aboutsummaryrefslogtreecommitdiff
path: root/arch/i386/kernel/traps.c
blob: 09a58cb6daa7050e018496a127458241f2fa0e30 (plain)
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
31
32
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
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
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
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
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
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
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
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
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
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
769
770
771
772
773
774
775
776
777
778
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
811
812
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
862
863
864
865
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
898
899
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
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
/*
 *  linux/arch/i386/traps.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/config.h>
#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>

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

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

#include <asm/processor.h>
#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/nmi.h>

#include <asm/smp.h>
#include <asm/arch_hooks.h>
#include <asm/kdebug.h>

#include <linux/irq.h>
#include <linux/module.h>

#include "mach_traps.h"

asmlinkage int system_call(void);

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

/* 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);

static int kstack_depth_to_print = 24;
struct notifier_block *i386die_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(&i386die_chain, nb);
	spin_unlock_irqrestore(&die_notifier_lock, flags);
	return err;
}
EXPORT_SYMBOL(register_die_notifier);

static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
{
	return	p > (void *)tinfo &&
		p < (void *)tinfo + THREAD_SIZE - 3;
}

static inline unsigned long print_context_stack(struct thread_info *tinfo,
				unsigned long *stack, unsigned long ebp)
{
	unsigned long addr;

#ifdef	CONFIG_FRAME_POINTER
	while (valid_stack_ptr(tinfo, (void *)ebp)) {
		addr = *(unsigned long *)(ebp + 4);
		printk(" [<%08lx>] ", addr);
		print_symbol("%s", addr);
		printk("\n");
		ebp = *(unsigned long *)ebp;
	}
#else
	while (valid_stack_ptr(tinfo, stack)) {
		addr = *stack++;
		if (__kernel_text_address(addr)) {
			printk(" [<%08lx>]", addr);
			print_symbol(" %s", addr);
			printk("\n");
		}
	}
#endif
	return ebp;
}

void show_trace(struct task_struct *task, unsigned long * stack)
{
	unsigned long ebp;

	if (!task)
		task = current;

	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;
	}

	while (1) {
		struct thread_info *context;
		context = (struct thread_info *)
			((unsigned long)stack & (~(THREAD_SIZE - 1)));
		ebp = print_context_stack(context, stack, ebp);
		stack = (unsigned long*)context->previous_esp;
		if (!stack)
			break;
		printk(" =======================\n");
	}
}

void show_stack(struct task_struct *task, unsigned long *esp)
{
	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       ");
		printk("%08lx ", *stack++);
	}
	printk("\nCall Trace:\n");
	show_trace(task, esp);
}

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

	show_trace(current, &stack);
}

EXPORT_SYMBOL(dump_stack);

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

	esp = (unsigned long) (&regs->esp);
	savesegment(ss, ss);
	if (user_mode(regs)) {
		in_kernel = 0;
		esp = regs->esp;
		ss = regs->xss & 0xffff;
	}
	print_modules();
	printk("CPU:    %d\nEIP:    %04x:[<%08lx>]    %s VLI\nEFLAGS: %08lx"
			"   (%s) \n",
		smp_processor_id(), 0xffff & regs->xcs, regs->eip,
		print_tainted(), regs->eflags, system_utsname.release);
	print_symbol("EIP is at %s\n", regs->eip);
	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, threadinfo=%p task=%p)",
		current->comm, current->pid, current_thread_info(), current);
	/*
	 * When in-kernel, we also print out the stack and code at the
	 * time of the fault..
	 */
	if (in_kernel) {
		u8 __user *eip;

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

		printk("Code: ");

		eip = (u8 __user *)regs->eip - 43;
		for (i = 0; i < 64; i++, eip++) {
			unsigned char c;

			if (eip < (u8 __user *)PAGE_OFFSET || __get_user(c, eip)) {
				printk(" Bad EIP value.");
				break;
			}
			if (eip == (u8 __user *)regs->eip)
				printk("<%02x> ", c);
			else
				printk("%02x ", c);
		}
	}
	printk("\n");
}	

static void handle_BUG(struct pt_regs *regs)
{
	unsigned short ud2;
	unsigned short line;
	char *file;
	char c;
	unsigned long eip;

	eip = regs->eip;

	if (eip < PAGE_OFFSET)
		goto no_bug;
	if (__get_user(ud2, (unsigned short __user *)eip))
		goto no_bug;
	if (ud2 != 0x0b0f)
		goto no_bug;
	if (__get_user(line, (unsigned short __user *)(eip + 2)))
		goto bug;
	if (__get_user(file, (char * __user *)(eip + 4)) ||
		(unsigned long)file < PAGE_OFFSET || __get_user(c, file))
		file = "<bad filename>";

	printk("------------[ cut here ]------------\n");
	printk(KERN_ALERT "kernel BUG at %s:%d!\n", file, line);

no_bug:
	return;

	/* Here we know it was a BUG but file-n-line is unavailable */
bug:
	printk("Kernel BUG\n");
}

/* 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,
		.lock_owner =		-1,
		.lock_owner_depth =	0
	};
	static int die_counter;

	if (die.lock_owner != raw_smp_processor_id()) {
		console_verbose();
		spin_lock_irq(&die.lock);
		die.lock_owner = smp_processor_id();
		die.lock_owner_depth = 0;
		bust_spinlocks(1);
	}

	if (++die.lock_owner_depth < 3) {
		int nl = 0;
		handle_BUG(regs);
		printk(KERN_ALERT "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
		printk("PREEMPT ");
		nl = 1;
#endif
#ifdef CONFIG_SMP
		printk("SMP ");
		nl = 1;
#endif
#ifdef CONFIG_DEBUG_PAGEALLOC
		printk("DEBUG_PAGEALLOC");
		nl = 1;
#endif
		if (nl)
			printk("\n");
	notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV);
		show_registers(regs);
  	} else
		printk(KERN_ERR "Recursive die() failure, output suppressed\n");

	bust_spinlocks(0);
	die.lock_owner = -1;
	spin_unlock_irq(&die.lock);

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

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

	if (panic_on_oops) {
		printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n");
		ssleep(5);
		panic("Fatal exception");
	}
	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;
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = trapnr;

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

	if (!user_mode(regs))
		goto kernel_trap;

	trap_signal: {
		if (info)
			force_sig_info(signr, info, tsk);
		else
			force_sig(signr, tsk);
		return;
	}

	kernel_trap: {
		if (!fixup_exception(regs))
			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) \
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, 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 operand", invalid_op, ILL_ILLOPN, regs->eip)
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)
DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0)

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->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->io_bitmap_base = IO_BITMAP_OFFSET;
		put_cpu();
		return;
	}
	put_cpu();

	current->thread.error_code = error_code;
	current->thread.trap_no = 13;

	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;
	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)) {
		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. */
	clear_mem_error(reason);
}

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 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();

#ifdef CONFIG_HOTPLUG_CPU
	if (!cpu_online(cpu)) {
		nmi_exit();
		return;
	}
#endif

	++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:
		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);
}

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);