/* domain-specific stats */
preempt_disable();
for_each_domain(cpu, sd) {
- enum idle_type itype;
+ enum cpu_idle_type itype;
char mask_str[NR_CPUS];
cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
seq_printf(seq, "domain%d %s", dcnt++, mask_str);
- for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
+ for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
itype++) {
seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu "
"%lu",
{
unsigned long flags;
struct rq *rq;
- int preempted;
+ struct prio_array *array;
+ int running;
repeat:
+ /*
+ * We do the initial early heuristics without holding
+ * any task-queue locks at all. We'll only try to get
+ * the runqueue lock when things look like they will
+ * work out!
+ */
+ rq = task_rq(p);
+
+ /*
+ * If the task is actively running on another CPU
+ * still, just relax and busy-wait without holding
+ * any locks.
+ *
+ * NOTE! Since we don't hold any locks, it's not
+ * even sure that "rq" stays as the right runqueue!
+ * But we don't care, since "task_running()" will
+ * return false if the runqueue has changed and p
+ * is actually now running somewhere else!
+ */
+ while (task_running(rq, p))
+ cpu_relax();
+
+ /*
+ * Ok, time to look more closely! We need the rq
+ * lock now, to be *sure*. If we're wrong, we'll
+ * just go back and repeat.
+ */
rq = task_rq_lock(p, &flags);
- /* Must be off runqueue entirely, not preempted. */
- if (unlikely(p->array || task_running(rq, p))) {
- /* If it's preempted, we yield. It could be a while. */
- preempted = !task_running(rq, p);
- task_rq_unlock(rq, &flags);
+ running = task_running(rq, p);
+ array = p->array;
+ task_rq_unlock(rq, &flags);
+
+ /*
+ * Was it really running after all now that we
+ * checked with the proper locks actually held?
+ *
+ * Oops. Go back and try again..
+ */
+ if (unlikely(running)) {
cpu_relax();
- if (preempted)
- yield();
goto repeat;
}
- task_rq_unlock(rq, &flags);
+
+ /*
+ * It's not enough that it's not actively running,
+ * it must be off the runqueue _entirely_, and not
+ * preempted!
+ *
+ * So if it wa still runnable (but just not actively
+ * running right now), it's preempted, and we should
+ * yield - it could be a while.
+ */
+ if (unlikely(array)) {
+ yield();
+ goto repeat;
+ }
+
+ /*
+ * Ahh, all good. It wasn't running, and it wasn't
+ * runnable, which means that it will never become
+ * running in the future either. We're all done!
+ */
}
/***
*/
static
int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
- struct sched_domain *sd, enum idle_type idle,
+ struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
/*
*/
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum idle_type idle,
+ struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
int idx, pulled = 0, pinned = 0, this_best_prio, best_prio,
*/
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
- unsigned long *imbalance, enum idle_type idle, int *sd_idle,
+ unsigned long *imbalance, enum cpu_idle_type idle, int *sd_idle,
cpumask_t *cpus, int *balance)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
max_load = this_load = total_load = total_pwr = 0;
busiest_load_per_task = busiest_nr_running = 0;
this_load_per_task = this_nr_running = 0;
- if (idle == NOT_IDLE)
+ if (idle == CPU_NOT_IDLE)
load_idx = sd->busy_idx;
- else if (idle == NEWLY_IDLE)
+ else if (idle == CPU_NEWLY_IDLE)
load_idx = sd->newidle_idx;
else
load_idx = sd->idle_idx;
* Busy processors will not participate in power savings
* balance.
*/
- if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+ if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
goto group_next;
/*
out_balanced:
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
- if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+ if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
goto ret;
if (this == group_leader && group_leader != group_min) {
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
static struct rq *
-find_busiest_queue(struct sched_group *group, enum idle_type idle,
+find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
unsigned long imbalance, cpumask_t *cpus)
{
struct rq *busiest = NULL, *rq;
* tasks if there is an imbalance.
*/
static int load_balance(int this_cpu, struct rq *this_rq,
- struct sched_domain *sd, enum idle_type idle,
+ struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
* When power savings policy is enabled for the parent domain, idle
* sibling can pick up load irrespective of busy siblings. In this case,
* let the state of idle sibling percolate up as IDLE, instead of
- * portraying it as NOT_IDLE.
+ * portraying it as CPU_NOT_IDLE.
*/
- if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
+ if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*
- * Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
+ * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
* this_rq is locked.
*/
static int
* When power savings policy is enabled for the parent domain, idle
* sibling can pick up load irrespective of busy siblings. In this case,
* let the state of idle sibling percolate up as IDLE, instead of
- * portraying it as NOT_IDLE.
+ * portraying it as CPU_NOT_IDLE.
*/
if (sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
- schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
+ schedstat_inc(sd, lb_cnt[CPU_NEWLY_IDLE]);
redo:
- group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE,
+ group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
&sd_idle, &cpus, NULL);
if (!group) {
- schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
+ schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance,
+ busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance,
&cpus);
if (!busiest) {
- schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
+ schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
goto out_balanced;
}
BUG_ON(busiest == this_rq);
- schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
+ schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
nr_moved = 0;
if (busiest->nr_running > 1) {
double_lock_balance(this_rq, busiest);
nr_moved = move_tasks(this_rq, this_cpu, busiest,
minus_1_or_zero(busiest->nr_running),
- imbalance, sd, NEWLY_IDLE, NULL);
+ imbalance, sd, CPU_NEWLY_IDLE, NULL);
spin_unlock(&busiest->lock);
if (!nr_moved) {
}
if (!nr_moved) {
- schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
+ schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
return nr_moved;
out_balanced:
- schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
+ schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
return -1;
unsigned long next_balance = jiffies + 60 * HZ;
for_each_domain(this_cpu, sd) {
- if (sd->flags & SD_BALANCE_NEWIDLE) {
+ unsigned long interval;
+
+ if (!(sd->flags & SD_LOAD_BALANCE))
+ continue;
+
+ if (sd->flags & SD_BALANCE_NEWIDLE)
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu,
- this_rq, sd);
- if (time_after(next_balance,
- sd->last_balance + sd->balance_interval))
- next_balance = sd->last_balance
- + sd->balance_interval;
- if (pulled_task)
- break;
- }
+ this_rq, sd);
+
+ interval = msecs_to_jiffies(sd->balance_interval);
+ if (time_after(next_balance, sd->last_balance + interval))
+ next_balance = sd->last_balance + interval;
+ if (pulled_task)
+ break;
}
if (!pulled_task)
/*
schedstat_inc(sd, alb_cnt);
if (move_tasks(target_rq, target_cpu, busiest_rq, 1,
- RTPRIO_TO_LOAD_WEIGHT(100), sd, SCHED_IDLE,
+ RTPRIO_TO_LOAD_WEIGHT(100), sd, CPU_IDLE,
NULL))
schedstat_inc(sd, alb_pushed);
else
*
* Balancing parameters are set up in arch_init_sched_domains.
*/
-static inline void rebalance_domains(int cpu, enum idle_type idle)
+static inline void rebalance_domains(int cpu, enum cpu_idle_type idle)
{
int balance = 1;
struct rq *rq = cpu_rq(cpu);
continue;
interval = sd->balance_interval;
- if (idle != SCHED_IDLE)
+ if (idle != CPU_IDLE)
interval *= sd->busy_factor;
/* scale ms to jiffies */
* longer idle, or one of our SMT siblings is
* not idle.
*/
- idle = NOT_IDLE;
+ idle = CPU_NOT_IDLE;
}
sd->last_balance = jiffies;
}
{
int local_cpu = smp_processor_id();
struct rq *local_rq = cpu_rq(local_cpu);
- enum idle_type idle = local_rq->idle_at_tick ? SCHED_IDLE : NOT_IDLE;
+ enum cpu_idle_type idle = local_rq->idle_at_tick ? CPU_IDLE : CPU_NOT_IDLE;
rebalance_domains(local_cpu, idle);
if (need_resched())
break;
- rebalance_domains(balance_cpu, SCHED_IDLE);
+ rebalance_domains(balance_cpu, CPU_IDLE);
rq = cpu_rq(balance_cpu);
if (time_after(local_rq->next_balance, rq->next_balance))
BUG_ON(!in_softirq());
if (need_resched() && system_state == SYSTEM_RUNNING) {
- raw_local_irq_disable();
- _local_bh_enable();
- raw_local_irq_enable();
+ local_bh_enable();
__cond_resched();
local_bh_disable();
return 1;
void normalize_rt_tasks(void)
{
struct prio_array *array;
- struct task_struct *p;
+ struct task_struct *g, *p;
unsigned long flags;
struct rq *rq;
read_lock_irq(&tasklist_lock);
- for_each_process(p) {
+
+ do_each_thread(g, p) {
if (!rt_task(p))
continue;
__task_rq_unlock(rq);
spin_unlock_irqrestore(&p->pi_lock, flags);
- }
+ } while_each_thread(g, p);
+
read_unlock_irq(&tasklist_lock);
}