traps.c 23.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
/*
 *  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 <gareth@valinux.com>, 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>
31
#include <linux/nmi.h>
32
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120

#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>

extern struct gate_struct idt_table[256]; 

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);
asmlinkage void call_debug(void);

struct notifier_block *die_chain;
static DEFINE_SPINLOCK(die_notifier_lock);

int register_die_notifier(struct notifier_block *nb)
{
	int err = 0;
	unsigned long flags;
	spin_lock_irqsave(&die_notifier_lock, flags);
	err = notifier_chain_register(&die_chain, nb);
	spin_unlock_irqrestore(&die_notifier_lock, flags);
	return err;
}

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

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

121 122 123 124 125 126 127 128 129 130 131
static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
					unsigned *usedp, const char **idp)
{
	static const char ids[N_EXCEPTION_STACKS][8] = {
		[DEBUG_STACK - 1] = "#DB",
		[NMI_STACK - 1] = "NMI",
		[DOUBLEFAULT_STACK - 1] = "#DF",
		[STACKFAULT_STACK - 1] = "#SS",
		[MCE_STACK - 1] = "#MC",
	};
	unsigned k;
L
Linus Torvalds 已提交
132

133 134 135 136 137 138 139 140 141 142 143 144 145
	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
		unsigned long end;

		end = per_cpu(init_tss, cpu).ist[k];
		if (stack >= end)
			continue;
		if (stack >= end - EXCEPTION_STKSZ) {
			if (*usedp & (1U << k))
				break;
			*usedp |= 1U << k;
			*idp = ids[k];
			return (unsigned long *)end;
		}
L
Linus Torvalds 已提交
146 147
	}
	return NULL;
148
}
L
Linus Torvalds 已提交
149 150 151 152 153

/*
 * x86-64 can have upto three kernel stacks: 
 * process stack
 * interrupt stack
154
 * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
L
Linus Torvalds 已提交
155 156 157 158 159
 */

void show_trace(unsigned long *stack)
{
	unsigned long addr;
160 161
	const unsigned cpu = safe_smp_processor_id();
	unsigned long *irqstack_end = (unsigned long *)cpu_pda[cpu].irqstackptr;
L
Linus Torvalds 已提交
162
	int i;
163
	unsigned used = 0;
L
Linus Torvalds 已提交
164 165

	printk("\nCall Trace:");
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200

#define HANDLE_STACK(cond) \
	do while (cond) { \
		addr = *stack++; \
		if (kernel_text_address(addr)) { \
			/* \
			 * 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); \
			if (i > 50) { \
				printk("\n       "); \
				i = 0; \
			} \
			else \
				i += printk(" "); \
		} \
	} while (0)

	for(i = 0; ; ) {
		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;
L
Linus Torvalds 已提交
201
		}
202 203 204 205 206 207 208 209 210 211 212 213
		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;
L
Linus Torvalds 已提交
214 215
			}
		}
216
		break;
L
Linus Torvalds 已提交
217
	}
218 219 220

	HANDLE_STACK (((long) stack & (THREAD_SIZE-1)) != 0);
#undef HANDLE_STACK
L
Linus Torvalds 已提交
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
	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++);
256
		touch_nmi_watchdog();
L
Linus Torvalds 已提交
257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
	}
	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;
275
	int in_kernel = !user_mode(regs);
L
Linus Torvalds 已提交
276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
	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, cur->thread_info, 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;
	char tmp;

319
	if (user_mode(regs))
L
Linus Torvalds 已提交
320 321 322 323
		return; 
	if (__copy_from_user(&f, (struct bug_frame *) regs->rip, 
			     sizeof(struct bug_frame)))
		return; 
324
	if (f.filename >= 0 ||
L
Linus Torvalds 已提交
325 326
	    f.ud2[0] != 0x0f || f.ud2[1] != 0x0b) 
		return;
327 328
	if (__get_user(tmp, (char *)(long)f.filename))
		f.filename = (int)(long)"unmapped filename";
L
Linus Torvalds 已提交
329
	printk("----------- [cut here ] --------- [please bite here ] ---------\n");
330
	printk(KERN_ALERT "Kernel BUG at %.50s:%d\n", (char *)(long)f.filename, f.line);
L
Linus Torvalds 已提交
331 332
} 

333
#ifdef CONFIG_BUG
L
Linus Torvalds 已提交
334 335 336 337
void out_of_line_bug(void)
{ 
	BUG(); 
} 
338
#endif
L
Linus Torvalds 已提交
339 340 341 342

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

343
unsigned long oops_begin(void)
L
Linus Torvalds 已提交
344
{
345 346 347 348 349
	int cpu = safe_smp_processor_id();
	unsigned long flags;

	/* racy, but better than risking deadlock. */
	local_irq_save(flags);
L
Linus Torvalds 已提交
350 351 352 353
	if (!spin_trylock(&die_lock)) { 
		if (cpu == die_owner) 
			/* nested oops. should stop eventually */;
		else
354
			spin_lock(&die_lock);
L
Linus Torvalds 已提交
355
	}
356
	die_owner = cpu;
L
Linus Torvalds 已提交
357
	console_verbose();
358 359
	bust_spinlocks(1);
	return flags;
L
Linus Torvalds 已提交
360 361
}

362
void oops_end(unsigned long flags)
L
Linus Torvalds 已提交
363 364
{ 
	die_owner = -1;
365 366
	bust_spinlocks(0);
	spin_unlock_irqrestore(&die_lock, flags);
L
Linus Torvalds 已提交
367
	if (panic_on_oops)
368 369
		panic("Oops");
}
L
Linus Torvalds 已提交
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384

void __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");
385
	notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV);
L
Linus Torvalds 已提交
386 387 388 389 390 391 392 393 394
	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); 
}

void die(const char * str, struct pt_regs * regs, long err)
{
395 396
	unsigned long flags = oops_begin();

L
Linus Torvalds 已提交
397 398
	handle_BUG(regs);
	__die(str, regs, err);
399
	oops_end(flags);
L
Linus Torvalds 已提交
400 401 402 403 404
	do_exit(SIGSEGV); 
}

void die_nmi(char *str, struct pt_regs *regs)
{
405 406
	unsigned long flags = oops_begin();

L
Linus Torvalds 已提交
407 408 409 410 411 412 413 414 415
	/*
	 * We are in trouble anyway, lets at least try
	 * to get a message out.
	 */
	printk(str, safe_smp_processor_id());
	show_registers(regs);
	if (panic_on_timeout || panic_on_oops)
		panic("nmi watchdog");
	printk("console shuts up ...\n");
416
	oops_end(flags);
L
Linus Torvalds 已提交
417 418 419
	do_exit(SIGSEGV);
}

420 421 422
static void __kprobes do_trap(int trapnr, int signr, char *str,
			      struct pt_regs * regs, long error_code,
			      siginfo_t *info)
L
Linus Torvalds 已提交
423
{
424 425
	struct task_struct *tsk = current;

L
Linus Torvalds 已提交
426 427
	conditional_sti(regs);

428 429
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = trapnr;
L
Linus Torvalds 已提交
430

431
	if (user_mode(regs)) {
L
Linus Torvalds 已提交
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490
		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;
		fixup = search_exception_tables(regs->rip);
		if (fixup) {
			regs->rip = fixup->fixup;
		} else	
			die(str, regs, error_code);
		return;
	}
}

#define DO_ERROR(trapnr, signr, str, name) \
asmlinkage 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, 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)
491
DO_ERROR(12, SIGBUS,  "stack segment", stack_segment)
492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508

asmlinkage void do_double_fault(struct pt_regs * regs, long error_code)
{
	static const char str[] = "double fault";
	struct task_struct *tsk = current;

	/* Return not checked because double check cannot be ignored */
	notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV);

	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 8;

	/* This is always a kernel trap and never fixable (and thus must
	   never return). */
	for (;;)
		die(str, regs, error_code);
}
L
Linus Torvalds 已提交
509

510 511
asmlinkage void __kprobes do_general_protection(struct pt_regs * regs,
						long error_code)
L
Linus Torvalds 已提交
512
{
513 514
	struct task_struct *tsk = current;

L
Linus Torvalds 已提交
515 516
	conditional_sti(regs);

517 518
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 13;
L
Linus Torvalds 已提交
519

520
	if (user_mode(regs)) {
L
Linus Torvalds 已提交
521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574
		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); 

		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");
}

575 576
/* Runs on IST stack. This code must keep interrupts off all the time.
   Nested NMIs are prevented by the CPU. */
L
Linus Torvalds 已提交
577 578 579
asmlinkage void default_do_nmi(struct pt_regs *regs)
{
	unsigned char reason = 0;
A
Ashok Raj 已提交
580 581 582
	int cpu;

	cpu = smp_processor_id();
L
Linus Torvalds 已提交
583 584

	/* Only the BSP gets external NMIs from the system.  */
A
Ashok Raj 已提交
585
	if (!cpu)
L
Linus Torvalds 已提交
586 587 588
		reason = get_nmi_reason();

	if (!(reason & 0xc0)) {
589
		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
L
Linus Torvalds 已提交
590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
								== 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;
	}
605
	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
L
Linus Torvalds 已提交
606 607 608 609 610 611 612 613 614 615
		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);
}

616
asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code)
L
Linus Torvalds 已提交
617 618 619 620 621 622 623 624
{
	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) {
		return;
	}
	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
	return;
}

625 626 627 628 629 630 631 632 633 634
/* 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 */
635
	else if (user_mode(eregs))
636 637 638 639 640 641 642 643 644 645
		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;
}

L
Linus Torvalds 已提交
646
/* runs on IST stack. */
647 648
asmlinkage void __kprobes do_debug(struct pt_regs * regs,
				   unsigned long error_code)
L
Linus Torvalds 已提交
649 650 651 652 653
{
	unsigned long condition;
	struct task_struct *tsk = current;
	siginfo_t info;

654
	get_debugreg(condition, 6);
L
Linus Torvalds 已提交
655 656

	if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code,
657
						SIGTRAP) == NOTIFY_STOP)
658
		return;
659

L
Linus Torvalds 已提交
660 661 662 663 664 665 666 667 668 669 670 671
	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 */
672
	if (condition & DR_STEP) {
L
Linus Torvalds 已提交
673 674 675 676 677 678 679 680 681
		/*
		 * 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.
		 */
682
                if (!user_mode(regs))
L
Linus Torvalds 已提交
683
                       goto clear_TF_reenable;
684 685 686 687 688 689 690 691
		/*
		 * 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;
		}
L
Linus Torvalds 已提交
692 693 694 695 696 697 698 699
	}

	/* 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;
700
	if (!user_mode(regs))
L
Linus Torvalds 已提交
701 702 703 704 705
		goto clear_dr7; 

	info.si_addr = (void __user *)regs->rip;
	force_sig_info(SIGTRAP, &info, tsk);	
clear_dr7:
706
	set_debugreg(0UL, 7);
707
	return;
L
Linus Torvalds 已提交
708 709 710 711 712 713

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

714
static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr)
L
Linus Torvalds 已提交
715 716 717 718 719 720 721
{
	const struct exception_table_entry *fixup;
	fixup = search_exception_tables(regs->rip);
	if (fixup) {
		regs->rip = fixup->fixup;
		return 1;
	}
722
	notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE);
723
	/* Illegal floating point operation in the kernel */
724
	current->thread.trap_no = trapnr;
L
Linus Torvalds 已提交
725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741
	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);
742
	if (!user_mode(regs) &&
743
	    kernel_math_error(regs, "kernel x87 math error", 16))
L
Linus Torvalds 已提交
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768
		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);
769
	switch (swd & ~cwd & 0x3f) {
L
Linus Torvalds 已提交
770 771 772 773
		case 0x000:
		default:
			break;
		case 0x001: /* Invalid Op */
774 775 776 777 778
			/*
			 * swd & 0x240 == 0x040: Stack Underflow
			 * swd & 0x240 == 0x240: Stack Overflow
			 * User must clear the SF bit (0x40) if set
			 */
L
Linus Torvalds 已提交
779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810
			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);
811
	if (!user_mode(regs) &&
812
        	kernel_math_error(regs, "kernel simd math error", 19))
L
Linus Torvalds 已提交
813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861
		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)
862 863 864 865
{
}

asmlinkage void __attribute__((weak)) mce_threshold_interrupt(void)
L
Linus Torvalds 已提交
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
{
}

/*
 *  '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);
898 899
	set_system_gate(4,&overflow);	/* int4 can be called from all */
	set_intr_gate(5,&bounds);
L
Linus Torvalds 已提交
900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
	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);