traps.c

来自「LINUX 2.6.17.4的源码」· C语言 代码 · 共 1,015 行 · 第 1/2 页

/*
 *  linux/arch/x86-64/traps.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 *
 *  $Id: traps.c,v 1.36 2002/03/24 11:09:10 ak Exp $
 */

/*
 * 'Traps.c' handles hardware traps and faults after we have saved some
 * state in 'entry.S'.
 */
#include <linux/config.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/nmi.h>
#include <linux/kprobes.h>
#include <linux/kexec.h>

#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include <asm/atomic.h>
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/i387.h>
#include <asm/kdebug.h>
#include <asm/processor.h>

#include <asm/smp.h>
#include <asm/pgalloc.h>
#include <asm/pda.h>
#include <asm/proto.h>
#include <asm/nmi.h>

asmlinkage void divide_error(void);
asmlinkage void debug(void);
asmlinkage void nmi(void);
asmlinkage void int3(void);
asmlinkage void overflow(void);
asmlinkage void bounds(void);
asmlinkage void invalid_op(void);
asmlinkage void device_not_available(void);
asmlinkage void double_fault(void);
asmlinkage void coprocessor_segment_overrun(void);
asmlinkage void invalid_TSS(void);
asmlinkage void segment_not_present(void);
asmlinkage void stack_segment(void);
asmlinkage void general_protection(void);
asmlinkage void page_fault(void);
asmlinkage void coprocessor_error(void);
asmlinkage void simd_coprocessor_error(void);
asmlinkage void reserved(void);
asmlinkage void alignment_check(void);
asmlinkage void machine_check(void);
asmlinkage void spurious_interrupt_bug(void);

ATOMIC_NOTIFIER_HEAD(die_chain);

int register_die_notifier(struct notifier_block *nb)
{
	vmalloc_sync_all();
	return atomic_notifier_chain_register(&die_chain, nb);
}
EXPORT_SYMBOL(register_die_notifier);

int unregister_die_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_unregister(&die_chain, nb);
}
EXPORT_SYMBOL(unregister_die_notifier);

static inline void conditional_sti(struct pt_regs *regs)
{
	if (regs->eflags & X86_EFLAGS_IF)
		local_irq_enable();
}

static inline void preempt_conditional_sti(struct pt_regs *regs)
{
	preempt_disable();
	if (regs->eflags & X86_EFLAGS_IF)
		local_irq_enable();
}

static inline void preempt_conditional_cli(struct pt_regs *regs)
{
	if (regs->eflags & X86_EFLAGS_IF)
		local_irq_disable();
	/* Make sure to not schedule here because we could be running
	   on an exception stack. */
	preempt_enable_no_resched();
}

static int kstack_depth_to_print = 10;

#ifdef CONFIG_KALLSYMS
#include <linux/kallsyms.h> 
int printk_address(unsigned long address)
{ 
	unsigned long offset = 0, symsize;
	const char *symname;
	char *modname;
	char *delim = ":"; 
	char namebuf[128];

	symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf); 
	if (!symname) 
		return printk("[<%016lx>]", address);
	if (!modname) 
		modname = delim = ""; 		
        return printk("<%016lx>{%s%s%s%s%+ld}",
		      address, delim, modname, delim, symname, offset); 
} 
#else
int printk_address(unsigned long address)
{ 
	return printk("[<%016lx>]", address);
} 
#endif

static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
					unsigned *usedp, const char **idp)
{
	static char ids[][8] = {
		[DEBUG_STACK - 1] = "#DB",
		[NMI_STACK - 1] = "NMI",
		[DOUBLEFAULT_STACK - 1] = "#DF",
		[STACKFAULT_STACK - 1] = "#SS",
		[MCE_STACK - 1] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
		[N_EXCEPTION_STACKS ... N_EXCEPTION_STACKS + DEBUG_STKSZ / EXCEPTION_STKSZ - 2] = "#DB[?]"
#endif
	};
	unsigned k;

	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
		unsigned long end;

		switch (k + 1) {
#if DEBUG_STKSZ > EXCEPTION_STKSZ
		case DEBUG_STACK:
			end = cpu_pda(cpu)->debugstack + DEBUG_STKSZ;
			break;
#endif
		default:
			end = per_cpu(init_tss, cpu).ist[k];
			break;
		}
		if (stack >= end)
			continue;
		if (stack >= end - EXCEPTION_STKSZ) {
			if (*usedp & (1U << k))
				break;
			*usedp |= 1U << k;
			*idp = ids[k];
			return (unsigned long *)end;
		}
#if DEBUG_STKSZ > EXCEPTION_STKSZ
		if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) {
			unsigned j = N_EXCEPTION_STACKS - 1;

			do {
				++j;
				end -= EXCEPTION_STKSZ;
				ids[j][4] = '1' + (j - N_EXCEPTION_STACKS);
			} while (stack < end - EXCEPTION_STKSZ);
			if (*usedp & (1U << j))
				break;
			*usedp |= 1U << j;
			*idp = ids[j];
			return (unsigned long *)end;
		}
#endif
	}
	return NULL;
}

/*
 * x86-64 can have upto three kernel stacks: 
 * process stack
 * interrupt stack
 * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
 */

void show_trace(unsigned long *stack)
{
	const unsigned cpu = safe_smp_processor_id();
	unsigned long *irqstack_end = (unsigned long *)cpu_pda(cpu)->irqstackptr;
	int i;
	unsigned used = 0;

	printk("\nCall Trace:");

#define HANDLE_STACK(cond) \
	do while (cond) { \
		unsigned long addr = *stack++; \
		if (kernel_text_address(addr)) { \
			if (i > 50) { \
				printk("\n       "); \
				i = 0; \
			} \
			else \
				i += printk(" "); \
			/* \
			 * If the address is either in the text segment of the \
			 * kernel, or in the region which contains vmalloc'ed \
			 * memory, it *may* be the address of a calling \
			 * routine; if so, print it so that someone tracing \
			 * down the cause of the crash will be able to figure \
			 * out the call path that was taken. \
			 */ \
			i += printk_address(addr); \
		} \
	} while (0)

	for(i = 11; ; ) {
		const char *id;
		unsigned long *estack_end;
		estack_end = in_exception_stack(cpu, (unsigned long)stack,
						&used, &id);

		if (estack_end) {
			i += printk(" <%s>", id);
			HANDLE_STACK (stack < estack_end);
			i += printk(" <EOE>");
			stack = (unsigned long *) estack_end[-2];
			continue;
		}
		if (irqstack_end) {
			unsigned long *irqstack;
			irqstack = irqstack_end -
				(IRQSTACKSIZE - 64) / sizeof(*irqstack);

			if (stack >= irqstack && stack < irqstack_end) {
				i += printk(" <IRQ>");
				HANDLE_STACK (stack < irqstack_end);
				stack = (unsigned long *) (irqstack_end[-1]);
				irqstack_end = NULL;
				i += printk(" <EOI>");
				continue;
			}
		}
		break;
	}

	HANDLE_STACK (((long) stack & (THREAD_SIZE-1)) != 0);
#undef HANDLE_STACK
	printk("\n");
}

void show_stack(struct task_struct *tsk, unsigned long * rsp)
{
	unsigned long *stack;
	int i;
	const int cpu = safe_smp_processor_id();
	unsigned long *irqstack_end = (unsigned long *) (cpu_pda(cpu)->irqstackptr);
	unsigned long *irqstack = (unsigned long *) (cpu_pda(cpu)->irqstackptr - IRQSTACKSIZE);

	// debugging aid: "show_stack(NULL, NULL);" prints the
	// back trace for this cpu.

	if (rsp == NULL) {
		if (tsk)
			rsp = (unsigned long *)tsk->thread.rsp;
		else
			rsp = (unsigned long *)&rsp;
	}

	stack = rsp;
	for(i=0; i < kstack_depth_to_print; i++) {
		if (stack >= irqstack && stack <= irqstack_end) {
			if (stack == irqstack_end) {
				stack = (unsigned long *) (irqstack_end[-1]);
				printk(" <EOI> ");
			}
		} else {
		if (((long) stack & (THREAD_SIZE-1)) == 0)
			break;
		}
		if (i && ((i % 4) == 0))
			printk("\n       ");
		printk("%016lx ", *stack++);
		touch_nmi_watchdog();
	}
	show_trace((unsigned long *)rsp);
}

/*
 * The architecture-independent dump_stack generator
 */
void dump_stack(void)
{
	unsigned long dummy;
	show_trace(&dummy);
}

EXPORT_SYMBOL(dump_stack);

void show_registers(struct pt_regs *regs)
{
	int i;
	int in_kernel = !user_mode(regs);
	unsigned long rsp;
	const int cpu = safe_smp_processor_id(); 
	struct task_struct *cur = cpu_pda(cpu)->pcurrent;

		rsp = regs->rsp;

	printk("CPU %d ", cpu);
	__show_regs(regs);
	printk("Process %s (pid: %d, threadinfo %p, task %p)\n",
		cur->comm, cur->pid, task_thread_info(cur), cur);

	/*
	 * When in-kernel, we also print out the stack and code at the
	 * time of the fault..
	 */
	if (in_kernel) {

		printk("Stack: ");
		show_stack(NULL, (unsigned long*)rsp);

		printk("\nCode: ");
		if (regs->rip < PAGE_OFFSET)
			goto bad;

		for (i=0; i<20; i++) {
			unsigned char c;
			if (__get_user(c, &((unsigned char*)regs->rip)[i])) {
bad:
				printk(" Bad RIP value.");
				break;
			}
			printk("%02x ", c);
		}
	}
	printk("\n");
}	

void handle_BUG(struct pt_regs *regs)
{ 
	struct bug_frame f;
	long len;
	const char *prefix = "";

	if (user_mode(regs))
		return; 
	if (__copy_from_user(&f, (const void __user *) regs->rip,
			     sizeof(struct bug_frame)))
		return; 
	if (f.filename >= 0 ||
	    f.ud2[0] != 0x0f || f.ud2[1] != 0x0b) 
		return;
	len = __strnlen_user((char *)(long)f.filename, PATH_MAX) - 1;
	if (len < 0 || len >= PATH_MAX)
		f.filename = (int)(long)"unmapped filename";
	else if (len > 50) {
		f.filename += len - 50;
		prefix = "...";
	}
	printk("----------- [cut here ] --------- [please bite here ] ---------\n");
	printk(KERN_ALERT "Kernel BUG at %s%.50s:%d\n", prefix, (char *)(long)f.filename, f.line);
} 

#ifdef CONFIG_BUG
void out_of_line_bug(void)
{ 
	BUG(); 
} 
#endif

static DEFINE_SPINLOCK(die_lock);
static int die_owner = -1;
static unsigned int die_nest_count;

unsigned __kprobes long oops_begin(void)
{
	int cpu = safe_smp_processor_id();
	unsigned long flags;

	/* racy, but better than risking deadlock. */
	local_irq_save(flags);
	if (!spin_trylock(&die_lock)) { 
		if (cpu == die_owner) 
			/* nested oops. should stop eventually */;
		else
			spin_lock(&die_lock);
	}
	die_nest_count++;
	die_owner = cpu;
	console_verbose();
	bust_spinlocks(1);
	return flags;
}

void __kprobes oops_end(unsigned long flags)
{ 
	die_owner = -1;
	bust_spinlocks(0);
	die_nest_count--;
	if (die_nest_count)
		/* We still own the lock */
		local_irq_restore(flags);
	else
		/* Nest count reaches zero, release the lock. */
		spin_unlock_irqrestore(&die_lock, flags);
	if (panic_on_oops)
		panic("Oops");
}

void __kprobes __die(const char * str, struct pt_regs * regs, long err)
{
	static int die_counter;
	printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff,++die_counter);
#ifdef CONFIG_PREEMPT
	printk("PREEMPT ");
#endif
#ifdef CONFIG_SMP
	printk("SMP ");
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
	printk("DEBUG_PAGEALLOC");
#endif
	printk("\n");
	notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV);
	show_registers(regs);
	/* Executive summary in case the oops scrolled away */
	printk(KERN_ALERT "RIP ");
	printk_address(regs->rip); 
	printk(" RSP <%016lx>\n", regs->rsp); 
	if (kexec_should_crash(current))
		crash_kexec(regs);
}

void die(const char * str, struct pt_regs * regs, long err)
{
	unsigned long flags = oops_begin();

	handle_BUG(regs);
	__die(str, regs, err);
	oops_end(flags);
	do_exit(SIGSEGV); 
}

void __kprobes die_nmi(char *str, struct pt_regs *regs)
{
	unsigned long flags = oops_begin();

	/*
	 * We are in trouble anyway, lets at least try
	 * to get a message out.
	 */
	printk(str, safe_smp_processor_id());
	show_registers(regs);
	if (kexec_should_crash(current))
		crash_kexec(regs);
	if (panic_on_timeout || panic_on_oops)
		panic("nmi watchdog");
	printk("console shuts up ...\n");
	oops_end(flags);
	nmi_exit();
	local_irq_enable();
	do_exit(SIGSEGV);
}

static void __kprobes do_trap(int trapnr, int signr, char *str,
			      struct pt_regs * regs, long error_code,
			      siginfo_t *info)
{
	struct task_struct *tsk = current;

	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = trapnr;

	if (user_mode(regs)) {
		if (exception_trace && unhandled_signal(tsk, signr))
			printk(KERN_INFO
			       "%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n",
			       tsk->comm, tsk->pid, str,
			       regs->rip, regs->rsp, error_code); 

		if (info)
			force_sig_info(signr, info, tsk);
		else
			force_sig(signr, tsk);
		return;
	}


	/* kernel trap */ 
	{	     
		const struct exception_table_entry *fixup;