Introduce basic support for loading a precompiled preamble while

reparsing an ASTUnit. When saving a preamble, create a buffer larger
than the actual file we're working with but fill everything from the
end of the preamble to the end of the file with spaces (so the lexer
will quickly skip them). When we load the file, create a buffer of the
same size, filling it with the file and then spaces. Then, instruct
the lexer to start lexing after the preamble, therefore continuing the
parse from the spot where the preamble left off.

It's now possible to perform a simple preamble build + parse (+
reparse) with ASTUnit. However, one has to disable a bunch of checking
in the PCH reader to do so. That part isn't committed; it will likely
be handled with some other kind of flag (e.g., -fno-validate-pch).

As part of this, fix some issues with null termination of the memory
buffers created for the preamble; we were trying to explicitly
NULL-terminate them, even though they were also getting implicitly
NULL terminated, leading to excess warnings about NULL characters in
source files.



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@109445 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 78 insertions, 11 deletions

diff --git a/include/clang/Basic/DiagnosticDriverKinds.td b/include/clang/Basic/DiagnosticDriverKinds.td
index f4a31cc576..34cd6004ed 100644
--- a/include/clang/Basic/DiagnosticDriverKinds.td
+++ b/include/clang/Basic/DiagnosticDriverKinds.td
@@ -68,6 +68,8 @@ def err_drv_invalid_gcc_output_type : Error<
     "invalid output type '%0' for use with gcc tool">;
 def err_drv_cc_print_options_failure : Error<
     "unable to open CC_PRINT_OPTIONS file: %0">;
+def err_drv_preamble_format : Error<
+    "incorrect format for -preamble-bytes=N,END">;
 
 def warn_drv_input_file_unused : Warning<
   "%0: '%1' input unused when '%2' is present">;
diff --git a/include/clang/Basic/SourceManager.h b/include/clang/Basic/SourceManager.h
index 5d98fb9253..b6a1ac4492 100644
--- a/include/clang/Basic/SourceManager.h
+++ b/include/clang/Basic/SourceManager.h
@@ -53,10 +53,17 @@ namespace SrcMgr {
   /// ContentCache - Once instance of this struct is kept for every file
   /// loaded or used.  This object owns the MemoryBuffer object.
   class ContentCache {
+    enum CCFlags {
+      /// \brief Whether the buffer is invalid.
+      InvalidFlag = 0x01,
+      /// \brief Whether the buffer should not be freed on destruction.
+      DoNotFreeFlag = 0x02
+    };
+    
     /// Buffer - The actual buffer containing the characters from the input
     /// file.  This is owned by the ContentCache object.
-    /// The bit indicates whether the buffer is invalid.
-    mutable llvm::PointerIntPair<const llvm::MemoryBuffer *, 1, bool> Buffer;
+    /// The bits indicate indicates whether the buffer is invalid.
+    mutable llvm::PointerIntPair<const llvm::MemoryBuffer *, 2> Buffer;
 
   public:
     /// Reference to the file entry.  This reference does not own
@@ -106,8 +113,18 @@ namespace SrcMgr {
 
     /// \brief Replace the existing buffer (which will be deleted)
     /// with the given buffer.
-    void replaceBuffer(const llvm::MemoryBuffer *B);
+    void replaceBuffer(const llvm::MemoryBuffer *B, bool DoNotFree = false);
 
+    /// \brief Determine whether the buffer itself is invalid.
+    bool isBufferInvalid() const {
+      return Buffer.getInt() & InvalidFlag;
+    }
+    
+    /// \brief Determine whether the buffer should be freed.
+    bool shouldFreeBuffer() const {
+      return (Buffer.getInt() & DoNotFreeFlag) == 0;
+    }
+    
     ContentCache(const FileEntry *Ent = 0)
       : Buffer(0, false), Entry(Ent), SourceLineCache(0), NumLines(0) {}
 
@@ -490,9 +507,13 @@ public:
   /// \param Buffer the memory buffer whose contents will be used as the
   /// data in the given source file.
   ///
+  /// \param DoNotFree If true, then the buffer will not be freed when the
+  /// source manager is destroyed.
+  ///
   /// \returns true if an error occurred, false otherwise.
   bool overrideFileContents(const FileEntry *SourceFile,
-                            const llvm::MemoryBuffer *Buffer);
+                            const llvm::MemoryBuffer *Buffer,
+                            bool DoNotFree = false);
 
   //===--------------------------------------------------------------------===//
   // FileID manipulation methods.
diff --git a/include/clang/Driver/CC1Options.td b/include/clang/Driver/CC1Options.td
index b17af4b8c8..b813fea75c 100644
--- a/include/clang/Driver/CC1Options.td
+++ b/include/clang/Driver/CC1Options.td
@@ -505,7 +505,7 @@ def include_pch : Separate<"-include-pch">, MetaVarName<"<file>">,
   HelpText<"Include precompiled header file">;
 def include_pth : Separate<"-include-pth">, MetaVarName<"<file>">,
   HelpText<"Include file before parsing">;
-def use_preamble_EQ : Joined<"-use-preamble=">,
+def preamble_bytes_EQ : Joined<"-preamble-bytes=">,
   HelpText<"Assume that the precompiled header is a precompiled preamble "
            "covering the first N bytes of the main file">;
 def token_cache : Separate<"-token-cache">, MetaVarName<"<path>">,
diff --git a/include/clang/Frontend/ASTUnit.h b/include/clang/Frontend/ASTUnit.h
index 9a4b4c6cb3..d0202dfe28 100644
--- a/include/clang/Frontend/ASTUnit.h
+++ b/include/clang/Frontend/ASTUnit.h
@@ -125,6 +125,12 @@ private:
   /// \c PreambleFile.
   std::vector<char> Preamble;
 
+  /// \brief Whether the preamble ends at the start of a new line.
+  /// 
+  /// Used to inform the lexer as to whether it's starting at the beginning of
+  /// a line after skipping the preamble.
+  bool PreambleEndsAtStartOfLine;
+  
   /// \brief The size of the source buffer that we've reserved for the main 
   /// file within the precompiled preamble.
   unsigned PreambleReservedSize;
@@ -137,9 +143,8 @@ private:
   void CleanTemporaryFiles();
   bool Parse(llvm::MemoryBuffer *OverrideMainBuffer);
   
-  std::pair<llvm::MemoryBuffer *, unsigned> ComputePreamble(
-                                                CompilerInvocation &Invocation,
-                                                          bool &CreatedBuffer);
+  std::pair<llvm::MemoryBuffer *, std::pair<unsigned, bool> >
+  ComputePreamble(CompilerInvocation &Invocation, bool &CreatedBuffer);
   
   llvm::MemoryBuffer *BuildPrecompiledPreamble();
   
diff --git a/include/clang/Frontend/PreprocessorOptions.h b/include/clang/Frontend/PreprocessorOptions.h
index 05159335ad..f2154955c2 100644
--- a/include/clang/Frontend/PreprocessorOptions.h
+++ b/include/clang/Frontend/PreprocessorOptions.h
@@ -43,6 +43,13 @@ public:
   /// The implicit PCH included at the start of the translation unit, or empty.
   std::string ImplicitPCHInclude;
 
+  /// \brief If non-zero, the implicit PCH include is actually a precompiled
+  /// preamble that covers this number of bytes in the main source file.
+  ///
+  /// The boolean indicates whether the preamble ends at the start of a new
+  /// line.
+  std::pair<unsigned, bool> PrecompiledPreambleBytes;
+  
   /// The implicit PTH input included at the start of the translation unit, or
   /// empty.
   std::string ImplicitPTHInclude;
@@ -62,6 +69,14 @@ public:
   std::vector<std::pair<std::string, const llvm::MemoryBuffer *> > 
     RemappedFileBuffers;
   
+  /// \brief Whether the compiler instance should retain (i.e., not free)
+  /// the buffers associated with remapped files.
+  ///
+  /// This flag defaults to false; it can be set true only through direct
+  /// manipulation of the compiler invocation object, in cases where the 
+  /// compiler invocation and its buffers will be reused.
+  bool RetainRemappedFileBuffers;
+  
   typedef std::vector<std::pair<std::string, std::string> >::iterator
     remapped_file_iterator;
   typedef std::vector<std::pair<std::string, std::string> >::const_iterator
@@ -97,7 +112,9 @@ public:
   }
   
 public:
-  PreprocessorOptions() : UsePredefines(true), DetailedRecord(false) {}
+  PreprocessorOptions() : UsePredefines(true), DetailedRecord(false),
+                          PrecompiledPreambleBytes(0, true),
+                          RetainRemappedFileBuffers(false) { }
 
   void addMacroDef(llvm::StringRef Name) {
     Macros.push_back(std::make_pair(Name, false));
diff --git a/include/clang/Lex/Lexer.h b/include/clang/Lex/Lexer.h
index 8dd37d0348..66a33f24f6 100644
--- a/include/clang/Lex/Lexer.h
+++ b/include/clang/Lex/Lexer.h
@@ -238,8 +238,10 @@ public:
   /// \param Buffer The memory buffer containing the file's contents.
   ///
   /// \returns The offset into the file where the preamble ends and the rest
-  /// of the file begins.
-  static unsigned ComputePreamble(const llvm::MemoryBuffer *Buffer);
+  /// of the file begins along with a boolean value indicating whether 
+  /// the preamble ends at the beginning of a new line.
+  static std::pair<unsigned, bool>
+  ComputePreamble(const llvm::MemoryBuffer *Buffer);
                                         
   //===--------------------------------------------------------------------===//
   // Internal implementation interfaces.
@@ -383,6 +385,8 @@ private:
   //===--------------------------------------------------------------------===//
   // Other lexer functions.
 
+  void SkipBytes(unsigned Bytes, bool StartOfLine);
+  
   // Helper functions to lex the remainder of a token of the specific type.
   void LexIdentifier         (Token &Result, const char *CurPtr);
   void LexNumericConstant    (Token &Result, const char *CurPtr);
diff --git a/include/clang/Lex/Preprocessor.h b/include/clang/Lex/Preprocessor.h
index 1ee4bb6351..380f788d22 100644
--- a/include/clang/Lex/Preprocessor.h
+++ b/include/clang/Lex/Preprocessor.h
@@ -134,6 +134,12 @@ class Preprocessor {
   /// \brief The file that we're performing code-completion for, if any.
   const FileEntry *CodeCompletionFile;
 
+  /// \brief The number of bytes that we will initially skip when entering the
+  /// main file, which is used when loading a precompiled preamble, along
+  /// with a flag that indicates whether skipping this number of bytes will
+  /// place the lexer at the start of a line.
+  std::pair<unsigned, bool> SkipMainFilePreamble;
+  
   /// CurLexer - This is the current top of the stack that we're lexing from if
   /// not expanding a macro and we are lexing directly from source code.
   ///  Only one of CurLexer, CurPTHLexer, or CurTokenLexer will be non-null.
@@ -556,6 +562,18 @@ public:
   /// for which we are performing code completion.
   bool isCodeCompletionFile(SourceLocation FileLoc) const;
 
+  /// \brief Instruct the preprocessor to skip part of the main
+  /// the main source file.
+  ///
+  /// \brief Bytes The number of bytes in the preamble to skip.
+  ///
+  /// \brief StartOfLine Whether skipping these bytes puts the lexer at the
+  /// start of a line.
+  void setSkipMainFilePreamble(unsigned Bytes, bool StartOfLine) { 
+    SkipMainFilePreamble.first = Bytes;
+    SkipMainFilePreamble.second = StartOfLine;
+  }
+  
   /// Diag - Forwarding function for diagnostics.  This emits a diagnostic at
   /// the specified Token's location, translating the token's start
   /// position in the current buffer into a SourcePosition object for rendering.