Free Electrons

Embedded Linux Experts

   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
/* By Ross Biro 1/23/92 */
/*
 * Pentium III FXSR, SSE support
 *	Gareth Hughes <gareth@valinux.com>, May 2000
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/ptrace.h>
#include <linux/regset.h>
#include <linux/tracehook.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/audit.h>
#include <linux/seccomp.h>
#include <linux/signal.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>

#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/debugreg.h>
#include <asm/ldt.h>
#include <asm/desc.h>
#include <asm/prctl.h>
#include <asm/proto.h>
#include <asm/hw_breakpoint.h>
#include <asm/traps.h>

#include "tls.h"

#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>

enum x86_regset {
	REGSET_GENERAL,
	REGSET_FP,
	REGSET_XFP,
	REGSET_IOPERM64 = REGSET_XFP,
	REGSET_XSTATE,
	REGSET_TLS,
	REGSET_IOPERM32,
};

struct pt_regs_offset {
	const char *name;
	int offset;
};

#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
#define REG_OFFSET_END {.name = NULL, .offset = 0}

static const struct pt_regs_offset regoffset_table[] = {
#ifdef CONFIG_X86_64
	REG_OFFSET_NAME(r15),
	REG_OFFSET_NAME(r14),
	REG_OFFSET_NAME(r13),
	REG_OFFSET_NAME(r12),
	REG_OFFSET_NAME(r11),
	REG_OFFSET_NAME(r10),
	REG_OFFSET_NAME(r9),
	REG_OFFSET_NAME(r8),
#endif
	REG_OFFSET_NAME(bx),
	REG_OFFSET_NAME(cx),
	REG_OFFSET_NAME(dx),
	REG_OFFSET_NAME(si),
	REG_OFFSET_NAME(di),
	REG_OFFSET_NAME(bp),
	REG_OFFSET_NAME(ax),
#ifdef CONFIG_X86_32
	REG_OFFSET_NAME(ds),
	REG_OFFSET_NAME(es),
	REG_OFFSET_NAME(fs),
	REG_OFFSET_NAME(gs),
#endif
	REG_OFFSET_NAME(orig_ax),
	REG_OFFSET_NAME(ip),
	REG_OFFSET_NAME(cs),
	REG_OFFSET_NAME(flags),
	REG_OFFSET_NAME(sp),
	REG_OFFSET_NAME(ss),
	REG_OFFSET_END,
};

/**
 * regs_query_register_offset() - query register offset from its name
 * @name:	the name of a register
 *
 * regs_query_register_offset() returns the offset of a register in struct
 * pt_regs from its name. If the name is invalid, this returns -EINVAL;
 */
int regs_query_register_offset(const char *name)
{
	const struct pt_regs_offset *roff;
	for (roff = regoffset_table; roff->name != NULL; roff++)
		if (!strcmp(roff->name, name))
			return roff->offset;
	return -EINVAL;
}

/**
 * regs_query_register_name() - query register name from its offset
 * @offset:	the offset of a register in struct pt_regs.
 *
 * regs_query_register_name() returns the name of a register from its
 * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
 */
const char *regs_query_register_name(unsigned int offset)
{
	const struct pt_regs_offset *roff;
	for (roff = regoffset_table; roff->name != NULL; roff++)
		if (roff->offset == offset)
			return roff->name;
	return NULL;
}

static const int arg_offs_table[] = {
#ifdef CONFIG_X86_32
	[0] = offsetof(struct pt_regs, ax),
	[1] = offsetof(struct pt_regs, dx),
	[2] = offsetof(struct pt_regs, cx)
#else /* CONFIG_X86_64 */
	[0] = offsetof(struct pt_regs, di),
	[1] = offsetof(struct pt_regs, si),
	[2] = offsetof(struct pt_regs, dx),
	[3] = offsetof(struct pt_regs, cx),
	[4] = offsetof(struct pt_regs, r8),
	[5] = offsetof(struct pt_regs, r9)
#endif
};

/*
 * does not yet catch signals sent when the child dies.
 * in exit.c or in signal.c.
 */

/*
 * Determines which flags the user has access to [1 = access, 0 = no access].
 */
#define FLAG_MASK_32		((unsigned long)			\
				 (X86_EFLAGS_CF | X86_EFLAGS_PF |	\
				  X86_EFLAGS_AF | X86_EFLAGS_ZF |	\
				  X86_EFLAGS_SF | X86_EFLAGS_TF |	\
				  X86_EFLAGS_DF | X86_EFLAGS_OF |	\
				  X86_EFLAGS_RF | X86_EFLAGS_AC))

/*
 * Determines whether a value may be installed in a segment register.
 */
static inline bool invalid_selector(u16 value)
{
	return unlikely(value != 0 && (value & SEGMENT_RPL_MASK) != USER_RPL);
}

#ifdef CONFIG_X86_32

#define FLAG_MASK		FLAG_MASK_32

static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long regno)
{
	BUILD_BUG_ON(offsetof(struct pt_regs, bx) != 0);
	return &regs->bx + (regno >> 2);
}

static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
{
	/*
	 * Returning the value truncates it to 16 bits.
	 */
	unsigned int retval;
	if (offset != offsetof(struct user_regs_struct, gs))
		retval = *pt_regs_access(task_pt_regs(task), offset);
	else {
		if (task == current)
			retval = get_user_gs(task_pt_regs(task));
		else
			retval = task_user_gs(task);
	}
	return retval;
}

static int set_segment_reg(struct task_struct *task,
			   unsigned long offset, u16 value)
{
	/*
	 * The value argument was already truncated to 16 bits.
	 */
	if (invalid_selector(value))
		return -EIO;

	/*
	 * For %cs and %ss we cannot permit a null selector.
	 * We can permit a bogus selector as long as it has USER_RPL.
	 * Null selectors are fine for other segment registers, but
	 * we will never get back to user mode with invalid %cs or %ss
	 * and will take the trap in iret instead.  Much code relies
	 * on user_mode() to distinguish a user trap frame (which can
	 * safely use invalid selectors) from a kernel trap frame.
	 */
	switch (offset) {
	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ss):
		if (unlikely(value == 0))
			return -EIO;

	default:
		*pt_regs_access(task_pt_regs(task), offset) = value;
		break;

	case offsetof(struct user_regs_struct, gs):
		if (task == current)
			set_user_gs(task_pt_regs(task), value);
		else
			task_user_gs(task) = value;
	}

	return 0;
}

#else  /* CONFIG_X86_64 */

#define FLAG_MASK		(FLAG_MASK_32 | X86_EFLAGS_NT)

static unsigned long *pt_regs_access(struct pt_regs *regs, unsigned long offset)
{
	BUILD_BUG_ON(offsetof(struct pt_regs, r15) != 0);
	return &regs->r15 + (offset / sizeof(regs->r15));
}

static u16 get_segment_reg(struct task_struct *task, unsigned long offset)
{
	/*
	 * Returning the value truncates it to 16 bits.
	 */
	unsigned int seg;

	switch (offset) {
	case offsetof(struct user_regs_struct, fs):
		if (task == current) {
			/* Older gas can't assemble movq %?s,%r?? */
			asm("movl %%fs,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.fsindex;
	case offsetof(struct user_regs_struct, gs):
		if (task == current) {
			asm("movl %%gs,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.gsindex;
	case offsetof(struct user_regs_struct, ds):
		if (task == current) {
			asm("movl %%ds,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.ds;
	case offsetof(struct user_regs_struct, es):
		if (task == current) {
			asm("movl %%es,%0" : "=r" (seg));
			return seg;
		}
		return task->thread.es;

	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ss):
		break;
	}
	return *pt_regs_access(task_pt_regs(task), offset);
}

static int set_segment_reg(struct task_struct *task,
			   unsigned long offset, u16 value)
{
	/*
	 * The value argument was already truncated to 16 bits.
	 */
	if (invalid_selector(value))
		return -EIO;

	switch (offset) {
	case offsetof(struct user_regs_struct,fs):
		/*
		 * If this is setting fs as for normal 64-bit use but
		 * setting fs_base has implicitly changed it, leave it.
		 */
		if ((value == FS_TLS_SEL && task->thread.fsindex == 0 &&
		     task->thread.fs != 0) ||
		    (value == 0 && task->thread.fsindex == FS_TLS_SEL &&
		     task->thread.fs == 0))
			break;
		task->thread.fsindex = value;
		if (task == current)
			loadsegment(fs, task->thread.fsindex);
		break;
	case offsetof(struct user_regs_struct,gs):
		/*
		 * If this is setting gs as for normal 64-bit use but
		 * setting gs_base has implicitly changed it, leave it.
		 */
		if ((value == GS_TLS_SEL && task->thread.gsindex == 0 &&
		     task->thread.gs != 0) ||
		    (value == 0 && task->thread.gsindex == GS_TLS_SEL &&
		     task->thread.gs == 0))
			break;
		task->thread.gsindex = value;
		if (task == current)
			load_gs_index(task->thread.gsindex);
		break;
	case offsetof(struct user_regs_struct,ds):
		task->thread.ds = value;
		if (task == current)
			loadsegment(ds, task->thread.ds);
		break;
	case offsetof(struct user_regs_struct,es):
		task->thread.es = value;
		if (task == current)
			loadsegment(es, task->thread.es);
		break;

		/*
		 * Can't actually change these in 64-bit mode.
		 */
	case offsetof(struct user_regs_struct,cs):
		if (unlikely(value == 0))
			return -EIO;
#ifdef CONFIG_IA32_EMULATION
		if (test_tsk_thread_flag(task, TIF_IA32))
			task_pt_regs(task)->cs = value;
#endif
		break;
	case offsetof(struct user_regs_struct,ss):
		if (unlikely(value == 0))
			return -EIO;
#ifdef CONFIG_IA32_EMULATION
		if (test_tsk_thread_flag(task, TIF_IA32))
			task_pt_regs(task)->ss = value;
#endif
		break;
	}

	return 0;
}

#endif	/* CONFIG_X86_32 */

static unsigned long get_flags(struct task_struct *task)
{
	unsigned long retval = task_pt_regs(task)->flags;

	/*
	 * If the debugger set TF, hide it from the readout.
	 */
	if (test_tsk_thread_flag(task, TIF_FORCED_TF))
		retval &= ~X86_EFLAGS_TF;

	return retval;
}

static int set_flags(struct task_struct *task, unsigned long value)
{
	struct pt_regs *regs = task_pt_regs(task);

	/*
	 * If the user value contains TF, mark that
	 * it was not "us" (the debugger) that set it.
	 * If not, make sure it stays set if we had.
	 */
	if (value & X86_EFLAGS_TF)
		clear_tsk_thread_flag(task, TIF_FORCED_TF);
	else if (test_tsk_thread_flag(task, TIF_FORCED_TF))
		value |= X86_EFLAGS_TF;

	regs->flags = (regs->flags & ~FLAG_MASK) | (value & FLAG_MASK);

	return 0;
}

static int putreg(struct task_struct *child,
		  unsigned long offset, unsigned long value)
{
	switch (offset) {
	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ds):
	case offsetof(struct user_regs_struct, es):
	case offsetof(struct user_regs_struct, fs):
	case offsetof(struct user_regs_struct, gs):
	case offsetof(struct user_regs_struct, ss):
		return set_segment_reg(child, offset, value);

	case offsetof(struct user_regs_struct, flags):
		return set_flags(child, value);

#ifdef CONFIG_X86_64
	case offsetof(struct user_regs_struct,fs_base):
		if (value >= TASK_SIZE_OF(child))
			return -EIO;
		/*
		 * When changing the segment base, use do_arch_prctl
		 * to set either thread.fs or thread.fsindex and the
		 * corresponding GDT slot.
		 */
		if (child->thread.fs != value)
			return do_arch_prctl(child, ARCH_SET_FS, value);
		return 0;
	case offsetof(struct user_regs_struct,gs_base):
		/*
		 * Exactly the same here as the %fs handling above.
		 */
		if (value >= TASK_SIZE_OF(child))
			return -EIO;
		if (child->thread.gs != value)
			return do_arch_prctl(child, ARCH_SET_GS, value);
		return 0;
#endif
	}

	*pt_regs_access(task_pt_regs(child), offset) = value;
	return 0;
}

static unsigned long getreg(struct task_struct *task, unsigned long offset)
{
	switch (offset) {
	case offsetof(struct user_regs_struct, cs):
	case offsetof(struct user_regs_struct, ds):
	case offsetof(struct user_regs_struct, es):
	case offsetof(struct user_regs_struct, fs):
	case offsetof(struct user_regs_struct, gs):
	case offsetof(struct user_regs_struct, ss):
		return get_segment_reg(task, offset);

	case offsetof(struct user_regs_struct, flags):
		return get_flags(task);

#ifdef CONFIG_X86_64
	case offsetof(struct user_regs_struct, fs_base): {
		/*
		 * do_arch_prctl may have used a GDT slot instead of
		 * the MSR.  To userland, it appears the same either
		 * way, except the %fs segment selector might not be 0.
		 */
		unsigned int seg = task->thread.fsindex;
		if (task->thread.fs != 0)
			return task->thread.fs;
		if (task == current)
			asm("movl %%fs,%0" : "=r" (seg));
		if (seg != FS_TLS_SEL)
			return 0;
		return get_desc_base(&task->thread.tls_array[FS_TLS]);
	}
	case offsetof(struct user_regs_struct, gs_base): {
		/*
		 * Exactly the same here as the %fs handling above.
		 */
		unsigned int seg = task->thread.gsindex;
		if (task->thread.gs != 0)
			return task->thread.gs;
		if (task == current)
			asm("movl %%gs,%0" : "=r" (seg));
		if (seg != GS_TLS_SEL)
			return 0;
		return get_desc_base(&task->thread.tls_array[GS_TLS]);
	}
#endif
	}

	return *pt_regs_access(task_pt_regs(task), offset);
}

static int genregs_get(struct task_struct *target,
		       const struct user_regset *regset,
		       unsigned int pos, unsigned int count,
		       void *kbuf, void __user *ubuf)
{
	if (kbuf) {
		unsigned long *k = kbuf;
		while (count >= sizeof(*k)) {
			*k++ = getreg(target, pos);
			count -= sizeof(*k);
			pos += sizeof(*k);
		}
	} else {
		unsigned long __user *u = ubuf;
		while (count >= sizeof(*u)) {
			if (__put_user(getreg(target, pos), u++))
				return -EFAULT;
			count -= sizeof(*u);
			pos += sizeof(*u);
		}
	}

	return 0;
}

static int genregs_set(struct task_struct *target,
		       const struct user_regset *regset,
		       unsigned int pos, unsigned int count,
		       const void *kbuf, const void __user *ubuf)
{
	int ret = 0;
	if (kbuf) {
		const unsigned long *k = kbuf;
		while (count >= sizeof(*k) && !ret) {
			ret = putreg(target, pos, *k++);
			count -= sizeof(*k);
			pos += sizeof(*k);
		}
	} else {
		const unsigned long  __user *u = ubuf;
		while (count >= sizeof(*u) && !ret) {
			unsigned long word;
			ret = __get_user(word, u++);
			if (ret)
				break;
			ret = putreg(target, pos, word);
			count -= sizeof(*u);
			pos += sizeof(*u);
		}
	}
	return ret;
}

static void ptrace_triggered(struct perf_event *bp,
			     struct perf_sample_data *data,
			     struct pt_regs *regs)
{
	int i;
	struct thread_struct *thread = &(current->thread);

	/*
	 * Store in the virtual DR6 register the fact that the breakpoint
	 * was hit so the thread's debugger will see it.
	 */
	for (i = 0; i < HBP_NUM; i++) {
		if (thread->ptrace_bps[i] == bp)
			break;
	}

	thread->debugreg6 |= (DR_TRAP0 << i);
}

/*
 * Walk through every ptrace breakpoints for this thread and
 * build the dr7 value on top of their attributes.
 *
 */
static unsigned long ptrace_get_dr7(struct perf_event *bp[])
{
	int i;
	int dr7 = 0;
	struct arch_hw_breakpoint *info;

	for (i = 0; i < HBP_NUM; i++) {
		if (bp[i] && !bp[i]->attr.disabled) {
			info = counter_arch_bp(bp[i]);
			dr7 |= encode_dr7(i, info->len, info->type);
		}
	}

	return dr7;
}

static int
ptrace_modify_breakpoint(struct perf_event *bp, int len, int type,
			 struct task_struct *tsk, int disabled)
{
	int err;
	int gen_len, gen_type;
	struct perf_event_attr attr;

	/*
	 * We should have at least an inactive breakpoint at this
	 * slot. It means the user is writing dr7 without having
	 * written the address register first
	 */
	if (!bp)
		return -EINVAL;

	err = arch_bp_generic_fields(len, type, &gen_len, &gen_type);
	if (err)
		return err;

	attr = bp->attr;
	attr.bp_len = gen_len;
	attr.bp_type = gen_type;
	attr.disabled = disabled;

	return modify_user_hw_breakpoint(bp, &attr);
}

/*
 * Handle ptrace writes to debug register 7.
 */
static int ptrace_write_dr7(struct task_struct *tsk, unsigned long data)
{
	struct thread_struct *thread = &(tsk->thread);
	unsigned long old_dr7;
	int i, orig_ret = 0, rc = 0;
	int enabled, second_pass = 0;
	unsigned len, type;
	struct perf_event *bp;

	if (ptrace_get_breakpoints(tsk) < 0)
		return -ESRCH;

	data &= ~DR_CONTROL_RESERVED;
	old_dr7 = ptrace_get_dr7(thread->ptrace_bps);
restore:
	/*
	 * Loop through all the hardware breakpoints, making the
	 * appropriate changes to each.
	 */
	for (i = 0; i < HBP_NUM; i++) {
		enabled = decode_dr7(data, i, &len, &type);
		bp = thread->ptrace_bps[i];

		if (!enabled) {
			if (bp) {
				/*
				 * Don't unregister the breakpoints right-away,
				 * unless all register_user_hw_breakpoint()
				 * requests have succeeded. This prevents
				 * any window of opportunity for debug
				 * register grabbing by other users.
				 */
				if (!second_pass)
					continue;

				rc = ptrace_modify_breakpoint(bp, len, type,
							      tsk, 1);
				if (rc)
					break;
			}
			continue;
		}

		rc = ptrace_modify_breakpoint(bp, len, type, tsk, 0);
		if (rc)
			break;
	}
	/*
	 * Make a second pass to free the remaining unused breakpoints
	 * or to restore the original breakpoints if an error occurred.
	 */
	if (!second_pass) {
		second_pass = 1;
		if (rc < 0) {
			orig_ret = rc;
			data = old_dr7;
		}
		goto restore;
	}

	ptrace_put_breakpoints(tsk);

	return ((orig_ret < 0) ? orig_ret : rc);
}

/*
 * Handle PTRACE_PEEKUSR calls for the debug register area.
 */
static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n)
{
	struct thread_struct *thread = &(tsk->thread);
	unsigned long val = 0;

	if (n < HBP_NUM) {
		struct perf_event *bp;

		if (ptrace_get_breakpoints(tsk) < 0)
			return -ESRCH;

		bp = thread->ptrace_bps[n];
		if (!bp)
			val = 0;
		else
			val = bp->hw.info.address;

		ptrace_put_breakpoints(tsk);
	} else if (n == 6) {
		val = thread->debugreg6;
	 } else if (n == 7) {
		val = thread->ptrace_dr7;
	}
	return val;
}

static int ptrace_set_breakpoint_addr(struct task_struct *tsk, int nr,
				      unsigned long addr)
{
	struct perf_event *bp;
	struct thread_struct *t = &tsk->thread;
	struct perf_event_attr attr;
	int err = 0;

	if (ptrace_get_breakpoints(tsk) < 0)
		return -ESRCH;

	if (!t->ptrace_bps[nr]) {
		ptrace_breakpoint_init(&attr);
		/*
		 * Put stub len and type to register (reserve) an inactive but
		 * correct bp
		 */
		attr.bp_addr = addr;
		attr.bp_len = HW_BREAKPOINT_LEN_1;
		attr.bp_type = HW_BREAKPOINT_W;
		attr.disabled = 1;

		bp = register_user_hw_breakpoint(&attr, ptrace_triggered,
						 NULL, tsk);

		/*
		 * CHECKME: the previous code returned -EIO if the addr wasn't
		 * a valid task virtual addr. The new one will return -EINVAL in
		 *  this case.
		 * -EINVAL may be what we want for in-kernel breakpoints users,
		 * but -EIO looks better for ptrace, since we refuse a register
		 * writing for the user. And anyway this is the previous
		 * behaviour.
		 */
		if (IS_ERR(bp)) {
			err = PTR_ERR(bp);
			goto put;
		}

		t->ptrace_bps[nr] = bp;
	} else {
		bp = t->ptrace_bps[nr];

		attr = bp->attr;
		attr.bp_addr = addr;
		err = modify_user_hw_breakpoint(bp, &attr);
	}

put:
	ptrace_put_breakpoints(tsk);
	return err;
}

/*
 * Handle PTRACE_POKEUSR calls for the debug register area.
 */
static int ptrace_set_debugreg(struct task_struct *tsk, int n,
			       unsigned long val)
{
	struct thread_struct *thread = &(tsk->thread);
	int rc = 0;

	/* There are no DR4 or DR5 registers */
	if (n == 4 || n == 5)
		return -EIO;

	if (n == 6) {
		thread->debugreg6 = val;
		goto ret_path;
	}
	if (n < HBP_NUM) {
		rc = ptrace_set_breakpoint_addr(tsk, n, val);
		if (rc)
			return rc;
	}
	/* All that's left is DR7 */
	if (n == 7) {
		rc = ptrace_write_dr7(tsk, val);
		if (!rc)
			thread->ptrace_dr7 = val;
	}

ret_path:
	return rc;
}

/*
 * These access the current or another (stopped) task's io permission
 * bitmap for debugging or core dump.
 */
static int ioperm_active(struct task_struct *target,
			 const struct user_regset *regset)
{
	return target->thread.io_bitmap_max / regset->size;
}

static int ioperm_get(struct task_struct *target,
		      const struct user_regset *regset,
		      unsigned int pos, unsigned int count,
		      void *kbuf, void __user *ubuf)
{
	if (!target->thread.io_bitmap_ptr)
		return -ENXIO;

	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
				   target->thread.io_bitmap_ptr,
				   0, IO_BITMAP_BYTES);
}

/*
 * Called by kernel/ptrace.c when detaching..
 *
 * Make sure the single step bit is not set.
 */
void ptrace_disable(struct task_struct *child)
{
	user_disable_single_step(child);
#ifdef TIF_SYSCALL_EMU
	clear_tsk_thread_flag(child, TIF_SYSCALL_EMU);
#endif
}

#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
static const struct user_regset_view user_x86_32_view; /* Initialized below. */
#endif

long arch_ptrace(struct task_struct *child, long request,
		 unsigned long addr, unsigned long data)
{
	int ret;
	unsigned long __user *datap = (unsigned long __user *)data;

	switch (request) {
	/* read the word at location addr in the USER area. */
	case PTRACE_PEEKUSR: {
		unsigned long tmp;

		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
			break;

		tmp = 0;  /* Default return condition */
		if (addr < sizeof(struct user_regs_struct))
			tmp = getreg(child, addr);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			tmp = ptrace_get_debugreg(child, addr / sizeof(data));
		}
		ret = put_user(tmp, datap);
		break;
	}

	case PTRACE_POKEUSR: /* write the word at location addr in the USER area */
		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user))
			break;

		if (addr < sizeof(struct user_regs_struct))
			ret = putreg(child, addr, data);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			ret = ptrace_set_debugreg(child,
						  addr / sizeof(data), data);
		}
		break;

	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
		return copy_regset_to_user(child,
					   task_user_regset_view(current),
					   REGSET_GENERAL,
					   0, sizeof(struct user_regs_struct),
					   datap);

	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
		return copy_regset_from_user(child,
					     task_user_regset_view(current),
					     REGSET_GENERAL,
					     0, sizeof(struct user_regs_struct),
					     datap);

	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
		return copy_regset_to_user(child,
					   task_user_regset_view(current),
					   REGSET_FP,
					   0, sizeof(struct user_i387_struct),
					   datap);

	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
		return copy_regset_from_user(child,
					     task_user_regset_view(current),
					     REGSET_FP,
					     0, sizeof(struct user_i387_struct),
					     datap);

#ifdef CONFIG_X86_32
	case PTRACE_GETFPXREGS:	/* Get the child extended FPU state. */
		return copy_regset_to_user(child, &user_x86_32_view,
					   REGSET_XFP,
					   0, sizeof(struct user_fxsr_struct),
					   datap) ? -EIO : 0;

	case PTRACE_SETFPXREGS:	/* Set the child extended FPU state. */
		return copy_regset_from_user(child, &user_x86_32_view,
					     REGSET_XFP,
					     0, sizeof(struct user_fxsr_struct),
					     datap) ? -EIO : 0;
#endif

#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
	case PTRACE_GET_THREAD_AREA:
		if ((int) addr < 0)
			return -EIO;
		ret = do_get_thread_area(child, addr,
					(struct user_desc __user *)data);
		break;

	case PTRACE_SET_THREAD_AREA:
		if ((int) addr < 0)
			return -EIO;
		ret = do_set_thread_area(child, addr,
					(struct user_desc __user *)data, 0);
		break;
#endif

#ifdef CONFIG_X86_64
		/* normal 64bit interface to access TLS data.
		   Works just like arch_prctl, except that the arguments
		   are reversed. */
	case PTRACE_ARCH_PRCTL:
		ret = do_arch_prctl(child, data, addr);
		break;
#endif

	default:
		ret = ptrace_request(child, request, addr, data);
		break;
	}

	return ret;
}

#ifdef CONFIG_IA32_EMULATION

#include <linux/compat.h>
#include <linux/syscalls.h>
#include <asm/ia32.h>
#include <asm/user32.h>

#define R32(l,q)							\
	case offsetof(struct user32, regs.l):				\
		regs->q = value; break

#define SEG32(rs)							\
	case offsetof(struct user32, regs.rs):				\
		return set_segment_reg(child,				\
				       offsetof(struct user_regs_struct, rs), \
				       value);				\
		break

static int putreg32(struct task_struct *child, unsigned regno, u32 value)
{
	struct pt_regs *regs = task_pt_regs(child);

	switch (regno) {

	SEG32(cs);
	SEG32(ds);
	SEG32(es);
	SEG32(fs);
	SEG32(gs);
	SEG32(ss);

	R32(ebx, bx);
	R32(ecx, cx);
	R32(edx, dx);
	R32(edi, di);
	R32(esi, si);
	R32(ebp, bp);
	R32(eax, ax);
	R32(eip, ip);
	R32(esp, sp);

	case offsetof(struct user32, regs.orig_eax):
		/*
		 * A 32-bit debugger setting orig_eax means to restore
		 * the state of the task restarting a 32-bit syscall.
		 * Make sure we interpret the -ERESTART* codes correctly
		 * in case the task is not actually still sitting at the
		 * exit from a 32-bit syscall with TS_COMPAT still set.
		 */
		regs->orig_ax = value;
		if (syscall_get_nr(child, regs) >= 0)
			task_thread_info(child)->status |= TS_COMPAT;
		break;

	case offsetof(struct user32, regs.eflags):
		return set_flags(child, value);

	case offsetof(struct user32, u_debugreg[0]) ...
		offsetof(struct user32, u_debugreg[7]):
		regno -= offsetof(struct user32, u_debugreg[0]);
		return ptrace_set_debugreg(child, regno / 4, value);

	default:
		if (regno > sizeof(struct user32) || (regno & 3))
			return -EIO;

		/*
		 * Other dummy fields in the virtual user structure
		 * are ignored
		 */
		break;
	}
	return 0;
}

#undef R32
#undef SEG32

#define R32(l,q)							\
	case offsetof(struct user32, regs.l):				\
		*val = regs->q; break

#define SEG32(rs)							\
	case offsetof(struct user32, regs.rs):				\
		*val = get_segment_reg(child,				\
				       offsetof(struct user_regs_struct, rs)); \
		break

static int getreg32(struct task_struct *child, unsigned regno, u32 *val)
{
	struct pt_regs *regs = task_pt_regs(child);

	switch (regno) {

	SEG32(ds);
	SEG32(es);
	SEG32(fs);
	SEG32(gs);

	R32(cs, cs);
	R32(ss, ss);
	R32(ebx, bx);
	R32(ecx, cx);
	R32(edx, dx);
	R32(edi, di);
	R32(esi, si);
	R32(ebp, bp);
	R32(eax, ax);
	R32(orig_eax, orig_ax);
	R32(eip, ip);
	R32(esp, sp);

	case offsetof(struct user32, regs.eflags):
		*val = get_flags(child);
		break;

	case offsetof(struct user32, u_debugreg[0]) ...
		offsetof(struct user32, u_debugreg[7]):
		regno -= offsetof(struct user32, u_debugreg[0]);
		*val = ptrace_get_debugreg(child, regno / 4);
		break;

	default:
		if (regno > sizeof(struct user32) || (regno & 3))
			return -EIO;

		/*
		 * Other dummy fields in the virtual user structure
		 * are ignored
		 */
		*val = 0;
		break;
	}
	return 0;
}

#undef R32
#undef SEG32

static int genregs32_get(struct task_struct *target,
			 const struct user_regset *regset,
			 unsigned int pos, unsigned int count,
			 void *kbuf, void __user *ubuf)
{
	if (kbuf) {
		compat_ulong_t *k = kbuf;
		while (count >= sizeof(*k)) {
			getreg32(target, pos, k++);
			count -= sizeof(*k);
			pos += sizeof(*k);
		}
	} else {
		compat_ulong_t __user *u = ubuf;
		while (count >= sizeof(*u)) {
			compat_ulong_t word;
			getreg32(target, pos, &word);
			if (__put_user(word, u++))
				return -EFAULT;
			count -= sizeof(*u);
			pos += sizeof(*u);
		}
	}

	return 0;
}

static int genregs32_set(struct task_struct *target,
			 const struct user_regset *regset,
			 unsigned int pos, unsigned int count,
			 const void *kbuf, const void __user *ubuf)
{
	int ret = 0;
	if (kbuf) {
		const compat_ulong_t *k = kbuf;
		while (count >= sizeof(*k) && !ret) {
			ret = putreg32(target, pos, *k++);
			count -= sizeof(*k);
			pos += sizeof(*k);
		}
	} else {
		const compat_ulong_t __user *u = ubuf;
		while (count >= sizeof(*u) && !ret) {
			compat_ulong_t word;
			ret = __get_user(word, u++);
			if (ret)
				break;
			ret = putreg32(target, pos, word);
			count -= sizeof(*u);
			pos += sizeof(*u);
		}
	}
	return ret;
}

#ifdef CONFIG_X86_X32_ABI
static long x32_arch_ptrace(struct task_struct *child,
			    compat_long_t request, compat_ulong_t caddr,
			    compat_ulong_t cdata)
{
	unsigned long addr = caddr;
	unsigned long data = cdata;
	void __user *datap = compat_ptr(data);
	int ret;

	switch (request) {
	/* Read 32bits at location addr in the USER area.  Only allow
	   to return the lower 32bits of segment and debug registers.  */
	case PTRACE_PEEKUSR: {
		u32 tmp;

		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
		    addr < offsetof(struct user_regs_struct, cs))
			break;

		tmp = 0;  /* Default return condition */
		if (addr < sizeof(struct user_regs_struct))
			tmp = getreg(child, addr);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			tmp = ptrace_get_debugreg(child, addr / sizeof(data));
		}
		ret = put_user(tmp, (__u32 __user *)datap);
		break;
	}

	/* Write the word at location addr in the USER area.  Only allow
	   to update segment and debug registers with the upper 32bits
	   zero-extended. */
	case PTRACE_POKEUSR:
		ret = -EIO;
		if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
		    addr < offsetof(struct user_regs_struct, cs))
			break;

		if (addr < sizeof(struct user_regs_struct))
			ret = putreg(child, addr, data);
		else if (addr >= offsetof(struct user, u_debugreg[0]) &&
			 addr <= offsetof(struct user, u_debugreg[7])) {
			addr -= offsetof(struct user, u_debugreg[0]);
			ret = ptrace_set_debugreg(child,
						  addr / sizeof(data), data);
		}
		break;

	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
		return copy_regset_to_user(child,
					   task_user_regset_view(current),
					   REGSET_GENERAL,
					   0, sizeof(struct user_regs_struct),
					   datap);

	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
		return copy_regset_from_user(child,
					     task_user_regset_view(current),
					     REGSET_GENERAL,
					     0, sizeof(struct user_regs_struct),
					     datap);

	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
		return copy_regset_to_user(child,
					   task_user_regset_view(current),
					   REGSET_FP,
					   0, sizeof(struct user_i387_struct),
					   datap);

	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
		return copy_regset_from_user(child,
					     task_user_regset_view(current),
					     REGSET_FP,
					     0, sizeof(struct user_i387_struct),
					     datap);

	default:
		return compat_ptrace_request(child, request, addr, data);
	}

	return ret;
}
#endif

long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
			compat_ulong_t caddr, compat_ulong_t cdata)
{
	unsigned long addr = caddr;
	unsigned long data = cdata;
	void __user *datap = compat_ptr(data);
	int ret;
	__u32 val;

#ifdef CONFIG_X86_X32_ABI
	if (!is_ia32_task())
		return x32_arch_ptrace(child, request, caddr, cdata);
#endif

	switch (request) {
	case PTRACE_PEEKUSR:
		ret = getreg32(child, addr, &val);
		if (ret == 0)
			ret = put_user(val, (__u32 __user *)datap);
		break;

	case PTRACE_POKEUSR:
		ret = putreg32(child, addr, data);
		break;

	case PTRACE_GETREGS:	/* Get all gp regs from the child. */
		return copy_regset_to_user(child, &user_x86_32_view,
					   REGSET_GENERAL,
					   0, sizeof(struct user_regs_struct32),
					   datap);

	case PTRACE_SETREGS:	/* Set all gp regs in the child. */
		return copy_regset_from_user(child, &user_x86_32_view,
					     REGSET_GENERAL, 0,
					     sizeof(struct user_regs_struct32),
					     datap);

	case PTRACE_GETFPREGS:	/* Get the child FPU state. */
		return copy_regset_to_user(child, &user_x86_32_view,
					   REGSET_FP, 0,
					   sizeof(struct user_i387_ia32_struct),
					   datap);

	case PTRACE_SETFPREGS:	/* Set the child FPU state. */
		return copy_regset_from_user(
			child, &user_x86_32_view, REGSET_FP,
			0, sizeof(struct user_i387_ia32_struct), datap);

	case PTRACE_GETFPXREGS:	/* Get the child extended FPU state. */
		return copy_regset_to_user(child, &user_x86_32_view,
					   REGSET_XFP, 0,
					   sizeof(struct user32_fxsr_struct),
					   datap);

	case PTRACE_SETFPXREGS:	/* Set the child extended FPU state. */
		return copy_regset_from_user(child, &user_x86_32_view,
					     REGSET_XFP, 0,
					     sizeof(struct user32_fxsr_struct),
					     datap);

	case PTRACE_GET_THREAD_AREA:
	case PTRACE_SET_THREAD_AREA:
		return arch_ptrace(child, request, addr, data);

	default:
		return compat_ptrace_request(child, request, addr, data);
	}

	return ret;
}

#endif	/* CONFIG_IA32_EMULATION */

#ifdef CONFIG_X86_64

static struct user_regset x86_64_regsets[] __read_mostly = {
	[REGSET_GENERAL] = {
		.core_note_type = NT_PRSTATUS,
		.n = sizeof(struct user_regs_struct) / sizeof(long),
		.size = sizeof(long), .align = sizeof(long),
		.get = genregs_get, .set = genregs_set
	},
	[REGSET_FP] = {
		.core_note_type = NT_PRFPREG,
		.n = sizeof(struct user_i387_struct) / sizeof(long),
		.size = sizeof(long), .align = sizeof(long),
		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
	},
	[REGSET_XSTATE] = {
		.core_note_type = NT_X86_XSTATE,
		.size = sizeof(u64), .align = sizeof(u64),
		.active = xstateregs_active, .get = xstateregs_get,
		.set = xstateregs_set
	},
	[REGSET_IOPERM64] = {
		.core_note_type = NT_386_IOPERM,
		.n = IO_BITMAP_LONGS,
		.size = sizeof(long), .align = sizeof(long),
		.active = ioperm_active, .get = ioperm_get
	},
};

static const struct user_regset_view user_x86_64_view = {
	.name = "x86_64", .e_machine = EM_X86_64,
	.regsets = x86_64_regsets, .n = ARRAY_SIZE(x86_64_regsets)
};

#else  /* CONFIG_X86_32 */

#define user_regs_struct32	user_regs_struct
#define genregs32_get		genregs_get
#define genregs32_set		genregs_set

#define user_i387_ia32_struct	user_i387_struct
#define user32_fxsr_struct	user_fxsr_struct

#endif	/* CONFIG_X86_64 */

#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
static struct user_regset x86_32_regsets[] __read_mostly = {
	[REGSET_GENERAL] = {
		.core_note_type = NT_PRSTATUS,
		.n = sizeof(struct user_regs_struct32) / sizeof(u32),
		.size = sizeof(u32), .align = sizeof(u32),
		.get = genregs32_get, .set = genregs32_set
	},
	[REGSET_FP] = {
		.core_note_type = NT_PRFPREG,
		.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
		.size = sizeof(u32), .align = sizeof(u32),
		.active = fpregs_active, .get = fpregs_get, .set = fpregs_set
	},
	[REGSET_XFP] = {
		.core_note_type = NT_PRXFPREG,
		.n = sizeof(struct user32_fxsr_struct) / sizeof(u32),
		.size = sizeof(u32), .align = sizeof(u32),
		.active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set
	},
	[REGSET_XSTATE] = {
		.core_note_type = NT_X86_XSTATE,
		.size = sizeof(u64), .align = sizeof(u64),
		.active = xstateregs_active, .get = xstateregs_get,
		.set = xstateregs_set
	},
	[REGSET_TLS] = {
		.core_note_type = NT_386_TLS,
		.n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN,
		.size = sizeof(struct user_desc),
		.align = sizeof(struct user_desc),
		.active = regset_tls_active,
		.get = regset_tls_get, .set = regset_tls_set
	},
	[REGSET_IOPERM32] = {
		.core_note_type = NT_386_IOPERM,
		.n = IO_BITMAP_BYTES / sizeof(u32),
		.size = sizeof(u32), .align = sizeof(u32),
		.active = ioperm_active, .get = ioperm_get
	},
};

static const struct user_regset_view user_x86_32_view = {
	.name = "i386", .e_machine = EM_386,
	.regsets = x86_32_regsets, .n = ARRAY_SIZE(x86_32_regsets)
};
#endif

/*
 * This represents bytes 464..511 in the memory layout exported through
 * the REGSET_XSTATE interface.
 */
u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];

void update_regset_xstate_info(unsigned int size, u64 xstate_mask)
{
#ifdef CONFIG_X86_64
	x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64);
#endif
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
	x86_32_regsets[REGSET_XSTATE].n = size / sizeof(u64);
#endif
	xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask;
}

const struct user_regset_view *task_user_regset_view(struct task_struct *task)
{
#ifdef CONFIG_IA32_EMULATION
	if (test_tsk_thread_flag(task, TIF_IA32))
#endif
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
		return &user_x86_32_view;
#endif
#ifdef CONFIG_X86_64
	return &user_x86_64_view;
#endif
}

static void fill_sigtrap_info(struct task_struct *tsk,
				struct pt_regs *regs,
				int error_code, int si_code,
				struct siginfo *info)
{
	tsk->thread.trap_nr = X86_TRAP_DB;
	tsk->thread.error_code = error_code;

	memset(info, 0, sizeof(*info));
	info->si_signo = SIGTRAP;
	info->si_code = si_code;
	info->si_addr = user_mode_vm(regs) ? (void __user *)regs->ip : NULL;
}

void user_single_step_siginfo(struct task_struct *tsk,
				struct pt_regs *regs,
				struct siginfo *info)
{
	fill_sigtrap_info(tsk, regs, 0, TRAP_BRKPT, info);
}

void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
					 int error_code, int si_code)
{
	struct siginfo info;

	fill_sigtrap_info(tsk, regs, error_code, si_code, &info);
	/* Send us the fake SIGTRAP */
	force_sig_info(SIGTRAP, &info, tsk);
}


#ifdef CONFIG_X86_32
# define IS_IA32	1
#elif defined CONFIG_IA32_EMULATION
# define IS_IA32	is_compat_task()
#else
# define IS_IA32	0
#endif

/*
 * We must return the syscall number to actually look up in the table.
 * This can be -1L to skip running any syscall at all.
 */
long syscall_trace_enter(struct pt_regs *regs)
{
	long ret = 0;

	/*
	 * If we stepped into a sysenter/syscall insn, it trapped in
	 * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
	 * If user-mode had set TF itself, then it's still clear from
	 * do_debug() and we need to set it again to restore the user
	 * state.  If we entered on the slow path, TF was already set.
	 */
	if (test_thread_flag(TIF_SINGLESTEP))
		regs->flags |= X86_EFLAGS_TF;

	/* do the secure computing check first */
	secure_computing(regs->orig_ax);

	if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
		ret = -1L;

	if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
	    tracehook_report_syscall_entry(regs))
		ret = -1L;

	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
		trace_sys_enter(regs, regs->orig_ax);

	if (IS_IA32)
		audit_syscall_entry(AUDIT_ARCH_I386,
				    regs->orig_ax,
				    regs->bx, regs->cx,
				    regs->dx, regs->si);
#ifdef CONFIG_X86_64
	else
		audit_syscall_entry(AUDIT_ARCH_X86_64,
				    regs->orig_ax,
				    regs->di, regs->si,
				    regs->dx, regs->r10);
#endif

	return ret ?: regs->orig_ax;
}

void syscall_trace_leave(struct pt_regs *regs)
{
	bool step;

	audit_syscall_exit(regs);

	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
		trace_sys_exit(regs, regs->ax);

	/*
	 * If TIF_SYSCALL_EMU is set, we only get here because of
	 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
	 * We already reported this syscall instruction in
	 * syscall_trace_enter().
	 */
	step = unlikely(test_thread_flag(TIF_SINGLESTEP)) &&
			!test_thread_flag(TIF_SYSCALL_EMU);
	if (step || test_thread_flag(TIF_SYSCALL_TRACE))
		tracehook_report_syscall_exit(regs, step);
}