return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+ list_add_rcu(&rt_rq->leaf_rt_rq_list,
+ &rq_of_rt_rq(rt_rq)->leaf_rt_rq_list);
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+ list_del_rcu(&rt_rq->leaf_rt_rq_list);
+}
+
#define for_each_leaf_rt_rq(rt_rq, rq) \
list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
return rt_se->my_q;
}
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
- struct sched_rt_entity *rt_se = rt_rq->rt_se;
+ struct sched_rt_entity *rt_se;
+
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_rq->rt_nr_running) {
if (rt_se && !on_rt_rq(rt_se))
- enqueue_rt_entity(rt_se);
+ enqueue_rt_entity(rt_se, false);
if (rt_rq->highest_prio.curr < curr->prio)
resched_task(curr);
}
static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
- struct sched_rt_entity *rt_se = rt_rq->rt_se;
+ struct sched_rt_entity *rt_se;
+ int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+ rt_se = rt_rq->tg->rt_se[cpu];
if (rt_se && on_rt_rq(rt_se))
dequeue_rt_entity(rt_se);
return ktime_to_ns(def_rt_bandwidth.rt_period);
}
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
#define for_each_leaf_rt_rq(rt_rq, rq) \
for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
weight = cpumask_weight(rd->span);
- spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
rt_period = ktime_to_ns(rt_b->rt_period);
for_each_cpu(i, rd->span) {
struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
if (iter == rt_rq)
continue;
- spin_lock(&iter->rt_runtime_lock);
+ raw_spin_lock(&iter->rt_runtime_lock);
/*
* Either all rqs have inf runtime and there's nothing to steal
* or __disable_runtime() below sets a specific rq to inf to
rt_rq->rt_runtime += diff;
more = 1;
if (rt_rq->rt_runtime == rt_period) {
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
break;
}
}
next:
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
}
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
return more;
}
s64 want;
int i;
- spin_lock(&rt_b->rt_runtime_lock);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
/*
* Either we're all inf and nobody needs to borrow, or we're
* already disabled and thus have nothing to do, or we have
if (rt_rq->rt_runtime == RUNTIME_INF ||
rt_rq->rt_runtime == rt_b->rt_runtime)
goto balanced;
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
/*
* Calculate the difference between what we started out with
if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
continue;
- spin_lock(&iter->rt_runtime_lock);
+ raw_spin_lock(&iter->rt_runtime_lock);
if (want > 0) {
diff = min_t(s64, iter->rt_runtime, want);
iter->rt_runtime -= diff;
iter->rt_runtime -= want;
want -= want;
}
- spin_unlock(&iter->rt_runtime_lock);
+ raw_spin_unlock(&iter->rt_runtime_lock);
if (!want)
break;
}
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
/*
* We cannot be left wanting - that would mean some runtime
* leaked out of the system.
* runtime - in which case borrowing doesn't make sense.
*/
rt_rq->rt_runtime = RUNTIME_INF;
- spin_unlock(&rt_rq->rt_runtime_lock);
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
}
{
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__disable_runtime(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static void __enable_runtime(struct rq *rq)
for_each_leaf_rt_rq(rt_rq, rq) {
struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
- spin_lock(&rt_b->rt_runtime_lock);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_b->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_runtime = rt_b->rt_runtime;
rt_rq->rt_time = 0;
rt_rq->rt_throttled = 0;
- spin_unlock(&rt_rq->rt_runtime_lock);
- spin_unlock(&rt_b->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_b->rt_runtime_lock);
}
}
{
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__enable_runtime(rq);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static int balance_runtime(struct rt_rq *rt_rq)
int more = 0;
if (rt_rq->rt_time > rt_rq->rt_runtime) {
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
more = do_balance_runtime(rt_rq);
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
}
return more;
struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
struct rq *rq = rq_of_rt_rq(rt_rq);
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
if (rt_rq->rt_time) {
u64 runtime;
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
if (rt_rq->rt_throttled)
balance_runtime(rt_rq);
runtime = rt_rq->rt_runtime;
}
if (rt_rq->rt_time || rt_rq->rt_nr_running)
idle = 0;
- spin_unlock(&rt_rq->rt_runtime_lock);
- } else if (rt_rq->rt_nr_running)
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
+ } else if (rt_rq->rt_nr_running) {
idle = 0;
+ if (!rt_rq_throttled(rt_rq))
+ enqueue = 1;
+ }
if (enqueue)
sched_rt_rq_enqueue(rt_rq);
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
return idle;
struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
u64 delta_exec;
- if (!task_has_rt_policy(curr))
+ if (curr->sched_class != &rt_sched_class)
return;
- delta_exec = rq->clock - curr->se.exec_start;
+ delta_exec = rq->clock_task - curr->se.exec_start;
if (unlikely((s64)delta_exec < 0))
delta_exec = 0;
- schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
+ schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
curr->se.sum_exec_runtime += delta_exec;
account_group_exec_runtime(curr, delta_exec);
- curr->se.exec_start = rq->clock;
+ curr->se.exec_start = rq->clock_task;
cpuacct_charge(curr, delta_exec);
+ sched_rt_avg_update(rq, delta_exec);
+
if (!rt_bandwidth_enabled())
return;
rt_rq = rt_rq_of_se(rt_se);
if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
- spin_lock(&rt_rq->rt_runtime_lock);
+ raw_spin_lock(&rt_rq->rt_runtime_lock);
rt_rq->rt_time += delta_exec;
if (sched_rt_runtime_exceeded(rt_rq))
resched_task(curr);
- spin_unlock(&rt_rq->rt_runtime_lock);
+ raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
}
}
dec_rt_group(rt_se, rt_rq);
}
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
{
struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
struct rt_prio_array *array = &rt_rq->active;
if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
return;
- list_add_tail(&rt_se->run_list, queue);
+ if (!rt_rq->rt_nr_running)
+ list_add_leaf_rt_rq(rt_rq);
+
+ if (head)
+ list_add(&rt_se->run_list, queue);
+ else
+ list_add_tail(&rt_se->run_list, queue);
__set_bit(rt_se_prio(rt_se), array->bitmap);
inc_rt_tasks(rt_se, rt_rq);
__clear_bit(rt_se_prio(rt_se), array->bitmap);
dec_rt_tasks(rt_se, rt_rq);
+ if (!rt_rq->rt_nr_running)
+ list_del_leaf_rt_rq(rt_rq);
}
/*
}
}
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
{
dequeue_rt_stack(rt_se);
for_each_sched_rt_entity(rt_se)
- __enqueue_rt_entity(rt_se);
+ __enqueue_rt_entity(rt_se, head);
}
static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
struct rt_rq *rt_rq = group_rt_rq(rt_se);
if (rt_rq && rt_rq->rt_nr_running)
- __enqueue_rt_entity(rt_se);
+ __enqueue_rt_entity(rt_se, false);
}
}
/*
* Adding/removing a task to/from a priority array:
*/
-static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
struct sched_rt_entity *rt_se = &p->rt;
- if (wakeup)
+ if (flags & ENQUEUE_WAKEUP)
rt_se->timeout = 0;
- enqueue_rt_entity(rt_se);
+ enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
enqueue_pushable_task(rq, p);
-
- inc_cpu_load(rq, p->se.load.weight);
}
-static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
+static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
struct sched_rt_entity *rt_se = &p->rt;
dequeue_rt_entity(rt_se);
dequeue_pushable_task(rq, p);
-
- dec_cpu_load(rq, p->se.load.weight);
}
/*
#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);
-static int select_task_rq_rt(struct task_struct *p, int sync)
+static int
+select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
{
- struct rq *rq = task_rq(p);
+ if (sd_flag != SD_BALANCE_WAKE)
+ return smp_processor_id();
/*
* If the current task is an RT task, then
* runqueue. Otherwise simply start this RT task
* on its current runqueue.
*
- * We want to avoid overloading runqueues. Even if
- * the RT task is of higher priority than the current RT task.
- * RT tasks behave differently than other tasks. If
- * one gets preempted, we try to push it off to another queue.
- * So trying to keep a preempting RT task on the same
- * cache hot CPU will force the running RT task to
- * a cold CPU. So we waste all the cache for the lower
- * RT task in hopes of saving some of a RT task
- * that is just being woken and probably will have
- * cold cache anyway.
+ * We want to avoid overloading runqueues. If the woken
+ * task is a higher priority, then it will stay on this CPU
+ * and the lower prio task should be moved to another CPU.
+ * Even though this will probably make the lower prio task
+ * lose its cache, we do not want to bounce a higher task
+ * around just because it gave up its CPU, perhaps for a
+ * lock?
+ *
+ * For equal prio tasks, we just let the scheduler sort it out.
*/
if (unlikely(rt_task(rq->curr)) &&
+ (rq->curr->rt.nr_cpus_allowed < 2 ||
+ rq->curr->prio < p->prio) &&
(p->rt.nr_cpus_allowed > 1)) {
int cpu = find_lowest_rq(p);
/*
* Preempt the current task with a newly woken task if needed:
*/
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync)
+static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
{
if (p->prio < rq->curr->prio) {
resched_task(rq->curr);
} while (rt_rq);
p = rt_task_of(rt_se);
- p->se.exec_start = rq->clock;
+ p->se.exec_start = rq->clock_task;
return p;
}
for_each_leaf_rt_rq(rt_rq, rq) {
array = &rt_rq->active;
idx = sched_find_first_bit(array->bitmap);
- next_idx:
+next_idx:
if (idx >= MAX_RT_PRIO)
continue;
if (next && next->prio < idx)
continue;
list_for_each_entry(rt_se, array->queue + idx, run_list) {
- struct task_struct *p = rt_task_of(rt_se);
+ struct task_struct *p;
+
+ if (!rt_entity_is_task(rt_se))
+ continue;
+
+ p = rt_task_of(rt_se);
if (pick_rt_task(rq, p, cpu)) {
next = p;
break;
static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
-static inline int pick_optimal_cpu(int this_cpu,
- const struct cpumask *mask)
-{
- int first;
-
- /* "this_cpu" is cheaper to preempt than a remote processor */
- if ((this_cpu != -1) && cpumask_test_cpu(this_cpu, mask))
- return this_cpu;
-
- first = cpumask_first(mask);
- if (first < nr_cpu_ids)
- return first;
-
- return -1;
-}
-
static int find_lowest_rq(struct task_struct *task)
{
struct sched_domain *sd;
struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
int this_cpu = smp_processor_id();
int cpu = task_cpu(task);
- cpumask_var_t domain_mask;
if (task->rt.nr_cpus_allowed == 1)
return -1; /* No other targets possible */
* Otherwise, we consult the sched_domains span maps to figure
* out which cpu is logically closest to our hot cache data.
*/
- if (this_cpu == cpu)
- this_cpu = -1; /* Skip this_cpu opt if the same */
+ if (!cpumask_test_cpu(this_cpu, lowest_mask))
+ this_cpu = -1; /* Skip this_cpu opt if not among lowest */
- if (alloc_cpumask_var(&domain_mask, GFP_ATOMIC)) {
- for_each_domain(cpu, sd) {
- if (sd->flags & SD_WAKE_AFFINE) {
- int best_cpu;
+ for_each_domain(cpu, sd) {
+ if (sd->flags & SD_WAKE_AFFINE) {
+ int best_cpu;
- cpumask_and(domain_mask,
- sched_domain_span(sd),
- lowest_mask);
-
- best_cpu = pick_optimal_cpu(this_cpu,
- domain_mask);
-
- if (best_cpu != -1) {
- free_cpumask_var(domain_mask);
- return best_cpu;
- }
- }
+ /*
+ * "this_cpu" is cheaper to preempt than a
+ * remote processor.
+ */
+ if (this_cpu != -1 &&
+ cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+ return this_cpu;
+
+ best_cpu = cpumask_first_and(lowest_mask,
+ sched_domain_span(sd));
+ if (best_cpu < nr_cpu_ids)
+ return best_cpu;
}
- free_cpumask_var(domain_mask);
}
/*
* just give the caller *something* to work with from the compatible
* locations.
*/
- return pick_optimal_cpu(this_cpu, lowest_mask);
+ if (this_cpu != -1)
+ return this_cpu;
+
+ cpu = cpumask_any(lowest_mask);
+ if (cpu < nr_cpu_ids)
+ return cpu;
+ return -1;
}
/* Will lock the rq it finds */
task_running(rq, task) ||
!task->se.on_rq)) {
- spin_unlock(&lowest_rq->lock);
+ raw_spin_unlock(&lowest_rq->lock);
lowest_rq = NULL;
break;
}
if (!next_task)
return 0;
- retry:
+retry:
if (unlikely(next_task == rq->curr)) {
WARN_ON(1);
return 0;
* but possible)
*/
}
- skip:
+skip:
double_unlock_balance(this_rq, src_rq);
}
* If we are not running and we are not going to reschedule soon, we should
* try to push tasks away now
*/
-static void task_wake_up_rt(struct rq *rq, struct task_struct *p)
+static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
if (!task_running(rq, p) &&
!test_tsk_need_resched(rq->curr) &&
has_pushable_tasks(rq) &&
- p->rt.nr_cpus_allowed > 1)
+ p->rt.nr_cpus_allowed > 1 &&
+ rt_task(rq->curr) &&
+ (rq->curr->rt.nr_cpus_allowed < 2 ||
+ rq->curr->prio < p->prio))
push_rt_tasks(rq);
}
-static unsigned long
-load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, int *this_best_prio)
-{
- /* don't touch RT tasks */
- return 0;
-}
-
-static int
-move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
- struct sched_domain *sd, enum cpu_idle_type idle)
-{
- /* don't touch RT tasks */
- return 0;
-}
-
static void set_cpus_allowed_rt(struct task_struct *p,
const struct cpumask *new_mask)
{
{
unsigned long soft, hard;
- if (!p->signal)
- return;
-
- soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur;
- hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max;
+ /* max may change after cur was read, this will be fixed next tick */
+ soft = task_rlimit(p, RLIMIT_RTTIME);
+ hard = task_rlimit_max(p, RLIMIT_RTTIME);
if (soft != RLIM_INFINITY) {
unsigned long next;
{
struct task_struct *p = rq->curr;
- p->se.exec_start = rq->clock;
+ p->se.exec_start = rq->clock_task;
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
}
+static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
+{
+ /*
+ * Time slice is 0 for SCHED_FIFO tasks
+ */
+ if (task->policy == SCHED_RR)
+ return DEF_TIMESLICE;
+ else
+ return 0;
+}
+
static const struct sched_class rt_sched_class = {
.next = &fair_sched_class,
.enqueue_task = enqueue_task_rt,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_rt,
- .load_balance = load_balance_rt,
- .move_one_task = move_one_task_rt,
.set_cpus_allowed = set_cpus_allowed_rt,
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
.pre_schedule = pre_schedule_rt,
.post_schedule = post_schedule_rt,
- .task_wake_up = task_wake_up_rt,
+ .task_woken = task_woken_rt,
.switched_from = switched_from_rt,
#endif
.set_curr_task = set_curr_task_rt,
.task_tick = task_tick_rt,
+ .get_rr_interval = get_rr_interval_rt,
+
.prio_changed = prio_changed_rt,
.switched_to = switched_to_rt,
};
projects / linux-flexiantxendom0-natty.git / blobdiff