srcu: Implement more-efficient reader counts

SRCU uses two per-cpu counters: a nesting counter to count the number of
active critical sections, and a sequence counter to ensure that the nesting
counters don't change while they are being added together in
srcu_readers_active_idx_check().

This patch instead uses per-cpu lock and unlock counters. Because both
counters only increase and srcu_readers_active_idx_check() reads the unlock
counter before the lock counter, this achieves the same end without having
to increment two different counters in srcu_read_lock(). This also saves a
smp_mb() in srcu_readers_active_idx_check().

Possible bug: There is no guarantee that the lock counter won't overflow
during srcu_readers_active_idx_check(), as there are no memory barriers
around srcu_flip() (see comment in srcu_readers_active_idx_check() for
details). However, this problem was already present before this patch.

Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Lance Roy <ldr709@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index dc8eb63..a598cf3 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -33,9 +33,9 @@
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-struct srcu_struct_array {
-	unsigned long c[2];
-	unsigned long seq[2];
+struct srcu_array {
+	unsigned long lock_count[2];
+	unsigned long unlock_count[2];
 };
 
 struct rcu_batch {
@@ -46,7 +46,7 @@ struct rcu_batch {
 
 struct srcu_struct {
 	unsigned long completed;
-	struct srcu_struct_array __percpu *per_cpu_ref;
+	struct srcu_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
 	/* callbacks just queued */
@@ -118,7 +118,7 @@ void process_srcu(struct work_struct *work);
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
 	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)