Currently, rcu_blocking_is_gp() invokes might_sleep() even during early
boot when interrupts are disabled and before the scheduler is scheduling.
This is at best an accident waiting to happen.  Therefore, this commit
moves that might_sleep() under an rcu_scheduler_active check in order
to ensure that might_sleep() is not invoked unless sleeping might actually
happen.
Signed-off-by: Zqiang <qiang1.zhang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>