rcu/nocb: Use separate flag to indicate offloaded ->cblist

RCU callback processing currently uses rcu_is_nocb_cpu() to determine
whether or not the current CPU's callbacks are to be offloaded.
This works, but it is not so good for cache locality.  Plus use of
->cblist for offloaded callbacks will greatly increase the frequency
of these checks.  This commit therefore adds a ->offloaded flag to the
rcu_segcblist structure to provide a more flexible and cache-friendly
means of checking for callback offloading.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>

include/linux/rcu_segcblist.h

@@ -71,6 +71,7 @@ struct rcu_segcblist {
 	long len;
 	long len_lazy;
 	u8 enabled;
+	u8 offloaded;
 };
 
 #define RCU_SEGCBLIST_INITIALIZER(n) \

kernel/rcu/rcu_segcblist.c

@@ -73,6 +73,18 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 	rsclp->enabled = 0;
 }
 
+/*
+ * Mark the specified rcu_segcblist structure as offloaded.  This
+ * structure must be empty.
+ */
+void rcu_segcblist_offload(struct rcu_segcblist *rsclp)
+{
+	WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
+	WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
+	WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
+	rsclp->offloaded = 1;
+}
+
 /*
  * Does the specified rcu_segcblist structure contain callbacks that
  * are ready to be invoked?

kernel/rcu/rcu_segcblist.h

@@ -66,6 +66,12 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
 	return rsclp->enabled;
 }
 
+/* Is the specified rcu_segcblist offloaded?  */
+static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
+{
+	return rsclp->offloaded;
+}
+
 /*
  * Are all segments following the specified segment of the specified
  * rcu_segcblist structure empty of callbacks?  (The specified
@@ -78,6 +84,7 @@ static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
 
 void rcu_segcblist_init(struct rcu_segcblist *rsclp);
 void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
+void rcu_segcblist_offload(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
 bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
 struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);

kernel/rcu/tree.c

@@ -2858,10 +2858,11 @@ void rcu_barrier(void)
 	 * corresponding CPU's preceding callbacks have been invoked.
 	 */
 	for_each_possible_cpu(cpu) {
-		if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu))
-			continue;
 		rdp = per_cpu_ptr(&rcu_data, cpu);
-		if (rcu_is_nocb_cpu(cpu)) {
+		if (!cpu_online(cpu) &&
+		    !rcu_segcblist_is_offloaded(&rdp->cblist))
+			continue;
+		if (rcu_segcblist_is_offloaded(&rdp->cblist)) {
 			if (!rcu_nocb_cpu_needs_barrier(cpu)) {
 				rcu_barrier_trace(TPS("OfflineNoCB"), cpu,
 						   rcu_state.barrier_sequence);
@@ -3155,7 +3156,8 @@ void rcutree_migrate_callbacks(int cpu)
 	struct rcu_node *rnp_root = rcu_get_root();
 	bool needwake;
 
-	if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist))
+	if (rcu_segcblist_is_offloaded(&rdp->cblist) ||
+	    rcu_segcblist_empty(&rdp->cblist))
 		return;  /* No callbacks to migrate. */
 
 	local_irq_save(flags);

kernel/rcu/tree_plugin.h

@@ -1382,7 +1382,7 @@ static void rcu_prepare_for_idle(void)
 	int tne;
 
 	lockdep_assert_irqs_disabled();
-	if (rcu_is_nocb_cpu(smp_processor_id()))
+	if (rcu_segcblist_is_offloaded(&rdp->cblist))
 		return;
 
 	/* Handle nohz enablement switches conservatively. */
@@ -1431,8 +1431,10 @@ static void rcu_prepare_for_idle(void)
  */
 static void rcu_cleanup_after_idle(void)
 {
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
 	lockdep_assert_irqs_disabled();
-	if (rcu_is_nocb_cpu(smp_processor_id()))
+	if (rcu_segcblist_is_offloaded(&rdp->cblist))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
@@ -1694,7 +1696,7 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 			    bool lazy, unsigned long flags)
 {
 
-	if (!rcu_is_nocb_cpu(rdp->cpu))
+	if (!rcu_segcblist_is_offloaded(&rdp->cblist))
 		return false;
 	__call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags);
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
@@ -1729,7 +1731,7 @@ static bool __maybe_unused rcu_nocb_adopt_orphan_cbs(struct rcu_data *my_rdp,
 						     unsigned long flags)
 {
 	lockdep_assert_irqs_disabled();
-	if (!rcu_is_nocb_cpu(smp_processor_id()))
+	if (!rcu_segcblist_is_offloaded(&my_rdp->cblist))
 		return false; /* Not NOCBs CPU, caller must migrate CBs. */
 	__call_rcu_nocb_enqueue(my_rdp, rcu_segcblist_head(&rdp->cblist),
 				rcu_segcblist_tail(&rdp->cblist),
@@ -2192,6 +2194,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 	}
 	rcu_segcblist_init(&rdp->cblist);
 	rcu_segcblist_disable(&rdp->cblist);
+	rcu_segcblist_offload(&rdp->cblist);
 	return true;
 }