| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20140629031121.GB10256@localhost>
Date: Sun, 29 Jun 2014 11:11:21 +0800
From: Fengguang Wu <fengguang.wu@...el.com>
To: Yuyang Du <yuyang.du@...el.com>
Cc: Jet Chen <jet.chen@...el.com>, Su Tao <tao.su@...el.com>,
Yuanhan Liu <yuanhan.liu@...el.com>, LKP <lkp@...org>,
linux-kernel@...r.kernel.org
Subject: [sched] WARNING: CPU: 0 PID: 1 at kernel/sched/core.c:6069 sd_init()
Greetings,
0day kernel testing robot got the below dmesg and the first bad commit is
git://bee.sh.intel.com/git/ydu19/linux cc-v4-on-3.16-rc2
commit 981fa8778958e70170ad2e757bc75f5e3c688665
Author: Yuyang Du <yuyang.du@...el.com>
AuthorDate: Wed Jun 25 03:57:18 2014 +0800
Commit: Yuyang Du <yuyang.du@...el.com>
CommitDate: Thu Jun 26 15:06:56 2014 +0800
Define SD_WORKLOAD_CONSOLIDATION and attach to sched_domain
Workload Consolidation is completely CPU topology and policy driven. To do so,
we define SD_WORKLOAD_CONSOLIDATION, and add some fields in sched_domain struct:
1) total_groups is the group number in total in this domain
2) group_number is this CPU's group sequence number
3) consolidating_coeff is the coefficient for consolidating CPUs, and is changeable
via sysctl tool to make consolidation more aggressive or less
4) first_group is the pointer to this domain's first group ordered by CPU number
This patchset enables SD_WORKLOAD_CONSOLIDATION in MC domain by default. But we need
to come up with a better way to determine on which architecture this flag should be
enabled or not. Thanks to PeterZ and Dietmar for pointing this out and help me
finally understand it.
Signed-off-by: Yuyang Du <yuyang.du@...el.com>
===================================================
PARENT COMMIT NOT CLEAN. LOOK OUT FOR WRONG BISECT!
===================================================
Attached dmesg for the parent commit, too, to help confirm whether it is a noise error.
+--------------------------------------------------+------------+------------+------------------+
| | 3b3fb61976 | 981fa87789 | v3.16-rc2_062617 |
+--------------------------------------------------+------------+------------+------------------+
| boot_successes | 56 | 0 | 0 |
| boot_failures | 1 | 19 | 13 |
| BUG:kernel_boot_crashed | 1 | | |
| WARNING:CPU:PID:at_kernel/sched/core.c:sd_init() | 0 | 19 | 13 |
| backtrace:sd_init | 0 | 19 | 13 |
| backtrace:warn_slowpath_fmt | 0 | 19 | 13 |
| backtrace:build_sched_domains | 0 | 19 | 13 |
| backtrace:sched_init_smp | 0 | 19 | 13 |
| backtrace:kernel_init_freeable | 0 | 19 | 13 |
+--------------------------------------------------+------------+------------+------------------+
[ 0.182210] ---------------------------------
[ 0.183384] smpboot: Total of 2 processors activated (10774.02 BogoMIPS)
[ 0.185468] ------------[ cut here ]------------
[ 0.185468] WARNING: CPU: 0 PID: 1 at kernel/sched/core.c:6069 sd_init+0x3e6/0x400()
[ 0.185468] wrong sd_flags in topology description
[ 0.190008] Modules linked in:
[ 0.191075] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.16.0-rc2-00004-g981fa87 #1
[ 0.193126] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
[ 0.195267] 0000000000000009 ffff880013487d30 ffffffff822ec723 ffff880013487d78
[ 0.197754] ffff880013487d68 ffffffff810ca0d7 ffffffff82d90038 0000000000008000
[ 0.200484] 0000000000000001 ffff8800135b8000 0000000000000001 ffff880013487dc8
[ 0.202956] Call Trace:
[ 0.203814] [<ffffffff822ec723>] dump_stack+0xc1/0x111
[ 0.205138] [<ffffffff810ca0d7>] warn_slowpath_common+0xc7/0x100
[ 0.206629] [<ffffffff810ca1f7>] warn_slowpath_fmt+0x57/0x70
[ 0.208029] [<ffffffff817c3eb4>] ? __bitmap_weight+0xe4/0x110
[ 0.209447] [<ffffffff811268d6>] sd_init+0x3e6/0x400
[ 0.210015] [<ffffffff81137851>] build_sched_domain+0x31/0x230
[ 0.211450] [<ffffffff81138696>] build_sched_domains+0xc46/0x1770
[ 0.212931] [<ffffffff83807858>] sched_init_smp+0x118/0x3b0
[ 0.214329] [<ffffffff837dec4c>] kernel_init_freeable+0xcd/0x31a
[ 0.215816] [<ffffffff822c46e0>] ? rest_init+0x120/0x120
[ 0.217155] [<ffffffff822c46f1>] kernel_init+0x11/0x230
[ 0.218491] [<ffffffff8230a97c>] ret_from_fork+0x7c/0xb0
[ 0.220014] [<ffffffff822c46e0>] ? rest_init+0x120/0x120
[ 0.221383] ---[ end trace 66f6dff8a935a04a ]---
[ 0.233431] gcov: version magic: 0x3430382a
git bisect start 9c33bf1e59d26dad8dc45e438cbdc28783589b11 a497c3ba1d97fc69c1e78e7b96435ba8c2cb42ee --
git bisect good 10d9d029067f2aacbdc140786efff146d79b34c5 # 08:26 19+ 0 Merge 'cgroup/for-3.16-fixes' into devel-hourly-2014062617
git bisect bad b8db0fc896849e940f23fbea02c137869c94f3d3 # 08:33 0- 6 Merge 'kvm-ppc/kvm-ppc-queue' into devel-hourly-2014062617
git bisect good 7135b130d9f1c30321f9a9e024498557026cdd03 # 08:41 19+ 0 Merge 'arm-platforms/kvm-arm64/irq-forward' into devel-hourly-2014062617
git bisect good c2484a8acda7d9ff41a98d3e2fcc5a65bbd02747 # 08:50 19+ 0 Merge 'arc/for-next' into devel-hourly-2014062617
git bisect good 1a799f5c9dbbd47d503af1e0cedf9d252cca2d6d # 09:00 19+ 0 Merge 'cryptodev/master' into devel-hourly-2014062617
git bisect bad 9c259d6a46e754ea8fb42bcf688255ffa2c8c048 # 09:09 0- 16 Merge 'yuyang/cc-v4-on-3.16-rc2' into devel-hourly-2014062617
git bisect bad 1a43e8a377f4adc5c9a412de1a57ab453f8313d4 # 09:17 0- 13 Workload Consolidation: Consolidating workload to a subset of CPUs if possible
git bisect good 7dee841147a972e809dfcd75f638d7145dd8e756 # 09:29 19+ 0 sched: Precise accumulated time and acount runnable number in update_entity_runnable_avg
git bisect bad 981fa8778958e70170ad2e757bc75f5e3c688665 # 09:41 0- 12 Define SD_WORKLOAD_CONSOLIDATION and attach to sched_domain
git bisect good 3b3fb61976509ef8f7c0c05adba0b61cea6b05db # 09:52 19+ 0 How CPU ConCurrency (CC) accrues with runqueue change and time
# first bad commit: [981fa8778958e70170ad2e757bc75f5e3c688665] Define SD_WORKLOAD_CONSOLIDATION and attach to sched_domain
git bisect good 3b3fb61976509ef8f7c0c05adba0b61cea6b05db # 09:58 57+ 1 How CPU ConCurrency (CC) accrues with runqueue change and time
git bisect bad 9c33bf1e59d26dad8dc45e438cbdc28783589b11 # 09:58 0- 13 0day head guard for 'devel-hourly-2014062617'
git bisect good 24b414d5a7d3e6a716350464dfdb44da610ed142 # 10:10 57+ 0 Merge tag 'spi-v3.16-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi
git bisect good 96426007c90cde23c0402856f3e0aec0f4cc2e48 # 10:18 57+ 0 Add linux-next specific files for 20140627
This script may reproduce the error.
-----------------------------------------------------------------------------
#!/bin/bash
kernel=$1
initrd=yocto-minimal-x86_64.cgz
wget --no-clobber https://github.com/fengguang/reproduce-kernel-bug/blob/master/initrd/$initrd
kvm=(
qemu-system-x86_64 -cpu kvm64 -enable-kvm
-kernel $kernel
-initrd $initrd
-smp 2
-m 256M
-net nic,vlan=0,macaddr=00:00:00:00:00:00,model=virtio
-net user,vlan=0
-net nic,vlan=1,model=e1000
-net user,vlan=1
-boot order=nc
-no-reboot
-watchdog i6300esb
-serial stdio
-display none
-monitor null
)
append=(
debug
sched_debug
apic=debug
ignore_loglevel
sysrq_always_enabled
panic=10
prompt_ramdisk=0
earlyprintk=ttyS0,115200
console=ttyS0,115200
console=tty0
vga=normal
root=/dev/ram0
rw
)
"${kvm[@]}" --append "${append[*]}"
-----------------------------------------------------------------------------
Thanks,
Fengguang
View attachment "dmesg-yocto-ivb41-51:20140629093503:x86_64-randconfig-hsxa0-06261808::" of type "text/plain" (50880 bytes)
View attachment "dmesg-yocto-lkp-wsx01-130:20140629095427:x86_64-randconfig-hsxa0-06261808::" of type "text/plain" (49139 bytes)
Download attachment "x86_64-randconfig-hsxa0-06261808-9c33bf1e59d26dad8dc45e438cbdc28783589b11-WARNING:---at----sd_init+-x-59038.log" of type "application/octet-stream" (37073 bytes)
View attachment "config-3.16.0-rc2-00004-g981fa87" of type "text/plain" (98464 bytes)
_______________________________________________
LKP mailing list
LKP@...ux.intel.com
Powered by blists - more mailing lists