Teresa Johnson 7ed8124d46 [HeapProf] Clang and LLVM support for heap profiling instrumentation
See RFC for background:
http://lists.llvm.org/pipermail/llvm-dev/2020-June/142744.html

Note that the runtime changes will be sent separately (hopefully this
week, need to add some tests).

This patch includes the LLVM pass to instrument memory accesses with
either inline sequences to increment the access count in the shadow
location, or alternatively to call into the runtime. It also changes
calls to memset/memcpy/memmove to the equivalent runtime version.
The pass is modeled on the address sanitizer pass.

The clang changes add the driver option to invoke the new pass, and to
link with the upcoming heap profiling runtime libraries.

Currently there is no attempt to optimize the instrumentation, e.g. to
aggregate updates to the same memory allocation. That will be
implemented as follow on work.

Differential Revision: https://reviews.llvm.org/D85948
2020-08-27 08:50:35 -07:00

132 lines
5.3 KiB
C++

//===-- Instrumentation.cpp - TransformUtils Infrastructure ---------------===//
//
// 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 defines the common initialization infrastructure for the
// Instrumentation library.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Instrumentation.h"
#include "llvm-c/Initialization.h"
#include "llvm/ADT/Triple.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/InitializePasses.h"
#include "llvm/PassRegistry.h"
using namespace llvm;
/// Moves I before IP. Returns new insert point.
static BasicBlock::iterator moveBeforeInsertPoint(BasicBlock::iterator I, BasicBlock::iterator IP) {
// If I is IP, move the insert point down.
if (I == IP) {
++IP;
} else {
// Otherwise, move I before IP and return IP.
I->moveBefore(&*IP);
}
return IP;
}
/// Instrumentation passes often insert conditional checks into entry blocks.
/// Call this function before splitting the entry block to move instructions
/// that must remain in the entry block up before the split point. Static
/// allocas and llvm.localescape calls, for example, must remain in the entry
/// block.
BasicBlock::iterator llvm::PrepareToSplitEntryBlock(BasicBlock &BB,
BasicBlock::iterator IP) {
assert(&BB.getParent()->getEntryBlock() == &BB);
for (auto I = IP, E = BB.end(); I != E; ++I) {
bool KeepInEntry = false;
if (auto *AI = dyn_cast<AllocaInst>(I)) {
if (AI->isStaticAlloca())
KeepInEntry = true;
} else if (auto *II = dyn_cast<IntrinsicInst>(I)) {
if (II->getIntrinsicID() == llvm::Intrinsic::localescape)
KeepInEntry = true;
}
if (KeepInEntry)
IP = moveBeforeInsertPoint(I, IP);
}
return IP;
}
// Create a constant for Str so that we can pass it to the run-time lib.
GlobalVariable *llvm::createPrivateGlobalForString(Module &M, StringRef Str,
bool AllowMerging,
const char *NamePrefix) {
Constant *StrConst = ConstantDataArray::getString(M.getContext(), Str);
// We use private linkage for module-local strings. If they can be merged
// with another one, we set the unnamed_addr attribute.
GlobalVariable *GV =
new GlobalVariable(M, StrConst->getType(), true,
GlobalValue::PrivateLinkage, StrConst, NamePrefix);
if (AllowMerging)
GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global);
GV->setAlignment(Align(1)); // Strings may not be merged w/o setting
// alignment explicitly.
return GV;
}
Comdat *llvm::GetOrCreateFunctionComdat(Function &F, Triple &T,
const std::string &ModuleId) {
if (auto Comdat = F.getComdat()) return Comdat;
assert(F.hasName());
Module *M = F.getParent();
std::string Name = std::string(F.getName());
// Make a unique comdat name for internal linkage things on ELF. On COFF, the
// name of the comdat group identifies the leader symbol of the comdat group.
// The linkage of the leader symbol is considered during comdat resolution,
// and internal symbols with the same name from different objects will not be
// merged.
if (T.isOSBinFormatELF() && F.hasLocalLinkage()) {
if (ModuleId.empty())
return nullptr;
Name += ModuleId;
}
// Make a new comdat for the function. Use the "no duplicates" selection kind
// for non-weak symbols if the object file format supports it.
Comdat *C = M->getOrInsertComdat(Name);
if (T.isOSBinFormatCOFF() && !F.isWeakForLinker())
C->setSelectionKind(Comdat::NoDuplicates);
F.setComdat(C);
return C;
}
/// initializeInstrumentation - Initialize all passes in the TransformUtils
/// library.
void llvm::initializeInstrumentation(PassRegistry &Registry) {
initializeAddressSanitizerLegacyPassPass(Registry);
initializeModuleAddressSanitizerLegacyPassPass(Registry);
initializeHeapProfilerLegacyPassPass(Registry);
initializeModuleHeapProfilerLegacyPassPass(Registry);
initializeBoundsCheckingLegacyPassPass(Registry);
initializeControlHeightReductionLegacyPassPass(Registry);
initializeGCOVProfilerLegacyPassPass(Registry);
initializePGOInstrumentationGenLegacyPassPass(Registry);
initializePGOInstrumentationUseLegacyPassPass(Registry);
initializePGOIndirectCallPromotionLegacyPassPass(Registry);
initializePGOMemOPSizeOptLegacyPassPass(Registry);
initializeCGProfileLegacyPassPass(Registry);
initializeInstrOrderFileLegacyPassPass(Registry);
initializeInstrProfilingLegacyPassPass(Registry);
initializeMemorySanitizerLegacyPassPass(Registry);
initializeHWAddressSanitizerLegacyPassPass(Registry);
initializeThreadSanitizerLegacyPassPass(Registry);
initializeModuleSanitizerCoverageLegacyPassPass(Registry);
initializeDataFlowSanitizerLegacyPassPass(Registry);
}
/// LLVMInitializeInstrumentation - C binding for
/// initializeInstrumentation.
void LLVMInitializeInstrumentation(LLVMPassRegistryRef R) {
initializeInstrumentation(*unwrap(R));
}