rcu: Make expedited grace periods recheck dyntick idle state

Expedited grace periods check dyntick-idle state, and avoid sending
IPIs to idle CPUs, including those running guest OSes, and, on NOHZ_FULL
kernels, nohz_full CPUs.  However, the kernel has been observed checking
a CPU while it was non-idle, but sending the IPI after it has gone
idle.  This commit therefore rechecks idle state immediately before
sending the IPI, refraining from IPIing CPUs that have since gone idle.

Reported-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.h

@@ -404,6 +404,7 @@ struct rcu_data {
 	atomic_long_t exp_workdone1;	/* # done by others #1. */
 	atomic_long_t exp_workdone2;	/* # done by others #2. */
 	atomic_long_t exp_workdone3;	/* # done by others #3. */
+	int exp_dynticks_snap;		/* Double-check need for IPI. */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU

kernel/rcu/tree_exp.h

@@ -358,8 +358,10 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
+			rdp->exp_dynticks_snap =
+				atomic_add_return(0, &rdtp->dynticks);
 			if (raw_smp_processor_id() == cpu ||
-			    !(atomic_add_return(0, &rdtp->dynticks) & 0x1) ||
+			    !(rdp->exp_dynticks_snap & 0x1) ||
 			    !(rnp->qsmaskinitnext & rdp->grpmask))
 				mask_ofl_test |= rdp->grpmask;
 		}
@@ -377,9 +379,17 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		/* IPI the remaining CPUs for expedited quiescent state. */
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
+			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
 			if (!(mask_ofl_ipi & mask))
 				continue;
 retry_ipi:
+			if (atomic_add_return(0, &rdtp->dynticks) !=
+			    rdp->exp_dynticks_snap) {
+				mask_ofl_test |= mask;
+				continue;
+			}
 			ret = smp_call_function_single(cpu, func, rsp, 0);
 			if (!ret) {
 				mask_ofl_ipi &= ~mask;