diff options
Diffstat (limited to 'contrib/llvm/lib/Bitcode/Writer')
| -rw-r--r-- | contrib/llvm/lib/Bitcode/Writer/BitWriter.cpp | 49 | ||||
| -rw-r--r-- | contrib/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp | 3119 | ||||
| -rw-r--r-- | contrib/llvm/lib/Bitcode/Writer/BitcodeWriterPass.cpp | 57 | ||||
| -rw-r--r-- | contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp | 792 | ||||
| -rw-r--r-- | contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.h | 209 |
5 files changed, 4226 insertions, 0 deletions
diff --git a/contrib/llvm/lib/Bitcode/Writer/BitWriter.cpp b/contrib/llvm/lib/Bitcode/Writer/BitWriter.cpp new file mode 100644 index 0000000..7218ea0 --- /dev/null +++ b/contrib/llvm/lib/Bitcode/Writer/BitWriter.cpp @@ -0,0 +1,49 @@ +//===-- BitWriter.cpp -----------------------------------------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#include "llvm-c/BitWriter.h" +#include "llvm/Bitcode/ReaderWriter.h" +#include "llvm/IR/Module.h" +#include "llvm/Support/FileSystem.h" +#include "llvm/Support/raw_ostream.h" +using namespace llvm; + + +/*===-- Operations on modules ---------------------------------------------===*/ + +int LLVMWriteBitcodeToFile(LLVMModuleRef M, const char *Path) { + std::error_code EC; + raw_fd_ostream OS(Path, EC, sys::fs::F_None); + + if (EC) + return -1; + + WriteBitcodeToFile(unwrap(M), OS); + return 0; +} + +int LLVMWriteBitcodeToFD(LLVMModuleRef M, int FD, int ShouldClose, + int Unbuffered) { + raw_fd_ostream OS(FD, ShouldClose, Unbuffered); + + WriteBitcodeToFile(unwrap(M), OS); + return 0; +} + +int LLVMWriteBitcodeToFileHandle(LLVMModuleRef M, int FileHandle) { + return LLVMWriteBitcodeToFD(M, FileHandle, true, false); +} + +LLVMMemoryBufferRef LLVMWriteBitcodeToMemoryBuffer(LLVMModuleRef M) { + std::string Data; + raw_string_ostream OS(Data); + + WriteBitcodeToFile(unwrap(M), OS); + return wrap(MemoryBuffer::getMemBufferCopy(OS.str()).release()); +} diff --git a/contrib/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/contrib/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp new file mode 100644 index 0000000..a1f8786 --- /dev/null +++ b/contrib/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp @@ -0,0 +1,3119 @@ +//===--- Bitcode/Writer/BitcodeWriter.cpp - Bitcode Writer ----------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// Bitcode writer implementation. +// +//===----------------------------------------------------------------------===// + +#include "llvm/Bitcode/ReaderWriter.h" +#include "ValueEnumerator.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/Triple.h" +#include "llvm/Bitcode/BitstreamWriter.h" +#include "llvm/Bitcode/LLVMBitCodes.h" +#include "llvm/IR/CallSite.h" +#include "llvm/IR/Constants.h" +#include "llvm/IR/DebugInfoMetadata.h" +#include "llvm/IR/DerivedTypes.h" +#include "llvm/IR/InlineAsm.h" +#include "llvm/IR/Instructions.h" +#include "llvm/IR/LLVMContext.h" +#include "llvm/IR/IntrinsicInst.h" +#include "llvm/IR/Module.h" +#include "llvm/IR/Operator.h" +#include "llvm/IR/UseListOrder.h" +#include "llvm/IR/ValueSymbolTable.h" +#include "llvm/Support/CommandLine.h" +#include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/MathExtras.h" +#include "llvm/Support/Program.h" +#include "llvm/Support/raw_ostream.h" +#include <cctype> +#include <map> +using namespace llvm; + +/// These are manifest constants used by the bitcode writer. They do not need to +/// be kept in sync with the reader, but need to be consistent within this file. +enum { + // VALUE_SYMTAB_BLOCK abbrev id's. + VST_ENTRY_8_ABBREV = bitc::FIRST_APPLICATION_ABBREV, + VST_ENTRY_7_ABBREV, + VST_ENTRY_6_ABBREV, + VST_BBENTRY_6_ABBREV, + + // CONSTANTS_BLOCK abbrev id's. + CONSTANTS_SETTYPE_ABBREV = bitc::FIRST_APPLICATION_ABBREV, + CONSTANTS_INTEGER_ABBREV, + CONSTANTS_CE_CAST_Abbrev, + CONSTANTS_NULL_Abbrev, + + // FUNCTION_BLOCK abbrev id's. + FUNCTION_INST_LOAD_ABBREV = bitc::FIRST_APPLICATION_ABBREV, + FUNCTION_INST_BINOP_ABBREV, + FUNCTION_INST_BINOP_FLAGS_ABBREV, + FUNCTION_INST_CAST_ABBREV, + FUNCTION_INST_RET_VOID_ABBREV, + FUNCTION_INST_RET_VAL_ABBREV, + FUNCTION_INST_UNREACHABLE_ABBREV, + FUNCTION_INST_GEP_ABBREV, +}; + +static unsigned GetEncodedCastOpcode(unsigned Opcode) { + switch (Opcode) { + default: llvm_unreachable("Unknown cast instruction!"); + case Instruction::Trunc : return bitc::CAST_TRUNC; + case Instruction::ZExt : return bitc::CAST_ZEXT; + case Instruction::SExt : return bitc::CAST_SEXT; + case Instruction::FPToUI : return bitc::CAST_FPTOUI; + case Instruction::FPToSI : return bitc::CAST_FPTOSI; + case Instruction::UIToFP : return bitc::CAST_UITOFP; + case Instruction::SIToFP : return bitc::CAST_SITOFP; + case Instruction::FPTrunc : return bitc::CAST_FPTRUNC; + case Instruction::FPExt : return bitc::CAST_FPEXT; + case Instruction::PtrToInt: return bitc::CAST_PTRTOINT; + case Instruction::IntToPtr: return bitc::CAST_INTTOPTR; + case Instruction::BitCast : return bitc::CAST_BITCAST; + case Instruction::AddrSpaceCast: return bitc::CAST_ADDRSPACECAST; + } +} + +static unsigned GetEncodedBinaryOpcode(unsigned Opcode) { + switch (Opcode) { + default: llvm_unreachable("Unknown binary instruction!"); + case Instruction::Add: + case Instruction::FAdd: return bitc::BINOP_ADD; + case Instruction::Sub: + case Instruction::FSub: return bitc::BINOP_SUB; + case Instruction::Mul: + case Instruction::FMul: return bitc::BINOP_MUL; + case Instruction::UDiv: return bitc::BINOP_UDIV; + case Instruction::FDiv: + case Instruction::SDiv: return bitc::BINOP_SDIV; + case Instruction::URem: return bitc::BINOP_UREM; + case Instruction::FRem: + case Instruction::SRem: return bitc::BINOP_SREM; + case Instruction::Shl: return bitc::BINOP_SHL; + case Instruction::LShr: return bitc::BINOP_LSHR; + case Instruction::AShr: return bitc::BINOP_ASHR; + case Instruction::And: return bitc::BINOP_AND; + case Instruction::Or: return bitc::BINOP_OR; + case Instruction::Xor: return bitc::BINOP_XOR; + } +} + +static unsigned GetEncodedRMWOperation(AtomicRMWInst::BinOp Op) { + switch (Op) { + default: llvm_unreachable("Unknown RMW operation!"); + case AtomicRMWInst::Xchg: return bitc::RMW_XCHG; + case AtomicRMWInst::Add: return bitc::RMW_ADD; + case AtomicRMWInst::Sub: return bitc::RMW_SUB; + case AtomicRMWInst::And: return bitc::RMW_AND; + case AtomicRMWInst::Nand: return bitc::RMW_NAND; + case AtomicRMWInst::Or: return bitc::RMW_OR; + case AtomicRMWInst::Xor: return bitc::RMW_XOR; + case AtomicRMWInst::Max: return bitc::RMW_MAX; + case AtomicRMWInst::Min: return bitc::RMW_MIN; + case AtomicRMWInst::UMax: return bitc::RMW_UMAX; + case AtomicRMWInst::UMin: return bitc::RMW_UMIN; + } +} + +static unsigned GetEncodedOrdering(AtomicOrdering Ordering) { + switch (Ordering) { + case NotAtomic: return bitc::ORDERING_NOTATOMIC; + case Unordered: return bitc::ORDERING_UNORDERED; + case Monotonic: return bitc::ORDERING_MONOTONIC; + case Acquire: return bitc::ORDERING_ACQUIRE; + case Release: return bitc::ORDERING_RELEASE; + case AcquireRelease: return bitc::ORDERING_ACQREL; + case SequentiallyConsistent: return bitc::ORDERING_SEQCST; + } + llvm_unreachable("Invalid ordering"); +} + +static unsigned GetEncodedSynchScope(SynchronizationScope SynchScope) { + switch (SynchScope) { + case SingleThread: return bitc::SYNCHSCOPE_SINGLETHREAD; + case CrossThread: return bitc::SYNCHSCOPE_CROSSTHREAD; + } + llvm_unreachable("Invalid synch scope"); +} + +static void WriteStringRecord(unsigned Code, StringRef Str, + unsigned AbbrevToUse, BitstreamWriter &Stream) { + SmallVector<unsigned, 64> Vals; + + // Code: [strchar x N] + for (unsigned i = 0, e = Str.size(); i != e; ++i) { + if (AbbrevToUse && !BitCodeAbbrevOp::isChar6(Str[i])) + AbbrevToUse = 0; + Vals.push_back(Str[i]); + } + + // Emit the finished record. + Stream.EmitRecord(Code, Vals, AbbrevToUse); +} + +static uint64_t getAttrKindEncoding(Attribute::AttrKind Kind) { + switch (Kind) { + case Attribute::Alignment: + return bitc::ATTR_KIND_ALIGNMENT; + case Attribute::AlwaysInline: + return bitc::ATTR_KIND_ALWAYS_INLINE; + case Attribute::ArgMemOnly: + return bitc::ATTR_KIND_ARGMEMONLY; + case Attribute::Builtin: + return bitc::ATTR_KIND_BUILTIN; + case Attribute::ByVal: + return bitc::ATTR_KIND_BY_VAL; + case Attribute::Convergent: + return bitc::ATTR_KIND_CONVERGENT; + case Attribute::InAlloca: + return bitc::ATTR_KIND_IN_ALLOCA; + case Attribute::Cold: + return bitc::ATTR_KIND_COLD; + case Attribute::InaccessibleMemOnly: + return bitc::ATTR_KIND_INACCESSIBLEMEM_ONLY; + case Attribute::InaccessibleMemOrArgMemOnly: + return bitc::ATTR_KIND_INACCESSIBLEMEM_OR_ARGMEMONLY; + case Attribute::InlineHint: + return bitc::ATTR_KIND_INLINE_HINT; + case Attribute::InReg: + return bitc::ATTR_KIND_IN_REG; + case Attribute::JumpTable: + return bitc::ATTR_KIND_JUMP_TABLE; + case Attribute::MinSize: + return bitc::ATTR_KIND_MIN_SIZE; + case Attribute::Naked: + return bitc::ATTR_KIND_NAKED; + case Attribute::Nest: + return bitc::ATTR_KIND_NEST; + case Attribute::NoAlias: + return bitc::ATTR_KIND_NO_ALIAS; + case Attribute::NoBuiltin: + return bitc::ATTR_KIND_NO_BUILTIN; + case Attribute::NoCapture: + return bitc::ATTR_KIND_NO_CAPTURE; + case Attribute::NoDuplicate: + return bitc::ATTR_KIND_NO_DUPLICATE; + case Attribute::NoImplicitFloat: + return bitc::ATTR_KIND_NO_IMPLICIT_FLOAT; + case Attribute::NoInline: + return bitc::ATTR_KIND_NO_INLINE; + case Attribute::NoRecurse: + return bitc::ATTR_KIND_NO_RECURSE; + case Attribute::NonLazyBind: + return bitc::ATTR_KIND_NON_LAZY_BIND; + case Attribute::NonNull: + return bitc::ATTR_KIND_NON_NULL; + case Attribute::Dereferenceable: + return bitc::ATTR_KIND_DEREFERENCEABLE; + case Attribute::DereferenceableOrNull: + return bitc::ATTR_KIND_DEREFERENCEABLE_OR_NULL; + case Attribute::NoRedZone: + return bitc::ATTR_KIND_NO_RED_ZONE; + case Attribute::NoReturn: + return bitc::ATTR_KIND_NO_RETURN; + case Attribute::NoUnwind: + return bitc::ATTR_KIND_NO_UNWIND; + case Attribute::OptimizeForSize: + return bitc::ATTR_KIND_OPTIMIZE_FOR_SIZE; + case Attribute::OptimizeNone: + return bitc::ATTR_KIND_OPTIMIZE_NONE; + case Attribute::ReadNone: + return bitc::ATTR_KIND_READ_NONE; + case Attribute::ReadOnly: + return bitc::ATTR_KIND_READ_ONLY; + case Attribute::Returned: + return bitc::ATTR_KIND_RETURNED; + case Attribute::ReturnsTwice: + return bitc::ATTR_KIND_RETURNS_TWICE; + case Attribute::SExt: + return bitc::ATTR_KIND_S_EXT; + case Attribute::StackAlignment: + return bitc::ATTR_KIND_STACK_ALIGNMENT; + case Attribute::StackProtect: + return bitc::ATTR_KIND_STACK_PROTECT; + case Attribute::StackProtectReq: + return bitc::ATTR_KIND_STACK_PROTECT_REQ; + case Attribute::StackProtectStrong: + return bitc::ATTR_KIND_STACK_PROTECT_STRONG; + case Attribute::SafeStack: + return bitc::ATTR_KIND_SAFESTACK; + case Attribute::StructRet: + return bitc::ATTR_KIND_STRUCT_RET; + case Attribute::SanitizeAddress: + return bitc::ATTR_KIND_SANITIZE_ADDRESS; + case Attribute::SanitizeThread: + return bitc::ATTR_KIND_SANITIZE_THREAD; + case Attribute::SanitizeMemory: + return bitc::ATTR_KIND_SANITIZE_MEMORY; + case Attribute::UWTable: + return bitc::ATTR_KIND_UW_TABLE; + case Attribute::ZExt: + return bitc::ATTR_KIND_Z_EXT; + case Attribute::EndAttrKinds: + llvm_unreachable("Can not encode end-attribute kinds marker."); + case Attribute::None: + llvm_unreachable("Can not encode none-attribute."); + } + + llvm_unreachable("Trying to encode unknown attribute"); +} + +static void WriteAttributeGroupTable(const ValueEnumerator &VE, + BitstreamWriter &Stream) { + const std::vector<AttributeSet> &AttrGrps = VE.getAttributeGroups(); + if (AttrGrps.empty()) return; + + Stream.EnterSubblock(bitc::PARAMATTR_GROUP_BLOCK_ID, 3); + + SmallVector<uint64_t, 64> Record; + for (unsigned i = 0, e = AttrGrps.size(); i != e; ++i) { + AttributeSet AS = AttrGrps[i]; + for (unsigned i = 0, e = AS.getNumSlots(); i != e; ++i) { + AttributeSet A = AS.getSlotAttributes(i); + + Record.push_back(VE.getAttributeGroupID(A)); + Record.push_back(AS.getSlotIndex(i)); + + for (AttributeSet::iterator I = AS.begin(0), E = AS.end(0); + I != E; ++I) { + Attribute Attr = *I; + if (Attr.isEnumAttribute()) { + Record.push_back(0); + Record.push_back(getAttrKindEncoding(Attr.getKindAsEnum())); + } else if (Attr.isIntAttribute()) { + Record.push_back(1); + Record.push_back(getAttrKindEncoding(Attr.getKindAsEnum())); + Record.push_back(Attr.getValueAsInt()); + } else { + StringRef Kind = Attr.getKindAsString(); + StringRef Val = Attr.getValueAsString(); + + Record.push_back(Val.empty() ? 3 : 4); + Record.append(Kind.begin(), Kind.end()); + Record.push_back(0); + if (!Val.empty()) { + Record.append(Val.begin(), Val.end()); + Record.push_back(0); + } + } + } + + Stream.EmitRecord(bitc::PARAMATTR_GRP_CODE_ENTRY, Record); + Record.clear(); + } + } + + Stream.ExitBlock(); +} + +static void WriteAttributeTable(const ValueEnumerator &VE, + BitstreamWriter &Stream) { + const std::vector<AttributeSet> &Attrs = VE.getAttributes(); + if (Attrs.empty()) return; + + Stream.EnterSubblock(bitc::PARAMATTR_BLOCK_ID, 3); + + SmallVector<uint64_t, 64> Record; + for (unsigned i = 0, e = Attrs.size(); i != e; ++i) { + const AttributeSet &A = Attrs[i]; + for (unsigned i = 0, e = A.getNumSlots(); i != e; ++i) + Record.push_back(VE.getAttributeGroupID(A.getSlotAttributes(i))); + + Stream.EmitRecord(bitc::PARAMATTR_CODE_ENTRY, Record); + Record.clear(); + } + + Stream.ExitBlock(); +} + +/// WriteTypeTable - Write out the type table for a module. +static void WriteTypeTable(const ValueEnumerator &VE, BitstreamWriter &Stream) { + const ValueEnumerator::TypeList &TypeList = VE.getTypes(); + + Stream.EnterSubblock(bitc::TYPE_BLOCK_ID_NEW, 4 /*count from # abbrevs */); + SmallVector<uint64_t, 64> TypeVals; + + uint64_t NumBits = VE.computeBitsRequiredForTypeIndicies(); + + // Abbrev for TYPE_CODE_POINTER. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_POINTER)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, NumBits)); + Abbv->Add(BitCodeAbbrevOp(0)); // Addrspace = 0 + unsigned PtrAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for TYPE_CODE_FUNCTION. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_FUNCTION)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // isvararg + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, NumBits)); + + unsigned FunctionAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for TYPE_CODE_STRUCT_ANON. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_STRUCT_ANON)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // ispacked + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, NumBits)); + + unsigned StructAnonAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for TYPE_CODE_STRUCT_NAME. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_STRUCT_NAME)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + unsigned StructNameAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for TYPE_CODE_STRUCT_NAMED. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_STRUCT_NAMED)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // ispacked + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, NumBits)); + + unsigned StructNamedAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for TYPE_CODE_ARRAY. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::TYPE_CODE_ARRAY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // size + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, NumBits)); + + unsigned ArrayAbbrev = Stream.EmitAbbrev(Abbv); + + // Emit an entry count so the reader can reserve space. + TypeVals.push_back(TypeList.size()); + Stream.EmitRecord(bitc::TYPE_CODE_NUMENTRY, TypeVals); + TypeVals.clear(); + + // Loop over all of the types, emitting each in turn. + for (unsigned i = 0, e = TypeList.size(); i != e; ++i) { + Type *T = TypeList[i]; + int AbbrevToUse = 0; + unsigned Code = 0; + + switch (T->getTypeID()) { + case Type::VoidTyID: Code = bitc::TYPE_CODE_VOID; break; + case Type::HalfTyID: Code = bitc::TYPE_CODE_HALF; break; + case Type::FloatTyID: Code = bitc::TYPE_CODE_FLOAT; break; + case Type::DoubleTyID: Code = bitc::TYPE_CODE_DOUBLE; break; + case Type::X86_FP80TyID: Code = bitc::TYPE_CODE_X86_FP80; break; + case Type::FP128TyID: Code = bitc::TYPE_CODE_FP128; break; + case Type::PPC_FP128TyID: Code = bitc::TYPE_CODE_PPC_FP128; break; + case Type::LabelTyID: Code = bitc::TYPE_CODE_LABEL; break; + case Type::MetadataTyID: Code = bitc::TYPE_CODE_METADATA; break; + case Type::X86_MMXTyID: Code = bitc::TYPE_CODE_X86_MMX; break; + case Type::TokenTyID: Code = bitc::TYPE_CODE_TOKEN; break; + case Type::IntegerTyID: + // INTEGER: [width] + Code = bitc::TYPE_CODE_INTEGER; + TypeVals.push_back(cast<IntegerType>(T)->getBitWidth()); + break; + case Type::PointerTyID: { + PointerType *PTy = cast<PointerType>(T); + // POINTER: [pointee type, address space] + Code = bitc::TYPE_CODE_POINTER; + TypeVals.push_back(VE.getTypeID(PTy->getElementType())); + unsigned AddressSpace = PTy->getAddressSpace(); + TypeVals.push_back(AddressSpace); + if (AddressSpace == 0) AbbrevToUse = PtrAbbrev; + break; + } + case Type::FunctionTyID: { + FunctionType *FT = cast<FunctionType>(T); + // FUNCTION: [isvararg, retty, paramty x N] + Code = bitc::TYPE_CODE_FUNCTION; + TypeVals.push_back(FT->isVarArg()); + TypeVals.push_back(VE.getTypeID(FT->getReturnType())); + for (unsigned i = 0, e = FT->getNumParams(); i != e; ++i) + TypeVals.push_back(VE.getTypeID(FT->getParamType(i))); + AbbrevToUse = FunctionAbbrev; + break; + } + case Type::StructTyID: { + StructType *ST = cast<StructType>(T); + // STRUCT: [ispacked, eltty x N] + TypeVals.push_back(ST->isPacked()); + // Output all of the element types. + for (StructType::element_iterator I = ST->element_begin(), + E = ST->element_end(); I != E; ++I) + TypeVals.push_back(VE.getTypeID(*I)); + + if (ST->isLiteral()) { + Code = bitc::TYPE_CODE_STRUCT_ANON; + AbbrevToUse = StructAnonAbbrev; + } else { + if (ST->isOpaque()) { + Code = bitc::TYPE_CODE_OPAQUE; + } else { + Code = bitc::TYPE_CODE_STRUCT_NAMED; + AbbrevToUse = StructNamedAbbrev; + } + + // Emit the name if it is present. + if (!ST->getName().empty()) + WriteStringRecord(bitc::TYPE_CODE_STRUCT_NAME, ST->getName(), + StructNameAbbrev, Stream); + } + break; + } + case Type::ArrayTyID: { + ArrayType *AT = cast<ArrayType>(T); + // ARRAY: [numelts, eltty] + Code = bitc::TYPE_CODE_ARRAY; + TypeVals.push_back(AT->getNumElements()); + TypeVals.push_back(VE.getTypeID(AT->getElementType())); + AbbrevToUse = ArrayAbbrev; + break; + } + case Type::VectorTyID: { + VectorType *VT = cast<VectorType>(T); + // VECTOR [numelts, eltty] + Code = bitc::TYPE_CODE_VECTOR; + TypeVals.push_back(VT->getNumElements()); + TypeVals.push_back(VE.getTypeID(VT->getElementType())); + break; + } + } + + // Emit the finished record. + Stream.EmitRecord(Code, TypeVals, AbbrevToUse); + TypeVals.clear(); + } + + Stream.ExitBlock(); +} + +static unsigned getEncodedLinkage(const GlobalValue &GV) { + switch (GV.getLinkage()) { + case GlobalValue::ExternalLinkage: + return 0; + case GlobalValue::WeakAnyLinkage: + return 16; + case GlobalValue::AppendingLinkage: + return 2; + case GlobalValue::InternalLinkage: + return 3; + case GlobalValue::LinkOnceAnyLinkage: + return 18; + case GlobalValue::ExternalWeakLinkage: + return 7; + case GlobalValue::CommonLinkage: + return 8; + case GlobalValue::PrivateLinkage: + return 9; + case GlobalValue::WeakODRLinkage: + return 17; + case GlobalValue::LinkOnceODRLinkage: + return 19; + case GlobalValue::AvailableExternallyLinkage: + return 12; + } + llvm_unreachable("Invalid linkage"); +} + +static unsigned getEncodedVisibility(const GlobalValue &GV) { + switch (GV.getVisibility()) { + case GlobalValue::DefaultVisibility: return 0; + case GlobalValue::HiddenVisibility: return 1; + case GlobalValue::ProtectedVisibility: return 2; + } + llvm_unreachable("Invalid visibility"); +} + +static unsigned getEncodedDLLStorageClass(const GlobalValue &GV) { + switch (GV.getDLLStorageClass()) { + case GlobalValue::DefaultStorageClass: return 0; + case GlobalValue::DLLImportStorageClass: return 1; + case GlobalValue::DLLExportStorageClass: return 2; + } + llvm_unreachable("Invalid DLL storage class"); +} + +static unsigned getEncodedThreadLocalMode(const GlobalValue &GV) { + switch (GV.getThreadLocalMode()) { + case GlobalVariable::NotThreadLocal: return 0; + case GlobalVariable::GeneralDynamicTLSModel: return 1; + case GlobalVariable::LocalDynamicTLSModel: return 2; + case GlobalVariable::InitialExecTLSModel: return 3; + case GlobalVariable::LocalExecTLSModel: return 4; + } + llvm_unreachable("Invalid TLS model"); +} + +static unsigned getEncodedComdatSelectionKind(const Comdat &C) { + switch (C.getSelectionKind()) { + case Comdat::Any: + return bitc::COMDAT_SELECTION_KIND_ANY; + case Comdat::ExactMatch: + return bitc::COMDAT_SELECTION_KIND_EXACT_MATCH; + case Comdat::Largest: + return bitc::COMDAT_SELECTION_KIND_LARGEST; + case Comdat::NoDuplicates: + return bitc::COMDAT_SELECTION_KIND_NO_DUPLICATES; + case Comdat::SameSize: + return bitc::COMDAT_SELECTION_KIND_SAME_SIZE; + } + llvm_unreachable("Invalid selection kind"); +} + +static void writeComdats(const ValueEnumerator &VE, BitstreamWriter &Stream) { + SmallVector<uint16_t, 64> Vals; + for (const Comdat *C : VE.getComdats()) { + // COMDAT: [selection_kind, name] + Vals.push_back(getEncodedComdatSelectionKind(*C)); + size_t Size = C->getName().size(); + assert(isUInt<16>(Size)); + Vals.push_back(Size); + for (char Chr : C->getName()) + Vals.push_back((unsigned char)Chr); + Stream.EmitRecord(bitc::MODULE_CODE_COMDAT, Vals, /*AbbrevToUse=*/0); + Vals.clear(); + } +} + +/// Write a record that will eventually hold the word offset of the +/// module-level VST. For now the offset is 0, which will be backpatched +/// after the real VST is written. Returns the bit offset to backpatch. +static uint64_t WriteValueSymbolTableForwardDecl(const ValueSymbolTable &VST, + BitstreamWriter &Stream) { + if (VST.empty()) + return 0; + + // Write a placeholder value in for the offset of the real VST, + // which is written after the function blocks so that it can include + // the offset of each function. The placeholder offset will be + // updated when the real VST is written. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MODULE_CODE_VSTOFFSET)); + // Blocks are 32-bit aligned, so we can use a 32-bit word offset to + // hold the real VST offset. Must use fixed instead of VBR as we don't + // know how many VBR chunks to reserve ahead of time. + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); + unsigned VSTOffsetAbbrev = Stream.EmitAbbrev(Abbv); + + // Emit the placeholder + uint64_t Vals[] = {bitc::MODULE_CODE_VSTOFFSET, 0}; + Stream.EmitRecordWithAbbrev(VSTOffsetAbbrev, Vals); + + // Compute and return the bit offset to the placeholder, which will be + // patched when the real VST is written. We can simply subtract the 32-bit + // fixed size from the current bit number to get the location to backpatch. + return Stream.GetCurrentBitNo() - 32; +} + +/// Emit top-level description of module, including target triple, inline asm, +/// descriptors for global variables, and function prototype info. +/// Returns the bit offset to backpatch with the location of the real VST. +static uint64_t WriteModuleInfo(const Module *M, const ValueEnumerator &VE, + BitstreamWriter &Stream) { + // Emit various pieces of data attached to a module. + if (!M->getTargetTriple().empty()) + WriteStringRecord(bitc::MODULE_CODE_TRIPLE, M->getTargetTriple(), + 0/*TODO*/, Stream); + const std::string &DL = M->getDataLayoutStr(); + if (!DL.empty()) + WriteStringRecord(bitc::MODULE_CODE_DATALAYOUT, DL, 0 /*TODO*/, Stream); + if (!M->getModuleInlineAsm().empty()) + WriteStringRecord(bitc::MODULE_CODE_ASM, M->getModuleInlineAsm(), + 0/*TODO*/, Stream); + + // Emit information about sections and GC, computing how many there are. Also + // compute the maximum alignment value. + std::map<std::string, unsigned> SectionMap; + std::map<std::string, unsigned> GCMap; + unsigned MaxAlignment = 0; + unsigned MaxGlobalType = 0; + for (const GlobalValue &GV : M->globals()) { + MaxAlignment = std::max(MaxAlignment, GV.getAlignment()); + MaxGlobalType = std::max(MaxGlobalType, VE.getTypeID(GV.getValueType())); + if (GV.hasSection()) { + // Give section names unique ID's. + unsigned &Entry = SectionMap[GV.getSection()]; + if (!Entry) { + WriteStringRecord(bitc::MODULE_CODE_SECTIONNAME, GV.getSection(), + 0/*TODO*/, Stream); + Entry = SectionMap.size(); + } + } + } + for (const Function &F : *M) { + MaxAlignment = std::max(MaxAlignment, F.getAlignment()); + if (F.hasSection()) { + // Give section names unique ID's. + unsigned &Entry = SectionMap[F.getSection()]; + if (!Entry) { + WriteStringRecord(bitc::MODULE_CODE_SECTIONNAME, F.getSection(), + 0/*TODO*/, Stream); + Entry = SectionMap.size(); + } + } + if (F.hasGC()) { + // Same for GC names. + unsigned &Entry = GCMap[F.getGC()]; + if (!Entry) { + WriteStringRecord(bitc::MODULE_CODE_GCNAME, F.getGC(), + 0/*TODO*/, Stream); + Entry = GCMap.size(); + } + } + } + + // Emit abbrev for globals, now that we know # sections and max alignment. + unsigned SimpleGVarAbbrev = 0; + if (!M->global_empty()) { + // Add an abbrev for common globals with no visibility or thread localness. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MODULE_CODE_GLOBALVAR)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, + Log2_32_Ceil(MaxGlobalType+1))); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // AddrSpace << 2 + //| explicitType << 1 + //| constant + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Initializer. + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 5)); // Linkage. + if (MaxAlignment == 0) // Alignment. + Abbv->Add(BitCodeAbbrevOp(0)); + else { + unsigned MaxEncAlignment = Log2_32(MaxAlignment)+1; + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, + Log2_32_Ceil(MaxEncAlignment+1))); + } + if (SectionMap.empty()) // Section. + Abbv->Add(BitCodeAbbrevOp(0)); + else + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, + Log2_32_Ceil(SectionMap.size()+1))); + // Don't bother emitting vis + thread local. + SimpleGVarAbbrev = Stream.EmitAbbrev(Abbv); + } + + // Emit the global variable information. + SmallVector<unsigned, 64> Vals; + for (const GlobalVariable &GV : M->globals()) { + unsigned AbbrevToUse = 0; + + // GLOBALVAR: [type, isconst, initid, + // linkage, alignment, section, visibility, threadlocal, + // unnamed_addr, externally_initialized, dllstorageclass, + // comdat] + Vals.push_back(VE.getTypeID(GV.getValueType())); + Vals.push_back(GV.getType()->getAddressSpace() << 2 | 2 | GV.isConstant()); + Vals.push_back(GV.isDeclaration() ? 0 : + (VE.getValueID(GV.getInitializer()) + 1)); + Vals.push_back(getEncodedLinkage(GV)); + Vals.push_back(Log2_32(GV.getAlignment())+1); + Vals.push_back(GV.hasSection() ? SectionMap[GV.getSection()] : 0); + if (GV.isThreadLocal() || + GV.getVisibility() != GlobalValue::DefaultVisibility || + GV.hasUnnamedAddr() || GV.isExternallyInitialized() || + GV.getDLLStorageClass() != GlobalValue::DefaultStorageClass || + GV.hasComdat()) { + Vals.push_back(getEncodedVisibility(GV)); + Vals.push_back(getEncodedThreadLocalMode(GV)); + Vals.push_back(GV.hasUnnamedAddr()); + Vals.push_back(GV.isExternallyInitialized()); + Vals.push_back(getEncodedDLLStorageClass(GV)); + Vals.push_back(GV.hasComdat() ? VE.getComdatID(GV.getComdat()) : 0); + } else { + AbbrevToUse = SimpleGVarAbbrev; + } + + Stream.EmitRecord(bitc::MODULE_CODE_GLOBALVAR, Vals, AbbrevToUse); + Vals.clear(); + } + + // Emit the function proto information. + for (const Function &F : *M) { + // FUNCTION: [type, callingconv, isproto, linkage, paramattrs, alignment, + // section, visibility, gc, unnamed_addr, prologuedata, + // dllstorageclass, comdat, prefixdata, personalityfn] + Vals.push_back(VE.getTypeID(F.getFunctionType())); + Vals.push_back(F.getCallingConv()); + Vals.push_back(F.isDeclaration()); + Vals.push_back(getEncodedLinkage(F)); + Vals.push_back(VE.getAttributeID(F.getAttributes())); + Vals.push_back(Log2_32(F.getAlignment())+1); + Vals.push_back(F.hasSection() ? SectionMap[F.getSection()] : 0); + Vals.push_back(getEncodedVisibility(F)); + Vals.push_back(F.hasGC() ? GCMap[F.getGC()] : 0); + Vals.push_back(F.hasUnnamedAddr()); + Vals.push_back(F.hasPrologueData() ? (VE.getValueID(F.getPrologueData()) + 1) + : 0); + Vals.push_back(getEncodedDLLStorageClass(F)); + Vals.push_back(F.hasComdat() ? VE.getComdatID(F.getComdat()) : 0); + Vals.push_back(F.hasPrefixData() ? (VE.getValueID(F.getPrefixData()) + 1) + : 0); + Vals.push_back( + F.hasPersonalityFn() ? (VE.getValueID(F.getPersonalityFn()) + 1) : 0); + + unsigned AbbrevToUse = 0; + Stream.EmitRecord(bitc::MODULE_CODE_FUNCTION, Vals, AbbrevToUse); + Vals.clear(); + } + + // Emit the alias information. + for (const GlobalAlias &A : M->aliases()) { + // ALIAS: [alias type, aliasee val#, linkage, visibility] + Vals.push_back(VE.getTypeID(A.getValueType())); + Vals.push_back(A.getType()->getAddressSpace()); + Vals.push_back(VE.getValueID(A.getAliasee())); + Vals.push_back(getEncodedLinkage(A)); + Vals.push_back(getEncodedVisibility(A)); + Vals.push_back(getEncodedDLLStorageClass(A)); + Vals.push_back(getEncodedThreadLocalMode(A)); + Vals.push_back(A.hasUnnamedAddr()); + unsigned AbbrevToUse = 0; + Stream.EmitRecord(bitc::MODULE_CODE_ALIAS, Vals, AbbrevToUse); + Vals.clear(); + } + + // Write a record indicating the number of module-level metadata IDs + // This is needed because the ids of metadata are assigned implicitly + // based on their ordering in the bitcode, with the function-level + // metadata ids starting after the module-level metadata ids. For + // function importing where we lazy load the metadata as a postpass, + // we want to avoid parsing the module-level metadata before parsing + // the imported functions. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MODULE_CODE_METADATA_VALUES)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + unsigned MDValsAbbrev = Stream.EmitAbbrev(Abbv); + Vals.push_back(VE.numMDs()); + Stream.EmitRecord(bitc::MODULE_CODE_METADATA_VALUES, Vals, MDValsAbbrev); + Vals.clear(); + + uint64_t VSTOffsetPlaceholder = + WriteValueSymbolTableForwardDecl(M->getValueSymbolTable(), Stream); + return VSTOffsetPlaceholder; +} + +static uint64_t GetOptimizationFlags(const Value *V) { + uint64_t Flags = 0; + + if (const auto *OBO = dyn_cast<OverflowingBinaryOperator>(V)) { + if (OBO->hasNoSignedWrap()) + Flags |= 1 << bitc::OBO_NO_SIGNED_WRAP; + if (OBO->hasNoUnsignedWrap()) + Flags |= 1 << bitc::OBO_NO_UNSIGNED_WRAP; + } else if (const auto *PEO = dyn_cast<PossiblyExactOperator>(V)) { + if (PEO->isExact()) + Flags |= 1 << bitc::PEO_EXACT; + } else if (const auto *FPMO = dyn_cast<FPMathOperator>(V)) { + if (FPMO->hasUnsafeAlgebra()) + Flags |= FastMathFlags::UnsafeAlgebra; + if (FPMO->hasNoNaNs()) + Flags |= FastMathFlags::NoNaNs; + if (FPMO->hasNoInfs()) + Flags |= FastMathFlags::NoInfs; + if (FPMO->hasNoSignedZeros()) + Flags |= FastMathFlags::NoSignedZeros; + if (FPMO->hasAllowReciprocal()) + Flags |= FastMathFlags::AllowReciprocal; + } + + return Flags; +} + +static void WriteValueAsMetadata(const ValueAsMetadata *MD, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record) { + // Mimic an MDNode with a value as one operand. + Value *V = MD->getValue(); + Record.push_back(VE.getTypeID(V->getType())); + Record.push_back(VE.getValueID(V)); + Stream.EmitRecord(bitc::METADATA_VALUE, Record, 0); + Record.clear(); +} + +static void WriteMDTuple(const MDTuple *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, unsigned Abbrev) { + for (unsigned i = 0, e = N->getNumOperands(); i != e; ++i) { + Metadata *MD = N->getOperand(i); + assert(!(MD && isa<LocalAsMetadata>(MD)) && + "Unexpected function-local metadata"); + Record.push_back(VE.getMetadataOrNullID(MD)); + } + Stream.EmitRecord(N->isDistinct() ? bitc::METADATA_DISTINCT_NODE + : bitc::METADATA_NODE, + Record, Abbrev); + Record.clear(); +} + +static void WriteDILocation(const DILocation *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getLine()); + Record.push_back(N->getColumn()); + Record.push_back(VE.getMetadataID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getInlinedAt())); + + Stream.EmitRecord(bitc::METADATA_LOCATION, Record, Abbrev); + Record.clear(); +} + +static void WriteGenericDINode(const GenericDINode *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(0); // Per-tag version field; unused for now. + + for (auto &I : N->operands()) + Record.push_back(VE.getMetadataOrNullID(I)); + + Stream.EmitRecord(bitc::METADATA_GENERIC_DEBUG, Record, Abbrev); + Record.clear(); +} + +static uint64_t rotateSign(int64_t I) { + uint64_t U = I; + return I < 0 ? ~(U << 1) : U << 1; +} + +static void WriteDISubrange(const DISubrange *N, const ValueEnumerator &, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getCount()); + Record.push_back(rotateSign(N->getLowerBound())); + + Stream.EmitRecord(bitc::METADATA_SUBRANGE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIEnumerator(const DIEnumerator *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(rotateSign(N->getValue())); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + + Stream.EmitRecord(bitc::METADATA_ENUMERATOR, Record, Abbrev); + Record.clear(); +} + +static void WriteDIBasicType(const DIBasicType *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(N->getSizeInBits()); + Record.push_back(N->getAlignInBits()); + Record.push_back(N->getEncoding()); + + Stream.EmitRecord(bitc::METADATA_BASIC_TYPE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIDerivedType(const DIDerivedType *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getBaseType())); + Record.push_back(N->getSizeInBits()); + Record.push_back(N->getAlignInBits()); + Record.push_back(N->getOffsetInBits()); + Record.push_back(N->getFlags()); + Record.push_back(VE.getMetadataOrNullID(N->getExtraData())); + + Stream.EmitRecord(bitc::METADATA_DERIVED_TYPE, Record, Abbrev); + Record.clear(); +} + +static void WriteDICompositeType(const DICompositeType *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getBaseType())); + Record.push_back(N->getSizeInBits()); + Record.push_back(N->getAlignInBits()); + Record.push_back(N->getOffsetInBits()); + Record.push_back(N->getFlags()); + Record.push_back(VE.getMetadataOrNullID(N->getElements().get())); + Record.push_back(N->getRuntimeLang()); + Record.push_back(VE.getMetadataOrNullID(N->getVTableHolder())); + Record.push_back(VE.getMetadataOrNullID(N->getTemplateParams().get())); + Record.push_back(VE.getMetadataOrNullID(N->getRawIdentifier())); + + Stream.EmitRecord(bitc::METADATA_COMPOSITE_TYPE, Record, Abbrev); + Record.clear(); +} + +static void WriteDISubroutineType(const DISubroutineType *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getFlags()); + Record.push_back(VE.getMetadataOrNullID(N->getTypeArray().get())); + + Stream.EmitRecord(bitc::METADATA_SUBROUTINE_TYPE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIFile(const DIFile *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getRawFilename())); + Record.push_back(VE.getMetadataOrNullID(N->getRawDirectory())); + + Stream.EmitRecord(bitc::METADATA_FILE, Record, Abbrev); + Record.clear(); +} + +static void WriteDICompileUnit(const DICompileUnit *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + assert(N->isDistinct() && "Expected distinct compile units"); + Record.push_back(/* IsDistinct */ true); + Record.push_back(N->getSourceLanguage()); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(VE.getMetadataOrNullID(N->getRawProducer())); + Record.push_back(N->isOptimized()); + Record.push_back(VE.getMetadataOrNullID(N->getRawFlags())); + Record.push_back(N->getRuntimeVersion()); + Record.push_back(VE.getMetadataOrNullID(N->getRawSplitDebugFilename())); + Record.push_back(N->getEmissionKind()); + Record.push_back(VE.getMetadataOrNullID(N->getEnumTypes().get())); + Record.push_back(VE.getMetadataOrNullID(N->getRetainedTypes().get())); + Record.push_back(VE.getMetadataOrNullID(N->getSubprograms().get())); + Record.push_back(VE.getMetadataOrNullID(N->getGlobalVariables().get())); + Record.push_back(VE.getMetadataOrNullID(N->getImportedEntities().get())); + Record.push_back(N->getDWOId()); + Record.push_back(VE.getMetadataOrNullID(N->getMacros().get())); + + Stream.EmitRecord(bitc::METADATA_COMPILE_UNIT, Record, Abbrev); + Record.clear(); +} + +static void WriteDISubprogram(const DISubprogram *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getRawLinkageName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + Record.push_back(N->isLocalToUnit()); + Record.push_back(N->isDefinition()); + Record.push_back(N->getScopeLine()); + Record.push_back(VE.getMetadataOrNullID(N->getContainingType())); + Record.push_back(N->getVirtuality()); + Record.push_back(N->getVirtualIndex()); + Record.push_back(N->getFlags()); + Record.push_back(N->isOptimized()); + Record.push_back(VE.getMetadataOrNullID(N->getTemplateParams().get())); + Record.push_back(VE.getMetadataOrNullID(N->getDeclaration())); + Record.push_back(VE.getMetadataOrNullID(N->getVariables().get())); + + Stream.EmitRecord(bitc::METADATA_SUBPROGRAM, Record, Abbrev); + Record.clear(); +} + +static void WriteDILexicalBlock(const DILexicalBlock *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(N->getColumn()); + + Stream.EmitRecord(bitc::METADATA_LEXICAL_BLOCK, Record, Abbrev); + Record.clear(); +} + +static void WriteDILexicalBlockFile(const DILexicalBlockFile *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getDiscriminator()); + + Stream.EmitRecord(bitc::METADATA_LEXICAL_BLOCK_FILE, Record, Abbrev); + Record.clear(); +} + +static void WriteDINamespace(const DINamespace *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(N->getLine()); + + Stream.EmitRecord(bitc::METADATA_NAMESPACE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIMacro(const DIMacro *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getMacinfoType()); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getRawValue())); + + Stream.EmitRecord(bitc::METADATA_MACRO, Record, Abbrev); + Record.clear(); +} + +static void WriteDIMacroFile(const DIMacroFile *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getMacinfoType()); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(VE.getMetadataOrNullID(N->getElements().get())); + + Stream.EmitRecord(bitc::METADATA_MACRO_FILE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIModule(const DIModule *N, const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, unsigned Abbrev) { + Record.push_back(N->isDistinct()); + for (auto &I : N->operands()) + Record.push_back(VE.getMetadataOrNullID(I)); + + Stream.EmitRecord(bitc::METADATA_MODULE, Record, Abbrev); + Record.clear(); +} + +static void WriteDITemplateTypeParameter(const DITemplateTypeParameter *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + + Stream.EmitRecord(bitc::METADATA_TEMPLATE_TYPE, Record, Abbrev); + Record.clear(); +} + +static void WriteDITemplateValueParameter(const DITemplateValueParameter *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + Record.push_back(VE.getMetadataOrNullID(N->getValue())); + + Stream.EmitRecord(bitc::METADATA_TEMPLATE_VALUE, Record, Abbrev); + Record.clear(); +} + +static void WriteDIGlobalVariable(const DIGlobalVariable *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getRawLinkageName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + Record.push_back(N->isLocalToUnit()); + Record.push_back(N->isDefinition()); + Record.push_back(VE.getMetadataOrNullID(N->getRawVariable())); + Record.push_back(VE.getMetadataOrNullID(N->getStaticDataMemberDeclaration())); + + Stream.EmitRecord(bitc::METADATA_GLOBAL_VAR, Record, Abbrev); + Record.clear(); +} + +static void WriteDILocalVariable(const DILocalVariable *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + Record.push_back(N->getArg()); + Record.push_back(N->getFlags()); + + Stream.EmitRecord(bitc::METADATA_LOCAL_VAR, Record, Abbrev); + Record.clear(); +} + +static void WriteDIExpression(const DIExpression *N, const ValueEnumerator &, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.reserve(N->getElements().size() + 1); + + Record.push_back(N->isDistinct()); + Record.append(N->elements_begin(), N->elements_end()); + + Stream.EmitRecord(bitc::METADATA_EXPRESSION, Record, Abbrev); + Record.clear(); +} + +static void WriteDIObjCProperty(const DIObjCProperty *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + Record.push_back(VE.getMetadataOrNullID(N->getFile())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getRawSetterName())); + Record.push_back(VE.getMetadataOrNullID(N->getRawGetterName())); + Record.push_back(N->getAttributes()); + Record.push_back(VE.getMetadataOrNullID(N->getType())); + + Stream.EmitRecord(bitc::METADATA_OBJC_PROPERTY, Record, Abbrev); + Record.clear(); +} + +static void WriteDIImportedEntity(const DIImportedEntity *N, + const ValueEnumerator &VE, + BitstreamWriter &Stream, + SmallVectorImpl<uint64_t> &Record, + unsigned Abbrev) { + Record.push_back(N->isDistinct()); + Record.push_back(N->getTag()); + Record.push_back(VE.getMetadataOrNullID(N->getScope())); + Record.push_back(VE.getMetadataOrNullID(N->getEntity())); + Record.push_back(N->getLine()); + Record.push_back(VE.getMetadataOrNullID(N->getRawName())); + + Stream.EmitRecord(bitc::METADATA_IMPORTED_ENTITY, Record, Abbrev); + Record.clear(); +} + +static void WriteModuleMetadata(const Module *M, + const ValueEnumerator &VE, + BitstreamWriter &Stream) { + const auto &MDs = VE.getMDs(); + if (MDs.empty() && M->named_metadata_empty()) + return; + + Stream.EnterSubblock(bitc::METADATA_BLOCK_ID, 3); + + unsigned MDSAbbrev = 0; + if (VE.hasMDString()) { + // Abbrev for METADATA_STRING. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::METADATA_STRING)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + MDSAbbrev = Stream.EmitAbbrev(Abbv); + } + + // Initialize MDNode abbreviations. +#define HANDLE_MDNODE_LEAF(CLASS) unsigned CLASS##Abbrev = 0; +#include "llvm/IR/Metadata.def" + + if (VE.hasDILocation()) { + // Abbrev for METADATA_LOCATION. + // + // Assume the column is usually under 128, and always output the inlined-at + // location (it's never more expensive than building an array size 1). + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::METADATA_LOCATION)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + DILocationAbbrev = Stream.EmitAbbrev(Abbv); + } + + if (VE.hasGenericDINode()) { + // Abbrev for METADATA_GENERIC_DEBUG. + // + // Assume the column is usually under 128, and always output the inlined-at + // location (it's never more expensive than building an array size 1). + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::METADATA_GENERIC_DEBUG)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + GenericDINodeAbbrev = Stream.EmitAbbrev(Abbv); + } + + unsigned NameAbbrev = 0; + if (!M->named_metadata_empty()) { + // Abbrev for METADATA_NAME. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::METADATA_NAME)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + NameAbbrev = Stream.EmitAbbrev(Abbv); + } + + SmallVector<uint64_t, 64> Record; + for (const Metadata *MD : MDs) { + if (const MDNode *N = dyn_cast<MDNode>(MD)) { + assert(N->isResolved() && "Expected forward references to be resolved"); + + switch (N->getMetadataID()) { + default: + llvm_unreachable("Invalid MDNode subclass"); +#define HANDLE_MDNODE_LEAF(CLASS) \ + case Metadata::CLASS##Kind: \ + Write##CLASS(cast<CLASS>(N), VE, Stream, Record, CLASS##Abbrev); \ + continue; +#include "llvm/IR/Metadata.def" + } + } + if (const auto *MDC = dyn_cast<ConstantAsMetadata>(MD)) { + WriteValueAsMetadata(MDC, VE, Stream, Record); + continue; + } + const MDString *MDS = cast<MDString>(MD); + // Code: [strchar x N] + Record.append(MDS->bytes_begin(), MDS->bytes_end()); + + // Emit the finished record. + Stream.EmitRecord(bitc::METADATA_STRING, Record, MDSAbbrev); + Record.clear(); + } + + // Write named metadata. + for (const NamedMDNode &NMD : M->named_metadata()) { + // Write name. + StringRef Str = NMD.getName(); + Record.append(Str.bytes_begin(), Str.bytes_end()); + Stream.EmitRecord(bitc::METADATA_NAME, Record, NameAbbrev); + Record.clear(); + + // Write named metadata operands. + for (const MDNode *N : NMD.operands()) + Record.push_back(VE.getMetadataID(N)); + Stream.EmitRecord(bitc::METADATA_NAMED_NODE, Record, 0); + Record.clear(); + } + + Stream.ExitBlock(); +} + +static void WriteFunctionLocalMetadata(const Function &F, + const ValueEnumerator &VE, + BitstreamWriter &Stream) { + bool StartedMetadataBlock = false; + SmallVector<uint64_t, 64> Record; + const SmallVectorImpl<const LocalAsMetadata *> &MDs = + VE.getFunctionLocalMDs(); + for (unsigned i = 0, e = MDs.size(); i != e; ++i) { + assert(MDs[i] && "Expected valid function-local metadata"); + if (!StartedMetadataBlock) { + Stream.EnterSubblock(bitc::METADATA_BLOCK_ID, 3); + StartedMetadataBlock = true; + } + WriteValueAsMetadata(MDs[i], VE, Stream, Record); + } + + if (StartedMetadataBlock) + Stream.ExitBlock(); +} + +static void WriteMetadataAttachment(const Function &F, + const ValueEnumerator &VE, + BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::METADATA_ATTACHMENT_ID, 3); + + SmallVector<uint64_t, 64> Record; + + // Write metadata attachments + // METADATA_ATTACHMENT - [m x [value, [n x [id, mdnode]]] + SmallVector<std::pair<unsigned, MDNode *>, 4> MDs; + F.getAllMetadata(MDs); + if (!MDs.empty()) { + for (const auto &I : MDs) { + Record.push_back(I.first); + Record.push_back(VE.getMetadataID(I.second)); + } + Stream.EmitRecord(bitc::METADATA_ATTACHMENT, Record, 0); + Record.clear(); + } + + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) { + MDs.clear(); + I.getAllMetadataOtherThanDebugLoc(MDs); + + // If no metadata, ignore instruction. + if (MDs.empty()) continue; + + Record.push_back(VE.getInstructionID(&I)); + + for (unsigned i = 0, e = MDs.size(); i != e; ++i) { + Record.push_back(MDs[i].first); + Record.push_back(VE.getMetadataID(MDs[i].second)); + } + Stream.EmitRecord(bitc::METADATA_ATTACHMENT, Record, 0); + Record.clear(); + } + + Stream.ExitBlock(); +} + +static void WriteModuleMetadataStore(const Module *M, BitstreamWriter &Stream) { + SmallVector<uint64_t, 64> Record; + + // Write metadata kinds + // METADATA_KIND - [n x [id, name]] + SmallVector<StringRef, 8> Names; + M->getMDKindNames(Names); + + if (Names.empty()) return; + + Stream.EnterSubblock(bitc::METADATA_KIND_BLOCK_ID, 3); + + for (unsigned MDKindID = 0, e = Names.size(); MDKindID != e; ++MDKindID) { + Record.push_back(MDKindID); + StringRef KName = Names[MDKindID]; + Record.append(KName.begin(), KName.end()); + + Stream.EmitRecord(bitc::METADATA_KIND, Record, 0); + Record.clear(); + } + + Stream.ExitBlock(); +} + +static void WriteOperandBundleTags(const Module *M, BitstreamWriter &Stream) { + // Write metadata kinds + // + // OPERAND_BUNDLE_TAGS_BLOCK_ID : N x OPERAND_BUNDLE_TAG + // + // OPERAND_BUNDLE_TAG - [strchr x N] + + SmallVector<StringRef, 8> Tags; + M->getOperandBundleTags(Tags); + + if (Tags.empty()) + return; + + Stream.EnterSubblock(bitc::OPERAND_BUNDLE_TAGS_BLOCK_ID, 3); + + SmallVector<uint64_t, 64> Record; + + for (auto Tag : Tags) { + Record.append(Tag.begin(), Tag.end()); + + Stream.EmitRecord(bitc::OPERAND_BUNDLE_TAG, Record, 0); + Record.clear(); + } + + Stream.ExitBlock(); +} + +static void emitSignedInt64(SmallVectorImpl<uint64_t> &Vals, uint64_t V) { + if ((int64_t)V >= 0) + Vals.push_back(V << 1); + else + Vals.push_back((-V << 1) | 1); +} + +static void WriteConstants(unsigned FirstVal, unsigned LastVal, + const ValueEnumerator &VE, + BitstreamWriter &Stream, bool isGlobal) { + if (FirstVal == LastVal) return; + + Stream.EnterSubblock(bitc::CONSTANTS_BLOCK_ID, 4); + + unsigned AggregateAbbrev = 0; + unsigned String8Abbrev = 0; + unsigned CString7Abbrev = 0; + unsigned CString6Abbrev = 0; + // If this is a constant pool for the module, emit module-specific abbrevs. + if (isGlobal) { + // Abbrev for CST_CODE_AGGREGATE. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_AGGREGATE)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, Log2_32_Ceil(LastVal+1))); + AggregateAbbrev = Stream.EmitAbbrev(Abbv); + + // Abbrev for CST_CODE_STRING. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_STRING)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + String8Abbrev = Stream.EmitAbbrev(Abbv); + // Abbrev for CST_CODE_CSTRING. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_CSTRING)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); + CString7Abbrev = Stream.EmitAbbrev(Abbv); + // Abbrev for CST_CODE_CSTRING. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_CSTRING)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + CString6Abbrev = Stream.EmitAbbrev(Abbv); + } + + SmallVector<uint64_t, 64> Record; + + const ValueEnumerator::ValueList &Vals = VE.getValues(); + Type *LastTy = nullptr; + for (unsigned i = FirstVal; i != LastVal; ++i) { + const Value *V = Vals[i].first; + // If we need to switch types, do so now. + if (V->getType() != LastTy) { + LastTy = V->getType(); + Record.push_back(VE.getTypeID(LastTy)); + Stream.EmitRecord(bitc::CST_CODE_SETTYPE, Record, + CONSTANTS_SETTYPE_ABBREV); + Record.clear(); + } + + if (const InlineAsm *IA = dyn_cast<InlineAsm>(V)) { + Record.push_back(unsigned(IA->hasSideEffects()) | + unsigned(IA->isAlignStack()) << 1 | + unsigned(IA->getDialect()&1) << 2); + + // Add the asm string. + const std::string &AsmStr = IA->getAsmString(); + Record.push_back(AsmStr.size()); + Record.append(AsmStr.begin(), AsmStr.end()); + + // Add the constraint string. + const std::string &ConstraintStr = IA->getConstraintString(); + Record.push_back(ConstraintStr.size()); + Record.append(ConstraintStr.begin(), ConstraintStr.end()); + Stream.EmitRecord(bitc::CST_CODE_INLINEASM, Record); + Record.clear(); + continue; + } + const Constant *C = cast<Constant>(V); + unsigned Code = -1U; + unsigned AbbrevToUse = 0; + if (C->isNullValue()) { + Code = bitc::CST_CODE_NULL; + } else if (isa<UndefValue>(C)) { + Code = bitc::CST_CODE_UNDEF; + } else if (const ConstantInt *IV = dyn_cast<ConstantInt>(C)) { + if (IV->getBitWidth() <= 64) { + uint64_t V = IV->getSExtValue(); + emitSignedInt64(Record, V); + Code = bitc::CST_CODE_INTEGER; + AbbrevToUse = CONSTANTS_INTEGER_ABBREV; + } else { // Wide integers, > 64 bits in size. + // We have an arbitrary precision integer value to write whose + // bit width is > 64. However, in canonical unsigned integer + // format it is likely that the high bits are going to be zero. + // So, we only write the number of active words. + unsigned NWords = IV->getValue().getActiveWords(); + const uint64_t *RawWords = IV->getValue().getRawData(); + for (unsigned i = 0; i != NWords; ++i) { + emitSignedInt64(Record, RawWords[i]); + } + Code = bitc::CST_CODE_WIDE_INTEGER; + } + } else if (const ConstantFP *CFP = dyn_cast<ConstantFP>(C)) { + Code = bitc::CST_CODE_FLOAT; + Type *Ty = CFP->getType(); + if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy()) { + Record.push_back(CFP->getValueAPF().bitcastToAPInt().getZExtValue()); + } else if (Ty->isX86_FP80Ty()) { + // api needed to prevent premature destruction + // bits are not in the same order as a normal i80 APInt, compensate. + APInt api = CFP->getValueAPF().bitcastToAPInt(); + const uint64_t *p = api.getRawData(); + Record.push_back((p[1] << 48) | (p[0] >> 16)); + Record.push_back(p[0] & 0xffffLL); + } else if (Ty->isFP128Ty() || Ty->isPPC_FP128Ty()) { + APInt api = CFP->getValueAPF().bitcastToAPInt(); + const uint64_t *p = api.getRawData(); + Record.push_back(p[0]); + Record.push_back(p[1]); + } else { + assert (0 && "Unknown FP type!"); + } + } else if (isa<ConstantDataSequential>(C) && + cast<ConstantDataSequential>(C)->isString()) { + const ConstantDataSequential *Str = cast<ConstantDataSequential>(C); + // Emit constant strings specially. + unsigned NumElts = Str->getNumElements(); + // If this is a null-terminated string, use the denser CSTRING encoding. + if (Str->isCString()) { + Code = bitc::CST_CODE_CSTRING; + --NumElts; // Don't encode the null, which isn't allowed by char6. + } else { + Code = bitc::CST_CODE_STRING; + AbbrevToUse = String8Abbrev; + } + bool isCStr7 = Code == bitc::CST_CODE_CSTRING; + bool isCStrChar6 = Code == bitc::CST_CODE_CSTRING; + for (unsigned i = 0; i != NumElts; ++i) { + unsigned char V = Str->getElementAsInteger(i); + Record.push_back(V); + isCStr7 &= (V & 128) == 0; + if (isCStrChar6) + isCStrChar6 = BitCodeAbbrevOp::isChar6(V); + } + + if (isCStrChar6) + AbbrevToUse = CString6Abbrev; + else if (isCStr7) + AbbrevToUse = CString7Abbrev; + } else if (const ConstantDataSequential *CDS = + dyn_cast<ConstantDataSequential>(C)) { + Code = bitc::CST_CODE_DATA; + Type *EltTy = CDS->getType()->getElementType(); + if (isa<IntegerType>(EltTy)) { + for (unsigned i = 0, e = CDS->getNumElements(); i != e; ++i) + Record.push_back(CDS->getElementAsInteger(i)); + } else if (EltTy->isFloatTy()) { + for (unsigned i = 0, e = CDS->getNumElements(); i != e; ++i) { + union { float F; uint32_t I; }; + F = CDS->getElementAsFloat(i); + Record.push_back(I); + } + } else { + assert(EltTy->isDoubleTy() && "Unknown ConstantData element type"); + for (unsigned i = 0, e = CDS->getNumElements(); i != e; ++i) { + union { double F; uint64_t I; }; + F = CDS->getElementAsDouble(i); + Record.push_back(I); + } + } + } else if (isa<ConstantArray>(C) || isa<ConstantStruct>(C) || + isa<ConstantVector>(C)) { + Code = bitc::CST_CODE_AGGREGATE; + for (const Value *Op : C->operands()) + Record.push_back(VE.getValueID(Op)); + AbbrevToUse = AggregateAbbrev; + } else if (const ConstantExpr *CE = dyn_cast<ConstantExpr>(C)) { + switch (CE->getOpcode()) { + default: + if (Instruction::isCast(CE->getOpcode())) { + Code = bitc::CST_CODE_CE_CAST; + Record.push_back(GetEncodedCastOpcode(CE->getOpcode())); + Record.push_back(VE.getTypeID(C->getOperand(0)->getType())); + Record.push_back(VE.getValueID(C->getOperand(0))); + AbbrevToUse = CONSTANTS_CE_CAST_Abbrev; + } else { + assert(CE->getNumOperands() == 2 && "Unknown constant expr!"); + Code = bitc::CST_CODE_CE_BINOP; + Record.push_back(GetEncodedBinaryOpcode(CE->getOpcode())); + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getValueID(C->getOperand(1))); + uint64_t Flags = GetOptimizationFlags(CE); + if (Flags != 0) + Record.push_back(Flags); + } + break; + case Instruction::GetElementPtr: { + Code = bitc::CST_CODE_CE_GEP; + const auto *GO = cast<GEPOperator>(C); + if (GO->isInBounds()) + Code = bitc::CST_CODE_CE_INBOUNDS_GEP; + Record.push_back(VE.getTypeID(GO->getSourceElementType())); + for (unsigned i = 0, e = CE->getNumOperands(); i != e; ++i) { + Record.push_back(VE.getTypeID(C->getOperand(i)->getType())); + Record.push_back(VE.getValueID(C->getOperand(i))); + } + break; + } + case Instruction::Select: + Code = bitc::CST_CODE_CE_SELECT; + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getValueID(C->getOperand(1))); + Record.push_back(VE.getValueID(C->getOperand(2))); + break; + case Instruction::ExtractElement: + Code = bitc::CST_CODE_CE_EXTRACTELT; + Record.push_back(VE.getTypeID(C->getOperand(0)->getType())); + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getTypeID(C->getOperand(1)->getType())); + Record.push_back(VE.getValueID(C->getOperand(1))); + break; + case Instruction::InsertElement: + Code = bitc::CST_CODE_CE_INSERTELT; + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getValueID(C->getOperand(1))); + Record.push_back(VE.getTypeID(C->getOperand(2)->getType())); + Record.push_back(VE.getValueID(C->getOperand(2))); + break; + case Instruction::ShuffleVector: + // If the return type and argument types are the same, this is a + // standard shufflevector instruction. If the types are different, + // then the shuffle is widening or truncating the input vectors, and + // the argument type must also be encoded. + if (C->getType() == C->getOperand(0)->getType()) { + Code = bitc::CST_CODE_CE_SHUFFLEVEC; + } else { + Code = bitc::CST_CODE_CE_SHUFVEC_EX; + Record.push_back(VE.getTypeID(C->getOperand(0)->getType())); + } + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getValueID(C->getOperand(1))); + Record.push_back(VE.getValueID(C->getOperand(2))); + break; + case Instruction::ICmp: + case Instruction::FCmp: + Code = bitc::CST_CODE_CE_CMP; + Record.push_back(VE.getTypeID(C->getOperand(0)->getType())); + Record.push_back(VE.getValueID(C->getOperand(0))); + Record.push_back(VE.getValueID(C->getOperand(1))); + Record.push_back(CE->getPredicate()); + break; + } + } else if (const BlockAddress *BA = dyn_cast<BlockAddress>(C)) { + Code = bitc::CST_CODE_BLOCKADDRESS; + Record.push_back(VE.getTypeID(BA->getFunction()->getType())); + Record.push_back(VE.getValueID(BA->getFunction())); + Record.push_back(VE.getGlobalBasicBlockID(BA->getBasicBlock())); + } else { +#ifndef NDEBUG + C->dump(); +#endif + llvm_unreachable("Unknown constant!"); + } + Stream.EmitRecord(Code, Record, AbbrevToUse); + Record.clear(); + } + + Stream.ExitBlock(); +} + +static void WriteModuleConstants(const ValueEnumerator &VE, + BitstreamWriter &Stream) { + const ValueEnumerator::ValueList &Vals = VE.getValues(); + + // Find the first constant to emit, which is the first non-globalvalue value. + // We know globalvalues have been emitted by WriteModuleInfo. + for (unsigned i = 0, e = Vals.size(); i != e; ++i) { + if (!isa<GlobalValue>(Vals[i].first)) { + WriteConstants(i, Vals.size(), VE, Stream, true); + return; + } + } +} + +/// PushValueAndType - The file has to encode both the value and type id for +/// many values, because we need to know what type to create for forward +/// references. However, most operands are not forward references, so this type +/// field is not needed. +/// +/// This function adds V's value ID to Vals. If the value ID is higher than the +/// instruction ID, then it is a forward reference, and it also includes the +/// type ID. The value ID that is written is encoded relative to the InstID. +static bool PushValueAndType(const Value *V, unsigned InstID, + SmallVectorImpl<unsigned> &Vals, + ValueEnumerator &VE) { + unsigned ValID = VE.getValueID(V); + // Make encoding relative to the InstID. + Vals.push_back(InstID - ValID); + if (ValID >= InstID) { + Vals.push_back(VE.getTypeID(V->getType())); + return true; + } + return false; +} + +static void WriteOperandBundles(BitstreamWriter &Stream, ImmutableCallSite CS, + unsigned InstID, ValueEnumerator &VE) { + SmallVector<unsigned, 64> Record; + LLVMContext &C = CS.getInstruction()->getContext(); + + for (unsigned i = 0, e = CS.getNumOperandBundles(); i != e; ++i) { + const auto &Bundle = CS.getOperandBundleAt(i); + Record.push_back(C.getOperandBundleTagID(Bundle.getTagName())); + + for (auto &Input : Bundle.Inputs) + PushValueAndType(Input, InstID, Record, VE); + + Stream.EmitRecord(bitc::FUNC_CODE_OPERAND_BUNDLE, Record); + Record.clear(); + } +} + +/// pushValue - Like PushValueAndType, but where the type of the value is +/// omitted (perhaps it was already encoded in an earlier operand). +static void pushValue(const Value *V, unsigned InstID, + SmallVectorImpl<unsigned> &Vals, + ValueEnumerator &VE) { + unsigned ValID = VE.getValueID(V); + Vals.push_back(InstID - ValID); +} + +static void pushValueSigned(const Value *V, unsigned InstID, + SmallVectorImpl<uint64_t> &Vals, + ValueEnumerator &VE) { + unsigned ValID = VE.getValueID(V); + int64_t diff = ((int32_t)InstID - (int32_t)ValID); + emitSignedInt64(Vals, diff); +} + +/// WriteInstruction - Emit an instruction to the specified stream. +static void WriteInstruction(const Instruction &I, unsigned InstID, + ValueEnumerator &VE, BitstreamWriter &Stream, + SmallVectorImpl<unsigned> &Vals) { + unsigned Code = 0; + unsigned AbbrevToUse = 0; + VE.setInstructionID(&I); + switch (I.getOpcode()) { + default: + if (Instruction::isCast(I.getOpcode())) { + Code = bitc::FUNC_CODE_INST_CAST; + if (!PushValueAndType(I.getOperand(0), InstID, Vals, VE)) + AbbrevToUse = FUNCTION_INST_CAST_ABBREV; + Vals.push_back(VE.getTypeID(I.getType())); + Vals.push_back(GetEncodedCastOpcode(I.getOpcode())); + } else { + assert(isa<BinaryOperator>(I) && "Unknown instruction!"); + Code = bitc::FUNC_CODE_INST_BINOP; + if (!PushValueAndType(I.getOperand(0), InstID, Vals, VE)) + AbbrevToUse = FUNCTION_INST_BINOP_ABBREV; + pushValue(I.getOperand(1), InstID, Vals, VE); + Vals.push_back(GetEncodedBinaryOpcode(I.getOpcode())); + uint64_t Flags = GetOptimizationFlags(&I); + if (Flags != 0) { + if (AbbrevToUse == FUNCTION_INST_BINOP_ABBREV) + AbbrevToUse = FUNCTION_INST_BINOP_FLAGS_ABBREV; + Vals.push_back(Flags); + } + } + break; + + case Instruction::GetElementPtr: { + Code = bitc::FUNC_CODE_INST_GEP; + AbbrevToUse = FUNCTION_INST_GEP_ABBREV; + auto &GEPInst = cast<GetElementPtrInst>(I); + Vals.push_back(GEPInst.isInBounds()); + Vals.push_back(VE.getTypeID(GEPInst.getSourceElementType())); + for (unsigned i = 0, e = I.getNumOperands(); i != e; ++i) + PushValueAndType(I.getOperand(i), InstID, Vals, VE); + break; + } + case Instruction::ExtractValue: { + Code = bitc::FUNC_CODE_INST_EXTRACTVAL; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + const ExtractValueInst *EVI = cast<ExtractValueInst>(&I); + Vals.append(EVI->idx_begin(), EVI->idx_end()); + break; + } + case Instruction::InsertValue: { + Code = bitc::FUNC_CODE_INST_INSERTVAL; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + PushValueAndType(I.getOperand(1), InstID, Vals, VE); + const InsertValueInst *IVI = cast<InsertValueInst>(&I); + Vals.append(IVI->idx_begin(), IVI->idx_end()); + break; + } + case Instruction::Select: + Code = bitc::FUNC_CODE_INST_VSELECT; + PushValueAndType(I.getOperand(1), InstID, Vals, VE); + pushValue(I.getOperand(2), InstID, Vals, VE); + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + break; + case Instruction::ExtractElement: + Code = bitc::FUNC_CODE_INST_EXTRACTELT; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + PushValueAndType(I.getOperand(1), InstID, Vals, VE); + break; + case Instruction::InsertElement: + Code = bitc::FUNC_CODE_INST_INSERTELT; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + pushValue(I.getOperand(1), InstID, Vals, VE); + PushValueAndType(I.getOperand(2), InstID, Vals, VE); + break; + case Instruction::ShuffleVector: + Code = bitc::FUNC_CODE_INST_SHUFFLEVEC; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + pushValue(I.getOperand(1), InstID, Vals, VE); + pushValue(I.getOperand(2), InstID, Vals, VE); + break; + case Instruction::ICmp: + case Instruction::FCmp: { + // compare returning Int1Ty or vector of Int1Ty + Code = bitc::FUNC_CODE_INST_CMP2; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + pushValue(I.getOperand(1), InstID, Vals, VE); + Vals.push_back(cast<CmpInst>(I).getPredicate()); + uint64_t Flags = GetOptimizationFlags(&I); + if (Flags != 0) + Vals.push_back(Flags); + break; + } + + case Instruction::Ret: + { + Code = bitc::FUNC_CODE_INST_RET; + unsigned NumOperands = I.getNumOperands(); + if (NumOperands == 0) + AbbrevToUse = FUNCTION_INST_RET_VOID_ABBREV; + else if (NumOperands == 1) { + if (!PushValueAndType(I.getOperand(0), InstID, Vals, VE)) + AbbrevToUse = FUNCTION_INST_RET_VAL_ABBREV; + } else { + for (unsigned i = 0, e = NumOperands; i != e; ++i) + PushValueAndType(I.getOperand(i), InstID, Vals, VE); + } + } + break; + case Instruction::Br: + { + Code = bitc::FUNC_CODE_INST_BR; + const BranchInst &II = cast<BranchInst>(I); + Vals.push_back(VE.getValueID(II.getSuccessor(0))); + if (II.isConditional()) { + Vals.push_back(VE.getValueID(II.getSuccessor(1))); + pushValue(II.getCondition(), InstID, Vals, VE); + } + } + break; + case Instruction::Switch: + { + Code = bitc::FUNC_CODE_INST_SWITCH; + const SwitchInst &SI = cast<SwitchInst>(I); + Vals.push_back(VE.getTypeID(SI.getCondition()->getType())); + pushValue(SI.getCondition(), InstID, Vals, VE); + Vals.push_back(VE.getValueID(SI.getDefaultDest())); + for (SwitchInst::ConstCaseIt Case : SI.cases()) { + Vals.push_back(VE.getValueID(Case.getCaseValue())); + Vals.push_back(VE.getValueID(Case.getCaseSuccessor())); + } + } + break; + case Instruction::IndirectBr: + Code = bitc::FUNC_CODE_INST_INDIRECTBR; + Vals.push_back(VE.getTypeID(I.getOperand(0)->getType())); + // Encode the address operand as relative, but not the basic blocks. + pushValue(I.getOperand(0), InstID, Vals, VE); + for (unsigned i = 1, e = I.getNumOperands(); i != e; ++i) + Vals.push_back(VE.getValueID(I.getOperand(i))); + break; + + case Instruction::Invoke: { + const InvokeInst *II = cast<InvokeInst>(&I); + const Value *Callee = II->getCalledValue(); + FunctionType *FTy = II->getFunctionType(); + + if (II->hasOperandBundles()) + WriteOperandBundles(Stream, II, InstID, VE); + + Code = bitc::FUNC_CODE_INST_INVOKE; + + Vals.push_back(VE.getAttributeID(II->getAttributes())); + Vals.push_back(II->getCallingConv() | 1 << 13); + Vals.push_back(VE.getValueID(II->getNormalDest())); + Vals.push_back(VE.getValueID(II->getUnwindDest())); + Vals.push_back(VE.getTypeID(FTy)); + PushValueAndType(Callee, InstID, Vals, VE); + + // Emit value #'s for the fixed parameters. + for (unsigned i = 0, e = FTy->getNumParams(); i != e; ++i) + pushValue(I.getOperand(i), InstID, Vals, VE); // fixed param. + + // Emit type/value pairs for varargs params. + if (FTy->isVarArg()) { + for (unsigned i = FTy->getNumParams(), e = I.getNumOperands()-3; + i != e; ++i) + PushValueAndType(I.getOperand(i), InstID, Vals, VE); // vararg + } + break; + } + case Instruction::Resume: + Code = bitc::FUNC_CODE_INST_RESUME; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + break; + case Instruction::CleanupRet: { + Code = bitc::FUNC_CODE_INST_CLEANUPRET; + const auto &CRI = cast<CleanupReturnInst>(I); + pushValue(CRI.getCleanupPad(), InstID, Vals, VE); + if (CRI.hasUnwindDest()) + Vals.push_back(VE.getValueID(CRI.getUnwindDest())); + break; + } + case Instruction::CatchRet: { + Code = bitc::FUNC_CODE_INST_CATCHRET; + const auto &CRI = cast<CatchReturnInst>(I); + pushValue(CRI.getCatchPad(), InstID, Vals, VE); + Vals.push_back(VE.getValueID(CRI.getSuccessor())); + break; + } + case Instruction::CleanupPad: + case Instruction::CatchPad: { + const auto &FuncletPad = cast<FuncletPadInst>(I); + Code = isa<CatchPadInst>(FuncletPad) ? bitc::FUNC_CODE_INST_CATCHPAD + : bitc::FUNC_CODE_INST_CLEANUPPAD; + pushValue(FuncletPad.getParentPad(), InstID, Vals, VE); + + unsigned NumArgOperands = FuncletPad.getNumArgOperands(); + Vals.push_back(NumArgOperands); + for (unsigned Op = 0; Op != NumArgOperands; ++Op) + PushValueAndType(FuncletPad.getArgOperand(Op), InstID, Vals, VE); + break; + } + case Instruction::CatchSwitch: { + Code = bitc::FUNC_CODE_INST_CATCHSWITCH; + const auto &CatchSwitch = cast<CatchSwitchInst>(I); + + pushValue(CatchSwitch.getParentPad(), InstID, Vals, VE); + + unsigned NumHandlers = CatchSwitch.getNumHandlers(); + Vals.push_back(NumHandlers); + for (const BasicBlock *CatchPadBB : CatchSwitch.handlers()) + Vals.push_back(VE.getValueID(CatchPadBB)); + + if (CatchSwitch.hasUnwindDest()) + Vals.push_back(VE.getValueID(CatchSwitch.getUnwindDest())); + break; + } + case Instruction::Unreachable: + Code = bitc::FUNC_CODE_INST_UNREACHABLE; + AbbrevToUse = FUNCTION_INST_UNREACHABLE_ABBREV; + break; + + case Instruction::PHI: { + const PHINode &PN = cast<PHINode>(I); + Code = bitc::FUNC_CODE_INST_PHI; + // With the newer instruction encoding, forward references could give + // negative valued IDs. This is most common for PHIs, so we use + // signed VBRs. + SmallVector<uint64_t, 128> Vals64; + Vals64.push_back(VE.getTypeID(PN.getType())); + for (unsigned i = 0, e = PN.getNumIncomingValues(); i != e; ++i) { + pushValueSigned(PN.getIncomingValue(i), InstID, Vals64, VE); + Vals64.push_back(VE.getValueID(PN.getIncomingBlock(i))); + } + // Emit a Vals64 vector and exit. + Stream.EmitRecord(Code, Vals64, AbbrevToUse); + Vals64.clear(); + return; + } + + case Instruction::LandingPad: { + const LandingPadInst &LP = cast<LandingPadInst>(I); + Code = bitc::FUNC_CODE_INST_LANDINGPAD; + Vals.push_back(VE.getTypeID(LP.getType())); + Vals.push_back(LP.isCleanup()); + Vals.push_back(LP.getNumClauses()); + for (unsigned I = 0, E = LP.getNumClauses(); I != E; ++I) { + if (LP.isCatch(I)) + Vals.push_back(LandingPadInst::Catch); + else + Vals.push_back(LandingPadInst::Filter); + PushValueAndType(LP.getClause(I), InstID, Vals, VE); + } + break; + } + + case Instruction::Alloca: { + Code = bitc::FUNC_CODE_INST_ALLOCA; + const AllocaInst &AI = cast<AllocaInst>(I); + Vals.push_back(VE.getTypeID(AI.getAllocatedType())); + Vals.push_back(VE.getTypeID(I.getOperand(0)->getType())); + Vals.push_back(VE.getValueID(I.getOperand(0))); // size. + unsigned AlignRecord = Log2_32(AI.getAlignment()) + 1; + assert(Log2_32(Value::MaximumAlignment) + 1 < 1 << 5 && + "not enough bits for maximum alignment"); + assert(AlignRecord < 1 << 5 && "alignment greater than 1 << 64"); + AlignRecord |= AI.isUsedWithInAlloca() << 5; + AlignRecord |= 1 << 6; + // Reserve bit 7 for SwiftError flag. + // AlignRecord |= AI.isSwiftError() << 7; + Vals.push_back(AlignRecord); + break; + } + + case Instruction::Load: + if (cast<LoadInst>(I).isAtomic()) { + Code = bitc::FUNC_CODE_INST_LOADATOMIC; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); + } else { + Code = bitc::FUNC_CODE_INST_LOAD; + if (!PushValueAndType(I.getOperand(0), InstID, Vals, VE)) // ptr + AbbrevToUse = FUNCTION_INST_LOAD_ABBREV; + } + Vals.push_back(VE.getTypeID(I.getType())); + Vals.push_back(Log2_32(cast<LoadInst>(I).getAlignment())+1); + Vals.push_back(cast<LoadInst>(I).isVolatile()); + if (cast<LoadInst>(I).isAtomic()) { + Vals.push_back(GetEncodedOrdering(cast<LoadInst>(I).getOrdering())); + Vals.push_back(GetEncodedSynchScope(cast<LoadInst>(I).getSynchScope())); + } + break; + case Instruction::Store: + if (cast<StoreInst>(I).isAtomic()) + Code = bitc::FUNC_CODE_INST_STOREATOMIC; + else + Code = bitc::FUNC_CODE_INST_STORE; + PushValueAndType(I.getOperand(1), InstID, Vals, VE); // ptrty + ptr + PushValueAndType(I.getOperand(0), InstID, Vals, VE); // valty + val + Vals.push_back(Log2_32(cast<StoreInst>(I).getAlignment())+1); + Vals.push_back(cast<StoreInst>(I).isVolatile()); + if (cast<StoreInst>(I).isAtomic()) { + Vals.push_back(GetEncodedOrdering(cast<StoreInst>(I).getOrdering())); + Vals.push_back(GetEncodedSynchScope(cast<StoreInst>(I).getSynchScope())); + } + break; + case Instruction::AtomicCmpXchg: + Code = bitc::FUNC_CODE_INST_CMPXCHG; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); // ptrty + ptr + PushValueAndType(I.getOperand(1), InstID, Vals, VE); // cmp. + pushValue(I.getOperand(2), InstID, Vals, VE); // newval. + Vals.push_back(cast<AtomicCmpXchgInst>(I).isVolatile()); + Vals.push_back(GetEncodedOrdering( + cast<AtomicCmpXchgInst>(I).getSuccessOrdering())); + Vals.push_back(GetEncodedSynchScope( + cast<AtomicCmpXchgInst>(I).getSynchScope())); + Vals.push_back(GetEncodedOrdering( + cast<AtomicCmpXchgInst>(I).getFailureOrdering())); + Vals.push_back(cast<AtomicCmpXchgInst>(I).isWeak()); + break; + case Instruction::AtomicRMW: + Code = bitc::FUNC_CODE_INST_ATOMICRMW; + PushValueAndType(I.getOperand(0), InstID, Vals, VE); // ptrty + ptr + pushValue(I.getOperand(1), InstID, Vals, VE); // val. + Vals.push_back(GetEncodedRMWOperation( + cast<AtomicRMWInst>(I).getOperation())); + Vals.push_back(cast<AtomicRMWInst>(I).isVolatile()); + Vals.push_back(GetEncodedOrdering(cast<AtomicRMWInst>(I).getOrdering())); + Vals.push_back(GetEncodedSynchScope( + cast<AtomicRMWInst>(I).getSynchScope())); + break; + case Instruction::Fence: + Code = bitc::FUNC_CODE_INST_FENCE; + Vals.push_back(GetEncodedOrdering(cast<FenceInst>(I).getOrdering())); + Vals.push_back(GetEncodedSynchScope(cast<FenceInst>(I).getSynchScope())); + break; + case Instruction::Call: { + const CallInst &CI = cast<CallInst>(I); + FunctionType *FTy = CI.getFunctionType(); + + if (CI.hasOperandBundles()) + WriteOperandBundles(Stream, &CI, InstID, VE); + + Code = bitc::FUNC_CODE_INST_CALL; + + Vals.push_back(VE.getAttributeID(CI.getAttributes())); + + unsigned Flags = GetOptimizationFlags(&I); + Vals.push_back(CI.getCallingConv() << bitc::CALL_CCONV | + unsigned(CI.isTailCall()) << bitc::CALL_TAIL | + unsigned(CI.isMustTailCall()) << bitc::CALL_MUSTTAIL | + 1 << bitc::CALL_EXPLICIT_TYPE | + unsigned(CI.isNoTailCall()) << bitc::CALL_NOTAIL | + unsigned(Flags != 0) << bitc::CALL_FMF); + if (Flags != 0) + Vals.push_back(Flags); + + Vals.push_back(VE.getTypeID(FTy)); + PushValueAndType(CI.getCalledValue(), InstID, Vals, VE); // Callee + + // Emit value #'s for the fixed parameters. + for (unsigned i = 0, e = FTy->getNumParams(); i != e; ++i) { + // Check for labels (can happen with asm labels). + if (FTy->getParamType(i)->isLabelTy()) + Vals.push_back(VE.getValueID(CI.getArgOperand(i))); + else + pushValue(CI.getArgOperand(i), InstID, Vals, VE); // fixed param. + } + + // Emit type/value pairs for varargs params. + if (FTy->isVarArg()) { + for (unsigned i = FTy->getNumParams(), e = CI.getNumArgOperands(); + i != e; ++i) + PushValueAndType(CI.getArgOperand(i), InstID, Vals, VE); // varargs + } + break; + } + case Instruction::VAArg: + Code = bitc::FUNC_CODE_INST_VAARG; + Vals.push_back(VE.getTypeID(I.getOperand(0)->getType())); // valistty + pushValue(I.getOperand(0), InstID, Vals, VE); // valist. + Vals.push_back(VE.getTypeID(I.getType())); // restype. + break; + } + + Stream.EmitRecord(Code, Vals, AbbrevToUse); + Vals.clear(); +} + +enum StringEncoding { SE_Char6, SE_Fixed7, SE_Fixed8 }; + +/// Determine the encoding to use for the given string name and length. +static StringEncoding getStringEncoding(const char *Str, unsigned StrLen) { + bool isChar6 = true; + for (const char *C = Str, *E = C + StrLen; C != E; ++C) { + if (isChar6) + isChar6 = BitCodeAbbrevOp::isChar6(*C); + if ((unsigned char)*C & 128) + // don't bother scanning the rest. + return SE_Fixed8; + } + if (isChar6) + return SE_Char6; + else + return SE_Fixed7; +} + +/// Emit names for globals/functions etc. The VSTOffsetPlaceholder, +/// BitcodeStartBit and FunctionIndex are only passed for the module-level +/// VST, where we are including a function bitcode index and need to +/// backpatch the VST forward declaration record. +static void WriteValueSymbolTable( + const ValueSymbolTable &VST, const ValueEnumerator &VE, + BitstreamWriter &Stream, uint64_t VSTOffsetPlaceholder = 0, + uint64_t BitcodeStartBit = 0, + DenseMap<const Function *, std::unique_ptr<FunctionInfo>> *FunctionIndex = + nullptr) { + if (VST.empty()) { + // WriteValueSymbolTableForwardDecl should have returned early as + // well. Ensure this handling remains in sync by asserting that + // the placeholder offset is not set. + assert(VSTOffsetPlaceholder == 0); + return; + } + + if (VSTOffsetPlaceholder > 0) { + // Get the offset of the VST we are writing, and backpatch it into + // the VST forward declaration record. + uint64_t VSTOffset = Stream.GetCurrentBitNo(); + // The BitcodeStartBit was the stream offset of the actual bitcode + // (e.g. excluding any initial darwin header). + VSTOffset -= BitcodeStartBit; + assert((VSTOffset & 31) == 0 && "VST block not 32-bit aligned"); + Stream.BackpatchWord(VSTOffsetPlaceholder, VSTOffset / 32); + } + + Stream.EnterSubblock(bitc::VALUE_SYMTAB_BLOCK_ID, 4); + + // For the module-level VST, add abbrev Ids for the VST_CODE_FNENTRY + // records, which are not used in the per-function VSTs. + unsigned FnEntry8BitAbbrev; + unsigned FnEntry7BitAbbrev; + unsigned FnEntry6BitAbbrev; + if (VSTOffsetPlaceholder > 0) { + // 8-bit fixed-width VST_FNENTRY function strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // value id + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + FnEntry8BitAbbrev = Stream.EmitAbbrev(Abbv); + + // 7-bit fixed width VST_FNENTRY function strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // value id + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); + FnEntry7BitAbbrev = Stream.EmitAbbrev(Abbv); + + // 6-bit char6 VST_FNENTRY function strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // value id + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + FnEntry6BitAbbrev = Stream.EmitAbbrev(Abbv); + } + + // FIXME: Set up the abbrev, we know how many values there are! + // FIXME: We know if the type names can use 7-bit ascii. + SmallVector<unsigned, 64> NameVals; + + for (const ValueName &Name : VST) { + // Figure out the encoding to use for the name. + StringEncoding Bits = + getStringEncoding(Name.getKeyData(), Name.getKeyLength()); + + unsigned AbbrevToUse = VST_ENTRY_8_ABBREV; + NameVals.push_back(VE.getValueID(Name.getValue())); + + Function *F = dyn_cast<Function>(Name.getValue()); + if (!F) { + // If value is an alias, need to get the aliased base object to + // see if it is a function. + auto *GA = dyn_cast<GlobalAlias>(Name.getValue()); + if (GA && GA->getBaseObject()) + F = dyn_cast<Function>(GA->getBaseObject()); + } + + // VST_ENTRY: [valueid, namechar x N] + // VST_FNENTRY: [valueid, funcoffset, namechar x N] + // VST_BBENTRY: [bbid, namechar x N] + unsigned Code; + if (isa<BasicBlock>(Name.getValue())) { + Code = bitc::VST_CODE_BBENTRY; + if (Bits == SE_Char6) + AbbrevToUse = VST_BBENTRY_6_ABBREV; + } else if (F && !F->isDeclaration()) { + // Must be the module-level VST, where we pass in the Index and + // have a VSTOffsetPlaceholder. The function-level VST should not + // contain any Function symbols. + assert(FunctionIndex); + assert(VSTOffsetPlaceholder > 0); + + // Save the word offset of the function (from the start of the + // actual bitcode written to the stream). + assert(FunctionIndex->count(F) == 1); + uint64_t BitcodeIndex = + (*FunctionIndex)[F]->bitcodeIndex() - BitcodeStartBit; + assert((BitcodeIndex & 31) == 0 && "function block not 32-bit aligned"); + NameVals.push_back(BitcodeIndex / 32); + + Code = bitc::VST_CODE_FNENTRY; + AbbrevToUse = FnEntry8BitAbbrev; + if (Bits == SE_Char6) + AbbrevToUse = FnEntry6BitAbbrev; + else if (Bits == SE_Fixed7) + AbbrevToUse = FnEntry7BitAbbrev; + } else { + Code = bitc::VST_CODE_ENTRY; + if (Bits == SE_Char6) + AbbrevToUse = VST_ENTRY_6_ABBREV; + else if (Bits == SE_Fixed7) + AbbrevToUse = VST_ENTRY_7_ABBREV; + } + + for (const auto P : Name.getKey()) + NameVals.push_back((unsigned char)P); + + // Emit the finished record. + Stream.EmitRecord(Code, NameVals, AbbrevToUse); + NameVals.clear(); + } + Stream.ExitBlock(); +} + +/// Emit function names and summary offsets for the combined index +/// used by ThinLTO. +static void WriteCombinedValueSymbolTable(const FunctionInfoIndex &Index, + BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::VALUE_SYMTAB_BLOCK_ID, 4); + + // 8-bit fixed-width VST_COMBINED_FNENTRY function strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_COMBINED_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + unsigned FnEntry8BitAbbrev = Stream.EmitAbbrev(Abbv); + + // 7-bit fixed width VST_COMBINED_FNENTRY function strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_COMBINED_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); + unsigned FnEntry7BitAbbrev = Stream.EmitAbbrev(Abbv); + + // 6-bit char6 VST_COMBINED_FNENTRY function strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_COMBINED_FNENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // funcoffset + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + unsigned FnEntry6BitAbbrev = Stream.EmitAbbrev(Abbv); + + // FIXME: We know if the type names can use 7-bit ascii. + SmallVector<unsigned, 64> NameVals; + + for (const auto &FII : Index) { + for (const auto &FI : FII.getValue()) { + NameVals.push_back(FI->bitcodeIndex()); + + StringRef FuncName = FII.first(); + + // Figure out the encoding to use for the name. + StringEncoding Bits = getStringEncoding(FuncName.data(), FuncName.size()); + + // VST_COMBINED_FNENTRY: [funcsumoffset, namechar x N] + unsigned AbbrevToUse = FnEntry8BitAbbrev; + if (Bits == SE_Char6) + AbbrevToUse = FnEntry6BitAbbrev; + else if (Bits == SE_Fixed7) + AbbrevToUse = FnEntry7BitAbbrev; + + for (const auto P : FuncName) + NameVals.push_back((unsigned char)P); + + // Emit the finished record. + Stream.EmitRecord(bitc::VST_CODE_COMBINED_FNENTRY, NameVals, AbbrevToUse); + NameVals.clear(); + } + } + Stream.ExitBlock(); +} + +static void WriteUseList(ValueEnumerator &VE, UseListOrder &&Order, + BitstreamWriter &Stream) { + assert(Order.Shuffle.size() >= 2 && "Shuffle too small"); + unsigned Code; + if (isa<BasicBlock>(Order.V)) + Code = bitc::USELIST_CODE_BB; + else + Code = bitc::USELIST_CODE_DEFAULT; + + SmallVector<uint64_t, 64> Record(Order.Shuffle.begin(), Order.Shuffle.end()); + Record.push_back(VE.getValueID(Order.V)); + Stream.EmitRecord(Code, Record); +} + +static void WriteUseListBlock(const Function *F, ValueEnumerator &VE, + BitstreamWriter &Stream) { + assert(VE.shouldPreserveUseListOrder() && + "Expected to be preserving use-list order"); + + auto hasMore = [&]() { + return !VE.UseListOrders.empty() && VE.UseListOrders.back().F == F; + }; + if (!hasMore()) + // Nothing to do. + return; + + Stream.EnterSubblock(bitc::USELIST_BLOCK_ID, 3); + while (hasMore()) { + WriteUseList(VE, std::move(VE.UseListOrders.back()), Stream); + VE.UseListOrders.pop_back(); + } + Stream.ExitBlock(); +} + +/// \brief Save information for the given function into the function index. +/// +/// At a minimum this saves the bitcode index of the function record that +/// was just written. However, if we are emitting function summary information, +/// for example for ThinLTO, then a \a FunctionSummary object is created +/// to hold the provided summary information. +static void SaveFunctionInfo( + const Function &F, + DenseMap<const Function *, std::unique_ptr<FunctionInfo>> &FunctionIndex, + unsigned NumInsts, uint64_t BitcodeIndex, bool EmitFunctionSummary) { + std::unique_ptr<FunctionSummary> FuncSummary; + if (EmitFunctionSummary) { + FuncSummary = llvm::make_unique<FunctionSummary>(NumInsts); + FuncSummary->setLocalFunction(F.hasLocalLinkage()); + } + FunctionIndex[&F] = + llvm::make_unique<FunctionInfo>(BitcodeIndex, std::move(FuncSummary)); +} + +/// Emit a function body to the module stream. +static void WriteFunction( + const Function &F, ValueEnumerator &VE, BitstreamWriter &Stream, + DenseMap<const Function *, std::unique_ptr<FunctionInfo>> &FunctionIndex, + bool EmitFunctionSummary) { + // Save the bitcode index of the start of this function block for recording + // in the VST. + uint64_t BitcodeIndex = Stream.GetCurrentBitNo(); + + Stream.EnterSubblock(bitc::FUNCTION_BLOCK_ID, 4); + VE.incorporateFunction(F); + + SmallVector<unsigned, 64> Vals; + + // Emit the number of basic blocks, so the reader can create them ahead of + // time. + Vals.push_back(VE.getBasicBlocks().size()); + Stream.EmitRecord(bitc::FUNC_CODE_DECLAREBLOCKS, Vals); + Vals.clear(); + + // If there are function-local constants, emit them now. + unsigned CstStart, CstEnd; + VE.getFunctionConstantRange(CstStart, CstEnd); + WriteConstants(CstStart, CstEnd, VE, Stream, false); + + // If there is function-local metadata, emit it now. + WriteFunctionLocalMetadata(F, VE, Stream); + + // Keep a running idea of what the instruction ID is. + unsigned InstID = CstEnd; + + bool NeedsMetadataAttachment = F.hasMetadata(); + + DILocation *LastDL = nullptr; + unsigned NumInsts = 0; + + // Finally, emit all the instructions, in order. + for (Function::const_iterator BB = F.begin(), E = F.end(); BB != E; ++BB) + for (BasicBlock::const_iterator I = BB->begin(), E = BB->end(); + I != E; ++I) { + WriteInstruction(*I, InstID, VE, Stream, Vals); + + if (!isa<DbgInfoIntrinsic>(I)) + ++NumInsts; + + if (!I->getType()->isVoidTy()) + ++InstID; + + // If the instruction has metadata, write a metadata attachment later. + NeedsMetadataAttachment |= I->hasMetadataOtherThanDebugLoc(); + + // If the instruction has a debug location, emit it. + DILocation *DL = I->getDebugLoc(); + if (!DL) + continue; + + if (DL == LastDL) { + // Just repeat the same debug loc as last time. + Stream.EmitRecord(bitc::FUNC_CODE_DEBUG_LOC_AGAIN, Vals); + continue; + } + + Vals.push_back(DL->getLine()); + Vals.push_back(DL->getColumn()); + Vals.push_back(VE.getMetadataOrNullID(DL->getScope())); + Vals.push_back(VE.getMetadataOrNullID(DL->getInlinedAt())); + Stream.EmitRecord(bitc::FUNC_CODE_DEBUG_LOC, Vals); + Vals.clear(); + + LastDL = DL; + } + + // Emit names for all the instructions etc. + WriteValueSymbolTable(F.getValueSymbolTable(), VE, Stream); + + if (NeedsMetadataAttachment) + WriteMetadataAttachment(F, VE, Stream); + if (VE.shouldPreserveUseListOrder()) + WriteUseListBlock(&F, VE, Stream); + VE.purgeFunction(); + Stream.ExitBlock(); + + SaveFunctionInfo(F, FunctionIndex, NumInsts, BitcodeIndex, + EmitFunctionSummary); +} + +// Emit blockinfo, which defines the standard abbreviations etc. +static void WriteBlockInfo(const ValueEnumerator &VE, BitstreamWriter &Stream) { + // We only want to emit block info records for blocks that have multiple + // instances: CONSTANTS_BLOCK, FUNCTION_BLOCK and VALUE_SYMTAB_BLOCK. + // Other blocks can define their abbrevs inline. + Stream.EnterBlockInfoBlock(2); + + { // 8-bit fixed-width VST_ENTRY/VST_BBENTRY strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + if (Stream.EmitBlockInfoAbbrev(bitc::VALUE_SYMTAB_BLOCK_ID, + Abbv) != VST_ENTRY_8_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + { // 7-bit fixed width VST_ENTRY strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); + if (Stream.EmitBlockInfoAbbrev(bitc::VALUE_SYMTAB_BLOCK_ID, + Abbv) != VST_ENTRY_7_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // 6-bit char6 VST_ENTRY strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + if (Stream.EmitBlockInfoAbbrev(bitc::VALUE_SYMTAB_BLOCK_ID, + Abbv) != VST_ENTRY_6_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // 6-bit char6 VST_BBENTRY strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::VST_CODE_BBENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + if (Stream.EmitBlockInfoAbbrev(bitc::VALUE_SYMTAB_BLOCK_ID, + Abbv) != VST_BBENTRY_6_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + + + { // SETTYPE abbrev for CONSTANTS_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_SETTYPE)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, + VE.computeBitsRequiredForTypeIndicies())); + if (Stream.EmitBlockInfoAbbrev(bitc::CONSTANTS_BLOCK_ID, + Abbv) != CONSTANTS_SETTYPE_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + { // INTEGER abbrev for CONSTANTS_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_INTEGER)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + if (Stream.EmitBlockInfoAbbrev(bitc::CONSTANTS_BLOCK_ID, + Abbv) != CONSTANTS_INTEGER_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + { // CE_CAST abbrev for CONSTANTS_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_CE_CAST)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 4)); // cast opc + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, // typeid + VE.computeBitsRequiredForTypeIndicies())); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // value id + + if (Stream.EmitBlockInfoAbbrev(bitc::CONSTANTS_BLOCK_ID, + Abbv) != CONSTANTS_CE_CAST_Abbrev) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // NULL abbrev for CONSTANTS_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::CST_CODE_NULL)); + if (Stream.EmitBlockInfoAbbrev(bitc::CONSTANTS_BLOCK_ID, + Abbv) != CONSTANTS_NULL_Abbrev) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + // FIXME: This should only use space for first class types! + + { // INST_LOAD abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_LOAD)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Ptr + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, // dest ty + VE.computeBitsRequiredForTypeIndicies())); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 4)); // Align + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // volatile + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_LOAD_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // INST_BINOP abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_BINOP)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // LHS + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // RHS + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 4)); // opc + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_BINOP_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // INST_BINOP_FLAGS abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_BINOP)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // LHS + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // RHS + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 4)); // opc + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); // flags + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_BINOP_FLAGS_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // INST_CAST abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_CAST)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // OpVal + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, // dest ty + VE.computeBitsRequiredForTypeIndicies())); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 4)); // opc + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_CAST_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + { // INST_RET abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_RET)); + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_RET_VOID_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // INST_RET abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_RET)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // ValID + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_RET_VAL_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { // INST_UNREACHABLE abbrev for FUNCTION_BLOCK. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_UNREACHABLE)); + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, + Abbv) != FUNCTION_INST_UNREACHABLE_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + { + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FUNC_CODE_INST_GEP)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, // dest ty + Log2_32_Ceil(VE.getTypes().size() + 1))); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + if (Stream.EmitBlockInfoAbbrev(bitc::FUNCTION_BLOCK_ID, Abbv) != + FUNCTION_INST_GEP_ABBREV) + llvm_unreachable("Unexpected abbrev ordering!"); + } + + Stream.ExitBlock(); +} + +/// Write the module path strings, currently only used when generating +/// a combined index file. +static void WriteModStrings(const FunctionInfoIndex &I, + BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::MODULE_STRTAB_BLOCK_ID, 3); + + // TODO: See which abbrev sizes we actually need to emit + + // 8-bit fixed-width MST_ENTRY strings. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MST_CODE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 8)); + unsigned Abbrev8Bit = Stream.EmitAbbrev(Abbv); + + // 7-bit fixed width MST_ENTRY strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MST_CODE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 7)); + unsigned Abbrev7Bit = Stream.EmitAbbrev(Abbv); + + // 6-bit char6 MST_ENTRY strings. + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::MST_CODE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + unsigned Abbrev6Bit = Stream.EmitAbbrev(Abbv); + + SmallVector<unsigned, 64> NameVals; + for (const StringMapEntry<uint64_t> &MPSE : I.modPathStringEntries()) { + StringEncoding Bits = + getStringEncoding(MPSE.getKey().data(), MPSE.getKey().size()); + unsigned AbbrevToUse = Abbrev8Bit; + if (Bits == SE_Char6) + AbbrevToUse = Abbrev6Bit; + else if (Bits == SE_Fixed7) + AbbrevToUse = Abbrev7Bit; + + NameVals.push_back(MPSE.getValue()); + + for (const auto P : MPSE.getKey()) + NameVals.push_back((unsigned char)P); + + // Emit the finished record. + Stream.EmitRecord(bitc::MST_CODE_ENTRY, NameVals, AbbrevToUse); + NameVals.clear(); + } + Stream.ExitBlock(); +} + +// Helper to emit a single function summary record. +static void WritePerModuleFunctionSummaryRecord( + SmallVector<unsigned, 64> &NameVals, FunctionSummary *FS, unsigned ValueID, + unsigned FSAbbrev, BitstreamWriter &Stream) { + assert(FS); + NameVals.push_back(ValueID); + NameVals.push_back(FS->isLocalFunction()); + NameVals.push_back(FS->instCount()); + + // Emit the finished record. + Stream.EmitRecord(bitc::FS_CODE_PERMODULE_ENTRY, NameVals, FSAbbrev); + NameVals.clear(); +} + +/// Emit the per-module function summary section alongside the rest of +/// the module's bitcode. +static void WritePerModuleFunctionSummary( + DenseMap<const Function *, std::unique_ptr<FunctionInfo>> &FunctionIndex, + const Module *M, const ValueEnumerator &VE, BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::FUNCTION_SUMMARY_BLOCK_ID, 3); + + // Abbrev for FS_CODE_PERMODULE_ENTRY. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FS_CODE_PERMODULE_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // valueid + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // islocal + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount + unsigned FSAbbrev = Stream.EmitAbbrev(Abbv); + + SmallVector<unsigned, 64> NameVals; + for (auto &I : FunctionIndex) { + // Skip anonymous functions. We will emit a function summary for + // any aliases below. + if (!I.first->hasName()) + continue; + + WritePerModuleFunctionSummaryRecord( + NameVals, I.second->functionSummary(), + VE.getValueID(M->getValueSymbolTable().lookup(I.first->getName())), + FSAbbrev, Stream); + } + + for (const GlobalAlias &A : M->aliases()) { + if (!A.getBaseObject()) + continue; + const Function *F = dyn_cast<Function>(A.getBaseObject()); + if (!F || F->isDeclaration()) + continue; + + assert(FunctionIndex.count(F) == 1); + WritePerModuleFunctionSummaryRecord( + NameVals, FunctionIndex[F]->functionSummary(), + VE.getValueID(M->getValueSymbolTable().lookup(A.getName())), FSAbbrev, + Stream); + } + + Stream.ExitBlock(); +} + +/// Emit the combined function summary section into the combined index +/// file. +static void WriteCombinedFunctionSummary(const FunctionInfoIndex &I, + BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::FUNCTION_SUMMARY_BLOCK_ID, 3); + + // Abbrev for FS_CODE_COMBINED_ENTRY. + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::FS_CODE_COMBINED_ENTRY)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // modid + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8)); // instcount + unsigned FSAbbrev = Stream.EmitAbbrev(Abbv); + + SmallVector<unsigned, 64> NameVals; + for (const auto &FII : I) { + for (auto &FI : FII.getValue()) { + FunctionSummary *FS = FI->functionSummary(); + assert(FS); + + NameVals.push_back(I.getModuleId(FS->modulePath())); + NameVals.push_back(FS->instCount()); + + // Record the starting offset of this summary entry for use + // in the VST entry. Add the current code size since the + // reader will invoke readRecord after the abbrev id read. + FI->setBitcodeIndex(Stream.GetCurrentBitNo() + Stream.GetAbbrevIDWidth()); + + // Emit the finished record. + Stream.EmitRecord(bitc::FS_CODE_COMBINED_ENTRY, NameVals, FSAbbrev); + NameVals.clear(); + } + } + + Stream.ExitBlock(); +} + +// Create the "IDENTIFICATION_BLOCK_ID" containing a single string with the +// current llvm version, and a record for the epoch number. +static void WriteIdentificationBlock(const Module *M, BitstreamWriter &Stream) { + Stream.EnterSubblock(bitc::IDENTIFICATION_BLOCK_ID, 5); + + // Write the "user readable" string identifying the bitcode producer + BitCodeAbbrev *Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::IDENTIFICATION_CODE_STRING)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Array)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Char6)); + auto StringAbbrev = Stream.EmitAbbrev(Abbv); + WriteStringRecord(bitc::IDENTIFICATION_CODE_STRING, + "LLVM" LLVM_VERSION_STRING, StringAbbrev, Stream); + + // Write the epoch version + Abbv = new BitCodeAbbrev(); + Abbv->Add(BitCodeAbbrevOp(bitc::IDENTIFICATION_CODE_EPOCH)); + Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); + auto EpochAbbrev = Stream.EmitAbbrev(Abbv); + SmallVector<unsigned, 1> Vals = {bitc::BITCODE_CURRENT_EPOCH}; + Stream.EmitRecord(bitc::IDENTIFICATION_CODE_EPOCH, Vals, EpochAbbrev); + Stream.ExitBlock(); +} + +/// WriteModule - Emit the specified module to the bitstream. +static void WriteModule(const Module *M, BitstreamWriter &Stream, + bool ShouldPreserveUseListOrder, + uint64_t BitcodeStartBit, bool EmitFunctionSummary) { + Stream.EnterSubblock(bitc::MODULE_BLOCK_ID, 3); + + SmallVector<unsigned, 1> Vals; + unsigned CurVersion = 1; + Vals.push_back(CurVersion); + Stream.EmitRecord(bitc::MODULE_CODE_VERSION, Vals); + + // Analyze the module, enumerating globals, functions, etc. + ValueEnumerator VE(*M, ShouldPreserveUseListOrder); + + // Emit blockinfo, which defines the standard abbreviations etc. + WriteBlockInfo(VE, Stream); + + // Emit information about attribute groups. + WriteAttributeGroupTable(VE, Stream); + + // Emit information about parameter attributes. + WriteAttributeTable(VE, Stream); + + // Emit information describing all of the types in the module. + WriteTypeTable(VE, Stream); + + writeComdats(VE, Stream); + + // Emit top-level description of module, including target triple, inline asm, + // descriptors for global variables, and function prototype info. + uint64_t VSTOffsetPlaceholder = WriteModuleInfo(M, VE, Stream); + + // Emit constants. + WriteModuleConstants(VE, Stream); + + // Emit metadata. + WriteModuleMetadata(M, VE, Stream); + + // Emit metadata. + WriteModuleMetadataStore(M, Stream); + + // Emit module-level use-lists. + if (VE.shouldPreserveUseListOrder()) + WriteUseListBlock(nullptr, VE, Stream); + + WriteOperandBundleTags(M, Stream); + + // Emit function bodies. + DenseMap<const Function *, std::unique_ptr<FunctionInfo>> FunctionIndex; + for (Module::const_iterator F = M->begin(), E = M->end(); F != E; ++F) + if (!F->isDeclaration()) + WriteFunction(*F, VE, Stream, FunctionIndex, EmitFunctionSummary); + + // Need to write after the above call to WriteFunction which populates + // the summary information in the index. + if (EmitFunctionSummary) + WritePerModuleFunctionSummary(FunctionIndex, M, VE, Stream); + + WriteValueSymbolTable(M->getValueSymbolTable(), VE, Stream, + VSTOffsetPlaceholder, BitcodeStartBit, &FunctionIndex); + + Stream.ExitBlock(); +} + +/// EmitDarwinBCHeader - If generating a bc file on darwin, we have to emit a +/// header and trailer to make it compatible with the system archiver. To do +/// this we emit the following header, and then emit a trailer that pads the +/// file out to be a multiple of 16 bytes. +/// +/// struct bc_header { +/// uint32_t Magic; // 0x0B17C0DE +/// uint32_t Version; // Version, currently always 0. +/// uint32_t BitcodeOffset; // Offset to traditional bitcode file. +/// uint32_t BitcodeSize; // Size of traditional bitcode file. +/// uint32_t CPUType; // CPU specifier. +/// ... potentially more later ... +/// }; +enum { + DarwinBCSizeFieldOffset = 3*4, // Offset to bitcode_size. + DarwinBCHeaderSize = 5*4 +}; + +static void WriteInt32ToBuffer(uint32_t Value, SmallVectorImpl<char> &Buffer, + uint32_t &Position) { + support::endian::write32le(&Buffer[Position], Value); + Position += 4; +} + +static void EmitDarwinBCHeaderAndTrailer(SmallVectorImpl<char> &Buffer, + const Triple &TT) { + unsigned CPUType = ~0U; + + // Match x86_64-*, i[3-9]86-*, powerpc-*, powerpc64-*, arm-*, thumb-*, + // armv[0-9]-*, thumbv[0-9]-*, armv5te-*, or armv6t2-*. The CPUType is a magic + // number from /usr/include/mach/machine.h. It is ok to reproduce the + // specific constants here because they are implicitly part of the Darwin ABI. + enum { + DARWIN_CPU_ARCH_ABI64 = 0x01000000, + DARWIN_CPU_TYPE_X86 = 7, + DARWIN_CPU_TYPE_ARM = 12, + DARWIN_CPU_TYPE_POWERPC = 18 + }; + + Triple::ArchType Arch = TT.getArch(); + if (Arch == Triple::x86_64) + CPUType = DARWIN_CPU_TYPE_X86 | DARWIN_CPU_ARCH_ABI64; + else if (Arch == Triple::x86) + CPUType = DARWIN_CPU_TYPE_X86; + else if (Arch == Triple::ppc) + CPUType = DARWIN_CPU_TYPE_POWERPC; + else if (Arch == Triple::ppc64) + CPUType = DARWIN_CPU_TYPE_POWERPC | DARWIN_CPU_ARCH_ABI64; + else if (Arch == Triple::arm || Arch == Triple::thumb) + CPUType = DARWIN_CPU_TYPE_ARM; + + // Traditional Bitcode starts after header. + assert(Buffer.size() >= DarwinBCHeaderSize && + "Expected header size to be reserved"); + unsigned BCOffset = DarwinBCHeaderSize; + unsigned BCSize = Buffer.size()-DarwinBCHeaderSize; + + // Write the magic and version. + unsigned Position = 0; + WriteInt32ToBuffer(0x0B17C0DE , Buffer, Position); + WriteInt32ToBuffer(0 , Buffer, Position); // Version. + WriteInt32ToBuffer(BCOffset , Buffer, Position); + WriteInt32ToBuffer(BCSize , Buffer, Position); + WriteInt32ToBuffer(CPUType , Buffer, Position); + + // If the file is not a multiple of 16 bytes, insert dummy padding. + while (Buffer.size() & 15) + Buffer.push_back(0); +} + +/// Helper to write the header common to all bitcode files. +static void WriteBitcodeHeader(BitstreamWriter &Stream) { + // Emit the file header. + Stream.Emit((unsigned)'B', 8); + Stream.Emit((unsigned)'C', 8); + Stream.Emit(0x0, 4); + Stream.Emit(0xC, 4); + Stream.Emit(0xE, 4); + Stream.Emit(0xD, 4); +} + +/// WriteBitcodeToFile - Write the specified module to the specified output +/// stream. +void llvm::WriteBitcodeToFile(const Module *M, raw_ostream &Out, + bool ShouldPreserveUseListOrder, + bool EmitFunctionSummary) { + SmallVector<char, 0> Buffer; + Buffer.reserve(256*1024); + + // If this is darwin or another generic macho target, reserve space for the + // header. + Triple TT(M->getTargetTriple()); + if (TT.isOSDarwin()) + Buffer.insert(Buffer.begin(), DarwinBCHeaderSize, 0); + + // Emit the module into the buffer. + { + BitstreamWriter Stream(Buffer); + // Save the start bit of the actual bitcode, in case there is space + // saved at the start for the darwin header above. The reader stream + // will start at the bitcode, and we need the offset of the VST + // to line up. + uint64_t BitcodeStartBit = Stream.GetCurrentBitNo(); + + // Emit the file header. + WriteBitcodeHeader(Stream); + + WriteIdentificationBlock(M, Stream); + + // Emit the module. + WriteModule(M, Stream, ShouldPreserveUseListOrder, BitcodeStartBit, + EmitFunctionSummary); + } + + if (TT.isOSDarwin()) + EmitDarwinBCHeaderAndTrailer(Buffer, TT); + + // Write the generated bitstream to "Out". + Out.write((char*)&Buffer.front(), Buffer.size()); +} + +// Write the specified function summary index to the given raw output stream, +// where it will be written in a new bitcode block. This is used when +// writing the combined index file for ThinLTO. +void llvm::WriteFunctionSummaryToFile(const FunctionInfoIndex &Index, + raw_ostream &Out) { + SmallVector<char, 0> Buffer; + Buffer.reserve(256 * 1024); + + BitstreamWriter Stream(Buffer); + + // Emit the bitcode header. + WriteBitcodeHeader(Stream); + + Stream.EnterSubblock(bitc::MODULE_BLOCK_ID, 3); + + SmallVector<unsigned, 1> Vals; + unsigned CurVersion = 1; + Vals.push_back(CurVersion); + Stream.EmitRecord(bitc::MODULE_CODE_VERSION, Vals); + + // Write the module paths in the combined index. + WriteModStrings(Index, Stream); + + // Write the function summary combined index records. + WriteCombinedFunctionSummary(Index, Stream); + + // Need a special VST writer for the combined index (we don't have a + // real VST and real values when this is invoked). + WriteCombinedValueSymbolTable(Index, Stream); + + Stream.ExitBlock(); + + Out.write((char *)&Buffer.front(), Buffer.size()); +} diff --git a/contrib/llvm/lib/Bitcode/Writer/BitcodeWriterPass.cpp b/contrib/llvm/lib/Bitcode/Writer/BitcodeWriterPass.cpp new file mode 100644 index 0000000..24de99a --- /dev/null +++ b/contrib/llvm/lib/Bitcode/Writer/BitcodeWriterPass.cpp @@ -0,0 +1,57 @@ +//===- BitcodeWriterPass.cpp - Bitcode writing pass -----------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// BitcodeWriterPass implementation. +// +//===----------------------------------------------------------------------===// + +#include "llvm/Bitcode/BitcodeWriterPass.h" +#include "llvm/Bitcode/ReaderWriter.h" +#include "llvm/IR/Module.h" +#include "llvm/IR/PassManager.h" +#include "llvm/Pass.h" +using namespace llvm; + +PreservedAnalyses BitcodeWriterPass::run(Module &M) { + WriteBitcodeToFile(&M, OS, ShouldPreserveUseListOrder, EmitFunctionSummary); + return PreservedAnalyses::all(); +} + +namespace { + class WriteBitcodePass : public ModulePass { + raw_ostream &OS; // raw_ostream to print on + bool ShouldPreserveUseListOrder; + bool EmitFunctionSummary; + + public: + static char ID; // Pass identification, replacement for typeid + explicit WriteBitcodePass(raw_ostream &o, bool ShouldPreserveUseListOrder, + bool EmitFunctionSummary) + : ModulePass(ID), OS(o), + ShouldPreserveUseListOrder(ShouldPreserveUseListOrder), + EmitFunctionSummary(EmitFunctionSummary) {} + + const char *getPassName() const override { return "Bitcode Writer"; } + + bool runOnModule(Module &M) override { + WriteBitcodeToFile(&M, OS, ShouldPreserveUseListOrder, + EmitFunctionSummary); + return false; + } + }; +} + +char WriteBitcodePass::ID = 0; + +ModulePass *llvm::createBitcodeWriterPass(raw_ostream &Str, + bool ShouldPreserveUseListOrder, + bool EmitFunctionSummary) { + return new WriteBitcodePass(Str, ShouldPreserveUseListOrder, + EmitFunctionSummary); +} diff --git a/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp b/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp new file mode 100644 index 0000000..e07563b --- /dev/null +++ b/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp @@ -0,0 +1,792 @@ +//===-- ValueEnumerator.cpp - Number values and types for bitcode writer --===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file implements the ValueEnumerator class. +// +//===----------------------------------------------------------------------===// + +#include "ValueEnumerator.h" +#include "llvm/ADT/STLExtras.h" +#include "llvm/ADT/SmallPtrSet.h" +#include "llvm/IR/Constants.h" +#include "llvm/IR/DebugInfoMetadata.h" +#include "llvm/IR/DerivedTypes.h" +#include "llvm/IR/Instructions.h" +#include "llvm/IR/Module.h" +#include "llvm/IR/UseListOrder.h" +#include "llvm/IR/ValueSymbolTable.h" +#include "llvm/Support/Debug.h" +#include "llvm/Support/raw_ostream.h" +#include <algorithm> +using namespace llvm; + +namespace { +struct OrderMap { + DenseMap<const Value *, std::pair<unsigned, bool>> IDs; + unsigned LastGlobalConstantID; + unsigned LastGlobalValueID; + + OrderMap() : LastGlobalConstantID(0), LastGlobalValueID(0) {} + + bool isGlobalConstant(unsigned ID) const { + return ID <= LastGlobalConstantID; + } + bool isGlobalValue(unsigned ID) const { + return ID <= LastGlobalValueID && !isGlobalConstant(ID); + } + + unsigned size() const { return IDs.size(); } + std::pair<unsigned, bool> &operator[](const Value *V) { return IDs[V]; } + std::pair<unsigned, bool> lookup(const Value *V) const { + return IDs.lookup(V); + } + void index(const Value *V) { + // Explicitly sequence get-size and insert-value operations to avoid UB. + unsigned ID = IDs.size() + 1; + IDs[V].first = ID; + } +}; +} + +static void orderValue(const Value *V, OrderMap &OM) { + if (OM.lookup(V).first) + return; + + if (const Constant *C = dyn_cast<Constant>(V)) + if (C->getNumOperands() && !isa<GlobalValue>(C)) + for (const Value *Op : C->operands()) + if (!isa<BasicBlock>(Op) && !isa<GlobalValue>(Op)) + orderValue(Op, OM); + + // Note: we cannot cache this lookup above, since inserting into the map + // changes the map's size, and thus affects the other IDs. + OM.index(V); +} + +static OrderMap orderModule(const Module &M) { + // This needs to match the order used by ValueEnumerator::ValueEnumerator() + // and ValueEnumerator::incorporateFunction(). + OrderMap OM; + + // In the reader, initializers of GlobalValues are set *after* all the + // globals have been read. Rather than awkwardly modeling this behaviour + // directly in predictValueUseListOrderImpl(), just assign IDs to + // initializers of GlobalValues before GlobalValues themselves to model this + // implicitly. + for (const GlobalVariable &G : M.globals()) + if (G.hasInitializer()) + if (!isa<GlobalValue>(G.getInitializer())) + orderValue(G.getInitializer(), OM); + for (const GlobalAlias &A : M.aliases()) + if (!isa<GlobalValue>(A.getAliasee())) + orderValue(A.getAliasee(), OM); + for (const Function &F : M) { + for (const Use &U : F.operands()) + if (!isa<GlobalValue>(U.get())) + orderValue(U.get(), OM); + } + OM.LastGlobalConstantID = OM.size(); + + // Initializers of GlobalValues are processed in + // BitcodeReader::ResolveGlobalAndAliasInits(). Match the order there rather + // than ValueEnumerator, and match the code in predictValueUseListOrderImpl() + // by giving IDs in reverse order. + // + // Since GlobalValues never reference each other directly (just through + // initializers), their relative IDs only matter for determining order of + // uses in their initializers. + for (const Function &F : M) + orderValue(&F, OM); + for (const GlobalAlias &A : M.aliases()) + orderValue(&A, OM); + for (const GlobalVariable &G : M.globals()) + orderValue(&G, OM); + OM.LastGlobalValueID = OM.size(); + + for (const Function &F : M) { + if (F.isDeclaration()) + continue; + // Here we need to match the union of ValueEnumerator::incorporateFunction() + // and WriteFunction(). Basic blocks are implicitly declared before + // anything else (by declaring their size). + for (const BasicBlock &BB : F) + orderValue(&BB, OM); + for (const Argument &A : F.args()) + orderValue(&A, OM); + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) + for (const Value *Op : I.operands()) + if ((isa<Constant>(*Op) && !isa<GlobalValue>(*Op)) || + isa<InlineAsm>(*Op)) + orderValue(Op, OM); + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) + orderValue(&I, OM); + } + return OM; +} + +static void predictValueUseListOrderImpl(const Value *V, const Function *F, + unsigned ID, const OrderMap &OM, + UseListOrderStack &Stack) { + // Predict use-list order for this one. + typedef std::pair<const Use *, unsigned> Entry; + SmallVector<Entry, 64> List; + for (const Use &U : V->uses()) + // Check if this user will be serialized. + if (OM.lookup(U.getUser()).first) + List.push_back(std::make_pair(&U, List.size())); + + if (List.size() < 2) + // We may have lost some users. + return; + + bool IsGlobalValue = OM.isGlobalValue(ID); + std::sort(List.begin(), List.end(), [&](const Entry &L, const Entry &R) { + const Use *LU = L.first; + const Use *RU = R.first; + if (LU == RU) + return false; + + auto LID = OM.lookup(LU->getUser()).first; + auto RID = OM.lookup(RU->getUser()).first; + + // Global values are processed in reverse order. + // + // Moreover, initializers of GlobalValues are set *after* all the globals + // have been read (despite having earlier IDs). Rather than awkwardly + // modeling this behaviour here, orderModule() has assigned IDs to + // initializers of GlobalValues before GlobalValues themselves. + if (OM.isGlobalValue(LID) && OM.isGlobalValue(RID)) + return LID < RID; + + // If ID is 4, then expect: 7 6 5 1 2 3. + if (LID < RID) { + if (RID <= ID) + if (!IsGlobalValue) // GlobalValue uses don't get reversed. + return true; + return false; + } + if (RID < LID) { + if (LID <= ID) + if (!IsGlobalValue) // GlobalValue uses don't get reversed. + return false; + return true; + } + + // LID and RID are equal, so we have different operands of the same user. + // Assume operands are added in order for all instructions. + if (LID <= ID) + if (!IsGlobalValue) // GlobalValue uses don't get reversed. + return LU->getOperandNo() < RU->getOperandNo(); + return LU->getOperandNo() > RU->getOperandNo(); + }); + + if (std::is_sorted( + List.begin(), List.end(), + [](const Entry &L, const Entry &R) { return L.second < R.second; })) + // Order is already correct. + return; + + // Store the shuffle. + Stack.emplace_back(V, F, List.size()); + assert(List.size() == Stack.back().Shuffle.size() && "Wrong size"); + for (size_t I = 0, E = List.size(); I != E; ++I) + Stack.back().Shuffle[I] = List[I].second; +} + +static void predictValueUseListOrder(const Value *V, const Function *F, + OrderMap &OM, UseListOrderStack &Stack) { + auto &IDPair = OM[V]; + assert(IDPair.first && "Unmapped value"); + if (IDPair.second) + // Already predicted. + return; + + // Do the actual prediction. + IDPair.second = true; + if (!V->use_empty() && std::next(V->use_begin()) != V->use_end()) + predictValueUseListOrderImpl(V, F, IDPair.first, OM, Stack); + + // Recursive descent into constants. + if (const Constant *C = dyn_cast<Constant>(V)) + if (C->getNumOperands()) // Visit GlobalValues. + for (const Value *Op : C->operands()) + if (isa<Constant>(Op)) // Visit GlobalValues. + predictValueUseListOrder(Op, F, OM, Stack); +} + +static UseListOrderStack predictUseListOrder(const Module &M) { + OrderMap OM = orderModule(M); + + // Use-list orders need to be serialized after all the users have been added + // to a value, or else the shuffles will be incomplete. Store them per + // function in a stack. + // + // Aside from function order, the order of values doesn't matter much here. + UseListOrderStack Stack; + + // We want to visit the functions backward now so we can list function-local + // constants in the last Function they're used in. Module-level constants + // have already been visited above. + for (auto I = M.rbegin(), E = M.rend(); I != E; ++I) { + const Function &F = *I; + if (F.isDeclaration()) + continue; + for (const BasicBlock &BB : F) + predictValueUseListOrder(&BB, &F, OM, Stack); + for (const Argument &A : F.args()) + predictValueUseListOrder(&A, &F, OM, Stack); + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) + for (const Value *Op : I.operands()) + if (isa<Constant>(*Op) || isa<InlineAsm>(*Op)) // Visit GlobalValues. + predictValueUseListOrder(Op, &F, OM, Stack); + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) + predictValueUseListOrder(&I, &F, OM, Stack); + } + + // Visit globals last, since the module-level use-list block will be seen + // before the function bodies are processed. + for (const GlobalVariable &G : M.globals()) + predictValueUseListOrder(&G, nullptr, OM, Stack); + for (const Function &F : M) + predictValueUseListOrder(&F, nullptr, OM, Stack); + for (const GlobalAlias &A : M.aliases()) + predictValueUseListOrder(&A, nullptr, OM, Stack); + for (const GlobalVariable &G : M.globals()) + if (G.hasInitializer()) + predictValueUseListOrder(G.getInitializer(), nullptr, OM, Stack); + for (const GlobalAlias &A : M.aliases()) + predictValueUseListOrder(A.getAliasee(), nullptr, OM, Stack); + for (const Function &F : M) { + for (const Use &U : F.operands()) + predictValueUseListOrder(U.get(), nullptr, OM, Stack); + } + + return Stack; +} + +static bool isIntOrIntVectorValue(const std::pair<const Value*, unsigned> &V) { + return V.first->getType()->isIntOrIntVectorTy(); +} + +ValueEnumerator::ValueEnumerator(const Module &M, + bool ShouldPreserveUseListOrder) + : HasMDString(false), HasDILocation(false), HasGenericDINode(false), + ShouldPreserveUseListOrder(ShouldPreserveUseListOrder) { + if (ShouldPreserveUseListOrder) + UseListOrders = predictUseListOrder(M); + + // Enumerate the global variables. + for (const GlobalVariable &GV : M.globals()) + EnumerateValue(&GV); + + // Enumerate the functions. + for (const Function & F : M) { + EnumerateValue(&F); + EnumerateAttributes(F.getAttributes()); + } + + // Enumerate the aliases. + for (const GlobalAlias &GA : M.aliases()) + EnumerateValue(&GA); + + // Remember what is the cutoff between globalvalue's and other constants. + unsigned FirstConstant = Values.size(); + + // Enumerate the global variable initializers. + for (const GlobalVariable &GV : M.globals()) + if (GV.hasInitializer()) + EnumerateValue(GV.getInitializer()); + + // Enumerate the aliasees. + for (const GlobalAlias &GA : M.aliases()) + EnumerateValue(GA.getAliasee()); + + // Enumerate any optional Function data. + for (const Function &F : M) + for (const Use &U : F.operands()) + EnumerateValue(U.get()); + + // Enumerate the metadata type. + // + // TODO: Move this to ValueEnumerator::EnumerateOperandType() once bitcode + // only encodes the metadata type when it's used as a value. + EnumerateType(Type::getMetadataTy(M.getContext())); + + // Insert constants and metadata that are named at module level into the slot + // pool so that the module symbol table can refer to them... + EnumerateValueSymbolTable(M.getValueSymbolTable()); + EnumerateNamedMetadata(M); + + SmallVector<std::pair<unsigned, MDNode *>, 8> MDs; + + // Enumerate types used by function bodies and argument lists. + for (const Function &F : M) { + for (const Argument &A : F.args()) + EnumerateType(A.getType()); + + // Enumerate metadata attached to this function. + F.getAllMetadata(MDs); + for (const auto &I : MDs) + EnumerateMetadata(I.second); + + for (const BasicBlock &BB : F) + for (const Instruction &I : BB) { + for (const Use &Op : I.operands()) { + auto *MD = dyn_cast<MetadataAsValue>(&Op); + if (!MD) { + EnumerateOperandType(Op); + continue; + } + + // Local metadata is enumerated during function-incorporation. + if (isa<LocalAsMetadata>(MD->getMetadata())) + continue; + + EnumerateMetadata(MD->getMetadata()); + } + EnumerateType(I.getType()); + if (const CallInst *CI = dyn_cast<CallInst>(&I)) + EnumerateAttributes(CI->getAttributes()); + else if (const InvokeInst *II = dyn_cast<InvokeInst>(&I)) + EnumerateAttributes(II->getAttributes()); + + // Enumerate metadata attached with this instruction. + MDs.clear(); + I.getAllMetadataOtherThanDebugLoc(MDs); + for (unsigned i = 0, e = MDs.size(); i != e; ++i) + EnumerateMetadata(MDs[i].second); + + // Don't enumerate the location directly -- it has a special record + // type -- but enumerate its operands. + if (DILocation *L = I.getDebugLoc()) + EnumerateMDNodeOperands(L); + } + } + + // Optimize constant ordering. + OptimizeConstants(FirstConstant, Values.size()); +} + +unsigned ValueEnumerator::getInstructionID(const Instruction *Inst) const { + InstructionMapType::const_iterator I = InstructionMap.find(Inst); + assert(I != InstructionMap.end() && "Instruction is not mapped!"); + return I->second; +} + +unsigned ValueEnumerator::getComdatID(const Comdat *C) const { + unsigned ComdatID = Comdats.idFor(C); + assert(ComdatID && "Comdat not found!"); + return ComdatID; +} + +void ValueEnumerator::setInstructionID(const Instruction *I) { + InstructionMap[I] = InstructionCount++; +} + +unsigned ValueEnumerator::getValueID(const Value *V) const { + if (auto *MD = dyn_cast<MetadataAsValue>(V)) + return getMetadataID(MD->getMetadata()); + + ValueMapType::const_iterator I = ValueMap.find(V); + assert(I != ValueMap.end() && "Value not in slotcalculator!"); + return I->second-1; +} + +void ValueEnumerator::dump() const { + print(dbgs(), ValueMap, "Default"); + dbgs() << '\n'; + print(dbgs(), MetadataMap, "MetaData"); + dbgs() << '\n'; +} + +void ValueEnumerator::print(raw_ostream &OS, const ValueMapType &Map, + const char *Name) const { + + OS << "Map Name: " << Name << "\n"; + OS << "Size: " << Map.size() << "\n"; + for (ValueMapType::const_iterator I = Map.begin(), + E = Map.end(); I != E; ++I) { + + const Value *V = I->first; + if (V->hasName()) + OS << "Value: " << V->getName(); + else + OS << "Value: [null]\n"; + V->dump(); + + OS << " Uses(" << std::distance(V->use_begin(),V->use_end()) << "):"; + for (const Use &U : V->uses()) { + if (&U != &*V->use_begin()) + OS << ","; + if(U->hasName()) + OS << " " << U->getName(); + else + OS << " [null]"; + + } + OS << "\n\n"; + } +} + +void ValueEnumerator::print(raw_ostream &OS, const MetadataMapType &Map, + const char *Name) const { + + OS << "Map Name: " << Name << "\n"; + OS << "Size: " << Map.size() << "\n"; + for (auto I = Map.begin(), E = Map.end(); I != E; ++I) { + const Metadata *MD = I->first; + OS << "Metadata: slot = " << I->second << "\n"; + MD->print(OS); + } +} + +/// OptimizeConstants - Reorder constant pool for denser encoding. +void ValueEnumerator::OptimizeConstants(unsigned CstStart, unsigned CstEnd) { + if (CstStart == CstEnd || CstStart+1 == CstEnd) return; + + if (ShouldPreserveUseListOrder) + // Optimizing constants makes the use-list order difficult to predict. + // Disable it for now when trying to preserve the order. + return; + + std::stable_sort(Values.begin() + CstStart, Values.begin() + CstEnd, + [this](const std::pair<const Value *, unsigned> &LHS, + const std::pair<const Value *, unsigned> &RHS) { + // Sort by plane. + if (LHS.first->getType() != RHS.first->getType()) + return getTypeID(LHS.first->getType()) < getTypeID(RHS.first->getType()); + // Then by frequency. + return LHS.second > RHS.second; + }); + + // Ensure that integer and vector of integer constants are at the start of the + // constant pool. This is important so that GEP structure indices come before + // gep constant exprs. + std::partition(Values.begin()+CstStart, Values.begin()+CstEnd, + isIntOrIntVectorValue); + + // Rebuild the modified portion of ValueMap. + for (; CstStart != CstEnd; ++CstStart) + ValueMap[Values[CstStart].first] = CstStart+1; +} + + +/// EnumerateValueSymbolTable - Insert all of the values in the specified symbol +/// table into the values table. +void ValueEnumerator::EnumerateValueSymbolTable(const ValueSymbolTable &VST) { + for (ValueSymbolTable::const_iterator VI = VST.begin(), VE = VST.end(); + VI != VE; ++VI) + EnumerateValue(VI->getValue()); +} + +/// Insert all of the values referenced by named metadata in the specified +/// module. +void ValueEnumerator::EnumerateNamedMetadata(const Module &M) { + for (const auto &I : M.named_metadata()) + EnumerateNamedMDNode(&I); +} + +void ValueEnumerator::EnumerateNamedMDNode(const NamedMDNode *MD) { + for (unsigned i = 0, e = MD->getNumOperands(); i != e; ++i) + EnumerateMetadata(MD->getOperand(i)); +} + +/// EnumerateMDNodeOperands - Enumerate all non-function-local values +/// and types referenced by the given MDNode. +void ValueEnumerator::EnumerateMDNodeOperands(const MDNode *N) { + for (unsigned i = 0, e = N->getNumOperands(); i != e; ++i) { + Metadata *MD = N->getOperand(i); + if (!MD) + continue; + assert(!isa<LocalAsMetadata>(MD) && "MDNodes cannot be function-local"); + EnumerateMetadata(MD); + } +} + +void ValueEnumerator::EnumerateMetadata(const Metadata *MD) { + assert( + (isa<MDNode>(MD) || isa<MDString>(MD) || isa<ConstantAsMetadata>(MD)) && + "Invalid metadata kind"); + + // Insert a dummy ID to block the co-recursive call to + // EnumerateMDNodeOperands() from re-visiting MD in a cyclic graph. + // + // Return early if there's already an ID. + if (!MetadataMap.insert(std::make_pair(MD, 0)).second) + return; + + // Visit operands first to minimize RAUW. + if (auto *N = dyn_cast<MDNode>(MD)) + EnumerateMDNodeOperands(N); + else if (auto *C = dyn_cast<ConstantAsMetadata>(MD)) + EnumerateValue(C->getValue()); + + HasMDString |= isa<MDString>(MD); + HasDILocation |= isa<DILocation>(MD); + HasGenericDINode |= isa<GenericDINode>(MD); + + // Replace the dummy ID inserted above with the correct one. MetadataMap may + // have changed by inserting operands, so we need a fresh lookup here. + MDs.push_back(MD); + MetadataMap[MD] = MDs.size(); +} + +/// EnumerateFunctionLocalMetadataa - Incorporate function-local metadata +/// information reachable from the metadata. +void ValueEnumerator::EnumerateFunctionLocalMetadata( + const LocalAsMetadata *Local) { + // Check to see if it's already in! + unsigned &MetadataID = MetadataMap[Local]; + if (MetadataID) + return; + + MDs.push_back(Local); + MetadataID = MDs.size(); + + EnumerateValue(Local->getValue()); + + // Also, collect all function-local metadata for easy access. + FunctionLocalMDs.push_back(Local); +} + +void ValueEnumerator::EnumerateValue(const Value *V) { + assert(!V->getType()->isVoidTy() && "Can't insert void values!"); + assert(!isa<MetadataAsValue>(V) && "EnumerateValue doesn't handle Metadata!"); + + // Check to see if it's already in! + unsigned &ValueID = ValueMap[V]; + if (ValueID) { + // Increment use count. + Values[ValueID-1].second++; + return; + } + + if (auto *GO = dyn_cast<GlobalObject>(V)) + if (const Comdat *C = GO->getComdat()) + Comdats.insert(C); + + // Enumerate the type of this value. + EnumerateType(V->getType()); + + if (const Constant *C = dyn_cast<Constant>(V)) { + if (isa<GlobalValue>(C)) { + // Initializers for globals are handled explicitly elsewhere. + } else if (C->getNumOperands()) { + // If a constant has operands, enumerate them. This makes sure that if a + // constant has uses (for example an array of const ints), that they are + // inserted also. + + // We prefer to enumerate them with values before we enumerate the user + // itself. This makes it more likely that we can avoid forward references + // in the reader. We know that there can be no cycles in the constants + // graph that don't go through a global variable. + for (User::const_op_iterator I = C->op_begin(), E = C->op_end(); + I != E; ++I) + if (!isa<BasicBlock>(*I)) // Don't enumerate BB operand to BlockAddress. + EnumerateValue(*I); + + // Finally, add the value. Doing this could make the ValueID reference be + // dangling, don't reuse it. + Values.push_back(std::make_pair(V, 1U)); + ValueMap[V] = Values.size(); + return; + } + } + + // Add the value. + Values.push_back(std::make_pair(V, 1U)); + ValueID = Values.size(); +} + + +void ValueEnumerator::EnumerateType(Type *Ty) { + unsigned *TypeID = &TypeMap[Ty]; + + // We've already seen this type. + if (*TypeID) + return; + + // If it is a non-anonymous struct, mark the type as being visited so that we + // don't recursively visit it. This is safe because we allow forward + // references of these in the bitcode reader. + if (StructType *STy = dyn_cast<StructType>(Ty)) + if (!STy->isLiteral()) + *TypeID = ~0U; + + // Enumerate all of the subtypes before we enumerate this type. This ensures + // that the type will be enumerated in an order that can be directly built. + for (Type *SubTy : Ty->subtypes()) + EnumerateType(SubTy); + + // Refresh the TypeID pointer in case the table rehashed. + TypeID = &TypeMap[Ty]; + + // Check to see if we got the pointer another way. This can happen when + // enumerating recursive types that hit the base case deeper than they start. + // + // If this is actually a struct that we are treating as forward ref'able, + // then emit the definition now that all of its contents are available. + if (*TypeID && *TypeID != ~0U) + return; + + // Add this type now that its contents are all happily enumerated. + Types.push_back(Ty); + + *TypeID = Types.size(); +} + +// Enumerate the types for the specified value. If the value is a constant, +// walk through it, enumerating the types of the constant. +void ValueEnumerator::EnumerateOperandType(const Value *V) { + EnumerateType(V->getType()); + + if (auto *MD = dyn_cast<MetadataAsValue>(V)) { + assert(!isa<LocalAsMetadata>(MD->getMetadata()) && + "Function-local metadata should be left for later"); + + EnumerateMetadata(MD->getMetadata()); + return; + } + + const Constant *C = dyn_cast<Constant>(V); + if (!C) + return; + + // If this constant is already enumerated, ignore it, we know its type must + // be enumerated. + if (ValueMap.count(C)) + return; + + // This constant may have operands, make sure to enumerate the types in + // them. + for (const Value *Op : C->operands()) { + // Don't enumerate basic blocks here, this happens as operands to + // blockaddress. + if (isa<BasicBlock>(Op)) + continue; + + EnumerateOperandType(Op); + } +} + +void ValueEnumerator::EnumerateAttributes(AttributeSet PAL) { + if (PAL.isEmpty()) return; // null is always 0. + + // Do a lookup. + unsigned &Entry = AttributeMap[PAL]; + if (Entry == 0) { + // Never saw this before, add it. + Attribute.push_back(PAL); + Entry = Attribute.size(); + } + + // Do lookups for all attribute groups. + for (unsigned i = 0, e = PAL.getNumSlots(); i != e; ++i) { + AttributeSet AS = PAL.getSlotAttributes(i); + unsigned &Entry = AttributeGroupMap[AS]; + if (Entry == 0) { + AttributeGroups.push_back(AS); + Entry = AttributeGroups.size(); + } + } +} + +void ValueEnumerator::incorporateFunction(const Function &F) { + InstructionCount = 0; + NumModuleValues = Values.size(); + NumModuleMDs = MDs.size(); + + // Adding function arguments to the value table. + for (const auto &I : F.args()) + EnumerateValue(&I); + + FirstFuncConstantID = Values.size(); + + // Add all function-level constants to the value table. + for (const BasicBlock &BB : F) { + for (const Instruction &I : BB) + for (const Use &OI : I.operands()) { + if ((isa<Constant>(OI) && !isa<GlobalValue>(OI)) || isa<InlineAsm>(OI)) + EnumerateValue(OI); + } + BasicBlocks.push_back(&BB); + ValueMap[&BB] = BasicBlocks.size(); + } + + // Optimize the constant layout. + OptimizeConstants(FirstFuncConstantID, Values.size()); + + // Add the function's parameter attributes so they are available for use in + // the function's instruction. + EnumerateAttributes(F.getAttributes()); + + FirstInstID = Values.size(); + + SmallVector<LocalAsMetadata *, 8> FnLocalMDVector; + // Add all of the instructions. + for (const BasicBlock &BB : F) { + for (const Instruction &I : BB) { + for (const Use &OI : I.operands()) { + if (auto *MD = dyn_cast<MetadataAsValue>(&OI)) + if (auto *Local = dyn_cast<LocalAsMetadata>(MD->getMetadata())) + // Enumerate metadata after the instructions they might refer to. + FnLocalMDVector.push_back(Local); + } + + if (!I.getType()->isVoidTy()) + EnumerateValue(&I); + } + } + + // Add all of the function-local metadata. + for (unsigned i = 0, e = FnLocalMDVector.size(); i != e; ++i) + EnumerateFunctionLocalMetadata(FnLocalMDVector[i]); +} + +void ValueEnumerator::purgeFunction() { + /// Remove purged values from the ValueMap. + for (unsigned i = NumModuleValues, e = Values.size(); i != e; ++i) + ValueMap.erase(Values[i].first); + for (unsigned i = NumModuleMDs, e = MDs.size(); i != e; ++i) + MetadataMap.erase(MDs[i]); + for (unsigned i = 0, e = BasicBlocks.size(); i != e; ++i) + ValueMap.erase(BasicBlocks[i]); + + Values.resize(NumModuleValues); + MDs.resize(NumModuleMDs); + BasicBlocks.clear(); + FunctionLocalMDs.clear(); +} + +static void IncorporateFunctionInfoGlobalBBIDs(const Function *F, + DenseMap<const BasicBlock*, unsigned> &IDMap) { + unsigned Counter = 0; + for (const BasicBlock &BB : *F) + IDMap[&BB] = ++Counter; +} + +/// getGlobalBasicBlockID - This returns the function-specific ID for the +/// specified basic block. This is relatively expensive information, so it +/// should only be used by rare constructs such as address-of-label. +unsigned ValueEnumerator::getGlobalBasicBlockID(const BasicBlock *BB) const { + unsigned &Idx = GlobalBasicBlockIDs[BB]; + if (Idx != 0) + return Idx-1; + + IncorporateFunctionInfoGlobalBBIDs(BB->getParent(), GlobalBasicBlockIDs); + return getGlobalBasicBlockID(BB); +} + +uint64_t ValueEnumerator::computeBitsRequiredForTypeIndicies() const { + return Log2_32_Ceil(getTypes().size() + 1); +} diff --git a/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.h b/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.h new file mode 100644 index 0000000..9fb8325 --- /dev/null +++ b/contrib/llvm/lib/Bitcode/Writer/ValueEnumerator.h @@ -0,0 +1,209 @@ +//===-- Bitcode/Writer/ValueEnumerator.h - Number values --------*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This class gives values and types Unique ID's. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_LIB_BITCODE_WRITER_VALUEENUMERATOR_H +#define LLVM_LIB_BITCODE_WRITER_VALUEENUMERATOR_H + +#include "llvm/ADT/DenseMap.h" +#include "llvm/ADT/SmallVector.h" +#include "llvm/ADT/UniqueVector.h" +#include "llvm/IR/Attributes.h" +#include "llvm/IR/UseListOrder.h" +#include <vector> + +namespace llvm { + +class Type; +class Value; +class Instruction; +class BasicBlock; +class Comdat; +class Function; +class Module; +class Metadata; +class LocalAsMetadata; +class MDNode; +class NamedMDNode; +class AttributeSet; +class ValueSymbolTable; +class MDSymbolTable; +class raw_ostream; + +class ValueEnumerator { +public: + typedef std::vector<Type*> TypeList; + + // For each value, we remember its Value* and occurrence frequency. + typedef std::vector<std::pair<const Value*, unsigned> > ValueList; + + UseListOrderStack UseListOrders; + +private: + typedef DenseMap<Type*, unsigned> TypeMapType; + TypeMapType TypeMap; + TypeList Types; + + typedef DenseMap<const Value*, unsigned> ValueMapType; + ValueMapType ValueMap; + ValueList Values; + + typedef UniqueVector<const Comdat *> ComdatSetType; + ComdatSetType Comdats; + + std::vector<const Metadata *> MDs; + SmallVector<const LocalAsMetadata *, 8> FunctionLocalMDs; + typedef DenseMap<const Metadata *, unsigned> MetadataMapType; + MetadataMapType MetadataMap; + bool HasMDString; + bool HasDILocation; + bool HasGenericDINode; + bool ShouldPreserveUseListOrder; + + typedef DenseMap<AttributeSet, unsigned> AttributeGroupMapType; + AttributeGroupMapType AttributeGroupMap; + std::vector<AttributeSet> AttributeGroups; + + typedef DenseMap<AttributeSet, unsigned> AttributeMapType; + AttributeMapType AttributeMap; + std::vector<AttributeSet> Attribute; + + /// GlobalBasicBlockIDs - This map memoizes the basic block ID's referenced by + /// the "getGlobalBasicBlockID" method. + mutable DenseMap<const BasicBlock*, unsigned> GlobalBasicBlockIDs; + + typedef DenseMap<const Instruction*, unsigned> InstructionMapType; + InstructionMapType InstructionMap; + unsigned InstructionCount; + + /// BasicBlocks - This contains all the basic blocks for the currently + /// incorporated function. Their reverse mapping is stored in ValueMap. + std::vector<const BasicBlock*> BasicBlocks; + + /// When a function is incorporated, this is the size of the Values list + /// before incorporation. + unsigned NumModuleValues; + + /// When a function is incorporated, this is the size of the Metadatas list + /// before incorporation. + unsigned NumModuleMDs; + + unsigned FirstFuncConstantID; + unsigned FirstInstID; + + ValueEnumerator(const ValueEnumerator &) = delete; + void operator=(const ValueEnumerator &) = delete; +public: + ValueEnumerator(const Module &M, bool ShouldPreserveUseListOrder); + + void dump() const; + void print(raw_ostream &OS, const ValueMapType &Map, const char *Name) const; + void print(raw_ostream &OS, const MetadataMapType &Map, + const char *Name) const; + + unsigned getValueID(const Value *V) const; + unsigned getMetadataID(const Metadata *MD) const { + auto ID = getMetadataOrNullID(MD); + assert(ID != 0 && "Metadata not in slotcalculator!"); + return ID - 1; + } + unsigned getMetadataOrNullID(const Metadata *MD) const { + return MetadataMap.lookup(MD); + } + unsigned numMDs() const { return MDs.size(); } + + bool hasMDString() const { return HasMDString; } + bool hasDILocation() const { return HasDILocation; } + bool hasGenericDINode() const { return HasGenericDINode; } + + bool shouldPreserveUseListOrder() const { return ShouldPreserveUseListOrder; } + + unsigned getTypeID(Type *T) const { + TypeMapType::const_iterator I = TypeMap.find(T); + assert(I != TypeMap.end() && "Type not in ValueEnumerator!"); + return I->second-1; + } + + unsigned getInstructionID(const Instruction *I) const; + void setInstructionID(const Instruction *I); + + unsigned getAttributeID(AttributeSet PAL) const { + if (PAL.isEmpty()) return 0; // Null maps to zero. + AttributeMapType::const_iterator I = AttributeMap.find(PAL); + assert(I != AttributeMap.end() && "Attribute not in ValueEnumerator!"); + return I->second; + } + + unsigned getAttributeGroupID(AttributeSet PAL) const { + if (PAL.isEmpty()) return 0; // Null maps to zero. + AttributeGroupMapType::const_iterator I = AttributeGroupMap.find(PAL); + assert(I != AttributeGroupMap.end() && "Attribute not in ValueEnumerator!"); + return I->second; + } + + /// getFunctionConstantRange - Return the range of values that corresponds to + /// function-local constants. + void getFunctionConstantRange(unsigned &Start, unsigned &End) const { + Start = FirstFuncConstantID; + End = FirstInstID; + } + + const ValueList &getValues() const { return Values; } + const std::vector<const Metadata *> &getMDs() const { return MDs; } + const SmallVectorImpl<const LocalAsMetadata *> &getFunctionLocalMDs() const { + return FunctionLocalMDs; + } + const TypeList &getTypes() const { return Types; } + const std::vector<const BasicBlock*> &getBasicBlocks() const { + return BasicBlocks; + } + const std::vector<AttributeSet> &getAttributes() const { + return Attribute; + } + const std::vector<AttributeSet> &getAttributeGroups() const { + return AttributeGroups; + } + + const ComdatSetType &getComdats() const { return Comdats; } + unsigned getComdatID(const Comdat *C) const; + + /// getGlobalBasicBlockID - This returns the function-specific ID for the + /// specified basic block. This is relatively expensive information, so it + /// should only be used by rare constructs such as address-of-label. + unsigned getGlobalBasicBlockID(const BasicBlock *BB) const; + + /// incorporateFunction/purgeFunction - If you'd like to deal with a function, + /// use these two methods to get its data into the ValueEnumerator! + /// + void incorporateFunction(const Function &F); + void purgeFunction(); + uint64_t computeBitsRequiredForTypeIndicies() const; + +private: + void OptimizeConstants(unsigned CstStart, unsigned CstEnd); + + void EnumerateMDNodeOperands(const MDNode *N); + void EnumerateMetadata(const Metadata *MD); + void EnumerateFunctionLocalMetadata(const LocalAsMetadata *Local); + void EnumerateNamedMDNode(const NamedMDNode *NMD); + void EnumerateValue(const Value *V); + void EnumerateType(Type *T); + void EnumerateOperandType(const Value *V); + void EnumerateAttributes(AttributeSet PAL); + + void EnumerateValueSymbolTable(const ValueSymbolTable &ST); + void EnumerateNamedMetadata(const Module &M); +}; + +} // End llvm namespace + +#endif |
