SMP - CPU local run queues

- each CPU has its own runqueues

- processes on BSP are put on the runqueues later after a switch to
  the final stack when cpuid works to avoid special cases

- enqueue() and dequeue() use the run queues of the cpu the process is
  assigned to

- pick_proc() uses the local run queues

- printing of per-CPU run queues ('2') on serial console

kernel/clock.c

@@ -194,6 +194,7 @@ PRIVATE void load_update(void)
 	u16_t slot;
 	int enqueued = 0, q;
 	struct proc *p;
+	struct proc **rdy_head;
 
 	/* Load average data is stored as a list of numbers in a circular
 	 * buffer. Each slot accumulates _LOAD_UNIT_SECS of samples of
@@ -207,6 +208,7 @@ PRIVATE void load_update(void)
 		kloadinfo.proc_last_slot = slot;
 	}
 
+	rdy_head = get_cpulocal_var(run_q_head);
 	/* Cumulation. How many processes are ready now? */
 	for(q = 0; q < NR_SCHED_QUEUES; q++) {
 		for(p = rdy_head[q]; p != NULL; p = p->p_nextready) {