extern void calc_global_load(unsigned long ticks);
extern void update_cpu_load_nohz(void);
+/* Notifier for when a task gets migrated to a new CPU */
+struct task_migration_notifier {
+ struct task_struct *task;
+ int from_cpu;
+ int to_cpu;
+};
+extern void register_task_migration_notifier(struct notifier_block *n);
+
extern unsigned long get_parent_ip(unsigned long addr);
extern void dump_cpu_task(int cpu);
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);
+ extern cpumask_var_t cpu_isolated_map;
+
extern int runqueue_is_locked(int cpu);
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
};
struct sched_avg {
+ u64 last_runnable_update;
+ s64 decay_count;
+ /*
+ * utilization_avg_contrib describes the amount of time that a
+ * sched_entity is running on a CPU. It is based on running_avg_sum
+ * and is scaled in the range [0..SCHED_LOAD_SCALE].
+ * load_avg_contrib described the amount of time that a sched_entity
+ * is runnable on a rq. It is based on both runnable_avg_sum and the
+ * weight of the task.
+ */
+ unsigned long load_avg_contrib, utilization_avg_contrib;
/*
* These sums represent an infinite geometric series and so are bound
* above by 1024/(1-y). Thus we only need a u32 to store them for all
* choices of y < 1-2^(-32)*1024.
+ * running_avg_sum reflects the time that the sched_entity is
+ * effectively running on the CPU.
+ * runnable_avg_sum represents the amount of time a sched_entity is on
+ * a runqueue which includes the running time that is monitored by
+ * running_avg_sum.
*/
- u32 runnable_avg_sum, runnable_avg_period;
- u64 last_runnable_update;
- s64 decay_count;
- unsigned long load_avg_contrib;
+ u32 runnable_avg_sum, avg_period, running_avg_sum;
};
#ifdef CONFIG_SCHEDSTATS
/*
* numa_faults_locality tracks if faults recorded during the last
- * scan window were remote/local. The task scan period is adapted
- * based on the locality of the faults with different weights
- * depending on whether they were shared or private faults
+ * scan window were remote/local or failed to migrate. The task scan
+ * period is adapted based on the locality of the faults with different
+ * weights depending on whether they were shared or private faults
*/
- unsigned long numa_faults_locality[2];
+ unsigned long numa_faults_locality[3];
unsigned long numa_pages_migrated;
#endif /* CONFIG_NUMA_BALANCING */
#define TNF_NO_GROUP 0x02
#define TNF_SHARED 0x04
#define TNF_FAULT_LOCAL 0x08
+#define TNF_MIGRATE_FAIL 0x10
#ifdef CONFIG_NUMA_BALANCING
extern void task_numa_fault(int last_node, int node, int pages, int flags);
*/
int sysctl_sched_rt_runtime = 950000;
+ /* cpus with isolated domains */
+ cpumask_var_t cpu_isolated_map;
+
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
#ifdef CONFIG_NO_HZ_FULL
bool sched_can_stop_tick(void)
{
+ /*
+ * FIFO realtime policy runs the highest priority task. Other runnable
+ * tasks are of a lower priority. The scheduler tick does nothing.
+ */
+ if (current->policy == SCHED_FIFO)
+ return true;
+
+ /*
+ * Round-robin realtime tasks time slice with other tasks at the same
+ * realtime priority. Is this task the only one at this priority?
+ */
+ if (current->policy == SCHED_RR) {
+ struct sched_rt_entity *rt_se = ¤t->rt;
+
+ return rt_se->run_list.prev == rt_se->run_list.next;
+ }
+
/*
* More than one running task need preemption.
* nr_running update is assumed to be visible
rq_clock_skip_update(rq, true);
}
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
#ifdef CONFIG_SMP
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
trace_sched_migrate_task(p, new_cpu);
if (task_cpu(p) != new_cpu) {
+ struct task_migration_notifier tmn;
+
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+
+ tmn.task = p;
+ tmn.from_cpu = task_cpu(p);
+ tmn.to_cpu = new_cpu;
+
+ atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
}
__set_task_cpu(p, new_cpu);
} else {
if (dl_prio(oldprio))
p->dl.dl_boosted = 0;
+ if (rt_prio(oldprio))
+ p->rt.timeout = 0;
p->sched_class = &fair_sched_class;
}
static int sched_cpu_inactive(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- unsigned long flags;
- long cpu = (long)hcpu;
- struct dl_bw *dl_b;
-
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
- set_cpu_active(cpu, false);
-
- /* explicitly allow suspend */
- if (!(action & CPU_TASKS_FROZEN)) {
- bool overflow;
- int cpus;
-
- rcu_read_lock_sched();
- dl_b = dl_bw_of(cpu);
-
- raw_spin_lock_irqsave(&dl_b->lock, flags);
- cpus = dl_bw_cpus(cpu);
- overflow = __dl_overflow(dl_b, cpus, 0, 0);
- raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
- rcu_read_unlock_sched();
-
- if (overflow)
- return notifier_from_errno(-EBUSY);
- }
+ set_cpu_active((long)hcpu, false);
return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
}
-
- return NOTIFY_DONE;
}
static int __init migration_init(void)
break;
}
- /*
- * Even though we initialize ->capacity to something semi-sane,
- * we leave capacity_orig unset. This allows us to detect if
- * domain iteration is still funny without causing /0 traps.
- */
- if (!group->sgc->capacity_orig) {
- printk(KERN_CONT "\n");
- printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
- break;
- }
-
if (!cpumask_weight(sched_group_cpus(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: empty group\n");
update_top_cache_domain(cpu);
}
- /* cpus with isolated domains */
- static cpumask_var_t cpu_isolated_map;
-
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
* die on a /0 trap.
*/
sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
- sg->sgc->capacity_orig = sg->sgc->capacity;
/*
* Make sure the first group of this domain contains the
*/
if (sd->flags & SD_SHARE_CPUCAPACITY) {
+ sd->flags |= SD_PREFER_SIBLING;
sd->imbalance_pct = 110;
sd->smt_gain = 1178; /* ~15% */
*/
case CPU_ONLINE:
- case CPU_DOWN_FAILED:
cpuset_update_active_cpus(true);
break;
default:
static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- switch (action) {
+ unsigned long flags;
+ long cpu = (long)hcpu;
+ struct dl_bw *dl_b;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_DOWN_PREPARE:
+ /* explicitly allow suspend */
+ if (!(action & CPU_TASKS_FROZEN)) {
+ bool overflow;
+ int cpus;
+
+ rcu_read_lock_sched();
+ dl_b = dl_bw_of(cpu);
+
+ raw_spin_lock_irqsave(&dl_b->lock, flags);
+ cpus = dl_bw_cpus(cpu);
+ overflow = __dl_overflow(dl_b, cpus, 0, 0);
+ raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+ rcu_read_unlock_sched();
+
+ if (overflow)
+ return notifier_from_errno(-EBUSY);
+ }
cpuset_update_active_cpus(false);
break;
case CPU_DOWN_PREPARE_FROZEN:
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
init_cfs_rq(&rq->cfs);
- init_rt_rq(&rq->rt, rq);
- init_dl_rq(&rq->dl, rq);
+ init_rt_rq(&rq->rt);
+ init_dl_rq(&rq->dl);
#ifdef CONFIG_FAIR_GROUP_SCHED
root_task_group.shares = ROOT_TASK_GROUP_LOAD;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
- rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+ rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
rq->post_schedule = 0;
rq->active_balance = 0;
rq->next_balance = jiffies;
}
#endif /* CONFIG_RT_GROUP_SCHED */
-static int sched_dl_global_constraints(void)
+static int sched_dl_global_validate(void)
{
u64 runtime = global_rt_runtime();
u64 period = global_rt_period();
if (ret)
goto undo;
- ret = sched_rt_global_constraints();
+ ret = sched_dl_global_validate();
if (ret)
goto undo;
- ret = sched_dl_global_constraints();
+ ret = sched_rt_global_constraints();
if (ret)
goto undo;