summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/alternative.c
blob: cf447ee18b3cc906a5882859f9f8432ad79a1b01 (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
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
// SPDX-License-Identifier: GPL-2.0-only
#define pr_fmt(fmt) "SMP alternatives: " fmt

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/perf_event.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/stringify.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/memory.h>
#include <linux/stop_machine.h>
#include <linux/slab.h>
#include <linux/kdebug.h>
#include <linux/kprobes.h>
#include <linux/mmu_context.h>
#include <linux/bsearch.h>
#include <linux/sync_core.h>
#include <asm/text-patching.h>
#include <asm/alternative.h>
#include <asm/sections.h>
#include <asm/mce.h>
#include <asm/nmi.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/fixmap.h>
#include <asm/paravirt.h>
#include <asm/asm-prototypes.h>

int __read_mostly alternatives_patched;

EXPORT_SYMBOL_GPL(alternatives_patched);

#define MAX_PATCH_LEN (255-1)

static int __initdata_or_module debug_alternative;

static int __init debug_alt(char *str)
{
	debug_alternative = 1;
	return 1;
}
__setup("debug-alternative", debug_alt);

static int noreplace_smp;

static int __init setup_noreplace_smp(char *str)
{
	noreplace_smp = 1;
	return 1;
}
__setup("noreplace-smp", setup_noreplace_smp);

#define DPRINTK(fmt, args...)						\
do {									\
	if (debug_alternative)						\
		printk(KERN_DEBUG pr_fmt(fmt) "\n", ##args);		\
} while (0)

#define DUMP_BYTES(buf, len, fmt, args...)				\
do {									\
	if (unlikely(debug_alternative)) {				\
		int j;							\
									\
		if (!(len))						\
			break;						\
									\
		printk(KERN_DEBUG pr_fmt(fmt), ##args);			\
		for (j = 0; j < (len) - 1; j++)				\
			printk(KERN_CONT "%02hhx ", buf[j]);		\
		printk(KERN_CONT "%02hhx\n", buf[j]);			\
	}								\
} while (0)

static const unsigned char x86nops[] =
{
	BYTES_NOP1,
	BYTES_NOP2,
	BYTES_NOP3,
	BYTES_NOP4,
	BYTES_NOP5,
	BYTES_NOP6,
	BYTES_NOP7,
	BYTES_NOP8,
};

const unsigned char * const x86_nops[ASM_NOP_MAX+1] =
{
	NULL,
	x86nops,
	x86nops + 1,
	x86nops + 1 + 2,
	x86nops + 1 + 2 + 3,
	x86nops + 1 + 2 + 3 + 4,
	x86nops + 1 + 2 + 3 + 4 + 5,
	x86nops + 1 + 2 + 3 + 4 + 5 + 6,
	x86nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
};

/* Use this to add nops to a buffer, then text_poke the whole buffer. */
static void __init_or_module add_nops(void *insns, unsigned int len)
{
	while (len > 0) {
		unsigned int noplen = len;
		if (noplen > ASM_NOP_MAX)
			noplen = ASM_NOP_MAX;
		memcpy(insns, x86_nops[noplen], noplen);
		insns += noplen;
		len -= noplen;
	}
}

extern s32 __retpoline_sites[], __retpoline_sites_end[];
extern s32 __return_sites[], __return_sites_end[];
extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
extern s32 __smp_locks[], __smp_locks_end[];
void text_poke_early(void *addr, const void *opcode, size_t len);

/*
 * Are we looking at a near JMP with a 1 or 4-byte displacement.
 */
static inline bool is_jmp(const u8 opcode)
{
	return opcode == 0xeb || opcode == 0xe9;
}

static void __init_or_module
recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insn_buff)
{
	u8 *next_rip, *tgt_rip;
	s32 n_dspl, o_dspl;
	int repl_len;

	if (a->replacementlen != 5)
		return;

	o_dspl = *(s32 *)(insn_buff + 1);

	/* next_rip of the replacement JMP */
	next_rip = repl_insn + a->replacementlen;
	/* target rip of the replacement JMP */
	tgt_rip  = next_rip + o_dspl;
	n_dspl = tgt_rip - orig_insn;

	DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl);

	if (tgt_rip - orig_insn >= 0) {
		if (n_dspl - 2 <= 127)
			goto two_byte_jmp;
		else
			goto five_byte_jmp;
	/* negative offset */
	} else {
		if (((n_dspl - 2) & 0xff) == (n_dspl - 2))
			goto two_byte_jmp;
		else
			goto five_byte_jmp;
	}

two_byte_jmp:
	n_dspl -= 2;

	insn_buff[0] = 0xeb;
	insn_buff[1] = (s8)n_dspl;
	add_nops(insn_buff + 2, 3);

	repl_len = 2;
	goto done;

five_byte_jmp:
	n_dspl -= 5;

	insn_buff[0] = 0xe9;
	*(s32 *)&insn_buff[1] = n_dspl;

	repl_len = 5;

done:

	DPRINTK("final displ: 0x%08x, JMP 0x%lx",
		n_dspl, (unsigned long)orig_insn + n_dspl + repl_len);
}

/*
 * optimize_nops_range() - Optimize a sequence of single byte NOPs (0x90)
 *
 * @instr: instruction byte stream
 * @instrlen: length of the above
 * @off: offset within @instr where the first NOP has been detected
 *
 * Return: number of NOPs found (and replaced).
 */
static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off)
{
	unsigned long flags;
	int i = off, nnops;

	while (i < instrlen) {
		if (instr[i] != 0x90)
			break;

		i++;
	}

	nnops = i - off;

	if (nnops <= 1)
		return nnops;

	local_irq_save(flags);
	add_nops(instr + off, nnops);
	local_irq_restore(flags);

	DUMP_BYTES(instr, instrlen, "%px: [%d:%d) optimized NOPs: ", instr, off, i);

	return nnops;
}

/*
 * "noinline" to cause control flow change and thus invalidate I$ and
 * cause refetch after modification.
 */
static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
{
	struct insn insn;
	int i = 0;

	/*
	 * Jump over the non-NOP insns and optimize single-byte NOPs into bigger
	 * ones.
	 */
	for (;;) {
		if (insn_decode_kernel(&insn, &instr[i]))
			return;

		/*
		 * See if this and any potentially following NOPs can be
		 * optimized.
		 */
		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
			i += optimize_nops_range(instr, len, i);
		else
			i += insn.length;

		if (i >= len)
			return;
	}
}

/*
 * Replace instructions with better alternatives for this CPU type. This runs
 * before SMP is initialized to avoid SMP problems with self modifying code.
 * This implies that asymmetric systems where APs have less capabilities than
 * the boot processor are not handled. Tough. Make sure you disable such
 * features by hand.
 *
 * Marked "noinline" to cause control flow change and thus insn cache
 * to refetch changed I$ lines.
 */
void __init_or_module noinline apply_alternatives(struct alt_instr *start,
						  struct alt_instr *end)
{
	struct alt_instr *a;
	u8 *instr, *replacement;
	u8 insn_buff[MAX_PATCH_LEN];

	DPRINTK("alt table %px, -> %px", start, end);
	/*
	 * The scan order should be from start to end. A later scanned
	 * alternative code can overwrite previously scanned alternative code.
	 * Some kernel functions (e.g. memcpy, memset, etc) use this order to
	 * patch code.
	 *
	 * So be careful if you want to change the scan order to any other
	 * order.
	 */
	for (a = start; a < end; a++) {
		int insn_buff_sz = 0;
		/* Mask away "NOT" flag bit for feature to test. */
		u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;

		instr = (u8 *)&a->instr_offset + a->instr_offset;
		replacement = (u8 *)&a->repl_offset + a->repl_offset;
		BUG_ON(a->instrlen > sizeof(insn_buff));
		BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);

		/*
		 * Patch if either:
		 * - feature is present
		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
		 *   patch if feature is *NOT* present.
		 */
		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV))
			goto next;

		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)",
			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
			feature >> 5,
			feature & 0x1f,
			instr, instr, a->instrlen,
			replacement, a->replacementlen);

		DUMP_BYTES(instr, a->instrlen, "%px:   old_insn: ", instr);
		DUMP_BYTES(replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);

		memcpy(insn_buff, replacement, a->replacementlen);
		insn_buff_sz = a->replacementlen;

		/*
		 * 0xe8 is a relative jump; fix the offset.
		 *
		 * Instruction length is checked before the opcode to avoid
		 * accessing uninitialized bytes for zero-length replacements.
		 */
		if (a->replacementlen == 5 && *insn_buff == 0xe8) {
			*(s32 *)(insn_buff + 1) += replacement - instr;
			DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
				*(s32 *)(insn_buff + 1),
				(unsigned long)instr + *(s32 *)(insn_buff + 1) + 5);
		}

		if (a->replacementlen && is_jmp(replacement[0]))
			recompute_jump(a, instr, replacement, insn_buff);

		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
			insn_buff[insn_buff_sz] = 0x90;

		DUMP_BYTES(insn_buff, insn_buff_sz, "%px: final_insn: ", instr);

		text_poke_early(instr, insn_buff, insn_buff_sz);

next:
		optimize_nops(instr, a->instrlen);
	}
}

#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL)

/*
 * CALL/JMP *%\reg
 */
static int emit_indirect(int op, int reg, u8 *bytes)
{
	int i = 0;
	u8 modrm;

	switch (op) {
	case CALL_INSN_OPCODE:
		modrm = 0x10; /* Reg = 2; CALL r/m */
		break;

	case JMP32_INSN_OPCODE:
		modrm = 0x20; /* Reg = 4; JMP r/m */
		break;

	default:
		WARN_ON_ONCE(1);
		return -1;
	}

	if (reg >= 8) {
		bytes[i++] = 0x41; /* REX.B prefix */
		reg -= 8;
	}

	modrm |= 0xc0; /* Mod = 3 */
	modrm += reg;

	bytes[i++] = 0xff; /* opcode */
	bytes[i++] = modrm;

	return i;
}

/*
 * Rewrite the compiler generated retpoline thunk calls.
 *
 * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate
 * indirect instructions, avoiding the extra indirection.
 *
 * For example, convert:
 *
 *   CALL __x86_indirect_thunk_\reg
 *
 * into:
 *
 *   CALL *%\reg
 *
 * It also tries to inline spectre_v2=retpoline,lfence when size permits.
 */
static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
{
	retpoline_thunk_t *target;
	int reg, ret, i = 0;
	u8 op, cc;

	target = addr + insn->length + insn->immediate.value;
	reg = target - __x86_indirect_thunk_array;

	if (WARN_ON_ONCE(reg & ~0xf))
		return -1;

	/* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */
	BUG_ON(reg == 4);

	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
		return -1;

	op = insn->opcode.bytes[0];

	/*
	 * Convert:
	 *
	 *   Jcc.d32 __x86_indirect_thunk_\reg
	 *
	 * into:
	 *
	 *   Jncc.d8 1f
	 *   [ LFENCE ]
	 *   JMP *%\reg
	 *   [ NOP ]
	 * 1:
	 */
	/* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */
	if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
		cc = insn->opcode.bytes[1] & 0xf;
		cc ^= 1; /* invert condition */

		bytes[i++] = 0x70 + cc;        /* Jcc.d8 */
		bytes[i++] = insn->length - 2; /* sizeof(Jcc.d8) == 2 */

		/* Continue as if: JMP.d32 __x86_indirect_thunk_\reg */
		op = JMP32_INSN_OPCODE;
	}

	/*
	 * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE.
	 */
	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
		bytes[i++] = 0x0f;
		bytes[i++] = 0xae;
		bytes[i++] = 0xe8; /* LFENCE */
	}

	ret = emit_indirect(op, reg, bytes + i);
	if (ret < 0)
		return ret;
	i += ret;

	for (; i < insn->length;)
		bytes[i++] = BYTES_NOP1;

	return i;
}

/*
 * Generated by 'objtool --retpoline'.
 */
void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
{
	s32 *s;

	for (s = start; s < end; s++) {
		void *addr = (void *)s + *s;
		struct insn insn;
		int len, ret;
		u8 bytes[16];
		u8 op1, op2;

		ret = insn_decode_kernel(&insn, addr);
		if (WARN_ON_ONCE(ret < 0))
			continue;

		op1 = insn.opcode.bytes[0];
		op2 = insn.opcode.bytes[1];

		switch (op1) {
		case CALL_INSN_OPCODE:
		case JMP32_INSN_OPCODE:
			break;

		case 0x0f: /* escape */
			if (op2 >= 0x80 && op2 <= 0x8f)
				break;
			fallthrough;
		default:
			WARN_ON_ONCE(1);
			continue;
		}

		DPRINTK("retpoline at: %pS (%px) len: %d to: %pS",
			addr, addr, insn.length,
			addr + insn.length + insn.immediate.value);

		len = patch_retpoline(addr, &insn, bytes);
		if (len == insn.length) {
			optimize_nops(bytes, len);
			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
			text_poke_early(addr, bytes, len);
		}
	}
}

/*
 * Rewrite the compiler generated return thunk tail-calls.
 *
 * For example, convert:
 *
 *   JMP __x86_return_thunk
 *
 * into:
 *
 *   RET
 */
static int patch_return(void *addr, struct insn *insn, u8 *bytes)
{
	int i = 0;

	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
		return -1;

	bytes[i++] = RET_INSN_OPCODE;

	for (; i < insn->length;)
		bytes[i++] = INT3_INSN_OPCODE;

	return i;
}

void __init_or_module noinline apply_returns(s32 *start, s32 *end)
{
	s32 *s;

	for (s = start; s < end; s++) {
		void *dest = NULL, *addr = (void *)s + *s;
		struct insn insn;
		int len, ret;
		u8 bytes[16];
		u8 op;

		ret = insn_decode_kernel(&insn, addr);
		if (WARN_ON_ONCE(ret < 0))
			continue;

		op = insn.opcode.bytes[0];
		if (op == JMP32_INSN_OPCODE)
			dest = addr + insn.length + insn.immediate.value;

		if (__static_call_fixup(addr, op, dest) ||
		    WARN_ON_ONCE(dest != &__x86_return_thunk))
			continue;

		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
			addr, addr, insn.length,
			addr + insn.length + insn.immediate.value);

		len = patch_return(addr, &insn, bytes);
		if (len == insn.length) {
			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
			text_poke_early(addr, bytes, len);
		}
	}
}
#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */

void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }

#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */

#ifdef CONFIG_X86_KERNEL_IBT

/*
 * Generated by: objtool --ibt
 */
void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
{
	s32 *s;

	for (s = start; s < end; s++) {
		u32 endbr, poison = gen_endbr_poison();
		void *addr = (void *)s + *s;

		if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
			continue;

		if (WARN_ON_ONCE(!is_endbr(endbr)))
			continue;

		DPRINTK("ENDBR at: %pS (%px)", addr, addr);

		/*
		 * When we have IBT, the lack of ENDBR will trigger #CP
		 */
		DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
		DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
		text_poke_early(addr, &poison, 4);
	}
}

#else

void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { }

#endif /* CONFIG_X86_KERNEL_IBT */

#ifdef CONFIG_SMP
static void alternatives_smp_lock(const s32 *start, const s32 *end,
				  u8 *text, u8 *text_end)
{
	const s32 *poff;

	for (poff = start; poff < end; poff++) {
		u8 *ptr = (u8 *)poff + *poff;

		if (!*poff || ptr < text || ptr >= text_end)
			continue;
		/* turn DS segment override prefix into lock prefix */
		if (*ptr == 0x3e)
			text_poke(ptr, ((unsigned char []){0xf0}), 1);
	}
}

static void alternatives_smp_unlock(const s32 *start, const s32 *end,
				    u8 *text, u8 *text_end)
{
	const s32 *poff;

	for (poff = start; poff < end; poff++) {
		u8 *ptr = (u8 *)poff + *poff;

		if (!*poff || ptr < text || ptr >= text_end)
			continue;
		/* turn lock prefix into DS segment override prefix */
		if (*ptr == 0xf0)
			text_poke(ptr, ((unsigned char []){0x3E}), 1);
	}
}

struct smp_alt_module {
	/* what is this ??? */
	struct module	*mod;
	char		*name;

	/* ptrs to lock prefixes */
	const s32	*locks;
	const s32	*locks_end;

	/* .text segment, needed to avoid patching init code ;) */
	u8		*text;
	u8		*text_end;

	struct list_head next;
};
static LIST_HEAD(smp_alt_modules);
static bool uniproc_patched = false;	/* protected by text_mutex */

void __init_or_module alternatives_smp_module_add(struct module *mod,
						  char *name,
						  void *locks, void *locks_end,
						  void *text,  void *text_end)
{
	struct smp_alt_module *smp;

	mutex_lock(&text_mutex);
	if (!uniproc_patched)
		goto unlock;

	if (num_possible_cpus() == 1)
		/* Don't bother remembering, we'll never have to undo it. */
		goto smp_unlock;

	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
	if (NULL == smp)
		/* we'll run the (safe but slow) SMP code then ... */
		goto unlock;

	smp->mod	= mod;
	smp->name	= name;
	smp->locks	= locks;
	smp->locks_end	= locks_end;
	smp->text	= text;
	smp->text_end	= text_end;
	DPRINTK("locks %p -> %p, text %p -> %p, name %s\n",
		smp->locks, smp->locks_end,
		smp->text, smp->text_end, smp->name);

	list_add_tail(&smp->next, &smp_alt_modules);
smp_unlock:
	alternatives_smp_unlock(locks, locks_end, text, text_end);
unlock:
	mutex_unlock(&text_mutex);
}

void __init_or_module alternatives_smp_module_del(struct module *mod)
{
	struct smp_alt_module *item;

	mutex_lock(&text_mutex);
	list_for_each_entry(item, &smp_alt_modules, next) {
		if (mod != item->mod)
			continue;
		list_del(&item->next);
		kfree(item);
		break;
	}
	mutex_unlock(&text_mutex);
}

void alternatives_enable_smp(void)
{
	struct smp_alt_module *mod;

	/* Why bother if there are no other CPUs? */
	BUG_ON(num_possible_cpus() == 1);

	mutex_lock(&text_mutex);

	if (uniproc_patched) {
		pr_info("switching to SMP code\n");
		BUG_ON(num_online_cpus() != 1);
		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
		clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
		list_for_each_entry(mod, &smp_alt_modules, next)
			alternatives_smp_lock(mod->locks, mod->locks_end,
					      mod->text, mod->text_end);
		uniproc_patched = false;
	}
	mutex_unlock(&text_mutex);
}

/*
 * Return 1 if the address range is reserved for SMP-alternatives.
 * Must hold text_mutex.
 */
int alternatives_text_reserved(void *start, void *end)
{
	struct smp_alt_module *mod;
	const s32 *poff;
	u8 *text_start = start;
	u8 *text_end = end;

	lockdep_assert_held(&text_mutex);

	list_for_each_entry(mod, &smp_alt_modules, next) {
		if (mod->text > text_end || mod->text_end < text_start)
			continue;
		for (poff = mod->locks; poff < mod->locks_end; poff++) {
			const u8 *ptr = (const u8 *)poff + *poff;

			if (text_start <= ptr && text_end > ptr)
				return 1;
		}
	}

	return 0;
}
#endif /* CONFIG_SMP */

#ifdef CONFIG_PARAVIRT
void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
				     struct paravirt_patch_site *end)
{
	struct paravirt_patch_site *p;
	char insn_buff[MAX_PATCH_LEN];

	for (p = start; p < end; p++) {
		unsigned int used;

		BUG_ON(p->len > MAX_PATCH_LEN);
		/* prep the buffer with the original instructions */
		memcpy(insn_buff, p->instr, p->len);
		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);

		BUG_ON(used > p->len);

		/* Pad the rest with nops */
		add_nops(insn_buff + used, p->len - used);
		text_poke_early(p->instr, insn_buff, p->len);
	}
}
extern struct paravirt_patch_site __start_parainstructions[],
	__stop_parainstructions[];
#endif	/* CONFIG_PARAVIRT */

/*
 * Self-test for the INT3 based CALL emulation code.
 *
 * This exercises int3_emulate_call() to make sure INT3 pt_regs are set up
 * properly and that there is a stack gap between the INT3 frame and the
 * previous context. Without this gap doing a virtual PUSH on the interrupted
 * stack would corrupt the INT3 IRET frame.
 *
 * See entry_{32,64}.S for more details.
 */

/*
 * We define the int3_magic() function in assembly to control the calling
 * convention such that we can 'call' it from assembly.
 */

extern void int3_magic(unsigned int *ptr); /* defined in asm */

asm (
"	.pushsection	.init.text, \"ax\", @progbits\n"
"	.type		int3_magic, @function\n"
"int3_magic:\n"
	ANNOTATE_NOENDBR
"	movl	$1, (%" _ASM_ARG1 ")\n"
	ASM_RET
"	.size		int3_magic, .-int3_magic\n"
"	.popsection\n"
);

extern void int3_selftest_ip(void); /* defined in asm below */

static int __init
int3_exception_notify(struct notifier_block *self, unsigned long val, void *data)
{
	unsigned long selftest = (unsigned long)&int3_selftest_ip;
	struct die_args *args = data;
	struct pt_regs *regs = args->regs;

	OPTIMIZER_HIDE_VAR(selftest);

	if (!regs || user_mode(regs))
		return NOTIFY_DONE;

	if (val != DIE_INT3)
		return NOTIFY_DONE;

	if (regs->ip - INT3_INSN_SIZE != selftest)
		return NOTIFY_DONE;

	int3_emulate_call(regs, (unsigned long)&int3_magic);
	return NOTIFY_STOP;
}

/* Must be noinline to ensure uniqueness of int3_selftest_ip. */
static noinline void __init int3_selftest(void)
{
	static __initdata struct notifier_block int3_exception_nb = {
		.notifier_call	= int3_exception_notify,
		.priority	= INT_MAX-1, /* last */
	};
	unsigned int val = 0;

	BUG_ON(register_die_notifier(&int3_exception_nb));

	/*
	 * Basically: int3_magic(&val); but really complicated :-)
	 *
	 * INT3 padded with NOP to CALL_INSN_SIZE. The int3_exception_nb
	 * notifier above will emulate CALL for us.
	 */
	asm volatile ("int3_selftest_ip:\n\t"
		      ANNOTATE_NOENDBR
		      "    int3; nop; nop; nop; nop\n\t"
		      : ASM_CALL_CONSTRAINT
		      : __ASM_SEL_RAW(a, D) (&val)
		      : "memory");

	BUG_ON(val != 1);

	unregister_die_notifier(&int3_exception_nb);
}

void __init alternative_instructions(void)
{
	int3_selftest();

	/*
	 * The patching is not fully atomic, so try to avoid local
	 * interruptions that might execute the to be patched code.
	 * Other CPUs are not running.
	 */
	stop_nmi();

	/*
	 * Don't stop machine check exceptions while patching.
	 * MCEs only happen when something got corrupted and in this
	 * case we must do something about the corruption.
	 * Ignoring it is worse than an unlikely patching race.
	 * Also machine checks tend to be broadcast and if one CPU
	 * goes into machine check the others follow quickly, so we don't
	 * expect a machine check to cause undue problems during to code
	 * patching.
	 */

	/*
	 * Paravirt patching and alternative patching can be combined to
	 * replace a function call with a short direct code sequence (e.g.
	 * by setting a constant return value instead of doing that in an
	 * external function).
	 * In order to make this work the following sequence is required:
	 * 1. set (artificial) features depending on used paravirt
	 *    functions which can later influence alternative patching
	 * 2. apply paravirt patching (generally replacing an indirect
	 *    function call with a direct one)
	 * 3. apply alternative patching (e.g. replacing a direct function
	 *    call with a custom code sequence)
	 * Doing paravirt patching after alternative patching would clobber
	 * the optimization of the custom code with a function call again.
	 */
	paravirt_set_cap();

	/*
	 * First patch paravirt functions, such that we overwrite the indirect
	 * call with the direct call.
	 */
	apply_paravirt(__parainstructions, __parainstructions_end);

	/*
	 * Rewrite the retpolines, must be done before alternatives since
	 * those can rewrite the retpoline thunks.
	 */
	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
	apply_returns(__return_sites, __return_sites_end);

	/*
	 * Then patch alternatives, such that those paravirt calls that are in
	 * alternatives can be overwritten by their immediate fragments.
	 */
	apply_alternatives(__alt_instructions, __alt_instructions_end);

	apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);

#ifdef CONFIG_SMP
	/* Patch to UP if other cpus not imminent. */
	if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
		uniproc_patched = true;
		alternatives_smp_module_add(NULL, "core kernel",
					    __smp_locks, __smp_locks_end,
					    _text, _etext);
	}

	if (!uniproc_patched || num_possible_cpus() == 1) {
		free_init_pages("SMP alternatives",
				(unsigned long)__smp_locks,
				(unsigned long)__smp_locks_end);
	}
#endif

	restart_nmi();
	alternatives_patched = 1;
}

/**
 * text_poke_early - Update instructions on a live kernel at boot time
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy
 *
 * When you use this code to patch more than one byte of an instruction
 * you need to make sure that other CPUs cannot execute this code in parallel.
 * Also no thread must be currently preempted in the middle of these
 * instructions. And on the local CPU you need to be protected against NMI or
 * MCE handlers seeing an inconsistent instruction while you patch.
 */
void __init_or_module text_poke_early(void *addr, const void *opcode,
				      size_t len)
{
	unsigned long flags;

	if (boot_cpu_has(X86_FEATURE_NX) &&
	    is_module_text_address((unsigned long)addr)) {
		/*
		 * Modules text is marked initially as non-executable, so the
		 * code cannot be running and speculative code-fetches are
		 * prevented. Just change the code.
		 */
		memcpy(addr, opcode, len);
	} else {
		local_irq_save(flags);
		memcpy(addr, opcode, len);
		local_irq_restore(flags);
		sync_core();

		/*
		 * Could also do a CLFLUSH here to speed up CPU recovery; but
		 * that causes hangs on some VIA CPUs.
		 */
	}
}

typedef struct {
	struct mm_struct *mm;
} temp_mm_state_t;

/*
 * Using a temporary mm allows to set temporary mappings that are not accessible
 * by other CPUs. Such mappings are needed to perform sensitive memory writes
 * that override the kernel memory protections (e.g., W^X), without exposing the
 * temporary page-table mappings that are required for these write operations to
 * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
 * mapping is torn down.
 *
 * Context: The temporary mm needs to be used exclusively by a single core. To
 *          harden security IRQs must be disabled while the temporary mm is
 *          loaded, thereby preventing interrupt handler bugs from overriding
 *          the kernel memory protection.
 */
static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
{
	temp_mm_state_t temp_state;

	lockdep_assert_irqs_disabled();

	/*
	 * Make sure not to be in TLB lazy mode, as otherwise we'll end up
	 * with a stale address space WITHOUT being in lazy mode after
	 * restoring the previous mm.
	 */
	if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
		leave_mm(smp_processor_id());

	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
	switch_mm_irqs_off(NULL, mm, current);

	/*
	 * If breakpoints are enabled, disable them while the temporary mm is
	 * used. Userspace might set up watchpoints on addresses that are used
	 * in the temporary mm, which would lead to wrong signals being sent or
	 * crashes.
	 *
	 * Note that breakpoints are not disabled selectively, which also causes
	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
	 * undesirable, but still seems reasonable as the code that runs in the
	 * temporary mm should be short.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_disable();

	return temp_state;
}

static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
{
	lockdep_assert_irqs_disabled();
	switch_mm_irqs_off(NULL, prev_state.mm, current);

	/*
	 * Restore the breakpoints if they were disabled before the temporary mm
	 * was loaded.
	 */
	if (hw_breakpoint_active())
		hw_breakpoint_restore();
}

__ro_after_init struct mm_struct *poking_mm;
__ro_after_init unsigned long poking_addr;

static void text_poke_memcpy(void *dst, const void *src, size_t len)
{
	memcpy(dst, src, len);
}

static void text_poke_memset(void *dst, const void *src, size_t len)
{
	int c = *(const int *)src;

	memset(dst, c, len);
}

typedef void text_poke_f(void *dst, const void *src, size_t len);

static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t len)
{
	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
	struct page *pages[2] = {NULL};
	temp_mm_state_t prev;
	unsigned long flags;
	pte_t pte, *ptep;
	spinlock_t *ptl;
	pgprot_t pgprot;

	/*
	 * While boot memory allocator is running we cannot use struct pages as
	 * they are not yet initialized. There is no way to recover.
	 */
	BUG_ON(!after_bootmem);

	if (!core_kernel_text((unsigned long)addr)) {
		pages[0] = vmalloc_to_page(addr);
		if (cross_page_boundary)
			pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
	} else {
		pages[0] = virt_to_page(addr);
		WARN_ON(!PageReserved(pages[0]));
		if (cross_page_boundary)
			pages[1] = virt_to_page(addr + PAGE_SIZE);
	}
	/*
	 * If something went wrong, crash and burn since recovery paths are not
	 * implemented.
	 */
	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));

	/*
	 * Map the page without the global bit, as TLB flushing is done with
	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
	 */
	pgprot = __pgprot(pgprot_val(PAGE_KERNEL) & ~_PAGE_GLOBAL);

	/*
	 * The lock is not really needed, but this allows to avoid open-coding.
	 */
	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);

	/*
	 * This must not fail; preallocated in poking_init().
	 */
	VM_BUG_ON(!ptep);

	local_irq_save(flags);

	pte = mk_pte(pages[0], pgprot);
	set_pte_at(poking_mm, poking_addr, ptep, pte);

	if (cross_page_boundary) {
		pte = mk_pte(pages[1], pgprot);
		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
	}

	/*
	 * Loading the temporary mm behaves as a compiler barrier, which
	 * guarantees that the PTE will be set at the time memcpy() is done.
	 */
	prev = use_temporary_mm(poking_mm);

	kasan_disable_current();
	func((u8 *)poking_addr + offset_in_page(addr), src, len);
	kasan_enable_current();

	/*
	 * Ensure that the PTE is only cleared after the instructions of memcpy
	 * were issued by using a compiler barrier.
	 */
	barrier();

	pte_clear(poking_mm, poking_addr, ptep);
	if (cross_page_boundary)
		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);

	/*
	 * Loading the previous page-table hierarchy requires a serializing
	 * instruction that already allows the core to see the updated version.
	 * Xen-PV is assumed to serialize execution in a similar manner.
	 */
	unuse_temporary_mm(prev);

	/*
	 * Flushing the TLB might involve IPIs, which would require enabled
	 * IRQs, but not if the mm is not used, as it is in this point.
	 */
	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
			   PAGE_SHIFT, false);

	if (func == text_poke_memcpy) {
		/*
		 * If the text does not match what we just wrote then something is
		 * fundamentally screwy; there's nothing we can really do about that.
		 */
		BUG_ON(memcmp(addr, src, len));
	}

	local_irq_restore(flags);
	pte_unmap_unlock(ptep, ptl);
	return addr;
}

/**
 * text_poke - Update instructions on a live kernel
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy
 *
 * Only atomic text poke/set should be allowed when not doing early patching.
 * It means the size must be writable atomically and the address must be aligned
 * in a way that permits an atomic write. It also makes sure we fit on a single
 * page.
 *
 * Note that the caller must ensure that if the modified code is part of a
 * module, the module would not be removed during poking. This can be achieved
 * by registering a module notifier, and ordering module removal and patching
 * trough a mutex.
 */
void *text_poke(void *addr, const void *opcode, size_t len)
{
	lockdep_assert_held(&text_mutex);

	return __text_poke(text_poke_memcpy, addr, opcode, len);
}

/**
 * text_poke_kgdb - Update instructions on a live kernel by kgdb
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy
 *
 * Only atomic text poke/set should be allowed when not doing early patching.
 * It means the size must be writable atomically and the address must be aligned
 * in a way that permits an atomic write. It also makes sure we fit on a single
 * page.
 *
 * Context: should only be used by kgdb, which ensures no other core is running,
 *	    despite the fact it does not hold the text_mutex.
 */
void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
{
	return __text_poke(text_poke_memcpy, addr, opcode, len);
}

/**
 * text_poke_copy - Copy instructions into (an unused part of) RX memory
 * @addr: address to modify
 * @opcode: source of the copy
 * @len: length to copy, could be more than 2x PAGE_SIZE
 *
 * Not safe against concurrent execution; useful for JITs to dump
 * new code blocks into unused regions of RX memory. Can be used in
 * conjunction with synchronize_rcu_tasks() to wait for existing
 * execution to quiesce after having made sure no existing functions
 * pointers are live.
 */
void *text_poke_copy(void *addr, const void *opcode, size_t len)
{
	unsigned long start = (unsigned long)addr;
	size_t patched = 0;

	if (WARN_ON_ONCE(core_kernel_text(start)))
		return NULL;

	mutex_lock(&text_mutex);
	while (patched < len) {
		unsigned long ptr = start + patched;
		size_t s;

		s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);

		__text_poke(text_poke_memcpy, (void *)ptr, opcode + patched, s);
		patched += s;
	}
	mutex_unlock(&text_mutex);
	return addr;
}

/**
 * text_poke_set - memset into (an unused part of) RX memory
 * @addr: address to modify
 * @c: the byte to fill the area with
 * @len: length to copy, could be more than 2x PAGE_SIZE
 *
 * This is useful to overwrite unused regions of RX memory with illegal
 * instructions.
 */
void *text_poke_set(void *addr, int c, size_t len)
{
	unsigned long start = (unsigned long)addr;
	size_t patched = 0;

	if (WARN_ON_ONCE(core_kernel_text(start)))
		return NULL;

	mutex_lock(&text_mutex);
	while (patched < len) {
		unsigned long ptr = start + patched;
		size_t s;

		s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);

		__text_poke(text_poke_memset, (void *)ptr, (void *)&c, s);
		patched += s;
	}
	mutex_unlock(&text_mutex);
	return addr;
}

static void do_sync_core(void *info)
{
	sync_core();
}

void text_poke_sync(void)
{
	on_each_cpu(do_sync_core, NULL, 1);
}

struct text_poke_loc {
	/* addr := _stext + rel_addr */
	s32 rel_addr;
	s32 disp;
	u8 len;
	u8 opcode;
	const u8 text[POKE_MAX_OPCODE_SIZE];
	/* see text_poke_bp_batch() */
	u8 old;
};

struct bp_patching_desc {
	struct text_poke_loc *vec;
	int nr_entries;
	atomic_t refs;
};

static struct bp_patching_desc *bp_desc;

static __always_inline
struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
{
	/* rcu_dereference */
	struct bp_patching_desc *desc = __READ_ONCE(*descp);

	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
		return NULL;

	return desc;
}

static __always_inline void put_desc(struct bp_patching_desc *desc)
{
	smp_mb__before_atomic();
	arch_atomic_dec(&desc->refs);
}

static __always_inline void *text_poke_addr(struct text_poke_loc *tp)
{
	return _stext + tp->rel_addr;
}

static __always_inline int patch_cmp(const void *key, const void *elt)
{
	struct text_poke_loc *tp = (struct text_poke_loc *) elt;

	if (key < text_poke_addr(tp))
		return -1;
	if (key > text_poke_addr(tp))
		return 1;
	return 0;
}

noinstr int poke_int3_handler(struct pt_regs *regs)
{
	struct bp_patching_desc *desc;
	struct text_poke_loc *tp;
	int ret = 0;
	void *ip;

	if (user_mode(regs))
		return 0;

	/*
	 * Having observed our INT3 instruction, we now must observe
	 * bp_desc:
	 *
	 *	bp_desc = desc			INT3
	 *	WMB				RMB
	 *	write INT3			if (desc)
	 */
	smp_rmb();

	desc = try_get_desc(&bp_desc);
	if (!desc)
		return 0;

	/*
	 * Discount the INT3. See text_poke_bp_batch().
	 */
	ip = (void *) regs->ip - INT3_INSN_SIZE;

	/*
	 * Skip the binary search if there is a single member in the vector.
	 */
	if (unlikely(desc->nr_entries > 1)) {
		tp = __inline_bsearch(ip, desc->vec, desc->nr_entries,
				      sizeof(struct text_poke_loc),
				      patch_cmp);
		if (!tp)
			goto out_put;
	} else {
		tp = desc->vec;
		if (text_poke_addr(tp) != ip)
			goto out_put;
	}

	ip += tp->len;

	switch (tp->opcode) {
	case INT3_INSN_OPCODE:
		/*
		 * Someone poked an explicit INT3, they'll want to handle it,
		 * do not consume.
		 */
		goto out_put;

	case RET_INSN_OPCODE:
		int3_emulate_ret(regs);
		break;

	case CALL_INSN_OPCODE:
		int3_emulate_call(regs, (long)ip + tp->disp);
		break;

	case JMP32_INSN_OPCODE:
	case JMP8_INSN_OPCODE:
		int3_emulate_jmp(regs, (long)ip + tp->disp);
		break;

	default:
		BUG();
	}

	ret = 1;

out_put:
	put_desc(desc);
	return ret;
}

#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
static struct text_poke_loc tp_vec[TP_VEC_MAX];
static int tp_vec_nr;

/**
 * text_poke_bp_batch() -- update instructions on live kernel on SMP
 * @tp:			vector of instructions to patch
 * @nr_entries:		number of entries in the vector
 *
 * Modify multi-byte instruction by using int3 breakpoint on SMP.
 * We completely avoid stop_machine() here, and achieve the
 * synchronization using int3 breakpoint.
 *
 * The way it is done:
 *	- For each entry in the vector:
 *		- add a int3 trap to the address that will be patched
 *	- sync cores
 *	- For each entry in the vector:
 *		- update all but the first byte of the patched range
 *	- sync cores
 *	- For each entry in the vector:
 *		- replace the first byte (int3) by the first byte of
 *		  replacing opcode
 *	- sync cores
 */
static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
{
	struct bp_patching_desc desc = {
		.vec = tp,
		.nr_entries = nr_entries,
		.refs = ATOMIC_INIT(1),
	};
	unsigned char int3 = INT3_INSN_OPCODE;
	unsigned int i;
	int do_sync;

	lockdep_assert_held(&text_mutex);

	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */

	/*
	 * Corresponding read barrier in int3 notifier for making sure the
	 * nr_entries and handler are correctly ordered wrt. patching.
	 */
	smp_wmb();

	/*
	 * First step: add a int3 trap to the address that will be patched.
	 */
	for (i = 0; i < nr_entries; i++) {
		tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
		text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
	}

	text_poke_sync();

	/*
	 * Second step: update all but the first byte of the patched range.
	 */
	for (do_sync = 0, i = 0; i < nr_entries; i++) {
		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
		int len = tp[i].len;

		if (len - INT3_INSN_SIZE > 0) {
			memcpy(old + INT3_INSN_SIZE,
			       text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
			       len - INT3_INSN_SIZE);
			text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
				  (const char *)tp[i].text + INT3_INSN_SIZE,
				  len - INT3_INSN_SIZE);
			do_sync++;
		}

		/*
		 * Emit a perf event to record the text poke, primarily to
		 * support Intel PT decoding which must walk the executable code
		 * to reconstruct the trace. The flow up to here is:
		 *   - write INT3 byte
		 *   - IPI-SYNC
		 *   - write instruction tail
		 * At this point the actual control flow will be through the
		 * INT3 and handler and not hit the old or new instruction.
		 * Intel PT outputs FUP/TIP packets for the INT3, so the flow
		 * can still be decoded. Subsequently:
		 *   - emit RECORD_TEXT_POKE with the new instruction
		 *   - IPI-SYNC
		 *   - write first byte
		 *   - IPI-SYNC
		 * So before the text poke event timestamp, the decoder will see
		 * either the old instruction flow or FUP/TIP of INT3. After the
		 * text poke event timestamp, the decoder will see either the
		 * new instruction flow or FUP/TIP of INT3. Thus decoders can
		 * use the timestamp as the point at which to modify the
		 * executable code.
		 * The old instruction is recorded so that the event can be
		 * processed forwards or backwards.
		 */
		perf_event_text_poke(text_poke_addr(&tp[i]), old, len,
				     tp[i].text, len);
	}

	if (do_sync) {
		/*
		 * According to Intel, this core syncing is very likely
		 * not necessary and we'd be safe even without it. But
		 * better safe than sorry (plus there's not only Intel).
		 */
		text_poke_sync();
	}

	/*
	 * Third step: replace the first byte (int3) by the first byte of
	 * replacing opcode.
	 */
	for (do_sync = 0, i = 0; i < nr_entries; i++) {
		if (tp[i].text[0] == INT3_INSN_OPCODE)
			continue;

		text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE);
		do_sync++;
	}

	if (do_sync)
		text_poke_sync();

	/*
	 * Remove and synchronize_rcu(), except we have a very primitive
	 * refcount based completion.
	 */
	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
	if (!atomic_dec_and_test(&desc.refs))
		atomic_cond_read_acquire(&desc.refs, !VAL);
}

static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
			       const void *opcode, size_t len, const void *emulate)
{
	struct insn insn;
	int ret, i;

	memcpy((void *)tp->text, opcode, len);
	if (!emulate)
		emulate = opcode;

	ret = insn_decode_kernel(&insn, emulate);
	BUG_ON(ret < 0);

	tp->rel_addr = addr - (void *)_stext;
	tp->len = len;
	tp->opcode = insn.opcode.bytes[0];

	switch (tp->opcode) {
	case RET_INSN_OPCODE:
	case JMP32_INSN_OPCODE:
	case JMP8_INSN_OPCODE:
		/*
		 * Control flow instructions without implied execution of the
		 * next instruction can be padded with INT3.
		 */
		for (i = insn.length; i < len; i++)
			BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
		break;

	default:
		BUG_ON(len != insn.length);
	};


	switch (tp->opcode) {
	case INT3_INSN_OPCODE:
	case RET_INSN_OPCODE:
		break;

	case CALL_INSN_OPCODE:
	case JMP32_INSN_OPCODE:
	case JMP8_INSN_OPCODE:
		tp->disp = insn.immediate.value;
		break;

	default: /* assume NOP */
		switch (len) {
		case 2: /* NOP2 -- emulate as JMP8+0 */
			BUG_ON(memcmp(emulate, x86_nops[len], len));
			tp->opcode = JMP8_INSN_OPCODE;
			tp->disp = 0;
			break;

		case 5: /* NOP5 -- emulate as JMP32+0 */
			BUG_ON(memcmp(emulate, x86_nops[len], len));
			tp->opcode = JMP32_INSN_OPCODE;
			tp->disp = 0;
			break;

		default: /* unknown instruction */
			BUG();
		}
		break;
	}
}

/*
 * We hard rely on the tp_vec being ordered; ensure this is so by flushing
 * early if needed.
 */
static bool tp_order_fail(void *addr)
{
	struct text_poke_loc *tp;

	if (!tp_vec_nr)
		return false;

	if (!addr) /* force */
		return true;

	tp = &tp_vec[tp_vec_nr - 1];
	if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr)
		return true;

	return false;
}

static void text_poke_flush(void *addr)
{
	if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) {
		text_poke_bp_batch(tp_vec, tp_vec_nr);
		tp_vec_nr = 0;
	}
}

void text_poke_finish(void)
{
	text_poke_flush(NULL);
}

void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
{
	struct text_poke_loc *tp;

	if (unlikely(system_state == SYSTEM_BOOTING)) {
		text_poke_early(addr, opcode, len);
		return;
	}

	text_poke_flush(addr);

	tp = &tp_vec[tp_vec_nr++];
	text_poke_loc_init(tp, addr, opcode, len, emulate);
}

/**
 * text_poke_bp() -- update instructions on live kernel on SMP
 * @addr:	address to patch
 * @opcode:	opcode of new instruction
 * @len:	length to copy
 * @emulate:	instruction to be emulated
 *
 * Update a single instruction with the vector in the stack, avoiding
 * dynamically allocated memory. This function should be used when it is
 * not possible to allocate memory.
 */
void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
{
	struct text_poke_loc tp;

	if (unlikely(system_state == SYSTEM_BOOTING)) {
		text_poke_early(addr, opcode, len);
		return;
	}

	text_poke_loc_init(&tp, addr, opcode, len, emulate);
	text_poke_bp_batch(&tp, 1);
}