summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/fault.c
blob: c7861c9864e69e7b6dc7efc16083063bbab99e98 (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
/*
 * Based on arch/arm/mm/fault.c
 *
 * Copyright (C) 1995  Linus Torvalds
 * Copyright (C) 1995-2004 Russell King
 * Copyright (C) 2012 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/extable.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.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/bug.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/sysreg.h>
#include <asm/system_misc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

#include <acpi/ghes.h>

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

static const struct fault_info fault_info[];

static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
{
	return fault_info + (esr & 63);
}

#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
{
	int ret = 0;

	/* kprobe_running() needs smp_processor_id() */
	if (!user_mode(regs)) {
		preempt_disable();
		if (kprobe_running() && kprobe_fault_handler(regs, esr))
			ret = 1;
		preempt_enable();
	}

	return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
{
	return 0;
}
#endif

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

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

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

	do {
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

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

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

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

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

	pr_cont("\n");
}

#ifdef CONFIG_ARM64_HW_AFDBM
/*
 * 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;
	unsigned int tmp;

	if (pte_same(*ptep, entry))
		return 0;

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

	/*
	 * PTE_RDONLY is cleared by default in the asm below, so set it in
	 * back if necessary (read-only or clean PTE).
	 */
	if (!pte_write(entry) || !pte_sw_dirty(entry))
		pte_val(entry) |= PTE_RDONLY;

	/*
	 * Setting the flags must be done atomically to avoid racing with the
	 * hardware update of the access/dirty state.
	 */
	asm volatile("//	ptep_set_access_flags\n"
	"	prfm	pstl1strm, %2\n"
	"1:	ldxr	%0, %2\n"
	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
	"	orr	%0, %0, %4		// set flags\n"
	"	stxr	%w1, %0, %2\n"
	"	cbnz	%w1, 1b\n"
	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));

	flush_tlb_fix_spurious_fault(vma, address);
	return 1;
}
#endif

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

static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
				       unsigned long addr)
{
	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 (addr < USER_DS && system_uses_ttbr0_pan())
		return fsc_type == ESR_ELx_FSC_FAULT &&
			(regs->pstate & PSR_PAN_BIT);

	return false;
}

/*
 * The kernel tried to access some page that wasn't present.
 */
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;

	/*
	 * No handler, we'll have to terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);

	if (is_permission_fault(esr, regs, addr)) {
		if (esr & ESR_ELx_WNR)
			msg = "write to read-only memory";
		else
			msg = "read from unreadable memory";
	} else if (addr < PAGE_SIZE) {
		msg = "NULL pointer dereference";
	} else {
		msg = "paging request";
	}

	pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
		 addr);

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

/*
 * Something tried to access memory that isn't in our memory map. User mode
 * accesses just cause a SIGSEGV
 */
static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
			    unsigned int esr, unsigned int sig, int code,
			    struct pt_regs *regs, int fault)
{
	struct siginfo si;
	const struct fault_info *inf;
	unsigned int lsb = 0;

	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
		inf = esr_to_fault_info(esr);
		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x",
			tsk->comm, task_pid_nr(tsk), inf->name, sig,
			addr, esr);
		print_vma_addr(KERN_CONT ", in ", regs->pc);
		pr_cont("\n");
		__show_regs(regs);
	}

	tsk->thread.fault_address = addr;
	tsk->thread.fault_code = esr;
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	/*
	 * Either small page or large page may be poisoned.
	 * In other words, VM_FAULT_HWPOISON_LARGE and
	 * VM_FAULT_HWPOISON are mutually exclusive.
	 */
	if (fault & VM_FAULT_HWPOISON_LARGE)
		lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
	else if (fault & VM_FAULT_HWPOISON)
		lsb = PAGE_SHIFT;
	si.si_addr_lsb = lsb;

	force_sig_info(sig, &si, tsk);
}

static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	struct task_struct *tsk = current;
	const struct fault_info *inf;

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (user_mode(regs)) {
		inf = esr_to_fault_info(esr);
		__do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs, 0);
	} else
		__do_kernel_fault(addr, esr, regs);
}

#define VM_FAULT_BADMAP		0x010000
#define VM_FAULT_BADACCESS	0x020000

static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
			   unsigned int mm_flags, unsigned long vm_flags,
			   struct task_struct *tsk)
{
	struct vm_area_struct *vma;
	int fault;

	vma = find_vma(mm, addr);
	fault = VM_FAULT_BADMAP;
	if (unlikely(!vma))
		goto out;
	if (unlikely(vma->vm_start > addr))
		goto check_stack;

	/*
	 * Ok, we have a good vm_area for this memory access, so we can handle
	 * it.
	 */
good_area:
	/*
	 * Check that the permissions on the VMA allow for the fault which
	 * occurred.
	 */
	if (!(vma->vm_flags & vm_flags)) {
		fault = VM_FAULT_BADACCESS;
		goto out;
	}

	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);

check_stack:
	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
		goto good_area;
out:
	return fault;
}

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

static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
				   struct pt_regs *regs)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	int fault, sig, code, major = 0;
	unsigned long vm_flags = VM_READ | VM_WRITE;
	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

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

	tsk = current;
	mm  = tsk->mm;

	/*
	 * 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;
	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
		vm_flags = VM_WRITE;
		mm_flags |= FAULT_FLAG_WRITE;
	}

	if (addr < USER_DS && is_permission_fault(esr, regs, addr)) {
		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
		if (regs->orig_addr_limit == KERNEL_DS)
			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);

		if (is_el1_instruction_abort(esr))
			die("Attempting to execute userspace memory", regs, esr);

		if (!search_exception_tables(regs->pc))
			die("Accessing user space memory outside uaccess.h routines", regs, esr);
	}

	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 (!down_read_trylock(&mm->mmap_sem)) {
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
retry:
		down_read(&mm->mmap_sem);
	} else {
		/*
		 * The above down_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))
			goto no_context;
#endif
	}

	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
	major |= fault & VM_FAULT_MAJOR;

	if (fault & VM_FAULT_RETRY) {
		/*
		 * If we need to retry but a fatal signal is pending,
		 * handle the signal first. We do not need to release
		 * the mmap_sem because it would already be released
		 * in __lock_page_or_retry in mm/filemap.c.
		 */
		if (fatal_signal_pending(current))
			return 0;

		/*
		 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
		 * starvation.
		 */
		if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
			mm_flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}
	up_read(&mm->mmap_sem);

	/*
	 * Handle the "normal" (no error) case first.
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
			      VM_FAULT_BADACCESS)))) {
		/*
		 * Major/minor page fault accounting is only done
		 * once. If we go through a retry, it is extremely
		 * likely that the page will be found in page cache at
		 * that point.
		 */
		if (major) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
				      addr);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
				      addr);
		}

		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;
	}

	if (fault & VM_FAULT_SIGBUS) {
		/*
		 * We had some memory, but were unable to successfully fix up
		 * this page fault.
		 */
		sig = SIGBUS;
		code = BUS_ADRERR;
	} else if (fault & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
		sig = SIGBUS;
		code = BUS_MCEERR_AR;
	} else {
		/*
		 * Something tried to access memory that isn't in our memory
		 * map.
		 */
		sig = SIGSEGV;
		code = fault == VM_FAULT_BADACCESS ?
			SEGV_ACCERR : SEGV_MAPERR;
	}

	__do_user_fault(tsk, addr, esr, sig, code, regs, fault);
	return 0;

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

/*
 * First Level Translation Fault Handler
 *
 * We enter here because the first level page table doesn't contain a valid
 * entry for the address.
 *
 * If the address is in kernel space (>= TASK_SIZE), then we are probably
 * faulting in the vmalloc() area.
 *
 * If the init_task's first level page tables contains the relevant entry, we
 * copy the it to this task.  If not, we send the process a signal, fixup the
 * exception, or oops the kernel.
 *
 * NOTE! We MUST NOT take any locks for this case. We may be in an interrupt
 * or a critical region, and should only copy the information from the master
 * page table, nothing more.
 */
static int __kprobes do_translation_fault(unsigned long addr,
					  unsigned int esr,
					  struct pt_regs *regs)
{
	if (addr < TASK_SIZE)
		return do_page_fault(addr, esr, regs);

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

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

/*
 * This abort handler always returns "fault".
 */
static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	return 1;
}

/*
 * This abort handler deals with Synchronous External Abort.
 * It calls notifiers, and then returns "fault".
 */
static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	struct siginfo info;
	const struct fault_info *inf;
	int ret = 0;

	inf = esr_to_fault_info(esr);
	pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
		inf->name, esr, addr);

	/*
	 * Synchronous aborts may interrupt code which had interrupts masked.
	 * Before calling out into the wider kernel tell the interested
	 * subsystems.
	 */
	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
		if (interrupts_enabled(regs))
			nmi_enter();

		ret = ghes_notify_sea();

		if (interrupts_enabled(regs))
			nmi_exit();
	}

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = 0;
	if (esr & ESR_ELx_FnV)
		info.si_addr = NULL;
	else
		info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);

	return ret;
}

static const struct fault_info fault_info[] = {
	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"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_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
	{ do_bad,		SIGBUS,  0,		"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,		SIGBUS,  0,		"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,  0,		"synchronous external abort"	},
	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
	{ do_sea,		SIGBUS,  0,		"level 0 (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },
	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},
	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},
	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
};

/*
 * Handle Synchronous External Aborts that occur in a guest kernel.
 *
 * The return value will be zero if the SEA was successfully handled
 * and non-zero if there was an error processing the error or there was
 * no error to process.
 */
int handle_guest_sea(phys_addr_t addr, unsigned int esr)
{
	int ret = -ENOENT;

	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
		ret = ghes_notify_sea();

	return ret;
}

/*
 * Dispatch a data abort to the relevant handler.
 */
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
					 struct pt_regs *regs)
{
	const struct fault_info *inf = esr_to_fault_info(esr);
	struct siginfo info;

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

	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
		 inf->name, esr, addr);

	info.si_signo = inf->sig;
	info.si_errno = 0;
	info.si_code  = inf->code;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);
}

/*
 * Handle stack alignment exceptions.
 */
asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
					   unsigned int esr,
					   struct pt_regs *regs)
{
	struct siginfo info;
	struct task_struct *tsk = current;

	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
				    tsk->comm, task_pid_nr(tsk),
				    esr_get_class_string(esr), (void *)regs->pc,
				    (void *)regs->sp);

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = BUS_ADRALN;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
}

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,	SIGBUS,		0,		"unknown 3"		},
	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
	{ do_bad,	SIGBUS,		0,		"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;
}

asmlinkage int __exception do_debug_exception(unsigned long addr,
					      unsigned int esr,
					      struct pt_regs *regs)
{
	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
	struct siginfo info;
	int rv;

	/*
	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
	 * already disabled to preserve the last enabled/disabled addresses.
	 */
	if (interrupts_enabled(regs))
		trace_hardirqs_off();

	if (!inf->fn(addr, esr, regs)) {
		rv = 1;
	} else {
		pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
			 inf->name, esr, addr);

		info.si_signo = inf->sig;
		info.si_errno = 0;
		info.si_code  = inf->code;
		info.si_addr  = (void __user *)addr;
		arm64_notify_die("", regs, &info, 0);
		rv = 0;
	}

	if (interrupts_enabled(regs))
		trace_hardirqs_on();

	return rv;
}
NOKPROBE_SYMBOL(do_debug_exception);

#ifdef CONFIG_ARM64_PAN
int cpu_enable_pan(void *__unused)
{
	/*
	 * We modify PSTATE. This won't work from irq context as the PSTATE
	 * is discarded once we return from the exception.
	 */
	WARN_ON_ONCE(in_interrupt());

	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
	asm(SET_PSTATE_PAN(1));
	return 0;
}
#endif /* CONFIG_ARM64_PAN */