rcu: Instrument synchronize_rcu_expedited() for debugfs tracing

This commit adds the counters to rcu_state and updates them in
synchronize_rcu_expedited() to provide the data needed for debugfs
tracing.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/rcutree.c

@@ -2321,6 +2321,7 @@ void synchronize_sched_expedited(void)
 			 (ulong)atomic_long_read(&rsp->expedited_done) +
 			 ULONG_MAX / 8)) {
 		synchronize_sched();
+		atomic_long_inc(&rsp->expedited_wrap);
 		return;
 	}
 
@@ -2341,11 +2342,14 @@ void synchronize_sched_expedited(void)
 			     synchronize_sched_expedited_cpu_stop,
 			     NULL) == -EAGAIN) {
 		put_online_cpus();
+		atomic_long_inc(&rsp->expedited_tryfail);
 
 		/* Check to see if someone else did our work for us. */
 		s = atomic_long_read(&rsp->expedited_done);
 		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
-			smp_mb(); /* ensure test happens before caller kfree */
+			/* ensure test happens before caller kfree */
+			smp_mb__before_atomic_inc(); /* ^^^ */
+			atomic_long_inc(&rsp->expedited_workdone1);
 			return;
 		}
 
@@ -2354,13 +2358,16 @@ void synchronize_sched_expedited(void)
 			udelay(trycount * num_online_cpus());
 		} else {
 			synchronize_sched();
+			atomic_long_inc(&rsp->expedited_normal);
 			return;
 		}
 
 		/* Recheck to see if someone else did our work for us. */
 		s = atomic_long_read(&rsp->expedited_done);
 		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
-			smp_mb(); /* ensure test happens before caller kfree */
+			/* ensure test happens before caller kfree */
+			smp_mb__before_atomic_inc(); /* ^^^ */
+			atomic_long_inc(&rsp->expedited_workdone2);
 			return;
 		}
 
@@ -2375,6 +2382,7 @@ void synchronize_sched_expedited(void)
 		snap = atomic_long_read(&rsp->expedited_start);
 		smp_mb(); /* ensure read is before try_stop_cpus(). */
 	}
+	atomic_long_inc(&rsp->expedited_stoppedcpus);
 
 	/*
 	 * Everyone up to our most recent fetch is covered by our grace
@@ -2383,12 +2391,16 @@ void synchronize_sched_expedited(void)
 	 * than we did already did their update.
 	 */
 	do {
+		atomic_long_inc(&rsp->expedited_done_tries);
 		s = atomic_long_read(&rsp->expedited_done);
 		if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
-			smp_mb(); /* ensure test happens before caller kfree */
+			/* ensure test happens before caller kfree */
+			smp_mb__before_atomic_inc(); /* ^^^ */
+			atomic_long_inc(&rsp->expedited_done_lost);
 			break;
 		}
 	} while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s);
+	atomic_long_inc(&rsp->expedited_done_exit);
 
 	put_online_cpus();
 }

kernel/rcutree.h

@@ -406,6 +406,15 @@ struct rcu_state {
 
 	atomic_long_t expedited_start;		/* Starting ticket. */
 	atomic_long_t expedited_done;		/* Done ticket. */
+	atomic_long_t expedited_wrap;		/* # near-wrap incidents. */
+	atomic_long_t expedited_tryfail;	/* # acquisition failures. */
+	atomic_long_t expedited_workdone1;	/* # done by others #1. */
+	atomic_long_t expedited_workdone2;	/* # done by others #2. */
+	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
+	atomic_long_t expedited_stoppedcpus;	/* # successful stop_cpus. */
+	atomic_long_t expedited_done_tries;	/* # tries to update _done. */
+	atomic_long_t expedited_done_lost;	/* # times beaten to _done. */
+	atomic_long_t expedited_done_exit;	/* # times exited _done loop. */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */