process_32.c

linux 内核源代码

/*
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 */

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

#include <stdarg.h>

#include <linux/cpu.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/user.h>
#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/utsname.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/init.h>
#include <linux/mc146818rtc.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/random.h>
#include <linux/personality.h>
#include <linux/tick.h>
#include <linux/percpu.h>

#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/i387.h>
#include <asm/desc.h>
#include <asm/vm86.h>
#ifdef CONFIG_MATH_EMULATION
#include <asm/math_emu.h>
#endif

#include <linux/err.h>

#include <asm/tlbflush.h>
#include <asm/cpu.h>

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

static int hlt_counter;

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);

DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);

DEFINE_PER_CPU(int, cpu_number);
EXPORT_PER_CPU_SYMBOL(cpu_number);

/*
 * Return saved PC of a blocked thread.
 */
unsigned long thread_saved_pc(struct task_struct *tsk)
{
	return ((unsigned long *)tsk->thread.esp)[3];
}

/*
 * Powermanagement idle function, if any..
 */
void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);

void disable_hlt(void)
{
	hlt_counter++;
}

EXPORT_SYMBOL(disable_hlt);

void enable_hlt(void)
{
	hlt_counter--;
}

EXPORT_SYMBOL(enable_hlt);

/*
 * We use this if we don't have any better
 * idle routine..
 */
void default_idle(void)
{
	if (!hlt_counter && boot_cpu_data.hlt_works_ok) {
		current_thread_info()->status &= ~TS_POLLING;
		/*
		 * TS_POLLING-cleared state must be visible before we
		 * test NEED_RESCHED:
		 */
		smp_mb();

		local_irq_disable();
		if (!need_resched())
			safe_halt();	/* enables interrupts racelessly */
		else
			local_irq_enable();
		current_thread_info()->status |= TS_POLLING;
	} else {
		/* loop is done by the caller */
		cpu_relax();
	}
}
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(default_idle);
#endif

/*
 * On SMP it's slightly faster (but much more power-consuming!)
 * to poll the ->work.need_resched flag instead of waiting for the
 * cross-CPU IPI to arrive. Use this option with caution.
 */
static void poll_idle (void)
{
	cpu_relax();
}

#ifdef CONFIG_HOTPLUG_CPU
#include <asm/nmi.h>
/* We don't actually take CPU down, just spin without interrupts. */
static inline void play_dead(void)
{
	/* This must be done before dead CPU ack */
	cpu_exit_clear();
	wbinvd();
	mb();
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	/*
	 * With physical CPU hotplug, we should halt the cpu
	 */
	local_irq_disable();
	while (1)
		halt();
}
#else
static inline void play_dead(void)
{
	BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */

/*
 * 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)
{
	int cpu = smp_processor_id();

	current_thread_info()->status |= TS_POLLING;

	/* endless idle loop with no priority at all */
	while (1) {
		tick_nohz_stop_sched_tick();
		while (!need_resched()) {
			void (*idle)(void);

			if (__get_cpu_var(cpu_idle_state))
				__get_cpu_var(cpu_idle_state) = 0;

			check_pgt_cache();
			rmb();
			idle = pm_idle;

			if (!idle)
				idle = default_idle;

			if (cpu_is_offline(cpu))
				play_dead();

			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
			idle();
		}
		tick_nohz_restart_sched_tick();
		preempt_enable_no_resched();
		schedule();
		preempt_disable();
	}
}

static void do_nothing(void *unused)
{
}

void cpu_idle_wait(void)
{
	unsigned int cpu, this_cpu = get_cpu();
	cpumask_t map, tmp = current->cpus_allowed;

	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
	put_cpu();

	cpus_clear(map);
	for_each_online_cpu(cpu) {
		per_cpu(cpu_idle_state, cpu) = 1;
		cpu_set(cpu, map);
	}

	__get_cpu_var(cpu_idle_state) = 0;

	wmb();
	do {
		ssleep(1);
		for_each_online_cpu(cpu) {
			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
				cpu_clear(cpu, map);
		}
		cpus_and(map, map, cpu_online_map);
		/*
		 * We waited 1 sec, if a CPU still did not call idle
		 * it may be because it is in idle and not waking up
		 * because it has nothing to do.
		 * Give all the remaining CPUS a kick.
		 */
		smp_call_function_mask(map, do_nothing, 0, 0);
	} while (!cpus_empty(map));

	set_cpus_allowed(current, tmp);
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);

/*
 * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
 * which can obviate IPI to trigger checking of need_resched.
 * We execute MONITOR against need_resched and enter optimized wait state
 * through MWAIT. Whenever someone changes need_resched, we would be woken
 * up from MWAIT (without an IPI).
 *
 * New with Core Duo processors, MWAIT can take some hints based on CPU
 * capability.
 */
void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
{
	if (!need_resched()) {
		__monitor((void *)&current_thread_info()->flags, 0, 0);
		smp_mb();
		if (!need_resched())
			__mwait(eax, ecx);
	}
}

/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
	local_irq_enable();
	mwait_idle_with_hints(0, 0);
}

void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
	if (cpu_has(c, X86_FEATURE_MWAIT)) {
		printk("monitor/mwait feature present.\n");
		/*
		 * Skip, if setup has overridden idle.
		 * One CPU supports mwait => All CPUs supports mwait
		 */
		if (!pm_idle) {
			printk("using mwait in idle threads.\n");
			pm_idle = mwait_idle;
		}
	}
}

static int __init idle_setup(char *str)
{
	if (!strcmp(str, "poll")) {
		printk("using polling idle threads.\n");
		pm_idle = poll_idle;
#ifdef CONFIG_X86_SMP
		if (smp_num_siblings > 1)
			printk("WARNING: polling idle and HT enabled, performance may degrade.\n");
#endif
	} else if (!strcmp(str, "mwait"))
		force_mwait = 1;
	else
		return -1;

	boot_option_idle_override = 1;
	return 0;
}
early_param("idle", idle_setup);

void __show_registers(struct pt_regs *regs, int all)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
	unsigned long d0, d1, d2, d3, d6, d7;
	unsigned long esp;
	unsigned short ss, gs;

	if (user_mode_vm(regs)) {
		esp = regs->esp;
		ss = regs->xss & 0xffff;
		savesegment(gs, gs);
	} else {
		esp = (unsigned long) (&regs->esp);
		savesegment(ss, ss);
		savesegment(gs, gs);
	}

	printk("\n");
	printk("Pid: %d, comm: %s %s (%s %.*s)\n",
			task_pid_nr(current), current->comm,
			print_tainted(), init_utsname()->release,
			(int)strcspn(init_utsname()->version, " "),
			init_utsname()->version);

	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
			0xffff & regs->xcs, regs->eip, regs->eflags,
			smp_processor_id());
	print_symbol("EIP is at %s\n", regs->eip);

	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 ESP: %08lx\n",
		regs->esi, regs->edi, regs->ebp, esp);
	printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
	       regs->xds & 0xffff, regs->xes & 0xffff,
	       regs->xfs & 0xffff, gs, ss);

	if (!all)
		return;

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = read_cr4_safe();
	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
			cr0, cr2, cr3, cr4);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	get_debugreg(d3, 3);
	printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
			d0, d1, d2, d3);

	get_debugreg(d6, 6);
	get_debugreg(d7, 7);
	printk("DR6: %08lx DR7: %08lx\n",
			d6, d7);
}

void show_regs(struct pt_regs *regs)
{
	__show_registers(regs, 1);
	show_trace(NULL, regs, &regs->esp);
}

/*
 * This gets run with %ebx containing the
 * function to call, and %edx containing
 * the "args".
 */
extern void kernel_thread_helper(void);

/*
 * Create a kernel thread
 */
int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
{
	struct pt_regs regs;

	memset(&regs, 0, sizeof(regs));

	regs.ebx = (unsigned long) fn;
	regs.edx = (unsigned long) arg;

	regs.xds = __USER_DS;
	regs.xes = __USER_DS;
	regs.xfs = __KERNEL_PERCPU;
	regs.orig_eax = -1;
	regs.eip = (unsigned long) kernel_thread_helper;
	regs.xcs = __KERNEL_CS | get_kernel_rpl();
	regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;

	/* Ok, create the new process.. */
	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
}
EXPORT_SYMBOL(kernel_thread);

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	/* The process may have allocated an io port bitmap... nuke it. */
	if (unlikely(test_thread_flag(TIF_IO_BITMAP))) {
		struct task_struct *tsk = current;
		struct thread_struct *t = &tsk->thread;
		int cpu = get_cpu();
		struct tss_struct *tss = &per_cpu(init_tss, cpu);

		kfree(t->io_bitmap_ptr);
		t->io_bitmap_ptr = NULL;
		clear_thread_flag(TIF_IO_BITMAP);
		/*
		 * Careful, clear this in the TSS too:
		 */
		memset(tss->io_bitmap, 0xff, tss->io_bitmap_max);
		t->io_bitmap_max = 0;
		tss->io_bitmap_owner = NULL;
		tss->io_bitmap_max = 0;
		tss->x86_tss.io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
		put_cpu();
	}
}

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

	memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));	
	clear_tsk_thread_flag(tsk, TIF_DEBUG);
	/*
	 * Forget coprocessor state..
	 */
	clear_fpu(tsk);
	clear_used_math();
}

void release_thread(struct task_struct *dead_task)
{
	BUG_ON(dead_task->mm);
	release_vm86_irqs(dead_task);
}

/*
 * This gets called before we allocate a new thread and copy
 * the current task into it.
 */
void prepare_to_copy(struct task_struct *tsk)
{
	unlazy_fpu(tsk);
}

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

	childregs = task_pt_regs(p);
	*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(gs,p->thread.gs);

	tsk = current;
	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
		p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
						IO_BITMAP_BYTES, GFP_KERNEL);
		if (!p->thread.io_bitmap_ptr) {
			p->thread.io_bitmap_max = 0;
			return -ENOMEM;
		}
		set_tsk_thread_flag(p, TIF_IO_BITMAP);
	}