Linux preempt-rt

Check our new training course

Real-Time Linux with PREEMPT_RT

Check our new training course
with Creative Commons CC-BY-SA
lecture and lab materials

Bootlin logo

Elixir Cross Referencer

   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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  Kernel Probes (KProbes)
 *
 * Copyright (C) IBM Corporation, 2002, 2004
 *
 * 2002-Oct	Created by Vamsi Krishna S <vamsi_krishna@in.ibm.com> Kernel
 *		Probes initial implementation ( includes contributions from
 *		Rusty Russell).
 * 2004-July	Suparna Bhattacharya <suparna@in.ibm.com> added jumper probes
 *		interface to access function arguments.
 * 2004-Oct	Jim Keniston <jkenisto@us.ibm.com> and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> adapted for x86_64 from i386.
 * 2005-Mar	Roland McGrath <roland@redhat.com>
 *		Fixed to handle %rip-relative addressing mode correctly.
 * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
 *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
 *		<prasanna@in.ibm.com> added function-return probes.
 * 2005-May	Rusty Lynch <rusty.lynch@intel.com>
 *		Added function return probes functionality
 * 2006-Feb	Masami Hiramatsu <hiramatu@sdl.hitachi.co.jp> added
 *		kprobe-booster and kretprobe-booster for i386.
 * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com> added kprobe-booster
 *		and kretprobe-booster for x86-64
 * 2007-Dec	Masami Hiramatsu <mhiramat@redhat.com>, Arjan van de Ven
 *		<arjan@infradead.org> and Jim Keniston <jkenisto@us.ibm.com>
 *		unified x86 kprobes code.
 */
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/hardirq.h>
#include <linux/preempt.h>
#include <linux/sched/debug.h>
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
#include <linux/kasan.h>
#include <linux/moduleloader.h>
#include <linux/objtool.h>
#include <linux/vmalloc.h>
#include <linux/pgtable.h>

#include <asm/text-patching.h>
#include <asm/cacheflush.h>
#include <asm/desc.h>
#include <linux/uaccess.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
#include <asm/set_memory.h>
#include <asm/ibt.h>

#include "common.h"

DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);

#define stack_addr(regs) ((unsigned long *)regs->sp)

#define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
	  (b8##UL << 0x8)|(b9##UL << 0x9)|(ba##UL << 0xa)|(bb##UL << 0xb) |   \
	  (bc##UL << 0xc)|(bd##UL << 0xd)|(be##UL << 0xe)|(bf##UL << 0xf))    \
	 << (row % 32))
	/*
	 * Undefined/reserved opcodes, conditional jump, Opcode Extension
	 * Groups, and some special opcodes can not boost.
	 * This is non-const and volatile to keep gcc from statically
	 * optimizing it out, as variable_test_bit makes gcc think only
	 * *(unsigned long*) is used.
	 */
static volatile u32 twobyte_is_boostable[256 / 32] = {
	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
	/*      ----------------------------------------------          */
	W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
	W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1) , /* 10 */
	W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
	W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
	W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
	W(0x50, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 50 */
	W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1) | /* 60 */
	W(0x70, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
	W(0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 80 */
	W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
	W(0xa0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* a0 */
	W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1) , /* b0 */
	W(0xc0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
	W(0xd0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) , /* d0 */
	W(0xe0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1) | /* e0 */
	W(0xf0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0)   /* f0 */
	/*      -----------------------------------------------         */
	/*      0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f          */
};
#undef W

struct kretprobe_blackpoint kretprobe_blacklist[] = {
	{"__switch_to", }, /* This function switches only current task, but
			      doesn't switch kernel stack.*/
	{NULL, NULL}	/* Terminator */
};

const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist);

static nokprobe_inline void
__synthesize_relative_insn(void *dest, void *from, void *to, u8 op)
{
	struct __arch_relative_insn {
		u8 op;
		s32 raddr;
	} __packed *insn;

	insn = (struct __arch_relative_insn *)dest;
	insn->raddr = (s32)((long)(to) - ((long)(from) + 5));
	insn->op = op;
}

/* Insert a jump instruction at address 'from', which jumps to address 'to'.*/
void synthesize_reljump(void *dest, void *from, void *to)
{
	__synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE);
}
NOKPROBE_SYMBOL(synthesize_reljump);

/* Insert a call instruction at address 'from', which calls address 'to'.*/
void synthesize_relcall(void *dest, void *from, void *to)
{
	__synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE);
}
NOKPROBE_SYMBOL(synthesize_relcall);

/*
 * Returns non-zero if INSN is boostable.
 * RIP relative instructions are adjusted at copying time in 64 bits mode
 */
int can_boost(struct insn *insn, void *addr)
{
	kprobe_opcode_t opcode;
	insn_byte_t prefix;
	int i;

	if (search_exception_tables((unsigned long)addr))
		return 0;	/* Page fault may occur on this address. */

	/* 2nd-byte opcode */
	if (insn->opcode.nbytes == 2)
		return test_bit(insn->opcode.bytes[1],
				(unsigned long *)twobyte_is_boostable);

	if (insn->opcode.nbytes != 1)
		return 0;

	for_each_insn_prefix(insn, i, prefix) {
		insn_attr_t attr;

		attr = inat_get_opcode_attribute(prefix);
		/* Can't boost Address-size override prefix and CS override prefix */
		if (prefix == 0x2e || inat_is_address_size_prefix(attr))
			return 0;
	}

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

	switch (opcode) {
	case 0x62:		/* bound */
	case 0x70 ... 0x7f:	/* Conditional jumps */
	case 0x9a:		/* Call far */
	case 0xc0 ... 0xc1:	/* Grp2 */
	case 0xcc ... 0xce:	/* software exceptions */
	case 0xd0 ... 0xd3:	/* Grp2 */
	case 0xd6:		/* (UD) */
	case 0xd8 ... 0xdf:	/* ESC */
	case 0xe0 ... 0xe3:	/* LOOP*, JCXZ */
	case 0xe8 ... 0xe9:	/* near Call, JMP */
	case 0xeb:		/* Short JMP */
	case 0xf0 ... 0xf4:	/* LOCK/REP, HLT */
	case 0xf6 ... 0xf7:	/* Grp3 */
	case 0xfe:		/* Grp4 */
		/* ... are not boostable */
		return 0;
	case 0xff:		/* Grp5 */
		/* Only indirect jmp is boostable */
		return X86_MODRM_REG(insn->modrm.bytes[0]) == 4;
	default:
		return 1;
	}
}

static unsigned long
__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
	struct kprobe *kp;
	bool faddr;

	kp = get_kprobe((void *)addr);
	faddr = ftrace_location(addr) == addr;
	/*
	 * Use the current code if it is not modified by Kprobe
	 * and it cannot be modified by ftrace.
	 */
	if (!kp && !faddr)
		return addr;

	/*
	 * Basically, kp->ainsn.insn has an original instruction.
	 * However, RIP-relative instruction can not do single-stepping
	 * at different place, __copy_instruction() tweaks the displacement of
	 * that instruction. In that case, we can't recover the instruction
	 * from the kp->ainsn.insn.
	 *
	 * On the other hand, in case on normal Kprobe, kp->opcode has a copy
	 * of the first byte of the probed instruction, which is overwritten
	 * by int3. And the instruction at kp->addr is not modified by kprobes
	 * except for the first byte, we can recover the original instruction
	 * from it and kp->opcode.
	 *
	 * In case of Kprobes using ftrace, we do not have a copy of
	 * the original instruction. In fact, the ftrace location might
	 * be modified at anytime and even could be in an inconsistent state.
	 * Fortunately, we know that the original code is the ideal 5-byte
	 * long NOP.
	 */
	if (copy_from_kernel_nofault(buf, (void *)addr,
		MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
		return 0UL;

	if (faddr)
		memcpy(buf, x86_nops[5], 5);
	else
		buf[0] = kp->opcode;
	return (unsigned long)buf;
}

/*
 * Recover the probed instruction at addr for further analysis.
 * Caller must lock kprobes by kprobe_mutex, or disable preemption
 * for preventing to release referencing kprobes.
 * Returns zero if the instruction can not get recovered (or access failed).
 */
unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
{
	unsigned long __addr;

	__addr = __recover_optprobed_insn(buf, addr);
	if (__addr != addr)
		return __addr;

	return __recover_probed_insn(buf, addr);
}

/* Check if paddr is at an instruction boundary */
static int can_probe(unsigned long paddr)
{
	unsigned long addr, __addr, offset = 0;
	struct insn insn;
	kprobe_opcode_t buf[MAX_INSN_SIZE];

	if (!kallsyms_lookup_size_offset(paddr, NULL, &offset))
		return 0;

	/* Decode instructions */
	addr = paddr - offset;
	while (addr < paddr) {
		int ret;

		/*
		 * Check if the instruction has been modified by another
		 * kprobe, in which case we replace the breakpoint by the
		 * original instruction in our buffer.
		 * Also, jump optimization will change the breakpoint to
		 * relative-jump. Since the relative-jump itself is
		 * normally used, we just go through if there is no kprobe.
		 */
		__addr = recover_probed_instruction(buf, addr);
		if (!__addr)
			return 0;

		ret = insn_decode_kernel(&insn, (void *)__addr);
		if (ret < 0)
			return 0;

		/*
		 * Another debugging subsystem might insert this breakpoint.
		 * In that case, we can't recover it.
		 */
		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
			return 0;
		addr += insn.length;
	}

	return (addr == paddr);
}

/* If x86 supports IBT (ENDBR) it must be skipped. */
kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
					 bool *on_func_entry)
{
	if (is_endbr(*(u32 *)addr)) {
		*on_func_entry = !offset || offset == 4;
		if (*on_func_entry)
			offset = 4;

	} else {
		*on_func_entry = !offset;
	}

	return (kprobe_opcode_t *)(addr + offset);
}

/*
 * Copy an instruction with recovering modified instruction by kprobes
 * and adjust the displacement if the instruction uses the %rip-relative
 * addressing mode. Note that since @real will be the final place of copied
 * instruction, displacement must be adjust by @real, not @dest.
 * This returns the length of copied instruction, or 0 if it has an error.
 */
int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
{
	kprobe_opcode_t buf[MAX_INSN_SIZE];
	unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src);
	int ret;

	if (!recovered_insn || !insn)
		return 0;

	/* This can access kernel text if given address is not recovered */
	if (copy_from_kernel_nofault(dest, (void *)recovered_insn,
			MAX_INSN_SIZE))
		return 0;

	ret = insn_decode_kernel(insn, dest);
	if (ret < 0)
		return 0;

	/* We can not probe force emulate prefixed instruction */
	if (insn_has_emulate_prefix(insn))
		return 0;

	/* Another subsystem puts a breakpoint, failed to recover */
	if (insn->opcode.bytes[0] == INT3_INSN_OPCODE)
		return 0;

	/* We should not singlestep on the exception masking instructions */
	if (insn_masking_exception(insn))
		return 0;

#ifdef CONFIG_X86_64
	/* Only x86_64 has RIP relative instructions */
	if (insn_rip_relative(insn)) {
		s64 newdisp;
		u8 *disp;
		/*
		 * The copied instruction uses the %rip-relative addressing
		 * mode.  Adjust the displacement for the difference between
		 * the original location of this instruction and the location
		 * of the copy that will actually be run.  The tricky bit here
		 * is making sure that the sign extension happens correctly in
		 * this calculation, since we need a signed 32-bit result to
		 * be sign-extended to 64 bits when it's added to the %rip
		 * value and yield the same 64-bit result that the sign-
		 * extension of the original signed 32-bit displacement would
		 * have given.
		 */
		newdisp = (u8 *) src + (s64) insn->displacement.value
			  - (u8 *) real;
		if ((s64) (s32) newdisp != newdisp) {
			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
			return 0;
		}
		disp = (u8 *) dest + insn_offset_displacement(insn);
		*(s32 *) disp = (s32) newdisp;
	}
#endif
	return insn->length;
}

/* Prepare reljump or int3 right after instruction */
static int prepare_singlestep(kprobe_opcode_t *buf, struct kprobe *p,
			      struct insn *insn)
{
	int len = insn->length;

	if (!IS_ENABLED(CONFIG_PREEMPTION) &&
	    !p->post_handler && can_boost(insn, p->addr) &&
	    MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) {
		/*
		 * These instructions can be executed directly if it
		 * jumps back to correct address.
		 */
		synthesize_reljump(buf + len, p->ainsn.insn + len,
				   p->addr + insn->length);
		len += JMP32_INSN_SIZE;
		p->ainsn.boostable = 1;
	} else {
		/* Otherwise, put an int3 for trapping singlestep */
		if (MAX_INSN_SIZE - len < INT3_INSN_SIZE)
			return -ENOSPC;

		buf[len] = INT3_INSN_OPCODE;
		len += INT3_INSN_SIZE;
	}

	return len;
}

/* Make page to RO mode when allocate it */
void *alloc_insn_page(void)
{
	void *page;

	page = module_alloc(PAGE_SIZE);
	if (!page)
		return NULL;

	set_vm_flush_reset_perms(page);
	/*
	 * First make the page read-only, and only then make it executable to
	 * prevent it from being W+X in between.
	 */
	set_memory_ro((unsigned long)page, 1);

	/*
	 * TODO: Once additional kernel code protection mechanisms are set, ensure
	 * that the page was not maliciously altered and it is still zeroed.
	 */
	set_memory_x((unsigned long)page, 1);

	return page;
}

/* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */

static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs)
{
	switch (p->ainsn.opcode) {
	case 0xfa:	/* cli */
		regs->flags &= ~(X86_EFLAGS_IF);
		break;
	case 0xfb:	/* sti */
		regs->flags |= X86_EFLAGS_IF;
		break;
	case 0x9c:	/* pushf */
		int3_emulate_push(regs, regs->flags);
		break;
	case 0x9d:	/* popf */
		regs->flags = int3_emulate_pop(regs);
		break;
	}
	regs->ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
}
NOKPROBE_SYMBOL(kprobe_emulate_ifmodifiers);

static void kprobe_emulate_ret(struct kprobe *p, struct pt_regs *regs)
{
	int3_emulate_ret(regs);
}
NOKPROBE_SYMBOL(kprobe_emulate_ret);

static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs)
{
	unsigned long func = regs->ip - INT3_INSN_SIZE + p->ainsn.size;

	func += p->ainsn.rel32;
	int3_emulate_call(regs, func);
}
NOKPROBE_SYMBOL(kprobe_emulate_call);

static nokprobe_inline
void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond)
{
	unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;

	if (cond)
		ip += p->ainsn.rel32;
	int3_emulate_jmp(regs, ip);
}

static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs)
{
	__kprobe_emulate_jmp(p, regs, true);
}
NOKPROBE_SYMBOL(kprobe_emulate_jmp);

static const unsigned long jcc_mask[6] = {
	[0] = X86_EFLAGS_OF,
	[1] = X86_EFLAGS_CF,
	[2] = X86_EFLAGS_ZF,
	[3] = X86_EFLAGS_CF | X86_EFLAGS_ZF,
	[4] = X86_EFLAGS_SF,
	[5] = X86_EFLAGS_PF,
};

static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
{
	bool invert = p->ainsn.jcc.type & 1;
	bool match;

	if (p->ainsn.jcc.type < 0xc) {
		match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1];
	} else {
		match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
			((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
		if (p->ainsn.jcc.type >= 0xe)
			match = match && (regs->flags & X86_EFLAGS_ZF);
	}
	__kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
}
NOKPROBE_SYMBOL(kprobe_emulate_jcc);

static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs)
{
	bool match;

	if (p->ainsn.loop.type != 3) {	/* LOOP* */
		if (p->ainsn.loop.asize == 32)
			match = ((*(u32 *)&regs->cx)--) != 0;
#ifdef CONFIG_X86_64
		else if (p->ainsn.loop.asize == 64)
			match = ((*(u64 *)&regs->cx)--) != 0;
#endif
		else
			match = ((*(u16 *)&regs->cx)--) != 0;
	} else {			/* JCXZ */
		if (p->ainsn.loop.asize == 32)
			match = *(u32 *)(&regs->cx) == 0;
#ifdef CONFIG_X86_64
		else if (p->ainsn.loop.asize == 64)
			match = *(u64 *)(&regs->cx) == 0;
#endif
		else
			match = *(u16 *)(&regs->cx) == 0;
	}

	if (p->ainsn.loop.type == 0)	/* LOOPNE */
		match = match && !(regs->flags & X86_EFLAGS_ZF);
	else if (p->ainsn.loop.type == 1)	/* LOOPE */
		match = match && (regs->flags & X86_EFLAGS_ZF);

	__kprobe_emulate_jmp(p, regs, match);
}
NOKPROBE_SYMBOL(kprobe_emulate_loop);

static const int addrmode_regoffs[] = {
	offsetof(struct pt_regs, ax),
	offsetof(struct pt_regs, cx),
	offsetof(struct pt_regs, dx),
	offsetof(struct pt_regs, bx),
	offsetof(struct pt_regs, sp),
	offsetof(struct pt_regs, bp),
	offsetof(struct pt_regs, si),
	offsetof(struct pt_regs, di),
#ifdef CONFIG_X86_64
	offsetof(struct pt_regs, r8),
	offsetof(struct pt_regs, r9),
	offsetof(struct pt_regs, r10),
	offsetof(struct pt_regs, r11),
	offsetof(struct pt_regs, r12),
	offsetof(struct pt_regs, r13),
	offsetof(struct pt_regs, r14),
	offsetof(struct pt_regs, r15),
#endif
};

static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs)
{
	unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];

	int3_emulate_call(regs, regs_get_register(regs, offs));
}
NOKPROBE_SYMBOL(kprobe_emulate_call_indirect);

static void kprobe_emulate_jmp_indirect(struct kprobe *p, struct pt_regs *regs)
{
	unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];

	int3_emulate_jmp(regs, regs_get_register(regs, offs));
}
NOKPROBE_SYMBOL(kprobe_emulate_jmp_indirect);

static int prepare_emulation(struct kprobe *p, struct insn *insn)
{
	insn_byte_t opcode = insn->opcode.bytes[0];

	switch (opcode) {
	case 0xfa:		/* cli */
	case 0xfb:		/* sti */
	case 0x9c:		/* pushfl */
	case 0x9d:		/* popf/popfd */
		/*
		 * IF modifiers must be emulated since it will enable interrupt while
		 * int3 single stepping.
		 */
		p->ainsn.emulate_op = kprobe_emulate_ifmodifiers;
		p->ainsn.opcode = opcode;
		break;
	case 0xc2:	/* ret/lret */
	case 0xc3:
	case 0xca:
	case 0xcb:
		p->ainsn.emulate_op = kprobe_emulate_ret;
		break;
	case 0x9a:	/* far call absolute -- segment is not supported */
	case 0xea:	/* far jmp absolute -- segment is not supported */
	case 0xcc:	/* int3 */
	case 0xcf:	/* iret -- in-kernel IRET is not supported */
		return -EOPNOTSUPP;
		break;
	case 0xe8:	/* near call relative */
		p->ainsn.emulate_op = kprobe_emulate_call;
		if (insn->immediate.nbytes == 2)
			p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
		else
			p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
		break;
	case 0xeb:	/* short jump relative */
	case 0xe9:	/* near jump relative */
		p->ainsn.emulate_op = kprobe_emulate_jmp;
		if (insn->immediate.nbytes == 1)
			p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
		else if (insn->immediate.nbytes == 2)
			p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
		else
			p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
		break;
	case 0x70 ... 0x7f:
		/* 1 byte conditional jump */
		p->ainsn.emulate_op = kprobe_emulate_jcc;
		p->ainsn.jcc.type = opcode & 0xf;
		p->ainsn.rel32 = *(char *)insn->immediate.bytes;
		break;
	case 0x0f:
		opcode = insn->opcode.bytes[1];
		if ((opcode & 0xf0) == 0x80) {
			/* 2 bytes Conditional Jump */
			p->ainsn.emulate_op = kprobe_emulate_jcc;
			p->ainsn.jcc.type = opcode & 0xf;
			if (insn->immediate.nbytes == 2)
				p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
			else
				p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
		} else if (opcode == 0x01 &&
			   X86_MODRM_REG(insn->modrm.bytes[0]) == 0 &&
			   X86_MODRM_MOD(insn->modrm.bytes[0]) == 3) {
			/* VM extensions - not supported */
			return -EOPNOTSUPP;
		}
		break;
	case 0xe0:	/* Loop NZ */
	case 0xe1:	/* Loop */
	case 0xe2:	/* Loop */
	case 0xe3:	/* J*CXZ */
		p->ainsn.emulate_op = kprobe_emulate_loop;
		p->ainsn.loop.type = opcode & 0x3;
		p->ainsn.loop.asize = insn->addr_bytes * 8;
		p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
		break;
	case 0xff:
		/*
		 * Since the 0xff is an extended group opcode, the instruction
		 * is determined by the MOD/RM byte.
		 */
		opcode = insn->modrm.bytes[0];
		if ((opcode & 0x30) == 0x10) {
			if ((opcode & 0x8) == 0x8)
				return -EOPNOTSUPP;	/* far call */
			/* call absolute, indirect */
			p->ainsn.emulate_op = kprobe_emulate_call_indirect;
		} else if ((opcode & 0x30) == 0x20) {
			if ((opcode & 0x8) == 0x8)
				return -EOPNOTSUPP;	/* far jmp */
			/* jmp near absolute indirect */
			p->ainsn.emulate_op = kprobe_emulate_jmp_indirect;
		} else
			break;

		if (insn->addr_bytes != sizeof(unsigned long))
			return -EOPNOTSUPP;	/* Don't support different size */
		if (X86_MODRM_MOD(opcode) != 3)
			return -EOPNOTSUPP;	/* TODO: support memory addressing */

		p->ainsn.indirect.reg = X86_MODRM_RM(opcode);
#ifdef CONFIG_X86_64
		if (X86_REX_B(insn->rex_prefix.value))
			p->ainsn.indirect.reg += 8;
#endif
		break;
	default:
		break;
	}
	p->ainsn.size = insn->length;

	return 0;
}

static int arch_copy_kprobe(struct kprobe *p)
{
	struct insn insn;
	kprobe_opcode_t buf[MAX_INSN_SIZE];
	int ret, len;

	/* Copy an instruction with recovering if other optprobe modifies it.*/
	len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn);
	if (!len)
		return -EINVAL;

	/* Analyze the opcode and setup emulate functions */
	ret = prepare_emulation(p, &insn);
	if (ret < 0)
		return ret;

	/* Add int3 for single-step or booster jmp */
	len = prepare_singlestep(buf, p, &insn);
	if (len < 0)
		return len;

	/* Also, displacement change doesn't affect the first byte */
	p->opcode = buf[0];

	p->ainsn.tp_len = len;
	perf_event_text_poke(p->ainsn.insn, NULL, 0, buf, len);

	/* OK, write back the instruction(s) into ROX insn buffer */
	text_poke(p->ainsn.insn, buf, len);

	return 0;
}

int arch_prepare_kprobe(struct kprobe *p)
{
	int ret;

	if (alternatives_text_reserved(p->addr, p->addr))
		return -EINVAL;

	if (!can_probe((unsigned long)p->addr))
		return -EILSEQ;

	memset(&p->ainsn, 0, sizeof(p->ainsn));

	/* insn: must be on special executable page on x86. */
	p->ainsn.insn = get_insn_slot();
	if (!p->ainsn.insn)
		return -ENOMEM;

	ret = arch_copy_kprobe(p);
	if (ret) {
		free_insn_slot(p->ainsn.insn, 0);
		p->ainsn.insn = NULL;
	}

	return ret;
}

void arch_arm_kprobe(struct kprobe *p)
{
	u8 int3 = INT3_INSN_OPCODE;

	text_poke(p->addr, &int3, 1);
	text_poke_sync();
	perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
}

void arch_disarm_kprobe(struct kprobe *p)
{
	u8 int3 = INT3_INSN_OPCODE;

	perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
	text_poke(p->addr, &p->opcode, 1);
	text_poke_sync();
}

void arch_remove_kprobe(struct kprobe *p)
{
	if (p->ainsn.insn) {
		/* Record the perf event before freeing the slot */
		perf_event_text_poke(p->ainsn.insn, p->ainsn.insn,
				     p->ainsn.tp_len, NULL, 0);
		free_insn_slot(p->ainsn.insn, p->ainsn.boostable);
		p->ainsn.insn = NULL;
	}
}

static nokprobe_inline void
save_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	kcb->prev_kprobe.kp = kprobe_running();
	kcb->prev_kprobe.status = kcb->kprobe_status;
	kcb->prev_kprobe.old_flags = kcb->kprobe_old_flags;
	kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags;
}

static nokprobe_inline void
restore_previous_kprobe(struct kprobe_ctlblk *kcb)
{
	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
	kcb->kprobe_status = kcb->prev_kprobe.status;
	kcb->kprobe_old_flags = kcb->prev_kprobe.old_flags;
	kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags;
}

static nokprobe_inline void
set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
		   struct kprobe_ctlblk *kcb)
{
	__this_cpu_write(current_kprobe, p);
	kcb->kprobe_saved_flags = kcb->kprobe_old_flags
		= (regs->flags & X86_EFLAGS_IF);
}

static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs,
			       struct kprobe_ctlblk *kcb)
{
	if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
		kcb->kprobe_status = KPROBE_HIT_SSDONE;
		cur->post_handler(cur, regs, 0);
	}

	/* Restore back the original saved kprobes variables and continue. */
	if (kcb->kprobe_status == KPROBE_REENTER)
		restore_previous_kprobe(kcb);
	else
		reset_current_kprobe();
}
NOKPROBE_SYMBOL(kprobe_post_process);

static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
			     struct kprobe_ctlblk *kcb, int reenter)
{
	if (setup_detour_execution(p, regs, reenter))
		return;

#if !defined(CONFIG_PREEMPTION)
	if (p->ainsn.boostable) {
		/* Boost up -- we can execute copied instructions directly */
		if (!reenter)
			reset_current_kprobe();
		/*
		 * Reentering boosted probe doesn't reset current_kprobe,
		 * nor set current_kprobe, because it doesn't use single
		 * stepping.
		 */
		regs->ip = (unsigned long)p->ainsn.insn;
		return;
	}
#endif
	if (reenter) {
		save_previous_kprobe(kcb);
		set_current_kprobe(p, regs, kcb);
		kcb->kprobe_status = KPROBE_REENTER;
	} else
		kcb->kprobe_status = KPROBE_HIT_SS;

	if (p->ainsn.emulate_op) {
		p->ainsn.emulate_op(p, regs);
		kprobe_post_process(p, regs, kcb);
		return;
	}

	/* Disable interrupt, and set ip register on trampoline */
	regs->flags &= ~X86_EFLAGS_IF;
	regs->ip = (unsigned long)p->ainsn.insn;
}
NOKPROBE_SYMBOL(setup_singlestep);

/*
 * Called after single-stepping.  p->addr is the address of the
 * instruction whose first byte has been replaced by the "int3"
 * instruction.  To avoid the SMP problems that can occur when we
 * temporarily put back the original opcode to single-step, we
 * single-stepped a copy of the instruction.  The address of this
 * copy is p->ainsn.insn. We also doesn't use trap, but "int3" again
 * right after the copied instruction.
 * Different from the trap single-step, "int3" single-step can not
 * handle the instruction which changes the ip register, e.g. jmp,
 * call, conditional jmp, and the instructions which changes the IF
 * flags because interrupt must be disabled around the single-stepping.
 * Such instructions are software emulated, but others are single-stepped
 * using "int3".
 *
 * When the 2nd "int3" handled, the regs->ip and regs->flags needs to
 * be adjusted, so that we can resume execution on correct code.
 */
static void resume_singlestep(struct kprobe *p, struct pt_regs *regs,
			      struct kprobe_ctlblk *kcb)
{
	unsigned long copy_ip = (unsigned long)p->ainsn.insn;
	unsigned long orig_ip = (unsigned long)p->addr;

	/* Restore saved interrupt flag and ip register */
	regs->flags |= kcb->kprobe_saved_flags;
	/* Note that regs->ip is executed int3 so must be a step back */
	regs->ip += (orig_ip - copy_ip) - INT3_INSN_SIZE;
}
NOKPROBE_SYMBOL(resume_singlestep);

/*
 * We have reentered the kprobe_handler(), since another probe was hit while
 * within the handler. We save the original kprobes variables and just single
 * step on the instruction of the new probe without calling any user handlers.
 */
static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
			  struct kprobe_ctlblk *kcb)
{
	switch (kcb->kprobe_status) {
	case KPROBE_HIT_SSDONE:
	case KPROBE_HIT_ACTIVE:
	case KPROBE_HIT_SS:
		kprobes_inc_nmissed_count(p);
		setup_singlestep(p, regs, kcb, 1);
		break;
	case KPROBE_REENTER:
		/* A probe has been hit in the codepath leading up to, or just
		 * after, single-stepping of a probed instruction. This entire
		 * codepath should strictly reside in .kprobes.text section.
		 * Raise a BUG or we'll continue in an endless reentering loop
		 * and eventually a stack overflow.
		 */
		pr_err("Unrecoverable kprobe detected.\n");
		dump_kprobe(p);
		BUG();
	default:
		/* impossible cases */
		WARN_ON(1);
		return 0;
	}

	return 1;
}
NOKPROBE_SYMBOL(reenter_kprobe);

static nokprobe_inline int kprobe_is_ss(struct kprobe_ctlblk *kcb)
{
	return (kcb->kprobe_status == KPROBE_HIT_SS ||
		kcb->kprobe_status == KPROBE_REENTER);
}

/*
 * Interrupts are disabled on entry as trap3 is an interrupt gate and they
 * remain disabled throughout this function.
 */
int kprobe_int3_handler(struct pt_regs *regs)
{
	kprobe_opcode_t *addr;
	struct kprobe *p;
	struct kprobe_ctlblk *kcb;

	if (user_mode(regs))
		return 0;

	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
	/*
	 * We don't want to be preempted for the entire duration of kprobe
	 * processing. Since int3 and debug trap disables irqs and we clear
	 * IF while singlestepping, it must be no preemptible.
	 */

	kcb = get_kprobe_ctlblk();
	p = get_kprobe(addr);

	if (p) {
		if (kprobe_running()) {
			if (reenter_kprobe(p, regs, kcb))
				return 1;
		} else {
			set_current_kprobe(p, regs, kcb);
			kcb->kprobe_status = KPROBE_HIT_ACTIVE;

			/*
			 * If we have no pre-handler or it returned 0, we
			 * continue with normal processing.  If we have a
			 * pre-handler and it returned non-zero, that means
			 * user handler setup registers to exit to another
			 * instruction, we must skip the single stepping.
			 */
			if (!p->pre_handler || !p->pre_handler(p, regs))
				setup_singlestep(p, regs, kcb, 0);
			else
				reset_current_kprobe();
			return 1;
		}
	} else if (kprobe_is_ss(kcb)) {
		p = kprobe_running();
		if ((unsigned long)p->ainsn.insn < regs->ip &&
		    (unsigned long)p->ainsn.insn + MAX_INSN_SIZE > regs->ip) {
			/* Most provably this is the second int3 for singlestep */
			resume_singlestep(p, regs, kcb);
			kprobe_post_process(p, regs, kcb);
			return 1;
		}
	}

	if (*addr != INT3_INSN_OPCODE) {
		/*
		 * The breakpoint instruction was removed right
		 * after we hit it.  Another cpu has removed
		 * either a probepoint or a debugger breakpoint
		 * at this address.  In either case, no further
		 * handling of this interrupt is appropriate.
		 * Back up over the (now missing) int3 and run
		 * the original instruction.
		 */
		regs->ip = (unsigned long)addr;
		return 1;
	} /* else: not a kprobe fault; let the kernel handle it */

	return 0;
}
NOKPROBE_SYMBOL(kprobe_int3_handler);

int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
	struct kprobe *cur = kprobe_running();
	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();

	if (unlikely(regs->ip == (unsigned long)cur->ainsn.insn)) {
		/* This must happen on single-stepping */
		WARN_ON(kcb->kprobe_status != KPROBE_HIT_SS &&
			kcb->kprobe_status != KPROBE_REENTER);
		/*
		 * We are here because the instruction being single
		 * stepped caused a page fault. We reset the current
		 * kprobe and the ip points back to the probe address
		 * and allow the page fault handler to continue as a
		 * normal page fault.
		 */
		regs->ip = (unsigned long)cur->addr;

		/*
		 * If the IF flag was set before the kprobe hit,
		 * don't touch it:
		 */
		regs->flags |= kcb->kprobe_old_flags;

		if (kcb->kprobe_status == KPROBE_REENTER)
			restore_previous_kprobe(kcb);
		else
			reset_current_kprobe();
	}

	return 0;
}
NOKPROBE_SYMBOL(kprobe_fault_handler);

int __init arch_populate_kprobe_blacklist(void)
{
	return kprobe_add_area_blacklist((unsigned long)__entry_text_start,
					 (unsigned long)__entry_text_end);
}

int __init arch_init_kprobes(void)
{
	return 0;
}

int arch_trampoline_kprobe(struct kprobe *p)
{
	return 0;
}