* by Peter Williams
* 2007-05-06 Interactivity improvements to CFS by Mike Galbraith
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
+ * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins,
+ * Thomas Gleixner, Mike Kravetz
*/
#include <linux/mm.h>
#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
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
struct cfs_rq **cfs_rq;
+
+ /*
+ * shares assigned to a task group governs how much of cpu bandwidth
+ * is allocated to the group. The more shares a group has, the more is
+ * the cpu bandwidth allocated to it.
+ *
+ * For ex, lets say that there are three task groups, A, B and C which
+ * have been assigned shares 1000, 2000 and 3000 respectively. Then,
+ * cpu bandwidth allocated by the scheduler to task groups A, B and C
+ * should be:
+ *
+ * Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
+ * Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
+ * Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
+ *
+ * The weight assigned to a task group's schedulable entities on every
+ * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
+ * group's shares. For ex: lets say that task group A has been
+ * assigned shares of 1000 and there are two CPUs in a system. Then,
+ *
+ * tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
+ *
+ * Note: It's not necessary that each of a task's group schedulable
+ * entity have the same weight on all CPUs. If the group
+ * has 2 of its tasks on CPU0 and 1 task on CPU1, then a
+ * better distribution of weight could be:
+ *
+ * tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
+ * tg_A->se[1]->load.weight = 1/2 * 2000 = 667
+ *
+ * rebalance_shares() is responsible for distributing the shares of a
+ * task groups like this among the group's schedulable entities across
+ * cpus.
+ *
+ */
unsigned long shares;
- /* spinlock to serialize modification to shares */
- spinlock_t lock;
+
struct rcu_head rcu;
};
static struct sched_entity *init_sched_entity_p[NR_CPUS];
static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
+/* task_group_mutex serializes add/remove of task groups and also changes to
+ * a task group's cpu shares.
+ */
+static DEFINE_MUTEX(task_group_mutex);
+
+/* doms_cur_mutex serializes access to doms_cur[] array */
+static DEFINE_MUTEX(doms_cur_mutex);
+
+#ifdef CONFIG_SMP
+/* kernel thread that runs rebalance_shares() periodically */
+static struct task_struct *lb_monitor_task;
+static int load_balance_monitor(void *unused);
+#endif
+
+static void set_se_shares(struct sched_entity *se, unsigned long shares);
+
/* Default task group.
* 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_GRP_LOAD 2*NICE_0_LOAD
+# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else
-# define INIT_TASK_GRP_LOAD NICE_0_LOAD
+# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
#endif
-static int init_task_group_load = INIT_TASK_GRP_LOAD;
+#define MIN_GROUP_SHARES 2
+
+static int init_task_group_load = INIT_TASK_GROUP_LOAD;
/* return group to which a task belongs */
static inline struct task_group *task_group(struct task_struct *p)
p->se.parent = task_group(p)->se[cpu];
}
+static inline void lock_task_group_list(void)
+{
+ mutex_lock(&task_group_mutex);
+}
+
+static inline void unlock_task_group_list(void)
+{
+ mutex_unlock(&task_group_mutex);
+}
+
+static inline void lock_doms_cur(void)
+{
+ mutex_lock(&doms_cur_mutex);
+}
+
+static inline void unlock_doms_cur(void)
+{
+ mutex_unlock(&doms_cur_mutex);
+}
+
#else
static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) { }
+static inline void lock_task_group_list(void) { }
+static inline void unlock_task_group_list(void) { }
+static inline void lock_doms_cur(void) { }
+static inline void unlock_doms_cur(void) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
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.
+ *
+ */
+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;
};
+/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+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 */
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static DEFINE_MUTEX(sched_hotcpu_mutex);
static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
{
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif
+static inline void inc_cpu_load(struct rq *rq, unsigned long load)
+{
+ update_load_add(&rq->load, load);
+}
+
+static inline void dec_cpu_load(struct rq *rq, unsigned long load)
+{
+ 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"
#define sched_class_highest (&rt_sched_class)
-/*
- * Update delta_exec, delta_fair fields for rq.
- *
- * delta_fair clock advances at a rate inversely proportional to
- * total load (rq->load.weight) on the runqueue, while
- * delta_exec advances at the same rate as wall-clock (provided
- * cpu is not idle).
- *
- * delta_exec / delta_fair is a measure of the (smoothened) load on this
- * runqueue over any given interval. This (smoothened) load is used
- * during load balance.
- *
- * This function is called /before/ updating rq->load
- * and when switching tasks.
- */
-static inline void inc_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_add(&rq->load, p->se.load.weight);
-}
-
-static inline void dec_load(struct rq *rq, const struct task_struct *p)
-{
- update_load_sub(&rq->load, p->se.load.weight);
-}
-
static void inc_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running++;
- inc_load(rq, p);
}
static void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
- dec_load(rq, p);
}
static void set_load_weight(struct task_struct *p)
#endif
}
+static inline void check_class_changed(struct rq *rq, struct task_struct *p,
+ const struct sched_class *prev_class,
+ int oldprio, int running)
+{
+ 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);
+}
+
#ifdef CONFIG_SMP
/*
* 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
unsigned long flags;
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
rq = task_rq_lock(p, &flags);
old_state = p->state;
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);
- if (new_cpu != cpu) {
- set_task_cpu(p, new_cpu);
+ cpu = p->sched_class->select_task_rq(p, sync);
+ if (cpu != orig_cpu) {
+ set_task_cpu(p, cpu);
task_rq_unlock(rq, &flags);
/* might preempt at this point */
rq = task_rq_lock(p, &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;
+#ifdef CONFIG_SMP
+ if (p->sched_class->task_wake_up)
+ p->sched_class->task_wake_up(rq, p);
+#endif
out:
task_rq_unlock(rq, &flags);
p->se.wait_max = 0;
#endif
- INIT_LIST_HEAD(&p->run_list);
+ INIT_LIST_HEAD(&p->rt.run_list);
p->se.on_rq = 0;
#ifdef CONFIG_PREEMPT_NOTIFIERS
inc_nr_running(p, rq);
}
check_preempt_curr(rq, p);
+#ifdef CONFIG_SMP
+ if (p->sched_class->task_wake_up)
+ p->sched_class->task_wake_up(rq, p);
+#endif
task_rq_unlock(rq, &flags);
}
prev_state = prev->state;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
+#ifdef CONFIG_SMP
+ if (current->sched_class->post_schedule)
+ current->sched_class->post_schedule(rq);
+#endif
+
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;
}
+#ifdef CONFIG_SMP
+ if (prev->sched_class->pre_schedule)
+ prev->sched_class->pre_schedule(rq, prev);
+#endif
+
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
unsigned long flags;
int oldprio, on_rq, running;
struct rq *rq;
+ const struct sched_class *prev_class = p->sched_class;
BUG_ON(prio < 0 || prio > MAX_PRIO);
if (on_rq) {
if (running)
p->sched_class->set_curr_task(rq);
+
enqueue_task(rq, p, 0);
- /*
- * 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 (p->prio > oldprio)
- resched_task(rq->curr);
- } else {
- check_preempt_curr(rq, p);
- }
+
+ check_class_changed(rq, p, prev_class, oldprio, running);
}
task_rq_unlock(rq, &flags);
}
goto out_unlock;
}
on_rq = p->se.on_rq;
- if (on_rq) {
+ if (on_rq)
dequeue_task(rq, p, 0);
- dec_load(rq, p);
- }
p->static_prio = NICE_TO_PRIO(nice);
set_load_weight(p);
if (on_rq) {
enqueue_task(rq, p, 0);
- inc_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
{
int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
+ const struct sched_class *prev_class = p->sched_class;
struct rq *rq;
/* may grab non-irq protected spin_locks */
if (on_rq) {
if (running)
p->sched_class->set_curr_task(rq);
+
activate_task(rq, p, 0);
- /*
- * 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 (p->prio > oldprio)
- resched_task(rq->curr);
- } else {
- check_preempt_curr(rq, p);
- }
+
+ check_class_changed(rq, p, prev_class, oldprio, running);
}
__task_rq_unlock(rq);
spin_unlock_irqrestore(&p->pi_lock, flags);
struct task_struct *p;
int retval;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
read_lock(&tasklist_lock);
p = find_process_by_pid(pid);
if (!p) {
read_unlock(&tasklist_lock);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return -ESRCH;
}
}
out_unlock:
put_task_struct(p);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return retval;
}
struct task_struct *p;
int retval;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
read_lock(&tasklist_lock);
retval = -ESRCH;
out_unlock:
read_unlock(&tasklist_lock);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return retval;
}
} while (need_resched());
}
-int __sched cond_resched(void)
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PREEMPT_VOLUNTARY)
+int __sched _cond_resched(void)
{
if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
system_state == SYSTEM_RUNNING) {
}
return 0;
}
-EXPORT_SYMBOL(cond_resched);
+EXPORT_SYMBOL(_cond_resched);
+#endif
/*
* cond_resched_lock() - if a reschedule is pending, drop the given lock,
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;
struct rq *rq;
switch (action) {
- case CPU_LOCK_ACQUIRE:
- mutex_lock(&sched_hotcpu_mutex);
- break;
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
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;
-#endif
- case CPU_LOCK_RELEASE:
- mutex_unlock(&sched_hotcpu_mutex);
+
+ 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);
+ }
+
+ cpu_clear(rq->cpu, old_rd->span);
+ cpu_clear(rq->cpu, old_rd->online);
+
+ if (atomic_dec_and_test(&old_rd->refcount))
+ kfree(old_rd);
+ }
+
+ atomic_inc(&rd->refcount);
+ rq->rd = rd;
+
+ cpu_set(rq->cpu, rd->span);
+ if (cpu_isset(rq->cpu, cpu_online_map))
+ cpu_set(rq->cpu, rd->online);
+
+ 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)
+{
+ memset(rd, 0, sizeof(*rd));
+
+ cpus_clear(rd->span);
+ cpus_clear(rd->online);
+}
+
+static void init_defrootdomain(void)
+{
+ init_rootdomain(&def_root_domain);
+ atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+ struct root_domain *rd;
+
+ rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+ if (!rd)
+ return NULL;
+
+ init_rootdomain(rd);
+
+ 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();
+ 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 i, j;
+ lock_doms_cur();
+
/* always unregister in case we don't destroy any domains */
unregister_sched_domain_sysctl();
ndoms_cur = ndoms_new;
register_sched_domain_sysctl();
+
+ unlock_doms_cur();
}
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
{
int err;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
detach_destroy_domains(&cpu_online_map);
err = arch_init_sched_domains(&cpu_online_map);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
return err;
}
{
cpumask_t non_isolated_cpus;
- mutex_lock(&sched_hotcpu_mutex);
+ get_online_cpus();
arch_init_sched_domains(&cpu_online_map);
cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
if (cpus_empty(non_isolated_cpus))
cpu_set(smp_processor_id(), non_isolated_cpus);
- mutex_unlock(&sched_hotcpu_mutex);
+ put_online_cpus();
/* XXX: Theoretical race here - CPU may be hotplugged now */
hotcpu_notifier(update_sched_domains, 0);
if (set_cpus_allowed(current, non_isolated_cpus) < 0)
BUG();
sched_init_granularity();
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ if (nr_cpu_ids == 1)
+ return;
+
+ lb_monitor_task = kthread_create(load_balance_monitor, NULL,
+ "group_balance");
+ if (!IS_ERR(lb_monitor_task)) {
+ lb_monitor_task->flags |= PF_NOFREEZE;
+ wake_up_process(lb_monitor_task);
+ } else {
+ printk(KERN_ERR "Could not create load balance monitor thread"
+ "(error = %ld) \n", PTR_ERR(lb_monitor_task));
+ }
+#endif
}
#else
void __init sched_init_smp(void)
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;
se->parent = NULL;
}
init_task_group.shares = init_task_group_load;
- spin_lock_init(&init_task_group.lock);
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
rq->cpu_load[j] = 0;
#ifdef CONFIG_SMP
rq->sd = NULL;
+ rq->rd = NULL;
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;
+ rq_attach_root(rq, &def_root_domain);
#endif
atomic_set(&rq->nr_iowait, 0);
#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_SMP
+/*
+ * distribute shares of all task groups among their schedulable entities,
+ * to reflect load distrbution across cpus.
+ */
+static int rebalance_shares(struct sched_domain *sd, int this_cpu)
+{
+ struct cfs_rq *cfs_rq;
+ struct rq *rq = cpu_rq(this_cpu);
+ cpumask_t sdspan = sd->span;
+ int balanced = 1;
+
+ /* Walk thr' all the task groups that we have */
+ for_each_leaf_cfs_rq(rq, cfs_rq) {
+ int i;
+ unsigned long total_load = 0, total_shares;
+ struct task_group *tg = cfs_rq->tg;
+
+ /* Gather total task load of this group across cpus */
+ for_each_cpu_mask(i, sdspan)
+ total_load += tg->cfs_rq[i]->load.weight;
+
+ /* Nothing to do if this group has no load */
+ if (!total_load)
+ continue;
+
+ /*
+ * tg->shares represents the number of cpu shares the task group
+ * is eligible to hold on a single cpu. On N cpus, it is
+ * eligible to hold (N * tg->shares) number of cpu shares.
+ */
+ total_shares = tg->shares * cpus_weight(sdspan);
+
+ /*
+ * redistribute total_shares across cpus as per the task load
+ * distribution.
+ */
+ for_each_cpu_mask(i, sdspan) {
+ unsigned long local_load, local_shares;
+
+ local_load = tg->cfs_rq[i]->load.weight;
+ local_shares = (local_load * total_shares) / total_load;
+ if (!local_shares)
+ local_shares = MIN_GROUP_SHARES;
+ if (local_shares == tg->se[i]->load.weight)
+ continue;
+
+ spin_lock_irq(&cpu_rq(i)->lock);
+ set_se_shares(tg->se[i], local_shares);
+ spin_unlock_irq(&cpu_rq(i)->lock);
+ balanced = 0;
+ }
+ }
+
+ return balanced;
+}
+
+/*
+ * How frequently should we rebalance_shares() across cpus?
+ *
+ * The more frequently we rebalance shares, the more accurate is the fairness
+ * of cpu bandwidth distribution between task groups. However higher frequency
+ * also implies increased scheduling overhead.
+ *
+ * sysctl_sched_min_bal_int_shares represents the minimum interval between
+ * consecutive calls to rebalance_shares() in the same sched domain.
+ *
+ * sysctl_sched_max_bal_int_shares represents the maximum interval between
+ * consecutive calls to rebalance_shares() in the same sched domain.
+ *
+ * These settings allows for the appropriate tradeoff between accuracy of
+ * fairness and the associated overhead.
+ *
+ */
+
+/* default: 8ms, units: milliseconds */
+const_debug unsigned int sysctl_sched_min_bal_int_shares = 8;
+
+/* default: 128ms, units: milliseconds */
+const_debug unsigned int sysctl_sched_max_bal_int_shares = 128;
+
+/* kernel thread that runs rebalance_shares() periodically */
+static int load_balance_monitor(void *unused)
+{
+ unsigned int timeout = sysctl_sched_min_bal_int_shares;
+ struct sched_param schedparm;
+ int ret;
+
+ /*
+ * We don't want this thread's execution to be limited by the shares
+ * assigned to default group (init_task_group). Hence make it run
+ * as a SCHED_RR RT task at the lowest priority.
+ */
+ schedparm.sched_priority = 1;
+ ret = sched_setscheduler(current, SCHED_RR, &schedparm);
+ if (ret)
+ printk(KERN_ERR "Couldn't set SCHED_RR policy for load balance"
+ " monitor thread (error = %d) \n", ret);
+
+ while (!kthread_should_stop()) {
+ int i, cpu, balanced = 1;
+
+ /* Prevent cpus going down or coming up */
+ get_online_cpus();
+ /* lockout changes to doms_cur[] array */
+ lock_doms_cur();
+ /*
+ * Enter a rcu read-side critical section to safely walk rq->sd
+ * chain on various cpus and to walk task group list
+ * (rq->leaf_cfs_rq_list) in rebalance_shares().
+ */
+ rcu_read_lock();
+
+ for (i = 0; i < ndoms_cur; i++) {
+ cpumask_t cpumap = doms_cur[i];
+ struct sched_domain *sd = NULL, *sd_prev = NULL;
+
+ cpu = first_cpu(cpumap);
+
+ /* Find the highest domain at which to balance shares */
+ for_each_domain(cpu, sd) {
+ if (!(sd->flags & SD_LOAD_BALANCE))
+ continue;
+ sd_prev = sd;
+ }
+
+ sd = sd_prev;
+ /* sd == NULL? No load balance reqd in this domain */
+ if (!sd)
+ continue;
+
+ balanced &= rebalance_shares(sd, cpu);
+ }
+
+ rcu_read_unlock();
+
+ unlock_doms_cur();
+ put_online_cpus();
+
+ if (!balanced)
+ timeout = sysctl_sched_min_bal_int_shares;
+ else if (timeout < sysctl_sched_max_bal_int_shares)
+ timeout *= 2;
+
+ msleep_interruptible(timeout);
+ }
+
+ return 0;
+}
+#endif /* CONFIG_SMP */
+
/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(void)
{
se->parent = NULL;
}
+ tg->shares = NICE_0_LOAD;
+
+ lock_task_group_list();
for_each_possible_cpu(i) {
rq = cpu_rq(i);
cfs_rq = tg->cfs_rq[i];
list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
}
-
- tg->shares = NICE_0_LOAD;
- spin_lock_init(&tg->lock);
+ unlock_task_group_list();
return tg;
struct cfs_rq *cfs_rq = NULL;
int i;
+ lock_task_group_list();
for_each_possible_cpu(i) {
cfs_rq = tg->cfs_rq[i];
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
}
+ unlock_task_group_list();
BUG_ON(!cfs_rq);
task_rq_unlock(rq, &flags);
}
+/* rq->lock to be locked by caller */
static void set_se_shares(struct sched_entity *se, unsigned long shares)
{
struct cfs_rq *cfs_rq = se->cfs_rq;
struct rq *rq = cfs_rq->rq;
int on_rq;
- spin_lock_irq(&rq->lock);
+ if (!shares)
+ shares = MIN_GROUP_SHARES;
on_rq = se->on_rq;
- if (on_rq)
+ if (on_rq) {
dequeue_entity(cfs_rq, se, 0);
+ dec_cpu_load(rq, se->load.weight);
+ }
se->load.weight = shares;
se->load.inv_weight = div64_64((1ULL<<32), shares);
- if (on_rq)
+ if (on_rq) {
enqueue_entity(cfs_rq, se, 0);
-
- spin_unlock_irq(&rq->lock);
+ inc_cpu_load(rq, se->load.weight);
+ }
}
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
+ struct cfs_rq *cfs_rq;
+ struct rq *rq;
+
+ lock_task_group_list();
+ if (tg->shares == shares)
+ goto done;
+
+ if (shares < MIN_GROUP_SHARES)
+ shares = MIN_GROUP_SHARES;
/*
- * A weight of 0 or 1 can cause arithmetics problems.
- * (The default weight is 1024 - so there's no practical
- * limitation from this.)
+ * Prevent any load balance activity (rebalance_shares,
+ * load_balance_fair) from referring to this group first,
+ * by taking it off the rq->leaf_cfs_rq_list on each cpu.
*/
- if (shares < 2)
- shares = 2;
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ }
- spin_lock(&tg->lock);
- if (tg->shares == shares)
- goto done;
+ /* wait for any ongoing reference to this group to finish */
+ synchronize_sched();
+ /*
+ * Now we are free to modify the group's share on each cpu
+ * w/o tripping rebalance_share or load_balance_fair.
+ */
tg->shares = shares;
- for_each_possible_cpu(i)
+ for_each_possible_cpu(i) {
+ spin_lock_irq(&cpu_rq(i)->lock);
set_se_shares(tg->se[i], shares);
+ spin_unlock_irq(&cpu_rq(i)->lock);
+ }
+ /*
+ * Enable load balance activity on this group, by inserting it back on
+ * each cpu's rq->leaf_cfs_rq_list.
+ */
+ for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+ cfs_rq = tg->cfs_rq[i];
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+ }
done:
- spin_unlock(&tg->lock);
+ unlock_task_group_list();
return 0;
}