Commit 32d572e3 authored by Breno Leitao's avatar Breno Leitao Committed by Tejun Heo
Browse files

workqueue: add CONFIG_BOOTPARAM_WQ_STALL_PANIC option 



Add a kernel config option to set the default value of
workqueue.panic_on_stall, similar to CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC,
CONFIG_BOOTPARAM_HARDLOCKUP_PANIC and CONFIG_BOOTPARAM_HUNG_TASK_PANIC.

This allows setting the number of workqueue stalls before triggering
a kernel panic at build time, which is useful for high-availability
systems that need consistent panic-on-stall, in other words, those
servers which run with CONFIG_BOOTPARAM_*_PANIC=y already.

The default remains 0 (disabled). Setting it to 1 will panic on the
first stall, and higher values will panic after that many stall
warnings. The value can still be overridden at runtime via the
workqueue.panic_on_stall boot parameter or sysfs.

Signed-off-by: default avatarBreno Leitao <leitao@debian.org>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 51cd2d2d

Documentation/admin-guide/kernel-parameters.txt

+2 −1
Original line number Diff line number Diff line
@@ -8336,7 +8336,8 @@ Kernel parameters 
			CONFIG_WQ_WATCHDOG. It sets the number times of the

			stall to trigger panic.



			The default is 0, which disables the panic on stall.

			The default is set by CONFIG_BOOTPARAM_WQ_STALL_PANIC,

			which is 0 (disabled) if not configured.



	workqueue.cpu_intensive_thresh_us=

			Per-cpu work items which run for longer than this

kernel/workqueue.c

+1 −1
Original line number Diff line number Diff line
@@ -7568,7 +7568,7 @@ static struct timer_list wq_watchdog_timer; 
static unsigned long wq_watchdog_touched = INITIAL_JIFFIES;

static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES;



static unsigned int wq_panic_on_stall;

static unsigned int wq_panic_on_stall = CONFIG_BOOTPARAM_WQ_STALL_PANIC;

module_param_named(panic_on_stall, wq_panic_on_stall, uint, 0644);



/*

lib/Kconfig.debug

+23 −0
Original line number Diff line number Diff line
@@ -1297,6 +1297,29 @@ config WQ_WATCHDOG 
	  state.  This can be configured through kernel parameter

	  "workqueue.watchdog_thresh" and its sysfs counterpart.



config BOOTPARAM_WQ_STALL_PANIC

	int "Panic on Nth workqueue stall"

	default 0

	range 0 100

	depends on WQ_WATCHDOG

	help

	  Set the number of workqueue stalls to trigger a kernel panic.

	  A workqueue stall occurs when a worker pool doesn't make forward

	  progress on a pending work item for over 30 seconds (configurable

	  using the workqueue.watchdog_thresh parameter).



	  If n = 0, the kernel will not panic on stall. If n > 0, the kernel

	  will panic after n stall warnings.



	  The panic can be used in combination with panic_timeout,

	  to cause the system to reboot automatically after a

	  stall has been detected. This feature is useful for

	  high-availability systems that have uptime guarantees and

	  where a stall must be resolved ASAP.



	  This setting can be overridden at runtime via the

	  workqueue.panic_on_stall kernel parameter.



config WQ_CPU_INTENSIVE_REPORT

	bool "Report per-cpu work items which hog CPU for too long"

	depends on DEBUG_KERNEL