llvm-project/llvm/lib/Transforms/IPO/StripSymbols.cpp

353 lines
11 KiB
C++
Raw Normal View History

//===- StripSymbols.cpp - Strip symbols and debug info from a module ------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The StripSymbols transformation implements code stripping. Specifically, it
// can delete:
//
// * names for virtual registers
// * symbols for internal globals and functions
// * debug information
//
// Note that this transformation makes code much less readable, so it should
// only be used in situations where the 'strip' utility would be used, such as
// reducing code size or making it harder to reverse engineer code.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/IPO.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/TypeFinder.h"
#include "llvm/IR/ValueSymbolTable.h"
#include "llvm/Pass.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
namespace {
class StripSymbols : public ModulePass {
bool OnlyDebugInfo;
public:
2007-05-06 21:37:16 +08:00
static char ID; // Pass identification, replacement for typeid
explicit StripSymbols(bool ODI = false)
: ModulePass(ID), OnlyDebugInfo(ODI) {
initializeStripSymbolsPass(*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
}
};
class StripNonDebugSymbols : public ModulePass {
public:
static char ID; // Pass identification, replacement for typeid
explicit StripNonDebugSymbols()
: ModulePass(ID) {
initializeStripNonDebugSymbolsPass(*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
}
};
class StripDebugDeclare : public ModulePass {
public:
static char ID; // Pass identification, replacement for typeid
explicit StripDebugDeclare()
: ModulePass(ID) {
initializeStripDebugDeclarePass(*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
}
};
class StripDeadDebugInfo : public ModulePass {
public:
static char ID; // Pass identification, replacement for typeid
explicit StripDeadDebugInfo()
: ModulePass(ID) {
initializeStripDeadDebugInfoPass(*PassRegistry::getPassRegistry());
}
bool runOnModule(Module &M) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesAll();
}
};
}
char StripSymbols::ID = 0;
INITIALIZE_PASS(StripSymbols, "strip",
"Strip all symbols from a module", false, false)
ModulePass *llvm::createStripSymbolsPass(bool OnlyDebugInfo) {
return new StripSymbols(OnlyDebugInfo);
}
char StripNonDebugSymbols::ID = 0;
INITIALIZE_PASS(StripNonDebugSymbols, "strip-nondebug",
"Strip all symbols, except dbg symbols, from a module",
false, false)
ModulePass *llvm::createStripNonDebugSymbolsPass() {
return new StripNonDebugSymbols();
}
char StripDebugDeclare::ID = 0;
INITIALIZE_PASS(StripDebugDeclare, "strip-debug-declare",
"Strip all llvm.dbg.declare intrinsics", false, false)
ModulePass *llvm::createStripDebugDeclarePass() {
return new StripDebugDeclare();
}
char StripDeadDebugInfo::ID = 0;
INITIALIZE_PASS(StripDeadDebugInfo, "strip-dead-debug-info",
"Strip debug info for unused symbols", false, false)
ModulePass *llvm::createStripDeadDebugInfoPass() {
return new StripDeadDebugInfo();
}
/// OnlyUsedBy - Return true if V is only used by Usr.
static bool OnlyUsedBy(Value *V, Value *Usr) {
[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 (User *U : V->users())
if (U != Usr)
return false;
[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
return true;
}
static void RemoveDeadConstant(Constant *C) {
assert(C->use_empty() && "Constant is not dead!");
SmallPtrSet<Constant*, 4> Operands;
for (Value *Op : C->operands())
if (OnlyUsedBy(Op, C))
Operands.insert(cast<Constant>(Op));
if (GlobalVariable *GV = dyn_cast<GlobalVariable>(C)) {
if (!GV->hasLocalLinkage()) return; // Don't delete non-static globals.
GV->eraseFromParent();
}
else if (!isa<Function>(C))
if (isa<CompositeType>(C->getType()))
C->destroyConstant();
// If the constant referenced anything, see if we can delete it as well.
for (Constant *O : Operands)
RemoveDeadConstant(O);
}
// Strip the symbol table of its names.
//
static void StripSymtab(ValueSymbolTable &ST, bool PreserveDbgInfo) {
for (ValueSymbolTable::iterator VI = ST.begin(), VE = ST.end(); VI != VE; ) {
Value *V = VI->getValue();
++VI;
if (!isa<GlobalValue>(V) || cast<GlobalValue>(V)->hasLocalLinkage()) {
if (!PreserveDbgInfo || !V->getName().startswith("llvm.dbg"))
// Set name to "", removing from symbol table!
V->setName("");
}
}
}
// Strip any named types of their names.
static void StripTypeNames(Module &M, bool PreserveDbgInfo) {
TypeFinder StructTypes;
StructTypes.run(M, false);
for (unsigned i = 0, e = StructTypes.size(); i != e; ++i) {
StructType *STy = StructTypes[i];
if (STy->isLiteral() || STy->getName().empty()) continue;
if (PreserveDbgInfo && STy->getName().startswith("llvm.dbg"))
continue;
STy->setName("");
}
}
/// Find values that are marked as llvm.used.
static void findUsedValues(GlobalVariable *LLVMUsed,
SmallPtrSetImpl<const GlobalValue*> &UsedValues) {
if (!LLVMUsed) return;
UsedValues.insert(LLVMUsed);
ConstantArray *Inits = cast<ConstantArray>(LLVMUsed->getInitializer());
for (unsigned i = 0, e = Inits->getNumOperands(); i != e; ++i)
if (GlobalValue *GV =
dyn_cast<GlobalValue>(Inits->getOperand(i)->stripPointerCasts()))
UsedValues.insert(GV);
}
/// StripSymbolNames - Strip symbol names.
static bool StripSymbolNames(Module &M, bool PreserveDbgInfo) {
SmallPtrSet<const GlobalValue*, 8> llvmUsedValues;
findUsedValues(M.getGlobalVariable("llvm.used"), llvmUsedValues);
findUsedValues(M.getGlobalVariable("llvm.compiler.used"), llvmUsedValues);
for (Module::global_iterator I = M.global_begin(), E = M.global_end();
I != E; ++I) {
if (I->hasLocalLinkage() && llvmUsedValues.count(&*I) == 0)
if (!PreserveDbgInfo || !I->getName().startswith("llvm.dbg"))
I->setName(""); // Internal symbols can't participate in linkage
}
for (Function &I : M) {
if (I.hasLocalLinkage() && llvmUsedValues.count(&I) == 0)
if (!PreserveDbgInfo || !I.getName().startswith("llvm.dbg"))
I.setName(""); // Internal symbols can't participate in linkage
StripSymtab(I.getValueSymbolTable(), PreserveDbgInfo);
}
// Remove all names from types.
StripTypeNames(M, PreserveDbgInfo);
return true;
}
bool StripSymbols::runOnModule(Module &M) {
if (skipModule(M))
return false;
bool Changed = false;
Changed |= StripDebugInfo(M);
if (!OnlyDebugInfo)
Changed |= StripSymbolNames(M, false);
return Changed;
}
bool StripNonDebugSymbols::runOnModule(Module &M) {
if (skipModule(M))
return false;
return StripSymbolNames(M, true);
}
bool StripDebugDeclare::runOnModule(Module &M) {
if (skipModule(M))
return false;
Function *Declare = M.getFunction("llvm.dbg.declare");
std::vector<Constant*> DeadConstants;
if (Declare) {
while (!Declare->use_empty()) {
[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
CallInst *CI = cast<CallInst>(Declare->user_back());
2010-06-30 20:40:35 +08:00
Value *Arg1 = CI->getArgOperand(0);
Value *Arg2 = CI->getArgOperand(1);
assert(CI->use_empty() && "llvm.dbg intrinsic should have void result");
CI->eraseFromParent();
if (Arg1->use_empty()) {
if (Constant *C = dyn_cast<Constant>(Arg1))
DeadConstants.push_back(C);
else
RecursivelyDeleteTriviallyDeadInstructions(Arg1);
}
if (Arg2->use_empty())
if (Constant *C = dyn_cast<Constant>(Arg2))
DeadConstants.push_back(C);
}
Declare->eraseFromParent();
}
while (!DeadConstants.empty()) {
Constant *C = DeadConstants.back();
DeadConstants.pop_back();
if (GlobalVariable *GV = dyn_cast<GlobalVariable>(C)) {
if (GV->hasLocalLinkage())
RemoveDeadConstant(GV);
} else
RemoveDeadConstant(C);
}
return true;
}
/// Remove any debug info for global variables/functions in the given module for
/// which said global variable/function no longer exists (i.e. is null).
///
/// Debugging information is encoded in llvm IR using metadata. This is designed
/// such a way that debug info for symbols preserved even if symbols are
/// optimized away by the optimizer. This special pass removes debug info for
/// such symbols.
bool StripDeadDebugInfo::runOnModule(Module &M) {
if (skipModule(M))
return false;
bool Changed = false;
LLVMContext &C = M.getContext();
// Find all debug info in F. This is actually overkill in terms of what we
// want to do, but we want to try and be as resilient as possible in the face
// of potential debug info changes by using the formal interfaces given to us
// as much as possible.
DebugInfoFinder F;
F.processModule(M);
// For each compile unit, find the live set of global variables/functions and
// replace the current list of potentially dead global variables/functions
// with the live list.
IR: Split Metadata from Value Split `Metadata` away from the `Value` class hierarchy, as part of PR21532. Assembly and bitcode changes are in the wings, but this is the bulk of the change for the IR C++ API. I have a follow-up patch prepared for `clang`. If this breaks other sub-projects, I apologize in advance :(. Help me compile it on Darwin I'll try to fix it. FWIW, the errors should be easy to fix, so it may be simpler to just fix it yourself. This breaks the build for all metadata-related code that's out-of-tree. Rest assured the transition is mechanical and the compiler should catch almost all of the problems. Here's a quick guide for updating your code: - `Metadata` is the root of a class hierarchy with three main classes: `MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from the `Value` class hierarchy. It is typeless -- i.e., instances do *not* have a `Type`. - `MDNode`'s operands are all `Metadata *` (instead of `Value *`). - `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively. If you're referring solely to resolved `MDNode`s -- post graph construction -- just use `MDNode*`. - `MDNode` (and the rest of `Metadata`) have only limited support for `replaceAllUsesWith()`. As long as an `MDNode` is pointing at a forward declaration -- the result of `MDNode::getTemporary()` -- it maintains a side map of its uses and can RAUW itself. Once the forward declarations are fully resolved RAUW support is dropped on the ground. This means that uniquing collisions on changing operands cause nodes to become "distinct". (This already happened fairly commonly, whenever an operand went to null.) If you're constructing complex (non self-reference) `MDNode` cycles, you need to call `MDNode::resolveCycles()` on each node (or on a top-level node that somehow references all of the nodes). Also, don't do that. Metadata cycles (and the RAUW machinery needed to construct them) are expensive. - An `MDNode` can only refer to a `Constant` through a bridge called `ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`). As a side effect, accessing an operand of an `MDNode` that is known to be, e.g., `ConstantInt`, takes three steps: first, cast from `Metadata` to `ConstantAsMetadata`; second, extract the `Constant`; third, cast down to `ConstantInt`. The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have metadata schema owners transition away from using `Constant`s when the type isn't important (and they don't care about referring to `GlobalValue`s). In the meantime, I've added transitional API to the `mdconst` namespace that matches semantics with the old code, in order to avoid adding the error-prone three-step equivalent to every call site. If your old code was: MDNode *N = foo(); bar(isa <ConstantInt>(N->getOperand(0))); baz(cast <ConstantInt>(N->getOperand(1))); bak(cast_or_null <ConstantInt>(N->getOperand(2))); bat(dyn_cast <ConstantInt>(N->getOperand(3))); bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4))); you can trivially match its semantics with: MDNode *N = foo(); bar(mdconst::hasa <ConstantInt>(N->getOperand(0))); baz(mdconst::extract <ConstantInt>(N->getOperand(1))); bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2))); bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3))); bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4))); and when you transition your metadata schema to `MDInt`: MDNode *N = foo(); bar(isa <MDInt>(N->getOperand(0))); baz(cast <MDInt>(N->getOperand(1))); bak(cast_or_null <MDInt>(N->getOperand(2))); bat(dyn_cast <MDInt>(N->getOperand(3))); bay(dyn_cast_or_null<MDInt>(N->getOperand(4))); - A `CallInst` -- specifically, intrinsic instructions -- can refer to metadata through a bridge called `MetadataAsValue`. This is a subclass of `Value` where `getType()->isMetadataTy()`. `MetadataAsValue` is the *only* class that can legally refer to a `LocalAsMetadata`, which is a bridged form of non-`Constant` values like `Argument` and `Instruction`. It can also refer to any other `Metadata` subclass. (I'll break all your testcases in a follow-up commit, when I propagate this change to assembly.) llvm-svn: 223802
2014-12-10 02:38:53 +08:00
SmallVector<Metadata *, 64> LiveGlobalVariables;
DenseSet<const MDNode *> VisitedSet;
std::set<DIGlobalVariable *> LiveGVs;
for (GlobalVariable &GV : M.globals()) {
SmallVector<DIGlobalVariable *, 1> DIs;
GV.getDebugInfo(DIs);
for (DIGlobalVariable *DI : DIs)
LiveGVs.insert(DI);
}
for (DICompileUnit *DIC : F.compile_units()) {
// Create our live global variable list.
bool GlobalVariableChange = false;
for (DIGlobalVariable *DIG : DIC->getGlobalVariables()) {
// Make sure we only visit each global variable only once.
if (!VisitedSet.insert(DIG).second)
continue;
// If a global variable references DIG, the global variable is live.
if (LiveGVs.count(DIG))
LiveGlobalVariables.push_back(DIG);
else
GlobalVariableChange = true;
}
// If we found dead global variables, replace the current global
// variable list with our new live global variable list.
if (GlobalVariableChange) {
DIC->replaceGlobalVariables(MDTuple::get(C, LiveGlobalVariables));
Changed = true;
}
// Reset lists for the next iteration.
LiveGlobalVariables.clear();
}
return Changed;
}