llvm-project/llvm/lib/Analysis/MemoryBuiltins.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1077 lines
41 KiB
C++
Raw Normal View History

//===- MemoryBuiltins.cpp - Identify calls to memory builtins -------------===//
//
// 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 family of functions identifies calls to builtin functions that allocate
// or free memory.
//
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Analysis/TargetFolder.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/Utils/Local.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Argument.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalAlias.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include <cassert>
#include <cstdint>
#include <iterator>
#include <utility>
using namespace llvm;
#define DEBUG_TYPE "memory-builtins"
enum AllocType : uint8_t {
OpNewLike = 1<<0, // allocates; never returns null
MallocLike = 1<<1 | OpNewLike, // allocates; may return null
AlignedAllocLike = 1<<2, // allocates with alignment; may return null
CallocLike = 1<<3, // allocates + bzero
ReallocLike = 1<<4, // reallocates
StrDupLike = 1<<5,
MallocOrCallocLike = MallocLike | CallocLike | AlignedAllocLike,
AllocLike = MallocOrCallocLike | StrDupLike,
AnyAlloc = AllocLike | ReallocLike
};
struct AllocFnsTy {
AllocType AllocTy;
unsigned NumParams;
// First and Second size parameters (or -1 if unused)
int FstParam, SndParam;
};
// FIXME: certain users need more information. E.g., SimplifyLibCalls needs to
// know which functions are nounwind, noalias, nocapture parameters, etc.
static const std::pair<LibFunc, AllocFnsTy> AllocationFnData[] = {
{LibFunc_malloc, {MallocLike, 1, 0, -1}},
{LibFunc_valloc, {MallocLike, 1, 0, -1}},
{LibFunc_Znwj, {OpNewLike, 1, 0, -1}}, // new(unsigned int)
{LibFunc_ZnwjRKSt9nothrow_t, {MallocLike, 2, 0, -1}}, // new(unsigned int, nothrow)
{LibFunc_ZnwjSt11align_val_t, {OpNewLike, 2, 0, -1}}, // new(unsigned int, align_val_t)
{LibFunc_ZnwjSt11align_val_tRKSt9nothrow_t, // new(unsigned int, align_val_t, nothrow)
{MallocLike, 3, 0, -1}},
{LibFunc_Znwm, {OpNewLike, 1, 0, -1}}, // new(unsigned long)
{LibFunc_ZnwmRKSt9nothrow_t, {MallocLike, 2, 0, -1}}, // new(unsigned long, nothrow)
{LibFunc_ZnwmSt11align_val_t, {OpNewLike, 2, 0, -1}}, // new(unsigned long, align_val_t)
{LibFunc_ZnwmSt11align_val_tRKSt9nothrow_t, // new(unsigned long, align_val_t, nothrow)
{MallocLike, 3, 0, -1}},
{LibFunc_Znaj, {OpNewLike, 1, 0, -1}}, // new[](unsigned int)
{LibFunc_ZnajRKSt9nothrow_t, {MallocLike, 2, 0, -1}}, // new[](unsigned int, nothrow)
{LibFunc_ZnajSt11align_val_t, {OpNewLike, 2, 0, -1}}, // new[](unsigned int, align_val_t)
{LibFunc_ZnajSt11align_val_tRKSt9nothrow_t, // new[](unsigned int, align_val_t, nothrow)
{MallocLike, 3, 0, -1}},
{LibFunc_Znam, {OpNewLike, 1, 0, -1}}, // new[](unsigned long)
{LibFunc_ZnamRKSt9nothrow_t, {MallocLike, 2, 0, -1}}, // new[](unsigned long, nothrow)
{LibFunc_ZnamSt11align_val_t, {OpNewLike, 2, 0, -1}}, // new[](unsigned long, align_val_t)
{LibFunc_ZnamSt11align_val_tRKSt9nothrow_t, // new[](unsigned long, align_val_t, nothrow)
{MallocLike, 3, 0, -1}},
{LibFunc_msvc_new_int, {OpNewLike, 1, 0, -1}}, // new(unsigned int)
{LibFunc_msvc_new_int_nothrow, {MallocLike, 2, 0, -1}}, // new(unsigned int, nothrow)
{LibFunc_msvc_new_longlong, {OpNewLike, 1, 0, -1}}, // new(unsigned long long)
{LibFunc_msvc_new_longlong_nothrow, {MallocLike, 2, 0, -1}}, // new(unsigned long long, nothrow)
{LibFunc_msvc_new_array_int, {OpNewLike, 1, 0, -1}}, // new[](unsigned int)
{LibFunc_msvc_new_array_int_nothrow, {MallocLike, 2, 0, -1}}, // new[](unsigned int, nothrow)
{LibFunc_msvc_new_array_longlong, {OpNewLike, 1, 0, -1}}, // new[](unsigned long long)
{LibFunc_msvc_new_array_longlong_nothrow, {MallocLike, 2, 0, -1}}, // new[](unsigned long long, nothrow)
{LibFunc_aligned_alloc, {AlignedAllocLike, 2, 1, -1}},
{LibFunc_calloc, {CallocLike, 2, 0, 1}},
{LibFunc_realloc, {ReallocLike, 2, 1, -1}},
{LibFunc_reallocf, {ReallocLike, 2, 1, -1}},
{LibFunc_strdup, {StrDupLike, 1, -1, -1}},
{LibFunc_strndup, {StrDupLike, 2, 1, -1}}
// TODO: Handle "int posix_memalign(void **, size_t, size_t)"
};
static const Function *getCalledFunction(const Value *V, bool LookThroughBitCast,
bool &IsNoBuiltin) {
// Don't care about intrinsics in this case.
if (isa<IntrinsicInst>(V))
return nullptr;
if (LookThroughBitCast)
V = V->stripPointerCasts();
const auto *CB = dyn_cast<CallBase>(V);
if (!CB)
return nullptr;
IsNoBuiltin = CB->isNoBuiltin();
if (const Function *Callee = CB->getCalledFunction())
return Callee;
return nullptr;
}
/// Returns the allocation data for the given value if it's either a call to a
/// known allocation function, or a call to a function with the allocsize
/// attribute.
static Optional<AllocFnsTy>
getAllocationDataForFunction(const Function *Callee, AllocType AllocTy,
const TargetLibraryInfo *TLI) {
// Make sure that the function is available.
StringRef FnName = Callee->getName();
LibFunc TLIFn;
if (!TLI || !TLI->getLibFunc(FnName, TLIFn) || !TLI->has(TLIFn))
return None;
const auto *Iter = find_if(
AllocationFnData, [TLIFn](const std::pair<LibFunc, AllocFnsTy> &P) {
return P.first == TLIFn;
});
if (Iter == std::end(AllocationFnData))
return None;
const AllocFnsTy *FnData = &Iter->second;
if ((FnData->AllocTy & AllocTy) != FnData->AllocTy)
return None;
// Check function prototype.
int FstParam = FnData->FstParam;
int SndParam = FnData->SndParam;
FunctionType *FTy = Callee->getFunctionType();
if (FTy->getReturnType() == Type::getInt8PtrTy(FTy->getContext()) &&
FTy->getNumParams() == FnData->NumParams &&
(FstParam < 0 ||
(FTy->getParamType(FstParam)->isIntegerTy(32) ||
FTy->getParamType(FstParam)->isIntegerTy(64))) &&
(SndParam < 0 ||
FTy->getParamType(SndParam)->isIntegerTy(32) ||
FTy->getParamType(SndParam)->isIntegerTy(64)))
return *FnData;
return None;
}
static Optional<AllocFnsTy> getAllocationData(const Value *V, AllocType AllocTy,
const TargetLibraryInfo *TLI,
bool LookThroughBitCast = false) {
bool IsNoBuiltinCall;
if (const Function *Callee =
getCalledFunction(V, LookThroughBitCast, IsNoBuiltinCall))
if (!IsNoBuiltinCall)
return getAllocationDataForFunction(Callee, AllocTy, TLI);
return None;
}
static Optional<AllocFnsTy>
getAllocationData(const Value *V, AllocType AllocTy,
function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
bool LookThroughBitCast = false) {
bool IsNoBuiltinCall;
if (const Function *Callee =
getCalledFunction(V, LookThroughBitCast, IsNoBuiltinCall))
if (!IsNoBuiltinCall)
return getAllocationDataForFunction(
Callee, AllocTy, &GetTLI(const_cast<Function &>(*Callee)));
return None;
}
static Optional<AllocFnsTy> getAllocationSize(const Value *V,
const TargetLibraryInfo *TLI) {
bool IsNoBuiltinCall;
const Function *Callee =
getCalledFunction(V, /*LookThroughBitCast=*/false, IsNoBuiltinCall);
if (!Callee)
return None;
// Prefer to use existing information over allocsize. This will give us an
// accurate AllocTy.
if (!IsNoBuiltinCall)
if (Optional<AllocFnsTy> Data =
getAllocationDataForFunction(Callee, AnyAlloc, TLI))
return Data;
Attribute Attr = Callee->getFnAttribute(Attribute::AllocSize);
if (Attr == Attribute())
return None;
std::pair<unsigned, Optional<unsigned>> Args = Attr.getAllocSizeArgs();
AllocFnsTy Result;
// Because allocsize only tells us how many bytes are allocated, we're not
// really allowed to assume anything, so we use MallocLike.
Result.AllocTy = MallocLike;
Result.NumParams = Callee->getNumOperands();
Result.FstParam = Args.first;
Result.SndParam = Args.second.getValueOr(-1);
return Result;
}
static bool hasNoAliasAttr(const Value *V, bool LookThroughBitCast) {
const auto *CB =
dyn_cast<CallBase>(LookThroughBitCast ? V->stripPointerCasts() : V);
return CB && CB->hasRetAttr(Attribute::NoAlias);
}
/// Tests if a value is a call or invoke to a library function that
/// allocates or reallocates memory (either malloc, calloc, realloc, or strdup
/// like).
bool llvm::isAllocationFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, AnyAlloc, TLI, LookThroughBitCast).hasValue();
}
bool llvm::isAllocationFn(
const Value *V, function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
bool LookThroughBitCast) {
return getAllocationData(V, AnyAlloc, GetTLI, LookThroughBitCast).hasValue();
}
/// Tests if a value is a call or invoke to a function that returns a
/// NoAlias pointer (including malloc/calloc/realloc/strdup-like functions).
bool llvm::isNoAliasFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
// it's safe to consider realloc as noalias since accessing the original
// pointer is undefined behavior
return isAllocationFn(V, TLI, LookThroughBitCast) ||
hasNoAliasAttr(V, LookThroughBitCast);
}
/// Tests if a value is a call or invoke to a library function that
/// allocates uninitialized memory (such as malloc).
bool llvm::isMallocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, MallocLike, TLI, LookThroughBitCast).hasValue();
}
bool llvm::isMallocLikeFn(
const Value *V, function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
bool LookThroughBitCast) {
return getAllocationData(V, MallocLike, GetTLI, LookThroughBitCast)
.hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates uninitialized memory with alignment (such as aligned_alloc).
bool llvm::isAlignedAllocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, AlignedAllocLike, TLI, LookThroughBitCast)
.hasValue();
}
bool llvm::isAlignedAllocLikeFn(
const Value *V, function_ref<const TargetLibraryInfo &(Function &)> GetTLI,
bool LookThroughBitCast) {
return getAllocationData(V, AlignedAllocLike, GetTLI, LookThroughBitCast)
.hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates zero-filled memory (such as calloc).
bool llvm::isCallocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, CallocLike, TLI, LookThroughBitCast).hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates memory similar to malloc or calloc.
bool llvm::isMallocOrCallocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, MallocOrCallocLike, TLI,
LookThroughBitCast).hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates memory (either malloc, calloc, or strdup like).
bool llvm::isAllocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, AllocLike, TLI, LookThroughBitCast).hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// reallocates memory (e.g., realloc).
bool llvm::isReallocLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, ReallocLike, TLI, LookThroughBitCast).hasValue();
}
/// Tests if a functions is a call or invoke to a library function that
/// reallocates memory (e.g., realloc).
bool llvm::isReallocLikeFn(const Function *F, const TargetLibraryInfo *TLI) {
return getAllocationDataForFunction(F, ReallocLike, TLI).hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates memory and throws if an allocation failed (e.g., new).
bool llvm::isOpNewLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, OpNewLike, TLI, LookThroughBitCast).hasValue();
}
/// Tests if a value is a call or invoke to a library function that
/// allocates memory (strdup, strndup).
bool llvm::isStrdupLikeFn(const Value *V, const TargetLibraryInfo *TLI,
bool LookThroughBitCast) {
return getAllocationData(V, StrDupLike, TLI, LookThroughBitCast).hasValue();
}
/// extractMallocCall - Returns the corresponding CallInst if the instruction
/// is a malloc call. Since CallInst::CreateMalloc() only creates calls, we
/// ignore InvokeInst here.
const CallInst *llvm::extractMallocCall(
const Value *I,
function_ref<const TargetLibraryInfo &(Function &)> GetTLI) {
return isMallocLikeFn(I, GetTLI) ? dyn_cast<CallInst>(I) : nullptr;
}
static Value *computeArraySize(const CallInst *CI, const DataLayout &DL,
const TargetLibraryInfo *TLI,
bool LookThroughSExt = false) {
if (!CI)
return nullptr;
// The size of the malloc's result type must be known to determine array size.
Type *T = getMallocAllocatedType(CI, TLI);
if (!T || !T->isSized())
return nullptr;
unsigned ElementSize = DL.getTypeAllocSize(T);
if (StructType *ST = dyn_cast<StructType>(T))
ElementSize = DL.getStructLayout(ST)->getSizeInBytes();
// If malloc call's arg can be determined to be a multiple of ElementSize,
// return the multiple. Otherwise, return NULL.
Value *MallocArg = CI->getArgOperand(0);
Value *Multiple = nullptr;
2016-07-08 00:19:09 +08:00
if (ComputeMultiple(MallocArg, ElementSize, Multiple, LookThroughSExt))
return Multiple;
return nullptr;
}
/// getMallocType - Returns the PointerType resulting from the malloc call.
/// The PointerType depends on the number of bitcast uses of the malloc call:
/// 0: PointerType is the calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
PointerType *llvm::getMallocType(const CallInst *CI,
const TargetLibraryInfo *TLI) {
assert(isMallocLikeFn(CI, TLI) && "getMallocType and not malloc call");
PointerType *MallocType = nullptr;
unsigned NumOfBitCastUses = 0;
// Determine if CallInst has a bitcast use.
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
for (Value::const_user_iterator UI = CI->user_begin(), E = CI->user_end();
UI != E;)
if (const BitCastInst *BCI = dyn_cast<BitCastInst>(*UI++)) {
MallocType = cast<PointerType>(BCI->getDestTy());
NumOfBitCastUses++;
}
// Malloc call has 1 bitcast use, so type is the bitcast's destination type.
if (NumOfBitCastUses == 1)
return MallocType;
// Malloc call was not bitcast, so type is the malloc function's return type.
if (NumOfBitCastUses == 0)
return cast<PointerType>(CI->getType());
// Type could not be determined.
return nullptr;
}
/// getMallocAllocatedType - Returns the Type allocated by malloc call.
/// The Type depends on the number of bitcast uses of the malloc call:
/// 0: PointerType is the malloc calls' return type.
/// 1: PointerType is the bitcast's result type.
/// >1: Unique PointerType cannot be determined, return NULL.
Type *llvm::getMallocAllocatedType(const CallInst *CI,
const TargetLibraryInfo *TLI) {
PointerType *PT = getMallocType(CI, TLI);
return PT ? PT->getElementType() : nullptr;
}
/// getMallocArraySize - Returns the array size of a malloc call. If the
/// argument passed to malloc is a multiple of the size of the malloced type,
/// then return that multiple. For non-array mallocs, the multiple is
/// constant 1. Otherwise, return NULL for mallocs whose array size cannot be
/// determined.
Value *llvm::getMallocArraySize(CallInst *CI, const DataLayout &DL,
const TargetLibraryInfo *TLI,
bool LookThroughSExt) {
assert(isMallocLikeFn(CI, TLI) && "getMallocArraySize and not malloc call");
return computeArraySize(CI, DL, TLI, LookThroughSExt);
}
/// extractCallocCall - Returns the corresponding CallInst if the instruction
/// is a calloc call.
const CallInst *llvm::extractCallocCall(const Value *I,
const TargetLibraryInfo *TLI) {
return isCallocLikeFn(I, TLI) ? cast<CallInst>(I) : nullptr;
}
/// isLibFreeFunction - Returns true if the function is a builtin free()
bool llvm::isLibFreeFunction(const Function *F, const LibFunc TLIFn) {
unsigned ExpectedNumParams;
if (TLIFn == LibFunc_free ||
TLIFn == LibFunc_ZdlPv || // operator delete(void*)
TLIFn == LibFunc_ZdaPv || // operator delete[](void*)
TLIFn == LibFunc_msvc_delete_ptr32 || // operator delete(void*)
TLIFn == LibFunc_msvc_delete_ptr64 || // operator delete(void*)
TLIFn == LibFunc_msvc_delete_array_ptr32 || // operator delete[](void*)
TLIFn == LibFunc_msvc_delete_array_ptr64) // operator delete[](void*)
ExpectedNumParams = 1;
else if (TLIFn == LibFunc_ZdlPvj || // delete(void*, uint)
TLIFn == LibFunc_ZdlPvm || // delete(void*, ulong)
TLIFn == LibFunc_ZdlPvRKSt9nothrow_t || // delete(void*, nothrow)
TLIFn == LibFunc_ZdlPvSt11align_val_t || // delete(void*, align_val_t)
TLIFn == LibFunc_ZdaPvj || // delete[](void*, uint)
TLIFn == LibFunc_ZdaPvm || // delete[](void*, ulong)
TLIFn == LibFunc_ZdaPvRKSt9nothrow_t || // delete[](void*, nothrow)
TLIFn == LibFunc_ZdaPvSt11align_val_t || // delete[](void*, align_val_t)
TLIFn == LibFunc_msvc_delete_ptr32_int || // delete(void*, uint)
TLIFn == LibFunc_msvc_delete_ptr64_longlong || // delete(void*, ulonglong)
TLIFn == LibFunc_msvc_delete_ptr32_nothrow || // delete(void*, nothrow)
TLIFn == LibFunc_msvc_delete_ptr64_nothrow || // delete(void*, nothrow)
TLIFn == LibFunc_msvc_delete_array_ptr32_int || // delete[](void*, uint)
TLIFn == LibFunc_msvc_delete_array_ptr64_longlong || // delete[](void*, ulonglong)
TLIFn == LibFunc_msvc_delete_array_ptr32_nothrow || // delete[](void*, nothrow)
TLIFn == LibFunc_msvc_delete_array_ptr64_nothrow) // delete[](void*, nothrow)
ExpectedNumParams = 2;
else if (TLIFn == LibFunc_ZdaPvSt11align_val_tRKSt9nothrow_t || // delete(void*, align_val_t, nothrow)
TLIFn == LibFunc_ZdlPvSt11align_val_tRKSt9nothrow_t || // delete[](void*, align_val_t, nothrow)
TLIFn == LibFunc_ZdlPvjSt11align_val_t || // delete(void*, unsigned long, align_val_t)
TLIFn == LibFunc_ZdlPvmSt11align_val_t || // delete(void*, unsigned long, align_val_t)
TLIFn == LibFunc_ZdaPvjSt11align_val_t || // delete[](void*, unsigned int, align_val_t)
TLIFn == LibFunc_ZdaPvmSt11align_val_t) // delete[](void*, unsigned long, align_val_t)
ExpectedNumParams = 3;
else
return false;
// Check free prototype.
// FIXME: workaround for PR5130, this will be obsolete when a nobuiltin
// attribute will exist.
FunctionType *FTy = F->getFunctionType();
if (!FTy->getReturnType()->isVoidTy())
return false;
if (FTy->getNumParams() != ExpectedNumParams)
return false;
if (FTy->getParamType(0) != Type::getInt8PtrTy(F->getContext()))
return false;
return true;
}
/// isFreeCall - Returns non-null if the value is a call to the builtin free()
const CallInst *llvm::isFreeCall(const Value *I, const TargetLibraryInfo *TLI) {
bool IsNoBuiltinCall;
const Function *Callee =
getCalledFunction(I, /*LookThroughBitCast=*/false, IsNoBuiltinCall);
if (Callee == nullptr || IsNoBuiltinCall)
return nullptr;
StringRef FnName = Callee->getName();
LibFunc TLIFn;
if (!TLI || !TLI->getLibFunc(FnName, TLIFn) || !TLI->has(TLIFn))
return nullptr;
return isLibFreeFunction(Callee, TLIFn) ? dyn_cast<CallInst>(I) : nullptr;
}
//===----------------------------------------------------------------------===//
// Utility functions to compute size of objects.
//
static APInt getSizeWithOverflow(const SizeOffsetType &Data) {
if (Data.second.isNegative() || Data.first.ult(Data.second))
return APInt(Data.first.getBitWidth(), 0);
return Data.first - Data.second;
}
/// Compute the size of the object pointed by Ptr. Returns true and the
/// object size in Size if successful, and false otherwise.
/// If RoundToAlign is true, then Size is rounded up to the alignment of
/// allocas, byval arguments, and global variables.
bool llvm::getObjectSize(const Value *Ptr, uint64_t &Size, const DataLayout &DL,
const TargetLibraryInfo *TLI, ObjectSizeOpts Opts) {
ObjectSizeOffsetVisitor Visitor(DL, TLI, Ptr->getContext(), Opts);
SizeOffsetType Data = Visitor.compute(const_cast<Value*>(Ptr));
if (!Visitor.bothKnown(Data))
return false;
Size = getSizeWithOverflow(Data).getZExtValue();
return true;
}
Value *llvm::lowerObjectSizeCall(IntrinsicInst *ObjectSize,
const DataLayout &DL,
const TargetLibraryInfo *TLI,
bool MustSucceed) {
assert(ObjectSize->getIntrinsicID() == Intrinsic::objectsize &&
"ObjectSize must be a call to llvm.objectsize!");
bool MaxVal = cast<ConstantInt>(ObjectSize->getArgOperand(1))->isZero();
ObjectSizeOpts EvalOptions;
// Unless we have to fold this to something, try to be as accurate as
// possible.
if (MustSucceed)
EvalOptions.EvalMode =
MaxVal ? ObjectSizeOpts::Mode::Max : ObjectSizeOpts::Mode::Min;
else
EvalOptions.EvalMode = ObjectSizeOpts::Mode::Exact;
EvalOptions.NullIsUnknownSize =
cast<ConstantInt>(ObjectSize->getArgOperand(2))->isOne();
auto *ResultType = cast<IntegerType>(ObjectSize->getType());
bool StaticOnly = cast<ConstantInt>(ObjectSize->getArgOperand(3))->isZero();
if (StaticOnly) {
// FIXME: Does it make sense to just return a failure value if the size won't
// fit in the output and `!MustSucceed`?
uint64_t Size;
if (getObjectSize(ObjectSize->getArgOperand(0), Size, DL, TLI, EvalOptions) &&
isUIntN(ResultType->getBitWidth(), Size))
return ConstantInt::get(ResultType, Size);
} else {
LLVMContext &Ctx = ObjectSize->getFunction()->getContext();
ObjectSizeOffsetEvaluator Eval(DL, TLI, Ctx, EvalOptions);
SizeOffsetEvalType SizeOffsetPair =
Eval.compute(ObjectSize->getArgOperand(0));
if (SizeOffsetPair != ObjectSizeOffsetEvaluator::unknown()) {
IRBuilder<TargetFolder> Builder(Ctx, TargetFolder(DL));
Builder.SetInsertPoint(ObjectSize);
// If we've outside the end of the object, then we can always access
// exactly 0 bytes.
Value *ResultSize =
Builder.CreateSub(SizeOffsetPair.first, SizeOffsetPair.second);
Value *UseZero =
Builder.CreateICmpULT(SizeOffsetPair.first, SizeOffsetPair.second);
ResultSize = Builder.CreateZExtOrTrunc(ResultSize, ResultType);
return Builder.CreateSelect(UseZero, ConstantInt::get(ResultType, 0),
ResultSize);
}
}
if (!MustSucceed)
return nullptr;
return ConstantInt::get(ResultType, MaxVal ? -1ULL : 0);
}
STATISTIC(ObjectVisitorArgument,
"Number of arguments with unsolved size and offset");
STATISTIC(ObjectVisitorLoad,
"Number of load instructions with unsolved size and offset");
APInt ObjectSizeOffsetVisitor::align(APInt Size, uint64_t Alignment) {
if (Options.RoundToAlign && Alignment)
return APInt(IntTyBits, alignTo(Size.getZExtValue(), Align(Alignment)));
return Size;
}
ObjectSizeOffsetVisitor::ObjectSizeOffsetVisitor(const DataLayout &DL,
const TargetLibraryInfo *TLI,
LLVMContext &Context,
ObjectSizeOpts Options)
: DL(DL), TLI(TLI), Options(Options) {
// Pointer size must be rechecked for each object visited since it could have
// a different address space.
}
SizeOffsetType ObjectSizeOffsetVisitor::compute(Value *V) {
IntTyBits = DL.getIndexTypeSizeInBits(V->getType());
Zero = APInt::getNullValue(IntTyBits);
V = V->stripPointerCasts();
if (Instruction *I = dyn_cast<Instruction>(V)) {
// If we have already seen this instruction, bail out. Cycles can happen in
// unreachable code after constant propagation.
if (!SeenInsts.insert(I).second)
return unknown();
if (GEPOperator *GEP = dyn_cast<GEPOperator>(V))
return visitGEPOperator(*GEP);
return visit(*I);
}
if (Argument *A = dyn_cast<Argument>(V))
return visitArgument(*A);
if (ConstantPointerNull *P = dyn_cast<ConstantPointerNull>(V))
return visitConstantPointerNull(*P);
if (GlobalAlias *GA = dyn_cast<GlobalAlias>(V))
return visitGlobalAlias(*GA);
if (GlobalVariable *GV = dyn_cast<GlobalVariable>(V))
return visitGlobalVariable(*GV);
if (UndefValue *UV = dyn_cast<UndefValue>(V))
return visitUndefValue(*UV);
if (ConstantExpr *CE = dyn_cast<ConstantExpr>(V)) {
if (CE->getOpcode() == Instruction::IntToPtr)
return unknown(); // clueless
if (CE->getOpcode() == Instruction::GetElementPtr)
return visitGEPOperator(cast<GEPOperator>(*CE));
}
LLVM_DEBUG(dbgs() << "ObjectSizeOffsetVisitor::compute() unhandled value: "
<< *V << '\n');
return unknown();
}
/// When we're compiling N-bit code, and the user uses parameters that are
/// greater than N bits (e.g. uint64_t on a 32-bit build), we can run into
/// trouble with APInt size issues. This function handles resizing + overflow
/// checks for us. Check and zext or trunc \p I depending on IntTyBits and
/// I's value.
bool ObjectSizeOffsetVisitor::CheckedZextOrTrunc(APInt &I) {
// More bits than we can handle. Checking the bit width isn't necessary, but
// it's faster than checking active bits, and should give `false` in the
// vast majority of cases.
if (I.getBitWidth() > IntTyBits && I.getActiveBits() > IntTyBits)
return false;
if (I.getBitWidth() != IntTyBits)
I = I.zextOrTrunc(IntTyBits);
return true;
}
SizeOffsetType ObjectSizeOffsetVisitor::visitAllocaInst(AllocaInst &I) {
if (!I.getAllocatedType()->isSized())
return unknown();
if (isa<ScalableVectorType>(I.getAllocatedType()))
return unknown();
APInt Size(IntTyBits, DL.getTypeAllocSize(I.getAllocatedType()));
if (!I.isArrayAllocation())
return std::make_pair(align(Size, I.getAlignment()), Zero);
Value *ArraySize = I.getArraySize();
if (const ConstantInt *C = dyn_cast<ConstantInt>(ArraySize)) {
APInt NumElems = C->getValue();
if (!CheckedZextOrTrunc(NumElems))
return unknown();
bool Overflow;
Size = Size.umul_ov(NumElems, Overflow);
return Overflow ? unknown() : std::make_pair(align(Size, I.getAlignment()),
Zero);
}
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitArgument(Argument &A) {
2016-07-08 00:19:09 +08:00
// No interprocedural analysis is done at the moment.
if (!A.hasPassPointeeByValueAttr()) {
++ObjectVisitorArgument;
return unknown();
}
PointerType *PT = cast<PointerType>(A.getType());
APInt Size(IntTyBits, DL.getTypeAllocSize(PT->getElementType()));
return std::make_pair(align(Size, A.getParamAlignment()), Zero);
}
SizeOffsetType ObjectSizeOffsetVisitor::visitCallBase(CallBase &CB) {
Optional<AllocFnsTy> FnData = getAllocationSize(&CB, TLI);
if (!FnData)
return unknown();
2016-07-08 00:19:09 +08:00
// Handle strdup-like functions separately.
if (FnData->AllocTy == StrDupLike) {
APInt Size(IntTyBits, GetStringLength(CB.getArgOperand(0)));
if (!Size)
return unknown();
2016-07-08 00:19:09 +08:00
// Strndup limits strlen.
if (FnData->FstParam > 0) {
ConstantInt *Arg =
dyn_cast<ConstantInt>(CB.getArgOperand(FnData->FstParam));
if (!Arg)
return unknown();
APInt MaxSize = Arg->getValue().zextOrSelf(IntTyBits);
if (Size.ugt(MaxSize))
Size = MaxSize + 1;
}
return std::make_pair(Size, Zero);
}
ConstantInt *Arg = dyn_cast<ConstantInt>(CB.getArgOperand(FnData->FstParam));
if (!Arg)
return unknown();
APInt Size = Arg->getValue();
if (!CheckedZextOrTrunc(Size))
return unknown();
2016-07-08 00:19:09 +08:00
// Size is determined by just 1 parameter.
if (FnData->SndParam < 0)
return std::make_pair(Size, Zero);
Arg = dyn_cast<ConstantInt>(CB.getArgOperand(FnData->SndParam));
if (!Arg)
return unknown();
APInt NumElems = Arg->getValue();
if (!CheckedZextOrTrunc(NumElems))
return unknown();
bool Overflow;
Size = Size.umul_ov(NumElems, Overflow);
return Overflow ? unknown() : std::make_pair(Size, Zero);
// TODO: handle more standard functions (+ wchar cousins):
// - strdup / strndup
// - strcpy / strncpy
// - strcat / strncat
// - memcpy / memmove
// - strcat / strncat
// - memset
}
SizeOffsetType
ObjectSizeOffsetVisitor::visitConstantPointerNull(ConstantPointerNull& CPN) {
// If null is unknown, there's nothing we can do. Additionally, non-zero
// address spaces can make use of null, so we don't presume to know anything
// about that.
//
// TODO: How should this work with address space casts? We currently just drop
// them on the floor, but it's unclear what we should do when a NULL from
// addrspace(1) gets casted to addrspace(0) (or vice-versa).
if (Options.NullIsUnknownSize || CPN.getType()->getAddressSpace())
return unknown();
return std::make_pair(Zero, Zero);
}
SizeOffsetType
ObjectSizeOffsetVisitor::visitExtractElementInst(ExtractElementInst&) {
return unknown();
}
SizeOffsetType
ObjectSizeOffsetVisitor::visitExtractValueInst(ExtractValueInst&) {
// Easy cases were already folded by previous passes.
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitGEPOperator(GEPOperator &GEP) {
SizeOffsetType PtrData = compute(GEP.getPointerOperand());
APInt Offset(DL.getIndexTypeSizeInBits(GEP.getPointerOperand()->getType()), 0);
if (!bothKnown(PtrData) || !GEP.accumulateConstantOffset(DL, Offset))
return unknown();
return std::make_pair(PtrData.first, PtrData.second + Offset);
}
SizeOffsetType ObjectSizeOffsetVisitor::visitGlobalAlias(GlobalAlias &GA) {
Don't IPO over functions that can be de-refined Summary: Fixes PR26774. If you're aware of the issue, feel free to skip the "Motivation" section and jump directly to "This patch". Motivation: I define "refinement" as discarding behaviors from a program that the optimizer has license to discard. So transforming: ``` void f(unsigned x) { unsigned t = 5 / x; (void)t; } ``` to ``` void f(unsigned x) { } ``` is refinement, since the behavior went from "if x == 0 then undefined else nothing" to "nothing" (the optimizer has license to discard undefined behavior). Refinement is a fundamental aspect of many mid-level optimizations done by LLVM. For instance, transforming `x == (x + 1)` to `false` also involves refinement since the expression's value went from "if x is `undef` then { `true` or `false` } else { `false` }" to "`false`" (by definition, the optimizer has license to fold `undef` to any non-`undef` value). Unfortunately, refinement implies that the optimizer cannot assume that the implementation of a function it can see has all of the behavior an unoptimized or a differently optimized version of the same function can have. This is a problem for functions with comdat linkage, where a function can be replaced by an unoptimized or a differently optimized version of the same source level function. For instance, FunctionAttrs cannot assume a comdat function is actually `readnone` even if it does not have any loads or stores in it; since there may have been loads and stores in the "original function" that were refined out in the currently visible variant, and at the link step the linker may in fact choose an implementation with a load or a store. As an example, consider a function that does two atomic loads from the same memory location, and writes to memory only if the two values are not equal. The optimizer is allowed to refine this function by first CSE'ing the two loads, and the folding the comparision to always report that the two values are equal. Such a refined variant will look like it is `readonly`. However, the unoptimized version of the function can still write to memory (since the two loads //can// result in different values), and selecting the unoptimized version at link time will retroactively invalidate transforms we may have done under the assumption that the function does not write to memory. Note: this is not just a problem with atomics or with linking differently optimized object files. See PR26774 for more realistic examples that involved neither. This patch: This change introduces a new set of linkage types, predicated as `GlobalValue::mayBeDerefined` that returns true if the linkage type allows a function to be replaced by a differently optimized variant at link time. It then changes a set of IPO passes to bail out if they see such a function. Reviewers: chandlerc, hfinkel, dexonsmith, joker.eph, rnk Subscribers: mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D18634 llvm-svn: 265762
2016-04-08 08:48:30 +08:00
if (GA.isInterposable())
return unknown();
return compute(GA.getAliasee());
}
SizeOffsetType ObjectSizeOffsetVisitor::visitGlobalVariable(GlobalVariable &GV){
if (!GV.hasDefinitiveInitializer())
return unknown();
APInt Size(IntTyBits, DL.getTypeAllocSize(GV.getValueType()));
return std::make_pair(align(Size, GV.getAlignment()), Zero);
}
SizeOffsetType ObjectSizeOffsetVisitor::visitIntToPtrInst(IntToPtrInst&) {
// clueless
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitLoadInst(LoadInst&) {
++ObjectVisitorLoad;
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitPHINode(PHINode&) {
// too complex to analyze statically.
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitSelectInst(SelectInst &I) {
SizeOffsetType TrueSide = compute(I.getTrueValue());
SizeOffsetType FalseSide = compute(I.getFalseValue());
if (bothKnown(TrueSide) && bothKnown(FalseSide)) {
if (TrueSide == FalseSide) {
return TrueSide;
}
APInt TrueResult = getSizeWithOverflow(TrueSide);
APInt FalseResult = getSizeWithOverflow(FalseSide);
if (TrueResult == FalseResult) {
return TrueSide;
}
if (Options.EvalMode == ObjectSizeOpts::Mode::Min) {
if (TrueResult.slt(FalseResult))
return TrueSide;
return FalseSide;
}
if (Options.EvalMode == ObjectSizeOpts::Mode::Max) {
if (TrueResult.sgt(FalseResult))
return TrueSide;
return FalseSide;
}
}
return unknown();
}
SizeOffsetType ObjectSizeOffsetVisitor::visitUndefValue(UndefValue&) {
return std::make_pair(Zero, Zero);
}
SizeOffsetType ObjectSizeOffsetVisitor::visitInstruction(Instruction &I) {
LLVM_DEBUG(dbgs() << "ObjectSizeOffsetVisitor unknown instruction:" << I
<< '\n');
return unknown();
}
ObjectSizeOffsetEvaluator::ObjectSizeOffsetEvaluator(
const DataLayout &DL, const TargetLibraryInfo *TLI, LLVMContext &Context,
ObjectSizeOpts EvalOpts)
: DL(DL), TLI(TLI), Context(Context),
Builder(Context, TargetFolder(DL),
IRBuilderCallbackInserter(
[&](Instruction *I) { InsertedInstructions.insert(I); })),
EvalOpts(EvalOpts) {
// IntTy and Zero must be set for each compute() since the address space may
// be different for later objects.
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::compute(Value *V) {
// XXX - Are vectors of pointers possible here?
IntTy = cast<IntegerType>(DL.getIndexType(V->getType()));
Zero = ConstantInt::get(IntTy, 0);
SizeOffsetEvalType Result = compute_(V);
if (!bothKnown(Result)) {
2016-07-08 00:19:09 +08:00
// Erase everything that was computed in this iteration from the cache, so
// that no dangling references are left behind. We could be a bit smarter if
// we kept a dependency graph. It's probably not worth the complexity.
for (const Value *SeenVal : SeenVals) {
CacheMapTy::iterator CacheIt = CacheMap.find(SeenVal);
// non-computable results can be safely cached
if (CacheIt != CacheMap.end() && anyKnown(CacheIt->second))
CacheMap.erase(CacheIt);
}
// Erase any instructions we inserted as part of the traversal.
for (Instruction *I : InsertedInstructions) {
I->replaceAllUsesWith(UndefValue::get(I->getType()));
I->eraseFromParent();
}
}
SeenVals.clear();
InsertedInstructions.clear();
return Result;
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::compute_(Value *V) {
ObjectSizeOffsetVisitor Visitor(DL, TLI, Context, EvalOpts);
SizeOffsetType Const = Visitor.compute(V);
if (Visitor.bothKnown(Const))
return std::make_pair(ConstantInt::get(Context, Const.first),
ConstantInt::get(Context, Const.second));
V = V->stripPointerCasts();
2016-07-08 00:19:09 +08:00
// Check cache.
CacheMapTy::iterator CacheIt = CacheMap.find(V);
if (CacheIt != CacheMap.end())
return CacheIt->second;
2016-07-08 00:19:09 +08:00
// Always generate code immediately before the instruction being
// processed, so that the generated code dominates the same BBs.
Analysis: Remove implicit ilist iterator conversions Remove implicit ilist iterator conversions from LLVMAnalysis. I came across something really scary in `llvm::isKnownNotFullPoison()` which relied on `Instruction::getNextNode()` being completely broken (not surprising, but scary nevertheless). This function is documented (and coded to) return `nullptr` when it gets to the sentinel, but with an `ilist_half_node` as a sentinel, the sentinel check looks into some other memory and we don't recognize we've hit the end. Rooting out these scary cases is the reason I'm removing the implicit conversions before doing anything else with `ilist`; I'm not at all surprised that clients rely on badness. I found another scary case -- this time, not relying on badness, just bad (but I guess getting lucky so far) -- in `ObjectSizeOffsetEvaluator::compute_()`. Here, we save out the insertion point, do some things, and then restore it. Previously, we let the iterator auto-convert to `Instruction*`, and then set it back using the `Instruction*` version: Instruction *PrevInsertPoint = Builder.GetInsertPoint(); /* Logic that may change insert point */ if (PrevInsertPoint) Builder.SetInsertPoint(PrevInsertPoint); The check for `PrevInsertPoint` doesn't protect correctly against bad accesses. If the insertion point has been set to the end of a basic block (i.e., `SetInsertPoint(SomeBB)`), then `GetInsertPoint()` returns an iterator pointing at the list sentinel. The version of `SetInsertPoint()` that's getting called will then call `PrevInsertPoint->getParent()`, which explodes horribly. The only reason this hasn't blown up is that it's fairly unlikely the builder is adding to the end of the block; usually, we're adding instructions somewhere before the terminator. llvm-svn: 249925
2015-10-10 08:53:03 +08:00
BuilderTy::InsertPointGuard Guard(Builder);
if (Instruction *I = dyn_cast<Instruction>(V))
Builder.SetInsertPoint(I);
2016-07-08 00:19:09 +08:00
// Now compute the size and offset.
SizeOffsetEvalType Result;
// Record the pointers that were handled in this run, so that they can be
// cleaned later if something fails. We also use this set to break cycles that
// can occur in dead code.
if (!SeenVals.insert(V).second) {
Result = unknown();
} else if (GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
Result = visitGEPOperator(*GEP);
} else if (Instruction *I = dyn_cast<Instruction>(V)) {
Result = visit(*I);
} else if (isa<Argument>(V) ||
(isa<ConstantExpr>(V) &&
cast<ConstantExpr>(V)->getOpcode() == Instruction::IntToPtr) ||
isa<GlobalAlias>(V) ||
isa<GlobalVariable>(V)) {
2016-07-08 00:19:09 +08:00
// Ignore values where we cannot do more than ObjectSizeVisitor.
Result = unknown();
} else {
LLVM_DEBUG(
dbgs() << "ObjectSizeOffsetEvaluator::compute() unhandled value: " << *V
<< '\n');
Result = unknown();
}
// Don't reuse CacheIt since it may be invalid at this point.
CacheMap[V] = Result;
return Result;
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitAllocaInst(AllocaInst &I) {
if (!I.getAllocatedType()->isSized())
return unknown();
// must be a VLA
assert(I.isArrayAllocation());
Value *ArraySize = I.getArraySize();
Value *Size = ConstantInt::get(ArraySize->getType(),
DL.getTypeAllocSize(I.getAllocatedType()));
Size = Builder.CreateMul(Size, ArraySize);
return std::make_pair(Size, Zero);
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitCallBase(CallBase &CB) {
Optional<AllocFnsTy> FnData = getAllocationSize(&CB, TLI);
if (!FnData)
return unknown();
2016-07-08 00:19:09 +08:00
// Handle strdup-like functions separately.
if (FnData->AllocTy == StrDupLike) {
// TODO
return unknown();
}
Value *FirstArg = CB.getArgOperand(FnData->FstParam);
FirstArg = Builder.CreateZExtOrTrunc(FirstArg, IntTy);
if (FnData->SndParam < 0)
return std::make_pair(FirstArg, Zero);
Value *SecondArg = CB.getArgOperand(FnData->SndParam);
SecondArg = Builder.CreateZExtOrTrunc(SecondArg, IntTy);
Value *Size = Builder.CreateMul(FirstArg, SecondArg);
return std::make_pair(Size, Zero);
// TODO: handle more standard functions (+ wchar cousins):
// - strdup / strndup
// - strcpy / strncpy
// - strcat / strncat
// - memcpy / memmove
// - strcat / strncat
// - memset
}
SizeOffsetEvalType
ObjectSizeOffsetEvaluator::visitExtractElementInst(ExtractElementInst&) {
return unknown();
}
SizeOffsetEvalType
ObjectSizeOffsetEvaluator::visitExtractValueInst(ExtractValueInst&) {
return unknown();
}
SizeOffsetEvalType
ObjectSizeOffsetEvaluator::visitGEPOperator(GEPOperator &GEP) {
SizeOffsetEvalType PtrData = compute_(GEP.getPointerOperand());
if (!bothKnown(PtrData))
return unknown();
Value *Offset = EmitGEPOffset(&Builder, DL, &GEP, /*NoAssumptions=*/true);
Offset = Builder.CreateAdd(PtrData.second, Offset);
return std::make_pair(PtrData.first, Offset);
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitIntToPtrInst(IntToPtrInst&) {
// clueless
return unknown();
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitLoadInst(LoadInst&) {
return unknown();
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitPHINode(PHINode &PHI) {
2016-07-08 00:19:09 +08:00
// Create 2 PHIs: one for size and another for offset.
PHINode *SizePHI = Builder.CreatePHI(IntTy, PHI.getNumIncomingValues());
PHINode *OffsetPHI = Builder.CreatePHI(IntTy, PHI.getNumIncomingValues());
2016-07-08 00:19:09 +08:00
// Insert right away in the cache to handle recursive PHIs.
CacheMap[&PHI] = std::make_pair(SizePHI, OffsetPHI);
2016-07-08 00:19:09 +08:00
// Compute offset/size for each PHI incoming pointer.
for (unsigned i = 0, e = PHI.getNumIncomingValues(); i != e; ++i) {
Analysis: Remove implicit ilist iterator conversions Remove implicit ilist iterator conversions from LLVMAnalysis. I came across something really scary in `llvm::isKnownNotFullPoison()` which relied on `Instruction::getNextNode()` being completely broken (not surprising, but scary nevertheless). This function is documented (and coded to) return `nullptr` when it gets to the sentinel, but with an `ilist_half_node` as a sentinel, the sentinel check looks into some other memory and we don't recognize we've hit the end. Rooting out these scary cases is the reason I'm removing the implicit conversions before doing anything else with `ilist`; I'm not at all surprised that clients rely on badness. I found another scary case -- this time, not relying on badness, just bad (but I guess getting lucky so far) -- in `ObjectSizeOffsetEvaluator::compute_()`. Here, we save out the insertion point, do some things, and then restore it. Previously, we let the iterator auto-convert to `Instruction*`, and then set it back using the `Instruction*` version: Instruction *PrevInsertPoint = Builder.GetInsertPoint(); /* Logic that may change insert point */ if (PrevInsertPoint) Builder.SetInsertPoint(PrevInsertPoint); The check for `PrevInsertPoint` doesn't protect correctly against bad accesses. If the insertion point has been set to the end of a basic block (i.e., `SetInsertPoint(SomeBB)`), then `GetInsertPoint()` returns an iterator pointing at the list sentinel. The version of `SetInsertPoint()` that's getting called will then call `PrevInsertPoint->getParent()`, which explodes horribly. The only reason this hasn't blown up is that it's fairly unlikely the builder is adding to the end of the block; usually, we're adding instructions somewhere before the terminator. llvm-svn: 249925
2015-10-10 08:53:03 +08:00
Builder.SetInsertPoint(&*PHI.getIncomingBlock(i)->getFirstInsertionPt());
SizeOffsetEvalType EdgeData = compute_(PHI.getIncomingValue(i));
if (!bothKnown(EdgeData)) {
OffsetPHI->replaceAllUsesWith(UndefValue::get(IntTy));
OffsetPHI->eraseFromParent();
InsertedInstructions.erase(OffsetPHI);
SizePHI->replaceAllUsesWith(UndefValue::get(IntTy));
SizePHI->eraseFromParent();
InsertedInstructions.erase(SizePHI);
return unknown();
}
SizePHI->addIncoming(EdgeData.first, PHI.getIncomingBlock(i));
OffsetPHI->addIncoming(EdgeData.second, PHI.getIncomingBlock(i));
}
Value *Size = SizePHI, *Offset = OffsetPHI;
if (Value *Tmp = SizePHI->hasConstantValue()) {
Size = Tmp;
SizePHI->replaceAllUsesWith(Size);
SizePHI->eraseFromParent();
InsertedInstructions.erase(SizePHI);
}
if (Value *Tmp = OffsetPHI->hasConstantValue()) {
Offset = Tmp;
OffsetPHI->replaceAllUsesWith(Offset);
OffsetPHI->eraseFromParent();
InsertedInstructions.erase(OffsetPHI);
}
return std::make_pair(Size, Offset);
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitSelectInst(SelectInst &I) {
SizeOffsetEvalType TrueSide = compute_(I.getTrueValue());
SizeOffsetEvalType FalseSide = compute_(I.getFalseValue());
if (!bothKnown(TrueSide) || !bothKnown(FalseSide))
return unknown();
if (TrueSide == FalseSide)
return TrueSide;
Value *Size = Builder.CreateSelect(I.getCondition(), TrueSide.first,
FalseSide.first);
Value *Offset = Builder.CreateSelect(I.getCondition(), TrueSide.second,
FalseSide.second);
return std::make_pair(Size, Offset);
}
SizeOffsetEvalType ObjectSizeOffsetEvaluator::visitInstruction(Instruction &I) {
LLVM_DEBUG(dbgs() << "ObjectSizeOffsetEvaluator unknown instruction:" << I
<< '\n');
return unknown();
}