static void __sched notrace __schedule(bool preempt)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
/* ==1==
找到当前cpu上的就绪队列rq
并将正在运行的进程curr保存到prev中 */
cpu = smp_processor_id();
rq = cpu_rq(cpu);
prev = rq->curr;
/*
* do_exit() calls schedule() with preemption disabled as an exception;
* however we must fix that up, otherwise the next task will see an
* inconsistent (higher) preempt count.
*
* It also avoids the below schedule_debug() test from complaining
* about this.
*/
if (unlikely(prev->state == TASK_DEAD))
preempt_enable_no_resched_notrace();
/* 如果禁止内核抢占，而又调用了cond_resched就会出错
* 这里就是用来捕获该错误的 */
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
/* 关闭本地中断 */
local_irq_disable();
/* 更新全局状态，
* 标识当前CPU发生上下文的切换 */
rcu_note_context_switch();
/*
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
*/
smp_mb__before_spinlock();
/* 锁住该队列 */
raw_spin_lock(&rq->lock);
lockdep_pin_lock(&rq->lock);
rq->clock_skip_update <<= 1; /* promote REQ to ACT */
/* 切换次数记录, 默认认为非主动调度计数(抢占) */
switch_count = &prev->nivcsw;
/*
* scheduler检查prev的状态state和内核抢占表示
* 如果prev是不可运行的, 并且在内核态没有被抢占
*
* 此时当前进程不是处于运行态, 并且不是被抢占
* 此时不能只检查抢占计数
* 因为可能某个进程(如网卡轮询)直接调用了schedule
* 如果不判断prev->stat就可能误认为task进程为RUNNING状态
* 到达这里，有两种可能，一种是主动schedule, 另外一种是被抢占
* 被抢占有两种情况, 一种是时间片到点, 一种是时间片没到点
* 时间片到点后, 主要是置当前进程的need_resched标志
* 接下来在时钟中断结束后, 会preempt_schedule_irq抢占调度
*
* 那么我们正常应该做的是应该将进程prev从就绪队列rq中删除,
* 但是如果当前进程prev有非阻塞等待信号,
* 并且它的状态是TASK_INTERRUPTIBLE
* 我们就不应该从就绪队列总删除它
* 而是配置其状态为TASK_RUNNING, 并且把他留在rq中
/* 如果内核态没有被抢占, 并且内核抢占有效
即是否同时满足以下条件：
1 该进程处于停止状态
2 该进程没有在内核态被抢占 */
if (!preempt && prev->state)
{
/* 如果当前进程有非阻塞等待信号，并且它的状态是TASK_INTERRUPTIBLE */
if (unlikely(signal_pending_state(prev->state, prev)))
{
/* 将当前进程的状态设为：TASK_RUNNING */
prev->state = TASK_RUNNING;
}
else /* 否则需要将prev进程从就绪队列中删除*/
{
/* 将当前进程从runqueue(运行队列)中删除 */
deactivate_task(rq, prev, DEQUEUE_SLEEP);
/* 标识当前进程不在runqueue中 */
prev->on_rq = 0;
/*
* If a worker went to sleep, notify and ask workqueue
* whether it wants to wake up a task to maintain
* concurrency.
*/
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
to_wakeup = wq_worker_sleeping(prev);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
}
/* 如果不是被抢占的，就累加主动切换次数 */
switch_count = &prev->nvcsw;
}
/* 如果prev进程仍然在就绪队列上没有被删除 */
if (task_on_rq_queued(prev))
update_rq_clock(rq); /* 跟新就绪队列的时钟 */
/* 挑选一个优先级最高的任务将其排进队列 */
next = pick_next_task(rq, prev);
/* 清除pre的TIF_NEED_RESCHED标志 */
clear_tsk_need_resched(prev);
/* 清楚内核抢占标识 */
clear_preempt_need_resched();
rq->clock_skip_update = 0;
/* 如果prev和next非同一个进程 */
if (likely(prev != next))
{
rq->nr_switches++; /* 队列切换次数更新 */
rq->curr = next; /* 将next标记为队列的curr进程 */
++*switch_count; /* 进程切换次数更新 */
trace_sched_switch(preempt, prev, next);
/* 进程之间上下文切换 */
rq = context_switch(rq, prev, next); /* unlocks the rq */
}
else /* 如果prev和next为同一进程，则不进行进程切换 */
{
lockdep_unpin_lock(&rq->lock);
raw_spin_unlock_irq(&rq->lock);
}
balance_callback(rq);
}
/*
* schedule() is the main scheduler function.
*/
asmlinkage void __sched schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
need_resched:
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
rcu_note_context_switch(cpu);
prev = rq->curr;
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
/*
* If a worker is going to sleep, notify and
* ask workqueue whether it wants to wake up a
* task to maintain concurrency. If so, wake
* up the task.
*/
if (prev->flags & PF_WQ_WORKER) {
struct task_struct *to_wakeup;
to_wakeup = wq_worker_sleeping(prev, cpu);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
deactivate_task(rq, prev, DEQUEUE_SLEEP);
/*
* If we are going to sleep and we have plugged IO queued, make
* sure to submit it to avoid deadlocks.
*/
if (blk_needs_flush_plug(prev)) {
raw_spin_unlock(&rq->lock);
blk_schedule_flush_plug(prev);
raw_spin_lock(&rq->lock);
}
}
switch_count = &prev->nvcsw;
}
pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
put_prev_task(rq, prev);
next = pick_next_task(rq);
clear_tsk_need_resched(prev);
rq->skip_clock_update = 0;
if (likely(prev != next)) {
rq->nr_switches++;
rq->curr = next;
++*switch_count;
context_switch(rq, prev, next); /* unlocks the rq */
/*
* The context switch have flipped the stack from under us
* and restored the local variables which were saved when
* this task called schedule() in the past. prev == current
* is still correct, but it can be moved to another cpu/rq.
*/
cpu = smp_processor_id();
rq = cpu_rq(cpu);
} else
raw_spin_unlock_irq(&rq->lock);
post_schedule(rq);
preempt_enable_no_resched();
if (need_resched())
goto need_resched;
}