insn-eval.c 23.4 KB
Newer Older
1 2 3 4 5 6 7
/*
 * Utility functions for x86 operand and address decoding
 *
 * Copyright (C) Intel Corporation 2017
 */
#include <linux/kernel.h>
#include <linux/string.h>
8
#include <linux/ratelimit.h>
9 10 11
#include <linux/mmu_context.h>
#include <asm/desc_defs.h>
#include <asm/desc.h>
12 13 14
#include <asm/inat.h>
#include <asm/insn.h>
#include <asm/insn-eval.h>
15
#include <asm/ldt.h>
16
#include <asm/vm86.h>
17

18 19 20
#undef pr_fmt
#define pr_fmt(fmt) "insn: " fmt

21 22 23 24 25 26
enum reg_type {
	REG_TYPE_RM = 0,
	REG_TYPE_INDEX,
	REG_TYPE_BASE,
};

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
/**
 * is_string_insn() - Determine if instruction is a string instruction
 * @insn:	Instruction containing the opcode to inspect
 *
 * Returns:
 *
 * true if the instruction, determined by the opcode, is any of the
 * string instructions as defined in the Intel Software Development manual.
 * False otherwise.
 */
static bool is_string_insn(struct insn *insn)
{
	insn_get_opcode(insn);

	/* All string instructions have a 1-byte opcode. */
	if (insn->opcode.nbytes != 1)
		return false;

	switch (insn->opcode.bytes[0]) {
	case 0x6c ... 0x6f:	/* INS, OUTS */
	case 0xa4 ... 0xa7:	/* MOVS, CMPS */
	case 0xaa ... 0xaf:	/* STOS, LODS, SCAS */
		return true;
	default:
		return false;
	}
}

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
/**
 * get_seg_reg_override_idx() - obtain segment register override index
 * @insn:	Valid instruction with segment override prefixes
 *
 * Inspect the instruction prefixes in @insn and find segment overrides, if any.
 *
 * Returns:
 *
 * A constant identifying the segment register to use, among CS, SS, DS,
 * ES, FS, or GS. INAT_SEG_REG_DEFAULT is returned if no segment override
 * prefixes were found.
 *
 * -EINVAL in case of error.
 */
static int get_seg_reg_override_idx(struct insn *insn)
{
	int idx = INAT_SEG_REG_DEFAULT;
	int num_overrides = 0, i;

	insn_get_prefixes(insn);

	/* Look for any segment override prefixes. */
	for (i = 0; i < insn->prefixes.nbytes; i++) {
		insn_attr_t attr;

		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
		switch (attr) {
		case INAT_MAKE_PREFIX(INAT_PFX_CS):
			idx = INAT_SEG_REG_CS;
			num_overrides++;
			break;
		case INAT_MAKE_PREFIX(INAT_PFX_SS):
			idx = INAT_SEG_REG_SS;
			num_overrides++;
			break;
		case INAT_MAKE_PREFIX(INAT_PFX_DS):
			idx = INAT_SEG_REG_DS;
			num_overrides++;
			break;
		case INAT_MAKE_PREFIX(INAT_PFX_ES):
			idx = INAT_SEG_REG_ES;
			num_overrides++;
			break;
		case INAT_MAKE_PREFIX(INAT_PFX_FS):
			idx = INAT_SEG_REG_FS;
			num_overrides++;
			break;
		case INAT_MAKE_PREFIX(INAT_PFX_GS):
			idx = INAT_SEG_REG_GS;
			num_overrides++;
			break;
		/* No default action needed. */
		}
	}

	/* More than one segment override prefix leads to undefined behavior. */
	if (num_overrides > 1)
		return -EINVAL;

	return idx;
}

/**
 * check_seg_overrides() - check if segment override prefixes are allowed
 * @insn:	Valid instruction with segment override prefixes
 * @regoff:	Operand offset, in pt_regs, for which the check is performed
 *
 * For a particular register used in register-indirect addressing, determine if
 * segment override prefixes can be used. Specifically, no overrides are allowed
 * for rDI if used with a string instruction.
 *
 * Returns:
 *
 * True if segment override prefixes can be used with the register indicated
 * in @regoff. False if otherwise.
 */
static bool check_seg_overrides(struct insn *insn, int regoff)
{
	if (regoff == offsetof(struct pt_regs, di) && is_string_insn(insn))
		return false;

	return true;
}

/**
 * resolve_default_seg() - resolve default segment register index for an operand
 * @insn:	Instruction with opcode and address size. Must be valid.
 * @regs:	Register values as seen when entering kernel mode
 * @off:	Operand offset, in pt_regs, for which resolution is needed
 *
 * Resolve the default segment register index associated with the instruction
 * operand register indicated by @off. Such index is resolved based on defaults
 * described in the Intel Software Development Manual.
 *
 * Returns:
 *
 * If in protected mode, a constant identifying the segment register to use,
 * among CS, SS, ES or DS. If in long mode, INAT_SEG_REG_IGNORE.
 *
 * -EINVAL in case of error.
 */
static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off)
{
	if (user_64bit_mode(regs))
		return INAT_SEG_REG_IGNORE;
	/*
	 * Resolve the default segment register as described in Section 3.7.4
	 * of the Intel Software Development Manual Vol. 1:
	 *
	 *  + DS for all references involving r[ABCD]X, and rSI.
	 *  + If used in a string instruction, ES for rDI. Otherwise, DS.
	 *  + AX, CX and DX are not valid register operands in 16-bit address
	 *    encodings but are valid for 32-bit and 64-bit encodings.
	 *  + -EDOM is reserved to identify for cases in which no register
	 *    is used (i.e., displacement-only addressing). Use DS.
	 *  + SS for rSP or rBP.
	 *  + CS for rIP.
	 */

	switch (off) {
	case offsetof(struct pt_regs, ax):
	case offsetof(struct pt_regs, cx):
	case offsetof(struct pt_regs, dx):
		/* Need insn to verify address size. */
		if (insn->addr_bytes == 2)
			return -EINVAL;

	case -EDOM:
	case offsetof(struct pt_regs, bx):
	case offsetof(struct pt_regs, si):
		return INAT_SEG_REG_DS;

	case offsetof(struct pt_regs, di):
		if (is_string_insn(insn))
			return INAT_SEG_REG_ES;
		return INAT_SEG_REG_DS;

	case offsetof(struct pt_regs, bp):
	case offsetof(struct pt_regs, sp):
		return INAT_SEG_REG_SS;

	case offsetof(struct pt_regs, ip):
		return INAT_SEG_REG_CS;

	default:
		return -EINVAL;
	}
}

/**
 * resolve_seg_reg() - obtain segment register index
 * @insn:	Instruction with operands
 * @regs:	Register values as seen when entering kernel mode
 * @regoff:	Operand offset, in pt_regs, used to deterimine segment register
 *
 * Determine the segment register associated with the operands and, if
 * applicable, prefixes and the instruction pointed by @insn.
 *
 * The segment register associated to an operand used in register-indirect
 * addressing depends on:
 *
 * a) Whether running in long mode (in such a case segments are ignored, except
 * if FS or GS are used).
 *
 * b) Whether segment override prefixes can be used. Certain instructions and
 *    registers do not allow override prefixes.
 *
 * c) Whether segment overrides prefixes are found in the instruction prefixes.
 *
 * d) If there are not segment override prefixes or they cannot be used, the
 *    default segment register associated with the operand register is used.
 *
 * The function checks first if segment override prefixes can be used with the
 * operand indicated by @regoff. If allowed, obtain such overridden segment
 * register index. Lastly, if not prefixes were found or cannot be used, resolve
 * the segment register index to use based on the defaults described in the
 * Intel documentation. In long mode, all segment register indexes will be
 * ignored, except if overrides were found for FS or GS. All these operations
 * are done using helper functions.
 *
 * The operand register, @regoff, is represented as the offset from the base of
 * pt_regs.
 *
 * As stated, the main use of this function is to determine the segment register
 * index based on the instruction, its operands and prefixes. Hence, @insn
 * must be valid. However, if @regoff indicates rIP, we don't need to inspect
 * @insn at all as in this case CS is used in all cases. This case is checked
 * before proceeding further.
 *
 * Please note that this function does not return the value in the segment
 * register (i.e., the segment selector) but our defined index. The segment
 * selector needs to be obtained using get_segment_selector() and passing the
 * segment register index resolved by this function.
 *
 * Returns:
 *
 * An index identifying the segment register to use, among CS, SS, DS,
 * ES, FS, or GS. INAT_SEG_REG_IGNORE is returned if running in long mode.
 *
 * -EINVAL in case of error.
 */
static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff)
{
	int idx;

	/*
	 * In the unlikely event of having to resolve the segment register
	 * index for rIP, do it first. Segment override prefixes should not
	 * be used. Hence, it is not necessary to inspect the instruction,
	 * which may be invalid at this point.
	 */
	if (regoff == offsetof(struct pt_regs, ip)) {
		if (user_64bit_mode(regs))
			return INAT_SEG_REG_IGNORE;
		else
			return INAT_SEG_REG_CS;
	}

	if (!insn)
		return -EINVAL;

	if (!check_seg_overrides(insn, regoff))
		return resolve_default_seg(insn, regs, regoff);

	idx = get_seg_reg_override_idx(insn);
	if (idx < 0)
		return idx;

	if (idx == INAT_SEG_REG_DEFAULT)
		return resolve_default_seg(insn, regs, regoff);

	/*
	 * In long mode, segment override prefixes are ignored, except for
	 * overrides for FS and GS.
	 */
	if (user_64bit_mode(regs)) {
		if (idx != INAT_SEG_REG_FS &&
		    idx != INAT_SEG_REG_GS)
			idx = INAT_SEG_REG_IGNORE;
	}

	return idx;
}

/**
 * get_segment_selector() - obtain segment selector
 * @regs:		Register values as seen when entering kernel mode
 * @seg_reg_idx:	Segment register index to use
 *
 * Obtain the segment selector from any of the CS, SS, DS, ES, FS, GS segment
 * registers. In CONFIG_X86_32, the segment is obtained from either pt_regs or
 * kernel_vm86_regs as applicable. In CONFIG_X86_64, CS and SS are obtained
 * from pt_regs. DS, ES, FS and GS are obtained by reading the actual CPU
 * registers. This done for only for completeness as in CONFIG_X86_64 segment
 * registers are ignored.
 *
 * Returns:
 *
 * Value of the segment selector, including null when running in
 * long mode.
 *
 * -EINVAL on error.
 */
static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
{
#ifdef CONFIG_X86_64
	unsigned short sel;

	switch (seg_reg_idx) {
	case INAT_SEG_REG_IGNORE:
		return 0;
	case INAT_SEG_REG_CS:
		return (unsigned short)(regs->cs & 0xffff);
	case INAT_SEG_REG_SS:
		return (unsigned short)(regs->ss & 0xffff);
	case INAT_SEG_REG_DS:
		savesegment(ds, sel);
		return sel;
	case INAT_SEG_REG_ES:
		savesegment(es, sel);
		return sel;
	case INAT_SEG_REG_FS:
		savesegment(fs, sel);
		return sel;
	case INAT_SEG_REG_GS:
		savesegment(gs, sel);
		return sel;
	default:
		return -EINVAL;
	}
#else /* CONFIG_X86_32 */
	struct kernel_vm86_regs *vm86regs = (struct kernel_vm86_regs *)regs;

	if (v8086_mode(regs)) {
		switch (seg_reg_idx) {
		case INAT_SEG_REG_CS:
			return (unsigned short)(regs->cs & 0xffff);
		case INAT_SEG_REG_SS:
			return (unsigned short)(regs->ss & 0xffff);
		case INAT_SEG_REG_DS:
			return vm86regs->ds;
		case INAT_SEG_REG_ES:
			return vm86regs->es;
		case INAT_SEG_REG_FS:
			return vm86regs->fs;
		case INAT_SEG_REG_GS:
			return vm86regs->gs;
		case INAT_SEG_REG_IGNORE:
			/* fall through */
		default:
			return -EINVAL;
		}
	}

	switch (seg_reg_idx) {
	case INAT_SEG_REG_CS:
		return (unsigned short)(regs->cs & 0xffff);
	case INAT_SEG_REG_SS:
		return (unsigned short)(regs->ss & 0xffff);
	case INAT_SEG_REG_DS:
		return (unsigned short)(regs->ds & 0xffff);
	case INAT_SEG_REG_ES:
		return (unsigned short)(regs->es & 0xffff);
	case INAT_SEG_REG_FS:
		return (unsigned short)(regs->fs & 0xffff);
	case INAT_SEG_REG_GS:
		/*
		 * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS.
		 * The macro below takes care of both cases.
		 */
		return get_user_gs(regs);
	case INAT_SEG_REG_IGNORE:
		/* fall through */
	default:
		return -EINVAL;
	}
#endif /* CONFIG_X86_64 */
}

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
static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
			  enum reg_type type)
{
	int regno = 0;

	static const int regoff[] = {
		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
	};
	int nr_registers = ARRAY_SIZE(regoff);
	/*
	 * Don't possibly decode a 32-bit instructions as
	 * reading a 64-bit-only register.
	 */
	if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
		nr_registers -= 8;

	switch (type) {
	case REG_TYPE_RM:
		regno = X86_MODRM_RM(insn->modrm.value);
430 431 432 433 434 435 436 437

		/*
		 * ModRM.mod == 0 and ModRM.rm == 5 means a 32-bit displacement
		 * follows the ModRM byte.
		 */
		if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
			return -EDOM;

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
		if (X86_REX_B(insn->rex_prefix.value))
			regno += 8;
		break;

	case REG_TYPE_INDEX:
		regno = X86_SIB_INDEX(insn->sib.value);
		if (X86_REX_X(insn->rex_prefix.value))
			regno += 8;

		/*
		 * If ModRM.mod != 3 and SIB.index = 4 the scale*index
		 * portion of the address computation is null. This is
		 * true only if REX.X is 0. In such a case, the SIB index
		 * is used in the address computation.
		 */
		if (X86_MODRM_MOD(insn->modrm.value) != 3 && regno == 4)
			return -EDOM;
		break;

	case REG_TYPE_BASE:
		regno = X86_SIB_BASE(insn->sib.value);
		/*
		 * If ModRM.mod is 0 and SIB.base == 5, the base of the
		 * register-indirect addressing is 0. In this case, a
		 * 32-bit displacement follows the SIB byte.
		 */
		if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
			return -EDOM;

		if (X86_REX_B(insn->rex_prefix.value))
			regno += 8;
		break;

	default:
472 473
		pr_err_ratelimited("invalid register type: %d\n", type);
		return -EINVAL;
474 475 476 477 478 479 480 481 482
	}

	if (regno >= nr_registers) {
		WARN_ONCE(1, "decoded an instruction with an invalid register");
		return -EINVAL;
	}
	return regoff[regno];
}

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
/**
 * get_desc() - Obtain pointer to a segment descriptor
 * @sel:	Segment selector
 *
 * Given a segment selector, obtain a pointer to the segment descriptor.
 * Both global and local descriptor tables are supported.
 *
 * Returns:
 *
 * Pointer to segment descriptor on success.
 *
 * NULL on error.
 */
static struct desc_struct *get_desc(unsigned short sel)
{
	struct desc_ptr gdt_desc = {0, 0};
	unsigned long desc_base;

#ifdef CONFIG_MODIFY_LDT_SYSCALL
	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) {
		struct desc_struct *desc = NULL;
		struct ldt_struct *ldt;

		/* Bits [15:3] contain the index of the desired entry. */
		sel >>= 3;

		mutex_lock(&current->active_mm->context.lock);
		ldt = current->active_mm->context.ldt;
		if (ldt && sel < ldt->nr_entries)
			desc = &ldt->entries[sel];

		mutex_unlock(&current->active_mm->context.lock);

		return desc;
	}
#endif
	native_store_gdt(&gdt_desc);

	/*
	 * Segment descriptors have a size of 8 bytes. Thus, the index is
	 * multiplied by 8 to obtain the memory offset of the desired descriptor
	 * from the base of the GDT. As bits [15:3] of the segment selector
	 * contain the index, it can be regarded as multiplied by 8 already.
	 * All that remains is to clear bits [2:0].
	 */
	desc_base = sel & ~(SEGMENT_RPL_MASK | SEGMENT_TI_MASK);

	if (desc_base > gdt_desc.size)
		return NULL;

	return (struct desc_struct *)(gdt_desc.address + desc_base);
}

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
/**
 * insn_get_seg_base() - Obtain base address of segment descriptor.
 * @regs:		Register values as seen when entering kernel mode
 * @seg_reg_idx:	Index of the segment register pointing to seg descriptor
 *
 * Obtain the base address of the segment as indicated by the segment descriptor
 * pointed by the segment selector. The segment selector is obtained from the
 * input segment register index @seg_reg_idx.
 *
 * Returns:
 *
 * In protected mode, base address of the segment. Zero in long mode,
 * except when FS or GS are used. In virtual-8086 mode, the segment
 * selector shifted 4 bits to the right.
 *
 * -1L in case of error.
 */
unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
{
	struct desc_struct *desc;
	short sel;

	sel = get_segment_selector(regs, seg_reg_idx);
	if (sel < 0)
		return -1L;

	if (v8086_mode(regs))
		/*
		 * Base is simply the segment selector shifted 4
		 * bits to the right.
		 */
		return (unsigned long)(sel << 4);

	if (user_64bit_mode(regs)) {
		/*
		 * Only FS or GS will have a base address, the rest of
		 * the segments' bases are forced to 0.
		 */
		unsigned long base;

		if (seg_reg_idx == INAT_SEG_REG_FS)
			rdmsrl(MSR_FS_BASE, base);
		else if (seg_reg_idx == INAT_SEG_REG_GS)
			/*
			 * swapgs was called at the kernel entry point. Thus,
			 * MSR_KERNEL_GS_BASE will have the user-space GS base.
			 */
			rdmsrl(MSR_KERNEL_GS_BASE, base);
		else
			base = 0;
		return base;
	}

	/* In protected mode the segment selector cannot be null. */
	if (!sel)
		return -1L;

	desc = get_desc(sel);
	if (!desc)
		return -1L;

	return get_desc_base(desc);
}

/**
 * get_seg_limit() - Obtain the limit of a segment descriptor
 * @regs:		Register values as seen when entering kernel mode
 * @seg_reg_idx:	Index of the segment register pointing to seg descriptor
 *
 * Obtain the limit of the segment as indicated by the segment descriptor
 * pointed by the segment selector. The segment selector is obtained from the
 * input segment register index @seg_reg_idx.
 *
 * Returns:
 *
 * In protected mode, the limit of the segment descriptor in bytes.
 * In long mode and virtual-8086 mode, segment limits are not enforced. Thus,
 * limit is returned as -1L to imply a limit-less segment.
 *
 * Zero is returned on error.
 */
static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx)
{
	struct desc_struct *desc;
	unsigned long limit;
	short sel;

	sel = get_segment_selector(regs, seg_reg_idx);
	if (sel < 0)
		return 0;

	if (user_64bit_mode(regs) || v8086_mode(regs))
		return -1L;

	if (!sel)
		return 0;

	desc = get_desc(sel);
	if (!desc)
		return 0;

	/*
	 * If the granularity bit is set, the limit is given in multiples
	 * of 4096. This also means that the 12 least significant bits are
	 * not tested when checking the segment limits. In practice,
	 * this means that the segment ends in (limit << 12) + 0xfff.
	 */
	limit = get_desc_limit(desc);
	if (desc->g)
		limit = (limit << 12) + 0xfff;

	return limit;
}

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
/**
 * insn_get_code_seg_params() - Obtain code segment parameters
 * @regs:	Structure with register values as seen when entering kernel mode
 *
 * Obtain address and operand sizes of the code segment. It is obtained from the
 * selector contained in the CS register in regs. In protected mode, the default
 * address is determined by inspecting the L and D bits of the segment
 * descriptor. In virtual-8086 mode, the default is always two bytes for both
 * address and operand sizes.
 *
 * Returns:
 *
 * A signed 8-bit value containing the default parameters on success.
 *
 * -EINVAL on error.
 */
char insn_get_code_seg_params(struct pt_regs *regs)
{
	struct desc_struct *desc;
	short sel;

	if (v8086_mode(regs))
		/* Address and operand size are both 16-bit. */
		return INSN_CODE_SEG_PARAMS(2, 2);

	sel = get_segment_selector(regs, INAT_SEG_REG_CS);
	if (sel < 0)
		return sel;

	desc = get_desc(sel);
	if (!desc)
		return -EINVAL;

	/*
	 * The most significant byte of the Type field of the segment descriptor
	 * determines whether a segment contains data or code. If this is a data
	 * segment, return error.
	 */
	if (!(desc->type & BIT(3)))
		return -EINVAL;

	switch ((desc->l << 1) | desc->d) {
	case 0: /*
		 * Legacy mode. CS.L=0, CS.D=0. Address and operand size are
		 * both 16-bit.
		 */
		return INSN_CODE_SEG_PARAMS(2, 2);
	case 1: /*
		 * Legacy mode. CS.L=0, CS.D=1. Address and operand size are
		 * both 32-bit.
		 */
		return INSN_CODE_SEG_PARAMS(4, 4);
	case 2: /*
		 * IA-32e 64-bit mode. CS.L=1, CS.D=0. Address size is 64-bit;
		 * operand size is 32-bit.
		 */
		return INSN_CODE_SEG_PARAMS(4, 8);
	case 3: /* Invalid setting. CS.L=1, CS.D=1 */
		/* fall through */
	default:
		return -EINVAL;
	}
}

714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730
/**
 * insn_get_modrm_rm_off() - Obtain register in r/m part of the ModRM byte
 * @insn:	Instruction containing the ModRM byte
 * @regs:	Register values as seen when entering kernel mode
 *
 * Returns:
 *
 * The register indicated by the r/m part of the ModRM byte. The
 * register is obtained as an offset from the base of pt_regs. In specific
 * cases, the returned value can be -EDOM to indicate that the particular value
 * of ModRM does not refer to a register and shall be ignored.
 */
int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
{
	return get_reg_offset(insn, regs, REG_TYPE_RM);
}

731
/**
732
 * get_seg_base_limit() - obtain base address and limit of a segment
733 734 735 736
 * @insn:	Instruction. Must be valid.
 * @regs:	Register values as seen when entering kernel mode
 * @regoff:	Operand offset, in pt_regs, used to resolve segment descriptor
 * @base:	Obtained segment base
737
 * @limit:	Obtained segment limit
738
 *
739 740
 * Obtain the base address and limit of the segment associated with the operand
 * @regoff and, if any or allowed, override prefixes in @insn. This function is
741
 * different from insn_get_seg_base() as the latter does not resolve the segment
742 743
 * associated with the instruction operand. If a limit is not needed (e.g.,
 * when running in long mode), @limit can be NULL.
744 745 746
 *
 * Returns:
 *
747 748
 * 0 on success. @base and @limit will contain the base address and of the
 * resolved segment, respectively.
749 750 751
 *
 * -EINVAL on error.
 */
752 753 754
static int get_seg_base_limit(struct insn *insn, struct pt_regs *regs,
			      int regoff, unsigned long *base,
			      unsigned long *limit)
755 756 757 758 759 760 761 762 763 764 765 766 767 768
{
	int seg_reg_idx;

	if (!base)
		return -EINVAL;

	seg_reg_idx = resolve_seg_reg(insn, regs, regoff);
	if (seg_reg_idx < 0)
		return seg_reg_idx;

	*base = insn_get_seg_base(regs, seg_reg_idx);
	if (*base == -1L)
		return -EINVAL;

769 770 771 772 773 774 775
	if (!limit)
		return 0;

	*limit = get_seg_limit(regs, seg_reg_idx);
	if (!(*limit))
		return -EINVAL;

776 777 778
	return 0;
}

779 780 781 782 783 784 785
/*
 * return the address being referenced be instruction
 * for rm=3 returning the content of the rm reg
 * for rm!=3 calculates the address using SIB and Disp
 */
void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
{
786 787
	int addr_offset, base_offset, indx_offset, ret;
	unsigned long linear_addr = -1L, seg_base;
788 789 790 791 792 793 794 795 796 797 798 799 800
	long eff_addr, base, indx;
	insn_byte_t sib;

	insn_get_modrm(insn);
	insn_get_sib(insn);
	sib = insn->sib.value;

	if (X86_MODRM_MOD(insn->modrm.value) == 3) {
		addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
		if (addr_offset < 0)
			goto out;

		eff_addr = regs_get_register(regs, addr_offset);
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
	} else {
		if (insn->sib.nbytes) {
			/*
			 * Negative values in the base and index offset means
			 * an error when decoding the SIB byte. Except -EDOM,
			 * which means that the registers should not be used
			 * in the address computation.
			 */
			base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
			if (base_offset == -EDOM)
				base = 0;
			else if (base_offset < 0)
				goto out;
			else
				base = regs_get_register(regs, base_offset);

			indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);

			if (indx_offset == -EDOM)
				indx = 0;
			else if (indx_offset < 0)
				goto out;
			else
				indx = regs_get_register(regs, indx_offset);

			eff_addr = base + indx * (1 << X86_SIB_SCALE(sib));
828 829 830 831 832 833 834

			/*
			 * The base determines the segment used to compute
			 * the linear address.
			 */
			addr_offset = base_offset;

835 836
		} else {
			addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
837 838 839 840 841 842 843 844 845 846 847
			/*
			 * -EDOM means that we must ignore the address_offset.
			 * In such a case, in 64-bit mode the effective address
			 * relative to the RIP of the following instruction.
			 */
			if (addr_offset == -EDOM) {
				if (user_64bit_mode(regs))
					eff_addr = (long)regs->ip + insn->length;
				else
					eff_addr = 0;
			} else if (addr_offset < 0) {
848
				goto out;
849 850 851
			} else {
				eff_addr = regs_get_register(regs, addr_offset);
			}
852 853 854 855 856
		}

		eff_addr += insn->displacement.value;
	}

857
	ret = get_seg_base_limit(insn, regs, addr_offset, &seg_base, NULL);
858 859 860 861
	if (ret)
		goto out;

	linear_addr = (unsigned long)eff_addr + seg_base;
862 863 864 865

out:
	return (void __user *)linear_addr;
}