Linux内核源代码情形分析-nanosleep()和pause()
Linux内核源代码情景分析-nanosleep()和pause()
我们介绍nanosleep()和pause()两个系统调用。
系统调用nanosleep()在内核中的实现为sys_nanosleep()，代码如下：
asmlinkage long sys_nanosleep(struct timespec *rqtp, struct timespec *rmtp)//第一个指针rqtp指向给定所需睡眠时间的数据结构；第二个指针rmtp，指向返回剩余时间的数据结构
{
struct timespec t;
unsigned long expire;
if(copy_from_user(&t, rqtp, sizeof(struct timespec)))//所需睡眠时间从用户空间复制到内核空间
return -EFAULT;
if (t.tv_nsec >= 1000000000L || t.tv_nsec < 0 || t.tv_sec < 0)
return -EINVAL;
if (t.tv_sec == 0 && t.tv_nsec <= 2000000L &&
current->policy != SCHED_OTHER)//由于时钟中断只能达到10毫秒的精度，如果要求睡眠的时间小于2毫秒，而要求睡眠的进程又是个实时要求的进程，那就不能真的让这个进程进入睡眠，因为那样有可能10毫秒以后才能将其唤醒，对于实时进程来说是不能接受的
{
/*
* Short delay requests up to 2 ms will be handled with
* high precision by a busy wait for all real-time processes.
*
* Its important on SMP not to do this holding locks.
*/
udelay((t.tv_nsec + 999) / 1000);//延迟两秒
return 0;
}
expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);//将数据结构t中的数值换算成时钟中断的次数
current->state = TASK_INTERRUPTIBLE;//将当期进程的状态设置为TASK_INTERRUPTIBLE
expire = schedule_timeout(expire);//让当期进程睡眠给定的时间；返回剩余的时钟中断次数，如果没有，返回0
if (expire) {
if (rmtp) {
jiffies_to_timespec(expire, &t);//剩余的时钟中断次数转换成数据结构t的数值
if (copy_to_user(rmtp, &t, sizeof(struct timespec)))//剩余时间从内核空间复制到用户空间
return -EFAULT;
}
return -EINTR;
}
return 0;
}
schedule_timeout，让当期进程睡眠给定的时间，代码如下：
signed long schedule_timeout(signed long timeout)
{
struct timer_list timer;
unsigned long expire;
switch (timeout)
{
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();//无限期等待
goto out;
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.
*/
if (timeout < 0)
{
printk(KERN_ERR "schedule_timeout: wrong timeout "
"value %lx from %p\n", timeout,
__builtin_return_address(0));
current->state = TASK_RUNNING;
goto out;
}
}
expire = timeout + jiffies;//timeout是把需要睡眠的时间先换算成时钟中断的次数，把这个次数与当前的jiffies相加就得到了"到点"的时间
init_timer(&timer);
timer.expires = expire;//初始化数据结构timer
timer.data = (unsigned long) current;
timer.function = process_timeout;
add_timer(&timer);//将timer挂入定时器队列
schedule();
del_timer_sync(&timer);
timeout = expire - jiffies;//剩余的时钟中断次数
out:
return timeout < 0 ? 0 : timeout;
}
struct timer_list {
struct list_head list;
unsigned long expires;
unsigned long data;
void (*function)(unsigned long);
};
void add_timer(struct timer_list *timer)
{
unsigned long flags;
spin_lock_irqsave(&timerlist_lock, flags);
if (timer_pending(timer))
goto bug;
internal_add_timer(timer);
spin_unlock_irqrestore(&timerlist_lock, flags);
return;
bug:
spin_unlock_irqrestore(&timerlist_lock, flags);
printk("bug: kernel timer added twice at %p.\n",
__builtin_return_address(0));
}
static inline void internal_add_timer(struct timer_list *timer)
{
/*
* must be cli-ed when calling this
*/
unsigned long expires = timer->expires;
unsigned long idx = expires - timer_jiffies;//期望时间点于当前时间点之差，就是中间要经过的中断次数，为32位
struct list_head * vec;
if (idx < TVR_SIZE) {
int i = expires & TVR_MASK;
vec = tv1.vec + i;
} else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
int i = (expires >> TVR_BITS) & TVN_MASK;//第一个expires为256，i为1
vec = tv2.vec + i;//所以tv2.vec[0]为空
} else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
vec = tv3.vec + i;
} else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
vec = tv4.vec + i;
} else if ((signed long) idx < 0) {
/* can happen if you add a timer with expires == jiffies,
* or you set a timer to go off in the past
*/
vec = tv1.vec + tv1.index;
} else if (idx <= 0xffffffffUL) {
int i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
vec = tv5.vec + i;
} else {
/* Can only get here on architectures with 64-bit jiffies */
INIT_LIST_HEAD(&timer->list);
return;
}
/*
* Timers are FIFO!
*/
list_add(&timer->list, vec->prev);
}
#define TVN_BITS 6
#define TVR_BITS 8
#define TVN_SIZE (1 << TVN_BITS)
#define TVR_SIZE (1 << TVR_BITS)
#define TVN_MASK (TVN_SIZE - 1)
#define TVR_MASK (TVR_SIZE - 1)
struct timer_vec {
int index;
struct list_head vec[TVN_SIZE];
};
struct timer_vec_root {
int index;
struct list_head vec[TVR_SIZE];
};
static struct timer_vec tv5;
static struct timer_vec tv4;
static struct timer_vec tv3;
static struct timer_vec tv2;
static struct timer_vec_root tv1;
static struct timer_vec * const tvecs[] = {
(struct timer_vec *)&tv1, &tv2, &tv3, &tv4, &tv5
}; 数据结构tv1、tv2、...、tv5每个都包含了一个timer_list指针数组，这就是所谓杂凑表，表中的每个指针都指向一个定时器队列。其中tv1与其它几个数据结构的不同仅在于数组的大小，tv1的数组大小是2 ^ 8，而其它几个的大小都是2 ^ 6。这样队列中的数量是2 ^ 8 + 4 * (2 ^ 6) = 512个。idx为32位，如下图：
如果idx小于2 ^ 8，以8位为下标链入数据结构tv1的vec[2 ^ 8]。
如果idx大于2 ^ 8小于2 ^ 14，也就是idx为14位；以14位中前6位为下标链入数据结构tv1的vec[2 ^ 6]，也就是说一个队列中最多会有256个定时器；因为相同的前6位，不同的后8位，一共有256种组合，都会链入一个队列(以前6位为下标)。
以此类推......
在Linux内核源代码情景分析-中断下半部(软中断)，最后时钟中断处理程序的下半部，执行timer_bh，代码如下：
void timer_bh(void)
{
update_times();
run_timer_list();
}
static inline void run_timer_list(void)
{
spin_lock_irq(&timerlist_lock);
while ((long)(jiffies - timer_jiffies) >= 0) {
struct list_head *head, *curr;
if (!tv1.index) {//当tv1.index为0，根据tv2.index的指引将tv2中的一个队列搬运到tv1中
int n = 1;
do {
cascade_timers(tvecs[n]);
} while (tvecs[n]->index == 1 && ++n < NOOF_TVECS);//当tv2.index为1，根据tv3.index的指引将tv2中的一个队列搬运到tv2中
}
repeat:
head = tv1.vec + tv1.index;//index共256个
curr = head->next;
if (curr != head) {//tv1的队列
struct timer_list *timer;
void (*fn)(unsigned long);
unsigned long data;
timer = list_entry(curr, struct timer_list, list);
fn = timer->function;
data= timer->data;
detach_timer(timer);//把定时器从队里中删除
timer->list.next = timer->list.prev = NULL;
timer_enter(timer);
spin_unlock_irq(&timerlist_lock);
fn(data);//process_timeout(current)
spin_lock_irq(&timerlist_lock);
timer_exit();
goto repeat;
}
++timer_jiffies;
tv1.index = (tv1.index + 1) & TVR_MASK;
}
spin_unlock_irq(&timerlist_lock);
}
static inline void cascade_timers(struct timer_vec *tv)
{
/* cascade all the timers from tv up one level */
struct list_head *head, *curr, *next;
head = tv->vec + tv->index;
curr = head->next;
/*
* We are removing _all_ timers from the list, so we don't have to
* detach them individually, just clear the list afterwards.
*/
while (curr != head) {
struct timer_list *tmp;
tmp = list_entry(curr, struct timer_list, list);
next = curr->next;
list_del(curr); // not needed
internal_add_timer(tmp);//链入到下一级的队列
curr = next;
}
INIT_LIST_HEAD(head);
tv->index = (tv->index + 1) & TVN_MASK;
} tv1一共有256个队列，每个队列只链入了一个定时器。把它们都执行完后，也就是tv1.index再次为0，就把tv2->vec + tv2->index这个队列这个队列的定时器，放入tv1的256个队列。我们说过tv2队列中的定时器最多是256个，所以正好链入tv1的256个队列。当tv2.index再次为1(tv2->vec + 0这个队列为空)，就把tv3->vec + tv3->index这个队列的定时器，放入tv2的128个队列。依次类推。每个被唤醒的定时器都会执行fn(data);//process_timeout(current)，代码如下：
static void process_timeout(unsigned long __data)
{
struct task_struct * p = (struct task_struct *) __data;
wake_up_process(p);
} 被唤醒后，这个进程再次被调度执行(我们不关心在什么情况下，调度到这个进程)，进程继续运行，返回schedule_timeout，又执行了一次del_timer_sync，这是因为该进程有可能被其他进程通过信号唤醒，且这个进程再次被调度执行。此事由于没有在run_timer_list执行detach_timer，所以这里补上一次。最后返回睡眠剩余的时间。pause的系统调用是，sys_pause，代码如下：
asmlinkage int sys_pause(void)
{
current->state = TASK_INTERRUPTIBLE;
schedule();
return -ERESTARTNOHAND;
} 和sys_nanosleep的区别是只有在接受到信号时才会被唤醒，不会定时被唤醒。 TASK_INTERRUPTIBLE和TASK_UNINTERRUPTIBLE最大的区别是是否在接受到信号，可以被唤醒。