#include "llvm/Transforms/IPO.h"
#include "llvm/ADT/EquivalenceClasses.h"
#include "llvm/ADT/Statistic.h"
+#include "llvm/ADT/Triple.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/GlobalObject.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Operator.h"
#include "llvm/Pass.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
using namespace llvm;
STATISTIC(NumBitSetCallsLowered, "Number of bitset calls lowered");
STATISTIC(NumBitSetDisjointSets, "Number of disjoint sets of bitsets");
+static cl::opt<bool> AvoidReuse(
+ "lowerbitsets-avoid-reuse",
+ cl::desc("Try to avoid reuse of byte array addresses using aliases"),
+ cl::Hidden, cl::init(true));
+
bool BitSetInfo::containsGlobalOffset(uint64_t Offset) const {
if (Offset < ByteOffset)
return false;
}
bool BitSetInfo::containsValue(
- const DataLayout *DL,
- const DenseMap<GlobalVariable *, uint64_t> &GlobalLayout, Value *V,
+ const DataLayout &DL,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout, Value *V,
uint64_t COffset) const {
- if (auto GV = dyn_cast<GlobalVariable>(V)) {
+ if (auto GV = dyn_cast<GlobalObject>(V)) {
auto I = GlobalLayout.find(GV);
if (I == GlobalLayout.end())
return false;
}
if (auto GEP = dyn_cast<GEPOperator>(V)) {
- APInt APOffset(DL->getPointerSizeInBits(0), 0);
- bool Result = GEP->accumulateConstantOffset(*DL, APOffset);
+ APInt APOffset(DL.getPointerSizeInBits(0), 0);
+ bool Result = GEP->accumulateConstantOffset(DL, APOffset);
if (!Result)
return false;
COffset += APOffset.getZExtValue();
return false;
}
+void BitSetInfo::print(raw_ostream &OS) const {
+ OS << "offset " << ByteOffset << " size " << BitSize << " align "
+ << (1 << AlignLog2);
+
+ if (isAllOnes()) {
+ OS << " all-ones\n";
+ return;
+ }
+
+ OS << " { ";
+ for (uint64_t B : Bits)
+ OS << B << ' ';
+ OS << "}\n";
+ return;
+}
+
BitSetInfo BitSetBuilder::build() {
if (Min > Max)
Min = 0;
Module *M;
- const DataLayout *DL;
+ bool LinkerSubsectionsViaSymbols;
+ Triple::ArchType Arch;
+ Triple::ObjectFormatType ObjectFormat;
IntegerType *Int1Ty;
IntegerType *Int8Ty;
IntegerType *Int32Ty;
Type *Int32PtrTy;
IntegerType *Int64Ty;
- Type *IntPtrTy;
+ IntegerType *IntPtrTy;
// The llvm.bitsets named metadata.
NamedMDNode *BitSetNM;
- // Mapping from bitset mdstrings to the call sites that test them.
- DenseMap<MDString *, std::vector<CallInst *>> BitSetTestCallSites;
+ // Mapping from bitset identifiers to the call sites that test them.
+ DenseMap<Metadata *, std::vector<CallInst *>> BitSetTestCallSites;
std::vector<ByteArrayInfo> ByteArrayInfos;
BitSetInfo
- buildBitSet(MDString *BitSet,
- const DenseMap<GlobalVariable *, uint64_t> &GlobalLayout);
+ buildBitSet(Metadata *BitSet,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout);
ByteArrayInfo *createByteArray(BitSetInfo &BSI);
void allocateByteArrays();
Value *createBitSetTest(IRBuilder<> &B, BitSetInfo &BSI, ByteArrayInfo *&BAI,
Value *BitOffset);
+ void lowerBitSetCalls(ArrayRef<Metadata *> BitSets,
+ Constant *CombinedGlobalAddr,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout);
Value *
lowerBitSetCall(CallInst *CI, BitSetInfo &BSI, ByteArrayInfo *&BAI,
- GlobalVariable *CombinedGlobal,
- const DenseMap<GlobalVariable *, uint64_t> &GlobalLayout);
- void buildBitSetsFromGlobals(const std::vector<MDString *> &BitSets,
- const std::vector<GlobalVariable *> &Globals);
+ Constant *CombinedGlobal,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout);
+ void buildBitSetsFromGlobalVariables(ArrayRef<Metadata *> BitSets,
+ ArrayRef<GlobalVariable *> Globals);
+ unsigned getJumpTableEntrySize();
+ Type *getJumpTableEntryType();
+ Constant *createJumpTableEntry(GlobalObject *Src, Function *Dest,
+ unsigned Distance);
+ void verifyBitSetMDNode(MDNode *Op);
+ void buildBitSetsFromFunctions(ArrayRef<Metadata *> BitSets,
+ ArrayRef<Function *> Functions);
+ void buildBitSetsFromDisjointSet(ArrayRef<Metadata *> BitSets,
+ ArrayRef<GlobalObject *> Globals);
bool buildBitSets();
bool eraseBitSetMetadata();
bool LowerBitSets::doInitialization(Module &Mod) {
M = &Mod;
+ const DataLayout &DL = Mod.getDataLayout();
- DL = M->getDataLayout();
- if (!DL)
- report_fatal_error("Data layout required");
+ Triple TargetTriple(M->getTargetTriple());
+ LinkerSubsectionsViaSymbols = TargetTriple.isMacOSX();
+ Arch = TargetTriple.getArch();
+ ObjectFormat = TargetTriple.getObjectFormat();
Int1Ty = Type::getInt1Ty(M->getContext());
Int8Ty = Type::getInt8Ty(M->getContext());
Int32Ty = Type::getInt32Ty(M->getContext());
Int32PtrTy = PointerType::getUnqual(Int32Ty);
Int64Ty = Type::getInt64Ty(M->getContext());
- IntPtrTy = DL->getIntPtrType(M->getContext(), 0);
+ IntPtrTy = DL.getIntPtrType(M->getContext(), 0);
BitSetNM = M->getNamedMetadata("llvm.bitsets");
/// Build a bit set for BitSet using the object layouts in
/// GlobalLayout.
BitSetInfo LowerBitSets::buildBitSet(
- MDString *BitSet,
- const DenseMap<GlobalVariable *, uint64_t> &GlobalLayout) {
+ Metadata *BitSet,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout) {
BitSetBuilder BSB;
// Compute the byte offset of each element of this bitset.
for (MDNode *Op : BitSetNM->operands()) {
if (Op->getOperand(0) != BitSet || !Op->getOperand(1))
continue;
- auto OpGlobal = cast<GlobalVariable>(
- cast<ConstantAsMetadata>(Op->getOperand(1))->getValue());
+ Constant *OpConst =
+ cast<ConstantAsMetadata>(Op->getOperand(1))->getValue();
+ if (auto GA = dyn_cast<GlobalAlias>(OpConst))
+ OpConst = GA->getAliasee();
+ auto OpGlobal = dyn_cast<GlobalObject>(OpConst);
+ if (!OpGlobal)
+ continue;
uint64_t Offset =
cast<ConstantInt>(cast<ConstantAsMetadata>(Op->getOperand(2))
->getValue())->getZExtValue();
Constant *Idxs[] = {ConstantInt::get(IntPtrTy, 0),
ConstantInt::get(IntPtrTy, ByteArrayOffsets[I])};
- Constant *GEP = ConstantExpr::getInBoundsGetElementPtr(ByteArray, Idxs);
+ Constant *GEP = ConstantExpr::getInBoundsGetElementPtr(
+ ByteArrayConst->getType(), ByteArray, Idxs);
// Create an alias instead of RAUW'ing the gep directly. On x86 this ensures
// that the pc-relative displacement is folded into the lea instead of the
// test instruction getting another displacement.
- GlobalAlias *Alias = GlobalAlias::create(
- Int8Ty, 0, GlobalValue::PrivateLinkage, "bits", GEP, M);
- BAI->ByteArray->replaceAllUsesWith(Alias);
+ if (LinkerSubsectionsViaSymbols) {
+ BAI->ByteArray->replaceAllUsesWith(GEP);
+ } else {
+ GlobalAlias *Alias = GlobalAlias::create(
+ Int8Ty, 0, GlobalValue::PrivateLinkage, "bits", GEP, M);
+ BAI->ByteArray->replaceAllUsesWith(Alias);
+ }
BAI->ByteArray->eraseFromParent();
}
BAI = createByteArray(BSI);
}
- Value *ByteAddr = B.CreateGEP(BAI->ByteArray, BitOffset);
+ Constant *ByteArray = BAI->ByteArray;
+ Type *Ty = BAI->ByteArray->getValueType();
+ if (!LinkerSubsectionsViaSymbols && AvoidReuse) {
+ // Each use of the byte array uses a different alias. This makes the
+ // backend less likely to reuse previously computed byte array addresses,
+ // improving the security of the CFI mechanism based on this pass.
+ ByteArray = GlobalAlias::create(BAI->ByteArray->getValueType(), 0,
+ GlobalValue::PrivateLinkage, "bits_use",
+ ByteArray, M);
+ }
+
+ Value *ByteAddr = B.CreateGEP(Ty, ByteArray, BitOffset);
Value *Byte = B.CreateLoad(ByteAddr);
Value *ByteAndMask = B.CreateAnd(Byte, BAI->Mask);
/// replace the call with.
Value *LowerBitSets::lowerBitSetCall(
CallInst *CI, BitSetInfo &BSI, ByteArrayInfo *&BAI,
- GlobalVariable *CombinedGlobal,
- const DenseMap<GlobalVariable *, uint64_t> &GlobalLayout) {
+ Constant *CombinedGlobalIntAddr,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout) {
Value *Ptr = CI->getArgOperand(0);
+ const DataLayout &DL = M->getDataLayout();
if (BSI.containsValue(DL, GlobalLayout, Ptr))
- return ConstantInt::getTrue(CombinedGlobal->getParent()->getContext());
+ return ConstantInt::getTrue(M->getContext());
- Constant *GlobalAsInt = ConstantExpr::getPtrToInt(CombinedGlobal, IntPtrTy);
Constant *OffsetedGlobalAsInt = ConstantExpr::getAdd(
- GlobalAsInt, ConstantInt::get(IntPtrTy, BSI.ByteOffset));
+ CombinedGlobalIntAddr, ConstantInt::get(IntPtrTy, BSI.ByteOffset));
BasicBlock *InitialBB = CI->getParent();
Value *OffsetSHR =
B.CreateLShr(PtrOffset, ConstantInt::get(IntPtrTy, BSI.AlignLog2));
Value *OffsetSHL = B.CreateShl(
- PtrOffset, ConstantInt::get(IntPtrTy, DL->getPointerSizeInBits(0) -
- BSI.AlignLog2));
+ PtrOffset,
+ ConstantInt::get(IntPtrTy, DL.getPointerSizeInBits(0) - BSI.AlignLog2));
BitOffset = B.CreateOr(OffsetSHR, OffsetSHL);
}
/// Given a disjoint set of bitsets and globals, layout the globals, build the
/// bit sets and lower the llvm.bitset.test calls.
-void LowerBitSets::buildBitSetsFromGlobals(
- const std::vector<MDString *> &BitSets,
- const std::vector<GlobalVariable *> &Globals) {
+void LowerBitSets::buildBitSetsFromGlobalVariables(
+ ArrayRef<Metadata *> BitSets, ArrayRef<GlobalVariable *> Globals) {
// Build a new global with the combined contents of the referenced globals.
+ // This global is a struct whose even-indexed elements contain the original
+ // contents of the referenced globals and whose odd-indexed elements contain
+ // any padding required to align the next element to the next power of 2.
std::vector<Constant *> GlobalInits;
+ const DataLayout &DL = M->getDataLayout();
for (GlobalVariable *G : Globals) {
GlobalInits.push_back(G->getInitializer());
- uint64_t InitSize = DL->getTypeAllocSize(G->getInitializer()->getType());
+ uint64_t InitSize = DL.getTypeAllocSize(G->getValueType());
- // Compute the amount of padding required to align the next element to the
- // next power of 2.
+ // Compute the amount of padding required.
uint64_t Padding = NextPowerOf2(InitSize - 1) - InitSize;
// Cap at 128 was found experimentally to have a good data/instruction
if (!GlobalInits.empty())
GlobalInits.pop_back();
Constant *NewInit = ConstantStruct::getAnon(M->getContext(), GlobalInits);
- auto CombinedGlobal =
+ auto *CombinedGlobal =
new GlobalVariable(*M, NewInit->getType(), /*isConstant=*/true,
GlobalValue::PrivateLinkage, NewInit);
- const StructLayout *CombinedGlobalLayout =
- DL->getStructLayout(cast<StructType>(NewInit->getType()));
+ StructType *NewTy = cast<StructType>(NewInit->getType());
+ const StructLayout *CombinedGlobalLayout = DL.getStructLayout(NewTy);
// Compute the offsets of the original globals within the new global.
- DenseMap<GlobalVariable *, uint64_t> GlobalLayout;
+ DenseMap<GlobalObject *, uint64_t> GlobalLayout;
for (unsigned I = 0; I != Globals.size(); ++I)
// Multiply by 2 to account for padding elements.
GlobalLayout[Globals[I]] = CombinedGlobalLayout->getElementOffset(I * 2);
+ lowerBitSetCalls(BitSets, CombinedGlobal, GlobalLayout);
+
+ // Build aliases pointing to offsets into the combined global for each
+ // global from which we built the combined global, and replace references
+ // to the original globals with references to the aliases.
+ for (unsigned I = 0; I != Globals.size(); ++I) {
+ // Multiply by 2 to account for padding elements.
+ Constant *CombinedGlobalIdxs[] = {ConstantInt::get(Int32Ty, 0),
+ ConstantInt::get(Int32Ty, I * 2)};
+ Constant *CombinedGlobalElemPtr = ConstantExpr::getGetElementPtr(
+ NewInit->getType(), CombinedGlobal, CombinedGlobalIdxs);
+ if (LinkerSubsectionsViaSymbols) {
+ Globals[I]->replaceAllUsesWith(CombinedGlobalElemPtr);
+ } else {
+ assert(Globals[I]->getType()->getAddressSpace() == 0);
+ GlobalAlias *GAlias = GlobalAlias::create(NewTy->getElementType(I * 2), 0,
+ Globals[I]->getLinkage(), "",
+ CombinedGlobalElemPtr, M);
+ GAlias->setVisibility(Globals[I]->getVisibility());
+ GAlias->takeName(Globals[I]);
+ Globals[I]->replaceAllUsesWith(GAlias);
+ }
+ Globals[I]->eraseFromParent();
+ }
+}
+
+void LowerBitSets::lowerBitSetCalls(
+ ArrayRef<Metadata *> BitSets, Constant *CombinedGlobalAddr,
+ const DenseMap<GlobalObject *, uint64_t> &GlobalLayout) {
+ Constant *CombinedGlobalIntAddr =
+ ConstantExpr::getPtrToInt(CombinedGlobalAddr, IntPtrTy);
+
// For each bitset in this disjoint set...
- for (MDString *BS : BitSets) {
+ for (Metadata *BS : BitSets) {
// Build the bitset.
BitSetInfo BSI = buildBitSet(BS, GlobalLayout);
+ DEBUG({
+ if (auto BSS = dyn_cast<MDString>(BS))
+ dbgs() << BSS->getString() << ": ";
+ else
+ dbgs() << "<unnamed>: ";
+ BSI.print(dbgs());
+ });
ByteArrayInfo *BAI = 0;
// Lower each call to llvm.bitset.test for this bitset.
for (CallInst *CI : BitSetTestCallSites[BS]) {
++NumBitSetCallsLowered;
- Value *Lowered = lowerBitSetCall(CI, BSI, BAI, CombinedGlobal, GlobalLayout);
+ Value *Lowered =
+ lowerBitSetCall(CI, BSI, BAI, CombinedGlobalIntAddr, GlobalLayout);
CI->replaceAllUsesWith(Lowered);
CI->eraseFromParent();
}
}
+}
- // Build aliases pointing to offsets into the combined global for each
- // global from which we built the combined global, and replace references
- // to the original globals with references to the aliases.
- for (unsigned I = 0; I != Globals.size(); ++I) {
- // Multiply by 2 to account for padding elements.
- Constant *CombinedGlobalIdxs[] = {ConstantInt::get(Int32Ty, 0),
- ConstantInt::get(Int32Ty, I * 2)};
- Constant *CombinedGlobalElemPtr =
- ConstantExpr::getGetElementPtr(CombinedGlobal, CombinedGlobalIdxs);
- GlobalAlias *GAlias = GlobalAlias::create(
- Globals[I]->getType()->getElementType(),
- Globals[I]->getType()->getAddressSpace(), Globals[I]->getLinkage(),
- "", CombinedGlobalElemPtr, M);
- GAlias->takeName(Globals[I]);
- Globals[I]->replaceAllUsesWith(GAlias);
- Globals[I]->eraseFromParent();
+void LowerBitSets::verifyBitSetMDNode(MDNode *Op) {
+ if (Op->getNumOperands() != 3)
+ report_fatal_error(
+ "All operands of llvm.bitsets metadata must have 3 elements");
+ if (!Op->getOperand(1))
+ return;
+
+ auto OpConstMD = dyn_cast<ConstantAsMetadata>(Op->getOperand(1));
+ if (!OpConstMD)
+ report_fatal_error("Bit set element must be a constant");
+ auto OpGlobal = dyn_cast<GlobalObject>(OpConstMD->getValue());
+ if (!OpGlobal)
+ return;
+
+ if (OpGlobal->isThreadLocal())
+ report_fatal_error("Bit set element may not be thread-local");
+ if (OpGlobal->hasSection())
+ report_fatal_error("Bit set element may not have an explicit section");
+
+ if (isa<GlobalVariable>(OpGlobal) && OpGlobal->isDeclarationForLinker())
+ report_fatal_error("Bit set global var element must be a definition");
+
+ auto OffsetConstMD = dyn_cast<ConstantAsMetadata>(Op->getOperand(2));
+ if (!OffsetConstMD)
+ report_fatal_error("Bit set element offset must be a constant");
+ auto OffsetInt = dyn_cast<ConstantInt>(OffsetConstMD->getValue());
+ if (!OffsetInt)
+ report_fatal_error("Bit set element offset must be an integer constant");
+}
+
+static const unsigned kX86JumpTableEntrySize = 8;
+
+unsigned LowerBitSets::getJumpTableEntrySize() {
+ if (Arch != Triple::x86 && Arch != Triple::x86_64)
+ report_fatal_error("Unsupported architecture for jump tables");
+
+ return kX86JumpTableEntrySize;
+}
+
+// Create a constant representing a jump table entry for the target. This
+// consists of an instruction sequence containing a relative branch to Dest. The
+// constant will be laid out at address Src+(Len*Distance) where Len is the
+// target-specific jump table entry size.
+Constant *LowerBitSets::createJumpTableEntry(GlobalObject *Src, Function *Dest,
+ unsigned Distance) {
+ if (Arch != Triple::x86 && Arch != Triple::x86_64)
+ report_fatal_error("Unsupported architecture for jump tables");
+
+ const unsigned kJmpPCRel32Code = 0xe9;
+ const unsigned kInt3Code = 0xcc;
+
+ ConstantInt *Jmp = ConstantInt::get(Int8Ty, kJmpPCRel32Code);
+
+ // Build a constant representing the displacement between the constant's
+ // address and Dest. This will resolve to a PC32 relocation referring to Dest.
+ Constant *DestInt = ConstantExpr::getPtrToInt(Dest, IntPtrTy);
+ Constant *SrcInt = ConstantExpr::getPtrToInt(Src, IntPtrTy);
+ Constant *Disp = ConstantExpr::getSub(DestInt, SrcInt);
+ ConstantInt *DispOffset =
+ ConstantInt::get(IntPtrTy, Distance * kX86JumpTableEntrySize + 5);
+ Constant *OffsetedDisp = ConstantExpr::getSub(Disp, DispOffset);
+ OffsetedDisp = ConstantExpr::getTrunc(OffsetedDisp, Int32Ty);
+
+ ConstantInt *Int3 = ConstantInt::get(Int8Ty, kInt3Code);
+
+ Constant *Fields[] = {
+ Jmp, OffsetedDisp, Int3, Int3, Int3,
+ };
+ return ConstantStruct::getAnon(Fields, /*Packed=*/true);
+}
+
+Type *LowerBitSets::getJumpTableEntryType() {
+ if (Arch != Triple::x86 && Arch != Triple::x86_64)
+ report_fatal_error("Unsupported architecture for jump tables");
+
+ return StructType::get(M->getContext(),
+ {Int8Ty, Int32Ty, Int8Ty, Int8Ty, Int8Ty},
+ /*Packed=*/true);
+}
+
+/// Given a disjoint set of bitsets and functions, build a jump table for the
+/// functions, build the bit sets and lower the llvm.bitset.test calls.
+void LowerBitSets::buildBitSetsFromFunctions(ArrayRef<Metadata *> BitSets,
+ ArrayRef<Function *> Functions) {
+ // Unlike the global bitset builder, the function bitset builder cannot
+ // re-arrange functions in a particular order and base its calculations on the
+ // layout of the functions' entry points, as we have no idea how large a
+ // particular function will end up being (the size could even depend on what
+ // this pass does!) Instead, we build a jump table, which is a block of code
+ // consisting of one branch instruction for each of the functions in the bit
+ // set that branches to the target function, and redirect any taken function
+ // addresses to the corresponding jump table entry. In the object file's
+ // symbol table, the symbols for the target functions also refer to the jump
+ // table entries, so that addresses taken outside the module will pass any
+ // verification done inside the module.
+ //
+ // In more concrete terms, suppose we have three functions f, g, h which are
+ // members of a single bitset, and a function foo that returns their
+ // addresses:
+ //
+ // f:
+ // mov 0, %eax
+ // ret
+ //
+ // g:
+ // mov 1, %eax
+ // ret
+ //
+ // h:
+ // mov 2, %eax
+ // ret
+ //
+ // foo:
+ // mov f, %eax
+ // mov g, %edx
+ // mov h, %ecx
+ // ret
+ //
+ // To create a jump table for these functions, we instruct the LLVM code
+ // generator to output a jump table in the .text section. This is done by
+ // representing the instructions in the jump table as an LLVM constant and
+ // placing them in a global variable in the .text section. The end result will
+ // (conceptually) look like this:
+ //
+ // f:
+ // jmp .Ltmp0 ; 5 bytes
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ //
+ // g:
+ // jmp .Ltmp1 ; 5 bytes
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ //
+ // h:
+ // jmp .Ltmp2 ; 5 bytes
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ // int3 ; 1 byte
+ //
+ // .Ltmp0:
+ // mov 0, %eax
+ // ret
+ //
+ // .Ltmp1:
+ // mov 1, %eax
+ // ret
+ //
+ // .Ltmp2:
+ // mov 2, %eax
+ // ret
+ //
+ // foo:
+ // mov f, %eax
+ // mov g, %edx
+ // mov h, %ecx
+ // ret
+ //
+ // Because the addresses of f, g, h are evenly spaced at a power of 2, in the
+ // normal case the check can be carried out using the same kind of simple
+ // arithmetic that we normally use for globals.
+
+ assert(!Functions.empty());
+
+ // Build a simple layout based on the regular layout of jump tables.
+ DenseMap<GlobalObject *, uint64_t> GlobalLayout;
+ unsigned EntrySize = getJumpTableEntrySize();
+ for (unsigned I = 0; I != Functions.size(); ++I)
+ GlobalLayout[Functions[I]] = I * EntrySize;
+
+ // Create a constant to hold the jump table.
+ ArrayType *JumpTableType =
+ ArrayType::get(getJumpTableEntryType(), Functions.size());
+ auto JumpTable = new GlobalVariable(*M, JumpTableType,
+ /*isConstant=*/true,
+ GlobalValue::PrivateLinkage, nullptr);
+ JumpTable->setSection(ObjectFormat == Triple::MachO
+ ? "__TEXT,__text,regular,pure_instructions"
+ : ".text");
+ lowerBitSetCalls(BitSets, JumpTable, GlobalLayout);
+
+ // Build aliases pointing to offsets into the jump table, and replace
+ // references to the original functions with references to the aliases.
+ for (unsigned I = 0; I != Functions.size(); ++I) {
+ Constant *CombinedGlobalElemPtr = ConstantExpr::getBitCast(
+ ConstantExpr::getGetElementPtr(
+ JumpTableType, JumpTable,
+ ArrayRef<Constant *>{ConstantInt::get(IntPtrTy, 0),
+ ConstantInt::get(IntPtrTy, I)}),
+ Functions[I]->getType());
+ if (LinkerSubsectionsViaSymbols || Functions[I]->isDeclarationForLinker()) {
+ Functions[I]->replaceAllUsesWith(CombinedGlobalElemPtr);
+ } else {
+ assert(Functions[I]->getType()->getAddressSpace() == 0);
+ GlobalAlias *GAlias = GlobalAlias::create(Functions[I]->getValueType(), 0,
+ Functions[I]->getLinkage(), "",
+ CombinedGlobalElemPtr, M);
+ GAlias->setVisibility(Functions[I]->getVisibility());
+ GAlias->takeName(Functions[I]);
+ Functions[I]->replaceAllUsesWith(GAlias);
+ }
+ if (!Functions[I]->isDeclarationForLinker())
+ Functions[I]->setLinkage(GlobalValue::PrivateLinkage);
+ }
+
+ // Build and set the jump table's initializer.
+ std::vector<Constant *> JumpTableEntries;
+ for (unsigned I = 0; I != Functions.size(); ++I)
+ JumpTableEntries.push_back(
+ createJumpTableEntry(JumpTable, Functions[I], I));
+ JumpTable->setInitializer(
+ ConstantArray::get(JumpTableType, JumpTableEntries));
+}
+
+void LowerBitSets::buildBitSetsFromDisjointSet(
+ ArrayRef<Metadata *> BitSets, ArrayRef<GlobalObject *> Globals) {
+ llvm::DenseMap<Metadata *, uint64_t> BitSetIndices;
+ llvm::DenseMap<GlobalObject *, uint64_t> GlobalIndices;
+ for (unsigned I = 0; I != BitSets.size(); ++I)
+ BitSetIndices[BitSets[I]] = I;
+ for (unsigned I = 0; I != Globals.size(); ++I)
+ GlobalIndices[Globals[I]] = I;
+
+ // For each bitset, build a set of indices that refer to globals referenced by
+ // the bitset.
+ std::vector<std::set<uint64_t>> BitSetMembers(BitSets.size());
+ if (BitSetNM) {
+ for (MDNode *Op : BitSetNM->operands()) {
+ // Op = { bitset name, global, offset }
+ if (!Op->getOperand(1))
+ continue;
+ auto I = BitSetIndices.find(Op->getOperand(0));
+ if (I == BitSetIndices.end())
+ continue;
+
+ auto OpGlobal = dyn_cast<GlobalObject>(
+ cast<ConstantAsMetadata>(Op->getOperand(1))->getValue());
+ if (!OpGlobal)
+ continue;
+ BitSetMembers[I->second].insert(GlobalIndices[OpGlobal]);
+ }
+ }
+
+ // Order the sets of indices by size. The GlobalLayoutBuilder works best
+ // when given small index sets first.
+ std::stable_sort(
+ BitSetMembers.begin(), BitSetMembers.end(),
+ [](const std::set<uint64_t> &O1, const std::set<uint64_t> &O2) {
+ return O1.size() < O2.size();
+ });
+
+ // Create a GlobalLayoutBuilder and provide it with index sets as layout
+ // fragments. The GlobalLayoutBuilder tries to lay out members of fragments as
+ // close together as possible.
+ GlobalLayoutBuilder GLB(Globals.size());
+ for (auto &&MemSet : BitSetMembers)
+ GLB.addFragment(MemSet);
+
+ // Build the bitsets from this disjoint set.
+ if (Globals.empty() || isa<GlobalVariable>(Globals[0])) {
+ // Build a vector of global variables with the computed layout.
+ std::vector<GlobalVariable *> OrderedGVs(Globals.size());
+ auto OGI = OrderedGVs.begin();
+ for (auto &&F : GLB.Fragments) {
+ for (auto &&Offset : F) {
+ auto GV = dyn_cast<GlobalVariable>(Globals[Offset]);
+ if (!GV)
+ report_fatal_error(
+ "Bit set may not contain both global variables and functions");
+ *OGI++ = GV;
+ }
+ }
+
+ buildBitSetsFromGlobalVariables(BitSets, OrderedGVs);
+ } else {
+ // Build a vector of functions with the computed layout.
+ std::vector<Function *> OrderedFns(Globals.size());
+ auto OFI = OrderedFns.begin();
+ for (auto &&F : GLB.Fragments) {
+ for (auto &&Offset : F) {
+ auto Fn = dyn_cast<Function>(Globals[Offset]);
+ if (!Fn)
+ report_fatal_error(
+ "Bit set may not contain both global variables and functions");
+ *OFI++ = Fn;
+ }
+ }
+
+ buildBitSetsFromFunctions(BitSets, OrderedFns);
}
}
// Equivalence class set containing bitsets and the globals they reference.
// This is used to partition the set of bitsets in the module into disjoint
// sets.
- typedef EquivalenceClasses<PointerUnion<GlobalVariable *, MDString *>>
+ typedef EquivalenceClasses<PointerUnion<GlobalObject *, Metadata *>>
GlobalClassesTy;
GlobalClassesTy GlobalClasses;
+ // Verify the bitset metadata and build a mapping from bitset identifiers to
+ // their last observed index in BitSetNM. This will used later to
+ // deterministically order the list of bitset identifiers.
+ llvm::DenseMap<Metadata *, unsigned> BitSetIdIndices;
+ if (BitSetNM) {
+ for (unsigned I = 0, E = BitSetNM->getNumOperands(); I != E; ++I) {
+ MDNode *Op = BitSetNM->getOperand(I);
+ verifyBitSetMDNode(Op);
+ BitSetIdIndices[Op->getOperand(0)] = I;
+ }
+ }
+
for (const Use &U : BitSetTestFunc->uses()) {
auto CI = cast<CallInst>(U.getUser());
auto BitSetMDVal = dyn_cast<MetadataAsValue>(CI->getArgOperand(1));
- if (!BitSetMDVal || !isa<MDString>(BitSetMDVal->getMetadata()))
+ if (!BitSetMDVal)
report_fatal_error(
- "Second argument of llvm.bitset.test must be metadata string");
- auto BitSet = cast<MDString>(BitSetMDVal->getMetadata());
+ "Second argument of llvm.bitset.test must be metadata");
+ auto BitSet = BitSetMDVal->getMetadata();
// Add the call site to the list of call sites for this bit set. We also use
// BitSetTestCallSites to keep track of whether we have seen this bit set
// before. If we have, we don't need to re-add the referenced globals to the
// equivalence class.
- std::pair<DenseMap<MDString *, std::vector<CallInst *>>::iterator,
+ std::pair<DenseMap<Metadata *, std::vector<CallInst *>>::iterator,
bool> Ins =
BitSetTestCallSites.insert(
std::make_pair(BitSet, std::vector<CallInst *>()));
if (!BitSetNM)
continue;
- // Verify the bitset metadata and add the referenced globals to the bitset's
- // equivalence class.
+ // Add the referenced globals to the bitset's equivalence class.
for (MDNode *Op : BitSetNM->operands()) {
- if (Op->getNumOperands() != 3)
- report_fatal_error(
- "All operands of llvm.bitsets metadata must have 3 elements");
-
if (Op->getOperand(0) != BitSet || !Op->getOperand(1))
continue;
- auto OpConstMD = dyn_cast<ConstantAsMetadata>(Op->getOperand(1));
- if (!OpConstMD)
- report_fatal_error("Bit set element must be a constant");
- auto OpGlobal = dyn_cast<GlobalVariable>(OpConstMD->getValue());
+ auto OpGlobal = dyn_cast<GlobalObject>(
+ cast<ConstantAsMetadata>(Op->getOperand(1))->getValue());
if (!OpGlobal)
- report_fatal_error("Bit set element must refer to global");
-
- auto OffsetConstMD = dyn_cast<ConstantAsMetadata>(Op->getOperand(2));
- if (!OffsetConstMD)
- report_fatal_error("Bit set element offset must be a constant");
- auto OffsetInt = dyn_cast<ConstantInt>(OffsetConstMD->getValue());
- if (!OffsetInt)
- report_fatal_error(
- "Bit set element offset must be an integer constant");
+ continue;
CurSet = GlobalClasses.unionSets(
CurSet, GlobalClasses.findLeader(GlobalClasses.insert(OpGlobal)));
if (GlobalClasses.empty())
return false;
- // For each disjoint set we found...
+ // Build a list of disjoint sets ordered by their maximum BitSetNM index
+ // for determinism.
+ std::vector<std::pair<GlobalClassesTy::iterator, unsigned>> Sets;
for (GlobalClassesTy::iterator I = GlobalClasses.begin(),
E = GlobalClasses.end();
I != E; ++I) {
if (!I->isLeader()) continue;
-
++NumBitSetDisjointSets;
- // Build the list of bitsets and referenced globals in this disjoint set.
- std::vector<MDString *> BitSets;
- std::vector<GlobalVariable *> Globals;
- llvm::DenseMap<MDString *, uint64_t> BitSetIndices;
- llvm::DenseMap<GlobalVariable *, uint64_t> GlobalIndices;
+ unsigned MaxIndex = 0;
for (GlobalClassesTy::member_iterator MI = GlobalClasses.member_begin(I);
MI != GlobalClasses.member_end(); ++MI) {
- if ((*MI).is<MDString *>()) {
- BitSetIndices[MI->get<MDString *>()] = BitSets.size();
- BitSets.push_back(MI->get<MDString *>());
- } else {
- GlobalIndices[MI->get<GlobalVariable *>()] = Globals.size();
- Globals.push_back(MI->get<GlobalVariable *>());
- }
+ if ((*MI).is<Metadata *>())
+ MaxIndex = std::max(MaxIndex, BitSetIdIndices[MI->get<Metadata *>()]);
}
+ Sets.emplace_back(I, MaxIndex);
+ }
+ std::sort(Sets.begin(), Sets.end(),
+ [](const std::pair<GlobalClassesTy::iterator, unsigned> &S1,
+ const std::pair<GlobalClassesTy::iterator, unsigned> &S2) {
+ return S1.second < S2.second;
+ });
- // For each bitset, build a set of indices that refer to globals referenced
- // by the bitset.
- std::vector<std::set<uint64_t>> BitSetMembers(BitSets.size());
- if (BitSetNM) {
- for (MDNode *Op : BitSetNM->operands()) {
- // Op = { bitset name, global, offset }
- if (!Op->getOperand(1))
- continue;
- auto I = BitSetIndices.find(cast<MDString>(Op->getOperand(0)));
- if (I == BitSetIndices.end())
- continue;
-
- auto OpGlobal = cast<GlobalVariable>(
- cast<ConstantAsMetadata>(Op->getOperand(1))->getValue());
- BitSetMembers[I->second].insert(GlobalIndices[OpGlobal]);
- }
+ // For each disjoint set we found...
+ for (const auto &S : Sets) {
+ // Build the list of bitsets in this disjoint set.
+ std::vector<Metadata *> BitSets;
+ std::vector<GlobalObject *> Globals;
+ for (GlobalClassesTy::member_iterator MI =
+ GlobalClasses.member_begin(S.first);
+ MI != GlobalClasses.member_end(); ++MI) {
+ if ((*MI).is<Metadata *>())
+ BitSets.push_back(MI->get<Metadata *>());
+ else
+ Globals.push_back(MI->get<GlobalObject *>());
}
- // Order the sets of indices by size. The GlobalLayoutBuilder works best
- // when given small index sets first.
- std::stable_sort(
- BitSetMembers.begin(), BitSetMembers.end(),
- [](const std::set<uint64_t> &O1, const std::set<uint64_t> &O2) {
- return O1.size() < O2.size();
- });
-
- // Create a GlobalLayoutBuilder and provide it with index sets as layout
- // fragments. The GlobalLayoutBuilder tries to lay out members of fragments
- // as close together as possible.
- GlobalLayoutBuilder GLB(Globals.size());
- for (auto &&MemSet : BitSetMembers)
- GLB.addFragment(MemSet);
-
- // Build a vector of globals with the computed layout.
- std::vector<GlobalVariable *> OrderedGlobals(Globals.size());
- auto OGI = OrderedGlobals.begin();
- for (auto &&F : GLB.Fragments)
- for (auto &&Offset : F)
- *OGI++ = Globals[Offset];
-
- // Order bitsets by name for determinism.
- std::sort(BitSets.begin(), BitSets.end(), [](MDString *S1, MDString *S2) {
- return S1->getString() < S2->getString();
+ // Order bitsets by BitSetNM index for determinism. This ordering is stable
+ // as there is a one-to-one mapping between metadata and indices.
+ std::sort(BitSets.begin(), BitSets.end(), [&](Metadata *M1, Metadata *M2) {
+ return BitSetIdIndices[M1] < BitSetIdIndices[M2];
});
- // Build the bitsets from this disjoint set.
- buildBitSetsFromGlobals(BitSets, OrderedGlobals);
+ // Lower the bitsets in this disjoint set.
+ buildBitSetsFromDisjointSet(BitSets, Globals);
}
allocateByteArrays();
projects / oota-llvm.git / blobdiff