MIR Serialization: Connect the machine function analysis pass to the MIR parser.

This commit connects the machine function analysis pass (which creates machine
functions) to the MIR parser, which will initialize the machine functions 
with the state from the MIR file and reconstruct the machine IR.

This commit introduces a new interface called 'MachineFunctionInitializer',
which can be used to provide custom initialization for the machine functions.

This commit also introduces a new diagnostic class called 
'DiagnosticInfoMIRParser' which is used for MIR parsing errors.
This commit modifies the default diagnostic handling in LLVMContext - now the
the diagnostics are printed directly into llvm::errs() so that the MIR parsing 
errors can be printed with colours.  

Reviewers: Justin Bogner

Differential Revision: http://reviews.llvm.org/D9928

llvm-svn: 239753

10 files changed, 161 insertions, 75 deletions

diff --git a/llvm/lib/CodeGen/LLVMTargetMachine.cpp b/llvm/lib/CodeGen/LLVMTargetMachine.cpp
index ef44fda3390..b7cac3ba381 100644
--- a/llvm/lib/CodeGen/LLVMTargetMachine.cpp
+++ b/llvm/lib/CodeGen/LLVMTargetMachine.cpp
@@ -87,11 +87,11 @@ TargetIRAnalysis LLVMTargetMachine::getTargetIRAnalysis() {
 }
 
 /// addPassesToX helper drives creation and initialization of TargetPassConfig.
-static MCContext *addPassesToGenerateCode(LLVMTargetMachine *TM,
-                                          PassManagerBase &PM,
-                                          bool DisableVerify,
-                                          AnalysisID StartAfter,
-                                          AnalysisID StopAfter) {
+static MCContext *
+addPassesToGenerateCode(LLVMTargetMachine *TM, PassManagerBase &PM,
+                        bool DisableVerify, AnalysisID StartAfter,
+                        AnalysisID StopAfter,
+                        MachineFunctionInitializer *MFInitializer = nullptr) {
 
   // Add internal analysis passes from the target machine.
   PM.add(createTargetTransformInfoWrapperPass(TM->getTargetIRAnalysis()));
@@ -121,7 +121,7 @@ static MCContext *addPassesToGenerateCode(LLVMTargetMachine *TM,
   PM.add(MMI);
 
   // Set up a MachineFunction for the rest of CodeGen to work on.
-  PM.add(new MachineFunctionAnalysis(*TM));
+  PM.add(new MachineFunctionAnalysis(*TM, MFInitializer));
 
   // Enable FastISel with -fast, but allow that to be overridden.
   if (EnableFastISelOption == cl::BOU_TRUE ||
@@ -142,10 +142,11 @@ static MCContext *addPassesToGenerateCode(LLVMTargetMachine *TM,
 
 bool LLVMTargetMachine::addPassesToEmitFile(
     PassManagerBase &PM, raw_pwrite_stream &Out, CodeGenFileType FileType,
-    bool DisableVerify, AnalysisID StartAfter, AnalysisID StopAfter) {
+    bool DisableVerify, AnalysisID StartAfter, AnalysisID StopAfter,
+    MachineFunctionInitializer *MFInitializer) {
   // Add common CodeGen passes.
-  MCContext *Context = addPassesToGenerateCode(this, PM, DisableVerify,
-                                               StartAfter, StopAfter);
+  MCContext *Context = addPassesToGenerateCode(
+      this, PM, DisableVerify, StartAfter, StopAfter, MFInitializer);
   if (!Context)
     return true;
 
diff --git a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
index 7a51b3881af..69ecb923ed7 100644
--- a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
@@ -14,9 +14,13 @@
 
 #include "llvm/CodeGen/MIRParser/MIRParser.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/AsmParser/Parser.h"
+#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MIRYamlMapping.h"
+#include "llvm/IR/DiagnosticInfo.h"
+#include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/LineIterator.h"
 #include "llvm/Support/SMLoc.h"
@@ -27,7 +31,7 @@
 
 using namespace llvm;
 
-namespace {
+namespace llvm {
 
 /// This class implements the parsing of LLVM IR that's embedded inside a MIR
 /// file.
@@ -35,29 +39,43 @@ class MIRParserImpl {
   SourceMgr SM;
   StringRef Filename;
   LLVMContext &Context;
+  StringMap<std::unique_ptr<yaml::MachineFunction>> Functions;
 
 public:
   MIRParserImpl(std::unique_ptr<MemoryBuffer> Contents, StringRef Filename,
                 LLVMContext &Context);
 
+  void reportDiagnostic(const SMDiagnostic &Diag);
+
+  /// Report an error with the given message at unknown location.
+  ///
+  /// Always returns true.
+  bool error(const Twine &Message);
+
   /// Try to parse the optional LLVM module and the machine functions in the MIR
   /// file.
   ///
   /// Return null if an error occurred.
-  std::unique_ptr<Module> parse(SMDiagnostic &Error);
+  std::unique_ptr<Module> parse();
 
   /// Parse the machine function in the current YAML document.
   ///
   /// Return true if an error occurred.
   bool parseMachineFunction(yaml::Input &In);
 
+  /// Initialize the machine function to the state that's described in the MIR
+  /// file.
+  ///
+  /// Return true if error occurred.
+  bool initializeMachineFunction(MachineFunction &MF);
+
 private:
   /// Return a MIR diagnostic converted from an LLVM assembly diagnostic.
   SMDiagnostic diagFromLLVMAssemblyDiag(const SMDiagnostic &Error,
                                         SMRange SourceRange);
 };
 
-} // end anonymous namespace
+} // end namespace llvm
 
 MIRParserImpl::MIRParserImpl(std::unique_ptr<MemoryBuffer> Contents,
                              StringRef Filename, LLVMContext &Context)
@@ -65,16 +83,38 @@ MIRParserImpl::MIRParserImpl(std::unique_ptr<MemoryBuffer> Contents,
   SM.AddNewSourceBuffer(std::move(Contents), SMLoc());
 }
 
+bool MIRParserImpl::error(const Twine &Message) {
+  Context.diagnose(DiagnosticInfoMIRParser(
+      DS_Error, SMDiagnostic(Filename, SourceMgr::DK_Error, Message.str())));
+  return true;
+}
+
+void MIRParserImpl::reportDiagnostic(const SMDiagnostic &Diag) {
+  DiagnosticSeverity Kind;
+  switch (Diag.getKind()) {
+  case SourceMgr::DK_Error:
+    Kind = DS_Error;
+    break;
+  case SourceMgr::DK_Warning:
+    Kind = DS_Warning;
+    break;
+  case SourceMgr::DK_Note:
+    Kind = DS_Note;
+    break;
+  }
+  Context.diagnose(DiagnosticInfoMIRParser(Kind, Diag));
+}
+
 static void handleYAMLDiag(const SMDiagnostic &Diag, void *Context) {
-  *reinterpret_cast<SMDiagnostic *>(Context) = Diag;
+  reinterpret_cast<MIRParserImpl *>(Context)->reportDiagnostic(Diag);
 }
 
-std::unique_ptr<Module> MIRParserImpl::parse(SMDiagnostic &Error) {
+std::unique_ptr<Module> MIRParserImpl::parse() {
   yaml::Input In(SM.getMemoryBuffer(SM.getMainFileID())->getBuffer(),
-                 /*Ctxt=*/nullptr, handleYAMLDiag, &Error);
+                 /*Ctxt=*/nullptr, handleYAMLDiag, this);
 
   if (!In.setCurrentDocument()) {
-    if (!Error.getMessage().empty())
+    if (In.error())
       return nullptr;
     // Create an empty module when the MIR file is empty.
     return llvm::make_unique<Module>(Filename, Context);
@@ -85,10 +125,11 @@ std::unique_ptr<Module> MIRParserImpl::parse(SMDiagnostic &Error) {
   // without having to go trough YAML traits.
   if (const auto *BSN =
           dyn_cast_or_null<yaml::BlockScalarNode>(In.getCurrentNode())) {
+    SMDiagnostic Error;
     M = parseAssembly(MemoryBufferRef(BSN->getValue(), Filename), Error,
                       Context);
     if (!M) {
-      Error = diagFromLLVMAssemblyDiag(Error, BSN->getSourceRange());
+      reportDiagnostic(diagFromLLVMAssemblyDiag(Error, BSN->getSourceRange()));
       return M;
     }
     In.nextDocument();
@@ -110,12 +151,21 @@ std::unique_ptr<Module> MIRParserImpl::parse(SMDiagnostic &Error) {
 }
 
 bool MIRParserImpl::parseMachineFunction(yaml::Input &In) {
-  yaml::MachineFunction MF;
-  yaml::yamlize(In, MF, false);
+  auto MF = llvm::make_unique<yaml::MachineFunction>();
+  yaml::yamlize(In, *MF, false);
   if (In.error())
     return true;
-  // TODO: Initialize the real machine function with the state in the yaml
-  // machine function later on.
+  auto FunctionName = MF->Name;
+  Functions.insert(std::make_pair(FunctionName, std::move(MF)));
+  return false;
+}
+
+bool MIRParserImpl::initializeMachineFunction(MachineFunction &MF) {
+  auto It = Functions.find(MF.getName());
+  if (It == Functions.end())
+    return error(Twine("no machine function information for function '") +
+                 MF.getName() + "' in the MIR file");
+  // TODO: Recreate the machine function.
   return false;
 }
 
@@ -150,22 +200,33 @@ SMDiagnostic MIRParserImpl::diagFromLLVMAssemblyDiag(const SMDiagnostic &Error,
                       Error.getFixIts());
 }
 
-std::unique_ptr<Module> llvm::parseMIRFile(StringRef Filename,
-                                           SMDiagnostic &Error,
-                                           LLVMContext &Context) {
+MIRParser::MIRParser(std::unique_ptr<MIRParserImpl> Impl)
+    : Impl(std::move(Impl)) {}
+
+MIRParser::~MIRParser() {}
+
+std::unique_ptr<Module> MIRParser::parseLLVMModule() { return Impl->parse(); }
+
+bool MIRParser::initializeMachineFunction(MachineFunction &MF) {
+  return Impl->initializeMachineFunction(MF);
+}
+
+std::unique_ptr<MIRParser> llvm::createMIRParserFromFile(StringRef Filename,
+                                                         SMDiagnostic &Error,
+                                                         LLVMContext &Context) {
   auto FileOrErr = MemoryBuffer::getFile(Filename);
   if (std::error_code EC = FileOrErr.getError()) {
     Error = SMDiagnostic(Filename, SourceMgr::DK_Error,
                          "Could not open input file: " + EC.message());
-    return std::unique_ptr<Module>();
+    return nullptr;
   }
-  return parseMIR(std::move(FileOrErr.get()), Error, Context);
+  return createMIRParser(std::move(FileOrErr.get()), Context);
 }
 
-std::unique_ptr<Module> llvm::parseMIR(std::unique_ptr<MemoryBuffer> Contents,
-                                       SMDiagnostic &Error,
-                                       LLVMContext &Context) {
+std::unique_ptr<MIRParser>
+llvm::createMIRParser(std::unique_ptr<MemoryBuffer> Contents,
+                      LLVMContext &Context) {
   auto Filename = Contents->getBufferIdentifier();
-  MIRParserImpl Parser(std::move(Contents), Filename, Context);
-  return Parser.parse(Error);
+  return llvm::make_unique<MIRParser>(
+      llvm::make_unique<MIRParserImpl>(std::move(Contents), Filename, Context));
 }
diff --git a/llvm/lib/CodeGen/MachineFunction.cpp b/llvm/lib/CodeGen/MachineFunction.cpp
index addb9e81d4a..960e06af2e3 100644
--- a/llvm/lib/CodeGen/MachineFunction.cpp
+++ b/llvm/lib/CodeGen/MachineFunction.cpp
@@ -19,6 +19,7 @@
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
+#include "llvm/CodeGen/MachineFunctionInitializer.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
@@ -41,6 +42,8 @@ using namespace llvm;
 
 #define DEBUG_TYPE "codegen"
 
+void MachineFunctionInitializer::anchor() {}
+
 //===----------------------------------------------------------------------===//
 // MachineFunction implementation
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/CodeGen/MachineFunctionAnalysis.cpp b/llvm/lib/CodeGen/MachineFunctionAnalysis.cpp
index f6f34ba9d92..338cd1e2203 100644
--- a/llvm/lib/CodeGen/MachineFunctionAnalysis.cpp
+++ b/llvm/lib/CodeGen/MachineFunctionAnalysis.cpp
@@ -15,12 +15,14 @@
 #include "llvm/CodeGen/GCMetadata.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/CodeGen/MachineFunctionInitializer.h"
 using namespace llvm;
 
 char MachineFunctionAnalysis::ID = 0;
 
-MachineFunctionAnalysis::MachineFunctionAnalysis(const TargetMachine &tm) :
-  FunctionPass(ID), TM(tm), MF(nullptr) {
+MachineFunctionAnalysis::MachineFunctionAnalysis(
+    const TargetMachine &tm, MachineFunctionInitializer *MFInitializer)
+    : FunctionPass(ID), TM(tm), MF(nullptr), MFInitializer(MFInitializer) {
   initializeMachineModuleInfoPass(*PassRegistry::getPassRegistry());
 }
 
@@ -47,6 +49,8 @@ bool MachineFunctionAnalysis::runOnFunction(Function &F) {
   assert(!MF && "MachineFunctionAnalysis already initialized!");
   MF = new MachineFunction(&F, TM, NextFnNum++,
                            getAnalysis<MachineModuleInfo>());
+  if (MFInitializer)
+    MFInitializer->initializeMachineFunction(*MF);
   return false;
 }
 
diff --git a/llvm/lib/IR/DiagnosticInfo.cpp b/llvm/lib/IR/DiagnosticInfo.cpp
index 50e1ccf834f..b8f77eda15a 100644
--- a/llvm/lib/IR/DiagnosticInfo.cpp
+++ b/llvm/lib/IR/DiagnosticInfo.cpp
@@ -170,6 +170,10 @@ bool DiagnosticInfoOptimizationRemarkAnalysis::isEnabled() const {
          PassRemarksAnalysisOptLoc.Pattern->match(getPassName());
 }
 
+void DiagnosticInfoMIRParser::print(DiagnosticPrinter &DP) const {
+  DP << Diagnostic;
+}
+
 void llvm::emitOptimizationRemark(LLVMContext &Ctx, const char *PassName,
                                   const Function &Fn, const DebugLoc &DLoc,
                                   const Twine &Msg) {
diff --git a/llvm/lib/IR/DiagnosticPrinter.cpp b/llvm/lib/IR/DiagnosticPrinter.cpp
index f25fc20a197..659ff49d623 100644
--- a/llvm/lib/IR/DiagnosticPrinter.cpp
+++ b/llvm/lib/IR/DiagnosticPrinter.cpp
@@ -16,6 +16,7 @@
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Value.h"
 #include "llvm/Support/raw_ostream.h"
+#include "llvm/Support/SourceMgr.h"
 
 using namespace llvm;
 
@@ -105,3 +106,12 @@ DiagnosticPrinter &DiagnosticPrinterRawOStream::operator<<(const Module &M) {
   Stream << M.getModuleIdentifier();
   return *this;
 }
+
+// Other types.
+DiagnosticPrinter &DiagnosticPrinterRawOStream::
+operator<<(const SMDiagnostic &Diag) {
+  // We don't have to print the SMDiagnostic kind, as the diagnostic severity
+  // is printed by the diagnostic handler.
+  Diag.print("", Stream, /*ShowColors=*/true, /*ShowKindLabel=*/false);
+  return *this;
+}
diff --git a/llvm/lib/IR/LLVMContext.cpp b/llvm/lib/IR/LLVMContext.cpp
index 7bcd829f9f5..0cd2a34eb16 100644
--- a/llvm/lib/IR/LLVMContext.cpp
+++ b/llvm/lib/IR/LLVMContext.cpp
@@ -199,6 +199,19 @@ static bool isDiagnosticEnabled(const DiagnosticInfo &DI) {
   return true;
 }
 
+static const char *getDiagnosticMessagePrefix(DiagnosticSeverity Severity) {
+  switch (Severity) {
+  case DS_Error:
+    return "error";
+  case DS_Warning:
+    return "warning";
+  case DS_Remark:
+    return "remark";
+  case DS_Note:
+    return "note";
+  }
+}
+
 void LLVMContext::diagnose(const DiagnosticInfo &DI) {
   // If there is a report handler, use it.
   if (pImpl->DiagnosticHandler) {
@@ -211,25 +224,12 @@ void LLVMContext::diagnose(const DiagnosticInfo &DI) {
     return;
 
   // Otherwise, print the message with a prefix based on the severity.
-  std::string MsgStorage;
-  raw_string_ostream Stream(MsgStorage);
-  DiagnosticPrinterRawOStream DP(Stream);
+  DiagnosticPrinterRawOStream DP(errs());
+  errs() << getDiagnosticMessagePrefix(DI.getSeverity()) << ": ";
   DI.print(DP);
-  Stream.flush();
-  switch (DI.getSeverity()) {
-  case DS_Error:
-    errs() << "error: " << MsgStorage << "\n";
+  errs() << "\n";
+  if (DI.getSeverity() == DS_Error)
     exit(1);
-  case DS_Warning:
-    errs() << "warning: " << MsgStorage << "\n";
-    break;
-  case DS_Remark:
-    errs() << "remark: " << MsgStorage << "\n";
-    break;
-  case DS_Note:
-    errs() << "note: " << MsgStorage << "\n";
-    break;
-  }
 }
 
 void LLVMContext::emitError(unsigned LocCookie, const Twine &ErrorStr) {
diff --git a/llvm/lib/Support/SourceMgr.cpp b/llvm/lib/Support/SourceMgr.cpp
index d5e3157b064..6d44a4d51f6 100644
--- a/llvm/lib/Support/SourceMgr.cpp
+++ b/llvm/lib/Support/SourceMgr.cpp
@@ -332,8 +332,8 @@ static bool isNonASCII(char c) {
   return c & 0x80;
 }
 
-void SMDiagnostic::print(const char *ProgName, raw_ostream &S,
-                         bool ShowColors) const {
+void SMDiagnostic::print(const char *ProgName, raw_ostream &S, bool ShowColors,
+                         bool ShowKindLabel) const {
   // Display colors only if OS supports colors.
   ShowColors &= S.has_colors();
 
@@ -357,27 +357,29 @@ void SMDiagnostic::print(const char *ProgName, raw_ostream &S,
     S << ": ";
   }
 
-  switch (Kind) {
-  case SourceMgr::DK_Error:
-    if (ShowColors)
-      S.changeColor(raw_ostream::RED, true);
-    S << "error: ";
-    break;
-  case SourceMgr::DK_Warning:
-    if (ShowColors)
-      S.changeColor(raw_ostream::MAGENTA, true);
-    S << "warning: ";
-    break;
-  case SourceMgr::DK_Note:
-    if (ShowColors)
-      S.changeColor(raw_ostream::BLACK, true);
-    S << "note: ";
-    break;
-  }
+  if (ShowKindLabel) {
+    switch (Kind) {
+    case SourceMgr::DK_Error:
+      if (ShowColors)
+        S.changeColor(raw_ostream::RED, true);
+      S << "error: ";
+      break;
+    case SourceMgr::DK_Warning:
+      if (ShowColors)
+        S.changeColor(raw_ostream::MAGENTA, true);
+      S << "warning: ";
+      break;
+    case SourceMgr::DK_Note:
+      if (ShowColors)
+        S.changeColor(raw_ostream::BLACK, true);
+      S << "note: ";
+      break;
+    }
 
-  if (ShowColors) {
-    S.resetColor();
-    S.changeColor(raw_ostream::SAVEDCOLOR, true);
+    if (ShowColors) {
+      S.resetColor();
+      S.changeColor(raw_ostream::SAVEDCOLOR, true);
+    }
   }
 
   S << Message << '\n';
diff --git a/llvm/lib/Target/CppBackend/CPPBackend.cpp b/llvm/lib/Target/CppBackend/CPPBackend.cpp
index b8377986ecc..36c421e2b14 100644
--- a/llvm/lib/Target/CppBackend/CPPBackend.cpp
+++ b/llvm/lib/Target/CppBackend/CPPBackend.cpp
@@ -2148,7 +2148,8 @@ char CppWriter::ID = 0;
 
 bool CPPTargetMachine::addPassesToEmitFile(
     PassManagerBase &PM, raw_pwrite_stream &o, CodeGenFileType FileType,
-    bool DisableVerify, AnalysisID StartAfter, AnalysisID StopAfter) {
+    bool DisableVerify, AnalysisID StartAfter, AnalysisID StopAfter,
+    MachineFunctionInitializer *MFInitializer) {
   if (FileType != TargetMachine::CGFT_AssemblyFile)
     return true;
   auto FOut = llvm::make_unique<formatted_raw_ostream>(o);
diff --git a/llvm/lib/Target/CppBackend/CPPTargetMachine.h b/llvm/lib/Target/CppBackend/CPPTargetMachine.h
index f7d0e18a0c4..ebf0635b12e 100644
--- a/llvm/lib/Target/CppBackend/CPPTargetMachine.h
+++ b/llvm/lib/Target/CppBackend/CPPTargetMachine.h
@@ -31,8 +31,8 @@ struct CPPTargetMachine : public TargetMachine {
 public:
   bool addPassesToEmitFile(PassManagerBase &PM, raw_pwrite_stream &Out,
                            CodeGenFileType FileType, bool DisableVerify,
-                           AnalysisID StartAfter,
-                           AnalysisID StopAfter) override;
+                           AnalysisID StartAfter, AnalysisID StopAfter,
+                           MachineFunctionInitializer *MFInitializer) override;
 };
 
 extern Target TheCppBackendTarget;