/*
* 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 cfs_rq;
/* task group related information */
-struct task_grp {
+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 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.
*/
-struct task_grp init_task_grp = {
- .se = init_sched_entity_p,
- .cfs_rq = init_cfs_rq_p,
- };
+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
+# define INIT_TASK_GRP_LOAD 2*NICE_0_LOAD
#else
-#define INIT_TASK_GRP_LOAD NICE_0_LOAD
+# define INIT_TASK_GRP_LOAD NICE_0_LOAD
#endif
-static int init_task_grp_load = INIT_TASK_GRP_LOAD;
+static int init_task_group_load = INIT_TASK_GRP_LOAD;
/* return group to which a task belongs */
-static inline struct task_grp *task_grp(struct task_struct *p)
+static inline struct task_group *task_group(struct task_struct *p)
{
- struct task_grp *tg;
+ struct task_group *tg;
#ifdef CONFIG_FAIR_USER_SCHED
tg = p->user->tg;
#else
- tg = &init_task_grp;
+ 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_grp(p)->cfs_rq[task_cpu(p)];
- p->se.parent = task_grp(p)->se[task_cpu(p)];
+ p->se.cfs_rq = task_group(p)->cfs_rq[task_cpu(p)];
+ p->se.parent = task_group(p)->se[task_cpu(p)];
}
#else
* list is used during load balance.
*/
struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
- struct task_grp *tg; /* group that "owns" this runqueue */
+ 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_USE_TREE_AVG = 4,
+ 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_USE_TREE_AVG *0 |
- SCHED_FEAT_APPROX_AVG *0;
+ 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)
return now;
}
+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;
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.
*/
* 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);
{
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 (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;
*
* 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);
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) &&
* 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;
}
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;
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
&& 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
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_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_grp_load;
+ 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_grp_load);
- se->parent = NULL;
- }
- init_task_grp.shares = init_task_grp_load;
+ 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
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
#ifdef CONFIG_FAIR_GROUP_SCHED
/* allocate runqueue etc for a new task group */
-struct task_grp *sched_create_group(void)
+struct task_group *sched_create_group(void)
{
- struct task_grp *tg;
+ struct task_group *tg;
struct cfs_rq *cfs_rq;
struct sched_entity *se;
struct rq *rq;
}
tg->shares = NICE_0_LOAD;
+ spin_lock_init(&tg->lock);
return tg;
err:
for_each_possible_cpu(i) {
- if (tg->cfs_rq && tg->cfs_rq[i])
+ if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
- if (tg->se && tg->se[i])
+ if (tg->se)
kfree(tg->se[i]);
}
- if (tg->cfs_rq)
- kfree(tg->cfs_rq);
- if (tg->se)
- kfree(tg->se);
- if (tg)
- kfree(tg);
+ kfree(tg->cfs_rq);
+ kfree(tg->se);
+ kfree(tg);
return ERR_PTR(-ENOMEM);
}
static void free_sched_group(struct rcu_head *rhp)
{
struct cfs_rq *cfs_rq = container_of(rhp, struct cfs_rq, rcu);
- struct task_grp *tg = cfs_rq->tg;
+ struct task_group *tg = cfs_rq->tg;
struct sched_entity *se;
int i;
}
/* Destroy runqueue etc associated with a task group */
-void sched_destroy_group(struct task_grp *tg)
+void sched_destroy_group(struct task_group *tg)
{
struct cfs_rq *cfs_rq;
int i;
}
/* 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.
+ * 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)
{
spin_unlock_irq(&rq->lock);
}
-int sched_group_set_shares(struct task_grp *tg, unsigned long shares)
+int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
int i;
+ spin_lock(&tg->lock);
if (tg->shares == shares)
- return 0;
+ goto done;
/* return -EINVAL if the new value is not sane */
for_each_possible_cpu(i)
set_se_shares(tg->se[i], shares);
+done:
+ spin_unlock(&tg->lock);
return 0;
}
-#endif /* CONFIG_FAIR_GROUP_SCHED */
+unsigned long sched_group_shares(struct task_group *tg)
+{
+ return tg->shares;
+}
+
+#endif /* CONFIG_FAIR_GROUP_SCHED */