* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
- struct sched_entity *curr, *next, *last;
+ struct sched_entity *curr, *next, *last, *skip;
unsigned int nr_spread_over;
__release(rq2->lock);
}
+#else /* CONFIG_SMP */
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+ __acquires(rq1->lock)
+ __acquires(rq2->lock)
+{
+ BUG_ON(!irqs_disabled());
+ BUG_ON(rq1 != rq2);
+ raw_spin_lock(&rq1->lock);
+ __acquire(rq2->lock); /* Fake it out ;) */
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+ __releases(rq1->lock)
+ __releases(rq2->lock)
+{
+ BUG_ON(rq1 != rq2);
+ raw_spin_unlock(&rq1->lock);
+ __release(rq2->lock);
+}
+
#endif
static void calc_load_account_idle(struct rq *this_rq);
*/
if (hardirq_count())
__this_cpu_add(cpu_hardirq_time, delta);
- else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
__this_cpu_add(cpu_softirq_time, delta);
irq_time_write_end();
sched_rt_avg_update(rq, irq_delta);
}
+static int irqtime_account_hi_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_hardirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_softirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+#define sched_clock_irqtime (0)
+
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
rq->clock_task += delta;
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
- int oldprio, int running)
+ int oldprio)
{
if (prev_class != p->sched_class) {
if (prev_class->switched_from)
- prev_class->switched_from(rq, p, running);
- p->sched_class->switched_to(rq, p, running);
- } else
- p->sched_class->prio_changed(rq, p, oldprio, running);
+ prev_class->switched_from(rq, p);
+ p->sched_class->switched_to(rq, p);
+ } else if (oldprio != p->prio)
+ p->sched_class->prio_changed(rq, p, oldprio);
}
static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
+ p->se.vruntime = 0;
#ifdef CONFIG_SCHEDSTATS
memset(&p->se.statistics, 0, sizeof(p->se.statistics));
}
}
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+ cputime64_t tmp = cputime_to_cputime64(cputime);
+
+ /* Add system time to process. */
+ p->stime = cputime_add(p->stime, cputime);
+ p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
+ account_group_system_time(p, cputime);
+
+ /* Add system time to cpustat. */
+ *target_cputime64 = cputime64_add(*target_cputime64, tmp);
+ cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
/*
* Account system cpu time to a process.
* @p: the process that the cpu time gets accounted to
cputime_t cputime, cputime_t cputime_scaled)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- cputime64_t tmp;
+ cputime64_t *target_cputime64;
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
account_guest_time(p, cputime, cputime_scaled);
return;
}
- /* Add system time to process. */
- p->stime = cputime_add(p->stime, cputime);
- p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
- account_group_system_time(p, cputime);
-
- /* Add system time to cpustat. */
- tmp = cputime_to_cputime64(cputime);
if (hardirq_count() - hardirq_offset)
- cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ target_cputime64 = &cpustat->irq;
else if (in_serving_softirq())
- cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ target_cputime64 = &cpustat->softirq;
else
- cpustat->system = cputime64_add(cpustat->system, tmp);
+ target_cputime64 = &cpustat->system;
- cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
-
- /* Account for system time used */
- acct_update_integrals(p);
+ __account_system_time(p, cputime, cputime_scaled, target_cputime64);
}
/*
* Account for involuntary wait time.
- * @steal: the cpu time spent in involuntary wait
+ * @cputime: the cpu time spent in involuntary wait
*/
void account_steal_time(cputime_t cputime)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ * - check for guest_time
+ * - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+ if (irqtime_account_hi_update()) {
+ cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ } else if (irqtime_account_si_update()) {
+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ } else if (this_cpu_ksoftirqd() == p) {
+ /*
+ * ksoftirqd time do not get accounted in cpu_softirq_time.
+ * So, we have to handle it separately here.
+ * Also, p->stime needs to be updated for ksoftirqd.
+ */
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->softirq);
+ } else if (user_tick) {
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else if (p == rq->idle) {
+ account_idle_time(cputime_one_jiffy);
+ } else if (p->flags & PF_VCPU) { /* System time or guest time */
+ account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else {
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->system);
+ }
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+ int i;
+ struct rq *rq = this_rq();
+
+ for (i = 0; i < ticks; i++)
+ irqtime_account_process_tick(current, 0, rq);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
/*
* Account a single tick of cpu time.
* @p: the process that the cpu time gets accounted to
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
+ if (sched_clock_irqtime) {
+ irqtime_account_process_tick(p, user_tick, rq);
+ return;
+ }
+
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
*/
void account_idle_ticks(unsigned long ticks)
{
+
+ if (sched_clock_irqtime) {
+ irqtime_account_idle_ticks(ticks);
+ return;
+ }
+
account_idle_time(jiffies_to_cputime(ticks));
}
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
task_rq_unlock(rq, &flags);
}
if (running)
p->sched_class->set_curr_task(rq);
- if (on_rq) {
+ if (on_rq)
activate_task(rq, p, 0);
- check_class_changed(rq, p, prev_class, oldprio, running);
- }
+ check_class_changed(rq, p, prev_class, oldprio);
__task_rq_unlock(rq);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
EXPORT_SYMBOL(yield);
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ *
+ * 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.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+ struct task_struct *curr = current;
+ struct rq *rq, *p_rq;
+ unsigned long flags;
+ bool yielded = 0;
+
+ local_irq_save(flags);
+ rq = this_rq();
+
+again:
+ p_rq = task_rq(p);
+ double_rq_lock(rq, p_rq);
+ while (task_rq(p) != p_rq) {
+ double_rq_unlock(rq, p_rq);
+ goto again;
+ }
+
+ if (!curr->sched_class->yield_to_task)
+ goto out;
+
+ if (curr->sched_class != p->sched_class)
+ goto out;
+
+ if (task_running(p_rq, p) || p->state)
+ goto out;
+
+ yielded = curr->sched_class->yield_to_task(rq, p, preempt);
+ if (yielded)
+ schedstat_inc(rq, yld_count);
+
+out:
+ double_rq_unlock(rq, p_rq);
+ local_irq_restore(flags);
+
+ if (yielded)
+ schedule();
+
+ return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
/*
* 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.
INIT_LIST_HEAD(&cfs_rq->tasks);
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->rq = rq;
+ /* allow initial update_cfs_load() to truncate */
+#ifdef CONFIG_SMP
+ cfs_rq->load_stamp = 1;
+#endif
#endif
cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
#ifdef CONFIG_MAGIC_SYSRQ
static void normalize_task(struct rq *rq, struct task_struct *p)
{
+ const struct sched_class *prev_class = p->sched_class;
+ int old_prio = p->prio;
int on_rq;
on_rq = p->se.on_rq;
activate_task(rq, p, 0);
resched_task(rq->curr);
}
+
+ check_class_changed(rq, p, prev_class, old_prio);
}
void normalize_rt_tasks(void)
/* Propagate contribution to hierarchy */
raw_spin_lock_irqsave(&rq->lock, flags);
for_each_sched_entity(se)
- update_cfs_shares(group_cfs_rq(se), 0);
+ update_cfs_shares(group_cfs_rq(se));
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
*/
unsigned int sysctl_sched_child_runs_first __read_mostly;
-/*
- * sys_sched_yield() compat mode
- *
- * This option switches the agressive yield implementation of the
- * old scheduler back on.
- */
-unsigned int __read_mostly sysctl_sched_compat_yield;
-
/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
-static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
return rb_entry(left, struct sched_entity, run_node);
}
+static struct sched_entity *__pick_next_entity(struct sched_entity *se)
+{
+ struct rb_node *next = rb_next(&se->run_node);
+
+ if (!next)
+ return NULL;
+
+ return rb_entry(next, struct sched_entity, run_node);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
* Scheduling class statistics methods:
*/
-#ifdef CONFIG_SCHED_DEBUG
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
}
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+static void update_cfs_shares(struct cfs_rq *cfs_rq);
/*
* Update the current task's runtime statistics. Skip current tasks that
now - cfs_rq->load_last > 4 * period) {
cfs_rq->load_period = 0;
cfs_rq->load_avg = 0;
+ delta = period - 1;
}
cfs_rq->load_stamp = now;
list_del_leaf_cfs_rq(cfs_rq);
}
-static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
long load_weight, load, shares;
- load = cfs_rq->load.weight + weight_delta;
+ load = cfs_rq->load.weight;
load_weight = atomic_read(&tg->load_weight);
- load_weight -= cfs_rq->load_contribution;
load_weight += load;
+ load_weight -= cfs_rq->load_contribution;
shares = (tg->shares * load);
if (load_weight)
{
if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
}
# else /* CONFIG_SMP */
{
}
-static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
- long weight_delta)
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
return tg->shares;
}
account_entity_enqueue(cfs_rq, se);
}
-static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static void update_cfs_shares(struct cfs_rq *cfs_rq)
{
struct task_group *tg;
struct sched_entity *se;
if (likely(se->load.weight == tg->shares))
return;
#endif
- shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
+ shares = calc_cfs_shares(cfs_rq, tg);
reweight_entity(cfs_rq_of(se), se, shares);
}
{
}
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
{
}
*/
update_curr(cfs_rq);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, se->load.weight);
account_entity_enqueue(cfs_rq, se);
+ update_cfs_shares(cfs_rq);
if (flags & ENQUEUE_WAKEUP) {
place_entity(cfs_rq, se, 0);
list_add_leaf_cfs_rq(cfs_rq);
}
-static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __clear_buddies_last(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
+ else
+ break;
+ }
+}
+
+static void __clear_buddies_next(struct sched_entity *se)
{
- if (!se || cfs_rq->last == se)
- cfs_rq->last = NULL;
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
+ else
+ break;
+ }
+}
- if (!se || cfs_rq->next == se)
- cfs_rq->next = NULL;
+static void __clear_buddies_skip(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ if (cfs_rq->skip == se)
+ cfs_rq->skip = NULL;
+ else
+ break;
+ }
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- for_each_sched_entity(se)
- __clear_buddies(cfs_rq_of(se), se);
+ if (cfs_rq->last == se)
+ __clear_buddies_last(se);
+
+ if (cfs_rq->next == se)
+ __clear_buddies_next(se);
+
+ if (cfs_rq->skip == se)
+ __clear_buddies_skip(se);
}
static void
update_cfs_load(cfs_rq, 0);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
/*
* Normalize the entity after updating the min_vruntime because the
return;
if (cfs_rq->nr_running > 1) {
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
s64 delta = curr->vruntime - se->vruntime;
if (delta < 0)
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
+/*
+ * Pick the next process, keeping these things in mind, in this order:
+ * 1) keep things fair between processes/task groups
+ * 2) pick the "next" process, since someone really wants that to run
+ * 3) pick the "last" process, for cache locality
+ * 4) do not run the "skip" process, if something else is available
+ */
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_next_entity(cfs_rq);
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *left = se;
- if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
- se = cfs_rq->next;
+ /*
+ * Avoid running the skip buddy, if running something else can
+ * be done without getting too unfair.
+ */
+ if (cfs_rq->skip == se) {
+ struct sched_entity *second = __pick_next_entity(se);
+ if (second && wakeup_preempt_entity(second, left) < 1)
+ se = second;
+ }
/*
* Prefer last buddy, try to return the CPU to a preempted task.
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
+ /*
+ * Someone really wants this to run. If it's not unfair, run it.
+ */
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;
+
clear_buddies(cfs_rq, se);
return se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
struct cfs_rq *cfs_rq = cfs_rq_of(se);
update_cfs_load(cfs_rq, 0);
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
}
hrtick_update(rq);
}
-/*
- * sched_yield() support is very simple - we dequeue and enqueue.
- *
- * If compat_yield is turned on then we requeue to the end of the tree.
- */
-static void yield_task_fair(struct rq *rq)
-{
- struct task_struct *curr = rq->curr;
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
- struct sched_entity *rightmost, *se = &curr->se;
-
- /*
- * Are we the only task in the tree?
- */
- if (unlikely(cfs_rq->nr_running == 1))
- return;
-
- clear_buddies(cfs_rq, se);
-
- if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
- update_rq_clock(rq);
- /*
- * Update run-time statistics of the 'current'.
- */
- update_curr(cfs_rq);
-
- return;
- }
- /*
- * Find the rightmost entry in the rbtree:
- */
- rightmost = __pick_last_entity(cfs_rq);
- /*
- * Already in the rightmost position?
- */
- if (unlikely(!rightmost || entity_before(rightmost, se)))
- return;
-
- /*
- * Minimally necessary key value to be last in the tree:
- * Upon rescheduling, sched_class::put_prev_task() will place
- * 'current' within the tree based on its new key value.
- */
- se->vruntime = rightmost->vruntime + 1;
-}
-
#ifdef CONFIG_SMP
static void task_waking_fair(struct rq *rq, struct task_struct *p)
}
}
+static void set_skip_buddy(struct sched_entity *se)
+{
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->skip = se;
+ }
+}
+
/*
* Preempt the current task with a newly woken task if needed:
*/
}
}
+/*
+ * sched_yield() is very simple
+ *
+ * The magic of dealing with the ->skip buddy is in pick_next_entity.
+ */
+static void yield_task_fair(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+ struct sched_entity *se = &curr->se;
+
+ /*
+ * Are we the only task in the tree?
+ */
+ if (unlikely(rq->nr_running == 1))
+ return;
+
+ clear_buddies(cfs_rq, se);
+
+ if (curr->policy != SCHED_BATCH) {
+ update_rq_clock(rq);
+ /*
+ * Update run-time statistics of the 'current'.
+ */
+ update_curr(cfs_rq);
+ }
+
+ set_skip_buddy(se);
+}
+
+static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt)
+{
+ struct sched_entity *se = &p->se;
+
+ if (!se->on_rq)
+ return false;
+
+ /* Tell the scheduler that we'd really like pse to run next. */
+ set_next_buddy(se);
+
+ /* Make p's CPU reschedule; pick_next_entity takes care of fairness. */
+ if (preempt)
+ resched_task(rq->curr);
+
+ yield_task_fair(rq);
+
+ return true;
+}
+
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
* We need to update shares after updating tg->load_weight in
* order to adjust the weight of groups with long running tasks.
*/
- update_cfs_shares(cfs_rq, 0);
+ update_cfs_shares(cfs_rq);
raw_spin_unlock_irqrestore(&rq->lock, flags);
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
* @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
* @local_group: Does group contain this_cpu.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
*/
static inline void update_sg_lb_stats(struct sched_domain *sd,
struct sched_group *group, int this_cpu,
- enum cpu_idle_type idle, int load_idx, int *sd_idle,
+ enum cpu_idle_type idle, int load_idx,
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
- if (*sd_idle && rq->nr_running)
- *sd_idle = 0;
-
/* Bias balancing toward cpus of our domain */
if (local_group) {
if (idle_cpu(i) && !first_idle_cpu) {
/*
* Consider the group unbalanced when the imbalance is larger
- * than the average weight of two tasks.
+ * than the average weight of a task.
*
* APZ: with cgroup the avg task weight can vary wildly and
* might not be a suitable number - should we keep a
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+ if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
sgs->group_imb = 1;
sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
* @sd: sched_domain whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing sg.
* @cpus: Set of cpus considered for load balancing.
* @balance: Should we balance.
* @sds: variable to hold the statistics for this sched_domain.
*/
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
- enum cpu_idle_type idle, int *sd_idle,
- const struct cpumask *cpus, int *balance,
- struct sd_lb_stats *sds)
+ enum cpu_idle_type idle, const struct cpumask *cpus,
+ int *balance, struct sd_lb_stats *sds)
{
struct sched_domain *child = sd->child;
struct sched_group *sg = sd->groups;
local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(sg));
memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx, sd_idle,
+ update_sg_lb_stats(sd, sg, this_cpu, idle, load_idx,
local_group, cpus, balance, &sgs);
if (local_group && !(*balance))
* @imbalance: Variable which stores amount of weighted load which should
* be moved to restore balance/put a group to idle.
* @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
* @cpus: The set of CPUs under consideration for load-balancing.
* @balance: Pointer to a variable indicating if this_cpu
* is the appropriate cpu to perform load balancing at this_level.
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
+ const struct cpumask *cpus, int *balance)
{
struct sd_lb_stats sds;
* Compute the various statistics relavent for load balancing at
* this level.
*/
- update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
- balance, &sds);
-
- /* Cases where imbalance does not exist from POV of this_cpu */
- /* 1) this_cpu is not the appropriate cpu to perform load balancing
- * at this level.
- * 2) There is no busy sibling group to pull from.
- * 3) This group is the busiest group.
- * 4) This group is more busy than the avg busieness at this
- * sched_domain.
- * 5) The imbalance is within the specified limit.
- *
- * Note: when doing newidle balance, if the local group has excess
- * capacity (i.e. nr_running < group_capacity) and the busiest group
- * does not have any capacity, we force a load balance to pull tasks
- * to the local group. In this case, we skip past checks 3, 4 and 5.
+ update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
+
+ /*
+ * this_cpu is not the appropriate cpu to perform load balancing at
+ * this level.
*/
if (!(*balance))
goto ret;
check_asym_packing(sd, &sds, this_cpu, imbalance))
return sds.busiest;
+ /* There is no busy sibling group to pull tasks from */
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
- /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+ /*
+ * If the busiest group is imbalanced the below checks don't
+ * work because they assumes all things are equal, which typically
+ * isn't true due to cpus_allowed constraints and the like.
+ */
+ if (sds.group_imb)
+ goto force_balance;
+
+ /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
!sds.busiest_has_capacity)
goto force_balance;
+ /*
+ * If the local group is more busy than the selected busiest group
+ * don't try and pull any tasks.
+ */
if (sds.this_load >= sds.max_load)
goto out_balanced;
+ /*
+ * Don't pull any tasks if this group is already above the domain
+ * average load.
+ */
sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
if (sds.this_load >= sds.avg_load)
goto out_balanced;
- /*
- * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
- * And to check for busy balance use !idle_cpu instead of
- * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
- * even when they are idle.
- */
- if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
- if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
- goto out_balanced;
- } else {
+ if (idle == CPU_IDLE) {
/*
* This cpu is idle. If the busiest group load doesn't
* have more tasks than the number of available cpu's and
* there is no imbalance between this and busiest group
* wrt to idle cpu's, it is balanced.
*/
- if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
+ if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
sds.busiest_nr_running <= sds.busiest_group_weight)
goto out_balanced;
+ } else {
+ /*
+ * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+ * imbalance_pct to be conservative.
+ */
+ if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+ goto out_balanced;
}
force_balance:
/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
-static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle,
+static int need_active_balance(struct sched_domain *sd, int idle,
int busiest_cpu, int this_cpu)
{
if (idle == CPU_NEWLY_IDLE) {
* move_tasks() will succeed. ld_moved will be true and this
* active balance code will not be triggered.
*/
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- return 0;
-
if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
return 0;
}
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
{
- int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+ int ld_moved, all_pinned = 0, active_balance = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
cpumask_copy(cpus, cpu_active_mask);
- /*
- * When power savings policy is enabled for the parent domain, idle
- * sibling can pick up load irrespective of busy siblings. In this case,
- * let the state of idle sibling percolate up as CPU_IDLE, instead of
- * portraying it as CPU_NOT_IDLE.
- */
- if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- sd_idle = 1;
-
schedstat_inc(sd, lb_count[idle]);
redo:
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle,
cpus, balance);
if (*balance == 0)
if (idle != CPU_NEWLY_IDLE)
sd->nr_balance_failed++;
- if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
- this_cpu)) {
+ if (need_active_balance(sd, idle, cpu_of(busiest), this_cpu)) {
raw_spin_lock_irqsave(&busiest->lock, flags);
/* don't kick the active_load_balance_cpu_stop,
sd->balance_interval *= 2;
}
- if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
-
goto out;
out_balanced:
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
- !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
- ld_moved = -1;
- else
- ld_moved = 0;
+ ld_moved = 0;
out:
return ld_moved;
}
if (load_balance(cpu, rq, sd, idle, &balance)) {
/*
* We've pulled tasks over so either we're no
- * longer idle, or one of our SMT siblings is
- * not idle.
+ * longer idle.
*/
idle = CPU_NOT_IDLE;
}
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
-static void prio_changed_fair(struct rq *rq, struct task_struct *p,
- int oldprio, int running)
+static void
+prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
- if (running) {
+ if (rq->curr == p) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p, 0);
}
+static void switched_from_fair(struct rq *rq, struct task_struct *p)
+{
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ /*
+ * Ensure the task's vruntime is normalized, so that when its
+ * switched back to the fair class the enqueue_entity(.flags=0) will
+ * do the right thing.
+ *
+ * If it was on_rq, then the dequeue_entity(.flags=0) will already
+ * have normalized the vruntime, if it was !on_rq, then only when
+ * the task is sleeping will it still have non-normalized vruntime.
+ */
+ if (!se->on_rq && p->state != TASK_RUNNING) {
+ /*
+ * Fix up our vruntime so that the current sleep doesn't
+ * cause 'unlimited' sleep bonus.
+ */
+ place_entity(cfs_rq, se, 0);
+ se->vruntime -= cfs_rq->min_vruntime;
+ }
+}
+
/*
* We switched to the sched_fair class.
*/
-static void switched_to_fair(struct rq *rq, struct task_struct *p,
- int running)
+static void switched_to_fair(struct rq *rq, struct task_struct *p)
{
+ if (!p->se.on_rq)
+ return;
+
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
- if (running)
+ if (rq->curr == p)
resched_task(rq->curr);
else
check_preempt_curr(rq, p, 0);
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
+ .yield_to_task = yield_to_task_fair,
.check_preempt_curr = check_preempt_wakeup,
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
+ .switched_from = switched_from_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,