rcu: Fix set/clear TICK_DEP_BIT_RCU_EXP bitmask race

For kernels built with CONFIG_NO_HZ_FULL=y, the following scenario can result
in the scheduling-clock interrupt remaining enabled on a holdout CPU after
its quiescent state has been reported:

	CPU1                                                 CPU2
rcu_report_exp_cpu_mult                          synchronize_rcu_expedited_wait
   acquires rnp->lock                               mask = rnp->expmask;
                                                    for_each_leaf_node_cpu_mask(rnp, cpu, mask)
   rnp->expmask = rnp->expmask & ~mask;                rdp = per_cpu_ptr(&rcu_data, cpu1);
   for_each_leaf_node_cpu_mask(rnp, cpu, mask)
      rdp = per_cpu_ptr(&rcu_data, cpu1);
      if (!rdp->rcu_forced_tick_exp)
             continue;                                 rdp->rcu_forced_tick_exp = true;
                                                       tick_dep_set_cpu(cpu1, TICK_DEP_BIT_RCU_EXP);

The problem is that CPU2's sampling of rnp->expmask is obsolete by the
time it invokes tick_dep_set_cpu(), and CPU1 is not guaranteed to see
CPU2's store to ->rcu_forced_tick_exp in time to clear it.  And even if
CPU1 does see that store, it might invoke tick_dep_clear_cpu() before
CPU2 got around to executing its tick_dep_set_cpu(), which would still
leave the victim CPU with its scheduler-clock tick running.

Either way, an nohz_full real-time application running on the victim
CPU would have its latency needlessly degraded.

Note that expedited RCU grace periods look at context-tracking
information, and so if the CPU is executing in nohz_full usermode
throughout, that CPU cannot be victimized in this manner.

This commit therefore causes synchronize_rcu_expedited_wait to hold
the rcu_node structure's ->lock when checking for holdout CPUs, setting
TICK_DEP_BIT_RCU_EXP, and invoking tick_dep_set_cpu(), thus preventing
this race.

Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>

1 files changed, 3 insertions, 2 deletions

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 249c2967d9e6c0..7cc4856da0817c 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -594,6 +594,7 @@ static void synchronize_rcu_expedited_wait(void)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_root = rcu_get_root();
+	unsigned long flags;
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_exp_jiffies_till_stall_check();
@@ -602,17 +603,17 @@ static void synchronize_rcu_expedited_wait(void)
 		if (synchronize_rcu_expedited_wait_once(1))
 			return;
 		rcu_for_each_leaf_node(rnp) {
+			raw_spin_lock_irqsave_rcu_node(rnp, flags);
 			mask = READ_ONCE(rnp->expmask);
 			for_each_leaf_node_cpu_mask(rnp, cpu, mask) {
 				rdp = per_cpu_ptr(&rcu_data, cpu);
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				preempt_disable();
 				if (cpu_online(cpu))
 					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
-				preempt_enable();
 			}
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
 		if (synchronize_rcu_expedited_wait_once(j + HZ))