sched.c

中科院徐志伟老师一书《操作系统 原理·技术与编程》的源代码和习题接

		tsk = find_task_by_pid(pid);
	return tsk;
}

static int setscheduler(pid_t pid, int policy, 
			struct sched_param *param)
{
	struct sched_param lp;
	struct task_struct *p;
	int retval;

	retval = -EINVAL;
	if (!param || pid < 0)
		goto out_nounlock;

	retval = -EFAULT;
	if (copy_from_user(&lp, param, sizeof(struct sched_param)))
		goto out_nounlock;

	/*
	 * We play safe to avoid deadlocks.
	 */
	read_lock_irq(&tasklist_lock);
	spin_lock(&runqueue_lock);

	p = find_process_by_pid(pid);

	retval = -ESRCH;
	if (!p)
		goto out_unlock;
			
	if (policy < 0)
		policy = p->policy;
	else {
		retval = -EINVAL;
		if (policy != SCHED_FIFO && policy != SCHED_RR &&
				policy != SCHED_OTHER)
			goto out_unlock;
	}
	
	/*
	 * Valid priorities for SCHED_FIFO and SCHED_RR are 1..99, valid
	 * priority for SCHED_OTHER is 0.
	 */
	retval = -EINVAL;
	if (lp.sched_priority < 0 || lp.sched_priority > 99)
		goto out_unlock;
	if ((policy == SCHED_OTHER) != (lp.sched_priority == 0))
		goto out_unlock;

	retval = -EPERM;
	if ((policy == SCHED_FIFO || policy == SCHED_RR) && 
	    !capable(CAP_SYS_NICE))
		goto out_unlock;
	if ((current->euid != p->euid) && (current->euid != p->uid) &&
	    !capable(CAP_SYS_NICE))
		goto out_unlock;

	retval = 0;
	p->policy = policy;
	p->rt_priority = lp.sched_priority;
	if (task_on_runqueue(p))
		move_first_runqueue(p);

	current->need_resched = 1;

out_unlock:
	spin_unlock(&runqueue_lock);
	read_unlock_irq(&tasklist_lock);

out_nounlock:
	return retval;
}

asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, 
				      struct sched_param *param)
{
	return setscheduler(pid, policy, param);
}

asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param *param)
{
	return setscheduler(pid, -1, param);
}

asmlinkage long sys_sched_getscheduler(pid_t pid)
{
	struct task_struct *p;
	int retval;

	retval = -EINVAL;
	if (pid < 0)
		goto out_nounlock;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (p)
		retval = p->policy & ~SCHED_YIELD;
	read_unlock(&tasklist_lock);

out_nounlock:
	return retval;
}

asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param *param)
{
	struct task_struct *p;
	struct sched_param lp;
	int retval;

	retval = -EINVAL;
	if (!param || pid < 0)
		goto out_nounlock;

	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	retval = -ESRCH;
	if (!p)
		goto out_unlock;
	lp.sched_priority = p->rt_priority;
	read_unlock(&tasklist_lock);

	/*
	 * This one might sleep, we cannot do it with a spinlock held ...
	 */
	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;

out_nounlock:
	return retval;

out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

asmlinkage long sys_sched_yield(void)
{
	/*
	 * Trick. sched_yield() first counts the number of truly 
	 * 'pending' runnable processes, then returns if it's
	 * only the current processes. (This test does not have
	 * to be atomic.) In threaded applications this optimization
	 * gets triggered quite often.
	 */

	int nr_pending = nr_running;

#if CONFIG_SMP
	int i;

	// Subtract non-idle processes running on other CPUs.
	for (i = 0; i < smp_num_cpus; i++) {
		int cpu = cpu_logical_map(i);
		if (aligned_data[cpu].schedule_data.curr != idle_task(cpu))
			nr_pending--;
	}
#else
	// on UP this process is on the runqueue as well
	nr_pending--;
#endif
	if (nr_pending) {
		/*
		 * This process can only be rescheduled by us,
		 * so this is safe without any locking.
		 */
		if (current->policy == SCHED_OTHER)
			current->policy |= SCHED_YIELD;
		current->need_resched = 1;

		spin_lock_irq(&runqueue_lock);
		move_last_runqueue(current);
		spin_unlock_irq(&runqueue_lock);
	}
	return 0;
}

asmlinkage long sys_sched_get_priority_max(int policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 99;
		break;
	case SCHED_OTHER:
		ret = 0;
		break;
	}
	return ret;
}

asmlinkage long sys_sched_get_priority_min(int policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 1;
		break;
	case SCHED_OTHER:
		ret = 0;
	}
	return ret;
}

asmlinkage long sys_sched_rr_get_interval(pid_t pid, struct timespec *interval)
{
	struct timespec t;
	struct task_struct *p;
	int retval = -EINVAL;

	if (pid < 0)
		goto out_nounlock;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (p)
		jiffies_to_timespec(p->policy & SCHED_FIFO ? 0 : NICE_TO_TICKS(p->nice),
				    &t);
	read_unlock(&tasklist_lock);
	if (p)
		retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
out_nounlock:
	return retval;
}

static void show_task(struct task_struct * p)
{
	unsigned long free = 0;
	int state;
	static const char * stat_nam[] = { "R", "S", "D", "Z", "T", "W" };

	printk("%-13.13s ", p->comm);
	state = p->state ? ffz(~p->state) + 1 : 0;
	if (((unsigned) state) < sizeof(stat_nam)/sizeof(char *))
		printk(stat_nam[state]);
	else
		printk(" ");
#if (BITS_PER_LONG == 32)
	if (p == current)
		printk(" current  ");
	else
		printk(" %08lX ", thread_saved_pc(&p->thread));
#else
	if (p == current)
		printk("   current task   ");
	else
		printk(" %016lx ", thread_saved_pc(&p->thread));
#endif
	{
		unsigned long * n = (unsigned long *) (p+1);
		while (!*n)
			n++;
		free = (unsigned long) n - (unsigned long)(p+1);
	}
	printk("%5lu %5d %6d ", free, p->pid, p->p_pptr->pid);
	if (p->p_cptr)
		printk("%5d ", p->p_cptr->pid);
	else
		printk("      ");
	if (p->p_ysptr)
		printk("%7d", p->p_ysptr->pid);
	else
		printk("       ");
	if (p->p_osptr)
		printk(" %5d", p->p_osptr->pid);
	else
		printk("      ");
	if (!p->mm)
		printk(" (L-TLB)\n");
	else
		printk(" (NOTLB)\n");

	{
		extern void show_trace_task(struct task_struct *tsk);
		show_trace_task(p);
	}
}

char * render_sigset_t(sigset_t *set, char *buffer)
{
	int i = _NSIG, x;
	do {
		i -= 4, x = 0;
		if (sigismember(set, i+1)) x |= 1;
		if (sigismember(set, i+2)) x |= 2;
		if (sigismember(set, i+3)) x |= 4;
		if (sigismember(set, i+4)) x |= 8;
		*buffer++ = (x < 10 ? '0' : 'a' - 10) + x;
	} while (i >= 4);
	*buffer = 0;
	return buffer;
}

void show_state(void)
{
	struct task_struct *p;

#if (BITS_PER_LONG == 32)
	printk("\n"
	       "                         free                        sibling\n");
	printk("  task             PC    stack   pid father child younger older\n");
#else
	printk("\n"
	       "                                 free                        sibling\n");
	printk("  task                 PC        stack   pid father child younger older\n");
#endif
	read_lock(&tasklist_lock);
	for_each_task(p) {
		/*
		 * reset the NMI-timeout, listing all files on a slow
		 * console might take alot of time:
		 */
		touch_nmi_watchdog();
		show_task(p);
	}
	read_unlock(&tasklist_lock);
}

/**
 * reparent_to_init() - Reparent the calling kernel thread to the init task.
 *
 * If a kernel thread is launched as a result of a system call, or if
 * it ever exits, it should generally reparent itself to init so that
 * it is correctly cleaned up on exit.
 *
 * The various task state such as scheduling policy and priority may have
 * been inherited fro a user process, so we reset them to sane values here.
 *
 * NOTE that reparent_to_init() gives the caller full capabilities.
 */
void reparent_to_init(void)
{
	struct task_struct *this_task = current;

	write_lock_irq(&tasklist_lock);

	/* Reparent to init */
	REMOVE_LINKS(this_task);
	this_task->p_pptr = child_reaper;
	this_task->p_opptr = child_reaper;
	SET_LINKS(this_task);

	/* Set the exit signal to SIGCHLD so we signal init on exit */
	this_task->exit_signal = SIGCHLD;

	/* We also take the runqueue_lock while altering task fields
	 * which affect scheduling decisions */
	spin_lock(&runqueue_lock);

	this_task->ptrace = 0;
	this_task->nice = DEF_NICE;
	this_task->policy = SCHED_OTHER;
	/* cpus_allowed? */
	/* rt_priority? */
	/* signals? */
	this_task->cap_effective = CAP_INIT_EFF_SET;
	this_task->cap_inheritable = CAP_INIT_INH_SET;
	this_task->cap_permitted = CAP_FULL_SET;
	this_task->keep_capabilities = 0;
	memcpy(this_task->rlim, init_task.rlim, sizeof(*(this_task->rlim)));
	this_task->user = INIT_USER;

	spin_unlock(&runqueue_lock);
	write_unlock_irq(&tasklist_lock);
}

/*
 *	Put all the gunge required to become a kernel thread without
 *	attached user resources in one place where it belongs.
 */

void daemonize(void)
{
	struct fs_struct *fs;


	/*
	 * If we were started as result of loading a module, close all of the
	 * user space pages.  We don't need them, and if we didn't close them
	 * they would be locked into memory.
	 */
	exit_mm(current);

	current->session = 1;
	current->pgrp = 1;
	current->tty = NULL;

	/* Become as one with the init task */

	exit_fs(current);	/* current->fs->count--; */
	fs = init_task.fs;
	current->fs = fs;
	atomic_inc(&fs->count);
 	exit_files(current);
	current->files = init_task.files;
	atomic_inc(&current->files->count);
}

extern unsigned long wait_init_idle;

void __init init_idle(void)
{
	struct schedule_data * sched_data;
	sched_data = &aligned_data[smp_processor_id()].schedule_data;

	if (current != &init_task && task_on_runqueue(current)) {
		printk("UGH! (%d:%d) was on the runqueue, removing.\n",
			smp_processor_id(), current->pid);
		del_from_runqueue(current);
	}
	sched_data->curr = current;
	sched_data->last_schedule = get_cycles();
	clear_bit(current->processor, &wait_init_idle);
}

extern void init_timervecs (void);

void __init sched_init(void)
{
	/*
	 * We have to do a little magic to get the first
	 * process right in SMP mode.
	 */
	int cpu = smp_processor_id();
	int nr;

	init_task.processor = cpu;

	for(nr = 0; nr < PIDHASH_SZ; nr++)
		pidhash[nr] = NULL;

	init_timervecs();

	init_bh(TIMER_BH, timer_bh);
	init_bh(TQUEUE_BH, tqueue_bh);
	init_bh(IMMEDIATE_BH, immediate_bh);

	/*
	 * The boot idle thread does lazy MMU switching as well:
	 */
	atomic_inc(&init_mm.mm_count);
	enter_lazy_tlb(&init_mm, current, cpu);
}