进程.txt

讲解linux内核 进程调度 部分经典讲义

                }
                sem->sleepers = 1;        /* us - see -1 above */
                spin_unlock_irq(&semaphore_lock);
                // 当semaphore被up()唤醒时,schedule()返回
                schedule();
                // 虽然已线程被up恢复,但为防止碰巧又有一个线程获得了semaphore,
                // 因此将它们放在循环体中
                tsk->state = TASK_UNINTERRUPTIBLE;
                spin_lock_irq(&semaphore_lock);
        }
        spin_unlock_irq(&semaphore_lock);
        // 该进程获得了semaphore,将它从等待队列中删除
        remove_wait_queue(&sem->wait, &wait);
        tsk->state = TASK_RUNNING;
        // 为什么这里要调用wake_up,是因为调用它没有副作用从而防止潜在的死锁吗?
        wake_up(&sem->wait);
}
void __up(struct semaphore *sem)
{
扩展为
__wake_up_common(&sem->wait,TASK_UNINTERRUPTIBLE|TASK_INTERRUPTIBLE,1,0);
唤醒队列中第1个进程,即将第1个进程放入运行队列
        wake_up(&sem->wait);
}
; sched.c
static inline void __wake_up_common (wait_queue_head_t *q, unsigned int
mode,
                                     int nr_exclusive, const int sync)
{
        struct list_head *tmp, *head;
        struct task_struct *p;
        unsigned long flags;
        if (!q)
                goto out;
        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;
        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;
                if (state & mode) {
#if WAITQUEUE_DEBUG
                        curr->__waker = (long)__builtin_return_address(0);
#endif
                        if (sync)
                                wake_up_process_synchronous(p);
                        else
                                wake_up_process(p);
                        if ((curr->flags & WQ_FLAG_EXCLUSIVE) && 
!--nr_exclusive)
                                break;
                }
        }
        wq_write_unlock_irqrestore(&q->lock, flags);
out:
        return;
}
; sched.c
inline void wake_up_process(struct task_struct * p)
{
        unsigned long flags;
        /*
        * We want the common case fall through straight, thus the goto.
        */
        spin_lock_irqsave(&runqueue_lock, flags);
        p->state = TASK_RUNNING;
        if (task_on_runqueue(p))
                goto out;
        add_to_runqueue(p);
        reschedule_idle(p);
out:
        spin_unlock_irqrestore(&runqueue_lock, flags);
}
; sched.c
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.
        */
        spin_lock_irqsave(&runqueue_lock, flags);
        p->state = TASK_RUNNING;
        if (task_on_runqueue(p))
                goto out;
        add_to_runqueue(p);
out:
        spin_unlock_irqrestore(&runqueue_lock, flags);
}
; sched.h
static inline int task_on_runqueue(struct task_struct *p)
{
        return (p->run_list.next != NULL);
}
; sched.c
static inline void add_to_runqueue(struct task_struct * p)
{
        list_add(&p->run_list, &runqueue_head);
        nr_running++;
}
static LIST_HEAD(runqueue_head);
; fork.c
void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *
wait)
{
        unsigned long flags;
        wq_write_lock_irqsave(&q->lock, flags);
        wait->flags = WQ_FLAG_EXCLUSIVE;
        __add_wait_queue_tail(q, wait);
        wq_write_unlock_irqrestore(&q->lock, flags);
}
; wait.h
static inline void __add_wait_queue_tail(wait_queue_head_t *head,
                                                wait_queue_t *new)
{
#if WAITQUEUE_DEBUG
        if (!head || !new)
                WQ_BUG();
        CHECK_MAGIC_WQHEAD(head);
        CHECK_MAGIC(new->__magic);
        if (!head->task_list.next || !head->task_list.prev)
                WQ_BUG();
#endif
        list_add_tail(&new->task_list, &head->task_list);
}
正执行调度的函数是schedule(void),它选择一个最合适的进程执行，并且真正进行上下文切换，
使得选中的进程得以执行。而reschedule_idle(struct task_struct *p)的作用是为进程选择
一个合适的CPU来执行，如果它选中了某个CPU，则将该CPU上当前运行进程的need_resched标志
置为1,然后向它发出一个重新调度的处理机间中断，使得选中的CPU能够在中断处理返回时执行
schedule函数，真正调度进程p在CPU上执行。在schedule()和reschedule_idle()中调用了goodness()
函数。goodness()函数用来衡量一个处于可运行状态的进程值得运行的程度。此外，在schedule()
函数中还调用了schedule_tail()函数;在reschedule_idle()函数中还调用了reschedule_idle_slow()。


[目录]




sched.c

|schedule
   |do_softirq // manages post-IRQ work
   |for each task
      |calculate counter
   |prepare_to__switch // does anything
   |switch_mm // change Memory context (change CR3 value)
   |switch_to (assembler)
      |SAVE ESP
      |RESTORE future_ESP
      |SAVE EIP
      |push future_EIP *** push parameter as we did a call
         |jmp __switch_to (it does some TSS work)
         |__switch_to()
          ..
         |ret *** ret from call using future_EIP in place of call address
      new_task

/*
* '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 extracts a field from
* current-task
*/
#include
#include
#include
#include
#include
#include
#include
#define LATCH (1193180/HZ)
extern void mem_use(void);
extern int timer_interrupt(void);
extern int system_call(void);
union task_union {
struct task_struct task;
char stack[PAGE_SIZE];
};
static union task_union init_task = {INIT_TASK,};
long volatile jiffies=0;
long startup_time=0;
struct task_struct *current = &(init_task.task), *last_task_used_math =
NULL;
struct task_struct * task[NR_TASKS] = {&(init_task.task), };
long user_stack [ PAGE_SIZE>>2 ] ;
struct {
long * a;
short b;
} stack_start = { & user_stack [PAGE_SIZE>>2] , 0x10 };
/*
* 'math_state_restore()' saves the current math information in the
* old math state array, and gets the new ones from the current task
*/
void math_state_restore() @@协处理器状态保存
{
if (last_task_used_math)
__asm__("fnsave %0"::"m" (last_task_used_math->tss.i387));
if (current->used_math)
__asm__("frstor %0"::"m" (current->tss.i387));
else {
__asm__("fninit"::);
current->used_math=1;
}
last_task_used_math=current;
}
/*
* 'schedule()' is the scheduler function. This is GOOD CODE! There
* probably won't be any reason to change this, as it should work well
* in all circumstances (ie gives IO-bound processes good response etc).
* The one thing you might take a look at is the signal-handler code
here.
*
* 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.
*/
void schedule(void)
{
int i,next,c;
struct task_struct ** p;
/* check alarm, wake up any interruptible tasks that have got a signal
*/
for(p = &LAST_TASK ; p > &FIRST_TASK ; --p)
if (*p) {
if ((*p)->alarm && (*p)->alarm < jiffies) {
@@??
(*p)->signal |= (1<<(SIGALRM-1));@@14-1
(*p)->alarm = 0;
}
if ((*p)->signal && (*p)->state==TASK_INTERRUPTIBLE)
(*p)->state=TASK_RUNNING;
}
@@ task 1 如何变为TASK_RUNNING??signal 如何得到,alarm如何变非0且 /* this is the
scheduler proper: */
@@操作系统最重要的函数，调度算法
@@这个循环要找到一个可运行的任务才能退出,会死在这吗?即如没有一个可运行
while (1) {
c = -1;
next = 0;
i = NR_TASKS;
p = &task[NR_TASKS];
while (--i) {
if (!*--p)