init/main.c: process 0 -> process 1

extand fork()

int fork(void)
{
long __res;
__asm__ volatile ("int $0x80"
   : "=a" (__res)
   : "0" (__NR_ fork)) ;
if (__res >= 0)
   return (int) __res;
errno = -__res;
return -1;
}

include-asm-system.h

#define move_to_user_mode() \
__asm__ ("movl %%esp,%%eax\n\t" \
  "pushl $0x17\n\t" \
	"pushl %%eax\n\t" \
	"pushfl\n\t" \
	"pushl $0x0f\n\t" \
	"pushl $1f\n\t" \
	"iret\n" \
	"1:\tmovl $0x17,%%eax\n\t" \
	"movw %%ax,%%ds\n\t" \
	"movw %%ax,%%es\n\t" \
	"movw %%ax,%%fs\n\t" \
	"movw %%ax,%%gs" \
	:::"ax")

#define sti() __asm__ ("sti"::)
#define cli() __asm__ ("cli"::)
#define nop() __asm__ ("nop"::)

#define iret() __asm__ ("iret"::)

#define _set_gate(gate_addr,type,dpl,addr) \
__asm__ ("movw %%dx,%%ax\n\t" \
	"movw %0,%%dx\n\t" \
	"movl %%eax,%1\n\t" \
	"movl %%edx,%2" \
	: \
	: "i" ((short) (0x8000+(dpl<<13)+(type<<8))), \
	"o" (*((char *) (gate_addr))), \
	"o" (*(4+(char *) (gate_addr))), \
	"d" ((char *) (addr)),"a" (0x00080000))

#define set_intr_gate(n,addr) \
	_set_gate(&idt[n],14,0,addr)

#define set_trap_gate(n,addr) \
	_set_gate(&idt[n],15,0,addr)

#define set_system_gate(n,addr) \
	_set_gate(&idt[n],15,3,addr)

#define _set_seg_desc(gate_addr,type,dpl,base,limit) {\
	*(gate_addr) = ((base) & 0xff000000) | \
		(((base) & 0x00ff0000)>>16) | \
		((limit) & 0xf0000) | \
		((dpl)<<13) | \
		(0x00408000) | \
		((type)<<8); \
	*((gate_addr)+1) = (((base) & 0x0000ffff)<<16) | \
		((limit) & 0x0ffff); }

#define _set_tssldt_desc(n,addr,type) \
__asm__ ("movw $104,%1\n\t" \
	"movw %%ax,%2\n\t" \
	"rorl $16,%%eax\n\t" \
	"movb %%al,%3\n\t" \
	"movb $" type ",%4\n\t" \
	"movb $0x00,%5\n\t" \
	"movb %%ah,%6\n\t" \
	"rorl $16,%%eax" \
	::"a" (addr), "m" (*(n)), "m" (*(n+2)), "m" (*(n+4)), \
	 "m" (*(n+5)), "m" (*(n+6)), "m" (*(n+7)) \
	)

#define set_tss_desc(n,addr) _set_tssldt_desc(((char *) (n)),addr,"0x89")
#define set_ldt_desc(n,addr) _set_tssldt_desc(((char *) (n)),addr,"0x82")

include-unistd.h

#ifndef _UNISTD_H
#define _UNISTD_H

/* ok, this may be a joke, but I'm working on it */
#define _POSIX_VERSION 198808L

#define _POSIX_CHOWN_RESTRICTED  /* only root can do a chown (I think..) */
#define _POSIX_NO_TRUNC		/* no pathname truncation (but see in kernel) */
#define _POSIX_VDISABLE '\0'	/* character to disable things like ^C */
/*#define _POSIX_SAVED_IDS */	/* we'll get to this yet */
/*#define _POSIX_JOB_CONTROL */	/* we aren't there quite yet. Soon hopefully */

#define STDIN_FILENO	0
#define STDOUT_FILENO	1
#define STDERR_FILENO	2

#ifndef NULL
#define NULL    ((void *)0)
#endif

/* access */
#define F_OK	0
#define X_OK	1
#define W_OK	2
#define R_OK	4

/* lseek */
#define SEEK_SET	0
#define SEEK_CUR	1
#define SEEK_END	2

/* _SC stands for System Configuration. We don't use them much */
#define _SC_ARG_MAX		1
#define _SC_CHILD_MAX		2
#define _SC_CLOCKS_PER_SEC	3
#define _SC_NGROUPS_MAX		4
#define _SC_OPEN_MAX		5
#define _SC_JOB_CONTROL		6
#define _SC_SAVED_IDS		7
#define _SC_VERSION		8

/* more (possibly) configurable things - now pathnames */
#define _PC_LINK_MAX		1
#define _PC_MAX_CANON		2
#define _PC_MAX_INPUT		3
#define _PC_NAME_MAX		4
#define _PC_PATH_MAX		5
#define _PC_PIPE_BUF		6
#define _PC_NO_TRUNC		7
#define _PC_VDISABLE		8
#define _PC_CHOWN_RESTRICTED	9

#include <sys/stat.h>
#include <sys/times.h>
#include <sys/utsname.h>
#include <utime.h>

#ifdef __LIBRARY__

#define __NR_setup	0	/* used only by init, to get system going */
#define __NR_exit	1
#define __NR_fork	2
#define __NR_read	3
#define __NR_write	4
#define __NR_open	5
#define __NR_close	6
#define __NR_waitpid	7
#define __NR_creat	8
#define __NR_link	9
#define __NR_unlink	10
#define __NR_execve	11
#define __NR_chdir	12
#define __NR_time	13
#define __NR_mknod	14
#define __NR_chmod	15
#define __NR_chown	16
#define __NR_break	17
#define __NR_stat	18
#define __NR_lseek	19
#define __NR_getpid	20
#define __NR_mount	21
#define __NR_umount	22
#define __NR_setuid	23
#define __NR_getuid	24
#define __NR_stime	25
#define __NR_ptrace	26
#define __NR_alarm	27
#define __NR_fstat	28
#define __NR_pause	29
#define __NR_utime	30
#define __NR_stty	31
#define __NR_gtty	32
#define __NR_access	33
#define __NR_nice	34
#define __NR_ftime	35
#define __NR_sync	36
#define __NR_kill	37
#define __NR_rename	38
#define __NR_mkdir	39
#define __NR_rmdir	40
#define __NR_dup	41
#define __NR_pipe	42
#define __NR_times	43
#define __NR_prof	44
#define __NR_brk	45
#define __NR_setgid	46
#define __NR_getgid	47
#define __NR_signal	48
#define __NR_geteuid	49
#define __NR_getegid	50
#define __NR_acct	51
#define __NR_phys	52
#define __NR_lock	53
#define __NR_ioctl	54
#define __NR_fcntl	55
#define __NR_mpx	56
#define __NR_setpgid	57
#define __NR_ulimit	58
#define __NR_uname	59
#define __NR_umask	60
#define __NR_chroot	61
#define __NR_ustat	62
#define __NR_dup2	63
#define __NR_getppid	64
#define __NR_getpgrp	65
#define __NR_setsid	66
#define __NR_sigaction	67
#define __NR_sgetmask	68
#define __NR_ssetmask	69
#define __NR_setreuid	70
#define __NR_setregid	71

#define _syscall0(type,name) \
type name(void) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
	: "=a" (__res) \
	: "0" (__NR_##name)); \
if (__res >= 0) \
	return (type) __res; \
errno = -__res; \
return -1; \
}

#define _syscall1(type,name,atype,a) \
type name(atype a) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
	: "=a" (__res) \
	: "0" (__NR_##name),"b" ((long)(a))); \
if (__res >= 0) \
	return (type) __res; \
errno = -__res; \
return -1; \
}

#define _syscall2(type,name,atype,a,btype,b) \
type name(atype a,btype b) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
	: "=a" (__res) \
	: "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b))); \
if (__res >= 0) \
	return (type) __res; \
errno = -__res; \
return -1; \
}

#define _syscall3(type,name,atype,a,btype,b,ctype,c) \
type name(atype a,btype b,ctype c) \
{ \
long __res; \
__asm__ volatile ("int $0x80" \
	: "=a" (__res) \
	: "0" (__NR_##name),"b" ((long)(a)),"c" ((long)(b)),"d" ((long)(c))); \
if (__res>=0) \
	return (type) __res; \
errno=-__res; \
return -1; \
}

#endif /* __LIBRARY__ */

extern int errno;

int access(const char * filename, mode_t mode);
int acct(const char * filename);
int alarm(int sec);
int brk(void * end_data_segment);
void * sbrk(ptrdiff_t increment);
int chdir(const char * filename);
int chmod(const char * filename, mode_t mode);
int chown(const char * filename, uid_t owner, gid_t group);
int chroot(const char * filename);
int close(int fildes);
int creat(const char * filename, mode_t mode);
int dup(int fildes);
int execve(const char * filename, char ** argv, char ** envp);
int execv(const char * pathname, char ** argv);
int execvp(const char * file, char ** argv);
int execl(const char * pathname, char * arg0, ...);
int execlp(const char * file, char * arg0, ...);
int execle(const char * pathname, char * arg0, ...);
volatile void exit(int status);
volatile void _exit(int status);
int fcntl(int fildes, int cmd, ...);
int fork(void);
int getpid(void);
int getuid(void);
int geteuid(void);
int getgid(void);
int getegid(void);
int ioctl(int fildes, int cmd, ...);
int kill(pid_t pid, int signal);
int link(const char * filename1, const char * filename2);
int lseek(int fildes, off_t offset, int origin);
int mknod(const char * filename, mode_t mode, dev_t dev);
int mount(const char * specialfile, const char * dir, int rwflag);
int nice(int val);
int open(const char * filename, int flag, ...);
int pause(void);
int pipe(int * fildes);
int read(int fildes, char * buf, off_t count);
int setpgrp(void);
int setpgid(pid_t pid,pid_t pgid);
int setuid(uid_t uid);
int setgid(gid_t gid);
void (*signal(int sig, void (*fn)(int)))(int);
int stat(const char * filename, struct stat * stat_buf);
int fstat(int fildes, struct stat * stat_buf);
int stime(time_t * tptr);
int sync(void);
time_t time(time_t * tloc);
time_t times(struct tms * tbuf);
int ulimit(int cmd, long limit);
mode_t umask(mode_t mask);
int umount(const char * specialfile);
int uname(struct utsname * name);
int unlink(const char * filename);
int ustat(dev_t dev, struct ustat * ubuf);
int utime(const char * filename, struct utimbuf * times);
pid_t waitpid(pid_t pid,int * wait_stat,int options);
pid_t wait(int * wait_stat);
int write(int fildes, const char * buf, off_t count);
int dup2(int oldfd, int newfd);
int getppid(void);
pid_t getpgrp(void);
pid_t setsid(void);

#endif

init-main.c

/*
 *  linux/init/main.c
 *
 *  (C) 1991  Linus Torvalds
 */

#define __LIBRARY__
#include <unistd.h>
#include <time.h>

/*
 * we need this inline - forking from kernel space will result
 * in NO COPY ON WRITE (!!!), until an execve is executed. This
 * is no problem, but for the stack. This is handled by not letting
 * main() use the stack at all after fork(). Thus, no function
 * calls - which means inline code for fork too, as otherwise we
 * would use the stack upon exit from 'fork()'.
 *
 * Actually only pause and fork are needed inline, so that there
 * won't be any messing with the stack from main(), but we define
 * some others too.
 */
static inline _syscall0(int,fork)
static inline _syscall0(int,pause)
static inline _syscall1(int,setup,void *,BIOS)
static inline _syscall0(int,sync)

#include <linux/tty.h>
#include <linux/sched.h>
#include <linux/head.h>
#include <asm/system.h>
#include <asm/io.h>

#include <stddef.h>
#include <stdarg.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/types.h>

#include <linux/fs.h>

static char printbuf[1024];

extern int vsprintf();
extern void init(void);
extern void blk_dev_init(void);
extern void chr_dev_init(void);
extern void hd_init(void);
extern void floppy_init(void);
extern void mem_init(long start, long end);
extern long rd_init(long mem_start, int length);
extern long kernel_mktime(struct tm * tm);
extern long startup_time;

/*
 * This is set up by the setup-routine at boot-time
 */
#define EXT_MEM_K (*(unsigned short *)0x90002)
#define DRIVE_INFO (*(struct drive_info *)0x90080)
#define ORIG_ROOT_DEV (*(unsigned short *)0x901FC)

/*
 * Yeah, yeah, it's ugly, but I cannot find how to do this correctly
 * and this seems to work. I anybody has more info on the real-time
 * clock I'd be interested. Most of this was trial and error, and some
 * bios-listing reading. Urghh.
 */

#define CMOS_READ(addr) ({ \
outb_p(0x80|addr,0x70); \
inb_p(0x71); \
})

#define BCD_TO_BIN(val) ((val)=((val)&15) + ((val)>>4)*10)

static void time_init(void)
{
  struct tm time;

	do {
		time.tm_sec = CMOS_READ(0);
		time.tm_min = CMOS_READ(2);
		time.tm_hour = CMOS_READ(4);
		time.tm_mday = CMOS_READ(7);
		time.tm_mon = CMOS_READ(8);
		time.tm_year = CMOS_READ(9);
	} while (time.tm_sec != CMOS_READ(0));
	BCD_TO_BIN(time.tm_sec);
	BCD_TO_BIN(time.tm_min);
	BCD_TO_BIN(time.tm_hour);
	BCD_TO_BIN(time.tm_mday);
	BCD_TO_BIN(time.tm_mon);
	BCD_TO_BIN(time.tm_year);
	time.tm_mon--;
	startup_time = kernel_mktime(&time);
}

static long memory_end = 0;
static long buffer_memory_end = 0;
static long main_memory_start = 0;

struct drive_info { char dummy[32]; } drive_info;

void main(void)		/* This really IS void, no error here. */
{			/* The startup routine assumes (well, ...) this */
/*
 * Interrupts are still disabled. Do necessary setups, then
 * enable them
 */
 	ROOT_DEV = ORIG_ROOT_DEV;
 	drive_info = DRIVE_INFO;
	memory_end = (1<<20) + (EXT_MEM_K<<10);
	memory_end &= 0xfffff000;
	if (memory_end > 16*1024*1024)
		memory_end = 16*1024*1024;
	if (memory_end > 12*1024*1024) 
		buffer_memory_end = 4*1024*1024;
	else if (memory_end > 6*1024*1024)
		buffer_memory_end = 2*1024*1024;
	else
		buffer_memory_end = 1*1024*1024;
	main_memory_start = buffer_memory_end;
#ifdef RAMDISK
	main_memory_start += rd_init(main_memory_start, RAMDISK*1024);
#endif
	mem_init(main_memory_start,memory_end);
	trap_init();
	blk_dev_init();
	chr_dev_init();
	tty_init();
	time_init();
	sched_init();
	buffer_init(buffer_memory_end);
	hd_init();
	floppy_init();
	sti();
	move_to_user_mode();
	if (!fork()) {		/* we count on this going ok */
		init();
	}
/*
 *   NOTE!!   For any other task 'pause()' would mean we have to get a
 * signal to awaken, but task0 is the sole exception (see 'schedule()')
 * as task 0 gets activated at every idle moment (when no other tasks
 * can run). For task0 'pause()' just means we go check if some other
 * task can run, and if not we return here.
 */
	for(;;) pause();
}

static int printf(const char *fmt, ...)
{
	va_list args;
	int i;

	va_start(args, fmt);
	write(1,printbuf,i=vsprintf(printbuf, fmt, args));
	va_end(args);
	return i;
}

static char * argv_rc[] = { "/bin/sh", NULL };
static char * envp_rc[] = { "HOME=/", NULL };

static char * argv[] = { "-/bin/sh",NULL };
static char * envp[] = { "HOME=/usr/root", NULL };

void init(void)
{
	int pid,i;

	setup((void *) &drive_info);
	(void) open("/dev/tty0",O_RDWR,0);
	(void) dup(0);
	(void) dup(0);
	printf("%d buffers = %d bytes buffer space\n\r",NR_BUFFERS,
		NR_BUFFERS*BLOCK_SIZE);
	printf("Free mem: %d bytes\n\r",memory_end-main_memory_start);
	if (!(pid=fork())) {
		close(0);
		if (open("/etc/rc",O_RDONLY,0))
			_exit(1);
		execve("/bin/sh",argv_rc,envp_rc);
		_exit(2);
	}
	if (pid>0)
		while (pid != wait(&i))
			/* nothing */;
	while (1) {
		if ((pid=fork())<0) {
			printf("Fork failed in init\r\n");
			continue;
		}
		if (!pid) {
			close(0);close(1);close(2);
			setsid();
			(void) open("/dev/tty0",O_RDWR,0);
			(void) dup(0);
			(void) dup(0);
			_exit(execve("/bin/sh",argv,envp));
		}
		while (1)
			if (pid == wait(&i))
				break;
		printf("\n\rchild %d died with code %04x\n\r",pid,i);
		sync();
	}
	_exit(0);	/* NOTE! _exit, not exit() */
}

kernel-fork.c

/*
 *  linux/kernel/fork.c
 *
 *  (C) 1991  Linus Torvalds
 */

/*
 *  'fork.c' contains the help-routines for the 'fork' system call
 * (see also system_call.s), and some misc functions ('verify_area').
 * Fork is rather simple, once you get the hang of it, but the memory
 * management can be a bitch. See 'mm/mm.c': 'copy_page_tables()'
 */
#include <errno.h>

#include <linux/sched.h>
#include <linux/kernel.h>
#include <asm/segment.h>
#include <asm/system.h>

extern void write_verify(unsigned long address);

long last_pid=0;

void verify_area(void * addr,int size)
{
  unsigned long start;

	start = (unsigned long) addr;
	size += start & 0xfff;
	start &= 0xfffff000;
	start += get_base(current->ldt[2]);
	while (size>0) {
		size -= 4096;
		write_verify(start);
		start += 4096;
	}
}

int copy_mem(int nr,struct task_struct * p)
{
	unsigned long old_data_base,new_data_base,data_limit;
	unsigned long old_code_base,new_code_base,code_limit;

	code_limit=get_limit(0x0f);
	data_limit=get_limit(0x17);
	old_code_base = get_base(current->ldt[1]);
	old_data_base = get_base(current->ldt[2]);
	if (old_data_base != old_code_base)
		panic("We don't support separate I&D");
	if (data_limit < code_limit)
		panic("Bad data_limit");
	new_data_base = new_code_base = nr * 0x4000000;
	p->start_code = new_code_base;
	set_base(p->ldt[1],new_code_base);
	set_base(p->ldt[2],new_data_base);
	if (copy_page_tables(old_data_base,new_data_base,data_limit)) {
		free_page_tables(new_data_base,data_limit);
		return -ENOMEM;
	}
	return 0;
}

/*
 *  Ok, this is the main fork-routine. It copies the system process
 * information (task[nr]) and sets up the necessary registers. It
 * also copies the data segment in it's entirety.
 */
int copy_process(int nr,long ebp,long edi,long esi,long gs,long none,
		long ebx,long ecx,long edx,
		long fs,long es,long ds,
		long eip,long cs,long eflags,long esp,long ss)
{
	struct task_struct *p;
	int i;
	struct file *f;

	p = (struct task_struct *) get_free_page();
	if (!p)
		return -EAGAIN;
	task[nr] = p;
	*p = *current;	/* NOTE! this doesn't copy the supervisor stack */
	p->state = TASK_UNINTERRUPTIBLE;
	p->pid = last_pid;
	p->father = current->pid;
	p->counter = p->priority;
	p->signal = 0;
	p->alarm = 0;
	p->leader = 0;		/* process leadership doesn't inherit */
	p->utime = p->stime = 0;
	p->cutime = p->cstime = 0;
	p->start_time = jiffies;
	p->tss.back_link = 0;
	p->tss.esp0 = PAGE_SIZE + (long) p;
	p->tss.ss0 = 0x10;
	p->tss.eip = eip;
	p->tss.eflags = eflags;
	p->tss.eax = 0;
	p->tss.ecx = ecx;
	p->tss.edx = edx;
	p->tss.ebx = ebx;
	p->tss.esp = esp;
	p->tss.ebp = ebp;
	p->tss.esi = esi;
	p->tss.edi = edi;
	p->tss.es = es & 0xffff;
	p->tss.cs = cs & 0xffff;
	p->tss.ss = ss & 0xffff;
	p->tss.ds = ds & 0xffff;
	p->tss.fs = fs & 0xffff;
	p->tss.gs = gs & 0xffff;
	p->tss.ldt = _LDT(nr);
	p->tss.trace_bitmap = 0x80000000;
	if (last_task_used_math == current)
		__asm__("clts ; fnsave %0"::"m" (p->tss.i387));
	if (copy_mem(nr,p)) {
		task[nr] = NULL;
		free_page((long) p);
		return -EAGAIN;
	}
	for (i=0; i<NR_OPEN;i++)
		if (f=p->filp[i])
			f->f_count++;
	if (current->pwd)
		current->pwd->i_count++;
	if (current->root)
		current->root->i_count++;
	if (current->executable)
		current->executable->i_count++;
	set_tss_desc(gdt+(nr<<1)+FIRST_TSS_ENTRY,&(p->tss));
	set_ldt_desc(gdt+(nr<<1)+FIRST_LDT_ENTRY,&(p->ldt));
	p->state = TASK_RUNNING;	/* do this last, just in case */
	return last_pid;
}

int find_empty_process(void)
{
	int i;

	repeat:
		if ((++last_pid)<0) last_pid=1;
		for(i=0 ; i<NR_TASKS ; i++)
			if (task[i] && task[i]->pid == last_pid) goto repeat;
	for(i=1 ; i<NR_TASKS ; i++)
		if (!task[i])
			return i;
	return -EAGAIN;
}

kernel-sched.c

/*
 *  linux/kernel/sched.c
 *
 *  (C) 1991  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/sched.h>
#include <linux/kernel.h>
#include <linux/sys.h>
#include <linux/fdreg.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/segment.h>

#include <signal.h>

#define _S(nr) (1<<((nr)-1))
#define _BLOCKABLE (~(_S(SIGKILL) | _S(SIGSTOP)))

void show_task(int nr,struct task_struct * p)
{
  int i,j = 4096-sizeof(struct task_struct);

	printk("%d: pid=%d, state=%d, ",nr,p->pid,p->state);
	i=0;
	while (i<j && !((char *)(p+1))[i])
		i++;
	printk("%d (of %d) chars free in kernel stack\n\r",i,j);
}

void show_stat(void)
{
	int i;

	for (i=0;i<NR_TASKS;i++)
		if (task[i])
			show_task(i,task[i]);
}

#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);
struct task_struct *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()
{
	if (last_task_used_math == current)
		return;
	__asm__("fwait");
	if (last_task_used_math) {
		__asm__("fnsave %0"::"m" (last_task_used_math->tss.i387));
	}
	last_task_used_math=current;
	if (current->used_math) {
		__asm__("frstor %0"::"m" (current->tss.i387));
	} else {
		__asm__("fninit"::);
		current->used_math=1;
	}
}

/*
 *  '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));
					(*p)->alarm = 0;
				}
			if (((*p)->signal & ~(_BLOCKABLE & (*p)->blocked)) &&
			(*p)->state==TASK_INTERRUPTIBLE)
				(*p)->state=TASK_RUNNING;
		}

/* this is the scheduler proper: */

	while (1) {
		c = -1;
		next = 0;
		i = NR_TASKS;
		p = &task[NR_TASKS];
		while (--i) {
			if (!*--p)
				continue;
			if ((*p)->state == TASK_RUNNING && (*p)->counter > c)
				c = (*p)->counter, next = i;
		}
		if (c) break;
		for(p = &LAST_TASK ; p > &FIRST_TASK ; --p)
			if (*p)
				(*p)->counter = ((*p)->counter >> 1) +
						(*p)->priority;
	}
	switch_to(next);
}

int sys_pause(void)
{
	current->state = TASK_INTERRUPTIBLE;
	schedule();
	return 0;
}

void sleep_on(struct task_struct **p)
{
	struct task_struct *tmp;

	if (!p)
		return;
	if (current == &(init_task.task))
		panic("task[0] trying to sleep");
	tmp = *p;
	*p = current;
	current->state = TASK_UNINTERRUPTIBLE;
	schedule();
	if (tmp)
		tmp->state=0;
}

void interruptible_sleep_on(struct task_struct **p)
{
	struct task_struct *tmp;

	if (!p)
		return;
	if (current == &(init_task.task))
		panic("task[0] trying to sleep");
	tmp=*p;
	*p=current;
repeat:	current->state = TASK_INTERRUPTIBLE;
	schedule();
	if (*p && *p != current) {
		(**p).state=0;
		goto repeat;
	}
	*p=NULL;
	if (tmp)
		tmp->state=0;
}

void wake_up(struct task_struct **p)
{
	if (p && *p) {
		(**p).state=0;
		*p=NULL;
	}
}

/*
 * OK, here are some floppy things that shouldn't be in the kernel
 * proper. They are here because the floppy needs a timer, and this
 * was the easiest way of doing it.
 */
static struct task_struct * wait_motor[4] = {NULL,NULL,NULL,NULL};
static int  mon_timer[4]={0,0,0,0};
static int moff_timer[4]={0,0,0,0};
unsigned char current_DOR = 0x0C;

int ticks_to_floppy_on(unsigned int nr)
{
	extern unsigned char selected;
	unsigned char mask = 0x10 << nr;

	if (nr>3)
		panic("floppy_on: nr>3");
	moff_timer[nr]=10000;		/* 100 s = very big :-) */
	cli();				/* use floppy_off to turn it off */
	mask |= current_DOR;
	if (!selected) {
		mask &= 0xFC;
		mask |= nr;
	}
	if (mask != current_DOR) {
		outb(mask,FD_DOR);
		if ((mask ^ current_DOR) & 0xf0)
			mon_timer[nr] = HZ/2;
		else if (mon_timer[nr] < 2)
			mon_timer[nr] = 2;
		current_DOR = mask;
	}
	sti();
	return mon_timer[nr];
}

void floppy_on(unsigned int nr)
{
	cli();
	while (ticks_to_floppy_on(nr))
		sleep_on(nr+wait_motor);
	sti();
}

void floppy_off(unsigned int nr)
{
	moff_timer[nr]=3*HZ;
}

void do_floppy_timer(void)
{
	int i;
	unsigned char mask = 0x10;

	for (i=0 ; i<4 ; i++,mask <<= 1) {
		if (!(mask & current_DOR))
			continue;
		if (mon_timer[i]) {
			if (!--mon_timer[i])
				wake_up(i+wait_motor);
		} else if (!moff_timer[i]) {
			current_DOR &= ~mask;
			outb(current_DOR,FD_DOR);
		} else
			moff_timer[i]--;
	}
}

#define TIME_REQUESTS 64

static struct timer_list {
	long jiffies;
	void (*fn)();
	struct timer_list * next;
} timer_list[TIME_REQUESTS], * next_timer = NULL;

void add_timer(long jiffies, void (*fn)(void))
{
	struct timer_list * p;

	if (!fn)
		return;
	cli();
	if (jiffies <= 0)
		(fn)();
	else {
		for (p = timer_list ; p < timer_list + TIME_REQUESTS ; p++)
			if (!p->fn)
				break;
		if (p >= timer_list + TIME_REQUESTS)
			panic("No more time requests free");
		p->fn = fn;
		p->jiffies = jiffies;
		p->next = next_timer;
		next_timer = p;
		while (p->next && p->next->jiffies < p->jiffies) {
			p->jiffies -= p->next->jiffies;
			fn = p->fn;
			p->fn = p->next->fn;
			p->next->fn = fn;
			jiffies = p->jiffies;
			p->jiffies = p->next->jiffies;
			p->next->jiffies = jiffies;
			p = p->next;
		}
	}
	sti();
}

void do_timer(long cpl)
{
	extern int beepcount;
	extern void sysbeepstop(void);

	if (beepcount)
		if (!--beepcount)
			sysbeepstop();

	if (cpl)
		current->utime++;
	else
		current->stime++;

	if (next_timer) {
		next_timer->jiffies--;
		while (next_timer && next_timer->jiffies <= 0) {
			void (*fn)(void);
			
			fn = next_timer->fn;
			next_timer->fn = NULL;
			next_timer = next_timer->next;
			(fn)();
		}
	}
	if (current_DOR & 0xf0)
		do_floppy_timer();
	if ((--current->counter)>0) return;
	current->counter=0;
	if (!cpl) return;
	schedule();
}

int sys_alarm(long seconds)
{
	int old = current->alarm;

	if (old)
		old = (old - jiffies) / HZ;
	current->alarm = (seconds>0)?(jiffies+HZ*seconds):0;
	return (old);
}

int sys_getpid(void)
{
	return current->pid;
}

int sys_getppid(void)
{
	return current->father;
}

int sys_getuid(void)
{
	return current->uid;
}

int sys_geteuid(void)
{
	return current->euid;
}

int sys_getgid(void)
{
	return current->gid;
}

int sys_getegid(void)
{
	return current->egid;
}

int sys_nice(long increment)
{
	if (current->priority-increment>0)
		current->priority -= increment;
	return 0;
}

void sched_init(void)
{
	int i;
	struct desc_struct * p;

	if (sizeof(struct sigaction) != 16)
		panic("Struct sigaction MUST be 16 bytes");
	set_tss_desc(gdt+FIRST_TSS_ENTRY,&(init_task.task.tss));
	set_ldt_desc(gdt+FIRST_LDT_ENTRY,&(init_task.task.ldt));
	p = gdt+2+FIRST_TSS_ENTRY;
	for(i=1;i<NR_TASKS;i++) {
		task[i] = NULL;
		p->a=p->b=0;
		p++;
		p->a=p->b=0;
		p++;
	}
/* Clear NT, so that we won't have troubles with that later on */
	__asm__("pushfl ; andl $0xffffbfff,(%esp) ; popfl");
	ltr(0);
	lldt(0);
	outb_p(0x36,0x43);		/* binary, mode 3, LSB/MSB, ch 0 */
	outb_p(LATCH & 0xff , 0x40);	/* LSB */
	outb(LATCH >> 8 , 0x40);	/* MSB */
	set_intr_gate(0x20,&timer_interrupt);
	outb(inb_p(0x21)&~0x01,0x21);
	set_system_gate(0x80,&system_call);
}

kernel-system_call.s

/*
 *  linux/kernel/system_call.s
 *
 *  (C) 1991  Linus Torvalds
 */

/*
 *  system_call.s  contains the system-call low-level handling routines.
 * This also contains the timer-interrupt handler, as some of the code is
 * the same. The hd- and flopppy-interrupts are also here.
 *
 * NOTE: This code handles signal-recognition, which happens every time
 * after a timer-interrupt and after each system call. Ordinary interrupts
 * don't handle signal-recognition, as that would clutter them up totally
 * unnecessarily.
 *
 * Stack layout in 'ret_from_system_call':
 *
 *   0(%esp) - %eax
 *	 4(%esp) - %ebx
 *	 8(%esp) - %ecx
 *	 C(%esp) - %edx
 *	10(%esp) - %fs
 *	14(%esp) - %es
 *	18(%esp) - %ds
 *	1C(%esp) - %eip
 *	20(%esp) - %cs
 *	24(%esp) - %eflags
 *	28(%esp) - %oldesp
 *	2C(%esp) - %oldss
 */

SIG_CHLD	= 17

EAX		= 0x00
EBX		= 0x04
ECX		= 0x08
EDX		= 0x0C
FS		= 0x10
ES		= 0x14
DS		= 0x18
EIP		= 0x1C
CS		= 0x20
EFLAGS		= 0x24
OLDESP		= 0x28
OLDSS		= 0x2C

state	= 0		# these are offsets into the task-struct.
counter	= 4
priority = 8
signal	= 12
sigaction = 16		# MUST be 16 (=len of sigaction)
blocked = (33*16)

# offsets within sigaction
sa_handler = 0
sa_mask = 4
sa_flags = 8
sa_restorer = 12

nr_system_calls = 72

/*
 * Ok, I get parallel printer interrupts while using the floppy for some
 * strange reason. Urgel. Now I just ignore them.
 */
.globl _system_call,_sys_fork,_timer_interrupt,_sys_execve
.globl _hd_interrupt,_floppy_interrupt,_parallel_interrupt
.globl _device_not_available, _coprocessor_error

.align 2
bad_sys_call:
	movl $-1,%eax
	iret
.align 2
reschedule:
	pushl $ret_from_sys_call
	jmp _schedule
.align 2
_system_call:
	cmpl $nr_system_calls-1,%eax
	ja bad_sys_call
	push %ds
	push %es
	push %fs
	pushl %edx
	pushl %ecx		# push %ebx,%ecx,%edx as parameters
	pushl %ebx		# to the system call
	movl $0x10,%edx		# set up ds,es to kernel space
	mov %dx,%ds
	mov %dx,%es
	movl $0x17,%edx		# fs points to local data space
	mov %dx,%fs
	call _sys_call_table(,%eax,4)
	pushl %eax
	movl _current,%eax
	cmpl $0,state(%eax)		# state
	jne reschedule
	cmpl $0,counter(%eax)		# counter
	je reschedule
ret_from_sys_call:
	movl _current,%eax		# task[0] cannot have signals
	cmpl _task,%eax
	je 3f
	cmpw $0x0f,CS(%esp)		# was old code segment supervisor ?
	jne 3f
	cmpw $0x17,OLDSS(%esp)		# was stack segment = 0x17 ?
	jne 3f
	movl signal(%eax),%ebx
	movl blocked(%eax),%ecx
	notl %ecx
	andl %ebx,%ecx
	bsfl %ecx,%ecx
	je 3f
	btrl %ecx,%ebx
	movl %ebx,signal(%eax)
	incl %ecx
	pushl %ecx
	call _do_signal
	popl %eax
3:	popl %eax
	popl %ebx
	popl %ecx
	popl %edx
	pop %fs
	pop %es
	pop %ds
	iret

.align 2
_coprocessor_error:
	push %ds
	push %es
	push %fs
	pushl %edx
	pushl %ecx
	pushl %ebx
	pushl %eax
	movl $0x10,%eax
	mov %ax,%ds
	mov %ax,%es
	movl $0x17,%eax
	mov %ax,%fs
	pushl $ret_from_sys_call
	jmp _math_error

.align 2
_device_not_available:
	push %ds
	push %es
	push %fs
	pushl %edx
	pushl %ecx
	pushl %ebx
	pushl %eax
	movl $0x10,%eax
	mov %ax,%ds
	mov %ax,%es
	movl $0x17,%eax
	mov %ax,%fs
	pushl $ret_from_sys_call
	clts				# clear TS so that we can use math
	movl %cr0,%eax
	testl $0x4,%eax			# EM (math emulation bit)
	je _math_state_restore
	pushl %ebp
	pushl %esi
	pushl %edi
	call _math_emulate
	popl %edi
	popl %esi
	popl %ebp
	ret

.align 2
_timer_interrupt:
	push %ds		# save ds,es and put kernel data space
	push %es		# into them. %fs is used by _system_call
	push %fs
	pushl %edx		# we save %eax,%ecx,%edx as gcc doesn't
	pushl %ecx		# save those across function calls. %ebx
	pushl %ebx		# is saved as we use that in ret_sys_call
	pushl %eax
	movl $0x10,%eax
	mov %ax,%ds
	mov %ax,%es
	movl $0x17,%eax
	mov %ax,%fs
	incl _jiffies
	movb $0x20,%al		# EOI to interrupt controller #1
	outb %al,$0x20
	movl CS(%esp),%eax
	andl $3,%eax		# %eax is CPL (0 or 3, 0=supervisor)
	pushl %eax
	call _do_timer		# 'do_timer(long CPL)' does everything from
	addl $4,%esp		# task switching to accounting ...
	jmp ret_from_sys_call

.align 2
_sys_execve:
	lea EIP(%esp),%eax
	pushl %eax
	call _do_execve
	addl $4,%esp
	ret

.align 2
_sys_fork:
	call _find_empty_process
	testl %eax,%eax
	js 1f
	push %gs
	pushl %esi
	pushl %edi
	pushl %ebp
	pushl %eax
	call _copy_process
	addl $20,%esp
1:	ret

_hd_interrupt:
	pushl %eax
	pushl %ecx
	pushl %edx
	push %ds
	push %es
	push %fs
	movl $0x10,%eax
	mov %ax,%ds
	mov %ax,%es
	movl $0x17,%eax
	mov %ax,%fs
	movb $0x20,%al
	outb %al,$0xA0		# EOI to interrupt controller #1
	jmp 1f			# give port chance to breathe
1:	jmp 1f
1:	xorl %edx,%edx
	xchgl _do_hd,%edx
	testl %edx,%edx
	jne 1f
	movl $_unexpected_hd_interrupt,%edx
1:	outb %al,$0x20
	call *%edx		# "interesting" way of handling intr.
	pop %fs
	pop %es
	pop %ds
	popl %edx
	popl %ecx
	popl %eax
	iret

_floppy_interrupt:
	pushl %eax
	pushl %ecx
	pushl %edx
	push %ds
	push %es
	push %fs
	movl $0x10,%eax
	mov %ax,%ds
	mov %ax,%es
	movl $0x17,%eax
	mov %ax,%fs
	movb $0x20,%al
	outb %al,$0x20		# EOI to interrupt controller #1
	xorl %eax,%eax
	xchgl _do_floppy,%eax
	testl %eax,%eax
	jne 1f
	movl $_unexpected_floppy_interrupt,%eax
1:	call *%eax		# "interesting" way of handling intr.
	pop %fs
	pop %es
	pop %ds
	popl %edx
	popl %ecx
	popl %eax
	iret

_parallel_interrupt:
	pushl %eax
	movb $0x20,%al
	outb %al,$0x20
	popl %eax
	iret

kernel-traps.c

/*
 *  linux/kernel/traps.c
 *
 *  (C) 1991  Linus Torvalds
 */

/*
 * 'Traps.c' handles hardware traps and faults after we have saved some
 * state in 'asm.s'. Currently mostly a debugging-aid, will be extended
 * to mainly kill the offending process (probably by giving it a signal,
 * but possibly by killing it outright if necessary).
 */
#include <string.h>

#include <linux/head.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <asm/system.h>
#include <asm/segment.h>
#include <asm/io.h>

#define get_seg_byte(seg,addr) ({ \
register char __res; \
__asm__("push %%fs;mov %%ax,%%fs;movb %%fs:%2,%%al;pop %%fs" \
  :"=a" (__res):"0" (seg),"m" (*(addr))); \
__res;})

#define get_seg_long(seg,addr) ({ \
register unsigned long __res; \
__asm__("push %%fs;mov %%ax,%%fs;movl %%fs:%2,%%eax;pop %%fs" \
	:"=a" (__res):"0" (seg),"m" (*(addr))); \
__res;})

#define _fs() ({ \
register unsigned short __res; \
__asm__("mov %%fs,%%ax":"=a" (__res):); \
__res;})

int do_exit(long code);

void page_exception(void);

void divide_error(void);
void debug(void);
void nmi(void);
void int3(void);
void overflow(void);
void bounds(void);
void invalid_op(void);
void device_not_available(void);
void double_fault(void);
void coprocessor_segment_overrun(void);
void invalid_TSS(void);
void segment_not_present(void);
void stack_segment(void);
void general_protection(void);
void page_fault(void);
void coprocessor_error(void);
void reserved(void);
void parallel_interrupt(void);
void irq13(void);

static void die(char * str,long esp_ptr,long nr)
{
	long * esp = (long *) esp_ptr;
	int i;

	printk("%s: %04x\n\r",str,nr&0xffff);
	printk("EIP:\t%04x:%p\nEFLAGS:\t%p\nESP:\t%04x:%p\n",
		esp[1],esp[0],esp[2],esp[4],esp[3]);
	printk("fs: %04x\n",_fs());
	printk("base: %p, limit: %p\n",get_base(current->ldt[1]),get_limit(0x17));
	if (esp[4] == 0x17) {
		printk("Stack: ");
		for (i=0;i<4;i++)
			printk("%p ",get_seg_long(0x17,i+(long *)esp[3]));
		printk("\n");
	}
	str(i);
	printk("Pid: %d, process nr: %d\n\r",current->pid,0xffff & i);
	for(i=0;i<10;i++)
		printk("%02x ",0xff & get_seg_byte(esp[1],(i+(char *)esp[0])));
	printk("\n\r");
	do_exit(11);		/* play segment exception */
}

void do_double_fault(long esp, long error_code)
{
	die("double fault",esp,error_code);
}

void do_general_protection(long esp, long error_code)
{
	die("general protection",esp,error_code);
}

void do_divide_error(long esp, long error_code)
{
	die("divide error",esp,error_code);
}

void do_int3(long * esp, long error_code,
		long fs,long es,long ds,
		long ebp,long esi,long edi,
		long edx,long ecx,long ebx,long eax)
{
	int tr;

	__asm__("str %%ax":"=a" (tr):"0" (0));
	printk("eax\t\tebx\t\tecx\t\tedx\n\r%8x\t%8x\t%8x\t%8x\n\r",
		eax,ebx,ecx,edx);
	printk("esi\t\tedi\t\tebp\t\tesp\n\r%8x\t%8x\t%8x\t%8x\n\r",
		esi,edi,ebp,(long) esp);
	printk("\n\rds\tes\tfs\ttr\n\r%4x\t%4x\t%4x\t%4x\n\r",
		ds,es,fs,tr);
	printk("EIP: %8x   CS: %4x  EFLAGS: %8x\n\r",esp[0],esp[1],esp[2]);
}

void do_nmi(long esp, long error_code)
{
	die("nmi",esp,error_code);
}

void do_debug(long esp, long error_code)
{
	die("debug",esp,error_code);
}

void do_overflow(long esp, long error_code)
{
	die("overflow",esp,error_code);
}

void do_bounds(long esp, long error_code)
{
	die("bounds",esp,error_code);
}

void do_invalid_op(long esp, long error_code)
{
	die("invalid operand",esp,error_code);
}

void do_device_not_available(long esp, long error_code)
{
	die("device not available",esp,error_code);
}

void do_coprocessor_segment_overrun(long esp, long error_code)
{
	die("coprocessor segment overrun",esp,error_code);
}

void do_invalid_TSS(long esp,long error_code)
{
	die("invalid TSS",esp,error_code);
}

void do_segment_not_present(long esp,long error_code)
{
	die("segment not present",esp,error_code);
}

void do_stack_segment(long esp,long error_code)
{
	die("stack segment",esp,error_code);
}

void do_coprocessor_error(long esp, long error_code)
{
	if (last_task_used_math != current)
		return;
	die("coprocessor error",esp,error_code);
}

void do_reserved(long esp, long error_code)
{
	die("reserved (15,17-47) error",esp,error_code);
}

void trap_init(void)
{
	int i;

	set_trap_gate(0,&divide_error);
	set_trap_gate(1,&debug);
	set_trap_gate(2,&nmi);
	set_system_gate(3,&int3);	/* int3-5 can be called from all */
	set_system_gate(4,&overflow);
	set_system_gate(5,&bounds);
	set_trap_gate(6,&invalid_op);
	set_trap_gate(7,&device_not_available);
	set_trap_gate(8,&double_fault);
	set_trap_gate(9,&coprocessor_segment_overrun);
	set_trap_gate(10,&invalid_TSS);
	set_trap_gate(11,&segment_not_present);
	set_trap_gate(12,&stack_segment);
	set_trap_gate(13,&general_protection);
	set_trap_gate(14,&page_fault);
	set_trap_gate(15,&reserved);
	set_trap_gate(16,&coprocessor_error);
	for (i=17;i<48;i++)
		set_trap_gate(i,&reserved);
	set_trap_gate(45,&irq13);
	outb_p(inb_p(0x21)&0xfb,0x21);
	outb(inb_p(0xA1)&0xdf,0xA1);
	set_trap_gate(39,&parallel_interrupt);
}

mm-memory.c

/*
 *  linux/mm/memory.c
 *
 *  (C) 1991  Linus Torvalds
 */

/*
 * demand-loading started 01.12.91 - seems it is high on the list of
 * things wanted, and it should be easy to implement. - Linus
 */

/*
 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
 * pages started 02.12.91, seems to work. - Linus.
 *
 * Tested sharing by executing about 30 /bin/sh: under the old kernel it
 * would have taken more than the 6M I have free, but it worked well as
 * far as I could see.
 *
 * Also corrected some "invalidate()"s - I wasn't doing enough of them.
 */

#include <signal.h>

#include <asm/system.h>

#include <linux/sched.h>
#include <linux/head.h>
#include <linux/kernel.h>

volatile void do_exit(long code);

static inline volatile void oom(void)
{
  printk("out of memory\n\r");
	do_exit(SIGSEGV);
}

#define invalidate() \
__asm__("movl %%eax,%%cr3"::"a" (0))

/* these are not to be changed without changing head.s etc */
#define LOW_MEM 0x100000
#define PAGING_MEMORY (15*1024*1024)
#define PAGING_PAGES (PAGING_MEMORY>>12)
#define MAP_NR(addr) (((addr)-LOW_MEM)>>12)
#define USED 100

#define CODE_SPACE(addr) ((((addr)+4095)&~4095) < \
current->start_code + current->end_code)

static long HIGH_MEMORY = 0;

#define copy_page(from,to) \
__asm__("cld ; rep ; movsl"::"S" (from),"D" (to),"c" (1024):"cx","di","si")

static unsigned char mem_map [ PAGING_PAGES ] = {0,};

/*
 * Get physical address of first (actually last :-) free page, and mark it
 * used. If no free pages left, return 0.
 */
unsigned long get_free_page(void)
{
register unsigned long __res asm("ax");

__asm__("std ; repne ; scasb\n\t"
	"jne 1f\n\t"
	"movb $1,1(%%edi)\n\t"
	"sall $12,%%ecx\n\t"
	"addl %2,%%ecx\n\t"
	"movl %%ecx,%%edx\n\t"
	"movl $1024,%%ecx\n\t"
	"leal 4092(%%edx),%%edi\n\t"
	"rep ; stosl\n\t"
	"movl %%edx,%%eax\n"
	"1:"
	:"=a" (__res)
	:"0" (0),"i" (LOW_MEM),"c" (PAGING_PAGES),
	"D" (mem_map+PAGING_PAGES-1)
	:"di","cx","dx");
return __res;
}

/*
 * Free a page of memory at physical address 'addr'. Used by
 * 'free_page_tables()'
 */
void free_page(unsigned long addr)
{
	if (addr < LOW_MEM) return;
	if (addr >= HIGH_MEMORY)
		panic("trying to free nonexistent page");
	addr -= LOW_MEM;
	addr >>= 12;
	if (mem_map[addr]--) return;
	mem_map[addr]=0;
	panic("trying to free free page");
}

/*
 * This function frees a continuos block of page tables, as needed
 * by 'exit()'. As does copy_page_tables(), this handles only 4Mb blocks.
 */
int free_page_tables(unsigned long from,unsigned long size)
{
	unsigned long *pg_table;
	unsigned long * dir, nr;

	if (from & 0x3fffff)
		panic("free_page_tables called with wrong alignment");
	if (!from)
		panic("Trying to free up swapper memory space");
	size = (size + 0x3fffff) >> 22;
	dir = (unsigned long *) ((from>>20) & 0xffc); /* _pg_dir = 0 */
	for ( ; size-->0 ; dir++) {
		if (!(1 & *dir))
			continue;
		pg_table = (unsigned long *) (0xfffff000 & *dir);
		for (nr=0 ; nr<1024 ; nr++) {
			if (1 & *pg_table)
				free_page(0xfffff000 & *pg_table);
			*pg_table = 0;
			pg_table++;
		}
		free_page(0xfffff000 & *dir);
		*dir = 0;
	}
	invalidate();
	return 0;
}

/*
 *  Well, here is one of the most complicated functions in mm. It
 * copies a range of linerar addresses by copying only the pages.
 * Let's hope this is bug-free, 'cause this one I don't want to debug :-)
 *
 * Note! We don't copy just any chunks of memory - addresses have to
 * be divisible by 4Mb (one page-directory entry), as this makes the
 * function easier. It's used only by fork anyway.
 *
 * NOTE 2!! When from==0 we are copying kernel space for the first
 * fork(). Then we DONT want to copy a full page-directory entry, as
 * that would lead to some serious memory waste - we just copy the
 * first 160 pages - 640kB. Even that is more than we need, but it
 * doesn't take any more memory - we don't copy-on-write in the low
 * 1 Mb-range, so the pages can be shared with the kernel. Thus the
 * special case for nr=xxxx.
 */
int copy_page_tables(unsigned long from,unsigned long to,long size)
{
	unsigned long * from_page_table;
	unsigned long * to_page_table;
	unsigned long this_page;
	unsigned long * from_dir, * to_dir;
	unsigned long nr;

	if ((from&0x3fffff) || (to&0x3fffff))
		panic("copy_page_tables called with wrong alignment");
	from_dir = (unsigned long *) ((from>>20) & 0xffc); /* _pg_dir = 0 */
	to_dir = (unsigned long *) ((to>>20) & 0xffc);
	size = ((unsigned) (size+0x3fffff)) >> 22;
	for( ; size-->0 ; from_dir++,to_dir++) {
		if (1 & *to_dir)
			panic("copy_page_tables: already exist");
		if (!(1 & *from_dir))
			continue;
		from_page_table = (unsigned long *) (0xfffff000 & *from_dir);
		if (!(to_page_table = (unsigned long *) get_free_page()))
			return -1;	/* Out of memory, see freeing */
		*to_dir = ((unsigned long) to_page_table) | 7;
		nr = (from==0)?0xA0:1024;
		for ( ; nr-- > 0 ; from_page_table++,to_page_table++) {
			this_page = *from_page_table;
			if (!(1 & this_page))
				continue;
			this_page &= ~2;
			*to_page_table = this_page;
			if (this_page > LOW_MEM) {
				*from_page_table = this_page;
				this_page -= LOW_MEM;
				this_page >>= 12;
				mem_map[this_page]++;
			}
		}
	}
	invalidate();
	return 0;
}

/*
 * This function puts a page in memory at the wanted address.
 * It returns the physical address of the page gotten, 0 if
 * out of memory (either when trying to access page-table or
 * page.)
 */
unsigned long put_page(unsigned long page,unsigned long address)
{
	unsigned long tmp, *page_table;

/* NOTE !!! This uses the fact that _pg_dir=0 */

	if (page < LOW_MEM || page >= HIGH_MEMORY)
		printk("Trying to put page %p at %p\n",page,address);
	if (mem_map[(page-LOW_MEM)>>12] != 1)
		printk("mem_map disagrees with %p at %p\n",page,address);
	page_table = (unsigned long *) ((address>>20) & 0xffc);
	if ((*page_table)&1)
		page_table = (unsigned long *) (0xfffff000 & *page_table);
	else {
		if (!(tmp=get_free_page()))
			return 0;
		*page_table = tmp|7;
		page_table = (unsigned long *) tmp;
	}
	page_table[(address>>12) & 0x3ff] = page | 7;
/* no need for invalidate */
	return page;
}

void un_wp_page(unsigned long * table_entry)
{
	unsigned long old_page,new_page;

	old_page = 0xfffff000 & *table_entry;
	if (old_page >= LOW_MEM && mem_map[MAP_NR(old_page)]==1) {
		*table_entry |= 2;
		invalidate();
		return;
	}
	if (!(new_page=get_free_page()))
		oom();
	if (old_page >= LOW_MEM)
		mem_map[MAP_NR(old_page)]--;
	*table_entry = new_page | 7;
	invalidate();
	copy_page(old_page,new_page);
}	

/*
 * This routine handles present pages, when users try to write
 * to a shared page. It is done by copying the page to a new address
 * and decrementing the shared-page counter for the old page.
 *
 * If it's in code space we exit with a segment error.
 */
void do_wp_page(unsigned long error_code,unsigned long address)
{
#if 0
/* we cannot do this yet: the estdio library writes to code space */
/* stupid, stupid. I really want the libc.a from GNU */
	if (CODE_SPACE(address))
		do_exit(SIGSEGV);
#endif
	un_wp_page((unsigned long *)
		(((address>>10) & 0xffc) + (0xfffff000 &
		*((unsigned long *) ((address>>20) &0xffc)))));

}

void write_verify(unsigned long address)
{
	unsigned long page;

	if (!( (page = *((unsigned long *) ((address>>20) & 0xffc)) )&1))
		return;
	page &= 0xfffff000;
	page += ((address>>10) & 0xffc);
	if ((3 & *(unsigned long *) page) == 1)  /* non-writeable, present */
		un_wp_page((unsigned long *) page);
	return;
}

void get_empty_page(unsigned long address)
{
	unsigned long tmp;

	if (!(tmp=get_free_page()) || !put_page(tmp,address)) {
		free_page(tmp);		/* 0 is ok - ignored */
		oom();
	}
}

/*
 * try_to_share() checks the page at address "address" in the task "p",
 * to see if it exists, and if it is clean. If so, share it with the current
 * task.
 *
 * NOTE! This assumes we have checked that p != current, and that they
 * share the same executable.
 */
static int try_to_share(unsigned long address, struct task_struct * p)
{
	unsigned long from;
	unsigned long to;
	unsigned long from_page;
	unsigned long to_page;
	unsigned long phys_addr;

	from_page = to_page = ((address>>20) & 0xffc);
	from_page += ((p->start_code>>20) & 0xffc);
	to_page += ((current->start_code>>20) & 0xffc);
/* is there a page-directory at from? */
	from = *(unsigned long *) from_page;
	if (!(from & 1))
		return 0;
	from &= 0xfffff000;
	from_page = from + ((address>>10) & 0xffc);
	phys_addr = *(unsigned long *) from_page;
/* is the page clean and present? */
	if ((phys_addr & 0x41) != 0x01)
		return 0;
	phys_addr &= 0xfffff000;
	if (phys_addr >= HIGH_MEMORY || phys_addr < LOW_MEM)
		return 0;
	to = *(unsigned long *) to_page;
	if (!(to & 1))
		if (to = get_free_page())
			*(unsigned long *) to_page = to | 7;
		else
			oom();
	to &= 0xfffff000;
	to_page = to + ((address>>10) & 0xffc);
	if (1 & *(unsigned long *) to_page)
		panic("try_to_share: to_page already exists");
/* share them: write-protect */
	*(unsigned long *) from_page &= ~2;
	*(unsigned long *) to_page = *(unsigned long *) from_page;
	invalidate();
	phys_addr -= LOW_MEM;
	phys_addr >>= 12;
	mem_map[phys_addr]++;
	return 1;
}

/*
 * share_page() tries to find a process that could share a page with
 * the current one. Address is the address of the wanted page relative
 * to the current data space.
 *
 * We first check if it is at all feasible by checking executable->i_count.
 * It should be >1 if there are other tasks sharing this inode.
 */
static int share_page(unsigned long address)
{
	struct task_struct ** p;

	if (!current->executable)
		return 0;
	if (current->executable->i_count < 2)
		return 0;
	for (p = &LAST_TASK ; p > &FIRST_TASK ; --p) {
		if (!*p)
			continue;
		if (current == *p)
			continue;
		if ((*p)->executable != current->executable)
			continue;
		if (try_to_share(address,*p))
			return 1;
	}
	return 0;
}

void do_no_page(unsigned long error_code,unsigned long address)
{
	int nr[4];
	unsigned long tmp;
	unsigned long page;
	int block,i;

	address &= 0xfffff000;
	tmp = address - current->start_code;
	if (!current->executable || tmp >= current->end_data) {
		get_empty_page(address);
		return;
	}
	if (share_page(tmp))
		return;
	if (!(page = get_free_page()))
		oom();
/* remember that 1 block is used for header */
	block = 1 + tmp/BLOCK_SIZE;
	for (i=0 ; i<4 ; block++,i++)
		nr[i] = bmap(current->executable,block);
	bread_page(page,current->executable->i_dev,nr);
	i = tmp + 4096 - current->end_data;
	tmp = page + 4096;
	while (i-- > 0) {
		tmp--;
		*(char *)tmp = 0;
	}
	if (put_page(page,address))
		return;
	free_page(page);
	oom();
}

void mem_init(long start_mem, long end_mem)
{
	int i;

	HIGH_MEMORY = end_mem;
	for (i=0 ; i<PAGING_PAGES ; i++)
		mem_map[i] = USED;
	i = MAP_NR(start_mem);
	end_mem -= start_mem;
	end_mem >>= 12;
	while (end_mem-->0)
		mem_map[i++]=0;
}

void calc_mem(void)
{
	int i,j,k,free=0;
	long * pg_tbl;

	for(i=0 ; i<PAGING_PAGES ; i++)
		if (!mem_map[i]) free++;
	printk("%d pages free (of %d)\n\r",free,PAGING_PAGES);
	for(i=2 ; i<1024 ; i++) {
		if (1&pg_dir[i]) {
			pg_tbl=(long *) (0xfffff000 & pg_dir[i]);
			for(j=k=0 ; j<1024 ; j++)
				if (pg_tbl[j]&1)
					k++;
			printk("Pg-dir[%d] uses %d pages\n",i,k);
		}
	}
}