rcu: Add quiescent states and boost states to show_rcu_gp_kthreads() output

This commit adds each rcu_node structure's ->qsmask and "bBEG" output
indicating whether: (1) There is a boost kthread, (2) A reader needs
to be (or is in the process of being) boosted, (3) A reader is blocking
an expedited grace period, and (4) A reader is blocking a normal grace
period.  This helps diagnose RCU priority boosting failures.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/tree.h

@@ -115,6 +115,7 @@ struct rcu_node {
 				/*  boosting for this rcu_node structure. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
+	unsigned long n_boosts;	/* Number of boosts for this rcu_node structure. */
 #ifdef CONFIG_RCU_NOCB_CPU
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */

kernel/rcu/tree_plugin.h

@@ -1098,6 +1098,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	/* Lock only for side effect: boosts task t's priority. */
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
+	rnp->n_boosts++;
 
 	return READ_ONCE(rnp->exp_tasks) != NULL ||
 	       READ_ONCE(rnp->boost_tasks) != NULL;

kernel/rcu/tree_stall.h

@@ -749,9 +749,15 @@ void show_rcu_gp_kthreads(void)
 		if (ULONG_CMP_GE(READ_ONCE(rcu_state.gp_seq),
 				 READ_ONCE(rnp->gp_seq_needed)))
 			continue;
-		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)data_race(rnp->gp_seq),
-			(long)data_race(rnp->gp_seq_needed));
+		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld ->qsmask %#lx %c%c%c%c ->n_boosts %ld\n",
+			rnp->grplo, rnp->grphi,
+			(long)data_race(rnp->gp_seq), (long)data_race(rnp->gp_seq_needed),
+			data_race(rnp->qsmask),
+			".b"[!!data_race(rnp->boost_kthread_task)],
+			".B"[!!data_race(rnp->boost_tasks)],
+			".E"[!!data_race(rnp->exp_tasks)],
+			".G"[!!data_race(rnp->gp_tasks)],
+			data_race(rnp->n_boosts));
 		if (!rcu_is_leaf_node(rnp))
 			continue;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {