struct rt_bandwidth {
/* nests inside the rq lock: */
- spinlock_t rt_runtime_lock;
+ raw_spinlock_t rt_runtime_lock;
ktime_t rt_period;
u64 rt_runtime;
struct hrtimer rt_period_timer;
rt_b->rt_period = ns_to_ktime(period);
rt_b->rt_runtime = runtime;
- spin_lock_init(&rt_b->rt_runtime_lock);
+ raw_spin_lock_init(&rt_b->rt_runtime_lock);
hrtimer_init(&rt_b->rt_period_timer,
CLOCK_MONOTONIC, HRTIMER_MODE_REL);
if (hrtimer_active(&rt_b->rt_period_timer))
return;
- spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
for (;;) {
unsigned long delta;
ktime_t soft, hard;
__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
HRTIMER_MODE_ABS_PINNED, 0);
}
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
#ifdef CONFIG_RT_GROUP_SCHED
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
}
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else /* !CONFIG_USER_SCHED */
u64 rt_time;
u64 rt_runtime;
/* Nests inside the rq lock: */
- spinlock_t rt_runtime_lock;
+ raw_spinlock_t rt_runtime_lock;
#ifdef CONFIG_RT_GROUP_SCHED
unsigned long rt_nr_boosted;
*/
struct rq {
/* runqueue lock: */
- spinlock_t lock;
+ raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
- unsigned long last_tick_seen;
unsigned char in_nohz_recently;
#endif
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
- u64 nr_migrations_in;
struct cfs_rq cfs;
struct rt_rq rt;
u64 rt_avg;
u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
/**
* runqueue_is_locked
+ * @cpu: the processor in question.
*
* Returns true if the current cpu runqueue is locked.
* This interface allows printk to be called with the runqueue lock
*/
int runqueue_is_locked(int cpu)
{
- return spin_is_locked(&cpu_rq(cpu)->lock);
+ return raw_spin_is_locked(&cpu_rq(cpu)->lock);
}
/*
if (!sched_feat_names[i])
return -EINVAL;
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
return single_open(filp, sched_feat_show, NULL);
}
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
.open = sched_feat_open,
.write = sched_feat_write,
.read = seq_read,
* default: 0.25ms
*/
unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
/*
* Inject some fuzzyness into changing the per-cpu group shares
*/
spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
next->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
#else
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
#endif
}
{
for (;;) {
struct rq *rq = task_rq(p);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p)))
return rq;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
}
for (;;) {
local_irq_save(*flags);
rq = task_rq(p);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (likely(rq == task_rq(p)))
return rq;
- spin_unlock_irqrestore(&rq->lock, *flags);
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
}
}
struct rq *rq = task_rq(p);
smp_mb(); /* spin-unlock-wait is not a full memory barrier */
- spin_unlock_wait(&rq->lock);
+ raw_spin_unlock_wait(&rq->lock);
}
static void __task_rq_unlock(struct rq *rq)
__releases(rq->lock)
{
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
__releases(rq->lock)
{
- spin_unlock_irqrestore(&rq->lock, *flags);
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
}
/*
local_irq_disable();
rq = this_rq();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
return rq;
}
WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
rq->curr->sched_class->task_tick(rq, rq->curr, 1);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
return HRTIMER_NORESTART;
}
{
struct rq *rq = arg;
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
hrtimer_restart(&rq->hrtick_timer);
rq->hrtick_csd_pending = 0;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
/*
{
int cpu;
- assert_spin_locked(&task_rq(p)->lock);
+ assert_raw_spin_locked(&task_rq(p)->lock);
if (test_tsk_need_resched(p))
return;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- if (!spin_trylock_irqsave(&rq->lock, flags))
+ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
return;
resched_task(cpu_curr(cpu));
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
#ifdef CONFIG_NO_HZ
#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
- assert_spin_locked(&task_rq(p)->lock);
+ assert_raw_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
-struct update_shares_data {
- unsigned long rq_weight[NR_CPUS];
-};
-
-static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+static __read_mostly unsigned long *update_shares_data;
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
static void update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long sd_shares,
unsigned long sd_rq_weight,
- struct update_shares_data *usd)
+ unsigned long *usd_rq_weight)
{
unsigned long shares, rq_weight;
int boost = 0;
- rq_weight = usd->rq_weight[cpu];
+ rq_weight = usd_rq_weight[cpu];
if (!rq_weight) {
boost = 1;
rq_weight = NICE_0_LOAD;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0, shares = 0;
- struct update_shares_data *usd;
+ unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
+ unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
unsigned long flags;
int i;
return 0;
local_irq_save(flags);
- usd = &__get_cpu_var(update_shares_data);
+ usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
for_each_cpu(i, sched_domain_span(sd)) {
weight = tg->cfs_rq[i]->load.weight;
- usd->rq_weight[i] = weight;
+ usd_rq_weight[i] = weight;
+ rq_weight += weight;
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
if (!weight)
weight = NICE_0_LOAD;
- rq_weight += weight;
+ sum_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
+ if (!rq_weight)
+ rq_weight = sum_weight;
+
if ((!shares && rq_weight) || shares > tg->shares)
shares = tg->shares;
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
local_irq_restore(flags);
if (root_task_group_empty())
return;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
update_shares(sd);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
}
static void update_h_load(long cpu)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
double_rq_lock(this_rq, busiest);
return 1;
{
int ret = 0;
- if (unlikely(!spin_trylock(&busiest->lock))) {
+ if (unlikely(!raw_spin_trylock(&busiest->lock))) {
if (busiest < this_rq) {
- spin_unlock(&this_rq->lock);
- spin_lock(&busiest->lock);
- spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_unlock(&this_rq->lock);
+ raw_spin_lock(&busiest->lock);
+ raw_spin_lock_nested(&this_rq->lock,
+ SINGLE_DEPTH_NESTING);
ret = 1;
} else
- spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock_nested(&busiest->lock,
+ SINGLE_DEPTH_NESTING);
}
return ret;
}
{
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
BUG_ON(1);
}
static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
__releases(busiest->lock)
{
- spin_unlock(&busiest->lock);
+ raw_spin_unlock(&busiest->lock);
lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
#endif
#endif
static void calc_load_account_active(struct rq *this_rq);
+static void update_sysctl(void);
+static int get_update_sysctl_factor(void);
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+ set_task_rq(p, cpu);
+#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+ * successfuly executed on another CPU. We must ensure that updates of
+ * per-task data have been completed by this moment.
+ */
+ smp_wmb();
+ task_thread_info(p)->cpu = cpu;
+#endif
+}
#include "sched_stats.h"
#include "sched_idletask.c"
return cpu_curr(task_cpu(p)) == p;
}
-static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-{
- set_task_rq(p, cpu);
-#ifdef CONFIG_SMP
- /*
- * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
- * successfuly executed on another CPU. We must ensure that updates of
- * per-task data have been completed by this moment.
- */
- smp_wmb();
- task_thread_info(p)->cpu = cpu;
-#endif
-}
-
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
int oldprio, int running)
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ /* Must have done schedule() in kthread() before we set_task_cpu */
+ if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+ WARN_ON(1);
+ return;
+ }
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+ set_task_cpu(p, cpu);
+ p->cpus_allowed = cpumask_of_cpu(cpu);
+ p->rt.nr_cpus_allowed = 1;
+ p->flags |= PF_THREAD_BOUND;
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
/*
* Buddy candidates are cache hot:
*/
- if (sched_feat(CACHE_HOT_BUDDY) &&
+ if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
int old_cpu = task_cpu(p);
- struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
struct cfs_rq *old_cfsrq = task_cfs_rq(p),
*new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
- u64 clock_offset;
-
- clock_offset = old_rq->clock - new_rq->clock;
trace_sched_migrate_task(p, new_cpu);
-#ifdef CONFIG_SCHEDSTATS
- if (p->se.wait_start)
- p->se.wait_start -= clock_offset;
- if (p->se.sleep_start)
- p->se.sleep_start -= clock_offset;
- if (p->se.block_start)
- p->se.block_start -= clock_offset;
-#endif
if (old_cpu != new_cpu) {
p->se.nr_migrations++;
- new_rq->nr_migrations_in++;
-#ifdef CONFIG_SCHEDSTATS
- if (task_hot(p, old_rq->clock, NULL))
- schedstat_inc(p, se.nr_forced2_migrations);
-#endif
perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
1, 1, NULL, 0);
}
* it is sufficient to simply update the task's cpu field.
*/
if (!p->se.on_rq && !task_running(rq, p)) {
+ update_rq_clock(rq);
set_task_cpu(p, dest_cpu);
return 0;
}
preempt_enable();
}
+#ifdef CONFIG_SMP
+static inline
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+{
+ return p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+}
+#endif
+
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
{
int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
- struct rq *rq;
+ struct rq *rq, *orig_rq;
if (!sched_feat(SYNC_WAKEUPS))
wake_flags &= ~WF_SYNC;
this_cpu = get_cpu();
smp_wmb();
- rq = task_rq_lock(p, &flags);
+ rq = orig_rq = task_rq_lock(p, &flags);
update_rq_clock(rq);
if (!(p->state & state))
goto out;
if (task_contributes_to_load(p))
rq->nr_uninterruptible--;
p->state = TASK_WAKING;
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
if (cpu != orig_cpu)
set_task_cpu(p, cpu);
- rq = task_rq_lock(p, &flags);
+ rq = __task_rq_lock(p);
+ update_rq_clock(rq);
+
WARN_ON(p->state != TASK_WAKING);
cpu = task_cpu(p);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
p->sched_class->task_wake_up(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
out:
task_rq_unlock(rq, &flags);
p->se.avg_overlap = 0;
p->se.start_runtime = 0;
p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
- p->se.avg_running = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
- p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
__sched_fork(p);
- /*
- * Make sure we do not leak PI boosting priority to the child.
- */
- p->prio = current->normal_prio;
-
/*
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
p->policy = SCHED_NORMAL;
-
- if (p->normal_prio < DEFAULT_PRIO)
- p->prio = DEFAULT_PRIO;
+ p->normal_prio = p->static_prio;
+ }
if (PRIO_TO_NICE(p->static_prio) < 0) {
p->static_prio = NICE_TO_PRIO(0);
+ p->normal_prio = p->static_prio;
set_load_weight(p);
}
p->sched_reset_on_fork = 0;
}
+ /*
+ * Make sure we do not leak PI boosting priority to the child.
+ */
+ p->prio = current->normal_prio;
+
if (!rt_prio(p->prio))
p->sched_class = &fair_sched_class;
+ if (p->sched_class->task_fork)
+ p->sched_class->task_fork(p);
+
#ifdef CONFIG_SMP
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
+ cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
#endif
set_task_cpu(p, cpu);
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
update_rq_clock(rq);
-
- p->prio = effective_prio(p);
-
- if (!p->sched_class->task_new || !current->se.on_rq) {
- activate_task(rq, p, 0);
- } else {
- /*
- * Let the scheduling class do new task startup
- * management (if any):
- */
- p->sched_class->task_new(rq, p);
- inc_nr_running(rq);
- }
+ activate_task(rq, p, 0);
trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
if (rq->post_schedule) {
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->curr->sched_class->post_schedule)
rq->curr->sched_class->post_schedule(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
rq->post_schedule = 0;
}
*/
arch_start_context_switch(prev);
- if (unlikely(!mm)) {
+ if (likely(!mm)) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
- if (unlikely(!prev->mm)) {
+ if (likely(!prev->mm)) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
}
}
-/*
- * Externally visible per-cpu scheduler statistics:
- * cpu_nr_migrations(cpu) - number of migrations into that cpu
- */
-u64 cpu_nr_migrations(int cpu)
-{
- return cpu_rq(cpu)->nr_migrations_in;
-}
-
/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC).
{
BUG_ON(!irqs_disabled());
if (rq1 == rq2) {
- spin_lock(&rq1->lock);
+ raw_spin_lock(&rq1->lock);
__acquire(rq2->lock); /* Fake it out ;) */
} else {
if (rq1 < rq2) {
- spin_lock(&rq1->lock);
- spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&rq1->lock);
+ raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
} else {
- spin_lock(&rq2->lock);
- spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+ raw_spin_lock(&rq2->lock);
+ raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
}
}
update_rq_clock(rq1);
__releases(rq1->lock)
__releases(rq2->lock)
{
- spin_unlock(&rq1->lock);
+ raw_spin_unlock(&rq1->lock);
if (rq1 != rq2)
- spin_unlock(&rq2->lock);
+ raw_spin_unlock(&rq2->lock);
else
__release(rq2->lock);
}
void sched_exec(void)
{
int new_cpu, this_cpu = get_cpu();
- new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
+ new_cpu = select_task_rq(current, SD_BALANCE_EXEC, 0);
put_cpu();
if (new_cpu != this_cpu)
sched_migrate_task(current, new_cpu);
deactivate_task(src_rq, p, 0);
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
- /*
- * Note that idle threads have a prio of MAX_PRIO, for this test
- * to be always true for them.
- */
check_preempt_curr(this_rq, p, 0);
}
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
* @group: sched_group whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
unsigned long flags;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
- spin_lock_irqsave(&busiest->lock, flags);
+ raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the migration_thread, if the curr
* task on busiest cpu can't be moved to this_cpu
*/
if (!cpumask_test_cpu(this_cpu,
&busiest->curr->cpus_allowed)) {
- spin_unlock_irqrestore(&busiest->lock, flags);
+ raw_spin_unlock_irqrestore(&busiest->lock,
+ flags);
all_pinned = 1;
goto out_one_pinned;
}
busiest->push_cpu = this_cpu;
active_balance = 1;
}
- spin_unlock_irqrestore(&busiest->lock, flags);
+ raw_spin_unlock_irqrestore(&busiest->lock, flags);
if (active_balance)
wake_up_process(busiest->migration_thread);
int all_pinned = 0;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
/*
* Should not call ttwu while holding a rq->lock
*/
- spin_unlock(&this_rq->lock);
+ raw_spin_unlock(&this_rq->lock);
if (active_balance)
wake_up_process(busiest->migration_thread);
- spin_lock(&this_rq->lock);
+ raw_spin_lock(&this_rq->lock);
} else
sd->nr_balance_failed = 0;
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ this_rq->idle_stamp = this_rq->clock;
+
+ if (this_rq->avg_idle < sysctl_sched_migration_cost)
+ return;
+
for_each_domain(this_cpu, sd) {
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
cpumask_set_cpu(cpu, nohz.cpu_mask);
/* time for ilb owner also to sleep */
- if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+ if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu)
atomic_set(&nohz.load_balancer, -1);
return 0;
p->gtime = cputime_add(p->gtime, cputime);
/* Add guest time to cpustat. */
- cpustat->user = cputime64_add(cpustat->user, tmp);
- cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ if (TASK_NICE(p) > 0) {
+ cpustat->nice = cputime64_add(cpustat->nice, tmp);
+ cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+ } else {
+ cpustat->user = cputime64_add(cpustat->user, tmp);
+ cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ }
}
/*
*/
void account_process_tick(struct task_struct *p, int user_tick)
{
- cputime_t one_jiffy = jiffies_to_cputime(1);
- cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
if (user_tick)
- account_user_time(p, one_jiffy, one_jiffy_scaled);
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
- account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+ account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
one_jiffy_scaled);
else
- account_idle_time(one_jiffy);
+ account_idle_time(cputime_one_jiffy);
}
/*
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-cputime_t task_utime(struct task_struct *p)
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->utime;
+ *ut = p->utime;
+ *st = p->stime;
}
-cputime_t task_stime(struct task_struct *p)
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->stime;
+ struct task_cputime cputime;
+
+ thread_group_cputime(p, &cputime);
+
+ *ut = cputime.utime;
+ *st = cputime.stime;
}
#else
-cputime_t task_utime(struct task_struct *p)
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
+#endif
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t utime = cputime_to_clock_t(p->utime),
- total = utime + cputime_to_clock_t(p->stime);
- u64 temp;
+ cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
/*
* Use CFS's precise accounting:
*/
- temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+ rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
if (total) {
- temp *= utime;
+ u64 temp;
+
+ temp = (u64)(rtime * utime);
do_div(temp, total);
- }
- utime = (clock_t)temp;
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
- p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
- return p->prev_utime;
+ /*
+ * Compare with previous values, to keep monotonicity:
+ */
+ p->prev_utime = max(p->prev_utime, utime);
+ p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));
+
+ *ut = p->prev_utime;
+ *st = p->prev_stime;
}
-cputime_t task_stime(struct task_struct *p)
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t stime;
+ struct signal_struct *sig = p->signal;
+ struct task_cputime cputime;
+ cputime_t rtime, utime, total;
- /*
- * Use CFS's precise accounting. (we subtract utime from
- * the total, to make sure the total observed by userspace
- * grows monotonically - apps rely on that):
- */
- stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
- cputime_to_clock_t(task_utime(p));
+ thread_group_cputime(p, &cputime);
- if (stime >= 0)
- p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+ total = cputime_add(cputime.utime, cputime.stime);
+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
- return p->prev_stime;
-}
-#endif
+ if (total) {
+ u64 temp;
-inline cputime_t task_gtime(struct task_struct *p)
-{
- return p->gtime;
+ temp = (u64)(rtime * cputime.utime);
+ do_div(temp, total);
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
+
+ sig->prev_utime = max(sig->prev_utime, utime);
+ sig->prev_stime = max(sig->prev_stime,
+ cputime_sub(rtime, sig->prev_utime));
+
+ *ut = sig->prev_utime;
+ *st = sig->prev_stime;
}
+#endif
/*
* This function gets called by the timer code, with HZ frequency.
sched_clock_tick();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
update_cpu_load(rq);
curr->sched_class->task_tick(rq, curr, 0);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
perf_event_task_tick(curr, cpu);
#endif
}
-static void put_prev_task(struct rq *rq, struct task_struct *p)
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;
+ if (prev->state == TASK_RUNNING) {
+ u64 runtime = prev->se.sum_exec_runtime;
- update_avg(&p->se.avg_running, runtime);
+ runtime -= prev->se.prev_sum_exec_runtime;
+ runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- if (p->state == TASK_RUNNING) {
/*
* In order to avoid avg_overlap growing stale when we are
* indeed overlapping and hence not getting put to sleep, grow
* correlates to the amount of cache footprint a task can
* build up.
*/
- runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- update_avg(&p->se.avg_overlap, runtime);
- } else {
- update_avg(&p->se.avg_running, 0);
+ update_avg(&prev->se.avg_overlap, runtime);
}
- p->sched_class->put_prev_task(rq, p);
+ prev->sched_class->put_prev_task(rq, prev);
}
/*
if (sched_feat(HRTICK))
hrtick_clear(rq);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
clear_tsk_need_resched(prev);
cpu = smp_processor_id();
rq = cpu_rq(cpu);
} else
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
BUG_ON(p->se.on_rq);
p->policy = policy;
- switch (p->policy) {
- case SCHED_NORMAL:
- case SCHED_BATCH:
- case SCHED_IDLE:
- p->sched_class = &fair_sched_class;
- break;
- case SCHED_FIFO:
- case SCHED_RR:
- p->sched_class = &rt_sched_class;
- break;
- }
-
p->rt_priority = prio;
p->normal_prio = normal_prio(p);
/* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
+ if (rt_prio(p->prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
set_load_weight(p);
}
* make sure no PI-waiters arrive (or leave) while we are
* changing the priority of the task:
*/
- spin_lock_irqsave(&p->pi_lock, flags);
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
/*
* To be able to change p->policy safely, the apropriate
* runqueue lock must be held.
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
__task_rq_unlock(rq);
- spin_unlock_irqrestore(&p->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
goto recheck;
}
update_rq_clock(rq);
check_class_changed(rq, p, prev_class, oldprio, running);
}
__task_rq_unlock(rq);
- spin_unlock_irqrestore(&p->pi_lock, flags);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
rt_mutex_adjust_pi(p);
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
+ unsigned long flags;
+ struct rq *rq;
int retval;
get_online_cpus();
if (retval)
goto out_unlock;
+ rq = task_rq_lock(p, &flags);
cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+ task_rq_unlock(rq, &flags);
out_unlock:
read_unlock(&tasklist_lock);
*/
__release(rq->lock);
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
- _raw_spin_unlock(&rq->lock);
+ do_raw_spin_unlock(&rq->lock);
preempt_enable_no_resched();
schedule();
/*
* 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.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
*/
void __sched io_schedule(void)
{
{
struct task_struct *p;
unsigned int time_slice;
+ unsigned long flags;
+ struct rq *rq;
int retval;
struct timespec t;
if (retval)
goto out_unlock;
- time_slice = p->sched_class->get_rr_interval(p);
+ rq = task_rq_lock(p, &flags);
+ time_slice = p->sched_class->get_rr_interval(rq, p);
+ task_rq_unlock(rq, &flags);
read_unlock(&tasklist_lock);
jiffies_to_timespec(time_slice, &t);
/*
* Only show locks if all tasks are dumped:
*/
- if (state_filter == -1)
+ if (!state_filter)
debug_show_all_locks();
}
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__sched_fork(idle);
idle->se.exec_start = sched_clock();
- idle->prio = idle->normal_prio = MAX_PRIO;
cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
__set_task_cpu(idle, cpu);
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
idle->oncpu = 1;
#endif
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
/* Set the preempt count _outside_ the spinlocks! */
#if defined(CONFIG_PREEMPT)
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static inline void sched_init_granularity(void)
+static int get_update_sysctl_factor(void)
{
- unsigned int factor = 1 + ilog2(num_online_cpus());
- const unsigned long limit = 200000000;
+ unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int factor;
- sysctl_sched_min_granularity *= factor;
- if (sysctl_sched_min_granularity > limit)
- sysctl_sched_min_granularity = limit;
+ switch (sysctl_sched_tunable_scaling) {
+ case SCHED_TUNABLESCALING_NONE:
+ factor = 1;
+ break;
+ case SCHED_TUNABLESCALING_LINEAR:
+ factor = cpus;
+ break;
+ case SCHED_TUNABLESCALING_LOG:
+ default:
+ factor = 1 + ilog2(cpus);
+ break;
+ }
- sysctl_sched_latency *= factor;
- if (sysctl_sched_latency > limit)
- sysctl_sched_latency = limit;
+ return factor;
+}
- sysctl_sched_wakeup_granularity *= factor;
+static void update_sysctl(void)
+{
+ unsigned int factor = get_update_sysctl_factor();
+
+#define SET_SYSCTL(name) \
+ (sysctl_##name = (factor) * normalized_sysctl_##name)
+ SET_SYSCTL(sched_min_granularity);
+ SET_SYSCTL(sched_latency);
+ SET_SYSCTL(sched_wakeup_granularity);
+ SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
- sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+ update_sysctl();
}
#ifdef CONFIG_SMP
int ret = 0;
rq = task_rq_lock(p, &flags);
- if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+ if (!cpumask_intersects(new_mask, cpu_active_mask)) {
ret = -EINVAL;
goto out;
}
if (cpumask_test_cpu(task_cpu(p), new_mask))
goto out;
- if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+ if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
struct task_struct *mt = rq->migration_thread;
struct migration_req *req;
struct list_head *head;
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
if (cpu_is_offline(cpu)) {
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
break;
}
head = &rq->migration_queue;
if (list_empty(head)) {
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
schedule();
set_current_state(TASK_INTERRUPTIBLE);
continue;
list_del_init(head->next);
if (req->task != NULL) {
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
__migrate_task(req->task, cpu, req->dest_cpu);
} else if (likely(cpu == (badcpu = smp_processor_id()))) {
req->dest_cpu = RCU_MIGRATION_GOT_QS;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
} else {
req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
}
local_irq_enable();
again:
/* Look for allowed, online CPU in same node. */
- for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+ for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
goto move;
/* Any allowed, online CPU? */
- dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
if (dest_cpu < nr_cpu_ids)
goto move;
/* No more Mr. Nice Guy. */
if (dest_cpu >= nr_cpu_ids) {
cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
- dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
+ dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
/*
* Don't tell them about moving exiting tasks or
*/
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+ struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
unsigned long flags;
local_irq_save(flags);
* Strictly not necessary since rest of the CPUs are stopped by now
* and interrupts disabled on the current cpu.
*/
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
update_rq_clock(rq);
activate_task(rq, p, 0);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
* that's OK. No task can be added to this CPU, so iteration is
* fine.
*/
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
move_task_off_dead_cpu(dead_cpu, p);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
put_task_struct(p);
}
.procname = "sched_domain",
.mode = 0555,
},
- {0, },
+ {}
};
static struct ctl_table sd_ctl_root[] = {
{
- .ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
.child = sd_ctl_dir,
},
- {0, },
+ {}
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
static struct ctl_table_header *sd_sysctl_header;
static void register_sched_domain_sysctl(void)
{
- int i, cpu_num = num_online_cpus();
+ int i, cpu_num = num_possible_cpus();
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
if (entry == NULL)
return;
- for_each_online_cpu(i) {
+ for_each_possible_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
/* Update our root-domain */
rq = cpu_rq(cpu);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_online(rq);
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
put_task_struct(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
deactivate_task(rq, rq->idle, 0);
- rq->idle->static_prio = MAX_PRIO;
__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
rq->idle->sched_class = &idle_sched_class;
migrate_dead_tasks(cpu);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
* they didn't take sched_hotcpu_mutex. Just wake up
* the requestors.
*/
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
while (!list_empty(&rq->migration_queue)) {
struct migration_req *req;
req = list_entry(rq->migration_queue.next,
struct migration_req, list);
list_del_init(&req->list);
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
complete(&req->done);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
}
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
break;
case CPU_DYING:
case CPU_DYING_FROZEN:
/* Update our root-domain */
rq = cpu_rq(cpu);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
set_rq_offline(rq);
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#endif
}
#ifdef CONFIG_SCHED_DEBUG
+static __read_mostly int sched_domain_debug_enabled;
+
+static int __init sched_domain_debug_setup(char *str)
+{
+ sched_domain_debug_enabled = 1;
+
+ return 0;
+}
+early_param("sched_debug", sched_domain_debug_setup);
+
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
{
cpumask_var_t groupmask;
int level = 0;
+ if (!sched_domain_debug_enabled)
+ return;
+
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
return;
static void free_rootdomain(struct root_domain *rd)
{
+ synchronize_sched();
+
cpupri_cleanup(&rd->cpupri);
free_cpumask_var(rd->rto_mask);
struct root_domain *old_rd = NULL;
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
if (old_rd)
free_rootdomain(old_rd);
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
+ alloc_bootmem_cpumask_var(&cpu_isolated_map);
cpulist_parse(str, cpu_isolated_map);
return 1;
}
*/
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
static int
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg, struct cpumask *unused)
{
if (sg)
- *sg = &per_cpu(sched_group_cpus, cpu).sg;
+ *sg = &per_cpu(sched_groups, cpu).sg;
return cpu;
}
#endif /* CONFIG_SCHED_SMT */
return __build_sched_domains(cpu_map, NULL);
}
-static struct cpumask *doms_cur; /* current sched domains */
+static cpumask_var_t *doms_cur; /* current sched domains */
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
/* attribues of custom domains in 'doms_cur' */
return 0;
}
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+ int i;
+ cpumask_var_t *doms;
+
+ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+ if (!doms)
+ return NULL;
+ for (i = 0; i < ndoms; i++) {
+ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+ free_sched_domains(doms, i);
+ return NULL;
+ }
+ }
+ return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+ unsigned int i;
+ for (i = 0; i < ndoms; i++)
+ free_cpumask_var(doms[i]);
+ kfree(doms);
+}
+
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* For now this just excludes isolated cpus, but could be used to
arch_update_cpu_topology();
ndoms_cur = 1;
- doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+ doms_cur = alloc_sched_domains(ndoms_cur);
if (!doms_cur)
- doms_cur = fallback_doms;
- cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+ doms_cur = &fallback_doms;
+ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
dattr_cur = NULL;
- err = build_sched_domains(doms_cur);
+ err = build_sched_domains(doms_cur[0]);
register_sched_domain_sysctl();
return err;
* doms_new[] to the current sched domain partitioning, doms_cur[].
* It destroys each deleted domain and builds each new domain.
*
- * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
* The masks don't intersect (don't overlap.) We should setup one
* sched domain for each mask. CPUs not in any of the cpumasks will
* not be load balanced. If the same cpumask appears both in the
* current 'doms_cur' domains and in the new 'doms_new', we can leave
* it as it is.
*
- * The passed in 'doms_new' should be kmalloc'd. This routine takes
- * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL &&
- * ndoms_new == 1, and partition_sched_domains() will fallback to
- * the single partition 'fallback_doms', it also forces the domains
- * to be rebuilt.
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains. This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
*
* If doms_new == NULL it will be replaced with cpu_online_mask.
* ndoms_new == 0 is a special case for destroying existing domains,
*
* Call with hotplug lock held
*/
-/* FIXME: Change to struct cpumask *doms_new[] */
-void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
int i, j, n;
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(&doms_cur[i], &doms_new[j])
+ if (cpumask_equal(doms_cur[i], doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* no match - a current sched domain not in new doms_new[] */
- detach_destroy_domains(doms_cur + i);
+ detach_destroy_domains(doms_cur[i]);
match1:
;
}
if (doms_new == NULL) {
ndoms_cur = 0;
- doms_new = fallback_doms;
- cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+ doms_new = &fallback_doms;
+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
WARN_ON_ONCE(dattr_new);
}
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < ndoms_cur && !new_topology; j++) {
- if (cpumask_equal(&doms_new[i], &doms_cur[j])
+ if (cpumask_equal(doms_new[i], doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* no match - add a new doms_new */
- __build_sched_domains(doms_new + i,
+ __build_sched_domains(doms_new[i],
dattr_new ? dattr_new + i : NULL);
match2:
;
}
/* Remember the new sched domains */
- if (doms_cur != fallback_doms)
- kfree(doms_cur);
+ if (doms_cur != &fallback_doms)
+ free_sched_domains(doms_cur, ndoms_cur);
kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
dattr_cur = dattr_new;
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_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);
return NOTIFY_OK;
#endif
get_online_cpus();
mutex_lock(&sched_domains_mutex);
- arch_init_sched_domains(cpu_online_mask);
+ arch_init_sched_domains(cpu_active_mask);
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
if (cpumask_empty(non_isolated_cpus))
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
- plist_head_init(&rt_rq->pushable_tasks, &rq->lock);
+ plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock);
#endif
rt_rq->rt_time = 0;
rt_rq->rt_throttled = 0;
rt_rq->rt_runtime = 0;
- spin_lock_init(&rt_rq->rt_runtime_lock);
+ raw_spin_lock_init(&rt_rq->rt_runtime_lock);
#ifdef CONFIG_RT_GROUP_SCHED
rt_rq->rt_nr_boosted = 0;
#ifdef CONFIG_CPUMASK_OFFSTACK
alloc_size += num_possible_cpus() * cpumask_size();
#endif
- /*
- * As sched_init() is called before page_alloc is setup,
- * we use alloc_bootmem().
- */
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_GROUP_SCHED */
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+ update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+ __alignof__(unsigned long));
+#endif
for_each_possible_cpu(i) {
struct rq *rq;
rq = cpu_rq(i);
- spin_lock_init(&rq->lock);
+ raw_spin_lock_init(&rq->lock);
rq->nr_running = 0;
rq->calc_load_active = 0;
rq->calc_load_update = jiffies + LOAD_FREQ;
#elif defined CONFIG_USER_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
init_tg_rt_entry(&init_task_group,
- &per_cpu(init_rt_rq, i),
+ &per_cpu(init_rt_rq_var, i),
&per_cpu(init_sched_rt_entity, i), i, 1,
root_task_group.rt_se[i]);
#endif
rq->cpu = i;
rq->online = 0;
rq->migration_thread = NULL;
+ rq->idle_stamp = 0;
+ rq->avg_idle = 2*sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->migration_queue);
rq_attach_root(rq, &def_root_domain);
#endif
#endif
#ifdef CONFIG_RT_MUTEXES
- plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+ plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock);
#endif
/*
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ /* May be allocated at isolcpus cmdline parse time */
+ if (cpu_isolated_map == NULL)
+ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
perf_event_init();
continue;
}
- spin_lock(&p->pi_lock);
+ raw_spin_lock(&p->pi_lock);
rq = __task_rq_lock(p);
normalize_task(rq, p);
__task_rq_unlock(rq);
- spin_unlock(&p->pi_lock);
+ raw_spin_unlock(&p->pi_lock);
} while_each_thread(g, p);
read_unlock_irqrestore(&tasklist_lock, flags);
se = kzalloc_node(sizeof(struct sched_entity),
GFP_KERNEL, cpu_to_node(i));
if (!se)
- goto err;
+ goto err_free_rq;
init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
}
return 1;
+ err_free_rq:
+ kfree(cfs_rq);
err:
return 0;
}
rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
GFP_KERNEL, cpu_to_node(i));
if (!rt_se)
- goto err;
+ goto err_free_rq;
init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
}
return 1;
+ err_free_rq:
+ kfree(rt_rq);
err:
return 0;
}
struct rq *rq = cfs_rq->rq;
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__set_se_shares(se, shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static DEFINE_MUTEX(shares_mutex);
if (err)
goto unlock;
- spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+ raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
tg->rt_bandwidth.rt_runtime = rt_runtime;
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = tg->rt_rq[i];
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = rt_runtime;
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
- spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+ raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
if (sysctl_sched_rt_runtime == 0)
return -EBUSY;
- spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+ raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
for_each_possible_cpu(i) {
struct rt_rq *rt_rq = &cpu_rq(i)->rt;
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = global_rt_runtime();
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
- spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+ raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
return 0;
}
#endif /* CONFIG_RT_GROUP_SCHED */
int sched_rt_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
old_period = sysctl_sched_rt_period;
old_runtime = sysctl_sched_rt_runtime;
- ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (!ret && write) {
ret = sched_rt_global_constraints();
}
static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct task_struct *tsk)
+cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
#ifdef CONFIG_RT_GROUP_SCHED
if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
if (tsk->sched_class != &fair_sched_class)
return -EINVAL;
#endif
+ return 0;
+}
+static int
+cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
+ struct task_struct *tsk, bool threadgroup)
+{
+ int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
+ if (retval)
+ return retval;
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ retval = cpu_cgroup_can_attach_task(cgrp, c);
+ if (retval) {
+ rcu_read_unlock();
+ return retval;
+ }
+ }
+ rcu_read_unlock();
+ }
return 0;
}
static void
cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup *old_cont, struct task_struct *tsk)
+ struct cgroup *old_cont, struct task_struct *tsk,
+ bool threadgroup)
{
sched_move_task(tsk);
+ if (threadgroup) {
+ struct task_struct *c;
+ rcu_read_lock();
+ list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
+ sched_move_task(c);
+ }
+ rcu_read_unlock();
+ }
}
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* Take rq->lock to make 64-bit read safe on 32-bit platforms.
*/
- spin_lock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_lock_irq(&cpu_rq(cpu)->lock);
data = *cpuusage;
- spin_unlock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
data = *cpuusage;
#endif
/*
* Take rq->lock to make 64-bit write safe on 32-bit platforms.
*/
- spin_lock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_lock_irq(&cpu_rq(cpu)->lock);
*cpuusage = val;
- spin_unlock_irq(&cpu_rq(cpu)->lock);
+ raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
*cpuusage = val;
#endif
init_completion(&req->done);
req->task = NULL;
req->dest_cpu = RCU_MIGRATION_NEED_QS;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
list_add(&req->list, &rq->migration_queue);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
wake_up_process(rq->migration_thread);
}
for_each_online_cpu(cpu) {
req = &per_cpu(rcu_migration_req, cpu);
rq = cpu_rq(cpu);
wait_for_completion(&req->done);
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
need_full_sync = 1;
req->dest_cpu = RCU_MIGRATION_IDLE;
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ synchronize_sched_expedited_count++;
mutex_unlock(&rcu_sched_expedited_mutex);
put_online_cpus();
if (need_full_sync)
Code Review / linux-2.6.git / blobdiff