traps.c

linux-2.6.15.6

		return; \
	do_trap(trapnr, signr, str, 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 __user *)siaddr; \
	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
							== NOTIFY_STOP) \
		return; \
	do_trap(trapnr, signr, str, regs, error_code, &info); \
}

DO_ERROR_INFO( 0, SIGFPE,  "divide error", divide_error, FPE_INTDIV, regs->rip)
DO_ERROR( 4, SIGSEGV, "overflow", overflow)
DO_ERROR( 5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO( 6, SIGILL,  "invalid operand", invalid_op, ILL_ILLOPN, regs->rip)
DO_ERROR( 7, SIGSEGV, "device not available", device_not_available)
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_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
DO_ERROR(18, SIGSEGV, "reserved", reserved)
DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
DO_ERROR( 8, SIGSEGV, "double fault", double_fault)

asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
						long error_code)
{
	conditional_sti(regs);

	if (user_mode(regs)) {
		struct task_struct *tsk = current;

		if (exception_trace && unhandled_signal(tsk, SIGSEGV))
			printk(KERN_INFO
		       "%s[%d] general protection rip:%lx rsp:%lx error:%lx\n",
			       tsk->comm, tsk->pid,
			       regs->rip,regs->rsp,error_code); 

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

	/* kernel gp */
	{
		const struct exception_table_entry *fixup;
		fixup = search_exception_tables(regs->rip);
		if (fixup) {
			regs->rip = fixup->fixup;
			return;
		}
		if (notify_die(DIE_GPF, "general protection fault", regs,
					error_code, 13, SIGSEGV) == NOTIFY_STOP)
			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)
{
	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);
	mdelay(2000);
	reason &= ~8;
	outb(reason, 0x61);
}

static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
{	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");
}

/* Runs on IST stack. This code must keep interrupts off all the time.
   Nested NMIs are prevented by the CPU. */
asmlinkage void default_do_nmi(struct pt_regs *regs)
{
	unsigned char reason = 0;
	int cpu;

	cpu = smp_processor_id();

	/* Only the BSP gets external NMIs from the system.  */
	if (!cpu)
		reason = get_nmi_reason();

	if (!(reason & 0xc0)) {
		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT)
								== NOTIFY_STOP)
			return;
#ifdef CONFIG_X86_LOCAL_APIC
		/*
		 * Ok, so this is none of the documented NMI sources,
		 * so it must be the NMI watchdog.
		 */
		if (nmi_watchdog > 0) {
			nmi_watchdog_tick(regs,reason);
			return;
		}
#endif
		unknown_nmi_error(reason, regs);
		return;
	}
	if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
		return; 

	/* AK: following checks seem to be broken on modern chipsets. FIXME */

	if (reason & 0x80)
		mem_parity_error(reason, regs);
	if (reason & 0x40)
		io_check_error(reason, regs);
}

asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code)
{
	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) {
		return;
	}
	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
	return;
}

/* Help handler running on IST stack to switch back to user stack
   for scheduling or signal handling. The actual stack switch is done in
   entry.S */
asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs)
{
	struct pt_regs *regs = eregs;
	/* Did already sync */
	if (eregs == (struct pt_regs *)eregs->rsp)
		;
	/* Exception from user space */
	else if (user_mode(eregs))
		regs = ((struct pt_regs *)current->thread.rsp0) - 1;
	/* Exception from kernel and interrupts are enabled. Move to
 	   kernel process stack. */
	else if (eregs->eflags & X86_EFLAGS_IF)
		regs = (struct pt_regs *)(eregs->rsp -= sizeof(struct pt_regs));
	if (eregs != regs)
		*regs = *eregs;
	return regs;
}

/* runs on IST stack. */
asmlinkage void __kprobes do_debug(struct pt_regs * regs,
				   unsigned long error_code)
{
	unsigned long condition;
	struct task_struct *tsk = current;
	siginfo_t info;

	get_debugreg(condition, 6);

	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
						SIGTRAP) == NOTIFY_STOP)
		return;

	conditional_sti(regs);

	/* Mask out spurious debug traps due to lazy DR7 setting */
	if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
		if (!tsk->thread.debugreg7) { 
			goto clear_dr7;
		}
	}

	tsk->thread.debugreg6 = condition;

	/* Mask out spurious TF errors due to lazy TF clearing */
	if (condition & DR_STEP) {
		/*
		 * The TF error should be masked out only if the current
		 * process is not traced and if the TRAP flag has been set
		 * previously by a tracing process (condition detected by
		 * the PT_DTRACE flag); remember that the i386 TRAP flag
		 * can be modified by the process itself in user mode,
		 * allowing programs to debug themselves without the ptrace()
		 * interface.
		 */
                if (!user_mode(regs))
                       goto clear_TF_reenable;
		/*
		 * Was the TF flag set by a debugger? If so, clear it now,
		 * so that register information is correct.
		 */
		if (tsk->ptrace & PT_DTRACE) {
			regs->eflags &= ~TF_MASK;
			tsk->ptrace &= ~PT_DTRACE;
		}
	}

	/* Ok, finally something we can handle */
	tsk->thread.trap_no = 1;
	tsk->thread.error_code = error_code;
	info.si_signo = SIGTRAP;
	info.si_errno = 0;
	info.si_code = TRAP_BRKPT;
	if (!user_mode(regs))
		goto clear_dr7; 

	info.si_addr = (void __user *)regs->rip;
	force_sig_info(SIGTRAP, &info, tsk);	
clear_dr7:
	set_debugreg(0UL, 7);
	return;

clear_TF_reenable:
	set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
	regs->eflags &= ~TF_MASK;
}

static int kernel_math_error(struct pt_regs *regs, char *str)
{
	const struct exception_table_entry *fixup;
	fixup = search_exception_tables(regs->rip);
	if (fixup) {
		regs->rip = fixup->fixup;
		return 1;
	}
	notify_die(DIE_GPF, str, regs, 0, 16, SIGFPE);
	/* Illegal floating point operation in the kernel */
	die(str, regs, 0);
	return 0;
}

/*
 * Note that we play around with the 'TS' bit in an attempt to get
 * the correct behaviour even in the presence of the asynchronous
 * IRQ13 behaviour
 */
asmlinkage void do_coprocessor_error(struct pt_regs *regs)
{
	void __user *rip = (void __user *)(regs->rip);
	struct task_struct * task;
	siginfo_t info;
	unsigned short cwd, swd;

	conditional_sti(regs);
	if (!user_mode(regs) &&
	    kernel_math_error(regs, "kernel x87 math error"))
		return;

	/*
	 * Save the info for the exception handler and clear the error.
	 */
	task = current;
	save_init_fpu(task);
	task->thread.trap_no = 16;
	task->thread.error_code = 0;
	info.si_signo = SIGFPE;
	info.si_errno = 0;
	info.si_code = __SI_FAULT;
	info.si_addr = rip;
	/*
	 * (~cwd & swd) will mask out exceptions that are not set to unmasked
	 * status.  0x3f is the exception bits in these regs, 0x200 is the
	 * C1 reg you need in case of a stack fault, 0x040 is the stack
	 * fault bit.  We should only be taking one exception at a time,
	 * so if this combination doesn't produce any single exception,
	 * then we have a bad program that isn't synchronizing its FPU usage
	 * and it will suffer the consequences since we won't be able to
	 * fully reproduce the context of the exception
	 */
	cwd = get_fpu_cwd(task);
	swd = get_fpu_swd(task);
	switch (swd & ~cwd & 0x3f) {
		case 0x000:
		default:
			break;
		case 0x001: /* Invalid Op */
			/*
			 * swd & 0x240 == 0x040: Stack Underflow
			 * swd & 0x240 == 0x240: Stack Overflow
			 * User must clear the SF bit (0x40) if set
			 */
			info.si_code = FPE_FLTINV;
			break;
		case 0x002: /* Denormalize */
		case 0x010: /* Underflow */
			info.si_code = FPE_FLTUND;
			break;
		case 0x004: /* Zero Divide */
			info.si_code = FPE_FLTDIV;
			break;
		case 0x008: /* Overflow */
			info.si_code = FPE_FLTOVF;
			break;
		case 0x020: /* Precision */
			info.si_code = FPE_FLTRES;
			break;
	}
	force_sig_info(SIGFPE, &info, task);
}

asmlinkage void bad_intr(void)
{
	printk("bad interrupt"); 
}

asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs)
{
	void __user *rip = (void __user *)(regs->rip);
	struct task_struct * task;
	siginfo_t info;
	unsigned short mxcsr;

	conditional_sti(regs);
	if (!user_mode(regs) &&
        	kernel_math_error(regs, "kernel simd math error"))
		return;

	/*
	 * Save the info for the exception handler and clear the error.
	 */
	task = current;
	save_init_fpu(task);
	task->thread.trap_no = 19;
	task->thread.error_code = 0;
	info.si_signo = SIGFPE;
	info.si_errno = 0;
	info.si_code = __SI_FAULT;
	info.si_addr = rip;
	/*
	 * The SIMD FPU exceptions are handled a little differently, as there
	 * is only a single status/control register.  Thus, to determine which
	 * unmasked exception was caught we must mask the exception mask bits
	 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
	 */
	mxcsr = get_fpu_mxcsr(task);
	switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
		case 0x000:
		default:
			break;
		case 0x001: /* Invalid Op */
			info.si_code = FPE_FLTINV;
			break;
		case 0x002: /* Denormalize */
		case 0x010: /* Underflow */
			info.si_code = FPE_FLTUND;
			break;
		case 0x004: /* Zero Divide */
			info.si_code = FPE_FLTDIV;
			break;
		case 0x008: /* Overflow */
			info.si_code = FPE_FLTOVF;
			break;
		case 0x020: /* Precision */
			info.si_code = FPE_FLTRES;
			break;
	}
	force_sig_info(SIGFPE, &info, task);
}

asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs)
{
}

asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void)
{
}

asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void)
{
}

/*
 *  'math_state_restore()' saves the current math information in the
 * old math state array, and gets the new ones from the current task
 *
 * Careful.. There are problems with IBM-designed IRQ13 behaviour.
 * Don't touch unless you *really* know how it works.
 */
asmlinkage void math_state_restore(void)
{
	struct task_struct *me = current;
	clts();			/* Allow maths ops (or we recurse) */

	if (!used_math())
		init_fpu(me);
	restore_fpu_checking(&me->thread.i387.fxsave);
	me->thread_info->status |= TS_USEDFPU;
}

void do_call_debug(struct pt_regs *regs) 
{ 
	notify_die(DIE_CALL, "debug call", regs, 0, 255, SIGINT); 
}

void __init trap_init(void)
{
	set_intr_gate(0,&divide_error);
	set_intr_gate_ist(1,&debug,DEBUG_STACK);
	set_intr_gate_ist(2,&nmi,NMI_STACK);
	set_system_gate(3,&int3);
	set_system_gate(4,&overflow);	/* int4-5 can be called from all */
	set_system_gate(5,&bounds);
	set_intr_gate(6,&invalid_op);
	set_intr_gate(7,&device_not_available);
	set_intr_gate_ist(8,&double_fault, DOUBLEFAULT_STACK);
	set_intr_gate(9,&coprocessor_segment_overrun);
	set_intr_gate(10,&invalid_TSS);
	set_intr_gate(11,&segment_not_present);
	set_intr_gate_ist(12,&stack_segment,STACKFAULT_STACK);
	set_intr_gate(13,&general_protection);
	set_intr_gate(14,&page_fault);
	set_intr_gate(15,&spurious_interrupt_bug);
	set_intr_gate(16,&coprocessor_error);
	set_intr_gate(17,&alignment_check);
#ifdef CONFIG_X86_MCE
	set_intr_gate_ist(18,&machine_check, MCE_STACK); 
#endif
	set_intr_gate(19,&simd_coprocessor_error);

#ifdef CONFIG_IA32_EMULATION
	set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
#endif
       
	set_intr_gate(KDB_VECTOR, call_debug);
       
	/*
	 * Should be a barrier for any external CPU state.
	 */
	cpu_init();
}


/* Actual parsing is done early in setup.c. */
static int __init oops_dummy(char *s)
{ 
	panic_on_oops = 1;
	return -1; 
} 
__setup("oops=", oops_dummy); 

static int __init kstack_setup(char *s)
{
	kstack_depth_to_print = simple_strtoul(s,NULL,0);
	return 0;
}
__setup("kstack=", kstack_setup);