#include <asm/irq_regs.h>
#include "sched_cpupri.h"
+#include "workqueue_sched.h"
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
*/
struct task_group init_task_group;
-/* return group to which a task belongs */
-static inline struct task_group *task_group(struct task_struct *p)
-{
- struct task_group *tg;
-
-#ifdef CONFIG_CGROUP_SCHED
- tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
- struct task_group, css);
-#else
- tg = &init_task_group;
-#endif
- return tg;
-}
-
-/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
-{
- /*
- * Strictly speaking this rcu_read_lock() is not needed since the
- * task_group is tied to the cgroup, which in turn can never go away
- * as long as there are tasks attached to it.
- *
- * However since task_group() uses task_subsys_state() which is an
- * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
- */
- rcu_read_lock();
-#ifdef CONFIG_FAIR_GROUP_SCHED
- p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
- p->se.parent = task_group(p)->se[cpu];
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
- p->rt.rt_rq = task_group(p)->rt_rq[cpu];
- p->rt.parent = task_group(p)->rt_se[cpu];
-#endif
- rcu_read_unlock();
-}
-
-#else
-
-static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
-static inline struct task_group *task_group(struct task_struct *p)
-{
- return NULL;
-}
-
#endif /* CONFIG_CGROUP_SCHED */
/* CFS-related fields in a runqueue */
struct root_domain *rd;
struct sched_domain *sd;
+ unsigned long cpu_power;
+
unsigned char idle_at_tick;
/* For active balancing */
int post_schedule;
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
#define raw_rq() (&__raw_get_cpu_var(runqueues))
+#ifdef CONFIG_CGROUP_SCHED
+
+/*
+ * Return the group to which this tasks belongs.
+ *
+ * We use task_subsys_state_check() and extend the RCU verification
+ * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach()
+ * holds that lock for each task it moves into the cgroup. Therefore
+ * by holding that lock, we pin the task to the current cgroup.
+ */
+static inline struct task_group *task_group(struct task_struct *p)
+{
+ struct cgroup_subsys_state *css;
+
+ css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
+ lockdep_is_held(&task_rq(p)->lock));
+ return container_of(css, struct task_group, css);
+}
+
+/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+ p->se.parent = task_group(p)->se[cpu];
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+ p->rt.rt_rq = task_group(p)->rt_rq[cpu];
+ p->rt.parent = task_group(p)->rt_se[cpu];
+#endif
+}
+
+#else /* CONFIG_CGROUP_SCHED */
+
+static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
+static inline struct task_group *task_group(struct task_struct *p)
+{
+ return NULL;
+}
+
+#endif /* CONFIG_CGROUP_SCHED */
+
inline void update_rq_clock(struct rq *rq)
{
if (!rq->skip_clock_update)
return max(rq->cpu_load[type-1], total);
}
-static struct sched_group *group_of(int cpu)
-{
- struct sched_domain *sd = rcu_dereference_sched(cpu_rq(cpu)->sd);
-
- if (!sd)
- return NULL;
-
- return sd->groups;
-}
-
static unsigned long power_of(int cpu)
{
- struct sched_group *group = group_of(cpu);
-
- if (!group)
- return SCHED_LOAD_SCALE;
-
- return group->cpu_power;
+ return cpu_rq(cpu)->cpu_power;
}
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
if (root_task_group_empty())
return;
- now = cpu_clock(raw_smp_processor_id());
+ now = local_clock();
elapsed = now - sd->last_update;
if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
static void set_load_weight(struct task_struct *p)
{
if (task_has_rt_policy(p)) {
- p->se.load.weight = prio_to_weight[0] * 2;
- p->se.load.inv_weight = prio_to_wmult[0] >> 1;
+ p->se.load.weight = 0;
+ p->se.load.inv_weight = WMULT_CONST;
return;
}
}
#endif
-/***
+static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
+ bool is_sync, bool is_migrate, bool is_local,
+ unsigned long en_flags)
+{
+ schedstat_inc(p, se.statistics.nr_wakeups);
+ if (is_sync)
+ schedstat_inc(p, se.statistics.nr_wakeups_sync);
+ if (is_migrate)
+ schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+ if (is_local)
+ schedstat_inc(p, se.statistics.nr_wakeups_local);
+ else
+ schedstat_inc(p, se.statistics.nr_wakeups_remote);
+
+ activate_task(rq, p, en_flags);
+}
+
+static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
+ int wake_flags, bool success)
+{
+ trace_sched_wakeup(p, success);
+ check_preempt_curr(rq, p, wake_flags);
+
+ p->state = TASK_RUNNING;
+#ifdef CONFIG_SMP
+ if (p->sched_class->task_woken)
+ p->sched_class->task_woken(rq, p);
+
+ if (unlikely(rq->idle_stamp)) {
+ u64 delta = rq->clock - rq->idle_stamp;
+ u64 max = 2*sysctl_sched_migration_cost;
+
+ if (delta > max)
+ rq->avg_idle = max;
+ else
+ update_avg(&rq->avg_idle, delta);
+ rq->idle_stamp = 0;
+ }
+#endif
+ /* if a worker is waking up, notify workqueue */
+ if ((p->flags & PF_WQ_WORKER) && success)
+ wq_worker_waking_up(p, cpu_of(rq));
+}
+
+/**
* try_to_wake_up - wake up a thread
- * @p: the to-be-woken-up thread
+ * @p: the thread to be awakened
* @state: the mask of task states that can be woken
- * @sync: do a synchronous wakeup?
+ * @wake_flags: wake modifier flags (WF_*)
*
* Put it on the run-queue if it's not already there. The "current"
* thread is always on the run-queue (except when the actual
* the simpler "current->state = TASK_RUNNING" to mark yourself
* runnable without the overhead of this.
*
- * returns failure only if the task is already active.
+ * Returns %true if @p was woken up, %false if it was already running
+ * or @state didn't match @p's state.
*/
static int try_to_wake_up(struct task_struct *p, unsigned int state,
int wake_flags)
out_activate:
#endif /* CONFIG_SMP */
- schedstat_inc(p, se.statistics.nr_wakeups);
- if (wake_flags & WF_SYNC)
- schedstat_inc(p, se.statistics.nr_wakeups_sync);
- if (orig_cpu != cpu)
- schedstat_inc(p, se.statistics.nr_wakeups_migrate);
- if (cpu == this_cpu)
- schedstat_inc(p, se.statistics.nr_wakeups_local);
- else
- schedstat_inc(p, se.statistics.nr_wakeups_remote);
- activate_task(rq, p, en_flags);
+ ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
+ cpu == this_cpu, en_flags);
success = 1;
-
out_running:
- trace_sched_wakeup(p, success);
- check_preempt_curr(rq, p, wake_flags);
-
- p->state = TASK_RUNNING;
-#ifdef CONFIG_SMP
- if (p->sched_class->task_woken)
- p->sched_class->task_woken(rq, p);
-
- if (unlikely(rq->idle_stamp)) {
- u64 delta = rq->clock - rq->idle_stamp;
- u64 max = 2*sysctl_sched_migration_cost;
-
- if (delta > max)
- rq->avg_idle = max;
- else
- update_avg(&rq->avg_idle, delta);
- rq->idle_stamp = 0;
- }
-#endif
+ ttwu_post_activation(p, rq, wake_flags, success);
out:
task_rq_unlock(rq, &flags);
put_cpu();
return success;
}
+/**
+ * try_to_wake_up_local - try to wake up a local task with rq lock held
+ * @p: the thread to be awakened
+ *
+ * Put @p on the run-queue if it's not alredy there. The caller must
+ * ensure that this_rq() is locked, @p is bound to this_rq() and not
+ * the current task. this_rq() stays locked over invocation.
+ */
+static void try_to_wake_up_local(struct task_struct *p)
+{
+ struct rq *rq = task_rq(p);
+ bool success = false;
+
+ BUG_ON(rq != this_rq());
+ BUG_ON(p == current);
+ lockdep_assert_held(&rq->lock);
+
+ if (!(p->state & TASK_NORMAL))
+ return;
+
+ if (!p->se.on_rq) {
+ if (likely(!task_running(rq, p))) {
+ schedstat_inc(rq, ttwu_count);
+ schedstat_inc(rq, ttwu_local);
+ }
+ ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
+ success = true;
+ }
+ ttwu_post_activation(p, rq, 0, success);
+}
+
/**
* wake_up_process - Wake up a specific process
* @p: The process to be woken up.
rq = cpu_rq(cpu);
rcu_note_context_switch(cpu);
prev = rq->curr;
- switch_count = &prev->nivcsw;
release_kernel_lock(prev);
need_resched_nonpreemptible:
raw_spin_lock_irq(&rq->lock);
clear_tsk_need_resched(prev);
+ switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
- if (unlikely(signal_pending_state(prev->state, prev)))
+ if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
- else
+ } else {
+ /*
+ * If a worker is going to sleep, notify and
+ * ask workqueue whether it wants to wake up a
+ * task to maintain concurrency. If so, wake
+ * up the task.
+ */
+ if (prev->flags & PF_WQ_WORKER) {
+ struct task_struct *to_wakeup;
+
+ to_wakeup = wq_worker_sleeping(prev, cpu);
+ if (to_wakeup)
+ try_to_wake_up_local(to_wakeup);
+ }
deactivate_task(rq, prev, DEQUEUE_SLEEP);
+ }
switch_count = &prev->nvcsw;
}
context_switch(rq, prev, next); /* unlocks the rq */
/*
- * the context switch might have flipped the stack from under
- * us, hence refresh the local variables.
+ * The context switch have flipped the stack from under us
+ * and restored the local variables which were saved when
+ * this task called schedule() in the past. prev == current
+ * is still correct, but it can be moved to another cpu/rq.
*/
cpu = smp_processor_id();
rq = cpu_rq(cpu);
post_schedule(rq);
- if (unlikely(reacquire_kernel_lock(current) < 0)) {
- prev = rq->curr;
- switch_count = &prev->nivcsw;
+ if (unlikely(reacquire_kernel_lock(prev)))
goto need_resched_nonpreemptible;
- }
preempt_enable_no_resched();
if (need_resched())
}
EXPORT_SYMBOL(wait_for_completion_killable);
+/**
+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
+ * @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. It can be
+ * interrupted by a kill signal. The timeout is in jiffies.
+ */
+unsigned long __sched
+wait_for_completion_killable_timeout(struct completion *x,
+ unsigned long timeout)
+{
+ return wait_for_common(x, timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(wait_for_completion_killable_timeout);
+
/**
* try_wait_for_completion - try to decrement a completion without blocking
* @x: completion structure
}
if (user) {
-#ifdef CONFIG_RT_GROUP_SCHED
- /*
- * Do not allow realtime tasks into groups that have no runtime
- * assigned.
- */
- if (rt_bandwidth_enabled() && rt_policy(policy) &&
- task_group(p)->rt_bandwidth.rt_runtime == 0)
- return -EPERM;
-#endif
-
retval = security_task_setscheduler(p, policy, param);
if (retval)
return retval;
* runqueue lock must be held.
*/
rq = __task_rq_lock(p);
+
+#ifdef CONFIG_RT_GROUP_SCHED
+ if (user) {
+ /*
+ * Do not allow realtime tasks into groups that have no runtime
+ * assigned.
+ */
+ if (rt_bandwidth_enabled() && rt_policy(policy) &&
+ task_group(p)->rt_bandwidth.rt_runtime == 0) {
+ __task_rq_unlock(rq);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ return -EPERM;
+ }
+ }
+#endif
+
/* recheck policy now with rq lock held */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
*/
static struct notifier_block __cpuinitdata migration_notifier = {
.notifier_call = migration_call,
- .priority = 10
+ .priority = CPU_PRI_MIGRATION,
};
+static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_ONLINE:
+ case CPU_DOWN_FAILED:
+ set_cpu_active((long)hcpu, true);
+ return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
+ }
+}
+
+static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_PREPARE:
+ set_cpu_active((long)hcpu, false);
+ return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
+ }
+}
+
static int __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
- /* Start one for the boot CPU: */
+ /* Initialize migration for the boot CPU */
err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
+ /* Register cpu active notifiers */
+ cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
+ cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
+
return 0;
}
early_initcall(migration_init);
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-#ifndef CONFIG_CPUSETS
/*
- * Add online and remove offline CPUs from the scheduler domains.
- * When cpusets are enabled they take over this function.
+ * Update cpusets according to cpu_active mask. If cpusets are
+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
+ * around partition_sched_domains().
*/
-static int update_sched_domains(struct notifier_block *nfb,
- unsigned long action, void *hcpu)
+static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
{
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- partition_sched_domains(1, NULL, NULL);
+ cpuset_update_active_cpus();
return NOTIFY_OK;
+ default:
+ return NOTIFY_DONE;
+ }
+}
+static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_PREPARE:
+ cpuset_update_active_cpus();
+ return NOTIFY_OK;
default:
return NOTIFY_DONE;
}
}
-#endif
static int update_runtime(struct notifier_block *nfb,
unsigned long action, void *hcpu)
mutex_unlock(&sched_domains_mutex);
put_online_cpus();
-#ifndef CONFIG_CPUSETS
- /* XXX: Theoretical race here - CPU may be hotplugged now */
- hotcpu_notifier(update_sched_domains, 0);
-#endif
+ hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
+ hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
/* RT runtime code needs to handle some hotplug events */
hotcpu_notifier(update_runtime, 0);
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
+ rq->cpu_power = SCHED_LOAD_SCALE;
rq->post_schedule = 0;
rq->active_balance = 0;
rq->next_balance = jiffies;