sched.c

Linux 1.0 内核C源代码 Linux最早版本代码 由Linus Torvalds亲自书写的

/*
 *  linux/kernel/sched.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

/*
 * '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 <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/kernel.h>
#include <linux/kernel_stat.h>
#include <linux/sys.h>
#include <linux/fdreg.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/ptrace.h>
#include <linux/segment.h>
#include <linux/delay.h>
#include <linux/interrupt.h>

#include <asm/system.h>
#include <asm/io.h>
#include <asm/segment.h>

#define TIMER_IRQ 0

#include <linux/timex.h>

/*
 * kernel variables
 */
long tick = 1000000 / HZ;               /* timer interrupt period */
volatile struct timeval xtime;		/* The current time */
int tickadj = 500/HZ;			/* microsecs */

/*
 * phase-lock loop variables
 */
int time_status = TIME_BAD;     /* clock synchronization status */
long time_offset = 0;           /* time adjustment (us) */
long time_constant = 0;         /* pll time constant */
long time_tolerance = MAXFREQ;  /* frequency tolerance (ppm) */
long time_precision = 1; 	/* clock precision (us) */
long time_maxerror = 0x70000000;/* maximum error */
long time_esterror = 0x70000000;/* estimated error */
long time_phase = 0;            /* phase offset (scaled us) */
long time_freq = 0;             /* frequency offset (scaled ppm) */
long time_adj = 0;              /* tick adjust (scaled 1 / HZ) */
long time_reftime = 0;          /* time at last adjustment (s) */

long time_adjust = 0;
long time_adjust_step = 0;

int need_resched = 0;

/*
 * Tell us the machine setup..
 */
int hard_math = 0;		/* set by boot/head.S */
int x86 = 0;			/* set by boot/head.S to 3 or 4 */
int ignore_irq13 = 0;		/* set if exception 16 works */
int wp_works_ok = 0;		/* set if paging hardware honours WP */ 

/*
 * Bus types ..
 */
int EISA_bus = 0;

extern int _setitimer(int, struct itimerval *, struct itimerval *);
unsigned long * prof_buffer = NULL;
unsigned long prof_len = 0;

#define _S(nr) (1<<((nr)-1))

extern void mem_use(void);

extern int timer_interrupt(void);
asmlinkage int system_call(void);

static unsigned long init_kernel_stack[1024];
struct task_struct init_task = INIT_TASK;

unsigned long volatile jiffies=0;

struct task_struct *current = &init_task;
struct task_struct *last_task_used_math = NULL;

struct task_struct * task[NR_TASKS] = {&init_task, };

long user_stack [ PAGE_SIZE>>2 ] ;

struct {
	long * a;
	short b;
	} stack_start = { & user_stack [PAGE_SIZE>>2] , KERNEL_DS };

struct kernel_stat kstat =
	{ 0, 0, 0, { 0, 0, 0, 0 }, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };

/*
 * int 0x80 entry points.. Moved away from the header file, as
 * iBCS2 may also want to use the '<linux/sys.h>' headers..
 */
#ifdef __cplusplus
extern "C" {
#endif

int sys_ni_syscall(void)
{
	return -EINVAL;
}

fn_ptr sys_call_table[] = { sys_setup, sys_exit, sys_fork, sys_read,
sys_write, sys_open, sys_close, sys_waitpid, sys_creat, sys_link,
sys_unlink, sys_execve, sys_chdir, sys_time, sys_mknod, sys_chmod,
sys_chown, sys_break, sys_stat, sys_lseek, sys_getpid, sys_mount,
sys_umount, sys_setuid, sys_getuid, sys_stime, sys_ptrace, sys_alarm,
sys_fstat, sys_pause, sys_utime, sys_stty, sys_gtty, sys_access,
sys_nice, sys_ftime, sys_sync, sys_kill, sys_rename, sys_mkdir,
sys_rmdir, sys_dup, sys_pipe, sys_times, sys_prof, sys_brk, sys_setgid,
sys_getgid, sys_signal, sys_geteuid, sys_getegid, sys_acct, sys_phys,
sys_lock, sys_ioctl, sys_fcntl, sys_mpx, sys_setpgid, sys_ulimit,
sys_olduname, sys_umask, sys_chroot, sys_ustat, sys_dup2, sys_getppid,
sys_getpgrp, sys_setsid, sys_sigaction, sys_sgetmask, sys_ssetmask,
sys_setreuid,sys_setregid, sys_sigsuspend, sys_sigpending,
sys_sethostname, sys_setrlimit, sys_getrlimit, sys_getrusage,
sys_gettimeofday, sys_settimeofday, sys_getgroups, sys_setgroups,
sys_select, sys_symlink, sys_lstat, sys_readlink, sys_uselib,
sys_swapon, sys_reboot, sys_readdir, sys_mmap, sys_munmap, sys_truncate,
sys_ftruncate, sys_fchmod, sys_fchown, sys_getpriority, sys_setpriority,
sys_profil, sys_statfs, sys_fstatfs, sys_ioperm, sys_socketcall,
sys_syslog, sys_setitimer, sys_getitimer, sys_newstat, sys_newlstat,
sys_newfstat, sys_uname, sys_iopl, sys_vhangup, sys_idle, sys_vm86,
sys_wait4, sys_swapoff, sys_sysinfo, sys_ipc, sys_fsync, sys_sigreturn,
sys_clone, sys_setdomainname, sys_newuname, sys_modify_ldt,
sys_adjtimex, sys_mprotect, sys_sigprocmask, sys_create_module,
sys_init_module, sys_delete_module, sys_get_kernel_syms, sys_quotactl,
sys_getpgid, sys_fchdir, sys_bdflush };

/* So we don't have to do any more manual updating.... */
int NR_syscalls = sizeof(sys_call_table)/sizeof(fn_ptr);

#ifdef __cplusplus
}
#endif

/*
 *  'math_state_restore()' saves the current math information in the
 * old math state array, and gets the new ones from the current task
 *
 * Careful.. There are problems with IBM-designed IRQ13 behaviour.
 * Don't touch unless you *really* know how it works.
 */
asmlinkage void math_state_restore(void)
{
	__asm__ __volatile__("clts");
	if (last_task_used_math == current)
		return;
	timer_table[COPRO_TIMER].expires = jiffies+50;
	timer_active |= 1<<COPRO_TIMER;	
	if (last_task_used_math)
		__asm__("fnsave %0":"=m" (last_task_used_math->tss.i387));
	else
		__asm__("fnclex");
	last_task_used_math = current;
	if (current->used_math) {
		__asm__("frstor %0": :"m" (current->tss.i387));
	} else {
		__asm__("fninit");
		current->used_math=1;
	}
	timer_active &= ~(1<<COPRO_TIMER);
}

#ifndef CONFIG_MATH_EMULATION

asmlinkage void math_emulate(long arg)
{
  printk("math-emulation not enabled and no coprocessor found.\n");
  printk("killing %s.\n",current->comm);
  send_sig(SIGFPE,current,1);
  schedule();
}

#endif /* CONFIG_MATH_EMULATION */

unsigned long itimer_ticks = 0;
unsigned long itimer_next = ~0;
static unsigned long lost_ticks = 0;

/*
 *  'schedule()' is the scheduler function. It's a very simple and nice
 * scheduler: it's not perfect, but certainly works for most things.
 * 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.
 *
 * The "confuse_gcc" goto is used only to get better assembly code..
 * Djikstra probably hates me.
 */
asmlinkage void schedule(void)
{
	int c;
	struct task_struct * p;
	struct task_struct * next;
	unsigned long ticks;

/* check alarm, wake up any interruptible tasks that have got a signal */

	cli();
	ticks = itimer_ticks;
	itimer_ticks = 0;
	itimer_next = ~0;
	sti();
	need_resched = 0;
	p = &init_task;
	for (;;) {
		if ((p = p->next_task) == &init_task)
			goto confuse_gcc1;
		if (ticks && p->it_real_value) {
			if (p->it_real_value <= ticks) {
				send_sig(SIGALRM, p, 1);
				if (!p->it_real_incr) {
					p->it_real_value = 0;
					goto end_itimer;
				}
				do {
					p->it_real_value += p->it_real_incr;
				} while (p->it_real_value <= ticks);
			}
			p->it_real_value -= ticks;
			if (p->it_real_value < itimer_next)
				itimer_next = p->it_real_value;
		}
end_itimer:
		if (p->state != TASK_INTERRUPTIBLE)
			continue;
		if (p->signal & ~p->blocked) {
			p->state = TASK_RUNNING;
			continue;
		}
		if (p->timeout && p->timeout <= jiffies) {
			p->timeout = 0;
			p->state = TASK_RUNNING;
		}
	}
confuse_gcc1:

/* this is the scheduler proper: */
#if 0
	/* give processes that go to sleep a bit higher priority.. */
	/* This depends on the values for TASK_XXX */
	/* This gives smoother scheduling for some things, but */
	/* can be very unfair under some circumstances, so.. */
 	if (TASK_UNINTERRUPTIBLE >= (unsigned) current->state &&
	    current->counter < current->priority*2) {
		++current->counter;
	}
#endif
	c = -1;
	next = p = &init_task;
	for (;;) {
		if ((p = p->next_task) == &init_task)
			goto confuse_gcc2;
		if (p->state == TASK_RUNNING && p->counter > c)
			c = p->counter, next = p;
	}
confuse_gcc2:
	if (!c) {
		for_each_task(p)
			p->counter = (p->counter >> 1) + p->priority;
	}
	if(current != next)
		kstat.context_swtch++;
	switch_to(next);
	/* Now maybe reload the debug registers */
	if(current->debugreg[7]){
		loaddebug(0);
		loaddebug(1);
		loaddebug(2);
		loaddebug(3);
		loaddebug(6);
	};
}

asmlinkage int sys_pause(void)
{
	current->state = TASK_INTERRUPTIBLE;
	schedule();
	return -ERESTARTNOHAND;
}

/*
 * wake_up doesn't wake up stopped processes - they have to be awakened
 * with signals or similar.
 *
 * Note that this doesn't need cli-sti pairs: interrupts may not change
 * the wait-queue structures directly, but only call wake_up() to wake
 * a process. The process itself must remove the queue once it has woken.
 */
void wake_up(struct wait_queue **q)
{
	struct wait_queue *tmp;
	struct task_struct * p;

	if (!q || !(tmp = *q))
		return;
	do {
		if ((p = tmp->task) != NULL) {
			if ((p->state == TASK_UNINTERRUPTIBLE) ||
			    (p->state == TASK_INTERRUPTIBLE)) {
				p->state = TASK_RUNNING;
				if (p->counter > current->counter)
					need_resched = 1;
			}
		}
		if (!tmp->next) {
			printk("wait_queue is bad (eip = %08lx)\n",((unsigned long *) q)[-1]);
			printk("        q = %p\n",q);
			printk("       *q = %p\n",*q);
			printk("      tmp = %p\n",tmp);
			break;
		}
		tmp = tmp->next;
	} while (tmp != *q);
}

void wake_up_interruptible(struct wait_queue **q)
{
	struct wait_queue *tmp;
	struct task_struct * p;

	if (!q || !(tmp = *q))
		return;
	do {
		if ((p = tmp->task) != NULL) {
			if (p->state == TASK_INTERRUPTIBLE) {
				p->state = TASK_RUNNING;
				if (p->counter > current->counter)
					need_resched = 1;
			}
		}
		if (!tmp->next) {
			printk("wait_queue is bad (eip = %08lx)\n",((unsigned long *) q)[-1]);
			printk("        q = %p\n",q);
			printk("       *q = %p\n",*q);
			printk("      tmp = %p\n",tmp);
			break;
		}
		tmp = tmp->next;
	} while (tmp != *q);
}

void __down(struct semaphore * sem)
{
	struct wait_queue wait = { current, NULL };
	add_wait_queue(&sem->wait, &wait);
	current->state = TASK_UNINTERRUPTIBLE;
	while (sem->count <= 0) {
		schedule();
		current->state = TASK_UNINTERRUPTIBLE;
	}
	current->state = TASK_RUNNING;
	remove_wait_queue(&sem->wait, &wait);
}

static inline void __sleep_on(struct wait_queue **p, int state)
{
	unsigned long flags;
	struct wait_queue wait = { current, NULL };

	if (!p)
		return;
	if (current == task[0])
		panic("task[0] trying to sleep");
	current->state = state;
	add_wait_queue(p, &wait);
	save_flags(flags);
	sti();
	schedule();
	remove_wait_queue(p, &wait);
	restore_flags(flags);
}

void interruptible_sleep_on(struct wait_queue **p)
{
	__sleep_on(p,TASK_INTERRUPTIBLE);
}

void sleep_on(struct wait_queue **p)
{
	__sleep_on(p,TASK_UNINTERRUPTIBLE);
}

static struct timer_list * next_timer = NULL;

void add_timer(struct timer_list * timer)
{
	unsigned long flags;
	struct timer_list ** p;

	if (!timer)
		return;
	timer->next = NULL;
	p = &next_timer;
	save_flags(flags);
	cli();
	while (*p) {
		if ((*p)->expires > timer->expires) {
			(*p)->expires -= timer->expires;
			timer->next = *p;