vendor/llvm/llvm-trunk-r300422

1 files changed, 191 insertions, 70 deletions

diff --git a/lib/Transforms/IPO/ThinLTOBitcodeWriter.cpp b/lib/Transforms/IPO/ThinLTOBitcodeWriter.cpp
index 3680cfc813a1..65deb82cd2a5 100644
--- a/lib/Transforms/IPO/ThinLTOBitcodeWriter.cpp
+++ b/lib/Transforms/IPO/ThinLTOBitcodeWriter.cpp
@@ -14,16 +14,21 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/Transforms/IPO.h"
+#include "llvm/Analysis/BasicAliasAnalysis.h"
 #include "llvm/Analysis/ModuleSummaryAnalysis.h"
 #include "llvm/Analysis/TypeMetadataUtils.h"
 #include "llvm/Bitcode/BitcodeWriter.h"
 #include "llvm/IR/Constants.h"
+#include "llvm/IR/DebugInfo.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
+#include "llvm/Support/FileSystem.h"
 #include "llvm/Support/ScopedPrinter.h"
+#include "llvm/Support/raw_ostream.h"
+#include "llvm/Transforms/IPO.h"
+#include "llvm/Transforms/IPO/FunctionAttrs.h"
 #include "llvm/Transforms/Utils/Cloning.h"
 using namespace llvm;
 
@@ -41,23 +46,14 @@ namespace {
 std::string getModuleId(Module *M) {
   MD5 Md5;
   bool ExportsSymbols = false;
-  auto AddGlobal = [&](GlobalValue &GV) {
+  for (auto &GV : M->global_values()) {
     if (GV.isDeclaration() || GV.getName().startswith("llvm.") ||
         !GV.hasExternalLinkage())
-      return;
+      continue;
     ExportsSymbols = true;
     Md5.update(GV.getName());
     Md5.update(ArrayRef<uint8_t>{0});
-  };
-
-  for (auto &F : *M)
-    AddGlobal(F);
-  for (auto &GV : M->globals())
-    AddGlobal(GV);
-  for (auto &GA : M->aliases())
-    AddGlobal(GA);
-  for (auto &IF : M->ifuncs())
-    AddGlobal(IF);
+  }
 
   if (!ExportsSymbols)
     return "";
@@ -73,15 +69,21 @@ std::string getModuleId(Module *M) {
 // Promote each local-linkage entity defined by ExportM and used by ImportM by
 // changing visibility and appending the given ModuleId.
 void promoteInternals(Module &ExportM, Module &ImportM, StringRef ModuleId) {
-  auto PromoteInternal = [&](GlobalValue &ExportGV) {
+  DenseMap<const Comdat *, Comdat *> RenamedComdats;
+  for (auto &ExportGV : ExportM.global_values()) {
     if (!ExportGV.hasLocalLinkage())
-      return;
+      continue;
 
-    GlobalValue *ImportGV = ImportM.getNamedValue(ExportGV.getName());
+    auto Name = ExportGV.getName();
+    GlobalValue *ImportGV = ImportM.getNamedValue(Name);
     if (!ImportGV || ImportGV->use_empty())
-      return;
+      continue;
+
+    std::string NewName = (Name + ModuleId).str();
 
-    std::string NewName = (ExportGV.getName() + ModuleId).str();
+    if (const auto *C = ExportGV.getComdat())
+      if (C->getName() == Name)
+        RenamedComdats.try_emplace(C, ExportM.getOrInsertComdat(NewName));
 
     ExportGV.setName(NewName);
     ExportGV.setLinkage(GlobalValue::ExternalLinkage);
@@ -89,16 +91,15 @@ void promoteInternals(Module &ExportM, Module &ImportM, StringRef ModuleId) {
 
     ImportGV->setName(NewName);
     ImportGV->setVisibility(GlobalValue::HiddenVisibility);
-  };
+  }
 
-  for (auto &F : ExportM)
-    PromoteInternal(F);
-  for (auto &GV : ExportM.globals())
-    PromoteInternal(GV);
-  for (auto &GA : ExportM.aliases())
-    PromoteInternal(GA);
-  for (auto &IF : ExportM.ifuncs())
-    PromoteInternal(IF);
+  if (!RenamedComdats.empty())
+    for (auto &GO : ExportM.global_objects())
+      if (auto *C = GO.getComdat()) {
+        auto Replacement = RenamedComdats.find(C);
+        if (Replacement != RenamedComdats.end())
+          GO.setComdat(Replacement->second);
+      }
 }
 
 // Promote all internal (i.e. distinct) type ids used by the module by replacing
@@ -194,24 +195,7 @@ void simplifyExternals(Module &M) {
 }
 
 void filterModule(
-    Module *M, std::function<bool(const GlobalValue *)> ShouldKeepDefinition) {
-  for (Function &F : *M) {
-    if (ShouldKeepDefinition(&F))
-      continue;
-
-    F.deleteBody();
-    F.clearMetadata();
-  }
-
-  for (GlobalVariable &GV : M->globals()) {
-    if (ShouldKeepDefinition(&GV))
-      continue;
-
-    GV.setInitializer(nullptr);
-    GV.setLinkage(GlobalValue::ExternalLinkage);
-    GV.clearMetadata();
-  }
-
+    Module *M, function_ref<bool(const GlobalValue *)> ShouldKeepDefinition) {
   for (Module::alias_iterator I = M->alias_begin(), E = M->alias_end();
        I != E;) {
     GlobalAlias *GA = &*I++;
@@ -219,7 +203,7 @@ void filterModule(
       continue;
 
     GlobalObject *GO;
-    if (I->getValueType()->isFunctionTy())
+    if (GA->getValueType()->isFunctionTy())
       GO = Function::Create(cast<FunctionType>(GA->getValueType()),
                             GlobalValue::ExternalLinkage, "", M);
     else
@@ -231,53 +215,168 @@ void filterModule(
     GA->replaceAllUsesWith(GO);
     GA->eraseFromParent();
   }
+
+  for (Function &F : *M) {
+    if (ShouldKeepDefinition(&F))
+      continue;
+
+    F.deleteBody();
+    F.setComdat(nullptr);
+    F.clearMetadata();
+  }
+
+  for (GlobalVariable &GV : M->globals()) {
+    if (ShouldKeepDefinition(&GV))
+      continue;
+
+    GV.setInitializer(nullptr);
+    GV.setLinkage(GlobalValue::ExternalLinkage);
+    GV.setComdat(nullptr);
+    GV.clearMetadata();
+  }
+}
+
+void forEachVirtualFunction(Constant *C, function_ref<void(Function *)> Fn) {
+  if (auto *F = dyn_cast<Function>(C))
+    return Fn(F);
+  if (isa<GlobalValue>(C))
+    return;
+  for (Value *Op : C->operands())
+    forEachVirtualFunction(cast<Constant>(Op), Fn);
 }
 
 // If it's possible to split M into regular and thin LTO parts, do so and write
 // a multi-module bitcode file with the two parts to OS. Otherwise, write only a
 // regular LTO bitcode file to OS.
-void splitAndWriteThinLTOBitcode(raw_ostream &OS, Module &M) {
+void splitAndWriteThinLTOBitcode(
+    raw_ostream &OS, raw_ostream *ThinLinkOS,
+    function_ref<AAResults &(Function &)> AARGetter, Module &M) {
   std::string ModuleId = getModuleId(&M);
   if (ModuleId.empty()) {
     // We couldn't generate a module ID for this module, just write it out as a
     // regular LTO module.
     WriteBitcodeToFile(&M, OS);
+    if (ThinLinkOS)
+      // We don't have a ThinLTO part, but still write the module to the
+      // ThinLinkOS if requested so that the expected output file is produced.
+      WriteBitcodeToFile(&M, *ThinLinkOS);
     return;
   }
 
   promoteTypeIds(M, ModuleId);
 
-  auto IsInMergedM = [&](const GlobalValue *GV) {
-    auto *GVar = dyn_cast<GlobalVariable>(GV->getBaseObject());
-    if (!GVar)
-      return false;
-
+  // Returns whether a global has attached type metadata. Such globals may
+  // participate in CFI or whole-program devirtualization, so they need to
+  // appear in the merged module instead of the thin LTO module.
+  auto HasTypeMetadata = [&](const GlobalObject *GO) {
     SmallVector<MDNode *, 1> MDs;
-    GVar->getMetadata(LLVMContext::MD_type, MDs);
+    GO->getMetadata(LLVMContext::MD_type, MDs);
     return !MDs.empty();
   };
 
+  // Collect the set of virtual functions that are eligible for virtual constant
+  // propagation. Each eligible function must not access memory, must return
+  // an integer of width <=64 bits, must take at least one argument, must not
+  // use its first argument (assumed to be "this") and all arguments other than
+  // the first one must be of <=64 bit integer type.
+  //
+  // Note that we test whether this copy of the function is readnone, rather
+  // than testing function attributes, which must hold for any copy of the
+  // function, even a less optimized version substituted at link time. This is
+  // sound because the virtual constant propagation optimizations effectively
+  // inline all implementations of the virtual function into each call site,
+  // rather than using function attributes to perform local optimization.
+  std::set<const Function *> EligibleVirtualFns;
+  // If any member of a comdat lives in MergedM, put all members of that
+  // comdat in MergedM to keep the comdat together.
+  DenseSet<const Comdat *> MergedMComdats;
+  for (GlobalVariable &GV : M.globals())
+    if (HasTypeMetadata(&GV)) {
+      if (const auto *C = GV.getComdat())
+        MergedMComdats.insert(C);
+      forEachVirtualFunction(GV.getInitializer(), [&](Function *F) {
+        auto *RT = dyn_cast<IntegerType>(F->getReturnType());
+        if (!RT || RT->getBitWidth() > 64 || F->arg_empty() ||
+            !F->arg_begin()->use_empty())
+          return;
+        for (auto &Arg : make_range(std::next(F->arg_begin()), F->arg_end())) {
+          auto *ArgT = dyn_cast<IntegerType>(Arg.getType());
+          if (!ArgT || ArgT->getBitWidth() > 64)
+            return;
+        }
+        if (computeFunctionBodyMemoryAccess(*F, AARGetter(*F)) == MAK_ReadNone)
+          EligibleVirtualFns.insert(F);
+      });
+    }
+
   ValueToValueMapTy VMap;
-  std::unique_ptr<Module> MergedM(CloneModule(&M, VMap, IsInMergedM));
+  std::unique_ptr<Module> MergedM(
+      CloneModule(&M, VMap, [&](const GlobalValue *GV) -> bool {
+        if (const auto *C = GV->getComdat())
+          if (MergedMComdats.count(C))
+            return true;
+        if (auto *F = dyn_cast<Function>(GV))
+          return EligibleVirtualFns.count(F);
+        if (auto *GVar = dyn_cast_or_null<GlobalVariable>(GV->getBaseObject()))
+          return HasTypeMetadata(GVar);
+        return false;
+      }));
+  StripDebugInfo(*MergedM);
+
+  for (Function &F : *MergedM)
+    if (!F.isDeclaration()) {
+      // Reset the linkage of all functions eligible for virtual constant
+      // propagation. The canonical definitions live in the thin LTO module so
+      // that they can be imported.
+      F.setLinkage(GlobalValue::AvailableExternallyLinkage);
+      F.setComdat(nullptr);
+    }
 
-  filterModule(&M, [&](const GlobalValue *GV) { return !IsInMergedM(GV); });
+  // Remove all globals with type metadata, globals with comdats that live in
+  // MergedM, and aliases pointing to such globals from the thin LTO module.
+  filterModule(&M, [&](const GlobalValue *GV) {
+    if (auto *GVar = dyn_cast_or_null<GlobalVariable>(GV->getBaseObject()))
+      if (HasTypeMetadata(GVar))
+        return false;
+    if (const auto *C = GV->getComdat())
+      if (MergedMComdats.count(C))
+        return false;
+    return true;
+  });
 
   promoteInternals(*MergedM, M, ModuleId);
   promoteInternals(M, *MergedM, ModuleId);
 
   simplifyExternals(*MergedM);
 
-  SmallVector<char, 0> Buffer;
-  BitcodeWriter W(Buffer);
 
   // FIXME: Try to re-use BSI and PFI from the original module here.
   ModuleSummaryIndex Index = buildModuleSummaryIndex(M, nullptr, nullptr);
-  W.writeModule(&M, /*ShouldPreserveUseListOrder=*/false, &Index,
-                /*GenerateHash=*/true);
 
-  W.writeModule(MergedM.get());
+  SmallVector<char, 0> Buffer;
 
+  BitcodeWriter W(Buffer);
+  // Save the module hash produced for the full bitcode, which will
+  // be used in the backends, and use that in the minimized bitcode
+  // produced for the full link.
+  ModuleHash ModHash = {{0}};
+  W.writeModule(&M, /*ShouldPreserveUseListOrder=*/false, &Index,
+                /*GenerateHash=*/true, &ModHash);
+  W.writeModule(MergedM.get());
   OS << Buffer;
+
+  // If a minimized bitcode module was requested for the thin link,
+  // strip the debug info (the merged module was already stripped above)
+  // and write it to the given OS.
+  if (ThinLinkOS) {
+    Buffer.clear();
+    BitcodeWriter W2(Buffer);
+    StripDebugInfo(M);
+    W2.writeModule(&M, /*ShouldPreserveUseListOrder=*/false, &Index,
+                   /*GenerateHash=*/false, &ModHash);
+    W2.writeModule(MergedM.get());
+    *ThinLinkOS << Buffer;
+  }
 }
 
 // Returns whether this module needs to be split because it uses type metadata.
@@ -292,28 +391,45 @@ bool requiresSplit(Module &M) {
   return false;
 }
 
-void writeThinLTOBitcode(raw_ostream &OS, Module &M,
-                         const ModuleSummaryIndex *Index) {
+void writeThinLTOBitcode(raw_ostream &OS, raw_ostream *ThinLinkOS,
+                         function_ref<AAResults &(Function &)> AARGetter,
+                         Module &M, const ModuleSummaryIndex *Index) {
   // See if this module has any type metadata. If so, we need to split it.
   if (requiresSplit(M))
-    return splitAndWriteThinLTOBitcode(OS, M);
+    return splitAndWriteThinLTOBitcode(OS, ThinLinkOS, AARGetter, M);
 
   // Otherwise we can just write it out as a regular module.
+
+  // Save the module hash produced for the full bitcode, which will
+  // be used in the backends, and use that in the minimized bitcode
+  // produced for the full link.
+  ModuleHash ModHash = {{0}};
   WriteBitcodeToFile(&M, OS, /*ShouldPreserveUseListOrder=*/false, Index,
-                     /*GenerateHash=*/true);
+                     /*GenerateHash=*/true, &ModHash);
+  // If a minimized bitcode module was requested for the thin link,
+  // strip the debug info and write it to the given OS.
+  if (ThinLinkOS) {
+    StripDebugInfo(M);
+    WriteBitcodeToFile(&M, *ThinLinkOS, /*ShouldPreserveUseListOrder=*/false,
+                       Index,
+                       /*GenerateHash=*/false, &ModHash);
+  }
 }
 
 class WriteThinLTOBitcode : public ModulePass {
   raw_ostream &OS; // raw_ostream to print on
+  // The output stream on which to emit a minimized module for use
+  // just in the thin link, if requested.
+  raw_ostream *ThinLinkOS;
 
 public:
   static char ID; // Pass identification, replacement for typeid
-  WriteThinLTOBitcode() : ModulePass(ID), OS(dbgs()) {
+  WriteThinLTOBitcode() : ModulePass(ID), OS(dbgs()), ThinLinkOS(nullptr) {
     initializeWriteThinLTOBitcodePass(*PassRegistry::getPassRegistry());
   }
 
-  explicit WriteThinLTOBitcode(raw_ostream &o)
-      : ModulePass(ID), OS(o) {
+  explicit WriteThinLTOBitcode(raw_ostream &o, raw_ostream *ThinLinkOS)
+      : ModulePass(ID), OS(o), ThinLinkOS(ThinLinkOS) {
     initializeWriteThinLTOBitcodePass(*PassRegistry::getPassRegistry());
   }
 
@@ -322,12 +438,14 @@ public:
   bool runOnModule(Module &M) override {
     const ModuleSummaryIndex *Index =
         &(getAnalysis<ModuleSummaryIndexWrapperPass>().getIndex());
-    writeThinLTOBitcode(OS, M, Index);
+    writeThinLTOBitcode(OS, ThinLinkOS, LegacyAARGetter(*this), M, Index);
     return true;
   }
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.setPreservesAll();
+    AU.addRequired<AssumptionCacheTracker>();
     AU.addRequired<ModuleSummaryIndexWrapperPass>();
+    AU.addRequired<TargetLibraryInfoWrapperPass>();
   }
 };
 } // anonymous namespace
@@ -335,10 +453,13 @@ public:
 char WriteThinLTOBitcode::ID = 0;
 INITIALIZE_PASS_BEGIN(WriteThinLTOBitcode, "write-thinlto-bitcode",
                       "Write ThinLTO Bitcode", false, true)
+INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
 INITIALIZE_PASS_DEPENDENCY(ModuleSummaryIndexWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_END(WriteThinLTOBitcode, "write-thinlto-bitcode",
                     "Write ThinLTO Bitcode", false, true)
 
-ModulePass *llvm::createWriteThinLTOBitcodePass(raw_ostream &Str) {
-  return new WriteThinLTOBitcode(Str);
+ModulePass *llvm::createWriteThinLTOBitcodePass(raw_ostream &Str,
+                                                raw_ostream *ThinLinkOS) {
+  return new WriteThinLTOBitcode(Str, ThinLinkOS);
 }