相對於 run queue 的是 wait queue，這是一個存放休眠中的行程的佇列。
由型態為 wait_queue_t 的雙向鏈結串列所組成，並具有一個型態為 wait_queue_head_t 的串列首。
wait_queue_t 結構中的 flags 值為 1 時，進入休眠的行程是 exclusive process，表示只有該行程在等待特定的系統資源。
若 flags 值為 0 時，則是 nonexclusive process，表示有多個行程在等待相同的系統資源。
而 func 欄位會在初始化時設定成 default_wake_function()，這是 exclusive process 的預設喚醒函式。
wait queue head 可以靜態的宣告：
DECLARE_WAIT_QUEUE_HEAD( wait_head );
或是動態的宣告：
wait_queue_head_t wait_head;
init_waitqueue_head( &wait_head );
要讓行程休眠可以呼叫下列巨集函式，將該行程加入一個等待佇列中，並交出 CPU 使用權。
wait_event(wait_head, condition)
wait_event_interruptible(wait_head, condition)
wait_event_timeout(wait_head, condition, timeout)
wait_event_interruptible_timeout(wait_head, condition, timeout)
要喚醒休眠中的行程可以呼叫下列巨集函式，被喚醒的行程會回到執行佇列之中。
wake_up( wait_head_pt )
wake_up_interruptible( wait_head_pt )
定義於 include/linux/wait.h
typedef struct __wait_queue wait_queue_t;
typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int sync, void *key);
int default_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
struct __wait_queue {
unsigned int flags;
#define WQ_FLAG_EXCLUSIVE 0x01
struct task_struct * task;
wait_queue_func_t func;
struct list_head task_list;
};
struct wait_bit_key {
void *flags;
int bit_nr;
};
struct wait_bit_queue {
struct wait_bit_key key;
wait_queue_t wait;
};
struct __wait_queue_head {
spinlock_t lock;
struct list_head task_list;
};
typedef struct __wait_queue_head wait_queue_head_t;
#define __wait_event(wq, condition) \
do { \
DEFINE_WAIT(__wait); \
\
for (;;) { \
prepare_to_wait(&wq, &__wait, TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
schedule(); \
} \
finish_wait(&wq, &__wait); \
} while (0)
#define wait_event(wq, condition) \
do { \
if (condition) \
break; \
__wait_event(wq, condition); \
} while (0)
void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key));
#define wake_up(x) __wake_up(x, TASK_UNINTERRUPTIBLE TASK_INTERRUPTIBLE, 1, NULL)
#define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
定義於 kernel/wait.c
/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
* wake-function that tests for the wait-queue being active
* will be guaranteed to see waitqueue addition _or_ subsequent
* tests in this thread will see the wakeup having taken place.
*
* The spin_unlock() itself is semi-permeable and only protects
* one way (it only protects stuff inside the critical region and
* stops them from bleeding out - it would still allow subsequent
* loads to move into the the critical region).
*/
void fastcall
prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
{
unsigned long flags;
wait->flags &= ~WQ_FLAG_EXCLUSIVE;
spin_lock_irqsave(&q->lock, flags);
if (list_empty(&wait->task_list))
__add_wait_queue(q, wait);
/*
* don't alter the task state if this is just going to
* queue an async wait queue callback
*/
if (is_sync_wait(wait))
set_current_state(state);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(prepare_to_wait);
定義於 kernel/sched.c
/*
* The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
* wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
* number) then we wake all the non-exclusive tasks and one exclusive task.
*
* There are circumstances in which we can try to wake a task which has already
* started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
* zero in this (rare) case, and we handle it by continuing to scan the queue.
*/
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, int sync, void *key)
{
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;
if (curr->func(curr, mode, sync, key) &&
(flags & WQ_FLAG_EXCLUSIVE) &&
!--nr_exclusive)
break;
}
}
/**
* __wake_up - wake up threads blocked on a waitqueue.
* @q: the waitqueue
* @mode: which threads
* @nr_exclusive: how many wake-one or wake-many threads to wake up
*/
void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
int nr_exclusive, void *key)
{
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__wake_up_common(q, mode, nr_exclusive, 0, key);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(__wake_up);
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
* @state: the mask of task states that can be woken
* @sync: do a synchronous wakeup?
*
* Put it on the run-queue if it's not already there. The "current"
* thread 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.
*
* returns failure only if the task is already active.
*/
static int try_to_wake_up(task_t *p, unsigned int state, int sync)
{
int cpu, this_cpu, success = 0;
unsigned long flags;
long old_state;
runqueue_t *rq;
#ifdef CONFIG_SMP
unsigned long load, this_load;
struct sched_domain *sd;
int new_cpu;
#endif
rq = task_rq_lock(p, &flags);
schedstat_inc(rq, ttwu_cnt);
old_state = p->state;
if (!(old_state & state))
goto out;
if (p->array)
goto out_running;
cpu = task_cpu(p);
this_cpu = smp_processor_id();
#ifdef CONFIG_SMP
if (unlikely(task_running(rq, p)))
goto out_activate;
new_cpu = cpu;
if (cpu == this_cpu unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
goto out_set_cpu;
load = source_load(cpu);
this_load = target_load(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)
this_load -= SCHED_LOAD_SCALE;
/* Don't pull the task off an idle CPU to a busy one */
if (load < SCHED_LOAD_SCALE/2 && this_load > SCHED_LOAD_SCALE/2)
goto out_set_cpu;
new_cpu = this_cpu; /* Wake to this CPU if we can */
/*
* Scan domains for affine wakeup and passive balancing
* possibilities.
*/
for_each_domain(this_cpu, sd) {
unsigned int imbalance;
/*
* Start passive balancing when half the imbalance_pct
* limit is reached.
*/
imbalance = sd->imbalance_pct + (sd->imbalance_pct - 100) / 2;
if ((sd->flags & SD_WAKE_AFFINE) &&
!task_hot(p, rq->timestamp_last_tick, sd)) {
/*
* This domain has SD_WAKE_AFFINE and p is cache cold
* in this domain.
*/
if (cpu_isset(cpu, sd->span)) {
schedstat_inc(sd, ttwu_wake_affine);
goto out_set_cpu;
}
} else if ((sd->flags & SD_WAKE_BALANCE) &&
imbalance*this_load <= 100*load) {
/*
* This domain has SD_WAKE_BALANCE and there is
* an imbalance.
*/
if (cpu_isset(cpu, sd->span)) {
schedstat_inc(sd, ttwu_wake_balance);
goto out_set_cpu;
}
}
}
new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
schedstat_inc(rq, ttwu_attempts);
new_cpu = wake_idle(new_cpu, p);
if (new_cpu != cpu) {
schedstat_inc(rq, ttwu_moved);
set_task_cpu(p, new_cpu);
task_rq_unlock(rq, &flags);
/* might preempt at this point */
rq = task_rq_lock(p, &flags);
old_state = p->state;
if (!(old_state & state))
goto out;
if (p->array)
goto out_running;
this_cpu = smp_processor_id();
cpu = task_cpu(p);
}
out_activate:
#endif /* CONFIG_SMP */
if (old_state == TASK_UNINTERRUPTIBLE) {
rq->nr_uninterruptible--;
/*
* Tasks on involuntary sleep don't earn
* sleep_avg beyond just interactive state.
*/
p->activated = -1;
}
/*
* Sync wakeups (i.e. those types of wakeups where the waker
* has indicated that it will leave the CPU in short order)
* don't trigger a preemption, if the woken up task will run on
* this cpu. (in this case the 'I will reschedule' promise of
* the waker guarantees that the freshly woken up task is going
* to be considered on this CPU.)
*/
activate_task(p, rq, cpu == this_cpu);
if (!sync cpu != this_cpu) {
if (TASK_PREEMPTS_CURR(p, rq))
resched_task(rq->curr);
}
success = 1;
out_running:
p->state = TASK_RUNNING;
out:
task_rq_unlock(rq, &flags);
return success;
}
int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, void *key)
{
task_t *p = curr->task;
return try_to_wake_up(p, mode, sync);
}
EXPORT_SYMBOL(default_wake_function);
