//
// The LLVM Compiler Infrastructure
//
-// This file was developed by Nate Begeman and is distributed under the
-// University of Illinois Open Source License. See LICENSE.TXT for details.
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//
//===----------------------------------------------------------------------===//
+#include "MachO.h"
+#include "MachOWriter.h"
+#include "MachOCodeEmitter.h"
+#include "llvm/Constants.h"
+#include "llvm/DerivedTypes.h"
#include "llvm/Module.h"
-#include "llvm/CodeGen/MachineCodeEmitter.h"
-#include "llvm/CodeGen/MachineConstantPool.h"
-#include "llvm/CodeGen/MachineJumpTableInfo.h"
-#include "llvm/CodeGen/MachOWriter.h"
-#include "llvm/ExecutionEngine/ExecutionEngine.h"
-#include "llvm/Target/TargetJITInfo.h"
+#include "llvm/PassManager.h"
+#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/Target/TargetData.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Target/TargetMachOWriterInfo.h"
#include "llvm/Support/Mangler.h"
-#include "llvm/Support/MathExtras.h"
-#include <algorithm>
-#include <iostream>
-using namespace llvm;
+#include "llvm/Support/OutputBuffer.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/raw_ostream.h"
+
+namespace llvm {
+
+/// AddMachOWriter - Concrete function to add the Mach-O writer to the function
+/// pass manager.
+ObjectCodeEmitter *AddMachOWriter(PassManagerBase &PM,
+ raw_ostream &O,
+ TargetMachine &TM) {
+ MachOWriter *MOW = new MachOWriter(O, TM);
+ PM.add(MOW);
+ return MOW->getObjectCodeEmitter();
+}
//===----------------------------------------------------------------------===//
-// MachOCodeEmitter Implementation
+// MachOWriter Implementation
//===----------------------------------------------------------------------===//
-namespace llvm {
- /// MachOCodeEmitter - This class is used by the MachOWriter to emit the code
- /// for functions to the Mach-O file.
- class MachOCodeEmitter : public MachineCodeEmitter {
- MachOWriter &MOW;
-
- /// MOS - The current section we're writing to
- MachOWriter::MachOSection *MOS;
-
- /// Relocations - These are the relocations that the function needs, as
- /// emitted.
- std::vector<MachineRelocation> Relocations;
-
- /// CPLocations - This is a map of constant pool indices to offsets from the
- /// start of the section for that constant pool index.
- std::vector<intptr_t> CPLocations;
-
- /// JTLocations - This is a map of jump table indices to offsets from the
- /// start of the section for that jump table index.
- std::vector<intptr_t> JTLocations;
-
- /// MBBLocations - This vector is a mapping from MBB ID's to their address.
- /// It is filled in by the StartMachineBasicBlock callback and queried by
- /// the getMachineBasicBlockAddress callback.
- std::vector<intptr_t> MBBLocations;
-
- public:
- MachOCodeEmitter(MachOWriter &mow) : MOW(mow) {}
-
- void startFunction(MachineFunction &F);
- bool finishFunction(MachineFunction &F);
-
- void addRelocation(const MachineRelocation &MR) {
- Relocations.push_back(MR);
- }
-
- void emitConstantPool(MachineConstantPool *MCP);
- void emitJumpTables(MachineJumpTableInfo *MJTI);
-
- virtual intptr_t getConstantPoolEntryAddress(unsigned Index) const {
- assert(0 && "CP not implementated yet!");
- return 0;
- }
- virtual intptr_t getJumpTableEntryAddress(unsigned Index) const {
- assert(JTLocations.size() > Index && "JT not emitted!");
- return JTLocations[Index];
- }
+char MachOWriter::ID = 0;
- virtual void StartMachineBasicBlock(MachineBasicBlock *MBB) {
- if (MBBLocations.size() <= (unsigned)MBB->getNumber())
- MBBLocations.resize((MBB->getNumber()+1)*2);
- MBBLocations[MBB->getNumber()] = getCurrentPCOffset();
- }
+MachOWriter::MachOWriter(raw_ostream &o, TargetMachine &tm)
+ : MachineFunctionPass(&ID), O(o), TM(tm) {
+ is64Bit = TM.getTargetData()->getPointerSizeInBits() == 64;
+ isLittleEndian = TM.getTargetData()->isLittleEndian();
- virtual intptr_t getMachineBasicBlockAddress(MachineBasicBlock *MBB) const {
- assert(MBBLocations.size() > (unsigned)MBB->getNumber() &&
- MBBLocations[MBB->getNumber()] && "MBB not emitted!");
- return MBBLocations[MBB->getNumber()];
- }
+ MAI = TM.getMCAsmInfo();
- /// JIT SPECIFIC FUNCTIONS - DO NOT IMPLEMENT THESE HERE!
- void startFunctionStub(unsigned StubSize, unsigned Alignment = 1) {
- assert(0 && "JIT specific function called!");
- abort();
- }
- void *finishFunctionStub(const Function *F) {
- assert(0 && "JIT specific function called!");
- abort();
- return 0;
- }
- };
+ // Create the machine code emitter object for this target.
+ MachOCE = new MachOCodeEmitter(*this, *getTextSection(true));
}
-/// startFunction - This callback is invoked when a new machine function is
-/// about to be emitted.
-void MachOCodeEmitter::startFunction(MachineFunction &F) {
- // Align the output buffer to the appropriate alignment, power of 2.
- // FIXME: GENERICIZE!!
- unsigned Align = 4;
-
- // Get the Mach-O Section that this function belongs in.
- MOS = &MOW.getTextSection();
-
- // FIXME: better memory management
- MOS->SectionData.reserve(4096);
- BufferBegin = &(MOS->SectionData[0]);
- BufferEnd = BufferBegin + MOS->SectionData.capacity();
- CurBufferPtr = BufferBegin + MOS->size;
-
- // Upgrade the section alignment if required.
- if (MOS->align < Align) MOS->align = Align;
-
- // Clear per-function data structures.
- CPLocations.clear();
- JTLocations.clear();
- MBBLocations.clear();
+MachOWriter::~MachOWriter() {
+ delete MachOCE;
}
-/// finishFunction - This callback is invoked after the function is completely
-/// finished.
-bool MachOCodeEmitter::finishFunction(MachineFunction &F) {
- MOS->size += CurBufferPtr - BufferBegin;
-
- // Get a symbol for the function to add to the symbol table
- const GlobalValue *FuncV = F.getFunction();
- MachOSym FnSym(FuncV, MOW.Mang->getValueName(FuncV), MOS->Index);
-
- // Emit constant pool to appropriate section(s)
- emitConstantPool(F.getConstantPool());
-
- // Emit jump tables to appropriate section
- emitJumpTables(F.getJumpTableInfo());
-
- // If we have emitted any relocations to function-specific objects such as
- // basic blocks, constant pools entries, or jump tables, record their
- // addresses now so that we can rewrite them with the correct addresses
- // later.
- for (unsigned i = 0, e = Relocations.size(); i != e; ++i) {
- MachineRelocation &MR = Relocations[i];
- intptr_t Addr;
- if (MR.isBasicBlock()) {
- Addr = getMachineBasicBlockAddress(MR.getBasicBlock());
- MR.setResultPointer((void *)Addr);
- } else if (MR.isConstantPoolIndex()) {
- Addr = getConstantPoolEntryAddress(MR.getConstantPoolIndex());
- MR.setResultPointer((void *)Addr);
- } else if (MR.isJumpTableIndex()) {
- // FIXME: handle PIC codegen
- Addr = getJumpTableEntryAddress(MR.getJumpTableIndex());
- MR.setResultPointer((void *)Addr);
- }
- MOS->Relocations.push_back(MR);
- }
- Relocations.clear();
-
- // Finally, add it to the symtab.
- MOW.SymbolTable.push_back(FnSym);
+bool MachOWriter::doInitialization(Module &M) {
+ // Set the magic value, now that we know the pointer size and endianness
+ Header.setMagic(isLittleEndian, is64Bit);
+
+ // Set the file type
+ // FIXME: this only works for object files, we do not support the creation
+ // of dynamic libraries or executables at this time.
+ Header.filetype = MachOHeader::MH_OBJECT;
+
+ Mang = new Mangler(M);
+ return false;
+}
+
+bool MachOWriter::runOnMachineFunction(MachineFunction &MF) {
return false;
}
-/// emitConstantPool - For each constant pool entry, figure out which section
-/// the constant should live in, allocate space for it, and emit it to the
-/// Section data buffer.
-void MachOCodeEmitter::emitConstantPool(MachineConstantPool *MCP) {
+/// doFinalization - Now that the module has been completely processed, emit
+/// the Mach-O file to 'O'.
+bool MachOWriter::doFinalization(Module &M) {
+ // FIXME: we don't handle debug info yet, we should probably do that.
+ // Okay, the.text section has been completed, build the .data, .bss, and
+ // "common" sections next.
+
+ for (Module::global_iterator I = M.global_begin(), E = M.global_end();
+ I != E; ++I)
+ EmitGlobal(I);
+
+ // Emit the header and load commands.
+ EmitHeaderAndLoadCommands();
+
+ // Emit the various sections and their relocation info.
+ EmitSections();
+ EmitRelocations();
+
+ // Write the symbol table and the string table to the end of the file.
+ O.write((char*)&SymT[0], SymT.size());
+ O.write((char*)&StrT[0], StrT.size());
+
+ // We are done with the abstract symbols.
+ SectionList.clear();
+ SymbolTable.clear();
+ DynamicSymbolTable.clear();
+
+ // Release the name mangler object.
+ delete Mang; Mang = 0;
+ return false;
}
-/// emitJumpTables - Emit all the jump tables for a given jump table info
-/// record to the appropriate section.
-void MachOCodeEmitter::emitJumpTables(MachineJumpTableInfo *MJTI) {
- const std::vector<MachineJumpTableEntry> &JT = MJTI->getJumpTables();
- if (JT.empty()) return;
-
- bool isPIC = MOW.TM.getRelocationModel() == Reloc::PIC_;
- assert(!isPIC && "PIC codegen not yet handled for mach-o jump tables!");
-
- MachOWriter::MachOSection &Sec = MOW.getJumpTableSection();
-
- for (unsigned i = 0, e = JT.size(); i != e; ++i) {
- // For each jump table, record its offset from the start of the section,
- // reserve space for the relocations to the MBBs, and add the relocations.
- const std::vector<MachineBasicBlock*> &MBBs = JT[i].MBBs;
- JTLocations.push_back(Sec.SectionData.size());
- for (unsigned mi = 0, me = MBBs.size(); mi != me; ++mi) {
- MachineRelocation MR(MOW.GetJTRelocation(Sec.SectionData.size(),
- MBBs[mi]));
- MR.setResultPointer((void *)JTLocations[i]);
- Sec.Relocations.push_back(MR);
- MOW.outaddr(Sec.SectionData, 0);
+// getConstSection - Get constant section for Constant 'C'
+MachOSection *MachOWriter::getConstSection(Constant *C) {
+ const ConstantArray *CVA = dyn_cast<ConstantArray>(C);
+ if (CVA && CVA->isCString())
+ return getSection("__TEXT", "__cstring",
+ MachOSection::S_CSTRING_LITERALS);
+
+ const Type *Ty = C->getType();
+ if (Ty->isPrimitiveType() || Ty->isInteger()) {
+ unsigned Size = TM.getTargetData()->getTypeAllocSize(Ty);
+ switch(Size) {
+ default: break; // Fall through to __TEXT,__const
+ case 4:
+ return getSection("__TEXT", "__literal4",
+ MachOSection::S_4BYTE_LITERALS);
+ case 8:
+ return getSection("__TEXT", "__literal8",
+ MachOSection::S_8BYTE_LITERALS);
+ case 16:
+ return getSection("__TEXT", "__literal16",
+ MachOSection::S_16BYTE_LITERALS);
}
}
- // FIXME: it really seems like keeping these in sync is redundant, someone
- // should do something about that (never access section size directly, only
- // look at buffer size).
- Sec.size = Sec.SectionData.size();
+ return getSection("__TEXT", "__const");
}
-//===----------------------------------------------------------------------===//
-// MachOWriter Implementation
-//===----------------------------------------------------------------------===//
+// getJumpTableSection - Select the Jump Table section
+MachOSection *MachOWriter::getJumpTableSection() {
+ if (TM.getRelocationModel() == Reloc::PIC_)
+ return getTextSection(false);
+ else
+ return getSection("__TEXT", "__const");
+}
-MachOWriter::MachOWriter(std::ostream &o, TargetMachine &tm) : O(o), TM(tm) {
- is64Bit = TM.getTargetData()->getPointerSizeInBits() == 64;
- isLittleEndian = TM.getTargetData()->isLittleEndian();
+// getSection - Return the section with the specified name, creating a new
+// section if one does not already exist.
+MachOSection *MachOWriter::getSection(const std::string &seg,
+ const std::string §,
+ unsigned Flags /* = 0 */ ) {
+ MachOSection *MOS = SectionLookup[seg+sect];
+ if (MOS) return MOS;
+
+ MOS = new MachOSection(seg, sect);
+ SectionList.push_back(MOS);
+ MOS->Index = SectionList.size();
+ MOS->flags = MachOSection::S_REGULAR | Flags;
+ SectionLookup[seg+sect] = MOS;
+ return MOS;
+}
- // Create the machine code emitter object for this target.
- MCE = new MachOCodeEmitter(*this);
+// getTextSection - Return text section with different flags for code/data
+MachOSection *MachOWriter::getTextSection(bool isCode /* = true */ ) {
+ if (isCode)
+ return getSection("__TEXT", "__text",
+ MachOSection::S_ATTR_PURE_INSTRUCTIONS |
+ MachOSection::S_ATTR_SOME_INSTRUCTIONS);
+ else
+ return getSection("__TEXT", "__text");
}
-MachOWriter::~MachOWriter() {
- delete MCE;
+MachOSection *MachOWriter::getBSSSection() {
+ return getSection("__DATA", "__bss", MachOSection::S_ZEROFILL);
}
-void MachOWriter::AddSymbolToSection(MachOSection &Sec, GlobalVariable *GV) {
+// GetJTRelocation - Get a relocation a new BB relocation based
+// on target information.
+MachineRelocation MachOWriter::GetJTRelocation(unsigned Offset,
+ MachineBasicBlock *MBB) const {
+ return TM.getMachOWriterInfo()->GetJTRelocation(Offset, MBB);
+}
+
+// GetTargetRelocation - Returns the number of relocations.
+unsigned MachOWriter::GetTargetRelocation(MachineRelocation &MR,
+ unsigned FromIdx, unsigned ToAddr,
+ unsigned ToIndex, OutputBuffer &RelocOut,
+ OutputBuffer &SecOut, bool Scattered,
+ bool Extern) {
+ return TM.getMachOWriterInfo()->GetTargetRelocation(MR, FromIdx, ToAddr,
+ ToIndex, RelocOut,
+ SecOut, Scattered,
+ Extern);
+}
+
+void MachOWriter::AddSymbolToSection(MachOSection *Sec, GlobalVariable *GV) {
const Type *Ty = GV->getType()->getElementType();
- unsigned Size = TM.getTargetData()->getTypeSize(Ty);
- unsigned Align = Log2_32(TM.getTargetData()->getTypeAlignment(Ty));
-
- MachOSym Sym(GV, Mang->getValueName(GV), Sec.Index);
+ unsigned Size = TM.getTargetData()->getTypeAllocSize(Ty);
+ unsigned Align = TM.getTargetData()->getPreferredAlignment(GV);
+
// Reserve space in the .bss section for this symbol while maintaining the
// desired section alignment, which must be at least as much as required by
// this symbol.
+ OutputBuffer SecDataOut(Sec->getData(), is64Bit, isLittleEndian);
+
if (Align) {
- Sec.align = std::max(unsigned(Sec.align), Align);
- Sec.size = (Sec.size + Align - 1) & ~(Align-1);
+ Align = Log2_32(Align);
+ Sec->align = std::max(unsigned(Sec->align), Align);
+
+ Sec->emitAlignment(Sec->align);
+ }
+ // Globals without external linkage apparently do not go in the symbol table.
+ if (!GV->hasLocalLinkage()) {
+ MachOSym Sym(GV, Mang->getMangledName(GV), Sec->Index, MAI);
+ Sym.n_value = Sec->size();
+ SymbolTable.push_back(Sym);
}
+
// Record the offset of the symbol, and then allocate space for it.
- Sym.n_value = Sec.size;
- Sec.size += Size;
+ // FIXME: remove when we have unified size + output buffer
- switch (GV->getLinkage()) {
- default: // weak/linkonce handled above
- assert(0 && "Unexpected linkage type!");
- case GlobalValue::ExternalLinkage:
- Sym.n_type |= MachOSym::N_EXT;
- break;
- case GlobalValue::InternalLinkage:
- break;
- }
- SymbolTable.push_back(Sym);
+ // Now that we know what section the GlovalVariable is going to be emitted
+ // into, update our mappings.
+ // FIXME: We may also need to update this when outputting non-GlobalVariable
+ // GlobalValues such as functions.
+
+ GVSection[GV] = Sec;
+ GVOffset[GV] = Sec->size();
+
+ // Allocate space in the section for the global.
+ for (unsigned i = 0; i < Size; ++i)
+ SecDataOut.outbyte(0);
}
void MachOWriter::EmitGlobal(GlobalVariable *GV) {
const Type *Ty = GV->getType()->getElementType();
- unsigned Size = TM.getTargetData()->getTypeSize(Ty);
+ unsigned Size = TM.getTargetData()->getTypeAllocSize(Ty);
bool NoInit = !GV->hasInitializer();
-
+
// If this global has a zero initializer, it is part of the .bss or common
// section.
if (NoInit || GV->getInitializer()->isNullValue()) {
// If this global is part of the common block, add it now. Variables are
// part of the common block if they are zero initialized and allowed to be
// merged with other symbols.
- if (NoInit || GV->hasLinkOnceLinkage() || GV->hasWeakLinkage()) {
- MachOSym ExtOrCommonSym(GV, Mang->getValueName(GV), MachOSym::NO_SECT);
+ if (NoInit || GV->hasLinkOnceLinkage() || GV->hasWeakLinkage() ||
+ GV->hasCommonLinkage()) {
+ MachOSym ExtOrCommonSym(GV, Mang->getMangledName(GV),
+ MachOSym::NO_SECT, MAI);
// For undefined (N_UNDF) external (N_EXT) types, n_value is the size in
// bytes of the symbol.
ExtOrCommonSym.n_value = Size;
- // If the symbol is external, we'll put it on a list of symbols whose
- // addition to the symbol table is being pended until we find a reference
- if (NoInit)
- PendingSyms.push_back(ExtOrCommonSym);
- else
- SymbolTable.push_back(ExtOrCommonSym);
+ SymbolTable.push_back(ExtOrCommonSym);
+ // Remember that we've seen this symbol
+ GVOffset[GV] = Size;
return;
}
// Otherwise, this symbol is part of the .bss section.
- MachOSection &BSS = getBSSSection();
+ MachOSection *BSS = getBSSSection();
AddSymbolToSection(BSS, GV);
return;
}
-
+
// Scalar read-only data goes in a literal section if the scalar is 4, 8, or
// 16 bytes, or a cstring. Other read only data goes into a regular const
// section. Read-write data goes in the data section.
- MachOSection &Sec = GV->isConstant() ? getConstSection(Ty) : getDataSection();
+ MachOSection *Sec = GV->isConstant() ? getConstSection(GV->getInitializer()) :
+ getDataSection();
AddSymbolToSection(Sec, GV);
-
- // FIXME: A couple significant changes are required for this to work, even for
- // trivial cases such as a constant integer:
- // 0. InitializeMemory needs to be split out of ExecutionEngine. We don't
- // want to have to create an ExecutionEngine such as JIT just to write
- // some bytes into a buffer. The only thing necessary for
- // InitializeMemory to function properly should be TargetData.
- //
- // 1. InitializeMemory needs to be enhanced to return MachineRelocations
- // rather than accessing the address of objects such basic blocks,
- // constant pools, and jump tables. The client of InitializeMemory such
- // as an object writer or jit emitter should then handle these relocs
- // appropriately.
- //
- // FIXME: need to allocate memory for the global initializer.
-}
-
-
-bool MachOWriter::runOnMachineFunction(MachineFunction &MF) {
- // Nothing to do here, this is all done through the MCE object.
- return false;
+ InitMem(GV->getInitializer(), GVOffset[GV], TM.getTargetData(), Sec);
}
-bool MachOWriter::doInitialization(Module &M) {
- // Set the magic value, now that we know the pointer size and endianness
- Header.setMagic(isLittleEndian, is64Bit);
-
- // Set the file type
- // FIXME: this only works for object files, we do not support the creation
- // of dynamic libraries or executables at this time.
- Header.filetype = MachOHeader::MH_OBJECT;
-
- Mang = new Mangler(M);
- return false;
-}
-
-/// doFinalization - Now that the module has been completely processed, emit
-/// the Mach-O file to 'O'.
-bool MachOWriter::doFinalization(Module &M) {
- // FIXME: we don't handle debug info yet, we should probably do that.
-
- // Okay, the.text section has been completed, build the .data, .bss, and
- // "common" sections next.
- for (Module::global_iterator I = M.global_begin(), E = M.global_end();
- I != E; ++I)
- EmitGlobal(I);
-
- // Emit the symbol table to temporary buffers, so that we know the size of
- // the string table when we write the load commands in the next phase.
- BufferSymbolAndStringTable();
-
- // Emit the header and load commands.
- EmitHeaderAndLoadCommands();
-
- // Emit the various sections and their relocation info.
- EmitSections();
-
- // Write the symbol table and the string table to the end of the file.
- O.write((char*)&SymT[0], SymT.size());
- O.write((char*)&StrT[0], StrT.size());
-
- // We are done with the abstract symbols.
- SectionList.clear();
- SymbolTable.clear();
- DynamicSymbolTable.clear();
- // Release the name mangler object.
- delete Mang; Mang = 0;
- return false;
-}
void MachOWriter::EmitHeaderAndLoadCommands() {
// Step #0: Fill in the segment load command size, since we need it to figure
// out the rest of the header fields
+
MachOSegment SEG("", is64Bit);
SEG.nsects = SectionList.size();
- SEG.cmdsize = SEG.cmdSize(is64Bit) +
- SEG.nsects * SectionList.begin()->cmdSize(is64Bit);
-
+ SEG.cmdsize = SEG.cmdSize(is64Bit) +
+ SEG.nsects * SectionList[0]->cmdSize(is64Bit);
+
// Step #1: calculate the number of load commands. We always have at least
// one, for the LC_SEGMENT load command, plus two for the normal
// and dynamic symbol tables, if there are any symbols.
Header.ncmds = SymbolTable.empty() ? 1 : 3;
-
+
// Step #2: calculate the size of the load commands
Header.sizeofcmds = SEG.cmdsize;
if (!SymbolTable.empty())
Header.sizeofcmds += SymTab.cmdsize + DySymTab.cmdsize;
-
+
// Step #3: write the header to the file
// Local alias to shortenify coming code.
- DataBuffer &FH = Header.HeaderData;
- outword(FH, Header.magic);
- outword(FH, Header.cputype);
- outword(FH, Header.cpusubtype);
- outword(FH, Header.filetype);
- outword(FH, Header.ncmds);
- outword(FH, Header.sizeofcmds);
- outword(FH, Header.flags);
+ std::vector<unsigned char> &FH = Header.HeaderData;
+ OutputBuffer FHOut(FH, is64Bit, isLittleEndian);
+
+ FHOut.outword(Header.magic);
+ FHOut.outword(TM.getMachOWriterInfo()->getCPUType());
+ FHOut.outword(TM.getMachOWriterInfo()->getCPUSubType());
+ FHOut.outword(Header.filetype);
+ FHOut.outword(Header.ncmds);
+ FHOut.outword(Header.sizeofcmds);
+ FHOut.outword(Header.flags);
if (is64Bit)
- outword(FH, Header.reserved);
-
+ FHOut.outword(Header.reserved);
+
// Step #4: Finish filling in the segment load command and write it out
- for (std::list<MachOSection>::iterator I = SectionList.begin(),
+ for (std::vector<MachOSection*>::iterator I = SectionList.begin(),
E = SectionList.end(); I != E; ++I)
- SEG.filesize += I->size;
+ SEG.filesize += (*I)->size();
+
SEG.vmsize = SEG.filesize;
SEG.fileoff = Header.cmdSize(is64Bit) + Header.sizeofcmds;
-
- outword(FH, SEG.cmd);
- outword(FH, SEG.cmdsize);
- outstring(FH, SEG.segname, 16);
- outaddr(FH, SEG.vmaddr);
- outaddr(FH, SEG.vmsize);
- outaddr(FH, SEG.fileoff);
- outaddr(FH, SEG.filesize);
- outword(FH, SEG.maxprot);
- outword(FH, SEG.initprot);
- outword(FH, SEG.nsects);
- outword(FH, SEG.flags);
-
- // Step #5: Finish filling in the fields of the MachOSections
+
+ FHOut.outword(SEG.cmd);
+ FHOut.outword(SEG.cmdsize);
+ FHOut.outstring(SEG.segname, 16);
+ FHOut.outaddr(SEG.vmaddr);
+ FHOut.outaddr(SEG.vmsize);
+ FHOut.outaddr(SEG.fileoff);
+ FHOut.outaddr(SEG.filesize);
+ FHOut.outword(SEG.maxprot);
+ FHOut.outword(SEG.initprot);
+ FHOut.outword(SEG.nsects);
+ FHOut.outword(SEG.flags);
+
+ // Step #5: Finish filling in the fields of the MachOSections
uint64_t currentAddr = 0;
- for (std::list<MachOSection>::iterator I = SectionList.begin(),
+ for (std::vector<MachOSection*>::iterator I = SectionList.begin(),
E = SectionList.end(); I != E; ++I) {
- I->addr = currentAddr;
- I->offset = currentAddr + SEG.fileoff;
-
+ MachOSection *MOS = *I;
+ MOS->addr = currentAddr;
+ MOS->offset = currentAddr + SEG.fileoff;
// FIXME: do we need to do something with alignment here?
- currentAddr += I->size;
+ currentAddr += MOS->size();
}
-
- // Step #6: Calculate the number of relocations for each section and write out
+
+ // Step #6: Emit the symbol table to temporary buffers, so that we know the
+ // size of the string table when we write the next load command. This also
+ // sorts and assigns indices to each of the symbols, which is necessary for
+ // emitting relocations to externally-defined objects.
+ BufferSymbolAndStringTable();
+
+ // Step #7: Calculate the number of relocations for each section and write out
// the section commands for each section
currentAddr += SEG.fileoff;
- for (std::list<MachOSection>::iterator I = SectionList.begin(),
+ for (std::vector<MachOSection*>::iterator I = SectionList.begin(),
E = SectionList.end(); I != E; ++I) {
- // calculate the relocation info for this section command
- CalculateRelocations(*I, currentAddr);
- currentAddr += I->nreloc * 8;
-
+ MachOSection *MOS = *I;
+
+ // Convert the relocations to target-specific relocations, and fill in the
+ // relocation offset for this section.
+ CalculateRelocations(*MOS);
+ MOS->reloff = MOS->nreloc ? currentAddr : 0;
+ currentAddr += MOS->nreloc * 8;
+
// write the finalized section command to the output buffer
- outstring(FH, I->sectname, 16);
- outstring(FH, I->segname, 16);
- outaddr(FH, I->addr);
- outaddr(FH, I->size);
- outword(FH, I->offset);
- outword(FH, I->align);
- outword(FH, I->reloff);
- outword(FH, I->nreloc);
- outword(FH, I->flags);
- outword(FH, I->reserved1);
- outword(FH, I->reserved2);
+ FHOut.outstring(MOS->sectname, 16);
+ FHOut.outstring(MOS->segname, 16);
+ FHOut.outaddr(MOS->addr);
+ FHOut.outaddr(MOS->size());
+ FHOut.outword(MOS->offset);
+ FHOut.outword(MOS->align);
+ FHOut.outword(MOS->reloff);
+ FHOut.outword(MOS->nreloc);
+ FHOut.outword(MOS->flags);
+ FHOut.outword(MOS->reserved1);
+ FHOut.outword(MOS->reserved2);
if (is64Bit)
- outword(FH, I->reserved3);
+ FHOut.outword(MOS->reserved3);
}
-
- // Step #7: Emit LC_SYMTAB/LC_DYSYMTAB load commands
- // FIXME: add size of relocs
+
+ // Step #8: Emit LC_SYMTAB/LC_DYSYMTAB load commands
SymTab.symoff = currentAddr;
SymTab.nsyms = SymbolTable.size();
SymTab.stroff = SymTab.symoff + SymT.size();
SymTab.strsize = StrT.size();
- outword(FH, SymTab.cmd);
- outword(FH, SymTab.cmdsize);
- outword(FH, SymTab.symoff);
- outword(FH, SymTab.nsyms);
- outword(FH, SymTab.stroff);
- outword(FH, SymTab.strsize);
+ FHOut.outword(SymTab.cmd);
+ FHOut.outword(SymTab.cmdsize);
+ FHOut.outword(SymTab.symoff);
+ FHOut.outword(SymTab.nsyms);
+ FHOut.outword(SymTab.stroff);
+ FHOut.outword(SymTab.strsize);
// FIXME: set DySymTab fields appropriately
// We should probably just update these in BufferSymbolAndStringTable since
// thats where we're partitioning up the different kinds of symbols.
- outword(FH, DySymTab.cmd);
- outword(FH, DySymTab.cmdsize);
- outword(FH, DySymTab.ilocalsym);
- outword(FH, DySymTab.nlocalsym);
- outword(FH, DySymTab.iextdefsym);
- outword(FH, DySymTab.nextdefsym);
- outword(FH, DySymTab.iundefsym);
- outword(FH, DySymTab.nundefsym);
- outword(FH, DySymTab.tocoff);
- outword(FH, DySymTab.ntoc);
- outword(FH, DySymTab.modtaboff);
- outword(FH, DySymTab.nmodtab);
- outword(FH, DySymTab.extrefsymoff);
- outword(FH, DySymTab.nextrefsyms);
- outword(FH, DySymTab.indirectsymoff);
- outword(FH, DySymTab.nindirectsyms);
- outword(FH, DySymTab.extreloff);
- outword(FH, DySymTab.nextrel);
- outword(FH, DySymTab.locreloff);
- outword(FH, DySymTab.nlocrel);
-
+ FHOut.outword(DySymTab.cmd);
+ FHOut.outword(DySymTab.cmdsize);
+ FHOut.outword(DySymTab.ilocalsym);
+ FHOut.outword(DySymTab.nlocalsym);
+ FHOut.outword(DySymTab.iextdefsym);
+ FHOut.outword(DySymTab.nextdefsym);
+ FHOut.outword(DySymTab.iundefsym);
+ FHOut.outword(DySymTab.nundefsym);
+ FHOut.outword(DySymTab.tocoff);
+ FHOut.outword(DySymTab.ntoc);
+ FHOut.outword(DySymTab.modtaboff);
+ FHOut.outword(DySymTab.nmodtab);
+ FHOut.outword(DySymTab.extrefsymoff);
+ FHOut.outword(DySymTab.nextrefsyms);
+ FHOut.outword(DySymTab.indirectsymoff);
+ FHOut.outword(DySymTab.nindirectsyms);
+ FHOut.outword(DySymTab.extreloff);
+ FHOut.outword(DySymTab.nextrel);
+ FHOut.outword(DySymTab.locreloff);
+ FHOut.outword(DySymTab.nlocrel);
+
O.write((char*)&FH[0], FH.size());
}
/// EmitSections - Now that we have constructed the file header and load
/// commands, emit the data for each section to the file.
void MachOWriter::EmitSections() {
- for (std::list<MachOSection>::iterator I = SectionList.begin(),
+ for (std::vector<MachOSection*>::iterator I = SectionList.begin(),
E = SectionList.end(); I != E; ++I)
// Emit the contents of each section
- O.write((char*)&I->SectionData[0], I->size);
- for (std::list<MachOSection>::iterator I = SectionList.begin(),
- E = SectionList.end(); I != E; ++I)
- // Emit the relocation entry data for each section.
- O.write((char*)&I->RelocBuffer[0], I->RelocBuffer.size());
-}
-
-/// PartitionByLocal - Simple boolean predicate that returns true if Sym is
-/// a local symbol rather than an external symbol.
-bool MachOWriter::PartitionByLocal(const MachOSym &Sym) {
- // FIXME: Not totally sure if private extern counts as external
- return (Sym.n_type & (MachOSym::N_EXT | MachOSym::N_PEXT)) == 0;
+ if ((*I)->size())
+ O.write((char*)&(*I)->getData()[0], (*I)->size());
}
-/// PartitionByDefined - Simple boolean predicate that returns true if Sym is
-/// defined in this module.
-bool MachOWriter::PartitionByDefined(const MachOSym &Sym) {
- // FIXME: Do N_ABS or N_INDR count as defined?
- return (Sym.n_type & MachOSym::N_SECT) == MachOSym::N_SECT;
+/// EmitRelocations - emit relocation data from buffer.
+void MachOWriter::EmitRelocations() {
+ for (std::vector<MachOSection*>::iterator I = SectionList.begin(),
+ E = SectionList.end(); I != E; ++I)
+ // Emit the relocation entry data for each section.
+ if ((*I)->RelocBuffer.size())
+ O.write((char*)&(*I)->RelocBuffer[0], (*I)->RelocBuffer.size());
}
/// BufferSymbolAndStringTable - Sort the symbols we encountered and assign them
// 1. local symbols
// 2. defined external symbols (sorted by name)
// 3. undefined external symbols (sorted by name)
-
+
+ // Before sorting the symbols, check the PendingGlobals for any undefined
+ // globals that need to be put in the symbol table.
+ for (std::vector<GlobalValue*>::iterator I = PendingGlobals.begin(),
+ E = PendingGlobals.end(); I != E; ++I) {
+ if (GVOffset[*I] == 0 && GVSection[*I] == 0) {
+ MachOSym UndfSym(*I, Mang->getMangledName(*I), MachOSym::NO_SECT, MAI);
+ SymbolTable.push_back(UndfSym);
+ GVOffset[*I] = -1;
+ }
+ }
+
// Sort the symbols by name, so that when we partition the symbols by scope
// of definition, we won't have to sort by name within each partition.
- std::sort(SymbolTable.begin(), SymbolTable.end(), MachOSymCmp());
+ std::sort(SymbolTable.begin(), SymbolTable.end(), MachOSym::SymCmp());
- // Parition the symbol table entries so that all local symbols come before
+ // Parition the symbol table entries so that all local symbols come before
// all symbols with external linkage. { 1 | 2 3 }
- std::partition(SymbolTable.begin(), SymbolTable.end(), PartitionByLocal);
-
+ std::partition(SymbolTable.begin(), SymbolTable.end(),
+ MachOSym::PartitionByLocal);
+
// Advance iterator to beginning of external symbols and partition so that
// all external symbols defined in this module come before all external
// symbols defined elsewhere. { 1 | 2 | 3 }
for (std::vector<MachOSym>::iterator I = SymbolTable.begin(),
E = SymbolTable.end(); I != E; ++I) {
- if (!PartitionByLocal(*I)) {
- std::partition(I, E, PartitionByDefined);
+ if (!MachOSym::PartitionByLocal(*I)) {
+ std::partition(I, E, MachOSym::PartitionByDefined);
break;
}
}
-
+
+ // Calculate the starting index for each of the local, extern defined, and
+ // undefined symbols, as well as the number of each to put in the LC_DYSYMTAB
+ // load command.
+ for (std::vector<MachOSym>::iterator I = SymbolTable.begin(),
+ E = SymbolTable.end(); I != E; ++I) {
+ if (MachOSym::PartitionByLocal(*I)) {
+ ++DySymTab.nlocalsym;
+ ++DySymTab.iextdefsym;
+ ++DySymTab.iundefsym;
+ } else if (MachOSym::PartitionByDefined(*I)) {
+ ++DySymTab.nextdefsym;
+ ++DySymTab.iundefsym;
+ } else {
+ ++DySymTab.nundefsym;
+ }
+ }
+
// Write out a leading zero byte when emitting string table, for n_strx == 0
// which means an empty string.
- outbyte(StrT, 0);
+ OutputBuffer StrTOut(StrT, is64Bit, isLittleEndian);
+ StrTOut.outbyte(0);
// The order of the string table is:
// 1. strings for external symbols
I->n_strx = 0;
} else {
I->n_strx = StrT.size();
- outstring(StrT, I->GVName, I->GVName.length()+1);
+ StrTOut.outstring(I->GVName, I->GVName.length()+1);
}
}
+ OutputBuffer SymTOut(SymT, is64Bit, isLittleEndian);
+
+ unsigned index = 0;
for (std::vector<MachOSym>::iterator I = SymbolTable.begin(),
- E = SymbolTable.end(); I != E; ++I) {
+ E = SymbolTable.end(); I != E; ++I, ++index) {
+ // Add the section base address to the section offset in the n_value field
+ // to calculate the full address.
+ // FIXME: handle symbols where the n_value field is not the address
+ GlobalValue *GV = const_cast<GlobalValue*>(I->GV);
+ if (GV && GVSection[GV])
+ I->n_value += GVSection[GV]->addr;
+ if (GV && (GVOffset[GV] == -1))
+ GVOffset[GV] = index;
+
// Emit nlist to buffer
- outword(SymT, I->n_strx);
- outbyte(SymT, I->n_type);
- outbyte(SymT, I->n_sect);
- outhalf(SymT, I->n_desc);
- outaddr(SymT, I->n_value);
+ SymTOut.outword(I->n_strx);
+ SymTOut.outbyte(I->n_type);
+ SymTOut.outbyte(I->n_sect);
+ SymTOut.outhalf(I->n_desc);
+ SymTOut.outaddr(I->n_value);
}
}
/// and the offset into that section. From this information, create the
/// appropriate target-specific MachORelocation type and add buffer it to be
/// written out after we are finished writing out sections.
-void MachOWriter::CalculateRelocations(MachOSection &MOS, unsigned RelOffset) {
- for (unsigned i = 0, e = MOS.Relocations.size(); i != e; ++i) {
- // FIXME: calculate the correct offset and section index for relocated
- // object.
- // FIXME: somehow convey the fact that the relocation might be external
- // to the relocating code.
- GetTargetRelocation(MOS.Relocations[i], MOS, MOS.Index);
+void MachOWriter::CalculateRelocations(MachOSection &MOS) {
+ std::vector<MachineRelocation> Relocations = MOS.getRelocations();
+ for (unsigned i = 0, e = Relocations.size(); i != e; ++i) {
+ MachineRelocation &MR = Relocations[i];
+ unsigned TargetSection = MR.getConstantVal();
+ unsigned TargetAddr = 0;
+ unsigned TargetIndex = 0;
+
+ // This is a scattered relocation entry if it points to a global value with
+ // a non-zero offset.
+ bool Scattered = false;
+ bool Extern = false;
+
+ // Since we may not have seen the GlobalValue we were interested in yet at
+ // the time we emitted the relocation for it, fix it up now so that it
+ // points to the offset into the correct section.
+ if (MR.isGlobalValue()) {
+ GlobalValue *GV = MR.getGlobalValue();
+ MachOSection *MOSPtr = GVSection[GV];
+ intptr_t Offset = GVOffset[GV];
+
+ // If we have never seen the global before, it must be to a symbol
+ // defined in another module (N_UNDF).
+ if (!MOSPtr) {
+ // FIXME: need to append stub suffix
+ Extern = true;
+ TargetAddr = 0;
+ TargetIndex = GVOffset[GV];
+ } else {
+ Scattered = TargetSection != 0;
+ TargetSection = MOSPtr->Index;
+ }
+ MR.setResultPointer((void*)Offset);
+ }
+
+ // If the symbol is locally defined, pass in the address of the section and
+ // the section index to the code which will generate the target relocation.
+ if (!Extern) {
+ MachOSection &To = *SectionList[TargetSection - 1];
+ TargetAddr = To.addr;
+ TargetIndex = To.Index;
+ }
+
+ OutputBuffer RelocOut(MOS.RelocBuffer, is64Bit, isLittleEndian);
+ OutputBuffer SecOut(MOS.getData(), is64Bit, isLittleEndian);
+
+ MOS.nreloc += GetTargetRelocation(MR, MOS.Index, TargetAddr, TargetIndex,
+ RelocOut, SecOut, Scattered, Extern);
}
- if (MOS.nreloc != 0)
- MOS.reloff = RelOffset;
}
-MachOSym::MachOSym(const GlobalValue *gv, std::string name, uint8_t sect) :
- GV(gv), GVName(name), n_strx(0), n_type(sect == NO_SECT ? N_UNDF : N_SECT),
- n_sect(sect), n_desc(0), n_value(0) {
- // FIXME: take a target machine, and then add the appropriate prefix for
- // the linkage type based on the TargetAsmInfo
+// InitMem - Write the value of a Constant to the specified memory location,
+// converting it into bytes and relocations.
+void MachOWriter::InitMem(const Constant *C, uintptr_t Offset,
+ const TargetData *TD, MachOSection* mos) {
+ typedef std::pair<const Constant*, intptr_t> CPair;
+ std::vector<CPair> WorkList;
+ uint8_t *Addr = &mos->getData()[0];
+
+ WorkList.push_back(CPair(C,(intptr_t)Addr + Offset));
+
+ intptr_t ScatteredOffset = 0;
+
+ while (!WorkList.empty()) {
+ const Constant *PC = WorkList.back().first;
+ intptr_t PA = WorkList.back().second;
+ WorkList.pop_back();
+
+ if (isa<UndefValue>(PC)) {
+ continue;
+ } else if (const ConstantVector *CP = dyn_cast<ConstantVector>(PC)) {
+ unsigned ElementSize =
+ TD->getTypeAllocSize(CP->getType()->getElementType());
+ for (unsigned i = 0, e = CP->getNumOperands(); i != e; ++i)
+ WorkList.push_back(CPair(CP->getOperand(i), PA+i*ElementSize));
+ } else if (const ConstantExpr *CE = dyn_cast<ConstantExpr>(PC)) {
+ //
+ // FIXME: Handle ConstantExpression. See EE::getConstantValue()
+ //
+ switch (CE->getOpcode()) {
+ case Instruction::GetElementPtr: {
+ SmallVector<Value*, 8> Indices(CE->op_begin()+1, CE->op_end());
+ ScatteredOffset = TD->getIndexedOffset(CE->getOperand(0)->getType(),
+ &Indices[0], Indices.size());
+ WorkList.push_back(CPair(CE->getOperand(0), PA));
+ break;
+ }
+ case Instruction::Add:
+ default:
+ errs() << "ConstantExpr not handled as global var init: " << *CE <<"\n";
+ llvm_unreachable(0);
+ }
+ } else if (PC->getType()->isSingleValueType()) {
+ unsigned char *ptr = (unsigned char *)PA;
+ switch (PC->getType()->getTypeID()) {
+ case Type::IntegerTyID: {
+ unsigned NumBits = cast<IntegerType>(PC->getType())->getBitWidth();
+ uint64_t val = cast<ConstantInt>(PC)->getZExtValue();
+ if (NumBits <= 8)
+ ptr[0] = val;
+ else if (NumBits <= 16) {
+ if (TD->isBigEndian())
+ val = ByteSwap_16(val);
+ ptr[0] = val;
+ ptr[1] = val >> 8;
+ } else if (NumBits <= 32) {
+ if (TD->isBigEndian())
+ val = ByteSwap_32(val);
+ ptr[0] = val;
+ ptr[1] = val >> 8;
+ ptr[2] = val >> 16;
+ ptr[3] = val >> 24;
+ } else if (NumBits <= 64) {
+ if (TD->isBigEndian())
+ val = ByteSwap_64(val);
+ ptr[0] = val;
+ ptr[1] = val >> 8;
+ ptr[2] = val >> 16;
+ ptr[3] = val >> 24;
+ ptr[4] = val >> 32;
+ ptr[5] = val >> 40;
+ ptr[6] = val >> 48;
+ ptr[7] = val >> 56;
+ } else {
+ llvm_unreachable("Not implemented: bit widths > 64");
+ }
+ break;
+ }
+ case Type::FloatTyID: {
+ uint32_t val = cast<ConstantFP>(PC)->getValueAPF().bitcastToAPInt().
+ getZExtValue();
+ if (TD->isBigEndian())
+ val = ByteSwap_32(val);
+ ptr[0] = val;
+ ptr[1] = val >> 8;
+ ptr[2] = val >> 16;
+ ptr[3] = val >> 24;
+ break;
+ }
+ case Type::DoubleTyID: {
+ uint64_t val = cast<ConstantFP>(PC)->getValueAPF().bitcastToAPInt().
+ getZExtValue();
+ if (TD->isBigEndian())
+ val = ByteSwap_64(val);
+ ptr[0] = val;
+ ptr[1] = val >> 8;
+ ptr[2] = val >> 16;
+ ptr[3] = val >> 24;
+ ptr[4] = val >> 32;
+ ptr[5] = val >> 40;
+ ptr[6] = val >> 48;
+ ptr[7] = val >> 56;
+ break;
+ }
+ case Type::PointerTyID:
+ if (isa<ConstantPointerNull>(PC))
+ memset(ptr, 0, TD->getPointerSize());
+ else if (const GlobalValue* GV = dyn_cast<GlobalValue>(PC)) {
+ // FIXME: what about function stubs?
+ mos->addRelocation(MachineRelocation::getGV(PA-(intptr_t)Addr,
+ MachineRelocation::VANILLA,
+ const_cast<GlobalValue*>(GV),
+ ScatteredOffset));
+ ScatteredOffset = 0;
+ } else
+ llvm_unreachable("Unknown constant pointer type!");
+ break;
+ default:
+ std::string msg;
+ raw_string_ostream Msg(msg);
+ Msg << "ERROR: Constant unimp for type: " << *PC->getType();
+ llvm_report_error(Msg.str());
+ }
+ } else if (isa<ConstantAggregateZero>(PC)) {
+ memset((void*)PA, 0, (size_t)TD->getTypeAllocSize(PC->getType()));
+ } else if (const ConstantArray *CPA = dyn_cast<ConstantArray>(PC)) {
+ unsigned ElementSize =
+ TD->getTypeAllocSize(CPA->getType()->getElementType());
+ for (unsigned i = 0, e = CPA->getNumOperands(); i != e; ++i)
+ WorkList.push_back(CPair(CPA->getOperand(i), PA+i*ElementSize));
+ } else if (const ConstantStruct *CPS = dyn_cast<ConstantStruct>(PC)) {
+ const StructLayout *SL =
+ TD->getStructLayout(cast<StructType>(CPS->getType()));
+ for (unsigned i = 0, e = CPS->getNumOperands(); i != e; ++i)
+ WorkList.push_back(CPair(CPS->getOperand(i),
+ PA+SL->getElementOffset(i)));
+ } else {
+ errs() << "Bad Type: " << *PC->getType() << "\n";
+ llvm_unreachable("Unknown constant type to initialize memory with!");
+ }
+ }
+}
+
+//===----------------------------------------------------------------------===//
+// MachOSym Implementation
+//===----------------------------------------------------------------------===//
+
+MachOSym::MachOSym(const GlobalValue *gv, std::string name, uint8_t sect,
+ const MCAsmInfo *MAI) :
+ GV(gv), n_strx(0), n_type(sect == NO_SECT ? N_UNDF : N_SECT), n_sect(sect),
+ n_desc(0), n_value(0) {
+
+ // FIXME: This is completely broken, it should use the mangler interface.
switch (GV->getLinkage()) {
default:
- assert(0 && "Unexpected linkage type!");
+ llvm_unreachable("Unexpected linkage type!");
break;
- case GlobalValue::WeakLinkage:
- case GlobalValue::LinkOnceLinkage:
+ case GlobalValue::WeakAnyLinkage:
+ case GlobalValue::WeakODRLinkage:
+ case GlobalValue::LinkOnceAnyLinkage:
+ case GlobalValue::LinkOnceODRLinkage:
+ case GlobalValue::CommonLinkage:
assert(!isa<Function>(gv) && "Unexpected linkage type for Function!");
case GlobalValue::ExternalLinkage:
- n_type |= N_EXT;
+ GVName = MAI->getGlobalPrefix() + name;
+ n_type |= GV->hasHiddenVisibility() ? N_PEXT : N_EXT;
+ break;
+ case GlobalValue::PrivateLinkage:
+ GVName = MAI->getPrivateGlobalPrefix() + name;
+ break;
+ case GlobalValue::LinkerPrivateLinkage:
+ GVName = MAI->getLinkerPrivateGlobalPrefix() + name;
break;
case GlobalValue::InternalLinkage:
+ GVName = MAI->getGlobalPrefix() + name;
break;
}
}
+
+} // end namespace llvm
projects / oota-llvm.git / blobdiff