/// GetAllUndefinedSymbols - calculates the set of undefined symbols that still
/// exist in an LLVM module. This is a bit tricky because there may be two
/// symbols with the same name but different LLVM types that will be resolved to
/// each other but aren't currently (thus we need to treat it as resolved).
///
/// Inputs:
/// M - The module in which to find undefined symbols.
///
/// Outputs:
/// UndefinedSymbols - A set of C++ strings containing the name of all
/// undefined symbols.
///
static void
GetAllUndefinedSymbols(Module *M, std::set<std::string> &UndefinedSymbols) {
std::set<std::string> DefinedSymbols;
UndefinedSymbols.clear();
// If the program doesn't define a main, try pulling one in from a .a file.
// This is needed for programs where the main function is defined in an
// archive, such f2c'd programs.
Function *Main = M->getFunction("main");
if (Main == 0 || Main->isDeclaration())
UndefinedSymbols.insert("main");
for (Module::iterator I = M->begin(), E = M->end(); I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
assert(!I->hasDLLImportLinkage()
&& "Found dllimported non-external symbol!");
DefinedSymbols.insert(I->getName());
}
}
for (Module::global_iterator I = M->global_begin(), E = M->global_end();
I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
assert(!I->hasDLLImportLinkage()
&& "Found dllimported non-external symbol!");
DefinedSymbols.insert(I->getName());
}
}
for (Module::alias_iterator I = M->alias_begin(), E = M->alias_end();
I != E; ++I)
if (I->hasName())
DefinedSymbols.insert(I->getName());
// Prune out any defined symbols from the undefined symbols set...
for (std::set<std::string>::iterator I = UndefinedSymbols.begin();
I != UndefinedSymbols.end(); )
if (DefinedSymbols.count(*I))
UndefinedSymbols.erase(I++); // This symbol really is defined!
else
++I; // Keep this symbol in the undefined symbols list
}
void
AndroidBitcodeLinker::GetAllSymbols(Module *M,
std::set<std::string> &UndefinedSymbols,
std::set<std::string> &DefinedSymbols) {
UndefinedSymbols.clear();
DefinedSymbols.clear();
Function *Main = M->getFunction("main");
if (Main == 0 || Main->isDeclaration())
UndefinedSymbols.insert("main");
for (Module::iterator I = M->begin(), E = M->end(); I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
assert(!I->hasDLLImportStorageClass()
&& "Found dllimported non-external symbol!");
DefinedSymbols.insert(I->getName());
}
}
for (Module::global_iterator I = M->global_begin(), E = M->global_end();
I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
assert(!I->hasDLLImportStorageClass()
&& "Found dllimported non-external symbol!");
DefinedSymbols.insert(I->getName());
}
}
for (Module::alias_iterator I = M->alias_begin(), E = M->alias_end();
I != E; ++I)
if (I->hasName())
DefinedSymbols.insert(I->getName());
for (std::set<std::string>::iterator I = UndefinedSymbols.begin();
I != UndefinedSymbols.end(); )
if (DefinedSymbols.count(*I))
UndefinedSymbols.erase(I++);
else
++I;
}
static void getSymbols(Module*M, std::vector<std::string>& symbols) {
// Loop over global variables
for (Module::global_iterator GI = M->global_begin(), GE=M->global_end(); GI != GE; ++GI)
if (!GI->isDeclaration() && !GI->hasLocalLinkage())
if (!GI->getName().empty())
symbols.push_back(GI->getName());
// Loop over functions
for (Module::iterator FI = M->begin(), FE = M->end(); FI != FE; ++FI)
if (!FI->isDeclaration() && !FI->hasLocalLinkage())
if (!FI->getName().empty())
symbols.push_back(FI->getName());
// Loop over aliases
for (Module::alias_iterator AI = M->alias_begin(), AE = M->alias_end();
AI != AE; ++AI) {
if (AI->hasName())
symbols.push_back(AI->getName());
}
}
bool InternalizePass::runOnModule(Module &M) {
CallGraph *CG = getAnalysisIfAvailable<CallGraph>();
CallGraphNode *ExternalNode = CG ? CG->getExternalCallingNode() : 0;
if (ExternalNames.empty()) {
// Return if we're not in 'all but main' mode and have no external api
if (!AllButMain)
return false;
// If no list or file of symbols was specified, check to see if there is a
// "main" symbol defined in the module. If so, use it, otherwise do not
// internalize the module, it must be a library or something.
//
Function *MainFunc = M.getFunction("main");
if (MainFunc == 0 || MainFunc->isDeclaration())
return false; // No main found, must be a library...
// Preserve main, internalize all else.
ExternalNames.insert(MainFunc->getName());
}
bool Changed = false;
// Never internalize functions which code-gen might insert.
ExternalNames.insert("__stack_chk_fail");
// Mark all functions not in the api as internal.
// FIXME: maybe use private linkage?
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
if (!I->isDeclaration() && // Function must be defined here
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!I->hasLocalLinkage() && // Can't already have internal linkage
!ExternalNames.count(I->getName())) {// Not marked to keep external?
I->setLinkage(GlobalValue::InternalLinkage);
// Remove a callgraph edge from the external node to this function.
if (ExternalNode) ExternalNode->removeOneAbstractEdgeTo((*CG)[I]);
Changed = true;
++NumFunctions;
DEBUG(dbgs() << "Internalizing func " << I->getName() << "\n");
}
// Never internalize the llvm.used symbol. It is used to implement
// attribute((used)).
// FIXME: Shouldn't this just filter on llvm.metadata section??
ExternalNames.insert("llvm.used");
ExternalNames.insert("llvm.compiler.used");
// Never internalize anchors used by the machine module info, else the info
// won't find them. (see MachineModuleInfo.)
ExternalNames.insert("llvm.global_ctors");
ExternalNames.insert("llvm.global_dtors");
ExternalNames.insert("llvm.global.annotations");
// Never internalize symbols code-gen inserts.
ExternalNames.insert("__stack_chk_guard");
// Mark all global variables with initializers that are not in the api as
// internal as well.
// FIXME: maybe use private linkage?
for (Module::global_iterator I = M.global_begin(), E = M.global_end();
I != E; ++I)
if (!I->isDeclaration() && !I->hasLocalLinkage() &&
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!ExternalNames.count(I->getName())) {
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumGlobals;
DEBUG(dbgs() << "Internalized gvar " << I->getName() << "\n");
}
// Mark all aliases that are not in the api as internal as well.
for (Module::alias_iterator I = M.alias_begin(), E = M.alias_end();
I != E; ++I)
if (!I->isDeclaration() && !I->hasInternalLinkage() &&
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!ExternalNames.count(I->getName())) {
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumAliases;
DEBUG(dbgs() << "Internalized alias " << I->getName() << "\n");
}
return Changed;
}
bool PNaClABIVerifyModule::runOnModule(Module &M) {
if (!M.getModuleInlineAsm().empty()) {
Reporter->addError() <<
"Module contains disallowed top-level inline assembly\n";
}
for (Module::const_global_iterator MI = M.global_begin(), ME = M.global_end();
MI != ME; ++MI) {
checkGlobalIsFlattened(MI);
checkGlobalValueCommon(MI);
if (MI->isThreadLocal()) {
Reporter->addError() << "Variable " << MI->getName() <<
" has disallowed \"thread_local\" attribute\n";
}
}
// No aliases allowed for now.
for (Module::alias_iterator MI = M.alias_begin(),
E = M.alias_end(); MI != E; ++MI) {
Reporter->addError() << "Variable " << MI->getName() <<
" is an alias (disallowed)\n";
}
for (Module::const_iterator MI = M.begin(), ME = M.end(); MI != ME; ++MI) {
if (MI->isIntrinsic()) {
// Check intrinsics.
if (!isWhitelistedIntrinsic(MI, MI->getIntrinsicID())) {
Reporter->addError() << "Function " << MI->getName()
<< " is a disallowed LLVM intrinsic\n";
}
} else {
// Check types of functions and their arguments. Not necessary
// for intrinsics, whose types are fixed anyway, and which have
// argument types that we disallow such as i8.
if (!PNaClABITypeChecker::isValidFunctionType(MI->getFunctionType())) {
Reporter->addError() << "Function " << MI->getName()
<< " has disallowed type: "
<< PNaClABITypeChecker::getTypeName(MI->getFunctionType())
<< "\n";
}
// This check is disabled in streaming mode because it would
// reject a function that is defined but not read in yet.
// Unfortunately this means we simply don't check this property
// when translating a pexe in the browser.
// TODO(mseaborn): Enforce this property in the bitcode reader.
if (!StreamingMode && MI->isDeclaration()) {
Reporter->addError() << "Function " << MI->getName()
<< " is declared but not defined (disallowed)\n";
}
if (!MI->getAttributes().isEmpty()) {
Reporter->addError()
<< "Function " << MI->getName() << " has disallowed attributes:"
<< getAttributesAsString(MI->getAttributes()) << "\n";
}
if (MI->getCallingConv() != CallingConv::C) {
Reporter->addError()
<< "Function " << MI->getName()
<< " has disallowed calling convention: "
<< MI->getCallingConv() << "\n";
}
}
checkGlobalValueCommon(MI);
if (MI->hasGC()) {
Reporter->addError() << "Function " << MI->getName() <<
" has disallowed \"gc\" attribute\n";
}
// Knowledge of what function alignments are useful is
// architecture-specific and sandbox-specific, so PNaCl pexes
// should not be able to specify function alignment.
if (MI->getAlignment() != 0) {
Reporter->addError() << "Function " << MI->getName() <<
" has disallowed \"align\" attribute\n";
}
}
// Check named metadata nodes
for (Module::const_named_metadata_iterator I = M.named_metadata_begin(),
E = M.named_metadata_end(); I != E; ++I) {
if (!isWhitelistedMetadata(I)) {
Reporter->addError() << "Named metadata node " << I->getName()
<< " is disallowed\n";
}
}
Reporter->checkForFatalErrors();
return false;
}
bool InternalizePass::runOnModule(Module &M) {
CallGraph *CG = getAnalysisIfAvailable<CallGraph>();
CallGraphNode *ExternalNode = CG ? CG->getExternalCallingNode() : 0;
bool Changed = false;
// Never internalize functions which code-gen might insert.
// FIXME: We should probably add this (and the __stack_chk_guard) via some
// type of call-back in CodeGen.
ExternalNames.insert("__stack_chk_fail");
// Mark all functions not in the api as internal.
// FIXME: maybe use private linkage?
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I)
if (!I->isDeclaration() && // Function must be defined here
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!I->hasLocalLinkage() && // Can't already have internal linkage
!ExternalNames.count(I->getName())) {// Not marked to keep external?
I->setLinkage(GlobalValue::InternalLinkage);
// Remove a callgraph edge from the external node to this function.
if (ExternalNode) ExternalNode->removeOneAbstractEdgeTo((*CG)[I]);
Changed = true;
++NumFunctions;
DEBUG(dbgs() << "Internalizing func " << I->getName() << "\n");
}
// Never internalize the llvm.used symbol. It is used to implement
// attribute((used)).
// FIXME: Shouldn't this just filter on llvm.metadata section??
ExternalNames.insert("llvm.used");
ExternalNames.insert("llvm.compiler.used");
// Never internalize anchors used by the machine module info, else the info
// won't find them. (see MachineModuleInfo.)
ExternalNames.insert("llvm.global_ctors");
ExternalNames.insert("llvm.global_dtors");
ExternalNames.insert("llvm.global.annotations");
// Never internalize symbols code-gen inserts.
ExternalNames.insert("__stack_chk_guard");
// Mark all global variables with initializers that are not in the api as
// internal as well.
// FIXME: maybe use private linkage?
for (Module::global_iterator I = M.global_begin(), E = M.global_end();
I != E; ++I)
if (!I->isDeclaration() && !I->hasLocalLinkage() &&
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!ExternalNames.count(I->getName())) {
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumGlobals;
DEBUG(dbgs() << "Internalized gvar " << I->getName() << "\n");
}
// Mark all aliases that are not in the api as internal as well.
for (Module::alias_iterator I = M.alias_begin(), E = M.alias_end();
I != E; ++I)
if (!I->isDeclaration() && !I->hasInternalLinkage() &&
// Available externally is really just a "declaration with a body".
!I->hasAvailableExternallyLinkage() &&
!ExternalNames.count(I->getName())) {
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumAliases;
DEBUG(dbgs() << "Internalized alias " << I->getName() << "\n");
}
return Changed;
}
int main(int argc, char **argv) {
// Print a stack trace if we signal out.
sys::PrintStackTraceOnErrorSignal(argv[0]);
PrettyStackTraceProgram X(argc, argv);
LLVMContext Context;
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
cl::ParseCommandLineOptions(argc, argv, "llvm extractor\n");
// Use lazy loading, since we only care about selected global values.
SMDiagnostic Err;
std::unique_ptr<Module> M = getLazyIRFileModule(InputFilename, Err, Context);
if (!M.get()) {
Err.print(argv[0], errs());
return 1;
}
// Use SetVector to avoid duplicates.
SetVector<GlobalValue *> GVs;
// Figure out which aliases we should extract.
for (size_t i = 0, e = ExtractAliases.size(); i != e; ++i) {
GlobalAlias *GA = M->getNamedAlias(ExtractAliases[i]);
if (!GA) {
errs() << argv[0] << ": program doesn't contain alias named '"
<< ExtractAliases[i] << "'!\n";
return 1;
}
GVs.insert(GA);
}
// Extract aliases via regular expression matching.
for (size_t i = 0, e = ExtractRegExpAliases.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpAliases[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpAliases[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::alias_iterator GA = M->alias_begin(), E = M->alias_end();
GA != E; GA++) {
if (RegEx.match(GA->getName())) {
GVs.insert(&*GA);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpAliases[i] << "'!\n";
return 1;
}
}
// Figure out which globals we should extract.
for (size_t i = 0, e = ExtractGlobals.size(); i != e; ++i) {
GlobalValue *GV = M->getNamedGlobal(ExtractGlobals[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractGlobals[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract globals via regular expression matching.
for (size_t i = 0, e = ExtractRegExpGlobals.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpGlobals[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpGlobals[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (auto &GV : M->globals()) {
if (RegEx.match(GV.getName())) {
GVs.insert(&GV);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpGlobals[i] << "'!\n";
return 1;
}
}
// Figure out which functions we should extract.
for (size_t i = 0, e = ExtractFuncs.size(); i != e; ++i) {
GlobalValue *GV = M->getFunction(ExtractFuncs[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain function named '"
<< ExtractFuncs[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract functions via regular expression matching.
for (size_t i = 0, e = ExtractRegExpFuncs.size(); i != e; ++i) {
std::string Error;
StringRef RegExStr = ExtractRegExpFuncs[i];
Regex RegEx(RegExStr);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpFuncs[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::iterator F = M->begin(), E = M->end(); F != E;
F++) {
if (RegEx.match(F->getName())) {
GVs.insert(&*F);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpFuncs[i] << "'!\n";
return 1;
}
}
auto Materialize = [&](GlobalValue &GV) {
if (std::error_code EC = GV.materialize()) {
errs() << argv[0] << ": error reading input: " << EC.message() << "\n";
exit(1);
}
};
// Materialize requisite global values.
if (!DeleteFn) {
for (size_t i = 0, e = GVs.size(); i != e; ++i)
Materialize(*GVs[i]);
} else {
// Deleting. Materialize every GV that's *not* in GVs.
SmallPtrSet<GlobalValue *, 8> GVSet(GVs.begin(), GVs.end());
for (auto &F : *M) {
if (!GVSet.count(&F))
Materialize(F);
}
}
{
std::vector<GlobalValue *> Gvs(GVs.begin(), GVs.end());
legacy::PassManager Extract;
Extract.add(createGVExtractionPass(Gvs, DeleteFn));
Extract.run(*M);
// Now that we have all the GVs we want, mark the module as fully
// materialized.
// FIXME: should the GVExtractionPass handle this?
M->materializeAll();
}
// In addition to deleting all other functions, we also want to spiff it
// up a little bit. Do this now.
legacy::PassManager Passes;
if (!DeleteFn)
Passes.add(createGlobalDCEPass()); // Delete unreachable globals
Passes.add(createStripDeadDebugInfoPass()); // Remove dead debug info
Passes.add(createStripDeadPrototypesPass()); // Remove dead func decls
std::error_code EC;
tool_output_file Out(OutputFilename, EC, sys::fs::F_None);
if (EC) {
errs() << EC.message() << '\n';
return 1;
}
if (OutputAssembly)
Passes.add(
createPrintModulePass(Out.os(), "", PreserveAssemblyUseListOrder));
else if (Force || !CheckBitcodeOutputToConsole(Out.os(), true))
Passes.add(createBitcodeWriterPass(Out.os(), PreserveBitcodeUseListOrder));
Passes.run(*M.get());
// Declare success.
Out.keep();
return 0;
}
int main(int argc, char **argv) {
InitLLVM X(argc, argv);
LLVMContext Context;
cl::ParseCommandLineOptions(argc, argv, "llvm extractor\n");
// Use lazy loading, since we only care about selected global values.
SMDiagnostic Err;
std::unique_ptr<Module> M = getLazyIRFileModule(InputFilename, Err, Context);
if (!M.get()) {
Err.print(argv[0], errs());
return 1;
}
// Use SetVector to avoid duplicates.
SetVector<GlobalValue *> GVs;
// Figure out which aliases we should extract.
for (size_t i = 0, e = ExtractAliases.size(); i != e; ++i) {
GlobalAlias *GA = M->getNamedAlias(ExtractAliases[i]);
if (!GA) {
errs() << argv[0] << ": program doesn't contain alias named '"
<< ExtractAliases[i] << "'!\n";
return 1;
}
GVs.insert(GA);
}
// Extract aliases via regular expression matching.
for (size_t i = 0, e = ExtractRegExpAliases.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpAliases[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpAliases[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::alias_iterator GA = M->alias_begin(), E = M->alias_end();
GA != E; GA++) {
if (RegEx.match(GA->getName())) {
GVs.insert(&*GA);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpAliases[i] << "'!\n";
return 1;
}
}
// Figure out which globals we should extract.
for (size_t i = 0, e = ExtractGlobals.size(); i != e; ++i) {
GlobalValue *GV = M->getNamedGlobal(ExtractGlobals[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractGlobals[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract globals via regular expression matching.
for (size_t i = 0, e = ExtractRegExpGlobals.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpGlobals[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpGlobals[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (auto &GV : M->globals()) {
if (RegEx.match(GV.getName())) {
GVs.insert(&GV);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpGlobals[i] << "'!\n";
return 1;
}
}
// Figure out which functions we should extract.
for (size_t i = 0, e = ExtractFuncs.size(); i != e; ++i) {
GlobalValue *GV = M->getFunction(ExtractFuncs[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain function named '"
<< ExtractFuncs[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract functions via regular expression matching.
for (size_t i = 0, e = ExtractRegExpFuncs.size(); i != e; ++i) {
std::string Error;
StringRef RegExStr = ExtractRegExpFuncs[i];
Regex RegEx(RegExStr);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpFuncs[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::iterator F = M->begin(), E = M->end(); F != E;
F++) {
if (RegEx.match(F->getName())) {
GVs.insert(&*F);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpFuncs[i] << "'!\n";
return 1;
}
}
// Figure out which BasicBlocks we should extract.
SmallVector<BasicBlock *, 4> BBs;
for (StringRef StrPair : ExtractBlocks) {
auto BBInfo = StrPair.split(':');
// Get the function.
Function *F = M->getFunction(BBInfo.first);
if (!F) {
errs() << argv[0] << ": program doesn't contain a function named '"
<< BBInfo.first << "'!\n";
return 1;
}
// Do not materialize this function.
GVs.insert(F);
// Get the basic block.
auto Res = llvm::find_if(*F, [&](const BasicBlock &BB) {
return BB.getName().equals(BBInfo.second);
});
if (Res == F->end()) {
errs() << argv[0] << ": function " << F->getName()
<< " doesn't contain a basic block named '" << BBInfo.second
<< "'!\n";
return 1;
}
BBs.push_back(&*Res);
}
// Use *argv instead of argv[0] to work around a wrong GCC warning.
ExitOnError ExitOnErr(std::string(*argv) + ": error reading input: ");
if (Recursive) {
std::vector<llvm::Function *> Workqueue;
for (GlobalValue *GV : GVs) {
if (auto *F = dyn_cast<Function>(GV)) {
Workqueue.push_back(F);
}
}
while (!Workqueue.empty()) {
Function *F = &*Workqueue.back();
Workqueue.pop_back();
ExitOnErr(F->materialize());
for (auto &BB : *F) {
for (auto &I : BB) {
auto *CI = dyn_cast<CallInst>(&I);
if (!CI)
continue;
Function *CF = CI->getCalledFunction();
if (!CF)
continue;
if (CF->isDeclaration() || GVs.count(CF))
continue;
GVs.insert(CF);
Workqueue.push_back(CF);
}
}
}
}
auto Materialize = [&](GlobalValue &GV) { ExitOnErr(GV.materialize()); };
// Materialize requisite global values.
if (!DeleteFn) {
for (size_t i = 0, e = GVs.size(); i != e; ++i)
Materialize(*GVs[i]);
} else {
// Deleting. Materialize every GV that's *not* in GVs.
SmallPtrSet<GlobalValue *, 8> GVSet(GVs.begin(), GVs.end());
for (auto &F : *M) {
if (!GVSet.count(&F))
Materialize(F);
}
}
{
std::vector<GlobalValue *> Gvs(GVs.begin(), GVs.end());
legacy::PassManager Extract;
Extract.add(createGVExtractionPass(Gvs, DeleteFn));
Extract.run(*M);
// Now that we have all the GVs we want, mark the module as fully
// materialized.
// FIXME: should the GVExtractionPass handle this?
ExitOnErr(M->materializeAll());
}
// Extract the specified basic blocks from the module and erase the existing
// functions.
if (!ExtractBlocks.empty()) {
legacy::PassManager PM;
PM.add(createBlockExtractorPass(BBs, true));
PM.run(*M);
}
// In addition to deleting all other functions, we also want to spiff it
// up a little bit. Do this now.
legacy::PassManager Passes;
if (!DeleteFn)
Passes.add(createGlobalDCEPass()); // Delete unreachable globals
Passes.add(createStripDeadDebugInfoPass()); // Remove dead debug info
Passes.add(createStripDeadPrototypesPass()); // Remove dead func decls
std::error_code EC;
ToolOutputFile Out(OutputFilename, EC, sys::fs::F_None);
if (EC) {
errs() << EC.message() << '\n';
return 1;
}
if (OutputAssembly)
Passes.add(
createPrintModulePass(Out.os(), "", PreserveAssemblyUseListOrder));
else if (Force || !CheckBitcodeOutputToConsole(Out.os(), true))
Passes.add(createBitcodeWriterPass(Out.os(), PreserveBitcodeUseListOrder));
Passes.run(*M.get());
// Declare success.
Out.keep();
return 0;
}
bool InternalizePass::runOnModule(Module &M) {
CallGraphWrapperPass *CGPass = getAnalysisIfAvailable<CallGraphWrapperPass>();
CallGraph *CG = CGPass ? &CGPass->getCallGraph() : 0;
CallGraphNode *ExternalNode = CG ? CG->getExternalCallingNode() : 0;
bool Changed = false;
SmallPtrSet<GlobalValue *, 8> Used;
collectUsedGlobalVariables(M, Used, false);
// We must assume that globals in llvm.used have a reference that not even
// the linker can see, so we don't internalize them.
// For llvm.compiler.used the situation is a bit fuzzy. The assembler and
// linker can drop those symbols. If this pass is running as part of LTO,
// one might think that it could just drop llvm.compiler.used. The problem
// is that even in LTO llvm doesn't see every reference. For example,
// we don't see references from function local inline assembly. To be
// conservative, we internalize symbols in llvm.compiler.used, but we
// keep llvm.compiler.used so that the symbol is not deleted by llvm.
for (SmallPtrSet<GlobalValue *, 8>::iterator I = Used.begin(), E = Used.end();
I != E; ++I) {
GlobalValue *V = *I;
ExternalNames.insert(V->getName());
}
// Mark all functions not in the api as internal.
for (Module::iterator I = M.begin(), E = M.end(); I != E; ++I) {
if (!shouldInternalize(*I, ExternalNames, OnlyHidden))
continue;
I->setLinkage(GlobalValue::InternalLinkage);
if (ExternalNode)
// Remove a callgraph edge from the external node to this function.
ExternalNode->removeOneAbstractEdgeTo((*CG)[I]);
Changed = true;
++NumFunctions;
DEBUG(dbgs() << "Internalizing func " << I->getName() << "\n");
}
// Never internalize the llvm.used symbol. It is used to implement
// attribute((used)).
// FIXME: Shouldn't this just filter on llvm.metadata section??
ExternalNames.insert("llvm.used");
ExternalNames.insert("llvm.compiler.used");
// Never internalize anchors used by the machine module info, else the info
// won't find them. (see MachineModuleInfo.)
ExternalNames.insert("llvm.global_ctors");
ExternalNames.insert("llvm.global_dtors");
ExternalNames.insert("llvm.global.annotations");
// Never internalize symbols code-gen inserts.
// FIXME: We should probably add this (and the __stack_chk_guard) via some
// type of call-back in CodeGen.
ExternalNames.insert("__stack_chk_fail");
ExternalNames.insert("__stack_chk_guard");
// Mark all global variables with initializers that are not in the api as
// internal as well.
for (Module::global_iterator I = M.global_begin(), E = M.global_end();
I != E; ++I) {
if (!shouldInternalize(*I, ExternalNames, OnlyHidden))
continue;
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumGlobals;
DEBUG(dbgs() << "Internalized gvar " << I->getName() << "\n");
}
// Mark all aliases that are not in the api as internal as well.
for (Module::alias_iterator I = M.alias_begin(), E = M.alias_end();
I != E; ++I) {
if (!shouldInternalize(*I, ExternalNames, OnlyHidden))
continue;
I->setLinkage(GlobalValue::InternalLinkage);
Changed = true;
++NumAliases;
DEBUG(dbgs() << "Internalized alias " << I->getName() << "\n");
}
return Changed;
}
/// Based on GetAllUndefinedSymbols() from LLVM3.2
///
/// GetAllUndefinedSymbols - calculates the set of undefined symbols that still
/// exist in an LLVM module. This is a bit tricky because there may be two
/// symbols with the same name but different LLVM types that will be resolved to
/// each other but aren't currently (thus we need to treat it as resolved).
///
/// Inputs:
/// M - The module in which to find undefined symbols.
///
/// Outputs:
/// UndefinedSymbols - A set of C++ strings containing the name of all
/// undefined symbols.
///
static void
GetAllUndefinedSymbols(Module *M, std::set<std::string> &UndefinedSymbols) {
static const std::string llvmIntrinsicPrefix="llvm.";
std::set<std::string> DefinedSymbols;
UndefinedSymbols.clear();
KLEE_DEBUG_WITH_TYPE("klee_linker",
dbgs() << "*** Computing undefined symbols ***\n");
for (Module::iterator I = M->begin(), E = M->end(); I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
#if LLVM_VERSION_CODE < LLVM_VERSION(3, 5)
assert(!I->hasDLLImportLinkage() && "Found dllimported non-external symbol!");
#else
assert(!I->hasDLLImportStorageClass() && "Found dllimported non-external symbol!");
#endif
DefinedSymbols.insert(I->getName());
}
}
for (Module::global_iterator I = M->global_begin(), E = M->global_end();
I != E; ++I)
if (I->hasName()) {
if (I->isDeclaration())
UndefinedSymbols.insert(I->getName());
else if (!I->hasLocalLinkage()) {
#if LLVM_VERSION_CODE < LLVM_VERSION(3, 5)
assert(!I->hasDLLImportLinkage() && "Found dllimported non-external symbol!");
#else
assert(!I->hasDLLImportStorageClass() && "Found dllimported non-external symbol!");
#endif
DefinedSymbols.insert(I->getName());
}
}
for (Module::alias_iterator I = M->alias_begin(), E = M->alias_end();
I != E; ++I)
if (I->hasName())
DefinedSymbols.insert(I->getName());
// Prune out any defined symbols from the undefined symbols set
// and other symbols we don't want to treat as an undefined symbol
std::vector<std::string> SymbolsToRemove;
for (std::set<std::string>::iterator I = UndefinedSymbols.begin();
I != UndefinedSymbols.end(); ++I )
{
if (DefinedSymbols.count(*I))
{
SymbolsToRemove.push_back(*I);
continue;
}
// Strip out llvm intrinsics
if ( (I->size() >= llvmIntrinsicPrefix.size() ) &&
(I->compare(0, llvmIntrinsicPrefix.size(), llvmIntrinsicPrefix) == 0) )
{
KLEE_DEBUG_WITH_TYPE("klee_linker", dbgs() << "LLVM intrinsic " << *I <<
" has will be removed from undefined symbols"<< "\n");
SymbolsToRemove.push_back(*I);
continue;
}
// Symbol really is undefined
KLEE_DEBUG_WITH_TYPE("klee_linker",
dbgs() << "Symbol " << *I << " is undefined.\n");
}
// Remove KLEE intrinsics from set of undefined symbols
for (SpecialFunctionHandler::const_iterator sf = SpecialFunctionHandler::begin(),
se = SpecialFunctionHandler::end(); sf != se; ++sf)
{
if (UndefinedSymbols.find(sf->name) == UndefinedSymbols.end())
continue;
SymbolsToRemove.push_back(sf->name);
KLEE_DEBUG_WITH_TYPE("klee_linker",
dbgs() << "KLEE intrinsic " << sf->name <<
" has will be removed from undefined symbols"<< "\n");
}
// Now remove the symbols from undefined set.
for (size_t i = 0, j = SymbolsToRemove.size(); i < j; ++i )
UndefinedSymbols.erase(SymbolsToRemove[i]);
KLEE_DEBUG_WITH_TYPE("klee_linker",
dbgs() << "*** Finished computing undefined symbols ***\n");
}
int main(int argc, char **argv) {
// Print a stack trace if we signal out.
sys::PrintStackTraceOnErrorSignal();
PrettyStackTraceProgram X(argc, argv);
LLVMContext &Context = getGlobalContext();
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
cl::ParseCommandLineOptions(argc, argv, "llvm extractor\n");
// Use lazy loading, since we only care about selected global values.
SMDiagnostic Err;
std::unique_ptr<Module> M;
M.reset(getLazyIRFileModule(InputFilename, Err, Context));
if (!M.get()) {
Err.print(argv[0], errs());
return 1;
}
// Use SetVector to avoid duplicates.
SetVector<GlobalValue *> GVs;
// Figure out which aliases we should extract.
for (size_t i = 0, e = ExtractAliases.size(); i != e; ++i) {
GlobalAlias *GA = M->getNamedAlias(ExtractAliases[i]);
if (!GA) {
errs() << argv[0] << ": program doesn't contain alias named '"
<< ExtractAliases[i] << "'!\n";
return 1;
}
GVs.insert(GA);
}
// Extract aliases via regular expression matching.
for (size_t i = 0, e = ExtractRegExpAliases.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpAliases[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpAliases[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::alias_iterator GA = M->alias_begin(), E = M->alias_end();
GA != E; GA++) {
if (RegEx.match(GA->getName())) {
GVs.insert(&*GA);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpAliases[i] << "'!\n";
return 1;
}
}
// Figure out which globals we should extract.
for (size_t i = 0, e = ExtractGlobals.size(); i != e; ++i) {
GlobalValue *GV = M->getNamedGlobal(ExtractGlobals[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractGlobals[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract globals via regular expression matching.
for (size_t i = 0, e = ExtractRegExpGlobals.size(); i != e; ++i) {
std::string Error;
Regex RegEx(ExtractRegExpGlobals[i]);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpGlobals[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::global_iterator GV = M->global_begin(),
E = M->global_end(); GV != E; GV++) {
if (RegEx.match(GV->getName())) {
GVs.insert(&*GV);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpGlobals[i] << "'!\n";
return 1;
}
}
// Figure out which functions we should extract.
for (size_t i = 0, e = ExtractFuncs.size(); i != e; ++i) {
GlobalValue *GV = M->getFunction(ExtractFuncs[i]);
if (!GV) {
errs() << argv[0] << ": program doesn't contain function named '"
<< ExtractFuncs[i] << "'!\n";
return 1;
}
GVs.insert(GV);
}
// Extract functions via regular expression matching.
for (size_t i = 0, e = ExtractRegExpFuncs.size(); i != e; ++i) {
std::string Error;
StringRef RegExStr = ExtractRegExpFuncs[i];
Regex RegEx(RegExStr);
if (!RegEx.isValid(Error)) {
errs() << argv[0] << ": '" << ExtractRegExpFuncs[i] << "' "
"invalid regex: " << Error;
}
bool match = false;
for (Module::iterator F = M->begin(), E = M->end(); F != E;
F++) {
if (RegEx.match(F->getName())) {
GVs.insert(&*F);
match = true;
}
}
if (!match) {
errs() << argv[0] << ": program doesn't contain global named '"
<< ExtractRegExpFuncs[i] << "'!\n";
return 1;
}
}
// Materialize requisite global values.
if (!DeleteFn)
for (size_t i = 0, e = GVs.size(); i != e; ++i) {
GlobalValue *GV = GVs[i];
if (GV->isMaterializable()) {
std::string ErrInfo;
if (GV->Materialize(&ErrInfo)) {
errs() << argv[0] << ": error reading input: " << ErrInfo << "\n";
return 1;
}
}
}
else {
// Deleting. Materialize every GV that's *not* in GVs.
SmallPtrSet<GlobalValue *, 8> GVSet(GVs.begin(), GVs.end());
for (Module::global_iterator I = M->global_begin(), E = M->global_end();
I != E; ++I) {
GlobalVariable *G = I;
if (!GVSet.count(G) && G->isMaterializable()) {
std::string ErrInfo;
if (G->Materialize(&ErrInfo)) {
errs() << argv[0] << ": error reading input: " << ErrInfo << "\n";
return 1;
}
}
}
for (Module::iterator I = M->begin(), E = M->end(); I != E; ++I) {
Function *F = I;
if (!GVSet.count(F) && F->isMaterializable()) {
std::string ErrInfo;
if (F->Materialize(&ErrInfo)) {
errs() << argv[0] << ": error reading input: " << ErrInfo << "\n";
return 1;
}
}
}
}
// In addition to deleting all other functions, we also want to spiff it
// up a little bit. Do this now.
PassManager Passes;
Passes.add(new DataLayoutPass(M.get())); // Use correct DataLayout
std::vector<GlobalValue*> Gvs(GVs.begin(), GVs.end());
Passes.add(createGVExtractionPass(Gvs, DeleteFn));
if (!DeleteFn)
Passes.add(createGlobalDCEPass()); // Delete unreachable globals
Passes.add(createStripDeadDebugInfoPass()); // Remove dead debug info
Passes.add(createStripDeadPrototypesPass()); // Remove dead func decls
std::string ErrorInfo;
tool_output_file Out(OutputFilename.c_str(), ErrorInfo, sys::fs::F_None);
if (!ErrorInfo.empty()) {
errs() << ErrorInfo << '\n';
return 1;
}
if (OutputAssembly)
Passes.add(createPrintModulePass(Out.os()));
else if (Force || !CheckBitcodeOutputToConsole(Out.os(), true))
Passes.add(createBitcodeWriterPass(Out.os()));
Passes.run(*M.get());
// Declare success.
Out.keep();
return 0;
}