#include <linux/times.h>
#include <linux/acct.h>
#include <linux/kprobes.h>
+#include <linux/delayacct.h>
#include <asm/tlb.h>
#include <asm/unistd.h>
* 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;
/*
unsigned long long timestamp_last_tick;
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;
/* For active balancing */
int active_balance;
int push_cpu;
+ int cpu; /* cpu of this runqueue */
struct task_struct *migration_thread;
struct list_head migration_queue;
struct lock_class_key rq_lock_key;
};
-static DEFINE_PER_CPU(struct runqueue, runqueues);
+static DEFINE_PER_CPU(struct rq, runqueues);
+
+static inline int cpu_of(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ return rq->cpu;
+#else
+ return 0;
+#endif
+}
/*
* The domain tree (rq->sd) is protected by RCU's quiescent state transition.
#endif
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
-static inline int task_running(runqueue_t *rq, struct task_struct *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, struct task_struct *next)
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
}
-static inline void finish_lock_switch(runqueue_t *rq, struct task_struct *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 */
}
#else /* __ARCH_WANT_UNLOCKED_CTXSW */
-static inline int task_running(runqueue_t *rq, struct task_struct *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, struct task_struct *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, struct task_struct *prev)
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
/*
* __task_rq_lock - lock the runqueue a given task resides on.
* Must be called interrupts disabled.
*/
-static inline runqueue_t *__task_rq_lock(struct task_struct *p)
+static inline struct rq *__task_rq_lock(struct task_struct *p)
__acquires(rq->lock)
{
- struct runqueue *rq;
+ struct rq *rq;
repeat_lock_task:
rq = task_rq(p);
* interrupts. Note the ordering: we can safely lookup the task_rq without
* explicitly disabling preemption.
*/
-static runqueue_t *task_rq_lock(struct task_struct *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)
+static inline void __task_rq_unlock(struct rq *rq)
__releases(rq->lock)
{
spin_unlock(&rq->lock);
}
-static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
+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;
.release = single_release,
};
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
+{
+ if (rq) {
+ rq->rq_sched_info.run_delay += delta_jiffies;
+ rq->rq_sched_info.pcnt++;
+ }
+}
+
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
+{
+ if (rq)
+ rq->rq_sched_info.cpu_time += delta_jiffies;
+}
# define schedstat_inc(rq, field) do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0)
#else /* !CONFIG_SCHEDSTATS */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long delta_jiffies)
+{}
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long delta_jiffies)
+{}
# define schedstat_inc(rq, field) do { } while (0)
# define schedstat_add(rq, field, amt) do { } while (0)
#endif
/*
* 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();
return rq;
}
-#ifdef CONFIG_SCHEDSTATS
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
/*
* Called when a process is dequeued from the active array and given
* the cpu. We should note that with the exception of interactive
*/
static void sched_info_arrive(struct task_struct *t)
{
- unsigned long now = jiffies, diff = 0;
- struct runqueue *rq = task_rq(t);
+ unsigned long now = jiffies, delta_jiffies = 0;
if (t->sched_info.last_queued)
- diff = now - t->sched_info.last_queued;
+ delta_jiffies = now - t->sched_info.last_queued;
sched_info_dequeued(t);
- t->sched_info.run_delay += diff;
+ t->sched_info.run_delay += delta_jiffies;
t->sched_info.last_arrival = now;
t->sched_info.pcnt++;
- if (!rq)
- return;
-
- rq->rq_sched_info.run_delay += diff;
- rq->rq_sched_info.pcnt++;
+ rq_sched_info_arrive(task_rq(t), delta_jiffies);
}
/*
*/
static inline void sched_info_queued(struct task_struct *t)
{
- if (!t->sched_info.last_queued)
- t->sched_info.last_queued = jiffies;
+ if (unlikely(sched_info_on()))
+ if (!t->sched_info.last_queued)
+ t->sched_info.last_queued = jiffies;
}
/*
*/
static inline void sched_info_depart(struct task_struct *t)
{
- struct runqueue *rq = task_rq(t);
- unsigned long diff = jiffies - t->sched_info.last_arrival;
+ unsigned long delta_jiffies = jiffies - t->sched_info.last_arrival;
- t->sched_info.cpu_time += diff;
-
- if (rq)
- rq->rq_sched_info.cpu_time += diff;
+ t->sched_info.cpu_time += delta_jiffies;
+ rq_sched_info_depart(task_rq(t), delta_jiffies);
}
/*
* the idle task.) We are only called when prev != next.
*/
static inline void
-sched_info_switch(struct task_struct *prev, struct task_struct *next)
+__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
if (next != rq->idle)
sched_info_arrive(next);
}
+static inline void
+sched_info_switch(struct task_struct *prev, struct task_struct *next)
+{
+ if (unlikely(sched_info_on()))
+ __sched_info_switch(prev, next);
+}
#else
#define sched_info_queued(t) do { } while (0)
#define sched_info_switch(t, next) do { } while (0)
-#endif /* CONFIG_SCHEDSTATS */
+#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
/*
* 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);
}
static inline void
-inc_raw_weighted_load(runqueue_t *rq, const struct task_struct *p)
+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(runqueue_t *rq, const struct task_struct *p)
+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, runqueue_t *rq)
+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, runqueue_t *rq)
+static inline void dec_nr_running(struct task_struct *p, struct rq *rq)
{
rq->nr_running--;
dec_raw_weighted_load(rq, p);
/*
* __activate_task - move a task to the runqueue.
*/
-static void __activate_task(struct task_struct *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;
/*
* __activate_idle_task - move idle task to the _front_ of runqueue.
*/
-static inline void __activate_idle_task(struct task_struct *p, runqueue_t *rq)
+static inline void __activate_idle_task(struct task_struct *p, struct rq *rq)
{
enqueue_task_head(p, rq->active);
inc_nr_running(p, rq);
* Update all the scheduling statistics stuff. (sleep average
* calculation, priority modifiers, etc.)
*/
-static void activate_task(struct task_struct *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)
{
dec_nr_running(p, rq);
dequeue_task(p, p->array);
}
#ifdef CONFIG_SMP
-typedef struct {
+struct migration_req {
struct list_head list;
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(struct task_struct *p, int dest_cpu, migration_req_t *req)
+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
void wait_task_inactive(struct task_struct *p)
{
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
int preempted;
repeat:
*/
static inline unsigned long source_load(int cpu, int type)
{
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
if (type == 0)
return rq->raw_weighted_load;
*/
static inline unsigned long target_load(int cpu, int type)
{
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
if (type == 0)
return rq->raw_weighted_load;
*/
static inline unsigned long cpu_avg_load_per_task(int cpu)
{
- runqueue_t *rq = cpu_rq(cpu);
+ struct rq *rq = cpu_rq(cpu);
unsigned long n = rq->nr_running;
return n ? rq->raw_weighted_load / n : SCHED_LOAD_SCALE;
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
INIT_LIST_HEAD(&p->run_list);
p->array = NULL;
-#ifdef CONFIG_SCHEDSTATS
- memset(&p->sched_info, 0, sizeof(p->sched_info));
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+ if (unlikely(sched_info_on()))
+ memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
p->oncpu = 0;
*/
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);
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, struct task_struct *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, struct task_struct *prev)
+static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
__releases(rq->lock)
{
struct mm_struct *mm = rq->prev_mm;
- unsigned long prev_task_flags;
+ long prev_state;
rq->prev_mm = NULL;
/*
* A task struct has one reference for the use as "current".
- * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
- * calls schedule one last time. The schedule call will never return,
- * and the scheduled task must drop that reference.
- * The test for EXIT_ZOMBIE must occur while the runqueue locks are
+ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
+ * schedule one last time. The schedule call will never return, and
+ * the scheduled task must drop that reference.
+ * The test for TASK_DEAD must occur while the runqueue locks are
* still held, otherwise prev could be scheduled on another cpu, die
* there before we look at prev->state, and then the reference would
* be dropped twice.
* Manfred Spraul <manfred@colorfullife.com>
*/
- prev_task_flags = prev->flags;
+ prev_state = prev->state;
finish_arch_switch(prev);
finish_lock_switch(rq, prev);
if (mm)
mmdrop(mm);
- if (unlikely(prev_task_flags & PF_DEAD)) {
+ if (unlikely(prev_state == TASK_DEAD)) {
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
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 */
* thread's register state.
*/
static inline struct task_struct *
-context_switch(runqueue_t *rq, struct task_struct *prev,
+context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
struct mm_struct *mm = next->mm;
WARN_ON(rq->prev_mm);
rq->prev_mm = oldmm;
}
+ /*
+ * Since the runqueue lock will be released by the next
+ * task (which is an invalid locking op but in the case
+ * of the scheduler it's an obvious special-case), so we
+ * do an early lockdep release here:
+ */
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
+#endif
/* Here we just switch the register state and the stack. */
switch_to(prev, next, prev);
* 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)
*/
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)
* 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,
- struct task_struct *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);
dec_nr_running(p, src_rq);
* can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
*/
static
-int can_migrate_task(struct task_struct *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)
{
*
* Called with both runqueues locked.
*/
-static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
+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)
{
int idx, pulled = 0, pinned = 0, this_best_prio, best_prio,
best_prio_seen, skip_for_load;
- prio_array_t *array, *dst_array;
+ struct prio_array *array, *dst_array;
struct list_head *head, *curr;
struct task_struct *tmp;
long rem_load_move;
*/
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
- unsigned long *imbalance, enum idle_type idle, int *sd_idle)
+ unsigned long *imbalance, enum idle_type idle, int *sd_idle,
+ cpumask_t *cpus)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
sum_weighted_load = sum_nr_running = avg_load = 0;
for_each_cpu_mask(i, group->cpumask) {
- runqueue_t *rq = cpu_rq(i);
+ struct rq *rq;
+
+ if (!cpu_isset(i, *cpus))
+ continue;
+
+ rq = cpu_rq(i);
if (*sd_idle && !idle_cpu(i))
*sd_idle = 0;
/*
* find_busiest_queue - find the busiest runqueue among the cpus in group.
*/
-static runqueue_t *
+static struct rq *
find_busiest_queue(struct sched_group *group, enum idle_type idle,
- unsigned long imbalance)
+ unsigned long imbalance, cpumask_t *cpus)
{
- runqueue_t *busiest = NULL, *rq;
+ struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
int i;
for_each_cpu_mask(i, group->cpumask) {
+
+ if (!cpu_isset(i, *cpus))
+ continue;
+
rq = cpu_rq(i);
if (rq->nr_running == 1 && rq->raw_weighted_load > 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;
unsigned long imbalance;
- runqueue_t *busiest;
+ struct rq *busiest;
+ cpumask_t cpus = CPU_MASK_ALL;
if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
!sched_smt_power_savings)
schedstat_inc(sd, lb_cnt[idle]);
- group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
+redo:
+ group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+ &cpus);
if (!group) {
schedstat_inc(sd, lb_nobusyg[idle]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, idle, imbalance);
+ busiest = find_busiest_queue(group, idle, imbalance, &cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
double_rq_unlock(this_rq, busiest);
/* All tasks on this runqueue were pinned by CPU affinity */
- if (unlikely(all_pinned))
+ if (unlikely(all_pinned)) {
+ cpu_clear(cpu_of(busiest), cpus);
+ if (!cpus_empty(cpus))
+ goto redo;
goto out_balanced;
+ }
}
if (!nr_moved) {
* this_rq is locked.
*/
static int
-load_balance_newidle(int this_cpu, runqueue_t *this_rq, struct sched_domain *sd)
+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;
+ cpumask_t cpus = CPU_MASK_ALL;
if (sd->flags & SD_SHARE_CPUPOWER && !sched_smt_power_savings)
sd_idle = 1;
schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
- group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
+redo:
+ group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE,
+ &sd_idle, &cpus);
if (!group) {
schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
goto out_balanced;
}
- busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance);
+ busiest = find_busiest_queue(group, NEWLY_IDLE, imbalance,
+ &cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
goto out_balanced;
minus_1_or_zero(busiest->nr_running),
imbalance, sd, NEWLY_IDLE, NULL);
spin_unlock(&busiest->lock);
+
+ if (!nr_moved) {
+ cpu_clear(cpu_of(busiest), cpus);
+ if (!cpus_empty(cpus))
+ goto redo;
+ }
}
if (!nr_moved) {
* 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;
*
* 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)
}
static void
-rebalance_tick(int this_cpu, runqueue_t *this_rq, enum idle_type idle)
+rebalance_tick(int this_cpu, struct rq *this_rq, enum idle_type idle)
{
unsigned long this_load, interval, j = cpu_offset(this_cpu);
struct sched_domain *sd;
/*
* 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;
* Bank in p->sched_time the ns elapsed since the last tick or switch.
*/
static inline void
-update_cpu_clock(struct task_struct *p, runqueue_t *rq, unsigned long long now)
+update_cpu_clock(struct task_struct *p, struct rq *rq, unsigned long long now)
{
p->sched_time += now - max(p->timestamp, rq->timestamp_last_tick);
}
* increasing number of running tasks. We also ignore the interactivity
* if a better static_prio task has expired:
*/
-static inline int expired_starving(runqueue_t *rq)
+static inline int expired_starving(struct rq *rq)
{
if (rq->curr->static_prio > rq->best_expired_prio)
return 1;
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);
unsigned long long now = sched_clock();
struct task_struct *p = current;
int cpu = smp_processor_id();
- runqueue_t *rq = this_rq();
+ struct rq *rq = cpu_rq(cpu);
update_cpu_clock(p, rq, now);
}
#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;
* need to be obeyed.
*/
static int
-dependent_sleeper(int this_cpu, runqueue_t *this_rq, struct task_struct *p)
+dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
{
struct sched_domain *tmp, *sd = NULL;
int ret = 0, i;
for_each_cpu_mask(i, sd->span) {
struct task_struct *smt_curr;
- runqueue_t *smt_rq;
+ struct rq *smt_rq;
if (i == this_cpu)
continue;
{
}
static inline int
-dependent_sleeper(int this_cpu, runqueue_t *this_rq, struct task_struct *p)
+dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
{
return 0;
}
asmlinkage void __sched schedule(void)
{
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;
- prio_array_t *array;
long *switch_count;
- runqueue_t *rq;
+ struct rq *rq;
/*
* Test if we are atomic. Since do_exit() needs to call into
spin_lock_irq(&rq->lock);
- if (unlikely(prev->flags & PF_DEAD))
- prev->state = EXIT_DEAD;
-
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
switch_count = &prev->nvcsw;
#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.
*/
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:
*/
void rt_mutex_setprio(struct task_struct *p, int prio)
{
+ struct prio_array *array;
unsigned long flags;
- prio_array_t *array;
- runqueue_t *rq;
+ struct rq *rq;
int oldprio;
BUG_ON(prio < 0 || prio > MAX_PRIO);
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;
+ struct rq *rq;
if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
return;
* @p: the task in question.
* @policy: new policy.
* @param: structure containing the new RT priority.
+ *
+ * NOTE: the task may be already dead
*/
int sched_setscheduler(struct task_struct *p, int policy,
struct sched_param *param)
{
int retval, oldprio, oldpolicy = -1;
- prio_array_t *array;
+ struct prio_array *array;
unsigned long flags;
- runqueue_t *rq;
+ struct rq *rq;
/* may grab non-irq protected spin_locks */
BUG_ON(in_interrupt());
(p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
(!p->mm && param->sched_priority > MAX_RT_PRIO-1))
return -EINVAL;
- if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
- != (param->sched_priority == 0))
+ if (is_rt_policy(policy) != (param->sched_priority != 0))
return -EINVAL;
/*
* Allow unprivileged RT tasks to decrease priority:
*/
if (!capable(CAP_SYS_NICE)) {
- /*
- * can't change policy, except between SCHED_NORMAL
- * and SCHED_BATCH:
- */
- if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
- (policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
- !p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
- return -EPERM;
- /* can't increase priority */
- if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
- param->sched_priority > p->rt_priority &&
- param->sched_priority >
- p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
- return -EPERM;
+ if (is_rt_policy(policy)) {
+ unsigned long rlim_rtprio;
+ unsigned long flags;
+
+ if (!lock_task_sighand(p, &flags))
+ return -ESRCH;
+ rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+ unlock_task_sighand(p, &flags);
+
+ /* can't set/change the rt policy */
+ if (policy != p->policy && !rlim_rtprio)
+ return -EPERM;
+
+ /* can't increase priority */
+ if (param->sched_priority > p->rt_priority &&
+ param->sched_priority > rlim_rtprio)
+ return -EPERM;
+ }
+
/* can't change other user's priorities */
if ((current->euid != p->euid) &&
(current->euid != p->uid))
return -EINVAL;
if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
return -EFAULT;
- read_lock_irq(&tasklist_lock);
+
+ rcu_read_lock();
+ retval = -ESRCH;
p = find_process_by_pid(pid);
- if (!p) {
- read_unlock_irq(&tasklist_lock);
- return -ESRCH;
- }
- get_task_struct(p);
- read_unlock_irq(&tasklist_lock);
- retval = sched_setscheduler(p, policy, &lparam);
- put_task_struct(p);
+ if (p != NULL)
+ retval = sched_setscheduler(p, policy, &lparam);
+ rcu_read_unlock();
return retval;
}
*/
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);
/*
return 0;
}
-static inline int __resched_legal(void)
+static inline int __resched_legal(int expected_preempt_count)
{
- if (unlikely(preempt_count()))
+ if (unlikely(preempt_count() != expected_preempt_count))
return 0;
if (unlikely(system_state != SYSTEM_RUNNING))
return 0;
int __sched cond_resched(void)
{
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(0)) {
__cond_resched();
return 1;
}
ret = 1;
spin_lock(lock);
}
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(1)) {
spin_release(&lock->dep_map, 1, _THIS_IP_);
_raw_spin_unlock(lock);
preempt_enable_no_resched();
{
BUG_ON(!in_softirq());
- if (need_resched() && __resched_legal()) {
+ if (need_resched() && __resched_legal(0)) {
raw_local_irq_disable();
_local_bh_enable();
raw_local_irq_enable();
*/
void __sched io_schedule(void)
{
- struct runqueue *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = &__raw_get_cpu_var(runqueues);
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
schedule();
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
}
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;
+ delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
ret = schedule_timeout(timeout);
atomic_dec(&rq->nr_iowait);
+ delayacct_blkio_end();
return ret;
}
return list_entry(p->sibling.next,struct task_struct,sibling);
}
-static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };
+static const char stat_nam[] = "RSDTtZX";
static void show_task(struct task_struct *p)
{
unsigned long free = 0;
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 __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();
/*
* 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
*/
int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
+ struct migration_req req;
unsigned long flags;
- migration_req_t req;
- runqueue_t *rq;
+ struct rq *rq;
int ret = 0;
rq = task_rq_lock(p, &flags);
*/
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)))
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);
}
static int migration_thread(void *data)
{
int cpu = (long)data;
- runqueue_t *rq;
+ 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);
/* 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 *p)
{
- runqueue_t *rq;
unsigned long flags;
- int dest_cpu;
cpumask_t mask;
+ struct rq *rq;
+ int dest_cpu;
restart:
/* On same node? */
* 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);
void sched_idle_next(void)
{
int this_cpu = smp_processor_id();
- runqueue_t *rq = cpu_rq(this_cpu);
+ struct rq *rq = cpu_rq(this_cpu);
struct task_struct *p = rq->idle;
unsigned long flags;
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(p->exit_state != EXIT_ZOMBIE && p->exit_state != EXIT_DEAD);
/* Cannot have done final schedule yet: would have vanished. */
- BUG_ON(p->flags & PF_DEAD);
+ BUG_ON(p->state == TASK_DEAD);
get_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)
{
- struct runqueue *rq = cpu_rq(dead_cpu);
+ struct rq *rq = cpu_rq(dead_cpu);
unsigned int arr, i;
for (arr = 0; arr < 2; arr++) {
{
struct task_struct *p;
int cpu = (long)hcpu;
- struct runqueue *rq;
unsigned long flags;
+ struct rq *rq;
switch (action) {
case CPU_UP_PREPARE:
* 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();
+ int err;
/* Start one for the boot CPU: */
- migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+ BUG_ON(err == NOTIFY_BAD);
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
*/
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. */
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) {
for (i = 0; i < MAX_NUMNODES; i++)
init_numa_sched_groups_power(sched_group_nodes[i]);
- init_numa_sched_groups_power(sched_group_allnodes);
+ if (sched_group_allnodes) {
+ int group = cpu_to_allnodes_group(first_cpu(*cpu_map));
+ struct sched_group *sg = &sched_group_allnodes[group];
+
+ init_numa_sched_groups_power(sg);
+ }
#endif
/* Attach the domains */
int i, j, k;
for_each_possible_cpu(i) {
- prio_array_t *array;
- runqueue_t *rq;
+ struct prio_array *array;
+ struct rq *rq;
rq = cpu_rq(i);
spin_lock_init(&rq->lock);
rq->cpu_load[j] = 0;
rq->active_balance = 0;
rq->push_cpu = 0;
+ rq->cpu = i;
rq->migration_thread = NULL;
INIT_LIST_HEAD(&rq->migration_queue);
#endif
}
set_load_weight(&init_task);
+
+#ifdef CONFIG_RT_MUTEXES
+ plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
+#endif
+
/*
* The boot idle thread does lazy MMU switching as well:
*/
#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) {
projects / karo-tx-linux.git / blobdiff