process.c

底层驱动开发

/*
 *  linux/arch/x86-64/kernel/process.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 * 
 *  X86-64 port
 *	Andi Kleen.
 *
 *	CPU hotplug support - [e-mail]
 *  $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $
 */

/*
 * 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/kernel.h>
#include <linux/mm.h>
#include <linux/elfcore.h>
#include <linux/smp.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/module.h>
#include <linux/a.out.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/ptrace.h>
#include <linux/utsname.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/processor.h>
#include <asm/i387.h>
#include <asm/mmu_context.h>
#include <asm/pda.h>
#include <asm/prctl.h>
#include <asm/kdebug.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>

asmlinkage extern void ret_from_fork(void);

unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;

static atomic_t hlt_counter = ATOMIC_INIT(0);

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);

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

void disable_hlt(void)
{
	atomic_inc(&hlt_counter);
}

EXPORT_SYMBOL(disable_hlt);

void enable_hlt(void)
{
	atomic_dec(&hlt_counter);
}

EXPORT_SYMBOL(enable_hlt);

/*
 * We use this if we don't have any better
 * idle routine..
 */
void default_idle(void)
{
	if (!atomic_read(&hlt_counter)) {
		local_irq_disable();
		if (!need_resched())
			safe_halt();
		else
			local_irq_enable();
	}
}

/*
 * On SMP it's slightly faster (but much more power-consuming!)
 * to poll the ->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();
	}
}

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);

#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);

#include <asm/nmi.h>
/* We don't actually take CPU down, just spin without interrupts. */
static inline void play_dead(void)
{
	idle_task_exit();
	wbinvd();
	mb();
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	while (1)
		safe_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)
{
	/* 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(smp_processor_id()))
				play_dead();
			idle();
		}

		schedule();
	}
}

/*
 * 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 __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
	static int printed;
	if (cpu_has(c, X86_FEATURE_MWAIT)) {
		/*
		 * Skip, if setup has overridden idle.
		 * One CPU supports mwait => All CPUs supports mwait
		 */
		if (!pm_idle) {
			if (!printed) {
				printk("using mwait in idle threads.\n");
				printed = 1;
			}
			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;
	}

	boot_option_idle_override = 1;
	return 1;
}

__setup("idle=", idle_setup);

/* Prints also some state that isn't saved in the pt_regs */ 
void __show_regs(struct pt_regs * regs)
{
	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs;
	unsigned int fsindex,gsindex;
	unsigned int ds,cs,es; 

	printk("\n");
	print_modules();
	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
		current->pid, current->comm, print_tainted(),
		system_utsname.release,
		(int)strcspn(system_utsname.version, " "),
		system_utsname.version);
	printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
	printk_address(regs->rip); 
	printk("\nRSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss, regs->rsp, regs->eflags);
	printk("RAX: %016lx RBX: %016lx RCX: %016lx\n",
	       regs->rax, regs->rbx, regs->rcx);
	printk("RDX: %016lx RSI: %016lx RDI: %016lx\n",
	       regs->rdx, regs->rsi, regs->rdi); 
	printk("RBP: %016lx R08: %016lx R09: %016lx\n",
	       regs->rbp, regs->r8, regs->r9); 
	printk("R10: %016lx R11: %016lx R12: %016lx\n",
	       regs->r10, regs->r11, regs->r12); 
	printk("R13: %016lx R14: %016lx R15: %016lx\n",
	       regs->r13, regs->r14, regs->r15); 

	asm("movl %%ds,%0" : "=r" (ds)); 
	asm("movl %%cs,%0" : "=r" (cs)); 
	asm("movl %%es,%0" : "=r" (es)); 
	asm("movl %%fs,%0" : "=r" (fsindex));
	asm("movl %%gs,%0" : "=r" (gsindex));

	rdmsrl(MSR_FS_BASE, fs);
	rdmsrl(MSR_GS_BASE, gs); 
	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); 

	asm("movq %%cr0, %0": "=r" (cr0));
	asm("movq %%cr2, %0": "=r" (cr2));
	asm("movq %%cr3, %0": "=r" (cr3));
	asm("movq %%cr4, %0": "=r" (cr4));

	printk("FS:  %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", 
	       fs,fsindex,gs,gsindex,shadowgs); 
	printk("CS:  %04x DS: %04x ES: %04x CR0: %016lx\n", cs, ds, es, cr0); 
	printk("CR2: %016lx CR3: %016lx CR4: %016lx\n", cr2, cr3, cr4);
}

void show_regs(struct pt_regs *regs)
{
	printk("CPU %d:", smp_processor_id());
	__show_regs(regs);
	show_trace(&regs->rsp);
}

/*
 * Free current thread data structures etc..
 */
void exit_thread(void)
{
	struct task_struct *me = current;
	struct thread_struct *t = &me->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(me);

	if (me->thread.io_bitmap_ptr) { 
		struct tss_struct *tss = &per_cpu(init_tss, get_cpu());

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

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

	/*
	 * 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);

	if (t->flags & _TIF_ABI_PENDING)
		t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32);

	tsk->thread.debugreg0 = 0;
	tsk->thread.debugreg1 = 0;
	tsk->thread.debugreg2 = 0;
	tsk->thread.debugreg3 = 0;
	tsk->thread.debugreg6 = 0;
	tsk->thread.debugreg7 = 0;
	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) {
		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();
		}
	}
}

static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr)
{
	struct user_desc ud = { 
		.base_addr = addr,
		.limit = 0xfffff,
		.seg_32bit = 1,
		.limit_in_pages = 1,
		.useable = 1,
	};
	struct n_desc_struct *desc = (void *)t->thread.tls_array;
	desc += tls;
	desc->a = LDT_entry_a(&ud); 
	desc->b = LDT_entry_b(&ud); 
}

static inline u32 read_32bit_tls(struct task_struct *t, int tls)
{
	struct desc_struct *desc = (void *)t->thread.tls_array;