rcu: Avoid IPIing idle CPUs from synchronize_sched_expedited()

Currently, synchronize_sched_expedited() sends IPIs to all online CPUs,
even those that are idle or executing in nohz_full= userspace. Because
idle CPUs and nohz_full= userspace CPUs are in extended quiescent states,
there is no need to IPI them in the first place. This commit therefore
avoids IPIing CPUs that are already in extended quiescent states.

Signed-off-by: Paul E. McKenney <[e-mail]>

kernel/rcu/tree.c

···
  */
 void synchronize_sched_expedited(void)
 {
+	cpumask_var_t cm;
+	bool cma = false;
+	int cpu;
 	long firstsnap, s, snap;
 	int trycount = 0;
 	struct rcu_state *rsp = &rcu_sched_state;
···
 	}
 	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
+	/* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
+	cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
+	if (cma) {
+		cpumask_copy(cm, cpu_online_mask);
+		cpumask_clear_cpu(raw_smp_processor_id(), cm);
+		for_each_cpu(cpu, cm) {
+			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+			if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+				cpumask_clear_cpu(cpu, cm);
+		}
+		if (cpumask_weight(cm) == 0)
+			goto all_cpus_idle;
+	}
+
 	/*
 	 * Each pass through the following loop attempts to force a
 	 * context switch on each CPU.
 	 */
-	while (try_stop_cpus(cpu_online_mask,
+	while (try_stop_cpus(cma ? cm : cpu_online_mask,
 			     synchronize_sched_expedited_cpu_stop,
 			     NULL) == -EAGAIN) {
 		put_online_cpus();
···
 			/* ensure test happens before caller kfree */
 			smp_mb__before_atomic(); /* ^^^ */
 			atomic_long_inc(&rsp->expedited_workdone1);
+			free_cpumask_var(cm);
 			return;
 		}
 
···
 		} else {
 			wait_rcu_gp(call_rcu_sched);
 			atomic_long_inc(&rsp->expedited_normal);
+			free_cpumask_var(cm);
 			return;
 		}
 
···
 			/* ensure test happens before caller kfree */
 			smp_mb__before_atomic(); /* ^^^ */
 			atomic_long_inc(&rsp->expedited_workdone2);
+			free_cpumask_var(cm);
 			return;
 		}
 
···
 			/* CPU hotplug operation in flight, use normal GP. */
 			wait_rcu_gp(call_rcu_sched);
 			atomic_long_inc(&rsp->expedited_normal);
+			free_cpumask_var(cm);
 			return;
 		}
 		snap = atomic_long_read(&rsp->expedited_start);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
 	atomic_long_inc(&rsp->expedited_stoppedcpus);
+
+all_cpus_idle:
+	free_cpumask_var(cm);
 
 	/*
 	 * Everyone up to our most recent fetch is covered by our grace