+ struct task_struct *g, *p;
+
+#if (BITS_PER_LONG == 32)
+ printk("\n"
+ " sibling\n");
+ printk(" task PC pid father child younger older\n");
+#else
+ printk("\n"
+ " sibling\n");
+ printk(" task PC pid father child younger older\n");
+#endif
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ /*
+ * reset the NMI-timeout, listing all files on a slow
+ * console might take alot of time:
+ */
+ touch_nmi_watchdog();
+ show_task(p);
+ } while_each_thread(g, p);
+
+ read_unlock(&tasklist_lock);
+ debug_show_all_locks();
+}
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void __devinit init_idle(struct task_struct *idle, int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ idle->timestamp = sched_clock();
+ idle->sleep_avg = 0;
+ idle->array = NULL;
+ idle->prio = idle->normal_prio = MAX_PRIO;
+ idle->state = TASK_RUNNING;
+ idle->cpus_allowed = cpumask_of_cpu(cpu);
+ set_task_cpu(idle, cpu);
+
+ spin_lock_irqsave(&rq->lock, flags);
+ rq->curr = rq->idle = idle;
+#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
+ idle->oncpu = 1;
+#endif
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ /* Set the preempt count _outside_ the spinlocks! */
+#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
+ task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
+#else
+ task_thread_info(idle)->preempt_count = 0;
+#endif
+}
+
+/*
+ * In a system that switches off the HZ timer nohz_cpu_mask
+ * indicates which cpus entered this state. This is used
+ * in the rcu update to wait only for active cpus. For system
+ * which do not switch off the HZ timer nohz_cpu_mask should
+ * always be CPU_MASK_NONE.
+ */
+cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+
+#ifdef CONFIG_SMP
+/*
+ * This is how migration works:
+ *
+ * 1) we queue a struct migration_req structure in the source CPU's
+ * runqueue and wake up that CPU's migration thread.
+ * 2) we down() the locked semaphore => thread blocks.
+ * 3) migration thread wakes up (implicitly it forces the migrated
+ * thread off the CPU)
+ * 4) it gets the migration request and checks whether the migrated
+ * task is still in the wrong runqueue.
+ * 5) if it's in the wrong runqueue then the migration thread removes
+ * it and puts it into the right queue.
+ * 6) migration thread up()s the semaphore.
+ * 7) we wake up and the migration is done.
+ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
+{
+ struct migration_req req;
+ unsigned long flags;
+ struct rq *rq;
+ int ret = 0;
+
+ rq = task_rq_lock(p, &flags);
+ if (!cpus_intersects(new_mask, cpu_online_map)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ p->cpus_allowed = new_mask;
+ /* Can the task run on the task's current CPU? If so, we're done */
+ if (cpu_isset(task_cpu(p), new_mask))
+ goto out;
+
+ if (migrate_task(p, any_online_cpu(new_mask), &req)) {
+ /* Need help from migration thread: drop lock and wait. */
+ task_rq_unlock(rq, &flags);
+ wake_up_process(rq->migration_thread);
+ wait_for_completion(&req.done);
+ tlb_migrate_finish(p->mm);
+ return 0;
+ }
+out:
+ task_rq_unlock(rq, &flags);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(set_cpus_allowed);
+
+/*
+ * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * this because either it can't run here any more (set_cpus_allowed()
+ * away from this CPU, or CPU going down), or because we're
+ * attempting to rebalance this task on exec (sched_exec).
+ *
+ * So we race with normal scheduler movements, but that's OK, as long
+ * as the task is no longer on this CPU.
+ *
+ * Returns non-zero if task was successfully migrated.
+ */
+static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+{
+ struct rq *rq_dest, *rq_src;
+ int ret = 0;
+
+ if (unlikely(cpu_is_offline(dest_cpu)))
+ return ret;
+
+ rq_src = cpu_rq(src_cpu);
+ rq_dest = cpu_rq(dest_cpu);
+
+ double_rq_lock(rq_src, rq_dest);
+ /* Already moved. */
+ if (task_cpu(p) != src_cpu)
+ goto out;
+ /* Affinity changed (again). */
+ if (!cpu_isset(dest_cpu, p->cpus_allowed))
+ goto out;
+
+ set_task_cpu(p, dest_cpu);
+ if (p->array) {
+ /*
+ * Sync timestamp with rq_dest's before activating.
+ * The same thing could be achieved by doing this step
+ * afterwards, and pretending it was a local activate.
+ * This way is cleaner and logically correct.
+ */
+ p->timestamp = p->timestamp - rq_src->timestamp_last_tick
+ + rq_dest->timestamp_last_tick;
+ deactivate_task(p, rq_src);
+ vx_activate_task(p);
+ __activate_task(p, rq_dest);
+ if (TASK_PREEMPTS_CURR(p, rq_dest))
+ resched_task(rq_dest->curr);
+ }
+ ret = 1;
+out:
+ double_rq_unlock(rq_src, rq_dest);
+ return ret;
+}
+
+/*
+ * migration_thread - this is a highprio system thread that performs
+ * thread migration by bumping thread off CPU then 'pushing' onto
+ * another runqueue.
+ */
+static int migration_thread(void *data)
+{
+ int cpu = (long)data;
+ struct rq *rq;
+
+ rq = cpu_rq(cpu);
+ BUG_ON(rq->migration_thread != current);
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ struct migration_req *req;
+ struct list_head *head;
+
+ try_to_freeze();
+
+ spin_lock_irq(&rq->lock);
+
+ if (cpu_is_offline(cpu)) {
+ spin_unlock_irq(&rq->lock);
+ goto wait_to_die;
+ }
+
+ if (rq->active_balance) {
+ active_load_balance(rq, cpu);
+ rq->active_balance = 0;
+ }
+
+ head = &rq->migration_queue;
+
+ if (list_empty(head)) {
+ spin_unlock_irq(&rq->lock);
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ continue;
+ }
+ req = list_entry(head->next, struct migration_req, list);
+ list_del_init(head->next);
+
+ spin_unlock(&rq->lock);
+ __migrate_task(req->task, cpu, req->dest_cpu);
+ local_irq_enable();
+
+ complete(&req->done);
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+
+wait_to_die:
+ /* Wait for kthread_stop */
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ schedule();
+ set_current_state(TASK_INTERRUPTIBLE);
+ }
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* Figure out where task on dead CPU should go, use force if neccessary. */
+static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+{
+ unsigned long flags;
+ cpumask_t mask;
+ struct rq *rq;
+ int dest_cpu;
+
+restart:
+ /* On same node? */
+ mask = node_to_cpumask(cpu_to_node(dead_cpu));
+ cpus_and(mask, mask, p->cpus_allowed);
+ dest_cpu = any_online_cpu(mask);
+
+ /* On any allowed CPU? */
+ if (dest_cpu == NR_CPUS)
+ dest_cpu = any_online_cpu(p->cpus_allowed);
+
+ /* No more Mr. Nice Guy. */
+ if (dest_cpu == NR_CPUS) {
+ rq = task_rq_lock(p, &flags);
+ cpus_setall(p->cpus_allowed);
+ dest_cpu = any_online_cpu(p->cpus_allowed);
+ task_rq_unlock(rq, &flags);
+
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit())
+ printk(KERN_INFO "process %d (%s) no "
+ "longer affine to cpu%d\n",
+ p->pid, p->comm, dead_cpu);
+ }
+ if (!__migrate_task(p, dead_cpu, dest_cpu))
+ goto restart;
+}
+
+/*
+ * While a dead CPU has no uninterruptible tasks queued at this point,
+ * it might still have a nonzero ->nr_uninterruptible counter, because
+ * for performance reasons the counter is not stricly tracking tasks to
+ * their home CPUs. So we just add the counter to another CPU's counter,
+ * to keep the global sum constant after CPU-down:
+ */
+static void migrate_nr_uninterruptible(struct rq *rq_src)
+{
+ struct rq *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
+ unsigned long flags;
+
+ local_irq_save(flags);
+ double_rq_lock(rq_src, rq_dest);
+ rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
+ rq_src->nr_uninterruptible = 0;
+ double_rq_unlock(rq_src, rq_dest);
+ local_irq_restore(flags);
+}
+
+/* Run through task list and migrate tasks from the dead cpu. */
+static void migrate_live_tasks(int src_cpu)
+{
+ struct task_struct *p, *t;
+
+ write_lock_irq(&tasklist_lock);
+
+ do_each_thread(t, p) {
+ if (p == current)
+ continue;
+
+ if (task_cpu(p) == src_cpu)
+ move_task_off_dead_cpu(src_cpu, p);
+ } while_each_thread(t, p);
+
+ write_unlock_irq(&tasklist_lock);
+}
+
+/* Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible and adding it to
+ * the _front_ of the runqueue. Used by CPU offline code.
+ */
+void sched_idle_next(void)
+{
+ int this_cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(this_cpu);
+ struct task_struct *p = rq->idle;
+ unsigned long flags;
+
+ /* cpu has to be offline */
+ BUG_ON(cpu_online(this_cpu));
+
+ /*
+ * Strictly not necessary since rest of the CPUs are stopped by now
+ * and interrupts disabled on the current cpu.
+ */
+ spin_lock_irqsave(&rq->lock, flags);
+
+ __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+
+ /* Add idle task to the _front_ of its priority queue: */
+ __activate_idle_task(p, rq);
+
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+/*
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+ struct mm_struct *mm = current->active_mm;
+
+ BUG_ON(cpu_online(smp_processor_id()));
+
+ if (mm != &init_mm)
+ switch_mm(mm, &init_mm, current);
+ mmdrop(mm);
+}
+
+static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+{
+ struct rq *rq = cpu_rq(dead_cpu);
+
+ /* Must be exiting, otherwise would be on tasklist. */
+ BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
+
+ /* Cannot have done final schedule yet: would have vanished. */
+ BUG_ON(p->flags & PF_DEAD);
+
+ get_task_struct(p);
+
+ /*
+ * Drop lock around migration; if someone else moves it,
+ * that's OK. No task can be added to this CPU, so iteration is
+ * fine.
+ */
+ spin_unlock_irq(&rq->lock);
+ move_task_off_dead_cpu(dead_cpu, p);
+ spin_lock_irq(&rq->lock);
+
+ put_task_struct(p);
+}
+
+/* release_task() removes task from tasklist, so we won't find dead tasks. */
+static void migrate_dead_tasks(unsigned int dead_cpu)
+{
+ struct rq *rq = cpu_rq(dead_cpu);
+ unsigned int arr, i;
+
+ for (arr = 0; arr < 2; arr++) {
+ for (i = 0; i < MAX_PRIO; i++) {
+ struct list_head *list = &rq->arrays[arr].queue[i];
+
+ while (!list_empty(list))
+ migrate_dead(dead_cpu, list_entry(list->next,
+ struct task_struct, run_list));
+ }
+ }
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+static int __cpuinit
+migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+ struct task_struct *p;
+ int cpu = (long)hcpu;
+ unsigned long flags;
+ struct rq *rq;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
+ if (IS_ERR(p))
+ return NOTIFY_BAD;
+ p->flags |= PF_NOFREEZE;
+ kthread_bind(p, cpu);
+ /* Must be high prio: stop_machine expects to yield to it. */
+ rq = task_rq_lock(p, &flags);
+ __setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
+ task_rq_unlock(rq, &flags);
+ cpu_rq(cpu)->migration_thread = p;
+ break;
+
+ case CPU_ONLINE:
+ /* Strictly unneccessary, as first user will wake it. */
+ wake_up_process(cpu_rq(cpu)->migration_thread);
+ break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+ case CPU_UP_CANCELED:
+ if (!cpu_rq(cpu)->migration_thread)
+ break;
+ /* Unbind it from offline cpu so it can run. Fall thru. */
+ kthread_bind(cpu_rq(cpu)->migration_thread,
+ any_online_cpu(cpu_online_map));
+ kthread_stop(cpu_rq(cpu)->migration_thread);
+ cpu_rq(cpu)->migration_thread = NULL;
+ break;
+
+ case CPU_DEAD:
+ migrate_live_tasks(cpu);
+ rq = cpu_rq(cpu);
+ kthread_stop(rq->migration_thread);
+ rq->migration_thread = NULL;
+ /* Idle task back to normal (off runqueue, low prio) */
+ rq = task_rq_lock(rq->idle, &flags);
+ deactivate_task(rq->idle, rq);
+ rq->idle->static_prio = MAX_PRIO;
+ __setscheduler(rq->idle, SCHED_NORMAL, 0);
+ migrate_dead_tasks(cpu);
+ task_rq_unlock(rq, &flags);
+ migrate_nr_uninterruptible(rq);
+ BUG_ON(rq->nr_running != 0);
+
+ /* No need to migrate the tasks: it was best-effort if
+ * they didn't do lock_cpu_hotplug(). Just wake up
+ * the requestors. */
+ spin_lock_irq(&rq->lock);
+ while (!list_empty(&rq->migration_queue)) {
+ struct migration_req *req;
+
+ req = list_entry(rq->migration_queue.next,
+ struct migration_req, list);
+ list_del_init(&req->list);
+ complete(&req->done);
+ }
+ spin_unlock_irq(&rq->lock);
+ break;
+#endif
+ }
+ return NOTIFY_OK;
+}
+
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block __cpuinitdata migration_notifier = {
+ .notifier_call = migration_call,
+ .priority = 10
+};
+
+int __init migration_init(void)
+{
+ void *cpu = (void *)(long)smp_processor_id();
+
+ /* Start one for the boot CPU: */
+ migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ migration_call(&migration_notifier, CPU_ONLINE, cpu);
+ register_cpu_notifier(&migration_notifier);
+
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+#undef SCHED_DOMAIN_DEBUG
+#ifdef SCHED_DOMAIN_DEBUG
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+ int level = 0;
+
+ if (!sd) {
+ printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+ return;
+ }
+
+ printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+ do {
+ int i;
+ char str[NR_CPUS];
+ struct sched_group *group = sd->groups;
+ cpumask_t groupmask;
+
+ cpumask_scnprintf(str, NR_CPUS, sd->span);
+ cpus_clear(groupmask);
+
+ printk(KERN_DEBUG);
+ for (i = 0; i < level + 1; i++)
+ printk(" ");
+ printk("domain %d: ", level);
+
+ if (!(sd->flags & SD_LOAD_BALANCE)) {
+ printk("does not load-balance\n");
+ if (sd->parent)
+ printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
+ break;
+ }
+
+ printk("span %s\n", str);
+
+ if (!cpu_isset(cpu, sd->span))
+ printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
+ if (!cpu_isset(cpu, group->cpumask))
+ printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
+
+ printk(KERN_DEBUG);
+ for (i = 0; i < level + 2; i++)
+ printk(" ");
+ printk("groups:");
+ do {
+ if (!group) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: group is NULL\n");
+ break;
+ }
+
+ if (!group->cpu_power) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: domain->cpu_power not set\n");
+ }
+
+ if (!cpus_weight(group->cpumask)) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: empty group\n");
+ }
+
+ if (cpus_intersects(groupmask, group->cpumask)) {
+ printk("\n");
+ printk(KERN_ERR "ERROR: repeated CPUs\n");
+ }
+
+ cpus_or(groupmask, groupmask, group->cpumask);
+
+ cpumask_scnprintf(str, NR_CPUS, group->cpumask);
+ printk(" %s", str);
+
+ group = group->next;
+ } while (group != sd->groups);
+ printk("\n");
+
+ if (!cpus_equal(sd->span, groupmask))
+ printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+ level++;
+ sd = sd->parent;
+
+ if (sd) {
+ if (!cpus_subset(groupmask, sd->span))
+ printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
+ }
+
+ } while (sd);
+}
+#else
+# define sched_domain_debug(sd, cpu) do { } while (0)
+#endif
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+ if (cpus_weight(sd->span) == 1)
+ return 1;
+
+ /* Following flags need at least 2 groups */
+ if (sd->flags & (SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC)) {
+ if (sd->groups != sd->groups->next)
+ return 0;
+ }
+
+ /* Following flags don't use groups */
+ if (sd->flags & (SD_WAKE_IDLE |
+ SD_WAKE_AFFINE |
+ SD_WAKE_BALANCE))
+ return 0;
+
+ return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+ unsigned long cflags = sd->flags, pflags = parent->flags;
+
+ if (sd_degenerate(parent))
+ return 1;
+
+ if (!cpus_equal(sd->span, parent->span))
+ return 0;
+
+ /* Does parent contain flags not in child? */
+ /* WAKE_BALANCE is a subset of WAKE_AFFINE */
+ if (cflags & SD_WAKE_AFFINE)
+ pflags &= ~SD_WAKE_BALANCE;
+ /* Flags needing groups don't count if only 1 group in parent */
+ if (parent->groups == parent->groups->next) {
+ pflags &= ~(SD_LOAD_BALANCE |
+ SD_BALANCE_NEWIDLE |
+ SD_BALANCE_FORK |
+ SD_BALANCE_EXEC);
+ }
+ if (~cflags & pflags)
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void cpu_attach_domain(struct sched_domain *sd, int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ struct sched_domain *tmp;
+
+ /* Remove the sched domains which do not contribute to scheduling. */
+ for (tmp = sd; tmp; tmp = tmp->parent) {
+ struct sched_domain *parent = tmp->parent;
+ if (!parent)
+ break;
+ if (sd_parent_degenerate(tmp, parent))
+ tmp->parent = parent->parent;
+ }
+
+ if (sd && sd_degenerate(sd))
+ sd = sd->parent;
+
+ sched_domain_debug(sd, cpu);
+
+ rcu_assign_pointer(rq->sd, sd);
+}
+
+/* cpus with isolated domains */
+static cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;
+
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+ int ints[NR_CPUS], i;
+
+ str = get_options(str, ARRAY_SIZE(ints), ints);
+ cpus_clear(cpu_isolated_map);
+ for (i = 1; i <= ints[0]; i++)
+ if (ints[i] < NR_CPUS)
+ cpu_set(ints[i], cpu_isolated_map);
+ return 1;
+}
+
+__setup ("isolcpus=", isolated_cpu_setup);
+
+/*
+ * init_sched_build_groups takes an array of groups, the cpumask we wish
+ * to span, and a pointer to a function which identifies what group a CPU
+ * belongs to. The return value of group_fn must be a valid index into the
+ * groups[] array, and must be >= 0 and < NR_CPUS (due to the fact that we
+ * keep track of groups covered with a cpumask_t).
+ *
+ * init_sched_build_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
+ */
+static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
+ int (*group_fn)(int cpu))
+{
+ struct sched_group *first = NULL, *last = NULL;
+ cpumask_t covered = CPU_MASK_NONE;
+ int i;
+
+ for_each_cpu_mask(i, span) {
+ int group = group_fn(i);
+ struct sched_group *sg = &groups[group];
+ int j;
+
+ if (cpu_isset(i, covered))
+ continue;
+
+ sg->cpumask = CPU_MASK_NONE;
+ sg->cpu_power = 0;
+
+ for_each_cpu_mask(j, span) {
+ if (group_fn(j) != group)
+ continue;
+
+ cpu_set(j, covered);
+ cpu_set(j, sg->cpumask);
+ }
+ if (!first)
+ first = sg;
+ if (last)
+ last->next = sg;
+ last = sg;
+ }
+ last->next = first;
+}
+
+#define SD_NODES_PER_DOMAIN 16
+
+/*
+ * Self-tuning task migration cost measurement between source and target CPUs.
+ *
+ * This is done by measuring the cost of manipulating buffers of varying
+ * sizes. For a given buffer-size here are the steps that are taken:
+ *
+ * 1) the source CPU reads+dirties a shared buffer
+ * 2) the target CPU reads+dirties the same shared buffer
+ *
+ * We measure how long they take, in the following 4 scenarios:
+ *
+ * - source: CPU1, target: CPU2 | cost1
+ * - source: CPU2, target: CPU1 | cost2
+ * - source: CPU1, target: CPU1 | cost3
+ * - source: CPU2, target: CPU2 | cost4
+ *
+ * We then calculate the cost3+cost4-cost1-cost2 difference - this is
+ * the cost of migration.
+ *
+ * We then start off from a small buffer-size and iterate up to larger
+ * buffer sizes, in 5% steps - measuring each buffer-size separately, and
+ * doing a maximum search for the cost. (The maximum cost for a migration
+ * normally occurs when the working set size is around the effective cache
+ * size.)
+ */
+#define SEARCH_SCOPE 2
+#define MIN_CACHE_SIZE (64*1024U)
+#define DEFAULT_CACHE_SIZE (5*1024*1024U)
+#define ITERATIONS 1
+#define SIZE_THRESH 130
+#define COST_THRESH 130
+
+/*
+ * The migration cost is a function of 'domain distance'. Domain
+ * distance is the number of steps a CPU has to iterate down its
+ * domain tree to share a domain with the other CPU. The farther
+ * two CPUs are from each other, the larger the distance gets.
+ *
+ * Note that we use the distance only to cache measurement results,
+ * the distance value is not used numerically otherwise. When two
+ * CPUs have the same distance it is assumed that the migration
+ * cost is the same. (this is a simplification but quite practical)
+ */
+#define MAX_DOMAIN_DISTANCE 32
+
+static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
+ { [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
+/*
+ * Architectures may override the migration cost and thus avoid
+ * boot-time calibration. Unit is nanoseconds. Mostly useful for
+ * virtualized hardware:
+ */
+#ifdef CONFIG_DEFAULT_MIGRATION_COST
+ CONFIG_DEFAULT_MIGRATION_COST
+#else
+ -1LL
+#endif
+};
+
+/*
+ * Allow override of migration cost - in units of microseconds.
+ * E.g. migration_cost=1000,2000,3000 will set up a level-1 cost
+ * of 1 msec, level-2 cost of 2 msecs and level3 cost of 3 msecs:
+ */
+static int __init migration_cost_setup(char *str)
+{
+ int ints[MAX_DOMAIN_DISTANCE+1], i;
+
+ str = get_options(str, ARRAY_SIZE(ints), ints);
+
+ printk("#ints: %d\n", ints[0]);
+ for (i = 1; i <= ints[0]; i++) {
+ migration_cost[i-1] = (unsigned long long)ints[i]*1000;
+ printk("migration_cost[%d]: %Ld\n", i-1, migration_cost[i-1]);
+ }
+ return 1;
+}
+
+__setup ("migration_cost=", migration_cost_setup);
+
+/*
+ * Global multiplier (divisor) for migration-cutoff values,
+ * in percentiles. E.g. use a value of 150 to get 1.5 times
+ * longer cache-hot cutoff times.
+ *
+ * (We scale it from 100 to 128 to long long handling easier.)
+ */
+
+#define MIGRATION_FACTOR_SCALE 128
+
+static unsigned int migration_factor = MIGRATION_FACTOR_SCALE;
+
+static int __init setup_migration_factor(char *str)
+{
+ get_option(&str, &migration_factor);
+ migration_factor = migration_factor * MIGRATION_FACTOR_SCALE / 100;
+ return 1;
+}
+
+__setup("migration_factor=", setup_migration_factor);
+
+/*
+ * Estimated distance of two CPUs, measured via the number of domains
+ * we have to pass for the two CPUs to be in the same span:
+ */
+static unsigned long domain_distance(int cpu1, int cpu2)
+{
+ unsigned long distance = 0;
+ struct sched_domain *sd;
+
+ for_each_domain(cpu1, sd) {
+ WARN_ON(!cpu_isset(cpu1, sd->span));
+ if (cpu_isset(cpu2, sd->span))
+ return distance;
+ distance++;
+ }
+ if (distance >= MAX_DOMAIN_DISTANCE) {
+ WARN_ON(1);
+ distance = MAX_DOMAIN_DISTANCE-1;
+ }
+
+ return distance;
+}
+
+static unsigned int migration_debug;
+
+static int __init setup_migration_debug(char *str)
+{
+ get_option(&str, &migration_debug);
+ return 1;
+}
+
+__setup("migration_debug=", setup_migration_debug);
+
+/*
+ * Maximum cache-size that the scheduler should try to measure.
+ * Architectures with larger caches should tune this up during
+ * bootup. Gets used in the domain-setup code (i.e. during SMP
+ * bootup).
+ */
+unsigned int max_cache_size;
+
+static int __init setup_max_cache_size(char *str)
+{
+ get_option(&str, &max_cache_size);
+ return 1;
+}
+
+__setup("max_cache_size=", setup_max_cache_size);
+
+/*
+ * Dirty a big buffer in a hard-to-predict (for the L2 cache) way. This
+ * is the operation that is timed, so we try to generate unpredictable
+ * cachemisses that still end up filling the L2 cache:
+ */
+static void touch_cache(void *__cache, unsigned long __size)
+{
+ unsigned long size = __size/sizeof(long), chunk1 = size/3,
+ chunk2 = 2*size/3;
+ unsigned long *cache = __cache;
+ int i;
+
+ for (i = 0; i < size/6; i += 8) {
+ switch (i % 6) {
+ case 0: cache[i]++;
+ case 1: cache[size-1-i]++;
+ case 2: cache[chunk1-i]++;
+ case 3: cache[chunk1+i]++;
+ case 4: cache[chunk2-i]++;
+ case 5: cache[chunk2+i]++;
+ }
+ }
+}
+
+/*
+ * Measure the cache-cost of one task migration. Returns in units of nsec.
+ */
+static unsigned long long
+measure_one(void *cache, unsigned long size, int source, int target)
+{
+ cpumask_t mask, saved_mask;
+ unsigned long long t0, t1, t2, t3, cost;
+
+ saved_mask = current->cpus_allowed;
+
+ /*
+ * Flush source caches to RAM and invalidate them:
+ */
+ sched_cacheflush();
+
+ /*
+ * Migrate to the source CPU:
+ */
+ mask = cpumask_of_cpu(source);
+ set_cpus_allowed(current, mask);
+ WARN_ON(smp_processor_id() != source);
+
+ /*
+ * Dirty the working set:
+ */
+ t0 = sched_clock();
+ touch_cache(cache, size);
+ t1 = sched_clock();
+
+ /*
+ * Migrate to the target CPU, dirty the L2 cache and access
+ * the shared buffer. (which represents the working set
+ * of a migrated task.)
+ */
+ mask = cpumask_of_cpu(target);
+ set_cpus_allowed(current, mask);
+ WARN_ON(smp_processor_id() != target);
+
+ t2 = sched_clock();
+ touch_cache(cache, size);
+ t3 = sched_clock();
+
+ cost = t1-t0 + t3-t2;
+
+ if (migration_debug >= 2)
+ printk("[%d->%d]: %8Ld %8Ld %8Ld => %10Ld.\n",
+ source, target, t1-t0, t1-t0, t3-t2, cost);
+ /*
+ * Flush target caches to RAM and invalidate them:
+ */
+ sched_cacheflush();
+
+ set_cpus_allowed(current, saved_mask);
+
+ return cost;
+}
+
+/*
+ * Measure a series of task migrations and return the average
+ * result. Since this code runs early during bootup the system
+ * is 'undisturbed' and the average latency makes sense.
+ *
+ * The algorithm in essence auto-detects the relevant cache-size,
+ * so it will properly detect different cachesizes for different
+ * cache-hierarchies, depending on how the CPUs are connected.
+ *
+ * Architectures can prime the upper limit of the search range via
+ * max_cache_size, otherwise the search range defaults to 20MB...64K.
+ */
+static unsigned long long
+measure_cost(int cpu1, int cpu2, void *cache, unsigned int size)
+{
+ unsigned long long cost1, cost2;
+ int i;
+
+ /*
+ * Measure the migration cost of 'size' bytes, over an
+ * average of 10 runs:
+ *
+ * (We perturb the cache size by a small (0..4k)
+ * value to compensate size/alignment related artifacts.
+ * We also subtract the cost of the operation done on
+ * the same CPU.)
+ */
+ cost1 = 0;
+
+ /*
+ * dry run, to make sure we start off cache-cold on cpu1,
+ * and to get any vmalloc pagefaults in advance:
+ */
+ measure_one(cache, size, cpu1, cpu2);
+ for (i = 0; i < ITERATIONS; i++)
+ cost1 += measure_one(cache, size - i*1024, cpu1, cpu2);
+
+ measure_one(cache, size, cpu2, cpu1);
+ for (i = 0; i < ITERATIONS; i++)
+ cost1 += measure_one(cache, size - i*1024, cpu2, cpu1);
+
+ /*
+ * (We measure the non-migrating [cached] cost on both
+ * cpu1 and cpu2, to handle CPUs with different speeds)
+ */
+ cost2 = 0;
+
+ measure_one(cache, size, cpu1, cpu1);
+ for (i = 0; i < ITERATIONS; i++)
+ cost2 += measure_one(cache, size - i*1024, cpu1, cpu1);
+
+ measure_one(cache, size, cpu2, cpu2);
+ for (i = 0; i < ITERATIONS; i++)
+ cost2 += measure_one(cache, size - i*1024, cpu2, cpu2);
+
+ /*
+ * Get the per-iteration migration cost:
+ */
+ do_div(cost1, 2*ITERATIONS);
+ do_div(cost2, 2*ITERATIONS);
+
+ return cost1 - cost2;
+}
+
+static unsigned long long measure_migration_cost(int cpu1, int cpu2)
+{
+ unsigned long long max_cost = 0, fluct = 0, avg_fluct = 0;
+ unsigned int max_size, size, size_found = 0;
+ long long cost = 0, prev_cost;
+ void *cache;
+
+ /*
+ * Search from max_cache_size*5 down to 64K - the real relevant
+ * cachesize has to lie somewhere inbetween.
+ */
+ if (max_cache_size) {
+ max_size = max(max_cache_size * SEARCH_SCOPE, MIN_CACHE_SIZE);
+ size = max(max_cache_size / SEARCH_SCOPE, MIN_CACHE_SIZE);
+ } else {
+ /*
+ * Since we have no estimation about the relevant
+ * search range
+ */
+ max_size = DEFAULT_CACHE_SIZE * SEARCH_SCOPE;
+ size = MIN_CACHE_SIZE;
+ }
+
+ if (!cpu_online(cpu1) || !cpu_online(cpu2)) {
+ printk("cpu %d and %d not both online!\n", cpu1, cpu2);
+ return 0;
+ }
+
+ /*
+ * Allocate the working set:
+ */
+ cache = vmalloc(max_size);
+ if (!cache) {
+ printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
+ return 1000000; /* return 1 msec on very small boxen */
+ }
+
+ while (size <= max_size) {
+ prev_cost = cost;
+ cost = measure_cost(cpu1, cpu2, cache, size);
+
+ /*
+ * Update the max:
+ */
+ if (cost > 0) {
+ if (max_cost < cost) {
+ max_cost = cost;
+ size_found = size;
+ }
+ }
+ /*
+ * Calculate average fluctuation, we use this to prevent
+ * noise from triggering an early break out of the loop:
+ */
+ fluct = abs(cost - prev_cost);
+ avg_fluct = (avg_fluct + fluct)/2;
+
+ if (migration_debug)
+ printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n",
+ cpu1, cpu2, size,
+ (long)cost / 1000000,
+ ((long)cost / 100000) % 10,
+ (long)max_cost / 1000000,
+ ((long)max_cost / 100000) % 10,
+ domain_distance(cpu1, cpu2),
+ cost, avg_fluct);
+
+ /*
+ * If we iterated at least 20% past the previous maximum,
+ * and the cost has dropped by more than 20% already,
+ * (taking fluctuations into account) then we assume to
+ * have found the maximum and break out of the loop early:
+ */
+ if (size_found && (size*100 > size_found*SIZE_THRESH))
+ if (cost+avg_fluct <= 0 ||
+ max_cost*100 > (cost+avg_fluct)*COST_THRESH) {
+
+ if (migration_debug)
+ printk("-> found max.\n");
+ break;
+ }
+ /*
+ * Increase the cachesize in 10% steps:
+ */
+ size = size * 10 / 9;
+ }
+
+ if (migration_debug)
+ printk("[%d][%d] working set size found: %d, cost: %Ld\n",
+ cpu1, cpu2, size_found, max_cost);
+
+ vfree(cache);
+
+ /*
+ * A task is considered 'cache cold' if at least 2 times
+ * the worst-case cost of migration has passed.
+ *
+ * (this limit is only listened to if the load-balancing
+ * situation is 'nice' - if there is a large imbalance we
+ * ignore it for the sake of CPU utilization and
+ * processing fairness.)
+ */
+ return 2 * max_cost * migration_factor / MIGRATION_FACTOR_SCALE;
+}
+
+static void calibrate_migration_costs(const cpumask_t *cpu_map)
+{
+ int cpu1 = -1, cpu2 = -1, cpu, orig_cpu = raw_smp_processor_id();
+ unsigned long j0, j1, distance, max_distance = 0;
+ struct sched_domain *sd;
+
+ j0 = jiffies;
+
+ /*
+ * First pass - calculate the cacheflush times:
+ */
+ for_each_cpu_mask(cpu1, *cpu_map) {
+ for_each_cpu_mask(cpu2, *cpu_map) {
+ if (cpu1 == cpu2)
+ continue;
+ distance = domain_distance(cpu1, cpu2);
+ max_distance = max(max_distance, distance);
+ /*
+ * No result cached yet?
+ */
+ if (migration_cost[distance] == -1LL)
+ migration_cost[distance] =
+ measure_migration_cost(cpu1, cpu2);
+ }
+ }
+ /*
+ * Second pass - update the sched domain hierarchy with
+ * the new cache-hot-time estimations:
+ */
+ for_each_cpu_mask(cpu, *cpu_map) {
+ distance = 0;
+ for_each_domain(cpu, sd) {
+ sd->cache_hot_time = migration_cost[distance];
+ distance++;
+ }
+ }
+ /*
+ * Print the matrix:
+ */
+ if (migration_debug)
+ printk("migration: max_cache_size: %d, cpu: %d MHz:\n",
+ max_cache_size,
+#ifdef CONFIG_X86
+ cpu_khz/1000
+#else
+ -1
+#endif
+ );
+ if (system_state == SYSTEM_BOOTING) {
+ if (num_online_cpus() > 1) {
+ printk("migration_cost=");
+ for (distance = 0; distance <= max_distance; distance++) {
+ if (distance)
+ printk(",");
+ printk("%ld", (long)migration_cost[distance] / 1000);
+ }
+ printk("\n");
+ }
+ }
+ j1 = jiffies;
+ if (migration_debug)
+ printk("migration: %ld seconds\n", (j1-j0)/HZ);
+
+ /*
+ * Move back to the original CPU. NUMA-Q gets confused
+ * if we migrate to another quad during bootup.
+ */
+ if (raw_smp_processor_id() != orig_cpu) {
+ cpumask_t mask = cpumask_of_cpu(orig_cpu),
+ saved_mask = current->cpus_allowed;
+
+ set_cpus_allowed(current, mask);
+ set_cpus_allowed(current, saved_mask);
+ }
+}
+
+#ifdef CONFIG_NUMA
+
+/**
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
+ *
+ * Find the next node to include in a given scheduling domain. Simply
+ * finds the closest node not already in the @used_nodes map.
+ *
+ * Should use nodemask_t.
+ */
+static int find_next_best_node(int node, unsigned long *used_nodes)
+{
+ int i, n, val, min_val, best_node = 0;
+
+ min_val = INT_MAX;
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ /* Start at @node */
+ n = (node + i) % MAX_NUMNODES;
+
+ if (!nr_cpus_node(n))
+ continue;
+
+ /* Skip already used nodes */
+ if (test_bit(n, used_nodes))
+ continue;
+
+ /* Simple min distance search */
+ val = node_distance(node, n);
+
+ if (val < min_val) {
+ min_val = val;
+ best_node = n;
+ }
+ }
+
+ set_bit(best_node, used_nodes);
+ return best_node;
+}
+
+/**
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @size: number of nodes to include in this span
+ *
+ * Given a node, construct a good cpumask for its sched_domain to span. It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
+ */
+static cpumask_t sched_domain_node_span(int node)
+{
+ DECLARE_BITMAP(used_nodes, MAX_NUMNODES);
+ cpumask_t span, nodemask;
+ int i;
+
+ cpus_clear(span);
+ bitmap_zero(used_nodes, MAX_NUMNODES);
+
+ nodemask = node_to_cpumask(node);
+ cpus_or(span, span, nodemask);
+ set_bit(node, used_nodes);
+
+ for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+ int next_node = find_next_best_node(node, used_nodes);
+
+ nodemask = node_to_cpumask(next_node);
+ cpus_or(span, span, nodemask);
+ }
+
+ return span;
+}
+#endif
+
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+
+/*
+ * SMT sched-domains:
+ */
+#ifdef CONFIG_SCHED_SMT
+static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
+static struct sched_group sched_group_cpus[NR_CPUS];
+
+static int cpu_to_cpu_group(int cpu)
+{
+ return cpu;
+}
+#endif
+
+/*
+ * multi-core sched-domains:
+ */
+#ifdef CONFIG_SCHED_MC
+static DEFINE_PER_CPU(struct sched_domain, core_domains);
+static struct sched_group *sched_group_core_bycpu[NR_CPUS];
+#endif
+
+#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
+static int cpu_to_core_group(int cpu)
+{
+ return first_cpu(cpu_sibling_map[cpu]);
+}
+#elif defined(CONFIG_SCHED_MC)
+static int cpu_to_core_group(int cpu)
+{
+ return cpu;
+}
+#endif
+
+static DEFINE_PER_CPU(struct sched_domain, phys_domains);
+static struct sched_group *sched_group_phys_bycpu[NR_CPUS];
+
+static int cpu_to_phys_group(int cpu)
+{
+#ifdef CONFIG_SCHED_MC
+ cpumask_t mask = cpu_coregroup_map(cpu);
+ return first_cpu(mask);
+#elif defined(CONFIG_SCHED_SMT)
+ return first_cpu(cpu_sibling_map[cpu]);
+#else
+ return cpu;
+#endif
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * The init_sched_build_groups can't handle what we want to do with node
+ * groups, so roll our own. Now each node has its own list of groups which
+ * gets dynamically allocated.
+ */
+static DEFINE_PER_CPU(struct sched_domain, node_domains);
+static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
+
+static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
+static struct sched_group *sched_group_allnodes_bycpu[NR_CPUS];
+
+static int cpu_to_allnodes_group(int cpu)
+{
+ return cpu_to_node(cpu);
+}
+static void init_numa_sched_groups_power(struct sched_group *group_head)
+{
+ struct sched_group *sg = group_head;
+ int j;
+
+ if (!sg)
+ return;
+next_sg:
+ for_each_cpu_mask(j, sg->cpumask) {
+ struct sched_domain *sd;
+
+ sd = &per_cpu(phys_domains, j);
+ if (j != first_cpu(sd->groups->cpumask)) {
+ /*
+ * Only add "power" once for each
+ * physical package.
+ */
+ continue;
+ }
+
+ sg->cpu_power += sd->groups->cpu_power;
+ }
+ sg = sg->next;
+ if (sg != group_head)
+ goto next_sg;
+}
+#endif
+
+/* Free memory allocated for various sched_group structures */
+static void free_sched_groups(const cpumask_t *cpu_map)
+{
+ int cpu;
+#ifdef CONFIG_NUMA
+ int i;
+
+ for_each_cpu_mask(cpu, *cpu_map) {
+ struct sched_group *sched_group_allnodes
+ = sched_group_allnodes_bycpu[cpu];
+ struct sched_group **sched_group_nodes
+ = sched_group_nodes_bycpu[cpu];
+
+ if (sched_group_allnodes) {
+ kfree(sched_group_allnodes);
+ sched_group_allnodes_bycpu[cpu] = NULL;
+ }
+
+ if (!sched_group_nodes)
+ continue;
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ cpumask_t nodemask = node_to_cpumask(i);
+ struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask))
+ continue;
+
+ if (sg == NULL)
+ continue;
+ sg = sg->next;
+next_sg:
+ oldsg = sg;
+ sg = sg->next;
+ kfree(oldsg);
+ if (oldsg != sched_group_nodes[i])
+ goto next_sg;
+ }
+ kfree(sched_group_nodes);
+ sched_group_nodes_bycpu[cpu] = NULL;
+ }
+#endif
+ for_each_cpu_mask(cpu, *cpu_map) {
+ if (sched_group_phys_bycpu[cpu]) {
+ kfree(sched_group_phys_bycpu[cpu]);
+ sched_group_phys_bycpu[cpu] = NULL;
+ }
+#ifdef CONFIG_SCHED_MC
+ if (sched_group_core_bycpu[cpu]) {
+ kfree(sched_group_core_bycpu[cpu]);
+ sched_group_core_bycpu[cpu] = NULL;
+ }
+#endif
+ }
+}
+
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int build_sched_domains(const cpumask_t *cpu_map)
+{
+ int i;
+ struct sched_group *sched_group_phys = NULL;
+#ifdef CONFIG_SCHED_MC
+ struct sched_group *sched_group_core = NULL;
+#endif
+#ifdef CONFIG_NUMA
+ struct sched_group **sched_group_nodes = NULL;
+ struct sched_group *sched_group_allnodes = NULL;
+
+ /*
+ * Allocate the per-node list of sched groups
+ */
+ sched_group_nodes = kzalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
+ GFP_KERNEL);
+ if (!sched_group_nodes) {
+ printk(KERN_WARNING "Can not alloc sched group node list\n");
+ return -ENOMEM;
+ }
+ sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
+#endif
+
+ /*
+ * Set up domains for cpus specified by the cpu_map.
+ */
+ for_each_cpu_mask(i, *cpu_map) {
+ int group;
+ struct sched_domain *sd = NULL, *p;
+ cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+
+#ifdef CONFIG_NUMA
+ if (cpus_weight(*cpu_map)
+ > SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
+ if (!sched_group_allnodes) {
+ sched_group_allnodes
+ = kmalloc(sizeof(struct sched_group)
+ * MAX_NUMNODES,
+ GFP_KERNEL);
+ if (!sched_group_allnodes) {
+ printk(KERN_WARNING
+ "Can not alloc allnodes sched group\n");
+ goto error;
+ }
+ sched_group_allnodes_bycpu[i]
+ = sched_group_allnodes;
+ }
+ sd = &per_cpu(allnodes_domains, i);
+ *sd = SD_ALLNODES_INIT;
+ sd->span = *cpu_map;
+ group = cpu_to_allnodes_group(i);
+ sd->groups = &sched_group_allnodes[group];
+ p = sd;
+ } else
+ p = NULL;
+
+ sd = &per_cpu(node_domains, i);
+ *sd = SD_NODE_INIT;
+ sd->span = sched_domain_node_span(cpu_to_node(i));
+ sd->parent = p;
+ cpus_and(sd->span, sd->span, *cpu_map);
+#endif
+
+ if (!sched_group_phys) {
+ sched_group_phys
+ = kmalloc(sizeof(struct sched_group) * NR_CPUS,
+ GFP_KERNEL);
+ if (!sched_group_phys) {
+ printk (KERN_WARNING "Can not alloc phys sched"
+ "group\n");
+ goto error;
+ }
+ sched_group_phys_bycpu[i] = sched_group_phys;
+ }
+
+ p = sd;
+ sd = &per_cpu(phys_domains, i);
+ group = cpu_to_phys_group(i);
+ *sd = SD_CPU_INIT;
+ sd->span = nodemask;
+ sd->parent = p;
+ sd->groups = &sched_group_phys[group];
+
+#ifdef CONFIG_SCHED_MC
+ if (!sched_group_core) {
+ sched_group_core
+ = kmalloc(sizeof(struct sched_group) * NR_CPUS,
+ GFP_KERNEL);
+ if (!sched_group_core) {
+ printk (KERN_WARNING "Can not alloc core sched"
+ "group\n");
+ goto error;
+ }
+ sched_group_core_bycpu[i] = sched_group_core;
+ }
+
+ p = sd;
+ sd = &per_cpu(core_domains, i);
+ group = cpu_to_core_group(i);
+ *sd = SD_MC_INIT;
+ sd->span = cpu_coregroup_map(i);
+ cpus_and(sd->span, sd->span, *cpu_map);
+ sd->parent = p;
+ sd->groups = &sched_group_core[group];
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+ p = sd;
+ sd = &per_cpu(cpu_domains, i);
+ group = cpu_to_cpu_group(i);
+ *sd = SD_SIBLING_INIT;
+ sd->span = cpu_sibling_map[i];
+ cpus_and(sd->span, sd->span, *cpu_map);
+ sd->parent = p;
+ sd->groups = &sched_group_cpus[group];
+#endif
+ }
+
+#ifdef CONFIG_SCHED_SMT
+ /* Set up CPU (sibling) groups */
+ for_each_cpu_mask(i, *cpu_map) {
+ cpumask_t this_sibling_map = cpu_sibling_map[i];
+ cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
+ if (i != first_cpu(this_sibling_map))
+ continue;
+
+ init_sched_build_groups(sched_group_cpus, this_sibling_map,
+ &cpu_to_cpu_group);
+ }
+#endif
+
+#ifdef CONFIG_SCHED_MC
+ /* Set up multi-core groups */
+ for_each_cpu_mask(i, *cpu_map) {
+ cpumask_t this_core_map = cpu_coregroup_map(i);
+ cpus_and(this_core_map, this_core_map, *cpu_map);
+ if (i != first_cpu(this_core_map))
+ continue;
+ init_sched_build_groups(sched_group_core, this_core_map,
+ &cpu_to_core_group);
+ }
+#endif
+
+
+ /* Set up physical groups */
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ cpumask_t nodemask = node_to_cpumask(i);
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask))
+ continue;
+
+ init_sched_build_groups(sched_group_phys, nodemask,
+ &cpu_to_phys_group);
+ }
+
+#ifdef CONFIG_NUMA
+ /* Set up node groups */
+ if (sched_group_allnodes)
+ init_sched_build_groups(sched_group_allnodes, *cpu_map,
+ &cpu_to_allnodes_group);
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ /* Set up node groups */
+ struct sched_group *sg, *prev;
+ cpumask_t nodemask = node_to_cpumask(i);
+ cpumask_t domainspan;
+ cpumask_t covered = CPU_MASK_NONE;
+ int j;
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask)) {
+ sched_group_nodes[i] = NULL;
+ continue;
+ }
+
+ domainspan = sched_domain_node_span(i);
+ cpus_and(domainspan, domainspan, *cpu_map);
+
+ sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i);
+ if (!sg) {
+ printk(KERN_WARNING "Can not alloc domain group for "
+ "node %d\n", i);
+ goto error;
+ }
+ sched_group_nodes[i] = sg;
+ for_each_cpu_mask(j, nodemask) {
+ struct sched_domain *sd;
+ sd = &per_cpu(node_domains, j);
+ sd->groups = sg;
+ }
+ sg->cpu_power = 0;
+ sg->cpumask = nodemask;
+ sg->next = sg;
+ cpus_or(covered, covered, nodemask);
+ prev = sg;
+
+ for (j = 0; j < MAX_NUMNODES; j++) {
+ cpumask_t tmp, notcovered;
+ int n = (i + j) % MAX_NUMNODES;
+
+ cpus_complement(notcovered, covered);
+ cpus_and(tmp, notcovered, *cpu_map);
+ cpus_and(tmp, tmp, domainspan);
+ if (cpus_empty(tmp))
+ break;
+
+ nodemask = node_to_cpumask(n);
+ cpus_and(tmp, tmp, nodemask);
+ if (cpus_empty(tmp))
+ continue;
+
+ sg = kmalloc_node(sizeof(struct sched_group),
+ GFP_KERNEL, i);
+ if (!sg) {
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", j);
+ goto error;
+ }
+ sg->cpu_power = 0;
+ sg->cpumask = tmp;
+ sg->next = prev->next;
+ cpus_or(covered, covered, tmp);
+ prev->next = sg;
+ prev = sg;
+ }
+ }
+#endif
+
+ /* Calculate CPU power for physical packages and nodes */
+#ifdef CONFIG_SCHED_SMT
+ for_each_cpu_mask(i, *cpu_map) {
+ struct sched_domain *sd;
+ sd = &per_cpu(cpu_domains, i);
+ sd->groups->cpu_power = SCHED_LOAD_SCALE;
+ }
+#endif
+#ifdef CONFIG_SCHED_MC
+ for_each_cpu_mask(i, *cpu_map) {
+ int power;
+ struct sched_domain *sd;
+ sd = &per_cpu(core_domains, i);
+ if (sched_smt_power_savings)
+ power = SCHED_LOAD_SCALE * cpus_weight(sd->groups->cpumask);
+ else
+ power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
+ * SCHED_LOAD_SCALE / 10;
+ sd->groups->cpu_power = power;
+ }
+#endif
+
+ for_each_cpu_mask(i, *cpu_map) {
+ struct sched_domain *sd;
+#ifdef CONFIG_SCHED_MC
+ sd = &per_cpu(phys_domains, i);
+ if (i != first_cpu(sd->groups->cpumask))
+ continue;