rcu: Introduce CONFIG_RCU_EXP_CPU_STALL_TIMEOUT

Currently both expedited and regular grace period stall warnings use
a single timeout value that with units of seconds.  However, recent
Android use cases problem require a sub-100-millisecond expedited RCU CPU
stall warning.  Given that expedited RCU grace periods normally complete
in far less than a single millisecond, especially for small systems,
this is not unreasonable.

Therefore introduce the CONFIG_RCU_EXP_CPU_STALL_TIMEOUT kernel
configuration that defaults to 20 msec on Android and remains the same
as that of the non-expedited stall warnings otherwise.  It also can be
changed in run-time via: /sys/.../parameters/rcu_exp_cpu_stall_timeout.

[ paulmck: Default of zero to use CONFIG_RCU_STALL_TIMEOUT. ]

Signed-off-by: Uladzislau Rezki <uladzislau.rezki@sony.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Documentation/RCU/stallwarn.rst

@@ -162,6 +162,26 @@ CONFIG_RCU_CPU_STALL_TIMEOUT
 	Stall-warning messages may be enabled and disabled completely via
 	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
 
+CONFIG_RCU_EXP_CPU_STALL_TIMEOUT
+--------------------------------
+
+	Same as the CONFIG_RCU_CPU_STALL_TIMEOUT parameter but only for
+	the expedited grace period. This parameter defines the period
+	of time that RCU will wait from the beginning of an expedited
+	grace period until it issues an RCU CPU stall warning. This time
+	period is normally 20 milliseconds on Android devices.	A zero
+	value causes the CONFIG_RCU_CPU_STALL_TIMEOUT value to be used,
+	after conversion to milliseconds.
+
+	This configuration parameter may be changed at runtime via the
+	/sys/module/rcupdate/parameters/rcu_exp_cpu_stall_timeout, however
+	this parameter is checked only at the beginning of a cycle. If you
+	are in a current stall cycle, setting it to a new value will change
+	the timeout for the -next- stall.
+
+	Stall-warning messages may be enabled and disabled completely via
+	/sys/module/rcupdate/parameters/rcu_cpu_stall_suppress.
+
 RCU_STALL_DELAY_DELTA
 ---------------------
 

Documentation/admin-guide/kernel-parameters.txt

@@ -4893,6 +4893,18 @@
 
 	rcupdate.rcu_cpu_stall_timeout= [KNL]
 			Set timeout for RCU CPU stall warning messages.
+			The value is in seconds and the maximum allowed
+			value is 300 seconds.
+
+	rcupdate.rcu_exp_cpu_stall_timeout= [KNL]
+			Set timeout for expedited RCU CPU stall warning
+			messages.  The value is in milliseconds
+			and the maximum allowed value is 21000
+			milliseconds. Please note that this value is
+			adjusted to an arch timer tick resolution.
+			Setting this to zero causes the value from
+			rcupdate.rcu_cpu_stall_timeout to be used (after
+			conversion from seconds to milliseconds).
 
 	rcupdate.rcu_expedited= [KNL]
 			Use expedited grace-period primitives, for

kernel/rcu/Kconfig.debug

@@ -91,6 +91,20 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
+config RCU_EXP_CPU_STALL_TIMEOUT
+	int "Expedited RCU CPU stall timeout in milliseconds"
+	depends on RCU_STALL_COMMON
+	range 0 21000
+	default 20 if ANDROID
+	default 0 if !ANDROID
+	help
+	  If a given expedited RCU grace period extends more than the
+	  specified number of milliseconds, a CPU stall warning is printed.
+	  If the RCU grace period persists, additional CPU stall warnings
+	  are printed at more widely spaced intervals.  A value of zero
+	  says to use the RCU_CPU_STALL_TIMEOUT value converted from
+	  seconds to milliseconds.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL

kernel/rcu/rcu.h

@@ -210,7 +210,9 @@ static inline bool rcu_stall_is_suppressed_at_boot(void)
 extern int rcu_cpu_stall_ftrace_dump;
 extern int rcu_cpu_stall_suppress;
 extern int rcu_cpu_stall_timeout;
+extern int rcu_exp_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
+int rcu_exp_jiffies_till_stall_check(void);
 
 static inline bool rcu_stall_is_suppressed(void)
 {

kernel/rcu/tree_exp.h

@@ -496,7 +496,7 @@ static void synchronize_rcu_expedited_wait(void)
 	struct rcu_node *rnp_root = rcu_get_root();
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
-	jiffies_stall = rcu_jiffies_till_stall_check();
+	jiffies_stall = rcu_exp_jiffies_till_stall_check();
 	jiffies_start = jiffies;
 	if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
 		if (synchronize_rcu_expedited_wait_once(1))
@@ -571,7 +571,7 @@ static void synchronize_rcu_expedited_wait(void)
 				dump_cpu_task(cpu);
 			}
 		}
-		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+		jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3;
 	}
 }
 

kernel/rcu/tree_stall.h

@@ -25,6 +25,34 @@ int sysctl_max_rcu_stall_to_panic __read_mostly;
 #define RCU_STALL_MIGHT_DIV		8
 #define RCU_STALL_MIGHT_MIN		(2 * HZ)
 
+int rcu_exp_jiffies_till_stall_check(void)
+{
+	int cpu_stall_timeout = READ_ONCE(rcu_exp_cpu_stall_timeout);
+	int exp_stall_delay_delta = 0;
+	int till_stall_check;
+
+	// Zero says to use rcu_cpu_stall_timeout, but in milliseconds.
+	if (!cpu_stall_timeout)
+		cpu_stall_timeout = jiffies_to_msecs(rcu_jiffies_till_stall_check());
+
+	// Limit check must be consistent with the Kconfig limits for
+	// CONFIG_RCU_EXP_CPU_STALL_TIMEOUT, so check the allowed range.
+	// The minimum clamped value is "2UL", because at least one full
+	// tick has to be guaranteed.
+	till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 21UL * HZ);
+
+	if (cpu_stall_timeout && jiffies_to_msecs(till_stall_check) != cpu_stall_timeout)
+		WRITE_ONCE(rcu_exp_cpu_stall_timeout, jiffies_to_msecs(till_stall_check));
+
+#ifdef CONFIG_PROVE_RCU
+	/* Add extra ~25% out of till_stall_check. */
+	exp_stall_delay_delta = ((till_stall_check * 25) / 100) + 1;
+#endif
+
+	return till_stall_check + exp_stall_delay_delta;
+}
+EXPORT_SYMBOL_GPL(rcu_exp_jiffies_till_stall_check);
+
 /* Limit-check stall timeouts specified at boottime and runtime. */
 int rcu_jiffies_till_stall_check(void)
 {

kernel/rcu/update.c

@@ -506,6 +506,8 @@ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
 int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
+int rcu_exp_cpu_stall_timeout __read_mostly = CONFIG_RCU_EXP_CPU_STALL_TIMEOUT;
+module_param(rcu_exp_cpu_stall_timeout, int, 0644);
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
 // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall