[DebugInfo] Support DWARF v5 source code embedding extension

In DWARF v5 the Line Number Program Header is extensible, allowing values with
new content types. In this extension a content type is added,
DW_LNCT_LLVM_source, which contains the embedded source code of the file.

Add new optional attribute for !DIFile IR metadata called source which contains
source text. Use this to output the source to the DWARF line table of code
objects. Analogously extend METADATA_FILE in Bitcode and .file directive in ASM
to support optional source.

Teach llvm-dwarfdump and llvm-objdump about the new values. Update the output
format of llvm-dwarfdump to make room for the new attribute on file_names
entries, and support embedded sources for the -source option in llvm-objdump.

Differential Revision: https://reviews.llvm.org/D42765

llvm-svn: 325970

5 files changed, 92 insertions, 31 deletions

diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index 7ea5b7677b8..f254cb50b60 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -7,6 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringExtras.h"
@@ -215,6 +216,7 @@ public:
                                                StringRef Directory,
                                                StringRef Filename,
                                                MD5::MD5Result *Checksum = 0,
+                                               Optional<StringRef> Source = None,
                                                unsigned CUID = 0) override;
   void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                              unsigned Column, unsigned Flags,
@@ -1076,13 +1078,13 @@ void MCAsmStreamer::EmitFileDirective(StringRef Filename) {
 
 Expected<unsigned> MCAsmStreamer::tryEmitDwarfFileDirective(
     unsigned FileNo, StringRef Directory, StringRef Filename,
-    MD5::MD5Result *Checksum, unsigned CUID) {
+    MD5::MD5Result *Checksum, Optional<StringRef> Source, unsigned CUID) {
   assert(CUID == 0);
 
   MCDwarfLineTable &Table = getContext().getMCDwarfLineTable(CUID);
   unsigned NumFiles = Table.getMCDwarfFiles().size();
   Expected<unsigned> FileNoOrErr =
-      Table.tryGetFile(Directory, Filename, Checksum, FileNo);
+      Table.tryGetFile(Directory, Filename, Checksum, Source, FileNo);
   if (!FileNoOrErr)
     return FileNoOrErr.takeError();
   FileNo = FileNoOrErr.get();
@@ -1114,6 +1116,10 @@ Expected<unsigned> MCAsmStreamer::tryEmitDwarfFileDirective(
     OS1 << " md5 ";
     PrintQuotedString(Checksum->digest(), OS1);
   }
+  if (Source) {
+    OS1 << " source ";
+    PrintQuotedString(*Source, OS1);
+  }
   if (MCTargetStreamer *TS = getTargetStreamer()) {
     TS->emitDwarfFileDirective(OS1.str());
   } else {
diff --git a/llvm/lib/MC/MCContext.cpp b/llvm/lib/MC/MCContext.cpp
index ea995288b28..69c10f535e5 100644
--- a/llvm/lib/MC/MCContext.cpp
+++ b/llvm/lib/MC/MCContext.cpp
@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCContext.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringMap.h"
@@ -532,7 +533,7 @@ MCSubtargetInfo &MCContext::getSubtargetCopy(const MCSubtargetInfo &STI) {
 // Dwarf Management
 //===----------------------------------------------------------------------===//
 
-/// getDwarfFile - takes a file name an number to place in the dwarf file and
+/// getDwarfFile - takes a file name and number to place in the dwarf file and
 /// directory tables.  If the file number has already been allocated it is an
 /// 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.
@@ -540,9 +541,10 @@ Expected<unsigned> MCContext::getDwarfFile(StringRef Directory,
                                            StringRef FileName,
                                            unsigned FileNumber,
                                            MD5::MD5Result *Checksum,
+                                           Optional<StringRef> Source,
                                            unsigned CUID) {
   MCDwarfLineTable &Table = MCDwarfLineTablesCUMap[CUID];
-  return Table.tryGetFile(Directory, FileName, Checksum, FileNumber);
+  return Table.tryGetFile(Directory, FileName, Checksum, Source, FileNumber);
 }
 
 /// isValidDwarfFileNumber - takes a dwarf file number and returns true if it
diff --git a/llvm/lib/MC/MCDwarf.cpp b/llvm/lib/MC/MCDwarf.cpp
index 1f0fa78bffc..685b46a606d 100644
--- a/llvm/lib/MC/MCDwarf.cpp
+++ b/llvm/lib/MC/MCDwarf.cpp
@@ -11,7 +11,7 @@
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Hashing.h"
-#include "llvm/ADT/None.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/SmallVector.h"
@@ -373,8 +373,13 @@ void MCDwarfLineTableHeader::emitV5FileDirTables(
 
   // The file format, which is the inline null-terminated filename and a
   // directory index.  We don't track file size/timestamp so don't emit them
-  // in the v5 table.  Emit MD5 checksums if we have them.
-  MCOS->EmitIntValue(HasMD5 ? 3 : 2, 1);
+  // in the v5 table.  Emit MD5 checksums and source if we have them.
+  uint64_t Entries = 2;
+  if (HasMD5)
+    Entries += 1;
+  if (HasSource)
+    Entries += 1;
+  MCOS->EmitIntValue(Entries, 1);
   MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_path);
   MCOS->EmitULEB128IntValue(LineStr ? dwarf::DW_FORM_line_strp
                                     : dwarf::DW_FORM_string);
@@ -384,6 +389,11 @@ void MCDwarfLineTableHeader::emitV5FileDirTables(
     MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_MD5);
     MCOS->EmitULEB128IntValue(dwarf::DW_FORM_data16);
   }
+  if (HasSource) {
+    MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_LLVM_source);
+    MCOS->EmitULEB128IntValue(LineStr ? dwarf::DW_FORM_line_strp
+                                      : dwarf::DW_FORM_string);
+  }
   // Then the list of file names. These start at 1.
   MCOS->EmitULEB128IntValue(MCDwarfFiles.size() - 1);
   for (unsigned i = 1; i < MCDwarfFiles.size(); ++i) {
@@ -401,6 +411,15 @@ void MCDwarfLineTableHeader::emitV5FileDirTables(
           StringRef(reinterpret_cast<const char *>(Cksum->Bytes.data()),
                     Cksum->Bytes.size()));
     }
+    if (HasSource) {
+      if (LineStr)
+        LineStr->emitRef(MCOS, MCDwarfFiles[i].Source.getValueOr(StringRef()));
+      else {
+        MCOS->EmitBytes(
+            MCDwarfFiles[i].Source.getValueOr(StringRef())); // Source and...
+        MCOS->EmitBytes(StringRef("\0", 1)); // its null terminator.
+      }
+    }
   }
 }
 
@@ -500,14 +519,17 @@ void MCDwarfLineTable::EmitCU(MCObjectStreamer *MCOS,
 Expected<unsigned> MCDwarfLineTable::tryGetFile(StringRef &Directory,
                                                 StringRef &FileName,
                                                 MD5::MD5Result *Checksum,
+                                                Optional<StringRef> Source,
                                                 unsigned FileNumber) {
-  return Header.tryGetFile(Directory, FileName, Checksum, FileNumber);
+  return Header.tryGetFile(Directory, FileName, Checksum, Source, FileNumber);
 }
 
-Expected<unsigned> MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
-                                                      StringRef &FileName,
-                                                      MD5::MD5Result *Checksum,
-                                                      unsigned FileNumber) {
+Expected<unsigned>
+MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
+                                   StringRef &FileName,
+                                   MD5::MD5Result *Checksum,
+                                   Optional<StringRef> &Source,
+                                   unsigned FileNumber) {
   if (Directory == CompilationDir)
     Directory = "";
   if (FileName.empty()) {
@@ -515,9 +537,11 @@ Expected<unsigned> MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
     Directory = "";
   }
   assert(!FileName.empty());
-  // If any files have an MD5 checksum, they all must.
-  if (MCDwarfFiles.empty())
+  // If any files have an MD5 checksum or embedded source, they all must.
+  if (MCDwarfFiles.empty()) {
     HasMD5 = (Checksum != nullptr);
+    HasSource = (Source != None);
+  }
   if (FileNumber == 0) {
     // File numbers start with 1 and/or after any file numbers
     // allocated by inline-assembler .file directives.
@@ -545,6 +569,10 @@ Expected<unsigned> MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
   if (HasMD5 != (Checksum != nullptr))
     return make_error<StringError>("inconsistent use of MD5 checksums",
                                    inconvertibleErrorCode());
+  // If any files have embedded source, they all must.
+  if (HasSource != (Source != None))
+    return make_error<StringError>("inconsistent use of embedded source",
+                                   inconvertibleErrorCode());
 
   if (Directory.empty()) {
     // Separate the directory part from the basename of the FileName.
@@ -582,6 +610,9 @@ Expected<unsigned> MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
   File.Checksum = Checksum;
   if (Checksum)
     HasMD5 = true;
+  File.Source = Source;
+  if (Source)
+    HasSource = true;
 
   // return the allocated FileNumber.
   return FileNumber;
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 8ede318e0e1..76eef5e3725 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -3250,7 +3250,7 @@ bool AsmParser::parseDirectiveAlign(bool IsPow2, unsigned ValueSize) {
 
 /// parseDirectiveFile
 /// ::= .file filename
-/// ::= .file number [directory] filename [md5 checksum]
+/// ::= .file number [directory] filename [md5 checksum] [source source-text]
 bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
   // FIXME: I'm not sure what this is.
   int64_t FileNumber = -1;
@@ -3286,23 +3286,36 @@ bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
   }
 
   std::string Checksum;
-  if (!parseOptionalToken(AsmToken::EndOfStatement)) {
+
+  Optional<StringRef> Source;
+  bool HasSource = false;
+  std::string SourceString;
+
+  while (!parseOptionalToken(AsmToken::EndOfStatement)) {
     StringRef Keyword;
     if (check(getTok().isNot(AsmToken::Identifier),
               "unexpected token in '.file' directive") ||
-        parseIdentifier(Keyword) ||
-        check(Keyword != "md5", "unexpected token in '.file' directive"))
-      return true;
-    if (getLexer().is(AsmToken::String) &&
-        check(FileNumber == -1, "MD5 checksum specified, but no file number"))
-      return true;
-    if (check(getTok().isNot(AsmToken::String),
-              "unexpected token in '.file' directive") ||
-        parseEscapedString(Checksum) ||
-        check(Checksum.size() != 32, "invalid MD5 checksum specified") ||
-        parseToken(AsmToken::EndOfStatement,
-                   "unexpected token in '.file' directive"))
+        parseIdentifier(Keyword))
       return true;
+    if (Keyword == "md5") {
+      if (check(FileNumber == -1,
+                "MD5 checksum specified, but no file number") ||
+          check(getTok().isNot(AsmToken::String),
+                "unexpected token in '.file' directive") ||
+          parseEscapedString(Checksum) ||
+          check(Checksum.size() != 32, "invalid MD5 checksum specified"))
+        return true;
+    } else if (Keyword == "source") {
+      HasSource = true;
+      if (check(FileNumber == -1,
+                "source specified, but no file number") ||
+          check(getTok().isNot(AsmToken::String),
+                "unexpected token in '.file' directive") ||
+          parseEscapedString(SourceString))
+        return true;
+    } else {
+      return TokError("unexpected token in '.file' directive");
+    }
   }
 
   if (FileNumber == -1)
@@ -3316,13 +3329,18 @@ bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
       CKMem = (MD5::MD5Result *)Ctx.allocate(sizeof(MD5::MD5Result), 1);
       memcpy(&CKMem->Bytes, Checksum.data(), 16);
     }
+    if (HasSource) {
+      char *SourceBuf = static_cast<char *>(Ctx.allocate(SourceString.size()));
+      memcpy(SourceBuf, SourceString.data(), SourceString.size());
+      Source = StringRef(SourceBuf, SourceString.size());
+    }
     // If there is -g option as well as debug info from directive file,
     // we turn off -g option, directly use the existing debug info instead.
     if (getContext().getGenDwarfForAssembly())
       getContext().setGenDwarfForAssembly(false);
     else {
       Expected<unsigned> FileNumOrErr = getStreamer().tryEmitDwarfFileDirective(
-          FileNumber, Directory, Filename, CKMem);
+          FileNumber, Directory, Filename, CKMem, Source);
       if (!FileNumOrErr)
         return Error(DirectiveLoc, toString(FileNumOrErr.takeError()));
       FileNumber = FileNumOrErr.get();
diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
index ab6fd9c7bb0..bf27a0abfda 100644
--- a/llvm/lib/MC/MCStreamer.cpp
+++ b/llvm/lib/MC/MCStreamer.cpp
@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/MC/MCStreamer.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Twine.h"
@@ -191,8 +192,11 @@ void MCStreamer::EmitZeros(uint64_t NumBytes) {
 Expected<unsigned>
 MCStreamer::tryEmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
                                       StringRef Filename,
-                                      MD5::MD5Result *Checksum, unsigned CUID) {
-  return getContext().getDwarfFile(Directory, Filename, FileNo, Checksum, CUID);
+                                      MD5::MD5Result *Checksum,
+                                      Optional<StringRef> Source,
+                                      unsigned CUID) {
+  return getContext().getDwarfFile(Directory, Filename, FileNo, Checksum,
+                                   Source, CUID);
 }
 
 void MCStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,