summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/traps.c
blob: e289ce1332ab4c7459b84ad6ad50f8fef940f332 (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
/*
 *  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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/context_tracking.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/spinlock.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/kgdb.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ptrace.h>
#include <linux/uprobes.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/kexec.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.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>

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

#include <asm/stacktrace.h>
#include <asm/processor.h>
#include <asm/debugreg.h>
#include <linux/atomic.h>
#include <asm/text-patching.h>
#include <asm/ftrace.h>
#include <asm/traps.h>
#include <asm/desc.h>
#include <asm/fpu/internal.h>
#include <asm/cpu_entry_area.h>
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
#include <asm/alternative.h>
#include <asm/fpu/xstate.h>
#include <asm/trace/mpx.h>
#include <asm/mpx.h>
#include <asm/vm86.h>
#include <asm/umip.h>

#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
#else
#include <asm/processor-flags.h>
#include <asm/setup.h>
#include <asm/proto.h>
#endif

DECLARE_BITMAP(system_vectors, NR_VECTORS);

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

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

/*
 * In IST context, we explicitly disable preemption.  This serves two
 * purposes: it makes it much less likely that we would accidentally
 * schedule in IST context and it will force a warning if we somehow
 * manage to schedule by accident.
 */
void ist_enter(struct pt_regs *regs)
{
	if (user_mode(regs)) {
		RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	} else {
		/*
		 * We might have interrupted pretty much anything.  In
		 * fact, if we're a machine check, we can even interrupt
		 * NMI processing.  We don't want in_nmi() to return true,
		 * but we need to notify RCU.
		 */
		rcu_nmi_enter();
	}

	preempt_disable();

	/* This code is a bit fragile.  Test it. */
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work");
}
NOKPROBE_SYMBOL(ist_enter);

void ist_exit(struct pt_regs *regs)
{
	preempt_enable_no_resched();

	if (!user_mode(regs))
		rcu_nmi_exit();
}

/**
 * ist_begin_non_atomic() - begin a non-atomic section in an IST exception
 * @regs:	regs passed to the IST exception handler
 *
 * IST exception handlers normally cannot schedule.  As a special
 * exception, if the exception interrupted userspace code (i.e.
 * user_mode(regs) would return true) and the exception was not
 * a double fault, it can be safe to schedule.  ist_begin_non_atomic()
 * begins a non-atomic section within an ist_enter()/ist_exit() region.
 * Callers are responsible for enabling interrupts themselves inside
 * the non-atomic section, and callers must call ist_end_non_atomic()
 * before ist_exit().
 */
void ist_begin_non_atomic(struct pt_regs *regs)
{
	BUG_ON(!user_mode(regs));

	/*
	 * Sanity check: we need to be on the normal thread stack.  This
	 * will catch asm bugs and any attempt to use ist_preempt_enable
	 * from double_fault.
	 */
	BUG_ON(!on_thread_stack());

	preempt_enable_no_resched();
}

/**
 * ist_end_non_atomic() - begin a non-atomic section in an IST exception
 *
 * Ends a non-atomic section started with ist_begin_non_atomic().
 */
void ist_end_non_atomic(void)
{
	preempt_disable();
}

int is_valid_bugaddr(unsigned long addr)
{
	unsigned short ud;

	if (addr < TASK_SIZE_MAX)
		return 0;

	if (probe_kernel_address((unsigned short *)addr, ud))
		return 0;

	return ud == INSN_UD0 || ud == INSN_UD2;
}

int fixup_bug(struct pt_regs *regs, int trapnr)
{
	if (trapnr != X86_TRAP_UD)
		return 0;

	switch (report_bug(regs->ip, regs)) {
	case BUG_TRAP_TYPE_NONE:
	case BUG_TRAP_TYPE_BUG:
		break;

	case BUG_TRAP_TYPE_WARN:
		regs->ip += LEN_UD2;
		return 1;
	}

	return 0;
}

static nokprobe_inline int
do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str,
		  struct pt_regs *regs,	long error_code)
{
	if (v8086_mode(regs)) {
		/*
		 * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
		 * On nmi (interrupt 2), do_trap should not be called.
		 */
		if (trapnr < X86_TRAP_UD) {
			if (!handle_vm86_trap((struct kernel_vm86_regs *) regs,
						error_code, trapnr))
				return 0;
		}
	} else if (!user_mode(regs)) {
		if (fixup_exception(regs, trapnr, error_code, 0))
			return 0;

		tsk->thread.error_code = error_code;
		tsk->thread.trap_nr = trapnr;
		die(str, regs, error_code);
	}

	/*
	 * We want error_code and trap_nr 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_nr = trapnr;

	return -1;
}

static void show_signal(struct task_struct *tsk, int signr,
			const char *type, const char *desc,
			struct pt_regs *regs, long error_code)
{
	if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
	    printk_ratelimit()) {
		pr_info("%s[%d] %s%s ip:%lx sp:%lx error:%lx",
			tsk->comm, task_pid_nr(tsk), type, desc,
			regs->ip, regs->sp, error_code);
		print_vma_addr(KERN_CONT " in ", regs->ip);
		pr_cont("\n");
	}
}

static void
do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
	long error_code, int sicode, void __user *addr)
{
	struct task_struct *tsk = current;


	if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
		return;

	show_signal(tsk, signr, "trap ", str, regs, error_code);

	if (!sicode)
		force_sig(signr, tsk);
	else
		force_sig_fault(signr, sicode, addr, tsk);
}
NOKPROBE_SYMBOL(do_trap);

static void do_error_trap(struct pt_regs *regs, long error_code, char *str,
	unsigned long trapnr, int signr, int sicode, void __user *addr)
{
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");

	/*
	 * WARN*()s end up here; fix them up before we call the
	 * notifier chain.
	 */
	if (!user_mode(regs) && fixup_bug(regs, trapnr))
		return;

	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) !=
			NOTIFY_STOP) {
		cond_local_irq_enable(regs);
		do_trap(trapnr, signr, str, regs, error_code, sicode, addr);
	}
}

#define IP ((void __user *)uprobe_get_trap_addr(regs))
#define DO_ERROR(trapnr, signr, sicode, addr, str, name)		   \
dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	   \
{									   \
	do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \
}

DO_ERROR(X86_TRAP_DE,     SIGFPE,  FPE_INTDIV,   IP, "divide error",        divide_error)
DO_ERROR(X86_TRAP_OF,     SIGSEGV,          0, NULL, "overflow",            overflow)
DO_ERROR(X86_TRAP_UD,     SIGILL,  ILL_ILLOPN,   IP, "invalid opcode",      invalid_op)
DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,           0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS,     SIGSEGV,          0, NULL, "invalid TSS",         invalid_TSS)
DO_ERROR(X86_TRAP_NP,     SIGBUS,           0, NULL, "segment not present", segment_not_present)
DO_ERROR(X86_TRAP_SS,     SIGBUS,           0, NULL, "stack segment",       stack_segment)
DO_ERROR(X86_TRAP_AC,     SIGBUS,  BUS_ADRALN, NULL, "alignment check",     alignment_check)
#undef IP

#ifdef CONFIG_VMAP_STACK
__visible void __noreturn handle_stack_overflow(const char *message,
						struct pt_regs *regs,
						unsigned long fault_address)
{
	printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n",
		 (void *)fault_address, current->stack,
		 (char *)current->stack + THREAD_SIZE - 1);
	die(message, regs, 0);

	/* Be absolutely certain we don't return. */
	panic("%s", message);
}
#endif

#ifdef CONFIG_X86_64
/* Runs on IST stack */
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
	static const char str[] = "double fault";
	struct task_struct *tsk = current;
#ifdef CONFIG_VMAP_STACK
	unsigned long cr2;
#endif

#ifdef CONFIG_X86_ESPFIX64
	extern unsigned char native_irq_return_iret[];

	/*
	 * If IRET takes a non-IST fault on the espfix64 stack, then we
	 * end up promoting it to a doublefault.  In that case, take
	 * advantage of the fact that we're not using the normal (TSS.sp0)
	 * stack right now.  We can write a fake #GP(0) frame at TSS.sp0
	 * and then modify our own IRET frame so that, when we return,
	 * we land directly at the #GP(0) vector with the stack already
	 * set up according to its expectations.
	 *
	 * The net result is that our #GP handler will think that we
	 * entered from usermode with the bad user context.
	 *
	 * No need for ist_enter here because we don't use RCU.
	 */
	if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
		regs->cs == __KERNEL_CS &&
		regs->ip == (unsigned long)native_irq_return_iret)
	{
		struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;

		/*
		 * regs->sp points to the failing IRET frame on the
		 * ESPFIX64 stack.  Copy it to the entry stack.  This fills
		 * in gpregs->ss through gpregs->ip.
		 *
		 */
		memmove(&gpregs->ip, (void *)regs->sp, 5*8);
		gpregs->orig_ax = 0;  /* Missing (lost) #GP error code */

		/*
		 * Adjust our frame so that we return straight to the #GP
		 * vector with the expected RSP value.  This is safe because
		 * we won't enable interupts or schedule before we invoke
		 * general_protection, so nothing will clobber the stack
		 * frame we just set up.
		 *
		 * We will enter general_protection with kernel GSBASE,
		 * which is what the stub expects, given that the faulting
		 * RIP will be the IRET instruction.
		 */
		regs->ip = (unsigned long)general_protection;
		regs->sp = (unsigned long)&gpregs->orig_ax;

		return;
	}
#endif

	ist_enter(regs);
	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);

	tsk->thread.error_code = error_code;
	tsk->thread.trap_nr = X86_TRAP_DF;

#ifdef CONFIG_VMAP_STACK
	/*
	 * If we overflow the stack into a guard page, the CPU will fail
	 * to deliver #PF and will send #DF instead.  Similarly, if we
	 * take any non-IST exception while too close to the bottom of
	 * the stack, the processor will get a page fault while
	 * delivering the exception and will generate a double fault.
	 *
	 * According to the SDM (footnote in 6.15 under "Interrupt 14 -
	 * Page-Fault Exception (#PF):
	 *
	 *   Processors update CR2 whenever a page fault is detected. If a
	 *   second page fault occurs while an earlier page fault is being
	 *   delivered, the faulting linear address of the second fault will
	 *   overwrite the contents of CR2 (replacing the previous
	 *   address). These updates to CR2 occur even if the page fault
	 *   results in a double fault or occurs during the delivery of a
	 *   double fault.
	 *
	 * The logic below has a small possibility of incorrectly diagnosing
	 * some errors as stack overflows.  For example, if the IDT or GDT
	 * gets corrupted such that #GP delivery fails due to a bad descriptor
	 * causing #GP and we hit this condition while CR2 coincidentally
	 * points to the stack guard page, we'll think we overflowed the
	 * stack.  Given that we're going to panic one way or another
	 * if this happens, this isn't necessarily worth fixing.
	 *
	 * If necessary, we could improve the test by only diagnosing
	 * a stack overflow if the saved RSP points within 47 bytes of
	 * the bottom of the stack: if RSP == tsk_stack + 48 and we
	 * take an exception, the stack is already aligned and there
	 * will be enough room SS, RSP, RFLAGS, CS, RIP, and a
	 * possible error code, so a stack overflow would *not* double
	 * fault.  With any less space left, exception delivery could
	 * fail, and, as a practical matter, we've overflowed the
	 * stack even if the actual trigger for the double fault was
	 * something else.
	 */
	cr2 = read_cr2();
	if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE)
		handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2);
#endif

#ifdef CONFIG_DOUBLEFAULT
	df_debug(regs, error_code);
#endif
	/*
	 * This is always a kernel trap and never fixable (and thus must
	 * never return).
	 */
	for (;;)
		die(str, regs, error_code);
}
#endif

dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
{
	const struct mpx_bndcsr *bndcsr;

	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	if (notify_die(DIE_TRAP, "bounds", regs, error_code,
			X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
		return;
	cond_local_irq_enable(regs);

	if (!user_mode(regs))
		die("bounds", regs, error_code);

	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
		/* The exception is not from Intel MPX */
		goto exit_trap;
	}

	/*
	 * We need to look at BNDSTATUS to resolve this exception.
	 * A NULL here might mean that it is in its 'init state',
	 * which is all zeros which indicates MPX was not
	 * responsible for the exception.
	 */
	bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR);
	if (!bndcsr)
		goto exit_trap;

	trace_bounds_exception_mpx(bndcsr);
	/*
	 * The error code field of the BNDSTATUS register communicates status
	 * information of a bound range exception #BR or operation involving
	 * bound directory.
	 */
	switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
	case 2:	/* Bound directory has invalid entry. */
		if (mpx_handle_bd_fault())
			goto exit_trap;
		break; /* Success, it was handled */
	case 1: /* Bound violation. */
	{
		struct task_struct *tsk = current;
		struct mpx_fault_info mpx;

		if (mpx_fault_info(&mpx, regs)) {
			/*
			 * We failed to decode the MPX instruction.  Act as if
			 * the exception was not caused by MPX.
			 */
			goto exit_trap;
		}
		/*
		 * Success, we decoded the instruction and retrieved
		 * an 'mpx' containing the address being accessed
		 * which caused the exception.  This information
		 * allows and application to possibly handle the
		 * #BR exception itself.
		 */
		if (!do_trap_no_signal(tsk, X86_TRAP_BR, "bounds", regs,
				       error_code))
			break;

		show_signal(tsk, SIGSEGV, "trap ", "bounds", regs, error_code);

		force_sig_bnderr(mpx.addr, mpx.lower, mpx.upper);
		break;
	}
	case 0: /* No exception caused by Intel MPX operations. */
		goto exit_trap;
	default:
		die("bounds", regs, error_code);
	}

	return;

exit_trap:
	/*
	 * This path out is for all the cases where we could not
	 * handle the exception in some way (like allocating a
	 * table or telling userspace about it.  We will also end
	 * up here if the kernel has MPX turned off at compile
	 * time..
	 */
	do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL);
}

dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
	const char *desc = "general protection fault";
	struct task_struct *tsk;

	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	cond_local_irq_enable(regs);

	if (static_cpu_has(X86_FEATURE_UMIP)) {
		if (user_mode(regs) && fixup_umip_exception(regs))
			return;
	}

	if (v8086_mode(regs)) {
		local_irq_enable();
		handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
		return;
	}

	tsk = current;
	if (!user_mode(regs)) {
		if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
			return;

		tsk->thread.error_code = error_code;
		tsk->thread.trap_nr = X86_TRAP_GP;

		/*
		 * To be potentially processing a kprobe fault and to
		 * trust the result from kprobe_running(), we have to
		 * be non-preemptible.
		 */
		if (!preemptible() && kprobe_running() &&
		    kprobe_fault_handler(regs, X86_TRAP_GP))
			return;

		if (notify_die(DIE_GPF, desc, regs, error_code,
			       X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
			die(desc, regs, error_code);
		return;
	}

	tsk->thread.error_code = error_code;
	tsk->thread.trap_nr = X86_TRAP_GP;

	show_signal(tsk, SIGSEGV, "", desc, regs, error_code);

	force_sig(SIGSEGV, tsk);
}
NOKPROBE_SYMBOL(do_general_protection);

dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
	/*
	 * ftrace must be first, everything else may cause a recursive crash.
	 * See note by declaration of modifying_ftrace_code in ftrace.c
	 */
	if (unlikely(atomic_read(&modifying_ftrace_code)) &&
	    ftrace_int3_handler(regs))
		return;
#endif
	if (poke_int3_handler(regs))
		return;

	/*
	 * Use ist_enter despite the fact that we don't use an IST stack.
	 * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
	 * mode or even during context tracking state changes.
	 *
	 * This means that we can't schedule.  That's okay.
	 */
	ist_enter(regs);
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
				SIGTRAP) == NOTIFY_STOP)
		goto exit;
#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */

#ifdef CONFIG_KPROBES
	if (kprobe_int3_handler(regs))
		goto exit;
#endif

	if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
			SIGTRAP) == NOTIFY_STOP)
		goto exit;

	cond_local_irq_enable(regs);
	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL);
	cond_local_irq_disable(regs);

exit:
	ist_exit(regs);
}
NOKPROBE_SYMBOL(do_int3);

#ifdef CONFIG_X86_64
/*
 * Help handler running on a per-cpu (IST or entry trampoline) stack
 * to switch to the normal thread stack if the interrupted code was in
 * user mode. The actual stack switch is done in entry_64.S
 */
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
	if (regs != eregs)
		*regs = *eregs;
	return regs;
}
NOKPROBE_SYMBOL(sync_regs);

struct bad_iret_stack {
	void *error_entry_ret;
	struct pt_regs regs;
};

asmlinkage __visible notrace
struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
{
	/*
	 * This is called from entry_64.S early in handling a fault
	 * caused by a bad iret to user mode.  To handle the fault
	 * correctly, we want to move our stack frame to where it would
	 * be had we entered directly on the entry stack (rather than
	 * just below the IRET frame) and we want to pretend that the
	 * exception came from the IRET target.
	 */
	struct bad_iret_stack *new_stack =
		(struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;

	/* Copy the IRET target to the new stack. */
	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);

	/* Copy the remainder of the stack from the current stack. */
	memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));

	BUG_ON(!user_mode(&new_stack->regs));
	return new_stack;
}
NOKPROBE_SYMBOL(fixup_bad_iret);
#endif

static bool is_sysenter_singlestep(struct pt_regs *regs)
{
	/*
	 * We don't try for precision here.  If we're anywhere in the region of
	 * code that can be single-stepped in the SYSENTER entry path, then
	 * assume that this is a useless single-step trap due to SYSENTER
	 * being invoked with TF set.  (We don't know in advance exactly
	 * which instructions will be hit because BTF could plausibly
	 * be set.)
	 */
#ifdef CONFIG_X86_32
	return (regs->ip - (unsigned long)__begin_SYSENTER_singlestep_region) <
		(unsigned long)__end_SYSENTER_singlestep_region -
		(unsigned long)__begin_SYSENTER_singlestep_region;
#elif defined(CONFIG_IA32_EMULATION)
	return (regs->ip - (unsigned long)entry_SYSENTER_compat) <
		(unsigned long)__end_entry_SYSENTER_compat -
		(unsigned long)entry_SYSENTER_compat;
#else
	return false;
#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 do_debug(struct pt_regs *regs, long error_code)
{
	struct task_struct *tsk = current;
	int user_icebp = 0;
	unsigned long dr6;
	int si_code;

	ist_enter(regs);

	get_debugreg(dr6, 6);
	/*
	 * The Intel SDM says:
	 *
	 *   Certain debug exceptions may clear bits 0-3. The remaining
	 *   contents of the DR6 register are never cleared by the
	 *   processor. To avoid confusion in identifying debug
	 *   exceptions, debug handlers should clear the register before
	 *   returning to the interrupted task.
	 *
	 * Keep it simple: clear DR6 immediately.
	 */
	set_debugreg(0, 6);

	/* Filter out all the reserved bits which are preset to 1 */
	dr6 &= ~DR6_RESERVED;

	/*
	 * The SDM says "The processor clears the BTF flag when it
	 * generates a debug exception."  Clear TIF_BLOCKSTEP to keep
	 * TIF_BLOCKSTEP in sync with the hardware BTF flag.
	 */
	clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP);

	if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) &&
		     is_sysenter_singlestep(regs))) {
		dr6 &= ~DR_STEP;
		if (!dr6)
			goto exit;
		/*
		 * else we might have gotten a single-step trap and hit a
		 * watchpoint at the same time, in which case we should fall
		 * through and handle the watchpoint.
		 */
	}

	/*
	 * If dr6 has no reason to give us about the origin of this trap,
	 * then it's very likely the result of an icebp/int01 trap.
	 * User wants a sigtrap for that.
	 */
	if (!dr6 && user_mode(regs))
		user_icebp = 1;

	/* Store the virtualized DR6 value */
	tsk->thread.debugreg6 = dr6;

#ifdef CONFIG_KPROBES
	if (kprobe_debug_handler(regs))
		goto exit;
#endif

	if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code,
							SIGTRAP) == NOTIFY_STOP)
		goto exit;

	/*
	 * Let others (NMI) know that the debug stack is in use
	 * as we may switch to the interrupt stack.
	 */
	debug_stack_usage_inc();

	/* It's safe to allow irq's after DR6 has been saved */
	cond_local_irq_enable(regs);

	if (v8086_mode(regs)) {
		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
					X86_TRAP_DB);
		cond_local_irq_disable(regs);
		debug_stack_usage_dec();
		goto exit;
	}

	if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) {
		/*
		 * Historical junk that used to handle SYSENTER single-stepping.
		 * This should be unreachable now.  If we survive for a while
		 * without anyone hitting this warning, we'll turn this into
		 * an oops.
		 */
		tsk->thread.debugreg6 &= ~DR_STEP;
		set_tsk_thread_flag(tsk, TIF_SINGLESTEP);
		regs->flags &= ~X86_EFLAGS_TF;
	}
	si_code = get_si_code(tsk->thread.debugreg6);
	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
		send_sigtrap(tsk, regs, error_code, si_code);
	cond_local_irq_disable(regs);
	debug_stack_usage_dec();

exit:
	ist_exit(regs);
}
NOKPROBE_SYMBOL(do_debug);

/*
 * 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
 */
static void math_error(struct pt_regs *regs, int error_code, int trapnr)
{
	struct task_struct *task = current;
	struct fpu *fpu = &task->thread.fpu;
	int si_code;
	char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
						"simd exception";

	cond_local_irq_enable(regs);

	if (!user_mode(regs)) {
		if (fixup_exception(regs, trapnr, error_code, 0))
			return;

		task->thread.error_code = error_code;
		task->thread.trap_nr = trapnr;

		if (notify_die(DIE_TRAP, str, regs, error_code,
					trapnr, SIGFPE) != NOTIFY_STOP)
			die(str, regs, error_code);
		return;
	}

	/*
	 * Save the info for the exception handler and clear the error.
	 */
	fpu__save(fpu);

	task->thread.trap_nr	= trapnr;
	task->thread.error_code = error_code;

	si_code = fpu__exception_code(fpu, trapnr);
	/* Retry when we get spurious exceptions: */
	if (!si_code)
		return;

	force_sig_fault(SIGFPE, si_code,
			(void __user *)uprobe_get_trap_addr(regs), task);
}

dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
{
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	math_error(regs, error_code, X86_TRAP_MF);
}

dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	math_error(regs, error_code, X86_TRAP_XF);
}

dotraplinkage void
do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
{
	cond_local_irq_enable(regs);
}

dotraplinkage void
do_device_not_available(struct pt_regs *regs, long error_code)
{
	unsigned long cr0;

	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");

#ifdef CONFIG_MATH_EMULATION
	if (!boot_cpu_has(X86_FEATURE_FPU) && (read_cr0() & X86_CR0_EM)) {
		struct math_emu_info info = { };

		cond_local_irq_enable(regs);

		info.regs = regs;
		math_emulate(&info);
		return;
	}
#endif

	/* This should not happen. */
	cr0 = read_cr0();
	if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
		/* Try to fix it up and carry on. */
		write_cr0(cr0 & ~X86_CR0_TS);
	} else {
		/*
		 * Something terrible happened, and we're better off trying
		 * to kill the task than getting stuck in a never-ending
		 * loop of #NM faults.
		 */
		die("unexpected #NM exception", regs, error_code);
	}
}
NOKPROBE_SYMBOL(do_device_not_available);

#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
	local_irq_enable();

	if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
			X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
		do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
			ILL_BADSTK, (void __user *)NULL);
	}
}
#endif

void __init trap_init(void)
{
	/* Init cpu_entry_area before IST entries are set up */
	setup_cpu_entry_areas();

	idt_setup_traps();

	/*
	 * Set the IDT descriptor to a fixed read-only location, so that the
	 * "sidt" instruction will not leak the location of the kernel, and
	 * to defend the IDT against arbitrary memory write vulnerabilities.
	 * It will be reloaded in cpu_init() */
	cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table),
		    PAGE_KERNEL_RO);
	idt_descr.address = CPU_ENTRY_AREA_RO_IDT;

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

	idt_setup_ist_traps();

	x86_init.irqs.trap_init();

	idt_setup_debugidt_traps();
}