rcu: Add fastpath bypassing funnel locking

In the common case, there will be only one expedited grace period in
the system at a given time, in which case it is not helpful to use
funnel locking.  This commit therefore adds a fastpath that bypasses
funnel locking when the root ->exp_funnel_mutex is not held.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

Documentation/RCU/trace.txt

@@ -237,42 +237,26 @@ o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 
 The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
 
-s=21872 d=21872 w=0 tf=0 wd1=0 wd2=0 n=0 sc=21872 dt=21872 dl=0 dx=21872
+s=21872 wd0=0 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
 
 These fields are as follows:
 
-o	"s" is the starting sequence number.
+o	"s" is the sequence number, with an odd number indicating that
+	an expedited grace period is in progress.
 
-o	"d" is the ending sequence number.  When the starting and ending
-	numbers differ, there is an expedited grace period in progress.
-
-o	"w" is the number of times that the sequence numbers have been
-	in danger of wrapping.
-
-o	"tf" is the number of times that contention has resulted in a
-	failure to begin an expedited grace period.
-
-o	"wd1" and "wd2" are the number of times that an attempt to
-	start an expedited grace period found that someone else had
-	completed an expedited grace period that satisfies the
+o	"wd0", "wd1", "wd2", and "wd3" are the number of times that an
+	attempt to start an expedited grace period found that someone
+	else had completed an expedited grace period that satisfies the
 	attempted request.  "Our work is done."
 
-o	"n" is number of times that contention was so great that
-	the request was demoted from an expedited grace period to
-	a normal grace period.
+o	"n" is number of times that a concurrent CPU-hotplug operation
+	forced a fallback to a normal grace period.
+
+o	"enq" is the number of quiescent states still outstanding.
 
 o	"sc" is the number of times that the attempt to start a
 	new expedited grace period succeeded.
 
-o	"dt" is the number of times that we attempted to update
-	the "d" counter.
-
-o	"dl" is the number of times that we failed to update the "d"
-	counter.
-
-o	"dx" is the number of times that we succeeded in updating
-	the "d" counter.
-
 
 The output of "cat rcu/rcu_preempt/rcugp" looks as follows:
 

kernel/rcu/tree.c

@@ -3355,6 +3355,22 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	struct rcu_node *rnp0;
 	struct rcu_node *rnp1 = NULL;
 
+	/*
+	 * First try directly acquiring the root lock in order to reduce
+	 * latency in the common case where expedited grace periods are
+	 * rare.  We check mutex_is_locked() to avoid pathological levels of
+	 * memory contention on ->exp_funnel_mutex in the heavy-load case.
+	 */
+	rnp0 = rcu_get_root(rsp);
+	if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) {
+		if (mutex_trylock(&rnp0->exp_funnel_mutex)) {
+			if (sync_exp_work_done(rsp, rnp0, NULL,
+					       &rsp->expedited_workdone0, s))
+				return NULL;
+			return rnp0;
+		}
+	}
+
 	/*
 	 * Each pass through the following loop works its way
 	 * up the rcu_node tree, returning if others have done the

kernel/rcu/tree.h

@@ -493,7 +493,7 @@ struct rcu_state {
 	/* End of fields guarded by barrier_mutex. */
 
 	unsigned long expedited_sequence;	/* Take a ticket. */
-	atomic_long_t expedited_tryfail;	/* # acquisition failures. */
+	atomic_long_t expedited_workdone0;	/* # done by others #0. */
 	atomic_long_t expedited_workdone1;	/* # done by others #1. */
 	atomic_long_t expedited_workdone2;	/* # done by others #2. */
 	atomic_long_t expedited_workdone3;	/* # done by others #3. */

kernel/rcu/tree_trace.c

@@ -185,9 +185,9 @@ static int show_rcuexp(struct seq_file *m, void *v)
 {
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
 
-	seq_printf(m, "t=%lu tf=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
 		   rsp->expedited_sequence,
-		   atomic_long_read(&rsp->expedited_tryfail),
+		   atomic_long_read(&rsp->expedited_workdone0),
 		   atomic_long_read(&rsp->expedited_workdone1),
 		   atomic_long_read(&rsp->expedited_workdone2),
 		   atomic_long_read(&rsp->expedited_workdone3),