Re: [GIT pull] CPU hotplug updates for 4.9

[Bart Van Assche]

On Mon, 2016-10-03 at 19:37 +0200, Thomas Gleixner wrote:
> Yet another batch of cpu hotplug core updates and conversions:
> 
>   - Provide core infrastructure for multi instance drivers so the drivers
>     do not have to keep custom lists.
> 
>   - Convert custom lists to the new infrastructure. The block-mq custom
>     list conversion comes through the block tree and makes the diffstat
>     tip over to more lines removed than added.
> 
>   - Handle unbalanced hotplug enable/disable calls more gracefully.
> 
>   - Remove the obsolete CPU_STARTING/DYING notifier support.
> 
>   - Convert another batch of notifier users. 
> 
>     The relayfs changes which conflicted with the conversion have been
>     shipped to me by Andrew.
> 
>     The remaining lot is targeted for 4.10 so that we finally can remove
>     the rest of the notifiers.

Hello Thomas,

Although I'm not sure this behavior has been introduced by the changes in this
pull request, since I started testing v4.11-rc[01] I ran several times into a
cpuhp_issue_call() hang:

# ./system-log | grep -a cpuhp_issue_call
Mar  3 11:32:49 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:04:38 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:12:50 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:21:02 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:29:13 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:37:25 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:45:36 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 12:53:48 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 16:59:52 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:08:04 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:16:15 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:24:27 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:32:39 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:40:50 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:49:02 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 17:57:13 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 18:05:25 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  3 18:13:36 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 16:34:17 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 16:42:29 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 16:50:40 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 16:58:52 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:07:04 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:15:15 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:23:27 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:31:38 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:39:50 kernel:  cpuhp_issue_call+0xb9/0xe0
Mar  6 17:48:01 kernel:  cpuhp_issue_call+0xb9/0xe0

The latest complaint is as follows:

INFO: task systemd-udevd:837 blocked for more than 480 seconds.
      Tainted: G          I     4.11.0-rc1-dbg+ #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
systemd-udevd   D    0   837    542 0x00000104
Call Trace:
 __schedule+0x302/0xc30
 schedule+0x38/0x90
 schedule_timeout+0x255/0x490
 wait_for_completion+0x103/0x170
 cpuhp_issue_call+0xb9/0xe0
 __cpuhp_setup_state+0xf6/0x180
 pkg_temp_thermal_init+0x76/0x1000 [x86_pkg_temp_thermal]
 do_one_initcall+0x3e/0x170
 do_init_module+0x5a/0x1ed
 load_module+0x2339/0x2a40
 SYSC_finit_module+0xbc/0xf0
 SyS_finit_module+0x9/0x10
 do_syscall_64+0x57/0x140
 entry_SYSCALL64_slow_path+0x25/0x25

Kernel v4.10 runs fine on the same system. From the dmidecode output:

Handle 0x0400, DMI type 4, 42 bytes
Processor Information
        Socket Designation: CPU1
        Type: Central Processor
        Family: Xeon
        Manufacturer: Intel
        ID: F2 06 03 00 FF FB EB BF
        Signature: Type 0, Family 6, Model 63, Stepping 2

Please let me know if you need more information. 

Thanks,

Bart.