- we should probably extend pthread_mutexattr_t with a field to create a
  single linked list of all instances.  This requires changing the
  pthread_mutexattr_* functions.


- a new attribute for mutexes: number of times we spin before calling
sys_futex

- for adaptive mutexes: when releasing, determine whether somebody spins.
If yes, for a short time release lock.  If someone else locks no wakeup
syscall needed.



- test with threaded process terminating and semadj (?) being applied
  only after all threads are gone