summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/traps.c
blob: a0f48f5671c076fdde9bbccf10300c3724c840a9 (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
/*
 *  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
 */

/*
 * Handle hardware traps and faults.
 */
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/spinlock.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/utsname.h>
#include <linux/kdebug.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/ptrace.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/kexec.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/init.h>
#include <linux/bug.h>
#include <linux/nmi.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/io.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/kmemcheck.h>
#include <asm/stacktrace.h>
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <asm/atomic.h>
#include <asm/system.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/i387.h>
#include <asm/mce.h>

#include <asm/mach_traps.h>

#ifdef CONFIG_X86_64
#include <asm/pgalloc.h>
#include <asm/proto.h>
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
#include <asm/traps.h>

asmlinkage int system_call(void);

/* Do we ignore FPU interrupts ? */
char ignore_fpu_irq;

/*
 * The IDT has to be page-aligned to simplify the Pentium
 * F0 0F bug workaround.. We have a special link segment
 * for this.
 */
gate_desc idt_table[256]
	__attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, };
#endif

DECLARE_BITMAP(used_vectors, NR_VECTORS);
EXPORT_SYMBOL_GPL(used_vectors);

static int ignore_nmis;

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

static inline void preempt_conditional_sti(struct pt_regs *regs)
{
	inc_preempt_count();
	if (regs->flags & X86_EFLAGS_IF)
		local_irq_enable();
}

static inline void conditional_cli(struct pt_regs *regs)
{
	if (regs->flags & X86_EFLAGS_IF)
		local_irq_disable();
}

static inline void preempt_conditional_cli(struct pt_regs *regs)
{
	if (regs->flags & X86_EFLAGS_IF)
		local_irq_disable();
	dec_preempt_count();
}

#ifdef CONFIG_X86_32
static inline void
die_if_kernel(const char *str, struct pt_regs *regs, long err)
{
	if (!user_mode_vm(regs))
		die(str, regs, err);
}
#endif

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

#ifdef CONFIG_X86_32
	if (regs->flags & X86_VM_MASK) {
		/*
		 * traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
		 * On nmi (interrupt 2), do_trap should not be called.
		 */
		if (trapnr < 6)
			goto vm86_trap;
		goto trap_signal;
	}
#endif

	if (!user_mode(regs))
		goto kernel_trap;

#ifdef CONFIG_X86_32
trap_signal:
#endif
	/*
	 * 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;

#ifdef CONFIG_X86_64
	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
	    printk_ratelimit()) {
		printk(KERN_INFO
		       "%s[%d] trap %s ip:%lx sp:%lx error:%lx",
		       tsk->comm, tsk->pid, str,
		       regs->ip, regs->sp, error_code);
		print_vma_addr(" in ", regs->ip);
		printk("\n");
	}
#endif

	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;

#ifdef CONFIG_X86_32
vm86_trap:
	if (handle_vm86_trap((struct kernel_vm86_regs *) regs,
						error_code, trapnr))
		goto trap_signal;
	return;
#endif
}

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

#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr)		\
dotraplinkage 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;							\
	conditional_sti(regs);						\
	do_trap(trapnr, signr, str, regs, error_code, &info);		\
}

DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
DO_ERROR(4, SIGSEGV, "overflow", overflow)
DO_ERROR(5, SIGSEGV, "bounds", bounds)
DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
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)
#ifdef CONFIG_X86_32
DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
#endif
DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)

#ifdef CONFIG_X86_64
/* Runs on IST stack */
dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
{
	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
			12, SIGBUS) == NOTIFY_STOP)
		return;
	preempt_conditional_sti(regs);
	do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
	preempt_conditional_cli(regs);
}

dotraplinkage 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);
}
#endif

dotraplinkage void __kprobes
do_general_protection(struct pt_regs *regs, long error_code)
{
	struct task_struct *tsk;

	conditional_sti(regs);

#ifdef CONFIG_X86_32
	if (regs->flags & X86_VM_MASK)
		goto gp_in_vm86;
#endif

	tsk = current;
	if (!user_mode(regs))
		goto gp_in_kernel;

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

	if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
			printk_ratelimit()) {
		printk(KERN_INFO
			"%s[%d] general protection ip:%lx sp:%lx error:%lx",
			tsk->comm, task_pid_nr(tsk),
			regs->ip, regs->sp, error_code);
		print_vma_addr(" in ", regs->ip);
		printk("\n");
	}

	force_sig(SIGSEGV, tsk);
	return;

#ifdef CONFIG_X86_32
gp_in_vm86:
	local_irq_enable();
	handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
	return;
#endif

gp_in_kernel:
	if (fixup_exception(regs))
		return;

	tsk->thread.error_code = error_code;
	tsk->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);
}

static notrace __kprobes void
mem_parity_error(unsigned char reason, struct pt_regs *regs)
{
	printk(KERN_EMERG
		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
			reason, smp_processor_id());

	printk(KERN_EMERG
		"You have some hardware problem, likely on the PCI bus.\n");

#if defined(CONFIG_EDAC)
	if (edac_handler_set()) {
		edac_atomic_assert_error();
		return;
	}
#endif

	if (panic_on_unrecovered_nmi)
		panic("NMI: Not continuing");

	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");

	/* Clear and disable the memory parity error line. */
	reason = (reason & 0xf) | 4;
	outb(reason, 0x61);
}

static notrace __kprobes void
io_check_error(unsigned char reason, struct pt_regs *regs)
{
	unsigned long i;

	printk(KERN_EMERG "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 notrace __kprobes void
unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
{
	if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
			NOTIFY_STOP)
		return;
#ifdef CONFIG_MCA
	/*
	 * Might actually be able to figure out what the guilty party
	 * is:
	 */
	if (MCA_bus) {
		mca_handle_nmi();
		return;
	}
#endif
	printk(KERN_EMERG
		"Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
			reason, smp_processor_id());

	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
	if (panic_on_unrecovered_nmi)
		panic("NMI: Not continuing");

	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
}

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

	cpu = smp_processor_id();

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

	if (!(reason & 0xc0)) {
		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, 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_tick(regs, reason))
			return;
		if (!do_nmi_callback(regs, cpu))
			unknown_nmi_error(reason, regs);
#else
		unknown_nmi_error(reason, regs);
#endif

		return;
	}
	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)
		return;

	/* AK: following checks seem to be broken on modern chipsets. FIXME */
	if (reason & 0x80)
		mem_parity_error(reason, regs);
	if (reason & 0x40)
		io_check_error(reason, regs);
#ifdef CONFIG_X86_32
	/*
	 * Reassert NMI in case it became active meanwhile
	 * as it's edge-triggered:
	 */
	reassert_nmi();
#endif
}

dotraplinkage notrace __kprobes void
do_nmi(struct pt_regs *regs, long error_code)
{
	nmi_enter();

	inc_irq_stat(__nmi_count);

	if (!ignore_nmis)
		default_do_nmi(regs);

	nmi_exit();
}

void stop_nmi(void)
{
	acpi_nmi_disable();
	ignore_nmis++;
}

void restart_nmi(void)
{
	ignore_nmis--;
	acpi_nmi_enable();
}

/* May run on IST stack. */
dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_KPROBES
	if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
			== NOTIFY_STOP)
		return;
#else
	if (notify_die(DIE_TRAP, "int3", regs, error_code, 3, SIGTRAP)
			== NOTIFY_STOP)
		return;
#endif

	preempt_conditional_sti(regs);
	do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
	preempt_conditional_cli(regs);
}

#ifdef CONFIG_X86_64
/*
 * 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 __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
{
	struct pt_regs *regs = eregs;
	/* Did already sync */
	if (eregs == (struct pt_regs *)eregs->sp)
		;
	/* Exception from user space */
	else if (user_mode(eregs))
		regs = task_pt_regs(current);
	/*
	 * Exception from kernel and interrupts are enabled. Move to
	 * kernel process stack.
	 */
	else if (eregs->flags & X86_EFLAGS_IF)
		regs = (struct pt_regs *)(eregs->sp -= sizeof(struct pt_regs));
	if (eregs != regs)
		*regs = *eregs;
	return regs;
}
#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)
 *
 * May run on IST stack.
 */
dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
{
	struct task_struct *tsk = current;
	unsigned long condition;
	int si_code;

	get_debugreg(condition, 6);

	/* Catch kmemcheck conditions first of all! */
	if (condition & DR_STEP && kmemcheck_trap(regs))
		return;

	/*
	 * The processor cleared BTF, so don't mark that we need it set.
	 */
	clear_tsk_thread_flag(tsk, TIF_DEBUGCTLMSR);
	tsk->thread.debugctlmsr = 0;

	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 */
	preempt_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;
	}

#ifdef CONFIG_X86_32
	if (regs->flags & X86_VM_MASK)
		goto debug_vm86;
#endif

	/* Save debug status register where ptrace can see it */
	tsk->thread.debugreg6 = 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) {
		if (!user_mode(regs))
			goto clear_TF_reenable;
	}

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

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

#ifdef CONFIG_X86_32
debug_vm86:
	/* reenable preemption: handle_vm86_trap() might sleep */
	dec_preempt_count();
	handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
	conditional_cli(regs);
	return;
#endif

clear_TF_reenable:
	set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
	regs->flags &= ~X86_EFLAGS_TF;
	preempt_conditional_cli(regs);
	return;
}

#ifdef CONFIG_X86_64
static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr)
{
	if (fixup_exception(regs))
		return 1;

	notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE);
	/* Illegal floating point operation in the kernel */
	current->thread.trap_no = trapnr;
	die(str, regs, 0);
	return 0;
}
#endif

/*
 * 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 *ip)
{
	struct task_struct *task;
	siginfo_t info;
	unsigned short cwd, swd, err;

	/*
	 * 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_addr = ip;
	/*
	 * (~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);

	err = swd & ~cwd;

	if (err & 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;
	} else if (err & 0x004) { /* Divide by Zero */
		info.si_code = FPE_FLTDIV;
	} else if (err & 0x008) { /* Overflow */
		info.si_code = FPE_FLTOVF;
	} else if (err & 0x012) { /* Denormal, Underflow */
		info.si_code = FPE_FLTUND;
	} else if (err & 0x020) { /* Precision */
		info.si_code = FPE_FLTRES;
	} else {
		/*
		 * If we're using IRQ 13, or supposedly even some trap 16
		 * implementations, it's possible we get a spurious trap...
		 */
		return;		/* Spurious trap, no error */
	}
	force_sig_info(SIGFPE, &info, task);
}

dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
{
	conditional_sti(regs);

#ifdef CONFIG_X86_32
	ignore_fpu_irq = 1;
#else
	if (!user_mode(regs) &&
	    kernel_math_error(regs, "kernel x87 math error", 16))
		return;
#endif

	math_error((void __user *)regs->ip);
}

static void simd_math_error(void __user *ip)
{
	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 = ip;
	/*
	 * 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);
}

dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
	conditional_sti(regs);

#ifdef CONFIG_X86_32
	if (cpu_has_xmm) {
		/* Handle SIMD FPU exceptions on PIII+ processors. */
		ignore_fpu_irq = 1;
		simd_math_error((void __user *)regs->ip);
		return;
	}
	/*
	 * Handle strange cache flush from user space exception
	 * in all other cases.  This is undocumented behaviour.
	 */
	if (regs->flags & X86_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);
#else
	if (!user_mode(regs) &&
			kernel_math_error(regs, "kernel simd math error", 19))
		return;
	simd_math_error((void __user *)regs->ip);
#endif
}

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

#ifdef CONFIG_X86_32
unsigned long patch_espfix_desc(unsigned long uesp, unsigned long kesp)
{
	struct desc_struct *gdt = get_cpu_gdt_table(smp_processor_id());
	unsigned long base = (kesp - uesp) & -THREAD_SIZE;
	unsigned long new_kesp = kesp - base;
	unsigned long lim_pages = (new_kesp | (THREAD_SIZE - 1)) >> PAGE_SHIFT;
	__u64 desc = *(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS];

	/* Set up base for espfix segment */
	desc &= 0x00f0ff0000000000ULL;
	desc |=	((((__u64)base) << 16) & 0x000000ffffff0000ULL) |
		((((__u64)base) << 32) & 0xff00000000000000ULL) |
		((((__u64)lim_pages) << 32) & 0x000f000000000000ULL) |
		(lim_pages & 0xffff);
	*(__u64 *)&gdt[GDT_ENTRY_ESPFIX_SS] = desc;

	return new_kesp;
}
#endif

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

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

/*
 * 'math_state_restore()' saves the current math information in the
 * old math state array, and gets the new ones from the current task
 *
 * Careful.. There are problems with IBM-designed IRQ13 behaviour.
 * Don't touch unless you *really* know how it works.
 *
 * 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(void)
{
	struct thread_info *thread = current_thread_info();
	struct task_struct *tsk = thread->task;

	if (!tsk_used_math(tsk)) {
		local_irq_enable();
		/*
		 * does a slab alloc which can sleep
		 */
		if (init_fpu(tsk)) {
			/*
			 * ran out of memory!
			 */
			do_group_exit(SIGKILL);
			return;
		}
		local_irq_disable();
	}

	clts();				/* Allow maths ops (or we recurse) */
	/*
	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
	 */
	if (unlikely(restore_fpu_checking(tsk))) {
		stts();
		force_sig(SIGSEGV, tsk);
		return;
	}

	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
	tsk->fpu_counter++;
}
EXPORT_SYMBOL_GPL(math_state_restore);

#ifndef CONFIG_MATH_EMULATION
void math_emulate(struct math_emu_info *info)
{
	printk(KERN_EMERG
		"math-emulation not enabled and no coprocessor found.\n");
	printk(KERN_EMERG "killing %s.\n", current->comm);
	force_sig(SIGFPE, current);
	schedule();
}
#endif /* CONFIG_MATH_EMULATION */

dotraplinkage void __kprobes
do_device_not_available(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_X86_32
	if (read_cr0() & X86_CR0_EM) {
		struct math_emu_info info = { };

		conditional_sti(regs);

		info.regs = regs;
		math_emulate(&info);
	} else {
		math_state_restore(); /* interrupts still off */
		conditional_sti(regs);
	}
#else
	math_state_restore();
#endif
}

#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
	siginfo_t info;
	local_irq_enable();

	info.si_signo = SIGILL;
	info.si_errno = 0;
	info.si_code = ILL_BADSTK;
	info.si_addr = NULL;
	if (notify_die(DIE_TRAP, "iret exception",
			regs, error_code, 32, SIGILL) == NOTIFY_STOP)
		return;
	do_trap(32, SIGILL, "iret exception", regs, error_code, &info);
}
#endif

void __init trap_init(void)
{
	int i;

#ifdef CONFIG_EISA
	void __iomem *p = early_ioremap(0x0FFFD9, 4);

	if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24))
		EISA_bus = 1;
	early_iounmap(p, 4);
#endif

	set_intr_gate(0, &divide_error);
	set_intr_gate_ist(1, &debug, DEBUG_STACK);
	set_intr_gate_ist(2, &nmi, NMI_STACK);
	/* int3 can be called from all */
	set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
	/* int4 can be called from all */
	set_system_intr_gate(4, &overflow);
	set_intr_gate(5, &bounds);
	set_intr_gate(6, &invalid_op);
	set_intr_gate(7, &device_not_available);
#ifdef CONFIG_X86_32
	set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS);
#else
	set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK);
#endif
	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);

	/* Reserve all the builtin and the syscall vector: */
	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
		set_bit(i, used_vectors);

#ifdef CONFIG_IA32_EMULATION
	set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall);
	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
#endif

#ifdef CONFIG_X86_32
	if (cpu_has_fxsr) {
		printk(KERN_INFO "Enabling fast FPU save and restore... ");
		set_in_cr4(X86_CR4_OSFXSR);
		printk("done.\n");
	}
	if (cpu_has_xmm) {
		printk(KERN_INFO
			"Enabling unmasked SIMD FPU exception support... ");
		set_in_cr4(X86_CR4_OSXMMEXCPT);
		printk("done.\n");
	}

	set_system_trap_gate(SYSCALL_VECTOR, &system_call);
	set_bit(SYSCALL_VECTOR, used_vectors);
#endif

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

#ifdef CONFIG_X86_32
	x86_quirk_trap_init();
#endif
}