DebugInfo: Improve reuse of file table entries in asm debug info

The previous deduping strategy was woefully inadequate - it only
considered the most recent file used and avoided emitting a duplicate in
that case - never considering the a/b/a scenario.

It was also lacking when it came to directory paths as the previous
filename would never match the current if the filename had been split
into file and directory components.

This change builds caching functionality into the line table at the
lowest level in an optional form (a file number of 0 indicates that one
should be chosen and returned) and will eventually be reused by the
normal source level debugging DWARF emission.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204027 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 34 insertions, 24 deletions

diff --git a/lib/MC/MCAsmStreamer.cpp b/lib/MC/MCAsmStreamer.cpp
index 75db7a96bb..b40305d0fc 100644
--- a/lib/MC/MCAsmStreamer.cpp
+++ b/lib/MC/MCAsmStreamer.cpp
@@ -197,8 +197,9 @@ public:
                          unsigned char Value = 0) override;
 
   void EmitFileDirective(StringRef Filename) override;
-  bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                              StringRef Filename, unsigned CUID = 0) override;
+  unsigned EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
+                                  StringRef Filename,
+                                  unsigned CUID = 0) override;
   void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                              unsigned Column, unsigned Flags,
                              unsigned Isa, unsigned Discriminator,
@@ -843,8 +844,10 @@ void MCAsmStreamer::EmitFileDirective(StringRef Filename) {
   EmitEOL();
 }
 
-bool MCAsmStreamer::EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                           StringRef Filename, unsigned CUID) {
+unsigned MCAsmStreamer::EmitDwarfFileDirective(unsigned FileNo,
+                                               StringRef Directory,
+                                               StringRef Filename,
+                                               unsigned CUID) {
   if (!UseDwarfDirectory && !Directory.empty()) {
     if (sys::path::is_absolute(Filename))
       return EmitDwarfFileDirective(FileNo, "", Filename, CUID);
diff --git a/lib/MC/MCDwarf.cpp b/lib/MC/MCDwarf.cpp
index 181e73dd43..72ecfa6cb4 100644
--- a/lib/MC/MCDwarf.cpp
+++ b/lib/MC/MCDwarf.cpp
@@ -336,7 +336,18 @@ unsigned MCDwarfLineTable::getFile(StringRef Directory, StringRef FileName,
   return Header.getFile(Directory, FileName, FileNumber);
 }
 
-unsigned MCDwarfLineTableHeader::getFile(StringRef Directory, StringRef FileName, unsigned FileNumber) {
+unsigned MCDwarfLineTableHeader::getFile(StringRef Directory,
+                                         StringRef FileName,
+                                         unsigned FileNumber) {
+  if (FileNumber == 0) {
+    FileNumber = SourceIdMap.size() + 1;
+    assert((MCDwarfFiles.empty() || FileNumber == MCDwarfFiles.size()) &&
+           "Don't mix autonumbered and explicit numbered line table usage");
+    StringMapEntry<unsigned> &Ent = SourceIdMap.GetOrCreateValue(
+        (Directory + Twine('\0') + FileName).str(), FileNumber);
+    if (Ent.getValue() != FileNumber)
+      return Ent.getValue();
+  }
   // Make space for this FileNumber in the MCDwarfFiles vector if needed.
   MCDwarfFiles.resize(FileNumber + 1);
 
diff --git a/lib/MC/MCNullStreamer.cpp b/lib/MC/MCNullStreamer.cpp
index 181000b249..894eada57d 100644
--- a/lib/MC/MCNullStreamer.cpp
+++ b/lib/MC/MCNullStreamer.cpp
@@ -85,10 +85,10 @@ namespace {
                            unsigned char Value = 0) override { return false; }
 
     void EmitFileDirective(StringRef Filename) override {}
-    bool EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
-                                StringRef Filename,
-                                unsigned CUID = 0) override {
-      return false;
+    unsigned EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
+                                    StringRef Filename,
+                                    unsigned CUID = 0) override {
+      return 0;
     }
     void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                                unsigned Column, unsigned Flags,
diff --git a/lib/MC/MCParser/AsmParser.cpp b/lib/MC/MCParser/AsmParser.cpp
index f3cf8f2d1c..fbbd4365bc 100644
--- a/lib/MC/MCParser/AsmParser.cpp
+++ b/lib/MC/MCParser/AsmParser.cpp
@@ -640,9 +640,8 @@ bool AsmParser::Run(bool NoInitialTextSection, bool NoFinalize) {
     MCSymbol *SectionStartSym = getContext().CreateTempSymbol();
     getStreamer().EmitLabel(SectionStartSym);
     getContext().setGenDwarfSectionStartSym(SectionStartSym);
-    getStreamer().EmitDwarfFileDirective(getContext().nextGenDwarfFileNumber(),
-                                         StringRef(),
-                                         getContext().getMainFileName());
+    getContext().setGenDwarfFileNumber(getStreamer().EmitDwarfFileDirective(
+        0, StringRef(), getContext().getMainFileName()));
   }
 
   // While we have input, parse each statement.
@@ -1589,14 +1588,10 @@ bool AsmParser::parseStatement(ParseStatementInfo &Info) {
     // If we previously parsed a cpp hash file line comment then make sure the
     // current Dwarf File is for the CppHashFilename if not then emit the
     // Dwarf File table for it and adjust the line number for the .loc.
-    const SmallVectorImpl<MCDwarfFile> &MCDwarfFiles =
-        getContext().getMCDwarfFiles();
     if (CppHashFilename.size() != 0) {
-      if (MCDwarfFiles[getContext().getGenDwarfFileNumber()].Name !=
-          CppHashFilename)
-        getStreamer().EmitDwarfFileDirective(
-            getContext().nextGenDwarfFileNumber(), StringRef(),
-            CppHashFilename);
+      unsigned FileNumber = getStreamer().EmitDwarfFileDirective(
+          0, StringRef(), CppHashFilename);
+      getContext().setGenDwarfFileNumber(FileNumber);
 
       // Since SrcMgr.FindLineNumber() is slow and messes up the SourceMgr's
       // cache with the different Loc from the call above we save the last
@@ -2762,7 +2757,8 @@ bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
             "input can't have .file dwarf directives when -g is "
             "used to generate dwarf debug info for assembly code");
 
-    if (getStreamer().EmitDwarfFileDirective(FileNumber, Directory, Filename))
+    if (getStreamer().EmitDwarfFileDirective(FileNumber, Directory, Filename) ==
+        0)
       Error(FileNumberLoc, "file number already allocated");
   }
 
diff --git a/lib/MC/MCStreamer.cpp b/lib/MC/MCStreamer.cpp
index 0837389581..ec3b5f9be4 100644
--- a/lib/MC/MCStreamer.cpp
+++ b/lib/MC/MCStreamer.cpp
@@ -174,10 +174,10 @@ void MCStreamer::EmitZeros(uint64_t NumBytes) {
   EmitFill(NumBytes, 0);
 }
 
-bool MCStreamer::EmitDwarfFileDirective(unsigned FileNo,
-                                        StringRef Directory,
-                                        StringRef Filename, unsigned CUID) {
-  return getContext().GetDwarfFile(Directory, Filename, FileNo, CUID) == 0;
+unsigned MCStreamer::EmitDwarfFileDirective(unsigned FileNo,
+                                            StringRef Directory,
+                                            StringRef Filename, unsigned CUID) {
+  return getContext().GetDwarfFile(Directory, Filename, FileNo, CUID);
 }
 
 void MCStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,