Re: [PATCH v2] hungtask: add filter kthread

[Michal Hocko]

On Thu 05-08-21 21:47:47, chenguanyou wrote:
> Some kernel threads are always in D state, when we enable hung_task,
> it will misjudge, we should skip these to narrow the scope.
> 
> exp mediatek:
> root            435   435      2       0      0 mtk_lpm_monitor_thread 0 D LPM-0
> root            436   436      2       0      0 mtk_lpm_monitor_thread 0 D LPM-1
> root            437   437      2       0      0 mtk_lpm_monitor_thread 0 D LPM-2
> root            438   438      2       0      0 mtk_lpm_monitor_thread 0 D LPM-3
> root            439   439      2       0      0 mtk_lpm_monitor_thread 0 D LPM-4
> root            440   440      2       0      0 mtk_lpm_monitor_thread 0 D LPM-5
> root            441   441      2       0      0 mtk_lpm_monitor_thread 0 D LPM-6
> root            442   442      2       0      0 mtk_lpm_monitor_thread 0 D LPM-7

A similar approch has been proposed in the past (sorry I do not have
links handy) and always deemed a wrong way to approach the problem.
Either those kernel threads should be fixed to use less sleep or
annotate the sleep properly (TASK_IDLE).

> Signed-off-by: chenguanyou <chenguanyou@xxxxxxxxxx>
> ---
>  Documentation/admin-guide/sysctl/kernel.rst | 10 ++++++++++
>  include/linux/sched/sysctl.h                |  1 +
>  kernel/hung_task.c                          |  8 ++++++++
>  kernel/sysctl.c                             |  9 +++++++++
>  lib/Kconfig.debug                           | 15 +++++++++++++++
>  5 files changed, 43 insertions(+)
> 
> diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
> index 68b21395a743..3c7c74b26d95 100644
> --- a/Documentation/admin-guide/sysctl/kernel.rst
> +++ b/Documentation/admin-guide/sysctl/kernel.rst
> @@ -405,6 +405,16 @@ This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
>  
>  -1: report an infinite number of warnings.
>  
> +hung_task_filter_kthread
> +========================
> +
> +We should skip kthread when a hung task is detected.
> +This file shows up if ``CONFIG_DEFAULT_HUNG_TASK_FILTER_KTHREAD`` is enabled.
> +
> += =========================================================
> +0 Not skip detect kthread.
> +1 Skip detect kthread.
> += =========================================================
>  
>  hyperv_record_panic_msg
>  =======================
> diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
> index db2c0f34aaaf..2b8b01b57559 100644
> --- a/include/linux/sched/sysctl.h
> +++ b/include/linux/sched/sysctl.h
> @@ -19,6 +19,7 @@ extern unsigned int  sysctl_hung_task_panic;
>  extern unsigned long sysctl_hung_task_timeout_secs;
>  extern unsigned long sysctl_hung_task_check_interval_secs;
>  extern int sysctl_hung_task_warnings;
> +extern unsigned int sysctl_hung_task_filter_kthread;
>  int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
>  		void *buffer, size_t *lenp, loff_t *ppos);
>  #else
> diff --git a/kernel/hung_task.c b/kernel/hung_task.c
> index 396ebaebea3f..74ad75c2dde8 100644
> --- a/kernel/hung_task.c
> +++ b/kernel/hung_task.c
> @@ -48,6 +48,11 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_
>   */
>  unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
>  
> +/*
> + * Non-zero means no checking kthread
> + */
> +unsigned int __read_mostly sysctl_hung_task_filter_kthread = CONFIG_DEFAULT_HUNG_TASK_FILTER_KTHREAD;
> +
>  int __read_mostly sysctl_hung_task_warnings = 10;
>  
>  static int __read_mostly did_panic;
> @@ -88,6 +93,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
>  {
>  	unsigned long switch_count = t->nvcsw + t->nivcsw;
>  
> +	if (unlikely(sysctl_hung_task_filter_kthread && t->flags & PF_KTHREAD))
> +		return;
> +
>  	/*
>  	 * Ensure the task is not frozen.
>  	 * Also, skip vfork and any other user process that freezer should skip.
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index d4a78e08f6d8..62067b9db486 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -2513,6 +2513,15 @@ static struct ctl_table kern_table[] = {
>  		.proc_handler	= proc_dointvec_minmax,
>  		.extra1		= &neg_one,
>  	},
> +	{
> +		.procname	= "hung_task_filter_kthread",
> +		.data		= &sysctl_hung_task_filter_kthread,
> +		.maxlen		= sizeof(int),
> +		.mode		= 0644,
> +		.proc_handler   = proc_dointvec_minmax,
> +		.extra1		= SYSCTL_ZERO,
> +		.extra2		= SYSCTL_ONE,
> +	},
>  #endif
>  #ifdef CONFIG_RT_MUTEXES
>  	{
> diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
> index 678c13967580..d7063f955987 100644
> --- a/lib/Kconfig.debug
> +++ b/lib/Kconfig.debug
> @@ -1110,6 +1110,21 @@ config DEFAULT_HUNG_TASK_TIMEOUT
>  	  A timeout of 0 disables the check.  The default is two minutes.
>  	  Keeping the default should be fine in most cases.
>  
> +config DEFAULT_HUNG_TASK_FILTER_KTHREAD
> +	int "Default filter kthread for hung task"
> +	depends on DETECT_HUNG_TASK
> +	range 0 1
> +	default 0
> +	help
> +	  This option controls filter kthread uses to determine when
> +	  a kernel task has become "state=TASK_UNINTERRUPTIBLE" and should be skipped.
> +
> +	  It can be adjusted at runtime via the kernel.hung_task_filter_kthread
> +	  sysctl or by writing a value to
> +	  /proc/sys/kernel/hung_task_filter_kthread.
> +
> +	  A filter of 1 disables the check.
> +
>  config BOOTPARAM_HUNG_TASK_PANIC
>  	bool "Panic (Reboot) On Hung Tasks"
>  	depends on DETECT_HUNG_TASK
> -- 
> 2.17.1

-- 
Michal Hocko
SUSE Labs