#ifdef CONFIG_FAIR_GROUP_SCHED
-#include <linux/container.h>
-
struct cfs_rq;
/* task group related information */
struct task_grp {
- struct container_subsys_state css;
/* schedulable entities of this group on each cpu */
struct sched_entity **se;
/* runqueue "owned" by this group on each cpu */
/* 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[CONFIG_NR_CPUS];
-static struct cfs_rq *init_cfs_rq_p[CONFIG_NR_CPUS];
+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.
+ * Every task in system belong to this group at bootup.
*/
-static struct task_grp init_task_grp = {
- .se = init_sched_entity_p,
- .cfs_rq = init_cfs_rq_p,
- };
+struct task_grp init_task_grp = {
+ .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_grp_load = INIT_TASK_GRP_LOAD;
/* return group to which a task belongs */
static inline struct task_grp *task_grp(struct task_struct *p)
{
- return container_of(task_subsys_state(p, cpu_subsys_id),
- struct task_grp, css);
+ struct task_grp *tg;
+
+#ifdef CONFIG_FAIR_USER_SCHED
+ tg = p->user->tg;
+#else
+ tg = &init_task_grp;
+#endif
+
+ return tg;
}
/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
* 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 */
*/
struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
struct task_grp *tg; /* group that "owns" this runqueue */
+ struct rcu_head rcu;
#endif
};
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;
};
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;
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
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.
*/
{
int old_cpu = task_cpu(p);
struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
+ 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;
if (p->se.block_start)
p->se.block_start -= clock_offset;
#endif
- if (likely(new_rq->cfs.min_vruntime))
- p->se.vruntime -= old_rq->cfs.min_vruntime -
- new_rq->cfs.min_vruntime;
+ p->se.vruntime -= old_cfsrq->min_vruntime -
+ new_cfsrq->min_vruntime;
__set_task_cpu(p, new_cpu);
}
* 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;
#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()))
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) {
activate_task(rq, p, 0);
* 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;
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) &&
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
- int oldprio, on_rq, running;
unsigned long flags;
+ int oldprio, on_rq, running;
struct rq *rq;
BUG_ON(prio < 0 || prio > MAX_PRIO);
* 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;
}
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);
{
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
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
&& 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;
#ifdef CONFIG_FAIR_GROUP_SCHED
cfs_rq->rq = rq;
#endif
+ cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}
void __init sched_init(void)
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);
- {
- 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_grp;
- list_add(&cfs_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_grp;
+ 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 = NICE_0_LOAD;
- se->load.inv_weight = div64_64(1ULL<<32, NICE_0_LOAD);
- se->parent = NULL;
- }
- init_task_grp.shares = NICE_0_LOAD;
+ init_sched_entity_p[i] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = init_task_grp_load;
+ se->load.inv_weight =
+ div64_64(1ULL<<32, init_task_grp_load);
+ se->parent = NULL;
+ }
+ init_task_grp.shares = init_task_grp_load;
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
#ifdef CONFIG_FAIR_GROUP_SCHED
-/* return corresponding task_grp object of a container */
-static inline struct task_grp *container_tg(struct container *cont)
-{
- return container_of(container_subsys_state(cont, cpu_subsys_id),
- struct task_grp, css);
-}
-
/* allocate runqueue etc for a new task group */
-static struct container_subsys_state *
-sched_create_group(struct container_subsys *ss, struct container *cont)
+struct task_grp *sched_create_group(void)
{
struct task_grp *tg;
struct cfs_rq *cfs_rq;
struct sched_entity *se;
+ struct rq *rq;
int i;
- if (!cont->parent) {
- /* This is early initialization for the top container */
- init_task_grp.css.container = cont;
- return &init_task_grp.css;
- }
-
- /* we support only 1-level deep hierarchical scheduler atm */
- if (cont->parent->parent)
- return ERR_PTR(-EINVAL);
-
tg = kzalloc(sizeof(*tg), GFP_KERNEL);
if (!tg)
return ERR_PTR(-ENOMEM);
- tg->cfs_rq = kzalloc(sizeof(cfs_rq) * num_possible_cpus(), GFP_KERNEL);
+ tg->cfs_rq = kzalloc(sizeof(cfs_rq) * NR_CPUS, GFP_KERNEL);
if (!tg->cfs_rq)
goto err;
- tg->se = kzalloc(sizeof(se) * num_possible_cpus(), GFP_KERNEL);
+ tg->se = kzalloc(sizeof(se) * NR_CPUS, GFP_KERNEL);
if (!tg->se)
goto err;
for_each_possible_cpu(i) {
- struct rq *rq = cpu_rq(i);
+ rq = cpu_rq(i);
cfs_rq = kmalloc_node(sizeof(struct cfs_rq), GFP_KERNEL,
cpu_to_node(i));
tg->cfs_rq[i] = cfs_rq;
init_cfs_rq(cfs_rq, rq);
cfs_rq->tg = tg;
- list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
tg->se[i] = se;
se->cfs_rq = &rq->cfs;
se->parent = NULL;
}
- tg->shares = NICE_0_LOAD;
+ 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);
+ }
- /* Bind the container to task_grp object we just created */
- tg->css.container = cont;
+ tg->shares = NICE_0_LOAD;
- return &tg->css;
+ return tg;
err:
for_each_possible_cpu(i) {
return ERR_PTR(-ENOMEM);
}
-
-/* destroy runqueue etc associated with a task group */
-static void sched_destroy_group(struct container_subsys *ss,
- struct container *cont)
+/* rcu callback to free various structures associated with a task group */
+static void free_sched_group(struct rcu_head *rhp)
{
- struct task_grp *tg = container_tg(cont);
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq = container_of(rhp, struct cfs_rq, rcu);
+ struct task_grp *tg = cfs_rq->tg;
struct sched_entity *se;
int i;
- for_each_possible_cpu(i) {
- cfs_rq = tg->cfs_rq[i];
- list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
- }
-
- /* wait for possible concurrent references to cfs_rqs complete */
- synchronize_sched();
-
/* now it should be safe to free those cfs_rqs */
for_each_possible_cpu(i) {
cfs_rq = tg->cfs_rq[i];
kfree(tg);
}
-static int sched_can_attach(struct container_subsys *ss,
- struct container *cont, struct task_struct *tsk)
+/* Destroy runqueue etc associated with a task group */
+void sched_destroy_group(struct task_grp *tg)
{
- /* We don't support RT-tasks being in separate groups */
- if (tsk->sched_class != &fair_sched_class)
- return -EINVAL;
+ struct cfs_rq *cfs_rq;
+ int i;
- return 0;
+ 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 */
-static void sched_move_task(struct container_subsys *ss, struct container *cont,
- struct container *old_cont, struct task_struct *tsk)
+/* 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;
spin_unlock_irq(&rq->lock);
}
-static ssize_t cpu_shares_write(struct container *cont, struct cftype *cftype,
- struct file *file, const char __user *userbuf,
- size_t nbytes, loff_t *ppos)
+int sched_group_set_shares(struct task_grp *tg, unsigned long shares)
{
int i;
- unsigned long shareval;
- struct task_grp *tg = container_tg(cont);
- char buffer[2*sizeof(unsigned long) + 1];
- if (nbytes > 2*sizeof(unsigned long)) /* safety check */
- return -E2BIG;
-
- if (copy_from_user(buffer, userbuf, nbytes))
- return -EFAULT;
+ if (tg->shares == shares)
+ return 0;
- buffer[nbytes] = 0; /* nul-terminate */
- shareval = simple_strtoul(buffer, NULL, 10);
+ /* return -EINVAL if the new value is not sane */
- tg->shares = shareval;
+ tg->shares = shares;
for_each_possible_cpu(i)
- set_se_shares(tg->se[i], shareval);
-
- return nbytes;
-}
-
-static u64 cpu_shares_read_uint(struct container *cont, struct cftype *cft)
-{
- struct task_grp *tg = container_tg(cont);
+ set_se_shares(tg->se[i], shares);
- return (u64) tg->shares;
-}
-
-struct cftype cpuctl_share = {
- .name = "shares",
- .read_uint = cpu_shares_read_uint,
- .write = cpu_shares_write,
-};
-
-static int sched_populate(struct container_subsys *ss, struct container *cont)
-{
- return container_add_file(cont, ss, &cpuctl_share);
+ return 0;
}
-struct container_subsys cpu_subsys = {
- .name = "cpu",
- .create = sched_create_group,
- .destroy = sched_destroy_group,
- .can_attach = sched_can_attach,
- .attach = sched_move_task,
- .populate = sched_populate,
- .subsys_id = cpu_subsys_id,
- .early_init = 1,
-};
-
#endif /* CONFIG_FAIR_GROUP_SCHED */
projects / deliverable / linux.git / blobdiff