srcu: Make Tiny SRCU poll_state_synchronize_srcu() more precise

This commit applies the more-precise grace-period-state check used by
rcu_seq_done_exact() to poll_state_synchronize_srcu().  This is important
because Tiny SRCU uses a 16-bit counter, which can wrap quite quickly.
If counter wrap continues to be a problem, then expanding ->srcu_idx
and ->srcu_idx_max to 32 bits might be warranted.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/srcutiny.c

@@ -240,10 +240,10 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
  */
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
-	bool ret = USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx), cookie);
+	unsigned short cur_s = READ_ONCE(ssp->srcu_idx);
 
 	barrier();
-	return ret;
+	return USHORT_CMP_GE(cur_s, cookie) || USHORT_CMP_LT(cur_s, cookie - 3);
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);