summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/fault.c
blob: 42515900ab2e6d08ad65398adc61246ad7763408 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Based on arch/arm/mm/fault.c
 *
 * Copyright (C) 1995  Linus Torvalds
 * Copyright (C) 1995-2004 Russell King
 * Copyright (C) 2012 ARM Ltd.
 */

#include <linux/acpi.h>
#include <linux/bitfield.h>
#include <linux/extable.h>
#include <linux/kfence.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kasan.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>
#include <linux/preempt.h>
#include <linux/hugetlb.h>

#include <asm/acpi.h>
#include <asm/bug.h>
#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/kprobes.h>
#include <asm/mte.h>
#include <asm/processor.h>
#include <asm/sysreg.h>
#include <asm/system_misc.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>

struct fault_info {
	int	(*fn)(unsigned long far, unsigned int esr,
		      struct pt_regs *regs);
	int	sig;
	int	code;
	const char *name;
};

static const struct fault_info fault_info[];
static struct fault_info debug_fault_info[];

static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
{
	return fault_info + (esr & ESR_ELx_FSC);
}

static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr)
{
	return debug_fault_info + DBG_ESR_EVT(esr);
}

static void data_abort_decode(unsigned int esr)
{
	pr_alert("Data abort info:\n");

	if (esr & ESR_ELx_ISV) {
		pr_alert("  Access size = %u byte(s)\n",
			 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
		pr_alert("  SSE = %lu, SRT = %lu\n",
			 (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
			 (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
		pr_alert("  SF = %lu, AR = %lu\n",
			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
	} else {
		pr_alert("  ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK);
	}

	pr_alert("  CM = %lu, WnR = %lu\n",
		 (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
		 (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
}

static void mem_abort_decode(unsigned int esr)
{
	pr_alert("Mem abort info:\n");

	pr_alert("  ESR = 0x%08x\n", esr);
	pr_alert("  EC = 0x%02lx: %s, IL = %u bits\n",
		 ESR_ELx_EC(esr), esr_get_class_string(esr),
		 (esr & ESR_ELx_IL) ? 32 : 16);
	pr_alert("  SET = %lu, FnV = %lu\n",
		 (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
		 (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
	pr_alert("  EA = %lu, S1PTW = %lu\n",
		 (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
		 (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);

	if (esr_is_data_abort(esr))
		data_abort_decode(esr);
}

static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm)
{
	/* Either init_pg_dir or swapper_pg_dir */
	if (mm == &init_mm)
		return __pa_symbol(mm->pgd);

	return (unsigned long)virt_to_phys(mm->pgd);
}

/*
 * Dump out the page tables associated with 'addr' in the currently active mm.
 */
static void show_pte(unsigned long addr)
{
	struct mm_struct *mm;
	pgd_t *pgdp;
	pgd_t pgd;

	if (is_ttbr0_addr(addr)) {
		/* TTBR0 */
		mm = current->active_mm;
		if (mm == &init_mm) {
			pr_alert("[%016lx] user address but active_mm is swapper\n",
				 addr);
			return;
		}
	} else if (is_ttbr1_addr(addr)) {
		/* TTBR1 */
		mm = &init_mm;
	} else {
		pr_alert("[%016lx] address between user and kernel address ranges\n",
			 addr);
		return;
	}

	pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n",
		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
		 vabits_actual, mm_to_pgd_phys(mm));
	pgdp = pgd_offset(mm, addr);
	pgd = READ_ONCE(*pgdp);
	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));

	do {
		p4d_t *p4dp, p4d;
		pud_t *pudp, pud;
		pmd_t *pmdp, pmd;
		pte_t *ptep, pte;

		if (pgd_none(pgd) || pgd_bad(pgd))
			break;

		p4dp = p4d_offset(pgdp, addr);
		p4d = READ_ONCE(*p4dp);
		pr_cont(", p4d=%016llx", p4d_val(p4d));
		if (p4d_none(p4d) || p4d_bad(p4d))
			break;

		pudp = pud_offset(p4dp, addr);
		pud = READ_ONCE(*pudp);
		pr_cont(", pud=%016llx", pud_val(pud));
		if (pud_none(pud) || pud_bad(pud))
			break;

		pmdp = pmd_offset(pudp, addr);
		pmd = READ_ONCE(*pmdp);
		pr_cont(", pmd=%016llx", pmd_val(pmd));
		if (pmd_none(pmd) || pmd_bad(pmd))
			break;

		ptep = pte_offset_map(pmdp, addr);
		pte = READ_ONCE(*ptep);
		pr_cont(", pte=%016llx", pte_val(pte));
		pte_unmap(ptep);
	} while(0);

	pr_cont("\n");
}

/*
 * This function sets the access flags (dirty, accessed), as well as write
 * permission, and only to a more permissive setting.
 *
 * It needs to cope with hardware update of the accessed/dirty state by other
 * agents in the system and can safely skip the __sync_icache_dcache() call as,
 * like set_pte_at(), the PTE is never changed from no-exec to exec here.
 *
 * Returns whether or not the PTE actually changed.
 */
int ptep_set_access_flags(struct vm_area_struct *vma,
			  unsigned long address, pte_t *ptep,
			  pte_t entry, int dirty)
{
	pteval_t old_pteval, pteval;
	pte_t pte = READ_ONCE(*ptep);

	if (pte_same(pte, entry))
		return 0;

	/* only preserve the access flags and write permission */
	pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;

	/*
	 * Setting the flags must be done atomically to avoid racing with the
	 * hardware update of the access/dirty state. The PTE_RDONLY bit must
	 * be set to the most permissive (lowest value) of *ptep and entry
	 * (calculated as: a & b == ~(~a | ~b)).
	 */
	pte_val(entry) ^= PTE_RDONLY;
	pteval = pte_val(pte);
	do {
		old_pteval = pteval;
		pteval ^= PTE_RDONLY;
		pteval |= pte_val(entry);
		pteval ^= PTE_RDONLY;
		pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
	} while (pteval != old_pteval);

	/* Invalidate a stale read-only entry */
	if (dirty)
		flush_tlb_page(vma, address);
	return 1;
}

static bool is_el1_instruction_abort(unsigned int esr)
{
	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
}

static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr,
					   struct pt_regs *regs)
{
	unsigned int ec       = ESR_ELx_EC(esr);
	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;

	if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
		return false;

	if (fsc_type == ESR_ELx_FSC_PERM)
		return true;

	if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan())
		return fsc_type == ESR_ELx_FSC_FAULT &&
			(regs->pstate & PSR_PAN_BIT);

	return false;
}

static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
							unsigned int esr,
							struct pt_regs *regs)
{
	unsigned long flags;
	u64 par, dfsc;

	if (ESR_ELx_EC(esr) != ESR_ELx_EC_DABT_CUR ||
	    (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT)
		return false;

	local_irq_save(flags);
	asm volatile("at s1e1r, %0" :: "r" (addr));
	isb();
	par = read_sysreg_par();
	local_irq_restore(flags);

	/*
	 * If we now have a valid translation, treat the translation fault as
	 * spurious.
	 */
	if (!(par & SYS_PAR_EL1_F))
		return true;

	/*
	 * If we got a different type of fault from the AT instruction,
	 * treat the translation fault as spurious.
	 */
	dfsc = FIELD_GET(SYS_PAR_EL1_FST, par);
	return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT;
}

static void die_kernel_fault(const char *msg, unsigned long addr,
			     unsigned int esr, struct pt_regs *regs)
{
	bust_spinlocks(1);

	pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg,
		 addr);

	mem_abort_decode(esr);

	show_pte(addr);
	die("Oops", regs, esr);
	bust_spinlocks(0);
	do_exit(SIGKILL);
}

#ifdef CONFIG_KASAN_HW_TAGS
static void report_tag_fault(unsigned long addr, unsigned int esr,
			     struct pt_regs *regs)
{
	static bool reported;
	bool is_write;

	if (READ_ONCE(reported))
		return;

	/*
	 * This is used for KASAN tests and assumes that no MTE faults
	 * happened before running the tests.
	 */
	if (mte_report_once())
		WRITE_ONCE(reported, true);

	/*
	 * SAS bits aren't set for all faults reported in EL1, so we can't
	 * find out access size.
	 */
	is_write = !!(esr & ESR_ELx_WNR);
	kasan_report(addr, 0, is_write, regs->pc);
}
#else
/* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */
static inline void report_tag_fault(unsigned long addr, unsigned int esr,
				    struct pt_regs *regs) { }
#endif

static void do_tag_recovery(unsigned long addr, unsigned int esr,
			   struct pt_regs *regs)
{

	report_tag_fault(addr, esr, regs);

	/*
	 * Disable MTE Tag Checking on the local CPU for the current EL.
	 * It will be done lazily on the other CPUs when they will hit a
	 * tag fault.
	 */
	sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_NONE);
	isb();
}

static bool is_el1_mte_sync_tag_check_fault(unsigned int esr)
{
	unsigned int ec = ESR_ELx_EC(esr);
	unsigned int fsc = esr & ESR_ELx_FSC;

	if (ec != ESR_ELx_EC_DABT_CUR)
		return false;

	if (fsc == ESR_ELx_FSC_MTE)
		return true;

	return false;
}

static void __do_kernel_fault(unsigned long addr, unsigned int esr,
			      struct pt_regs *regs)
{
	const char *msg;

	/*
	 * Are we prepared to handle this kernel fault?
	 * We are almost certainly not prepared to handle instruction faults.
	 */
	if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
		return;

	if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs),
	    "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr))
		return;

	if (is_el1_mte_sync_tag_check_fault(esr)) {
		do_tag_recovery(addr, esr, regs);

		return;
	}

	if (is_el1_permission_fault(addr, esr, regs)) {
		if (esr & ESR_ELx_WNR)
			msg = "write to read-only memory";
		else if (is_el1_instruction_abort(esr))
			msg = "execute from non-executable memory";
		else
			msg = "read from unreadable memory";
	} else if (addr < PAGE_SIZE) {
		msg = "NULL pointer dereference";
	} else {
		if (kfence_handle_page_fault(addr))
			return;

		msg = "paging request";
	}

	die_kernel_fault(msg, addr, esr, regs);
}

static void set_thread_esr(unsigned long address, unsigned int esr)
{
	current->thread.fault_address = address;

	/*
	 * If the faulting address is in the kernel, we must sanitize the ESR.
	 * From userspace's point of view, kernel-only mappings don't exist
	 * at all, so we report them as level 0 translation faults.
	 * (This is not quite the way that "no mapping there at all" behaves:
	 * an alignment fault not caused by the memory type would take
	 * precedence over translation fault for a real access to empty
	 * space. Unfortunately we can't easily distinguish "alignment fault
	 * not caused by memory type" from "alignment fault caused by memory
	 * type", so we ignore this wrinkle and just return the translation
	 * fault.)
	 */
	if (!is_ttbr0_addr(current->thread.fault_address)) {
		switch (ESR_ELx_EC(esr)) {
		case ESR_ELx_EC_DABT_LOW:
			/*
			 * These bits provide only information about the
			 * faulting instruction, which userspace knows already.
			 * We explicitly clear bits which are architecturally
			 * RES0 in case they are given meanings in future.
			 * We always report the ESR as if the fault was taken
			 * to EL1 and so ISV and the bits in ISS[23:14] are
			 * clear. (In fact it always will be a fault to EL1.)
			 */
			esr &= ESR_ELx_EC_MASK | ESR_ELx_IL |
				ESR_ELx_CM | ESR_ELx_WNR;
			esr |= ESR_ELx_FSC_FAULT;
			break;
		case ESR_ELx_EC_IABT_LOW:
			/*
			 * Claim a level 0 translation fault.
			 * All other bits are architecturally RES0 for faults
			 * reported with that DFSC value, so we clear them.
			 */
			esr &= ESR_ELx_EC_MASK | ESR_ELx_IL;
			esr |= ESR_ELx_FSC_FAULT;
			break;
		default:
			/*
			 * This should never happen (entry.S only brings us
			 * into this code for insn and data aborts from a lower
			 * exception level). Fail safe by not providing an ESR
			 * context record at all.
			 */
			WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr);
			esr = 0;
			break;
		}
	}

	current->thread.fault_code = esr;
}

static void do_bad_area(unsigned long far, unsigned int esr,
			struct pt_regs *regs)
{
	unsigned long addr = untagged_addr(far);

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (user_mode(regs)) {
		const struct fault_info *inf = esr_to_fault_info(esr);

		set_thread_esr(addr, esr);
		arm64_force_sig_fault(inf->sig, inf->code, far, inf->name);
	} else {
		__do_kernel_fault(addr, esr, regs);
	}
}

#define VM_FAULT_BADMAP		0x010000
#define VM_FAULT_BADACCESS	0x020000

static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
				  unsigned int mm_flags, unsigned long vm_flags,
				  struct pt_regs *regs)
{
	struct vm_area_struct *vma = find_vma(mm, addr);

	if (unlikely(!vma))
		return VM_FAULT_BADMAP;

	/*
	 * Ok, we have a good vm_area for this memory access, so we can handle
	 * it.
	 */
	if (unlikely(vma->vm_start > addr)) {
		if (!(vma->vm_flags & VM_GROWSDOWN))
			return VM_FAULT_BADMAP;
		if (expand_stack(vma, addr))
			return VM_FAULT_BADMAP;
	}

	/*
	 * Check that the permissions on the VMA allow for the fault which
	 * occurred.
	 */
	if (!(vma->vm_flags & vm_flags))
		return VM_FAULT_BADACCESS;
	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
}

static bool is_el0_instruction_abort(unsigned int esr)
{
	return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
}

/*
 * Note: not valid for EL1 DC IVAC, but we never use that such that it
 * should fault. EL0 cannot issue DC IVAC (undef).
 */
static bool is_write_abort(unsigned int esr)
{
	return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM);
}

static int __kprobes do_page_fault(unsigned long far, unsigned int esr,
				   struct pt_regs *regs)
{
	const struct fault_info *inf;
	struct mm_struct *mm = current->mm;
	vm_fault_t fault;
	unsigned long vm_flags = VM_ACCESS_FLAGS;
	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
	unsigned long addr = untagged_addr(far);

	if (kprobe_page_fault(regs, esr))
		return 0;

	/*
	 * If we're in an interrupt or have no user context, we must not take
	 * the fault.
	 */
	if (faulthandler_disabled() || !mm)
		goto no_context;

	if (user_mode(regs))
		mm_flags |= FAULT_FLAG_USER;

	if (is_el0_instruction_abort(esr)) {
		vm_flags = VM_EXEC;
		mm_flags |= FAULT_FLAG_INSTRUCTION;
	} else if (is_write_abort(esr)) {
		vm_flags = VM_WRITE;
		mm_flags |= FAULT_FLAG_WRITE;
	}

	if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) {
		if (is_el1_instruction_abort(esr))
			die_kernel_fault("execution of user memory",
					 addr, esr, regs);

		if (!search_exception_tables(regs->pc))
			die_kernel_fault("access to user memory outside uaccess routines",
					 addr, esr, regs);
	}

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);

	/*
	 * As per x86, we may deadlock here. However, since the kernel only
	 * validly references user space from well defined areas of the code,
	 * we can bug out early if this is from code which shouldn't.
	 */
	if (!mmap_read_trylock(mm)) {
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
retry:
		mmap_read_lock(mm);
	} else {
		/*
		 * The above mmap_read_trylock() might have succeeded in which
		 * case, we'll have missed the might_sleep() from down_read().
		 */
		might_sleep();
#ifdef CONFIG_DEBUG_VM
		if (!user_mode(regs) && !search_exception_tables(regs->pc)) {
			mmap_read_unlock(mm);
			goto no_context;
		}
#endif
	}

	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs);

	/* Quick path to respond to signals */
	if (fault_signal_pending(fault, regs)) {
		if (!user_mode(regs))
			goto no_context;
		return 0;
	}

	if (fault & VM_FAULT_RETRY) {
		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
			mm_flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}
	mmap_read_unlock(mm);

	/*
	 * Handle the "normal" (no error) case first.
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
			      VM_FAULT_BADACCESS))))
		return 0;

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (!user_mode(regs))
		goto no_context;

	if (fault & VM_FAULT_OOM) {
		/*
		 * We ran out of memory, call the OOM killer, and return to
		 * userspace (which will retry the fault, or kill us if we got
		 * oom-killed).
		 */
		pagefault_out_of_memory();
		return 0;
	}

	inf = esr_to_fault_info(esr);
	set_thread_esr(addr, esr);
	if (fault & VM_FAULT_SIGBUS) {
		/*
		 * We had some memory, but were unable to successfully fix up
		 * this page fault.
		 */
		arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name);
	} else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) {
		unsigned int lsb;

		lsb = PAGE_SHIFT;
		if (fault & VM_FAULT_HWPOISON_LARGE)
			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));

		arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name);
	} else {
		/*
		 * Something tried to access memory that isn't in our memory
		 * map.
		 */
		arm64_force_sig_fault(SIGSEGV,
				      fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR,
				      far, inf->name);
	}

	return 0;

no_context:
	__do_kernel_fault(addr, esr, regs);
	return 0;
}

static int __kprobes do_translation_fault(unsigned long far,
					  unsigned int esr,
					  struct pt_regs *regs)
{
	unsigned long addr = untagged_addr(far);

	if (is_ttbr0_addr(addr))
		return do_page_fault(far, esr, regs);

	do_bad_area(far, esr, regs);
	return 0;
}

static int do_alignment_fault(unsigned long far, unsigned int esr,
			      struct pt_regs *regs)
{
	do_bad_area(far, esr, regs);
	return 0;
}

static int do_bad(unsigned long far, unsigned int esr, struct pt_regs *regs)
{
	return 1; /* "fault" */
}

static int do_sea(unsigned long far, unsigned int esr, struct pt_regs *regs)
{
	const struct fault_info *inf;
	unsigned long siaddr;

	inf = esr_to_fault_info(esr);

	if (user_mode(regs) && apei_claim_sea(regs) == 0) {
		/*
		 * APEI claimed this as a firmware-first notification.
		 * Some processing deferred to task_work before ret_to_user().
		 */
		return 0;
	}

	if (esr & ESR_ELx_FnV) {
		siaddr = 0;
	} else {
		/*
		 * The architecture specifies that the tag bits of FAR_EL1 are
		 * UNKNOWN for synchronous external aborts. Mask them out now
		 * so that userspace doesn't see them.
		 */
		siaddr  = untagged_addr(far);
	}
	arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);

	return 0;
}

static int do_tag_check_fault(unsigned long far, unsigned int esr,
			      struct pt_regs *regs)
{
	/*
	 * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN
	 * for tag check faults. Set them to corresponding bits in the untagged
	 * address.
	 */
	far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK);
	do_bad_area(far, esr, regs);
	return 0;
}

static const struct fault_info fault_info[] = {
	{ do_bad,		SIGKILL, SI_KERNEL,	"ttbr address size fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"level 1 address size fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"level 2 address size fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"level 3 address size fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 8"			},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 12"			},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
	{ do_sea,		SIGBUS,  BUS_OBJERR,	"synchronous external abort"	},
	{ do_tag_check_fault,	SIGSEGV, SEGV_MTESERR,	"synchronous tag check fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 18"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 19"			},
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 0 (translation table walk)"	},
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 1 (translation table walk)"	},
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 2 (translation table walk)"	},
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 3 (translation table walk)"	},
	{ do_sea,		SIGBUS,  BUS_OBJERR,	"synchronous parity or ECC error" },	// Reserved when RAS is implemented
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 25"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 26"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 27"			},
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 0 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 1 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 2 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
	{ do_sea,		SIGKILL, SI_KERNEL,	"level 3 synchronous parity error (translation table walk)"	},	// Reserved when RAS is implemented
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 32"			},
	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 34"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 35"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 36"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 37"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 38"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 39"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 40"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 41"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 42"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 43"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 44"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 45"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 46"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 47"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"TLB conflict abort"		},
	{ do_bad,		SIGKILL, SI_KERNEL,	"Unsupported atomic hardware update fault"	},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 50"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 51"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"implementation fault (lockdown abort)" },
	{ do_bad,		SIGBUS,  BUS_OBJERR,	"implementation fault (unsupported exclusive)" },
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 54"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 55"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 56"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 57"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 58" 			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 59"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 60"			},
	{ do_bad,		SIGKILL, SI_KERNEL,	"section domain fault"		},
	{ do_bad,		SIGKILL, SI_KERNEL,	"page domain fault"		},
	{ do_bad,		SIGKILL, SI_KERNEL,	"unknown 63"			},
};

void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs)
{
	const struct fault_info *inf = esr_to_fault_info(esr);
	unsigned long addr = untagged_addr(far);

	if (!inf->fn(far, esr, regs))
		return;

	if (!user_mode(regs)) {
		pr_alert("Unhandled fault at 0x%016lx\n", addr);
		mem_abort_decode(esr);
		show_pte(addr);
	}

	/*
	 * At this point we have an unrecognized fault type whose tag bits may
	 * have been defined as UNKNOWN. Therefore we only expose the untagged
	 * address to the signal handler.
	 */
	arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr);
}
NOKPROBE_SYMBOL(do_mem_abort);

void do_el0_irq_bp_hardening(void)
{
	/* PC has already been checked in entry.S */
	arm64_apply_bp_hardening();
}
NOKPROBE_SYMBOL(do_el0_irq_bp_hardening);

void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN,
			 addr, esr);
}
NOKPROBE_SYMBOL(do_sp_pc_abort);

int __init early_brk64(unsigned long addr, unsigned int esr,
		       struct pt_regs *regs);

/*
 * __refdata because early_brk64 is __init, but the reference to it is
 * clobbered at arch_initcall time.
 * See traps.c and debug-monitors.c:debug_traps_init().
 */
static struct fault_info __refdata debug_fault_info[] = {
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
	{ do_bad,	SIGKILL,	SI_KERNEL,	"unknown 3"		},
	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
	{ do_bad,	SIGKILL,	SI_KERNEL,	"aarch32 vector catch"	},
	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
	{ do_bad,	SIGKILL,	SI_KERNEL,	"unknown 7"		},
};

void __init hook_debug_fault_code(int nr,
				  int (*fn)(unsigned long, unsigned int, struct pt_regs *),
				  int sig, int code, const char *name)
{
	BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info));

	debug_fault_info[nr].fn		= fn;
	debug_fault_info[nr].sig	= sig;
	debug_fault_info[nr].code	= code;
	debug_fault_info[nr].name	= name;
}

/*
 * In debug exception context, we explicitly disable preemption despite
 * having interrupts disabled.
 * This serves two purposes: it makes it much less likely that we would
 * accidentally schedule in exception context and it will force a warning
 * if we somehow manage to schedule by accident.
 */
static void debug_exception_enter(struct pt_regs *regs)
{
	preempt_disable();

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

static void debug_exception_exit(struct pt_regs *regs)
{
	preempt_enable_no_resched();
}
NOKPROBE_SYMBOL(debug_exception_exit);

void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr,
			struct pt_regs *regs)
{
	const struct fault_info *inf = esr_to_debug_fault_info(esr);
	unsigned long pc = instruction_pointer(regs);

	debug_exception_enter(regs);

	if (user_mode(regs) && !is_ttbr0_addr(pc))
		arm64_apply_bp_hardening();

	if (inf->fn(addr_if_watchpoint, esr, regs)) {
		arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr);
	}

	debug_exception_exit(regs);
}
NOKPROBE_SYMBOL(do_debug_exception);