#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
+#include <linux/debug_locks.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
*/
#define SCALE_PRIO(x, prio) \
- max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)
+ max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)
-static unsigned int task_timeslice(task_t *p)
+static unsigned int static_prio_timeslice(int static_prio)
{
- if (p->static_prio < NICE_TO_PRIO(0))
- return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
+ if (static_prio < NICE_TO_PRIO(0))
+ return SCALE_PRIO(DEF_TIMESLICE * 4, static_prio);
else
- return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
+ return SCALE_PRIO(DEF_TIMESLICE, static_prio);
+}
+
+static inline unsigned int task_timeslice(struct task_struct *p)
+{
+ return static_prio_timeslice(p->static_prio);
}
-#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran) \
- < (long long) (sd)->cache_hot_time)
/*
* These are the runqueue data structures:
*/
-typedef struct runqueue runqueue_t;
-
struct prio_array {
unsigned int nr_active;
DECLARE_BITMAP(bitmap, MAX_PRIO+1); /* include 1 bit for delimiter */
* (such as the load balancing or the thread migration code), lock
* acquire operations must be ordered by ascending &runqueue.
*/
-struct runqueue {
+struct rq {
spinlock_t lock;
/*
* remote CPUs use both these fields when doing load calculation.
*/
unsigned long nr_running;
+ unsigned long raw_weighted_load;
#ifdef CONFIG_SMP
unsigned long cpu_load[3];
#endif
unsigned long expired_timestamp;
unsigned long long timestamp_last_tick;
- task_t *curr, *idle;
+ struct task_struct *curr, *idle;
struct mm_struct *prev_mm;
- prio_array_t *active, *expired, arrays[2];
+ struct prio_array *active, *expired, arrays[2];
int best_expired_prio;
atomic_t nr_iowait;
int active_balance;
int push_cpu;
- task_t *migration_thread;
+ struct task_struct *migration_thread;
struct list_head migration_queue;
#endif
unsigned long ttwu_cnt;
unsigned long ttwu_local;
#endif
+ struct lock_class_key rq_lock_key;
};
-static DEFINE_PER_CPU(struct runqueue, runqueues);
+static DEFINE_PER_CPU(struct rq, runqueues);
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
* The domain tree of any CPU may only be accessed from within
* preempt-disabled sections.
*/
-#define for_each_domain(cpu, domain) \
-for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
+#define for_each_domain(cpu, __sd) \
+ for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#endif
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
-static inline int task_running(runqueue_t *rq, task_t *p)
+static inline int task_running(struct rq *rq, struct task_struct *p)
{
return rq->curr == p;
}
-static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
}
-static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_DEBUG_SPINLOCK
/* this is a valid case when another task releases the spinlock */
rq->lock.owner = current;
#endif
+ /*
+ * If we are tracking spinlock dependencies then we have to
+ * fix up the runqueue lock - which gets 'carried over' from
+ * prev into current:
+ */
+ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+
spin_unlock_irq(&rq->lock);
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline int task_running(runqueue_t *rq, task_t *p)
+static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
return p->oncpu;
#endif
}
-static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
/*
#endif
}
-static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
+/*
+ * __task_rq_lock - lock the runqueue a given task resides on.
+ * Must be called interrupts disabled.
+ */
+static inline struct rq *__task_rq_lock(struct task_struct *p)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+repeat_lock_task:
+ rq = task_rq(p);
+ spin_lock(&rq->lock);
+ if (unlikely(rq != task_rq(p))) {
+ spin_unlock(&rq->lock);
+ goto repeat_lock_task;
+ }
+ return rq;
+}
+
/*
* task_rq_lock - lock the runqueue a given task resides on and disable
* interrupts. Note the ordering: we can safely lookup the task_rq without
* explicitly disabling preemption.
*/
-static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
+static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
__acquires(rq->lock)
{
- struct runqueue *rq;
+ struct rq *rq;
repeat_lock_task:
local_irq_save(*flags);
return rq;
}
-static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
+static inline void __task_rq_unlock(struct rq *rq)
+ __releases(rq->lock)
+{
+ spin_unlock(&rq->lock);
+}
+
+static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
__releases(rq->lock)
{
spin_unlock_irqrestore(&rq->lock, *flags);
seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
seq_printf(seq, "timestamp %lu\n", jiffies);
for_each_online_cpu(cpu) {
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
struct sched_domain *sd;
int dcnt = 0;
/*
* rq_lock - lock a given runqueue and disable interrupts.
*/
-static inline runqueue_t *this_rq_lock(void)
+static inline struct rq *this_rq_lock(void)
__acquires(rq->lock)
{
- runqueue_t *rq;
+ struct rq *rq;
local_irq_disable();
rq = this_rq();
* long it was from the *first* time it was queued to the time that it
* finally hit a cpu.
*/
-static inline void sched_info_dequeued(task_t *t)
+static inline void sched_info_dequeued(struct task_struct *t)
{
t->sched_info.last_queued = 0;
}
* long it was waiting to run. We also note when it began so that we
* can keep stats on how long its timeslice is.
*/
-static void sched_info_arrive(task_t *t)
+static void sched_info_arrive(struct task_struct *t)
{
unsigned long now = jiffies, diff = 0;
- struct runqueue *rq = task_rq(t);
+ struct rq *rq = task_rq(t);
if (t->sched_info.last_queued)
diff = now - t->sched_info.last_queued;
* the timestamp if it is already not set. It's assumed that
* sched_info_dequeued() will clear that stamp when appropriate.
*/
-static inline void sched_info_queued(task_t *t)
+static inline void sched_info_queued(struct task_struct *t)
{
if (!t->sched_info.last_queued)
t->sched_info.last_queued = jiffies;
* Called when a process ceases being the active-running process, either
* voluntarily or involuntarily. Now we can calculate how long we ran.
*/
-static inline void sched_info_depart(task_t *t)
+static inline void sched_info_depart(struct task_struct *t)
{
- struct runqueue *rq = task_rq(t);
+ struct rq *rq = task_rq(t);
unsigned long diff = jiffies - t->sched_info.last_arrival;
t->sched_info.cpu_time += diff;
* their time slice. (This may also be called when switching to or from
* the idle task.) We are only called when prev != next.
*/
-static inline void sched_info_switch(task_t *prev, task_t *next)
+static inline void
+sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
- struct runqueue *rq = task_rq(prev);
+ struct rq *rq = task_rq(prev);
/*
* prev now departs the cpu. It's not interesting to record
/*
* Adding/removing a task to/from a priority array:
*/
-static void dequeue_task(struct task_struct *p, prio_array_t *array)
+static void dequeue_task(struct task_struct *p, struct prio_array *array)
{
array->nr_active--;
list_del(&p->run_list);
__clear_bit(p->prio, array->bitmap);
}
-static void enqueue_task(struct task_struct *p, prio_array_t *array)
+static void enqueue_task(struct task_struct *p, struct prio_array *array)
{
sched_info_queued(p);
list_add_tail(&p->run_list, array->queue + p->prio);
* Put task to the end of the run list without the overhead of dequeue
* followed by enqueue.
*/
-static void requeue_task(struct task_struct *p, prio_array_t *array)
+static void requeue_task(struct task_struct *p, struct prio_array *array)
{
list_move_tail(&p->run_list, array->queue + p->prio);
}
-static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
+static inline void
+enqueue_task_head(struct task_struct *p, struct prio_array *array)
{
list_add(&p->run_list, array->queue + p->prio);
__set_bit(p->prio, array->bitmap);
}
/*
- * effective_prio - return the priority that is based on the static
+ * __normal_prio - return the priority that is based on the static
* priority but is modified by bonuses/penalties.
*
* We scale the actual sleep average [0 .... MAX_SLEEP_AVG]
*
* Both properties are important to certain workloads.
*/
-static int effective_prio(task_t *p)
+
+static inline int __normal_prio(struct task_struct *p)
{
int bonus, prio;
- if (rt_task(p))
- return p->prio;
-
bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;
prio = p->static_prio - bonus;
return prio;
}
+/*
+ * To aid in avoiding the subversion of "niceness" due to uneven distribution
+ * of tasks with abnormal "nice" values across CPUs the contribution that
+ * each task makes to its run queue's load is weighted according to its
+ * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
+ * scaled version of the new time slice allocation that they receive on time
+ * slice expiry etc.
+ */
+
+/*
+ * Assume: static_prio_timeslice(NICE_TO_PRIO(0)) == DEF_TIMESLICE
+ * If static_prio_timeslice() is ever changed to break this assumption then
+ * this code will need modification
+ */
+#define TIME_SLICE_NICE_ZERO DEF_TIMESLICE
+#define LOAD_WEIGHT(lp) \
+ (((lp) * SCHED_LOAD_SCALE) / TIME_SLICE_NICE_ZERO)
+#define PRIO_TO_LOAD_WEIGHT(prio) \
+ LOAD_WEIGHT(static_prio_timeslice(prio))
+#define RTPRIO_TO_LOAD_WEIGHT(rp) \
+ (PRIO_TO_LOAD_WEIGHT(MAX_RT_PRIO) + LOAD_WEIGHT(rp))
+
+static void set_load_weight(struct task_struct *p)
+{
+ if (has_rt_policy(p)) {
+#ifdef CONFIG_SMP
+ if (p == task_rq(p)->migration_thread)
+ /*
+ * The migration thread does the actual balancing.
+ * Giving its load any weight will skew balancing
+ * adversely.
+ */
+ p->load_weight = 0;
+ else
+#endif
+ p->load_weight = RTPRIO_TO_LOAD_WEIGHT(p->rt_priority);
+ } else
+ p->load_weight = PRIO_TO_LOAD_WEIGHT(p->static_prio);
+}
+
+static inline void
+inc_raw_weighted_load(struct rq *rq, const struct task_struct *p)
+{
+ rq->raw_weighted_load += p->load_weight;
+}
+
+static inline void
+dec_raw_weighted_load(struct rq *rq, const struct task_struct *p)
+{
+ rq->raw_weighted_load -= p->load_weight;
+}
+
+static inline void inc_nr_running(struct task_struct *p, struct rq *rq)
+{
+ rq->nr_running++;
+ inc_raw_weighted_load(rq, p);
+}
+
+static inline void dec_nr_running(struct task_struct *p, struct rq *rq)
+{
+ rq->nr_running--;
+ dec_raw_weighted_load(rq, p);
+}
+
+/*
+ * Calculate the expected normal priority: i.e. priority
+ * without taking RT-inheritance into account. Might be
+ * boosted by interactivity modifiers. Changes upon fork,
+ * setprio syscalls, and whenever the interactivity
+ * estimator recalculates.
+ */
+static inline int normal_prio(struct task_struct *p)
+{
+ int prio;
+
+ if (has_rt_policy(p))
+ prio = MAX_RT_PRIO-1 - p->rt_priority;
+ else
+ prio = __normal_prio(p);
+ return prio;
+}
+
+/*
+ * Calculate the current priority, i.e. the priority
+ * taken into account by the scheduler. This value might
+ * be boosted by RT tasks, or might be boosted by
+ * interactivity modifiers. Will be RT if the task got
+ * RT-boosted. If not then it returns p->normal_prio.
+ */
+static int effective_prio(struct task_struct *p)
+{
+ p->normal_prio = normal_prio(p);
+ /*
+ * If we are RT tasks or we were boosted to RT priority,
+ * keep the priority unchanged. Otherwise, update priority
+ * to the normal priority:
+ */
+ if (!rt_prio(p->prio))
+ return p->normal_prio;
+ return p->prio;
+}
+
/*
* __activate_task - move a task to the runqueue.
*/
-static void __activate_task(task_t *p, runqueue_t *rq)
+static void __activate_task(struct task_struct *p, struct rq *rq)
{
- prio_array_t *target = rq->active;
+ struct prio_array *target = rq->active;
if (batch_task(p))
target = rq->expired;
enqueue_task(p, target);
- rq->nr_running++;
+ inc_nr_running(p, rq);
}
/*
* __activate_idle_task - move idle task to the _front_ of runqueue.
*/
-static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
+static inline void __activate_idle_task(struct task_struct *p, struct rq *rq)
{
enqueue_task_head(p, rq->active);
- rq->nr_running++;
+ inc_nr_running(p, rq);
}
-static int recalc_task_prio(task_t *p, unsigned long long now)
+/*
+ * Recalculate p->normal_prio and p->prio after having slept,
+ * updating the sleep-average too:
+ */
+static int recalc_task_prio(struct task_struct *p, unsigned long long now)
{
/* Caller must always ensure 'now >= p->timestamp' */
unsigned long sleep_time = now - p->timestamp;
* Update all the scheduling statistics stuff. (sleep average
* calculation, priority modifiers, etc.)
*/
-static void activate_task(task_t *p, runqueue_t *rq, int local)
+static void activate_task(struct task_struct *p, struct rq *rq, int local)
{
unsigned long long now;
#ifdef CONFIG_SMP
if (!local) {
/* Compensate for drifting sched_clock */
- runqueue_t *this_rq = this_rq();
+ struct rq *this_rq = this_rq();
now = (now - this_rq->timestamp_last_tick)
+ rq->timestamp_last_tick;
}
/*
* deactivate_task - remove a task from the runqueue.
*/
-static void deactivate_task(struct task_struct *p, runqueue_t *rq)
+static void deactivate_task(struct task_struct *p, struct rq *rq)
{
- rq->nr_running--;
+ dec_nr_running(p, rq);
dequeue_task(p, p->array);
p->array = NULL;
}
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif
-static void resched_task(task_t *p)
+static void resched_task(struct task_struct *p)
{
int cpu;
smp_send_reschedule(cpu);
}
#else
-static inline void resched_task(task_t *p)
+static inline void resched_task(struct task_struct *p)
{
assert_spin_locked(&task_rq(p)->lock);
set_tsk_need_resched(p);
* task_curr - is this task currently executing on a CPU?
* @p: the task in question.
*/
-inline int task_curr(const task_t *p)
+inline int task_curr(const struct task_struct *p)
{
return cpu_curr(task_cpu(p)) == p;
}
+/* Used instead of source_load when we know the type == 0 */
+unsigned long weighted_cpuload(const int cpu)
+{
+ return cpu_rq(cpu)->raw_weighted_load;
+}
+
#ifdef CONFIG_SMP
-typedef struct {
+struct migration_req {
struct list_head list;
- task_t *task;
+ struct task_struct *task;
int dest_cpu;
struct completion done;
-} migration_req_t;
+};
/*
* The task's runqueue lock must be held.
* Returns true if you have to wait for migration thread.
*/
-static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
+static int
+migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
{
- runqueue_t *rq = task_rq(p);
+ struct rq *rq = task_rq(p);
/*
* If the task is not on a runqueue (and not running), then
req->task = p;
req->dest_cpu = dest_cpu;
list_add(&req->list, &rq->migration_queue);
+
return 1;
}
* smp_call_function() if an IPI is sent by the same process we are
* waiting to become inactive.
*/
-void wait_task_inactive(task_t *p)
+void wait_task_inactive(struct task_struct *p)
{
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
int preempted;
repeat:
* to another CPU then no harm is done and the purpose has been
* achieved as well.
*/
-void kick_process(task_t *p)
+void kick_process(struct task_struct *p)
{
int cpu;
}
/*
- * Return a low guess at the load of a migration-source cpu.
+ * Return a low guess at the load of a migration-source cpu weighted
+ * according to the scheduling class and "nice" value.
*
* We want to under-estimate the load of migration sources, to
* balance conservatively.
*/
static inline unsigned long source_load(int cpu, int type)
{
- runqueue_t *rq = cpu_rq(cpu);
- unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+ struct rq *rq = cpu_rq(cpu);
+
if (type == 0)
- return load_now;
+ return rq->raw_weighted_load;
- return min(rq->cpu_load[type-1], load_now);
+ return min(rq->cpu_load[type-1], rq->raw_weighted_load);
}
/*
- * Return a high guess at the load of a migration-target 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)
{
- runqueue_t *rq = cpu_rq(cpu);
- unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
+ struct rq *rq = cpu_rq(cpu);
+
if (type == 0)
- return load_now;
+ return rq->raw_weighted_load;
+
+ return max(rq->cpu_load[type-1], rq->raw_weighted_load);
+}
- return max(rq->cpu_load[type-1], load_now);
+/*
+ * Return the average load per task on the cpu's run queue
+ */
+static inline unsigned long cpu_avg_load_per_task(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long n = rq->nr_running;
+
+ return n ? rq->raw_weighted_load / n : SCHED_LOAD_SCALE;
}
/*
cpus_and(tmp, group->cpumask, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
- load = source_load(i, 0);
+ load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
min_load = load;
struct sched_domain *tmp, *sd = NULL;
for_each_domain(cpu, tmp) {
+ /*
+ * If power savings logic is enabled for a domain, stop there.
+ */
+ if (tmp->flags & SD_POWERSAVINGS_BALANCE)
+ break;
if (tmp->flags & flag)
sd = tmp;
}
* Returns the CPU we should wake onto.
*/
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-static int wake_idle(int cpu, task_t *p)
+static int wake_idle(int cpu, struct task_struct *p)
{
cpumask_t tmp;
struct sched_domain *sd;
return cpu;
}
#else
-static inline int wake_idle(int cpu, task_t *p)
+static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
}
*
* returns failure only if the task is already active.
*/
-static int try_to_wake_up(task_t *p, unsigned int state, int sync)
+static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
int cpu, this_cpu, success = 0;
unsigned long flags;
long old_state;
- runqueue_t *rq;
+ struct rq *rq;
#ifdef CONFIG_SMP
- unsigned long load, this_load;
struct sched_domain *sd, *this_sd = NULL;
+ unsigned long load, this_load;
int new_cpu;
#endif
if (this_sd->flags & SD_WAKE_AFFINE) {
unsigned long tl = this_load;
+ unsigned long tl_per_task = cpu_avg_load_per_task(this_cpu);
+
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
if (sync)
- tl -= SCHED_LOAD_SCALE;
+ tl -= current->load_weight;
if ((tl <= load &&
- tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) ||
- 100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) {
+ tl + target_load(cpu, idx) <= tl_per_task) ||
+ 100*(tl + p->load_weight) <= imbalance*load) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
return success;
}
-int fastcall wake_up_process(task_t *p)
+int fastcall wake_up_process(struct task_struct *p)
{
return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}
-
EXPORT_SYMBOL(wake_up_process);
-int fastcall wake_up_state(task_t *p, unsigned int state)
+int fastcall wake_up_state(struct task_struct *p, unsigned int state)
{
return try_to_wake_up(p, state, 0);
}
* Perform scheduler related setup for a newly forked process p.
* p is forked by current.
*/
-void fastcall sched_fork(task_t *p, int clone_flags)
+void fastcall sched_fork(struct task_struct *p, int clone_flags)
{
int cpu = get_cpu();
* event cannot wake it up and insert it on the runqueue either.
*/
p->state = TASK_RUNNING;
+
+ /*
+ * Make sure we do not leak PI boosting priority to the child:
+ */
+ p->prio = current->normal_prio;
+
INIT_LIST_HEAD(&p->run_list);
p->array = NULL;
#ifdef CONFIG_SCHEDSTATS
* 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(task_t *p, unsigned long clone_flags)
+void fastcall wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
+ struct rq *rq, *this_rq;
unsigned long flags;
int this_cpu, cpu;
- runqueue_t *rq, *this_rq;
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
__activate_task(p, rq);
else {
p->prio = current->prio;
+ p->normal_prio = current->normal_prio;
list_add_tail(&p->run_list, ¤t->run_list);
p->array = current->array;
p->array->nr_active++;
- rq->nr_running++;
+ inc_nr_running(p, rq);
}
set_need_resched();
} else
* artificially, because any timeslice recovered here
* was given away by the parent in the first place.)
*/
-void fastcall sched_exit(task_t *p)
+void fastcall sched_exit(struct task_struct *p)
{
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
/*
* If the child was a (relative-) CPU hog then decrease
* prepare_task_switch sets up locking and calls architecture specific
* hooks.
*/
-static inline void prepare_task_switch(runqueue_t *rq, task_t *next)
+static inline void prepare_task_switch(struct rq *rq, struct task_struct *next)
{
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
-static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
+static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
__releases(rq->lock)
{
struct mm_struct *mm = rq->prev_mm;
* schedule_tail - first thing a freshly forked thread must call.
* @prev: the thread we just switched away from.
*/
-asmlinkage void schedule_tail(task_t *prev)
+asmlinkage void schedule_tail(struct task_struct *prev)
__releases(rq->lock)
{
- runqueue_t *rq = this_rq();
+ struct rq *rq = this_rq();
+
finish_task_switch(rq, prev);
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
/* In this case, finish_task_switch does not reenable preemption */
* context_switch - switch to the new MM and the new
* thread's register state.
*/
-static inline
-task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next)
+static inline struct task_struct *
+context_switch(struct rq *rq, struct task_struct *prev,
+ struct task_struct *next)
{
struct mm_struct *mm = next->mm;
struct mm_struct *oldmm = prev->active_mm;
WARN_ON(rq->prev_mm);
rq->prev_mm = oldmm;
}
+ spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
#ifdef CONFIG_SMP
+/*
+ * Is this task likely cache-hot:
+ */
+static inline int
+task_hot(struct task_struct *p, unsigned long long now, struct sched_domain *sd)
+{
+ return (long long)(now - p->last_ran) < (long long)sd->cache_hot_time;
+}
+
/*
* double_rq_lock - safely lock two runqueues
*
* Note this does not disable interrupts like task_rq_lock,
* you need to do so manually before calling.
*/
-static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
__acquires(rq1->lock)
__acquires(rq2->lock)
{
* Note this does not restore interrupts like task_rq_unlock,
* you need to do so manually after calling.
*/
-static void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2)
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
__releases(rq1->lock)
__releases(rq2->lock)
{
/*
* double_lock_balance - lock the busiest runqueue, this_rq is locked already.
*/
-static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
+static void double_lock_balance(struct rq *this_rq, struct rq *busiest)
__releases(this_rq->lock)
__acquires(busiest->lock)
__acquires(this_rq->lock)
* allow dest_cpu, which will force the cpu onto dest_cpu. Then
* the cpu_allowed mask is restored.
*/
-static void sched_migrate_task(task_t *p, int dest_cpu)
+static void sched_migrate_task(struct task_struct *p, int dest_cpu)
{
- migration_req_t req;
- runqueue_t *rq;
+ struct migration_req req;
unsigned long flags;
+ struct rq *rq;
rq = task_rq_lock(p, &flags);
if (!cpu_isset(dest_cpu, p->cpus_allowed)
if (migrate_task(p, dest_cpu, &req)) {
/* Need to wait for migration thread (might exit: take ref). */
struct task_struct *mt = rq->migration_thread;
+
get_task_struct(mt);
task_rq_unlock(rq, &flags);
wake_up_process(mt);
put_task_struct(mt);
wait_for_completion(&req.done);
+
return;
}
out:
* pull_task - move a task from a remote runqueue to the local runqueue.
* Both runqueues must be locked.
*/
-static
-void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
- runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
+static void pull_task(struct rq *src_rq, struct prio_array *src_array,
+ struct task_struct *p, struct rq *this_rq,
+ struct prio_array *this_array, int this_cpu)
{
dequeue_task(p, src_array);
- src_rq->nr_running--;
+ dec_nr_running(p, src_rq);
set_task_cpu(p, this_cpu);
- this_rq->nr_running++;
+ inc_nr_running(p, this_rq);
enqueue_task(p, this_array);
p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
+ this_rq->timestamp_last_tick;
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
static
-int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
+int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
struct sched_domain *sd, enum idle_type idle,
int *all_pinned)
{
return 1;
}
+#define rq_best_prio(rq) min((rq)->curr->prio, (rq)->best_expired_prio)
+
/*
- * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq,
- * as part of a balancing operation within "domain". Returns the number of
- * tasks moved.
+ * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted
+ * load from busiest to this_rq, as part of a balancing operation within
+ * "domain". Returns the number of tasks moved.
*
* Called with both runqueues locked.
*/
-static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
- unsigned long max_nr_move, struct sched_domain *sd,
- enum idle_type idle, int *all_pinned)
+static int move_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 idle_type idle,
+ int *all_pinned)
{
- prio_array_t *array, *dst_array;
+ int idx, pulled = 0, pinned = 0, this_best_prio, best_prio,
+ best_prio_seen, skip_for_load;
+ struct prio_array *array, *dst_array;
struct list_head *head, *curr;
- int idx, pulled = 0, pinned = 0;
- task_t *tmp;
+ struct task_struct *tmp;
+ long rem_load_move;
- if (max_nr_move == 0)
+ if (max_nr_move == 0 || max_load_move == 0)
goto out;
+ rem_load_move = max_load_move;
pinned = 1;
+ this_best_prio = rq_best_prio(this_rq);
+ best_prio = rq_best_prio(busiest);
+ /*
+ * Enable handling of the case where there is more than one task
+ * with the best priority. If the current running task is one
+ * of those with prio==best_prio we know it won't be moved
+ * and therefore it's safe to override the skip (based on load) of
+ * any task we find with that prio.
+ */
+ best_prio_seen = best_prio == busiest->curr->prio;
/*
* We first consider expired tasks. Those will likely not be
head = array->queue + idx;
curr = head->prev;
skip_queue:
- tmp = list_entry(curr, task_t, run_list);
+ tmp = list_entry(curr, struct task_struct, run_list);
curr = curr->prev;
- if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
+ /*
+ * To help distribute high priority tasks accross 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
+ */
+ skip_for_load = tmp->load_weight > rem_load_move;
+ if (skip_for_load && idx < this_best_prio)
+ skip_for_load = !best_prio_seen && idx == best_prio;
+ if (skip_for_load ||
+ !can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
+
+ best_prio_seen |= idx == best_prio;
if (curr != head)
goto skip_queue;
idx++;
pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
pulled++;
+ rem_load_move -= tmp->load_weight;
- /* We only want to steal up to the prescribed number of tasks. */
- if (pulled < max_nr_move) {
+ /*
+ * We only want to steal up to the prescribed number of tasks
+ * and the prescribed amount of weighted load.
+ */
+ if (pulled < max_nr_move && rem_load_move > 0) {
+ if (idx < this_best_prio)
+ this_best_prio = idx;
if (curr != head)
goto skip_queue;
idx++;
/*
* find_busiest_group finds and returns the busiest CPU group within the
- * domain. It calculates and returns the number of tasks which should be
- * moved to restore balance via the imbalance parameter.
+ * domain. It calculates and returns the amount of weighted load which
+ * should be moved to restore balance via the imbalance parameter.
*/
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
unsigned long max_pull;
+ unsigned long busiest_load_per_task, busiest_nr_running;
+ unsigned long this_load_per_task, this_nr_running;
int load_idx;
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+ int power_savings_balance = 1;
+ unsigned long leader_nr_running = 0, min_load_per_task = 0;
+ unsigned long min_nr_running = ULONG_MAX;
+ struct sched_group *group_min = NULL, *group_leader = NULL;
+#endif
max_load = this_load = total_load = total_pwr = 0;
+ busiest_load_per_task = busiest_nr_running = 0;
+ this_load_per_task = this_nr_running = 0;
if (idle == NOT_IDLE)
load_idx = sd->busy_idx;
else if (idle == NEWLY_IDLE)
load_idx = sd->idle_idx;
do {
- unsigned long load;
+ unsigned long load, group_capacity;
int local_group;
int i;
+ unsigned long sum_nr_running, sum_weighted_load;
local_group = cpu_isset(this_cpu, group->cpumask);
/* Tally up the load of all CPUs in the group */
- avg_load = 0;
+ sum_weighted_load = sum_nr_running = avg_load = 0;
for_each_cpu_mask(i, group->cpumask) {
+ struct rq *rq = cpu_rq(i);
+
if (*sd_idle && !idle_cpu(i))
*sd_idle = 0;
load = source_load(i, load_idx);
avg_load += load;
+ sum_nr_running += rq->nr_running;
+ sum_weighted_load += rq->raw_weighted_load;
}
total_load += avg_load;
/* Adjust by relative CPU power of the group */
avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+ group_capacity = group->cpu_power / SCHED_LOAD_SCALE;
+
if (local_group) {
this_load = avg_load;
this = group;
- } else if (avg_load > max_load) {
+ this_nr_running = sum_nr_running;
+ this_load_per_task = sum_weighted_load;
+ } else if (avg_load > max_load &&
+ sum_nr_running > group_capacity) {
max_load = avg_load;
busiest = group;
+ busiest_nr_running = sum_nr_running;
+ busiest_load_per_task = sum_weighted_load;
+ }
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+ /*
+ * Busy processors will not participate in power savings
+ * balance.
+ */
+ if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+ goto group_next;
+
+ /*
+ * If the local group is idle or completely loaded
+ * no need to do power savings balance at this domain
+ */
+ if (local_group && (this_nr_running >= group_capacity ||
+ !this_nr_running))
+ power_savings_balance = 0;
+
+ /*
+ * If a group is already running at full capacity or idle,
+ * don't include that group in power savings calculations
+ */
+ if (!power_savings_balance || sum_nr_running >= group_capacity
+ || !sum_nr_running)
+ goto group_next;
+
+ /*
+ * Calculate the group which has the least non-idle load.
+ * This is the group from where we need to pick up the load
+ * for saving power
+ */
+ if ((sum_nr_running < min_nr_running) ||
+ (sum_nr_running == min_nr_running &&
+ first_cpu(group->cpumask) <
+ first_cpu(group_min->cpumask))) {
+ group_min = group;
+ min_nr_running = sum_nr_running;
+ min_load_per_task = sum_weighted_load /
+ sum_nr_running;
+ }
+
+ /*
+ * Calculate the group which is almost near its
+ * capacity but still has some space to pick up some load
+ * from other group and save more power
+ */
+ if (sum_nr_running <= group_capacity - 1) {
+ if (sum_nr_running > leader_nr_running ||
+ (sum_nr_running == leader_nr_running &&
+ first_cpu(group->cpumask) >
+ first_cpu(group_leader->cpumask))) {
+ group_leader = group;
+ leader_nr_running = sum_nr_running;
+ }
}
+group_next:
+#endif
group = group->next;
} while (group != sd->groups);
- if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
+ if (!busiest || this_load >= max_load || busiest_nr_running == 0)
goto out_balanced;
avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
100*max_load <= sd->imbalance_pct*this_load)
goto out_balanced;
+ busiest_load_per_task /= busiest_nr_running;
/*
* We're trying to get all the cpus to the average_load, so we don't
* want to push ourselves above the average load, nor do we wish to
* by pulling tasks to us. Be careful of negative numbers as they'll
* appear as very large values with unsigned longs.
*/
+ if (max_load <= busiest_load_per_task)
+ goto out_balanced;
+
+ /*
+ * In the presence of smp nice balancing, certain scenarios can have
+ * max load less than avg load(as we skip the groups at or below
+ * its cpu_power, while calculating max_load..)
+ */
+ if (max_load < avg_load) {
+ *imbalance = 0;
+ goto small_imbalance;
+ }
/* Don't want to pull so many tasks that a group would go idle */
- max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE);
+ max_pull = min(max_load - avg_load, max_load - busiest_load_per_task);
/* How much load to actually move to equalise the imbalance */
*imbalance = min(max_pull * busiest->cpu_power,
(avg_load - this_load) * this->cpu_power)
/ SCHED_LOAD_SCALE;
- if (*imbalance < SCHED_LOAD_SCALE) {
- unsigned long pwr_now = 0, pwr_move = 0;
- unsigned long tmp;
+ /*
+ * if *imbalance is less than the average load per runnable task
+ * there is no gaurantee that any tasks will be moved so we'll have
+ * a think about bumping its value to force at least one task to be
+ * moved
+ */
+ if (*imbalance < busiest_load_per_task) {
+ unsigned long tmp, pwr_now, pwr_move;
+ unsigned int imbn;
+
+small_imbalance:
+ pwr_move = pwr_now = 0;
+ imbn = 2;
+ if (this_nr_running) {
+ this_load_per_task /= this_nr_running;
+ if (busiest_load_per_task > this_load_per_task)
+ imbn = 1;
+ } else
+ this_load_per_task = SCHED_LOAD_SCALE;
- if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
- *imbalance = 1;
+ if (max_load - this_load >= busiest_load_per_task * imbn) {
+ *imbalance = busiest_load_per_task;
return busiest;
}
* moving them.
*/
- pwr_now += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load);
- pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
+ pwr_now += busiest->cpu_power *
+ min(busiest_load_per_task, max_load);
+ pwr_now += this->cpu_power *
+ min(this_load_per_task, this_load);
pwr_now /= SCHED_LOAD_SCALE;
/* Amount of load we'd subtract */
- tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power;
+ tmp = busiest_load_per_task*SCHED_LOAD_SCALE/busiest->cpu_power;
if (max_load > tmp)
- pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE,
- max_load - tmp);
+ pwr_move += busiest->cpu_power *
+ min(busiest_load_per_task, max_load - tmp);
/* Amount of load we'd add */
if (max_load*busiest->cpu_power <
- SCHED_LOAD_SCALE*SCHED_LOAD_SCALE)
+ busiest_load_per_task*SCHED_LOAD_SCALE)
tmp = max_load*busiest->cpu_power/this->cpu_power;
else
- tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
- pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
+ tmp = busiest_load_per_task*SCHED_LOAD_SCALE/this->cpu_power;
+ pwr_move += this->cpu_power*min(this_load_per_task, this_load + tmp);
pwr_move /= SCHED_LOAD_SCALE;
/* Move if we gain throughput */
if (pwr_move <= pwr_now)
goto out_balanced;
- *imbalance = 1;
- return busiest;
+ *imbalance = busiest_load_per_task;
}
- /* Get rid of the scaling factor, rounding down as we divide */
- *imbalance = *imbalance / SCHED_LOAD_SCALE;
return busiest;
out_balanced:
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+ if (idle == NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+ goto ret;
+ if (this == group_leader && group_leader != group_min) {
+ *imbalance = min_load_per_task;
+ return group_min;
+ }
+ret:
+#endif
*imbalance = 0;
return NULL;
}
/*
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
-static runqueue_t *find_busiest_queue(struct sched_group *group,
- enum idle_type idle)
+static struct rq *
+find_busiest_queue(struct sched_group *group, enum idle_type idle,
+ unsigned long imbalance)
{
- unsigned long load, max_load = 0;
- runqueue_t *busiest = NULL;
+ struct rq *busiest = NULL, *rq;
+ unsigned long max_load = 0;
int i;
for_each_cpu_mask(i, group->cpumask) {
- load = source_load(i, 0);
+ rq = cpu_rq(i);
+
+ if (rq->nr_running == 1 && rq->raw_weighted_load > imbalance)
+ continue;
- if (load > max_load) {
- max_load = load;
- busiest = cpu_rq(i);
+ if (rq->raw_weighted_load > max_load) {
+ max_load = rq->raw_weighted_load;
+ busiest = rq;
}
}
*/
#define MAX_PINNED_INTERVAL 512
+static inline unsigned long minus_1_or_zero(unsigned long n)
+{
+ return n > 0 ? n - 1 : 0;
+}
+
/*
* Check this_cpu to ensure it is balanced within domain. Attempt to move
* tasks if there is an imbalance.
*
* Called with this_rq unlocked.
*/
-static int load_balance(int this_cpu, runqueue_t *this_rq,
+static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum idle_type idle)
{
+ int nr_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
- runqueue_t *busiest;
unsigned long imbalance;
- int nr_moved, all_pinned = 0;
- int active_balance = 0;
- int sd_idle = 0;
+ struct rq *busiest;
- if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
+ if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
+ !sched_smt_power_savings)
sd_idle = 1;
schedstat_inc(sd, lb_cnt[idle]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, idle);
+ busiest = find_busiest_queue(group, idle, imbalance);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
*/
double_rq_lock(this_rq, busiest);
nr_moved = move_tasks(this_rq, this_cpu, busiest,
- imbalance, sd, idle, &all_pinned);
+ minus_1_or_zero(busiest->nr_running),
+ imbalance, sd, idle, &all_pinned);
double_rq_unlock(this_rq, busiest);
/* All tasks on this runqueue were pinned by CPU affinity */
sd->balance_interval *= 2;
}
- if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+ !sched_smt_power_savings)
return -1;
return nr_moved;
(sd->balance_interval < sd->max_interval))
sd->balance_interval *= 2;
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+ !sched_smt_power_savings)
return -1;
return 0;
}
* Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
* this_rq is locked.
*/
-static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
- struct sched_domain *sd)
+static int
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
struct sched_group *group;
- runqueue_t *busiest = NULL;
+ struct rq *busiest = NULL;
unsigned long imbalance;
int nr_moved = 0;
int sd_idle = 0;
- if (sd->flags & SD_SHARE_CPUPOWER)
+ if (sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings)
sd_idle = 1;
schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, NEWLY_IDLE);
+ busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
goto out_balanced;
/* Attempt to move tasks */
double_lock_balance(this_rq, busiest);
nr_moved = move_tasks(this_rq, this_cpu, busiest,
+ minus_1_or_zero(busiest->nr_running),
imbalance, sd, NEWLY_IDLE, NULL);
spin_unlock(&busiest->lock);
}
out_balanced:
schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
- if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+ if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+ !sched_smt_power_savings)
return -1;
sd->nr_balance_failed = 0;
+
return 0;
}
* idle_balance is called by schedule() if this_cpu is about to become
* idle. Attempts to pull tasks from other CPUs.
*/
-static void idle_balance(int this_cpu, runqueue_t *this_rq)
+static void idle_balance(int this_cpu, struct rq *this_rq)
{
struct sched_domain *sd;
for_each_domain(this_cpu, sd) {
if (sd->flags & SD_BALANCE_NEWIDLE) {
- if (load_balance_newidle(this_cpu, this_rq, sd)) {
- /* We've pulled tasks over so stop searching */
+ /* If we've pulled tasks over stop searching: */
+ if (load_balance_newidle(this_cpu, this_rq, sd))
break;
- }
}
}
}
*
* Called with busiest_rq locked.
*/
-static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu)
+static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
{
- struct sched_domain *sd;
- runqueue_t *target_rq;
int target_cpu = busiest_rq->push_cpu;
+ struct sched_domain *sd;
+ struct rq *target_rq;
+ /* Is there any task to move? */
if (busiest_rq->nr_running <= 1)
- /* no task to move */
return;
target_rq = cpu_rq(target_cpu);
/* Search for an sd spanning us and the target CPU. */
for_each_domain(target_cpu, sd) {
if ((sd->flags & SD_LOAD_BALANCE) &&
- cpu_isset(busiest_cpu, sd->span))
+ cpu_isset(busiest_cpu, sd->span))
break;
}
- if (unlikely(sd == NULL))
- goto out;
-
- schedstat_inc(sd, alb_cnt);
+ if (likely(sd)) {
+ schedstat_inc(sd, alb_cnt);
- if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL))
- schedstat_inc(sd, alb_pushed);
- else
- schedstat_inc(sd, alb_failed);
-out:
+ if (move_tasks(target_rq, target_cpu, busiest_rq, 1,
+ RTPRIO_TO_LOAD_WEIGHT(100), sd, SCHED_IDLE,
+ NULL))
+ schedstat_inc(sd, alb_pushed);
+ else
+ schedstat_inc(sd, alb_failed);
+ }
spin_unlock(&target_rq->lock);
}
* Balancing parameters are set up in arch_init_sched_domains.
*/
-/* Don't have all balancing operations going off at once */
-#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)
+/* Don't have all balancing operations going off at once: */
+static inline unsigned long cpu_offset(int cpu)
+{
+ return jiffies + cpu * HZ / NR_CPUS;
+}
-static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
- enum idle_type idle)
+static void
+rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle)
{
- unsigned long old_load, this_load;
- unsigned long j = jiffies + CPU_OFFSET(this_cpu);
+ unsigned long this_load, interval, j = cpu_offset(this_cpu);
struct sched_domain *sd;
- int i;
+ int i, scale;
+
+ this_load = this_rq->raw_weighted_load;
+
+ /* Update our load: */
+ for (i = 0, scale = 1; i < 3; i++, scale <<= 1) {
+ unsigned long old_load, new_load;
- this_load = this_rq->nr_running * SCHED_LOAD_SCALE;
- /* Update our load */
- for (i = 0; i < 3; i++) {
- unsigned long new_load = this_load;
- int scale = 1 << i;
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
}
for_each_domain(this_cpu, sd) {
- unsigned long interval;
-
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
/*
* on UP we do not need to balance between CPUs:
*/
-static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
+static inline void rebalance_tick(int cpu, struct rq *rq, enum idle_type idle)
{
}
-static inline void idle_balance(int cpu, runqueue_t *rq)
+static inline void idle_balance(int cpu, struct rq *rq)
{
}
#endif
-static inline int wake_priority_sleeper(runqueue_t *rq)
+static inline int wake_priority_sleeper(struct rq *rq)
{
int ret = 0;
+
#ifdef CONFIG_SCHED_SMT
spin_lock(&rq->lock);
/*
* This is called on clock ticks and on context switches.
* Bank in p->sched_time the ns elapsed since the last tick or switch.
*/
-static inline void update_cpu_clock(task_t *p, runqueue_t *rq,
- unsigned long long now)
+static inline void
+update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now)
{
- unsigned long long last = max(p->timestamp, rq->timestamp_last_tick);
- p->sched_time += now - last;
+ p->sched_time += now - max(p->timestamp, rq->timestamp_last_tick);
}
/*
* Return current->sched_time plus any more ns on the sched_clock
* that have not yet been banked.
*/
-unsigned long long current_sched_time(const task_t *tsk)
+unsigned long long current_sched_time(const struct task_struct *p)
{
unsigned long long ns;
unsigned long flags;
+
local_irq_save(flags);
- ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick);
- ns = tsk->sched_time + (sched_clock() - ns);
+ ns = max(p->timestamp, task_rq(p)->timestamp_last_tick);
+ ns = p->sched_time + sched_clock() - ns;
local_irq_restore(flags);
+
return ns;
}
* increasing number of running tasks. We also ignore the interactivity
* if a better static_prio task has expired:
*/
-#define EXPIRED_STARVING(rq) \
- ((STARVATION_LIMIT && ((rq)->expired_timestamp && \
- (jiffies - (rq)->expired_timestamp >= \
- STARVATION_LIMIT * ((rq)->nr_running) + 1))) || \
- ((rq)->curr->static_prio > (rq)->best_expired_prio))
+static inline int expired_starving(struct rq *rq)
+{
+ if (rq->curr->static_prio > rq->best_expired_prio)
+ return 1;
+ if (!STARVATION_LIMIT || !rq->expired_timestamp)
+ return 0;
+ if (jiffies - rq->expired_timestamp > STARVATION_LIMIT * rq->nr_running)
+ return 1;
+ return 0;
+}
/*
* Account user cpu time to a process.
cputime_t cputime)
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
- runqueue_t *rq = this_rq();
+ struct rq *rq = this_rq();
cputime64_t tmp;
p->stime = cputime_add(p->stime, cputime);
{
struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
cputime64_t tmp = cputime_to_cputime64(steal);
- runqueue_t *rq = this_rq();
+ struct rq *rq = this_rq();
if (p == rq->idle) {
p->stime = cputime_add(p->stime, steal);
*/
void scheduler_tick(void)
{
- int cpu = smp_processor_id();
- runqueue_t *rq = this_rq();
- task_t *p = current;
unsigned long long now = sched_clock();
+ struct task_struct *p = current;
+ int cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(cpu);
update_cpu_clock(p, rq, now);
if (!rq->expired_timestamp)
rq->expired_timestamp = jiffies;
- if (!TASK_INTERACTIVE(p) || EXPIRED_STARVING(rq)) {
+ if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
enqueue_task(p, rq->expired);
if (p->static_prio < rq->best_expired_prio)
rq->best_expired_prio = p->static_prio;
}
#ifdef CONFIG_SCHED_SMT
-static inline void wakeup_busy_runqueue(runqueue_t *rq)
+static inline void wakeup_busy_runqueue(struct rq *rq)
{
/* If an SMT runqueue is sleeping due to priority reasons wake it up */
if (rq->curr == rq->idle && rq->nr_running)
return;
for_each_cpu_mask(i, sd->span) {
- runqueue_t *smt_rq = cpu_rq(i);
+ struct rq *smt_rq = cpu_rq(i);
if (i == this_cpu)
continue;
* utilize, if another task runs on a sibling. This models the
* slowdown effect of other tasks running on siblings:
*/
-static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd)
+static inline unsigned long
+smt_slice(struct task_struct *p, struct sched_domain *sd)
{
return p->time_slice * (100 - sd->per_cpu_gain) / 100;
}
* acquire their lock. As we only trylock the normal locking order does not
* need to be obeyed.
*/
-static int dependent_sleeper(int this_cpu, runqueue_t *this_rq, task_t *p)
+static int
+dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
{
struct sched_domain *tmp, *sd = NULL;
int ret = 0, i;
return 0;
for_each_cpu_mask(i, sd->span) {
- runqueue_t *smt_rq;
- task_t *smt_curr;
+ struct task_struct *smt_curr;
+ struct rq *smt_rq;
if (i == this_cpu)
continue;
static inline void wake_sleeping_dependent(int this_cpu)
{
}
-
-static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq,
- task_t *p)
+static inline int
+dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
{
return 0;
}
/*
* Underflow?
*/
- BUG_ON((preempt_count() < 0));
+ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
+ return;
preempt_count() += val;
/*
* Spinlock count overflowing soon?
*/
- BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
+ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
}
EXPORT_SYMBOL(add_preempt_count);
/*
* Underflow?
*/
- BUG_ON(val > preempt_count());
+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+ return;
/*
* Is the spinlock portion underflowing?
*/
- BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK));
+ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
+ !(preempt_count() & PREEMPT_MASK)))
+ return;
+
preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);
*/
asmlinkage void __sched schedule(void)
{
- long *switch_count;
- task_t *prev, *next;
- runqueue_t *rq;
- prio_array_t *array;
+ struct task_struct *prev, *next;
+ struct prio_array *array;
struct list_head *queue;
unsigned long long now;
unsigned long run_time;
int cpu, idx, new_prio;
+ long *switch_count;
+ struct rq *rq;
/*
* Test if we are atomic. Since do_exit() needs to call into
idx = sched_find_first_bit(array->bitmap);
queue = array->queue + idx;
- next = list_entry(queue->next, task_t, run_list);
+ next = list_entry(queue->next, struct task_struct, run_list);
if (!rt_task(next) && interactive_sleep(next->sleep_type)) {
unsigned long long delta = now - next->timestamp;
if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
goto need_resched;
}
-
EXPORT_SYMBOL(schedule);
#ifdef CONFIG_PREEMPT
/*
- * this is is the entry point to schedule() from in-kernel preemption
+ * this is the entry point to schedule() from in-kernel preemption
* off of preempt_enable. Kernel preemptions off return from interrupt
* occur there and call schedule directly.
*/
if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
goto need_resched;
}
-
EXPORT_SYMBOL(preempt_schedule);
/*
- * this is is the entry point to schedule() from kernel preemption
+ * this is the entry point to schedule() from kernel preemption
* off of irq context.
* Note, that this is called and return with irqs disabled. This will
* protect us against recursive calling from irq.
struct task_struct *task = current;
int saved_lock_depth;
#endif
- /* Catch callers which need to be fixed*/
+ /* Catch callers which need to be fixed */
BUG_ON(ti->preempt_count || !irqs_disabled());
need_resched:
int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
void *key)
{
- task_t *p = curr->private;
- return try_to_wake_up(p, mode, sync);
+ return try_to_wake_up(curr->private, mode, sync);
}
-
EXPORT_SYMBOL(default_wake_function);
/*
struct list_head *tmp, *next;
list_for_each_safe(tmp, next, &q->task_list) {
- wait_queue_t *curr;
- unsigned flags;
- curr = list_entry(tmp, wait_queue_t, task_list);
- flags = curr->flags;
+ wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
+ unsigned flags = curr->flags;
+
if (curr->func(curr, mode, sync, key) &&
- (flags & WQ_FLAG_EXCLUSIVE) &&
- !--nr_exclusive)
+ (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
break;
}
}
__wake_up_common(q, mode, nr_exclusive, 0, key);
spin_unlock_irqrestore(&q->lock, flags);
}
-
EXPORT_SYMBOL(__wake_up);
/*
void fastcall __sched wait_for_completion(struct completion *x)
{
might_sleep();
+
spin_lock_irq(&x->wait.lock);
if (!x->done) {
DECLARE_WAITQUEUE(wait, current);
schedule();
SLEEP_ON_TAIL
}
-
EXPORT_SYMBOL(interruptible_sleep_on);
long fastcall __sched
return timeout;
}
-
EXPORT_SYMBOL(interruptible_sleep_on_timeout);
void fastcall __sched sleep_on(wait_queue_head_t *q)
schedule();
SLEEP_ON_TAIL
}
-
EXPORT_SYMBOL(sleep_on);
long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
EXPORT_SYMBOL(sleep_on_timeout);
-void set_user_nice(task_t *p, long nice)
+#ifdef CONFIG_RT_MUTEXES
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task
+ * @prio: prio value (kernel-internal form)
+ *
+ * This function changes the 'effective' priority of a task. It does
+ * not touch ->normal_prio like __setscheduler().
+ *
+ * Used by the rt_mutex code to implement priority inheritance logic.
+ */
+void rt_mutex_setprio(struct task_struct *p, int prio)
+{
+ struct prio_array *array;
+ unsigned long flags;
+ struct rq *rq;
+ int oldprio;
+
+ BUG_ON(prio < 0 || prio > MAX_PRIO);
+
+ rq = task_rq_lock(p, &flags);
+
+ oldprio = p->prio;
+ array = p->array;
+ if (array)
+ dequeue_task(p, array);
+ p->prio = prio;
+
+ if (array) {
+ /*
+ * If changing to an RT priority then queue it
+ * in the active array!
+ */
+ if (rt_task(p))
+ array = rq->active;
+ enqueue_task(p, array);
+ /*
+ * 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 (p->prio > oldprio)
+ resched_task(rq->curr);
+ } else if (TASK_PREEMPTS_CURR(p, rq))
+ resched_task(rq->curr);
+ }
+ task_rq_unlock(rq, &flags);
+}
+
+#endif
+
+void set_user_nice(struct task_struct *p, long nice)
{
+ struct prio_array *array;
+ int old_prio, delta;
unsigned long flags;
- prio_array_t *array;
- runqueue_t *rq;
- int old_prio, new_prio, delta;
+ struct rq *rq;
if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
return;
* it wont have any effect on scheduling until the task is
* not SCHED_NORMAL/SCHED_BATCH:
*/
- if (rt_task(p)) {
+ if (has_rt_policy(p)) {
p->static_prio = NICE_TO_PRIO(nice);
goto out_unlock;
}
array = p->array;
- if (array)
+ if (array) {
dequeue_task(p, array);
+ dec_raw_weighted_load(rq, p);
+ }
- old_prio = p->prio;
- new_prio = NICE_TO_PRIO(nice);
- delta = new_prio - old_prio;
p->static_prio = NICE_TO_PRIO(nice);
- p->prio += delta;
+ set_load_weight(p);
+ old_prio = p->prio;
+ p->prio = effective_prio(p);
+ delta = p->prio - old_prio;
if (array) {
enqueue_task(p, array);
+ inc_raw_weighted_load(rq, p);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
out_unlock:
task_rq_unlock(rq, &flags);
}
-
EXPORT_SYMBOL(set_user_nice);
/*
* @p: task
* @nice: nice value
*/
-int can_nice(const task_t *p, const int nice)
+int can_nice(const struct task_struct *p, const int nice)
{
/* convert nice value [19,-20] to rlimit style value [1,40] */
int nice_rlim = 20 - nice;
+
return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
capable(CAP_SYS_NICE));
}
*/
asmlinkage long sys_nice(int increment)
{
- int retval;
- long nice;
+ long nice, retval;
/*
* Setpriority might change our priority at the same moment.
* RT tasks are offset by -200. Normal tasks are centered
* around 0, value goes from -16 to +15.
*/
-int task_prio(const task_t *p)
+int task_prio(const struct task_struct *p)
{
return p->prio - MAX_RT_PRIO;
}
* task_nice - return the nice value of a given task.
* @p: the task in question.
*/
-int task_nice(const task_t *p)
+int task_nice(const struct task_struct *p)
{
return TASK_NICE(p);
}
* idle_task - return the idle task for a given cpu.
* @cpu: the processor in question.
*/
-task_t *idle_task(int cpu)
+struct task_struct *idle_task(int cpu)
{
return cpu_rq(cpu)->idle;
}
* find_process_by_pid - find a process with a matching PID value.
* @pid: the pid in question.
*/
-static inline task_t *find_process_by_pid(pid_t pid)
+static inline struct task_struct *find_process_by_pid(pid_t pid)
{
return pid ? find_task_by_pid(pid) : current;
}
static void __setscheduler(struct task_struct *p, int policy, int prio)
{
BUG_ON(p->array);
+
p->policy = policy;
p->rt_priority = prio;
- if (policy != SCHED_NORMAL && policy != SCHED_BATCH) {
- p->prio = MAX_RT_PRIO-1 - p->rt_priority;
- } else {
- p->prio = p->static_prio;
- /*
- * SCHED_BATCH tasks are treated as perpetual CPU hogs:
- */
- if (policy == SCHED_BATCH)
- p->sleep_avg = 0;
- }
+ p->normal_prio = normal_prio(p);
+ /* we are holding p->pi_lock already */
+ p->prio = rt_mutex_getprio(p);
+ /*
+ * SCHED_BATCH tasks are treated as perpetual CPU hogs:
+ */
+ if (policy == SCHED_BATCH)
+ p->sleep_avg = 0;
+ set_load_weight(p);
}
/**
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
{
- int retval;
- int oldprio, oldpolicy = -1;
- prio_array_t *array;
+ int retval, oldprio, oldpolicy = -1;
+ struct prio_array *array;
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
+ /* may grab non-irq protected spin_locks */
+ BUG_ON(in_interrupt());
recheck:
/* double check policy once rq lock held */
if (policy < 0)
retval = security_task_setscheduler(p, policy, param);
if (retval)
return retval;
+ /*
+ * make sure no PI-waiters arrive (or leave) while we are
+ * changing the priority of the task:
+ */
+ spin_lock_irqsave(&p->pi_lock, flags);
/*
* To be able to change p->policy safely, the apropriate
* runqueue lock must be held.
*/
- rq = task_rq_lock(p, &flags);
+ rq = __task_rq_lock(p);
/* recheck policy now with rq lock held */
if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
policy = oldpolicy = -1;
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
+ spin_unlock_irqrestore(&p->pi_lock, flags);
goto recheck;
}
array = p->array;
} else if (TASK_PREEMPTS_CURR(p, rq))
resched_task(rq->curr);
}
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
+ spin_unlock_irqrestore(&p->pi_lock, flags);
+
+ rt_mutex_adjust_pi(p);
+
return 0;
}
EXPORT_SYMBOL_GPL(sched_setscheduler);
static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
- int retval;
struct sched_param lparam;
struct task_struct *p;
+ int retval;
if (!param || pid < 0)
return -EINVAL;
read_unlock_irq(&tasklist_lock);
return -ESRCH;
}
- retval = sched_setscheduler(p, policy, &lparam);
+ get_task_struct(p);
read_unlock_irq(&tasklist_lock);
+ retval = sched_setscheduler(p, policy, &lparam);
+ put_task_struct(p);
+
return retval;
}
*/
asmlinkage long sys_sched_getscheduler(pid_t pid)
{
+ struct task_struct *p;
int retval = -EINVAL;
- task_t *p;
if (pid < 0)
goto out_nounlock;
asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
{
struct sched_param lp;
+ struct task_struct *p;
int retval = -EINVAL;
- task_t *p;
if (!param || pid < 0)
goto out_nounlock;
long sched_setaffinity(pid_t pid, cpumask_t new_mask)
{
- task_t *p;
- int retval;
cpumask_t cpus_allowed;
+ struct task_struct *p;
+ int retval;
lock_cpu_hotplug();
read_lock(&tasklist_lock);
long sched_getaffinity(pid_t pid, cpumask_t *mask)
{
+ struct task_struct *p;
int retval;
- task_t *p;
lock_cpu_hotplug();
read_lock(&tasklist_lock);
*/
asmlinkage long sys_sched_yield(void)
{
- runqueue_t *rq = this_rq_lock();
- prio_array_t *array = current->array;
- prio_array_t *target = rq->expired;
+ struct rq *rq = this_rq_lock();
+ struct prio_array *array = current->array, *target = rq->expired;
schedstat_inc(rq, yld_cnt);
/*
* no need to preempt or enable interrupts:
*/
__release(rq->lock);
+ spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
_raw_spin_unlock(&rq->lock);
preempt_enable_no_resched();
return 0;
}
-static inline void __cond_resched(void)
+static inline int __resched_legal(void)
+{
+ if (unlikely(preempt_count()))
+ return 0;
+ if (unlikely(system_state != SYSTEM_RUNNING))
+ return 0;
+ return 1;
+}
+
+static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
__might_sleep(__FILE__, __LINE__);
* PREEMPT_ACTIVE, which could trigger a second
* cond_resched() call.
*/
- if (unlikely(preempt_count()))
- return;
- if (unlikely(system_state != SYSTEM_RUNNING))
- return;
do {
add_preempt_count(PREEMPT_ACTIVE);
schedule();
int __sched cond_resched(void)
{
- if (need_resched()) {
+ if (need_resched() && __resched_legal()) {
__cond_resched();
return 1;
}
return 0;
}
-
EXPORT_SYMBOL(cond_resched);
/*
ret = 1;
spin_lock(lock);
}
- if (need_resched()) {
+ if (need_resched() && __resched_legal()) {
+ spin_release(&lock->dep_map, 1, _THIS_IP_);
_raw_spin_unlock(lock);
preempt_enable_no_resched();
__cond_resched();
}
return ret;
}
-
EXPORT_SYMBOL(cond_resched_lock);
int __sched cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
- if (need_resched()) {
- __local_bh_enable();
+ if (need_resched() && __resched_legal()) {
+ raw_local_irq_disable();
+ _local_bh_enable();
+ raw_local_irq_enable();
__cond_resched();
local_bh_disable();
return 1;
}
return 0;
}
-
EXPORT_SYMBOL(cond_resched_softirq);
-
/**
* yield - yield the current processor to other threads.
*
set_current_state(TASK_RUNNING);
sys_sched_yield();
}
-
EXPORT_SYMBOL(yield);
/*
*/
void __sched io_schedule(void)
{
- struct runqueue *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = &__raw_get_cpu_var(runqueues);
atomic_inc(&rq->nr_iowait);
schedule();
atomic_dec(&rq->nr_iowait);
}
-
EXPORT_SYMBOL(io_schedule);
long __sched io_schedule_timeout(long timeout)
{
- struct runqueue *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = &__raw_get_cpu_var(runqueues);
long ret;
atomic_inc(&rq->nr_iowait);
asmlinkage
long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
{
+ struct task_struct *p;
int retval = -EINVAL;
struct timespec t;
- task_t *p;
if (pid < 0)
goto out_nounlock;
static inline struct task_struct *eldest_child(struct task_struct *p)
{
- if (list_empty(&p->children)) return NULL;
+ if (list_empty(&p->children))
+ return NULL;
return list_entry(p->children.next,struct task_struct,sibling);
}
static inline struct task_struct *older_sibling(struct task_struct *p)
{
- if (p->sibling.prev==&p->parent->children) return NULL;
+ if (p->sibling.prev==&p->parent->children)
+ return NULL;
return list_entry(p->sibling.prev,struct task_struct,sibling);
}
static inline struct task_struct *younger_sibling(struct task_struct *p)
{
- if (p->sibling.next==&p->parent->children) return NULL;
+ if (p->sibling.next==&p->parent->children)
+ return NULL;
return list_entry(p->sibling.next,struct task_struct,sibling);
}
-static void show_task(task_t *p)
+static const char stat_nam[] = "RSDTtZX";
+
+static void show_task(struct task_struct *p)
{
- task_t *relative;
- unsigned state;
+ struct task_struct *relative;
unsigned long free = 0;
- static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };
+ unsigned state;
- printk("%-13.13s ", p->comm);
state = p->state ? __ffs(p->state) + 1 : 0;
- if (state < ARRAY_SIZE(stat_nam))
- printk(stat_nam[state]);
- else
- printk("?");
+ printk("%-13.13s %c", p->comm,
+ state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if (BITS_PER_LONG == 32)
if (state == TASK_RUNNING)
printk(" running ");
void show_state(void)
{
- task_t *g, *p;
+ struct task_struct *g, *p;
#if (BITS_PER_LONG == 32)
printk("\n"
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
- mutex_debug_show_all_locks();
+ debug_show_all_locks();
}
/**
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
-void __devinit init_idle(task_t *idle, int cpu)
+void __devinit init_idle(struct task_struct *idle, int cpu)
{
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
unsigned long flags;
idle->timestamp = sched_clock();
idle->sleep_avg = 0;
idle->array = NULL;
- idle->prio = MAX_PRIO;
+ idle->prio = idle->normal_prio = MAX_PRIO;
idle->state = TASK_RUNNING;
idle->cpus_allowed = cpumask_of_cpu(cpu);
set_task_cpu(idle, cpu);
/*
* This is how migration works:
*
- * 1) we queue a migration_req_t structure in the source CPU's
+ * 1) we queue a struct migration_req structure in the source CPU's
* runqueue and wake up that CPU's migration thread.
* 2) we down() the locked semaphore => thread blocks.
* 3) migration thread wakes up (implicitly it forces the migrated
* task must not exit() & deallocate itself prematurely. The
* call is not atomic; no spinlocks may be held.
*/
-int set_cpus_allowed(task_t *p, cpumask_t new_mask)
+int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
+ struct migration_req req;
unsigned long flags;
+ struct rq *rq;
int ret = 0;
- migration_req_t req;
- runqueue_t *rq;
rq = task_rq_lock(p, &flags);
if (!cpus_intersects(new_mask, cpu_online_map)) {
}
out:
task_rq_unlock(rq, &flags);
+
return ret;
}
-
EXPORT_SYMBOL_GPL(set_cpus_allowed);
/*
*
* So we race with normal scheduler movements, but that's OK, as long
* as the task is no longer on this CPU.
+ *
+ * Returns non-zero if task was successfully migrated.
*/
-static void __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
+static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
{
- runqueue_t *rq_dest, *rq_src;
+ struct rq *rq_dest, *rq_src;
+ int ret = 0;
if (unlikely(cpu_is_offline(dest_cpu)))
- return;
+ return ret;
rq_src = cpu_rq(src_cpu);
rq_dest = cpu_rq(dest_cpu);
p->timestamp = p->timestamp - rq_src->timestamp_last_tick
+ rq_dest->timestamp_last_tick;
deactivate_task(p, rq_src);
- activate_task(p, rq_dest, 0);
+ __activate_task(p, rq_dest);
if (TASK_PREEMPTS_CURR(p, rq_dest))
resched_task(rq_dest->curr);
}
-
+ ret = 1;
out:
double_rq_unlock(rq_src, rq_dest);
+ return ret;
}
/*
*/
static int migration_thread(void *data)
{
- runqueue_t *rq;
int cpu = (long)data;
+ struct rq *rq;
rq = cpu_rq(cpu);
BUG_ON(rq->migration_thread != current);
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
+ struct migration_req *req;
struct list_head *head;
- migration_req_t *req;
try_to_freeze();
set_current_state(TASK_INTERRUPTIBLE);
continue;
}
- req = list_entry(head->next, migration_req_t, list);
+ req = list_entry(head->next, struct migration_req, list);
list_del_init(head->next);
spin_unlock(&rq->lock);
#ifdef CONFIG_HOTPLUG_CPU
/* Figure out where task on dead CPU should go, use force if neccessary. */
-static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
+static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
- int dest_cpu;
+ unsigned long flags;
cpumask_t mask;
+ struct rq *rq;
+ int dest_cpu;
+restart:
/* On same node? */
mask = node_to_cpumask(cpu_to_node(dead_cpu));
- cpus_and(mask, mask, tsk->cpus_allowed);
+ cpus_and(mask, mask, p->cpus_allowed);
dest_cpu = any_online_cpu(mask);
/* On any allowed CPU? */
if (dest_cpu == NR_CPUS)
- dest_cpu = any_online_cpu(tsk->cpus_allowed);
+ dest_cpu = any_online_cpu(p->cpus_allowed);
/* No more Mr. Nice Guy. */
if (dest_cpu == NR_CPUS) {
- cpus_setall(tsk->cpus_allowed);
- dest_cpu = any_online_cpu(tsk->cpus_allowed);
+ rq = task_rq_lock(p, &flags);
+ cpus_setall(p->cpus_allowed);
+ dest_cpu = any_online_cpu(p->cpus_allowed);
+ task_rq_unlock(rq, &flags);
/*
* Don't tell them about moving exiting tasks or
* kernel threads (both mm NULL), since they never
* leave kernel.
*/
- if (tsk->mm && printk_ratelimit())
+ if (p->mm && printk_ratelimit())
printk(KERN_INFO "process %d (%s) no "
"longer affine to cpu%d\n",
- tsk->pid, tsk->comm, dead_cpu);
+ p->pid, p->comm, dead_cpu);
}
- __migrate_task(tsk, dead_cpu, dest_cpu);
+ if (!__migrate_task(p, dead_cpu, dest_cpu))
+ goto restart;
}
/*
* their home CPUs. So we just add the counter to another CPU's counter,
* to keep the global sum constant after CPU-down:
*/
-static void migrate_nr_uninterruptible(runqueue_t *rq_src)
+static void migrate_nr_uninterruptible(struct rq *rq_src)
{
- runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
+ struct rq *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
unsigned long flags;
local_irq_save(flags);
/* Run through task list and migrate tasks from the dead cpu. */
static void migrate_live_tasks(int src_cpu)
{
- struct task_struct *tsk, *t;
+ struct task_struct *p, *t;
write_lock_irq(&tasklist_lock);
- do_each_thread(t, tsk) {
- if (tsk == current)
+ do_each_thread(t, p) {
+ if (p == current)
continue;
- if (task_cpu(tsk) == src_cpu)
- move_task_off_dead_cpu(src_cpu, tsk);
- } while_each_thread(t, tsk);
+ if (task_cpu(p) == src_cpu)
+ move_task_off_dead_cpu(src_cpu, p);
+ } while_each_thread(t, p);
write_unlock_irq(&tasklist_lock);
}
/* 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 runqueue. Used by CPU offline code.
+ * the _front_ of the runqueue. Used by CPU offline code.
*/
void sched_idle_next(void)
{
- int cpu = smp_processor_id();
- runqueue_t *rq = this_rq();
+ int this_cpu = smp_processor_id();
+ struct rq *rq = cpu_rq(this_cpu);
struct task_struct *p = rq->idle;
unsigned long flags;
/* cpu has to be offline */
- BUG_ON(cpu_online(cpu));
+ BUG_ON(cpu_online(this_cpu));
- /* Strictly not necessary since rest of the CPUs are stopped by now
- * and interrupts disabled on current cpu.
+ /*
+ * Strictly not necessary since rest of the CPUs are stopped by now
+ * and interrupts disabled on the current cpu.
*/
spin_lock_irqsave(&rq->lock, flags);
__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
- /* Add idle task to _front_ of it's priority queue */
+
+ /* Add idle task to the _front_ of its priority queue: */
__activate_idle_task(p, rq);
spin_unlock_irqrestore(&rq->lock, flags);
}
-/* Ensures that the idle task is using init_mm right before its cpu goes
+/*
+ * Ensures that the idle task is using init_mm right before its cpu goes
* offline.
*/
void idle_task_exit(void)
mmdrop(mm);
}
-static void migrate_dead(unsigned int dead_cpu, task_t *tsk)
+static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
{
- struct runqueue *rq = cpu_rq(dead_cpu);
+ struct rq *rq = cpu_rq(dead_cpu);
/* Must be exiting, otherwise would be on tasklist. */
- BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD);
+ BUG_ON(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
/* Cannot have done final schedule yet: would have vanished. */
- BUG_ON(tsk->flags & PF_DEAD);
+ BUG_ON(p->flags & PF_DEAD);
- get_task_struct(tsk);
+ get_task_struct(p);
/*
* Drop lock around migration; if someone else moves it,
* fine.
*/
spin_unlock_irq(&rq->lock);
- move_task_off_dead_cpu(dead_cpu, tsk);
+ move_task_off_dead_cpu(dead_cpu, p);
spin_lock_irq(&rq->lock);
- put_task_struct(tsk);
+ put_task_struct(p);
}
/* release_task() removes task from tasklist, so we won't find dead tasks. */
static void migrate_dead_tasks(unsigned int dead_cpu)
{
- unsigned arr, i;
- struct runqueue *rq = cpu_rq(dead_cpu);
+ struct rq *rq = cpu_rq(dead_cpu);
+ unsigned int arr, i;
for (arr = 0; arr < 2; arr++) {
for (i = 0; i < MAX_PRIO; i++) {
struct list_head *list = &rq->arrays[arr].queue[i];
+
while (!list_empty(list))
- migrate_dead(dead_cpu,
- list_entry(list->next, task_t,
- run_list));
+ migrate_dead(dead_cpu, list_entry(list->next,
+ struct task_struct, run_list));
}
}
}
* migration_call - callback that gets triggered when a CPU is added.
* Here we can start up the necessary migration thread for the new CPU.
*/
-static int __cpuinit migration_call(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
+static int __cpuinit
+migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
- int cpu = (long)hcpu;
struct task_struct *p;
- struct runqueue *rq;
+ int cpu = (long)hcpu;
unsigned long flags;
+ struct rq *rq;
switch (action) {
case CPU_UP_PREPARE:
task_rq_unlock(rq, &flags);
cpu_rq(cpu)->migration_thread = p;
break;
+
case CPU_ONLINE:
/* Strictly unneccessary, as first user will wake it. */
wake_up_process(cpu_rq(cpu)->migration_thread);
break;
+
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
if (!cpu_rq(cpu)->migration_thread)
kthread_stop(cpu_rq(cpu)->migration_thread);
cpu_rq(cpu)->migration_thread = NULL;
break;
+
case CPU_DEAD:
migrate_live_tasks(cpu);
rq = cpu_rq(cpu);
* the requestors. */
spin_lock_irq(&rq->lock);
while (!list_empty(&rq->migration_queue)) {
- migration_req_t *req;
+ struct migration_req *req;
+
req = list_entry(rq->migration_queue.next,
- migration_req_t, list);
+ struct migration_req, list);
list_del_init(&req->list);
complete(&req->done);
}
int __init migration_init(void)
{
void *cpu = (void *)(long)smp_processor_id();
- /* Start one for boot CPU. */
+
+ /* Start one for the boot CPU: */
migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
+
return 0;
}
#endif
} while (sd);
}
#else
-#define sched_domain_debug(sd, cpu) {}
+# define sched_domain_debug(sd, cpu) do { } while (0)
#endif
static int sd_degenerate(struct sched_domain *sd)
return 1;
}
-static int sd_parent_degenerate(struct sched_domain *sd,
- struct sched_domain *parent)
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
unsigned long cflags = sd->flags, pflags = parent->flags;
*/
static void cpu_attach_domain(struct sched_domain *sd, int cpu)
{
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
struct sched_domain *tmp;
/* Remove the sched domains which do not contribute to scheduling. */
/*
* Measure the cache-cost of one task migration. Returns in units of nsec.
*/
-static unsigned long long measure_one(void *cache, unsigned long size,
- int source, int target)
+static unsigned long long
+measure_one(void *cache, unsigned long size, int source, int target)
{
cpumask_t mask, saved_mask;
unsigned long long t0, t1, t2, t3, cost;
cache = vmalloc(max_size);
if (!cache) {
printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
- return 1000000; // return 1 msec on very small boxen
+ return 1000000; /* return 1 msec on very small boxen */
}
while (size <= max_size) {
*/
static cpumask_t sched_domain_node_span(int node)
{
- int i;
- cpumask_t span, nodemask;
DECLARE_BITMAP(used_nodes, MAX_NUMNODES);
+ cpumask_t span, nodemask;
+ int i;
cpus_clear(span);
bitmap_zero(used_nodes, MAX_NUMNODES);
for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
int next_node = find_next_best_node(node, used_nodes);
+
nodemask = node_to_cpumask(next_node);
cpus_or(span, span, nodemask);
}
}
#endif
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+
/*
- * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
- * can switch it on easily if needed.
+ * SMT sched-domains:
*/
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static struct sched_group sched_group_cpus[NR_CPUS];
+
static int cpu_to_cpu_group(int cpu)
{
return cpu;
}
#endif
+/*
+ * multi-core sched-domains:
+ */
#ifdef CONFIG_SCHED_MC
static DEFINE_PER_CPU(struct sched_domain, core_domains);
-static struct sched_group sched_group_core[NR_CPUS];
+static struct sched_group *sched_group_core_bycpu[NR_CPUS];
#endif
#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
#endif
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
-static struct sched_group sched_group_phys[NR_CPUS];
+static struct sched_group *sched_group_phys_bycpu[NR_CPUS];
+
static int cpu_to_phys_group(int cpu)
{
-#if defined(CONFIG_SCHED_MC)
+#ifdef CONFIG_SCHED_MC
cpumask_t mask = cpu_coregroup_map(cpu);
return first_cpu(mask);
#elif defined(CONFIG_SCHED_SMT)
}
#endif
+/* Free memory allocated for various sched_group structures */
+static void free_sched_groups(const cpumask_t *cpu_map)
+{
+ int cpu;
+#ifdef CONFIG_NUMA
+ int i;
+
+ for_each_cpu_mask(cpu, *cpu_map) {
+ struct sched_group *sched_group_allnodes
+ = sched_group_allnodes_bycpu[cpu];
+ struct sched_group **sched_group_nodes
+ = sched_group_nodes_bycpu[cpu];
+
+ if (sched_group_allnodes) {
+ kfree(sched_group_allnodes);
+ sched_group_allnodes_bycpu[cpu] = NULL;
+ }
+
+ if (!sched_group_nodes)
+ continue;
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ cpumask_t nodemask = node_to_cpumask(i);
+ struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+ cpus_and(nodemask, nodemask, *cpu_map);
+ if (cpus_empty(nodemask))
+ continue;
+
+ if (sg == NULL)
+ continue;
+ sg = sg->next;
+next_sg:
+ oldsg = sg;
+ sg = sg->next;
+ kfree(oldsg);
+ if (oldsg != sched_group_nodes[i])
+ goto next_sg;
+ }
+ kfree(sched_group_nodes);
+ sched_group_nodes_bycpu[cpu] = NULL;
+ }
+#endif
+ for_each_cpu_mask(cpu, *cpu_map) {
+ if (sched_group_phys_bycpu[cpu]) {
+ kfree(sched_group_phys_bycpu[cpu]);
+ sched_group_phys_bycpu[cpu] = NULL;
+ }
+#ifdef CONFIG_SCHED_MC
+ if (sched_group_core_bycpu[cpu]) {
+ kfree(sched_group_core_bycpu[cpu]);
+ sched_group_core_bycpu[cpu] = NULL;
+ }
+#endif
+ }
+}
+
/*
* Build sched domains for a given set of cpus and attach the sched domains
* to the individual cpus
*/
-void build_sched_domains(const cpumask_t *cpu_map)
+static int build_sched_domains(const cpumask_t *cpu_map)
{
int i;
+ struct sched_group *sched_group_phys = NULL;
+#ifdef CONFIG_SCHED_MC
+ struct sched_group *sched_group_core = NULL;
+#endif
#ifdef CONFIG_NUMA
struct sched_group **sched_group_nodes = NULL;
struct sched_group *sched_group_allnodes = NULL;
/*
* Allocate the per-node list of sched groups
*/
- sched_group_nodes = kmalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
- GFP_ATOMIC);
+ sched_group_nodes = kzalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
+ GFP_KERNEL);
if (!sched_group_nodes) {
printk(KERN_WARNING "Can not alloc sched group node list\n");
- return;
+ return -ENOMEM;
}
sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
if (!sched_group_allnodes) {
printk(KERN_WARNING
"Can not alloc allnodes sched group\n");
- break;
+ goto error;
}
sched_group_allnodes_bycpu[i]
= sched_group_allnodes;
cpus_and(sd->span, sd->span, *cpu_map);
#endif
+ if (!sched_group_phys) {
+ sched_group_phys
+ = kmalloc(sizeof(struct sched_group) * NR_CPUS,
+ GFP_KERNEL);
+ if (!sched_group_phys) {
+ printk (KERN_WARNING "Can not alloc phys sched"
+ "group\n");
+ goto error;
+ }
+ sched_group_phys_bycpu[i] = sched_group_phys;
+ }
+
p = sd;
sd = &per_cpu(phys_domains, i);
group = cpu_to_phys_group(i);
sd->groups = &sched_group_phys[group];
#ifdef CONFIG_SCHED_MC
+ if (!sched_group_core) {
+ sched_group_core
+ = kmalloc(sizeof(struct sched_group) * NR_CPUS,
+ GFP_KERNEL);
+ if (!sched_group_core) {
+ printk (KERN_WARNING "Can not alloc core sched"
+ "group\n");
+ goto error;
+ }
+ sched_group_core_bycpu[i] = sched_group_core;
+ }
+
p = sd;
sd = &per_cpu(core_domains, i);
group = cpu_to_core_group(i);
domainspan = sched_domain_node_span(i);
cpus_and(domainspan, domainspan, *cpu_map);
- sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+ sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i);
+ if (!sg) {
+ printk(KERN_WARNING "Can not alloc domain group for "
+ "node %d\n", i);
+ goto error;
+ }
sched_group_nodes[i] = sg;
for_each_cpu_mask(j, nodemask) {
struct sched_domain *sd;
sd = &per_cpu(node_domains, j);
sd->groups = sg;
- if (sd->groups == NULL) {
- /* Turn off balancing if we have no groups */
- sd->flags = 0;
- }
- }
- if (!sg) {
- printk(KERN_WARNING
- "Can not alloc domain group for node %d\n", i);
- continue;
}
sg->cpu_power = 0;
sg->cpumask = nodemask;
+ sg->next = sg;
cpus_or(covered, covered, nodemask);
prev = sg;
if (cpus_empty(tmp))
continue;
- sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
+ sg = kmalloc_node(sizeof(struct sched_group),
+ GFP_KERNEL, i);
if (!sg) {
printk(KERN_WARNING
"Can not alloc domain group for node %d\n", j);
- break;
+ goto error;
}
sg->cpu_power = 0;
sg->cpumask = tmp;
+ sg->next = prev->next;
cpus_or(covered, covered, tmp);
prev->next = sg;
prev = sg;
}
- prev->next = sched_group_nodes[i];
}
#endif
/* Calculate CPU power for physical packages and nodes */
+#ifdef CONFIG_SCHED_SMT
for_each_cpu_mask(i, *cpu_map) {
- int power;
struct sched_domain *sd;
-#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i);
- power = SCHED_LOAD_SCALE;
- sd->groups->cpu_power = power;
+ sd->groups->cpu_power = SCHED_LOAD_SCALE;
+ }
#endif
#ifdef CONFIG_SCHED_MC
+ for_each_cpu_mask(i, *cpu_map) {
+ int power;
+ struct sched_domain *sd;
sd = &per_cpu(core_domains, i);
- power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
+ if (sched_smt_power_savings)
+ power = SCHED_LOAD_SCALE * cpus_weight(sd->groups->cpumask);
+ else
+ power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
* SCHED_LOAD_SCALE / 10;
sd->groups->cpu_power = power;
+ }
+#endif
+ for_each_cpu_mask(i, *cpu_map) {
+ struct sched_domain *sd;
+#ifdef CONFIG_SCHED_MC
sd = &per_cpu(phys_domains, i);
+ if (i != first_cpu(sd->groups->cpumask))
+ continue;
- /*
- * This has to be < 2 * SCHED_LOAD_SCALE
- * Lets keep it SCHED_LOAD_SCALE, so that
- * while calculating NUMA group's cpu_power
- * we can simply do
- * numa_group->cpu_power += phys_group->cpu_power;
- *
- * See "only add power once for each physical pkg"
- * comment below
- */
- sd->groups->cpu_power = SCHED_LOAD_SCALE;
+ sd->groups->cpu_power = 0;
+ if (sched_mc_power_savings || sched_smt_power_savings) {
+ int j;
+
+ for_each_cpu_mask(j, sd->groups->cpumask) {
+ struct sched_domain *sd1;
+ sd1 = &per_cpu(core_domains, j);
+ /*
+ * for each core we will add once
+ * to the group in physical domain
+ */
+ if (j != first_cpu(sd1->groups->cpumask))
+ continue;
+
+ if (sched_smt_power_savings)
+ sd->groups->cpu_power += sd1->groups->cpu_power;
+ else
+ sd->groups->cpu_power += SCHED_LOAD_SCALE;
+ }
+ } else
+ /*
+ * This has to be < 2 * SCHED_LOAD_SCALE
+ * Lets keep it SCHED_LOAD_SCALE, so that
+ * while calculating NUMA group's cpu_power
+ * we can simply do
+ * numa_group->cpu_power += phys_group->cpu_power;
+ *
+ * See "only add power once for each physical pkg"
+ * comment below
+ */
+ sd->groups->cpu_power = SCHED_LOAD_SCALE;
#else
+ int power;
sd = &per_cpu(phys_domains, i);
- power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
- (cpus_weight(sd->groups->cpumask)-1) / 10;
+ if (sched_smt_power_savings)
+ power = SCHED_LOAD_SCALE * cpus_weight(sd->groups->cpumask);
+ else
+ power = SCHED_LOAD_SCALE;
sd->groups->cpu_power = power;
#endif
}
* Tune cache-hot values:
*/
calibrate_migration_costs(cpu_map);
+
+ return 0;
+
+error:
+ free_sched_groups(cpu_map);
+ return -ENOMEM;
}
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
*/
-static void arch_init_sched_domains(const cpumask_t *cpu_map)
+static int arch_init_sched_domains(const cpumask_t *cpu_map)
{
cpumask_t cpu_default_map;
+ int err;
/*
* Setup mask for cpus without special case scheduling requirements.
*/
cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
- build_sched_domains(&cpu_default_map);
+ err = build_sched_domains(&cpu_default_map);
+
+ return err;
}
static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
{
-#ifdef CONFIG_NUMA
- int i;
- int cpu;
-
- for_each_cpu_mask(cpu, *cpu_map) {
- struct sched_group *sched_group_allnodes
- = sched_group_allnodes_bycpu[cpu];
- struct sched_group **sched_group_nodes
- = sched_group_nodes_bycpu[cpu];
-
- if (sched_group_allnodes) {
- kfree(sched_group_allnodes);
- sched_group_allnodes_bycpu[cpu] = NULL;
- }
-
- if (!sched_group_nodes)
- continue;
-
- for (i = 0; i < MAX_NUMNODES; i++) {
- cpumask_t nodemask = node_to_cpumask(i);
- struct sched_group *oldsg, *sg = sched_group_nodes[i];
-
- cpus_and(nodemask, nodemask, *cpu_map);
- if (cpus_empty(nodemask))
- continue;
-
- if (sg == NULL)
- continue;
- sg = sg->next;
-next_sg:
- oldsg = sg;
- sg = sg->next;
- kfree(oldsg);
- if (oldsg != sched_group_nodes[i])
- goto next_sg;
- }
- kfree(sched_group_nodes);
- sched_group_nodes_bycpu[cpu] = NULL;
- }
-#endif
+ free_sched_groups(cpu_map);
}
/*
* correct sched domains
* Call with hotplug lock held
*/
-void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
+int partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
{
cpumask_t change_map;
+ int err = 0;
cpus_and(*partition1, *partition1, cpu_online_map);
cpus_and(*partition2, *partition2, cpu_online_map);
/* Detach sched domains from all of the affected cpus */
detach_destroy_domains(&change_map);
if (!cpus_empty(*partition1))
- build_sched_domains(partition1);
- if (!cpus_empty(*partition2))
- build_sched_domains(partition2);
+ err = build_sched_domains(partition1);
+ if (!err && !cpus_empty(*partition2))
+ err = build_sched_domains(partition2);
+
+ return err;
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+int arch_reinit_sched_domains(void)
+{
+ int err;
+
+ lock_cpu_hotplug();
+ detach_destroy_domains(&cpu_online_map);
+ err = arch_init_sched_domains(&cpu_online_map);
+ unlock_cpu_hotplug();
+
+ return err;
}
+static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
+{
+ int ret;
+
+ if (buf[0] != '0' && buf[0] != '1')
+ return -EINVAL;
+
+ if (smt)
+ sched_smt_power_savings = (buf[0] == '1');
+ else
+ sched_mc_power_savings = (buf[0] == '1');
+
+ ret = arch_reinit_sched_domains();
+
+ return ret ? ret : count;
+}
+
+int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+{
+ int err = 0;
+
+#ifdef CONFIG_SCHED_SMT
+ if (smt_capable())
+ err = sysfs_create_file(&cls->kset.kobj,
+ &attr_sched_smt_power_savings.attr);
+#endif
+#ifdef CONFIG_SCHED_MC
+ if (!err && mc_capable())
+ err = sysfs_create_file(&cls->kset.kobj,
+ &attr_sched_mc_power_savings.attr);
+#endif
+ return err;
+}
+#endif
+
+#ifdef CONFIG_SCHED_MC
+static ssize_t sched_mc_power_savings_show(struct sys_device *dev, char *page)
+{
+ return sprintf(page, "%u\n", sched_mc_power_savings);
+}
+static ssize_t sched_mc_power_savings_store(struct sys_device *dev,
+ const char *buf, size_t count)
+{
+ return sched_power_savings_store(buf, count, 0);
+}
+SYSDEV_ATTR(sched_mc_power_savings, 0644, sched_mc_power_savings_show,
+ sched_mc_power_savings_store);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+static ssize_t sched_smt_power_savings_show(struct sys_device *dev, char *page)
+{
+ return sprintf(page, "%u\n", sched_smt_power_savings);
+}
+static ssize_t sched_smt_power_savings_store(struct sys_device *dev,
+ const char *buf, size_t count)
+{
+ return sched_power_savings_store(buf, count, 1);
+}
+SYSDEV_ATTR(sched_smt_power_savings, 0644, sched_smt_power_savings_show,
+ sched_smt_power_savings_store);
+#endif
+
+
#ifdef CONFIG_HOTPLUG_CPU
/*
* Force a reinitialization of the sched domains hierarchy. The domains
{
/* Linker adds these: start and end of __sched functions */
extern char __sched_text_start[], __sched_text_end[];
+
return in_lock_functions(addr) ||
(addr >= (unsigned long)__sched_text_start
&& addr < (unsigned long)__sched_text_end);
void __init sched_init(void)
{
- runqueue_t *rq;
int i, j, k;
for_each_possible_cpu(i) {
- prio_array_t *array;
+ struct prio_array *array;
+ struct rq *rq;
rq = cpu_rq(i);
spin_lock_init(&rq->lock);
+ lockdep_set_class(&rq->lock, &rq->rq_lock_key);
rq->nr_running = 0;
rq->active = rq->arrays;
rq->expired = rq->arrays + 1;
}
}
+ set_load_weight(&init_task);
/*
* The boot idle thread does lazy MMU switching as well:
*/
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
void __might_sleep(char *file, int line)
{
-#if defined(in_atomic)
+#ifdef in_atomic
static unsigned long prev_jiffy; /* ratelimiting */
if ((in_atomic() || irqs_disabled()) &&
#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{
+ struct prio_array *array;
struct task_struct *p;
- prio_array_t *array;
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
read_lock_irq(&tasklist_lock);
for_each_process(p) {
if (!rt_task(p))
continue;
- rq = task_rq_lock(p, &flags);
+ spin_lock_irqsave(&p->pi_lock, flags);
+ rq = __task_rq_lock(p);
array = p->array;
if (array)
resched_task(rq->curr);
}
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
+ spin_unlock_irqrestore(&p->pi_lock, flags);
}
read_unlock_irq(&tasklist_lock);
}
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*/
-task_t *curr_task(int cpu)
+struct task_struct *curr_task(int cpu)
{
return cpu_curr(cpu);
}
*
* ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
*/
-void set_curr_task(int cpu, task_t *p)
+void set_curr_task(int cpu, struct task_struct *p)
{
cpu_curr(cpu) = p;
}
git.openpandora.org / pandora-kernel.git / blobdiff