AFLplusplus/instrumentation/SanitizerCoveragePCGUARD.so.cc
2024-01-18 17:12:09 +01:00

1301 lines
42 KiB
C++

//===-- SanitizerCoverage.cpp - coverage instrumentation for sanitizers ---===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// Coverage instrumentation done on LLVM IR level, works with Sanitizers.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Instrumentation/SanitizerCoverage.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallVector.h"
#if LLVM_VERSION_MAJOR >= 15
#if LLVM_VERSION_MAJOR < 17
#include "llvm/ADT/Triple.h"
#endif
#endif
#include "llvm/Analysis/PostDominators.h"
#if LLVM_VERSION_MAJOR < 15
#include "llvm/IR/CFG.h"
#endif
#include "llvm/IR/Constant.h"
#include "llvm/IR/DataLayout.h"
#if LLVM_VERSION_MAJOR < 15
#include "llvm/IR/DebugInfo.h"
#endif
#include "llvm/IR/Dominators.h"
#if LLVM_VERSION_MAJOR >= 17
#include "llvm/IR/EHPersonalities.h"
#else
#include "llvm/Analysis/EHPersonalities.h"
#endif
#include "llvm/IR/Function.h"
#if LLVM_VERSION_MAJOR >= 16
#include "llvm/IR/GlobalVariable.h"
#endif
#include "llvm/IR/IRBuilder.h"
#if LLVM_VERSION_MAJOR < 15
#include "llvm/IR/InlineAsm.h"
#endif
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#if LLVM_VERSION_MAJOR < 15
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Mangler.h"
#endif
#include "llvm/IR/Module.h"
#include "llvm/IR/PassManager.h"
#include "llvm/Passes/PassBuilder.h"
#include "llvm/Passes/PassPlugin.h"
#include "llvm/IR/Type.h"
#if LLVM_VERSION_MAJOR < 17
#include "llvm/InitializePasses.h"
#endif
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/SpecialCaseList.h"
#include "llvm/Support/VirtualFileSystem.h"
#if LLVM_VERSION_MAJOR < 15
#include "llvm/Support/raw_ostream.h"
#endif
#if LLVM_VERSION_MAJOR < 17
#include "llvm/Transforms/Instrumentation.h"
#else
#include "llvm/TargetParser/Triple.h"
#endif
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
#include "config.h"
#include "debug.h"
#include "afl-llvm-common.h"
using namespace llvm;
#define DEBUG_TYPE "sancov"
static const uint64_t SanCtorAndDtorPriority = 2;
const char SanCovTracePCName[] = "__sanitizer_cov_trace_pc";
const char SanCovTraceCmp1[] = "__sanitizer_cov_trace_cmp1";
const char SanCovTraceCmp2[] = "__sanitizer_cov_trace_cmp2";
const char SanCovTraceCmp4[] = "__sanitizer_cov_trace_cmp4";
const char SanCovTraceCmp8[] = "__sanitizer_cov_trace_cmp8";
const char SanCovTraceConstCmp1[] = "__sanitizer_cov_trace_const_cmp1";
const char SanCovTraceConstCmp2[] = "__sanitizer_cov_trace_const_cmp2";
const char SanCovTraceConstCmp4[] = "__sanitizer_cov_trace_const_cmp4";
const char SanCovTraceConstCmp8[] = "__sanitizer_cov_trace_const_cmp8";
const char SanCovTraceSwitchName[] = "__sanitizer_cov_trace_switch";
const char SanCovModuleCtorTracePcGuardName[] =
"sancov.module_ctor_trace_pc_guard";
const char SanCovTracePCGuardInitName[] = "__sanitizer_cov_trace_pc_guard_init";
const char SanCovTracePCGuardName[] = "__sanitizer_cov_trace_pc_guard";
const char SanCovGuardsSectionName[] = "sancov_guards";
const char SanCovCountersSectionName[] = "sancov_cntrs";
const char SanCovBoolFlagSectionName[] = "sancov_bools";
const char SanCovPCsSectionName[] = "sancov_pcs";
const char SanCovLowestStackName[] = "__sancov_lowest_stack";
static const char *skip_nozero;
static const char *use_threadsafe_counters;
namespace {
SanitizerCoverageOptions OverrideFromCL(SanitizerCoverageOptions Options) {
Options.CoverageType = SanitizerCoverageOptions::SCK_Edge;
// Options.NoPrune = true;
Options.TracePCGuard = true; // TracePCGuard is default.
return Options;
}
using DomTreeCallback = function_ref<const DominatorTree *(Function &F)>;
using PostDomTreeCallback =
function_ref<const PostDominatorTree *(Function &F)>;
class ModuleSanitizerCoverageAFL
: public PassInfoMixin<ModuleSanitizerCoverageAFL> {
public:
ModuleSanitizerCoverageAFL(
const SanitizerCoverageOptions &Options = SanitizerCoverageOptions())
: Options(OverrideFromCL(Options)) {
}
PreservedAnalyses run(Module &M, ModuleAnalysisManager &MAM);
bool instrumentModule(Module &M, DomTreeCallback DTCallback,
PostDomTreeCallback PDTCallback);
private:
void instrumentFunction(Function &F, DomTreeCallback DTCallback,
PostDomTreeCallback PDTCallback);
void InjectTraceForCmp(Function &F, ArrayRef<Instruction *> CmpTraceTargets);
void InjectTraceForSwitch(Function &F,
ArrayRef<Instruction *> SwitchTraceTargets);
bool InjectCoverage(Function &F, ArrayRef<BasicBlock *> AllBlocks,
bool IsLeafFunc = true);
GlobalVariable *CreateFunctionLocalArrayInSection(size_t NumElements,
Function &F, Type *Ty,
const char *Section);
GlobalVariable *CreatePCArray(Function &F, ArrayRef<BasicBlock *> AllBlocks);
void CreateFunctionLocalArrays(Function &F, ArrayRef<BasicBlock *> AllBlocks,
uint32_t special);
void InjectCoverageAtBlock(Function &F, BasicBlock &BB, size_t Idx,
bool IsLeafFunc = true);
Function *CreateInitCallsForSections(Module &M, const char *CtorName,
const char *InitFunctionName, Type *Ty,
const char *Section);
std::pair<Value *, Value *> CreateSecStartEnd(Module &M, const char *Section,
Type *Ty);
void SetNoSanitizeMetadata(Instruction *I) {
#if LLVM_VERSION_MAJOR >= 16
I->setMetadata(LLVMContext::MD_nosanitize, MDNode::get(*C, std::nullopt));
#else
I->setMetadata(I->getModule()->getMDKindID("nosanitize"),
MDNode::get(*C, None));
#endif
}
std::string getSectionName(const std::string &Section) const;
std::string getSectionStart(const std::string &Section) const;
std::string getSectionEnd(const std::string &Section) const;
FunctionCallee SanCovTracePC, SanCovTracePCGuard;
FunctionCallee SanCovTraceCmpFunction[4];
FunctionCallee SanCovTraceConstCmpFunction[4];
FunctionCallee SanCovTraceSwitchFunction;
GlobalVariable *SanCovLowestStack;
Type *IntptrTy, *IntptrPtrTy, *Int64Ty, *Int64PtrTy, *Int32Ty, *Int32PtrTy,
*Int16Ty, *Int8Ty, *Int8PtrTy, *Int1Ty, *Int1PtrTy;
Module *CurModule;
std::string CurModuleUniqueId;
Triple TargetTriple;
LLVMContext *C;
const DataLayout *DL;
GlobalVariable *FunctionGuardArray; // for trace-pc-guard.
GlobalVariable *Function8bitCounterArray; // for inline-8bit-counters.
GlobalVariable *FunctionBoolArray; // for inline-bool-flag.
GlobalVariable *FunctionPCsArray; // for pc-table.
SmallVector<GlobalValue *, 20> GlobalsToAppendToUsed;
SmallVector<GlobalValue *, 20> GlobalsToAppendToCompilerUsed;
SanitizerCoverageOptions Options;
uint32_t instr = 0, selects = 0, unhandled = 0;
GlobalVariable *AFLMapPtr = NULL;
ConstantInt *One = NULL;
ConstantInt *Zero = NULL;
};
} // namespace
extern "C" ::llvm::PassPluginLibraryInfo LLVM_ATTRIBUTE_WEAK
llvmGetPassPluginInfo() {
return {LLVM_PLUGIN_API_VERSION, "SanitizerCoveragePCGUARD", "v0.2",
/* lambda to insert our pass into the pass pipeline. */
[](PassBuilder &PB) {
#if LLVM_VERSION_MAJOR == 13
using OptimizationLevel = typename PassBuilder::OptimizationLevel;
#endif
#if LLVM_VERSION_MAJOR >= 16
PB.registerOptimizerEarlyEPCallback(
#else
PB.registerOptimizerLastEPCallback(
#endif
[](ModulePassManager &MPM, OptimizationLevel OL) {
MPM.addPass(ModuleSanitizerCoverageAFL());
});
}};
}
PreservedAnalyses ModuleSanitizerCoverageAFL::run(Module &M,
ModuleAnalysisManager &MAM) {
ModuleSanitizerCoverageAFL ModuleSancov(Options);
auto &FAM = MAM.getResult<FunctionAnalysisManagerModuleProxy>(M).getManager();
auto DTCallback = [&FAM](Function &F) -> const DominatorTree *{
return &FAM.getResult<DominatorTreeAnalysis>(F);
};
auto PDTCallback = [&FAM](Function &F) -> const PostDominatorTree * {
return &FAM.getResult<PostDominatorTreeAnalysis>(F);
};
if (ModuleSancov.instrumentModule(M, DTCallback, PDTCallback))
return PreservedAnalyses::none();
return PreservedAnalyses::all();
}
std::pair<Value *, Value *> ModuleSanitizerCoverageAFL::CreateSecStartEnd(
Module &M, const char *Section, Type *Ty) {
// Use ExternalWeak so that if all sections are discarded due to section
// garbage collection, the linker will not report undefined symbol errors.
// Windows defines the start/stop symbols in compiler-rt so no need for
// ExternalWeak.
GlobalValue::LinkageTypes Linkage = TargetTriple.isOSBinFormatCOFF()
? GlobalVariable::ExternalLinkage
: GlobalVariable::ExternalWeakLinkage;
GlobalVariable *SecStart = new GlobalVariable(M, Ty, false, Linkage, nullptr,
getSectionStart(Section));
SecStart->setVisibility(GlobalValue::HiddenVisibility);
GlobalVariable *SecEnd = new GlobalVariable(M, Ty, false, Linkage, nullptr,
getSectionEnd(Section));
SecEnd->setVisibility(GlobalValue::HiddenVisibility);
IRBuilder<> IRB(M.getContext());
if (!TargetTriple.isOSBinFormatCOFF())
return std::make_pair(SecStart, SecEnd);
// Account for the fact that on windows-msvc __start_* symbols actually
// point to a uint64_t before the start of the array.
auto SecStartI8Ptr = IRB.CreatePointerCast(SecStart, Int8PtrTy);
auto GEP = IRB.CreateGEP(Int8Ty, SecStartI8Ptr,
ConstantInt::get(IntptrTy, sizeof(uint64_t)));
return std::make_pair(IRB.CreatePointerCast(GEP, PointerType::getUnqual(Ty)),
SecEnd);
}
Function *ModuleSanitizerCoverageAFL::CreateInitCallsForSections(
Module &M, const char *CtorName, const char *InitFunctionName, Type *Ty,
const char *Section) {
auto SecStartEnd = CreateSecStartEnd(M, Section, Ty);
auto SecStart = SecStartEnd.first;
auto SecEnd = SecStartEnd.second;
Function *CtorFunc;
Type *PtrTy = PointerType::getUnqual(Ty);
std::tie(CtorFunc, std::ignore) = createSanitizerCtorAndInitFunctions(
M, CtorName, InitFunctionName, {PtrTy, PtrTy}, {SecStart, SecEnd});
assert(CtorFunc->getName() == CtorName);
if (TargetTriple.supportsCOMDAT()) {
// Use comdat to dedup CtorFunc.
CtorFunc->setComdat(M.getOrInsertComdat(CtorName));
appendToGlobalCtors(M, CtorFunc, SanCtorAndDtorPriority, CtorFunc);
} else {
appendToGlobalCtors(M, CtorFunc, SanCtorAndDtorPriority);
}
if (TargetTriple.isOSBinFormatCOFF()) {
// In COFF files, if the contructors are set as COMDAT (they are because
// COFF supports COMDAT) and the linker flag /OPT:REF (strip unreferenced
// functions and data) is used, the constructors get stripped. To prevent
// this, give the constructors weak ODR linkage and ensure the linker knows
// to include the sancov constructor. This way the linker can deduplicate
// the constructors but always leave one copy.
CtorFunc->setLinkage(GlobalValue::WeakODRLinkage);
}
return CtorFunc;
}
bool ModuleSanitizerCoverageAFL::instrumentModule(
Module &M, DomTreeCallback DTCallback, PostDomTreeCallback PDTCallback) {
setvbuf(stdout, NULL, _IONBF, 0);
if (getenv("AFL_DEBUG")) { debug = 1; }
if ((isatty(2) && !getenv("AFL_QUIET")) || debug) {
SAYF(cCYA "SanitizerCoveragePCGUARD" VERSION cRST "\n");
} else {
be_quiet = 1;
}
skip_nozero = getenv("AFL_LLVM_SKIP_NEVERZERO");
use_threadsafe_counters = getenv("AFL_LLVM_THREADSAFE_INST");
initInstrumentList();
scanForDangerousFunctions(&M);
C = &(M.getContext());
DL = &M.getDataLayout();
CurModule = &M;
CurModuleUniqueId = getUniqueModuleId(CurModule);
TargetTriple = Triple(M.getTargetTriple());
FunctionGuardArray = nullptr;
Function8bitCounterArray = nullptr;
FunctionBoolArray = nullptr;
FunctionPCsArray = nullptr;
IntptrTy = Type::getIntNTy(*C, DL->getPointerSizeInBits());
IntptrPtrTy = PointerType::getUnqual(IntptrTy);
Type *VoidTy = Type::getVoidTy(*C);
IRBuilder<> IRB(*C);
Int64PtrTy = PointerType::getUnqual(IRB.getInt64Ty());
Int32PtrTy = PointerType::getUnqual(IRB.getInt32Ty());
Int8PtrTy = PointerType::getUnqual(IRB.getInt8Ty());
Int1PtrTy = PointerType::getUnqual(IRB.getInt1Ty());
Int64Ty = IRB.getInt64Ty();
Int32Ty = IRB.getInt32Ty();
Int16Ty = IRB.getInt16Ty();
Int8Ty = IRB.getInt8Ty();
Int1Ty = IRB.getInt1Ty();
LLVMContext &Ctx = M.getContext();
AFLMapPtr =
new GlobalVariable(M, PointerType::get(Int8Ty, 0), false,
GlobalValue::ExternalLinkage, 0, "__afl_area_ptr");
One = ConstantInt::get(IntegerType::getInt8Ty(Ctx), 1);
Zero = ConstantInt::get(IntegerType::getInt8Ty(Ctx), 0);
// Make sure smaller parameters are zero-extended to i64 if required by the
// target ABI.
AttributeList SanCovTraceCmpZeroExtAL;
SanCovTraceCmpZeroExtAL =
SanCovTraceCmpZeroExtAL.addParamAttribute(*C, 0, Attribute::ZExt);
SanCovTraceCmpZeroExtAL =
SanCovTraceCmpZeroExtAL.addParamAttribute(*C, 1, Attribute::ZExt);
SanCovTraceCmpFunction[0] =
M.getOrInsertFunction(SanCovTraceCmp1, SanCovTraceCmpZeroExtAL, VoidTy,
IRB.getInt8Ty(), IRB.getInt8Ty());
SanCovTraceCmpFunction[1] =
M.getOrInsertFunction(SanCovTraceCmp2, SanCovTraceCmpZeroExtAL, VoidTy,
IRB.getInt16Ty(), IRB.getInt16Ty());
SanCovTraceCmpFunction[2] =
M.getOrInsertFunction(SanCovTraceCmp4, SanCovTraceCmpZeroExtAL, VoidTy,
IRB.getInt32Ty(), IRB.getInt32Ty());
SanCovTraceCmpFunction[3] =
M.getOrInsertFunction(SanCovTraceCmp8, VoidTy, Int64Ty, Int64Ty);
SanCovTraceConstCmpFunction[0] = M.getOrInsertFunction(
SanCovTraceConstCmp1, SanCovTraceCmpZeroExtAL, VoidTy, Int8Ty, Int8Ty);
SanCovTraceConstCmpFunction[1] = M.getOrInsertFunction(
SanCovTraceConstCmp2, SanCovTraceCmpZeroExtAL, VoidTy, Int16Ty, Int16Ty);
SanCovTraceConstCmpFunction[2] = M.getOrInsertFunction(
SanCovTraceConstCmp4, SanCovTraceCmpZeroExtAL, VoidTy, Int32Ty, Int32Ty);
SanCovTraceConstCmpFunction[3] =
M.getOrInsertFunction(SanCovTraceConstCmp8, VoidTy, Int64Ty, Int64Ty);
SanCovTraceSwitchFunction =
M.getOrInsertFunction(SanCovTraceSwitchName, VoidTy, Int64Ty, Int64PtrTy);
Constant *SanCovLowestStackConstant =
M.getOrInsertGlobal(SanCovLowestStackName, IntptrTy);
SanCovLowestStack = dyn_cast<GlobalVariable>(SanCovLowestStackConstant);
if (!SanCovLowestStack || SanCovLowestStack->getValueType() != IntptrTy) {
C->emitError(StringRef("'") + SanCovLowestStackName +
"' should not be declared by the user");
return true;
}
SanCovLowestStack->setThreadLocalMode(
GlobalValue::ThreadLocalMode::InitialExecTLSModel);
SanCovTracePC = M.getOrInsertFunction(SanCovTracePCName, VoidTy);
SanCovTracePCGuard =
M.getOrInsertFunction(SanCovTracePCGuardName, VoidTy, Int32PtrTy);
for (auto &F : M)
instrumentFunction(F, DTCallback, PDTCallback);
Function *Ctor = nullptr;
if (FunctionGuardArray)
Ctor = CreateInitCallsForSections(M, SanCovModuleCtorTracePcGuardName,
SanCovTracePCGuardInitName, Int32PtrTy,
SanCovGuardsSectionName);
if (Ctor && debug) {
fprintf(stderr, "SANCOV: installed pcguard_init in ctor\n");
}
appendToUsed(M, GlobalsToAppendToUsed);
appendToCompilerUsed(M, GlobalsToAppendToCompilerUsed);
if (!be_quiet) {
if (!instr) {
WARNF("No instrumentation targets found.");
} else {
char modeline[128];
snprintf(modeline, sizeof(modeline), "%s%s%s%s%s%s",
getenv("AFL_HARDEN") ? "hardened" : "non-hardened",
getenv("AFL_USE_ASAN") ? ", ASAN" : "",
getenv("AFL_USE_MSAN") ? ", MSAN" : "",
getenv("AFL_USE_TSAN") ? ", TSAN" : "",
getenv("AFL_USE_CFISAN") ? ", CFISAN" : "",
getenv("AFL_USE_UBSAN") ? ", UBSAN" : "");
OKF("Instrumented %u locations with no collisions (%s mode) of which are "
"%u handled and %u unhandled selects.",
instr, modeline, selects, unhandled);
}
}
return true;
}
// True if block has successors and it dominates all of them.
static bool isFullDominator(const BasicBlock *BB, const DominatorTree *DT) {
if (succ_empty(BB)) return false;
return llvm::all_of(successors(BB), [&](const BasicBlock *SUCC) {
return DT->dominates(BB, SUCC);
});
}
// True if block has predecessors and it postdominates all of them.
static bool isFullPostDominator(const BasicBlock *BB,
const PostDominatorTree *PDT) {
if (pred_empty(BB)) return false;
return llvm::all_of(predecessors(BB), [&](const BasicBlock *PRED) {
return PDT->dominates(BB, PRED);
});
}
static bool shouldInstrumentBlock(const Function &F, const BasicBlock *BB,
const DominatorTree *DT,
const PostDominatorTree *PDT,
const SanitizerCoverageOptions &Options) {
// Don't insert coverage for blocks containing nothing but unreachable: we
// will never call __sanitizer_cov() for them, so counting them in
// NumberOfInstrumentedBlocks() might complicate calculation of code coverage
// percentage. Also, unreachable instructions frequently have no debug
// locations.
if (isa<UnreachableInst>(BB->getFirstNonPHIOrDbgOrLifetime())) return false;
// Don't insert coverage into blocks without a valid insertion point
// (catchswitch blocks).
if (BB->getFirstInsertionPt() == BB->end()) return false;
if (Options.NoPrune || &F.getEntryBlock() == BB) return true;
// Do not instrument full dominators, or full post-dominators with multiple
// predecessors.
return !isFullDominator(BB, DT) &&
!(isFullPostDominator(BB, PDT) && !BB->getSinglePredecessor());
}
// Returns true iff From->To is a backedge.
// A twist here is that we treat From->To as a backedge if
// * To dominates From or
// * To->UniqueSuccessor dominates From
#if 0
static bool IsBackEdge(BasicBlock *From, BasicBlock *To,
const DominatorTree *DT) {
if (DT->dominates(To, From))
return true;
if (auto Next = To->getUniqueSuccessor())
if (DT->dominates(Next, From))
return true;
return false;
}
#endif
// Prunes uninteresting Cmp instrumentation:
// * CMP instructions that feed into loop backedge branch.
//
// Note that Cmp pruning is controlled by the same flag as the
// BB pruning.
#if 0
static bool IsInterestingCmp(ICmpInst *CMP, const DominatorTree *DT,
const SanitizerCoverageOptions &Options) {
if (!Options.NoPrune)
if (CMP->hasOneUse())
if (auto BR = dyn_cast<BranchInst>(CMP->user_back()))
for (BasicBlock *B : BR->successors())
if (IsBackEdge(BR->getParent(), B, DT))
return false;
return true;
}
#endif
void ModuleSanitizerCoverageAFL::instrumentFunction(
Function &F, DomTreeCallback DTCallback, PostDomTreeCallback PDTCallback) {
if (F.empty()) return;
if (!isInInstrumentList(&F, FMNAME)) return;
if (F.getName().find(".module_ctor") != std::string::npos)
return; // Should not instrument sanitizer init functions.
#if LLVM_VERSION_MAJOR >= 18
if (F.getName().starts_with("__sanitizer_"))
#else
if (F.getName().startswith("__sanitizer_"))
#endif
return; // Don't instrument __sanitizer_* callbacks.
// Don't touch available_externally functions, their actual body is elewhere.
if (F.getLinkage() == GlobalValue::AvailableExternallyLinkage) return;
// Don't instrument MSVC CRT configuration helpers. They may run before normal
// initialization.
if (F.getName() == "__local_stdio_printf_options" ||
F.getName() == "__local_stdio_scanf_options")
return;
if (isa<UnreachableInst>(F.getEntryBlock().getTerminator())) return;
// Don't instrument functions using SEH for now. Splitting basic blocks like
// we do for coverage breaks WinEHPrepare.
// FIXME: Remove this when SEH no longer uses landingpad pattern matching.
if (F.hasPersonalityFn() &&
isAsynchronousEHPersonality(classifyEHPersonality(F.getPersonalityFn())))
return;
if (F.hasFnAttribute(Attribute::NoSanitizeCoverage)) return;
if (Options.CoverageType >= SanitizerCoverageOptions::SCK_Edge)
SplitAllCriticalEdges(
F, CriticalEdgeSplittingOptions().setIgnoreUnreachableDests());
SmallVector<BasicBlock *, 16> BlocksToInstrument;
SmallVector<Instruction *, 8> CmpTraceTargets;
SmallVector<Instruction *, 8> SwitchTraceTargets;
const DominatorTree *DT = DTCallback(F);
const PostDominatorTree *PDT = PDTCallback(F);
bool IsLeafFunc = true;
for (auto &BB : F) {
if (shouldInstrumentBlock(F, &BB, DT, PDT, Options))
BlocksToInstrument.push_back(&BB);
/*
for (auto &Inst : BB) {
if (Options.TraceCmp) {
if (ICmpInst *CMP = dyn_cast<ICmpInst>(&Inst))
if (IsInterestingCmp(CMP, DT, Options))
CmpTraceTargets.push_back(&Inst);
if (isa<SwitchInst>(&Inst))
SwitchTraceTargets.push_back(&Inst);
}
}
*/
}
if (debug) {
fprintf(stderr, "SanitizerCoveragePCGUARD: instrumenting %s in %s\n",
F.getName().str().c_str(), F.getParent()->getName().str().c_str());
}
InjectCoverage(F, BlocksToInstrument, IsLeafFunc);
// InjectTraceForCmp(F, CmpTraceTargets);
// InjectTraceForSwitch(F, SwitchTraceTargets);
}
GlobalVariable *ModuleSanitizerCoverageAFL::CreateFunctionLocalArrayInSection(
size_t NumElements, Function &F, Type *Ty, const char *Section) {
ArrayType *ArrayTy = ArrayType::get(Ty, NumElements);
auto Array = new GlobalVariable(
*CurModule, ArrayTy, false, GlobalVariable::PrivateLinkage,
Constant::getNullValue(ArrayTy), "__sancov_gen_");
if (TargetTriple.supportsCOMDAT() &&
(TargetTriple.isOSBinFormatELF() || !F.isInterposable()))
if (auto Comdat = getOrCreateFunctionComdat(F, TargetTriple))
Array->setComdat(Comdat);
Array->setSection(getSectionName(Section));
#if LLVM_VERSION_MAJOR >= 16
Array->setAlignment(Align(DL->getTypeStoreSize(Ty).getFixedValue()));
#else
Array->setAlignment(Align(DL->getTypeStoreSize(Ty).getFixedSize()));
#endif
// sancov_pcs parallels the other metadata section(s). Optimizers (e.g.
// GlobalOpt/ConstantMerge) may not discard sancov_pcs and the other
// section(s) as a unit, so we conservatively retain all unconditionally in
// the compiler.
//
// With comdat (COFF/ELF), the linker can guarantee the associated sections
// will be retained or discarded as a unit, so llvm.compiler.used is
// sufficient. Otherwise, conservatively make all of them retained by the
// linker.
if (Array->hasComdat())
GlobalsToAppendToCompilerUsed.push_back(Array);
else
GlobalsToAppendToUsed.push_back(Array);
return Array;
}
GlobalVariable *ModuleSanitizerCoverageAFL::CreatePCArray(
Function &F, ArrayRef<BasicBlock *> AllBlocks) {
size_t N = AllBlocks.size();
assert(N);
SmallVector<Constant *, 32> PCs;
IRBuilder<> IRB(&*F.getEntryBlock().getFirstInsertionPt());
for (size_t i = 0; i < N; i++) {
if (&F.getEntryBlock() == AllBlocks[i]) {
PCs.push_back((Constant *)IRB.CreatePointerCast(&F, IntptrPtrTy));
PCs.push_back((Constant *)IRB.CreateIntToPtr(
ConstantInt::get(IntptrTy, 1), IntptrPtrTy));
} else {
PCs.push_back((Constant *)IRB.CreatePointerCast(
BlockAddress::get(AllBlocks[i]), IntptrPtrTy));
#if LLVM_VERSION_MAJOR >= 16
PCs.push_back(Constant::getNullValue(IntptrPtrTy));
#else
PCs.push_back((Constant *)IRB.CreateIntToPtr(
ConstantInt::get(IntptrTy, 0), IntptrPtrTy));
#endif
}
}
auto *PCArray = CreateFunctionLocalArrayInSection(N * 2, F, IntptrPtrTy,
SanCovPCsSectionName);
PCArray->setInitializer(
ConstantArray::get(ArrayType::get(IntptrPtrTy, N * 2), PCs));
PCArray->setConstant(true);
return PCArray;
}
void ModuleSanitizerCoverageAFL::CreateFunctionLocalArrays(
Function &F, ArrayRef<BasicBlock *> AllBlocks, uint32_t special) {
if (Options.TracePCGuard)
FunctionGuardArray = CreateFunctionLocalArrayInSection(
AllBlocks.size() + special, F, Int32Ty, SanCovGuardsSectionName);
}
bool ModuleSanitizerCoverageAFL::InjectCoverage(
Function &F, ArrayRef<BasicBlock *> AllBlocks, bool IsLeafFunc) {
if (AllBlocks.empty()) return false;
uint32_t cnt_cov = 0, cnt_sel = 0, cnt_sel_inc = 0;
static uint32_t first = 1;
for (auto &BB : F) {
for (auto &IN : BB) {
CallInst *callInst = nullptr;
if ((callInst = dyn_cast<CallInst>(&IN))) {
Function *Callee = callInst->getCalledFunction();
if (!Callee) continue;
if (callInst->getCallingConv() != llvm::CallingConv::C) continue;
StringRef FuncName = Callee->getName();
if (!FuncName.compare(StringRef("dlopen")) ||
!FuncName.compare(StringRef("_dlopen"))) {
fprintf(stderr,
"WARNING: dlopen() detected. To have coverage for a library "
"that your target dlopen()'s this must either happen before "
"__AFL_INIT() or you must use AFL_PRELOAD to preload all "
"dlopen()'ed libraries!\n");
continue;
}
if (!FuncName.compare(StringRef("__afl_coverage_interesting"))) {
cnt_cov++;
}
}
SelectInst *selectInst = nullptr;
if ((selectInst = dyn_cast<SelectInst>(&IN))) {
Value *c = selectInst->getCondition();
auto t = c->getType();
if (t->getTypeID() == llvm::Type::IntegerTyID) {
cnt_sel++;
cnt_sel_inc += 2;
}
else if (t->getTypeID() == llvm::Type::FixedVectorTyID) {
FixedVectorType *tt = dyn_cast<FixedVectorType>(t);
if (tt) {
cnt_sel++;
cnt_sel_inc += (tt->getElementCount().getKnownMinValue() * 2);
}
}
}
}
}
CreateFunctionLocalArrays(F, AllBlocks, first + cnt_cov + cnt_sel_inc);
if (first) { first = 0; }
selects += cnt_sel;
uint32_t special = 0, local_selects = 0, skip_next = 0;
for (auto &BB : F) {
for (auto &IN : BB) {
CallInst *callInst = nullptr;
if ((callInst = dyn_cast<CallInst>(&IN))) {
Function *Callee = callInst->getCalledFunction();
if (!Callee) continue;
if (callInst->getCallingConv() != llvm::CallingConv::C) continue;
StringRef FuncName = Callee->getName();
if (FuncName.compare(StringRef("__afl_coverage_interesting"))) continue;
IRBuilder<> IRB(callInst);
if (!FunctionGuardArray) {
fprintf(stderr,
"SANCOV: FunctionGuardArray is NULL, failed to emit "
"instrumentation.");
continue;
}
Value *GuardPtr = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(IntptrTy, (++special + AllBlocks.size()) * 4)),
Int32PtrTy);
LoadInst *Idx = IRB.CreateLoad(IRB.getInt32Ty(), GuardPtr);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(Idx);
callInst->setOperand(1, Idx);
}
SelectInst *selectInst = nullptr;
if (!skip_next && (selectInst = dyn_cast<SelectInst>(&IN))) {
uint32_t vector_cnt = 0;
Value *condition = selectInst->getCondition();
Value *result;
auto t = condition->getType();
IRBuilder<> IRB(selectInst->getNextNode());
if (t->getTypeID() == llvm::Type::IntegerTyID) {
if (!FunctionGuardArray) {
fprintf(stderr,
"SANCOV: FunctionGuardArray is NULL, failed to emit "
"instrumentation.");
continue;
}
auto GuardPtr1 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(
IntptrTy,
(cnt_cov + local_selects++ + AllBlocks.size()) * 4)),
Int32PtrTy);
auto GuardPtr2 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(
IntptrTy,
(cnt_cov + local_selects++ + AllBlocks.size()) * 4)),
Int32PtrTy);
result = IRB.CreateSelect(condition, GuardPtr1, GuardPtr2);
} else
#if LLVM_VERSION_MAJOR >= 14
if (t->getTypeID() == llvm::Type::FixedVectorTyID) {
FixedVectorType *tt = dyn_cast<FixedVectorType>(t);
if (tt) {
uint32_t elements = tt->getElementCount().getFixedValue();
vector_cnt = elements;
if (elements) {
FixedVectorType *GuardPtr1 =
FixedVectorType::get(Int32PtrTy, elements);
FixedVectorType *GuardPtr2 =
FixedVectorType::get(Int32PtrTy, elements);
Value *x, *y;
if (!FunctionGuardArray) {
fprintf(stderr,
"SANCOV: FunctionGuardArray is NULL, failed to emit "
"instrumentation.");
continue;
}
Value *val1 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(
IntptrTy,
(cnt_cov + local_selects++ + AllBlocks.size()) * 4)),
Int32PtrTy);
x = IRB.CreateInsertElement(GuardPtr1, val1, (uint64_t)0);
Value *val2 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(
IntptrTy,
(cnt_cov + local_selects++ + AllBlocks.size()) * 4)),
Int32PtrTy);
y = IRB.CreateInsertElement(GuardPtr2, val2, (uint64_t)0);
for (uint64_t i = 1; i < elements; i++) {
val1 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(IntptrTy, (cnt_cov + local_selects++ +
AllBlocks.size()) *
4)),
Int32PtrTy);
x = IRB.CreateInsertElement(x, val1, i);
val2 = IRB.CreateIntToPtr(
IRB.CreateAdd(
IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(IntptrTy, (cnt_cov + local_selects++ +
AllBlocks.size()) *
4)),
Int32PtrTy);
y = IRB.CreateInsertElement(y, val2, i);
}
result = IRB.CreateSelect(condition, x, y);
}
}
} else
#endif
{
// fprintf(stderr, "UNHANDLED: %u\n", t->getTypeID());
unhandled++;
continue;
}
uint32_t vector_cur = 0;
/* Load SHM pointer */
LoadInst *MapPtr =
IRB.CreateLoad(PointerType::get(Int8Ty, 0), AFLMapPtr);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(MapPtr);
while (1) {
/* Get CurLoc */
LoadInst *CurLoc = nullptr;
Value *MapPtrIdx = nullptr;
/* Load counter for CurLoc */
if (!vector_cnt) {
CurLoc = IRB.CreateLoad(IRB.getInt32Ty(), result);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(CurLoc);
MapPtrIdx = IRB.CreateGEP(Int8Ty, MapPtr, CurLoc);
} else {
auto element = IRB.CreateExtractElement(result, vector_cur++);
auto elementptr = IRB.CreateIntToPtr(element, Int32PtrTy);
auto elementld = IRB.CreateLoad(IRB.getInt32Ty(), elementptr);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(elementld);
MapPtrIdx = IRB.CreateGEP(Int8Ty, MapPtr, elementld);
}
if (use_threadsafe_counters) {
IRB.CreateAtomicRMW(llvm::AtomicRMWInst::BinOp::Add, MapPtrIdx, One,
#if LLVM_VERSION_MAJOR >= 13
llvm::MaybeAlign(1),
#endif
llvm::AtomicOrdering::Monotonic);
} else {
LoadInst *Counter = IRB.CreateLoad(IRB.getInt8Ty(), MapPtrIdx);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(Counter);
/* Update bitmap */
Value *Incr = IRB.CreateAdd(Counter, One);
if (skip_nozero == NULL) {
auto cf = IRB.CreateICmpEQ(Incr, Zero);
auto carry = IRB.CreateZExt(cf, Int8Ty);
Incr = IRB.CreateAdd(Incr, carry);
}
StoreInst *StoreCtx = IRB.CreateStore(Incr, MapPtrIdx);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(StoreCtx);
}
if (!vector_cnt) {
vector_cnt = 2;
break;
} else if (vector_cnt == vector_cur) {
break;
}
}
skip_next = 1;
instr += vector_cnt;
} else {
skip_next = 0;
}
}
}
if (AllBlocks.empty() && !special && !local_selects) return false;
if (!AllBlocks.empty())
for (size_t i = 0, N = AllBlocks.size(); i < N; i++)
InjectCoverageAtBlock(F, *AllBlocks[i], i, IsLeafFunc);
return true;
}
// For every switch statement we insert a call:
// __sanitizer_cov_trace_switch(CondValue,
// {NumCases, ValueSizeInBits, Case0Value, Case1Value, Case2Value, ... })
void ModuleSanitizerCoverageAFL::InjectTraceForSwitch(
Function &, ArrayRef<Instruction *> SwitchTraceTargets) {
for (auto I : SwitchTraceTargets) {
if (SwitchInst *SI = dyn_cast<SwitchInst>(I)) {
IRBuilder<> IRB(I);
SmallVector<Constant *, 16> Initializers;
Value *Cond = SI->getCondition();
if (Cond->getType()->getScalarSizeInBits() >
Int64Ty->getScalarSizeInBits())
continue;
Initializers.push_back(ConstantInt::get(Int64Ty, SI->getNumCases()));
Initializers.push_back(
ConstantInt::get(Int64Ty, Cond->getType()->getScalarSizeInBits()));
if (Cond->getType()->getScalarSizeInBits() <
Int64Ty->getScalarSizeInBits())
Cond = IRB.CreateIntCast(Cond, Int64Ty, false);
for (auto It : SI->cases()) {
Constant *C = It.getCaseValue();
if (C->getType()->getScalarSizeInBits() <
Int64Ty->getScalarSizeInBits())
C = ConstantExpr::getCast(CastInst::ZExt, It.getCaseValue(), Int64Ty);
Initializers.push_back(C);
}
llvm::sort(drop_begin(Initializers, 2),
[](const Constant *A, const Constant *B) {
return cast<ConstantInt>(A)->getLimitedValue() <
cast<ConstantInt>(B)->getLimitedValue();
});
ArrayType *ArrayOfInt64Ty = ArrayType::get(Int64Ty, Initializers.size());
GlobalVariable *GV = new GlobalVariable(
*CurModule, ArrayOfInt64Ty, false, GlobalVariable::InternalLinkage,
ConstantArray::get(ArrayOfInt64Ty, Initializers),
"__sancov_gen_cov_switch_values");
IRB.CreateCall(SanCovTraceSwitchFunction,
{Cond, IRB.CreatePointerCast(GV, Int64PtrTy)});
}
}
}
void ModuleSanitizerCoverageAFL::InjectTraceForCmp(
Function &, ArrayRef<Instruction *> CmpTraceTargets) {
for (auto I : CmpTraceTargets) {
if (ICmpInst *ICMP = dyn_cast<ICmpInst>(I)) {
IRBuilder<> IRB(ICMP);
Value *A0 = ICMP->getOperand(0);
Value *A1 = ICMP->getOperand(1);
if (!A0->getType()->isIntegerTy()) continue;
uint64_t TypeSize = DL->getTypeStoreSizeInBits(A0->getType());
int CallbackIdx = TypeSize == 8 ? 0
: TypeSize == 16 ? 1
: TypeSize == 32 ? 2
: TypeSize == 64 ? 3
: -1;
if (CallbackIdx < 0) continue;
// __sanitizer_cov_trace_cmp((type_size << 32) | predicate, A0, A1);
auto CallbackFunc = SanCovTraceCmpFunction[CallbackIdx];
bool FirstIsConst = isa<ConstantInt>(A0);
bool SecondIsConst = isa<ConstantInt>(A1);
// If both are const, then we don't need such a comparison.
if (FirstIsConst && SecondIsConst) continue;
// If only one is const, then make it the first callback argument.
if (FirstIsConst || SecondIsConst) {
CallbackFunc = SanCovTraceConstCmpFunction[CallbackIdx];
if (SecondIsConst) std::swap(A0, A1);
}
auto Ty = Type::getIntNTy(*C, TypeSize);
IRB.CreateCall(CallbackFunc, {IRB.CreateIntCast(A0, Ty, true),
IRB.CreateIntCast(A1, Ty, true)});
}
}
}
void ModuleSanitizerCoverageAFL::InjectCoverageAtBlock(Function &F,
BasicBlock &BB,
size_t Idx,
bool IsLeafFunc) {
BasicBlock::iterator IP = BB.getFirstInsertionPt();
bool IsEntryBB = &BB == &F.getEntryBlock();
DebugLoc EntryLoc;
if (IsEntryBB) {
if (auto SP = F.getSubprogram())
EntryLoc = DILocation::get(SP->getContext(), SP->getScopeLine(), 0, SP);
// Keep static allocas and llvm.localescape calls in the entry block. Even
// if we aren't splitting the block, it's nice for allocas to be before
// calls.
IP = PrepareToSplitEntryBlock(BB, IP);
#if LLVM_VERSION_MAJOR < 15
} else {
EntryLoc = IP->getDebugLoc();
if (!EntryLoc)
if (auto *SP = F.getSubprogram())
EntryLoc = DILocation::get(SP->getContext(), 0, 0, SP);
#endif
}
#if LLVM_VERSION_MAJOR >= 16
InstrumentationIRBuilder IRB(&*IP);
#else
IRBuilder<> IRB(&*IP);
#endif
if (EntryLoc) IRB.SetCurrentDebugLocation(EntryLoc);
if (Options.TracePCGuard) {
/*
auto GuardPtr = IRB.CreateIntToPtr(
IRB.CreateAdd(IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(IntptrTy, Idx * 4)),
Int32PtrTy);
IRB.CreateCall(SanCovTracePCGuard, GuardPtr)->setCannotMerge();
*/
/* Get CurLoc */
Value *GuardPtr = IRB.CreateIntToPtr(
IRB.CreateAdd(IRB.CreatePointerCast(FunctionGuardArray, IntptrTy),
ConstantInt::get(IntptrTy, Idx * 4)),
Int32PtrTy);
LoadInst *CurLoc = IRB.CreateLoad(IRB.getInt32Ty(), GuardPtr);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(CurLoc);
/* Load SHM pointer */
LoadInst *MapPtr = IRB.CreateLoad(PointerType::get(Int8Ty, 0), AFLMapPtr);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(MapPtr);
/* Load counter for CurLoc */
Value *MapPtrIdx = IRB.CreateGEP(Int8Ty, MapPtr, CurLoc);
if (use_threadsafe_counters) {
IRB.CreateAtomicRMW(llvm::AtomicRMWInst::BinOp::Add, MapPtrIdx, One,
#if LLVM_VERSION_MAJOR >= 13
llvm::MaybeAlign(1),
#endif
llvm::AtomicOrdering::Monotonic);
} else {
LoadInst *Counter = IRB.CreateLoad(IRB.getInt8Ty(), MapPtrIdx);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(Counter);
/* Update bitmap */
Value *Incr = IRB.CreateAdd(Counter, One);
if (skip_nozero == NULL) {
auto cf = IRB.CreateICmpEQ(Incr, Zero);
auto carry = IRB.CreateZExt(cf, Int8Ty);
Incr = IRB.CreateAdd(Incr, carry);
}
StoreInst *StoreCtx = IRB.CreateStore(Incr, MapPtrIdx);
ModuleSanitizerCoverageAFL::SetNoSanitizeMetadata(StoreCtx);
}
// done :)
// IRB.CreateCall(SanCovTracePCGuard, Offset)->setCannotMerge();
// IRB.CreateCall(SanCovTracePCGuard, GuardPtr)->setCannotMerge();
++instr;
}
}
std::string ModuleSanitizerCoverageAFL::getSectionName(
const std::string &Section) const {
if (TargetTriple.isOSBinFormatCOFF()) {
if (Section == SanCovCountersSectionName) return ".SCOV$CM";
if (Section == SanCovBoolFlagSectionName) return ".SCOV$BM";
if (Section == SanCovPCsSectionName) return ".SCOVP$M";
return ".SCOV$GM"; // For SanCovGuardsSectionName.
}
if (TargetTriple.isOSBinFormatMachO()) return "__DATA,__" + Section;
return "__" + Section;
}
std::string ModuleSanitizerCoverageAFL::getSectionStart(
const std::string &Section) const {
if (TargetTriple.isOSBinFormatMachO())
return "\1section$start$__DATA$__" + Section;
return "__start___" + Section;
}
std::string ModuleSanitizerCoverageAFL::getSectionEnd(
const std::string &Section) const {
if (TargetTriple.isOSBinFormatMachO())
return "\1section$end$__DATA$__" + Section;
return "__stop___" + Section;
}