump:
7f804800 419e00cc 813e0004 80090010 7f830000 41be003c 81230014 2f890000 
419e0024 80090000 21400000 7c0a0114 <0f000000> 7c004828 30000001 7c00492d 

and

------------[ cut here ]------------
kernel BUG at include/linux/dcache.h:316!
Oops: Exception in kernel mode, sig: 5 [#3]

Modules linked in: nfs lockd sunrpc af_packet eth1394 ohci1394 ieee1394 snd_via82xx snd_ac97_codec ac97_bus snd_pcm snd_timer snd_pa
ge_alloc snd_mpu401_uart snd_rawmidi parport_pc parport i2c_viapro snd_seq_device snd soundcore
NIP: C0075270 LR: C0075188 CTR: C00E86EC
REGS: de925bc0 TRAP: 0700   Not tainted  (2.6.21-gentoo-r2)
MSR: 00029032 <EE,ME,IR,DR>  CR: 28422468  XER: 00000000
TASK = dffac720[7519] 'bash' THREAD: de924000
GPR00: 00000001 DE925C70 DFFAC720 C088BA34 00000001 DE925E80 DE925D2C 00000000 
GPR08: 0000002F CFC14414 00000000 00002298 00000000 100CF1DC FFFFFFFF 00000000 
GPR16: 00000000 00000000 00000000 100C0000 100C0000 00000000 100EA5C0 100EA568 
GPR24: 00000001 DF04205F 00000000 DE925D60 DE925CE0 CFBE01E0 DE925E80 00000000 
NIP [C0075270] __link_path_walk+0x250/0xeb0
LR [C0075188] __link_path_walk+0x168/0xeb0
Call Trace:
[DE925C70] [C0075188] __link_path_walk+0x168/0xeb0 (unreliable)
[DE925CD0] [C0075F50] link_path_walk+0x80/0x13c
[DE925D40] [C0075C3C] __link_path_walk+0xc1c/0xeb0
[DE925DA0] [C0075F50] link_path_walk+0x80/0x13c
[DE925E10] [C0076208] do_path_lookup+0x1fc/0x26c
[DE925E40] [C0076350] __path_lookup_intent_open+0x58/0xb0
[DE925E70] [C0071874] open_exec+0x2c/0xe4
[DE925EE0] [C00725E8] do_execve+0x4c/0x248
[DE925F10] [C0008758] sys_execve+0x60/0x94
[DE925F40] [C0012114] ret_from_syscall+0x0/0x38
--- Exception: c01 at 0xfeb9884
    LR = 0x10025e04
Instruction dump:
7f804800 419e00cc 813e0004 80090010 7f830000 41be003c 81230014 2f890000 
419e0024 80090000 21400000 7c0a0114 <0f000000> 7c004828 30000001 7c00492d 
Comment 9 Daniel Drake (RETIRED) gentoo-dev 2007-06-16 00:39:13 UTC
please provide the info requested in comment #6
Comment 10 Florian Steinel 2007-06-16 21:36:51 UTC
root@pegasos memtester # free -m
             total       used       free     shared    buffers     cached
Mem:           503         55        447          0          8         33
-/+ buffers/cache:         13        489
Swap:         2012          0       2012
root@pegasos memtester # memtester 440
memtester version 4.0.7 (32-bit)
Copyright (C) 2006 Charles Cazabon.
Licensed under the GNU General Public License version 2 (only).

pagesize is 4096
pagesizemask is 0xfffff000
want 440MB (461373440 bytes)
got  440MB (461373440 bytes), trying mlock ...locked.
Loop 1:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 2:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 3:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 4:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 5:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 6:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 7:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 8:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 9:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

Loop 10:
  Stuck Address       : ok         
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok         
  Block Sequential    : ok         
  Checkerboard        : ok         
  Bit Spread          : ok         
  Bit Flip            : ok         
  Walking Ones        : ok         
  Walking Zeroes      : ok         

and still running Loop 11 (no oops in dmesg)...
Comment 11 Florian Steinel 2007-07-01 10:15:57 UTC
memtester is at 330 from 440.

Now I get 
root@pegasos ~ # stat /var/cache/edb/dep/usr/portage/dev-lang/yasm-0.5.0 
stat: cannot stat `/var/cache/edb/dep/usr/portage/dev-lang/yasm-0.5.0': Input/output error
Comment 12 Florian Steinel 2007-07-01 10:18:23 UTC
output from slabtop:
 Active / Total Objects (% used)    : 45372 / 95767 (47.4%)
 Active / Total Slabs (% used)      : 6965 / 6965 (100.0%)
 Active / Total Caches (% used)     : 75 / 123 (61.0%)
 Active / Total Size (% used)       : 13138.75K / 26378.76K (49.8%)
 Minimum / Average / Maximum Object : 0.01K / 0.28K / 128.00K

  OBJS ACTIVE  USE OBJ SIZE  SLABS OBJ/SLAB CACHE SIZE NAME                   
 39568  19082  48%    0.47K   4946        8     19784K ext3_inode_cache
 37500  13162  35%    0.12K   1250       30      5000K dentry_cache
  2856   2819  98%    0.04K     34       84       136K sysfs_dir_cache
  2626   2086  79%    0.28K    202       13       808K radix_tree_node
  2486   2211  88%    0.03K     22      113        88K size-32
  1593    683  42%    0.06K     27       59       108K size-64
  1012    782  77%    0.08K     22       46        88K vm_area_struct
   930    901  96%    0.12K     31       30       124K size-128
   708    672  94%    0.31K     59       12       236K inode_cache
   678    274  40%    0.01K      2      339         8K anon_vma
   590    112  18%    0.06K     10       59        40K buffer_head
   480    251  52%    0.16K     20       24        80K filp
   360    356  98%    0.41K     40        9       160K shmem_inode_cache
   296    288  97%    0.50K     37        8       148K size-512
   280    260  92%    0.09K      7       40        28K bio
   254      2   0%    0.01K      1      254         4K revoke_table
   203     11   5%    0.02K      1      203         4K biovec-1
   203      3   1%    0.02K      1      203         4K tcp_bind_bucket
   202     39  19%    0.04K      2      101         8K pid
   200    155  77%    0.09K      5       40        20K size-96
   169      4   2%    0.02K      1      169         4K journal_handle
   160    122  76%    0.09K      4       40        16K kmem_cache
   144      6   4%    0.05K      2       72         8K journal_head
   127     17  13%    0.03K      1      127         4K blkdev_ioc
   120     20  16%    0.19K      6       20        24K skbuff_head_cache
   116    113  97%    0.13K      4       29        16K idr_layer_cache
   113     18  15%    0.03K      1      113         4K fs_cache
   113     10   8%    0.03K      1      113         4K ip_fib_hash
   113     10   8%    0.03K      1      113         4K ip_fib_alias
   100     89  89%    0.19K      5       20        20K size-192
   100     19  19%    0.19K      5       20        20K files_cache
    92      1   1%    0.04K      1       92         4K inotify_watch_cache
    80     78  97%    1.00K     20        4        80K size-1024
    75     72  96%    0.25K      5       15        20K size-256
    72     37  51%    0.41K      8        9        32K signal_cache
    70     37  52%    1.45K     14        5       112K task_struct
    63     19  30%    0.41K      7        9        28K mm_struct
    59      7  11%    0.06K      1       59         4K biovec-4
    59      4   6%    0.06K      1       59         4K uid_cache
    52     52 100%    2.00K     26        2       104K size-2048
    48     37  77%    1.28K     16        3        64K sighand_cache
Comment 13 Florian Steinel 2007-08-20 16:49:17 UTC
last line from memtester:
Loop 739:
  Stuck Address       : ok
  Random Value        : ok
  Compare XOR         : ok
  Compare SUB         : ok
  Compare MUL         : ok
  Compare DIV         : ok
  Compare OR          : ok
  Compare AND         : ok
  Sequential Increment: ok
  Solid Bits          : ok
  Block Sequential    : setting  35
Comment 14 Florian Steinel 2007-08-20 16:49:56 UTC
now with 2.6.22-gentoo-r2:
------------[ cut here ]------------
kernel BUG at include/linux/dcache.h:322!
Oops: Exception in kernel mode, sig: 5 [#1]
CHRP
Modules linked in: snd_pcm_oss snd_mixer_oss snd_seq_oss snd_seq_midi_event snd_seq ipv6 nfs lockd sunrpc af_packet parport_pc parport snd_via82xx snd_ac97_codec ac97_bus snd_pcm snd_timer snd_page_alloc snd_mpu401_uart snd_rawmidi snd_seq_device snd soundcore ohci1394 ieee1394 i2c_viapro
NIP: c007f91c LR: c007f898 CTR: 00000000
REGS: de069c50 TRAP: 0700   Not tainted  (2.6.22-gentoo-r2)
MSR: 00029032 <EE,ME,IR,DR>  CR: 24042488  XER: 20000000
TASK = dffbf2e0[26031] 'rsync' THREAD: de068000
GPR00: 00000001 de069d00 dffbf2e0 d11b0d10 cb8e901b 00000000 d11b0cc0 00000004 
GPR08: d11b0cf0 00000000 d11b0ce8 d11b0ce0 00000000 10067aa0 10060000 10060000 
GPR16: 00000001 10060000 10060000 10060000 10060000 00000003 00000003 00000001 
GPR24: dffef1a0 de069d60 c0320000 d11b0cb4 d11b0d10 de069d60 d3dc5a54 d11b0cb4 
NIP [c007f91c] d_alloc+0x11c/0x188
LR [c007f898] d_alloc+0x98/0x188
Call Trace:
[de069d00] [c007f82c] d_alloc+0x2c/0x188 (unreliable)
[de069d20] [c0073b00] do_lookup+0x94/0x1a0
[de069d50] [c0075f00] __link_path_walk+0x904/0xe70
[de069da0] [c00764ec] link_path_walk+0x80/0x144
[de069e10] [c0076904] do_path_lookup+0x1f0/0x280
[de069e40] [c00771f8] __user_walk_fd+0x4c/0x70
[de069e60] [c006f5e8] vfs_lstat_fd+0x24/0x60
[de069ed0] [c006f6ac] sys_lstat64+0x20/0x50
[de069f40] [c0012398] ret_from_syscall+0x0/0x38
--- Exception: c01 at 0xff1d5ac
    LR = 0x100154b0
Instruction dump:
91260004 916b0004 917f0024 397f002c 914a0004 915f0034 91080004 911f003c 
419e004c 801e0000 7c000034 5400d97e <0f000000> 7c00f028 30000001 7c00f12d 
Comment 15 Maarten Bressers (RETIRED) gentoo-dev 2007-09-18 22:37:41 UTC
Any news here? Do these problems still occur with latest development kernel (2.6.23-rc6 as of this writing)?
Comment 16 Daniel Drake (RETIRED) gentoo-dev 2007-09-23 13:30:42 UTC
Apart from the fact that this smells like a hardware problem, the oops always being in the same place suggests otherwise. Please test the latest development kernel (currently 2.6.23-rc7) then report this upstream at http://bugzilla.kernel.org and post the new URL here.
Comment 17 Florian Steinel 2007-09-23 15:50:28 UTC
(In reply to comment #16)
currently testing with 2.6.23-rc7 (with enabled rtc and changed i/o scheduler cfq)
memtester is running now...
will retest with exact kernel-config copy.
Comment 18 Mike Pagano gentoo-dev 2007-10-06 19:32:38 UTC
Florian,

Any results from your testing to report?
Comment 19 Florian Steinel 2007-10-06 20:52:19 UTC
(In reply to comment #18)
memtester is still running (Loop 324 with 480MB).
openssl build results in an error, this is expected with only 23MB (from 503MB) left (i/o scheduler / oom-killer output in dmesg).
Comment 20 Florian Steinel 2007-10-13 18:43:11 UTC
Bad news: machine restarted.
But how?

Oct  9 21:08:47 pegasos sshd(pam_unix)[15721]: session opened for user root by root(uid=0)
Oct 10 02:55:55 pegasos syslog-ng[3417]: STATS: dropped 0
Oct 10 14:55:57 pegasos syslog-ng[3417]: STATS: dropped 0
Sep  3 10:36:48 pegasos syslog-ng[4138]: syslog-ng version 1.6.11 starting
Sep  3 10:36:48 pegasos syslog-ng[4138]: Changing permissions on special file /dev/tty12
Sep  3 10:36:48 pegasos Using CHRP machine description
Sep  3 10:36:48 pegasos Total memory = 512MB; using 1024kB for hash table (at cff00000)
Sep  3 10:36:48 pegasos Linux version 2.6.23-rc7 (root@pegasos) (gcc version 4.1.2 (Gentoo 4.1.2)) #1 Sat Sep 22 14:28:21 CEST 2007
Sep  3 10:36:48 pegasos Found legacy serial port 0 for /pci@80000000/isa@C/serial@i2F8
Sep  3 10:36:48 pegasos port=2f8, taddr=fe0002f8, irq=0, clk=1843200, speed=0
Sep  3 10:36:48 pegasos console [udbg0] enabled
Sep  3 10:36:48 pegasos Entering add_active_range(0, 0, 131072) 0 entries of 256 used
Sep  3 10:36:48 pegasos chrp type = 6 [Genesi Pegasos]

Maybe i should add an cronjob for autobackup of dmesg?
Any other info you need?
Comment 21 Maarten Bressers (RETIRED) gentoo-dev 2007-10-14 00:45:40 UTC
So you're not able to build a 2.6.23 kernel to test with? If you're still running and old(er) kernel version, you should try to upgrade and see if you can still reproduce this behavior. This will also be asked if you report this upstream.

If you manage to get a 2.6.23 kernel up and running, please post your .config and dmesg output here. 
Comment 22 Florian Steinel 2007-10-14 11:48:05 UTC
Created attachment 133430 [details]
config for vanilla Linux 2.6.23-rc7

(In reply to comment #21)
I'm already running vanilla-sources-2.6.23_rc7.
Sorry, i didn't posted this earlier...
Comment 23 Florian Steinel 2007-10-14 11:51:36 UTC
Created attachment 133432 [details]
dmesg vanilla Linux 2.6.23_rc7
Comment 24 Daniel Drake (RETIRED) gentoo-dev 2007-10-14 23:44:16 UTC
Please now file this bug report upstream as mentioned in comment #7. Post the new URL here when done. Don't worry about adding too many details, I'll add them once you have opened the bug.
Comment 25 Daniel Drake (RETIRED) gentoo-dev 2007-10-14 23:44:46 UTC
oops, i meant comment #16