mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 04:30:12 +00:00
6f45b1f0d6
Objective-C data structures. This is allows tools such as darwin's otool(1) that uses the LLVM disassembler take a pointer value being loaded by an instruction and add a comment to what it is being referenced to make following disassembly of Objective-C programs more readable. For example disassembling the Mac OS X TextEdit app one will see comments like the following: movq 0x20684(%rip), %rsi ## Objc selector ref: standardUserDefaults movq 0x21985(%rip), %rdi ## Objc class ref: _OBJC_CLASS_$_NSUserDefaults movq 0x1d156(%rip), %r14 ## Objc message: +[NSUserDefaults standardUserDefaults] leaq 0x23615(%rip), %rdx ## Objc cfstring ref: @"SelectLinePanel" callq 0x10001386c ## Objc message: -[[%rdi super] initWithWindowNibName:] These diffs also include putting quotes around C strings in literal pools and uses "symbol address" in the comment when adding a symbol name to the comment to tell these types of references apart: leaq 0x4f(%rip), %rax ## literal pool for: "Hello world" movq 0x1c3ea(%rip), %rax ## literal pool symbol address: ___stack_chk_guard Of course the easy changes are in the LLVM disassembler and the hard work is up to the implementer of the SymbolLookUp() call back. rdar://10602439 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193833 91177308-0d34-0410-b5e6-96231b3b80d8
217 lines
9.8 KiB
C
217 lines
9.8 KiB
C
/*===-- llvm-c/Disassembler.h - Disassembler Public C Interface ---*- C -*-===*\
|
|
|* *|
|
|
|* The LLVM Compiler Infrastructure *|
|
|
|* *|
|
|
|* This file is distributed under the University of Illinois Open Source *|
|
|
|* License. See LICENSE.TXT for details. *|
|
|
|* *|
|
|
|*===----------------------------------------------------------------------===*|
|
|
|* *|
|
|
|* This header provides a public interface to a disassembler library. *|
|
|
|* LLVM provides an implementation of this interface. *|
|
|
|* *|
|
|
\*===----------------------------------------------------------------------===*/
|
|
|
|
#ifndef LLVM_C_DISASSEMBLER_H
|
|
#define LLVM_C_DISASSEMBLER_H
|
|
|
|
#include "llvm/Support/DataTypes.h"
|
|
#include <stddef.h>
|
|
|
|
/**
|
|
* @defgroup LLVMCDisassembler Disassembler
|
|
* @ingroup LLVMC
|
|
*
|
|
* @{
|
|
*/
|
|
|
|
/**
|
|
* An opaque reference to a disassembler context.
|
|
*/
|
|
typedef void *LLVMDisasmContextRef;
|
|
|
|
/**
|
|
* The type for the operand information call back function. This is called to
|
|
* get the symbolic information for an operand of an instruction. Typically
|
|
* this is from the relocation information, symbol table, etc. That block of
|
|
* information is saved when the disassembler context is created and passed to
|
|
* the call back in the DisInfo parameter. The instruction containing operand
|
|
* is at the PC parameter. For some instruction sets, there can be more than
|
|
* one operand with symbolic information. To determine the symbolic operand
|
|
* information for each operand, the bytes for the specific operand in the
|
|
* instruction are specified by the Offset parameter and its byte widith is the
|
|
* size parameter. For instructions sets with fixed widths and one symbolic
|
|
* operand per instruction, the Offset parameter will be zero and Size parameter
|
|
* will be the instruction width. The information is returned in TagBuf and is
|
|
* Triple specific with its specific information defined by the value of
|
|
* TagType for that Triple. If symbolic information is returned the function
|
|
* returns 1, otherwise it returns 0.
|
|
*/
|
|
typedef int (*LLVMOpInfoCallback)(void *DisInfo, uint64_t PC,
|
|
uint64_t Offset, uint64_t Size,
|
|
int TagType, void *TagBuf);
|
|
|
|
/**
|
|
* The initial support in LLVM MC for the most general form of a relocatable
|
|
* expression is "AddSymbol - SubtractSymbol + Offset". For some Darwin targets
|
|
* this full form is encoded in the relocation information so that AddSymbol and
|
|
* SubtractSymbol can be link edited independent of each other. Many other
|
|
* platforms only allow a relocatable expression of the form AddSymbol + Offset
|
|
* to be encoded.
|
|
*
|
|
* The LLVMOpInfoCallback() for the TagType value of 1 uses the struct
|
|
* LLVMOpInfo1. The value of the relocatable expression for the operand,
|
|
* including any PC adjustment, is passed in to the call back in the Value
|
|
* field. The symbolic information about the operand is returned using all
|
|
* the fields of the structure with the Offset of the relocatable expression
|
|
* returned in the Value field. It is possible that some symbols in the
|
|
* relocatable expression were assembly temporary symbols, for example
|
|
* "Ldata - LpicBase + constant", and only the Values of the symbols without
|
|
* symbol names are present in the relocation information. The VariantKind
|
|
* type is one of the Target specific #defines below and is used to print
|
|
* operands like "_foo@GOT", ":lower16:_foo", etc.
|
|
*/
|
|
struct LLVMOpInfoSymbol1 {
|
|
uint64_t Present; /* 1 if this symbol is present */
|
|
const char *Name; /* symbol name if not NULL */
|
|
uint64_t Value; /* symbol value if name is NULL */
|
|
};
|
|
|
|
struct LLVMOpInfo1 {
|
|
struct LLVMOpInfoSymbol1 AddSymbol;
|
|
struct LLVMOpInfoSymbol1 SubtractSymbol;
|
|
uint64_t Value;
|
|
uint64_t VariantKind;
|
|
};
|
|
|
|
/**
|
|
* The operand VariantKinds for symbolic disassembly.
|
|
*/
|
|
#define LLVMDisassembler_VariantKind_None 0 /* all targets */
|
|
|
|
/**
|
|
* The ARM target VariantKinds.
|
|
*/
|
|
#define LLVMDisassembler_VariantKind_ARM_HI16 1 /* :upper16: */
|
|
#define LLVMDisassembler_VariantKind_ARM_LO16 2 /* :lower16: */
|
|
|
|
/**
|
|
* The type for the symbol lookup function. This may be called by the
|
|
* disassembler for things like adding a comment for a PC plus a constant
|
|
* offset load instruction to use a symbol name instead of a load address value.
|
|
* It is passed the block information is saved when the disassembler context is
|
|
* created and the ReferenceValue to look up as a symbol. If no symbol is found
|
|
* for the ReferenceValue NULL is returned. The ReferenceType of the
|
|
* instruction is passed indirectly as is the PC of the instruction in
|
|
* ReferencePC. If the output reference can be determined its type is returned
|
|
* indirectly in ReferenceType along with ReferenceName if any, or that is set
|
|
* to NULL.
|
|
*/
|
|
typedef const char *(*LLVMSymbolLookupCallback)(void *DisInfo,
|
|
uint64_t ReferenceValue,
|
|
uint64_t *ReferenceType,
|
|
uint64_t ReferencePC,
|
|
const char **ReferenceName);
|
|
/**
|
|
* The reference types on input and output.
|
|
*/
|
|
/* No input reference type or no output reference type. */
|
|
#define LLVMDisassembler_ReferenceType_InOut_None 0
|
|
|
|
/* The input reference is from a branch instruction. */
|
|
#define LLVMDisassembler_ReferenceType_In_Branch 1
|
|
/* The input reference is from a PC relative load instruction. */
|
|
#define LLVMDisassembler_ReferenceType_In_PCrel_Load 2
|
|
|
|
/* The output reference is to as symbol stub. */
|
|
#define LLVMDisassembler_ReferenceType_Out_SymbolStub 1
|
|
/* The output reference is to a symbol address in a literal pool. */
|
|
#define LLVMDisassembler_ReferenceType_Out_LitPool_SymAddr 2
|
|
/* The output reference is to a cstring address in a literal pool. */
|
|
#define LLVMDisassembler_ReferenceType_Out_LitPool_CstrAddr 3
|
|
|
|
/* The output reference is to a Objective-C CoreFoundation string. */
|
|
#define LLVMDisassembler_ReferenceType_Out_Objc_CFString_Ref 4
|
|
/* The output reference is to a Objective-C message. */
|
|
#define LLVMDisassembler_ReferenceType_Out_Objc_Message 5
|
|
/* The output reference is to a Objective-C message ref. */
|
|
#define LLVMDisassembler_ReferenceType_Out_Objc_Message_Ref 6
|
|
/* The output reference is to a Objective-C selector ref. */
|
|
#define LLVMDisassembler_ReferenceType_Out_Objc_Selector_Ref 7
|
|
/* The output reference is to a Objective-C class ref. */
|
|
#define LLVMDisassembler_ReferenceType_Out_Objc_Class_Ref 8
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif /* !defined(__cplusplus) */
|
|
|
|
/**
|
|
* Create a disassembler for the TripleName. Symbolic disassembly is supported
|
|
* by passing a block of information in the DisInfo parameter and specifying the
|
|
* TagType and callback functions as described above. These can all be passed
|
|
* as NULL. If successful, this returns a disassembler context. If not, it
|
|
* returns NULL. This function is equivalent to calling LLVMCreateDisasmCPU()
|
|
* with an empty CPU name.
|
|
*/
|
|
LLVMDisasmContextRef LLVMCreateDisasm(const char *TripleName, void *DisInfo,
|
|
int TagType, LLVMOpInfoCallback GetOpInfo,
|
|
LLVMSymbolLookupCallback SymbolLookUp);
|
|
|
|
/**
|
|
* Create a disassembler for the TripleName and a specific CPU. Symbolic
|
|
* disassembly is supported by passing a block of information in the DisInfo
|
|
* parameter and specifying the TagType and callback functions as described
|
|
* above. These can all be passed * as NULL. If successful, this returns a
|
|
* disassembler context. If not, it returns NULL.
|
|
*/
|
|
LLVMDisasmContextRef LLVMCreateDisasmCPU(const char *Triple, const char *CPU,
|
|
void *DisInfo, int TagType,
|
|
LLVMOpInfoCallback GetOpInfo,
|
|
LLVMSymbolLookupCallback SymbolLookUp);
|
|
|
|
/**
|
|
* Set the disassembler's options. Returns 1 if it can set the Options and 0
|
|
* otherwise.
|
|
*/
|
|
int LLVMSetDisasmOptions(LLVMDisasmContextRef DC, uint64_t Options);
|
|
|
|
/* The option to produce marked up assembly. */
|
|
#define LLVMDisassembler_Option_UseMarkup 1
|
|
/* The option to print immediates as hex. */
|
|
#define LLVMDisassembler_Option_PrintImmHex 2
|
|
/* The option use the other assembler printer variant */
|
|
#define LLVMDisassembler_Option_AsmPrinterVariant 4
|
|
/* The option to set comment on instructions */
|
|
#define LLVMDisassembler_Option_SetInstrComments 8
|
|
/* The option to print latency information alongside instructions */
|
|
#define LLVMDisassembler_Option_PrintLatency 16
|
|
|
|
/**
|
|
* Dispose of a disassembler context.
|
|
*/
|
|
void LLVMDisasmDispose(LLVMDisasmContextRef DC);
|
|
|
|
/**
|
|
* Disassemble a single instruction using the disassembler context specified in
|
|
* the parameter DC. The bytes of the instruction are specified in the
|
|
* parameter Bytes, and contains at least BytesSize number of bytes. The
|
|
* instruction is at the address specified by the PC parameter. If a valid
|
|
* instruction can be disassembled, its string is returned indirectly in
|
|
* OutString whose size is specified in the parameter OutStringSize. This
|
|
* function returns the number of bytes in the instruction or zero if there was
|
|
* no valid instruction.
|
|
*/
|
|
size_t LLVMDisasmInstruction(LLVMDisasmContextRef DC, uint8_t *Bytes,
|
|
uint64_t BytesSize, uint64_t PC,
|
|
char *OutString, size_t OutStringSize);
|
|
|
|
/**
|
|
* @}
|
|
*/
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif /* !defined(__cplusplus) */
|
|
|
|
#endif /* !defined(LLVM_C_DISASSEMBLER_H) */
|