#include <asm/unistd.h>
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+ return (unsigned long long)jiffies * (1000000000 / HZ);
+}
+
/*
* Convert user-nice values [ -20 ... 0 ... 19 ]
* to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
struct mm_struct *mm = next->mm;
struct mm_struct *oldmm = prev->active_mm;
+ /*
+ * For paravirt, this is coupled with an exit in switch_to to
+ * combine the page table reload and the switch backend into
+ * one hypercall.
+ */
+ arch_enter_lazy_cpu_mode();
+
if (!mm) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
static void update_load(struct rq *this_rq)
{
unsigned long this_load;
- int i, scale;
+ unsigned int i, scale;
this_load = this_rq->raw_weighted_load;
/* Update our load: */
- for (i = 0, scale = 1; i < 3; i++, scale <<= 1) {
+ for (i = 0, scale = 1; i < 3; i++, scale += scale) {
unsigned long old_load, new_load;
+ /* scale is effectively 1 << i now, and >> i divides by scale */
+
old_load = this_rq->cpu_load[i];
new_load = this_load;
/*
*/
if (new_load > old_load)
new_load += scale-1;
- this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale;
+ this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
}
}
}
#endif
-static inline void wake_priority_sleeper(struct rq *rq)
-{
-#ifdef CONFIG_SCHED_SMT
- if (!rq->nr_running)
- return;
-
- spin_lock(&rq->lock);
- /*
- * If an SMT sibling task has been put to sleep for priority
- * reasons reschedule the idle task to see if it can now run.
- */
- if (rq->nr_running)
- resched_task(rq->idle);
- spin_unlock(&rq->lock);
-#endif
-}
-
DEFINE_PER_CPU(struct kernel_stat, kstat);
EXPORT_PER_CPU_SYMBOL(kstat);
update_cpu_clock(p, rq, now);
- if (p == rq->idle)
- /* Task on the idle queue */
- wake_priority_sleeper(rq);
- else
+ if (p != rq->idle)
task_running_tick(rq, p);
#ifdef CONFIG_SMP
update_load(rq);
#endif
}
-#ifdef CONFIG_SCHED_SMT
-static inline void wakeup_busy_runqueue(struct rq *rq)
-{
- /* If an SMT runqueue is sleeping due to priority reasons wake it up */
- if (rq->curr == rq->idle && rq->nr_running)
- resched_task(rq->idle);
-}
-
-/*
- * Called with interrupt disabled and this_rq's runqueue locked.
- */
-static void wake_sleeping_dependent(int this_cpu)
-{
- struct sched_domain *tmp, *sd = NULL;
- int i;
-
- for_each_domain(this_cpu, tmp) {
- if (tmp->flags & SD_SHARE_CPUPOWER) {
- sd = tmp;
- break;
- }
- }
-
- if (!sd)
- return;
-
- for_each_cpu_mask(i, sd->span) {
- struct rq *smt_rq = cpu_rq(i);
-
- if (i == this_cpu)
- continue;
- if (unlikely(!spin_trylock(&smt_rq->lock)))
- continue;
-
- wakeup_busy_runqueue(smt_rq);
- spin_unlock(&smt_rq->lock);
- }
-}
-
-/*
- * number of 'lost' timeslices this task wont be able to fully
- * utilize, if another task runs on a sibling. This models the
- * slowdown effect of other tasks running on siblings:
- */
-static inline unsigned long
-smt_slice(struct task_struct *p, struct sched_domain *sd)
-{
- return p->time_slice * (100 - sd->per_cpu_gain) / 100;
-}
-
-/*
- * To minimise lock contention and not have to drop this_rq's runlock we only
- * trylock the sibling runqueues and bypass those runqueues if we fail to
- * acquire their lock. As we only trylock the normal locking order does not
- * need to be obeyed.
- */
-static int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
-{
- struct sched_domain *tmp, *sd = NULL;
- int ret = 0, i;
-
- /* kernel/rt threads do not participate in dependent sleeping */
- if (!p->mm || rt_task(p))
- return 0;
-
- for_each_domain(this_cpu, tmp) {
- if (tmp->flags & SD_SHARE_CPUPOWER) {
- sd = tmp;
- break;
- }
- }
-
- if (!sd)
- return 0;
-
- for_each_cpu_mask(i, sd->span) {
- struct task_struct *smt_curr;
- struct rq *smt_rq;
-
- if (i == this_cpu)
- continue;
-
- smt_rq = cpu_rq(i);
- if (unlikely(!spin_trylock(&smt_rq->lock)))
- continue;
-
- smt_curr = smt_rq->curr;
-
- if (!smt_curr->mm)
- goto unlock;
-
- /*
- * If a user task with lower static priority than the
- * running task on the SMT sibling is trying to schedule,
- * delay it till there is proportionately less timeslice
- * left of the sibling task to prevent a lower priority
- * task from using an unfair proportion of the
- * physical cpu's resources. -ck
- */
- if (rt_task(smt_curr)) {
- /*
- * With real time tasks we run non-rt tasks only
- * per_cpu_gain% of the time.
- */
- if ((jiffies % DEF_TIMESLICE) >
- (sd->per_cpu_gain * DEF_TIMESLICE / 100))
- ret = 1;
- } else {
- if (smt_curr->static_prio < p->static_prio &&
- !TASK_PREEMPTS_CURR(p, smt_rq) &&
- smt_slice(smt_curr, sd) > task_timeslice(p))
- ret = 1;
- }
-unlock:
- spin_unlock(&smt_rq->lock);
- }
- return ret;
-}
-#else
-static inline void wake_sleeping_dependent(int this_cpu)
-{
-}
-static inline int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
-{
- return 0;
-}
-#endif
-
#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
void fastcall add_preempt_count(int val)
if (!rq->nr_running) {
next = rq->idle;
rq->expired_timestamp = 0;
- wake_sleeping_dependent(cpu);
goto switch_tasks;
}
}
}
}
next->sleep_type = SLEEP_NORMAL;
- if (dependent_sleeper(cpu, rq, next))
- next = rq->idle;
switch_tasks:
if (next == rq->idle)
schedstat_inc(rq, sched_goidle);
sched_info_switch(prev, next);
if (likely(prev != next)) {
- next->timestamp = now;
+ next->timestamp = next->last_ran = now;
rq->nr_switches++;
rq->curr = next;
++*switch_count;
}
/**
- * sched_setscheduler - change the scheduling policy and/or RT priority of
- * a thread.
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
* @p: the task in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
*
- * NOTE: the task may be already dead
+ * NOTE that the task may be already dead.
*/
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
/**
* sys_sched_yield - yield the current processor to other threads.
*
- * this function yields the current CPU by moving the calling thread
+ * This function yields the current CPU by moving the calling thread
* to the expired array. If there are no other threads running on this
* CPU then this function will return.
*/
return 0;
}
-static inline int __resched_legal(int expected_preempt_count)
-{
-#ifdef CONFIG_PREEMPT
- if (unlikely(preempt_count() != expected_preempt_count))
- return 0;
-#endif
- if (unlikely(system_state != SYSTEM_RUNNING))
- return 0;
- return 1;
-}
-
static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
int __sched cond_resched(void)
{
- if (need_resched() && __resched_legal(0)) {
+ if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
+ system_state == SYSTEM_RUNNING) {
__cond_resched();
return 1;
}
ret = 1;
spin_lock(lock);
}
- if (need_resched() && __resched_legal(1)) {
+ if (need_resched() && system_state == SYSTEM_RUNNING) {
spin_release(&lock->dep_map, 1, _THIS_IP_);
_raw_spin_unlock(lock);
preempt_enable_no_resched();
{
BUG_ON(!in_softirq());
- if (need_resched() && __resched_legal(0)) {
+ if (need_resched() && system_state == SYSTEM_RUNNING) {
raw_local_irq_disable();
_local_bh_enable();
raw_local_irq_enable();
/**
* yield - yield the current processor to other threads.
*
- * this is a shortcut for kernel-space yielding - it marks the
+ * This is a shortcut for kernel-space yielding - it marks the
* thread runnable and calls sys_sched_yield().
*/
void __sched yield(void)
return retval;
}
-static inline struct task_struct *eldest_child(struct task_struct *p)
-{
- if (list_empty(&p->children))
- return NULL;
- return list_entry(p->children.next,struct task_struct,sibling);
-}
-
-static inline struct task_struct *older_sibling(struct task_struct *p)
-{
- if (p->sibling.prev==&p->parent->children)
- return NULL;
- return list_entry(p->sibling.prev,struct task_struct,sibling);
-}
-
-static inline struct task_struct *younger_sibling(struct task_struct *p)
-{
- if (p->sibling.next==&p->parent->children)
- return NULL;
- return list_entry(p->sibling.next,struct task_struct,sibling);
-}
-
static const char stat_nam[] = "RSDTtZX";
static void show_task(struct task_struct *p)
{
- struct task_struct *relative;
unsigned long free = 0;
unsigned state;
free = (unsigned long)n - (unsigned long)end_of_stack(p);
}
#endif
- printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
- if ((relative = eldest_child(p)))
- printk("%5d ", relative->pid);
- else
- printk(" ");
- if ((relative = younger_sibling(p)))
- printk("%7d", relative->pid);
- else
- printk(" ");
- if ((relative = older_sibling(p)))
- printk(" %5d", relative->pid);
- else
- printk(" ");
+ printk("%5lu %5d %6d", free, p->pid, p->parent->pid);
if (!p->mm)
printk(" (L-TLB)\n");
else
lock_cpu_hotplug();
arch_init_sched_domains(&cpu_online_map);
- cpus_andnot(non_isolated_cpus, cpu_online_map, cpu_isolated_map);
+ cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
if (cpus_empty(non_isolated_cpus))
cpu_set(smp_processor_id(), non_isolated_cpus);
unlock_cpu_hotplug();