Add support for -fno-builtin to LTO and ThinLTO to libLTO

Reviewers: tejohnson, pcc

Subscribers: Prazek, dexonsmith, llvm-commits

Differential Revision: https://reviews.llvm.org/D30791

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298936 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/LTO/legacy/LTOCodeGenerator.h

@@ -175,6 +175,10 @@ struct LTOCodeGenerator {
   /// Calls \a verifyMergedModuleOnce().
   bool compileOptimized(ArrayRef<raw_pwrite_stream *> Out);
 
+  /// Enable the Freestanding mode: indicate that the optimizer should not
+  /// assume builtins are present on the target.
+  void setFreestanding(bool Enabled) { Freestanding = Enabled; }
+
   void setDiagnosticHandler(lto_diagnostic_handler_t, void *);
 
   LLVMContext &getContext() { return Context; }
@@ -237,6 +241,7 @@ struct LTOCodeGenerator {
   bool ShouldRestoreGlobalsLinkage = false;
   TargetMachine::CodeGenFileType FileType = TargetMachine::CGFT_ObjectFile;
   std::unique_ptr<tool_output_file> DiagnosticOutputFile;
+  bool Freestanding = false;
 };
 }
 #endif

include/llvm/LTO/legacy/ThinLTOCodeGenerator.h

@@ -205,6 +205,10 @@ class ThinLTOCodeGenerator {
     TMBuilder.Options = std::move(Options);
   }
 
+  /// Enable the Freestanding mode: indicate that the optimizer should not
+  /// assume builtins are present on the target.
+  void setFreestanding(bool Enabled) { Freestanding = Enabled; }
+
   /// CodeModel
   void setCodePICModel(Optional<Reloc::Model> Model) {
     TMBuilder.RelocModel = Model;
@@ -322,6 +326,10 @@ class ThinLTOCodeGenerator {
   /// importing or optimization.
   bool CodeGenOnly = false;
 
+  /// Flag to indicate that the optimizer should not assume builtins are present
+  /// on the target.
+  bool Freestanding = false;
+
   /// IR Optimization Level [0-3].
   unsigned OptLevel = 3;
 };

lib/LTO/LTOCodeGenerator.cpp

@@ -555,6 +555,8 @@ bool LTOCodeGenerator::optimize(bool DisableVerify, bool DisableInline,
   if (!DisableInline)
     PMB.Inliner = createFunctionInliningPass();
   PMB.LibraryInfo = new TargetLibraryInfoImpl(TargetTriple);
+  if (Freestanding)
+    PMB.LibraryInfo->disableAllFunctions();
   PMB.OptLevel = OptLevel;
   PMB.VerifyInput = !DisableVerify;
   PMB.VerifyOutput = !DisableVerify;

lib/LTO/ThinLTOCodeGenerator.cpp

@@ -187,10 +187,12 @@ crossImportIntoModule(Module &TheModule, const ModuleSummaryIndex &Index,
 }
 
 static void optimizeModule(Module &TheModule, TargetMachine &TM,
-                           unsigned OptLevel) {
+                           unsigned OptLevel, bool Freestanding) {
   // Populate the PassManager
   PassManagerBuilder PMB;
   PMB.LibraryInfo = new TargetLibraryInfoImpl(TM.getTargetTriple());
+  if (Freestanding)
+    PMB.LibraryInfo->disableAllFunctions();
   PMB.Inliner = createFunctionInliningPass();
   // FIXME: should get it from the bitcode?
   PMB.OptLevel = OptLevel;
@@ -264,7 +266,7 @@ class ModuleCacheEntry {
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       const GVSummaryMapTy &DefinedFunctions,
       const DenseSet<GlobalValue::GUID> &PreservedSymbols, unsigned OptLevel,
-      const TargetMachineBuilder &TMBuilder) {
+      bool Freestanding, const TargetMachineBuilder &TMBuilder) {
     if (CachePath.empty())
       return;
 
@@ -321,6 +323,7 @@ class ModuleCacheEntry {
       AddUnsigned(*TMBuilder.RelocModel);
     AddUnsigned(TMBuilder.CGOptLevel);
     AddUnsigned(OptLevel);
+    AddUnsigned(Freestanding);
 
     Hasher.update(ArrayRef<uint8_t>((uint8_t *)&ModHash[0], sizeof(ModHash)));
     for (auto F : ExportList)
@@ -404,7 +407,7 @@ ProcessThinLTOModule(Module &TheModule, ModuleSummaryIndex &Index,
                      const GVSummaryMapTy &DefinedGlobals,
                      const ThinLTOCodeGenerator::CachingOptions &CacheOptions,
                      bool DisableCodeGen, StringRef SaveTempsDir,
-                     unsigned OptLevel, unsigned count) {
+                     bool Freestanding, unsigned OptLevel, unsigned count) {
 
   // "Benchmark"-like optimization: single-source case
   bool SingleModule = (ModuleMap.size() == 1);
@@ -436,7 +439,7 @@ ProcessThinLTOModule(Module &TheModule, ModuleSummaryIndex &Index,
     saveTempBitcode(TheModule, SaveTempsDir, count, ".3.imported.bc");
   }
 
-  optimizeModule(TheModule, TM, OptLevel);
+  optimizeModule(TheModule, TM, OptLevel, Freestanding);
 
   saveTempBitcode(TheModule, SaveTempsDir, count, ".4.opt.bc");
 
@@ -762,7 +765,7 @@ void ThinLTOCodeGenerator::optimize(Module &TheModule) {
   initTMBuilder(TMBuilder, Triple(TheModule.getTargetTriple()));
 
   // Optimize now
-  optimizeModule(TheModule, *TMBuilder.create(), OptLevel);
+  optimizeModule(TheModule, *TMBuilder.create(), OptLevel, Freestanding);
 }
 
 /**
@@ -948,7 +951,7 @@ void ThinLTOCodeGenerator::run() {
                                     ImportLists[ModuleIdentifier], ExportList,
                                     ResolvedODR[ModuleIdentifier],
                                     DefinedFunctions, GUIDPreservedSymbols,
-                                    OptLevel, TMBuilder);
+                                    OptLevel, Freestanding, TMBuilder);
         auto CacheEntryPath = CacheEntry.getEntryPath();
 
         {
@@ -994,7 +997,7 @@ void ThinLTOCodeGenerator::run() {
             *TheModule, *Index, ModuleMap, *TMBuilder.create(), ImportList,
             ExportList, GUIDPreservedSymbols,
             ModuleToDefinedGVSummaries[ModuleIdentifier], CacheOptions,
-            DisableCodeGen, SaveTempsDir, OptLevel, count);
+            DisableCodeGen, SaveTempsDir, Freestanding, OptLevel, count);
 
         // Commit to the cache (if enabled)
         CacheEntry.write(*OutputBuffer);

test/ThinLTO/X86/tli-nobuiltin.ll

@@ -0,0 +1,46 @@
+; Test -lto-freestanding option for libLTO.
+; RUN: llvm-as < %s > %t.bc
+
+; Regular run: expects fprintf to be turned into fwrite
+; RUN: llvm-lto %t.bc -exported-symbol=_foo -o %t.o
+; RUN: llvm-nm %t.o | FileCheck %s --check-prefix=LTO
+; LTO: fwrite
+
+; Freestanding run: expects fprintf to NOT be turned into fwrite
+; RUN: llvm-lto %t.bc -lto-freestanding -exported-symbol=_foo -o %t.o
+; RUN: llvm-nm %t.o | FileCheck %s --check-prefix=LTO-FREESTANDING
+; LTO-FREESTANDING: fprintf
+
+; Same with ThinLTO now.
+; RUN: opt -module-hash -module-summary %s -o %t.bc
+
+; Regular run: expects fprintf to be turned into fwrite
+; RUN: llvm-lto -exported-symbol=_foo -thinlto-action=run %t.bc
+; RUN: llvm-nm %t.bc.thinlto.o | FileCheck %s --check-prefix=ThinLTO
+; ThinLTO: fwrite
+
+; Freestanding run: expects fprintf to NOT be turned into fwrite
+; RUN: llvm-lto -lto-freestanding -exported-symbol=_foo -thinlto-action=run %t.bc
+; RUN: llvm-nm %t.bc.thinlto.o | FileCheck %s --check-prefix=ThinLTO-FREESTANDING
+; ThinLTO-FREESTANDING: fprintf
+
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.11.0"
+
+declare i32 @fprintf(%FILE*, i8*, ...)
+
+%FILE = type { }
+
+@hello_world = constant [13 x i8] c"hello world\0A\00"
+@percent_s = constant [3 x i8] c"%s\00"
+
+; Check fprintf(fp, "%s", str) -> fwrite(str, fp) only when builtins are enabled
+
+define void @foo(%FILE* %fp) {
+  %fmt = getelementptr [3 x i8], [3 x i8]* @percent_s, i32 0, i32 0
+  %str = getelementptr [13 x i8], [13 x i8]* @hello_world, i32 0, i32 0
+  call i32 (%FILE*, i8*, ...) @fprintf(%FILE* %fp, i8* %fmt, i8* %str)
+  ret void
+}
+

tools/llvm-lto/llvm-lto.cpp

@@ -63,6 +63,10 @@ static cl::opt<bool> DisableLTOVectorization(
     "disable-lto-vectorization", cl::init(false),
     cl::desc("Do not run loop or slp vectorization during LTO"));
 
+static cl::opt<bool> EnableFreestanding(
+    "lto-freestanding", cl::init(false),
+    cl::desc("Enable Freestanding (disable builtins / TLI) during LTO"));
+
 static cl::opt<bool> UseDiagnosticHandler(
     "use-diagnostic-handler", cl::init(false),
     cl::desc("Use a diagnostic handler to test the handler interface"));
@@ -433,6 +437,7 @@ class ThinLTOProcessing {
     ThinGenerator.setCodePICModel(getRelocModel());
     ThinGenerator.setTargetOptions(Options);
     ThinGenerator.setCacheDir(ThinLTOCacheDir);
+    ThinGenerator.setFreestanding(EnableFreestanding);
 
     // Add all the exported symbols to the table of symbols to preserve.
     for (unsigned i = 0; i < ExportedSymbols.size(); ++i)
@@ -809,6 +814,7 @@ int main(int argc, char **argv) {
     CodeGen.setDiagnosticHandler(handleDiagnostics, nullptr);
 
   CodeGen.setCodePICModel(getRelocModel());
+  CodeGen.setFreestanding(EnableFreestanding);
 
   CodeGen.setDebugInfo(LTO_DEBUG_MODEL_DWARF);
   CodeGen.setTargetOptions(Options);

tools/lto/lto.cpp

@@ -44,9 +44,13 @@ static cl::opt<bool>
 DisableGVNLoadPRE("disable-gvn-loadpre", cl::init(false),
   cl::desc("Do not run the GVN load PRE pass"));
 
-static cl::opt<bool>
-DisableLTOVectorization("disable-lto-vectorization", cl::init(false),
-  cl::desc("Do not run loop or slp vectorization during LTO"));
+static cl::opt<bool> DisableLTOVectorization(
+    "disable-lto-vectorization", cl::init(false),
+    cl::desc("Do not run loop or slp vectorization during LTO"));
+
+static cl::opt<bool> EnableFreestanding(
+    "lto-freestanding", cl::init(false),
+    cl::desc("Enable Freestanding (disable builtins / TLI) during LTO"));
 
 #ifdef NDEBUG
 static bool VerifyByDefault = false;
@@ -159,6 +163,7 @@ static void lto_add_attrs(lto_code_gen_t cg) {
   if (OptLevel < '0' || OptLevel > '3')
     report_fatal_error("Optimization level must be between 0 and 3");
   CG->setOptLevel(OptLevel - '0');
+  CG->setFreestanding(EnableFreestanding);
 }
 
 extern const char* lto_get_version() {
@@ -464,6 +469,7 @@ thinlto_code_gen_t thinlto_create_codegen(void) {
   lto_initialize();
   ThinLTOCodeGenerator *CodeGen = new ThinLTOCodeGenerator();
   CodeGen->setTargetOptions(InitTargetOptionsFromCodeGenFlags());
+  CodeGen->setFreestanding(EnableFreestanding);
 
   if (OptLevel.getNumOccurrences()) {
     if (OptLevel < '0' || OptLevel > '3')