struct list_head queue[MAX_RT_PRIO];
};
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED
#include <linux/cgroup.h>
/* task group related information */
struct task_group {
-#ifdef CONFIG_FAIR_CGROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
struct cgroup_subsys_state css;
#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
struct cfs_rq **cfs_rq;
+ unsigned long shares;
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
struct sched_rt_entity **rt_se;
struct rt_rq **rt_rq;
- unsigned int rt_ratio;
-
- /*
- * 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;
+ u64 rt_runtime;
+#endif
struct rcu_head rcu;
struct list_head list;
};
+#ifdef CONFIG_FAIR_GROUP_SCHED
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
-
static struct sched_entity *init_sched_entity_p[NR_CPUS];
static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
+#endif
+
+#ifdef CONFIG_RT_GROUP_SCHED
+static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
+static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
static struct sched_rt_entity *init_sched_rt_entity_p[NR_CPUS];
static struct rt_rq *init_rt_rq_p[NR_CPUS];
+#endif
-/* task_group_mutex serializes add/remove of task groups and also changes to
+/* task_group_lock serializes add/remove of task groups and also changes to
* a task group's cpu shares.
*/
-static DEFINE_MUTEX(task_group_mutex);
+static DEFINE_SPINLOCK(task_group_lock);
/* 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);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_USER_SCHED
+# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
+#else
+# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
#endif
-static void set_se_shares(struct sched_entity *se, unsigned long shares);
+static int init_task_group_load = INIT_TASK_GROUP_LOAD;
+#endif
/* Default task group.
* Every task in system belong to this group at bootup.
*/
struct task_group init_task_group = {
+#ifdef CONFIG_FAIR_GROUP_SCHED
.se = init_sched_entity_p,
.cfs_rq = init_cfs_rq_p,
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
.rt_se = init_sched_rt_entity_p,
.rt_rq = init_rt_rq_p,
-};
-
-#ifdef CONFIG_FAIR_USER_SCHED
-# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
-#else
-# define INIT_TASK_GROUP_LOAD NICE_0_LOAD
#endif
-
-#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)
{
struct task_group *tg;
-#ifdef CONFIG_FAIR_USER_SCHED
+#ifdef CONFIG_USER_SCHED
tg = p->user->tg;
-#elif defined(CONFIG_FAIR_CGROUP_SCHED)
+#elif defined(CONFIG_CGROUP_SCHED)
tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
struct task_group, css);
#else
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
+#ifdef CONFIG_FAIR_GROUP_SCHED
p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
p->se.parent = task_group(p)->se[cpu];
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
p->rt.rt_rq = task_group(p)->rt_rq[cpu];
p->rt.parent = task_group(p)->rt_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);
+#endif
}
static inline void lock_doms_cur(void)
#else
static inline void set_task_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 */
+#endif /* CONFIG_GROUP_SCHED */
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct rt_rq {
struct rt_prio_array active;
unsigned long rt_nr_running;
-#if defined CONFIG_SMP || defined CONFIG_FAIR_GROUP_SCHED
+#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
int highest_prio; /* highest queued rt task prio */
#endif
#ifdef CONFIG_SMP
int rt_throttled;
u64 rt_time;
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_RT_GROUP_SCHED
+ unsigned long rt_nr_boosted;
+
struct rq *rq;
struct list_head leaf_rt_rq_list;
struct task_group *tg;
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
struct list_head leaf_rt_rq_list;
#endif
const_debug unsigned int sysctl_sched_nr_migrate = 32;
/*
- * period over which we measure -rt task cpu usage in ms.
+ * period over which we measure -rt task cpu usage in us.
* default: 1s
*/
-const_debug unsigned int sysctl_sched_rt_period = 1000;
+unsigned int sysctl_sched_rt_period = 1000000;
+
+static __read_mostly int scheduler_running;
-#define SCHED_RT_FRAC_SHIFT 16
-#define SCHED_RT_FRAC (1UL << SCHED_RT_FRAC_SHIFT)
+/*
+ * part of the period that we allow rt tasks to run in us.
+ * default: 0.95s
+ */
+int sysctl_sched_rt_runtime = 950000;
/*
- * ratio of time -rt tasks may consume.
- * default: 95%
+ * single value that denotes runtime == period, ie unlimited time.
*/
-const_debug unsigned int sysctl_sched_rt_ratio = 62259;
+#define RUNTIME_INF ((u64)~0ULL)
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
unsigned long flags;
struct rq *rq;
- local_irq_save(flags);
- rq = cpu_rq(cpu);
/*
* Only call sched_clock() if the scheduler has already been
* initialized (some code might call cpu_clock() very early):
*/
- if (rq->idle)
- update_rq_clock(rq);
+ if (unlikely(!scheduler_running))
+ return 0;
+
+ local_irq_save(flags);
+ rq = cpu_rq(cpu);
+ update_rq_clock(rq);
now = rq->clock;
local_irq_restore(flags);
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);
#define sched_class_highest (&rt_sched_class)
+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)
*/
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
- if (p->state == TASK_UNINTERRUPTIBLE)
+ if (task_contributes_to_load(p))
rq->nr_uninterruptible--;
enqueue_task(rq, p, wakeup);
*/
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
{
- if (p->state == TASK_UNINTERRUPTIBLE)
+ if (task_contributes_to_load(p))
rq->nr_uninterruptible++;
dequeue_task(rq, p, sleep);
long old_state;
struct rq *rq;
+ smp_wmb();
rq = task_rq_lock(p, &flags);
old_state = p->state;
if (!(old_state & state))
return success;
}
-int fastcall wake_up_process(struct task_struct *p)
+int wake_up_process(struct task_struct *p)
{
- return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
- TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
+ return try_to_wake_up(p, TASK_ALL, 0);
}
EXPORT_SYMBOL(wake_up_process);
-int fastcall wake_up_state(struct task_struct *p, unsigned int state)
+int wake_up_state(struct task_struct *p, unsigned int state)
{
return try_to_wake_up(p, state, 0);
}
* that must be done for every newly created context, then puts the task
* on the runqueue and wakes it.
*/
-void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
+void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
unsigned long flags;
struct rq *rq;
#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
-void fastcall add_preempt_count(int val)
+void __kprobes add_preempt_count(int val)
{
/*
* Underflow?
}
EXPORT_SYMBOL(add_preempt_count);
-void fastcall sub_preempt_count(int val)
+void __kprobes sub_preempt_count(int val)
{
/*
* Underflow?
asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
- long *switch_count;
+ unsigned long *switch_count;
struct rq *rq;
int cpu;
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*/
-void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, void *key)
{
unsigned long flags;
/*
* Same as __wake_up but called with the spinlock in wait_queue_head_t held.
*/
-void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
{
__wake_up_common(q, mode, 1, 0, NULL);
}
*
* On UP it can prevent extra preemption.
*/
-void fastcall
+void
__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
{
unsigned long flags;
spin_lock_irqsave(&x->wait.lock, flags);
x->done++;
- __wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
- 1, 0, NULL);
+ __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);
spin_lock_irqsave(&x->wait.lock, flags);
x->done += UINT_MAX/2;
- __wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
- 0, 0, NULL);
+ __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);
wait.flags |= WQ_FLAG_EXCLUSIVE;
__add_wait_queue_tail(&x->wait, &wait);
do {
- if (state == TASK_INTERRUPTIBLE &&
- signal_pending(current)) {
+ if ((state == TASK_INTERRUPTIBLE &&
+ signal_pending(current)) ||
+ (state == TASK_KILLABLE &&
+ fatal_signal_pending(current))) {
__remove_wait_queue(&x->wait, &wait);
return -ERESTARTSYS;
}
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+int __sched wait_for_completion_killable(struct completion *x)
+{
+ long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+ if (t == -ERESTARTSYS)
+ return t;
+ return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
static long __sched
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
{
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:
return -EPERM;
}
+#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * Do not allow realtime tasks into groups that have no runtime
+ * assigned.
+ */
+ if (rt_policy(policy) && task_group(p)->rt_runtime == 0)
+ return -EPERM;
+#endif
+
retval = security_task_setscheduler(p, policy, param);
if (retval)
return retval;
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)
/* delimiter for bitsearch: */
__set_bit(MAX_RT_PRIO, array->bitmap);
-#if defined CONFIG_SMP || defined CONFIG_FAIR_GROUP_SCHED
+#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
rt_rq->highest_prio = MAX_RT_PRIO;
#endif
#ifdef CONFIG_SMP
rt_rq->rt_time = 0;
rt_rq->rt_throttled = 0;
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_RT_GROUP_SCHED
+ rt_rq->rt_nr_boosted = 0;
rt_rq->rq = rq;
#endif
}
se->load.inv_weight = div64_64(1ULL<<32, se->load.weight);
se->parent = NULL;
}
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
static void init_tg_rt_entry(struct rq *rq, struct task_group *tg,
struct rt_rq *rt_rq, struct sched_rt_entity *rt_se,
int cpu, int add)
init_defrootdomain();
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED
list_add(&init_task_group.list, &task_groups);
#endif
&per_cpu(init_cfs_rq, i),
&per_cpu(init_sched_entity, i), i, 1);
- init_task_group.rt_ratio = sysctl_sched_rt_ratio; /* XXX */
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
+ init_task_group.rt_runtime =
+ sysctl_sched_rt_runtime * NSEC_PER_USEC;
INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
init_tg_rt_entry(rq, &init_task_group,
&per_cpu(init_rt_rq, i),
* During early bootup we pretend to be a normal task:
*/
current->sched_class = &fair_sched_class;
+
+ scheduler_running = 1;
}
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
unsigned long flags;
struct rq *rq;
- read_lock_irq(&tasklist_lock);
+ read_lock_irqsave(&tasklist_lock, flags);
do_each_thread(g, p) {
/*
* Only normalize user tasks:
continue;
}
- spin_lock_irqsave(&p->pi_lock, flags);
+ spin_lock(&p->pi_lock);
rq = __task_rq_lock(p);
normalize_task(rq, p);
__task_rq_unlock(rq);
- spin_unlock_irqrestore(&p->pi_lock, flags);
+ spin_unlock(&p->pi_lock);
} while_each_thread(g, p);
- read_unlock_irq(&tasklist_lock);
+ read_unlock_irqrestore(&tasklist_lock, flags);
}
#endif /* CONFIG_MAGIC_SYSRQ */
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_GROUP_SCHED
-#ifdef CONFIG_SMP
-/*
- * distribute shares of all task groups among their schedulable entities,
- * to reflect load distribution across cpus.
- */
-static int rebalance_shares(struct sched_domain *sd, int this_cpu)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void free_fair_sched_group(struct task_group *tg)
{
- 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;
+ int i;
- spin_lock_irq(&cpu_rq(i)->lock);
- set_se_shares(tg->se[i], local_shares);
- spin_unlock_irq(&cpu_rq(i)->lock);
- balanced = 0;
- }
+ for_each_possible_cpu(i) {
+ if (tg->cfs_rq)
+ kfree(tg->cfs_rq[i]);
+ if (tg->se)
+ kfree(tg->se[i]);
}
- return balanced;
+ kfree(tg->cfs_rq);
+ kfree(tg->se);
}
-/*
- * 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 trade-off 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)
+static int alloc_fair_sched_group(struct task_group *tg)
{
- unsigned int timeout = sysctl_sched_min_bal_int_shares;
- struct sched_param schedparm;
- int ret;
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *se;
+ struct rq *rq;
+ int i;
- /*
- * 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);
+ tg->cfs_rq = kzalloc(sizeof(cfs_rq) * NR_CPUS, GFP_KERNEL);
+ if (!tg->cfs_rq)
+ goto err;
+ tg->se = kzalloc(sizeof(se) * NR_CPUS, GFP_KERNEL);
+ if (!tg->se)
+ goto err;
- while (!kthread_should_stop()) {
- int i, cpu, balanced = 1;
+ tg->shares = NICE_0_LOAD;
- /* 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_each_possible_cpu(i) {
+ rq = cpu_rq(i);
- for (i = 0; i < ndoms_cur; i++) {
- cpumask_t cpumap = doms_cur[i];
- struct sched_domain *sd = NULL, *sd_prev = NULL;
+ cfs_rq = kmalloc_node(sizeof(struct cfs_rq),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ if (!cfs_rq)
+ goto err;
- cpu = first_cpu(cpumap);
+ se = kmalloc_node(sizeof(struct sched_entity),
+ GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+ if (!se)
+ goto err;
- /* Find the highest domain at which to balance shares */
- for_each_domain(cpu, sd) {
- if (!(sd->flags & SD_LOAD_BALANCE))
- continue;
- sd_prev = sd;
- }
+ init_tg_cfs_entry(rq, tg, cfs_rq, se, i, 0);
+ }
- sd = sd_prev;
- /* sd == NULL? No load balance reqd in this domain */
- if (!sd)
- continue;
+ return 1;
- balanced &= rebalance_shares(sd, cpu);
- }
+ err:
+ return 0;
+}
- rcu_read_unlock();
+static inline void register_fair_sched_group(struct task_group *tg, int cpu)
+{
+ list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
+ &cpu_rq(cpu)->leaf_cfs_rq_list);
+}
- unlock_doms_cur();
- put_online_cpus();
+static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
+{
+ list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
+}
+#else
+static inline void free_fair_sched_group(struct task_group *tg)
+{
+}
- if (!balanced)
- timeout = sysctl_sched_min_bal_int_shares;
- else if (timeout < sysctl_sched_max_bal_int_shares)
- timeout *= 2;
+static inline int alloc_fair_sched_group(struct task_group *tg)
+{
+ return 1;
+}
- msleep_interruptible(timeout);
- }
+static inline void register_fair_sched_group(struct task_group *tg, int cpu)
+{
+}
- return 0;
+static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
+{
}
-#endif /* CONFIG_SMP */
+#endif
-static void free_sched_group(struct task_group *tg)
+#ifdef CONFIG_RT_GROUP_SCHED
+static void free_rt_sched_group(struct task_group *tg)
{
int i;
for_each_possible_cpu(i) {
- if (tg->cfs_rq)
- kfree(tg->cfs_rq[i]);
- if (tg->se)
- kfree(tg->se[i]);
if (tg->rt_rq)
kfree(tg->rt_rq[i]);
if (tg->rt_se)
kfree(tg->rt_se[i]);
}
- kfree(tg->cfs_rq);
- kfree(tg->se);
kfree(tg->rt_rq);
kfree(tg->rt_se);
- kfree(tg);
}
-/* allocate runqueue etc for a new task group */
-struct task_group *sched_create_group(void)
+static int alloc_rt_sched_group(struct task_group *tg)
{
- struct task_group *tg;
- struct cfs_rq *cfs_rq;
- struct sched_entity *se;
struct rt_rq *rt_rq;
struct sched_rt_entity *rt_se;
struct rq *rq;
int i;
- tg = kzalloc(sizeof(*tg), GFP_KERNEL);
- if (!tg)
- return ERR_PTR(-ENOMEM);
-
- tg->cfs_rq = kzalloc(sizeof(cfs_rq) * NR_CPUS, GFP_KERNEL);
- if (!tg->cfs_rq)
- goto err;
- tg->se = kzalloc(sizeof(se) * NR_CPUS, GFP_KERNEL);
- if (!tg->se)
- goto err;
tg->rt_rq = kzalloc(sizeof(rt_rq) * NR_CPUS, GFP_KERNEL);
if (!tg->rt_rq)
goto err;
if (!tg->rt_se)
goto err;
- tg->shares = NICE_0_LOAD;
- tg->rt_ratio = 0; /* XXX */
+ tg->rt_runtime = 0;
for_each_possible_cpu(i) {
rq = cpu_rq(i);
- cfs_rq = kmalloc_node(sizeof(struct cfs_rq),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
- if (!cfs_rq)
- goto err;
-
- se = kmalloc_node(sizeof(struct sched_entity),
- GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
- if (!se)
- goto err;
-
rt_rq = kmalloc_node(sizeof(struct rt_rq),
GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
if (!rt_rq)
if (!rt_se)
goto err;
- init_tg_cfs_entry(rq, tg, cfs_rq, se, i, 0);
init_tg_rt_entry(rq, tg, rt_rq, rt_se, i, 0);
}
- lock_task_group_list();
+ return 1;
+
+ err:
+ return 0;
+}
+
+static inline void register_rt_sched_group(struct task_group *tg, int cpu)
+{
+ list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
+ &cpu_rq(cpu)->leaf_rt_rq_list);
+}
+
+static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
+{
+ list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
+}
+#else
+static inline void free_rt_sched_group(struct task_group *tg)
+{
+}
+
+static inline int alloc_rt_sched_group(struct task_group *tg)
+{
+ return 1;
+}
+
+static inline void register_rt_sched_group(struct task_group *tg, int cpu)
+{
+}
+
+static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
+{
+}
+#endif
+
+static void free_sched_group(struct task_group *tg)
+{
+ free_fair_sched_group(tg);
+ free_rt_sched_group(tg);
+ kfree(tg);
+}
+
+/* allocate runqueue etc for a new task group */
+struct task_group *sched_create_group(void)
+{
+ struct task_group *tg;
+ unsigned long flags;
+ int i;
+
+ tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+ if (!tg)
+ return ERR_PTR(-ENOMEM);
+
+ if (!alloc_fair_sched_group(tg))
+ goto err;
+
+ if (!alloc_rt_sched_group(tg))
+ goto err;
+
+ spin_lock_irqsave(&task_group_lock, flags);
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);
- rt_rq = tg->rt_rq[i];
- list_add_rcu(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
+ register_fair_sched_group(tg, i);
+ register_rt_sched_group(tg, i);
}
list_add_rcu(&tg->list, &task_groups);
- unlock_task_group_list();
+ spin_unlock_irqrestore(&task_group_lock, flags);
return tg;
/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
- struct cfs_rq *cfs_rq = NULL;
- struct rt_rq *rt_rq = NULL;
+ unsigned long flags;
int i;
- lock_task_group_list();
+ spin_lock_irqsave(&task_group_lock, flags);
for_each_possible_cpu(i) {
- cfs_rq = tg->cfs_rq[i];
- list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
- rt_rq = tg->rt_rq[i];
- list_del_rcu(&rt_rq->leaf_rt_rq_list);
+ unregister_fair_sched_group(tg, i);
+ unregister_rt_sched_group(tg, i);
}
list_del_rcu(&tg->list);
- unlock_task_group_list();
-
- BUG_ON(!cfs_rq);
+ spin_unlock_irqrestore(&task_group_lock, flags);
/* wait for possible concurrent references to cfs_rqs complete */
call_rcu(&tg->rcu, free_sched_group_rcu);
task_rq_unlock(rq, &flags);
}
-/* rq->lock to be locked by caller */
+#ifdef CONFIG_FAIR_GROUP_SCHED
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;
- if (!shares)
- shares = MIN_GROUP_SHARES;
+ spin_lock_irq(&rq->lock);
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);
- inc_cpu_load(rq, se->load.weight);
- }
+
+ spin_unlock_irq(&rq->lock);
}
+static DEFINE_MUTEX(shares_mutex);
+
int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
- struct cfs_rq *cfs_rq;
- struct rq *rq;
+ unsigned long flags;
- lock_task_group_list();
+ /*
+ * A weight of 0 or 1 can cause arithmetics problems.
+ * (The default weight is 1024 - so there's no practical
+ * limitation from this.)
+ */
+ if (shares < 2)
+ shares = 2;
+
+ mutex_lock(&shares_mutex);
if (tg->shares == shares)
goto done;
- if (shares < MIN_GROUP_SHARES)
- shares = MIN_GROUP_SHARES;
-
- /*
- * 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.
- */
- for_each_possible_cpu(i) {
- cfs_rq = tg->cfs_rq[i];
- list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
- }
+ spin_lock_irqsave(&task_group_lock, flags);
+ for_each_possible_cpu(i)
+ unregister_fair_sched_group(tg, i);
+ spin_unlock_irqrestore(&task_group_lock, flags);
/* wait for any ongoing reference to this group to finish */
synchronize_sched();
* w/o tripping rebalance_share or load_balance_fair.
*/
tg->shares = shares;
- for_each_possible_cpu(i) {
- spin_lock_irq(&cpu_rq(i)->lock);
+ for_each_possible_cpu(i)
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);
- }
+ spin_lock_irqsave(&task_group_lock, flags);
+ for_each_possible_cpu(i)
+ register_fair_sched_group(tg, i);
+ spin_unlock_irqrestore(&task_group_lock, flags);
done:
- unlock_task_group_list();
+ mutex_unlock(&shares_mutex);
return 0;
}
{
return tg->shares;
}
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
/*
- * Ensure the total rt_ratio <= sysctl_sched_rt_ratio
+ * Ensure that the real time constraints are schedulable.
*/
-int sched_group_set_rt_ratio(struct task_group *tg, unsigned long rt_ratio)
+static DEFINE_MUTEX(rt_constraints_mutex);
+
+static unsigned long to_ratio(u64 period, u64 runtime)
+{
+ if (runtime == RUNTIME_INF)
+ return 1ULL << 16;
+
+ runtime *= (1ULL << 16);
+ div64_64(runtime, period);
+ return runtime;
+}
+
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
struct task_group *tgi;
unsigned long total = 0;
+ unsigned long global_ratio =
+ to_ratio(sysctl_sched_rt_period,
+ sysctl_sched_rt_runtime < 0 ?
+ RUNTIME_INF : sysctl_sched_rt_runtime);
rcu_read_lock();
- list_for_each_entry_rcu(tgi, &task_groups, list)
- total += tgi->rt_ratio;
- rcu_read_unlock();
+ list_for_each_entry_rcu(tgi, &task_groups, list) {
+ if (tgi == tg)
+ continue;
- if (total + rt_ratio - tg->rt_ratio > sysctl_sched_rt_ratio)
- return -EINVAL;
+ total += to_ratio(period, tgi->rt_runtime);
+ }
+ rcu_read_unlock();
- tg->rt_ratio = rt_ratio;
- return 0;
+ return total + to_ratio(period, runtime) < global_ratio;
}
-unsigned long sched_group_rt_ratio(struct task_group *tg)
+int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
- return tg->rt_ratio;
+ u64 rt_runtime, rt_period;
+ int err = 0;
+
+ rt_period = sysctl_sched_rt_period * NSEC_PER_USEC;
+ rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+ if (rt_runtime_us == -1)
+ rt_runtime = rt_period;
+
+ mutex_lock(&rt_constraints_mutex);
+ if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
+ err = -EINVAL;
+ goto unlock;
+ }
+ if (rt_runtime_us == -1)
+ rt_runtime = RUNTIME_INF;
+ tg->rt_runtime = rt_runtime;
+ unlock:
+ mutex_unlock(&rt_constraints_mutex);
+
+ return err;
}
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+long sched_group_rt_runtime(struct task_group *tg)
+{
+ u64 rt_runtime_us;
+
+ if (tg->rt_runtime == RUNTIME_INF)
+ return -1;
+
+ rt_runtime_us = tg->rt_runtime;
+ do_div(rt_runtime_us, NSEC_PER_USEC);
+ return rt_runtime_us;
+}
+#endif
+#endif /* CONFIG_GROUP_SCHED */
-#ifdef CONFIG_FAIR_CGROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
/* return corresponding task_group object of a cgroup */
static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
struct task_struct *tsk)
{
+#ifdef CONFIG_RT_GROUP_SCHED
+ /* Don't accept realtime tasks when there is no way for them to run */
+ if (rt_task(tsk) && cgroup_tg(cgrp)->rt_runtime == 0)
+ return -EINVAL;
+#else
/* We don't support RT-tasks being in separate groups */
if (tsk->sched_class != &fair_sched_class)
return -EINVAL;
+#endif
return 0;
}
sched_move_task(tsk);
}
+#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_uint(struct cgroup *cgrp, struct cftype *cftype,
u64 shareval)
{
return (u64) tg->shares;
}
+#endif
-static int cpu_rt_ratio_write_uint(struct cgroup *cgrp, struct cftype *cftype,
- u64 rt_ratio_val)
+#ifdef CONFIG_RT_GROUP_SCHED
+static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
+ struct file *file,
+ const char __user *userbuf,
+ size_t nbytes, loff_t *unused_ppos)
{
- return sched_group_set_rt_ratio(cgroup_tg(cgrp), rt_ratio_val);
+ char buffer[64];
+ int retval = 0;
+ s64 val;
+ char *end;
+
+ if (!nbytes)
+ return -EINVAL;
+ if (nbytes >= sizeof(buffer))
+ return -E2BIG;
+ if (copy_from_user(buffer, userbuf, nbytes))
+ return -EFAULT;
+
+ buffer[nbytes] = 0; /* nul-terminate */
+
+ /* strip newline if necessary */
+ if (nbytes && (buffer[nbytes-1] == '\n'))
+ buffer[nbytes-1] = 0;
+ val = simple_strtoll(buffer, &end, 0);
+ if (*end)
+ return -EINVAL;
+
+ /* Pass to subsystem */
+ retval = sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
+ if (!retval)
+ retval = nbytes;
+ return retval;
}
-static u64 cpu_rt_ratio_read_uint(struct cgroup *cgrp, struct cftype *cft)
+static ssize_t cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft,
+ struct file *file,
+ char __user *buf, size_t nbytes,
+ loff_t *ppos)
{
- struct task_group *tg = cgroup_tg(cgrp);
+ char tmp[64];
+ long val = sched_group_rt_runtime(cgroup_tg(cgrp));
+ int len = sprintf(tmp, "%ld\n", val);
- return (u64) tg->rt_ratio;
+ return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}
+#endif
static struct cftype cpu_files[] = {
+#ifdef CONFIG_FAIR_GROUP_SCHED
{
.name = "shares",
.read_uint = cpu_shares_read_uint,
.write_uint = cpu_shares_write_uint,
},
+#endif
+#ifdef CONFIG_RT_GROUP_SCHED
{
- .name = "rt_ratio",
- .read_uint = cpu_rt_ratio_read_uint,
- .write_uint = cpu_rt_ratio_write_uint,
+ .name = "rt_runtime_us",
+ .read = cpu_rt_runtime_read,
+ .write = cpu_rt_runtime_write,
},
+#endif
};
static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
.early_init = 1,
};
-#endif /* CONFIG_FAIR_CGROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
#ifdef CONFIG_CGROUP_CPUACCT