summaryrefslogtreecommitdiff
path: root/arch/x86/mm/fault.c
blob: e238517968836ea1c60475662825cf923d938fdd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
// SPDX-License-Identifier: GPL-2.0
/*
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
 *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
 */
#include <linux/sched.h>		/* test_thread_flag(), ...	*/
#include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
#include <linux/kdebug.h>		/* oops_begin/end, ...		*/
#include <linux/extable.h>		/* search_exception_tables	*/
#include <linux/memblock.h>		/* max_low_pfn			*/
#include <linux/kfence.h>		/* kfence_handle_page_fault	*/
#include <linux/kprobes.h>		/* NOKPROBE_SYMBOL, ...		*/
#include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
#include <linux/perf_event.h>		/* perf_sw_event		*/
#include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
#include <linux/prefetch.h>		/* prefetchw			*/
#include <linux/context_tracking.h>	/* exception_enter(), ...	*/
#include <linux/uaccess.h>		/* faulthandler_disabled()	*/
#include <linux/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
#include <linux/mm_types.h>
#include <linux/mm.h>			/* find_and_lock_vma() */

#include <asm/cpufeature.h>		/* boot_cpu_has, ...		*/
#include <asm/traps.h>			/* dotraplinkage, ...		*/
#include <asm/fixmap.h>			/* VSYSCALL_ADDR		*/
#include <asm/vsyscall.h>		/* emulate_vsyscall		*/
#include <asm/vm86.h>			/* struct vm86			*/
#include <asm/mmu_context.h>		/* vma_pkey()			*/
#include <asm/efi.h>			/* efi_crash_gracefully_on_page_fault()*/
#include <asm/desc.h>			/* store_idt(), ...		*/
#include <asm/cpu_entry_area.h>		/* exception stack		*/
#include <asm/pgtable_areas.h>		/* VMALLOC_START, ...		*/
#include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
#include <asm/vdso.h>			/* fixup_vdso_exception()	*/
#include <asm/irq_stack.h>

#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>

/*
 * Returns 0 if mmiotrace is disabled, or if the fault is not
 * handled by mmiotrace:
 */
static nokprobe_inline int
kmmio_fault(struct pt_regs *regs, unsigned long addr)
{
	if (unlikely(is_kmmio_active()))
		if (kmmio_handler(regs, addr) == 1)
			return -1;
	return 0;
}

/*
 * Prefetch quirks:
 *
 * 32-bit mode:
 *
 *   Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
 *   Check that here and ignore it.  This is AMD erratum #91.
 *
 * 64-bit mode:
 *
 *   Sometimes the CPU reports invalid exceptions on prefetch.
 *   Check that here and ignore it.
 *
 * Opcode checker based on code by Richard Brunner.
 */
static inline int
check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
		      unsigned char opcode, int *prefetch)
{
	unsigned char instr_hi = opcode & 0xf0;
	unsigned char instr_lo = opcode & 0x0f;

	switch (instr_hi) {
	case 0x20:
	case 0x30:
		/*
		 * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
		 * In X86_64 long mode, the CPU will signal invalid
		 * opcode if some of these prefixes are present so
		 * X86_64 will never get here anyway
		 */
		return ((instr_lo & 7) == 0x6);
#ifdef CONFIG_X86_64
	case 0x40:
		/*
		 * In 64-bit mode 0x40..0x4F are valid REX prefixes
		 */
		return (!user_mode(regs) || user_64bit_mode(regs));
#endif
	case 0x60:
		/* 0x64 thru 0x67 are valid prefixes in all modes. */
		return (instr_lo & 0xC) == 0x4;
	case 0xF0:
		/* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
		return !instr_lo || (instr_lo>>1) == 1;
	case 0x00:
		/* Prefetch instruction is 0x0F0D or 0x0F18 */
		if (get_kernel_nofault(opcode, instr))
			return 0;

		*prefetch = (instr_lo == 0xF) &&
			(opcode == 0x0D || opcode == 0x18);
		return 0;
	default:
		return 0;
	}
}

static bool is_amd_k8_pre_npt(void)
{
	struct cpuinfo_x86 *c = &boot_cpu_data;

	return unlikely(IS_ENABLED(CONFIG_CPU_SUP_AMD) &&
			c->x86_vendor == X86_VENDOR_AMD &&
			c->x86 == 0xf && c->x86_model < 0x40);
}

static int
is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
{
	unsigned char *max_instr;
	unsigned char *instr;
	int prefetch = 0;

	/* Erratum #91 affects AMD K8, pre-NPT CPUs */
	if (!is_amd_k8_pre_npt())
		return 0;

	/*
	 * If it was a exec (instruction fetch) fault on NX page, then
	 * do not ignore the fault:
	 */
	if (error_code & X86_PF_INSTR)
		return 0;

	instr = (void *)convert_ip_to_linear(current, regs);
	max_instr = instr + 15;

	/*
	 * This code has historically always bailed out if IP points to a
	 * not-present page (e.g. due to a race).  No one has ever
	 * complained about this.
	 */
	pagefault_disable();

	while (instr < max_instr) {
		unsigned char opcode;

		if (user_mode(regs)) {
			if (get_user(opcode, (unsigned char __user *) instr))
				break;
		} else {
			if (get_kernel_nofault(opcode, instr))
				break;
		}

		instr++;

		if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
			break;
	}

	pagefault_enable();
	return prefetch;
}

DEFINE_SPINLOCK(pgd_lock);
LIST_HEAD(pgd_list);

#ifdef CONFIG_X86_32
static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
{
	unsigned index = pgd_index(address);
	pgd_t *pgd_k;
	p4d_t *p4d, *p4d_k;
	pud_t *pud, *pud_k;
	pmd_t *pmd, *pmd_k;

	pgd += index;
	pgd_k = init_mm.pgd + index;

	if (!pgd_present(*pgd_k))
		return NULL;

	/*
	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
	 * and redundant with the set_pmd() on non-PAE. As would
	 * set_p4d/set_pud.
	 */
	p4d = p4d_offset(pgd, address);
	p4d_k = p4d_offset(pgd_k, address);
	if (!p4d_present(*p4d_k))
		return NULL;

	pud = pud_offset(p4d, address);
	pud_k = pud_offset(p4d_k, address);
	if (!pud_present(*pud_k))
		return NULL;

	pmd = pmd_offset(pud, address);
	pmd_k = pmd_offset(pud_k, address);

	if (pmd_present(*pmd) != pmd_present(*pmd_k))
		set_pmd(pmd, *pmd_k);

	if (!pmd_present(*pmd_k))
		return NULL;
	else
		BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));

	return pmd_k;
}

/*
 *   Handle a fault on the vmalloc or module mapping area
 *
 *   This is needed because there is a race condition between the time
 *   when the vmalloc mapping code updates the PMD to the point in time
 *   where it synchronizes this update with the other page-tables in the
 *   system.
 *
 *   In this race window another thread/CPU can map an area on the same
 *   PMD, finds it already present and does not synchronize it with the
 *   rest of the system yet. As a result v[mz]alloc might return areas
 *   which are not mapped in every page-table in the system, causing an
 *   unhandled page-fault when they are accessed.
 */
static noinline int vmalloc_fault(unsigned long address)
{
	unsigned long pgd_paddr;
	pmd_t *pmd_k;
	pte_t *pte_k;

	/* Make sure we are in vmalloc area: */
	if (!(address >= VMALLOC_START && address < VMALLOC_END))
		return -1;

	/*
	 * Synchronize this task's top level page-table
	 * with the 'reference' page table.
	 *
	 * Do _not_ use "current" here. We might be inside
	 * an interrupt in the middle of a task switch..
	 */
	pgd_paddr = read_cr3_pa();
	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
	if (!pmd_k)
		return -1;

	if (pmd_large(*pmd_k))
		return 0;

	pte_k = pte_offset_kernel(pmd_k, address);
	if (!pte_present(*pte_k))
		return -1;

	return 0;
}
NOKPROBE_SYMBOL(vmalloc_fault);

void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
{
	unsigned long addr;

	for (addr = start & PMD_MASK;
	     addr >= TASK_SIZE_MAX && addr < VMALLOC_END;
	     addr += PMD_SIZE) {
		struct page *page;

		spin_lock(&pgd_lock);
		list_for_each_entry(page, &pgd_list, lru) {
			spinlock_t *pgt_lock;

			/* the pgt_lock only for Xen */
			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;

			spin_lock(pgt_lock);
			vmalloc_sync_one(page_address(page), addr);
			spin_unlock(pgt_lock);
		}
		spin_unlock(&pgd_lock);
	}
}

static bool low_pfn(unsigned long pfn)
{
	return pfn < max_low_pfn;
}

static void dump_pagetable(unsigned long address)
{
	pgd_t *base = __va(read_cr3_pa());
	pgd_t *pgd = &base[pgd_index(address)];
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

#ifdef CONFIG_X86_PAE
	pr_info("*pdpt = %016Lx ", pgd_val(*pgd));
	if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd))
		goto out;
#define pr_pde pr_cont
#else
#define pr_pde pr_info
#endif
	p4d = p4d_offset(pgd, address);
	pud = pud_offset(p4d, address);
	pmd = pmd_offset(pud, address);
	pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd));
#undef pr_pde

	/*
	 * We must not directly access the pte in the highpte
	 * case if the page table is located in highmem.
	 * And let's rather not kmap-atomic the pte, just in case
	 * it's allocated already:
	 */
	if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd))
		goto out;

	pte = pte_offset_kernel(pmd, address);
	pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte));
out:
	pr_cont("\n");
}

#else /* CONFIG_X86_64: */

#ifdef CONFIG_CPU_SUP_AMD
static const char errata93_warning[] =
KERN_ERR 
"******* Your BIOS seems to not contain a fix for K8 errata #93\n"
"******* Working around it, but it may cause SEGVs or burn power.\n"
"******* Please consider a BIOS update.\n"
"******* Disabling USB legacy in the BIOS may also help.\n";
#endif

static int bad_address(void *p)
{
	unsigned long dummy;

	return get_kernel_nofault(dummy, (unsigned long *)p);
}

static void dump_pagetable(unsigned long address)
{
	pgd_t *base = __va(read_cr3_pa());
	pgd_t *pgd = base + pgd_index(address);
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (bad_address(pgd))
		goto bad;

	pr_info("PGD %lx ", pgd_val(*pgd));

	if (!pgd_present(*pgd))
		goto out;

	p4d = p4d_offset(pgd, address);
	if (bad_address(p4d))
		goto bad;

	pr_cont("P4D %lx ", p4d_val(*p4d));
	if (!p4d_present(*p4d) || p4d_large(*p4d))
		goto out;

	pud = pud_offset(p4d, address);
	if (bad_address(pud))
		goto bad;

	pr_cont("PUD %lx ", pud_val(*pud));
	if (!pud_present(*pud) || pud_leaf(*pud))
		goto out;

	pmd = pmd_offset(pud, address);
	if (bad_address(pmd))
		goto bad;

	pr_cont("PMD %lx ", pmd_val(*pmd));
	if (!pmd_present(*pmd) || pmd_large(*pmd))
		goto out;

	pte = pte_offset_kernel(pmd, address);
	if (bad_address(pte))
		goto bad;

	pr_cont("PTE %lx", pte_val(*pte));
out:
	pr_cont("\n");
	return;
bad:
	pr_info("BAD\n");
}

#endif /* CONFIG_X86_64 */

/*
 * Workaround for K8 erratum #93 & buggy BIOS.
 *
 * BIOS SMM functions are required to use a specific workaround
 * to avoid corruption of the 64bit RIP register on C stepping K8.
 *
 * A lot of BIOS that didn't get tested properly miss this.
 *
 * The OS sees this as a page fault with the upper 32bits of RIP cleared.
 * Try to work around it here.
 *
 * Note we only handle faults in kernel here.
 * Does nothing on 32-bit.
 */
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD)
	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD
	    || boot_cpu_data.x86 != 0xf)
		return 0;

	if (user_mode(regs))
		return 0;

	if (address != regs->ip)
		return 0;

	if ((address >> 32) != 0)
		return 0;

	address |= 0xffffffffUL << 32;
	if ((address >= (u64)_stext && address <= (u64)_etext) ||
	    (address >= MODULES_VADDR && address <= MODULES_END)) {
		printk_once(errata93_warning);
		regs->ip = address;
		return 1;
	}
#endif
	return 0;
}

/*
 * Work around K8 erratum #100 K8 in compat mode occasionally jumps
 * to illegal addresses >4GB.
 *
 * We catch this in the page fault handler because these addresses
 * are not reachable. Just detect this case and return.  Any code
 * segment in LDT is compatibility mode.
 */
static int is_errata100(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
	if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
		return 1;
#endif
	return 0;
}

/* Pentium F0 0F C7 C8 bug workaround: */
static int is_f00f_bug(struct pt_regs *regs, unsigned long error_code,
		       unsigned long address)
{
#ifdef CONFIG_X86_F00F_BUG
	if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) &&
	    idt_is_f00f_address(address)) {
		handle_invalid_op(regs);
		return 1;
	}
#endif
	return 0;
}

static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
{
	u32 offset = (index >> 3) * sizeof(struct desc_struct);
	unsigned long addr;
	struct ldttss_desc desc;

	if (index == 0) {
		pr_alert("%s: NULL\n", name);
		return;
	}

	if (offset + sizeof(struct ldttss_desc) >= gdt->size) {
		pr_alert("%s: 0x%hx -- out of bounds\n", name, index);
		return;
	}

	if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
			      sizeof(struct ldttss_desc))) {
		pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
			 name, index);
		return;
	}

	addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24);
#ifdef CONFIG_X86_64
	addr |= ((u64)desc.base3 << 32);
#endif
	pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n",
		 name, index, addr, (desc.limit0 | (desc.limit1 << 16)));
}

static void
show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
	if (!oops_may_print())
		return;

	if (error_code & X86_PF_INSTR) {
		unsigned int level;
		pgd_t *pgd;
		pte_t *pte;

		pgd = __va(read_cr3_pa());
		pgd += pgd_index(address);

		pte = lookup_address_in_pgd(pgd, address, &level);

		if (pte && pte_present(*pte) && !pte_exec(*pte))
			pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n",
				from_kuid(&init_user_ns, current_uid()));
		if (pte && pte_present(*pte) && pte_exec(*pte) &&
				(pgd_flags(*pgd) & _PAGE_USER) &&
				(__read_cr4() & X86_CR4_SMEP))
			pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n",
				from_kuid(&init_user_ns, current_uid()));
	}

	if (address < PAGE_SIZE && !user_mode(regs))
		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
			(void *)address);
	else
		pr_alert("BUG: unable to handle page fault for address: %px\n",
			(void *)address);

	pr_alert("#PF: %s %s in %s mode\n",
		 (error_code & X86_PF_USER)  ? "user" : "supervisor",
		 (error_code & X86_PF_INSTR) ? "instruction fetch" :
		 (error_code & X86_PF_WRITE) ? "write access" :
					       "read access",
			     user_mode(regs) ? "user" : "kernel");
	pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code,
		 !(error_code & X86_PF_PROT) ? "not-present page" :
		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
		 (error_code & X86_PF_PK)    ? "protection keys violation" :
					       "permissions violation");

	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
		struct desc_ptr idt, gdt;
		u16 ldtr, tr;

		/*
		 * This can happen for quite a few reasons.  The more obvious
		 * ones are faults accessing the GDT, or LDT.  Perhaps
		 * surprisingly, if the CPU tries to deliver a benign or
		 * contributory exception from user code and gets a page fault
		 * during delivery, the page fault can be delivered as though
		 * it originated directly from user code.  This could happen
		 * due to wrong permissions on the IDT, GDT, LDT, TSS, or
		 * kernel or IST stack.
		 */
		store_idt(&idt);

		/* Usable even on Xen PV -- it's just slow. */
		native_store_gdt(&gdt);

		pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n",
			 idt.address, idt.size, gdt.address, gdt.size);

		store_ldt(ldtr);
		show_ldttss(&gdt, "LDTR", ldtr);

		store_tr(tr);
		show_ldttss(&gdt, "TR", tr);
	}

	dump_pagetable(address);
}

static noinline void
pgtable_bad(struct pt_regs *regs, unsigned long error_code,
	    unsigned long address)
{
	struct task_struct *tsk;
	unsigned long flags;
	int sig;

	flags = oops_begin();
	tsk = current;
	sig = SIGKILL;

	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
	       tsk->comm, address);
	dump_pagetable(address);

	if (__die("Bad pagetable", regs, error_code))
		sig = 0;

	oops_end(flags, regs, sig);
}

static void sanitize_error_code(unsigned long address,
				unsigned long *error_code)
{
	/*
	 * To avoid leaking information about the kernel page
	 * table layout, pretend that user-mode accesses to
	 * kernel addresses are always protection faults.
	 *
	 * NB: This means that failed vsyscalls with vsyscall=none
	 * will have the PROT bit.  This doesn't leak any
	 * information and does not appear to cause any problems.
	 */
	if (address >= TASK_SIZE_MAX)
		*error_code |= X86_PF_PROT;
}

static void set_signal_archinfo(unsigned long address,
				unsigned long error_code)
{
	struct task_struct *tsk = current;

	tsk->thread.trap_nr = X86_TRAP_PF;
	tsk->thread.error_code = error_code | X86_PF_USER;
	tsk->thread.cr2 = address;
}

static noinline void
page_fault_oops(struct pt_regs *regs, unsigned long error_code,
		unsigned long address)
{
#ifdef CONFIG_VMAP_STACK
	struct stack_info info;
#endif
	unsigned long flags;
	int sig;

	if (user_mode(regs)) {
		/*
		 * Implicit kernel access from user mode?  Skip the stack
		 * overflow and EFI special cases.
		 */
		goto oops;
	}

#ifdef CONFIG_VMAP_STACK
	/*
	 * Stack overflow?  During boot, we can fault near the initial
	 * stack in the direct map, but that's not an overflow -- check
	 * that we're in vmalloc space to avoid this.
	 */
	if (is_vmalloc_addr((void *)address) &&
	    get_stack_guard_info((void *)address, &info)) {
		/*
		 * We're likely to be running with very little stack space
		 * left.  It's plausible that we'd hit this condition but
		 * double-fault even before we get this far, in which case
		 * we're fine: the double-fault handler will deal with it.
		 *
		 * We don't want to make it all the way into the oops code
		 * and then double-fault, though, because we're likely to
		 * break the console driver and lose most of the stack dump.
		 */
		call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*),
			      handle_stack_overflow,
			      ASM_CALL_ARG3,
			      , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));

		unreachable();
	}
#endif

	/*
	 * Buggy firmware could access regions which might page fault.  If
	 * this happens, EFI has a special OOPS path that will try to
	 * avoid hanging the system.
	 */
	if (IS_ENABLED(CONFIG_EFI))
		efi_crash_gracefully_on_page_fault(address);

	/* Only not-present faults should be handled by KFENCE. */
	if (!(error_code & X86_PF_PROT) &&
	    kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs))
		return;

oops:
	/*
	 * Oops. The kernel tried to access some bad page. We'll have to
	 * terminate things with extreme prejudice:
	 */
	flags = oops_begin();

	show_fault_oops(regs, error_code, address);

	if (task_stack_end_corrupted(current))
		printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");

	sig = SIGKILL;
	if (__die("Oops", regs, error_code))
		sig = 0;

	/* Executive summary in case the body of the oops scrolled away */
	printk(KERN_DEFAULT "CR2: %016lx\n", address);

	oops_end(flags, regs, sig);
}

static noinline void
kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
			 unsigned long address, int signal, int si_code,
			 u32 pkey)
{
	WARN_ON_ONCE(user_mode(regs));

	/* Are we prepared to handle this kernel fault? */
	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
		/*
		 * Any interrupt that takes a fault gets the fixup. This makes
		 * the below recursive fault logic only apply to a faults from
		 * task context.
		 */
		if (in_interrupt())
			return;

		/*
		 * Per the above we're !in_interrupt(), aka. task context.
		 *
		 * In this case we need to make sure we're not recursively
		 * faulting through the emulate_vsyscall() logic.
		 */
		if (current->thread.sig_on_uaccess_err && signal) {
			sanitize_error_code(address, &error_code);

			set_signal_archinfo(address, error_code);

			if (si_code == SEGV_PKUERR) {
				force_sig_pkuerr((void __user *)address, pkey);
			} else {
				/* XXX: hwpoison faults will set the wrong code. */
				force_sig_fault(signal, si_code, (void __user *)address);
			}
		}

		/*
		 * Barring that, we can do the fixup and be happy.
		 */
		return;
	}

	/*
	 * AMD erratum #91 manifests as a spurious page fault on a PREFETCH
	 * instruction.
	 */
	if (is_prefetch(regs, error_code, address))
		return;

	page_fault_oops(regs, error_code, address);
}

/*
 * Print out info about fatal segfaults, if the show_unhandled_signals
 * sysctl is set:
 */
static inline void
show_signal_msg(struct pt_regs *regs, unsigned long error_code,
		unsigned long address, struct task_struct *tsk)
{
	const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG;
	/* This is a racy snapshot, but it's better than nothing. */
	int cpu = raw_smp_processor_id();

	if (!unhandled_signal(tsk, SIGSEGV))
		return;

	if (!printk_ratelimit())
		return;

	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx",
		loglvl, tsk->comm, task_pid_nr(tsk), address,
		(void *)regs->ip, (void *)regs->sp, error_code);

	print_vma_addr(KERN_CONT " in ", regs->ip);

	/*
	 * Dump the likely CPU where the fatal segfault happened.
	 * This can help identify faulty hardware.
	 */
	printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu,
	       topology_core_id(cpu), topology_physical_package_id(cpu));


	printk(KERN_CONT "\n");

	show_opcodes(regs, loglvl);
}

static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
		       unsigned long address, u32 pkey, int si_code)
{
	struct task_struct *tsk = current;

	if (!user_mode(regs)) {
		kernelmode_fixup_or_oops(regs, error_code, address,
					 SIGSEGV, si_code, pkey);
		return;
	}

	if (!(error_code & X86_PF_USER)) {
		/* Implicit user access to kernel memory -- just oops */
		page_fault_oops(regs, error_code, address);
		return;
	}

	/*
	 * User mode accesses just cause a SIGSEGV.
	 * It's possible to have interrupts off here:
	 */
	local_irq_enable();

	/*
	 * Valid to do another page fault here because this one came
	 * from user space:
	 */
	if (is_prefetch(regs, error_code, address))
		return;

	if (is_errata100(regs, address))
		return;

	sanitize_error_code(address, &error_code);

	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
		return;

	if (likely(show_unhandled_signals))
		show_signal_msg(regs, error_code, address, tsk);

	set_signal_archinfo(address, error_code);

	if (si_code == SEGV_PKUERR)
		force_sig_pkuerr((void __user *)address, pkey);
	else
		force_sig_fault(SIGSEGV, si_code, (void __user *)address);

	local_irq_disable();
}

static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
		     unsigned long address)
{
	__bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR);
}

static void
__bad_area(struct pt_regs *regs, unsigned long error_code,
	   unsigned long address, u32 pkey, int si_code)
{
	struct mm_struct *mm = current->mm;
	/*
	 * Something tried to access memory that isn't in our memory map..
	 * Fix it, but check if it's kernel or user first..
	 */
	mmap_read_unlock(mm);

	__bad_area_nosemaphore(regs, error_code, address, pkey, si_code);
}

static inline bool bad_area_access_from_pkeys(unsigned long error_code,
		struct vm_area_struct *vma)
{
	/* This code is always called on the current mm */
	bool foreign = false;

	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
		return false;
	if (error_code & X86_PF_PK)
		return true;
	/* this checks permission keys on the VMA: */
	if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE),
				       (error_code & X86_PF_INSTR), foreign))
		return true;
	return false;
}

static noinline void
bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
		      unsigned long address, struct vm_area_struct *vma)
{
	/*
	 * This OSPKE check is not strictly necessary at runtime.
	 * But, doing it this way allows compiler optimizations
	 * if pkeys are compiled out.
	 */
	if (bad_area_access_from_pkeys(error_code, vma)) {
		/*
		 * A protection key fault means that the PKRU value did not allow
		 * access to some PTE.  Userspace can figure out what PKRU was
		 * from the XSAVE state.  This function captures the pkey from
		 * the vma and passes it to userspace so userspace can discover
		 * which protection key was set on the PTE.
		 *
		 * If we get here, we know that the hardware signaled a X86_PF_PK
		 * fault and that there was a VMA once we got in the fault
		 * handler.  It does *not* guarantee that the VMA we find here
		 * was the one that we faulted on.
		 *
		 * 1. T1   : mprotect_key(foo, PAGE_SIZE, pkey=4);
		 * 2. T1   : set PKRU to deny access to pkey=4, touches page
		 * 3. T1   : faults...
		 * 4.    T2: mprotect_key(foo, PAGE_SIZE, pkey=5);
		 * 5. T1   : enters fault handler, takes mmap_lock, etc...
		 * 6. T1   : reaches here, sees vma_pkey(vma)=5, when we really
		 *	     faulted on a pte with its pkey=4.
		 */
		u32 pkey = vma_pkey(vma);

		__bad_area(regs, error_code, address, pkey, SEGV_PKUERR);
	} else {
		__bad_area(regs, error_code, address, 0, SEGV_ACCERR);
	}
}

static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
	  vm_fault_t fault)
{
	/* Kernel mode? Handle exceptions or die: */
	if (!user_mode(regs)) {
		kernelmode_fixup_or_oops(regs, error_code, address,
					 SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY);
		return;
	}

	/* User-space => ok to do another page fault: */
	if (is_prefetch(regs, error_code, address))
		return;

	sanitize_error_code(address, &error_code);

	if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address))
		return;

	set_signal_archinfo(address, error_code);

#ifdef CONFIG_MEMORY_FAILURE
	if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
		struct task_struct *tsk = current;
		unsigned lsb = 0;

		pr_err(
	"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
			tsk->comm, tsk->pid, address);
		if (fault & VM_FAULT_HWPOISON_LARGE)
			lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
		if (fault & VM_FAULT_HWPOISON)
			lsb = PAGE_SHIFT;
		force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb);
		return;
	}
#endif
	force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
}

static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
{
	if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
		return 0;

	if ((error_code & X86_PF_INSTR) && !pte_exec(*pte))
		return 0;

	return 1;
}

/*
 * Handle a spurious fault caused by a stale TLB entry.
 *
 * This allows us to lazily refresh the TLB when increasing the
 * permissions of a kernel page (RO -> RW or NX -> X).  Doing it
 * eagerly is very expensive since that implies doing a full
 * cross-processor TLB flush, even if no stale TLB entries exist
 * on other processors.
 *
 * Spurious faults may only occur if the TLB contains an entry with
 * fewer permission than the page table entry.  Non-present (P = 0)
 * and reserved bit (R = 1) faults are never spurious.
 *
 * There are no security implications to leaving a stale TLB when
 * increasing the permissions on a page.
 *
 * Returns non-zero if a spurious fault was handled, zero otherwise.
 *
 * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3
 * (Optional Invalidation).
 */
static noinline int
spurious_kernel_fault(unsigned long error_code, unsigned long address)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int ret;

	/*
	 * Only writes to RO or instruction fetches from NX may cause
	 * spurious faults.
	 *
	 * These could be from user or supervisor accesses but the TLB
	 * is only lazily flushed after a kernel mapping protection
	 * change, so user accesses are not expected to cause spurious
	 * faults.
	 */
	if (error_code != (X86_PF_WRITE | X86_PF_PROT) &&
	    error_code != (X86_PF_INSTR | X86_PF_PROT))
		return 0;

	pgd = init_mm.pgd + pgd_index(address);
	if (!pgd_present(*pgd))
		return 0;

	p4d = p4d_offset(pgd, address);
	if (!p4d_present(*p4d))
		return 0;

	if (p4d_large(*p4d))
		return spurious_kernel_fault_check(error_code, (pte_t *) p4d);

	pud = pud_offset(p4d, address);
	if (!pud_present(*pud))
		return 0;

	if (pud_leaf(*pud))
		return spurious_kernel_fault_check(error_code, (pte_t *) pud);

	pmd = pmd_offset(pud, address);
	if (!pmd_present(*pmd))
		return 0;

	if (pmd_large(*pmd))
		return spurious_kernel_fault_check(error_code, (pte_t *) pmd);

	pte = pte_offset_kernel(pmd, address);
	if (!pte_present(*pte))
		return 0;

	ret = spurious_kernel_fault_check(error_code, pte);
	if (!ret)
		return 0;

	/*
	 * Make sure we have permissions in PMD.
	 * If not, then there's a bug in the page tables:
	 */
	ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd);
	WARN_ONCE(!ret, "PMD has incorrect permission bits\n");

	return ret;
}
NOKPROBE_SYMBOL(spurious_kernel_fault);

int show_unhandled_signals = 1;

static inline int
access_error(unsigned long error_code, struct vm_area_struct *vma)
{
	/* This is only called for the current mm, so: */
	bool foreign = false;

	/*
	 * Read or write was blocked by protection keys.  This is
	 * always an unconditional error and can never result in
	 * a follow-up action to resolve the fault, like a COW.
	 */
	if (error_code & X86_PF_PK)
		return 1;

	/*
	 * SGX hardware blocked the access.  This usually happens
	 * when the enclave memory contents have been destroyed, like
	 * after a suspend/resume cycle. In any case, the kernel can't
	 * fix the cause of the fault.  Handle the fault as an access
	 * error even in cases where no actual access violation
	 * occurred.  This allows userspace to rebuild the enclave in
	 * response to the signal.
	 */
	if (unlikely(error_code & X86_PF_SGX))
		return 1;

	/*
	 * Make sure to check the VMA so that we do not perform
	 * faults just to hit a X86_PF_PK as soon as we fill in a
	 * page.
	 */
	if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE),
				       (error_code & X86_PF_INSTR), foreign))
		return 1;

	/*
	 * Shadow stack accesses (PF_SHSTK=1) are only permitted to
	 * shadow stack VMAs. All other accesses result in an error.
	 */
	if (error_code & X86_PF_SHSTK) {
		if (unlikely(!(vma->vm_flags & VM_SHADOW_STACK)))
			return 1;
		if (unlikely(!(vma->vm_flags & VM_WRITE)))
			return 1;
		return 0;
	}

	if (error_code & X86_PF_WRITE) {
		/* write, present and write, not present: */
		if (unlikely(vma->vm_flags & VM_SHADOW_STACK))
			return 1;
		if (unlikely(!(vma->vm_flags & VM_WRITE)))
			return 1;
		return 0;
	}

	/* read, present: */
	if (unlikely(error_code & X86_PF_PROT))
		return 1;

	/* read, not present: */
	if (unlikely(!vma_is_accessible(vma)))
		return 1;

	return 0;
}

bool fault_in_kernel_space(unsigned long address)
{
	/*
	 * On 64-bit systems, the vsyscall page is at an address above
	 * TASK_SIZE_MAX, but is not considered part of the kernel
	 * address space.
	 */
	if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address))
		return false;

	return address >= TASK_SIZE_MAX;
}

/*
 * Called for all faults where 'address' is part of the kernel address
 * space.  Might get called for faults that originate from *code* that
 * ran in userspace or the kernel.
 */
static void
do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
		   unsigned long address)
{
	/*
	 * Protection keys exceptions only happen on user pages.  We
	 * have no user pages in the kernel portion of the address
	 * space, so do not expect them here.
	 */
	WARN_ON_ONCE(hw_error_code & X86_PF_PK);

#ifdef CONFIG_X86_32
	/*
	 * We can fault-in kernel-space virtual memory on-demand. The
	 * 'reference' page table is init_mm.pgd.
	 *
	 * 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.
	 *
	 * Before doing this on-demand faulting, ensure that the
	 * fault is not any of the following:
	 * 1. A fault on a PTE with a reserved bit set.
	 * 2. A fault caused by a user-mode access.  (Do not demand-
	 *    fault kernel memory due to user-mode accesses).
	 * 3. A fault caused by a page-level protection violation.
	 *    (A demand fault would be on a non-present page which
	 *     would have X86_PF_PROT==0).
	 *
	 * This is only needed to close a race condition on x86-32 in
	 * the vmalloc mapping/unmapping code. See the comment above
	 * vmalloc_fault() for details. On x86-64 the race does not
	 * exist as the vmalloc mappings don't need to be synchronized
	 * there.
	 */
	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
		if (vmalloc_fault(address) >= 0)
			return;
	}
#endif

	if (is_f00f_bug(regs, hw_error_code, address))
		return;

	/* Was the fault spurious, caused by lazy TLB invalidation? */
	if (spurious_kernel_fault(hw_error_code, address))
		return;

	/* kprobes don't want to hook the spurious faults: */
	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
		return;

	/*
	 * Note, despite being a "bad area", there are quite a few
	 * acceptable reasons to get here, such as erratum fixups
	 * and handling kernel code that can fault, like get_user().
	 *
	 * Don't take the mm semaphore here. If we fixup a prefetch
	 * fault we could otherwise deadlock:
	 */
	bad_area_nosemaphore(regs, hw_error_code, address);
}
NOKPROBE_SYMBOL(do_kern_addr_fault);

/*
 * Handle faults in the user portion of the address space.  Nothing in here
 * should check X86_PF_USER without a specific justification: for almost
 * all purposes, we should treat a normal kernel access to user memory
 * (e.g. get_user(), put_user(), etc.) the same as the WRUSS instruction.
 * The one exception is AC flag handling, which is, per the x86
 * architecture, special for WRUSS.
 */
static inline
void do_user_addr_fault(struct pt_regs *regs,
			unsigned long error_code,
			unsigned long address)
{
	struct vm_area_struct *vma;
	struct task_struct *tsk;
	struct mm_struct *mm;
	vm_fault_t fault;
	unsigned int flags = FAULT_FLAG_DEFAULT;

	tsk = current;
	mm = tsk->mm;

	if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) {
		/*
		 * Whoops, this is kernel mode code trying to execute from
		 * user memory.  Unless this is AMD erratum #93, which
		 * corrupts RIP such that it looks like a user address,
		 * this is unrecoverable.  Don't even try to look up the
		 * VMA or look for extable entries.
		 */
		if (is_errata93(regs, address))
			return;

		page_fault_oops(regs, error_code, address);
		return;
	}

	/* kprobes don't want to hook the spurious faults: */
	if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF)))
		return;

	/*
	 * Reserved bits are never expected to be set on
	 * entries in the user portion of the page tables.
	 */
	if (unlikely(error_code & X86_PF_RSVD))
		pgtable_bad(regs, error_code, address);

	/*
	 * If SMAP is on, check for invalid kernel (supervisor) access to user
	 * pages in the user address space.  The odd case here is WRUSS,
	 * which, according to the preliminary documentation, does not respect
	 * SMAP and will have the USER bit set so, in all cases, SMAP
	 * enforcement appears to be consistent with the USER bit.
	 */
	if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) &&
		     !(error_code & X86_PF_USER) &&
		     !(regs->flags & X86_EFLAGS_AC))) {
		/*
		 * No extable entry here.  This was a kernel access to an
		 * invalid pointer.  get_kernel_nofault() will not get here.
		 */
		page_fault_oops(regs, error_code, address);
		return;
	}

	/*
	 * If we're in an interrupt, have no user context or are running
	 * in a region with pagefaults disabled then we must not take the fault
	 */
	if (unlikely(faulthandler_disabled() || !mm)) {
		bad_area_nosemaphore(regs, error_code, address);
		return;
	}

	/*
	 * It's safe to allow irq's after cr2 has been saved and the
	 * vmalloc fault has been handled.
	 *
	 * User-mode registers count as a user access even for any
	 * potential system fault or CPU buglet:
	 */
	if (user_mode(regs)) {
		local_irq_enable();
		flags |= FAULT_FLAG_USER;
	} else {
		if (regs->flags & X86_EFLAGS_IF)
			local_irq_enable();
	}

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

	/*
	 * Read-only permissions can not be expressed in shadow stack PTEs.
	 * Treat all shadow stack accesses as WRITE faults. This ensures
	 * that the MM will prepare everything (e.g., break COW) such that
	 * maybe_mkwrite() can create a proper shadow stack PTE.
	 */
	if (error_code & X86_PF_SHSTK)
		flags |= FAULT_FLAG_WRITE;
	if (error_code & X86_PF_WRITE)
		flags |= FAULT_FLAG_WRITE;
	if (error_code & X86_PF_INSTR)
		flags |= FAULT_FLAG_INSTRUCTION;

#ifdef CONFIG_X86_64
	/*
	 * Faults in the vsyscall page might need emulation.  The
	 * vsyscall page is at a high address (>PAGE_OFFSET), but is
	 * considered to be part of the user address space.
	 *
	 * The vsyscall page does not have a "real" VMA, so do this
	 * emulation before we go searching for VMAs.
	 *
	 * PKRU never rejects instruction fetches, so we don't need
	 * to consider the PF_PK bit.
	 */
	if (is_vsyscall_vaddr(address)) {
		if (emulate_vsyscall(error_code, regs, address))
			return;
	}
#endif

	if (!(flags & FAULT_FLAG_USER))
		goto lock_mmap;

	vma = lock_vma_under_rcu(mm, address);
	if (!vma)
		goto lock_mmap;

	if (unlikely(access_error(error_code, vma))) {
		vma_end_read(vma);
		goto lock_mmap;
	}
	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
		vma_end_read(vma);

	if (!(fault & VM_FAULT_RETRY)) {
		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
		goto done;
	}
	count_vm_vma_lock_event(VMA_LOCK_RETRY);

	/* Quick path to respond to signals */
	if (fault_signal_pending(fault, regs)) {
		if (!user_mode(regs))
			kernelmode_fixup_or_oops(regs, error_code, address,
						 SIGBUS, BUS_ADRERR,
						 ARCH_DEFAULT_PKEY);
		return;
	}
lock_mmap:

retry:
	vma = lock_mm_and_find_vma(mm, address, regs);
	if (unlikely(!vma)) {
		bad_area_nosemaphore(regs, error_code, address);
		return;
	}

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it..
	 */
	if (unlikely(access_error(error_code, vma))) {
		bad_area_access_error(regs, error_code, address, vma);
		return;
	}

	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.  Since we never set FAULT_FLAG_RETRY_NOWAIT, if
	 * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked.
	 *
	 * Note that handle_userfault() may also release and reacquire mmap_lock
	 * (and not return with VM_FAULT_RETRY), when returning to userland to
	 * repeat the page fault later with a VM_FAULT_NOPAGE retval
	 * (potentially after handling any pending signal during the return to
	 * userland). The return to userland is identified whenever
	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
	 */
	fault = handle_mm_fault(vma, address, flags, regs);

	if (fault_signal_pending(fault, regs)) {
		/*
		 * Quick path to respond to signals.  The core mm code
		 * has unlocked the mm for us if we get here.
		 */
		if (!user_mode(regs))
			kernelmode_fixup_or_oops(regs, error_code, address,
						 SIGBUS, BUS_ADRERR,
						 ARCH_DEFAULT_PKEY);
		return;
	}

	/* The fault is fully completed (including releasing mmap lock) */
	if (fault & VM_FAULT_COMPLETED)
		return;

	/*
	 * If we need to retry the mmap_lock has already been released,
	 * and if there is a fatal signal pending there is no guarantee
	 * that we made any progress. Handle this case first.
	 */
	if (unlikely(fault & VM_FAULT_RETRY)) {
		flags |= FAULT_FLAG_TRIED;
		goto retry;
	}

	mmap_read_unlock(mm);
done:
	if (likely(!(fault & VM_FAULT_ERROR)))
		return;

	if (fatal_signal_pending(current) && !user_mode(regs)) {
		kernelmode_fixup_or_oops(regs, error_code, address,
					 0, 0, ARCH_DEFAULT_PKEY);
		return;
	}

	if (fault & VM_FAULT_OOM) {
		/* Kernel mode? Handle exceptions or die: */
		if (!user_mode(regs)) {
			kernelmode_fixup_or_oops(regs, error_code, address,
						 SIGSEGV, SEGV_MAPERR,
						 ARCH_DEFAULT_PKEY);
			return;
		}

		/*
		 * We ran out of memory, call the OOM killer, and return the
		 * userspace (which will retry the fault, or kill us if we got
		 * oom-killed):
		 */
		pagefault_out_of_memory();
	} else {
		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
			     VM_FAULT_HWPOISON_LARGE))
			do_sigbus(regs, error_code, address, fault);
		else if (fault & VM_FAULT_SIGSEGV)
			bad_area_nosemaphore(regs, error_code, address);
		else
			BUG();
	}
}
NOKPROBE_SYMBOL(do_user_addr_fault);

static __always_inline void
trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
			 unsigned long address)
{
	if (!trace_pagefault_enabled())
		return;

	if (user_mode(regs))
		trace_page_fault_user(address, regs, error_code);
	else
		trace_page_fault_kernel(address, regs, error_code);
}

static __always_inline void
handle_page_fault(struct pt_regs *regs, unsigned long error_code,
			      unsigned long address)
{
	trace_page_fault_entries(regs, error_code, address);

	if (unlikely(kmmio_fault(regs, address)))
		return;

	/* Was the fault on kernel-controlled part of the address space? */
	if (unlikely(fault_in_kernel_space(address))) {
		do_kern_addr_fault(regs, error_code, address);
	} else {
		do_user_addr_fault(regs, error_code, address);
		/*
		 * User address page fault handling might have reenabled
		 * interrupts. Fixing up all potential exit points of
		 * do_user_addr_fault() and its leaf functions is just not
		 * doable w/o creating an unholy mess or turning the code
		 * upside down.
		 */
		local_irq_disable();
	}
}

DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
{
	unsigned long address = read_cr2();
	irqentry_state_t state;

	prefetchw(&current->mm->mmap_lock);

	/*
	 * KVM uses #PF vector to deliver 'page not present' events to guests
	 * (asynchronous page fault mechanism). The event happens when a
	 * userspace task is trying to access some valid (from guest's point of
	 * view) memory which is not currently mapped by the host (e.g. the
	 * memory is swapped out). Note, the corresponding "page ready" event
	 * which is injected when the memory becomes available, is delivered via
	 * an interrupt mechanism and not a #PF exception
	 * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()).
	 *
	 * We are relying on the interrupted context being sane (valid RSP,
	 * relevant locks not held, etc.), which is fine as long as the
	 * interrupted context had IF=1.  We are also relying on the KVM
	 * async pf type field and CR2 being read consistently instead of
	 * getting values from real and async page faults mixed up.
	 *
	 * Fingers crossed.
	 *
	 * The async #PF handling code takes care of idtentry handling
	 * itself.
	 */
	if (kvm_handle_async_pf(regs, (u32)address))
		return;

	/*
	 * Entry handling for valid #PF from kernel mode is slightly
	 * different: RCU is already watching and ct_irq_enter() must not
	 * be invoked because a kernel fault on a user space address might
	 * sleep.
	 *
	 * In case the fault hit a RCU idle region the conditional entry
	 * code reenabled RCU to avoid subsequent wreckage which helps
	 * debuggability.
	 */
	state = irqentry_enter(regs);

	instrumentation_begin();
	handle_page_fault(regs, error_code, address);
	instrumentation_end();

	irqentry_exit(regs, state);
}