raw_spin_unlock_irqrestore(&rq->lock, flags);
}
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* In the semi idle case, use the nearest busy cpu for migrating timers
* from an idle cpu. This is good for power-savings.
* account when the CPU goes back to idle and evaluates the timer
* wheel for the next timer event.
*/
-void wake_up_idle_cpu(int cpu)
+static void wake_up_idle_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
smp_send_reschedule(cpu);
}
+static bool wake_up_full_nohz_cpu(int cpu)
+{
+ if (tick_nohz_full_cpu(cpu)) {
+ if (cpu != smp_processor_id() ||
+ tick_nohz_tick_stopped())
+ smp_send_reschedule(cpu);
+ return true;
+ }
+
+ return false;
+}
+
+void wake_up_nohz_cpu(int cpu)
+{
+ if (!wake_up_full_nohz_cpu(cpu))
+ wake_up_idle_cpu(cpu);
+}
+
static inline bool got_nohz_idle_kick(void)
{
int cpu = smp_processor_id();
return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
}
-#else /* CONFIG_NO_HZ */
+#else /* CONFIG_NO_HZ_COMMON */
static inline bool got_nohz_idle_kick(void)
{
return false;
}
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
+
+#ifdef CONFIG_NO_HZ_FULL
+bool sched_can_stop_tick(void)
+{
+ struct rq *rq;
+
+ rq = this_rq();
+
+ /* Make sure rq->nr_running update is visible after the IPI */
+ smp_rmb();
+
+ /* More than one running task need preemption */
+ if (rq->nr_running > 1)
+ return false;
+
+ return true;
+}
+#endif /* CONFIG_NO_HZ_FULL */
void sched_avg_update(struct rq *rq)
{
*/
static int select_fallback_rq(int cpu, struct task_struct *p)
{
- const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
+ int nid = cpu_to_node(cpu);
+ const struct cpumask *nodemask = NULL;
enum { cpuset, possible, fail } state = cpuset;
int dest_cpu;
- /* Look for allowed, online CPU in same node. */
- for_each_cpu(dest_cpu, nodemask) {
- if (!cpu_online(dest_cpu))
- continue;
- if (!cpu_active(dest_cpu))
- continue;
- if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
- return dest_cpu;
+ /*
+ * If the node that the cpu is on has been offlined, cpu_to_node()
+ * will return -1. There is no cpu on the node, and we should
+ * select the cpu on the other node.
+ */
+ if (nid != -1) {
+ nodemask = cpumask_of_node(nid);
+
+ /* Look for allowed, online CPU in same node. */
+ for_each_cpu(dest_cpu, nodemask) {
+ if (!cpu_online(dest_cpu))
+ continue;
+ if (!cpu_active(dest_cpu))
+ continue;
+ if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p)))
+ return dest_cpu;
+ }
}
for (;;) {
static void
ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
- trace_sched_wakeup(p, true);
check_preempt_curr(rq, p, wake_flags);
+ trace_sched_wakeup(p, true);
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
void scheduler_ipi(void)
{
- if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
+ if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()
+ && !tick_nohz_full_cpu(smp_processor_id()))
return;
/*
* somewhat pessimize the simple resched case.
*/
irq_enter();
+ tick_nohz_full_check();
sched_ttwu_pending();
/*
static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
struct preempt_notifier *notifier;
- struct hlist_node *node;
- hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
notifier->ops->sched_in(notifier, raw_smp_processor_id());
}
struct task_struct *next)
{
struct preempt_notifier *notifier;
- struct hlist_node *node;
- hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
notifier->ops->sched_out(notifier, next);
}
kprobe_flush_task(prev);
put_task_struct(prev);
}
+
+ tick_nohz_task_switch(current);
}
#ifdef CONFIG_SMP
}
/*
- * nr_running, nr_uninterruptible and nr_context_switches:
+ * nr_running and nr_context_switches:
*
* externally visible scheduler statistics: current number of runnable
- * threads, current number of uninterruptible-sleeping threads, total
- * number of context switches performed since bootup.
+ * threads, total number of context switches performed since bootup.
*/
unsigned long nr_running(void)
{
return sum;
}
-unsigned long nr_uninterruptible(void)
-{
- unsigned long i, sum = 0;
-
- for_each_possible_cpu(i)
- sum += cpu_rq(i)->nr_uninterruptible;
-
- /*
- * Since we read the counters lockless, it might be slightly
- * inaccurate. Do not allow it to go below zero though:
- */
- if (unlikely((long)sum < 0))
- sum = 0;
-
- return sum;
-}
-
unsigned long long nr_context_switches(void)
{
int i;
return load >> FSHIFT;
}
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* Handle NO_HZ for the global load-average.
*
smp_wmb();
calc_load_idx++;
}
-#else /* !CONFIG_NO_HZ */
+#else /* !CONFIG_NO_HZ_COMMON */
static inline long calc_load_fold_idle(void) { return 0; }
static inline void calc_global_nohz(void) { }
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
/*
* calc_load - update the avenrun load estimates 10 ticks after the
sched_avg_update(this_rq);
}
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* There is no sane way to deal with nohz on smp when using jiffies because the
* cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
}
raw_spin_unlock(&this_rq->lock);
}
-#endif /* CONFIG_NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from scheduler_tick()
if (irqs_disabled())
print_irqtrace_events(prev);
dump_stack();
- add_taint(TAINT_WARN);
+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
}
/*
asmlinkage void __sched preempt_schedule_irq(void)
{
struct thread_info *ti = current_thread_info();
+ enum ctx_state prev_state;
/* Catch callers which need to be fixed */
BUG_ON(ti->preempt_count || !irqs_disabled());
- user_exit();
+ prev_state = exception_enter();
+
do {
add_preempt_count(PREEMPT_ACTIVE);
local_irq_enable();
*/
barrier();
} while (need_resched());
+
+ exception_exit(prev_state);
}
#endif /* CONFIG_PREEMPT */
EXPORT_SYMBOL(complete_all);
static inline long __sched
-do_wait_for_common(struct completion *x, long timeout, int state)
+do_wait_for_common(struct completion *x,
+ long (*action)(long), long timeout, int state)
{
if (!x->done) {
DECLARE_WAITQUEUE(wait, current);
}
__set_current_state(state);
spin_unlock_irq(&x->wait.lock);
- timeout = schedule_timeout(timeout);
+ timeout = action(timeout);
spin_lock_irq(&x->wait.lock);
} while (!x->done && timeout);
__remove_wait_queue(&x->wait, &wait);
return timeout ?: 1;
}
-static long __sched
-wait_for_common(struct completion *x, long timeout, int state)
+static inline long __sched
+__wait_for_common(struct completion *x,
+ long (*action)(long), long timeout, int state)
{
might_sleep();
spin_lock_irq(&x->wait.lock);
- timeout = do_wait_for_common(x, timeout, state);
+ timeout = do_wait_for_common(x, action, timeout, state);
spin_unlock_irq(&x->wait.lock);
return timeout;
}
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+ return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+ return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
/**
* wait_for_completion: - waits for completion of a task
* @x: holds the state of this particular completion
}
EXPORT_SYMBOL(wait_for_completion_timeout);
+/**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x: holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+ wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x: holds the state of this particular completion
+ * @timeout: timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+ return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
/**
* wait_for_completion_interruptible: - waits for completion of a task (w/intr)
* @x: holds the state of this particular completion
* It's the caller's job to ensure that the target task struct
* can't go away on us before we can do any checks.
*
- * Returns true if we indeed boosted the target task.
+ * Returns:
+ * true (>0) if we indeed boosted the target task.
+ * false (0) if we failed to boost the target.
+ * -ESRCH if there's no task to yield to.
*/
bool __sched yield_to(struct task_struct *p, bool preempt)
{
again:
p_rq = task_rq(p);
+ /*
+ * If we're the only runnable task on the rq and target rq also
+ * has only one task, there's absolutely no point in yielding.
+ */
+ if (rq->nr_running == 1 && p_rq->nr_running == 1) {
+ yielded = -ESRCH;
+ goto out_irq;
+ }
+
double_rq_lock(rq, p_rq);
while (task_rq(p) != p_rq) {
double_rq_unlock(rq, p_rq);
}
if (!curr->sched_class->yield_to_task)
- goto out;
+ goto out_unlock;
if (curr->sched_class != p->sched_class)
- goto out;
+ goto out_unlock;
if (task_running(p_rq, p) || p->state)
- goto out;
+ goto out_unlock;
yielded = curr->sched_class->yield_to_task(rq, p, preempt);
if (yielded) {
resched_task(p_rq->curr);
}
-out:
+out_unlock:
double_rq_unlock(rq, p_rq);
+out_irq:
local_irq_restore(flags);
- if (yielded)
+ if (yielded > 0)
schedule();
return yielded;
}
#ifdef CONFIG_CGROUP_SCHED
+/*
+ * Default task group.
+ * Every task in system belongs to this group at bootup.
+ */
struct task_group root_task_group;
LIST_HEAD(task_groups);
#endif
INIT_LIST_HEAD(&rq->cfs_tasks);
rq_attach_root(rq, &def_root_domain);
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
rq->nohz_flags = 0;
#endif
#endif
return err;
}
-int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
+static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
u64 rt_runtime, rt_period;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}
-long sched_group_rt_runtime(struct task_group *tg)
+static long sched_group_rt_runtime(struct task_group *tg)
{
u64 rt_runtime_us;
return rt_runtime_us;
}
-int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
+static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
{
u64 rt_runtime, rt_period;
return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
}
-long sched_group_rt_period(struct task_group *tg)
+static long sched_group_rt_period(struct task_group *tg)
{
u64 rt_period_us;
return ret;
}
-int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
{
/* Don't accept realtime tasks when there is no way for them to run */
if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)