/*
* linux/kernel/sched.c
*
* Kernel scheduler and related syscalls
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and
* make semaphores SMP safe
* 1998-11-19 Implemented schedule_timeout() and related stuff
* by Andrea Arcangeli
* 1998-12-28 Implemented better SMP scheduling by Ingo Molnar
*/
/*
* 'sched.c' is the main kernel file. It contains scheduling primitives
* (sleep_on, wakeup, schedule etc) as well as a number of simple system
* call functions (type getpid()), which just extract a field from
* current-task
*/
#include <linux/config.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
extern void timer_bh(void);
extern void tqueue_bh(void);
extern void immediate_bh(void);
/*
* scheduler variables
*/
unsigned securebits = SECUREBITS_DEFAULT; /* systemwide security settings */
extern void mem_use(void);
/*
* Scheduling quanta.
*
* NOTE! The unix "nice" value influences how long a process
* gets. The nice value ranges from -20 to +19, where a -20
* is a "high-priority" task, and a "+10" is a low-priority
* task.
*
* We want the time-slice to be around 50ms or so, so this
* calculation depends on the value of HZ.
*/
#if HZ < 200
#define TICK_SCALE(x) ((x) >> 2)
#elif HZ < 400
#define TICK_SCALE(x) ((x) >> 1)
#elif HZ < 800
#define TICK_SCALE(x) (x)
#elif HZ < 1600
#define TICK_SCALE(x) ((x) << 1)
#else
#define TICK_SCALE(x) ((x) << 2)
#endif
#define NICE_TO_TICKS(nice) (TICK_SCALE(20-(nice))+1)
/*
* Init task must be ok at boot for the ix86 as we will check its signals
* via the SMP irq return path.
*/
struct task_struct * init_tasks[NR_CPUS] = {&init_task, };
/*
* The tasklist_lock protects the linked list of processes.
*
* The runqueue_lock locks the parts that actually access
* and change the run-queues, and have to be interrupt-safe.
*
* If both locks are to be concurrently held, the runqueue_lock
* nests inside the tasklist_lock.
*/
spinlock_t runqueue_lock __cacheline_aligned = SPIN_LOCK_UNLOCKED; /* inner */
rwlock_t tasklist_lock __cacheline_aligned = RW_LOCK_UNLOCKED; /* outer */
static LIST_HEAD(runqueue_head);
/*
* We align per-CPU scheduling data on cacheline boundaries,
* to prevent cacheline ping-pong.
*/
static union {
struct schedule_data {
struct task_struct * curr;
cycles_t last_schedule;
} schedule_data;
char __pad [SMP_CACHE_BYTES];
} aligned_data [NR_CPUS] __cacheline_aligned = { {{&init_task,0}}};
#define cpu_curr(cpu) aligned_data[(cpu)].schedule_data.curr
#define last_schedule(cpu) aligned_data[(cpu)].schedule_data.last_schedule
struct kernel_stat kstat;
#ifdef CONFIG_SMP
#define idle_task(cpu) (init_tasks[cpu_number_map(cpu)])
#define can_schedule(p,cpu) ((!(p)->has_cpu) && \
((p)->cpus_allowed & (1 << cpu)))
#else
#define idle_task(cpu) (&init_task)
#define can_schedule(p,cpu) (1)
#endif
121 void scheduling_functions_start_here(void) { }
/*
* This is the function that decides how desirable a process is..
* You can weigh different processes against each other depending
* on what CPU they've run on lately etc to try to handle cache
* and TLB miss penalties.
*
* Return values:
* -1000: never select this
* 0: out of time, recalculate counters (but it might still be
* selected)
* +ve: "goodness" value (the larger, the better)
* +1000: realtime process, select this.
*/
137 static inline int goodness(struct task_struct * p, int this_cpu, struct mm_struct *this_mm)
{
int weight;
/*
* select the current process after every other
* runnable process, but before the idle thread.
* Also, dont trigger a counter recalculation.
*/
weight = -1;
147 if (p->policy & SCHED_YIELD)
148 goto out;
/*
* Non-RT process - normal case first.
*/
153 if (p->policy == SCHED_OTHER) {
/*
* Give the process a first-approximation goodness value
* according to the number of clock-ticks it has left.
*
* Don't do any other calculations if the time slice is
* over..
*/
weight = p->counter;
162 if (!weight)
163 goto out;
#ifdef CONFIG_SMP
/* Give a largish advantage to the same processor... */
/* (this is equivalent to penalizing other processors) */
if (p->processor == this_cpu)
weight += PROC_CHANGE_PENALTY;
#endif
/* .. and a slight advantage to the current MM */
173 if (p->mm == this_mm || !p->mm)
weight += 1;
weight += 20 - p->nice;
176 goto out;
}
/*
* Realtime process, select the first one on the
* runqueue (taking priorities within processes
* into account).
*/
weight = 1000 + p->rt_priority;
out:
186 return weight;
}
/*
* the 'goodness value' of replacing a process on a given CPU.
* positive value means 'replace', zero or negative means 'dont'.
*/
193 static inline int preemption_goodness(struct task_struct * prev, struct task_struct * p, int cpu)
{
195 return goodness(p, cpu, prev->active_mm) - goodness(prev, cpu, prev->active_mm);
}
/*
* This is ugly, but reschedule_idle() is very timing-critical.
* We are called with the runqueue spinlock held and we must
* not claim the tasklist_lock.
*/
static FASTCALL(void reschedule_idle(struct task_struct * p));
205 static void reschedule_idle(struct task_struct * p)
{
#ifdef CONFIG_SMP
int this_cpu = smp_processor_id();
struct task_struct *tsk, *target_tsk;
int cpu, best_cpu, i, max_prio;
cycles_t oldest_idle;
/*
* shortcut if the woken up task's last CPU is
* idle now.
*/
best_cpu = p->processor;
if (can_schedule(p, best_cpu)) {
tsk = idle_task(best_cpu);
if (cpu_curr(best_cpu) == tsk) {
int need_resched;
send_now_idle:
/*
* If need_resched == -1 then we can skip sending
* the IPI altogether, tsk->need_resched is
* actively watched by the idle thread.
*/
need_resched = tsk->need_resched;
tsk->need_resched = 1;
if ((best_cpu != this_cpu) && !need_resched)
smp_send_reschedule(best_cpu);
return;
}
}
/*
* We know that the preferred CPU has a cache-affine current
* process, lets try to find a new idle CPU for the woken-up
* process. Select the least recently active idle CPU. (that
* one will have the least active cache context.) Also find
* the executing process which has the least priority.
*/
oldest_idle = (cycles_t) -1;
target_tsk = NULL;
max_prio = 1;
for (i = 0; i < smp_num_cpus; i++) {
cpu = cpu_logical_map(i);
if (!can_schedule(p, cpu))
continue;
tsk = cpu_curr(cpu);
/*
* We use the first available idle CPU. This creates
* a priority list between idle CPUs, but this is not
* a problem.
*/
if (tsk == idle_task(cpu)) {
if (last_schedule(cpu) < oldest_idle) {
oldest_idle = last_schedule(cpu);
target_tsk = tsk;
}
} else {
if (oldest_idle == -1ULL) {
int prio = preemption_goodness(tsk, p, cpu);
if (prio > max_prio) {
max_prio = prio;
target_tsk = tsk;
}
}
}
}
tsk = target_tsk;
if (tsk) {
if (oldest_idle != -1ULL) {
best_cpu = tsk->processor;
goto send_now_idle;
}
tsk->need_resched = 1;
if (tsk->processor != this_cpu)
smp_send_reschedule(tsk->processor);
}
return;
#else /* UP */
int this_cpu = smp_processor_id();
struct task_struct *tsk;
tsk = cpu_curr(this_cpu);
291 if (preemption_goodness(tsk, p, this_cpu) > 1)
tsk->need_resched = 1;
#endif
}
/*
* Careful!
*
* This has to add the process to the _beginning_ of the
* run-queue, not the end. See the comment about "This is
* subtle" in the scheduler proper..
*/
303 static inline void add_to_runqueue(struct task_struct * p)
{
list_add(&p->run_list, &runqueue_head);
nr_running++;
}
309 static inline void move_last_runqueue(struct task_struct * p)
{
list_del(&p->run_list);
list_add_tail(&p->run_list, &runqueue_head);
}
315 static inline void move_first_runqueue(struct task_struct * p)
{
list_del(&p->run_list);
list_add(&p->run_list, &runqueue_head);
}
/*
* Wake up a process. Put it on the run-queue if it's not
* already there. The "current" process is always on the
* run-queue (except when the actual re-schedule is in
* progress), and as such you're allowed to do the simpler
* "current->state = TASK_RUNNING" to mark yourself runnable
* without the overhead of this.
*/
329 inline void wake_up_process(struct task_struct * p)
{
unsigned long flags;
/*
* We want the common case fall through straight, thus the goto.
*/
336 spin_lock_irqsave(&runqueue_lock, flags);
p->state = TASK_RUNNING;
338 if (task_on_runqueue(p))
339 goto out;
add_to_runqueue(p);
reschedule_idle(p);
out:
343 spin_unlock_irqrestore(&runqueue_lock, flags);
}
346 static inline void wake_up_process_synchronous(struct task_struct * p)
{
unsigned long flags;
/*
* We want the common case fall through straight, thus the goto.
*/
353 spin_lock_irqsave(&runqueue_lock, flags);
p->state = TASK_RUNNING;
355 if (task_on_runqueue(p))
356 goto out;
add_to_runqueue(p);
out:
359 spin_unlock_irqrestore(&runqueue_lock, flags);
}
362 static void process_timeout(unsigned long __data)
{
struct task_struct * p = (struct task_struct *) __data;
wake_up_process(p);
}
369 signed long schedule_timeout(signed long timeout)
{
struct timer_list timer;
unsigned long expire;
374 switch (timeout)
{
376 case MAX_SCHEDULE_TIMEOUT:
/*
* These two special cases are useful to be comfortable
* in the caller. Nothing more. We could take
* MAX_SCHEDULE_TIMEOUT from one of the negative value
* but I' d like to return a valid offset (>=0) to allow
* the caller to do everything it want with the retval.
*/
schedule();
385 goto out;
386 default:
/*
* Another bit of PARANOID. Note that the retval will be
* 0 since no piece of kernel is supposed to do a check
* for a negative retval of schedule_timeout() (since it
* should never happens anyway). You just have the printk()
* that will tell you if something is gone wrong and where.
*/
394 if (timeout < 0)
{
printk(KERN_ERR "schedule_timeout: wrong timeout "
"value %lx from %p\n", timeout,
__builtin_return_address(0));
current->state = TASK_RUNNING;
400 goto out;
}
}
expire = timeout + jiffies;
init_timer(&timer);
timer.expires = expire;
timer.data = (unsigned long) current;
timer.function = process_timeout;
add_timer(&timer);
schedule();
del_timer_sync(&timer);
timeout = expire - jiffies;
out:
418 return timeout < 0 ? 0 : timeout;
}
/*
* schedule_tail() is getting called from the fork return path. This
* cleans up all remaining scheduler things, without impacting the
* common case.
*/
426 static inline void __schedule_tail(struct task_struct *prev)
{
#ifdef CONFIG_SMP
int policy;
/*
* prev->policy can be written from here only before `prev'
* can be scheduled (before setting prev->has_cpu to zero).
* Of course it must also be read before allowing prev
* to be rescheduled, but since the write depends on the read
* to complete, wmb() is enough. (the spin_lock() acquired
* before setting has_cpu is not enough because the spin_lock()
* common code semantics allows code outside the critical section
* to enter inside the critical section)
*/
policy = prev->policy;
prev->policy = policy & ~SCHED_YIELD;
wmb();
/*
* fast path falls through. We have to clear has_cpu before
* checking prev->state to avoid a wakeup race - thus we
* also have to protect against the task exiting early.
*/
task_lock(prev);
prev->has_cpu = 0;
mb();
if (prev->state == TASK_RUNNING)
goto needs_resched;
out_unlock:
task_unlock(prev); /* Synchronise here with release_task() if prev is TASK_ZOMBIE */
return;
/*
* Slow path - we 'push' the previous process and
* reschedule_idle() will attempt to find a new
* processor for it. (but it might preempt the
* current process as well.) We must take the runqueue
* lock and re-check prev->state to be correct. It might
* still happen that this process has a preemption
* 'in progress' already - but this is not a problem and
* might happen in other circumstances as well.
*/
needs_resched:
{
unsigned long flags;
/*
* Avoid taking the runqueue lock in cases where
* no preemption-check is necessery:
*/
if ((prev == idle_task(smp_processor_id())) ||
(policy & SCHED_YIELD))
goto out_unlock;
spin_lock_irqsave(&runqueue_lock, flags);
if (prev->state == TASK_RUNNING)
reschedule_idle(prev);
spin_unlock_irqrestore(&runqueue_lock, flags);
goto out_unlock;
}
#else
prev->policy &= ~SCHED_YIELD;
#endif /* CONFIG_SMP */
}
493 void schedule_tail(struct task_struct *prev)
{
__schedule_tail(prev);
}
/*
* 'schedule()' is the scheduler function. It's a very simple and nice
* scheduler: it's not perfect, but certainly works for most things.
*
* The goto is "interesting".
*
* NOTE!! Task 0 is the 'idle' task, which gets called when no other
* tasks can run. It can not be killed, and it cannot sleep. The 'state'
* information in task[0] is never used.
*/
508 asmlinkage void schedule(void)
{
struct schedule_data * sched_data;
struct task_struct *prev, *next, *p;
struct list_head *tmp;
int this_cpu, c;
515 if (!current->active_mm) BUG();
need_resched_back:
prev = current;
this_cpu = prev->processor;
520 if (in_interrupt())
521 goto scheduling_in_interrupt;
523 release_kernel_lock(prev, this_cpu);
/* Do "administrative" work here while we don't hold any locks */
526 if (softirq_active(this_cpu) & softirq_mask(this_cpu))
527 goto handle_softirq;
handle_softirq_back:
/*
* 'sched_data' is protected by the fact that we can run
* only one process per CPU.
*/
sched_data = & aligned_data[this_cpu].schedule_data;
536 spin_lock_irq(&runqueue_lock);
/* move an exhausted RR process to be last.. */
539 if (prev->policy == SCHED_RR)
540 goto move_rr_last;
move_rr_back:
543 switch (prev->state) {
544 case TASK_INTERRUPTIBLE:
545 if (signal_pending(prev)) {
prev->state = TASK_RUNNING;
547 break;
}
549 default:
del_from_runqueue(prev);
551 case TASK_RUNNING:
}
prev->need_resched = 0;
/*
* this is the scheduler proper:
*/
repeat_schedule:
/*
* Default process to select..
*/
next = idle_task(this_cpu);
c = -1000;
565 if (prev->state == TASK_RUNNING)
566 goto still_running;
still_running_back:
569 list_for_each(tmp, &runqueue_head) {
p = list_entry(tmp, struct task_struct, run_list);
571 if (can_schedule(p, this_cpu)) {
int weight = goodness(p, this_cpu, prev->active_mm);
573 if (weight > c)
c = weight, next = p;
}
}
/* Do we need to re-calculate counters? */
579 if (!c)
580 goto recalculate;
/*
* from this point on nothing can prevent us from
* switching to the next task, save this fact in
* sched_data.
*/
sched_data->curr = next;
#ifdef CONFIG_SMP
next->has_cpu = 1;
next->processor = this_cpu;
#endif
591 spin_unlock_irq(&runqueue_lock);
593 if (prev == next)
594 goto same_process;
#ifdef CONFIG_SMP
/*
* maintain the per-process 'last schedule' value.
* (this has to be recalculated even if we reschedule to
* the same process) Currently this is only used on SMP,
* and it's approximate, so we do not have to maintain
* it while holding the runqueue spinlock.
*/
sched_data->last_schedule = get_cycles();
/*
* We drop the scheduler lock early (it's a global spinlock),
* thus we have to lock the previous process from getting
* rescheduled during switch_to().
*/
#endif /* CONFIG_SMP */
kstat.context_swtch++;
/*
* there are 3 processes which are affected by a context switch:
*
* prev == .... ==> (last => next)
*
* It's the 'much more previous' 'prev' that is on next's stack,
* but prev is set to (the just run) 'last' process by switch_to().
* This might sound slightly confusing but makes tons of sense.
*/
624 prepare_to_switch();
{
struct mm_struct *mm = next->mm;
struct mm_struct *oldmm = prev->active_mm;
628 if (!mm) {
629 if (next->active_mm) BUG();
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next, this_cpu);
633 } else {
634 if (next->active_mm != mm) BUG();
switch_mm(oldmm, mm, next, this_cpu);
}
638 if (!prev->mm) {
prev->active_mm = NULL;
mmdrop(oldmm);
}
}
/*
* This just switches the register state and the
* stack.
*/
648 switch_to(prev, next, prev);
__schedule_tail(prev);
same_process:
652 reacquire_kernel_lock(current);
653 if (current->need_resched)
654 goto need_resched_back;
656 return;
recalculate:
{
struct task_struct *p;
661 spin_unlock_irq(&runqueue_lock);
read_lock(&tasklist_lock);
663 for_each_task(p)
p->counter = (p->counter >> 1) + NICE_TO_TICKS(p->nice);
665 read_unlock(&tasklist_lock);
666 spin_lock_irq(&runqueue_lock);
}
668 goto repeat_schedule;
still_running:
c = goodness(prev, this_cpu, prev->active_mm);
next = prev;
673 goto still_running_back;
handle_softirq:
do_softirq();
677 goto handle_softirq_back;
move_rr_last:
680 if (!prev->counter) {
prev->counter = NICE_TO_TICKS(prev->nice);
move_last_runqueue(prev);
}
684 goto move_rr_back;
scheduling_in_interrupt:
printk("Scheduling in interrupt\n");
688 BUG();
689 return;
}
692 static inline void __wake_up_common (wait_queue_head_t *q, unsigned int mode,
unsigned int wq_mode, const int sync)
{
struct list_head *tmp, *head;
struct task_struct *p, *best_exclusive;
unsigned long flags;
int best_cpu, irq;
700 if (!q)
701 goto out;
best_cpu = smp_processor_id();
irq = in_interrupt();
best_exclusive = NULL;
706 wq_write_lock_irqsave(&q->lock, flags);
#if WAITQUEUE_DEBUG
CHECK_MAGIC_WQHEAD(q);
#endif
head = &q->task_list;
#if WAITQUEUE_DEBUG
if (!head->next || !head->prev)
WQ_BUG();
#endif
tmp = head->next;
718 while (tmp != head) {
unsigned int state;
wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
tmp = tmp->next;
#if WAITQUEUE_DEBUG
CHECK_MAGIC(curr->__magic);
#endif
p = curr->task;
state = p->state;
729 if (state & mode) {
#if WAITQUEUE_DEBUG
curr->__waker = (long)__builtin_return_address(0);
#endif
/*
* If waking up from an interrupt context then
* prefer processes which are affine to this
* CPU.
*/
738 if (irq && (curr->flags & wq_mode & WQ_FLAG_EXCLUSIVE)) {
739 if (!best_exclusive)
best_exclusive = p;
741 if (p->processor == best_cpu) {
best_exclusive = p;
743 break;
}
745 } else {
746 if (sync)
wake_up_process_synchronous(p);
748 else
wake_up_process(p);
750 if (curr->flags & wq_mode & WQ_FLAG_EXCLUSIVE)
751 break;
}
}
}
755 if (best_exclusive) {
756 if (sync)
wake_up_process_synchronous(best_exclusive);
758 else
wake_up_process(best_exclusive);
}
761 wq_write_unlock_irqrestore(&q->lock, flags);
out:
763 return;
}
766 void __wake_up(wait_queue_head_t *q, unsigned int mode, unsigned int wq_mode)
{
__wake_up_common(q, mode, wq_mode, 0);
}
771 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, unsigned int wq_mode)
{
__wake_up_common(q, mode, wq_mode, 1);
}
#define SLEEP_ON_VAR \
unsigned long flags; \
wait_queue_t wait; \
init_waitqueue_entry(&wait, current);
#define SLEEP_ON_HEAD \
wq_write_lock_irqsave(&q->lock,flags); \
__add_wait_queue(q, &wait); \
wq_write_unlock(&q->lock);
#define SLEEP_ON_TAIL \
wq_write_lock_irq(&q->lock); \
__remove_wait_queue(q, &wait); \
wq_write_unlock_irqrestore(&q->lock,flags);
791 void interruptible_sleep_on(wait_queue_head_t *q)
{
SLEEP_ON_VAR
current->state = TASK_INTERRUPTIBLE;
797 SLEEP_ON_HEAD
schedule();
799 SLEEP_ON_TAIL
}
802 long interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
SLEEP_ON_VAR
current->state = TASK_INTERRUPTIBLE;
808 SLEEP_ON_HEAD
timeout = schedule_timeout(timeout);
810 SLEEP_ON_TAIL
812 return timeout;
}
815 void sleep_on(wait_queue_head_t *q)
{
SLEEP_ON_VAR
current->state = TASK_UNINTERRUPTIBLE;
821 SLEEP_ON_HEAD
schedule();
823 SLEEP_ON_TAIL
}
826 long sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
SLEEP_ON_VAR
current->state = TASK_UNINTERRUPTIBLE;
832 SLEEP_ON_HEAD
timeout = schedule_timeout(timeout);
834 SLEEP_ON_TAIL
836 return timeout;
}
839 void scheduling_functions_end_here(void) { }
#ifndef __alpha__
/*
* This has been replaced by sys_setpriority. Maybe it should be
* moved into the arch dependent tree for those ports that require
* it for backward compatibility?
*/
849 asmlinkage long sys_nice(int increment)
{
long newprio;
/*
* Setpriority might change our priority at the same moment.
* We don't have to worry. Conceptually one call occurs first
* and we have a single winner.
*/
858 if (increment < 0) {
859 if (!capable(CAP_SYS_NICE))
860 return -EPERM;
861 if (increment < -40)
increment = -40;
}
864 if (increment > 40)
increment = 40;
newprio = current->nice + increment;
868 if (newprio < -20)
newprio = -20;
870 if (newprio > 19)
newprio = 19;
current->nice = newprio;
873 return 0;
}
#endif
878 static inline struct task_struct *find_process_by_pid(pid_t pid)
{
struct task_struct *tsk = current;
882 if (pid)
tsk = find_task_by_pid(pid);
884 return tsk;
}
887 static int setscheduler(pid_t pid, int policy,
struct sched_param *param)
{
struct sched_param lp;
struct task_struct *p;
int retval;
retval = -EINVAL;
895 if (!param || pid < 0)
896 goto out_nounlock;
retval = -EFAULT;
899 if (copy_from_user(&lp, param, sizeof(struct sched_param)))
900 goto out_nounlock;
/*
* We play safe to avoid deadlocks.
*/
905 read_lock_irq(&tasklist_lock);
spin_lock(&runqueue_lock);
p = find_process_by_pid(pid);
retval = -ESRCH;
911 if (!p)
912 goto out_unlock;
914 if (policy < 0)
policy = p->policy;
916 else {
retval = -EINVAL;
if (policy != SCHED_FIFO && policy != SCHED_RR &&
919 policy != SCHED_OTHER)
920 goto out_unlock;
}
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are 1..99, valid
* priority for SCHED_OTHER is 0.
*/
retval = -EINVAL;
928 if (lp.sched_priority < 0 || lp.sched_priority > 99)
929 goto out_unlock;
930 if ((policy == SCHED_OTHER) != (lp.sched_priority == 0))
931 goto out_unlock;
retval = -EPERM;
if ((policy == SCHED_FIFO || policy == SCHED_RR) &&
935 !capable(CAP_SYS_NICE))
936 goto out_unlock;
if ((current->euid != p->euid) && (current->euid != p->uid) &&
938 !capable(CAP_SYS_NICE))
939 goto out_unlock;
retval = 0;
p->policy = policy;
p->rt_priority = lp.sched_priority;
944 if (task_on_runqueue(p))
move_first_runqueue(p);
current->need_resched = 1;
out_unlock:
950 spin_unlock(&runqueue_lock);
951 read_unlock_irq(&tasklist_lock);
out_nounlock:
954 return retval;
}
957 asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
struct sched_param *param)
{
960 return setscheduler(pid, policy, param);
}
963 asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param *param)
{
965 return setscheduler(pid, -1, param);
}
968 asmlinkage long sys_sched_getscheduler(pid_t pid)
{
struct task_struct *p;
int retval;
retval = -EINVAL;
974 if (pid < 0)
975 goto out_nounlock;
retval = -ESRCH;
read_lock(&tasklist_lock);
p = find_process_by_pid(pid);
980 if (p)
retval = p->policy & ~SCHED_YIELD;
982 read_unlock(&tasklist_lock);
out_nounlock:
985 return retval;
}
988 asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param *param)
{
struct task_struct *p;
struct sched_param lp;
int retval;
retval = -EINVAL;
995 if (!param || pid < 0)
996 goto out_nounlock;
read_lock(&tasklist_lock);
p = find_process_by_pid(pid);
retval = -ESRCH;
1001 if (!p)
1002 goto out_unlock;
lp.sched_priority = p->rt_priority;
1004 read_unlock(&tasklist_lock);
/*
* This one might sleep, we cannot do it with a spinlock held ...
*/
retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
out_nounlock:
1012 return retval;
out_unlock:
1015 read_unlock(&tasklist_lock);
1016 return retval;
}
1019 asmlinkage long sys_sched_yield(void)
{
/*
* Trick. sched_yield() first counts the number of truly
* 'pending' runnable processes, then returns if it's
* only the current processes. (This test does not have
* to be atomic.) In threaded applications this optimization
* gets triggered quite often.
*/
int nr_pending = nr_running;
#if CONFIG_SMP
int i;
// Substract non-idle processes running on other CPUs.
for (i = 0; i < smp_num_cpus; i++)
if (aligned_data[i].schedule_data.curr != idle_task(i))
nr_pending--;
#else
// on UP this process is on the runqueue as well
nr_pending--;
#endif
1042 if (nr_pending) {
/*
* This process can only be rescheduled by us,
* so this is safe without any locking.
*/
1047 if (current->policy == SCHED_OTHER)
current->policy |= SCHED_YIELD;
current->need_resched = 1;
}
1051 return 0;
}
1054 asmlinkage long sys_sched_get_priority_max(int policy)
{
int ret = -EINVAL;
1058 switch (policy) {
1059 case SCHED_FIFO:
1060 case SCHED_RR:
ret = 99;
1062 break;
1063 case SCHED_OTHER:
ret = 0;
1065 break;
}
1067 return ret;
}
1070 asmlinkage long sys_sched_get_priority_min(int policy)
{
int ret = -EINVAL;
1074 switch (policy) {
1075 case SCHED_FIFO:
1076 case SCHED_RR:
ret = 1;
1078 break;
1079 case SCHED_OTHER:
ret = 0;
}
1082 return ret;
}
1085 asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct timespec *interval)
{
struct timespec t;
struct task_struct *p;
int retval = -EINVAL;
1091 if (pid < 0)
1092 goto out_nounlock;
retval = -ESRCH;
read_lock(&tasklist_lock);
p = find_process_by_pid(pid);
1097 if (p)
jiffies_to_timespec(p->policy & SCHED_FIFO ? 0 : NICE_TO_TICKS(p->nice),
&t);
1100 read_unlock(&tasklist_lock);
1101 if (p)
retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
out_nounlock:
1104 return retval;
}
1107 static void show_task(struct task_struct * p)
{
unsigned long free = 0;
int state;
static const char * stat_nam[] = { "R", "S", "D", "Z", "T", "W" };
printk("%-8s ", p->comm);
state = p->state ? ffz(~p->state) + 1 : 0;
1115 if (((unsigned) state) < sizeof(stat_nam)/sizeof(char *))
printk(stat_nam[state]);
1117 else
printk(" ");
#if (BITS_PER_LONG == 32)
1120 if (p == current)
printk(" current ");
1122 else
printk(" %08lX ", thread_saved_pc(&p->thread));
#else
if (p == current)
printk(" current task ");
else
printk(" %016lx ", thread_saved_pc(&p->thread));
#endif
{
unsigned long * n = (unsigned long *) (p+1);
1132 while (!*n)
n++;
free = (unsigned long) n - (unsigned long)(p+1);
}
printk("%5lu %5d %6d ", free, p->pid, p->p_pptr->pid);
1137 if (p->p_cptr)
printk("%5d ", p->p_cptr->pid);
1139 else
printk(" ");
1141 if (!p->mm)
printk(" (L-TLB) ");
1143 else
printk(" (NOTLB) ");
1145 if (p->p_ysptr)
printk("%7d", p->p_ysptr->pid);
1147 else
printk(" ");
1149 if (p->p_osptr)
printk(" %5d\n", p->p_osptr->pid);
1151 else
printk("\n");
#ifdef CONFIG_X86
/* This is very useful, but only works on x86 right now */
{
extern void show_trace(unsigned long);
show_trace(p->thread.esp);
}
#endif
}
1163 char * render_sigset_t(sigset_t *set, char *buffer)
{
int i = _NSIG, x;
1166 do {
i -= 4, x = 0;
1168 if (sigismember(set, i+1)) x |= 1;
1169 if (sigismember(set, i+2)) x |= 2;
1170 if (sigismember(set, i+3)) x |= 4;
1171 if (sigismember(set, i+4)) x |= 8;
*buffer++ = (x < 10 ? '0' : 'a' - 10) + x;
1173 } while (i >= 4);
*buffer = 0;
1175 return buffer;
}
1178 void show_state(void)
{
struct task_struct *p;
#if (BITS_PER_LONG == 32)
printk("\n"
" free sibling\n");
printk(" task PC stack pid father child younger older\n");
#else
printk("\n"
" free sibling\n");
printk(" task PC stack pid father child younger older\n");
#endif
read_lock(&tasklist_lock);
1192 for_each_task(p)
show_task(p);
1194 read_unlock(&tasklist_lock);
}
/*
* Put all the gunge required to become a kernel thread without
* attached user resources in one place where it belongs.
*/
1202 void daemonize(void)
{
struct fs_struct *fs;
/*
* If we were started as result of loading a module, close all of the
* user space pages. We don't need them, and if we didn't close them
* they would be locked into memory.
*/
exit_mm(current);
current->session = 1;
current->pgrp = 1;
/* Become as one with the init task */
exit_fs(current); /* current->fs->count--; */
fs = init_task.fs;
current->fs = fs;
atomic_inc(&fs->count);
exit_files(current);
current->files = init_task.files;
atomic_inc(¤t->files->count);
}
1228 void __init init_idle(void)
{
struct schedule_data * sched_data;
sched_data = &aligned_data[smp_processor_id()].schedule_data;
1233 if (current != &init_task && task_on_runqueue(current)) {
printk("UGH! (%d:%d) was on the runqueue, removing.\n",
smp_processor_id(), current->pid);
del_from_runqueue(current);
}
sched_data->curr = current;
sched_data->last_schedule = get_cycles();
}
extern void init_timervecs (void);
1244 void __init sched_init(void)
{
/*
* We have to do a little magic to get the first
* process right in SMP mode.
*/
int cpu = smp_processor_id();
int nr;
init_task.processor = cpu;
1255 for(nr = 0; nr < PIDHASH_SZ; nr++)
pidhash[nr] = NULL;
init_timervecs();
init_bh(TIMER_BH, timer_bh);
init_bh(TQUEUE_BH, tqueue_bh);
init_bh(IMMEDIATE_BH, immediate_bh);
/*
* The boot idle thread does lazy MMU switching as well:
*/
atomic_inc(&init_mm.mm_count);
enter_lazy_tlb(&init_mm, current, cpu);
}