At present, a trivial algorithm is used: wake up once in a while, look for
a less-loaded cpu, and push a waiting thread from this cpu to the other cpu.

This is very simple wrt. locking, since the waiting thread is guaranteed not
to be running, and to be on the runqueue of the load balancer thread.

Lost when remote wakeups were added.

While it is the default, we'll rely heavily on constant time size
to compute the load (from remote processors, too).  Document it to
avoid having someone "optimize" it away.

This allows copying thread::attr objects around without leaking stacks.

Interferes with the scheduler

Without fairness, the concurrent alloc/free test fails quickly on smp, as
the allocator thread hogs the allocator mutex and quickly exhausts all memory.
While we could fix up the test to avoid this, fairness is a desirable quality,
so implement it.

We do so by adding and owner field, and having the unlocker transfer ownership
of the locked mutex instead of freeing it and letting the waiter race with
a newcomer.

Also simplify the wait list to a singly linked list.  There was some
corruption with the original implementation, and rather than fix it,
simplify it to a singly linked list which is all that is needed.

So it doesn't interfere with the scheduler

Time might stop under some hosts without this fix.

The tests themselves didn't change and all the changes their are just
changes of namespace usage and variable movement.

the vtest class) and running them one after the other.
It moves the test code outside of loader.cc

* 'master' of github.com:cloudius-systems/osv: (41 commits)
  sched: default thread attributes
  sched: add new thread::attr object
  enable locking in libc
  apic clockevents: per-cpu setup
  sched: use cpu::init_on_cpu()
  libc/manifest update
  add a real wcsftime_l implementation
  add real implementation of locale-aware strto{f,d,ld} routines
  add floating support to *printf and *scanf
  enable stro*
  add the license for FreeBSDs realpath
  remove the unused old environ-related variables
  sched: per-cpu timer list
  remove an accidentally added file
  remove getenv debugging
  import a real realpath from FreeBSD
  add lstat()
  mutex: zero the mutex structure in mutex_init
  add a full getenv/putenv & friends implementation from musl
  sched: maintain a list of active thread timers
  ...

This makes it easier to create a thread with no special properties.

Run 2 threads, one allocated mem, the other deletes the allocation.

This makes it easy to configure a thread with various parameters.  The first
is the existing stack_info parameter.

pushing it into a dummy bio structure. In addition, expand the test some more

The apic needs to be programmed on each cpu that is brought up.

We used cpu_arch::init_on_cpu() instead of the arch-indepdendent version.

Of course we don't actually support locales yet, so these are trivial wrappers.

Maintain the list of active timers per-cpu, instead of globally.

This removes the need for locking (other than disabling preemption).

The clock_event interface is awkward in that the callback is global, not
per-cpu.  This requires us to have a global dispatch object that then
uses cpu::current() to pick up the current cpu and dispatch the event.  We
should probably make clock_event explicitly per-cpu in the future.