rcu: Silence lockdep false positive for expedited grace periods

In a CONFIG_PREEMPT=y kernel, synchronize_rcu_expedited()
acquires the ->exp_funnel_mutex in rcu_preempt_state, then invokes
synchronize_sched_expedited, which acquires the ->exp_funnel_mutex in
rcu_sched_state.  There can be no deadlock because rcu_preempt_state
->exp_funnel_mutex acquisition always precedes that of rcu_sched_state.
But lockdep does not know that, so it gives false-positive splats.

This commit therefore associates a separate lock_class_key structure
with the rcu_sched_state structure's ->exp_funnel_mutex, allowing
lockdep to see the lock ordering, avoiding the false positives.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcu/tree.c

@@ -71,6 +71,7 @@ MODULE_ALIAS("rcutree");
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
+static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS];
 
 /*
  * In order to export the rcu_state name to the tracing tools, it
@@ -4049,6 +4050,7 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	static const char * const buf[] = RCU_NODE_NAME_INIT;
 	static const char * const fqs[] = RCU_FQS_NAME_INIT;
 	static const char * const exp[] = RCU_EXP_NAME_INIT;
+	static const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT;
 	static u8 fl_mask = 0x1;
 
 	int levelcnt[RCU_NUM_LVLS];		/* # nodes in each level. */
@@ -4108,7 +4110,13 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
 			rcu_init_one_nocb(rnp);
 			mutex_init(&rnp->exp_funnel_mutex);
-			lockdep_set_class_and_name(&rnp->exp_funnel_mutex,
+			if (rsp == &rcu_sched_state)
+				lockdep_set_class_and_name(
+					&rnp->exp_funnel_mutex,
+					&rcu_exp_sched_class[i], exp_sched[i]);
+			else
+				lockdep_set_class_and_name(
+					&rnp->exp_funnel_mutex,
 					&rcu_exp_class[i], exp[i]);
 		}
 	}

kernel/rcu/tree.h

@@ -70,6 +70,8 @@
 #  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0" }
 #elif NR_CPUS <= RCU_FANOUT_2
 #  define RCU_NUM_LVLS	      2
 #  define NUM_RCU_LVL_0	      1
@@ -79,6 +81,8 @@
 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" }
 #elif NR_CPUS <= RCU_FANOUT_3
 #  define RCU_NUM_LVLS	      3
 #  define NUM_RCU_LVL_0	      1
@@ -89,6 +93,8 @@
 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" }
 #elif NR_CPUS <= RCU_FANOUT_4
 #  define RCU_NUM_LVLS	      4
 #  define NUM_RCU_LVL_0	      1
@@ -100,6 +106,8 @@
 #  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
 #  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
 #  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" }
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
 #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */