blob: 4c827aca20ec8f06ba534a96da82a29716b806b9 [file] [log] [blame]
//===- AddressSanitizer.cpp - memory error detector -----------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file is a part of AddressSanitizer, an address sanity checker.
// Details of the algorithm:
// https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Instrumentation/AddressSanitizer.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DepthFirstIterator.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Triple.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/BinaryFormat/MachO.h"
#include "llvm/IR/Argument.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/Comdat.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DIBuilder.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugInfoMetadata.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalAlias.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Use.h"
#include "llvm/IR/Value.h"
#include "llvm/MC/MCSectionMachO.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/ScopedPrinter.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Instrumentation.h"
#include "llvm/Transforms/Utils/ASanStackFrameLayout.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
#include "llvm/Transforms/Utils/PromoteMemToReg.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <iomanip>
#include <limits>
#include <memory>
#include <sstream>
#include <string>
#include <tuple>
using namespace llvm;
#define DEBUG_TYPE "asan"
static const uint64_t kDefaultShadowScale = 3;
static const uint64_t kDefaultShadowOffset32 = 1ULL << 29;
static const uint64_t kDefaultShadowOffset64 = 1ULL << 44;
static const uint64_t kDynamicShadowSentinel =
std::numeric_limits<uint64_t>::max();
static const uint64_t kIOSShadowOffset32 = 1ULL << 30;
static const uint64_t kIOSSimShadowOffset32 = 1ULL << 30;
static const uint64_t kIOSSimShadowOffset64 = kDefaultShadowOffset64;
static const uint64_t kSmallX86_64ShadowOffsetBase = 0x7FFFFFFF; // < 2G.
static const uint64_t kSmallX86_64ShadowOffsetAlignMask = ~0xFFFULL;
static const uint64_t kLinuxKasan_ShadowOffset64 = 0xdffffc0000000000;
static const uint64_t kPPC64_ShadowOffset64 = 1ULL << 44;
static const uint64_t kSystemZ_ShadowOffset64 = 1ULL << 52;
static const uint64_t kMIPS32_ShadowOffset32 = 0x0aaa0000;
static const uint64_t kMIPS64_ShadowOffset64 = 1ULL << 37;
static const uint64_t kAArch64_ShadowOffset64 = 1ULL << 36;
static const uint64_t kFreeBSD_ShadowOffset32 = 1ULL << 30;
static const uint64_t kFreeBSD_ShadowOffset64 = 1ULL << 46;
static const uint64_t kNetBSD_ShadowOffset32 = 1ULL << 30;
static const uint64_t kNetBSD_ShadowOffset64 = 1ULL << 46;
static const uint64_t kNetBSDKasan_ShadowOffset64 = 0xdfff900000000000;
static const uint64_t kPS4CPU_ShadowOffset64 = 1ULL << 40;
static const uint64_t kWindowsShadowOffset32 = 3ULL << 28;
static const uint64_t kMyriadShadowScale = 5;
static const uint64_t kMyriadMemoryOffset32 = 0x80000000ULL;
static const uint64_t kMyriadMemorySize32 = 0x20000000ULL;
static const uint64_t kMyriadTagShift = 29;
static const uint64_t kMyriadDDRTag = 4;
static const uint64_t kMyriadCacheBitMask32 = 0x40000000ULL;
// The shadow memory space is dynamically allocated.
static const uint64_t kWindowsShadowOffset64 = kDynamicShadowSentinel;
static const size_t kMinStackMallocSize = 1 << 6; // 64B
static const size_t kMaxStackMallocSize = 1 << 16; // 64K
static const uintptr_t kCurrentStackFrameMagic = 0x41B58AB3;
static const uintptr_t kRetiredStackFrameMagic = 0x45E0360E;
static const char *const kAsanModuleCtorName = "asan.module_ctor";
static const char *const kAsanModuleDtorName = "asan.module_dtor";
static const uint64_t kAsanCtorAndDtorPriority = 1;
static const char *const kAsanReportErrorTemplate = "__asan_report_";
static const char *const kAsanRegisterGlobalsName = "__asan_register_globals";
static const char *const kAsanUnregisterGlobalsName =
"__asan_unregister_globals";
static const char *const kAsanRegisterImageGlobalsName =
"__asan_register_image_globals";
static const char *const kAsanUnregisterImageGlobalsName =
"__asan_unregister_image_globals";
static const char *const kAsanRegisterElfGlobalsName =
"__asan_register_elf_globals";
static const char *const kAsanUnregisterElfGlobalsName =
"__asan_unregister_elf_globals";
static const char *const kAsanPoisonGlobalsName = "__asan_before_dynamic_init";
static const char *const kAsanUnpoisonGlobalsName = "__asan_after_dynamic_init";
static const char *const kAsanInitName = "__asan_init";
static const char *const kAsanVersionCheckNamePrefix =
"__asan_version_mismatch_check_v";
static const char *const kAsanPtrCmp = "__sanitizer_ptr_cmp";
static const char *const kAsanPtrSub = "__sanitizer_ptr_sub";
static const char *const kAsanHandleNoReturnName = "__asan_handle_no_return";
static const int kMaxAsanStackMallocSizeClass = 10;
static const char *const kAsanStackMallocNameTemplate = "__asan_stack_malloc_";
static const char *const kAsanStackFreeNameTemplate = "__asan_stack_free_";
static const char *const kAsanGenPrefix = "___asan_gen_";
static const char *const kODRGenPrefix = "__odr_asan_gen_";
static const char *const kSanCovGenPrefix = "__sancov_gen_";
static const char *const kAsanSetShadowPrefix = "__asan_set_shadow_";
static const char *const kAsanPoisonStackMemoryName =
"__asan_poison_stack_memory";
static const char *const kAsanUnpoisonStackMemoryName =
"__asan_unpoison_stack_memory";
// ASan version script has __asan_* wildcard. Triple underscore prevents a
// linker (gold) warning about attempting to export a local symbol.
static const char *const kAsanGlobalsRegisteredFlagName =
"___asan_globals_registered";
static const char *const kAsanOptionDetectUseAfterReturn =
"__asan_option_detect_stack_use_after_return";
static const char *const kAsanShadowMemoryDynamicAddress =
"__asan_shadow_memory_dynamic_address";
static const char *const kAsanAllocaPoison = "__asan_alloca_poison";
static const char *const kAsanAllocasUnpoison = "__asan_allocas_unpoison";
// Accesses sizes are powers of two: 1, 2, 4, 8, 16.
static const size_t kNumberOfAccessSizes = 5;
static const unsigned kAllocaRzSize = 32;
// Command-line flags.
static cl::opt<bool> ClEnableKasan(
"asan-kernel", cl::desc("Enable KernelAddressSanitizer instrumentation"),
cl::Hidden, cl::init(false));
static cl::opt<bool> ClRecover(
"asan-recover",
cl::desc("Enable recovery mode (continue-after-error)."),
cl::Hidden, cl::init(false));
// This flag may need to be replaced with -f[no-]asan-reads.
static cl::opt<bool> ClInstrumentReads("asan-instrument-reads",
cl::desc("instrument read instructions"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClInstrumentWrites(
"asan-instrument-writes", cl::desc("instrument write instructions"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClInstrumentAtomics(
"asan-instrument-atomics",
cl::desc("instrument atomic instructions (rmw, cmpxchg)"), cl::Hidden,
cl::init(true));
static cl::opt<bool> ClAlwaysSlowPath(
"asan-always-slow-path",
cl::desc("use instrumentation with slow path for all accesses"), cl::Hidden,
cl::init(false));
static cl::opt<bool> ClForceDynamicShadow(
"asan-force-dynamic-shadow",
cl::desc("Load shadow address into a local variable for each function"),
cl::Hidden, cl::init(false));
static cl::opt<bool>
ClWithIfunc("asan-with-ifunc",
cl::desc("Access dynamic shadow through an ifunc global on "
"platforms that support this"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClWithIfuncSuppressRemat(
"asan-with-ifunc-suppress-remat",
cl::desc("Suppress rematerialization of dynamic shadow address by passing "
"it through inline asm in prologue."),
cl::Hidden, cl::init(true));
// This flag limits the number of instructions to be instrumented
// in any given BB. Normally, this should be set to unlimited (INT_MAX),
// but due to http://llvm.org/bugs/show_bug.cgi?id=12652 we temporary
// set it to 10000.
static cl::opt<int> ClMaxInsnsToInstrumentPerBB(
"asan-max-ins-per-bb", cl::init(10000),
cl::desc("maximal number of instructions to instrument in any given BB"),
cl::Hidden);
// This flag may need to be replaced with -f[no]asan-stack.
static cl::opt<bool> ClStack("asan-stack", cl::desc("Handle stack memory"),
cl::Hidden, cl::init(true));
static cl::opt<uint32_t> ClMaxInlinePoisoningSize(
"asan-max-inline-poisoning-size",
cl::desc(
"Inline shadow poisoning for blocks up to the given size in bytes."),
cl::Hidden, cl::init(64));
static cl::opt<bool> ClUseAfterReturn("asan-use-after-return",
cl::desc("Check stack-use-after-return"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClRedzoneByvalArgs("asan-redzone-byval-args",
cl::desc("Create redzones for byval "
"arguments (extra copy "
"required)"), cl::Hidden,
cl::init(true));
static cl::opt<bool> ClUseAfterScope("asan-use-after-scope",
cl::desc("Check stack-use-after-scope"),
cl::Hidden, cl::init(false));
// This flag may need to be replaced with -f[no]asan-globals.
static cl::opt<bool> ClGlobals("asan-globals",
cl::desc("Handle global objects"), cl::Hidden,
cl::init(true));
static cl::opt<bool> ClInitializers("asan-initialization-order",
cl::desc("Handle C++ initializer order"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClInvalidPointerPairs(
"asan-detect-invalid-pointer-pair",
cl::desc("Instrument <, <=, >, >=, - with pointer operands"), cl::Hidden,
cl::init(false));
static cl::opt<bool> ClInvalidPointerCmp(
"asan-detect-invalid-pointer-cmp",
cl::desc("Instrument <, <=, >, >= with pointer operands"), cl::Hidden,
cl::init(false));
static cl::opt<bool> ClInvalidPointerSub(
"asan-detect-invalid-pointer-sub",
cl::desc("Instrument - operations with pointer operands"), cl::Hidden,
cl::init(false));
static cl::opt<unsigned> ClRealignStack(
"asan-realign-stack",
cl::desc("Realign stack to the value of this flag (power of two)"),
cl::Hidden, cl::init(32));
static cl::opt<int> ClInstrumentationWithCallsThreshold(
"asan-instrumentation-with-call-threshold",
cl::desc(
"If the function being instrumented contains more than "
"this number of memory accesses, use callbacks instead of "
"inline checks (-1 means never use callbacks)."),
cl::Hidden, cl::init(7000));
static cl::opt<std::string> ClMemoryAccessCallbackPrefix(
"asan-memory-access-callback-prefix",
cl::desc("Prefix for memory access callbacks"), cl::Hidden,
cl::init("__asan_"));
static cl::opt<bool>
ClInstrumentDynamicAllocas("asan-instrument-dynamic-allocas",
cl::desc("instrument dynamic allocas"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClSkipPromotableAllocas(
"asan-skip-promotable-allocas",
cl::desc("Do not instrument promotable allocas"), cl::Hidden,
cl::init(true));
// These flags allow to change the shadow mapping.
// The shadow mapping looks like
// Shadow = (Mem >> scale) + offset
static cl::opt<int> ClMappingScale("asan-mapping-scale",
cl::desc("scale of asan shadow mapping"),
cl::Hidden, cl::init(0));
static cl::opt<unsigned long long> ClMappingOffset(
"asan-mapping-offset",
cl::desc("offset of asan shadow mapping [EXPERIMENTAL]"), cl::Hidden,
cl::init(0));
// Optimization flags. Not user visible, used mostly for testing
// and benchmarking the tool.
static cl::opt<bool> ClOpt("asan-opt", cl::desc("Optimize instrumentation"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClOptSameTemp(
"asan-opt-same-temp", cl::desc("Instrument the same temp just once"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClOptGlobals("asan-opt-globals",
cl::desc("Don't instrument scalar globals"),
cl::Hidden, cl::init(true));
static cl::opt<bool> ClOptStack(
"asan-opt-stack", cl::desc("Don't instrument scalar stack variables"),
cl::Hidden, cl::init(false));
static cl::opt<bool> ClDynamicAllocaStack(
"asan-stack-dynamic-alloca",
cl::desc("Use dynamic alloca to represent stack variables"), cl::Hidden,
cl::init(true));
static cl::opt<uint32_t> ClForceExperiment(
"asan-force-experiment",
cl::desc("Force optimization experiment (for testing)"), cl::Hidden,
cl::init(0));
static cl::opt<bool>
ClUsePrivateAlias("asan-use-private-alias",
cl::desc("Use private aliases for global variables"),
cl::Hidden, cl::init(false));
static cl::opt<bool>
ClUseOdrIndicator("asan-use-odr-indicator",
cl::desc("Use odr indicators to improve ODR reporting"),
cl::Hidden, cl::init(false));
static cl::opt<bool>
ClUseGlobalsGC("asan-globals-live-support",
cl::desc("Use linker features to support dead "
"code stripping of globals"),
cl::Hidden, cl::init(true));
// This is on by default even though there is a bug in gold:
// https://sourceware.org/bugzilla/show_bug.cgi?id=19002
static cl::opt<bool>
ClWithComdat("asan-with-comdat",
cl::desc("Place ASan constructors in comdat sections"),
cl::Hidden, cl::init(true));
// Debug flags.
static cl::opt<int> ClDebug("asan-debug", cl::desc("debug"), cl::Hidden,
cl::init(0));
static cl::opt<int> ClDebugStack("asan-debug-stack", cl::desc("debug stack"),
cl::Hidden, cl::init(0));
static cl::opt<std::string> ClDebugFunc("asan-debug-func", cl::Hidden,
cl::desc("Debug func"));
static cl::opt<int> ClDebugMin("asan-debug-min", cl::desc("Debug min inst"),
cl::Hidden, cl::init(-1));
static cl::opt<int> ClDebugMax("asan-debug-max", cl::desc("Debug max inst"),
cl::Hidden, cl::init(-1));
STATISTIC(NumInstrumentedReads, "Number of instrumented reads");
STATISTIC(NumInstrumentedWrites, "Number of instrumented writes");
STATISTIC(NumOptimizedAccessesToGlobalVar,
"Number of optimized accesses to global vars");
STATISTIC(NumOptimizedAccessesToStackVar,
"Number of optimized accesses to stack vars");
namespace {
/// This struct defines the shadow mapping using the rule:
/// shadow = (mem >> Scale) ADD-or-OR Offset.
/// If InGlobal is true, then
/// extern char __asan_shadow[];
/// shadow = (mem >> Scale) + &__asan_shadow
struct ShadowMapping {
int Scale;
uint64_t Offset;
bool OrShadowOffset;
bool InGlobal;
};
} // end anonymous namespace
static ShadowMapping getShadowMapping(Triple &TargetTriple, int LongSize,
bool IsKasan) {
bool IsAndroid = TargetTriple.isAndroid();
bool IsIOS = TargetTriple.isiOS() || TargetTriple.isWatchOS();
bool IsFreeBSD = TargetTriple.isOSFreeBSD();
bool IsNetBSD = TargetTriple.isOSNetBSD();
bool IsPS4CPU = TargetTriple.isPS4CPU();
bool IsLinux = TargetTriple.isOSLinux();
bool IsPPC64 = TargetTriple.getArch() == Triple::ppc64 ||
TargetTriple.getArch() == Triple::ppc64le;
bool IsSystemZ = TargetTriple.getArch() == Triple::systemz;
bool IsX86 = TargetTriple.getArch() == Triple::x86;
bool IsX86_64 = TargetTriple.getArch() == Triple::x86_64;
bool IsMIPS32 = TargetTriple.isMIPS32();
bool IsMIPS64 = TargetTriple.isMIPS64();
bool IsArmOrThumb = TargetTriple.isARM() || TargetTriple.isThumb();
bool IsAArch64 = TargetTriple.getArch() == Triple::aarch64;
bool IsWindows = TargetTriple.isOSWindows();
bool IsFuchsia = TargetTriple.isOSFuchsia();
bool IsMyriad = TargetTriple.getVendor() == llvm::Triple::Myriad;
ShadowMapping Mapping;
Mapping.Scale = IsMyriad ? kMyriadShadowScale : kDefaultShadowScale;
if (ClMappingScale.getNumOccurrences() > 0) {
Mapping.Scale = ClMappingScale;
}
if (LongSize == 32) {
if (IsAndroid)
Mapping.Offset = kDynamicShadowSentinel;
else if (IsMIPS32)
Mapping.Offset = kMIPS32_ShadowOffset32;
else if (IsFreeBSD)
Mapping.Offset = kFreeBSD_ShadowOffset32;
else if (IsNetBSD)
Mapping.Offset = kNetBSD_ShadowOffset32;
else if (IsIOS)
// If we're targeting iOS and x86, the binary is built for iOS simulator.
Mapping.Offset = IsX86 ? kIOSSimShadowOffset32 : kIOSShadowOffset32;
else if (IsWindows)
Mapping.Offset = kWindowsShadowOffset32;
else if (IsMyriad) {
uint64_t ShadowOffset = (kMyriadMemoryOffset32 + kMyriadMemorySize32 -
(kMyriadMemorySize32 >> Mapping.Scale));
Mapping.Offset = ShadowOffset - (kMyriadMemoryOffset32 >> Mapping.Scale);
}
else
Mapping.Offset = kDefaultShadowOffset32;
} else { // LongSize == 64
// Fuchsia is always PIE, which means that the beginning of the address
// space is always available.
if (IsFuchsia)
Mapping.Offset = 0;
else if (IsPPC64)
Mapping.Offset = kPPC64_ShadowOffset64;
else if (IsSystemZ)
Mapping.Offset = kSystemZ_ShadowOffset64;
else if (IsFreeBSD && !IsMIPS64)
Mapping.Offset = kFreeBSD_ShadowOffset64;
else if (IsNetBSD) {
if (IsKasan)
Mapping.Offset = kNetBSDKasan_ShadowOffset64;
else
Mapping.Offset = kNetBSD_ShadowOffset64;
} else if (IsPS4CPU)
Mapping.Offset = kPS4CPU_ShadowOffset64;
else if (IsLinux && IsX86_64) {
if (IsKasan)
Mapping.Offset = kLinuxKasan_ShadowOffset64;
else
Mapping.Offset = (kSmallX86_64ShadowOffsetBase &
(kSmallX86_64ShadowOffsetAlignMask << Mapping.Scale));
} else if (IsWindows && IsX86_64) {
Mapping.Offset = kWindowsShadowOffset64;
} else if (IsMIPS64)
Mapping.Offset = kMIPS64_ShadowOffset64;
else if (IsIOS)
// If we're targeting iOS and x86, the binary is built for iOS simulator.
// We are using dynamic shadow offset on the 64-bit devices.
Mapping.Offset =
IsX86_64 ? kIOSSimShadowOffset64 : kDynamicShadowSentinel;
else if (IsAArch64)
Mapping.Offset = kAArch64_ShadowOffset64;
else
Mapping.Offset = kDefaultShadowOffset64;
}
if (ClForceDynamicShadow) {
Mapping.Offset = kDynamicShadowSentinel;
}
if (ClMappingOffset.getNumOccurrences() > 0) {
Mapping.Offset = ClMappingOffset;
}
// OR-ing shadow offset if more efficient (at least on x86) if the offset
// is a power of two, but on ppc64 we have to use add since the shadow
// offset is not necessary 1/8-th of the address space. On SystemZ,
// we could OR the constant in a single instruction, but it's more
// efficient to load it once and use indexed addressing.
Mapping.OrShadowOffset = !IsAArch64 && !IsPPC64 && !IsSystemZ && !IsPS4CPU &&
!(Mapping.Offset & (Mapping.Offset - 1)) &&
Mapping.Offset != kDynamicShadowSentinel;
bool IsAndroidWithIfuncSupport =
IsAndroid && !TargetTriple.isAndroidVersionLT(21);
Mapping.InGlobal = ClWithIfunc && IsAndroidWithIfuncSupport && IsArmOrThumb;
return Mapping;
}
static size_t RedzoneSizeForScale(int MappingScale) {
// Redzone used for stack and globals is at least 32 bytes.
// For scales 6 and 7, the redzone has to be 64 and 128 bytes respectively.
return std::max(32U, 1U << MappingScale);
}
namespace {
/// Module analysis for getting various metadata about the module.
class ASanGlobalsMetadataWrapperPass : public ModulePass {
public:
static char ID;
ASanGlobalsMetadataWrapperPass() : ModulePass(ID) {
initializeASanGlobalsMetadataWrapperPassPass(
*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override {
GlobalsMD = GlobalsMetadata(M);
return false;
}
StringRef getPassName() const override {
return "ASanGlobalsMetadataWrapperPass";
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
}
GlobalsMetadata &getGlobalsMD() { return GlobalsMD; }
private:
GlobalsMetadata GlobalsMD;
};
char ASanGlobalsMetadataWrapperPass::ID = 0;
/// AddressSanitizer: instrument the code in module to find memory bugs.
struct AddressSanitizer {
AddressSanitizer(Module &M, GlobalsMetadata &GlobalsMD,
bool CompileKernel = false, bool Recover = false,
bool UseAfterScope = false)
: UseAfterScope(UseAfterScope || ClUseAfterScope), GlobalsMD(GlobalsMD) {
this->Recover = ClRecover.getNumOccurrences() > 0 ? ClRecover : Recover;
this->CompileKernel =
ClEnableKasan.getNumOccurrences() > 0 ? ClEnableKasan : CompileKernel;
C = &(M.getContext());
LongSize = M.getDataLayout().getPointerSizeInBits();
IntptrTy = Type::getIntNTy(*C, LongSize);
TargetTriple = Triple(M.getTargetTriple());
Mapping = getShadowMapping(TargetTriple, LongSize, this->CompileKernel);
}
uint64_t getAllocaSizeInBytes(const AllocaInst &AI) const {
uint64_t ArraySize = 1;
if (AI.isArrayAllocation()) {
const ConstantInt *CI = dyn_cast<ConstantInt>(AI.getArraySize());
assert(CI && "non-constant array size");
ArraySize = CI->getZExtValue();
}
Type *Ty = AI.getAllocatedType();
uint64_t SizeInBytes =
AI.getModule()->getDataLayout().getTypeAllocSize(Ty);
return SizeInBytes * ArraySize;
}
/// Check if we want (and can) handle this alloca.
bool isInterestingAlloca(const AllocaInst &AI);
/// If it is an interesting memory access, return the PointerOperand
/// and set IsWrite/Alignment. Otherwise return nullptr.
/// MaybeMask is an output parameter for the mask Value, if we're looking at a
/// masked load/store.
Value *isInterestingMemoryAccess(Instruction *I, bool *IsWrite,
uint64_t *TypeSize, unsigned *Alignment,
Value **MaybeMask = nullptr);
void instrumentMop(ObjectSizeOffsetVisitor &ObjSizeVis, Instruction *I,
bool UseCalls, const DataLayout &DL);
void instrumentPointerComparisonOrSubtraction(Instruction *I);
void instrumentAddress(Instruction *OrigIns, Instruction *InsertBefore,
Value *Addr, uint32_t TypeSize, bool IsWrite,
Value *SizeArgument, bool UseCalls, uint32_t Exp);
void instrumentUnusualSizeOrAlignment(Instruction *I,
Instruction *InsertBefore, Value *Addr,
uint32_t TypeSize, bool IsWrite,
Value *SizeArgument, bool UseCalls,
uint32_t Exp);
Value *createSlowPathCmp(IRBuilder<> &IRB, Value *AddrLong,
Value *ShadowValue, uint32_t TypeSize);
Instruction *generateCrashCode(Instruction *InsertBefore, Value *Addr,
bool IsWrite, size_t AccessSizeIndex,
Value *SizeArgument, uint32_t Exp);
void instrumentMemIntrinsic(MemIntrinsic *MI);
Value *memToShadow(Value *Shadow, IRBuilder<> &IRB);
bool instrumentFunction(Function &F, const TargetLibraryInfo *TLI);
bool maybeInsertAsanInitAtFunctionEntry(Function &F);
void maybeInsertDynamicShadowAtFunctionEntry(Function &F);
void markEscapedLocalAllocas(Function &F);
private:
friend struct FunctionStackPoisoner;
void initializeCallbacks(Module &M);
bool LooksLikeCodeInBug11395(Instruction *I);
bool GlobalIsLinkerInitialized(GlobalVariable *G);
bool isSafeAccess(ObjectSizeOffsetVisitor &ObjSizeVis, Value *Addr,
uint64_t TypeSize) const;
/// Helper to cleanup per-function state.
struct FunctionStateRAII {
AddressSanitizer *Pass;
FunctionStateRAII(AddressSanitizer *Pass) : Pass(Pass) {
assert(Pass->ProcessedAllocas.empty() &&
"last pass forgot to clear cache");
assert(!Pass->LocalDynamicShadow);
}
~FunctionStateRAII() {
Pass->LocalDynamicShadow = nullptr;
Pass->ProcessedAllocas.clear();
}
};
LLVMContext *C;
Triple TargetTriple;
int LongSize;
bool CompileKernel;
bool Recover;
bool UseAfterScope;
Type *IntptrTy;
ShadowMapping Mapping;
FunctionCallee AsanHandleNoReturnFunc;
FunctionCallee AsanPtrCmpFunction, AsanPtrSubFunction;
Constant *AsanShadowGlobal;
// These arrays is indexed by AccessIsWrite, Experiment and log2(AccessSize).
FunctionCallee AsanErrorCallback[2][2][kNumberOfAccessSizes];
FunctionCallee AsanMemoryAccessCallback[2][2][kNumberOfAccessSizes];
// These arrays is indexed by AccessIsWrite and Experiment.
FunctionCallee AsanErrorCallbackSized[2][2];
FunctionCallee AsanMemoryAccessCallbackSized[2][2];
FunctionCallee AsanMemmove, AsanMemcpy, AsanMemset;
InlineAsm *EmptyAsm;
Value *LocalDynamicShadow = nullptr;
GlobalsMetadata GlobalsMD;
DenseMap<const AllocaInst *, bool> ProcessedAllocas;
};
class AddressSanitizerLegacyPass : public FunctionPass {
public:
static char ID;
explicit AddressSanitizerLegacyPass(bool CompileKernel = false,
bool Recover = false,
bool UseAfterScope = false)
: FunctionPass(ID), CompileKernel(CompileKernel), Recover(Recover),
UseAfterScope(UseAfterScope) {
initializeAddressSanitizerLegacyPassPass(*PassRegistry::getPassRegistry());
}
StringRef getPassName() const override {
return "AddressSanitizerFunctionPass";
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<ASanGlobalsMetadataWrapperPass>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
}
bool runOnFunction(Function &F) override {
GlobalsMetadata &GlobalsMD =
getAnalysis<ASanGlobalsMetadataWrapperPass>().getGlobalsMD();
const TargetLibraryInfo *TLI =
&getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
AddressSanitizer ASan(*F.getParent(), GlobalsMD, CompileKernel, Recover,
UseAfterScope);
return ASan.instrumentFunction(F, TLI);
}
private:
bool CompileKernel;
bool Recover;
bool UseAfterScope;
};
class ModuleAddressSanitizer {
public:
ModuleAddressSanitizer(Module &M, GlobalsMetadata &GlobalsMD,
bool CompileKernel = false, bool Recover = false,
bool UseGlobalsGC = true, bool UseOdrIndicator = false)
: GlobalsMD(GlobalsMD), UseGlobalsGC(UseGlobalsGC && ClUseGlobalsGC),
// Enable aliases as they should have no downside with ODR indicators.
UsePrivateAlias(UseOdrIndicator || ClUsePrivateAlias),
UseOdrIndicator(UseOdrIndicator || ClUseOdrIndicator),
// Not a typo: ClWithComdat is almost completely pointless without
// ClUseGlobalsGC (because then it only works on modules without
// globals, which are rare); it is a prerequisite for ClUseGlobalsGC;
// and both suffer from gold PR19002 for which UseGlobalsGC constructor
// argument is designed as workaround. Therefore, disable both
// ClWithComdat and ClUseGlobalsGC unless the frontend says it's ok to
// do globals-gc.
UseCtorComdat(UseGlobalsGC && ClWithComdat) {
this->Recover = ClRecover.getNumOccurrences() > 0 ? ClRecover : Recover;
this->CompileKernel =
ClEnableKasan.getNumOccurrences() > 0 ? ClEnableKasan : CompileKernel;
C = &(M.getContext());
int LongSize = M.getDataLayout().getPointerSizeInBits();
IntptrTy = Type::getIntNTy(*C, LongSize);
TargetTriple = Triple(M.getTargetTriple());
Mapping = getShadowMapping(TargetTriple, LongSize, this->CompileKernel);
}
bool instrumentModule(Module &);
private:
void initializeCallbacks(Module &M);
bool InstrumentGlobals(IRBuilder<> &IRB, Module &M, bool *CtorComdat);
void InstrumentGlobalsCOFF(IRBuilder<> &IRB, Module &M,
ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers);
void InstrumentGlobalsELF(IRBuilder<> &IRB, Module &M,
ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers,
const std::string &UniqueModuleId);
void InstrumentGlobalsMachO(IRBuilder<> &IRB, Module &M,
ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers);
void
InstrumentGlobalsWithMetadataArray(IRBuilder<> &IRB, Module &M,
ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers);
GlobalVariable *CreateMetadataGlobal(Module &M, Constant *Initializer,
StringRef OriginalName);
void SetComdatForGlobalMetadata(GlobalVariable *G, GlobalVariable *Metadata,
StringRef InternalSuffix);
IRBuilder<> CreateAsanModuleDtor(Module &M);
bool ShouldInstrumentGlobal(GlobalVariable *G);
bool ShouldUseMachOGlobalsSection() const;
StringRef getGlobalMetadataSection() const;
void poisonOneInitializer(Function &GlobalInit, GlobalValue *ModuleName);
void createInitializerPoisonCalls(Module &M, GlobalValue *ModuleName);
size_t MinRedzoneSizeForGlobal() const {
return RedzoneSizeForScale(Mapping.Scale);
}
int GetAsanVersion(const Module &M) const;
GlobalsMetadata GlobalsMD;
bool CompileKernel;
bool Recover;
bool UseGlobalsGC;
bool UsePrivateAlias;
bool UseOdrIndicator;
bool UseCtorComdat;
Type *IntptrTy;
LLVMContext *C;
Triple TargetTriple;
ShadowMapping Mapping;
FunctionCallee AsanPoisonGlobals;
FunctionCallee AsanUnpoisonGlobals;
FunctionCallee AsanRegisterGlobals;
FunctionCallee AsanUnregisterGlobals;
FunctionCallee AsanRegisterImageGlobals;
FunctionCallee AsanUnregisterImageGlobals;
FunctionCallee AsanRegisterElfGlobals;
FunctionCallee AsanUnregisterElfGlobals;
Function *AsanCtorFunction = nullptr;
Function *AsanDtorFunction = nullptr;
};
class ModuleAddressSanitizerLegacyPass : public ModulePass {
public:
static char ID;
explicit ModuleAddressSanitizerLegacyPass(bool CompileKernel = false,
bool Recover = false,
bool UseGlobalGC = true,
bool UseOdrIndicator = false)
: ModulePass(ID), CompileKernel(CompileKernel), Recover(Recover),
UseGlobalGC(UseGlobalGC), UseOdrIndicator(UseOdrIndicator) {
initializeModuleAddressSanitizerLegacyPassPass(
*PassRegistry::getPassRegistry());
}
StringRef getPassName() const override { return "ModuleAddressSanitizer"; }
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<ASanGlobalsMetadataWrapperPass>();
}
bool runOnModule(Module &M) override {
GlobalsMetadata &GlobalsMD =
getAnalysis<ASanGlobalsMetadataWrapperPass>().getGlobalsMD();
ModuleAddressSanitizer ASanModule(M, GlobalsMD, CompileKernel, Recover,
UseGlobalGC, UseOdrIndicator);
return ASanModule.instrumentModule(M);
}
private:
bool CompileKernel;
bool Recover;
bool UseGlobalGC;
bool UseOdrIndicator;
};
// Stack poisoning does not play well with exception handling.
// When an exception is thrown, we essentially bypass the code
// that unpoisones the stack. This is why the run-time library has
// to intercept __cxa_throw (as well as longjmp, etc) and unpoison the entire
// stack in the interceptor. This however does not work inside the
// actual function which catches the exception. Most likely because the
// compiler hoists the load of the shadow value somewhere too high.
// This causes asan to report a non-existing bug on 453.povray.
// It sounds like an LLVM bug.
struct FunctionStackPoisoner : public InstVisitor<FunctionStackPoisoner> {
Function &F;
AddressSanitizer &ASan;
DIBuilder DIB;
LLVMContext *C;
Type *IntptrTy;
Type *IntptrPtrTy;
ShadowMapping Mapping;
SmallVector<AllocaInst *, 16> AllocaVec;
SmallVector<AllocaInst *, 16> StaticAllocasToMoveUp;
SmallVector<Instruction *, 8> RetVec;
unsigned StackAlignment;
FunctionCallee AsanStackMallocFunc[kMaxAsanStackMallocSizeClass + 1],
AsanStackFreeFunc[kMaxAsanStackMallocSizeClass + 1];
FunctionCallee AsanSetShadowFunc[0x100] = {};
FunctionCallee AsanPoisonStackMemoryFunc, AsanUnpoisonStackMemoryFunc;
FunctionCallee AsanAllocaPoisonFunc, AsanAllocasUnpoisonFunc;
// Stores a place and arguments of poisoning/unpoisoning call for alloca.
struct AllocaPoisonCall {
IntrinsicInst *InsBefore;
AllocaInst *AI;
uint64_t Size;
bool DoPoison;
};
SmallVector<AllocaPoisonCall, 8> DynamicAllocaPoisonCallVec;
SmallVector<AllocaPoisonCall, 8> StaticAllocaPoisonCallVec;
SmallVector<AllocaInst *, 1> DynamicAllocaVec;
SmallVector<IntrinsicInst *, 1> StackRestoreVec;
AllocaInst *DynamicAllocaLayout = nullptr;
IntrinsicInst *LocalEscapeCall = nullptr;
// Maps Value to an AllocaInst from which the Value is originated.
using AllocaForValueMapTy = DenseMap<Value *, AllocaInst *>;
AllocaForValueMapTy AllocaForValue;
bool HasNonEmptyInlineAsm = false;
bool HasReturnsTwiceCall = false;
std::unique_ptr<CallInst> EmptyInlineAsm;
FunctionStackPoisoner(Function &F, AddressSanitizer &ASan)
: F(F), ASan(ASan), DIB(*F.getParent(), /*AllowUnresolved*/ false),
C(ASan.C), IntptrTy(ASan.IntptrTy),
IntptrPtrTy(PointerType::get(IntptrTy, 0)), Mapping(ASan.Mapping),
StackAlignment(1 << Mapping.Scale),
EmptyInlineAsm(CallInst::Create(ASan.EmptyAsm)) {}
bool runOnFunction() {
if (!ClStack) return false;
if (ClRedzoneByvalArgs)
copyArgsPassedByValToAllocas();
// Collect alloca, ret, lifetime instructions etc.
for (BasicBlock *BB : depth_first(&F.getEntryBlock())) visit(*BB);
if (AllocaVec.empty() && DynamicAllocaVec.empty()) return false;
initializeCallbacks(*F.getParent());
processDynamicAllocas();
processStaticAllocas();
if (ClDebugStack) {
LLVM_DEBUG(dbgs() << F);
}
return true;
}
// Arguments marked with the "byval" attribute are implicitly copied without
// using an alloca instruction. To produce redzones for those arguments, we
// copy them a second time into memory allocated with an alloca instruction.
void copyArgsPassedByValToAllocas();
// Finds all Alloca instructions and puts
// poisoned red zones around all of them.
// Then unpoison everything back before the function returns.
void processStaticAllocas();
void processDynamicAllocas();
void createDynamicAllocasInitStorage();
// ----------------------- Visitors.
/// Collect all Ret instructions.
void visitReturnInst(ReturnInst &RI) { RetVec.push_back(&RI); }
/// Collect all Resume instructions.
void visitResumeInst(ResumeInst &RI) { RetVec.push_back(&RI); }
/// Collect all CatchReturnInst instructions.
void visitCleanupReturnInst(CleanupReturnInst &CRI) { RetVec.push_back(&CRI); }
void unpoisonDynamicAllocasBeforeInst(Instruction *InstBefore,
Value *SavedStack) {
IRBuilder<> IRB(InstBefore);
Value *DynamicAreaPtr = IRB.CreatePtrToInt(SavedStack, IntptrTy);
// When we insert _asan_allocas_unpoison before @llvm.stackrestore, we
// need to adjust extracted SP to compute the address of the most recent
// alloca. We have a special @llvm.get.dynamic.area.offset intrinsic for
// this purpose.
if (!isa<ReturnInst>(InstBefore)) {
Function *DynamicAreaOffsetFunc = Intrinsic::getDeclaration(
InstBefore->getModule(), Intrinsic::get_dynamic_area_offset,
{IntptrTy});
Value *DynamicAreaOffset = IRB.CreateCall(DynamicAreaOffsetFunc, {});
DynamicAreaPtr = IRB.CreateAdd(IRB.CreatePtrToInt(SavedStack, IntptrTy),
DynamicAreaOffset);
}
IRB.CreateCall(
AsanAllocasUnpoisonFunc,
{IRB.CreateLoad(IntptrTy, DynamicAllocaLayout), DynamicAreaPtr});
}
// Unpoison dynamic allocas redzones.
void unpoisonDynamicAllocas() {
for (auto &Ret : RetVec)
unpoisonDynamicAllocasBeforeInst(Ret, DynamicAllocaLayout);
for (auto &StackRestoreInst : StackRestoreVec)
unpoisonDynamicAllocasBeforeInst(StackRestoreInst,
StackRestoreInst->getOperand(0));
}
// Deploy and poison redzones around dynamic alloca call. To do this, we
// should replace this call with another one with changed parameters and
// replace all its uses with new address, so
// addr = alloca type, old_size, align
// is replaced by
// new_size = (old_size + additional_size) * sizeof(type)
// tmp = alloca i8, new_size, max(align, 32)
// addr = tmp + 32 (first 32 bytes are for the left redzone).
// Additional_size is added to make new memory allocation contain not only
// requested memory, but also left, partial and right redzones.
void handleDynamicAllocaCall(AllocaInst *AI);
/// Collect Alloca instructions we want (and can) handle.
void visitAllocaInst(AllocaInst &AI) {
if (!ASan.isInterestingAlloca(AI)) {
if (AI.isStaticAlloca()) {
// Skip over allocas that are present *before* the first instrumented
// alloca, we don't want to move those around.
if (AllocaVec.empty())
return;
StaticAllocasToMoveUp.push_back(&AI);
}
return;
}
StackAlignment = std::max(StackAlignment, AI.getAlignment());
if (!AI.isStaticAlloca())
DynamicAllocaVec.push_back(&AI);
else
AllocaVec.push_back(&AI);
}
/// Collect lifetime intrinsic calls to check for use-after-scope
/// errors.
void visitIntrinsicInst(IntrinsicInst &II) {
Intrinsic::ID ID = II.getIntrinsicID();
if (ID == Intrinsic::stackrestore) StackRestoreVec.push_back(&II);
if (ID == Intrinsic::localescape) LocalEscapeCall = &II;
if (!ASan.UseAfterScope)
return;
if (!II.isLifetimeStartOrEnd())
return;
// Found lifetime intrinsic, add ASan instrumentation if necessary.
ConstantInt *Size = dyn_cast<ConstantInt>(II.getArgOperand(0));
// If size argument is undefined, don't do anything.
if (Size->isMinusOne()) return;
// Check that size doesn't saturate uint64_t and can
// be stored in IntptrTy.
const uint64_t SizeValue = Size->getValue().getLimitedValue();
if (SizeValue == ~0ULL ||
!ConstantInt::isValueValidForType(IntptrTy, SizeValue))
return;
// Find alloca instruction that corresponds to llvm.lifetime argument.
AllocaInst *AI =
llvm::findAllocaForValue(II.getArgOperand(1), AllocaForValue);
// We're interested only in allocas we can handle.
if (!AI || !ASan.isInterestingAlloca(*AI))
return;
bool DoPoison = (ID == Intrinsic::lifetime_end);
AllocaPoisonCall APC = {&II, AI, SizeValue, DoPoison};
if (AI->isStaticAlloca())
StaticAllocaPoisonCallVec.push_back(APC);
else if (ClInstrumentDynamicAllocas)
DynamicAllocaPoisonCallVec.push_back(APC);
}
void visitCallSite(CallSite CS) {
Instruction *I = CS.getInstruction();
if (CallInst *CI = dyn_cast<CallInst>(I)) {
HasNonEmptyInlineAsm |= CI->isInlineAsm() &&
!CI->isIdenticalTo(EmptyInlineAsm.get()) &&
I != ASan.LocalDynamicShadow;
HasReturnsTwiceCall |= CI->canReturnTwice();
}
}
// ---------------------- Helpers.
void initializeCallbacks(Module &M);
// Copies bytes from ShadowBytes into shadow memory for indexes where
// ShadowMask is not zero. If ShadowMask[i] is zero, we assume that
// ShadowBytes[i] is constantly zero and doesn't need to be overwritten.
void copyToShadow(ArrayRef<uint8_t> ShadowMask, ArrayRef<uint8_t> ShadowBytes,
IRBuilder<> &IRB, Value *ShadowBase);
void copyToShadow(ArrayRef<uint8_t> ShadowMask, ArrayRef<uint8_t> ShadowBytes,
size_t Begin, size_t End, IRBuilder<> &IRB,
Value *ShadowBase);
void copyToShadowInline(ArrayRef<uint8_t> ShadowMask,
ArrayRef<uint8_t> ShadowBytes, size_t Begin,
size_t End, IRBuilder<> &IRB, Value *ShadowBase);
void poisonAlloca(Value *V, uint64_t Size, IRBuilder<> &IRB, bool DoPoison);
Value *createAllocaForLayout(IRBuilder<> &IRB, const ASanStackFrameLayout &L,
bool Dynamic);
PHINode *createPHI(IRBuilder<> &IRB, Value *Cond, Value *ValueIfTrue,
Instruction *ThenTerm, Value *ValueIfFalse);
};
} // end anonymous namespace
void LocationMetadata::parse(MDNode *MDN) {
assert(MDN->getNumOperands() == 3);
MDString *DIFilename = cast<MDString>(MDN->getOperand(0));
Filename = DIFilename->getString();
LineNo = mdconst::extract<ConstantInt>(MDN->getOperand(1))->getLimitedValue();
ColumnNo =
mdconst::extract<ConstantInt>(MDN->getOperand(2))->getLimitedValue();
}
// FIXME: It would be cleaner to instead attach relevant metadata to the globals
// we want to sanitize instead and reading this metadata on each pass over a
// function instead of reading module level metadata at first.
GlobalsMetadata::GlobalsMetadata(Module &M) {
NamedMDNode *Globals = M.getNamedMetadata("llvm.asan.globals");
if (!Globals)
return;
for (auto MDN : Globals->operands()) {
// Metadata node contains the global and the fields of "Entry".
assert(MDN->getNumOperands() == 5);
auto *V = mdconst::extract_or_null<Constant>(MDN->getOperand(0));
// The optimizer may optimize away a global entirely.
if (!V)
continue;
auto *StrippedV = V->stripPointerCasts();
auto *GV = dyn_cast<GlobalVariable>(StrippedV);
if (!GV)
continue;
// We can already have an entry for GV if it was merged with another
// global.
Entry &E = Entries[GV];
if (auto *Loc = cast_or_null<MDNode>(MDN->getOperand(1)))
E.SourceLoc.parse(Loc);
if (auto *Name = cast_or_null<MDString>(MDN->getOperand(2)))
E.Name = Name->getString();
ConstantInt *IsDynInit = mdconst::extract<ConstantInt>(MDN->getOperand(3));
E.IsDynInit |= IsDynInit->isOne();
ConstantInt *IsBlacklisted =
mdconst::extract<ConstantInt>(MDN->getOperand(4));
E.IsBlacklisted |= IsBlacklisted->isOne();
}
}
AnalysisKey ASanGlobalsMetadataAnalysis::Key;
GlobalsMetadata ASanGlobalsMetadataAnalysis::run(Module &M,
ModuleAnalysisManager &AM) {
return GlobalsMetadata(M);
}
AddressSanitizerPass::AddressSanitizerPass(bool CompileKernel, bool Recover,
bool UseAfterScope)
: CompileKernel(CompileKernel), Recover(Recover),
UseAfterScope(UseAfterScope) {}
PreservedAnalyses AddressSanitizerPass::run(Function &F,
AnalysisManager<Function> &AM) {
auto &MAMProxy = AM.getResult<ModuleAnalysisManagerFunctionProxy>(F);
auto &MAM = MAMProxy.getManager();
Module &M = *F.getParent();
if (auto *R = MAM.getCachedResult<ASanGlobalsMetadataAnalysis>(M)) {
const TargetLibraryInfo *TLI = &AM.getResult<TargetLibraryAnalysis>(F);
AddressSanitizer Sanitizer(M, *R, CompileKernel, Recover, UseAfterScope);
if (Sanitizer.instrumentFunction(F, TLI))
return PreservedAnalyses::none();
return PreservedAnalyses::all();
}
report_fatal_error(
"The ASanGlobalsMetadataAnalysis is required to run before "
"AddressSanitizer can run");
return PreservedAnalyses::all();
}
ModuleAddressSanitizerPass::ModuleAddressSanitizerPass(bool CompileKernel,
bool Recover,
bool UseGlobalGC,
bool UseOdrIndicator)
: CompileKernel(CompileKernel), Recover(Recover), UseGlobalGC(UseGlobalGC),
UseOdrIndicator(UseOdrIndicator) {}
PreservedAnalyses ModuleAddressSanitizerPass::run(Module &M,
AnalysisManager<Module> &AM) {
GlobalsMetadata &GlobalsMD = AM.getResult<ASanGlobalsMetadataAnalysis>(M);
ModuleAddressSanitizer Sanitizer(M, GlobalsMD, CompileKernel, Recover,
UseGlobalGC, UseOdrIndicator);
if (Sanitizer.instrumentModule(M))
return PreservedAnalyses::none();
return PreservedAnalyses::all();
}
INITIALIZE_PASS(ASanGlobalsMetadataWrapperPass, "asan-globals-md",
"Read metadata to mark which globals should be instrumented "
"when running ASan.",
false, true)
char AddressSanitizerLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(
AddressSanitizerLegacyPass, "asan",
"AddressSanitizer: detects use-after-free and out-of-bounds bugs.", false,
false)
INITIALIZE_PASS_DEPENDENCY(ASanGlobalsMetadataWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(
AddressSanitizerLegacyPass, "asan",
"AddressSanitizer: detects use-after-free and out-of-bounds bugs.", false,
false)
FunctionPass *llvm::createAddressSanitizerFunctionPass(bool CompileKernel,
bool Recover,
bool UseAfterScope) {
assert(!CompileKernel || Recover);
return new AddressSanitizerLegacyPass(CompileKernel, Recover, UseAfterScope);
}
char ModuleAddressSanitizerLegacyPass::ID = 0;
INITIALIZE_PASS(
ModuleAddressSanitizerLegacyPass, "asan-module",
"AddressSanitizer: detects use-after-free and out-of-bounds bugs."
"ModulePass",
false, false)
ModulePass *llvm::createModuleAddressSanitizerLegacyPassPass(
bool CompileKernel, bool Recover, bool UseGlobalsGC, bool UseOdrIndicator) {
assert(!CompileKernel || Recover);
return new ModuleAddressSanitizerLegacyPass(CompileKernel, Recover,
UseGlobalsGC, UseOdrIndicator);
}
static size_t TypeSizeToSizeIndex(uint32_t TypeSize) {
size_t Res = countTrailingZeros(TypeSize / 8);
assert(Res < kNumberOfAccessSizes);
return Res;
}
/// Create a global describing a source location.
static GlobalVariable *createPrivateGlobalForSourceLoc(Module &M,
LocationMetadata MD) {
Constant *LocData[] = {
createPrivateGlobalForString(M, MD.Filename, true, kAsanGenPrefix),
ConstantInt::get(Type::getInt32Ty(M.getContext()), MD.LineNo),
ConstantInt::get(Type::getInt32Ty(M.getContext()), MD.ColumnNo),
};
auto LocStruct = ConstantStruct::getAnon(LocData);
auto GV = new GlobalVariable(M, LocStruct->getType(), true,
GlobalValue::PrivateLinkage, LocStruct,
kAsanGenPrefix);
GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global);
return GV;
}
/// Check if \p G has been created by a trusted compiler pass.
static bool GlobalWasGeneratedByCompiler(GlobalVariable *G) {
// Do not instrument @llvm.global_ctors, @llvm.used, etc.
if (G->getName().startswith("llvm."))
return true;
// Do not instrument asan globals.
if (G->getName().startswith(kAsanGenPrefix) ||
G->getName().startswith(kSanCovGenPrefix) ||
G->getName().startswith(kODRGenPrefix))
return true;
// Do not instrument gcov counter arrays.
if (G->getName() == "__llvm_gcov_ctr")
return true;
return false;
}
Value *AddressSanitizer::memToShadow(Value *Shadow, IRBuilder<> &IRB) {
// Shadow >> scale
Shadow = IRB.CreateLShr(Shadow, Mapping.Scale);
if (Mapping.Offset == 0) return Shadow;
// (Shadow >> scale) | offset
Value *ShadowBase;
if (LocalDynamicShadow)
ShadowBase = LocalDynamicShadow;
else
ShadowBase = ConstantInt::get(IntptrTy, Mapping.Offset);
if (Mapping.OrShadowOffset)
return IRB.CreateOr(Shadow, ShadowBase);
else
return IRB.CreateAdd(Shadow, ShadowBase);
}
// Instrument memset/memmove/memcpy
void AddressSanitizer::instrumentMemIntrinsic(MemIntrinsic *MI) {
IRBuilder<> IRB(MI);
if (isa<MemTransferInst>(MI)) {
IRB.CreateCall(
isa<MemMoveInst>(MI) ? AsanMemmove : AsanMemcpy,
{IRB.CreatePointerCast(MI->getOperand(0), IRB.getInt8PtrTy()),
IRB.CreatePointerCast(MI->getOperand(1), IRB.getInt8PtrTy()),
IRB.CreateIntCast(MI->getOperand(2), IntptrTy, false)});
} else if (isa<MemSetInst>(MI)) {
IRB.CreateCall(
AsanMemset,
{IRB.CreatePointerCast(MI->getOperand(0), IRB.getInt8PtrTy()),
IRB.CreateIntCast(MI->getOperand(1), IRB.getInt32Ty(), false),
IRB.CreateIntCast(MI->getOperand(2), IntptrTy, false)});
}
MI->eraseFromParent();
}
/// Check if we want (and can) handle this alloca.
bool AddressSanitizer::isInterestingAlloca(const AllocaInst &AI) {
auto PreviouslySeenAllocaInfo = ProcessedAllocas.find(&AI);
if (PreviouslySeenAllocaInfo != ProcessedAllocas.end())
return PreviouslySeenAllocaInfo->getSecond();
bool IsInteresting =
(AI.getAllocatedType()->isSized() &&
// alloca() may be called with 0 size, ignore it.
((!AI.isStaticAlloca()) || getAllocaSizeInBytes(AI) > 0) &&
// We are only interested in allocas not promotable to registers.
// Promotable allocas are common under -O0.
(!ClSkipPromotableAllocas || !isAllocaPromotable(&AI)) &&
// inalloca allocas are not treated as static, and we don't want
// dynamic alloca instrumentation for them as well.
!AI.isUsedWithInAlloca() &&
// swifterror allocas are register promoted by ISel
!AI.isSwiftError());
ProcessedAllocas[&AI] = IsInteresting;
return IsInteresting;
}
Value *AddressSanitizer::isInterestingMemoryAccess(Instruction *I,
bool *IsWrite,
uint64_t *TypeSize,
unsigned *Alignment,
Value **MaybeMask) {
// Skip memory accesses inserted by another instrumentation.
if (I->getMetadata("nosanitize")) return nullptr;
// Do not instrument the load fetching the dynamic shadow address.
if (LocalDynamicShadow == I)
return nullptr;
Value *PtrOperand = nullptr;
const DataLayout &DL = I->getModule()->getDataLayout();
if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
if (!ClInstrumentReads) return nullptr;
*IsWrite = false;
*TypeSize = DL.getTypeStoreSizeInBits(LI->getType());
*Alignment = LI->getAlignment();
PtrOperand = LI->getPointerOperand();
} else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
if (!ClInstrumentWrites) return nullptr;
*IsWrite = true;
*TypeSize = DL.getTypeStoreSizeInBits(SI->getValueOperand()->getType());
*Alignment = SI->getAlignment();
PtrOperand = SI->getPointerOperand();
} else if (AtomicRMWInst *RMW = dyn_cast<AtomicRMWInst>(I)) {
if (!ClInstrumentAtomics) return nullptr;
*IsWrite = true;
*TypeSize = DL.getTypeStoreSizeInBits(RMW->getValOperand()->getType());
*Alignment = 0;
PtrOperand = RMW->getPointerOperand();
} else if (AtomicCmpXchgInst *XCHG = dyn_cast<AtomicCmpXchgInst>(I)) {
if (!ClInstrumentAtomics) return nullptr;
*IsWrite = true;
*TypeSize = DL.getTypeStoreSizeInBits(XCHG->getCompareOperand()->getType());
*Alignment = 0;
PtrOperand = XCHG->getPointerOperand();
} else if (auto CI = dyn_cast<CallInst>(I)) {
auto *F = dyn_cast<Function>(CI->getCalledValue());
if (F && (F->getName().startswith("llvm.masked.load.") ||
F->getName().startswith("llvm.masked.store."))) {
unsigned OpOffset = 0;
if (F->getName().startswith("llvm.masked.store.")) {
if (!ClInstrumentWrites)
return nullptr;
// Masked store has an initial operand for the value.
OpOffset = 1;
*IsWrite = true;
} else {
if (!ClInstrumentReads)
return nullptr;
*IsWrite = false;
}
auto BasePtr = CI->getOperand(0 + OpOffset);
auto Ty = cast<PointerType>(BasePtr->getType())->getElementType();
*TypeSize = DL.getTypeStoreSizeInBits(Ty);
if (auto AlignmentConstant =
dyn_cast<ConstantInt>(CI->getOperand(1 + OpOffset)))
*Alignment = (unsigned)AlignmentConstant->getZExtValue();
else
*Alignment = 1; // No alignment guarantees. We probably got Undef
if (MaybeMask)
*MaybeMask = CI->getOperand(2 + OpOffset);
PtrOperand = BasePtr;
}
}
if (PtrOperand) {
// Do not instrument acesses from different address spaces; we cannot deal
// with them.
Type *PtrTy = cast<PointerType>(PtrOperand->getType()->getScalarType());
if (PtrTy->getPointerAddressSpace() != 0)
return nullptr;
// Ignore swifterror addresses.
// swifterror memory addresses are mem2reg promoted by instruction
// selection. As such they cannot have regular uses like an instrumentation
// function and it makes no sense to track them as memory.
if (PtrOperand->isSwiftError())
return nullptr;
}
// Treat memory accesses to promotable allocas as non-interesting since they
// will not cause memory violations. This greatly speeds up the instrumented
// executable at -O0.
if (ClSkipPromotableAllocas)
if (auto AI = dyn_cast_or_null<AllocaInst>(PtrOperand))
return isInterestingAlloca(*AI) ? AI : nullptr;
return PtrOperand;
}
static bool isPointerOperand(Value *V) {
return V->getType()->isPointerTy() || isa<PtrToIntInst>(V);
}
// This is a rough heuristic; it may cause both false positives and
// false negatives. The proper implementation requires cooperation with
// the frontend.
static bool isInterestingPointerComparison(Instruction *I) {
if (ICmpInst *Cmp = dyn_cast<ICmpInst>(I)) {
if (!Cmp->isRelational())
return false;
} else {
return false;
}
return isPointerOperand(I->getOperand(0)) &&
isPointerOperand(I->getOperand(1));
}
// This is a rough heuristic; it may cause both false positives and
// false negatives. The proper implementation requires cooperation with
// the frontend.
static bool isInterestingPointerSubtraction(Instruction *I) {
if (BinaryOperator *BO = dyn_cast<BinaryOperator>(I)) {
if (BO->getOpcode() != Instruction::Sub)
return false;
} else {
return false;
}
return isPointerOperand(I->getOperand(0)) &&
isPointerOperand(I->getOperand(1));
}
bool AddressSanitizer::GlobalIsLinkerInitialized(GlobalVariable *G) {
// If a global variable does not have dynamic initialization we don't
// have to instrument it. However, if a global does not have initializer
// at all, we assume it has dynamic initializer (in other TU).
//
// FIXME: Metadata should be attched directly to the global directly instead
// of being added to llvm.asan.globals.
return G->hasInitializer() && !GlobalsMD.get(G).IsDynInit;
}
void AddressSanitizer::instrumentPointerComparisonOrSubtraction(
Instruction *I) {
IRBuilder<> IRB(I);
FunctionCallee F = isa<ICmpInst>(I) ? AsanPtrCmpFunction : AsanPtrSubFunction;
Value *Param[2] = {I->getOperand(0), I->getOperand(1)};
for (Value *&i : Param) {
if (i->getType()->isPointerTy())
i = IRB.CreatePointerCast(i, IntptrTy);
}
IRB.CreateCall(F, Param);
}
static void doInstrumentAddress(AddressSanitizer *Pass, Instruction *I,
Instruction *InsertBefore, Value *Addr,
unsigned Alignment, unsigned Granularity,
uint32_t TypeSize, bool IsWrite,
Value *SizeArgument, bool UseCalls,
uint32_t Exp) {
// Instrument a 1-, 2-, 4-, 8-, or 16- byte access with one check
// if the data is properly aligned.
if ((TypeSize == 8 || TypeSize == 16 || TypeSize == 32 || TypeSize == 64 ||
TypeSize == 128) &&
(Alignment >= Granularity || Alignment == 0 || Alignment >= TypeSize / 8))
return Pass->instrumentAddress(I, InsertBefore, Addr, TypeSize, IsWrite,
nullptr, UseCalls, Exp);
Pass->instrumentUnusualSizeOrAlignment(I, InsertBefore, Addr, TypeSize,
IsWrite, nullptr, UseCalls, Exp);
}
static void instrumentMaskedLoadOrStore(AddressSanitizer *Pass,
const DataLayout &DL, Type *IntptrTy,
Value *Mask, Instruction *I,
Value *Addr, unsigned Alignment,
unsigned Granularity, uint32_t TypeSize,
bool IsWrite, Value *SizeArgument,
bool UseCalls, uint32_t Exp) {
auto *VTy = cast<PointerType>(Addr->getType())->getElementType();
uint64_t ElemTypeSize = DL.getTypeStoreSizeInBits(VTy->getScalarType());
unsigned Num = VTy->getVectorNumElements();
auto Zero = ConstantInt::get(IntptrTy, 0);
for (unsigned Idx = 0; Idx < Num; ++Idx) {
Value *InstrumentedAddress = nullptr;
Instruction *InsertBefore = I;
if (auto *Vector = dyn_cast<ConstantVector>(Mask)) {
// dyn_cast as we might get UndefValue
if (auto *Masked = dyn_cast<ConstantInt>(Vector->getOperand(Idx))) {
if (Masked->isZero())
// Mask is constant false, so no instrumentation needed.
continue;
// If we have a true or undef value, fall through to doInstrumentAddress
// with InsertBefore == I
}
} else {
IRBuilder<> IRB(I);
Value *MaskElem = IRB.CreateExtractElement(Mask, Idx);
Instruction *ThenTerm = SplitBlockAndInsertIfThen(MaskElem, I, false);
InsertBefore = ThenTerm;
}
IRBuilder<> IRB(InsertBefore);
InstrumentedAddress =
IRB.CreateGEP(VTy, Addr, {Zero, ConstantInt::get(IntptrTy, Idx)});
doInstrumentAddress(Pass, I, InsertBefore, InstrumentedAddress, Alignment,
Granularity, ElemTypeSize, IsWrite, SizeArgument,
UseCalls, Exp);
}
}
void AddressSanitizer::instrumentMop(ObjectSizeOffsetVisitor &ObjSizeVis,
Instruction *I, bool UseCalls,
const DataLayout &DL) {
bool IsWrite = false;
unsigned Alignment = 0;
uint64_t TypeSize = 0;
Value *MaybeMask = nullptr;
Value *Addr =
isInterestingMemoryAccess(I, &IsWrite, &TypeSize, &Alignment, &MaybeMask);
assert(Addr);
// Optimization experiments.
// The experiments can be used to evaluate potential optimizations that remove
// instrumentation (assess false negatives). Instead of completely removing
// some instrumentation, you set Exp to a non-zero value (mask of optimization
// experiments that want to remove instrumentation of this instruction).
// If Exp is non-zero, this pass will emit special calls into runtime
// (e.g. __asan_report_exp_load1 instead of __asan_report_load1). These calls
// make runtime terminate the program in a special way (with a different
// exit status). Then you run the new compiler on a buggy corpus, collect
// the special terminations (ideally, you don't see them at all -- no false
// negatives) and make the decision on the optimization.
uint32_t Exp = ClForceExperiment;
if (ClOpt && ClOptGlobals) {
// If initialization order checking is disabled, a simple access to a
// dynamically initialized global is always valid.
GlobalVariable *G = dyn_cast<GlobalVariable>(GetUnderlyingObject(Addr, DL));
if (G && (!ClInitializers || GlobalIsLinkerInitialized(G)) &&
isSafeAccess(ObjSizeVis, Addr, TypeSize)) {
NumOptimizedAccessesToGlobalVar++;
return;
}
}
if (ClOpt && ClOptStack) {
// A direct inbounds access to a stack variable is always valid.
if (isa<AllocaInst>(GetUnderlyingObject(Addr, DL)) &&
isSafeAccess(ObjSizeVis, Addr, TypeSize)) {
NumOptimizedAccessesToStackVar++;
return;
}
}
if (IsWrite)
NumInstrumentedWrites++;
else
NumInstrumentedReads++;
unsigned Granularity = 1 << Mapping.Scale;
if (MaybeMask) {
instrumentMaskedLoadOrStore(this, DL, IntptrTy, MaybeMask, I, Addr,
Alignment, Granularity, TypeSize, IsWrite,
nullptr, UseCalls, Exp);
} else {
doInstrumentAddress(this, I, I, Addr, Alignment, Granularity, TypeSize,
IsWrite, nullptr, UseCalls, Exp);
}
}
Instruction *AddressSanitizer::generateCrashCode(Instruction *InsertBefore,
Value *Addr, bool IsWrite,
size_t AccessSizeIndex,
Value *SizeArgument,
uint32_t Exp) {
IRBuilder<> IRB(InsertBefore);
Value *ExpVal = Exp == 0 ? nullptr : ConstantInt::get(IRB.getInt32Ty(), Exp);
CallInst *Call = nullptr;
if (SizeArgument) {
if (Exp == 0)
Call = IRB.CreateCall(AsanErrorCallbackSized[IsWrite][0],
{Addr, SizeArgument});
else
Call = IRB.CreateCall(AsanErrorCallbackSized[IsWrite][1],
{Addr, SizeArgument, ExpVal});
} else {
if (Exp == 0)
Call =
IRB.CreateCall(AsanErrorCallback[IsWrite][0][AccessSizeIndex], Addr);
else
Call = IRB.CreateCall(AsanErrorCallback[IsWrite][1][AccessSizeIndex],
{Addr, ExpVal});
}
// We don't do Call->setDoesNotReturn() because the BB already has
// UnreachableInst at the end.
// This EmptyAsm is required to avoid callback merge.
IRB.CreateCall(EmptyAsm, {});
return Call;
}
Value *AddressSanitizer::createSlowPathCmp(IRBuilder<> &IRB, Value *AddrLong,
Value *ShadowValue,
uint32_t TypeSize) {
size_t Granularity = static_cast<size_t>(1) << Mapping.Scale;
// Addr & (Granularity - 1)
Value *LastAccessedByte =
IRB.CreateAnd(AddrLong, ConstantInt::get(IntptrTy, Granularity - 1));
// (Addr & (Granularity - 1)) + size - 1
if (TypeSize / 8 > 1)
LastAccessedByte = IRB.CreateAdd(
LastAccessedByte, ConstantInt::get(IntptrTy, TypeSize / 8 - 1));
// (uint8_t) ((Addr & (Granularity-1)) + size - 1)
LastAccessedByte =
IRB.CreateIntCast(LastAccessedByte, ShadowValue->getType(), false);
// ((uint8_t) ((Addr & (Granularity-1)) + size - 1)) >= ShadowValue
return IRB.CreateICmpSGE(LastAccessedByte, ShadowValue);
}
void AddressSanitizer::instrumentAddress(Instruction *OrigIns,
Instruction *InsertBefore, Value *Addr,
uint32_t TypeSize, bool IsWrite,
Value *SizeArgument, bool UseCalls,
uint32_t Exp) {
bool IsMyriad = TargetTriple.getVendor() == llvm::Triple::Myriad;
IRBuilder<> IRB(InsertBefore);
Value *AddrLong = IRB.CreatePointerCast(Addr, IntptrTy);
size_t AccessSizeIndex = TypeSizeToSizeIndex(TypeSize);
if (UseCalls) {
if (Exp == 0)
IRB.CreateCall(AsanMemoryAccessCallback[IsWrite][0][AccessSizeIndex],
AddrLong);
else
IRB.CreateCall(AsanMemoryAccessCallback[IsWrite][1][AccessSizeIndex],
{AddrLong, ConstantInt::get(IRB.getInt32Ty(), Exp)});
return;
}
if (IsMyriad) {
// Strip the cache bit and do range check.
// AddrLong &= ~kMyriadCacheBitMask32
AddrLong = IRB.CreateAnd(AddrLong, ~kMyriadCacheBitMask32);
// Tag = AddrLong >> kMyriadTagShift
Value *Tag = IRB.CreateLShr(AddrLong, kMyriadTagShift);
// Tag == kMyriadDDRTag
Value *TagCheck =
IRB.CreateICmpEQ(Tag, ConstantInt::get(IntptrTy, kMyriadDDRTag));
Instruction *TagCheckTerm =
SplitBlockAndInsertIfThen(TagCheck, InsertBefore, false,
MDBuilder(*C).createBranchWeights(1, 100000));
assert(cast<BranchInst>(TagCheckTerm)->isUnconditional());
IRB.SetInsertPoint(TagCheckTerm);
InsertBefore = TagCheckTerm;
}
Type *ShadowTy =
IntegerType::get(*C, std::max(8U, TypeSize >> Mapping.Scale));
Type *ShadowPtrTy = PointerType::get(ShadowTy, 0);
Value *ShadowPtr = memToShadow(AddrLong, IRB);
Value *CmpVal = Constant::getNullValue(ShadowTy);
Value *ShadowValue =
IRB.CreateLoad(ShadowTy, IRB.CreateIntToPtr(ShadowPtr, ShadowPtrTy));
Value *Cmp = IRB.CreateICmpNE(ShadowValue, CmpVal);
size_t Granularity = 1ULL << Mapping.Scale;
Instruction *CrashTerm = nullptr;
if (ClAlwaysSlowPath || (TypeSize < 8 * Granularity)) {
// We use branch weights for the slow path check, to indicate that the slow
// path is rarely taken. This seems to be the case for SPEC benchmarks.
Instruction *CheckTerm = SplitBlockAndInsertIfThen(
Cmp, InsertBefore, false, MDBuilder(*C).createBranchWeights(1, 100000));
assert(cast<BranchInst>(CheckTerm)->isUnconditional());
BasicBlock *NextBB = CheckTerm->getSuccessor(0);
IRB.SetInsertPoint(CheckTerm);
Value *Cmp2 = createSlowPathCmp(IRB, AddrLong, ShadowValue, TypeSize);
if (Recover) {
CrashTerm = SplitBlockAndInsertIfThen(Cmp2, CheckTerm, false);
} else {
BasicBlock *CrashBlock =
BasicBlock::Create(*C, "", NextBB->getParent(), NextBB);
CrashTerm = new UnreachableInst(*C, CrashBlock);
BranchInst *NewTerm = BranchInst::Create(CrashBlock, NextBB, Cmp2);
ReplaceInstWithInst(CheckTerm, NewTerm);
}
} else {
CrashTerm = SplitBlockAndInsertIfThen(Cmp, InsertBefore, !Recover);
}
Instruction *Crash = generateCrashCode(CrashTerm, AddrLong, IsWrite,
AccessSizeIndex, SizeArgument, Exp);
Crash->setDebugLoc(OrigIns->getDebugLoc());
}
// Instrument unusual size or unusual alignment.
// We can not do it with a single check, so we do 1-byte check for the first
// and the last bytes. We call __asan_report_*_n(addr, real_size) to be able
// to report the actual access size.
void AddressSanitizer::instrumentUnusualSizeOrAlignment(
Instruction *I, Instruction *InsertBefore, Value *Addr, uint32_t TypeSize,
bool IsWrite, Value *SizeArgument, bool UseCalls, uint32_t Exp) {
IRBuilder<> IRB(InsertBefore);
Value *Size = ConstantInt::get(IntptrTy, TypeSize / 8);
Value *AddrLong = IRB.CreatePointerCast(Addr, IntptrTy);
if (UseCalls) {
if (Exp == 0)
IRB.CreateCall(AsanMemoryAccessCallbackSized[IsWrite][0],
{AddrLong, Size});
else
IRB.CreateCall(AsanMemoryAccessCallbackSized[IsWrite][1],
{AddrLong, Size, ConstantInt::get(IRB.getInt32Ty(), Exp)});
} else {
Value *LastByte = IRB.CreateIntToPtr(
IRB.CreateAdd(AddrLong, ConstantInt::get(IntptrTy, TypeSize / 8 - 1)),
Addr->getType());
instrumentAddress(I, InsertBefore, Addr, 8, IsWrite, Size, false, Exp);
instrumentAddress(I, InsertBefore, LastByte, 8, IsWrite, Size, false, Exp);
}
}
void ModuleAddressSanitizer::poisonOneInitializer(Function &GlobalInit,
GlobalValue *ModuleName) {
// Set up the arguments to our poison/unpoison functions.
IRBuilder<> IRB(&GlobalInit.front(),
GlobalInit.front().getFirstInsertionPt());
// Add a call to poison all external globals before the given function starts.
Value *ModuleNameAddr = ConstantExpr::getPointerCast(ModuleName, IntptrTy);
IRB.CreateCall(AsanPoisonGlobals, ModuleNameAddr);
// Add calls to unpoison all globals before each return instruction.
for (auto &BB : GlobalInit.getBasicBlockList())
if (ReturnInst *RI = dyn_cast<ReturnInst>(BB.getTerminator()))
CallInst::Create(AsanUnpoisonGlobals, "", RI);
}
void ModuleAddressSanitizer::createInitializerPoisonCalls(
Module &M, GlobalValue *ModuleName) {
GlobalVariable *GV = M.getGlobalVariable("llvm.global_ctors");
if (!GV)
return;
ConstantArray *CA = dyn_cast<ConstantArray>(GV->getInitializer());
if (!CA)
return;
for (Use &OP : CA->operands()) {
if (isa<ConstantAggregateZero>(OP)) continue;
ConstantStruct *CS = cast<ConstantStruct>(OP);
// Must have a function or null ptr.
if (Function *F = dyn_cast<Function>(CS->getOperand(1))) {
if (F->getName() == kAsanModuleCtorName) continue;
ConstantInt *Priority = dyn_cast<ConstantInt>(CS->getOperand(0));
// Don't instrument CTORs that will run before asan.module_ctor.
if (Priority->getLimitedValue() <= kAsanCtorAndDtorPriority) continue;
poisonOneInitializer(*F, ModuleName);
}
}
}
bool ModuleAddressSanitizer::ShouldInstrumentGlobal(GlobalVariable *G) {
Type *Ty = G->getValueType();
LLVM_DEBUG(dbgs() << "GLOBAL: " << *G << "\n");
// FIXME: Metadata should be attched directly to the global directly instead
// of being added to llvm.asan.globals.
if (GlobalsMD.get(G).IsBlacklisted) return false;
if (!Ty->isSized()) return false;
if (!G->hasInitializer()) return false;
if (GlobalWasGeneratedByCompiler(G)) return false; // Our own globals.
// Two problems with thread-locals:
// - The address of the main thread's copy can't be computed at link-time.
// - Need to poison all copies, not just the main thread's one.
if (G->isThreadLocal()) return false;
// For now, just ignore this Global if the alignment is large.
if (G->getAlignment() > MinRedzoneSizeForGlobal()) return false;
// For non-COFF targets, only instrument globals known to be defined by this
// TU.
// FIXME: We can instrument comdat globals on ELF if we are using the
// GC-friendly metadata scheme.
if (!TargetTriple.isOSBinFormatCOFF()) {
if (!G->hasExactDefinition() || G->hasComdat())
return false;
} else {
// On COFF, don't instrument non-ODR linkages.
if (G->isInterposable())
return false;
}
// If a comdat is present, it must have a selection kind that implies ODR
// semantics: no duplicates, any, or exact match.
if (Comdat *C = G->getComdat()) {
switch (C->getSelectionKind()) {
case Comdat::Any:
case Comdat::ExactMatch:
case Comdat::NoDuplicates:
break;
case Comdat::Largest:
case Comdat::SameSize:
return false;
}
}
if (G->hasSection()) {
StringRef Section = G->getSection();
// Globals from llvm.metadata aren't emitted, do not instrument them.
if (Section == "llvm.metadata") return false;
// Do not instrument globals from special LLVM sections.
if (Section.find("__llvm") != StringRef::npos || Section.find("__LLVM") != StringRef::npos) return false;
// Do not instrument function pointers to initialization and termination
// routines: dynamic linker will not properly handle redzones.
if (Section.startswith(".preinit_array") ||
Section.startswith(".init_array") ||
Section.startswith(".fini_array")) {
return false;
}
// On COFF, if the section name contains '$', it is highly likely that the
// user is using section sorting to create an array of globals similar to
// the way initialization callbacks are registered in .init_array and
// .CRT$XCU. The ATL also registers things in .ATL$__[azm]. Adding redzones
// to such globals is counterproductive, because the intent is that they
// will form an array, and out-of-bounds accesses are expected.
// See https://github.com/google/sanitizers/issues/305
// and http://msdn.microsoft.com/en-US/en-en/library/bb918180(v=vs.120).aspx
if (TargetTriple.isOSBinFormatCOFF() && Section.contains('$')) {
LLVM_DEBUG(dbgs() << "Ignoring global in sorted section (contains '$'): "
<< *G << "\n");
return false;
}
if (TargetTriple.isOSBinFormatMachO()) {
StringRef ParsedSegment, ParsedSection;
unsigned TAA = 0, StubSize = 0;
bool TAAParsed;
std::string ErrorCode = MCSectionMachO::ParseSectionSpecifier(
Section, ParsedSegment, ParsedSection, TAA, TAAParsed, StubSize);
assert(ErrorCode.empty() && "Invalid section specifier.");
// Ignore the globals from the __OBJC section. The ObjC runtime assumes
// those conform to /usr/lib/objc/runtime.h, so we can't add redzones to
// them.
if (ParsedSegment == "__OBJC" ||
(ParsedSegment == "__DATA" && ParsedSection.startswith("__objc_"))) {
LLVM_DEBUG(dbgs() << "Ignoring ObjC runtime global: " << *G << "\n");
return false;
}
// See https://github.com/google/sanitizers/issues/32
// Constant CFString instances are compiled in the following way:
// -- the string buffer is emitted into
// __TEXT,__cstring,cstring_literals
// -- the constant NSConstantString structure referencing that buffer
// is placed into __DATA,__cfstring
// Therefore there's no point in placing redzones into __DATA,__cfstring.
// Moreover, it causes the linker to crash on OS X 10.7
if (ParsedSegment == "__DATA" && ParsedSection == "__cfstring") {
LLVM_DEBUG(dbgs() << "Ignoring CFString: " << *G << "\n");
return false;
}
// The linker merges the contents of cstring_literals and removes the
// trailing zeroes.
if (ParsedSegment == "__TEXT" && (TAA & MachO::S_CSTRING_LITERALS)) {
LLVM_DEBUG(dbgs() << "Ignoring a cstring literal: " << *G << "\n");
return false;
}
}
}
return true;
}
// On Mach-O platforms, we emit global metadata in a separate section of the
// binary in order to allow the linker to properly dead strip. This is only
// supported on recent versions of ld64.
bool ModuleAddressSanitizer::ShouldUseMachOGlobalsSection() const {
if (!TargetTriple.isOSBinFormatMachO())
return false;
if (TargetTriple.isMacOSX() && !TargetTriple.isMacOSXVersionLT(10, 11))
return true;
if (TargetTriple.isiOS() /* or tvOS */ && !TargetTriple.isOSVersionLT(9))
return true;
if (TargetTriple.isWatchOS() && !TargetTriple.isOSVersionLT(2))
return true;
return false;
}
StringRef ModuleAddressSanitizer::getGlobalMetadataSection() const {
switch (TargetTriple.getObjectFormat()) {
case Triple::COFF: return ".ASAN$GL";
case Triple::ELF: return "asan_globals";
case Triple::MachO: return "__DATA,__asan_globals,regular";
default: break;
}
llvm_unreachable("unsupported object format");
}
void ModuleAddressSanitizer::initializeCallbacks(Module &M) {
IRBuilder<> IRB(*C);
// Declare our poisoning and unpoisoning functions.
AsanPoisonGlobals =
M.getOrInsertFunction(kAsanPoisonGlobalsName, IRB.getVoidTy(), IntptrTy);
AsanUnpoisonGlobals =
M.getOrInsertFunction(kAsanUnpoisonGlobalsName, IRB.getVoidTy());
// Declare functions that register/unregister globals.
AsanRegisterGlobals = M.getOrInsertFunction(
kAsanRegisterGlobalsName, IRB.getVoidTy(), IntptrTy, IntptrTy);
AsanUnregisterGlobals = M.getOrInsertFunction(
kAsanUnregisterGlobalsName, IRB.getVoidTy(), IntptrTy, IntptrTy);
// Declare the functions that find globals in a shared object and then invoke
// the (un)register function on them.
AsanRegisterImageGlobals = M.getOrInsertFunction(
kAsanRegisterImageGlobalsName, IRB.getVoidTy(), IntptrTy);
AsanUnregisterImageGlobals = M.getOrInsertFunction(
kAsanUnregisterImageGlobalsName, IRB.getVoidTy(), IntptrTy);
AsanRegisterElfGlobals =
M.getOrInsertFunction(kAsanRegisterElfGlobalsName, IRB.getVoidTy(),
IntptrTy, IntptrTy, IntptrTy);
AsanUnregisterElfGlobals =
M.getOrInsertFunction(kAsanUnregisterElfGlobalsName, IRB.getVoidTy(),
IntptrTy, IntptrTy, IntptrTy);
}
// Put the metadata and the instrumented global in the same group. This ensures
// that the metadata is discarded if the instrumented global is discarded.
void ModuleAddressSanitizer::SetComdatForGlobalMetadata(
GlobalVariable *G, GlobalVariable *Metadata, StringRef InternalSuffix) {
Module &M = *G->getParent();
Comdat *C = G->getComdat();
if (!C) {
if (!G->hasName()) {
// If G is unnamed, it must be internal. Give it an artificial name
// so we can put it in a comdat.
assert(G->hasLocalLinkage());
G->setName(Twine(kAsanGenPrefix) + "_anon_global");
}
if (!InternalSuffix.empty() && G->hasLocalLinkage()) {
std::string Name = G->getName();
Name += InternalSuffix;
C = M.getOrInsertComdat(Name);
} else {
C = M.getOrInsertComdat(G->getName());
}
// Make this IMAGE_COMDAT_SELECT_NODUPLICATES on COFF. Also upgrade private
// linkage to internal linkage so that a symbol table entry is emitted. This
// is necessary in order to create the comdat group.
if (TargetTriple.isOSBinFormatCOFF()) {
C->setSelectionKind(Comdat::NoDuplicates);
if (G->hasPrivateLinkage())
G->setLinkage(GlobalValue::InternalLinkage);
}
G->setComdat(C);
}
assert(G->hasComdat());
Metadata->setComdat(G->getComdat());
}
// Create a separate metadata global and put it in the appropriate ASan
// global registration section.
GlobalVariable *
ModuleAddressSanitizer::CreateMetadataGlobal(Module &M, Constant *Initializer,
StringRef OriginalName) {
auto Linkage = TargetTriple.isOSBinFormatMachO()
? GlobalVariable::InternalLinkage
: GlobalVariable::PrivateLinkage;
GlobalVariable *Metadata = new GlobalVariable(
M, Initializer->getType(), false, Linkage, Initializer,
Twine("__asan_global_") + GlobalValue::dropLLVMManglingEscape(OriginalName));
Metadata->setSection(getGlobalMetadataSection());
return Metadata;
}
IRBuilder<> ModuleAddressSanitizer::CreateAsanModuleDtor(Module &M) {
AsanDtorFunction =
Function::Create(FunctionType::get(Type::getVoidTy(*C), false),
GlobalValue::InternalLinkage, kAsanModuleDtorName, &M);
BasicBlock *AsanDtorBB = BasicBlock::Create(*C, "", AsanDtorFunction);
return IRBuilder<>(ReturnInst::Create(*C, AsanDtorBB));
}
void ModuleAddressSanitizer::InstrumentGlobalsCOFF(
IRBuilder<> &IRB, Module &M, ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers) {
assert(ExtendedGlobals.size() == MetadataInitializers.size());
auto &DL = M.getDataLayout();
for (size_t i = 0; i < ExtendedGlobals.size(); i++) {
Constant *Initializer = MetadataInitializers[i];
GlobalVariable *G = ExtendedGlobals[i];
GlobalVariable *Metadata =
CreateMetadataGlobal(M, Initializer, G->getName());
// The MSVC linker always inserts padding when linking incrementally. We
// cope with that by aligning each struct to its size, which must be a power
// of two.
unsigned SizeOfGlobalStruct = DL.getTypeAllocSize(Initializer->getType());
assert(isPowerOf2_32(SizeOfGlobalStruct) &&
"global metadata will not be padded appropriately");
Metadata->setAlignment(SizeOfGlobalStruct);
SetComdatForGlobalMetadata(G, Metadata, "");
}
}
void ModuleAddressSanitizer::InstrumentGlobalsELF(
IRBuilder<> &IRB, Module &M, ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers,
const std::string &UniqueModuleId) {
assert(ExtendedGlobals.size() == MetadataInitializers.size());
SmallVector<GlobalValue *, 16> MetadataGlobals(ExtendedGlobals.size());
for (size_t i = 0; i < ExtendedGlobals.size(); i++) {
GlobalVariable *G = ExtendedGlobals[i];
GlobalVariable *Metadata =
CreateMetadataGlobal(M, MetadataInitializers[i], G->getName());
MDNode *MD = MDNode::get(M.getContext(), ValueAsMetadata::get(G));
Metadata->setMetadata(LLVMContext::MD_associated, MD);
MetadataGlobals[i] = Metadata;
SetComdatForGlobalMetadata(G, Metadata, UniqueModuleId);
}
// Update llvm.compiler.used, adding the new metadata globals. This is
// needed so that during LTO these variables stay alive.
if (!MetadataGlobals.empty())
appendToCompilerUsed(M, MetadataGlobals);
// RegisteredFlag serves two purposes. First, we can pass it to dladdr()
// to look up the loaded image that contains it. Second, we can store in it
// whether registration has already occurred, to prevent duplicate
// registration.
//
// Common linkage ensures that there is only one global per shared library.
GlobalVariable *RegisteredFlag = new GlobalVariable(
M, IntptrTy, false, GlobalVariable::CommonLinkage,
ConstantInt::get(IntptrTy, 0), kAsanGlobalsRegisteredFlagName);
RegisteredFlag->setVisibility(GlobalVariable::HiddenVisibility);
// Create start and stop symbols.
GlobalVariable *StartELFMetadata = new GlobalVariable(
M, IntptrTy, false, GlobalVariable::ExternalWeakLinkage, nullptr,
"__start_" + getGlobalMetadataSection());
StartELFMetadata->setVisibility(GlobalVariable::HiddenVisibility);
GlobalVariable *StopELFMetadata = new GlobalVariable(
M, IntptrTy, false, GlobalVariable::ExternalWeakLinkage, nullptr,
"__stop_" + getGlobalMetadataSection());
StopELFMetadata->setVisibility(GlobalVariable::HiddenVisibility);
// Create a call to register the globals with the runtime.
IRB.CreateCall(AsanRegisterElfGlobals,
{IRB.CreatePointerCast(RegisteredFlag, IntptrTy),
IRB.CreatePointerCast(StartELFMetadata, IntptrTy),
IRB.CreatePointerCast(StopELFMetadata, IntptrTy)});
// We also need to unregister globals at the end, e.g., when a shared library
// gets closed.
IRBuilder<> IRB_Dtor = CreateAsanModuleDtor(M);
IRB_Dtor.CreateCall(AsanUnregisterElfGlobals,
{IRB.CreatePointerCast(RegisteredFlag, IntptrTy),
IRB.CreatePointerCast(StartELFMetadata, IntptrTy),
IRB.CreatePointerCast(StopELFMetadata, IntptrTy)});
}
void ModuleAddressSanitizer::InstrumentGlobalsMachO(
IRBuilder<> &IRB, Module &M, ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers) {
assert(ExtendedGlobals.size() == MetadataInitializers.size());
// On recent Mach-O platforms, use a structure which binds the liveness of
// the global variable to the metadata struct. Keep the list of "Liveness" GV
// created to be added to llvm.compiler.used
StructType *LivenessTy = StructType::get(IntptrTy, IntptrTy);
SmallVector<GlobalValue *, 16> LivenessGlobals(ExtendedGlobals.size());
for (size_t i = 0; i < ExtendedGlobals.size(); i++) {
Constant *Initializer = MetadataInitializers[i];
GlobalVariable *G = ExtendedGlobals[i];
GlobalVariable *Metadata =
CreateMetadataGlobal(M, Initializer, G->getName());
// On recent Mach-O platforms, we emit the global metadata in a way that
// allows the linker to properly strip dead globals.
auto LivenessBinder =
ConstantStruct::get(LivenessTy, Initializer->getAggregateElement(0u),
ConstantExpr::getPointerCast(Metadata, IntptrTy));
GlobalVariable *Liveness = new GlobalVariable(
M, LivenessTy, false, GlobalVariable::InternalLinkage, LivenessBinder,
Twine("__asan_binder_") + G->getName());
Liveness->setSection("__DATA,__asan_liveness,regular,live_support");
LivenessGlobals[i] = Liveness;
}
// Update llvm.compiler.used, adding the new liveness globals. This is
// needed so that during LTO these variables stay alive. The alternative
// would be to have the linker handling the LTO symbols, but libLTO
// current API does not expose access to the section for each symbol.
if (!LivenessGlobals.empty())
appendToCompilerUsed(M, LivenessGlobals);
// RegisteredFlag serves two purposes. First, we can pass it to dladdr()
// to look up the loaded image that contains it. Second, we can store in it
// whether registration has already occurred, to prevent duplicate
// registration.
//
// common linkage ensures that there is only one global per shared library.
GlobalVariable *RegisteredFlag = new GlobalVariable(
M, IntptrTy, false, GlobalVariable::CommonLinkage,
ConstantInt::get(IntptrTy, 0), kAsanGlobalsRegisteredFlagName);
RegisteredFlag->setVisibility(GlobalVariable::HiddenVisibility);
IRB.CreateCall(AsanRegisterImageGlobals,
{IRB.CreatePointerCast(RegisteredFlag, IntptrTy)});
// We also need to unregister globals at the end, e.g., when a shared library
// gets closed.
IRBuilder<> IRB_Dtor = CreateAsanModuleDtor(M);
IRB_Dtor.CreateCall(AsanUnregisterImageGlobals,
{IRB.CreatePointerCast(RegisteredFlag, IntptrTy)});
}
void ModuleAddressSanitizer::InstrumentGlobalsWithMetadataArray(
IRBuilder<> &IRB, Module &M, ArrayRef<GlobalVariable *> ExtendedGlobals,
ArrayRef<Constant *> MetadataInitializers) {
assert(ExtendedGlobals.size() == MetadataInitializers.size());
unsigned N = ExtendedGlobals.size();
assert(N > 0);
// On platforms that don't have a custom metadata section, we emit an array
// of global metadata structures.
ArrayType *ArrayOfGlobalStructTy =
ArrayType::get(MetadataInitializers[0]->getType(), N);
auto AllGlobals = new GlobalVariable(
M, ArrayOfGlobalStructTy, false, GlobalVariable::InternalLinkage,
ConstantArray::get(ArrayOfGlobalStructTy, MetadataInitializers), "");
if (Mapping.Scale > 3)
AllGlobals->setAlignment(1ULL << Mapping.Scale);
IRB.CreateCall(AsanRegisterGlobals,
{IRB.CreatePointerCast(AllGlobals, IntptrTy),
ConstantInt::get(IntptrTy, N)});
// We also need to unregister globals at the end, e.g., when a shared library
// gets closed.
IRBuilder<> IRB_Dtor = CreateAsanModuleDtor(M);
IRB_Dtor.CreateCall(AsanUnregisterGlobals,
{IRB.CreatePointerCast(AllGlobals, IntptrTy),
ConstantInt::get(IntptrTy, N)});
}
// This function replaces all global variables with new variables that have
// trailing redzones. It also creates a function that poisons
// redzones and inserts this function into llvm.global_ctors.
// Sets *CtorComdat to true if the global registration code emitted into the
// asan constructor is comdat-compatible.
bool ModuleAddressSanitizer::InstrumentGlobals(IRBuilder<> &IRB, Module &M,
bool *CtorComdat) {
*CtorComdat = false;
SmallVector<GlobalVariable *, 16> GlobalsToChange;
for (auto &G : M.globals()) {
if (ShouldInstrumentGlobal(&G)) GlobalsToChange.push_back(&G);
}
size_t n = GlobalsToChange.size();
if (n == 0) {
*CtorComdat = true;
return false;
}
auto &DL = M.getDataLayout();
// A global is described by a structure
// size_t beg;
// size_t size;
// size_t size_with_redzone;
// const char *name;
// const char *module_name;
// size_t has_dynamic_init;
// void *source_location;
// size_t odr_indicator;
// We initialize an array of such structures and pass it to a run-time call.
StructType *GlobalStructTy =
StructType::get(IntptrTy, IntptrTy, IntptrTy, IntptrTy, IntptrTy,
IntptrTy, IntptrTy, IntptrTy);
SmallVector<GlobalVariable *, 16> NewGlobals(n);
SmallVector<Constant *, 16> Initializers(n);
bool HasDynamicallyInitializedGlobals = false;
// We shouldn't merge same module names, as this string serves as unique
// module ID in runtime.
GlobalVariable *ModuleName = createPrivateGlobalForString(
M, M.getModuleIdentifier(), /*AllowMerging*/ false, kAsanGenPrefix);
for (size_t i = 0; i < n; i++) {
static const uint64_t kMaxGlobalRedzone = 1 << 18;
GlobalVariable *G = GlobalsToChange[i];
// FIXME: Metadata should be attched directly to the global directly instead
// of being added to llvm.asan.globals.
auto MD = GlobalsMD.get(G);
StringRef NameForGlobal = G->getName();
// Create string holding the global name (use global name from metadata
// if it's available, otherwise just write the name of global variable).
GlobalVariable *Name = createPrivateGlobalForString(
M, MD.Name.empty() ? NameForGlobal : MD.Name,
/*AllowMerging*/ true, kAsanGenPrefix);
Type *Ty = G->getValueType();
uint64_t SizeInBytes = DL.getTypeAllocSize(Ty);
uint64_t MinRZ = MinRedzoneSizeForGlobal();
// MinRZ <= RZ <= kMaxGlobalRedzone
// and trying to make RZ to be ~ 1/4 of SizeInBytes.
uint64_t RZ = std::max(
MinRZ, std::min(kMaxGlobalRedzone, (SizeInBytes / MinRZ / 4) * MinRZ));
uint64_t RightRedzoneSize = RZ;
// Round up to MinRZ
if (SizeInBytes % MinRZ) RightRedzoneSize += MinRZ - (SizeInBytes % MinRZ);
assert(((RightRedzoneSize + SizeInBytes) % MinRZ) == 0);
Type *RightRedZoneTy = ArrayType::get(IRB.getInt8Ty(), RightRedzoneSize);
StructType *NewTy = StructType::get(Ty, RightRedZoneTy);
Constant *NewInitializer = ConstantStruct::get(
NewTy, G->getInitializer(), Constant::getNullValue(RightRedZoneTy));
// Create a new global variable with enough space for a redzone.
GlobalValue::LinkageTypes Linkage = G->getLinkage();
if (G->isConstant() && Linkage == GlobalValue::PrivateLinkage)
Linkage = GlobalValue::InternalLinkage;
GlobalVariable *NewGlobal =
new GlobalVariable(M, NewTy, G->isConstant(), Linkage, NewInitializer,
"", G, G->getThreadLocalMode());
NewGlobal->copyAttributesFrom(G);
NewGlobal->setComdat(G->getComdat());
NewGlobal->setAlignment(MinRZ);
// Don't fold globals with redzones. ODR violation detector and redzone
// poisoning implicitly creates a dependence on the global's address, so it
// is no longer valid for it to be marked unnamed_addr.
NewGlobal->setUnnamedAddr(GlobalValue::UnnamedAddr::None);
// Move null-terminated C strings to "__asan_cstring" section on Darwin.
if (TargetTriple.isOSBinFormatMachO() && !G->hasSection() &&
G->isConstant()) {
auto Seq = dyn_cast<ConstantDataSequential>(G->getInitializer());
if (Seq && Seq->isCString())
NewGlobal->setSection("__TEXT,__asan_cstring,regular");
}
// Transfer the debug info. The payload starts at offset zero so we can
// copy the debug info over as is.
SmallVector<DIGlobalVariableExpression *, 1> GVs;
G->getDebugInfo(GVs);
for (auto *GV : GVs)
NewGlobal->addDebugInfo(GV);
Value *Indices2[2];
Indices2[0] = IRB.getInt32(0);
Indices2[1] = IRB.getInt32(0);
G->replaceAllUsesWith(
ConstantExpr::getGetElementPtr(NewTy, NewGlobal, Indices2, true));
NewGlobal->takeName(G);
G->eraseFromParent();
NewGlobals[i] = NewGlobal;
Constant *SourceLoc;
if (!MD.SourceLoc.empty()) {
auto SourceLocGlobal = createPrivateGlobalForSourceLoc(M, MD.SourceLoc);
SourceLoc = ConstantExpr::getPointerCast(SourceLocGlobal, IntptrTy);
} else {
SourceLoc = ConstantInt::get(IntptrTy, 0);
}
Constant *ODRIndicator = ConstantExpr::getNullValue(IRB.getInt8PtrTy());
GlobalValue *InstrumentedGlobal = NewGlobal;
bool CanUsePrivateAliases =
TargetTriple.isOSBinFormatELF() || TargetTriple.isOSBinFormatMachO() ||
TargetTriple.isOSBinFormatWasm();
if (CanUsePrivateAliases && UsePrivateAlias) {
// Create local alias for NewGlobal to avoid crash on ODR between
// instrumented and non-instrumented libraries.
InstrumentedGlobal =
GlobalAlias::create(GlobalValue::PrivateLinkage, "", NewGlobal);
}
// ODR should not happen for local linkage.
if (NewGlobal->hasLocalLinkage()) {
ODRIndicator = ConstantExpr::getIntToPtr(ConstantInt::get(IntptrTy, -1),
IRB.getInt8PtrTy());
} else if (UseOdrIndicator) {
// With local aliases, we need to provide another externally visible
// symbol __odr_asan_XXX to detect ODR violation.
auto *ODRIndicatorSym =
new GlobalVariable(M, IRB.getInt8Ty(), false, Linkage,
Constant::getNullValue(IRB.getInt8Ty()),
kODRGenPrefix + NameForGlobal, nullptr,
NewGlobal->getThreadLocalMode());
// Set meaningful attributes for indicator symbol.
ODRIndicatorSym->setVisibility(NewGlobal->getVisibility());
ODRIndicatorSym->setDLLStorageClass(NewGlobal->getDLLStorageClass());
ODRIndicatorSym->setAlignment(1);
ODRIndicator = ODRIndicatorSym;
}
Constant *Initializer = ConstantStruct::get(
GlobalStructTy,
ConstantExpr::getPointerCast(InstrumentedGlobal, IntptrTy),
ConstantInt::get(IntptrTy, SizeInBytes),
ConstantInt::get(IntptrTy, SizeInBytes + RightRedzoneSize),
ConstantExpr::getPointerCast(Name, IntptrTy),
ConstantExpr::getPointerCast(ModuleName, IntptrTy),
ConstantInt::get(IntptrTy, MD.IsDynInit), SourceLoc,
ConstantExpr::getPointerCast(ODRIndicator, IntptrTy));
if (ClInitializers && MD.IsDynInit) HasDynamicallyInitializedGlobals = true;
LLVM_DEBUG(dbgs() << "NEW GLOBAL: " << *NewGlobal << "\n");
Initializers[i] = Initializer;
}
// Add instrumented globals to llvm.compiler.used list to avoid LTO from
// ConstantMerge'ing them.
SmallVector<GlobalValue *, 16> GlobalsToAddToUsedList;
for (size_t i = 0; i < n; i++) {
GlobalVariable *G = NewGlobals[i];
if (G->getName().empty()) continue;
GlobalsToAddToUsedList.push_back(G);
}
appendToCompilerUsed(M, ArrayRef<GlobalValue *>(GlobalsToAddToUsedList));
std::string ELFUniqueModuleId =
(UseGlobalsGC && TargetTriple.isOSBinFormatELF()) ? getUniqueModuleId(&M)
: "";
if (!ELFUniqueModuleId.empty()) {
InstrumentGlobalsELF(IRB, M, NewGlobals, Initializers, ELFUniqueModuleId);
*CtorComdat = true;
} else if (UseGlobalsGC && TargetTriple.isOSBinFormatCOFF()) {
InstrumentGlobalsCOFF(IRB, M, NewGlobals, Initializers);
} else if (UseGlobalsGC && ShouldUseMachOGlobalsSection()) {
InstrumentGlobalsMachO(IRB, M, NewGlobals, <