path: root/arch/i386/kernel/process.c

/*
 *  linux/arch/i386/kernel/process.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 */

/*
 * This file handles the architecture-dependent parts of process handling..
 */

#define __KERNEL_SYSCALLS__
#include <stdarg.h>

#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/malloc.h>
#include <linux/vmalloc.h>
#include <linux/user.h>
#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/config.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/init.h>
#if defined(CONFIG_APM) && defined(CONFIG_APM_POWER_OFF)
#include <linux/apm_bios.h>
#endif

#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/ldt.h>
#include <asm/processor.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
#endif

#include <linux/irq.h>

spinlock_t semaphore_wake_lock = SPIN_LOCK_UNLOCKED;

asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");

int hlt_counter=0;

void disable_hlt(void)
{
	hlt_counter++;
}

void enable_hlt(void)
{
	hlt_counter--;
}

/*
 * Powermanagement idle function, if any..
 */
void (*acpi_idle)(void) = NULL;

/*
 * The idle thread. There's no useful work to be
 * done, so just try to conserve power and have a
 * low exit latency (ie sit in a loop waiting for
 * somebody to say that they'd like to reschedule)
 */
void cpu_idle(void)
{
	/* endless idle loop with no priority at all */
	init_idle();
	current->priority = 0;
	current->counter = -100;

	while (1) {
		while (!current->need_resched) {
			if (!current_cpu_data.hlt_works_ok)
				continue;
			if (hlt_counter)
				continue;
			asm volatile("sti ; hlt" : : : "memory");
		}
		schedule();
		check_pgt_cache();
		if (acpi_idle)
			acpi_idle();
	}
}

/*
 * This routine reboots the machine by asking the keyboard
 * controller to pulse the reset-line low. We try that for a while,
 * and if it doesn't work, we do some other stupid things.
 */

static long no_idt[2] = {0, 0};
static int reboot_mode = 0;
static int reboot_thru_bios = 0;

static int __init reboot_setup(char *str)
{
	while(1) {
		switch (*str) {
		case 'w': /* "warm" reboot (no memory testing etc) */
			reboot_mode = 0x1234;
			break;
		case 'c': /* "cold" reboot (with memory testing etc) */
			reboot_mode = 0x0;
			break;
		case 'b': /* "bios" reboot by jumping through the BIOS */
			reboot_thru_bios = 1;
			break;
		case 'h': /* "hard" reboot by toggling RESET and/or crashing the CPU */
			reboot_thru_bios = 0;
			break;
		}
		if((str = strchr(str,',')) != NULL)
			str++;
		else
			break;
	}
	return 1;
}

__setup("reboot=", reboot_setup);

/* The following code and data reboots the machine by switching to real
   mode and jumping to the BIOS reset entry point, as if the CPU has
   really been reset.  The previous version asked the keyboard
   controller to pulse the CPU reset line, which is more thorough, but
   doesn't work with at least one type of 486 motherboard.  It is easy
   to stop this code working; hence the copious comments. */

static unsigned long long
real_mode_gdt_entries [3] =
{
	0x0000000000000000ULL,	/* Null descriptor */
	0x00009a000000ffffULL,	/* 16-bit real-mode 64k code at 0x00000000 */
	0x000092000100ffffULL	/* 16-bit real-mode 64k data at 0x00000100 */
};

static struct
{
	unsigned short       size __attribute__ ((packed));
	unsigned long long * base __attribute__ ((packed));
}
real_mode_gdt = { sizeof (real_mode_gdt_entries) - 1, real_mode_gdt_entries },
real_mode_idt = { 0x3ff, 0 };

/* This is 16-bit protected mode code to disable paging and the cache,
   switch to real mode and jump to the BIOS reset code.

   The instruction that switches to real mode by writing to CR0 must be
   followed immediately by a far jump instruction, which set CS to a
   valid value for real mode, and flushes the prefetch queue to avoid
   running instructions that have already been decoded in protected
   mode.

   Clears all the flags except ET, especially PG (paging), PE
   (protected-mode enable) and TS (task switch for coprocessor state
   save).  Flushes the TLB after paging has been disabled.  Sets CD and
   NW, to disable the cache on a 486, and invalidates the cache.  This
   is more like the state of a 486 after reset.  I don't know if
   something else should be done for other chips.

   More could be done here to set up the registers as if a CPU reset had
   occurred; hopefully real BIOSs don't assume much. */

static unsigned char real_mode_switch [] =
{
	0x66, 0x0f, 0x20, 0xc0,			/*    movl  %cr0,%eax        */
	0x66, 0x83, 0xe0, 0x11,			/*    andl  $0x00000011,%eax */
	0x66, 0x0d, 0x00, 0x00, 0x00, 0x60,	/*    orl   $0x60000000,%eax */
	0x66, 0x0f, 0x22, 0xc0,			/*    movl  %eax,%cr0        */
	0x66, 0x0f, 0x22, 0xd8,			/*    movl  %eax,%cr3        */
	0x66, 0x0f, 0x20, 0xc3,			/*    movl  %cr0,%ebx        */
	0x66, 0x81, 0xe3, 0x00, 0x00, 0x00, 0x60,	/*    andl  $0x60000000,%ebx */
	0x74, 0x02,				/*    jz    f                */
	0x0f, 0x08,				/*    invd                   */
	0x24, 0x10,				/* f: andb  $0x10,al         */
	0x66, 0x0f, 0x22, 0xc0,			/*    movl  %eax,%cr0        */
	0xea, 0x00, 0x00, 0xff, 0xff		/*    ljmp  $0xffff,$0x0000  */
};

static inline void kb_wait(void)
{
	int i;

	for (i=0; i<0x10000; i++)
		if ((inb_p(0x64) & 0x02) == 0)
			break;
}

void machine_restart(char * __unused)
{
#if __SMP__
	/*
	 * turn off the IO-APIC, so we can do a clean reboot
	 */
	init_pic_mode();
#endif

	if(!reboot_thru_bios) {
		/* rebooting needs to touch the page at absolute addr 0 */
		*((unsigned short *)__va(0x472)) = reboot_mode;
		for (;;) {
			int i;
			for (i=0; i<100; i++) {
				kb_wait();
				udelay(50);
				outb(0xfe,0x64);         /* pulse reset low */
				udelay(50);
			}
			/* That didn't work - force a triple fault.. */
			__asm__ __volatile__("lidt %0": :"m" (no_idt));
			__asm__ __volatile__("int3");
		}
	}

	cli();

	/* Write zero to CMOS register number 0x0f, which the BIOS POST
	   routine will recognize as telling it to do a proper reboot.  (Well
	   that's what this book in front of me says -- it may only apply to
	   the Phoenix BIOS though, it's not clear).  At the same time,
	   disable NMIs by setting the top bit in the CMOS address register,
	   as we're about to do peculiar things to the CPU.  I'm not sure if
	   `outb_p' is needed instead of just `outb'.  Use it to be on the
	   safe side. */

	outb_p (0x8f, 0x70);
	outb_p (0x00, 0x71);

	/* Remap the kernel at virtual address zero, as well as offset zero
	   from the kernel segment.  This assumes the kernel segment starts at
	   virtual address PAGE_OFFSET. */

	memcpy (swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
		sizeof (swapper_pg_dir [0]) * KERNEL_PGD_PTRS);

	/* Make sure the first page is mapped to the start of physical memory.
	   It is normally not mapped, to trap kernel NULL pointer dereferences. */

	pg0[0] = _PAGE_RW | _PAGE_PRESENT;

	/*
	 * Use `swapper_pg_dir' as our page directory.
	 */
	asm volatile("movl %0,%%cr3": :"r" (__pa(swapper_pg_dir)));

	/* Write 0x1234 to absolute memory location 0x472.  The BIOS reads
	   this on booting to tell it to "Bypass memory test (also warm
	   boot)".  This seems like a fairly standard thing that gets set by
	   REBOOT.COM programs, and the previous reset routine did this
	   too. */

	*((unsigned short *)0x472) = reboot_mode;

	/* For the switch to real mode, copy some code to low memory.  It has
	   to be in the first 64k because it is running in 16-bit mode, and it
	   has to have the same physical and virtual address, because it turns
	   off paging.  Copy it near the end of the first page, out of the way
	   of BIOS variables. */

	memcpy ((void *) (0x1000 - sizeof (real_mode_switch)),
		real_mode_switch, sizeof (real_mode_switch));

	/* Set up the IDT for real mode. */

	__asm__ __volatile__ ("lidt %0" : : "m" (real_mode_idt));

	/* Set up a GDT from which we can load segment descriptors for real
	   mode.  The GDT is not used in real mode; it is just needed here to
	   prepare the descriptors. */

	__asm__ __volatile__ ("lgdt %0" : : "m" (real_mode_gdt));

	/* Load the data segment registers, and thus the descriptors ready for
	   real mode.  The base address of each segment is 0x100, 16 times the
	   selector value being loaded here.  This is so that the segment
	   registers don't have to be reloaded after switching to real mode:
	   the values are consistent for real mode operation already. */

	__asm__ __volatile__ ("movl $0x0010,%%eax\n"
				"\tmovl %%ax,%%ds\n"
				"\tmovl %%ax,%%es\n"
				"\tmovl %%ax,%%fs\n"
				"\tmovl %%ax,%%gs\n"
				"\tmovl %%ax,%%ss" : : : "eax");

	/* Jump to the 16-bit code that we copied earlier.  It disables paging
	   and the cache, switches to real mode, and jumps to the BIOS reset
	   entry point. */

	__asm__ __volatile__ ("ljmp $0x0008,%0"
				:
				: "i" ((void *) (0x1000 - sizeof (real_mode_switch))));
}

void machine_halt(void)
{
}

void machine_power_off(void)
{
#if defined(CONFIG_APM) && defined(CONFIG_APM_POWER_OFF)
	apm_power_off();
#endif
}


void show_regs(struct pt_regs * regs)
{
	long cr0 = 0L, cr2 = 0L, cr3 = 0L;

	printk("\n");
	printk("EIP: %04x:[<%08lx>]",0xffff & regs->xcs,regs->eip);
	if (regs->xcs & 3)
		printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
	printk(" EFLAGS: %08lx\n",regs->eflags);
	printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
		regs->eax,regs->ebx,regs->ecx,regs->edx);
	printk("ESI: %08lx EDI: %08lx EBP: %08lx",
		regs->esi, regs->edi, regs->ebp);
	printk(" DS: %04x ES: %04x\n",
		0xffff & regs->xds,0xffff & regs->xes);

	__asm__("movl %%cr0, %0": "=r" (cr0));
	__asm__("movl %%cr2, %0": "=r" (cr2));
	__asm__("movl %%cr3, %0": "=r" (cr3));
	printk("CR0: %08lx CR2: %08lx CR3: %08lx\n", cr0, cr2, cr3);
}

/*
 * Allocation and freeing of basic task resources.
 *
 * NOTE! The task struct and the stack go together
 *
 * The task structure is a two-page thing, and as such
 * not reliable to allocate using the basic page alloc
 * functions. We have a small cache of structures for
 * when the allocations fail..
 *
 * This extra buffer essentially acts to make for less
 * "jitter" in the allocations..
 *
 * On SMP we don't do this right now because:
 *  - we aren't holding any locks when called, and we might
 *    as well just depend on the generic memory management
 *    to do proper locking for us instead of complicating it
 *    here.
 *  - if you use SMP you have a beefy enough machine that
 *    this shouldn't matter..
 */
#ifndef __SMP__
#define EXTRA_TASK_STRUCT	16
static struct task_struct * task_struct_stack[EXTRA_TASK_STRUCT];
static int task_struct_stack_ptr = -1;
#endif

struct task_struct * alloc_task_struct(void)
{
#ifndef EXTRA_TASK_STRUCT
	return (struct task_struct *) __get_free_pages(GFP_KERNEL,1);
#else
	int index;
	struct task_struct *ret;

	index = task_struct_stack_ptr;
	if (index >= EXTRA_TASK_STRUCT/2)
		goto use_cache;
	ret = (struct task_struct *) __get_free_pages(GFP_KERNEL,1);
	if (!ret) {
		index = task_struct_stack_ptr;
		if (index >= 0) {
use_cache:
			ret = task_struct_stack[index];
			task_struct_stack_ptr = index-1;
		}
	}
	return ret;
#endif
}

void free_task_struct(struct task_struct *p)
{
#ifdef EXTRA_TASK_STRUCT
	int index = task_struct_stack_ptr+1;

	if (index < EXTRA_TASK_STRUCT) {
		task_struct_stack[index] = p;
		task_struct_stack_ptr = index;
	} else
#endif
		free_pages((unsigned long) p, 1);
}

/*
 * No need to lock the MM as we are the last user
 */
void release_segments(struct mm_struct *mm)
{
	void * ldt = mm->segments;

	/*
	 * free the LDT
	 */
	if (ldt) {
		mm->segments = NULL;
		clear_LDT();
		vfree(ldt);
	}
}

void forget_segments(void)
{
	/* forget local segments */
	__asm__ __volatile__("movl %w0,%%fs ; movl %w0,%%gs"
		: /* no outputs */
		: "r" (0));

	/*
	 * Load the LDT entry of init_task.
	 */
	load_LDT(&init_mm);
}

/*
 * Create a kernel thread
 */
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
{
	long retval, d0;

	__asm__ __volatile__(
		"movl %%esp,%%esi\n\t"
		"int $0x80\n\t"		/* Linux/i386 system call */
		"cmpl %%esp,%%esi\n\t"	/* child or parent? */
		"je 1f\n\t"		/* parent - jump */
		/* Load the argument into eax, and push it.  That way, it does
		 * not matter whether the called function is compiled with
		 * -mregparm or not.  */
		"movl %4,%%eax\n\t"
		"pushl %%eax\n\t"		
		"call *%5\n\t"		/* call fn */
		"movl %3,%0\n\t"	/* exit */
		"int $0x80\n"
		"1:\t"
		:"=&a" (retval), "=&S" (d0)
		:"0" (__NR_clone), "i" (__NR_exit),
		 "r" (arg), "r" (fn),
		 "b" (flags | CLONE_VM)
		: "memory");
	return retval;
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	/* nothing to do ... */
}

void flush_thread(void)
{
	struct task_struct *tsk = current;

	memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
	/*
	 * Forget coprocessor state..
	 */
	clear_fpu(tsk);
	tsk->used_math = 0;
}

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		void * ldt = dead_task->mm->segments;

		// temporary debugging check
		if (ldt) {
			printk("WARNING: dead process %8s still has LDT? <%p>\n",
					dead_task->comm, ldt);
			BUG();
		}
	}
}

/*
 * we do not have to muck with descriptors here, that is
 * done in switch_mm() as needed.
 */
void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
{
	struct mm_struct * old_mm = current->mm;
	void * old_ldt = old_mm->segments, * ldt = old_ldt;

	if (!old_mm->segments) {
		/*
		 * default LDT - use the one from init_task
		 */
		new_mm->segments = NULL;
		return;
	}

	/*
	 * Completely new LDT, we initialize it from the parent:
	 */
	ldt = vmalloc(LDT_ENTRIES*LDT_ENTRY_SIZE);
	if (!ldt)
		printk(KERN_WARNING "ldt allocation failed\n");
	else
		memcpy(ldt, old_ldt, LDT_ENTRIES*LDT_ENTRY_SIZE);
	new_mm->segments = ldt;
	return;
}

/*
 * Save a segment.
 */
#define savesegment(seg,value) \
	asm volatile("movl %%" #seg ",%0":"=m" (*(int *)&(value)))

int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
	struct task_struct * p, struct pt_regs * regs)
{
	struct pt_regs * childregs;

	childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p)) - 1;
	*childregs = *regs;
	childregs->eax = 0;
	childregs->esp = esp;

	p->thread.esp = (unsigned long) childregs;
	p->thread.esp0 = (unsigned long) (childregs+1);

	p->thread.eip = (unsigned long) ret_from_fork;

	savesegment(fs,p->thread.fs);
	savesegment(gs,p->thread.gs);

	unlazy_fpu(current);
	p->thread.i387 = current->thread.i387;

	return 0;
}

/*
 * fill in the FPU structure for a core dump.
 */
int dump_fpu (struct pt_regs * regs, struct user_i387_struct* fpu)
{
	int fpvalid;
	struct task_struct *tsk = current;

	fpvalid = tsk->used_math;
	if (fpvalid) {
		unlazy_fpu(tsk);
		memcpy(fpu,&tsk->thread.i387.hard,sizeof(*fpu));
	}

	return fpvalid;
}

/*
 * fill in the user structure for a core dump..
 */
void dump_thread(struct pt_regs * regs, struct user * dump)
{
	int i;

/* changed the size calculations - should hopefully work better. lbt */
	dump->magic = CMAGIC;
	dump->start_code = 0;
	dump->start_stack = regs->esp & ~(PAGE_SIZE - 1);
	dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT;
	dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT;
	dump->u_dsize -= dump->u_tsize;
	dump->u_ssize = 0;
	for (i = 0; i < 8; i++)
		dump->u_debugreg[i] = current->thread.debugreg[i];  

	if (dump->start_stack < TASK_SIZE)
		dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT;

	dump->regs.ebx = regs->ebx;
	dump->regs.ecx = regs->ecx;
	dump->regs.edx = regs->edx;
	dump->regs.esi = regs->esi;
	dump->regs.edi = regs->edi;
	dump->regs.ebp = regs->ebp;
	dump->regs.eax = regs->eax;
	dump->regs.ds = regs->xds;
	dump->regs.es = regs->xes;
	savesegment(fs,dump->regs.fs);
	savesegment(gs,dump->regs.gs);
	dump->regs.orig_eax = regs->orig_eax;
	dump->regs.eip = regs->eip;
	dump->regs.cs = regs->xcs;
	dump->regs.eflags = regs->eflags;
	dump->regs.esp = regs->esp;
	dump->regs.ss = regs->xss;

	dump->u_fpvalid = dump_fpu (regs, &dump->i387);
}

/*
 * This special macro can be used to load a debugging register
 */
#define loaddebug(thread,register) \
		__asm__("movl %0,%%db" #register  \
			: /* no output */ \
			:"r" (thread->debugreg[register]))

/*
 *	switch_to(x,yn) should switch tasks from x to y.
 *
 * We fsave/fwait so that an exception goes off at the right time
 * (as a call from the fsave or fwait in effect) rather than to
 * the wrong process. Lazy FP saving no longer makes any sense
 * with modern CPU's, and this simplifies a lot of things (SMP
 * and UP become the same).
 *
 * NOTE! We used to use the x86 hardware context switching. The
 * reason for not using it any more becomes apparent when you
 * try to recover gracefully from saved state that is no longer
 * valid (stale segment register values in particular). With the
 * hardware task-switch, there is no way to fix up bad state in
 * a reasonable manner.
 *
 * The fact that Intel documents the hardware task-switching to
 * be slow is a fairly red herring - this code is not noticeably
 * faster. However, there _is_ some room for improvement here,
 * so the performance issues may eventually be a valid point.
 * More important, however, is the fact that this allows us much
 * more flexibility.
 */
extern int cpus_initialized;
void __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread,
				 *next = &next_p->thread;
	struct tss_struct *tss = init_tss + smp_processor_id();

	unlazy_fpu(prev_p);

	/*
	 * Reload esp0, LDT and the page table pointer:
	 */
	tss->esp0 = next->esp0;

	/*
	 * Save away %fs and %gs. No need to save %es and %ds, as
	 * those are always kernel segments while inside the kernel.
	 */
	asm volatile("movl %%fs,%0":"=m" (*(int *)&prev->fs));
	asm volatile("movl %%gs,%0":"=m" (*(int *)&prev->gs));

	/*
	 * Restore %fs and %gs.
	 */
	loadsegment(fs, next->fs);
	loadsegment(gs, next->gs);

	/*
	 * Now maybe reload the debug registers
	 */
	if (next->debugreg[7]){
		loaddebug(next, 0);
		loaddebug(next, 1);
		loaddebug(next, 2);
		loaddebug(next, 3);
		/* no 4 and 5 */
		loaddebug(next, 6);
		loaddebug(next, 7);
	}

	if (prev->ioperm || next->ioperm) {
		if (next->ioperm) {
			/*
			 * 4 cachelines copy ... not good, but not that
			 * bad either. Anyone got something better?
			 * This only affects processes which use ioperm().
			 * [Putting the TSSs into 4k-tlb mapped regions
			 * and playing VM tricks to switch the IO bitmap
			 * is not really acceptable.]
			 */
			memcpy(tss->io_bitmap, next->io_bitmap,
				 IO_BITMAP_SIZE*sizeof(unsigned long));
			tss->bitmap = IO_BITMAP_OFFSET;
		} else
			/*
			 * a bitmap offset pointing outside of the TSS limit
			 * causes a nicely controllable SIGSEGV if a process
			 * tries to use a port IO instruction. The first
			 * sys_ioperm() call sets up the bitmap properly.
			 */
			tss->bitmap = INVALID_IO_BITMAP_OFFSET;
	}
}

asmlinkage int sys_fork(struct pt_regs regs)
{
	return do_fork(SIGCHLD, regs.esp, &regs);
}

asmlinkage int sys_clone(struct pt_regs regs)
{
	unsigned long clone_flags;
	unsigned long newsp;

	clone_flags = regs.ebx;
	newsp = regs.ecx;
	if (!newsp)
		newsp = regs.esp;
	return do_fork(clone_flags, newsp, &regs);
}

/*
 * This is trivial, and on the face of it looks like it
 * could equally well be done in user mode.
 *
 * Not so, for quite unobvious reasons - register pressure.
 * In user mode vfork() cannot have a stack frame, and if
 * done by calling the "clone()" system call directly, you
 * do not have enough call-clobbered registers to hold all
 * the information you need.
 */
asmlinkage int sys_vfork(struct pt_regs regs)
{
	return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, &regs);
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage int sys_execve(struct pt_regs regs)
{
	int error;
	char * filename;

	lock_kernel();
	filename = getname((char *) regs.ebx);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;
	error = do_execve(filename, (char **) regs.ecx, (char **) regs.edx, &regs);
	if (error == 0)
		current->flags &= ~PF_DTRACE;
	putname(filename);
out:
	unlock_kernel();
	return error;
}