#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
-#include <linux/cpu_acct.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
*/
unsigned long long __attribute__((weak)) sched_clock(void)
{
- return (unsigned long long)jiffies * (1000000000 / HZ);
+ return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
}
/*
/*
* Some helpers for converting nanosecond timing to jiffy resolution
*/
-#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (1000000000 / HZ))
-#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ))
+#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
unsigned long shares;
/* spinlock to serialize modification to shares */
spinlock_t lock;
+ struct rcu_head rcu;
};
/* Default task group's sched entity on each cpu */
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
-static inline void set_task_cfs_rq(struct task_struct *p)
+static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu)
{
- p->se.cfs_rq = task_group(p)->cfs_rq[task_cpu(p)];
- p->se.parent = task_group(p)->se[task_cpu(p)];
+ p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
+ p->se.parent = task_group(p)->se[cpu];
}
#else
-static inline void set_task_cfs_rq(struct task_struct *p) { }
+static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) { }
#endif /* CONFIG_FAIR_GROUP_SCHED */
*/
struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
struct task_group *tg; /* group that "owns" this runqueue */
- struct rcu_head rcu;
#endif
};
*/
enum {
SCHED_FEAT_NEW_FAIR_SLEEPERS = 1,
- SCHED_FEAT_START_DEBIT = 2,
- SCHED_FEAT_TREE_AVG = 4,
- SCHED_FEAT_APPROX_AVG = 8,
- SCHED_FEAT_WAKEUP_PREEMPT = 16,
- SCHED_FEAT_PREEMPT_RESTRICT = 32,
+ SCHED_FEAT_WAKEUP_PREEMPT = 2,
+ SCHED_FEAT_START_DEBIT = 4,
+ SCHED_FEAT_TREE_AVG = 8,
+ SCHED_FEAT_APPROX_AVG = 16,
};
const_debug unsigned int sysctl_sched_features =
SCHED_FEAT_NEW_FAIR_SLEEPERS * 1 |
+ SCHED_FEAT_WAKEUP_PREEMPT * 1 |
SCHED_FEAT_START_DEBIT * 1 |
SCHED_FEAT_TREE_AVG * 0 |
- SCHED_FEAT_APPROX_AVG * 0 |
- SCHED_FEAT_WAKEUP_PREEMPT * 1 |
- SCHED_FEAT_PREEMPT_RESTRICT * 1;
+ SCHED_FEAT_APPROX_AVG * 0;
#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)
+/*
+ * Number of tasks to iterate in a single balance run.
+ * Limited because this is done with IRQs disabled.
+ */
+const_debug unsigned int sysctl_sched_nr_migrate = 32;
+
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
struct task_struct *(*next)(void *);
};
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator);
+#ifdef CONFIG_SMP
+static unsigned long
+balance_tasks(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, struct rq_iterator *iterator);
+
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ struct rq_iterator *iterator);
+#endif
#include "sched_stats.h"
#include "sched_idletask.c"
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
+ set_task_cfs_rq(p, cpu);
#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+ * successfuly executed on another CPU. We must ensure that updates of
+ * per-task data have been completed by this moment.
+ */
+ smp_wmb();
task_thread_info(p)->cpu = cpu;
#endif
- set_task_cfs_rq(p);
}
#ifdef CONFIG_SMP
return 1;
}
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator)
+static unsigned long
+balance_tasks(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, struct rq_iterator *iterator)
{
- int pulled = 0, pinned = 0, skip_for_load;
+ int loops = 0, pulled = 0, pinned = 0, skip_for_load;
struct task_struct *p;
long rem_load_move = max_load_move;
- if (max_nr_move == 0 || max_load_move == 0)
+ if (max_load_move == 0)
goto out;
pinned = 1;
*/
p = iterator->start(iterator->arg);
next:
- if (!p)
+ if (!p || loops++ > sysctl_sched_nr_migrate)
goto out;
/*
- * To help distribute high priority tasks accross CPUs we don't
+ * To help distribute high priority tasks across CPUs we don't
* skip a task if it will be the highest priority task (i.e. smallest
* prio value) on its new queue regardless of its load weight
*/
rem_load_move -= p->se.load.weight;
/*
- * We only want to steal up to the prescribed number of tasks
- * and the prescribed amount of weighted load.
+ * We only want to steal up to the prescribed amount of weighted load.
*/
- if (pulled < max_nr_move && rem_load_move > 0) {
+ if (rem_load_move > 0) {
if (p->prio < *this_best_prio)
*this_best_prio = p->prio;
p = iterator->next(iterator->arg);
}
out:
/*
- * Right now, this is the only place pull_task() is called,
+ * Right now, this is one of only two places pull_task() is called,
* so we can safely collect pull_task() stats here rather than
* inside pull_task().
*/
if (all_pinned)
*all_pinned = pinned;
- *load_moved = max_load_move - rem_load_move;
- return pulled;
+
+ return max_load_move - rem_load_move;
}
/*
do {
total_load_moved +=
class->load_balance(this_rq, this_cpu, busiest,
- ULONG_MAX, max_load_move - total_load_moved,
+ max_load_move - total_load_moved,
sd, idle, all_pinned, &this_best_prio);
class = class->next;
} while (class && max_load_move > total_load_moved);
return total_load_moved > 0;
}
+static int
+iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ struct rq_iterator *iterator)
+{
+ struct task_struct *p = iterator->start(iterator->arg);
+ int pinned = 0;
+
+ while (p) {
+ if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
+ pull_task(busiest, p, this_rq, this_cpu);
+ /*
+ * Right now, this is only the second place pull_task()
+ * is called, so we can safely collect pull_task()
+ * stats here rather than inside pull_task().
+ */
+ schedstat_inc(sd, lb_gained[idle]);
+
+ return 1;
+ }
+ p = iterator->next(iterator->arg);
+ }
+
+ return 0;
+}
+
/*
* move_one_task tries to move exactly one task from busiest to this_rq, as
* part of active balancing operations within "domain".
struct sched_domain *sd, enum cpu_idle_type idle)
{
const struct sched_class *class;
- int this_best_prio = MAX_PRIO;
for (class = sched_class_highest; class; class = class->next)
- if (class->load_balance(this_rq, this_cpu, busiest,
- 1, ULONG_MAX, sd, idle, NULL,
- &this_best_prio))
+ if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
return 1;
return 0;
{
}
-/* Avoid "used but not defined" warning on UP */
-static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
- unsigned long max_nr_move, unsigned long max_load_move,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned, unsigned long *load_moved,
- int *this_best_prio, struct rq_iterator *iterator)
-{
- *load_moved = 0;
-
- return 0;
-}
-
#endif
DEFINE_PER_CPU(struct kernel_stat, kstat);
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
cputime64_t tmp;
- struct rq *rq = this_rq();
p->utime = cputime_add(p->utime, cputime);
- if (p != rq->idle)
- cpuacct_charge(p, cputime);
-
/* Add user time to cpustat. */
tmp = cputime_to_cputime64(cputime);
if (TASK_NICE(p) > 0)
* @p: the process that the cpu time gets accounted to
* @cputime: the cpu time spent in virtual machine since the last update
*/
-void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime)
{
cputime64_t tmp;
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
struct rq *rq = this_rq();
cputime64_t tmp;
- if (p->flags & PF_VCPU) {
- account_guest_time(p, cputime);
- return;
- }
+ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
+ return account_guest_time(p, cputime);
p->stime = cputime_add(p->stime, cputime);
cpustat->irq = cputime64_add(cpustat->irq, tmp);
else if (softirq_count())
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
- else if (p != rq->idle) {
+ else if (p != rq->idle)
cpustat->system = cputime64_add(cpustat->system, tmp);
- cpuacct_charge(p, cputime);
- } else if (atomic_read(&rq->nr_iowait) > 0)
+ else if (atomic_read(&rq->nr_iowait) > 0)
cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
cpustat->idle = cputime64_add(cpustat->idle, tmp);
cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
else
cpustat->idle = cputime64_add(cpustat->idle, tmp);
- } else {
+ } else
cpustat->steal = cputime64_add(cpustat->steal, tmp);
- cpuacct_charge(p, -tmp);
- }
}
/*
*/
cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+/*
+ * Increase the granularity value when there are more CPUs,
+ * because with more CPUs the 'effective latency' as visible
+ * to users decreases. But the relationship is not linear,
+ * so pick a second-best guess by going with the log2 of the
+ * number of CPUs.
+ *
+ * This idea comes from the SD scheduler of Con Kolivas:
+ */
+static inline void sched_init_granularity(void)
+{
+ unsigned int factor = 1 + ilog2(num_online_cpus());
+ const unsigned long limit = 200000000;
+
+ sysctl_sched_min_granularity *= factor;
+ if (sysctl_sched_min_granularity > limit)
+ sysctl_sched_min_granularity = limit;
+
+ sysctl_sched_latency *= factor;
+ if (sysctl_sched_latency > limit)
+ sysctl_sched_latency = limit;
+
+ sysctl_sched_wakeup_granularity *= factor;
+ sysctl_sched_batch_wakeup_granularity *= factor;
+}
+
#ifdef CONFIG_SMP
/*
* This is how migration works:
read_unlock(&tasklist_lock);
}
-/*
- * activate_idle_task - move idle task to the _front_ of runqueue.
- */
-static void activate_idle_task(struct task_struct *p, struct rq *rq)
-{
- update_rq_clock(rq);
-
- if (p->state == TASK_UNINTERRUPTIBLE)
- rq->nr_uninterruptible--;
-
- enqueue_task(rq, p, 0);
- inc_nr_running(p, rq);
-}
-
/*
* Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible and adding it to
- * the _front_ of the runqueue. Used by CPU offline code.
+ * It does so by boosting its priority to highest possible.
+ * Used by CPU offline code.
*/
void sched_idle_next(void)
{
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
- /* Add idle task to the _front_ of its priority queue: */
- activate_idle_task(p, rq);
+ update_rq_clock(rq);
+ activate_task(rq, p, 0);
spin_unlock_irqrestore(&rq->lock, flags);
}
.procname = "sched_domain",
.mode = 0555,
},
- {0,},
+ {0, },
};
static struct ctl_table sd_ctl_root[] = {
.mode = 0555,
.child = sd_ctl_dir,
},
- {0,},
+ {0, },
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
.priority = 10
};
-int __init migration_init(void)
+void __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
int err;
BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
-
- return 0;
}
#endif
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed(current, non_isolated_cpus) < 0)
BUG();
+ sched_init_granularity();
}
#else
void __init sched_init_smp(void)
{
+ sched_init_granularity();
}
#endif /* CONFIG_SMP */
/* rcu callback to free various structures associated with a task group */
static void free_sched_group(struct rcu_head *rhp)
{
- struct cfs_rq *cfs_rq = container_of(rhp, struct cfs_rq, rcu);
- struct task_group *tg = cfs_rq->tg;
+ struct task_group *tg = container_of(rhp, struct task_group, rcu);
+ struct cfs_rq *cfs_rq;
struct sched_entity *se;
int i;
/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq = NULL;
int i;
for_each_possible_cpu(i) {
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
}
- cfs_rq = tg->cfs_rq[0];
+ BUG_ON(!cfs_rq);
/* wait for possible concurrent references to cfs_rqs complete */
- call_rcu(&cfs_rq->rcu, free_sched_group);
+ call_rcu(&tg->rcu, free_sched_group);
}
/* change task's runqueue when it moves between groups.
rq = task_rq_lock(tsk, &flags);
- if (tsk->sched_class != &fair_sched_class)
+ if (tsk->sched_class != &fair_sched_class) {
+ set_task_cfs_rq(tsk, task_cpu(tsk));
goto done;
+ }
update_rq_clock(rq);
tsk->sched_class->put_prev_task(rq, tsk);
}
- set_task_cfs_rq(tsk);
+ set_task_cfs_rq(tsk, task_cpu(tsk));
if (on_rq) {
if (unlikely(running))
return (u64) tg->shares;
}
-static struct cftype cpu_shares = {
- .name = "shares",
- .read_uint = cpu_shares_read_uint,
- .write_uint = cpu_shares_write_uint,
+static u64 cpu_usage_read(struct cgroup *cgrp, struct cftype *cft)
+{
+ struct task_group *tg = cgroup_tg(cgrp);
+ unsigned long flags;
+ u64 res = 0;
+ int i;
+
+ for_each_possible_cpu(i) {
+ /*
+ * Lock to prevent races with updating 64-bit counters
+ * on 32-bit arches.
+ */
+ spin_lock_irqsave(&cpu_rq(i)->lock, flags);
+ res += tg->se[i]->sum_exec_runtime;
+ spin_unlock_irqrestore(&cpu_rq(i)->lock, flags);
+ }
+ /* Convert from ns to ms */
+ do_div(res, NSEC_PER_MSEC);
+
+ return res;
+}
+
+static struct cftype cpu_files[] = {
+ {
+ .name = "shares",
+ .read_uint = cpu_shares_read_uint,
+ .write_uint = cpu_shares_write_uint,
+ },
+ {
+ .name = "usage",
+ .read_uint = cpu_usage_read,
+ },
};
static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
- return cgroup_add_file(cont, ss, &cpu_shares);
+ return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
}
struct cgroup_subsys cpu_cgroup_subsys = {
- .name = "cpu",
- .create = cpu_cgroup_create,
- .destroy = cpu_cgroup_destroy,
- .can_attach = cpu_cgroup_can_attach,
- .attach = cpu_cgroup_attach,
- .populate = cpu_cgroup_populate,
- .subsys_id = cpu_cgroup_subsys_id,
+ .name = "cpu",
+ .create = cpu_cgroup_create,
+ .destroy = cpu_cgroup_destroy,
+ .can_attach = cpu_cgroup_can_attach,
+ .attach = cpu_cgroup_attach,
+ .populate = cpu_cgroup_populate,
+ .subsys_id = cpu_cgroup_subsys_id,
.early_init = 1,
};