Debug Info: store the files and directories for each compile unit.

We now emit a line table for each compile unit. To reduce the prologue size
of each line table, the files and directories used by each compile unit are
stored in std::map<unsigned, std::vector< > > instead of std::vector< >.

The prologue for a lto'ed image can be as big as 93K. Duplicating 93K for each
compile unit causes a huge increase of debug info. With this patch, each
prologue will only emit the files required by the compile unit.

rdar://problem/13342023


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176605 91177308-0d34-0410-b5e6-96231b3b80d8

12 files changed, 87 insertions, 46 deletions

diff --git a/include/llvm/MC/MCContext.h b/include/llvm/MC/MCContext.h
index 20d52ebb3e..1251c5fbe2 100644
--- a/include/llvm/MC/MCContext.h
+++ b/include/llvm/MC/MCContext.h
@@ -17,6 +17,7 @@
 #include "llvm/Support/Allocator.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/raw_ostream.h"
+#include <map>
 #include <vector> // FIXME: Shouldn't be needed.
 
 namespace llvm {
@@ -101,8 +102,12 @@ namespace llvm {
     std::string MainFileName;
 
     /// The dwarf file and directory tables from the dwarf .file directive.
-    std::vector<MCDwarfFile *> MCDwarfFiles;
-    std::vector<StringRef> MCDwarfDirs;
+    /// We now emit a line table for each compile unit. To reduce the prologue
+    /// size of each line table, the files and directories used by each compile
+    /// unit are separated.
+    typedef std::map<unsigned, std::vector<MCDwarfFile *> > MCDwarfFilesMap;
+    MCDwarfFilesMap MCDwarfFilesCUMap;
+    std::map<unsigned, std::vector<StringRef> > MCDwarfDirsCUMap;
 
     /// The current dwarf line information from the last dwarf .loc directive.
     MCDwarfLoc CurrentDwarfLoc;
@@ -282,19 +287,25 @@ namespace llvm {
 
     /// GetDwarfFile - creates an entry in the dwarf file and directory tables.
     unsigned GetDwarfFile(StringRef Directory, StringRef FileName,
-                          unsigned FileNumber);
+                          unsigned FileNumber, unsigned CUID);
 
-    bool isValidDwarfFileNumber(unsigned FileNumber);
+    bool isValidDwarfFileNumber(unsigned FileNumber, unsigned CUID = 0);
 
     bool hasDwarfFiles() const {
-      return !MCDwarfFiles.empty();
+      // Traverse MCDwarfFilesCUMap and check whether each entry is empty.
+      MCDwarfFilesMap::const_iterator MapB, MapE;
+      for (MapB = MCDwarfFilesCUMap.begin(), MapE = MCDwarfFilesCUMap.end();
+           MapB != MapE; MapB++)
+        if (!MapB->second.empty())
+           return true;
+      return false;
     }
 
-    const std::vector<MCDwarfFile *> &getMCDwarfFiles() {
-      return MCDwarfFiles;
+    const std::vector<MCDwarfFile *> &getMCDwarfFiles(unsigned CUID = 0) {
+      return MCDwarfFilesCUMap[CUID];
     }
-    const std::vector<StringRef> &getMCDwarfDirs() {
-      return MCDwarfDirs;
+    const std::vector<StringRef> &getMCDwarfDirs(unsigned CUID = 0) {
+      return MCDwarfDirsCUMap[CUID];
     }
 
     const DenseMap<const MCSection *, MCLineSection *>
diff --git a/include/llvm/MC/MCStreamer.h b/include/llvm/MC/MCStreamer.h
index d247066cd9..a069a2b0ca 100644
--- a/include/llvm/MC/MCStreamer.h
+++ b/include/llvm/MC/MCStreamer.h
@@ -525,7 +525,7 @@ namespace llvm {
     /// file number.  This implements the DWARF2 '.file 4 "foo.c"' assembler
     /// directive.
     virtual bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                        StringRef Filename);
+                                        StringRef Filename, unsigned CUID = 0);
 
     /// EmitDwarfLocDirective - This implements the DWARF2
     // '.loc fileno lineno ...' assembler directive.
diff --git a/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp b/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
index d9f6b5eb0a..bc3f27cf2a 100644
--- a/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
+++ b/lib/CodeGen/AsmPrinter/DwarfCompileUnit.cpp
@@ -241,7 +241,8 @@ void CompileUnit::addSourceLine(DIE *Die, DIVariable V) {
   if (Line == 0)
     return;
   unsigned FileID = DD->getOrCreateSourceID(V.getContext().getFilename(),
-                                            V.getContext().getDirectory());
+                                            V.getContext().getDirectory(),
+                                            getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
@@ -257,7 +258,8 @@ void CompileUnit::addSourceLine(DIE *Die, DIGlobalVariable G) {
   unsigned Line = G.getLineNumber();
   if (Line == 0)
     return;
-  unsigned FileID = DD->getOrCreateSourceID(G.getFilename(), G.getDirectory());
+  unsigned FileID = DD->getOrCreateSourceID(G.getFilename(), G.getDirectory(),
+                                            getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
@@ -276,7 +278,7 @@ void CompileUnit::addSourceLine(DIE *Die, DISubprogram SP) {
     return;
 
   unsigned FileID = DD->getOrCreateSourceID(SP.getFilename(),
-                                            SP.getDirectory());
+                                            SP.getDirectory(), getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
@@ -293,7 +295,7 @@ void CompileUnit::addSourceLine(DIE *Die, DIType Ty) {
   if (Line == 0)
     return;
   unsigned FileID = DD->getOrCreateSourceID(Ty.getFilename(),
-                                            Ty.getDirectory());
+                                            Ty.getDirectory(), getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
@@ -311,7 +313,7 @@ void CompileUnit::addSourceLine(DIE *Die, DIObjCProperty Ty) {
     return;
   DIFile File = Ty.getFile();
   unsigned FileID = DD->getOrCreateSourceID(File.getFilename(),
-                                            File.getDirectory());
+                                            File.getDirectory(), getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
@@ -329,7 +331,8 @@ void CompileUnit::addSourceLine(DIE *Die, DINameSpace NS) {
     return;
   StringRef FN = NS.getFilename();
 
-  unsigned FileID = DD->getOrCreateSourceID(FN, NS.getDirectory());
+  unsigned FileID = DD->getOrCreateSourceID(FN, NS.getDirectory(),
+                                            getUniqueID());
   assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, 0, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, 0, Line);
diff --git a/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index 87659ef667..bc0e84b0f1 100644
--- a/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -528,7 +528,8 @@ DIE *DwarfDebug::constructInlinedScopeDIE(CompileUnit *TheCU,
 
   DILocation DL(Scope->getInlinedAt());
   TheCU->addUInt(ScopeDIE, dwarf::DW_AT_call_file, 0,
-                 getOrCreateSourceID(DL.getFilename(), DL.getDirectory()));
+                 getOrCreateSourceID(DL.getFilename(), DL.getDirectory(),
+                                     TheCU->getUniqueID()));
   TheCU->addUInt(ScopeDIE, dwarf::DW_AT_call_line, 0, DL.getLineNumber());
 
   // Add name to the name table, we do this here because we're guaranteed
@@ -617,19 +618,28 @@ DIE *DwarfDebug::constructScopeDIE(CompileUnit *TheCU, LexicalScope *Scope) {
 // SourceIds map. This can update DirectoryNames and SourceFileNames maps
 // as well.
 unsigned DwarfDebug::getOrCreateSourceID(StringRef FileName,
-                                         StringRef DirName) {
+                                         StringRef DirName, unsigned CUID) {
+  // If we use .loc in assembly, we can't separate .file entries according to
+  // compile units. Thus all files will belong to the default compile unit.
+  if (Asm->TM.hasMCUseLoc() &&
+      Asm->OutStreamer.getKind() == MCStreamer::SK_AsmStreamer)
+    CUID = 0;
+
   // If FE did not provide a file name, then assume stdin.
   if (FileName.empty())
-    return getOrCreateSourceID("<stdin>", StringRef());
+    return getOrCreateSourceID("<stdin>", StringRef(), CUID);
 
   // TODO: this might not belong here. See if we can factor this better.
   if (DirName == CompilationDir)
     DirName = "";
 
-  unsigned SrcId = SourceIdMap.size()+1;
+  // FileIDCUMap stores the current ID for the given compile unit.
+  unsigned SrcId = FileIDCUMap[CUID] + 1;
 
-  // We look up the file/dir pair by concatenating them with a zero byte.
+  // We look up the CUID/file/dir by concatenating them with a zero byte.
   SmallString<128> NamePair;
+  NamePair += CUID;
+  NamePair += '\0';
   NamePair += DirName;
   NamePair += '\0'; // Zero bytes are not allowed in paths.
   NamePair += FileName;
@@ -638,8 +648,9 @@ unsigned DwarfDebug::getOrCreateSourceID(StringRef FileName,
   if (Ent.getValue() != SrcId)
     return Ent.getValue();
 
+  FileIDCUMap[CUID] = SrcId;
   // Print out a .file directive to specify files for .loc directives.
-  Asm->OutStreamer.EmitDwarfFileDirective(SrcId, DirName, FileName);
+  Asm->OutStreamer.EmitDwarfFileDirective(SrcId, DirName, FileName, CUID);
 
   return SrcId;
 }
@@ -650,14 +661,17 @@ CompileUnit *DwarfDebug::constructCompileUnit(const MDNode *N) {
   DICompileUnit DIUnit(N);
   StringRef FN = DIUnit.getFilename();
   CompilationDir = DIUnit.getDirectory();
-  // Call this to emit a .file directive if it wasn't emitted for the source
-  // file this CU comes from yet.
-  getOrCreateSourceID(FN, CompilationDir);
 
   DIE *Die = new DIE(dwarf::DW_TAG_compile_unit);
   CompileUnit *NewCU = new CompileUnit(GlobalCUIndexCount++,
                                        DIUnit.getLanguage(), Die, Asm,
                                        this, &InfoHolder);
+
+  FileIDCUMap[NewCU->getUniqueID()] = 0;
+  // Call this to emit a .file directive if it wasn't emitted for the source
+  // file this CU comes from yet.
+  getOrCreateSourceID(FN, CompilationDir, NewCU->getUniqueID());
+
   NewCU->addString(Die, dwarf::DW_AT_producer, DIUnit.getProducer());
   NewCU->addUInt(Die, dwarf::DW_AT_language, dwarf::DW_FORM_data2,
                  DIUnit.getLanguage());
@@ -1707,7 +1721,8 @@ void DwarfDebug::recordSourceLine(unsigned Line, unsigned Col, const MDNode *S,
     } else
       llvm_unreachable("Unexpected scope info");
 
-    Src = getOrCreateSourceID(Fn, Dir);
+    Src = getOrCreateSourceID(Fn, Dir,
+            Asm->OutStreamer.getContext().getDwarfCompileUnitID());
   }
   Asm->OutStreamer.EmitDwarfLocDirective(Src, Line, Col, Flags, 0, 0, Fn);
 }
diff --git a/lib/CodeGen/AsmPrinter/DwarfDebug.h b/lib/CodeGen/AsmPrinter/DwarfDebug.h
index 7b56815040..8cb30495aa 100644
--- a/lib/CodeGen/AsmPrinter/DwarfDebug.h
+++ b/lib/CodeGen/AsmPrinter/DwarfDebug.h
@@ -305,7 +305,9 @@ class DwarfDebug {
   // A list of all the unique abbreviations in use.
   std::vector<DIEAbbrev *> Abbreviations;
 
-  // Source id map, i.e. pair of source filename and directory,
+  // Stores the current file ID for a given compile unit.
+  DenseMap <unsigned, unsigned> FileIDCUMap;
+  // Source id map, i.e. CUID, source filename and directory,
   // separated by a zero byte, mapped to a unique id.
   StringMap<unsigned, BumpPtrAllocator&> SourceIdMap;
 
@@ -626,7 +628,8 @@ public:
   /// \brief Look up the source id with the given directory and source file
   /// names. If none currently exists, create a new id and insert it in the
   /// SourceIds map.
-  unsigned getOrCreateSourceID(StringRef DirName, StringRef FullName);
+  unsigned getOrCreateSourceID(StringRef DirName, StringRef FullName,
+                               unsigned CUID);
 
   /// \brief Recursively Emits a debug information entry.
   void emitDIE(DIE *Die, std::vector<DIEAbbrev *> *Abbrevs);
diff --git a/lib/MC/MCAsmStreamer.cpp b/lib/MC/MCAsmStreamer.cpp
index 7eb7202332..35613b411c 100644
--- a/lib/MC/MCAsmStreamer.cpp
+++ b/lib/MC/MCAsmStreamer.cpp
@@ -215,7 +215,7 @@ public:
 
   virtual void EmitFileDirective(StringRef Filename);
   virtual bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                      StringRef Filename);
+                                      StringRef Filename, unsigned CUID = 0);
   virtual void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                                      unsigned Column, unsigned Flags,
                                      unsigned Isa, unsigned Discriminator,
@@ -828,14 +828,14 @@ void MCAsmStreamer::EmitFileDirective(StringRef Filename) {
 }
 
 bool MCAsmStreamer::EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                           StringRef Filename) {
+                                           StringRef Filename, unsigned CUID) {
   if (!UseDwarfDirectory && !Directory.empty()) {
     if (sys::path::is_absolute(Filename))
-      return EmitDwarfFileDirective(FileNo, "", Filename);
+      return EmitDwarfFileDirective(FileNo, "", Filename, CUID);
 
     SmallString<128> FullPathName = Directory;
     sys::path::append(FullPathName, Filename);
-    return EmitDwarfFileDirective(FileNo, "", FullPathName);
+    return EmitDwarfFileDirective(FileNo, "", FullPathName, CUID);
   }
 
   if (UseLoc) {
@@ -846,8 +846,11 @@ bool MCAsmStreamer::EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
     }
     PrintQuotedString(Filename, OS);
     EmitEOL();
+    // All .file will belong to a single CUID.
+    CUID = 0;
   }
-  return this->MCStreamer::EmitDwarfFileDirective(FileNo, Directory, Filename);
+  return this->MCStreamer::EmitDwarfFileDirective(FileNo, Directory, Filename,
+                                                  CUID);
 }
 
 void MCAsmStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
diff --git a/lib/MC/MCContext.cpp b/lib/MC/MCContext.cpp
index 1a7df6041e..26d378e6c0 100644
--- a/lib/MC/MCContext.cpp
+++ b/lib/MC/MCContext.cpp
@@ -77,8 +77,8 @@ void MCContext::reset() {
   Symbols.clear();
   Allocator.Reset();
   Instances.clear();
-  MCDwarfFiles.clear();
-  MCDwarfDirs.clear();
+  MCDwarfFilesCUMap.clear();
+  MCDwarfDirsCUMap.clear();
   MCGenDwarfLabelEntries.clear();
   DwarfDebugFlags = StringRef();
   MCLineSections.clear();
@@ -299,11 +299,13 @@ const MCSection *MCContext::getCOFFSection(StringRef Section,
 /// error and zero is returned and the client reports the error, else the
 /// allocated file number is returned.  The file numbers may be in any order.
 unsigned MCContext::GetDwarfFile(StringRef Directory, StringRef FileName,
-                                 unsigned FileNumber) {
+                                 unsigned FileNumber, unsigned CUID) {
   // TODO: a FileNumber of zero says to use the next available file number.
   // Note: in GenericAsmParser::ParseDirectiveFile() FileNumber was checked
   // to not be less than one.  This needs to be change to be not less than zero.
 
+  std::vector<MCDwarfFile *>& MCDwarfFiles = MCDwarfFilesCUMap[CUID];
+  std::vector<StringRef>& MCDwarfDirs = MCDwarfDirsCUMap[CUID];
   // Make space for this FileNumber in the MCDwarfFiles vector if needed.
   if (FileNumber >= MCDwarfFiles.size()) {
     MCDwarfFiles.resize(FileNumber + 1);
@@ -363,7 +365,8 @@ unsigned MCContext::GetDwarfFile(StringRef Directory, StringRef FileName,
 
 /// isValidDwarfFileNumber - takes a dwarf file number and returns true if it
 /// currently is assigned and false otherwise.
-bool MCContext::isValidDwarfFileNumber(unsigned FileNumber) {
+bool MCContext::isValidDwarfFileNumber(unsigned FileNumber, unsigned CUID) {
+  std::vector<MCDwarfFile *>& MCDwarfFiles = MCDwarfFilesCUMap[CUID];
   if(FileNumber == 0 || FileNumber >= MCDwarfFiles.size())
     return false;
 
diff --git a/lib/MC/MCDwarf.cpp b/lib/MC/MCDwarf.cpp
index fea057af3e..c81abe952a 100644
--- a/lib/MC/MCDwarf.cpp
+++ b/lib/MC/MCDwarf.cpp
@@ -299,7 +299,7 @@ const MCSymbol *MCDwarfFileTable::EmitCU(MCStreamer *MCOS, unsigned CUID) {
 
   // First the directory table.
   const std::vector<StringRef> &MCDwarfDirs =
-    context.getMCDwarfDirs();
+    context.getMCDwarfDirs(CUID);
   for (unsigned i = 0; i < MCDwarfDirs.size(); i++) {
     MCOS->EmitBytes(MCDwarfDirs[i]); // the DirectoryName
     MCOS->EmitBytes(StringRef("\0", 1)); // the null term. of the string
@@ -308,7 +308,7 @@ const MCSymbol *MCDwarfFileTable::EmitCU(MCStreamer *MCOS, unsigned CUID) {
 
   // Second the file table.
   const std::vector<MCDwarfFile *> &MCDwarfFiles =
-    MCOS->getContext().getMCDwarfFiles();
+    MCOS->getContext().getMCDwarfFiles(CUID);
   for (unsigned i = 1; i < MCDwarfFiles.size(); i++) {
     MCOS->EmitBytes(MCDwarfFiles[i]->getName()); // FileName
     MCOS->EmitBytes(StringRef("\0", 1)); // the null term. of the string
diff --git a/lib/MC/MCNullStreamer.cpp b/lib/MC/MCNullStreamer.cpp
index 89f74c1709..c872b2203f 100644
--- a/lib/MC/MCNullStreamer.cpp
+++ b/lib/MC/MCNullStreamer.cpp
@@ -89,7 +89,7 @@ namespace {
 
     virtual void EmitFileDirective(StringRef Filename) {}
     virtual bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                        StringRef Filename) {
+                                        StringRef Filename, unsigned CUID = 0) {
       return false;
     }
     virtual void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
diff --git a/lib/MC/MCPureStreamer.cpp b/lib/MC/MCPureStreamer.cpp
index 573308abb8..0e04c5537a 100644
--- a/lib/MC/MCPureStreamer.cpp
+++ b/lib/MC/MCPureStreamer.cpp
@@ -95,7 +95,7 @@ public:
     report_fatal_error("unsupported directive in pure streamer");
   }
   virtual bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                      StringRef Filename) {
+                                      StringRef Filename, unsigned CUID = 0) {
     report_fatal_error("unsupported directive in pure streamer");
   }
 
diff --git a/lib/MC/MCStreamer.cpp b/lib/MC/MCStreamer.cpp
index 9857f7bb08..51ef415542 100644
--- a/lib/MC/MCStreamer.cpp
+++ b/lib/MC/MCStreamer.cpp
@@ -157,8 +157,8 @@ void MCStreamer::EmitFill(uint64_t NumBytes, uint8_t FillValue,
 
 bool MCStreamer::EmitDwarfFileDirective(unsigned FileNo,
                                         StringRef Directory,
-                                        StringRef Filename) {
-  return getContext().GetDwarfFile(Directory, Filename, FileNo) == 0;
+                                        StringRef Filename, unsigned CUID) {
+  return getContext().GetDwarfFile(Directory, Filename, FileNo, CUID) == 0;
 }
 
 void MCStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
diff --git a/test/DebugInfo/X86/stmt-list-multiple-compile-units.ll b/test/DebugInfo/X86/stmt-list-multiple-compile-units.ll
index 601d08f114..814f86c335 100644
--- a/test/DebugInfo/X86/stmt-list-multiple-compile-units.ll
+++ b/test/DebugInfo/X86/stmt-list-multiple-compile-units.ll
@@ -9,13 +9,16 @@
 
 ; CHECK: DW_TAG_compile_unit
 ; CHECK: DW_AT_low_pc [DW_FORM_addr]       (0x0000000000000000)
-; CHECK: DW_AT_stmt_list [DW_FORM_data4]   (0x00000049)
+; CHECK: DW_AT_stmt_list [DW_FORM_data4]   (0x0000003c)
 
 ; CHECK: .debug_line contents:
 ; CHECK-NEXT: Line table prologue:
-; CHECK-NEXT: total_length: 0x00000045
+; CHECK-NEXT: total_length: 0x00000038
+; CHECK: file_names[  1]    0 0x00000000 0x00000000 simple.c
 ; CHECK: Line table prologue:
-; CHECK: total_length: 0x00000047
+; CHECK-NEXT: total_length: 0x00000039
+; CHECK: file_names[  1]    0 0x00000000 0x00000000 simple2.c
+; CHECK-NOT: file_names
 
 define i32 @test(i32 %a) nounwind uwtable ssp {
 entry: