x86: honor _PAGE_PSE bit on page walks

[linux-2.6-block.git] / arch / x86 / kernel / traps_32.c

/*
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 */

/*
 * 'Traps.c' handles hardware traps and faults after we have saved some
 * state in 'asm.s'.
 */
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.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/highmem.h>
#include <linux/kallsyms.h>
#include <linux/ptrace.h>
#include <linux/utsname.h>
#include <linux/kprobes.h>
#include <linux/kexec.h>
#include <linux/unwind.h>
#include <linux/uaccess.h>
#include <linux/nmi.h>
#include <linux/bug.h>

#ifdef CONFIG_EISA
#include <linux/ioport.h>
#include <linux/eisa.h>
#endif

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

#if defined(CONFIG_EDAC)
#include <linux/edac.h>
#endif

#include <asm/processor.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/atomic.h>
#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/i387.h>
#include <asm/nmi.h>
#include <asm/unwind.h>
#include <asm/smp.h>
#include <asm/arch_hooks.h>
#include <linux/kdebug.h>
#include <asm/stacktrace.h>

#include <linux/module.h>

#include "mach_traps.h"

int panic_on_unrecovered_nmi;

asmlinkage int system_call(void);

/* Do we ignore FPU interrupts ? */
char ignore_fpu_irq = 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}, };

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 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;
static unsigned int code_bytes = 64;

static inline int valid_stack_ptr(struct thread_info *tinfo, void *p, unsigned size)
{
	return	p > (void *)tinfo &&
		p <= (void *)tinfo + THREAD_SIZE - size;
}

/* The form of the top of the frame on the stack */
struct stack_frame {
	struct stack_frame *next_frame;
	unsigned long return_address;
};

static inline unsigned long print_context_stack(struct thread_info *tinfo,
				unsigned long *stack, unsigned long ebp,
				const struct stacktrace_ops *ops, void *data)
{
#ifdef	CONFIG_FRAME_POINTER
	struct stack_frame *frame = (struct stack_frame *)ebp;
	while (valid_stack_ptr(tinfo, frame, sizeof(*frame))) {
		struct stack_frame *next;
		unsigned long addr;

		addr = frame->return_address;
		ops->address(data, addr);
		/*
		 * break out of recursive entries (such as
		 * end_of_stack_stop_unwind_function). Also,
		 * we can never allow a frame pointer to
		 * move downwards!
		 */
		next = frame->next_frame;
		if (next <= frame)
			break;
		frame = next;
	}
#else
	while (valid_stack_ptr(tinfo, stack, sizeof(*stack))) {
		unsigned long addr;

		addr = *stack++;
		if (__kernel_text_address(addr))
			ops->address(data, addr);
	}
#endif
	return ebp;
}

#define MSG(msg) ops->warning(data, msg)

void dump_trace(struct task_struct *task, struct pt_regs *regs,
	        unsigned long *stack,
		const struct stacktrace_ops *ops, void *data)
{
	unsigned long ebp = 0;

	if (!task)
		task = current;

	if (!stack) {
		unsigned long dummy;
		stack = &dummy;
		if (task != current)
			stack = (unsigned long *)task->thread.esp;
	}

#ifdef CONFIG_FRAME_POINTER
	if (!ebp) {
		if (task == current) {
			/* Grab ebp right from our regs */
			asm ("movl %%ebp, %0" : "=r" (ebp) : );
		} else {
			/* ebp is the last reg pushed by switch_to */
			ebp = *(unsigned long *) task->thread.esp;
		}
	}
#endif

	while (1) {
		struct thread_info *context;
		context = (struct thread_info *)
			((unsigned long)stack & (~(THREAD_SIZE - 1)));
		ebp = print_context_stack(context, stack, ebp, ops, data);
		/* Should be after the line below, but somewhere
		   in early boot context comes out corrupted and we
		   can't reference it -AK */
		if (ops->stack(data, "IRQ") < 0)
			break;
		stack = (unsigned long*)context->previous_esp;
		if (!stack)
			break;
		touch_nmi_watchdog();
	}
}
EXPORT_SYMBOL(dump_trace);

static void
print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
{
	printk(data);
	print_symbol(msg, symbol);
	printk("\n");
}

static void print_trace_warning(void *data, char *msg)
{
	printk("%s%s\n", (char *)data, msg);
}

static int print_trace_stack(void *data, char *name)
{
	return 0;
}

/*
 * Print one address/symbol entries per line.
 */
static void print_trace_address(void *data, unsigned long addr)
{
	printk("%s [<%08lx>] ", (char *)data, addr);
	print_symbol("%s\n", addr);
	touch_nmi_watchdog();
}

static const struct stacktrace_ops print_trace_ops = {
	.warning = print_trace_warning,
	.warning_symbol = print_trace_warning_symbol,
	.stack = print_trace_stack,
	.address = print_trace_address,
};

static void
show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
		   unsigned long * stack, char *log_lvl)
{
	dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
	printk("%s =======================\n", log_lvl);
}

void show_trace(struct task_struct *task, struct pt_regs *regs,
		unsigned long * stack)
{
	show_trace_log_lvl(task, regs, stack, "");
}

static void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
			       unsigned long *esp, char *log_lvl)
{
	unsigned long *stack;
	int i;

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

	stack = esp;
	for(i = 0; i < kstack_depth_to_print; i++) {
		if (kstack_end(stack))
			break;
		if (i && ((i % 8) == 0))
			printk("\n%s       ", log_lvl);
		printk("%08lx ", *stack++);
	}
	printk("\n%sCall Trace:\n", log_lvl);
	show_trace_log_lvl(task, regs, esp, log_lvl);
}

void show_stack(struct task_struct *task, unsigned long *esp)
{
	printk("       ");
	show_stack_log_lvl(task, NULL, esp, "");
}

/*
 * The architecture-independent dump_stack generator
 */
void dump_stack(void)
{
	unsigned long stack;

	show_trace(current, NULL, &stack);
}

EXPORT_SYMBOL(dump_stack);

void show_registers(struct pt_regs *regs)
{
	int i;

	print_modules();
	__show_registers(regs, 0);
	printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)",
		TASK_COMM_LEN, current->comm, current->pid,
		current_thread_info(), current, task_thread_info(current));
	/*
	 * When in-kernel, we also print out the stack and code at the
	 * time of the fault..
	 */
	if (!user_mode_vm(regs)) {
		u8 *eip;
		unsigned int code_prologue = code_bytes * 43 / 64;
		unsigned int code_len = code_bytes;
		unsigned char c;

		printk("\n" KERN_EMERG "Stack: ");
		show_stack_log_lvl(NULL, regs, &regs->esp, KERN_EMERG);

		printk(KERN_EMERG "Code: ");

		eip = (u8 *)regs->eip - code_prologue;
		if (eip < (u8 *)PAGE_OFFSET ||
			probe_kernel_address(eip, c)) {
			/* try starting at EIP */
			eip = (u8 *)regs->eip;
			code_len = code_len - code_prologue + 1;
		}
		for (i = 0; i < code_len; i++, eip++) {
			if (eip < (u8 *)PAGE_OFFSET ||
				probe_kernel_address(eip, c)) {
				printk(" Bad EIP value.");
				break;
			}
			if (eip == (u8 *)regs->eip)
				printk("<%02x> ", c);
			else
				printk("%02x ", c);
		}
	}
	printk("\n");
}	

int is_valid_bugaddr(unsigned long eip)
{
	unsigned short ud2;

	if (eip < PAGE_OFFSET)
		return 0;
	if (probe_kernel_address((unsigned short *)eip, ud2))
		return 0;

	return ud2 == 0x0b0f;
}

/*
 * This is gone through when something in the kernel has done something bad and
 * is about to be terminated.
 */
void die(const char * str, struct pt_regs * regs, long err)
{
	static struct {
		spinlock_t lock;
		u32 lock_owner;
		int lock_owner_depth;
	} die = {
		.lock =			__SPIN_LOCK_UNLOCKED(die.lock),
		.lock_owner =		-1,
		.lock_owner_depth =	0
	};
	static int die_counter;
	unsigned long flags;

	oops_enter();

	if (die.lock_owner != raw_smp_processor_id()) {
		console_verbose();
		spin_lock_irqsave(&die.lock, flags);
		die.lock_owner = smp_processor_id();
		die.lock_owner_depth = 0;
		bust_spinlocks(1);
	}
	else
		local_save_flags(flags);

	if (++die.lock_owner_depth < 3) {
		unsigned long esp;
		unsigned short ss;

		report_bug(regs->eip, regs);

		printk(KERN_EMERG "%s: %04lx [#%d] ", 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");

		if (notify_die(DIE_OOPS, str, regs, err,
					current->thread.trap_no, SIGSEGV) !=
				NOTIFY_STOP) {
			show_registers(regs);
			/* Executive summary in case the oops scrolled away */
			esp = (unsigned long) (&regs->esp);
			savesegment(ss, ss);
			if (user_mode(regs)) {
				esp = regs->esp;
				ss = regs->xss & 0xffff;
			}
			printk(KERN_EMERG "EIP: [<%08lx>] ", regs->eip);
			print_symbol("%s", regs->eip);
			printk(" SS:ESP %04x:%08lx\n", ss, esp);
		}
		else
			regs = NULL;
  	} else
		printk(KERN_EMERG "Recursive die() failure, output suppressed\n");

	bust_spinlocks(0);
	die.lock_owner = -1;
	add_taint(TAINT_DIE);
	spin_unlock_irqrestore(&die.lock, flags);

	if (!regs)
		return;

	if (kexec_should_crash(current))
		crash_kexec(regs);

	if (in_interrupt())
		panic("Fatal exception in interrupt");

	if (panic_on_oops)
		panic("Fatal exception");

	oops_exit();
	do_exit(SIGSEGV);
}

static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err)
{
	if (!user_mode_vm(regs))
		die(str, regs, err);
}

static void __kprobes do_trap(int trapnr, int signr, char *str, int vm86,
			      struct pt_regs * regs, long error_code,
			      siginfo_t *info)
{
	struct task_struct *tsk = current;

	if (regs->eflags & VM_MASK) {
		if (vm86)
			goto vm86_trap;
		goto trap_signal;
	}

	if (!user_mode(regs))
		goto kernel_trap;

	trap_signal: {
		/*
		 * We want error_code and trap_no set for userspace faults and
		 * kernelspace faults which result in die(), but not
		 * kernelspace faults which are fixed up.  die() gives the
		 * process no chance to handle the signal and notice the
		 * kernel fault information, so that won't result in polluting
		 * the information about previously queued, but not yet
		 * delivered, faults.  See also do_general_protection below.
		 */
		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: {
		if (!fixup_exception(regs)) {
			tsk->thread.error_code = error_code;
			tsk->thread.trap_no = trapnr;
			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) \
fastcall void do_##name(struct pt_regs * regs, long error_code) \
{ \
	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
						== NOTIFY_STOP) \
		return; \
	do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \
}

#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr, irq) \
fastcall void do_##name(struct pt_regs * regs, long error_code) \
{ \
	siginfo_t info; \
	if (irq) \
		local_irq_enable(); \
	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, 0, regs, error_code, &info); \
}

#define DO_VM86_ERROR(trapnr, signr, str, name) \
fastcall void do_##name(struct pt_regs * regs, long error_code) \
{ \
	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
						== NOTIFY_STOP) \
		return; \
	do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \
}

#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
fastcall 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, 1, regs, error_code, &info); \
}

DO_VM86_ERROR_INFO( 0, SIGFPE,  "divide error", divide_error, FPE_INTDIV, regs->eip)
#ifndef CONFIG_KPROBES
DO_VM86_ERROR( 3, SIGTRAP, "int3", int3)
#endif
DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow)
DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO( 6, SIGILL,  "invalid opcode", invalid_op, ILL_ILLOPN, regs->eip, 0)
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, 0, 0)
DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0, 1)

fastcall void __kprobes do_general_protection(struct pt_regs * regs,
					      long error_code)
{
	int cpu = get_cpu();
	struct tss_struct *tss = &per_cpu(init_tss, cpu);
	struct thread_struct *thread = &current->thread;

	/*
	 * Perform the lazy TSS's I/O bitmap copy. If the TSS has an
	 * invalid offset set (the LAZY one) and the faulting thread has
	 * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS
	 * and we set the offset field correctly. Then we let the CPU to
	 * restart the faulting instruction.
	 */
	if (tss->x86_tss.io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY &&
	    thread->io_bitmap_ptr) {
		memcpy(tss->io_bitmap, thread->io_bitmap_ptr,
		       thread->io_bitmap_max);
		/*
		 * If the previously set map was extending to higher ports
		 * than the current one, pad extra space with 0xff (no access).
		 */
		if (thread->io_bitmap_max < tss->io_bitmap_max)
			memset((char *) tss->io_bitmap +
				thread->io_bitmap_max, 0xff,
				tss->io_bitmap_max - thread->io_bitmap_max);
		tss->io_bitmap_max = thread->io_bitmap_max;
		tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
		tss->io_bitmap_owner = thread;
		put_cpu();
		return;
	}
	put_cpu();

	if (regs->eflags & VM_MASK)
		goto gp_in_vm86;

	if (!user_mode(regs))
		goto gp_in_kernel;

	current->thread.error_code = error_code;
	current->thread.trap_no = 13;
	if (show_unhandled_signals && unhandled_signal(current, SIGSEGV) &&
	    printk_ratelimit())
		printk(KERN_INFO
		    "%s[%d] general protection eip:%lx esp:%lx error:%lx\n",
		    current->comm, current->pid,
		    regs->eip, regs->esp, error_code);

	force_sig(SIGSEGV, current);
	return;

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

gp_in_kernel:
	if (!fixup_exception(regs)) {
		current->thread.error_code = error_code;
		current->thread.trap_no = 13;
		if (notify_die(DIE_GPF, "general protection fault", regs,
				error_code, 13, SIGSEGV) == NOTIFY_STOP)
			return;
		die("general protection fault", regs, error_code);
	}
}