#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO))
/*
- * Some helpers for converting nanosecond timing to jiffy resolution
+ * Helpers for converting nanosecond timing to jiffy resolution
*/
#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
-#define JIFFIES_TO_NS(TIME) ((TIME) * (NSEC_PER_SEC / HZ))
#define NICE_0_LOAD SCHED_LOAD_SCALE
#define NICE_0_SHIFT SCHED_LOAD_SHIFT
* Every task in system belong to this group at bootup.
*/
struct task_group init_task_group = {
- .se = init_sched_entity_p,
+ .se = init_sched_entity_p,
.cfs_rq = init_cfs_rq_p,
};
#ifdef CONFIG_FAIR_USER_SCHED
-# define INIT_TASK_GROUP_LOAD 2*NICE_0_LOAD
+# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else
# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
#endif
-#define MIN_GROUP_SHARES 2
+#define MIN_GROUP_SHARES 2
static int init_task_group_load = INIT_TASK_GROUP_LOAD;
struct rt_prio_array active;
int rt_load_balance_idx;
struct list_head *rt_load_balance_head, *rt_load_balance_curr;
+ unsigned long rt_nr_running;
+ unsigned long rt_nr_migratory;
+ /* highest queued rt task prio */
+ int highest_prio;
+ int overloaded;
};
+#ifdef CONFIG_SMP
+
+/*
+ * We add the notion of a root-domain which will be used to define per-domain
+ * variables. Each exclusive cpuset essentially defines an island domain by
+ * fully partitioning the member cpus from any other cpuset. Whenever a new
+ * exclusive cpuset is created, we also create and attach a new root-domain
+ * object.
+ *
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+struct root_domain {
+ atomic_t refcount;
+ cpumask_t span;
+ cpumask_t online;
+
+ /*
+ * The "RT overload" flag: it gets set if a CPU has more than
+ * one runnable RT task.
+ */
+ cpumask_t rto_mask;
+ atomic_t rto_count;
+};
+
+static struct root_domain def_root_domain;
+
+#endif
+
/*
* This is the main, per-CPU runqueue data structure.
*
atomic_t nr_iowait;
#ifdef CONFIG_SMP
+ struct root_domain *rd;
struct sched_domain *sd;
/* For active balancing */
update_load_sub(&rq->load, load);
}
+#ifdef CONFIG_SMP
+static unsigned long source_load(int cpu, int type);
+static unsigned long target_load(int cpu, int type);
+static unsigned long cpu_avg_load_per_task(int cpu);
+static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
+#endif /* CONFIG_SMP */
+
#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
/*
* Is this task likely cache-hot:
*/
-static inline int
+static int
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
{
s64 delta;
/*
* Return the average load per task on the cpu's run queue
*/
-static inline unsigned long cpu_avg_load_per_task(int cpu)
+static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
#endif /* CONFIG_SMP */
-/*
- * wake_idle() will wake a task on an idle cpu if task->cpu is
- * not idle and an idle cpu is available. The span of cpus to
- * search starts with cpus closest then further out as needed,
- * so we always favor a closer, idle cpu.
- *
- * Returns the CPU we should wake onto.
- */
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-static int wake_idle(int cpu, struct task_struct *p)
-{
- cpumask_t tmp;
- struct sched_domain *sd;
- int i;
-
- /*
- * If it is idle, then it is the best cpu to run this task.
- *
- * This cpu is also the best, if it has more than one task already.
- * Siblings must be also busy(in most cases) as they didn't already
- * pickup the extra load from this cpu and hence we need not check
- * sibling runqueue info. This will avoid the checks and cache miss
- * penalities associated with that.
- */
- if (idle_cpu(cpu) || cpu_rq(cpu)->nr_running > 1)
- return cpu;
-
- for_each_domain(cpu, sd) {
- if (sd->flags & SD_WAKE_IDLE) {
- cpus_and(tmp, sd->span, p->cpus_allowed);
- for_each_cpu_mask(i, tmp) {
- if (idle_cpu(i)) {
- if (i != task_cpu(p)) {
- schedstat_inc(p,
- se.nr_wakeups_idle);
- }
- return i;
- }
- }
- } else {
- break;
- }
- }
- return cpu;
-}
-#else
-static inline int wake_idle(int cpu, struct task_struct *p)
-{
- return cpu;
-}
-#endif
-
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
long old_state;
struct rq *rq;
#ifdef CONFIG_SMP
- struct sched_domain *sd, *this_sd = NULL;
- unsigned long load, this_load;
int new_cpu;
#endif
if (unlikely(task_running(rq, p)))
goto out_activate;
- new_cpu = cpu;
-
- schedstat_inc(rq, ttwu_count);
- if (cpu == this_cpu) {
- schedstat_inc(rq, ttwu_local);
- goto out_set_cpu;
- }
-
- for_each_domain(this_cpu, sd) {
- if (cpu_isset(cpu, sd->span)) {
- schedstat_inc(sd, ttwu_wake_remote);
- this_sd = sd;
- break;
- }
- }
-
- if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
- goto out_set_cpu;
-
- /*
- * Check for affine wakeup and passive balancing possibilities.
- */
- if (this_sd) {
- int idx = this_sd->wake_idx;
- unsigned int imbalance;
-
- imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
-
- load = source_load(cpu, idx);
- this_load = target_load(this_cpu, idx);
-
- new_cpu = this_cpu; /* Wake to this CPU if we can */
-
- if (this_sd->flags & SD_WAKE_AFFINE) {
- unsigned long tl = this_load;
- unsigned long tl_per_task;
-
- /*
- * Attract cache-cold tasks on sync wakeups:
- */
- if (sync && !task_hot(p, rq->clock, this_sd))
- goto out_set_cpu;
-
- schedstat_inc(p, se.nr_wakeups_affine_attempts);
- tl_per_task = cpu_avg_load_per_task(this_cpu);
-
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync)
- tl -= current->se.load.weight;
-
- if ((tl <= load &&
- tl + target_load(cpu, idx) <= tl_per_task) ||
- 100*(tl + p->se.load.weight) <= imbalance*load) {
- /*
- * This domain has SD_WAKE_AFFINE and
- * p is cache cold in this domain, and
- * there is no bad imbalance.
- */
- schedstat_inc(this_sd, ttwu_move_affine);
- schedstat_inc(p, se.nr_wakeups_affine);
- goto out_set_cpu;
- }
- }
-
- /*
- * Start passive balancing when half the imbalance_pct
- * limit is reached.
- */
- if (this_sd->flags & SD_WAKE_BALANCE) {
- if (imbalance*this_load <= 100*load) {
- schedstat_inc(this_sd, ttwu_move_balance);
- schedstat_inc(p, se.nr_wakeups_passive);
- goto out_set_cpu;
- }
- }
- }
-
- new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
-out_set_cpu:
- new_cpu = wake_idle(new_cpu, p);
+ new_cpu = p->sched_class->select_task_rq(p, sync);
if (new_cpu != cpu) {
set_task_cpu(p, new_cpu);
task_rq_unlock(rq, &flags);
cpu = task_cpu(p);
}
+#ifdef CONFIG_SCHEDSTATS
+ schedstat_inc(rq, ttwu_count);
+ if (cpu == this_cpu)
+ schedstat_inc(rq, ttwu_local);
+ else {
+ struct sched_domain *sd;
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(cpu, sd->span)) {
+ schedstat_inc(sd, ttwu_wake_remote);
+ break;
+ }
+ }
+ }
+
+#endif
+
+
out_activate:
#endif /* CONFIG_SMP */
schedstat_inc(p, se.nr_wakeups);
out_running:
p->state = TASK_RUNNING;
+ wakeup_balance_rt(rq, p);
out:
task_rq_unlock(rq, &flags);
inc_nr_running(p, rq);
}
check_preempt_curr(rq, p);
+ wakeup_balance_rt(rq, p);
task_rq_unlock(rq, &flags);
}
prev_state = prev->state;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
+ schedule_tail_balance_rt(rq);
+
fire_sched_in_preempt_notifiers(current);
if (mm)
mmdrop(mm);
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
-static void double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
{
+ int ret = 0;
+
if (unlikely(!irqs_disabled())) {
/* printk() doesn't work good under rq->lock */
spin_unlock(&this_rq->lock);
spin_unlock(&this_rq->lock);
spin_lock(&busiest->lock);
spin_lock(&this_rq->lock);
+ ret = 1;
} else
spin_lock(&busiest->lock);
}
+ return ret;
}
/*
switch_count = &prev->nvcsw;
}
+ schedule_balance_rt(rq, prev);
+
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
static const char stat_nam[] = "RSDTtZX";
-static void show_task(struct task_struct *p)
+void sched_show_task(struct task_struct *p)
{
unsigned long free = 0;
unsigned state;
*/
touch_nmi_watchdog();
if (!state_filter || (p->state & state_filter))
- show_task(p);
+ sched_show_task(p);
} while_each_thread(g, p);
touch_all_softlockup_watchdogs();
goto out;
}
- p->cpus_allowed = new_mask;
+ if (p->sched_class->set_cpus_allowed)
+ p->sched_class->set_cpus_allowed(p, &new_mask);
+ else {
+ p->cpus_allowed = new_mask;
+ p->nr_cpus_allowed = cpus_weight(new_mask);
+ }
+
/* Can the task run on the task's current CPU? If so, we're done */
if (cpu_isset(task_cpu(p), new_mask))
goto out;
case CPU_ONLINE_FROZEN:
/* Strictly unnecessary, as first user will wake it. */
wake_up_process(cpu_rq(cpu)->migration_thread);
+
+ /* Update our root-domain */
+ rq = cpu_rq(cpu);
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpu_isset(cpu, rq->rd->span));
+ cpu_set(cpu, rq->rd->online);
+ }
+ spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
}
spin_unlock_irq(&rq->lock);
break;
+
+ case CPU_DOWN_PREPARE:
+ /* Update our root-domain */
+ rq = cpu_rq(cpu);
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->rd) {
+ BUG_ON(!cpu_isset(cpu, rq->rd->span));
+ cpu_clear(cpu, rq->rd->online);
+ }
+ spin_unlock_irqrestore(&rq->lock, flags);
+ break;
#endif
}
return NOTIFY_OK;
return 1;
}
+static void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+ unsigned long flags;
+ const struct sched_class *class;
+
+ spin_lock_irqsave(&rq->lock, flags);
+
+ if (rq->rd) {
+ struct root_domain *old_rd = rq->rd;
+
+ for (class = sched_class_highest; class; class = class->next) {
+ if (class->leave_domain)
+ class->leave_domain(rq);
+ }
+
+ if (atomic_dec_and_test(&old_rd->refcount))
+ kfree(old_rd);
+ }
+
+ atomic_inc(&rd->refcount);
+ rq->rd = rd;
+
+ for (class = sched_class_highest; class; class = class->next) {
+ if (class->join_domain)
+ class->join_domain(rq);
+ }
+
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static void init_rootdomain(struct root_domain *rd, const cpumask_t *map)
+{
+ memset(rd, 0, sizeof(*rd));
+
+ rd->span = *map;
+ cpus_and(rd->online, rd->span, cpu_online_map);
+}
+
+static void init_defrootdomain(void)
+{
+ cpumask_t cpus = CPU_MASK_ALL;
+
+ init_rootdomain(&def_root_domain, &cpus);
+ atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(const cpumask_t *map)
+{
+ struct root_domain *rd;
+
+ rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+ if (!rd)
+ return NULL;
+
+ init_rootdomain(rd, map);
+
+ return rd;
+}
+
/*
- * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
* hold the hotplug lock.
*/
-static void cpu_attach_domain(struct sched_domain *sd, int cpu)
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
struct rq *rq = cpu_rq(cpu);
struct sched_domain *tmp;
sched_domain_debug(sd, cpu);
+ rq_attach_root(rq, rd);
rcu_assign_pointer(rq->sd, sd);
}
static int build_sched_domains(const cpumask_t *cpu_map)
{
int i;
+ struct root_domain *rd;
#ifdef CONFIG_NUMA
struct sched_group **sched_group_nodes = NULL;
int sd_allnodes = 0;
sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
+ rd = alloc_rootdomain(cpu_map);
+ if (!rd) {
+ printk(KERN_WARNING "Cannot alloc root domain\n");
+ return -ENOMEM;
+ }
+
/*
* Set up domains for cpus specified by the cpu_map.
*/
#else
sd = &per_cpu(phys_domains, i);
#endif
- cpu_attach_domain(sd, i);
+ cpu_attach_domain(sd, rd, i);
}
return 0;
unregister_sched_domain_sysctl();
for_each_cpu_mask(i, *cpu_map)
- cpu_attach_domain(NULL, i);
+ cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
arch_destroy_sched_domains(cpu_map);
}
int highest_cpu = 0;
int i, j;
+#ifdef CONFIG_SMP
+ init_defrootdomain();
+#endif
+
for_each_possible_cpu(i) {
struct rt_prio_array *array;
struct rq *rq;
rq->cpu_load[j] = 0;
#ifdef CONFIG_SMP
rq->sd = NULL;
+ rq->rd = NULL;
+ rq_attach_root(rq, &def_root_domain);
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
rq->cpu = i;
rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
+ rq->rt.highest_prio = MAX_RT_PRIO;
+ rq->rt.overloaded = 0;
#endif
atomic_set(&rq->nr_iowait, 0);
for_each_cpu_mask(i, sdspan)
total_load += tg->cfs_rq[i]->load.weight;
- /* Nothing to do if this group has no load */
+ /* Nothing to do if this group has no load */
if (!total_load)
continue;