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>

1 files changed, 129 insertions, 30 deletions

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 094fd454b6c3..d6e4c076b051 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -257,6 +257,31 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
 }
 
 /*
+ * LAZY_FLUSH_JIFFIES decides the maximum amount of time that
+ * can elapse before lazy callbacks are flushed. Lazy callbacks
+ * could be flushed much earlier for a number of other reasons
+ * however, LAZY_FLUSH_JIFFIES will ensure no lazy callbacks are
+ * left unsubmitted to RCU after those many jiffies.
+ */
+#define LAZY_FLUSH_JIFFIES (10 * HZ)
+static unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES;
+
+#ifdef CONFIG_RCU_LAZY
+// To be called only from test code.
+void rcu_lazy_set_jiffies_till_flush(unsigned long jif)
+{
+	jiffies_till_flush = jif;
+}
+EXPORT_SYMBOL(rcu_lazy_set_jiffies_till_flush);
+
+unsigned long rcu_lazy_get_jiffies_till_flush(void)
+{
+	return jiffies_till_flush;
+}
+EXPORT_SYMBOL(rcu_lazy_get_jiffies_till_flush);
+#endif
+
+/*
  * Arrange to wake the GP kthread for this NOCB group at some future
  * time when it is safe to do so.
  */
@@ -269,10 +294,14 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
 	raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags);
 
 	/*
-	 * Bypass wakeup overrides previous deferments. In case
-	 * of callback storm, no need to wake up too early.
+	 * Bypass wakeup overrides previous deferments. In case of
+	 * callback storms, no need to wake up too early.
 	 */
-	if (waketype == RCU_NOCB_WAKE_BYPASS) {
+	if (waketype == RCU_NOCB_WAKE_LAZY &&
+	    rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) {
+		mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush);
+		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
+	} else if (waketype == RCU_NOCB_WAKE_BYPASS) {
 		mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
 		WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
 	} else {
@@ -293,10 +322,13 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
  * proves to be initially empty, just return false because the no-CB GP
  * kthread may need to be awakened in this case.
  *
+ * Return true if there was something to be flushed and it succeeded, otherwise
+ * false.
+ *
  * Note that this function always returns true if rhp is NULL.
  */
 static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				     unsigned long j)
+				     unsigned long j, bool lazy)
 {
 	struct rcu_cblist rcl;
 
@@ -310,7 +342,20 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	/* Note: ->cblist.len already accounts for ->nocb_bypass contents. */
 	if (rhp)
 		rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
-	rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
+
+	/*
+	 * If the new CB requested was a lazy one, queue it onto the main
+	 * ->cblist so we can take advantage of a sooner grade period.
+	 */
+	if (lazy && rhp) {
+		rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, NULL);
+		rcu_cblist_enqueue(&rcl, rhp);
+		WRITE_ONCE(rdp->lazy_len, 0);
+	} else {
+		rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
+		WRITE_ONCE(rdp->lazy_len, 0);
+	}
+
 	rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rcl);
 	WRITE_ONCE(rdp->nocb_bypass_first, j);
 	rcu_nocb_bypass_unlock(rdp);
@@ -326,13 +371,13 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
  * Note that this function always returns true if rhp is NULL.
  */
 static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
-				  unsigned long j)
+				  unsigned long j, bool lazy)
 {
 	if (!rcu_rdp_is_offloaded(rdp))
 		return true;
 	rcu_lockdep_assert_cblist_protected(rdp);
 	rcu_nocb_bypass_lock(rdp);
-	return rcu_nocb_do_flush_bypass(rdp, rhp, j);
+	return rcu_nocb_do_flush_bypass(rdp, rhp, j, lazy);
 }
 
 /*
@@ -345,7 +390,7 @@ static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j)
 	if (!rcu_rdp_is_offloaded(rdp) ||
 	    !rcu_nocb_bypass_trylock(rdp))
 		return;
-	WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j));
+	WARN_ON_ONCE(!rcu_nocb_do_flush_bypass(rdp, NULL, j, false));
 }
 
 /*
@@ -367,12 +412,14 @@ static void rcu_nocb_try_flush_bypass(struct rcu_data *rdp, unsigned long j)
  * there is only one CPU in operation.
  */
 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)
 {
 	unsigned long c;
 	unsigned long cur_gp_seq;
 	unsigned long j = jiffies;
 	long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+	bool bypass_is_lazy = (ncbs == READ_ONCE(rdp->lazy_len));
 
 	lockdep_assert_irqs_disabled();
 
@@ -417,25 +464,29 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	// If there hasn't yet been all that many ->cblist enqueues
 	// this jiffy, tell the caller to enqueue onto ->cblist.  But flush
 	// ->nocb_bypass first.
-	if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy) {
+	// Lazy CBs throttle this back and do immediate bypass queuing.
+	if (rdp->nocb_nobypass_count < nocb_nobypass_lim_per_jiffy && !lazy) {
 		rcu_nocb_lock(rdp);
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
 		if (*was_alldone)
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("FirstQ"));
-		WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j));
+
+		WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, j, false));
 		WARN_ON_ONCE(rcu_cblist_n_cbs(&rdp->nocb_bypass));
 		return false; // Caller must enqueue the callback.
 	}
 
 	// If ->nocb_bypass has been used too long or is too full,
 	// flush ->nocb_bypass to ->cblist.
-	if ((ncbs && j != READ_ONCE(rdp->nocb_bypass_first)) ||
+	if ((ncbs && !bypass_is_lazy && j != READ_ONCE(rdp->nocb_bypass_first)) ||
+	    (ncbs &&  bypass_is_lazy &&
+	     (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush))) ||
 	    ncbs >= qhimark) {
 		rcu_nocb_lock(rdp);
 		*was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist);
 
-		if (!rcu_nocb_flush_bypass(rdp, rhp, j)) {
+		if (!rcu_nocb_flush_bypass(rdp, rhp, j, lazy)) {
 			if (*was_alldone)
 				trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 						    TPS("FirstQ"));
@@ -463,13 +514,24 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
 	ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
 	rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
 	rcu_cblist_enqueue(&rdp->nocb_bypass, rhp);
+
+	if (lazy)
+		WRITE_ONCE(rdp->lazy_len, rdp->lazy_len + 1);
+
 	if (!ncbs) {
 		WRITE_ONCE(rdp->nocb_bypass_first, j);
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQ"));
 	}
 	rcu_nocb_bypass_unlock(rdp);
 	smp_mb(); /* Order enqueue before wake. */
-	if (ncbs) {
+	// A wake up of the grace period kthread or timer adjustment
+	// needs to be done only if:
+	// 1. Bypass list was fully empty before (this is the first
+	//    bypass list entry), or:
+	// 2. Both of these conditions are met:
+	//    a. The bypass list previously had only lazy CBs, and:
+	//    b. The new CB is non-lazy.
+	if (ncbs && (!bypass_is_lazy || lazy)) {
 		local_irq_restore(flags);
 	} else {
 		// No-CBs GP kthread might be indefinitely asleep, if so, wake.
@@ -497,8 +559,10 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 				 unsigned long flags)
 				 __releases(rdp->nocb_lock)
 {
+	long bypass_len;
 	unsigned long cur_gp_seq;
 	unsigned long j;
+	long lazy_len;
 	long len;
 	struct task_struct *t;
 
@@ -512,9 +576,16 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	}
 	// Need to actually to a wakeup.
 	len = rcu_segcblist_n_cbs(&rdp->cblist);
+	bypass_len = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+	lazy_len = READ_ONCE(rdp->lazy_len);
 	if (was_alldone) {
 		rdp->qlen_last_fqs_check = len;
-		if (!irqs_disabled_flags(flags)) {
+		// Only lazy CBs in bypass list
+		if (lazy_len && bypass_len == lazy_len) {
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+			wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY,
+					   TPS("WakeLazy"));
+		} else if (!irqs_disabled_flags(flags)) {
 			/* ... if queue was empty ... */
 			rcu_nocb_unlock_irqrestore(rdp, flags);
 			wake_nocb_gp(rdp, false);
@@ -605,12 +676,12 @@ static void nocb_gp_sleep(struct rcu_data *my_rdp, int cpu)
 static void nocb_gp_wait(struct rcu_data *my_rdp)
 {
 	bool bypass = false;
-	long bypass_ncbs;
 	int __maybe_unused cpu = my_rdp->cpu;
 	unsigned long cur_gp_seq;
 	unsigned long flags;
 	bool gotcbs = false;
 	unsigned long j = jiffies;
+	bool lazy = false;
 	bool needwait_gp = false; // This prevents actual uninitialized use.
 	bool needwake;
 	bool needwake_gp;
@@ -640,24 +711,43 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	 * won't be ignored for long.
 	 */
 	list_for_each_entry(rdp, &my_rdp->nocb_head_rdp, nocb_entry_rdp) {
+		long bypass_ncbs;
+		bool flush_bypass = false;
+		long lazy_ncbs;
+
 		trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check"));
 		rcu_nocb_lock_irqsave(rdp, flags);
 		lockdep_assert_held(&rdp->nocb_lock);
 		bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
-		if (bypass_ncbs &&
+		lazy_ncbs = READ_ONCE(rdp->lazy_len);
+
+		if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) &&
+		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) ||
+		     bypass_ncbs > 2 * qhimark)) {
+			flush_bypass = true;
+		} else if (bypass_ncbs && (lazy_ncbs != bypass_ncbs) &&
 		    (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) ||
 		     bypass_ncbs > 2 * qhimark)) {
-			// Bypass full or old, so flush it.
-			(void)rcu_nocb_try_flush_bypass(rdp, j);
-			bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+			flush_bypass = true;
 		} else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) {
 			rcu_nocb_unlock_irqrestore(rdp, flags);
 			continue; /* No callbacks here, try next. */
 		}
+
+		if (flush_bypass) {
+			// Bypass full or old, so flush it.
+			(void)rcu_nocb_try_flush_bypass(rdp, j);
+			bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+			lazy_ncbs = READ_ONCE(rdp->lazy_len);
+		}
+
 		if (bypass_ncbs) {
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
-					    TPS("Bypass"));
-			bypass = true;
+					    bypass_ncbs == lazy_ncbs ? TPS("Lazy") : TPS("Bypass"));
+			if (bypass_ncbs == lazy_ncbs)
+				lazy = true;
+			else
+				bypass = true;
 		}
 		rnp = rdp->mynode;
 
@@ -705,12 +795,20 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	my_rdp->nocb_gp_gp = needwait_gp;
 	my_rdp->nocb_gp_seq = needwait_gp ? wait_gp_seq : 0;
 
-	if (bypass && !rcu_nocb_poll) {
-		// At least one child with non-empty ->nocb_bypass, so set
-		// timer in order to avoid stranding its callbacks.
-		wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_BYPASS,
-				   TPS("WakeBypassIsDeferred"));
+	// At least one child with non-empty ->nocb_bypass, so set
+	// timer in order to avoid stranding its callbacks.
+	if (!rcu_nocb_poll) {
+		// If bypass list only has lazy CBs. Add a deferred lazy wake up.
+		if (lazy && !bypass) {
+			wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_LAZY,
+					TPS("WakeLazyIsDeferred"));
+		// Otherwise add a deferred bypass wake up.
+		} else if (bypass) {
+			wake_nocb_gp_defer(my_rdp, RCU_NOCB_WAKE_BYPASS,
+					TPS("WakeBypassIsDeferred"));
+		}
 	}
+
 	if (rcu_nocb_poll) {
 		/* Polling, so trace if first poll in the series. */
 		if (gotcbs)
@@ -1036,7 +1134,7 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	 * return false, which means that future calls to rcu_nocb_try_bypass()
 	 * will refuse to put anything into the bypass.
 	 */
-	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false));
 	/*
 	 * Start with invoking rcu_core() early. This way if the current thread
 	 * happens to preempt an ongoing call to rcu_core() in the middle,
@@ -1278,6 +1376,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
 	raw_spin_lock_init(&rdp->nocb_gp_lock);
 	timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0);
 	rcu_cblist_init(&rdp->nocb_bypass);
+	WRITE_ONCE(rdp->lazy_len, 0);
 	mutex_init(&rdp->nocb_gp_kthread_mutex);
 }
 
@@ -1564,13 +1663,13 @@ 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)
 {
 	return true;
 }
 
 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)
 {
 	return false;
 }