rcu: Mark loads from rcu_state.n_online_cpus

The rcu_state.n_online_cpus value is only ever updated by CPU-hotplug
operations, which are serialized.  However, this value is read locklessly.
This commit therefore marks those reads.  While in the area, it also
adds ASSERT_EXCLUSIVE_WRITER() calls just in case parallel CPU hotplug
becomes a thing.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>

kernel/rcu/tree.c

@@ -4328,7 +4328,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
 // whether spinlocks may be acquired safely.
 static bool rcu_init_invoked(void)
 {
-	return !!rcu_state.n_online_cpus;
+	return !!READ_ONCE(rcu_state.n_online_cpus);
 }
 
 /*
@@ -4538,6 +4538,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	rcu_spawn_rnp_kthreads(rnp);
 	rcu_spawn_cpu_nocb_kthread(cpu);
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus);
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
 
 	return 0;
@@ -4806,6 +4807,7 @@ void rcutree_migrate_callbacks(int cpu)
  */
 int rcutree_dead_cpu(unsigned int cpu)
 {
+	ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus);
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
 	// Stop-machine done, so allow nohz_full to disable tick.
 	tick_dep_clear(TICK_DEP_BIT_RCU);

kernel/rcu/tree_stall.h

@@ -628,7 +628,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_err("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n",
 	       smp_processor_id(), (long)(jiffies - gps),
-	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus);
+	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen,
+	       data_race(rcu_state.n_online_cpus)); // Diagnostic read
 	if (ndetected) {
 		rcu_dump_cpu_stacks();
 
@@ -689,7 +690,8 @@ static void print_cpu_stall(unsigned long gps)
 		totqlen += rcu_get_n_cbs_cpu(cpu);
 	pr_err("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n",
 		jiffies - gps,
-		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus);
+		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen,
+		data_race(rcu_state.n_online_cpus)); // Diagnostic read
 
 	rcu_check_gp_kthread_expired_fqs_timer();
 	rcu_check_gp_kthread_starvation();