[cfi] CFI-ICall for ThinLTO.

Implement ControlFlowIntegrity for indirect function calls in ThinLTO.
Design follows the RFC in llvm-dev, see
https://groups.google.com/d/msg/llvm-dev/MgUlaphu4Qc/kywu0AqjAQAJ

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@305533 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Analysis/TypeMetadataUtils.h

@@ -20,6 +20,13 @@
 
 namespace llvm {
 
+/// The type of CFI jumptable needed for a function.
+enum CfiFunctionLinkage {
+  CFL_Definition = 0,
+  CFL_Declaration = 1,
+  CFL_WeakDeclaration = 2
+};
+
 /// A call site that could be devirtualized.
 struct DevirtCallSite {
   /// The offset from the address point to the virtual function.

include/llvm/Bitcode/BitcodeWriter.h

@@ -67,6 +67,10 @@ namespace llvm {
     void writeModule(const Module *M, bool ShouldPreserveUseListOrder = false,
                      const ModuleSummaryIndex *Index = nullptr,
                      bool GenerateHash = false, ModuleHash *ModHash = nullptr);
+
+    void writeIndex(
+        const ModuleSummaryIndex *Index,
+        const std::map<std::string, GVSummaryMapTy> *ModuleToSummariesForIndex);
   };
 
   /// \brief Write the specified module to the specified raw output stream.

include/llvm/Bitcode/LLVMBitCodes.h

@@ -240,6 +240,14 @@ enum GlobalValueSummarySymtabCodes {
   // summaries, but it can also appear in per-module summaries for PGO data.
   // [valueid, guid]
   FS_VALUE_GUID = 16,
+  // The list of local functions with CFI jump tables. Function names are
+  // strings in strtab.
+  // [n * name]
+  FS_CFI_FUNCTION_DEFS = 17,
+  // The list of external functions with CFI jump tables. Function names are
+  // strings in strtab.
+  // [n * name]
+  FS_CFI_FUNCTION_DECLS = 18,
 };
 
 enum MetadataCodes {

include/llvm/IR/ModuleSummaryIndex.h

@@ -32,6 +32,7 @@
 #include <cstdint>
 #include <map>
 #include <memory>
+#include <set>
 #include <string>
 #include <utility>
 #include <vector>
@@ -542,6 +543,9 @@ class ModuleSummaryIndex {
   /// considered live.
   bool WithGlobalValueDeadStripping = false;
 
+  std::set<std::string> CfiFunctionDefs;
+  std::set<std::string> CfiFunctionDecls;
+
   // YAML I/O support.
   friend yaml::MappingTraits<ModuleSummaryIndex>;
 
@@ -593,6 +597,12 @@ class ModuleSummaryIndex {
     return I == OidGuidMap.end() ? 0 : I->second;
   }
 
+  std::set<std::string> &cfiFunctionDefs() { return CfiFunctionDefs; }
+  const std::set<std::string> &cfiFunctionDefs() const { return CfiFunctionDefs; }
+
+  std::set<std::string> &cfiFunctionDecls() { return CfiFunctionDecls; }
+  const std::set<std::string> &cfiFunctionDecls() const { return CfiFunctionDecls; }
+
   /// Add a global value summary for a value of the given name.
   void addGlobalValueSummary(StringRef ValueName,
                              std::unique_ptr<GlobalValueSummary> Summary) {

include/llvm/IR/ModuleSummaryIndexYAML.h

@@ -188,6 +188,7 @@ template <> struct MappingTraits<FunctionSummaryYaml> {
 
 LLVM_YAML_IS_STRING_MAP(TypeIdSummary)
 LLVM_YAML_IS_SEQUENCE_VECTOR(FunctionSummaryYaml)
+LLVM_YAML_IS_SEQUENCE_VECTOR(std::string)
 
 namespace llvm {
 namespace yaml {
@@ -240,6 +241,23 @@ template <> struct MappingTraits<ModuleSummaryIndex> {
     io.mapOptional("TypeIdMap", index.TypeIdMap);
     io.mapOptional("WithGlobalValueDeadStripping",
                    index.WithGlobalValueDeadStripping);
+
+    if (io.outputting()) {
+      std::vector<std::string> CfiFunctionDefs(index.CfiFunctionDefs.begin(),
+                                               index.CfiFunctionDefs.end());
+      io.mapOptional("CfiFunctionDefs", CfiFunctionDefs);
+      std::vector<std::string> CfiFunctionDecls(index.CfiFunctionDecls.begin(),
+                                                index.CfiFunctionDecls.end());
+      io.mapOptional("CfiFunctionDecls", CfiFunctionDecls);
+    } else {
+      std::vector<std::string> CfiFunctionDefs;
+      io.mapOptional("CfiFunctionDefs", CfiFunctionDefs);
+      index.CfiFunctionDefs = {CfiFunctionDefs.begin(), CfiFunctionDefs.end()};
+      std::vector<std::string> CfiFunctionDecls;
+      io.mapOptional("CfiFunctionDecls", CfiFunctionDecls);
+      index.CfiFunctionDecls = {CfiFunctionDecls.begin(),
+                                CfiFunctionDecls.end()};
+    }
   }
 };
 

lib/Bitcode/Reader/BitcodeReader.cpp

@@ -5252,6 +5252,18 @@ Error ModuleSummaryIndexBitcodeReader::parseEntireSummary(unsigned ID) {
           {{Record[0], Record[1]}, {Record.begin() + 2, Record.end()}});
       break;
     }
+    case bitc::FS_CFI_FUNCTION_DEFS: {
+      std::set<std::string> &CfiFunctionDefs = TheIndex.cfiFunctionDefs();
+      for (unsigned I = 0; I != Record.size(); I += 2)
+        CfiFunctionDefs.insert({Strtab.data() + Record[I], Record[I+1]});
+      break;
+    }
+    case bitc::FS_CFI_FUNCTION_DECLS: {
+      std::set<std::string> &CfiFunctionDecls = TheIndex.cfiFunctionDecls();
+      for (unsigned I = 0; I != Record.size(); I += 2)
+        CfiFunctionDecls.insert({Strtab.data() + Record[I], Record[I+1]});
+      break;
+    }
     }
   }
   llvm_unreachable("Exit infinite loop");

lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -77,10 +77,13 @@ class BitcodeWriterBase {
   /// The stream created and owned by the client.
   BitstreamWriter &Stream;
 
+  StringTableBuilder &StrtabBuilder;
+
 public:
   /// Constructs a BitcodeWriterBase object that writes to the provided
   /// \p Stream.
-  BitcodeWriterBase(BitstreamWriter &Stream) : Stream(Stream) {}
+  BitcodeWriterBase(BitstreamWriter &Stream, StringTableBuilder &StrtabBuilder)
+      : Stream(Stream), StrtabBuilder(StrtabBuilder) {}
 
 protected:
   void writeBitcodeHeader();
@@ -97,8 +100,6 @@ class ModuleBitcodeWriter : public BitcodeWriterBase {
   /// Pointer to the buffer allocated by caller for bitcode writing.
   const SmallVectorImpl<char> &Buffer;
 
-  StringTableBuilder &StrtabBuilder;
-
   /// The Module to write to bitcode.
   const Module &M;
 
@@ -142,8 +143,8 @@ class ModuleBitcodeWriter : public BitcodeWriterBase {
                       BitstreamWriter &Stream, bool ShouldPreserveUseListOrder,
                       const ModuleSummaryIndex *Index, bool GenerateHash,
                       ModuleHash *ModHash = nullptr)
-      : BitcodeWriterBase(Stream), Buffer(Buffer), StrtabBuilder(StrtabBuilder),
-        M(*M), VE(*M, ShouldPreserveUseListOrder), Index(Index),
+      : BitcodeWriterBase(Stream, StrtabBuilder), Buffer(Buffer), M(*M),
+        VE(*M, ShouldPreserveUseListOrder), Index(Index),
         GenerateHash(GenerateHash), ModHash(ModHash),
         BitcodeStartBit(Stream.GetCurrentBitNo()) {
     // Assign ValueIds to any callee values in the index that came from
@@ -331,10 +332,11 @@ class IndexBitcodeWriter : public BitcodeWriterBase {
   /// Constructs a IndexBitcodeWriter object for the given combined index,
   /// writing to the provided \p Buffer. When writing a subset of the index
   /// for a distributed backend, provide a \p ModuleToSummariesForIndex map.
-  IndexBitcodeWriter(BitstreamWriter &Stream, const ModuleSummaryIndex &Index,
+  IndexBitcodeWriter(BitstreamWriter &Stream, StringTableBuilder &StrtabBuilder,
+                     const ModuleSummaryIndex &Index,
                      const std::map<std::string, GVSummaryMapTy>
                          *ModuleToSummariesForIndex = nullptr)
-      : BitcodeWriterBase(Stream), Index(Index),
+      : BitcodeWriterBase(Stream, StrtabBuilder), Index(Index),
         ModuleToSummariesForIndex(ModuleToSummariesForIndex) {
     // Assign unique value ids to all summaries to be written, for use
     // in writing out the call graph edges. Save the mapping from GUID
@@ -3595,6 +3597,24 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
     MaybeEmitOriginalName(*AS);
   }
 
+  if (!Index.cfiFunctionDefs().empty()) {
+    for (auto &S : Index.cfiFunctionDefs()) {
+      NameVals.push_back(StrtabBuilder.add(S));
+      NameVals.push_back(S.size());
+    }
+    Stream.EmitRecord(bitc::FS_CFI_FUNCTION_DEFS, NameVals);
+    NameVals.clear();
+  }
+
+  if (!Index.cfiFunctionDecls().empty()) {
+    for (auto &S : Index.cfiFunctionDecls()) {
+      NameVals.push_back(StrtabBuilder.add(S));
+      NameVals.push_back(S.size());
+    }
+    Stream.EmitRecord(bitc::FS_CFI_FUNCTION_DECLS, NameVals);
+    NameVals.clear();
+  }
+
   Stream.ExitBlock();
 }
 
@@ -3829,6 +3849,14 @@ void BitcodeWriter::writeModule(const Module *M,
   ModuleWriter.write();
 }
 
+void BitcodeWriter::writeIndex(
+    const ModuleSummaryIndex *Index,
+    const std::map<std::string, GVSummaryMapTy> *ModuleToSummariesForIndex) {
+  IndexBitcodeWriter IndexWriter(*Stream, StrtabBuilder, *Index,
+                                 ModuleToSummariesForIndex);
+  IndexWriter.write();
+}
+
 /// WriteBitcodeToFile - Write the specified module to the specified output
 /// stream.
 void llvm::WriteBitcodeToFile(const Module *M, raw_ostream &Out,
@@ -3880,11 +3908,9 @@ void llvm::WriteIndexToFile(
   SmallVector<char, 0> Buffer;
   Buffer.reserve(256 * 1024);
 
-  BitstreamWriter Stream(Buffer);
-  writeBitcodeHeader(Stream);
-
-  IndexBitcodeWriter IndexWriter(Stream, Index, ModuleToSummariesForIndex);
-  IndexWriter.write();
+  BitcodeWriter Writer(Buffer);
+  Writer.writeIndex(&Index, ModuleToSummariesForIndex);
+  Writer.writeStrtab();
 
   Out.write((char *)&Buffer.front(), Buffer.size());
 }

lib/IR/ModuleSummaryIndex.cpp

@@ -60,8 +60,11 @@ ModuleSummaryIndex::getGlobalValueSummary(uint64_t ValueGUID,
 bool ModuleSummaryIndex::isGUIDLive(GlobalValue::GUID GUID) const {
   auto VI = getValueInfo(GUID);
   if (!VI)
-    return false;
-  for (auto &I : VI.getSummaryList())
+    return true;
+  const auto &SummaryList = VI.getSummaryList();
+  if (SummaryList.empty())
+    return true;
+  for (auto &I : SummaryList)
     if (isGlobalValueLive(I.get()))
       return true;
   return false;

lib/Transforms/IPO/CrossDSOCFI.cpp

@@ -95,6 +95,17 @@ void CrossDSOCFI::buildCFICheck(Module &M) {
     }
   }
 
+  NamedMDNode *CfiFunctionsMD = M.getNamedMetadata("cfi.functions");
+  if (CfiFunctionsMD) {
+    for (auto Func : CfiFunctionsMD->operands()) {
+      assert(Func->getNumOperands() >= 2);
+      for (unsigned I = 2; I < Func->getNumOperands(); ++I)
+        if (ConstantInt *TypeId =
+                extractNumericTypeId(cast<MDNode>(Func->getOperand(I).get())))
+          TypeIds.insert(TypeId->getZExtValue());
+    }
+  }
+
   LLVMContext &Ctx = M.getContext();
   Constant *C = M.getOrInsertFunction(
       "__cfi_check", Type::getVoidTy(Ctx), Type::getInt64Ty(Ctx),