rcu: Make call_rcu() lazy to save power

Implement timer-based RCU callback batching (also known as lazy
callbacks). With this we save about 5-10% of power consumed due
to RCU requests that happen when system is lightly loaded or idle.

By default, all async callbacks (queued via call_rcu) are marked
lazy. An alternate API call_rcu_hurry() is provided for the few users,
for example synchronize_rcu(), that need the old behavior.

The batch is flushed whenever a certain amount of time has passed, or
the batch on a particular CPU grows too big. Also memory pressure will
flush it in a future patch.

To handle several corner cases automagically (such as rcu_barrier() and
hotplug), we re-use bypass lists which were originally introduced to
address lock contention, to handle lazy CBs as well. The bypass list
length has the lazy CB length included in it. A separate lazy CB length
counter is also introduced to keep track of the number of lazy CBs.

[ paulmck: Fix formatting of inline call_rcu_lazy() definition. ]
[ paulmck: Apply Zqiang feedback. ]
[ paulmck: Apply s/call_rcu_flush/call_rcu_hurry/ feedback from Tejun Heo. ]
Suggested-by: Paul McKenney <paulmck@kernel.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

include/linux/rcupdate.h

@@ -108,6 +108,15 @@ static inline int rcu_preempt_depth(void)
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_RCU_LAZY
+void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func);
+#else
+static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
+{
+	call_rcu(head, func);
+}
+#endif
+
 /* Internal to kernel */
 void rcu_init(void);
 extern int rcu_scheduler_active;

kernel/rcu/Kconfig

@@ -311,4 +311,12 @@ config TASKS_TRACE_RCU_READ_MB
 	  Say N here if you hate read-side memory barriers.
 	  Take the default if you are unsure.
 
+config RCU_LAZY
+	bool "RCU callback lazy invocation functionality"
+	depends on RCU_NOCB_CPU
+	default n
+	help
+	  To save power, batch RCU callbacks and flush after delay, memory
+	  pressure, or callback list growing too big.
+
 endmenu # "RCU Subsystem"

kernel/rcu/rcu.h

@@ -474,6 +474,14 @@ enum rcutorture_type {
 	INVALID_RCU_FLAVOR
 };
 
+#if defined(CONFIG_RCU_LAZY)
+unsigned long rcu_lazy_get_jiffies_till_flush(void);
+void rcu_lazy_set_jiffies_till_flush(unsigned long j);
+#else
+static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; }
+static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { }
+#endif
+
 #if defined(CONFIG_TREE_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gp_seq);

kernel/rcu/tiny.c

@@ -44,7 +44,7 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
 
 void rcu_barrier(void)
 {
-	wait_rcu_gp(call_rcu);
+	wait_rcu_gp(call_rcu_hurry);
 }
 EXPORT_SYMBOL(rcu_barrier);
 

kernel/rcu/tree.c

@@ -2728,47 +2728,8 @@ static void check_cb_ovld(struct rcu_data *rdp)
 	raw_spin_unlock_rcu_node(rnp);
 }
 
-/**
- * call_rcu() - Queue an RCU callback for invocation after a grace period.
- * @head: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all pre-existing RCU read-side
- * critical sections have completed.  However, the callback function
- * might well execute concurrently with RCU read-side critical sections
- * that started after call_rcu() was invoked.
- *
- * RCU read-side critical sections are delimited by rcu_read_lock()
- * and rcu_read_unlock(), and may be nested.  In addition, but only in
- * v5.0 and later, regions of code across which interrupts, preemption,
- * or softirqs have been disabled also serve as RCU read-side critical
- * sections.  This includes hardware interrupt handlers, softirq handlers,
- * and NMI handlers.
- *
- * Note that all CPUs must agree that the grace period extended beyond
- * all pre-existing RCU read-side critical section.  On systems with more
- * than one CPU, this means that when "func()" is invoked, each CPU is
- * guaranteed to have executed a full memory barrier since the end of its
- * last RCU read-side critical section whose beginning preceded the call
- * to call_rcu().  It also means that each CPU executing an RCU read-side
- * critical section that continues beyond the start of "func()" must have
- * executed a memory barrier after the call_rcu() but before the beginning
- * of that RCU read-side critical section.  Note that these guarantees
- * include CPUs that are offline, idle, or executing in user mode, as
- * well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
- * resulting RCU callback function "func()", then both CPU A and CPU B are
- * guaranteed to execute a full memory barrier during the time interval
- * between the call to call_rcu() and the invocation of "func()" -- even
- * if CPU A and CPU B are the same CPU (but again only if the system has
- * more than one CPU).
- *
- * Implementation of these memory-ordering guarantees is described here:
- * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
- */
-void call_rcu(struct rcu_head *head, rcu_callback_t func)
+static void
+__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy)
 {
 	static atomic_t doublefrees;
 	unsigned long flags;
@@ -2809,7 +2770,7 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 	}
 
 	check_cb_ovld(rdp);
-	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags))
+	if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy))
 		return; // Enqueued onto ->nocb_bypass, so just leave.
 	// If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock.
 	rcu_segcblist_enqueue(&rdp->cblist, head);
@@ -2831,8 +2792,84 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func)
 		local_irq_restore(flags);
 	}
 }
-EXPORT_SYMBOL_GPL(call_rcu);
 
+#ifdef CONFIG_RCU_LAZY
+/**
+ * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and
+ * flush all lazy callbacks (including the new one) to the main ->cblist while
+ * doing so.
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.
+ *
+ * Use this API instead of call_rcu() if you don't want the callback to be
+ * invoked after very long periods of time, which can happen on systems without
+ * memory pressure and on systems which are lightly loaded or mostly idle.
+ * This function will cause callbacks to be invoked sooner than later at the
+ * expense of extra power. Other than that, this function is identical to, and
+ * reuses call_rcu()'s logic. Refer to call_rcu() for more details about memory
+ * ordering and other functionality.
+ */
+void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func)
+{
+	return __call_rcu_common(head, func, false);
+}
+EXPORT_SYMBOL_GPL(call_rcu_hurry);
+#endif
+
+/**
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
+ * By default the callbacks are 'lazy' and are kept hidden from the main
+ * ->cblist to prevent starting of grace periods too soon.
+ * If you desire grace periods to start very soon, use call_rcu_hurry().
+ *
+ * @head: structure to be used for queueing the RCU updates.
+ * @func: actual callback function to be invoked after the grace period
+ *
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.  However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.
+ *
+ * RCU read-side critical sections are delimited by rcu_read_lock()
+ * and rcu_read_unlock(), and may be nested.  In addition, but only in
+ * v5.0 and later, regions of code across which interrupts, preemption,
+ * or softirqs have been disabled also serve as RCU read-side critical
+ * sections.  This includes hardware interrupt handlers, softirq handlers,
+ * and NMI handlers.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing RCU read-side critical section.  On systems with more
+ * than one CPU, this means that when "func()" is invoked, each CPU is
+ * guaranteed to have executed a full memory barrier since the end of its
+ * last RCU read-side critical section whose beginning preceded the call
+ * to call_rcu().  It also means that each CPU executing an RCU read-side
+ * critical section that continues beyond the start of "func()" must have
+ * executed a memory barrier after the call_rcu() but before the beginning
+ * of that RCU read-side critical section.  Note that these guarantees
+ * include CPUs that are offline, idle, or executing in user mode, as
+ * well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting RCU callback function "func()", then both CPU A and CPU B are
+ * guaranteed to execute a full memory barrier during the time interval
+ * between the call to call_rcu() and the invocation of "func()" -- even
+ * if CPU A and CPU B are the same CPU (but again only if the system has
+ * more than one CPU).
+ *
+ * Implementation of these memory-ordering guarantees is described here:
+ * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst.
+ */
+void call_rcu(struct rcu_head *head, rcu_callback_t func)
+{
+	return __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY));
+}
+EXPORT_SYMBOL_GPL(call_rcu);
 
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (5 * HZ)
@@ -3507,7 +3544,7 @@ void synchronize_rcu(void)
 		if (rcu_gp_is_expedited())
 			synchronize_rcu_expedited();
 		else
-			wait_rcu_gp(call_rcu);
+			wait_rcu_gp(call_rcu_hurry);
 		return;
 	}
 
@@ -3910,7 +3947,7 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 	 * if it's fully lazy.
 	 */
 	was_alldone = rcu_rdp_is_offloaded(rdp) && !rcu_segcblist_pend_cbs(&rdp->cblist);
-	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
 	wake_nocb = was_alldone && rcu_segcblist_pend_cbs(&rdp->cblist);
 	if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) {
 		atomic_inc(&rcu_state.barrier_cpu_count);
@@ -4336,7 +4373,7 @@ void rcutree_migrate_callbacks(int cpu)
 	my_rdp = this_cpu_ptr(&rcu_data);
 	my_rnp = my_rdp->mynode;
 	rcu_nocb_lock(my_rdp); /* irqs already disabled. */
-	WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies));
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(my_rdp, NULL, jiffies, false));
 	raw_spin_lock_rcu_node(my_rnp); /* irqs already disabled. */
 	/* Leverage recent GPs and set GP for new callbacks. */
 	needwake = rcu_advance_cbs(my_rnp, rdp) ||

kernel/rcu/tree.h

@@ -263,14 +263,16 @@ struct rcu_data {
 	unsigned long last_fqs_resched;	/* Time of last rcu_resched(). */
 	unsigned long last_sched_clock;	/* Jiffies of last rcu_sched_clock_irq(). */
 
+	long lazy_len;			/* Length of buffered lazy callbacks. */
 	int cpu;
 };
 
 /* Values for nocb_defer_wakeup field in struct rcu_data. */
 #define RCU_NOCB_WAKE_NOT	0
 #define RCU_NOCB_WAKE_BYPASS	1
-#define RCU_NOCB_WAKE		2
-#define RCU_NOCB_WAKE_FORCE	3
+#define RCU_NOCB_WAKE_LAZY	2
+#define RCU_NOCB_WAKE		3
+#define RCU_NOCB_WAKE_FORCE	4
 
 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
 					/* For jiffies_till_first_fqs and */
@@ -441,9 +443,10 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
 static void rcu_init_one_nocb(struct rcu_node *rnp);
 static bool wake_nocb_gp(struct rcu_data *rdp, bool force);
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				  unsigned long j);
+				  unsigned long j, bool lazy);
 static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				bool *was_alldone, unsigned long flags);
+				bool *was_alldone, unsigned long flags,
+				bool lazy);
 static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
 				 unsigned long flags);
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);

kernel/rcu/tree_exp.h

@@ -937,7 +937,7 @@ void synchronize_rcu_expedited(void)
 
 	/* If expedited grace periods are prohibited, fall back to normal. */
 	if (rcu_gp_is_normal()) {
-		wait_rcu_gp(call_rcu);
+		wait_rcu_gp(call_rcu_hurry);
 		return;
 	}