srcu: use ACCESS_ONCE() to access sp->completed in srcu_read_lock()

The old SRCU implementation loads sp->completed within an
RCU-sched section, courtesy of preempt_disable().  This was required
due to the use of synchronize_sched() in the old implemenation's
synchronize_srcu().  However, the new implementation does not rely
on synchronize_sched(), so it in turn does not require the load of
sp->completed and the ->c[] counter to be in a single preempt-disabled
region of code.  This commit therefore moves the sp->completed access
outside of the preempt-disabled region and applies ACCESS_ONCE().

The resulting code is almost as the same as before, but it removes the
now-misleading rcu_dereference_index_check() call.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

kernel/srcu.c

@@ -298,9 +298,8 @@ int __srcu_read_lock(struct srcu_struct *sp)
 {
 	int idx;
 
+	idx = ACCESS_ONCE(sp->completed) & 0x1;
 	preempt_disable();
-	idx = rcu_dereference_index_check(sp->completed,
-					  rcu_read_lock_sched_held()) & 0x1;
 	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1;
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1;