{
s64 delta;
- if (rq->skip_clock_update > 0)
+ lockdep_assert_held(&rq->lock);
+
+ if (rq->clock_skip_update & RQCF_ACT_SKIP)
return;
delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
*/
int sysctl_sched_rt_runtime = 950000;
-/*
- * __task_rq_lock - lock the rq @p resides on.
- */
-static inline struct rq *__task_rq_lock(struct task_struct *p)
- __acquires(rq->lock)
-{
- struct rq *rq;
-
- lockdep_assert_held(&p->pi_lock);
-
- for (;;) {
- rq = task_rq(p);
- raw_spin_lock(&rq->lock);
- if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
- return rq;
- raw_spin_unlock(&rq->lock);
-
- while (unlikely(task_on_rq_migrating(p)))
- cpu_relax();
- }
-}
-
-/*
- * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
- */
-static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
- __acquires(p->pi_lock)
- __acquires(rq->lock)
-{
- struct rq *rq;
-
- for (;;) {
- raw_spin_lock_irqsave(&p->pi_lock, *flags);
- rq = task_rq(p);
- raw_spin_lock(&rq->lock);
- if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
- return rq;
- raw_spin_unlock(&rq->lock);
- raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-
- while (unlikely(task_on_rq_migrating(p)))
- cpu_relax();
- }
-}
-
-static void __task_rq_unlock(struct rq *rq)
- __releases(rq->lock)
-{
- raw_spin_unlock(&rq->lock);
-}
-
-static inline void
-task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
- __releases(rq->lock)
- __releases(p->pi_lock)
-{
- raw_spin_unlock(&rq->lock);
- raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-}
+/* cpus with isolated domains */
+cpumask_var_t cpu_isolated_map;
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
void hrtick_start(struct rq *rq, u64 delay)
{
+ /*
+ * Don't schedule slices shorter than 10000ns, that just
+ * doesn't make sense. Rely on vruntime for fairness.
+ */
+ delay = max_t(u64, delay, 10000LL);
__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
HRTIMER_MODE_REL_PINNED, 0);
}
* this case, we can save a useless back to back clock update.
*/
if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
- rq->skip_clock_update = 1;
+ rq_clock_skip_update(rq, true);
}
#ifdef CONFIG_SMP
if (p->sched_class->migrate_task_rq)
p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
- perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+ perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
}
__set_task_cpu(p, new_cpu);
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
p->se.vruntime = 0;
+#ifdef CONFIG_SMP
+ p->se.avg.decay_count = 0;
+#endif
INIT_LIST_HEAD(&p->se.group_node);
#ifdef CONFIG_SCHEDSTATS
* - explicit schedule() call
* - return from syscall or exception to user-space
* - return from interrupt-handler to user-space
+ *
+ * WARNING: all callers must re-check need_resched() afterward and reschedule
+ * accordingly in case an event triggered the need for rescheduling (such as
+ * an interrupt waking up a task) while preemption was disabled in __schedule().
*/
static void __sched __schedule(void)
{
struct rq *rq;
int cpu;
-need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
smp_mb__before_spinlock();
raw_spin_lock_irq(&rq->lock);
+ rq->clock_skip_update <<= 1; /* promote REQ to ACT */
+
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely(signal_pending_state(prev->state, prev))) {
switch_count = &prev->nvcsw;
}
- if (task_on_rq_queued(prev) || rq->skip_clock_update < 0)
+ if (task_on_rq_queued(prev))
update_rq_clock(rq);
next = pick_next_task(rq, prev);
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
- rq->skip_clock_update = 0;
+ rq->clock_skip_update = 0;
if (likely(prev != next)) {
rq->nr_switches++;
post_schedule(rq);
sched_preempt_enable_no_resched();
- if (need_resched())
- goto need_resched;
}
static inline void sched_submit_work(struct task_struct *tsk)
struct task_struct *tsk = current;
sched_submit_work(tsk);
- __schedule();
+ do {
+ __schedule();
+ } while (need_resched());
}
EXPORT_SYMBOL(schedule);
preempt_disable();
}
+static void __sched notrace preempt_schedule_common(void)
+{
+ do {
+ __preempt_count_add(PREEMPT_ACTIVE);
+ __schedule();
+ __preempt_count_sub(PREEMPT_ACTIVE);
+
+ /*
+ * Check again in case we missed a preemption opportunity
+ * between schedule and now.
+ */
+ barrier();
+ } while (need_resched());
+}
+
#ifdef CONFIG_PREEMPT
/*
* this is the entry point to schedule() from in-kernel preemption
if (likely(!preemptible()))
return;
- do {
- __preempt_count_add(PREEMPT_ACTIVE);
- __schedule();
- __preempt_count_sub(PREEMPT_ACTIVE);
-
- /*
- * Check again in case we missed a preemption opportunity
- * between schedule and now.
- */
- barrier();
- } while (need_resched());
+ preempt_schedule_common();
}
NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
return match;
}
+static bool dl_param_changed(struct task_struct *p,
+ const struct sched_attr *attr)
+{
+ struct sched_dl_entity *dl_se = &p->dl;
+
+ if (dl_se->dl_runtime != attr->sched_runtime ||
+ dl_se->dl_deadline != attr->sched_deadline ||
+ dl_se->dl_period != attr->sched_period ||
+ dl_se->flags != attr->sched_flags)
+ return true;
+
+ return false;
+}
+
static int __sched_setscheduler(struct task_struct *p,
const struct sched_attr *attr,
bool user)
goto change;
if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
goto change;
- if (dl_policy(policy))
+ if (dl_policy(policy) && dl_param_changed(p, attr))
goto change;
p->sched_reset_on_fork = reset_on_fork;
return 0;
}
-static void __cond_resched(void)
-{
- __preempt_count_add(PREEMPT_ACTIVE);
- __schedule();
- __preempt_count_sub(PREEMPT_ACTIVE);
-}
-
int __sched _cond_resched(void)
{
if (should_resched()) {
- __cond_resched();
+ preempt_schedule_common();
return 1;
}
return 0;
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
- __cond_resched();
+ preempt_schedule_common();
else
cpu_relax();
ret = 1;
if (should_resched()) {
local_bh_enable();
- __cond_resched();
+ preempt_schedule_common();
local_bh_disable();
return 1;
}
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
*/
-void __sched io_schedule(void)
-{
- struct rq *rq = raw_rq();
-
- delayacct_blkio_start();
- atomic_inc(&rq->nr_iowait);
- blk_flush_plug(current);
- current->in_iowait = 1;
- schedule();
- current->in_iowait = 0;
- atomic_dec(&rq->nr_iowait);
- delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
long __sched io_schedule_timeout(long timeout)
{
- struct rq *rq = raw_rq();
+ int old_iowait = current->in_iowait;
+ struct rq *rq;
long ret;
+ current->in_iowait = 1;
+ if (old_iowait)
+ blk_schedule_flush_plug(current);
+ else
+ blk_flush_plug(current);
+
delayacct_blkio_start();
+ rq = raw_rq();
atomic_inc(&rq->nr_iowait);
- blk_flush_plug(current);
- current->in_iowait = 1;
ret = schedule_timeout(timeout);
- current->in_iowait = 0;
+ current->in_iowait = old_iowait;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
+
return ret;
}
+EXPORT_SYMBOL(io_schedule_timeout);
/**
* sys_sched_get_priority_max - return maximum RT priority.
{
unsigned long free = 0;
int ppid;
- unsigned state;
+ unsigned long state = p->state;
- state = p->state ? __ffs(p->state) + 1 : 0;
+ if (state)
+ state = __ffs(state) + 1;
printk(KERN_INFO "%-15.15s %c", p->comm,
state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
- if (p->sched_class && p->sched_class->set_cpus_allowed)
+ if (p->sched_class->set_cpus_allowed)
p->sched_class->set_cpus_allowed(p, new_mask);
cpumask_copy(&p->cpus_allowed, new_mask);
struct cpumask *groupmask)
{
struct sched_group *group = sd->groups;
- char str[256];
- cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
cpumask_clear(groupmask);
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
return -1;
}
- printk(KERN_CONT "span %s level %s\n", str, sd->name);
+ printk(KERN_CONT "span %*pbl level %s\n",
+ cpumask_pr_args(sched_domain_span(sd)), sd->name);
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain "
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
- cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
-
- printk(KERN_CONT " %s", str);
+ printk(KERN_CONT " %*pbl",
+ cpumask_pr_args(sched_group_cpus(group)));
if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
printk(KERN_CONT " (cpu_capacity = %d)",
group->sgc->capacity);
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)
{
atomic_inc(&init_mm.mm_count);
enter_lazy_tlb(&init_mm, current);
+ /*
+ * During early bootup we pretend to be a normal task:
+ */
+ current->sched_class = &fair_sched_class;
+
/*
* Make us the idle thread. Technically, schedule() should not be
* called from this thread, however somewhere below it might be,
calc_load_update = jiffies + LOAD_FREQ;
- /*
- * During early bootup we pretend to be a normal task:
- */
- current->sched_class = &fair_sched_class;
-
#ifdef CONFIG_SMP
zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
/* May be allocated at isolcpus cmdline parse time */
in_atomic(), irqs_disabled(),
current->pid, current->comm);
+ if (task_stack_end_corrupted(current))
+ printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
+
debug_show_held_locks(current);
if (irqs_disabled())
print_irqtrace_events(current);
{
struct task_struct *g, *p;
+ /*
+ * Autogroups do not have RT tasks; see autogroup_create().
+ */
+ if (task_group_is_autogroup(tg))
+ return 0;
+
for_each_process_thread(g, p) {
if (rt_task(p) && task_group(p) == tg)
return 1;
{
int i, err = 0;
+ /*
+ * Disallowing the root group RT runtime is BAD, it would disallow the
+ * kernel creating (and or operating) RT threads.
+ */
+ if (tg == &root_task_group && rt_runtime == 0)
+ return -EINVAL;
+
+ /* No period doesn't make any sense. */
+ if (rt_period == 0)
+ return -EINVAL;
+
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
err = __rt_schedulable(tg, rt_period, rt_runtime);
rt_period = (u64)rt_period_us * NSEC_PER_USEC;
rt_runtime = tg->rt_bandwidth.rt_runtime;
- if (rt_period == 0)
- return -EINVAL;
-
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}