traps.c

包括初始化、进程管理、进程通信、内存管理、设备管理、中断、文件系统、系统调用等精选源码分析。

/*
 *  linux/arch/i386/traps.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <[e-mail]>, May 2000
 */

/*
 * 'Traps.c' handles hardware traps and faults after we have saved some
 * state in 'asm.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>

#ifdef CONFIG_MCA
#include <linux/mca.h>
#include <asm/processor.h>
#endif

#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/smp.h>
#include <asm/pgalloc.h>

#ifdef CONFIG_X86_VISWS_APIC
#include <asm/fixmap.h>
#include <asm/cobalt.h>
#include <asm/lithium.h>
#endif

#include <linux/irq.h>

asmlinkage int system_call(void);
asmlinkage void lcall7(void);
asmlinkage void lcall27(void);

struct desc_struct default_ldt[] = { { 0, 0 }, { 0, 0 }, { 0, 0 },
		{ 0, 0 }, { 0, 0 } };

/*
 * The IDT has to be page-aligned to simplify the Pentium
 * F0 0F bug workaround.. We have a special link segment
 * for this.
 */
struct desc_struct idt_table[256] __attribute__((__section__(".data.idt"))) = { {0, 0}, };

extern void bust_spinlocks(void);

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 alignment_check(void);
asmlinkage void spurious_interrupt_bug(void);
asmlinkage void machine_check(void);

int kstack_depth_to_print = 24;

/*
 * These constants are for searching for possible module text
 * segments.
 */

void show_trace(unsigned long * stack)
{
	int i;
	unsigned long addr, module_start, module_end;

	if (!stack)
		stack = (unsigned long*)&stack;

	printk("Call Trace: ");
	i = 1;
	module_start = VMALLOC_START;
	module_end = VMALLOC_END;
	while (((long) stack & (THREAD_SIZE-1)) != 0) {
		addr = *stack++;
		/*
		 * 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.
		 */
		if (((addr >= (unsigned long) &_stext) &&
		     (addr <= (unsigned long) &_etext)) ||
		    ((addr >= module_start) && (addr <= module_end))) {
			if (i && ((i % 8) == 0))
				printk("\n       ");
			printk("[<%08lx>] ", addr);
			i++;
		}
	}
	printk("\n");
}

void show_stack(unsigned long * esp)
{
	unsigned long *stack;
	int i;

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

	if(esp==NULL)
		esp=(unsigned long*)&esp;

	stack = esp;
	for(i=0; i < kstack_depth_to_print; i++) {
		if (((long) stack & (THREAD_SIZE-1)) == 0)
			break;
		if (i && ((i % 8) == 0))
			printk("\n       ");
		printk("%08lx ", *stack++);
	}
	printk("\n");
	show_trace(esp);
}

static void show_registers(struct pt_regs *regs)
{
	int i;
	int in_kernel = 1;
	unsigned long esp;
	unsigned short ss;

	esp = (unsigned long) (&regs->esp);
	ss = __KERNEL_DS;
	if (regs->xcs & 3) {
		in_kernel = 0;
		esp = regs->esp;
		ss = regs->xss & 0xffff;
	}
	printk("CPU:    %d\nEIP:    %04x:[<%08lx>]\nEFLAGS: %08lx\n",
		smp_processor_id(), 0xffff & regs->xcs, regs->eip, regs->eflags);
	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   ss: %04x\n",
		regs->xds & 0xffff, regs->xes & 0xffff, ss);
	printk("Process %s (pid: %d, stackpage=%08lx)",
		current->comm, current->pid, 4096+(unsigned long)current);
	/*
	 * When in-kernel, we also print out the stack and code at the
	 * time of the fault..
	 */
	if (in_kernel) {

		printk("\nStack: ");
		show_stack((unsigned long*)esp);

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

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

spinlock_t die_lock = SPIN_LOCK_UNLOCKED;

void die(const char * str, struct pt_regs * regs, long err)
{
	console_verbose();
	spin_lock_irq(&die_lock);
	printk("%s: %04lx\n", str, err & 0xffff);
	show_registers(regs);

	spin_unlock_irq(&die_lock);
	do_exit(SIGSEGV);
}

static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
{
	if (!(regs->eflags & VM_MASK) && !(3 & regs->xcs))
		die(str, regs, err);
}

static inline unsigned long get_cr2(void)
{
	unsigned long address;

	/* get the address */
	__asm__("movl %%cr2,%0":"=r" (address));
	return address;
}

static void inline do_trap(int trapnr, int signr, char *str, int vm86,
			   struct pt_regs * regs, long error_code, siginfo_t *info)
{
	if (vm86 && regs->eflags & VM_MASK)
		goto vm86_trap;
	if (!(regs->xcs & 3))
		goto kernel_trap;

	trap_signal: {
		struct task_struct *tsk = current;
		tsk->thread.error_code = error_code;
		tsk->thread.trap_no = trapnr;
		if (info)
			force_sig_info(signr, info, tsk);
		else
			force_sig(signr, tsk);
		return;
	}

	kernel_trap: {
		unsigned long fixup = search_exception_table(regs->eip);
		if (fixup)
			regs->eip = fixup;
		else	
			die(str, regs, error_code);
		return;
	}

	vm86_trap: {
		int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr);
		if (ret) goto trap_signal;
		return;
	}
}

#define DO_ERROR(trapnr, signr, str, name) \
asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
{ \
	do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \
}

#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
{ \
	siginfo_t info; \
	info.si_signo = signr; \
	info.si_errno = 0; \
	info.si_code = sicode; \
	info.si_addr = (void *)siaddr; \
	do_trap(trapnr, signr, str, 0, regs, error_code, &info); \
}

#define DO_VM86_ERROR(trapnr, signr, str, name) \
asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
{ \
	do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \
}

#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
asmlinkage void do_##name(struct pt_regs * regs, long error_code) \
{ \
	siginfo_t info; \
	info.si_signo = signr; \
	info.si_errno = 0; \
	info.si_code = sicode; \
	info.si_addr = (void *)siaddr; \
	do_trap(trapnr, signr, str, 1, regs, error_code, &info); \
}

DO_VM86_ERROR_INFO( 0, SIGFPE,  "divide error", divide_error, FPE_INTDIV, regs->eip)
DO_VM86_ERROR( 3, SIGTRAP, "int3", int3)
DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow)
DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO( 6, SIGILL,  "invalid operand", invalid_op, ILL_ILLOPN, regs->eip)
DO_VM86_ERROR( 7, SIGSEGV, "device not available", device_not_available)
DO_ERROR( 8, SIGSEGV, "double fault", double_fault)
DO_ERROR( 9, SIGFPE,  "coprocessor segment overrun", coprocessor_segment_overrun)
DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(11, SIGBUS,  "segment not present", segment_not_present)
DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, get_cr2())

asmlinkage void do_general_protection(struct pt_regs * regs, long error_code)
{
	if (regs->eflags & VM_MASK)
		goto gp_in_vm86;

	if (!(regs->xcs & 3))
		goto gp_in_kernel;

	current->thread.error_code = error_code;
	current->thread.trap_no = 13;
	force_sig(SIGSEGV, current);
	return;

gp_in_vm86:
	handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
	return;

gp_in_kernel:
	{
		unsigned long fixup;
		fixup = search_exception_table(regs->eip);
		if (fixup) {
			regs->eip = fixup;
			return;
		}
		die("general protection fault", regs, error_code);
	}
}

static void mem_parity_error(unsigned char reason, struct pt_regs * regs)
{
	printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n");
	printk("You probably have a hardware problem with your RAM chips\n");

	/* Clear and disable the memory parity error line. */
	reason = (reason & 0xf) | 4;
	outb(reason, 0x61);
}

static void io_check_error(unsigned char reason, struct pt_regs * regs)
{
	unsigned long i;

	printk("NMI: IOCK error (debug interrupt?)\n");
	show_registers(regs);

	/* Re-enable the IOCK line, wait for a few seconds */
	reason = (reason & 0xf) | 8;
	outb(reason, 0x61);
	i = 2000;
	while (--i) udelay(1000);
	reason &= ~8;
	outb(reason, 0x61);
}

static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
{
#ifdef CONFIG_MCA
	/* Might actually be able to figure out what the guilty party
	* is. */
	if( MCA_bus ) {
		mca_handle_nmi();
		return;
	}
#endif
	printk("Uhhuh. NMI received for unknown reason %02x.\n", reason);
	printk("Dazed and confused, but trying to continue\n");
	printk("Do you have a strange power saving mode enabled?\n");
}

#if CONFIG_X86_IO_APIC

int nmi_watchdog = 1;

static int __init setup_nmi_watchdog(char *str)
{
        get_option(&str, &nmi_watchdog);
        return 1;
}

__setup("nmi_watchdog=", setup_nmi_watchdog);

static spinlock_t nmi_print_lock = SPIN_LOCK_UNLOCKED;

inline void nmi_watchdog_tick(struct pt_regs * regs)
{
	/*
	 * the best way to detect wether a CPU has a 'hard lockup' problem
	 * is to check it's local APIC timer IRQ counts. If they are not
	 * changing then that CPU has some problem.
	 *
	 * as these watchdog NMI IRQs are broadcasted to every CPU, here
	 * we only have to check the current processor.
	 *
	 * since NMIs dont listen to _any_ locks, we have to be extremely
	 * careful not to rely on unsafe variables. The printk might lock
	 * up though, so we have to break up console_lock first ...
	 * [when there will be more tty-related locks, break them up
	 *  here too!]
	 */

	static unsigned int last_irq_sums [NR_CPUS],
				alert_counter [NR_CPUS];

	/*
	 * Since current-> is always on the stack, and we always switch
	 * the stack NMI-atomically, it's safe to use smp_processor_id().
	 */
	int sum, cpu = smp_processor_id();

	sum = apic_timer_irqs[cpu];

	if (last_irq_sums[cpu] == sum) {
		/*
		 * Ayiee, looks like this CPU is stuck ...
		 * wait a few IRQs (5 seconds) before doing the oops ...
		 */
		alert_counter[cpu]++;
		if (alert_counter[cpu] == 5*HZ) {
			spin_lock(&nmi_print_lock);
			/*
			 * We are in trouble anyway, lets at least try
			 * to get a message out.
			 */
			bust_spinlocks();
			printk("NMI Watchdog detected LOCKUP on CPU%d, registers:\n", cpu);
			show_registers(regs);
			printk("console shuts up ...\n");
			console_silent();
			spin_unlock(&nmi_print_lock);
			do_exit(SIGSEGV);
		}
	} else {
		last_irq_sums[cpu] = sum;
		alert_counter[cpu] = 0;
	}
}
#endif

asmlinkage void do_nmi(struct pt_regs * regs, long error_code)
{
	unsigned char reason = inb(0x61);


	++nmi_count(smp_processor_id());
	if (!(reason & 0xc0)) {
#if CONFIG_X86_IO_APIC
		/*
		 * Ok, so this is none of the documented NMI sources,
		 * so it must be the NMI watchdog.
		 */
		if (nmi_watchdog) {
			nmi_watchdog_tick(regs);
			return;
		} else
			unknown_nmi_error(reason, regs);
#else
		unknown_nmi_error(reason, regs);
#endif
		return;
	}
	if (reason & 0x80)
		mem_parity_error(reason, regs);
	if (reason & 0x40)
		io_check_error(reason, regs);
	/*
	 * Reassert NMI in case it became active meanwhile
	 * as it's edge-triggered.
	 */
	outb(0x8f, 0x70);
	inb(0x71);		/* dummy */
	outb(0x0f, 0x70);
	inb(0x71);		/* dummy */
}

/*
 * Our handling of the processor debug registers is non-trivial.
 * We do not clear them on entry and exit from the kernel. Therefore
 * it is possible to get a watchpoint trap here from inside the kernel.
 * However, the code in ./ptrace.c has ensured that the user can
 * only set watchpoints on userspace addresses. Therefore the in-kernel
 * watchpoint trap can only occur in code which is reading/writing
 * from user space. Such code must not hold kernel locks (since it
 * can equally take a page fault), therefore it is safe to call
 * force_sig_info even though that claims and releases locks.
 * 
 * Code in ./signal.c ensures that the debug control register