process_64.c

linux 内核源代码

/*
 *  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]
 */

/*
 * 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/fs.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/notifier.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/tick.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/desc.h>
#include <asm/proto.h>
#include <asm/ia32.h>
#include <asm/idle.h>

asmlinkage extern void ret_from_fork(void);

unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);

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

static ATOMIC_NOTIFIER_HEAD(idle_notifier);

void idle_notifier_register(struct notifier_block *n)
{
	atomic_notifier_chain_register(&idle_notifier, n);
}
EXPORT_SYMBOL_GPL(idle_notifier_register);

void idle_notifier_unregister(struct notifier_block *n)
{
	atomic_notifier_chain_unregister(&idle_notifier, n);
}
EXPORT_SYMBOL(idle_notifier_unregister);

void enter_idle(void)
{
	write_pda(isidle, 1);
	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}

static void __exit_idle(void)
{
	if (test_and_clear_bit_pda(0, isidle) == 0)
		return;
	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
}

/* Called from interrupts to signify idle end */
void exit_idle(void)
{
	/* idle loop has pid 0 */
	if (current->pid)
		return;
	__exit_idle();
}

/*
 * We use this if we don't have any better
 * idle routine..
 */
static void default_idle(void)
{
	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()) {
		/* Enables interrupts one instruction before HLT.
		   x86 special cases this so there is no race. */
		safe_halt();
	} else
		local_irq_enable();
	current_thread_info()->status |= TS_POLLING;
}

/*
 * 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)
{
	local_irq_enable();
	cpu_relax();
}

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);

#ifdef CONFIG_HOTPLUG_CPU
DECLARE_PER_CPU(int, cpu_state);

#include <asm/nmi.h>
/* We halt the CPU with physical CPU hotplug */
static inline void play_dead(void)
{
	idle_task_exit();
	wbinvd();
	mb();
	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	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)
{
	current_thread_info()->status |= TS_POLLING;
	/* 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;

			tick_nohz_stop_sched_tick();

			rmb();
			idle = pm_idle;
			if (!idle)
				idle = default_idle;
			if (cpu_is_offline(smp_processor_id()))
				play_dead();
			/*
			 * Idle routines should keep interrupts disabled
			 * from here on, until they go to idle.
			 * Otherwise, idle callbacks can misfire.
			 */
			local_irq_disable();
			enter_idle();
			idle();
			/* In many cases the interrupt that ended idle
			   has already called exit_idle. But some idle
			   loops can be woken up without interrupt. */
			__exit_idle();
		}

		tick_nohz_restart_sched_tick();
		preempt_enable_no_resched();
		schedule();
		preempt_disable();
	}
}

/*
 * 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)
{
	if (!need_resched()) {
		__monitor((void *)&current_thread_info()->flags, 0, 0);
		smp_mb();
		if (!need_resched())
			__sti_mwait(0, 0);
		else
			local_irq_enable();
	} else {
		local_irq_enable();
	}
}

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(KERN_INFO "using mwait in idle threads.\n");
				printed = 1;
			}
			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;
	} else if (!strcmp(str, "mwait"))
		force_mwait = 1;
	else
		return -1;

	boot_option_idle_override = 1;
	return 0;
}
early_param("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 long d0, d1, d2, d3, d6, d7;
	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(),
		init_utsname()->release,
		(int)strcspn(init_utsname()->version, " "),
		init_utsname()->version);
	printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip);
	printk_address(regs->rip); 
	printk("RSP: %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); 

	cr0 = read_cr0();
	cr2 = read_cr2();
	cr3 = read_cr3();
	cr4 = read_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);

	get_debugreg(d0, 0);
	get_debugreg(d1, 1);
	get_debugreg(d2, 2);
	printk("DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
	get_debugreg(d3, 3);
	get_debugreg(d6, 6);
	get_debugreg(d7, 7);
	printk("DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
}

void show_regs(struct pt_regs *regs)
{
	printk("CPU %d:", smp_processor_id());
	__show_regs(regs);
	show_trace(NULL, regs, (void *)(regs + 1));
}

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

	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;
		clear_thread_flag(TIF_IO_BITMAP);
		/*
		 * 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;

	if (test_tsk_thread_flag(tsk, TIF_ABI_PENDING)) {
		clear_tsk_thread_flag(tsk, TIF_ABI_PENDING);
		if (test_tsk_thread_flag(tsk, TIF_IA32)) {
			clear_tsk_thread_flag(tsk, TIF_IA32);
		} else {
			set_tsk_thread_flag(tsk, TIF_IA32);
			current_thread_info()->status |= TS_COMPAT;
		}
	}
	clear_tsk_thread_flag(tsk, TIF_DEBUG);

	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;