process.c

底层驱动开发

/*
 *  linux/arch/i386/kernel/process.c
 *
 *  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/smp_lock.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/config.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/kprobes.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>
#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);

/*
 * 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) {
		local_irq_disable();
		if (!need_resched())
			safe_halt();
		else
			local_irq_enable();
	} else {
		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)
{
	int oldval;

	local_irq_enable();

	/*
	 * Deal with another CPU just having chosen a thread to
	 * run here:
	 */
	oldval = test_and_clear_thread_flag(TIF_NEED_RESCHED);

	if (!oldval) {
		set_thread_flag(TIF_POLLING_NRFLAG);
		asm volatile(
			"2:"
			"testl %0, %1;"
			"rep; nop;"
			"je 2b;"
			: : "i"(_TIF_NEED_RESCHED), "m" (current_thread_info()->flags));

		clear_thread_flag(TIF_POLLING_NRFLAG);
	} else {
		set_need_resched();
	}
}

#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 = raw_smp_processor_id();

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

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

			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();
		}
		schedule();
	}
}

void cpu_idle_wait(void)
{
	unsigned int cpu, this_cpu = get_cpu();
	cpumask_t map;

	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);
	} while (!cpus_empty(map));
}
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).
 */
static void mwait_idle(void)
{
	local_irq_enable();

	if (!need_resched()) {
		set_thread_flag(TIF_POLLING_NRFLAG);
		do {
			__monitor((void *)&current_thread_info()->flags, 0, 0);
			if (need_resched())
				break;
			__mwait(0, 0);
		} while (!need_resched());
		clear_thread_flag(TIF_POLLING_NRFLAG);
	}
}

void __devinit 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 (!strncmp(str, "poll", 4)) {
		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 (!strncmp(str, "halt", 4)) {
		printk("using halt in idle threads.\n");
		pm_idle = default_idle;
	}

	boot_option_idle_override = 1;
	return 1;
}

__setup("idle=", idle_setup);

void show_regs(struct pt_regs * regs)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;

	printk("\n");
	printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
	printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id());
	print_symbol("EIP is at %s\n", regs->eip);

	if (user_mode(regs))
		printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
	printk(" EFLAGS: %08lx    %s  (%s)\n",
	       regs->eflags, print_tainted(), system_utsname.release);
	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);

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	if (current_cpu_data.x86 > 4) {
		cr4 = read_cr4();
	}
	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
	show_trace(NULL, &regs->esp);
}

/*
 * This gets run with %ebx containing the
 * function to call, and %edx containing
 * the "args".
 */
extern void kernel_thread_helper(void);
__asm__(".section .text\n"
	".align 4\n"
	"kernel_thread_helper:\n\t"
	"movl %edx,%eax\n\t"
	"pushl %edx\n\t"
	"call *%ebx\n\t"
	"pushl %eax\n\t"
	"call do_exit\n"
	".previous");

/*
 * 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.orig_eax = -1;
	regs.eip = (unsigned long) kernel_thread_helper;
	regs.xcs = __KERNEL_CS;
	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)
{
	struct task_struct *tsk = current;
	struct thread_struct *t = &tsk->thread;

	/*
	 * Remove function-return probe instances associated with this task
	 * and put them back on the free list. Do not insert an exit probe for
	 * this function, it will be disabled by kprobe_flush_task if you do.
	 */
	kprobe_flush_task(tsk);

	/* The process may have allocated an io port bitmap... nuke it. */
	if (unlikely(NULL != t->io_bitmap_ptr)) {
		int cpu = get_cpu();
		struct tss_struct *tss = &per_cpu(init_tss, cpu);

		kfree(t->io_bitmap_ptr);
		t->io_bitmap_ptr = NULL;
		/*
		 * 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->io_bitmap_base = INVALID_IO_BITMAP_OFFSET;
		put_cpu();
	}
}

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

	/*
	 * Remove function-return probe instances associated with this task
	 * and put them back on the free list. Do not insert an exit probe for
	 * this function, it will be disabled by kprobe_flush_task if you do.
	 */
	kprobe_flush_task(tsk);

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

void release_thread(struct task_struct *dead_task)
{
	if (dead_task->mm) {
		// temporary debugging check
		if (dead_task->mm->context.size) {
			printk("WARNING: dead process %8s still has LDT? <%p/%d>\n",
					dead_task->comm,
					dead_task->mm->context.ldt,
					dead_task->mm->context.size);
			BUG();
		}
	}

	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 = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1;
	/*
	 * The below -8 is to reserve 8 bytes on top of the ring0 stack.
	 * This is necessary to guarantee that the entire "struct pt_regs"
	 * is accessable even if the CPU haven't stored the SS/ESP registers
	 * on the stack (interrupt gate does not save these registers
	 * when switching to the same priv ring).
	 * Therefore beware: accessing the xss/esp fields of the
	 * "struct pt_regs" is possible, but they may contain the
	 * completely wrong values.
	 */
	childregs = (struct pt_regs *) ((unsigned long) childregs - 8);
	*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);

	tsk = current;