rcu: Move smp_mb() from rcu_seq_snap() to rcu_exp_gp_seq_snap()

The memory barrier in rcu_seq_snap() is needed only for grace periods,
so this commit moves it to the grace-period-oriented wrapper
rcu_exp_gp_seq_snap().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index bd2605c..a4a0475 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3347,7 +3347,6 @@
 {
 	unsigned long s;
 
-	smp_mb(); /* Caller's modifications seen first by other CPUs. */
 	s = (READ_ONCE(*sp) + 3) & ~0x1;
 	smp_mb(); /* Above access must not bleed into critical section. */
 	return s;
@@ -3374,6 +3373,7 @@
 }
 static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 {
+	smp_mb(); /* Caller's modifications seen first by other CPUs. */
 	return rcu_seq_snap(&rsp->expedited_sequence);
 }
 static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)