blob: 2673cd5c46cb486b9e78a20c589462552f0b4747 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
* emulate.c
*
* Generic x86 (32-bit and 64-bit) instruction decoder and emulator.
*
* Copyright (c) 2005 Keir Fraser
*
* Linux coding style, mod r/m decoder, segment base fixes, real-mode
* privileged instructions:
*
* Copyright (C) 2006 Qumranet
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Avi Kivity <avi@qumranet.com>
* Yaniv Kamay <yaniv@qumranet.com>
*
* From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kvm_host.h>
#include "kvm_cache_regs.h"
#include "kvm_emulate.h"
#include <linux/stringify.h>
#include <asm/debugreg.h>
#include <asm/nospec-branch.h>
#include <asm/ibt.h>
#include "x86.h"
#include "tss.h"
#include "mmu.h"
#include "pmu.h"
/*
* Operand types
*/
#define OpNone 0ull
#define OpImplicit 1ull /* No generic decode */
#define OpReg 2ull /* Register */
#define OpMem 3ull /* Memory */
#define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */
#define OpDI 5ull /* ES:DI/EDI/RDI */
#define OpMem64 6ull /* Memory, 64-bit */
#define OpImmUByte 7ull /* Zero-extended 8-bit immediate */
#define OpDX 8ull /* DX register */
#define OpCL 9ull /* CL register (for shifts) */
#define OpImmByte 10ull /* 8-bit sign extended immediate */
#define OpOne 11ull /* Implied 1 */
#define OpImm 12ull /* Sign extended up to 32-bit immediate */
#define OpMem16 13ull /* Memory operand (16-bit). */
#define OpMem32 14ull /* Memory operand (32-bit). */
#define OpImmU 15ull /* Immediate operand, zero extended */
#define OpSI 16ull /* SI/ESI/RSI */
#define OpImmFAddr 17ull /* Immediate far address */
#define OpMemFAddr 18ull /* Far address in memory */
#define OpImmU16 19ull /* Immediate operand, 16 bits, zero extended */
#define OpES 20ull /* ES */
#define OpCS 21ull /* CS */
#define OpSS 22ull /* SS */
#define OpDS 23ull /* DS */
#define OpFS 24ull /* FS */
#define OpGS 25ull /* GS */
#define OpMem8 26ull /* 8-bit zero extended memory operand */
#define OpImm64 27ull /* Sign extended 16/32/64-bit immediate */
#define OpXLat 28ull /* memory at BX/EBX/RBX + zero-extended AL */
#define OpAccLo 29ull /* Low part of extended acc (AX/AX/EAX/RAX) */
#define OpAccHi 30ull /* High part of extended acc (-/DX/EDX/RDX) */
#define OpBits 5 /* Width of operand field */
#define OpMask ((1ull << OpBits) - 1)
/*
* Opcode effective-address decode tables.
* Note that we only emulate instructions that have at least one memory
* operand (excluding implicit stack references). We assume that stack
* references and instruction fetches will never occur in special memory
* areas that require emulation. So, for example, 'mov <imm>,<reg>' need
* not be handled.
*/
/* Operand sizes: 8-bit operands or specified/overridden size. */
#define ByteOp (1<<0) /* 8-bit operands. */
/* Destination operand type. */
#define DstShift 1
#define ImplicitOps (OpImplicit << DstShift)
#define DstReg (OpReg << DstShift)
#define DstMem (OpMem << DstShift)
#define DstAcc (OpAcc << DstShift)
#define DstDI (OpDI << DstShift)
#define DstMem64 (OpMem64 << DstShift)
#define DstMem16 (OpMem16 << DstShift)
#define DstImmUByte (OpImmUByte << DstShift)
#define DstDX (OpDX << DstShift)
#define DstAccLo (OpAccLo << DstShift)
#define DstMask (OpMask << DstShift)
/* Source operand type. */
#define SrcShift 6
#define SrcNone (OpNone << SrcShift)
#define SrcReg (OpReg << SrcShift)
#define SrcMem (OpMem << SrcShift)
#define SrcMem16 (OpMem16 << SrcShift)
#define SrcMem32 (OpMem32 << SrcShift)
#define SrcImm (OpImm << SrcShift)
#define SrcImmByte (OpImmByte << SrcShift)
#define SrcOne (OpOne << SrcShift)
#define SrcImmUByte (OpImmUByte << SrcShift)
#define SrcImmU (OpImmU << SrcShift)
#define SrcSI (OpSI << SrcShift)
#define SrcXLat (OpXLat << SrcShift)
#define SrcImmFAddr (OpImmFAddr << SrcShift)
#define SrcMemFAddr (OpMemFAddr << SrcShift)
#define SrcAcc (OpAcc << SrcShift)
#define SrcImmU16 (OpImmU16 << SrcShift)
#define SrcImm64 (OpImm64 << SrcShift)
#define SrcDX (OpDX << SrcShift)
#define SrcMem8 (OpMem8 << SrcShift)
#define SrcAccHi (OpAccHi << SrcShift)
#define SrcMask (OpMask << SrcShift)
#define BitOp (1<<11)
#define MemAbs (1<<12) /* Memory operand is absolute displacement */
#define String (1<<13) /* String instruction (rep capable) */
#define Stack (1<<14) /* Stack instruction (push/pop) */
#define GroupMask (7<<15) /* Opcode uses one of the group mechanisms */
#define Group (1<<15) /* Bits 3:5 of modrm byte extend opcode */
#define GroupDual (2<<15) /* Alternate decoding of mod == 3 */
#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */
#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */
#define Escape (5<<15) /* Escape to coprocessor instruction */
#define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */
#define ModeDual (7<<15) /* Different instruction for 32/64 bit */
#define Sse (1<<18) /* SSE Vector instruction */
/* Generic ModRM decode. */
#define ModRM (1<<19)
/* Destination is only written; never read. */
#define Mov (1<<20)
/* Misc flags */
#define Prot (1<<21) /* instruction generates #UD if not in prot-mode */
#define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */
#define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */
#define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */
#define Undefined (1<<25) /* No Such Instruction */
#define Lock (1<<26) /* lock prefix is allowed for the instruction */
#define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */
#define No64 (1<<28)
#define PageTable (1 << 29) /* instruction used to write page table */
#define NotImpl (1 << 30) /* instruction is not implemented */
/* Source 2 operand type */
#define Src2Shift (31)
#define Src2None (OpNone << Src2Shift)
#define Src2Mem (OpMem << Src2Shift)
#define Src2CL (OpCL << Src2Shift)
#define Src2ImmByte (OpImmByte << Src2Shift)
#define Src2One (OpOne << Src2Shift)
#define Src2Imm (OpImm << Src2Shift)
#define Src2ES (OpES << Src2Shift)
#define Src2CS (OpCS << Src2Shift)
#define Src2SS (OpSS << Src2Shift)
#define Src2DS (OpDS << Src2Shift)
#define Src2FS (OpFS << Src2Shift)
#define Src2GS (OpGS << Src2Shift)
#define Src2Mask (OpMask << Src2Shift)
#define Mmx ((u64)1 << 40) /* MMX Vector instruction */
#define AlignMask ((u64)7 << 41)
#define Aligned ((u64)1 << 41) /* Explicitly aligned (e.g. MOVDQA) */
#define Unaligned ((u64)2 << 41) /* Explicitly unaligned (e.g. MOVDQU) */
#define Avx ((u64)3 << 41) /* Advanced Vector Extensions */
#define Aligned16 ((u64)4 << 41) /* Aligned to 16 byte boundary (e.g. FXSAVE) */
#define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */
#define NoWrite ((u64)1 << 45) /* No writeback */
#define SrcWrite ((u64)1 << 46) /* Write back src operand */
#define NoMod ((u64)1 << 47) /* Mod field is ignored */
#define Intercept ((u64)1 << 48) /* Has valid intercept field */
#define CheckPerm ((u64)1 << 49) /* Has valid check_perm field */
#define PrivUD ((u64)1 << 51) /* #UD instead of #GP on CPL > 0 */
#define NearBranch ((u64)1 << 52) /* Near branches */
#define No16 ((u64)1 << 53) /* No 16 bit operand */
#define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */
#define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */
#define IsBranch ((u64)1 << 56) /* Instruction is considered a branch. */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
#define X2(x...) x, x
#define X3(x...) X2(x), x
#define X4(x...) X2(x), X2(x)
#define X5(x...) X4(x), x
#define X6(x...) X4(x), X2(x)
#define X7(x...) X4(x), X3(x)
#define X8(x...) X4(x), X4(x)
#define X16(x...) X8(x), X8(x)
struct opcode {
u64 flags;
u8 intercept;
u8 pad[7];
union {
int (*execute)(struct x86_emulate_ctxt *ctxt);
const struct opcode *group;
const struct group_dual *gdual;
const struct gprefix *gprefix;
const struct escape *esc;
const struct instr_dual *idual;
const struct mode_dual *mdual;
void (*fastop)(struct fastop *fake);
} u;
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
};
struct group_dual {
struct opcode mod012[8];
struct opcode mod3[8];
};
struct gprefix {
struct opcode pfx_no;
struct opcode pfx_66;
struct opcode pfx_f2;
struct opcode pfx_f3;
};
struct escape {
struct opcode op[8];
struct opcode high[64];
};
struct instr_dual {
struct opcode mod012;
struct opcode mod3;
};
struct mode_dual {
struct opcode mode32;
struct opcode mode64;
};
#define EFLG_RESERVED_ZEROS_MASK 0xffc0802a
enum x86_transfer_type {
X86_TRANSFER_NONE,
X86_TRANSFER_CALL_JMP,
X86_TRANSFER_RET,
X86_TRANSFER_TASK_SWITCH,
};
static void writeback_registers(struct x86_emulate_ctxt *ctxt)
{
unsigned long dirty = ctxt->regs_dirty;
unsigned reg;
for_each_set_bit(reg, &dirty, NR_EMULATOR_GPRS)
ctxt->ops->write_gpr(ctxt, reg, ctxt->_regs[reg]);
}
static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
{
ctxt->regs_dirty = 0;
ctxt->regs_valid = 0;
}
/*
* These EFLAGS bits are restored from saved value during emulation, and
* any changes are written back to the saved value after emulation.
*/
#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\
X86_EFLAGS_PF|X86_EFLAGS_CF)
#ifdef CONFIG_X86_64
#define ON64(x) x
#else
#define ON64(x)
#endif
/*
* fastop functions have a special calling convention:
*
* dst: rax (in/out)
* src: rdx (in/out)
* src2: rcx (in)
* flags: rflags (in/out)
* ex: rsi (in:fastop pointer, out:zero if exception)
*
* Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for
* different operand sizes can be reached by calculation, rather than a jump
* table (which would be bigger than the code).
*
* The 16 byte alignment, considering 5 bytes for the RET thunk, 3 for ENDBR
* and 1 for the straight line speculation INT3, leaves 7 bytes for the
* body of the function. Currently none is larger than 4.
*/
static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
#define FASTOP_SIZE 16
#define __FOP_FUNC(name) \
".align " __stringify(FASTOP_SIZE) " \n\t" \
".type " name ", @function \n\t" \
name ":\n\t" \
ASM_ENDBR \
IBT_NOSEAL(name)
#define FOP_FUNC(name) \
__FOP_FUNC(#name)
#define __FOP_RET(name) \
"11: " ASM_RET \
".size " name ", .-" name "\n\t"
#define FOP_RET(name) \
__FOP_RET(#name)
#define __FOP_START(op, align) \
extern void em_##op(struct fastop *fake); \
asm(".pushsection .text, \"ax\" \n\t" \
".global em_" #op " \n\t" \
".align " __stringify(align) " \n\t" \
"em_" #op ":\n\t"
#define FOP_START(op) __FOP_START(op, FASTOP_SIZE)
#define FOP_END \
".popsection")
#define __FOPNOP(name) \
__FOP_FUNC(name) \
__FOP_RET(name)
#define FOPNOP() \
__FOPNOP(__stringify(__UNIQUE_ID(nop)))
#define FOP1E(op, dst) \
__FOP_FUNC(#op "_" #dst) \
"10: " #op " %" #dst " \n\t" \
__FOP_RET(#op "_" #dst)
#define FOP1EEX(op, dst) \
FOP1E(op, dst) _ASM_EXTABLE_TYPE_REG(10b, 11b, EX_TYPE_ZERO_REG, %%esi)
#define FASTOP1(op) \
FOP_START(op) \
FOP1E(op##b, al) \
FOP1E(op##w, ax) \
FOP1E(op##l, eax) \
ON64(FOP1E(op##q, rax)) \
FOP_END
/* 1-operand, using src2 (for MUL/DIV r/m) */
#define FASTOP1SRC2(op, name) \
FOP_START(name) \
FOP1E(op, cl) \
FOP1E(op, cx) \
FOP1E(op, ecx) \
ON64(FOP1E(op, rcx)) \
FOP_END
/* 1-operand, using src2 (for MUL/DIV r/m), with exceptions */
#define FASTOP1SRC2EX(op, name) \
FOP_START(name) \
FOP1EEX(op, cl) \
FOP1EEX(op, cx) \
FOP1EEX(op, ecx) \
ON64(FOP1EEX(op, rcx)) \
FOP_END
#define FOP2E(op, dst, src) \
__FOP_FUNC(#op "_" #dst "_" #src) \
#op " %" #src ", %" #dst " \n\t" \
__FOP_RET(#op "_" #dst "_" #src)
#define FASTOP2(op) \
FOP_START(op) \
FOP2E(op##b, al, dl) \
FOP2E(op##w, ax, dx) \
FOP2E(op##l, eax, edx) \
ON64(FOP2E(op##q, rax, rdx)) \
FOP_END
/* 2 operand, word only */
#define FASTOP2W(op) \
FOP_START(op) \
FOPNOP() \
FOP2E(op##w, ax, dx) \
FOP2E(op##l, eax, edx) \
ON64(FOP2E(op##q, rax, rdx)) \
FOP_END
/* 2 operand, src is CL */
#define FASTOP2CL(op) \
FOP_START(op) \
FOP2E(op##b, al, cl) \
FOP2E(op##w, ax, cl) \
FOP2E(op##l, eax, cl) \
ON64(FOP2E(op##q, rax, cl)) \
FOP_END
/* 2 operand, src and dest are reversed */
#define FASTOP2R(op, name) \
FOP_START(name) \
FOP2E(op##b, dl, al) \
FOP2E(op##w, dx, ax) \
FOP2E(op##l, edx, eax) \
ON64(FOP2E(op##q, rdx, rax)) \
FOP_END
#define FOP3E(op, dst, src, src2) \
__FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \
#op " %" #src2 ", %" #src ", %" #dst " \n\t"\
__FOP_RET(#op "_" #dst "_" #src "_" #src2)
/* 3-operand, word-only, src2=cl */
#define FASTOP3WCL(op) \
FOP_START(op) \
FOPNOP() \
FOP3E(op##w, ax, dx, cl) \
FOP3E(op##l, eax, edx, cl) \
ON64(FOP3E(op##q, rax, rdx, cl)) \
FOP_END
/* Special case for SETcc - 1 instruction per cc */
#define FOP_SETCC(op) \
FOP_FUNC(op) \
#op " %al \n\t" \
FOP_RET(op)
FOP_START(setcc)
FOP_SETCC(seto)
FOP_SETCC(setno)
FOP_SETCC(setc)
FOP_SETCC(setnc)
FOP_SETCC(setz)
FOP_SETCC(setnz)
FOP_SETCC(setbe)
FOP_SETCC(setnbe)
FOP_SETCC(sets)
FOP_SETCC(setns)
FOP_SETCC(setp)
FOP_SETCC(setnp)
FOP_SETCC(setl)
FOP_SETCC(setnl)
FOP_SETCC(setle)
FOP_SETCC(setnle)
FOP_END;
FOP_START(salc)
FOP_FUNC(salc)
"pushf; sbb %al, %al; popf \n\t"
FOP_RET(salc)
FOP_END;
/*
* XXX: inoutclob user must know where the argument is being expanded.
* Using asm goto would allow us to remove _fault.
*/
#define asm_safe(insn, inoutclob...) \
({ \
int _fault = 0; \
\
asm volatile("1:" insn "\n" \
"2:\n" \
_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[_fault]) \
: [_fault] "+r"(_fault) inoutclob ); \
\
_fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \
})
static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt,
enum x86_intercept intercept,
enum x86_intercept_stage stage)
{
struct x86_instruction_info info = {
.intercept = intercept,
.rep_prefix = ctxt->rep_prefix,
.modrm_mod = ctxt->modrm_mod,
.modrm_reg = ctxt->modrm_reg,
.modrm_rm = ctxt->modrm_rm,
.src_val = ctxt->src.val64,
.dst_val = ctxt->dst.val64,
.src_bytes = ctxt->src.bytes,
.dst_bytes = ctxt->dst.bytes,
.ad_bytes = ctxt->ad_bytes,
.next_rip = ctxt->eip,
};
return ctxt->ops->intercept(ctxt, &info, stage);
}
static void assign_masked(ulong *dest, ulong src, ulong mask)
{
*dest = (*dest & ~mask) | (src & mask);
}
static void assign_register(unsigned long *reg, u64 val, int bytes)
{
/* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
switch (bytes) {
case 1:
*(u8 *)reg = (u8)val;
break;
case 2:
*(u16 *)reg = (u16)val;
break;
case 4:
*reg = (u32)val;
break; /* 64b: zero-extend */
case 8:
*reg = val;
break;
}
}
static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt)
{
return (1UL << (ctxt->ad_bytes << 3)) - 1;
}
static ulong stack_mask(struct x86_emulate_ctxt *ctxt)
{
u16 sel;
struct desc_struct ss;
if (ctxt->mode == X86EMUL_MODE_PROT64)
return ~0UL;
ctxt->ops->get_segment(ctxt, &sel, &ss, NULL, VCPU_SREG_SS);
return ~0U >> ((ss.d ^ 1) * 16); /* d=0: 0xffff; d=1: 0xffffffff */
}
static int stack_size(struct x86_emulate_ctxt *ctxt)
{
return (__fls(stack_mask(ctxt)) + 1) >> 3;
}
/* Access/update address held in a register, based on addressing mode. */
static inline unsigned long
address_mask(struct x86_emulate_ctxt *ctxt, unsigned long reg)
{
if (ctxt->ad_bytes == sizeof(unsigned long))
return reg;
else
return reg & ad_mask(ctxt);
}
static inline unsigned long
register_address(struct x86_emulate_ctxt *ctxt, int reg)
{
return address_mask(ctxt, reg_read(ctxt, reg));
}
static void masked_increment(ulong *reg, ulong mask, int inc)
{
assign_masked(reg, *reg + inc, mask);
}
static inline void
register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
{
ulong *preg = reg_rmw(ctxt, reg);
assign_register(preg, *preg + inc, ctxt->ad_bytes);
}
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
{
masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
}
static u32 desc_limit_scaled(struct desc_struct *desc)
{
u32 limit = get_desc_limit(desc);
return desc->g ? (limit << 12) | 0xfff : limit;
}
static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
{
if (ctxt->mode == X86EMUL_MODE_PROT64 && seg < VCPU_SREG_FS)
return 0;
return ctxt->ops->get_cached_segment_base(ctxt, seg);
}
static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec,
u32 error, bool valid)
{
if (KVM_EMULATOR_BUG_ON(vec > 0x1f, ctxt))
return X86EMUL_UNHANDLEABLE;
ctxt->exception.vector = vec;
ctxt->exception.error_code = error;
ctxt->exception.error_code_valid = valid;
return X86EMUL_PROPAGATE_FAULT;
}
static int emulate_db(struct x86_emulate_ctxt *ctxt)
{
return emulate_exception(ctxt, DB_VECTOR, 0, false);
}
static int emulate_gp(struct x86_emulate_ctxt *ctxt, int err)
{
return emulate_exception(ctxt, GP_VECTOR, err, true);
}
static int emulate_ss(struct x86_emulate_ctxt *ctxt, int err)
{
return emulate_exception(ctxt, SS_VECTOR, err, true);
}
static int emulate_ud(struct x86_emulate_ctxt *ctxt)
{
return emulate_exception(ctxt, UD_VECTOR, 0, false);
}
static int emulate_ts(struct x86_emulate_ctxt *ctxt, int err)
{
return emulate_exception(ctxt, TS_VECTOR, err, true);
}
static int emulate_de(struct x86_emulate_ctxt *ctxt)
{
return emulate_exception(ctxt, DE_VECTOR, 0, false);
}
static int emulate_nm(struct x86_emulate_ctxt *ctxt)
{
return emulate_exception(ctxt, NM_VECTOR, 0, false);
}
static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
{
u16 selector;
struct desc_struct desc;
ctxt->ops->get_segment(ctxt, &selector, &desc, NULL, seg);
return selector;
}
static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
unsigned seg)
{
u16 dummy;
u32 base3;
struct desc_struct desc;
ctxt->ops->get_segment(ctxt, &dummy, &desc, &base3, seg);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg);
}
static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
{
return (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_LA57) ? 57 : 48;
}
static inline bool emul_is_noncanonical_address(u64 la,
struct x86_emulate_ctxt *ctxt)
{
return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt));
}
/*
* x86 defines three classes of vector instructions: explicitly
* aligned, explicitly unaligned, and the rest, which change behaviour
* depending on whether they're AVX encoded or not.
*
* Also included is CMPXCHG16B which is not a vector instruction, yet it is
* subject to the same check. FXSAVE and FXRSTOR are checked here too as their
* 512 bytes of data must be aligned to a 16 byte boundary.
*/
static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size)
{
u64 alignment = ctxt->d & AlignMask;
if (likely(size < 16))
return 1;
switch (alignment) {
case Unaligned:
case Avx:
return 1;
case Aligned16:
return 16;
case Aligned:
default:
return size;
}
}
static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
unsigned *max_size, unsigned size,
bool write, bool fetch,
enum x86emul_mode mode, ulong *linear)
{
struct desc_struct desc;
bool usable;
ulong la;
u32 lim;
u16 sel;
u8 va_bits;
la = seg_base(ctxt, addr.seg) + addr.ea;
*max_size = 0;
switch (mode) {
case X86EMUL_MODE_PROT64:
*linear = la;
va_bits = ctxt_virt_addr_bits(ctxt);
if (!__is_canonical_address(la, va_bits))
goto bad;
*max_size = min_t(u64, ~0u, (1ull << va_bits) - la);
if (size > *max_size)
goto bad;
break;
default:
*linear = la = (u32)la;
usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
addr.seg);
if (!usable)
goto bad;
/* code segment in protected mode or read-only data segment */
if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8))
|| !(desc.type & 2)) && write)
goto bad;
/* unreadable code segment */
if (!fetch && (desc.type & 8) && !(desc.type & 2))
goto bad;
lim = desc_limit_scaled(&desc);
if (!(desc.type & 8) && (desc.type & 4)) {
/* expand-down segment */
if (addr.ea <= lim)
goto bad;
lim = desc.d ? 0xffffffff : 0xffff;
}
if (addr.ea > lim)
goto bad;
if (lim == 0xffffffff)
*max_size = ~0u;
else {
*max_size = (u64)lim + 1 - addr.ea;
if (size > *max_size)
goto bad;
}
break;
}
if (la & (insn_alignment(ctxt, size) - 1))
return emulate_gp(ctxt, 0);
return X86EMUL_CONTINUE;
bad:
if (addr.seg == VCPU_SREG_SS)
return emulate_ss(ctxt, 0);
else
return emulate_gp(ctxt, 0);
}
static int linearize(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
unsigned size, bool write,
ulong *linear)
{
unsigned max_size;
return __linearize(ctxt, addr, &max_size, size, write, false,
ctxt->mode, linear);
}
static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
{
ulong linear;
int rc;
unsigned max_size;
struct segmented_address addr = { .seg = VCPU_SREG_CS,
.ea = dst };
if (ctxt->op_bytes != sizeof(unsigned long))
addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
if (rc == X86EMUL_CONTINUE)
ctxt->_eip = addr.ea;
return rc;
}
static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt)
{
u64 efer;
struct desc_struct cs;
u16 selector;
u32 base3;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) {
/* Real mode. cpu must not have long mode active */
if (efer & EFER_LMA)
return X86EMUL_UNHANDLEABLE;
ctxt->mode = X86EMUL_MODE_REAL;
return X86EMUL_CONTINUE;
}
if (ctxt->eflags & X86_EFLAGS_VM) {
/* Protected/VM86 mode. cpu must not have long mode active */
if (efer & EFER_LMA)
return X86EMUL_UNHANDLEABLE;
ctxt->mode = X86EMUL_MODE_VM86;
return X86EMUL_CONTINUE;
}
if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS))
return X86EMUL_UNHANDLEABLE;
if (efer & EFER_LMA) {
if (cs.l) {
/* Proper long mode */
ctxt->mode = X86EMUL_MODE_PROT64;
} else if (cs.d) {
/* 32 bit compatibility mode*/
ctxt->mode = X86EMUL_MODE_PROT32;
} else {
ctxt->mode = X86EMUL_MODE_PROT16;
}
} else {
/* Legacy 32 bit / 16 bit mode */
ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
}
return X86EMUL_CONTINUE;
}
static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
{
return assign_eip(ctxt, dst);
}
static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst)
{
int rc = emulator_recalc_and_set_mode(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
return assign_eip(ctxt, dst);
}
static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
{
return assign_eip_near(ctxt, ctxt->_eip + rel);
}
static int linear_read_system(struct x86_emulate_ctxt *ctxt, ulong linear,
void *data, unsigned size)
{
return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, true);
}
static int linear_write_system(struct x86_emulate_ctxt *ctxt,
ulong linear, void *data,
unsigned int size)
{
return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, true);
}
static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
void *data,
unsigned size)
{
int rc;
ulong linear;
rc = linearize(ctxt, addr, size, false, &linear);
if (rc != X86EMUL_CONTINUE)
return rc;
return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, false);
}
static int segmented_write_std(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
void *data,
unsigned int size)
{
int rc;
ulong linear;
rc = linearize(ctxt, addr, size, true, &linear);
if (rc != X86EMUL_CONTINUE)
return rc;
return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, false);
}
/*
* Prefetch the remaining bytes of the instruction without crossing page
* boundary if they are not in fetch_cache yet.
*/
static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
{
int rc;
unsigned size, max_size;
unsigned long linear;
int cur_size = ctxt->fetch.end - ctxt->fetch.data;
struct segmented_address addr = { .seg = VCPU_SREG_CS,
.ea = ctxt->eip + cur_size };
/*
* We do not know exactly how many bytes will be needed, and
* __linearize is expensive, so fetch as much as possible. We
* just have to avoid going beyond the 15 byte limit, the end
* of the segment, or the end of the page.
*
* __linearize is called with size 0 so that it does not do any
* boundary check itself. Instead, we use max_size to check
* against op_size.
*/
rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode,
&linear);
if (unlikely(rc != X86EMUL_CONTINUE))
return rc;
size = min_t(unsigned, 15UL ^ cur_size, max_size);
size = min_t(unsigned, size, PAGE_SIZE - offset_in_page(linear));
/*
* One instruction can only straddle two pages,
* and one has been loaded at the beginning of
* x86_decode_insn. So, if not enough bytes
* still, we must have hit the 15-byte boundary.
*/
if (unlikely(size < op_size))
return emulate_gp(ctxt, 0);
rc = ctxt->ops->fetch(ctxt, linear, ctxt->fetch.end,
size, &ctxt->exception);
if (unlikely(rc != X86EMUL_CONTINUE))
return rc;
ctxt->fetch.end += size;
return X86EMUL_CONTINUE;
}
static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt,
unsigned size)
{
unsigned done_size = ctxt->fetch.end - ctxt->fetch.ptr;
if (unlikely(done_size < size))
return __do_insn_fetch_bytes(ctxt, size - done_size);
else
return X86EMUL_CONTINUE;
}
/* Fetch next part of the instruction being emulated. */
#define insn_fetch(_type, _ctxt) \
({ _type _x; \
\
rc = do_insn_fetch_bytes(_ctxt, sizeof(_type)); \
if (rc != X86EMUL_CONTINUE) \
goto done; \
ctxt->_eip += sizeof(_type); \
memcpy(&_x, ctxt->fetch.ptr, sizeof(_type)); \
ctxt->fetch.ptr += sizeof(_type); \
_x; \
})
#define insn_fetch_arr(_arr, _size, _ctxt) \
({ \
rc = do_insn_fetch_bytes(_ctxt, _size); \
if (rc != X86EMUL_CONTINUE) \
goto done; \
ctxt->_eip += (_size); \
memcpy(_arr, ctxt->fetch.ptr, _size); \
ctxt->fetch.ptr += (_size); \
})
/*
* Given the 'reg' portion of a ModRM byte, and a register block, return a
* pointer into the block that addresses the relevant register.
* @highbyte_regs specifies whether to decode AH,CH,DH,BH.
*/
static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg,
int byteop)
{
void *p;
int highbyte_regs = (ctxt->rex_prefix == 0) && byteop;
if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8)
p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1;
else
p = reg_rmw(ctxt, modrm_reg);
return p;
}
static int read_descriptor(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
u16 *size, unsigned long *address, int op_bytes)
{
int rc;
if (op_bytes == 2)
op_bytes = 3;
*address = 0;
rc = segmented_read_std(ctxt, addr, size, 2);
if (rc != X86EMUL_CONTINUE)
return rc;
addr.ea += 2;
rc = segmented_read_std(ctxt, addr, address, op_bytes);
return rc;
}
FASTOP2(add);
FASTOP2(or);
FASTOP2(adc);
FASTOP2(sbb);
FASTOP2(and);
FASTOP2(sub);
FASTOP2(xor);
FASTOP2(cmp);
FASTOP2(test);
FASTOP1SRC2(mul, mul_ex);
FASTOP1SRC2(imul, imul_ex);
FASTOP1SRC2EX(div, div_ex);
FASTOP1SRC2EX(idiv, idiv_ex);
FASTOP3WCL(shld);
FASTOP3WCL(shrd);
FASTOP2W(imul);
FASTOP1(not);
FASTOP1(neg);
FASTOP1(inc);
FASTOP1(dec);
FASTOP2CL(rol);
FASTOP2CL(ror);
FASTOP2CL(rcl);
FASTOP2CL(rcr);
FASTOP2CL(shl);
FASTOP2CL(shr);
FASTOP2CL(sar);
FASTOP2W(bsf);
FASTOP2W(bsr);
FASTOP2W(bt);
FASTOP2W(bts);
FASTOP2W(btr);
FASTOP2W(btc);
FASTOP2(xadd);
FASTOP2R(cmp, cmp_r);
static int em_bsf_c(struct x86_emulate_ctxt *ctxt)
{
/* If src is zero, do not writeback, but update flags */
if (ctxt->src.val == 0)
ctxt->dst.type = OP_NONE;
return fastop(ctxt, em_bsf);
}
static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
{
/* If src is zero, do not writeback, but update flags */
if (ctxt->src.val == 0)
ctxt->dst.type = OP_NONE;
return fastop(ctxt, em_bsr);
}
static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
{
u8 rc;
void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
asm("push %[flags]; popf; " CALL_NOSPEC
: "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags));
return rc;
}
static void fetch_register_operand(struct operand *op)
{
switch (op->bytes) {
case 1:
op->val = *(u8 *)op->addr.reg;
break;
case 2:
op->val = *(u16 *)op->addr.reg;
break;
case 4:
op->val = *(u32 *)op->addr.reg;
break;
case 8:
op->val = *(u64 *)op->addr.reg;
break;
}
}
static int em_fninit(struct x86_emulate_ctxt *ctxt)
{
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
kvm_fpu_get();
asm volatile("fninit");
kvm_fpu_put();
return X86EMUL_CONTINUE;
}
static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
{
u16 fcw;
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
kvm_fpu_get();
asm volatile("fnstcw %0": "+m"(fcw));
kvm_fpu_put();
ctxt->dst.val = fcw;
return X86EMUL_CONTINUE;
}
static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
{
u16 fsw;
if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
return emulate_nm(ctxt);
kvm_fpu_get();
asm volatile("fnstsw %0": "+m"(fsw));
kvm_fpu_put();
ctxt->dst.val = fsw;
return X86EMUL_CONTINUE;
}
static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
struct operand *op)
{
unsigned int reg;
if (ctxt->d & ModRM)
reg = ctxt->modrm_reg;
else
reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3);
if (ctxt->d & Sse) {
op->type = OP_XMM;
op->bytes = 16;
op->addr.xmm = reg;
kvm_read_sse_reg(reg, &op->vec_val);
return;
}
if (ctxt->d & Mmx) {
reg &= 7;
op->type = OP_MM;
op->bytes = 8;
op->addr.mm = reg;
return;
}
op->type = OP_REG;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp);
fetch_register_operand(op);
op->orig_val = op->val;
}
static void adjust_modrm_seg(struct x86_emulate_ctxt *ctxt, int base_reg)
{
if (base_reg == VCPU_REGS_RSP || base_reg == VCPU_REGS_RBP)
ctxt->modrm_seg = VCPU_SREG_SS;
}
static int decode_modrm(struct x86_emulate_ctxt *ctxt,
struct operand *op)
{
u8 sib;
int index_reg, base_reg, scale;
int rc = X86EMUL_CONTINUE;
ulong modrm_ea = 0;
ctxt->modrm_reg = ((ctxt->rex_prefix << 1) & 8); /* REX.R */
index_reg = (ctxt->rex_prefix << 2) & 8; /* REX.X */
base_reg = (ctxt->rex_prefix << 3) & 8; /* REX.B */
ctxt->modrm_mod = (ctxt->modrm & 0xc0) >> 6;
ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3;
ctxt->modrm_rm = base_reg | (ctxt->modrm & 0x07);
ctxt->modrm_seg = VCPU_SREG_DS;
if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) {
op->type = OP_REG;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
ctxt->d & ByteOp);
if (ctxt->d & Sse) {
op->type = OP_XMM;
op->bytes = 16;
op->addr.xmm = ctxt->modrm_rm;
kvm_read_sse_reg(ctxt->modrm_rm, &op->vec_val);
return rc;
}
if (ctxt->d & Mmx) {
op->type = OP_MM;
op->bytes = 8;
op->addr.mm = ctxt->modrm_rm & 7;
return rc;
}
fetch_register_operand(op);
return rc;
}
op->type = OP_MEM;
if (ctxt->ad_bytes == 2) {
unsigned bx = reg_read(ctxt, VCPU_REGS_RBX);
unsigned bp = reg_read(ctxt, VCPU_REGS_RBP);
unsigned si = reg_read(ctxt, VCPU_REGS_RSI);
unsigned di = reg_read(ctxt, VCPU_REGS_RDI);
/* 16-bit ModR/M decode. */
switch (ctxt->modrm_mod) {
case 0:
if (ctxt->modrm_rm == 6)
modrm_ea += insn_fetch(u16, ctxt);
break;
case 1:
modrm_ea += insn_fetch(s8, ctxt);
break;
case 2:
modrm_ea += insn_fetch(u16, ctxt);
break;
}
switch (ctxt->modrm_rm) {
case 0:
modrm_ea += bx + si;
break;
case 1:
modrm_ea += bx + di;
break;
case 2:
modrm_ea += bp + si;
break;
case 3:
modrm_ea += bp + di;
break;
case 4:
modrm_ea += si;
break;
case 5:
modrm_ea += di;
break;
case 6:
if (ctxt->modrm_mod != 0)
modrm_ea += bp;
break;
case 7:
modrm_ea += bx;
break;
}
if (ctxt->modrm_rm == 2 || ctxt->modrm_rm == 3 ||
(ctxt->modrm_rm == 6 && ctxt->modrm_mod != 0))
ctxt->modrm_seg = VCPU_SREG_SS;
modrm_ea = (u16)modrm_ea;
} else {
/* 32/64-bit ModR/M decode. */
if ((ctxt->modrm_rm & 7) == 4) {
sib = insn_fetch(u8, ctxt);
index_reg |= (sib >> 3) & 7;
base_reg |= sib & 7;
scale = sib >> 6;
if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0)
modrm_ea += insn_fetch(s32, ctxt);
else {
modrm_ea += reg_read(ctxt, base_reg);
adjust_modrm_seg(ctxt, base_reg);
/* Increment ESP on POP [ESP] */
if ((ctxt->d & IncSP) &&
base_reg == VCPU_REGS_RSP)
modrm_ea += ctxt->op_bytes;
}
if (index_reg != 4)
modrm_ea += reg_read(ctxt, index_reg) << scale;
} else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) {
modrm_ea += insn_fetch(s32, ctxt);
if (ctxt->mode == X86EMUL_MODE_PROT64)
ctxt->rip_relative = 1;
} else {
base_reg = ctxt->modrm_rm;
modrm_ea += reg_read(ctxt, base_reg);
adjust_modrm_seg(ctxt, base_reg);
}
switch (ctxt->modrm_mod) {
case 1:
modrm_ea += insn_fetch(s8, ctxt);
break;
case 2:
modrm_ea += insn_fetch(s32, ctxt);
break;
}
}
op->addr.mem.ea = modrm_ea;
if (ctxt->ad_bytes != 8)
ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea;
done:
return rc;
}
static int decode_abs(struct x86_emulate_ctxt *ctxt,
struct operand *op)
{
int rc = X86EMUL_CONTINUE;
op->type = OP_MEM;
switch (ctxt->ad_bytes) {
case 2:
op->addr.mem.ea = insn_fetch(u16, ctxt);
break;
case 4:
op->addr.mem.ea = insn_fetch(u32, ctxt);
break;
case 8:
op->addr.mem.ea = insn_fetch(u64, ctxt);
break;
}
done:
return rc;
}
static void fetch_bit_operand(struct x86_emulate_ctxt *ctxt)
{
long sv = 0, mask;
if (ctxt->dst.type == OP_MEM && ctxt->src.type == OP_REG) {
mask = ~((long)ctxt->dst.bytes * 8 - 1);
if (ctxt->src.bytes == 2)
sv = (s16)ctxt->src.val & (s16)mask;
else if (ctxt->src.bytes == 4)
sv = (s32)ctxt->src.val & (s32)mask;
else
sv = (s64)ctxt->src.val & (s64)mask;
ctxt->dst.addr.mem.ea = address_mask(ctxt,
ctxt->dst.addr.mem.ea + (sv >> 3));
}
/* only subword offset */
ctxt->src.val &= (ctxt->dst.bytes << 3) - 1;
}
static int read_emulated(struct x86_emulate_ctxt *ctxt,
unsigned long addr, void *dest, unsigned size)
{
int rc;
struct read_cache *mc = &ctxt->mem_read;
if (mc->pos < mc->end)
goto read_cached;
if (KVM_EMULATOR_BUG_ON((mc->end + size) >= sizeof(mc->data), ctxt))
return X86EMUL_UNHANDLEABLE;
rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, size,
&ctxt->exception);
if (rc != X86EMUL_CONTINUE)
return rc;
mc->end += size;
read_cached:
memcpy(dest, mc->data + mc->pos, size);
mc->pos += size;
return X86EMUL_CONTINUE;
}
static int segmented_read(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
void *data,
unsigned size)
{
int rc;
ulong linear;
rc = linearize(ctxt, addr, size, false, &linear);
if (rc != X86EMUL_CONTINUE)
return rc;
return read_emulated(ctxt, linear, data, size);
}
static int segmented_write(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
const void *data,
unsigned size)
{
int rc;
ulong linear;
rc = linearize(ctxt, addr, size, true, &linear);
if (rc != X86EMUL_CONTINUE)
return rc;
return ctxt->ops->write_emulated(ctxt, linear, data, size,
&ctxt->exception);
}
static int segmented_cmpxchg(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
const void *orig_data, const void *data,
unsigned size)
{
int rc;
ulong linear;
rc = linearize(ctxt, addr, size, true, &linear);
if (rc != X86EMUL_CONTINUE)
return rc;
return ctxt->ops->cmpxchg_emulated(ctxt, linear, orig_data, data,
size, &ctxt->exception);
}
static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
unsigned int size, unsigned short port,
void *dest)
{
struct read_cache *rc = &ctxt->io_read;
if (rc->pos == rc->end) { /* refill pio read ahead */
unsigned int in_page, n;
unsigned int count = ctxt->rep_prefix ?
address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1;
in_page = (ctxt->eflags & X86_EFLAGS_DF) ?
offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) :
PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI));
n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count);
if (n == 0)
n = 1;
rc->pos = rc->end = 0;
if (!ctxt->ops->pio_in_emulated(ctxt, size, port, rc->data, n))
return 0;
rc->end = n * size;
}
if (ctxt->rep_prefix && (ctxt->d & String) &&
!(ctxt->eflags & X86_EFLAGS_DF)) {
ctxt->dst.data = rc->data + rc->pos;
ctxt->dst.type = OP_MEM_STR;
ctxt->dst.count = (rc->end - rc->pos) / size;
rc->pos = rc->end;
} else {
memcpy(dest, rc->data + rc->pos, size);
rc->pos += size;
}
return 1;
}
static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt,
u16 index, struct desc_struct *desc)
{
struct desc_ptr dt;
ulong addr;
ctxt->ops->get_idt(ctxt, &dt);
if (dt.size < index * 8 + 7)
return emulate_gp(ctxt, index << 3 | 0x2);
addr = dt.address + index * 8;
return linear_read_system(ctxt, addr, desc, sizeof(*desc));
}
static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
u16 selector, struct desc_ptr *dt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
u32 base3 = 0;
if (selector & 1 << 2) {
struct desc_struct desc;
u16 sel;
memset(dt, 0, sizeof(*dt));
if (!ops->get_segment(ctxt, &sel, &desc, &base3,
VCPU_SREG_LDTR))
return;
dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */
dt->address = get_desc_base(&desc) | ((u64)base3 << 32);
} else
ops->get_gdt(ctxt, dt);
}
static int get_descriptor_ptr(struct x86_emulate_ctxt *ctxt,
u16 selector, ulong *desc_addr_p)
{
struct desc_ptr dt;
u16 index = selector >> 3;
ulong addr;
get_descriptor_table_ptr(ctxt, selector, &dt);
if (dt.size < index * 8 + 7)
return emulate_gp(ctxt, selector & 0xfffc);
addr = dt.address + index * 8;
#ifdef CONFIG_X86_64
if (addr >> 32 != 0) {
u64 efer = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (!(efer & EFER_LMA))
addr &= (u32)-1;
}
#endif
*desc_addr_p = addr;
return X86EMUL_CONTINUE;
}
/* allowed just for 8 bytes segments */
static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, struct desc_struct *desc,
ulong *desc_addr_p)
{
int rc;
rc = get_descriptor_ptr(ctxt, selector, desc_addr_p);
if (rc != X86EMUL_CONTINUE)
return rc;
return linear_read_system(ctxt, *desc_addr_p, desc, sizeof(*desc));
}
/* allowed just for 8 bytes segments */
static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, struct desc_struct *desc)
{
int rc;
ulong addr;
rc = get_descriptor_ptr(ctxt, selector, &addr);
if (rc != X86EMUL_CONTINUE)
return rc;
return linear_write_system(ctxt, addr, desc, sizeof(*desc));
}
static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg, u8 cpl,
enum x86_transfer_type transfer,
struct desc_struct *desc)
{
struct desc_struct seg_desc, old_desc;
u8 dpl, rpl;
unsigned err_vec = GP_VECTOR;
u32 err_code = 0;
bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
ulong desc_addr;
int ret;
u16 dummy;
u32 base3 = 0;
memset(&seg_desc, 0, sizeof(seg_desc));
if (ctxt->mode == X86EMUL_MODE_REAL) {
/* set real mode segment descriptor (keep limit etc. for
* unreal mode) */
ctxt->ops->get_segment(ctxt, &dummy, &seg_desc, NULL, seg);
set_desc_base(&seg_desc, selector << 4);
goto load;
} else if (seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) {
/* VM86 needs a clean new segment descriptor */
set_desc_base(&seg_desc, selector << 4);
set_desc_limit(&seg_desc, 0xffff);
seg_desc.type = 3;
seg_desc.p = 1;
seg_desc.s = 1;
seg_desc.dpl = 3;
goto load;
}
rpl = selector & 3;
/* TR should be in GDT only */
if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
goto exception;
/* NULL selector is not valid for TR, CS and (except for long mode) SS */
if (null_selector) {
if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR)
goto exception;
if (seg == VCPU_SREG_SS) {
if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)
goto exception;
/*
* ctxt->ops->set_segment expects the CPL to be in
* SS.DPL, so fake an expand-up 32-bit data segment.
*/
seg_desc.type = 3;
seg_desc.p = 1;
seg_desc.s = 1;
seg_desc.dpl = cpl;
seg_desc.d = 1;
seg_desc.g = 1;
}
/* Skip all following checks */
goto load;
}
ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr);
if (ret != X86EMUL_CONTINUE)
return ret;
err_code = selector & 0xfffc;
err_vec = (transfer == X86_TRANSFER_TASK_SWITCH) ? TS_VECTOR :
GP_VECTOR;
/* can't load system descriptor into segment selector */
if (seg <= VCPU_SREG_GS && !seg_desc.s) {
if (transfer == X86_TRANSFER_CALL_JMP)
return X86EMUL_UNHANDLEABLE;
goto exception;
}
dpl = seg_desc.dpl;
switch (seg) {
case VCPU_SREG_SS:
/*
* segment is not a writable data segment or segment
* selector's RPL != CPL or DPL != CPL
*/
if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl)
goto exception;
break;
case VCPU_SREG_CS:
/*
* KVM uses "none" when loading CS as part of emulating Real
* Mode exceptions and IRET (handled above). In all other
* cases, loading CS without a control transfer is a KVM bug.
*/
if (WARN_ON_ONCE(transfer == X86_TRANSFER_NONE))
goto exception;
if (!(seg_desc.type & 8))
goto exception;
if (transfer == X86_TRANSFER_RET) {
/* RET can never return to an inner privilege level. */
if (rpl < cpl)
goto exception;
/* Outer-privilege level return is not implemented */
if (rpl > cpl)
return X86EMUL_UNHANDLEABLE;
}
if (transfer == X86_TRANSFER_RET || transfer == X86_TRANSFER_TASK_SWITCH) {
if (seg_desc.type & 4) {
/* conforming */
if (dpl > rpl)
goto exception;
} else {
/* nonconforming */
if (dpl != rpl)
goto exception;
}
} else { /* X86_TRANSFER_CALL_JMP */
if (seg_desc.type & 4) {
/* conforming */
if (dpl > cpl)
goto exception;
} else {
/* nonconforming */
if (rpl > cpl || dpl != cpl)
goto exception;
}
}
/* in long-mode d/b must be clear if l is set */
if (seg_desc.d && seg_desc.l) {
u64 efer = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (efer & EFER_LMA)
goto exception;
}
/* CS(RPL) <- CPL */
selector = (selector & 0xfffc) | cpl;
break;
case VCPU_SREG_TR:
if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
goto exception;
break;
case VCPU_SREG_LDTR:
if (seg_desc.s || seg_desc.type != 2)
goto exception;
break;
default: /* DS, ES, FS, or GS */
/*
* segment is not a data or readable code segment or
* ((segment is a data or nonconforming code segment)
* and ((RPL > DPL) or (CPL > DPL)))
*/
if ((seg_desc.type & 0xa) == 0x8 ||
(((seg_desc.type & 0xc) != 0xc) &&
(rpl > dpl || cpl > dpl)))
goto exception;
break;
}
if (!seg_desc.p) {
err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
goto exception;
}
if (seg_desc.s) {
/* mark segment as accessed */
if (!(seg_desc.type & 1)) {
seg_desc.type |= 1;
ret = write_segment_descriptor(ctxt, selector,
&seg_desc);
if (ret != X86EMUL_CONTINUE)
return ret;
}
} else if (ctxt->mode == X86EMUL_MODE_PROT64) {
ret = linear_read_system(ctxt, desc_addr+8, &base3, sizeof(base3));
if (ret != X86EMUL_CONTINUE)
return ret;
if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
((u64)base3 << 32), ctxt))
return emulate_gp(ctxt, err_code);
}
if (seg == VCPU_SREG_TR) {
old_desc = seg_desc;
seg_desc.type |= 2; /* busy */
ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc,
sizeof(seg_desc), &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
return ret;
}
load:
ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
if (desc)
*desc = seg_desc;
return X86EMUL_CONTINUE;
exception:
return emulate_exception(ctxt, err_vec, err_code, true);
}
static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg)
{
u8 cpl = ctxt->ops->cpl(ctxt);
/*
* None of MOV, POP and LSS can load a NULL selector in CPL=3, but
* they can load it at CPL<3 (Intel's manual says only LSS can,
* but it's wrong).
*
* However, the Intel manual says that putting IST=1/DPL=3 in
* an interrupt gate will result in SS=3 (the AMD manual instead
* says it doesn't), so allow SS=3 in __load_segment_descriptor
* and only forbid it here.
*/
if (seg == VCPU_SREG_SS && selector == 3 &&
ctxt->mode == X86EMUL_MODE_PROT64)
return emulate_exception(ctxt, GP_VECTOR, 0, true);
return __load_segment_descriptor(ctxt, selector, seg, cpl,
X86_TRANSFER_NONE, NULL);
}
static void write_register_operand(struct operand *op)
{
return assign_register(op->addr.reg, op->val, op->bytes);
}
static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op)
{
switch (op->type) {
case OP_REG:
write_register_operand(op);
break;
case OP_MEM:
if (ctxt->lock_prefix)
return segmented_cmpxchg(ctxt,
op->addr.mem,
&op->orig_val,
&op->val,
op->bytes);
else
return segmented_write(ctxt,
op->addr.mem,
&op->val,
op->bytes);
case OP_MEM_STR:
return segmented_write(ctxt,
op->addr.mem,
op->data,
op->bytes * op->count);
case OP_XMM:
kvm_write_sse_reg(op->addr.xmm, &op->vec_val);
break;
case OP_MM:
kvm_write_mmx_reg(op->addr.mm, &op->mm_val);
break;
case OP_NONE:
/* no writeback */
break;
default:
break;
}
return X86EMUL_CONTINUE;
}
static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes)
{
struct segmented_address addr;
rsp_increment(ctxt, -bytes);
addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
return segmented_write(ctxt, addr, data, bytes);
}
static int em_push(struct x86_emulate_ctxt *ctxt)
{
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
return push(ctxt, &ctxt->src.val, ctxt->op_bytes);
}
static int emulate_pop(struct x86_emulate_ctxt *ctxt,
void *dest, int len)
{
int rc;
struct segmented_address addr;
addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
rc = segmented_read(ctxt, addr, dest, len);
if (rc != X86EMUL_CONTINUE)
return rc;
rsp_increment(ctxt, len);
return rc;
}
static int em_pop(struct x86_emulate_ctxt *ctxt)
{
return emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
}
static int emulate_popf(struct x86_emulate_ctxt *ctxt,
void *dest, int len)
{
int rc;
unsigned long val, change_mask;
int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT;
int cpl = ctxt->ops->cpl(ctxt);
rc = emulate_pop(ctxt, &val, len);
if (rc != X86EMUL_CONTINUE)
return rc;
change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF |
X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT |
X86_EFLAGS_AC | X86_EFLAGS_ID;
switch(ctxt->mode) {
case X86EMUL_MODE_PROT64:
case X86EMUL_MODE_PROT32:
case X86EMUL_MODE_PROT16:
if (cpl == 0)
change_mask |= X86_EFLAGS_IOPL;
if (cpl <= iopl)
change_mask |= X86_EFLAGS_IF;
break;
case X86EMUL_MODE_VM86:
if (iopl < 3)
return emulate_gp(ctxt, 0);
change_mask |= X86_EFLAGS_IF;
break;
default: /* real mode */
change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF);
break;
}
*(unsigned long *)dest =
(ctxt->eflags & ~change_mask) | (val & change_mask);
return rc;
}
static int em_popf(struct x86_emulate_ctxt *ctxt)
{
ctxt->dst.type = OP_REG;
ctxt->dst.addr.reg = &ctxt->eflags;
ctxt->dst.bytes = ctxt->op_bytes;
return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes);
}
static int em_enter(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned frame_size = ctxt->src.val;
unsigned nesting_level = ctxt->src2.val & 31;
ulong rbp;
if (nesting_level)
return X86EMUL_UNHANDLEABLE;
rbp = reg_read(ctxt, VCPU_REGS_RBP);
rc = push(ctxt, &rbp, stack_size(ctxt));
if (rc != X86EMUL_CONTINUE)
return rc;
assign_masked(reg_rmw(ctxt, VCPU_REGS_RBP), reg_read(ctxt, VCPU_REGS_RSP),
stack_mask(ctxt));
assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP),
reg_read(ctxt, VCPU_REGS_RSP) - frame_size,
stack_mask(ctxt));
return X86EMUL_CONTINUE;
}
static int em_leave(struct x86_emulate_ctxt *ctxt)
{
assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP), reg_read(ctxt, VCPU_REGS_RBP),
stack_mask(ctxt));
return emulate_pop(ctxt, reg_rmw(ctxt, VCPU_REGS_RBP), ctxt->op_bytes);
}
static int em_push_sreg(struct x86_emulate_ctxt *ctxt)
{
int seg = ctxt->src2.val;
ctxt->src.val = get_segment_selector(ctxt, seg);
if (ctxt->op_bytes == 4) {
rsp_increment(ctxt, -2);
ctxt->op_bytes = 2;
}
return em_push(ctxt);
}
static int em_pop_sreg(struct x86_emulate_ctxt *ctxt)
{
int seg = ctxt->src2.val;
unsigned long selector;
int rc;
rc = emulate_pop(ctxt, &selector, 2);
if (rc != X86EMUL_CONTINUE)
return rc;
if (seg == VCPU_SREG_SS)
ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS;
if (ctxt->op_bytes > 2)
rsp_increment(ctxt, ctxt->op_bytes - 2);
rc = load_segment_descriptor(ctxt, (u16)selector, seg);
return rc;
}
static int em_pusha(struct x86_emulate_ctxt *ctxt)
{
unsigned long old_esp = reg_read(ctxt, VCPU_REGS_RSP);
int rc = X86EMUL_CONTINUE;
int reg = VCPU_REGS_RAX;
while (reg <= VCPU_REGS_RDI) {
(reg == VCPU_REGS_RSP) ?
(ctxt->src.val = old_esp) : (ctxt->src.val = reg_read(ctxt, reg));
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
++reg;
}
return rc;
}
static int em_pushf(struct x86_emulate_ctxt *ctxt)
{
ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM;
return em_push(ctxt);
}
static int em_popa(struct x86_emulate_ctxt *ctxt)
{
int rc = X86EMUL_CONTINUE;
int reg = VCPU_REGS_RDI;
u32 val;
while (reg >= VCPU_REGS_RAX) {
if (reg == VCPU_REGS_RSP) {
rsp_increment(ctxt, ctxt->op_bytes);
--reg;
}
rc = emulate_pop(ctxt, &val, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
break;
assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes);
--reg;
}
return rc;
}
static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
{
const struct x86_emulate_ops *ops = ctxt->ops;
int rc;
struct desc_ptr dt;
gva_t cs_addr;
gva_t eip_addr;
u16 cs, eip;
/* TODO: Add limit checks */
ctxt->src.val = ctxt->eflags;
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC);
ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS);
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->src.val = ctxt->_eip;
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
ops->get_idt(ctxt, &dt);
eip_addr = dt.address + (irq << 2);
cs_addr = dt.address + (irq << 2) + 2;
rc = linear_read_system(ctxt, cs_addr, &cs, 2);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = linear_read_system(ctxt, eip_addr, &eip, 2);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = load_segment_descriptor(ctxt, cs, VCPU_SREG_CS);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->_eip = eip;
return rc;
}
int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
{
int rc;
invalidate_registers(ctxt);
rc = __emulate_int_real(ctxt, irq);
if (rc == X86EMUL_CONTINUE)
writeback_registers(ctxt);
return rc;
}
static int emulate_int(struct x86_emulate_ctxt *ctxt, int irq)
{
switch(ctxt->mode) {
case X86EMUL_MODE_REAL:
return __emulate_int_real(ctxt, irq);
case X86EMUL_MODE_VM86:
case X86EMUL_MODE_PROT16:
case X86EMUL_MODE_PROT32:
case X86EMUL_MODE_PROT64:
default:
/* Protected mode interrupts unimplemented yet */
return X86EMUL_UNHANDLEABLE;
}
}
static int emulate_iret_real(struct x86_emulate_ctxt *ctxt)
{
int rc = X86EMUL_CONTINUE;
unsigned long temp_eip = 0;
unsigned long temp_eflags = 0;
unsigned long cs = 0;
unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF |
X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF |
X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF |
X86_EFLAGS_AC | X86_EFLAGS_ID |
X86_EFLAGS_FIXED;
unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF |
X86_EFLAGS_VIP;
/* TODO: Add stack limit check */
rc = emulate_pop(ctxt, &temp_eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
if (temp_eip & ~0xffff)
return emulate_gp(ctxt, 0);
rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = emulate_pop(ctxt, &temp_eflags, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->_eip = temp_eip;
if (ctxt->op_bytes == 4)
ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask));
else if (ctxt->op_bytes == 2) {
ctxt->eflags &= ~0xffff;
ctxt->eflags |= temp_eflags;
}
ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */
ctxt->eflags |= X86_EFLAGS_FIXED;
ctxt->ops->set_nmi_mask(ctxt, false);
return rc;
}
static int em_iret(struct x86_emulate_ctxt *ctxt)
{
switch(ctxt->mode) {
case X86EMUL_MODE_REAL:
return emulate_iret_real(ctxt);
case X86EMUL_MODE_VM86:
case X86EMUL_MODE_PROT16:
case X86EMUL_MODE_PROT32:
case X86EMUL_MODE_PROT64:
default:
/* iret from protected mode unimplemented yet */
return X86EMUL_UNHANDLEABLE;
}
}
static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned short sel;
struct desc_struct new_desc;
u8 cpl = ctxt->ops->cpl(ctxt);
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
X86_TRANSFER_CALL_JMP,
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = assign_eip_far(ctxt, ctxt->src.val);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
return rc;
}
static int em_jmp_abs(struct x86_emulate_ctxt *ctxt)
{
return assign_eip_near(ctxt, ctxt->src.val);
}
static int em_call_near_abs(struct x86_emulate_ctxt *ctxt)
{
int rc;
long int old_eip;
old_eip = ctxt->_eip;
rc = assign_eip_near(ctxt, ctxt->src.val);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->src.val = old_eip;
rc = em_push(ctxt);
return rc;
}
static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
{
u64 old = ctxt->dst.orig_val64;
if (ctxt->dst.bytes == 16)
return X86EMUL_UNHANDLEABLE;
if (((u32) (old >> 0) != (u32) reg_read(ctxt, VCPU_REGS_RAX)) ||
((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) {
*reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0);
*reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32);
ctxt->eflags &= ~X86_EFLAGS_ZF;
} else {
ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) |
(u32) reg_read(ctxt, VCPU_REGS_RBX);
ctxt->eflags |= X86_EFLAGS_ZF;
}
return X86EMUL_CONTINUE;
}
static int em_ret(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long eip;
rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
return assign_eip_near(ctxt, eip);
}
static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
unsigned long eip, cs;
int cpl = ctxt->ops->cpl(ctxt);
struct desc_struct new_desc;
rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl,
X86_TRANSFER_RET,
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
rc = assign_eip_far(ctxt, eip);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
return rc;
}
static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
{
int rc;
rc = em_ret_far(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
rsp_increment(ctxt, ctxt->src.val);
return X86EMUL_CONTINUE;
}
static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
{
/* Save real source value, then compare EAX against destination. */
ctxt->dst.orig_val = ctxt->dst.val;
ctxt->dst.val = reg_read(ctxt, VCPU_REGS_RAX);
ctxt->src.orig_val = ctxt->src.val;
ctxt->src.val = ctxt->dst.orig_val;
fastop(ctxt, em_cmp);
if (ctxt->eflags & X86_EFLAGS_ZF) {
/* Success: write back to memory; no update of EAX */
ctxt->src.type = OP_NONE;
ctxt->dst.val = ctxt->src.orig_val;
} else {
/* Failure: write the value we saw to EAX. */
ctxt->src.type = OP_REG;
ctxt->src.addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX);
ctxt->src.val = ctxt->dst.orig_val;
/* Create write-cycle to dest by writing the same value */
ctxt->dst.val = ctxt->dst.orig_val;
}
return X86EMUL_CONTINUE;
}
static int em_lseg(struct x86_emulate_ctxt *ctxt)
{
int seg = ctxt->src2.val;
unsigned short sel;
int rc;
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
rc = load_segment_descriptor(ctxt, sel, seg);
if (rc != X86EMUL_CONTINUE)
return rc;
ctxt->dst.val = ctxt->src.val;
return rc;
}
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
if (!ctxt->ops->is_smm(ctxt))
return emulate_ud(ctxt);
if (ctxt->ops->leave_smm(ctxt))
ctxt->ops->triple_fault(ctxt);
return emulator_recalc_and_set_mode(ctxt);
}
static void
setup_syscalls_segments(struct desc_struct *cs, struct desc_struct *ss)
{
cs->l = 0; /* will be adjusted later */
set_desc_base(cs, 0); /* flat segment */
cs->g = 1; /* 4kb granularity */
set_desc_limit(cs, 0xfffff); /* 4GB limit */
cs->type = 0x0b; /* Read, Execute, Accessed */
cs->s = 1;
cs->dpl = 0; /* will be adjusted later */
cs->p = 1;
cs->d = 1;
cs->avl = 0;
set_desc_base(ss, 0); /* flat segment */
set_desc_limit(ss, 0xfffff); /* 4GB limit */
ss->g = 1; /* 4kb granularity */
ss->s = 1;
ss->type = 0x03; /* Read/Write, Accessed */
ss->d = 1; /* 32bit stack segment */
ss->dpl = 0;
ss->p = 1;
ss->l = 0;
ss->avl = 0;
}
static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
{
u32 eax, ebx, ecx, edx;
eax = ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
return is_guest_vendor_intel(ebx, ecx, edx);
}
static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
u32 eax, ebx, ecx, edx;
/*
* syscall should always be enabled in longmode - so only become
* vendor specific (cpuid) if other modes are active...
*/
if (ctxt->mode == X86EMUL_MODE_PROT64)
return true;
eax = 0x00000000;
ecx = 0x00000000;
ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true);
/*
* remark: Intel CPUs only support "syscall" in 64bit longmode. Also a
* 64bit guest with a 32bit compat-app running will #UD !! While this
* behaviour can be fixed (by emulating) into AMD response - CPUs of
* AMD can't behave like Intel.
*/
if (is_guest_vendor_intel(ebx, ecx, edx))
return false;
if (is_guest_vendor_amd(ebx, ecx, edx) ||
is_guest_vendor_hygon(ebx, ecx, edx))
return true;
/*
* default: (not Intel, not AMD, not Hygon), apply Intel's
* stricter rules...
*/
return false;
}
static int em_syscall(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data;
u16 cs_sel, ss_sel;
u64 efer = 0;
/* syscall is not available in real mode */
if (ctxt->mode == X86EMUL_MODE_REAL ||
ctxt->mode == X86EMUL_MODE_VM86)
return emulate_ud(ctxt);
if (!(em_syscall_is_enabled(ctxt)))
return emulate_ud(ctxt);
ops->get_msr(ctxt, MSR_EFER, &efer);
if (!(efer & EFER_SCE))
return emulate_ud(ctxt);
setup_syscalls_segments(&cs, &ss);
ops->get_msr(ctxt, MSR_STAR, &msr_data);
msr_data >>= 32;
cs_sel = (u16)(msr_data & 0xfffc);
ss_sel = (u16)(msr_data + 8);
if (efer & EFER_LMA) {
cs.d = 0;
cs.l = 1;
}
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
*reg_write(ctxt, VCPU_REGS_RCX) = ctxt->_eip;
if (efer & EFER_LMA) {
#ifdef CONFIG_X86_64
*reg_write(ctxt, VCPU_REGS_R11) = ctxt->eflags;
ops->get_msr(ctxt,
ctxt->mode == X86EMUL_MODE_PROT64 ?
MSR_LSTAR : MSR_CSTAR, &msr_data);
ctxt->_eip = msr_data;
ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data);
ctxt->eflags &= ~msr_data;
ctxt->eflags |= X86_EFLAGS_FIXED;
#endif
} else {
/* legacy mode */
ops->get_msr(ctxt, MSR_STAR, &msr_data);
ctxt->_eip = (u32)msr_data;
ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
}
ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
return X86EMUL_CONTINUE;
}
static int em_sysenter(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data;
u16 cs_sel, ss_sel;
u64 efer = 0;
ops->get_msr(ctxt, MSR_EFER, &efer);
/* inject #GP if in real mode */
if (ctxt->mode == X86EMUL_MODE_REAL)
return emulate_gp(ctxt, 0);
/*
* Not recognized on AMD in compat mode (but is recognized in legacy
* mode).
*/
if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA)
&& !vendor_intel(ctxt))
return emulate_ud(ctxt);
/* sysenter/sysexit have not been tested in 64bit mode. */
if (ctxt->mode == X86EMUL_MODE_PROT64)
return X86EMUL_UNHANDLEABLE;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
if ((msr_data & 0xfffc) == 0x0)
return emulate_gp(ctxt, 0);
setup_syscalls_segments(&cs, &ss);
ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK;
ss_sel = cs_sel + 8;
if (efer & EFER_LMA) {
cs.d = 0;
cs.l = 1;
}
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data);
ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
(u32)msr_data;
if (efer & EFER_LMA)
ctxt->mode = X86EMUL_MODE_PROT64;
return X86EMUL_CONTINUE;
}
static int em_sysexit(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data, rcx, rdx;
int usermode;
u16 cs_sel = 0, ss_sel = 0;
/* inject #GP if in real mode or Virtual 8086 mode */
if (ctxt->mode == X86EMUL_MODE_REAL ||
ctxt->mode == X86EMUL_MODE_VM86)
return emulate_gp(ctxt, 0);
setup_syscalls_segments(&cs, &ss);
if ((ctxt->rex_prefix & 0x8) != 0x0)
usermode = X86EMUL_MODE_PROT64;
else
usermode = X86EMUL_MODE_PROT32;
rcx = reg_read(ctxt, VCPU_REGS_RCX);
rdx = reg_read(ctxt, VCPU_REGS_RDX);
cs.dpl = 3;
ss.dpl = 3;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
switch (usermode) {
case X86EMUL_MODE_PROT32:
cs_sel = (u16)(msr_data + 16);
if ((msr_data & 0xfffc) == 0x0)
return emulate_gp(ctxt, 0);
ss_sel = (u16)(msr_data + 24);
rcx = (u32)rcx;
rdx = (u32)rdx;
break;
case X86EMUL_MODE_PROT64:
cs_sel = (u16)(msr_data + 32);
if (msr_data == 0x0)
return emulate_gp(ctxt, 0);
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
if (emul_is_noncanonical_address(rcx, ctxt) ||
emul_is_noncanonical_address(rdx, ctxt))
return emulate_gp(ctxt, 0);
break;
}
cs_sel |= SEGMENT_RPL_MASK;
ss_sel |= SEGMENT_RPL_MASK;
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ctxt->_eip = rdx;
ctxt->mode = usermode;
*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
}
static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
{
int iopl;
if (ctxt->mode == X86EMUL_MODE_REAL)
return false;
if (ctxt->mode == X86EMUL_MODE_VM86)
return true;
iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT;
return ctxt->ops->cpl(ctxt) > iopl;
}
#define VMWARE_PORT_VMPORT (0x5658)
#define VMWARE_PORT_VMRPC (0x5659)
static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
u16 port, u16 len)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct tr_seg;
u32 base3;
int r;
u16 tr, io_bitmap_ptr, perm, bit_idx = port & 0x7;
unsigned mask = (1 << len) - 1;
unsigned long base;
/*
* VMware allows access to these ports even if denied
* by TSS I/O permission bitmap. Mimic behavior.
*/
if (enable_vmware_backdoor &&
((port == VMWARE_PORT_VMPORT) || (port == VMWARE_PORT_VMRPC)))
return true;
ops->get_segment(ctxt, &tr, &tr_seg, &base3, VCPU_SREG_TR);
if (!tr_seg.p)
return false;
if (desc_limit_scaled(&tr_seg) < 103)
return false;
base = get_desc_base(&tr_seg);
#ifdef CONFIG_X86_64
base |= ((u64)base3) << 32;
#endif
r = ops->read_std(ctxt, base + 102, &io_bitmap_ptr, 2, NULL, true);
if (r != X86EMUL_CONTINUE)
return false;
if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg))
return false;
r = ops->read_std(ctxt, base + io_bitmap_ptr + port/8, &perm, 2, NULL, true);
if (r != X86EMUL_CONTINUE)
return false;
if ((perm >> bit_idx) & mask)
return false;
return true;
}
static bool emulator_io_permitted(struct x86_emulate_ctxt *ctxt,
u16 port, u16 len)
{
if (ctxt->perm_ok)
return true;
if (emulator_bad_iopl(ctxt))
if (!emulator_io_port_access_allowed(ctxt, port, len))
return false;
ctxt->perm_ok = true;
return true;
}
static void string_registers_quirk(struct x86_emulate_ctxt *ctxt)
{
/*
* Intel CPUs mask the counter and pointers in quite strange
* manner when ECX is zero due to REP-string optimizations.
*/
#ifdef CONFIG_X86_64
if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt))
return;
*reg_write(ctxt, VCPU_REGS_RCX) = 0;
switch (ctxt->b) {
case 0xa4: /* movsb */
case 0xa5: /* movsd/w */
*reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1;
fallthrough;
case 0xaa: /* stosb */
case 0xab: /* stosd/w */
*reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1;
}
#endif
}
static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
struct tss_segment_16 *tss)
{
tss->ip = ctxt->_eip;
tss->flag = ctxt->eflags;
tss->ax = reg_read(ctxt, VCPU_REGS_RAX);
tss->cx = reg_read(ctxt, VCPU_REGS_RCX);
tss->dx = reg_read(ctxt, VCPU_REGS_RDX);
tss->bx = reg_read(ctxt, VCPU_REGS_RBX);
tss->sp = reg_read(ctxt, VCPU_REGS_RSP);
tss->bp = reg_read(ctxt, VCPU_REGS_RBP);
tss->si = reg_read(ctxt, VCPU_REGS_RSI);
tss->di = reg_read(ctxt, VCPU_REGS_RDI);
tss->es = get_segment_selector(ctxt, VCPU_SREG_ES);
tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS);
tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS);
tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS);
tss->ldt = get_segment_selector(ctxt, VCPU_SREG_LDTR);
}
static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
struct tss_segment_16 *tss)
{
int ret;
u8 cpl;
ctxt->_eip = tss->ip;
ctxt->eflags = tss->flag | 2;
*reg_write(ctxt, VCPU_REGS_RAX) = tss->ax;
*reg_write(ctxt, VCPU_REGS_RCX) = tss->cx;
*reg_write(ctxt, VCPU_REGS_RDX) = tss->dx;
*reg_write(ctxt, VCPU_REGS_RBX) = tss->bx;
*reg_write(ctxt, VCPU_REGS_RSP) = tss->sp;
*reg_write(ctxt, VCPU_REGS_RBP) = tss->bp;
*reg_write(ctxt, VCPU_REGS_RSI) = tss->si;
*reg_write(ctxt, VCPU_REGS_RDI) = tss->di;
/*
* SDM says that segment selectors are loaded before segment
* descriptors
*/
set_segment_selector(ctxt, tss->ldt, VCPU_SREG_LDTR);
set_segment_selector(ctxt, tss->es, VCPU_SREG_ES);
set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS);
set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS);
set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
cpl = tss->cs & 3;
/*
* Now load segment descriptors. If fault happens at this stage
* it is handled in a context of new task
*/
ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
return X86EMUL_CONTINUE;
}
static int task_switch_16(struct x86_emulate_ctxt *ctxt, u16 old_tss_sel,
ulong old_tss_base, struct desc_struct *new_desc)
{
struct tss_segment_16 tss_seg;
int ret;
u32 new_tss_base = get_desc_base(new_desc);
ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof(tss_seg));
if (ret != X86EMUL_CONTINUE)
return ret;
save_state_to_tss16(ctxt, &tss_seg);
ret = linear_write_system(ctxt, old_tss_base, &tss_seg, sizeof(tss_seg));
if (ret != X86EMUL_CONTINUE)
return ret;
ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof(tss_seg));
if (ret != X86EMUL_CONTINUE)
return ret;
if (old_tss_sel != 0xffff) {
tss_seg.prev_task_link = old_tss_sel;
ret = linear_write_system(ctxt, new_tss_base,
&tss_seg.prev_task_link,
sizeof(tss_seg.prev_task_link));
if (ret != X86EMUL_CONTINUE)
return ret;
}
return load_state_from_tss16(ctxt, &tss_seg);
}
static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
struct tss_segment_32 *tss)
{
/* CR3 and ldt selector are not saved intentionally */
tss->eip = ctxt->_eip;
tss->eflags = ctxt->eflags;
tss->eax = reg_read(ctxt, VCPU_REGS_RAX);
tss->ecx = reg_read(ctxt, VCPU_REGS_RCX);
tss->edx = reg_read(ctxt, VCPU_REGS_RDX);
tss->ebx = reg_read(ctxt, VCPU_REGS_RBX);
tss->esp = reg_read(ctxt, VCPU_REGS_RSP);
tss->ebp = reg_read(ctxt, VCPU_REGS_RBP);
tss->esi = reg_read(ctxt, VCPU_REGS_RSI);
tss->edi = reg_read(ctxt, VCPU_REGS_RDI);
tss->es = get_segment_selector(ctxt, VCPU_SREG_ES);
tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS);
tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS);
tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS);
tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS);
tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS);
}
static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
struct tss_segment_32 *tss)
{
int ret;
u8 cpl;
if (ctxt->ops->set_cr(ctxt, 3, tss->cr3))
return emulate_gp(ctxt, 0);
ctxt->_eip = tss->eip;
ctxt->eflags = tss->eflags | 2;
/* General purpose registers */
*reg_write(ctxt, VCPU_REGS_RAX) = tss->eax;
*reg_write(ctxt, VCPU_REGS_RCX) = tss->ecx;
*reg_write(ctxt, VCPU_REGS_RDX) = tss->edx;
*reg_write(ctxt, VCPU_REGS_RBX) = tss->ebx;
*reg_write(ctxt, VCPU_REGS_RSP) = tss->esp;
*reg_write(ctxt, VCPU_REGS_RBP) = tss->ebp;
*reg_write(ctxt, VCPU_REGS_RSI) = tss->esi;
*reg_write(ctxt, VCPU_REGS_RDI) = tss->edi;
/*
* SDM says that segment selectors are loaded before segment
* descriptors. This is important because CPL checks will
* use CS.RPL.
*/
set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR);
set_segment_selector(ctxt, tss->es, VCPU_SREG_ES);
set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS);
set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS);
set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
set_segment_selector(ctxt, tss->fs, VCPU_SREG_FS);
set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS);
/*
* If we're switching between Protected Mode and VM86, we need to make
* sure to update the mode before loading the segment descriptors so
* that the selectors are interpreted correctly.
*/
if (ctxt->eflags & X86_EFLAGS_VM) {
ctxt->mode = X86EMUL_MODE_VM86;
cpl = 3;
} else {
ctxt->mode = X86EMUL_MODE_PROT32;
cpl = tss->cs & 3;
}
/*
* Now load segment descriptors. If fault happens at this stage
* it is handled in a context of new task
*/
ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR,
cpl, X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl,
X86_TRANSFER_TASK_SWITCH, NULL);
return ret;
}
static int task_switch_32(struct x86_emulate_ctxt *ctxt, u16 old_tss_sel,
ulong old_tss_base, struct desc_struct *new_desc)
{
struct tss_segment_32 tss_seg;
int ret;
u32 new_tss_base = get_desc_base(new_desc);
u32 eip_offset = offsetof(struct tss_segment_32, eip);
u32 ldt_sel_offset = offsetof(struct tss_segment_32,