/*
* Some helpers for converting nanosecond timing to jiffy resolution
*/
-#define NS_TO_JIFFIES(TIME) ((TIME) / (1000000000 / HZ))
+#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (1000000000 / HZ))
#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ))
#define NICE_0_LOAD SCHED_LOAD_SCALE
/*
* These are the 'tuning knobs' of the scheduler:
*
- * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
- * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
* Timeslices get refilled after they expire.
*/
-#define MIN_TIMESLICE max(5 * HZ / 1000, 1)
#define DEF_TIMESLICE (100 * HZ / 1000)
#ifdef CONFIG_SMP
}
#endif
-#define SCALE_PRIO(x, prio) \
- max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)
-
-/*
- * static_prio_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
- * to time slice values: [800ms ... 100ms ... 5ms]
- */
-static unsigned int static_prio_timeslice(int static_prio)
-{
- if (static_prio == NICE_TO_PRIO(19))
- return 1;
-
- if (static_prio < NICE_TO_PRIO(0))
- return SCALE_PRIO(DEF_TIMESLICE * 4, static_prio);
- else
- return SCALE_PRIO(DEF_TIMESLICE, static_prio);
-}
-
static inline int rt_policy(int policy)
{
if (unlikely(policy == SCHED_FIFO) || unlikely(policy == SCHED_RR))
struct list_head queue[MAX_RT_PRIO];
};
-struct load_stat {
- struct load_weight load;
- u64 load_update_start, load_update_last;
- unsigned long delta_fair, delta_exec, delta_stat;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
+struct cfs_rq;
+
+/* task group related information */
+struct task_group {
+ /* 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;
+ /* spinlock to serialize modification to shares */
+ spinlock_t lock;
+};
+
+/* 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 struct sched_entity *init_sched_entity_p[NR_CPUS];
+static struct cfs_rq *init_cfs_rq_p[NR_CPUS];
+
+/* Default task group.
+ * Every task in system belong to this group at bootup.
+ */
+struct task_group init_task_group = {
+ .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
+#else
+# define INIT_TASK_GRP_LOAD NICE_0_LOAD
+#endif
+
+static int init_task_group_load = INIT_TASK_GRP_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
+ tg = p->user->tg;
+#else
+ tg = &init_task_group;
+#endif
+
+ return tg;
+}
+
+/* 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)
+{
+ p->se.cfs_rq = task_group(p)->cfs_rq[task_cpu(p)];
+ p->se.parent = task_group(p)->se[task_cpu(p)];
+}
+
+#else
+
+static inline void set_task_cfs_rq(struct task_struct *p) { }
+
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
unsigned long nr_running;
- s64 fair_clock;
u64 exec_clock;
- s64 wait_runtime;
- u64 sleeper_bonus;
- unsigned long wait_runtime_overruns, wait_runtime_underruns;
+ u64 min_vruntime;
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
struct rb_node *rb_load_balance_curr;
-#ifdef CONFIG_FAIR_GROUP_SCHED
/* 'curr' points to currently running entity on this cfs_rq.
* It is set to NULL otherwise (i.e when none are currently running).
*/
struct sched_entity *curr;
+
+ unsigned long nr_spread_over;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
/* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
* list is used during load balance.
*/
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
};
#ifdef CONFIG_NO_HZ
unsigned char in_nohz_recently;
#endif
- struct load_stat ls; /* capture load from *all* tasks on this cpu */
+ struct load_weight load; /* capture load from *all* tasks on this cpu */
unsigned long nr_load_updates;
u64 nr_switches;
unsigned long yld_exp_empty;
unsigned long yld_act_empty;
unsigned long yld_both_empty;
- unsigned long yld_cnt;
+ unsigned long yld_count;
/* schedule() stats */
unsigned long sched_switch;
- unsigned long sched_cnt;
+ unsigned long sched_count;
unsigned long sched_goidle;
/* try_to_wake_up() stats */
- unsigned long ttwu_cnt;
+ unsigned long ttwu_count;
unsigned long ttwu_local;
+
+ /* BKL stats */
+ unsigned long bkl_count;
#endif
struct lock_class_key rq_lock_key;
};
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+/*
+ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
+ */
+#ifdef CONFIG_SCHED_DEBUG
+# define const_debug __read_mostly
+#else
+# define const_debug static const
+#endif
+
+/*
+ * Debugging: various feature bits
+ */
+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,
+};
+
+const_debug unsigned int sysctl_sched_features =
+ SCHED_FEAT_NEW_FAIR_SLEEPERS *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;
+
+#define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x)
+
/*
* For kernel-internal use: high-speed (but slightly incorrect) per-cpu
* clock constructed from sched_clock():
return now;
}
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/* Change a task's ->cfs_rq if it moves across CPUs */
-static inline void set_task_cfs_rq(struct task_struct *p)
-{
- p->se.cfs_rq = &task_rq(p)->cfs;
-}
-#else
-static inline void set_task_cfs_rq(struct task_struct *p)
-{
-}
-#endif
+EXPORT_SYMBOL_GPL(cpu_clock);
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
return rq;
}
-static inline void __task_rq_unlock(struct rq *rq)
+static void __task_rq_unlock(struct rq *rq)
__releases(rq->lock)
{
spin_unlock(&rq->lock);
/*
* this_rq_lock - lock this runqueue and disable interrupts.
*/
-static inline struct rq *this_rq_lock(void)
+static struct rq *this_rq_lock(void)
__acquires(rq->lock)
{
struct rq *rq;
}
#endif
-static u64 div64_likely32(u64 divident, unsigned long divisor)
-{
-#if BITS_PER_LONG == 32
- if (likely(divident <= 0xffffffffULL))
- return (u32)divident / divisor;
- do_div(divident, divisor);
-
- return divident;
-#else
- return divident / divisor;
-#endif
-}
-
#if BITS_PER_LONG == 32
# define WMULT_CONST (~0UL)
#else
return calc_delta_mine(delta_exec, NICE_0_LOAD, lw);
}
-static void update_load_add(struct load_weight *lw, unsigned long inc)
+static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
- lw->inv_weight = 0;
}
-static void update_load_sub(struct load_weight *lw, unsigned long dec)
+static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
lw->weight -= dec;
- lw->inv_weight = 0;
}
/*
int *this_best_prio, struct rq_iterator *iterator);
#include "sched_stats.h"
-#include "sched_rt.c"
-#include "sched_fair.c"
#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif
#define sched_class_highest (&rt_sched_class)
-static void __update_curr_load(struct rq *rq, struct load_stat *ls)
-{
- if (rq->curr != rq->idle && ls->load.weight) {
- ls->delta_exec += ls->delta_stat;
- ls->delta_fair += calc_delta_fair(ls->delta_stat, &ls->load);
- ls->delta_stat = 0;
- }
-}
-
/*
* Update delta_exec, delta_fair fields for rq.
*
* delta_fair clock advances at a rate inversely proportional to
- * total load (rq->ls.load.weight) on the runqueue, while
+ * total load (rq->load.weight) on the runqueue, while
* delta_exec advances at the same rate as wall-clock (provided
* cpu is not idle).
*
* runqueue over any given interval. This (smoothened) load is used
* during load balance.
*
- * This function is called /before/ updating rq->ls.load
+ * This function is called /before/ updating rq->load
* and when switching tasks.
*/
-static void update_curr_load(struct rq *rq)
-{
- struct load_stat *ls = &rq->ls;
- u64 start;
-
- start = ls->load_update_start;
- ls->load_update_start = rq->clock;
- ls->delta_stat += rq->clock - start;
- /*
- * Stagger updates to ls->delta_fair. Very frequent updates
- * can be expensive.
- */
- if (ls->delta_stat >= sysctl_sched_stat_granularity)
- __update_curr_load(rq, ls);
-}
-
static inline void inc_load(struct rq *rq, const struct task_struct *p)
{
- update_curr_load(rq);
- update_load_add(&rq->ls.load, p->se.load.weight);
+ update_load_add(&rq->load, p->se.load.weight);
}
static inline void dec_load(struct rq *rq, const struct task_struct *p)
{
- update_curr_load(rq);
- update_load_sub(&rq->ls.load, p->se.load.weight);
+ update_load_sub(&rq->load, p->se.load.weight);
}
static void inc_nr_running(struct task_struct *p, struct rq *rq)
static void set_load_weight(struct task_struct *p)
{
- p->se.wait_runtime = 0;
-
if (task_has_rt_policy(p)) {
p->se.load.weight = prio_to_weight[0] * 2;
p->se.load.inv_weight = prio_to_wmult[0] >> 1;
inc_nr_running(p, rq);
}
-/*
- * activate_idle_task - move idle task to the _front_ of runqueue.
- */
-static inline 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);
-}
-
/*
* deactivate_task - remove a task from the runqueue.
*/
/* Used instead of source_load when we know the type == 0 */
unsigned long weighted_cpuload(const int cpu)
{
- return cpu_rq(cpu)->ls.load.weight;
+ return cpu_rq(cpu)->load.weight;
}
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
#ifdef CONFIG_SMP
task_thread_info(p)->cpu = cpu;
- set_task_cfs_rq(p);
#endif
+ set_task_cfs_rq(p);
}
#ifdef CONFIG_SMP
{
int old_cpu = task_cpu(p);
struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
- u64 clock_offset, fair_clock_offset;
+ struct cfs_rq *old_cfsrq = task_cfs_rq(p),
+ *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
+ u64 clock_offset;
clock_offset = old_rq->clock - new_rq->clock;
- fair_clock_offset = old_rq->cfs.fair_clock - new_rq->cfs.fair_clock;
-
- if (p->se.wait_start_fair)
- p->se.wait_start_fair -= fair_clock_offset;
- if (p->se.sleep_start_fair)
- p->se.sleep_start_fair -= fair_clock_offset;
#ifdef CONFIG_SCHEDSTATS
if (p->se.wait_start)
if (p->se.block_start)
p->se.block_start -= clock_offset;
#endif
+ p->se.vruntime -= old_cfsrq->min_vruntime -
+ new_cfsrq->min_vruntime;
__set_task_cpu(p, new_cpu);
}
* yield - it could be a while.
*/
if (unlikely(on_rq)) {
- yield();
+ schedule_timeout_uninterruptible(1);
goto repeat;
}
* We want to under-estimate the load of migration sources, to
* balance conservatively.
*/
-static inline unsigned long source_load(int cpu, int type)
+static unsigned long source_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
* Return a high guess at the load of a migration-target cpu weighted
* according to the scheduling class and "nice" value.
*/
-static inline unsigned long target_load(int cpu, int type)
+static unsigned long target_load(int cpu, int type)
{
struct rq *rq = cpu_rq(cpu);
unsigned long total = weighted_cpuload(cpu);
new_cpu = cpu;
- schedstat_inc(rq, ttwu_cnt);
+ schedstat_inc(rq, ttwu_count);
if (cpu == this_cpu) {
schedstat_inc(rq, ttwu_local);
goto out_set_cpu;
*/
static void __sched_fork(struct task_struct *p)
{
- p->se.wait_start_fair = 0;
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
- p->se.delta_exec = 0;
- p->se.delta_fair_run = 0;
- p->se.delta_fair_sleep = 0;
- p->se.wait_runtime = 0;
- p->se.sleep_start_fair = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
- p->se.sum_wait_runtime = 0;
p->se.sum_sleep_runtime = 0;
p->se.sleep_start = 0;
p->se.block_start = 0;
p->se.sleep_max = 0;
p->se.block_max = 0;
p->se.exec_max = 0;
+ p->se.slice_max = 0;
p->se.wait_max = 0;
- p->se.wait_runtime_overruns = 0;
- p->se.wait_runtime_underruns = 0;
#endif
INIT_LIST_HEAD(&p->run_list);
#ifdef CONFIG_SMP
cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
- __set_task_cpu(p, cpu);
+ set_task_cpu(p, cpu);
/*
* Make sure we do not leak PI boosting priority to the child:
*/
p->prio = current->normal_prio;
+ if (!rt_prio(p->prio))
+ p->sched_class = &fair_sched_class;
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
if (likely(sched_info_on()))
put_cpu();
}
-/*
- * After fork, child runs first. (default) If set to 0 then
- * parent will (try to) run first.
- */
-unsigned int __read_mostly sysctl_sched_child_runs_first = 1;
-
/*
* wake_up_new_task - wake up a newly created task for the first time.
*
{
unsigned long flags;
struct rq *rq;
- int this_cpu;
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
- this_cpu = smp_processor_id(); /* parent's CPU */
update_rq_clock(rq);
p->prio = effective_prio(p);
- if (rt_prio(p->prio))
- p->sched_class = &rt_sched_class;
- else
- p->sched_class = &fair_sched_class;
-
- if (task_cpu(p) != this_cpu || !p->sched_class->task_new ||
- !current->se.on_rq) {
+ if (!p->sched_class->task_new || !current->se.on_rq || !rq->cfs.curr) {
activate_task(rq, p, 0);
} else {
/*
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
-static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
+static void finish_task_switch(struct rq *rq, struct task_struct *prev)
__releases(rq->lock)
{
struct mm_struct *mm = rq->prev_mm;
*/
static void update_cpu_load(struct rq *this_rq)
{
- u64 fair_delta64, exec_delta64, idle_delta64, sample_interval64, tmp64;
- unsigned long total_load = this_rq->ls.load.weight;
- unsigned long this_load = total_load;
- struct load_stat *ls = &this_rq->ls;
+ unsigned long this_load = this_rq->load.weight;
int i, scale;
this_rq->nr_load_updates++;
- if (unlikely(!(sysctl_sched_features & SCHED_FEAT_PRECISE_CPU_LOAD)))
- goto do_avg;
-
- /* Update delta_fair/delta_exec fields first */
- update_curr_load(this_rq);
-
- fair_delta64 = ls->delta_fair + 1;
- ls->delta_fair = 0;
-
- exec_delta64 = ls->delta_exec + 1;
- ls->delta_exec = 0;
-
- sample_interval64 = this_rq->clock - ls->load_update_last;
- ls->load_update_last = this_rq->clock;
-
- if ((s64)sample_interval64 < (s64)TICK_NSEC)
- sample_interval64 = TICK_NSEC;
-
- if (exec_delta64 > sample_interval64)
- exec_delta64 = sample_interval64;
-
- idle_delta64 = sample_interval64 - exec_delta64;
-
- tmp64 = div64_64(SCHED_LOAD_SCALE * exec_delta64, fair_delta64);
- tmp64 = div64_64(tmp64 * exec_delta64, sample_interval64);
-
- this_load = (unsigned long)tmp64;
-
-do_avg:
/* Update our load: */
for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
old_load = this_rq->cpu_load[i];
new_load = this_load;
-
+ /*
+ * Round up the averaging division if load is increasing. This
+ * prevents us from getting stuck on 9 if the load is 10, for
+ * example.
+ */
+ if (new_load > old_load)
+ new_load += scale-1;
this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
}
}
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned)
{
- struct sched_class *class = sched_class_highest;
+ const struct sched_class *class = sched_class_highest;
unsigned long total_load_moved = 0;
int this_best_prio = this_rq->curr->prio;
static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
struct sched_domain *sd, enum cpu_idle_type idle)
{
- struct sched_class *class;
+ const struct sched_class *class;
int this_best_prio = MAX_PRIO;
for (class = sched_class_highest; class; class = class->next)
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
- schedstat_inc(sd, lb_cnt[idle]);
+ schedstat_inc(sd, lb_count[idle]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
!test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
sd_idle = 1;
- schedstat_inc(sd, lb_cnt[CPU_NEWLY_IDLE]);
+ schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
&sd_idle, &cpus, NULL);
}
if (likely(sd)) {
- schedstat_inc(sd, alb_cnt);
+ schedstat_inc(sd, alb_count);
if (move_one_task(target_rq, target_cpu, busiest_rq,
sd, CPU_IDLE))
*
* Balancing parameters are set up in arch_init_sched_domains.
*/
-static inline void rebalance_domains(int cpu, enum cpu_idle_type idle)
+static void rebalance_domains(int cpu, enum cpu_idle_type idle)
{
int balance = 1;
struct rq *rq = cpu_rq(cpu);
profile_hit(SCHED_PROFILING, __builtin_return_address(0));
- schedstat_inc(this_rq(), sched_cnt);
+ schedstat_inc(this_rq(), sched_count);
+#ifdef CONFIG_SCHEDSTATS
+ if (unlikely(prev->lock_depth >= 0)) {
+ schedstat_inc(this_rq(), bkl_count);
+ schedstat_inc(prev, sched_info.bkl_count);
+ }
+#endif
}
/*
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev)
{
- struct sched_class *class;
+ const struct sched_class *class;
struct task_struct *p;
/*
schedule_debug(prev);
- spin_lock_irq(&rq->lock);
- clear_tsk_need_resched(prev);
+ /*
+ * Do the rq-clock update outside the rq lock:
+ */
+ local_irq_disable();
__update_rq_clock(rq);
+ spin_lock(&rq->lock);
+ clear_tsk_need_resched(prev);
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, int sync, void *key)
{
- struct list_head *tmp, *next;
+ wait_queue_t *curr, *next;
- list_for_each_safe(tmp, next, &q->task_list) {
- wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
+ list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
unsigned flags = curr->flags;
if (curr->func(curr, mode, sync, key) &&
void rt_mutex_setprio(struct task_struct *p, int prio)
{
unsigned long flags;
- int oldprio, on_rq;
+ int oldprio, on_rq, running;
struct rq *rq;
BUG_ON(prio < 0 || prio > MAX_PRIO);
oldprio = p->prio;
on_rq = p->se.on_rq;
- if (on_rq)
+ running = task_running(rq, p);
+ if (on_rq) {
dequeue_task(rq, p, 0);
+ if (running)
+ p->sched_class->put_prev_task(rq, p);
+ }
if (rt_prio(prio))
p->sched_class = &rt_sched_class;
p->prio = 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 (task_running(rq, p)) {
+ if (running) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else {
* find_process_by_pid - find a process with a matching PID value.
* @pid: the pid in question.
*/
-static inline struct task_struct *find_process_by_pid(pid_t pid)
+static struct task_struct *find_process_by_pid(pid_t pid)
{
return pid ? find_task_by_pid(pid) : current;
}
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
{
- int retval, oldprio, oldpolicy = -1, on_rq;
+ int retval, oldprio, oldpolicy = -1, on_rq, running;
unsigned long flags;
struct rq *rq;
}
update_rq_clock(rq);
on_rq = p->se.on_rq;
- if (on_rq)
+ running = task_running(rq, p);
+ if (on_rq) {
deactivate_task(rq, p, 0);
+ if (running)
+ p->sched_class->put_prev_task(rq, p);
+ }
+
oldprio = p->prio;
__setscheduler(rq, p, policy, param->sched_priority);
+
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 (task_running(rq, p)) {
+ if (running) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else {
{
struct rq *rq = this_rq_lock();
- schedstat_inc(rq, yld_cnt);
- current->sched_class->yield_task(rq, current);
+ schedstat_inc(rq, yld_count);
+ current->sched_class->yield_task(rq);
/*
* Since we are going to call schedule() anyway, there's
long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
{
struct task_struct *p;
+ unsigned int time_slice;
int retval = -EINVAL;
struct timespec t;
if (retval)
goto out_unlock;
- jiffies_to_timespec(p->policy == SCHED_FIFO ?
- 0 : static_prio_timeslice(p->static_prio), &t);
+ if (p->policy == SCHED_FIFO)
+ time_slice = 0;
+ else if (p->policy == SCHED_RR)
+ time_slice = DEF_TIMESLICE;
+ else {
+ struct sched_entity *se = &p->se;
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(p, &flags);
+ time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
+ task_rq_unlock(rq, &flags);
+ }
read_unlock(&tasklist_lock);
+ jiffies_to_timespec(time_slice, &t);
retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
out_nounlock:
return retval;
*/
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 = 100000000;
-
- 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_runtime_limit = sysctl_sched_latency;
- sysctl_sched_wakeup_granularity = sysctl_sched_min_granularity / 2;
-}
-
#ifdef CONFIG_SMP
/*
* This is how migration works:
write_unlock_irq(&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
static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
- struct ctl_table *table = sd_alloc_ctl_entry(14);
+ struct ctl_table *table = sd_alloc_ctl_entry(12);
set_table_entry(&table[0], "min_interval", &sd->min_interval,
sizeof(long), 0644, proc_doulongvec_minmax);
sizeof(int), 0644, proc_dointvec_minmax);
set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[10], "cache_nice_tries",
+ set_table_entry(&table[9], "cache_nice_tries",
&sd->cache_nice_tries,
sizeof(int), 0644, proc_dointvec_minmax);
- set_table_entry(&table[12], "flags", &sd->flags,
+ set_table_entry(&table[10], "flags", &sd->flags,
sizeof(int), 0644, proc_dointvec_minmax);
return table;
int nr_cpu_ids __read_mostly = NR_CPUS;
EXPORT_SYMBOL(nr_cpu_ids);
-#undef SCHED_DOMAIN_DEBUG
-#ifdef SCHED_DOMAIN_DEBUG
+#ifdef CONFIG_SCHED_DEBUG
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
int level = 0;
printk("\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
+ break;
}
if (!cpus_weight(group->cpumask)) {
printk("\n");
printk(KERN_ERR "ERROR: empty group\n");
+ break;
}
if (cpus_intersects(groupmask, group->cpumask)) {
printk("\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
+ break;
}
cpus_or(groupmask, groupmask, group->cpumask);
return 1;
}
-__setup ("isolcpus=", isolated_cpu_setup);
+__setup("isolcpus=", isolated_cpu_setup);
/*
* init_sched_build_groups takes the cpumask we wish to span, and a pointer
/* 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 */
&& addr < (unsigned long)__sched_text_end);
}
-static inline void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
+static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
{
cfs_rq->tasks_timeline = RB_ROOT;
- cfs_rq->fair_clock = 1;
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->rq = rq;
#endif
+ cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
void __init sched_init(void)
{
- u64 now = sched_clock();
int highest_cpu = 0;
int i, j;
- /*
- * Link up the scheduling class hierarchy:
- */
- rt_sched_class.next = &fair_sched_class;
- fair_sched_class.next = &idle_sched_class;
- idle_sched_class.next = NULL;
-
for_each_possible_cpu(i) {
struct rt_prio_array *array;
struct rq *rq;
init_cfs_rq(&rq->cfs, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
- list_add(&rq->cfs.leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+ {
+ struct cfs_rq *cfs_rq = &per_cpu(init_cfs_rq, i);
+ struct sched_entity *se =
+ &per_cpu(init_sched_entity, i);
+
+ init_cfs_rq_p[i] = cfs_rq;
+ init_cfs_rq(cfs_rq, rq);
+ cfs_rq->tg = &init_task_group;
+ list_add(&cfs_rq->leaf_cfs_rq_list,
+ &rq->leaf_cfs_rq_list);
+
+ init_sched_entity_p[i] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = init_task_group_load;
+ se->load.inv_weight =
+ div64_64(1ULL<<32, init_task_group_load);
+ se->parent = NULL;
+ }
+ init_task_group.shares = init_task_group_load;
+ spin_lock_init(&init_task_group.lock);
#endif
- rq->ls.load_update_last = now;
- rq->ls.load_update_start = now;
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
rq->cpu_load[j] = 0;
read_lock_irq(&tasklist_lock);
do_each_thread(g, p) {
- p->se.fair_key = 0;
- p->se.wait_runtime = 0;
p->se.exec_start = 0;
- p->se.wait_start_fair = 0;
- p->se.sleep_start_fair = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
p->se.sleep_start = 0;
p->se.block_start = 0;
#endif
- task_rq(p)->cfs.fair_clock = 0;
task_rq(p)->clock = 0;
if (!rt_task(p)) {
}
#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
+/* allocate runqueue etc for a new task group */
+struct task_group *sched_create_group(void)
+{
+ struct task_group *tg;
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *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;
+
+ for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+
+ cfs_rq = kmalloc_node(sizeof(struct cfs_rq), GFP_KERNEL,
+ cpu_to_node(i));
+ if (!cfs_rq)
+ goto err;
+
+ se = kmalloc_node(sizeof(struct sched_entity), GFP_KERNEL,
+ cpu_to_node(i));
+ if (!se)
+ goto err;
+
+ memset(cfs_rq, 0, sizeof(struct cfs_rq));
+ memset(se, 0, sizeof(struct sched_entity));
+
+ tg->cfs_rq[i] = cfs_rq;
+ init_cfs_rq(cfs_rq, rq);
+ cfs_rq->tg = tg;
+
+ tg->se[i] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = NICE_0_LOAD;
+ se->load.inv_weight = div64_64(1ULL<<32, NICE_0_LOAD);
+ se->parent = NULL;
+ }
+
+ 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);
+
+ return tg;
+
+err:
+ for_each_possible_cpu(i) {
+ if (tg->cfs_rq)
+ kfree(tg->cfs_rq[i]);
+ if (tg->se)
+ kfree(tg->se[i]);
+ }
+ kfree(tg->cfs_rq);
+ kfree(tg->se);
+ kfree(tg);
+
+ return ERR_PTR(-ENOMEM);
+}
+
+/* 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 sched_entity *se;
+ int i;
+
+ /* now it should be safe to free those cfs_rqs */
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ kfree(cfs_rq);
+
+ se = tg->se[i];
+ kfree(se);
+ }
+
+ kfree(tg->cfs_rq);
+ kfree(tg->se);
+ kfree(tg);
+}
+
+/* Destroy runqueue etc associated with a task group */
+void sched_destroy_group(struct task_group *tg)
+{
+ struct cfs_rq *cfs_rq;
+ int i;
+
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ }
+
+ cfs_rq = tg->cfs_rq[0];
+
+ /* wait for possible concurrent references to cfs_rqs complete */
+ call_rcu(&cfs_rq->rcu, free_sched_group);
+}
+
+/* change task's runqueue when it moves between groups.
+ * The caller of this function should have put the task in its new group
+ * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
+ * reflect its new group.
+ */
+void sched_move_task(struct task_struct *tsk)
+{
+ int on_rq, running;
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(tsk, &flags);
+
+ if (tsk->sched_class != &fair_sched_class)
+ goto done;
+
+ update_rq_clock(rq);
+
+ running = task_running(rq, tsk);
+ on_rq = tsk->se.on_rq;
+
+ if (on_rq) {
+ dequeue_task(rq, tsk, 0);
+ if (unlikely(running))
+ tsk->sched_class->put_prev_task(rq, tsk);
+ }
+
+ set_task_cfs_rq(tsk);
+
+ if (on_rq) {
+ if (unlikely(running))
+ tsk->sched_class->set_curr_task(rq);
+ enqueue_task(rq, tsk, 0);
+ }
+
+done:
+ task_rq_unlock(rq, &flags);
+}
+
+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);
+
+ on_rq = se->on_rq;
+ if (on_rq)
+ dequeue_entity(cfs_rq, se, 0);
+
+ se->load.weight = shares;
+ se->load.inv_weight = div64_64((1ULL<<32), shares);
+
+ if (on_rq)
+ enqueue_entity(cfs_rq, se, 0);
+
+ spin_unlock_irq(&rq->lock);
+}
+
+int sched_group_set_shares(struct task_group *tg, unsigned long shares)
+{
+ int i;
+
+ spin_lock(&tg->lock);
+ if (tg->shares == shares)
+ goto done;
+
+ /* return -EINVAL if the new value is not sane */
+
+ tg->shares = shares;
+ for_each_possible_cpu(i)
+ set_se_shares(tg->se[i], shares);
+
+done:
+ spin_unlock(&tg->lock);
+ return 0;
+}
+
+unsigned long sched_group_shares(struct task_group *tg)
+{
+ return tg->shares;
+}
+
+#endif /* CONFIG_FAIR_GROUP_SCHED */