rcu: Panic after fixed number of stalls

Some stalls are transient, so that system fully recovers.  This commit
therefore allows users to configure the number of stalls that must happen
in order to trigger kernel panic.

Signed-off-by: chao <chao@eero.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

include/linux/kernel.h

@@ -536,6 +536,7 @@ extern int panic_on_warn;
 extern unsigned long panic_on_taint;
 extern bool panic_on_taint_nousertaint;
 extern int sysctl_panic_on_rcu_stall;
+extern int sysctl_max_rcu_stall_to_panic;
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;

kernel/rcu/tree_stall.h

@@ -13,6 +13,7 @@
 
 /* panic() on RCU Stall sysctl. */
 int sysctl_panic_on_rcu_stall __read_mostly;
+int sysctl_max_rcu_stall_to_panic __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
@@ -106,6 +107,11 @@ early_initcall(check_cpu_stall_init);
 /* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
 static void panic_on_rcu_stall(void)
 {
+	static int cpu_stall;
+
+	if (++cpu_stall < sysctl_max_rcu_stall_to_panic)
+		return;
+
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
 }

kernel/sysctl.c

@@ -2650,6 +2650,17 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
+#if defined(CONFIG_TREE_RCU)
+	{
+		.procname	= "max_rcu_stall_to_panic",
+		.data		= &sysctl_max_rcu_stall_to_panic,
+		.maxlen		= sizeof(sysctl_max_rcu_stall_to_panic),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+#endif
 #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
 	{
 		.procname	= "stack_erasing",