dm crypt: fix a possible hang due to race condition on exit

A kernel thread executes __set_current_state(TASK_INTERRUPTIBLE),
__add_wait_queue, spin_unlock_irq and then tests kthread_should_stop().
It is possible that the processor reorders memory accesses so that
kthread_should_stop() is executed before __set_current_state().  If such
reordering happens, there is a possible race on thread termination:

CPU 0:
calls kthread_should_stop()
	it tests KTHREAD_SHOULD_STOP bit, returns false
CPU 1:
calls kthread_stop(cc->write_thread)
	sets the KTHREAD_SHOULD_STOP bit
	calls wake_up_process on the kernel thread, that sets the thread
	state to TASK_RUNNING
CPU 0:
sets __set_current_state(TASK_INTERRUPTIBLE)
spin_unlock_irq(&cc->write_thread_wait.lock)
schedule() - and the process is stuck and never terminates, because the
	state is TASK_INTERRUPTIBLE and wake_up_process on CPU 1 already
	terminated

Fix this race condition by using a new flag DM_CRYPT_EXIT_THREAD to
signal that the kernel thread should exit.  The flag is set and tested
while holding cc->write_thread_wait.lock, so there is no possibility of
racy access to the flag.

Also, remove the unnecessary set_task_state(current, TASK_RUNNING)
following the schedule() call.  When the process was woken up, its state
was already set to TASK_RUNNING.  Other kernel code also doesn't set the
state to TASK_RUNNING following schedule() (for example,
do_wait_for_common in completion.c doesn't do it).

Fixes: dc267621 ("dm crypt: offload writes to thread")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org # v4.0+
Signed-off-by: Mike Snitzer <snitzer@redhat.com>