IR: Allow metadata attachments on declarations, and fix lazy loaded metadata issue with globals.

This change is motivated by an upcoming change to the metadata representation
used for CFI. The indirect function call checker needs type information for
external function declarations in order to correctly generate jump table
entries for such declarations. We currently associate such type information
with declarations using a global metadata node, but I plan [1] to move all
such metadata to global object attachments.

In bitcode, metadata attachments for function declarations appear in the
global metadata block. This seems reasonable to me because I expect metadata
attachments on declarations to be uncommon. In the long term I'd also expect
this to be the case for CFI, because we'd want to use some specialized bitcode
format for this metadata that could be read as part of the ThinLTO thin-link
phase, which would mean that it would not appear in the global metadata block.

To solve the lazy loaded metadata issue I was seeing with D20147, I use the
same bitcode representation for metadata attachments for global variables as I
do for function declarations. Since there's a use case for metadata attachments
in the global metadata block, we might as well use that representation for
global variables as well, at least until we have a mechanism for lazy loading
global variables.

In the assembly format, the metadata attachments appear after the "declare"
keyword in order to avoid a parsing ambiguity.

[1] http://lists.llvm.org/pipermail/llvm-dev/2016-June/100462.html

Differential Revision: http://reviews.llvm.org/D21052

llvm-svn: 273336

7 files changed, 79 insertions, 44 deletions

diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 2725386f8da..691625209e4 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -397,8 +397,21 @@ bool LLParser::ParseDeclare() {
   assert(Lex.getKind() == lltok::kw_declare);
   Lex.Lex();
 
+  std::vector<std::pair<unsigned, MDNode *>> MDs;
+  while (Lex.getKind() == lltok::MetadataVar) {
+    unsigned MDK;
+    MDNode *N;
+    if (ParseMetadataAttachment(MDK, N))
+      return true;
+    MDs.push_back({MDK, N});
+  }
+
   Function *F;
-  return ParseFunctionHeader(F, false);
+  if (ParseFunctionHeader(F, false))
+    return true;
+  for (auto &MD : MDs)
+    F->addMetadata(MD.first, *MD.second);
+  return false;
 }
 
 /// toplevelentity
diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index ac534f35bb4..a89bb07f052 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -2692,6 +2692,16 @@ std::error_code BitcodeReader::parseMetadata(bool ModuleLevel) {
               parseMetadataStrings(Record, Blob, NextMetadataNo))
         return EC;
       break;
+    case bitc::METADATA_GLOBAL_DECL_ATTACHMENT: {
+      if (Record.size() % 2 == 0)
+        return error("Invalid record");
+      unsigned ValueID = Record[0];
+      if (ValueID >= ValueList.size())
+        return error("Invalid record");
+      if (auto *GO = dyn_cast<GlobalObject>(ValueList[ValueID]))
+        parseGlobalObjectAttachment(*GO, ArrayRef<uint64_t>(Record).slice(1));
+      break;
+    }
     case bitc::METADATA_KIND: {
       // Support older bitcode files that had METADATA_KIND records in a
       // block with METADATA_BLOCK_ID.
@@ -3840,16 +3850,6 @@ std::error_code BitcodeReader::parseModule(uint64_t ResumeBit,
 
       break;
     }
-    case bitc::MODULE_CODE_GLOBALVAR_ATTACHMENT: {
-      if (Record.size() % 2 == 0)
-        return error("Invalid record");
-      unsigned ValueID = Record[0];
-      if (ValueID >= ValueList.size())
-        return error("Invalid record");
-      if (auto *GV = dyn_cast<GlobalVariable>(ValueList[ValueID]))
-        parseGlobalObjectAttachment(*GV, ArrayRef<uint64_t>(Record).slice(1));
-      break;
-    }
     // FUNCTION:  [type, callingconv, isproto, linkage, paramattr,
     //             alignment, section, visibility, gc, unnamed_addr,
     //             prologuedata, dllstorageclass, comdat, prefixdata]
diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 4699e7dac77..20cbc2bf4b6 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -227,7 +227,7 @@ private:
   void writeGlobalVariableMetadataAttachment(const GlobalVariable &GV);
   void pushGlobalMetadataAttachment(SmallVectorImpl<uint64_t> &Record,
                                     const GlobalObject &GO);
-  void writeModuleMetadataStore();
+  void writeModuleMetadataKinds();
   void writeOperandBundleTags();
   void writeConstants(unsigned FirstVal, unsigned LastVal, bool isGlobal);
   void writeModuleConstants();
@@ -1832,6 +1832,22 @@ void ModuleBitcodeWriter::writeModuleMetadata() {
   writeMetadataStrings(VE.getMDStrings(), Record);
   writeMetadataRecords(VE.getNonMDStrings(), Record);
   writeNamedMetadata(Record);
+
+  auto AddDeclAttachedMetadata = [&](const GlobalObject &GO) {
+    SmallVector<uint64_t, 4> Record;
+    Record.push_back(VE.getValueID(&GO));
+    pushGlobalMetadataAttachment(Record, GO);
+    Stream.EmitRecord(bitc::METADATA_GLOBAL_DECL_ATTACHMENT, Record);
+  };
+  for (const Function &F : M)
+    if (F.isDeclaration() && F.hasMetadata())
+      AddDeclAttachedMetadata(F);
+  // FIXME: Only store metadata for declarations here, and move data for global
+  // variable definitions to a separate block (PR28134).
+  for (const GlobalVariable &GV : M.globals())
+    if (GV.hasMetadata())
+      AddDeclAttachedMetadata(GV);
+
   Stream.ExitBlock();
 }
 
@@ -1892,7 +1908,7 @@ void ModuleBitcodeWriter::writeFunctionMetadataAttachment(const Function &F) {
   Stream.ExitBlock();
 }
 
-void ModuleBitcodeWriter::writeModuleMetadataStore() {
+void ModuleBitcodeWriter::writeModuleMetadataKinds() {
   SmallVector<uint64_t, 64> Record;
 
   // Write metadata kinds
@@ -3593,11 +3609,11 @@ void ModuleBitcodeWriter::writeModule() {
   // Emit constants.
   writeModuleConstants();
 
-  // Emit metadata.
-  writeModuleMetadata();
+  // Emit metadata kind names.
+  writeModuleMetadataKinds();
 
   // Emit metadata.
-  writeModuleMetadataStore();
+  writeModuleMetadata();
 
   // Emit module-level use-lists.
   if (VE.shouldPreserveUseListOrder())
@@ -3619,14 +3635,6 @@ void ModuleBitcodeWriter::writeModule() {
   writeValueSymbolTable(M.getValueSymbolTable(),
                         /* IsModuleLevel */ true, &FunctionToBitcodeIndex);
 
-  for (const GlobalVariable &GV : M.globals())
-    if (GV.hasMetadata()) {
-      SmallVector<uint64_t, 4> Record;
-      Record.push_back(VE.getValueID(&GV));
-      pushGlobalMetadataAttachment(Record, GV);
-      Stream.EmitRecord(bitc::MODULE_CODE_GLOBALVAR_ATTACHMENT, Record);
-    }
-
   if (GenerateHash) {
     writeModuleHash(BlockStartPos);
   }
diff --git a/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp b/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp
index 98eb7faf224..398f7d7d00a 100644
--- a/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp
+++ b/llvm/lib/Bitcode/Writer/ValueEnumerator.cpp
@@ -348,7 +348,10 @@ ValueEnumerator::ValueEnumerator(const Module &M,
     MDs.clear();
     GV.getAllMetadata(MDs);
     for (const auto &I : MDs)
-      EnumerateMetadata(&GV, I.second);
+      // FIXME: Pass GV to EnumerateMetadata and arrange for the bitcode writer
+      // to write metadata to the global variable's own metadata block
+      // (PR28134).
+      EnumerateMetadata(nullptr, I.second);
   }
 
   // Enumerate types used by function bodies and argument lists.
@@ -360,7 +363,7 @@ ValueEnumerator::ValueEnumerator(const Module &M,
     MDs.clear();
     F.getAllMetadata(MDs);
     for (const auto &I : MDs)
-      EnumerateMetadata(&F, I.second);
+      EnumerateMetadata(F.isDeclaration() ? nullptr : &F, I.second);
 
     for (const BasicBlock &BB : F)
       for (const Instruction &I : BB) {
@@ -530,18 +533,17 @@ void ValueEnumerator::EnumerateNamedMDNode(const NamedMDNode *MD) {
     EnumerateMetadata(nullptr, MD->getOperand(i));
 }
 
-unsigned ValueEnumerator::getMetadataGlobalID(const GlobalObject *GO) const {
-  return GO ? getValueID(GO) + 1 : 0;
+unsigned ValueEnumerator::getMetadataFunctionID(const Function *F) const {
+  return F ? getValueID(F) + 1 : 0;
 }
 
-void ValueEnumerator::EnumerateMetadata(const GlobalObject *GO,
-                                        const Metadata *MD) {
-  EnumerateMetadata(getMetadataGlobalID(GO), MD);
+void ValueEnumerator::EnumerateMetadata(const Function *F, const Metadata *MD) {
+  EnumerateMetadata(getMetadataFunctionID(F), MD);
 }
 
 void ValueEnumerator::EnumerateFunctionLocalMetadata(
     const Function &F, const LocalAsMetadata *Local) {
-  EnumerateFunctionLocalMetadata(getMetadataGlobalID(&F), Local);
+  EnumerateFunctionLocalMetadata(getMetadataFunctionID(&F), Local);
 }
 
 void ValueEnumerator::dropFunctionFromMetadata(
diff --git a/llvm/lib/Bitcode/Writer/ValueEnumerator.h b/llvm/lib/Bitcode/Writer/ValueEnumerator.h
index 34d33fc418b..bff2de70b3e 100644
--- a/llvm/lib/Bitcode/Writer/ValueEnumerator.h
+++ b/llvm/lib/Bitcode/Writer/ValueEnumerator.h
@@ -255,7 +255,7 @@ private:
   /// it's an \a MDNode.
   const MDNode *enumerateMetadataImpl(unsigned F, const Metadata *MD);
 
-  unsigned getMetadataGlobalID(const GlobalObject *GO) const;
+  unsigned getMetadataFunctionID(const Function *F) const;
 
   /// Enumerate reachable metadata in (almost) post-order.
   ///
@@ -272,7 +272,7 @@ private:
   /// \a organizeMetadata() will later partition distinct nodes ahead of
   /// uniqued ones.
   ///{
-  void EnumerateMetadata(const GlobalObject *GO, const Metadata *MD);
+  void EnumerateMetadata(const Function *F, const Metadata *MD);
   void EnumerateMetadata(unsigned F, const Metadata *MD);
   ///}
 
diff --git a/llvm/lib/IR/AsmWriter.cpp b/llvm/lib/IR/AsmWriter.cpp
index 3404ae7dc7f..17b622458c4 100644
--- a/llvm/lib/IR/AsmWriter.cpp
+++ b/llvm/lib/IR/AsmWriter.cpp
@@ -2616,9 +2616,15 @@ void AssemblyWriter::printFunction(const Function *F) {
       Out << "; Function Attrs: " << AttrStr << '\n';
   }
 
-  if (F->isDeclaration())
-    Out << "declare ";
-  else
+  Machine.incorporateFunction(F);
+
+  if (F->isDeclaration()) {
+    Out << "declare";
+    SmallVector<std::pair<unsigned, MDNode *>, 4> MDs;
+    F->getAllMetadata(MDs);
+    printMetadataAttachments(MDs, " ");
+    Out << ' ';
+  } else
     Out << "define ";
 
   Out << getLinkagePrintName(F->getLinkage());
@@ -2638,7 +2644,6 @@ void AssemblyWriter::printFunction(const Function *F) {
   Out << ' ';
   WriteAsOperandInternal(Out, F, &TypePrinter, &Machine, F->getParent());
   Out << '(';
-  Machine.incorporateFunction(F);
 
   // Loop over the arguments, printing them...
   if (F->isDeclaration() && !IsForDebug) {
@@ -2698,13 +2703,13 @@ void AssemblyWriter::printFunction(const Function *F) {
     writeOperand(F->getPersonalityFn(), /*PrintType=*/true);
   }
 
-  SmallVector<std::pair<unsigned, MDNode *>, 4> MDs;
-  F->getAllMetadata(MDs);
-  printMetadataAttachments(MDs, " ");
-
   if (F->isDeclaration()) {
     Out << '\n';
   } else {
+    SmallVector<std::pair<unsigned, MDNode *>, 4> MDs;
+    F->getAllMetadata(MDs);
+    printMetadataAttachments(MDs, " ");
+
     Out << " {";
     // Output all of the function's basic blocks.
     for (Function::const_iterator I = F->begin(), E = F->end(); I != E; ++I)
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index ecba8be7eb8..7297d658bb9 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -1956,8 +1956,15 @@ void Verifier::visitFunction(const Function &F) {
     Assert(MDs.empty(), "unmaterialized function cannot have metadata", &F,
            MDs.empty() ? nullptr : MDs.front().second);
   } else if (F.isDeclaration()) {
-    Assert(MDs.empty(), "function without a body cannot have metadata", &F,
-           MDs.empty() ? nullptr : MDs.front().second);
+    for (const auto &I : MDs) {
+      AssertDI(I.first != LLVMContext::MD_dbg,
+               "function declaration may not have a !dbg attachment", &F);
+      Assert(I.first != LLVMContext::MD_prof,
+             "function declaration may not have a !prof attachment", &F);
+
+      // Verify the metadata itself.
+      visitMDNode(*I.second);
+    }
     Assert(!F.hasPersonalityFn(),
            "Function declaration shouldn't have a personality routine", &F);
   } else {