2011-07-26 02:43:53 +08:00
|
|
|
//===-- X86BaseInfo.h - Top level definitions for X86 -------- --*- C++ -*-===//
|
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file contains small standalone helper functions and enum definitions for
|
|
|
|
// the X86 target useful for the compiler back-end and the MC libraries.
|
|
|
|
// As such, it deliberately does not include references to LLVM core
|
|
|
|
// code gen types, passes, etc..
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#ifndef X86BASEINFO_H
|
|
|
|
#define X86BASEINFO_H
|
|
|
|
|
|
|
|
#include "X86MCTargetDesc.h"
|
|
|
|
#include "llvm/Support/DataTypes.h"
|
2012-02-05 13:38:58 +08:00
|
|
|
#include "llvm/Support/ErrorHandling.h"
|
2011-07-26 02:43:53 +08:00
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
|
|
|
namespace X86 {
|
|
|
|
// Enums for memory operand decoding. Each memory operand is represented with
|
|
|
|
// a 5 operand sequence in the form:
|
|
|
|
// [BaseReg, ScaleAmt, IndexReg, Disp, Segment]
|
|
|
|
// These enums help decode this.
|
|
|
|
enum {
|
|
|
|
AddrBaseReg = 0,
|
|
|
|
AddrScaleAmt = 1,
|
|
|
|
AddrIndexReg = 2,
|
|
|
|
AddrDisp = 3,
|
|
|
|
|
|
|
|
/// AddrSegmentReg - The operand # of the segment in the memory operand.
|
|
|
|
AddrSegmentReg = 4,
|
|
|
|
|
|
|
|
/// AddrNumOperands - Total number of operands in a memory reference.
|
|
|
|
AddrNumOperands = 5
|
|
|
|
};
|
|
|
|
} // end namespace X86;
|
|
|
|
|
|
|
|
|
|
|
|
/// X86II - This namespace holds all of the target specific flags that
|
|
|
|
/// instruction info tracks.
|
|
|
|
///
|
|
|
|
namespace X86II {
|
|
|
|
/// Target Operand Flag enum.
|
|
|
|
enum TOF {
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// X86 Specific MachineOperand flags.
|
|
|
|
|
|
|
|
MO_NO_FLAG,
|
|
|
|
|
|
|
|
/// MO_GOT_ABSOLUTE_ADDRESS - On a symbol operand, this represents a
|
|
|
|
/// relocation of:
|
|
|
|
/// SYMBOL_LABEL + [. - PICBASELABEL]
|
|
|
|
MO_GOT_ABSOLUTE_ADDRESS,
|
|
|
|
|
|
|
|
/// MO_PIC_BASE_OFFSET - On a symbol operand this indicates that the
|
|
|
|
/// immediate should get the value of the symbol minus the PIC base label:
|
|
|
|
/// SYMBOL_LABEL - PICBASELABEL
|
|
|
|
MO_PIC_BASE_OFFSET,
|
|
|
|
|
|
|
|
/// MO_GOT - On a symbol operand this indicates that the immediate is the
|
|
|
|
/// offset to the GOT entry for the symbol name from the base of the GOT.
|
|
|
|
///
|
|
|
|
/// See the X86-64 ELF ABI supplement for more details.
|
|
|
|
/// SYMBOL_LABEL @GOT
|
|
|
|
MO_GOT,
|
|
|
|
|
|
|
|
/// MO_GOTOFF - On a symbol operand this indicates that the immediate is
|
|
|
|
/// the offset to the location of the symbol name from the base of the GOT.
|
|
|
|
///
|
|
|
|
/// See the X86-64 ELF ABI supplement for more details.
|
|
|
|
/// SYMBOL_LABEL @GOTOFF
|
|
|
|
MO_GOTOFF,
|
|
|
|
|
|
|
|
/// MO_GOTPCREL - On a symbol operand this indicates that the immediate is
|
|
|
|
/// offset to the GOT entry for the symbol name from the current code
|
|
|
|
/// location.
|
|
|
|
///
|
|
|
|
/// See the X86-64 ELF ABI supplement for more details.
|
|
|
|
/// SYMBOL_LABEL @GOTPCREL
|
|
|
|
MO_GOTPCREL,
|
|
|
|
|
|
|
|
/// MO_PLT - On a symbol operand this indicates that the immediate is
|
|
|
|
/// offset to the PLT entry of symbol name from the current code location.
|
|
|
|
///
|
|
|
|
/// See the X86-64 ELF ABI supplement for more details.
|
|
|
|
/// SYMBOL_LABEL @PLT
|
|
|
|
MO_PLT,
|
|
|
|
|
|
|
|
/// MO_TLSGD - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// See 'ELF Handling for Thread-Local Storage' for more details.
|
|
|
|
/// SYMBOL_LABEL @TLSGD
|
|
|
|
MO_TLSGD,
|
|
|
|
|
|
|
|
/// MO_GOTTPOFF - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// See 'ELF Handling for Thread-Local Storage' for more details.
|
|
|
|
/// SYMBOL_LABEL @GOTTPOFF
|
|
|
|
MO_GOTTPOFF,
|
|
|
|
|
|
|
|
/// MO_INDNTPOFF - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// See 'ELF Handling for Thread-Local Storage' for more details.
|
|
|
|
/// SYMBOL_LABEL @INDNTPOFF
|
|
|
|
MO_INDNTPOFF,
|
|
|
|
|
|
|
|
/// MO_TPOFF - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// See 'ELF Handling for Thread-Local Storage' for more details.
|
|
|
|
/// SYMBOL_LABEL @TPOFF
|
|
|
|
MO_TPOFF,
|
|
|
|
|
|
|
|
/// MO_NTPOFF - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// See 'ELF Handling for Thread-Local Storage' for more details.
|
|
|
|
/// SYMBOL_LABEL @NTPOFF
|
|
|
|
MO_NTPOFF,
|
|
|
|
|
|
|
|
/// MO_DLLIMPORT - On a symbol operand "FOO", this indicates that the
|
|
|
|
/// reference is actually to the "__imp_FOO" symbol. This is used for
|
|
|
|
/// dllimport linkage on windows.
|
|
|
|
MO_DLLIMPORT,
|
|
|
|
|
|
|
|
/// MO_DARWIN_STUB - On a symbol operand "FOO", this indicates that the
|
|
|
|
/// reference is actually to the "FOO$stub" symbol. This is used for calls
|
|
|
|
/// and jumps to external functions on Tiger and earlier.
|
|
|
|
MO_DARWIN_STUB,
|
|
|
|
|
|
|
|
/// MO_DARWIN_NONLAZY - On a symbol operand "FOO", this indicates that the
|
|
|
|
/// reference is actually to the "FOO$non_lazy_ptr" symbol, which is a
|
|
|
|
/// non-PIC-base-relative reference to a non-hidden dyld lazy pointer stub.
|
|
|
|
MO_DARWIN_NONLAZY,
|
|
|
|
|
|
|
|
/// MO_DARWIN_NONLAZY_PIC_BASE - On a symbol operand "FOO", this indicates
|
|
|
|
/// that the reference is actually to "FOO$non_lazy_ptr - PICBASE", which is
|
|
|
|
/// a PIC-base-relative reference to a non-hidden dyld lazy pointer stub.
|
|
|
|
MO_DARWIN_NONLAZY_PIC_BASE,
|
|
|
|
|
|
|
|
/// MO_DARWIN_HIDDEN_NONLAZY_PIC_BASE - On a symbol operand "FOO", this
|
|
|
|
/// indicates that the reference is actually to "FOO$non_lazy_ptr -PICBASE",
|
|
|
|
/// which is a PIC-base-relative reference to a hidden dyld lazy pointer
|
|
|
|
/// stub.
|
|
|
|
MO_DARWIN_HIDDEN_NONLAZY_PIC_BASE,
|
|
|
|
|
|
|
|
/// MO_TLVP - On a symbol operand this indicates that the immediate is
|
|
|
|
/// some TLS offset.
|
|
|
|
///
|
|
|
|
/// This is the TLS offset for the Darwin TLS mechanism.
|
|
|
|
MO_TLVP,
|
|
|
|
|
|
|
|
/// MO_TLVP_PIC_BASE - On a symbol operand this indicates that the immediate
|
|
|
|
/// is some TLS offset from the picbase.
|
|
|
|
///
|
|
|
|
/// This is the 32-bit TLS offset for Darwin TLS in PIC mode.
|
2012-02-12 01:26:53 +08:00
|
|
|
MO_TLVP_PIC_BASE,
|
|
|
|
|
|
|
|
/// MO_SECREL - On a symbol operand this indicates that the immediate is
|
|
|
|
/// the offset from beginning of section.
|
|
|
|
///
|
|
|
|
/// This is the TLS offset for the COFF/Windows TLS mechanism.
|
|
|
|
MO_SECREL
|
2011-07-26 02:43:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
enum {
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// Instruction encodings. These are the standard/most common forms for X86
|
|
|
|
// instructions.
|
|
|
|
//
|
|
|
|
|
|
|
|
// PseudoFrm - This represents an instruction that is a pseudo instruction
|
|
|
|
// or one that has not been implemented yet. It is illegal to code generate
|
|
|
|
// it, but tolerated for intermediate implementation stages.
|
|
|
|
Pseudo = 0,
|
|
|
|
|
|
|
|
/// Raw - This form is for instructions that don't have any operands, so
|
|
|
|
/// they are just a fixed opcode value, like 'leave'.
|
|
|
|
RawFrm = 1,
|
|
|
|
|
|
|
|
/// AddRegFrm - This form is used for instructions like 'push r32' that have
|
|
|
|
/// their one register operand added to their opcode.
|
|
|
|
AddRegFrm = 2,
|
|
|
|
|
|
|
|
/// MRMDestReg - This form is used for instructions that use the Mod/RM byte
|
|
|
|
/// to specify a destination, which in this case is a register.
|
|
|
|
///
|
|
|
|
MRMDestReg = 3,
|
|
|
|
|
|
|
|
/// MRMDestMem - This form is used for instructions that use the Mod/RM byte
|
|
|
|
/// to specify a destination, which in this case is memory.
|
|
|
|
///
|
|
|
|
MRMDestMem = 4,
|
|
|
|
|
|
|
|
/// MRMSrcReg - This form is used for instructions that use the Mod/RM byte
|
|
|
|
/// to specify a source, which in this case is a register.
|
|
|
|
///
|
|
|
|
MRMSrcReg = 5,
|
|
|
|
|
|
|
|
/// MRMSrcMem - This form is used for instructions that use the Mod/RM byte
|
|
|
|
/// to specify a source, which in this case is memory.
|
|
|
|
///
|
|
|
|
MRMSrcMem = 6,
|
|
|
|
|
|
|
|
/// MRM[0-7][rm] - These forms are used to represent instructions that use
|
|
|
|
/// a Mod/RM byte, and use the middle field to hold extended opcode
|
|
|
|
/// information. In the intel manual these are represented as /0, /1, ...
|
|
|
|
///
|
|
|
|
|
|
|
|
// First, instructions that operate on a register r/m operand...
|
|
|
|
MRM0r = 16, MRM1r = 17, MRM2r = 18, MRM3r = 19, // Format /0 /1 /2 /3
|
|
|
|
MRM4r = 20, MRM5r = 21, MRM6r = 22, MRM7r = 23, // Format /4 /5 /6 /7
|
|
|
|
|
|
|
|
// Next, instructions that operate on a memory r/m operand...
|
|
|
|
MRM0m = 24, MRM1m = 25, MRM2m = 26, MRM3m = 27, // Format /0 /1 /2 /3
|
|
|
|
MRM4m = 28, MRM5m = 29, MRM6m = 30, MRM7m = 31, // Format /4 /5 /6 /7
|
|
|
|
|
|
|
|
// MRMInitReg - This form is used for instructions whose source and
|
|
|
|
// destinations are the same register.
|
|
|
|
MRMInitReg = 32,
|
|
|
|
|
2012-02-18 16:19:49 +08:00
|
|
|
//// MRM_XX - A mod/rm byte of exactly 0xXX.
|
|
|
|
MRM_C1 = 33, MRM_C2 = 34, MRM_C3 = 35, MRM_C4 = 36,
|
|
|
|
MRM_C8 = 37, MRM_C9 = 38, MRM_E8 = 39, MRM_F0 = 40,
|
|
|
|
MRM_F8 = 41, MRM_F9 = 42, MRM_D0 = 45, MRM_D1 = 46,
|
2012-02-19 09:39:49 +08:00
|
|
|
MRM_D4 = 47, MRM_D8 = 48, MRM_D9 = 49, MRM_DA = 50,
|
|
|
|
MRM_DB = 51, MRM_DC = 52, MRM_DD = 53, MRM_DE = 54,
|
|
|
|
MRM_DF = 55,
|
2011-07-26 02:43:53 +08:00
|
|
|
|
|
|
|
/// RawFrmImm8 - This is used for the ENTER instruction, which has two
|
|
|
|
/// immediates, the first of which is a 16-bit immediate (specified by
|
|
|
|
/// the imm encoding) and the second is a 8-bit fixed value.
|
|
|
|
RawFrmImm8 = 43,
|
|
|
|
|
|
|
|
/// RawFrmImm16 - This is used for CALL FAR instructions, which have two
|
|
|
|
/// immediates, the first of which is a 16 or 32-bit immediate (specified by
|
|
|
|
/// the imm encoding) and the second is a 16-bit fixed value. In the AMD
|
|
|
|
/// manual, this operand is described as pntr16:32 and pntr16:16
|
|
|
|
RawFrmImm16 = 44,
|
|
|
|
|
|
|
|
FormMask = 63,
|
|
|
|
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// Actual flags...
|
|
|
|
|
|
|
|
// OpSize - Set if this instruction requires an operand size prefix (0x66),
|
|
|
|
// which most often indicates that the instruction operates on 16 bit data
|
|
|
|
// instead of 32 bit data.
|
|
|
|
OpSize = 1 << 6,
|
|
|
|
|
|
|
|
// AsSize - Set if this instruction requires an operand size prefix (0x67),
|
|
|
|
// which most often indicates that the instruction address 16 bit address
|
|
|
|
// instead of 32 bit address (or 32 bit address in 64 bit mode).
|
|
|
|
AdSize = 1 << 7,
|
|
|
|
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// Op0Mask - There are several prefix bytes that are used to form two byte
|
|
|
|
// opcodes. These are currently 0x0F, 0xF3, and 0xD8-0xDF. This mask is
|
|
|
|
// used to obtain the setting of this field. If no bits in this field is
|
|
|
|
// set, there is no prefix byte for obtaining a multibyte opcode.
|
|
|
|
//
|
|
|
|
Op0Shift = 8,
|
|
|
|
Op0Mask = 0x1F << Op0Shift,
|
|
|
|
|
|
|
|
// TB - TwoByte - Set if this instruction has a two byte opcode, which
|
|
|
|
// starts with a 0x0F byte before the real opcode.
|
|
|
|
TB = 1 << Op0Shift,
|
|
|
|
|
|
|
|
// REP - The 0xF3 prefix byte indicating repetition of the following
|
|
|
|
// instruction.
|
|
|
|
REP = 2 << Op0Shift,
|
|
|
|
|
|
|
|
// D8-DF - These escape opcodes are used by the floating point unit. These
|
|
|
|
// values must remain sequential.
|
|
|
|
D8 = 3 << Op0Shift, D9 = 4 << Op0Shift,
|
|
|
|
DA = 5 << Op0Shift, DB = 6 << Op0Shift,
|
|
|
|
DC = 7 << Op0Shift, DD = 8 << Op0Shift,
|
|
|
|
DE = 9 << Op0Shift, DF = 10 << Op0Shift,
|
|
|
|
|
|
|
|
// XS, XD - These prefix codes are for single and double precision scalar
|
|
|
|
// floating point operations performed in the SSE registers.
|
|
|
|
XD = 11 << Op0Shift, XS = 12 << Op0Shift,
|
|
|
|
|
|
|
|
// T8, TA, A6, A7 - Prefix after the 0x0F prefix.
|
|
|
|
T8 = 13 << Op0Shift, TA = 14 << Op0Shift,
|
|
|
|
A6 = 15 << Op0Shift, A7 = 16 << Op0Shift,
|
|
|
|
|
2011-10-17 00:50:08 +08:00
|
|
|
// T8XD - Prefix before and after 0x0F. Combination of T8 and XD.
|
|
|
|
T8XD = 17 << Op0Shift,
|
|
|
|
|
|
|
|
// T8XS - Prefix before and after 0x0F. Combination of T8 and XS.
|
|
|
|
T8XS = 18 << Op0Shift,
|
2011-07-26 02:43:53 +08:00
|
|
|
|
2011-10-23 15:34:00 +08:00
|
|
|
// TAXD - Prefix before and after 0x0F. Combination of TA and XD.
|
|
|
|
TAXD = 19 << Op0Shift,
|
|
|
|
|
2011-12-13 03:12:26 +08:00
|
|
|
// XOP8 - Prefix to include use of imm byte.
|
|
|
|
XOP8 = 20 << Op0Shift,
|
|
|
|
|
|
|
|
// XOP9 - Prefix to exclude use of imm byte.
|
|
|
|
XOP9 = 21 << Op0Shift,
|
|
|
|
|
2011-07-26 02:43:53 +08:00
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// REX_W - REX prefixes are instruction prefixes used in 64-bit mode.
|
|
|
|
// They are used to specify GPRs and SSE registers, 64-bit operand size,
|
|
|
|
// etc. We only cares about REX.W and REX.R bits and only the former is
|
|
|
|
// statically determined.
|
|
|
|
//
|
|
|
|
REXShift = Op0Shift + 5,
|
|
|
|
REX_W = 1 << REXShift,
|
|
|
|
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// This three-bit field describes the size of an immediate operand. Zero is
|
|
|
|
// unused so that we can tell if we forgot to set a value.
|
|
|
|
ImmShift = REXShift + 1,
|
|
|
|
ImmMask = 7 << ImmShift,
|
|
|
|
Imm8 = 1 << ImmShift,
|
|
|
|
Imm8PCRel = 2 << ImmShift,
|
|
|
|
Imm16 = 3 << ImmShift,
|
|
|
|
Imm16PCRel = 4 << ImmShift,
|
|
|
|
Imm32 = 5 << ImmShift,
|
|
|
|
Imm32PCRel = 6 << ImmShift,
|
|
|
|
Imm64 = 7 << ImmShift,
|
|
|
|
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
// FP Instruction Classification... Zero is non-fp instruction.
|
|
|
|
|
|
|
|
// FPTypeMask - Mask for all of the FP types...
|
|
|
|
FPTypeShift = ImmShift + 3,
|
|
|
|
FPTypeMask = 7 << FPTypeShift,
|
|
|
|
|
|
|
|
// NotFP - The default, set for instructions that do not use FP registers.
|
|
|
|
NotFP = 0 << FPTypeShift,
|
|
|
|
|
|
|
|
// ZeroArgFP - 0 arg FP instruction which implicitly pushes ST(0), f.e. fld0
|
|
|
|
ZeroArgFP = 1 << FPTypeShift,
|
|
|
|
|
|
|
|
// OneArgFP - 1 arg FP instructions which implicitly read ST(0), such as fst
|
|
|
|
OneArgFP = 2 << FPTypeShift,
|
|
|
|
|
|
|
|
// OneArgFPRW - 1 arg FP instruction which implicitly read ST(0) and write a
|
|
|
|
// result back to ST(0). For example, fcos, fsqrt, etc.
|
|
|
|
//
|
|
|
|
OneArgFPRW = 3 << FPTypeShift,
|
|
|
|
|
|
|
|
// TwoArgFP - 2 arg FP instructions which implicitly read ST(0), and an
|
|
|
|
// explicit argument, storing the result to either ST(0) or the implicit
|
|
|
|
// argument. For example: fadd, fsub, fmul, etc...
|
|
|
|
TwoArgFP = 4 << FPTypeShift,
|
|
|
|
|
|
|
|
// CompareFP - 2 arg FP instructions which implicitly read ST(0) and an
|
|
|
|
// explicit argument, but have no destination. Example: fucom, fucomi, ...
|
|
|
|
CompareFP = 5 << FPTypeShift,
|
|
|
|
|
|
|
|
// CondMovFP - "2 operand" floating point conditional move instructions.
|
|
|
|
CondMovFP = 6 << FPTypeShift,
|
|
|
|
|
|
|
|
// SpecialFP - Special instruction forms. Dispatch by opcode explicitly.
|
|
|
|
SpecialFP = 7 << FPTypeShift,
|
|
|
|
|
|
|
|
// Lock prefix
|
|
|
|
LOCKShift = FPTypeShift + 3,
|
|
|
|
LOCK = 1 << LOCKShift,
|
|
|
|
|
|
|
|
// Segment override prefixes. Currently we just need ability to address
|
|
|
|
// stuff in gs and fs segments.
|
|
|
|
SegOvrShift = LOCKShift + 1,
|
|
|
|
SegOvrMask = 3 << SegOvrShift,
|
|
|
|
FS = 1 << SegOvrShift,
|
|
|
|
GS = 2 << SegOvrShift,
|
|
|
|
|
|
|
|
// Execution domain for SSE instructions in bits 23, 24.
|
|
|
|
// 0 in bits 23-24 means normal, non-SSE instruction.
|
|
|
|
SSEDomainShift = SegOvrShift + 2,
|
|
|
|
|
|
|
|
OpcodeShift = SSEDomainShift + 2,
|
|
|
|
|
|
|
|
//===------------------------------------------------------------------===//
|
|
|
|
/// VEX - The opcode prefix used by AVX instructions
|
|
|
|
VEXShift = OpcodeShift + 8,
|
|
|
|
VEX = 1U << 0,
|
|
|
|
|
|
|
|
/// VEX_W - Has a opcode specific functionality, but is used in the same
|
|
|
|
/// way as REX_W is for regular SSE instructions.
|
|
|
|
VEX_W = 1U << 1,
|
|
|
|
|
|
|
|
/// VEX_4V - Used to specify an additional AVX/SSE register. Several 2
|
|
|
|
/// address instructions in SSE are represented as 3 address ones in AVX
|
|
|
|
/// and the additional register is encoded in VEX_VVVV prefix.
|
|
|
|
VEX_4V = 1U << 2,
|
|
|
|
|
2011-10-16 15:55:05 +08:00
|
|
|
/// VEX_4VOp3 - Similar to VEX_4V, but used on instructions that encode
|
|
|
|
/// operand 3 with VEX.vvvv.
|
|
|
|
VEX_4VOp3 = 1U << 3,
|
|
|
|
|
2011-07-26 02:43:53 +08:00
|
|
|
/// VEX_I8IMM - Specifies that the last register used in a AVX instruction,
|
|
|
|
/// must be encoded in the i8 immediate field. This usually happens in
|
|
|
|
/// instructions with 4 operands.
|
2011-10-16 15:55:05 +08:00
|
|
|
VEX_I8IMM = 1U << 4,
|
2011-07-26 02:43:53 +08:00
|
|
|
|
|
|
|
/// VEX_L - Stands for a bit in the VEX opcode prefix meaning the current
|
|
|
|
/// instruction uses 256-bit wide registers. This is usually auto detected
|
|
|
|
/// if a VR256 register is used, but some AVX instructions also have this
|
|
|
|
/// field marked when using a f256 memory references.
|
2011-10-16 15:55:05 +08:00
|
|
|
VEX_L = 1U << 5,
|
2011-07-26 02:43:53 +08:00
|
|
|
|
2011-10-04 14:30:42 +08:00
|
|
|
// VEX_LIG - Specifies that this instruction ignores the L-bit in the VEX
|
|
|
|
// prefix. Usually used for scalar instructions. Needed by disassembler.
|
2011-10-16 15:55:05 +08:00
|
|
|
VEX_LIG = 1U << 6,
|
2011-10-04 14:30:42 +08:00
|
|
|
|
2011-07-26 02:43:53 +08:00
|
|
|
/// Has3DNow0F0FOpcode - This flag indicates that the instruction uses the
|
|
|
|
/// wacky 0x0F 0x0F prefix for 3DNow! instructions. The manual documents
|
|
|
|
/// this as having a 0x0F prefix with a 0x0F opcode, and each instruction
|
|
|
|
/// storing a classifier in the imm8 field. To simplify our implementation,
|
|
|
|
/// we handle this by storeing the classifier in the opcode field and using
|
|
|
|
/// this flag to indicate that the encoder should do the wacky 3DNow! thing.
|
2011-11-26 03:33:42 +08:00
|
|
|
Has3DNow0F0FOpcode = 1U << 7,
|
|
|
|
|
2011-12-30 12:48:54 +08:00
|
|
|
/// MemOp4 - Used to indicate swapping of operand 3 and 4 to be encoded in
|
|
|
|
/// ModRM or I8IMM. This is used for FMA4 and XOP instructions.
|
|
|
|
MemOp4 = 1U << 8,
|
2011-12-13 03:12:26 +08:00
|
|
|
|
|
|
|
/// XOP - Opcode prefix used by XOP instructions.
|
|
|
|
XOP = 1U << 9
|
|
|
|
|
2011-07-26 02:43:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
// getBaseOpcodeFor - This function returns the "base" X86 opcode for the
|
|
|
|
// specified machine instruction.
|
|
|
|
//
|
|
|
|
static inline unsigned char getBaseOpcodeFor(uint64_t TSFlags) {
|
|
|
|
return TSFlags >> X86II::OpcodeShift;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool hasImm(uint64_t TSFlags) {
|
|
|
|
return (TSFlags & X86II::ImmMask) != 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/// getSizeOfImm - Decode the "size of immediate" field from the TSFlags field
|
|
|
|
/// of the specified instruction.
|
|
|
|
static inline unsigned getSizeOfImm(uint64_t TSFlags) {
|
|
|
|
switch (TSFlags & X86II::ImmMask) {
|
2012-02-05 13:38:58 +08:00
|
|
|
default: llvm_unreachable("Unknown immediate size");
|
2011-07-26 02:43:53 +08:00
|
|
|
case X86II::Imm8:
|
|
|
|
case X86II::Imm8PCRel: return 1;
|
|
|
|
case X86II::Imm16:
|
|
|
|
case X86II::Imm16PCRel: return 2;
|
|
|
|
case X86II::Imm32:
|
|
|
|
case X86II::Imm32PCRel: return 4;
|
|
|
|
case X86II::Imm64: return 8;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// isImmPCRel - Return true if the immediate of the specified instruction's
|
|
|
|
/// TSFlags indicates that it is pc relative.
|
|
|
|
static inline unsigned isImmPCRel(uint64_t TSFlags) {
|
|
|
|
switch (TSFlags & X86II::ImmMask) {
|
2012-02-05 13:38:58 +08:00
|
|
|
default: llvm_unreachable("Unknown immediate size");
|
2011-07-26 02:43:53 +08:00
|
|
|
case X86II::Imm8PCRel:
|
|
|
|
case X86II::Imm16PCRel:
|
|
|
|
case X86II::Imm32PCRel:
|
|
|
|
return true;
|
|
|
|
case X86II::Imm8:
|
|
|
|
case X86II::Imm16:
|
|
|
|
case X86II::Imm32:
|
|
|
|
case X86II::Imm64:
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// getMemoryOperandNo - The function returns the MCInst operand # for the
|
|
|
|
/// first field of the memory operand. If the instruction doesn't have a
|
|
|
|
/// memory operand, this returns -1.
|
|
|
|
///
|
|
|
|
/// Note that this ignores tied operands. If there is a tied register which
|
|
|
|
/// is duplicated in the MCInst (e.g. "EAX = addl EAX, [mem]") it is only
|
|
|
|
/// counted as one operand.
|
|
|
|
///
|
2011-10-16 11:51:13 +08:00
|
|
|
static inline int getMemoryOperandNo(uint64_t TSFlags, unsigned Opcode) {
|
2011-07-26 02:43:53 +08:00
|
|
|
switch (TSFlags & X86II::FormMask) {
|
2012-04-30 11:56:44 +08:00
|
|
|
case X86II::MRMInitReg:
|
|
|
|
// FIXME: Remove this form.
|
|
|
|
return -1;
|
2012-02-05 13:38:58 +08:00
|
|
|
default: llvm_unreachable("Unknown FormMask value in getMemoryOperandNo!");
|
2011-07-26 02:43:53 +08:00
|
|
|
case X86II::Pseudo:
|
|
|
|
case X86II::RawFrm:
|
|
|
|
case X86II::AddRegFrm:
|
|
|
|
case X86II::MRMDestReg:
|
|
|
|
case X86II::MRMSrcReg:
|
|
|
|
case X86II::RawFrmImm8:
|
|
|
|
case X86II::RawFrmImm16:
|
|
|
|
return -1;
|
|
|
|
case X86II::MRMDestMem:
|
|
|
|
return 0;
|
|
|
|
case X86II::MRMSrcMem: {
|
|
|
|
bool HasVEX_4V = (TSFlags >> X86II::VEXShift) & X86II::VEX_4V;
|
2011-12-30 12:48:54 +08:00
|
|
|
bool HasMemOp4 = (TSFlags >> X86II::VEXShift) & X86II::MemOp4;
|
2011-07-26 02:43:53 +08:00
|
|
|
unsigned FirstMemOp = 1;
|
2011-10-16 15:55:05 +08:00
|
|
|
if (HasVEX_4V)
|
2011-07-26 02:43:53 +08:00
|
|
|
++FirstMemOp;// Skip the register source (which is encoded in VEX_VVVV).
|
2011-12-30 12:48:54 +08:00
|
|
|
if (HasMemOp4)
|
2011-11-26 03:33:42 +08:00
|
|
|
++FirstMemOp;// Skip the register source (which is encoded in I8IMM).
|
2011-07-26 02:43:53 +08:00
|
|
|
|
|
|
|
// FIXME: Maybe lea should have its own form? This is a horrible hack.
|
|
|
|
//if (Opcode == X86::LEA64r || Opcode == X86::LEA64_32r ||
|
|
|
|
// Opcode == X86::LEA16r || Opcode == X86::LEA32r)
|
|
|
|
return FirstMemOp;
|
|
|
|
}
|
|
|
|
case X86II::MRM0r: case X86II::MRM1r:
|
|
|
|
case X86II::MRM2r: case X86II::MRM3r:
|
|
|
|
case X86II::MRM4r: case X86II::MRM5r:
|
|
|
|
case X86II::MRM6r: case X86II::MRM7r:
|
|
|
|
return -1;
|
|
|
|
case X86II::MRM0m: case X86II::MRM1m:
|
|
|
|
case X86II::MRM2m: case X86II::MRM3m:
|
|
|
|
case X86II::MRM4m: case X86II::MRM5m:
|
2011-10-16 04:46:47 +08:00
|
|
|
case X86II::MRM6m: case X86II::MRM7m: {
|
|
|
|
bool HasVEX_4V = (TSFlags >> X86II::VEXShift) & X86II::VEX_4V;
|
|
|
|
unsigned FirstMemOp = 0;
|
|
|
|
if (HasVEX_4V)
|
|
|
|
++FirstMemOp;// Skip the register dest (which is encoded in VEX_VVVV).
|
|
|
|
return FirstMemOp;
|
|
|
|
}
|
2012-02-18 16:19:49 +08:00
|
|
|
case X86II::MRM_C1: case X86II::MRM_C2:
|
|
|
|
case X86II::MRM_C3: case X86II::MRM_C4:
|
|
|
|
case X86II::MRM_C8: case X86II::MRM_C9:
|
|
|
|
case X86II::MRM_E8: case X86II::MRM_F0:
|
|
|
|
case X86II::MRM_F8: case X86II::MRM_F9:
|
|
|
|
case X86II::MRM_D0: case X86II::MRM_D1:
|
2012-02-19 09:39:49 +08:00
|
|
|
case X86II::MRM_D4: case X86II::MRM_D8:
|
|
|
|
case X86II::MRM_D9: case X86II::MRM_DA:
|
|
|
|
case X86II::MRM_DB: case X86II::MRM_DC:
|
|
|
|
case X86II::MRM_DD: case X86II::MRM_DE:
|
|
|
|
case X86II::MRM_DF:
|
2011-07-26 02:43:53 +08:00
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// isX86_64ExtendedReg - Is the MachineOperand a x86-64 extended (r8 or
|
|
|
|
/// higher) register? e.g. r8, xmm8, xmm13, etc.
|
|
|
|
static inline bool isX86_64ExtendedReg(unsigned RegNo) {
|
|
|
|
switch (RegNo) {
|
|
|
|
default: break;
|
|
|
|
case X86::R8: case X86::R9: case X86::R10: case X86::R11:
|
|
|
|
case X86::R12: case X86::R13: case X86::R14: case X86::R15:
|
|
|
|
case X86::R8D: case X86::R9D: case X86::R10D: case X86::R11D:
|
|
|
|
case X86::R12D: case X86::R13D: case X86::R14D: case X86::R15D:
|
|
|
|
case X86::R8W: case X86::R9W: case X86::R10W: case X86::R11W:
|
|
|
|
case X86::R12W: case X86::R13W: case X86::R14W: case X86::R15W:
|
|
|
|
case X86::R8B: case X86::R9B: case X86::R10B: case X86::R11B:
|
|
|
|
case X86::R12B: case X86::R13B: case X86::R14B: case X86::R15B:
|
|
|
|
case X86::XMM8: case X86::XMM9: case X86::XMM10: case X86::XMM11:
|
|
|
|
case X86::XMM12: case X86::XMM13: case X86::XMM14: case X86::XMM15:
|
|
|
|
case X86::YMM8: case X86::YMM9: case X86::YMM10: case X86::YMM11:
|
|
|
|
case X86::YMM12: case X86::YMM13: case X86::YMM14: case X86::YMM15:
|
|
|
|
case X86::CR8: case X86::CR9: case X86::CR10: case X86::CR11:
|
|
|
|
case X86::CR12: case X86::CR13: case X86::CR14: case X86::CR15:
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool isX86_64NonExtLowByteReg(unsigned reg) {
|
|
|
|
return (reg == X86::SPL || reg == X86::BPL ||
|
|
|
|
reg == X86::SIL || reg == X86::DIL);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
} // end namespace llvm;
|
|
|
|
|
|
|
|
#endif
|