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: Breno Leitao <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>

Author: leitao

Documentation/admin-guide/kernel-parameters.txt

@@ -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

@@ -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

@@ -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