traps.c

linux-2.6.15.6

	}
#endif
	printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
		reason, smp_processor_id());
	printk("Dazed and confused, but trying to continue\n");
	printk("Do you have a strange power saving mode enabled?\n");
}

static DEFINE_SPINLOCK(nmi_print_lock);

void die_nmi (struct pt_regs *regs, const char *msg)
{
	if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 0, SIGINT) ==
	    NOTIFY_STOP)
		return;

	spin_lock(&nmi_print_lock);
	/*
	* We are in trouble anyway, lets at least try
	* to get a message out.
	*/
	bust_spinlocks(1);
	printk(msg);
	printk(" on CPU%d, eip %08lx, registers:\n",
		smp_processor_id(), regs->eip);
	show_registers(regs);
	printk("console shuts up ...\n");
	console_silent();
	spin_unlock(&nmi_print_lock);
	bust_spinlocks(0);

	/* If we are in kernel we are probably nested up pretty bad
	 * and might aswell get out now while we still can.
	*/
	if (!user_mode(regs)) {
		current->thread.trap_no = 2;
		crash_kexec(regs);
	}

	do_exit(SIGSEGV);
}

static void default_do_nmi(struct pt_regs * regs)
{
	unsigned char reason = 0;

	/* Only the BSP gets external NMIs from the system.  */
	if (!smp_processor_id())
		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) {
			nmi_watchdog_tick(regs);
			return;
		}
#endif
		unknown_nmi_error(reason, regs);
		return;
	}
	if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
		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.
	 */
	reassert_nmi();
}

static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
{
	return 0;
}
 
static nmi_callback_t nmi_callback = dummy_nmi_callback;
 
fastcall void do_nmi(struct pt_regs * regs, long error_code)
{
	int cpu;

	nmi_enter();

	cpu = smp_processor_id();

	++nmi_count(cpu);

	if (!rcu_dereference(nmi_callback)(regs, cpu))
		default_do_nmi(regs);

	nmi_exit();
}

void set_nmi_callback(nmi_callback_t callback)
{
	rcu_assign_pointer(nmi_callback, callback);
}
EXPORT_SYMBOL_GPL(set_nmi_callback);

void unset_nmi_callback(void)
{
	nmi_callback = dummy_nmi_callback;
}
EXPORT_SYMBOL_GPL(unset_nmi_callback);

#ifdef CONFIG_KPROBES
fastcall 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;
	/* This is an interrupt gate, because kprobes wants interrupts
	disabled.  Normal trap handlers don't. */
	restore_interrupts(regs);
	do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL);
}
#endif

/*
 * 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
 * is restored before we deliver any signal, and therefore that
 * user code runs with the correct debug control register even though
 * we clear it here.
 *
 * Being careful here means that we don't have to be as careful in a
 * lot of more complicated places (task switching can be a bit lazy
 * about restoring all the debug state, and ptrace doesn't have to
 * find every occurrence of the TF bit that could be saved away even
 * by user code)
 */
fastcall void __kprobes do_debug(struct pt_regs * regs, long error_code)
{
	unsigned int condition;
	struct task_struct *tsk = current;

	get_debugreg(condition, 6);

	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
					SIGTRAP) == NOTIFY_STOP)
		return;
	/* It's safe to allow irq's after DR6 has been saved */
	if (regs->eflags & X86_EFLAGS_IF)
		local_irq_enable();

	/* Mask out spurious debug traps due to lazy DR7 setting */
	if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) {
		if (!tsk->thread.debugreg[7])
			goto clear_dr7;
	}

	if (regs->eflags & VM_MASK)
		goto debug_vm86;

	/* Save debug status register where ptrace can see it */
	tsk->thread.debugreg[6] = condition;

	/*
	 * Single-stepping through TF: make sure we ignore any events in
	 * kernel space (but re-enable TF when returning to user mode).
	 */
	if (condition & DR_STEP) {
		/*
		 * We already checked v86 mode above, so we can
		 * check for kernel mode by just checking the CPL
		 * of CS.
		 */
		if (!user_mode(regs))
			goto clear_TF_reenable;
	}

	/* Ok, finally something we can handle */
	send_sigtrap(tsk, regs, error_code);

	/* Disable additional traps. They'll be re-enabled when
	 * the signal is delivered.
	 */
clear_dr7:
	set_debugreg(0, 7);
	return;

debug_vm86:
	handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
	return;

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

/*
 * 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
 */
void math_error(void __user *eip)
{
	struct task_struct * task;
	siginfo_t info;
	unsigned short cwd, swd;

	/*
	 * 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 = eip;
	/*
	 * (~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 syncronizing 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: /* No unmasked exception */
			return;
		default:    /* Multiple exceptions */
			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);
}

fastcall void do_coprocessor_error(struct pt_regs * regs, long error_code)
{
	ignore_fpu_irq = 1;
	math_error((void __user *)regs->eip);
}

static void simd_math_error(void __user *eip)
{
	struct task_struct * task;
	siginfo_t info;
	unsigned short mxcsr;

	/*
	 * 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 = eip;
	/*
	 * 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);
}

fastcall void do_simd_coprocessor_error(struct pt_regs * regs,
					  long error_code)
{
	if (cpu_has_xmm) {
		/* Handle SIMD FPU exceptions on PIII+ processors. */
		ignore_fpu_irq = 1;
		simd_math_error((void __user *)regs->eip);
	} else {
		/*
		 * Handle strange cache flush from user space exception
		 * in all other cases.  This is undocumented behaviour.
		 */
		if (regs->eflags & VM_MASK) {
			handle_vm86_fault((struct kernel_vm86_regs *)regs,
					  error_code);
			return;
		}
		current->thread.trap_no = 19;
		current->thread.error_code = error_code;
		die_if_kernel("cache flush denied", regs, error_code);
		force_sig(SIGSEGV, current);
	}
}

fastcall void do_spurious_interrupt_bug(struct pt_regs * regs,
					  long error_code)
{
#if 0
	/* No need to warn about this any longer. */
	printk("Ignoring P6 Local APIC Spurious Interrupt Bug...\n");
#endif
}

fastcall void setup_x86_bogus_stack(unsigned char * stk)
{
	unsigned long *switch16_ptr, *switch32_ptr;
	struct pt_regs *regs;
	unsigned long stack_top, stack_bot;
	unsigned short iret_frame16_off;
	int cpu = smp_processor_id();
	/* reserve the space on 32bit stack for the magic switch16 pointer */
	memmove(stk, stk + 8, sizeof(struct pt_regs));
	switch16_ptr = (unsigned long *)(stk + sizeof(struct pt_regs));
	regs = (struct pt_regs *)stk;
	/* now the switch32 on 16bit stack */
	stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu);
	stack_top = stack_bot +	CPU_16BIT_STACK_SIZE;
	switch32_ptr = (unsigned long *)(stack_top - 8);
	iret_frame16_off = CPU_16BIT_STACK_SIZE - 8 - 20;
	/* copy iret frame on 16bit stack */
	memcpy((void *)(stack_bot + iret_frame16_off), &regs->eip, 20);
	/* fill in the switch pointers */
	switch16_ptr[0] = (regs->esp & 0xffff0000) | iret_frame16_off;
	switch16_ptr[1] = __ESPFIX_SS;
	switch32_ptr[0] = (unsigned long)stk + sizeof(struct pt_regs) +
		8 - CPU_16BIT_STACK_SIZE;
	switch32_ptr[1] = __KERNEL_DS;
}

fastcall unsigned char * fixup_x86_bogus_stack(unsigned short sp)
{
	unsigned long *switch32_ptr;
	unsigned char *stack16, *stack32;
	unsigned long stack_top, stack_bot;
	int len;
	int cpu = smp_processor_id();
	stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu);
	stack_top = stack_bot +	CPU_16BIT_STACK_SIZE;
	switch32_ptr = (unsigned long *)(stack_top - 8);
	/* copy the data from 16bit stack to 32bit stack */
	len = CPU_16BIT_STACK_SIZE - 8 - sp;
	stack16 = (unsigned char *)(stack_bot + sp);
	stack32 = (unsigned char *)
		(switch32_ptr[0] + CPU_16BIT_STACK_SIZE - 8 - len);
	memcpy(stack32, stack16, len);
	return stack32;
}

/*
 *  '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.
 *
 * Must be called with kernel preemption disabled (in this case,
 * local interrupts are disabled at the call-site in entry.S).
 */
asmlinkage void math_state_restore(struct pt_regs regs)
{
	struct thread_info *thread = current_thread_info();
	struct task_struct *tsk = thread->task;

	clts();		/* Allow maths ops (or we recurse) */
	if (!tsk_used_math(tsk))
		init_fpu(tsk);
	restore_fpu(tsk);
	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
}

#ifndef CONFIG_MATH_EMULATION

asmlinkage void math_emulate(long arg)
{
	printk("math-emulation not enabled and no coprocessor found.\n");
	printk("killing %s.\n",current->comm);
	force_sig(SIGFPE,current);
	schedule();
}

#endif /* CONFIG_MATH_EMULATION */

#ifdef CONFIG_X86_F00F_BUG
void __init trap_init_f00f_bug(void)
{
	__set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO);

	/*
	 * Update the IDT descriptor and reload the IDT so that
	 * it uses the read-only mapped virtual address.
	 */
	idt_descr.address = fix_to_virt(FIX_F00F_IDT);
	load_idt(&idt_descr);
}
#endif

#define _set_gate(gate_addr,type,dpl,addr,seg) \
do { \
  int __d0, __d1; \
  __asm__ __volatile__ ("movw %%dx,%%ax\n\t" \
	"movw %4,%%dx\n\t" \
	"movl %%eax,%0\n\t" \
	"movl %%edx,%1" \
	:"=m" (*((long *) (gate_addr))), \
	 "=m" (*(1+(long *) (gate_addr))), "=&a" (__d0), "=&d" (__d1) \
	:"i" ((short) (0x8000+(dpl<<13)+(type<<8))), \
	 "3" ((char *) (addr)),"2" ((seg) << 16)); \
} while (0)


/*
 * This needs to use 'idt_table' rather than 'idt', and
 * thus use the _nonmapped_ version of the IDT, as the
 * Pentium F0 0F bugfix can have resulted in the mapped
 * IDT being write-protected.
 */
void set_intr_gate(unsigned int n, void *addr)
{
	_set_gate(idt_table+n,14,0,addr,__KERNEL_CS);
}

/*
 * This routine sets up an interrupt gate at directory privilege level 3.
 */
static inline void set_system_intr_gate(unsigned int n, void *addr)
{
	_set_gate(idt_table+n, 14, 3, addr, __KERNEL_CS);
}

static void __init set_trap_gate(unsigned int n, void *addr)
{
	_set_gate(idt_table+n,15,0,addr,__KERNEL_CS);
}

static void __init set_system_gate(unsigned int n, void *addr)
{
	_set_gate(idt_table+n,15,3,addr,__KERNEL_CS);
}

static void __init set_task_gate(unsigned int n, unsigned int gdt_entry)
{
	_set_gate(idt_table+n,5,0,0,(gdt_entry<<3));
}


void __init trap_init(void)
{
#ifdef CONFIG_EISA
	void __iomem *p = ioremap(0x0FFFD9, 4);
	if (readl(p) == 'E'+('I'<<8)+('S'<<16)+('A'<<24)) {
		EISA_bus = 1;
	}
	iounmap(p);
#endif

#ifdef CONFIG_X86_LOCAL_APIC
	init_apic_mappings();
#endif

	set_trap_gate(0,&divide_error);
	set_intr_gate(1,&debug);
	set_intr_gate(2,&nmi);
	set_system_intr_gate(3, &int3); /* int3-5 can be called from all */
	set_system_gate(4,&overflow);
	set_system_gate(5,&bounds);
	set_trap_gate(6,&invalid_op);
	set_trap_gate(7,&device_not_available);
	set_task_gate(8,GDT_ENTRY_DOUBLEFAULT_TSS);
	set_trap_gate(9,&coprocessor_segment_overrun);
	set_trap_gate(10,&invalid_TSS);
	set_trap_gate(11,&segment_not_present);
	set_trap_gate(12,&stack_segment);
	set_trap_gate(13,&general_protection);
	set_intr_gate(14,&page_fault);
	set_trap_gate(15,&spurious_interrupt_bug);
	set_trap_gate(16,&coprocessor_error);
	set_trap_gate(17,&alignment_check);
#ifdef CONFIG_X86_MCE
	set_trap_gate(18,&machine_check);
#endif
	set_trap_gate(19,&simd_coprocessor_error);

	set_system_gate(SYSCALL_VECTOR,&system_call);

	/*
	 * Should be a barrier for any external CPU state.
	 */
	cpu_init();

	trap_init_hook();
}

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