linux调度schedule（）
将当前进程从相应的队列删除，计算更新调度实体以及进程相关信息，将进程插入到调度队列中，对于CFS，根据具体时间插入，对于实时调度插入到对应的有限队列尾，从运行队列中选择一个可运行进程，并进行进程上下文切换。
schedule函数任务是用一个进程来替换当前正在执行的进程；
asmlinkage void __sched schedule(void)
{
struct task_struct *tsk = current;
/*If we are going to sleep and we have plugged IO queued,
<span style="white-space:pre"> </span> * make sure to submit it to avoid deadlocks.*/
sched_submit_work(tsk); 避免死锁
__schedule();
}
* __schedule() is the main scheduler function.
*/
static void __sched __schedule(void)
{
struct task_struct *prev, *next;
unsigned long *switch_count;
struct rq *rq;
int cpu;
need_resched:
preempt_disable(); 禁止内核抢占
cpu = smp_processor_id(); 当前cpu id
rq = cpu_rq(cpu); 当前cpu所拥有的runqueue；
rcu_note_context_switch(cpu); RCU ？？？
prev = rq->curr; 当前运行的进程赋值给prev
schedule_debug(prev);
if (sched_feat(HRTICK))
hrtick_clear(rq);
寻找别的进程时需要关闭抢占，获取自旋锁；
raw_spin_lock_irq(&rq->lock);
switch_count = &prev->nivcsw;
检查prev->state的标志，如果不是可运行态，在内核态没有被抢占，则从运行队列中将此删除；但是如果是由于非阻塞信号挂起，而且状态为TASK_INTERRUPTIBLE，则将进程设置为TASK_RUNNING并插入队列；
if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
if (unlikely(signal_pending_state(prev->state, prev))) {
prev->state = TASK_RUNNING;
} else {
deactivate_task(rq, prev, DEQUEUE_SLEEP);
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, cpu);
if (to_wakeup)
try_to_wake_up_local(to_wakeup);
}
}
switch_count = &prev->nvcsw;
}
/*现只对实时进程有用*/
pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
/*将当前进程，也就是被切换出去的进程重新
插入到各自的运行队列中，对于CFS算法插入
到合适的位置上，对于实时调度插入到同一个
优先级队列的链表尾部*/
put_prev_task(rq, prev);
/*从各自的运行队列中选择下一个进程来运行*/
next = pick_next_task(rq);
/清除prev的TIF_NEED_RESCHED标志。
clear_tsk_need_resched(prev);
rq->skip_clock_update = 0;
if (likely(prev != next)) {如果prev和next不同
rq->nr_switches++; 队列切换次数
rq->curr = next;
++*switch_count;进程切换次数
context_switch(rq, prev, next); /* unlocks the rq */ 进程上下文切换
/*
* 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);
实时进程会用到
post_schedule(rq);
允许抢占
sched_preempt_enable_no_resched();
if (need_resched())
goto need_resched;
}
对于cpu_rq等宏：
/*通过向上加偏移的方式得到rq，这里可以看出
runqueues为一个rq结构的数组，cpu为数组下标*/
#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
{
if (task_contributes_to_load(p))
rq->nr_uninterruptible++;
dequeue_task(rq, p, flags);
}
static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
{
update_rq_clock(rq); //更新rq时间
sched_info_dequeued(p); /*更新进程的sched_info数据结构中相关属性*/
p->sched_class->dequeue_task(rq, p, flags);/*调用具体调度类的函数从他的运行队列中删除*/
}选择下一个进程：
/*
* Pick up the highest-prio task:
*/
static inline struct task_struct *
pick_next_task(struct rq *rq)
{
const struct sched_class *class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in
* the fair class we can call that function directly:
*/
if (likely(rq->nr_running == rq->cfs.h_nr_running)) {//如果nr_running==cfs.h_nr_running，则说明当前rq队列中是没有rt任务的，
p = fair_sched_class.pick_next_task(rq);//在cfs队列中挑选即将被切换进去的进程
if (likely(p))
return p;
}
/* #define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next) */
for_each_class(class) {
p = class->pick_next_task(rq);
if (p)
return p;
}
BUG(); /* the idle class will always have a runnable task */
}
对于进程调度信息的切换：
对于context_switch（）；进程间的切换：
/*
* context_switch - switch to the new MM and the new
* thread's register state.
*/
static inline void
context_switch(struct rq *rq, struct task_struct *prev,
struct task_struct *next)
{
struct mm_struct *mm, *oldmm;
prepare_task_switch(rq, prev, next);
mm = next->mm; next进程所拥有的内存描述符，对于一般进程mm和active_mm两个字段一样，有相同的地址，但是内核线程没有自己的地址空间
oldmm = prev->active_mm; 进程正在使用的内存描述符
/*
* For paravirt, this is coupled with an exit in switch_to to
* combine the page table reload and the switch backend into
* one hypercall.
*/
arch_start_context_switch(prev);
if (!mm) {如果为内核线程 使用
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else 否则就用 next的地址空间替换prev的地址空间
switch_mm(oldmm, mm, next);
if (!prev->mm) { 如果prev是内核线程或者正在退出的进程，就将prev的内存描述符保存在运行队列的prev_mm中；并设置prev->active_mm = NULL;为空
prev->active_mm = NULL;
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);
在执行switch_to后prev指向被替换回来的进程
barrier();
/*
* this_rq must be evaluated again because prev may have moved
* CPUs since it called schedule(), thus the 'rq' on its stack
* frame will be invalid.
*/
finish_task_switch(this_rq(), prev);
}
对于
/**
* finish_task_switch - clean up after a task-switch
* @rq: runqueue associated with task-switch
* @prev: the thread we just switched away from.
*
* finish_task_switch must be called after the context switch, paired
* with a prepare_task_switch call before the context switch.
* finish_task_switch will reconcile locking set up by prepare_task_switch,
* and do any other architecture-specific cleanup actions.
*
* Note that we may have delayed dropping an mm in context_switch(). If
* so, we finish that here outside of the runqueue lock. (Doing it
* with the lock held can cause deadlocks; see schedule() for
* details.)
*/
static void finish_task_switch(struct rq *rq, struct task_struct *prev)
__releases(rq->lock)
{
struct mm_struct *mm = rq->prev_mm;
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 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_state = prev->state;
finish_arch_switch(prev);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
local_irq_disable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
perf_event_task_sched_in(prev, current);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
local_irq_enable();
#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
fire_sched_in_preempt_notifiers(current);
if (mm)
mmdrop(mm);
if (unlikely(prev_state == TASK_DEAD)) {
/*
* Remove function-return probe instances associated with this
* task and put them back on the free list.
*/
kprobe_flush_task(prev);
put_task_struct(prev);
}
可知如果prev是一个内核线程，那么运行队列rq->prev_mm字段存放了prev 的内存描述地址；mmdrop减少内存的引用计数；如果该技术为0，那么
该函数还要释放与页表相关的描述符、虚拟内存区，同时还要释放运行队列的自旋锁、并打开本地中断；如果prev是一个正在从系统删除的僵尸任务，就调用
put_task_struct 释放进程描述符引用计数；（见进程删除、、）
对于prepare_task_switch(rq, prev, next);
-------------->sched_info_switch（）
--------------------------->__sched_info_switch
static inline void
__sched_info_switch(struct task_struct *prev, struct task_struct *next)
{
struct rq *rq = task_rq(prev);
/*
* prev now departs the cpu. It's not interesting to record
* stats about how efficient we were at scheduling the idle
* process, however.
*/
if (prev != rq->idle)/*如果被切换出去的进程不是idle进程*/
sched_info_depart(prev);/*更新prev进程和他对应rq的相关变量*/
if (next != rq->idle)
sched_info_arrive(next);
}/*
* Called when a process ceases being the active-running process, either
* voluntarily or involuntarily. Now we can calculate how long we ran.
* Also, if the process is still in the TASK_RUNNING state, call
* sched_info_queued() to mark that it has now again started waiting on
* the runqueue.
*/
static inline void sched_info_depart(struct task_struct *t)
{
unsigned long long delta = task_rq(t)->clock -
t->sched_info.last_arrival; //更新runqueue中的task所得到的cpu执行累加时间
rq_sched_info_depart(task_rq(t), delta);
/*如果被切换出去进程的状态是运行状态
那么将进程sched_info.last_queued设置为rq的clock_last_queued为最后一次排队等待运行的时间*/
if (t->state == TASK_RUNNING)
sched_info_queued(t);
}
/*
* This function is only called from enqueue_task(), but also only updates
* 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(struct task_struct *t)
{
if (unlikely(sched_info_on()))
<span style="white-space:pre"> </span>if (!t->sched_info.last_queued)
<span style="white-space:pre"> </span>t->sched_info.last_queued = task_rq(t)->clock;
}
/*
* Called when a task finally hits the cpu. We can now calculate how
* 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(struct task_struct *t)
{
unsigned long long now = task_rq(t)->clock, delta = 0;
if (t->sched_info.last_queued)/*如果被切换进来前在运行进程中排队*/
delta = now - t->sched_info.last_queued;/*计算排队等待的时间长度*/
sched_info_reset_dequeued(t);/*因为进程将被切换进来运行，设定last_queued为0*/
t->sched_info.run_delay += delta;/*更新进程在运行队列里面等待的时间*/
t->sched_info.last_arrival = now;/*更新最后一次运行的时间*/
t->sched_info.pcount++;/*cpu上运行的次数加一*/
/*更新rq中rq_sched_info中的对应的变量*/
rq_sched_info_arrive(task_rq(t), delta);
}可见调度后并不是马上就运行。。。。
下图来自 http://www.cnblogs.com/tianchi/archive/2012/08/07/2626013.html
1367
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
