rcu: Synchronize ->qsmaskinitnext in rcu_boost_kthread_setaffinity()

Once either rcutree_online_cpu() or rcutree_dead_cpu() is invoked
concurrently, the following rcu_boost_kthread_setaffinity() race can
occur:

        CPU 1                               CPU2
mask = rcu_rnp_online_cpus(rnp);
...

                                   mask = rcu_rnp_online_cpus(rnp);
                                   ...
                                   set_cpus_allowed_ptr(t, cm);

set_cpus_allowed_ptr(t, cm);

This results in CPU2's update being overwritten by that of CPU1, and
thus the possibility of ->boost_kthread_task continuing to run on a
to-be-offlined CPU.

This commit therefore eliminates this race by relying on the pre-existing
acquisition of ->boost_kthread_mutex to serialize the full process of
changing the affinity of ->boost_kthread_task.

Signed-off-by: Pingfan Liu <[email protected]>
Cc: David Woodhouse <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Neeraj Upadhyay <[email protected]>
Cc: Josh Triplett <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Mathieu Desnoyers <[email protected]>
Cc: Lai Jiangshan <[email protected]>
Cc: Joel Fernandes <[email protected]>
Cc: "Jason A. Donenfeld" <[email protected]>
Signed-off-by: Paul E. McKenney <[email protected]>

Author: liupingfan

kernel/rcu/tree_plugin.h

@@ -1221,11 +1221,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
  * We don't include outgoingcpu in the affinity set, use -1 if there is
  * no outgoing CPU.  If there are no CPUs left in the affinity set,
  * this function allows the kthread to execute on any CPU.
+ *
+ * Any future concurrent calls are serialized via ->boost_kthread_mutex.
  */
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 {
 	struct task_struct *t = rnp->boost_kthread_task;
-	unsigned long mask = rcu_rnp_online_cpus(rnp);
+	unsigned long mask;
 	cpumask_var_t cm;
 	int cpu;
 
@@ -1234,6 +1236,7 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 	if (!zalloc_cpumask_var(&cm, GFP_KERNEL))
 		return;
 	mutex_lock(&rnp->boost_kthread_mutex);
+	mask = rcu_rnp_online_cpus(rnp);
 	for_each_leaf_node_possible_cpu(rnp, cpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)