[DWARFv5] MC support for MD5 file checksums

Extend .file directive syntax to allow specifying an MD5 checksum for
the source file.  Emit the checksums in DWARF v5 line tables.

llvm-svn: 322134

5 files changed, 68 insertions, 19 deletions

diff --git a/llvm/lib/MC/MCAsmStreamer.cpp b/llvm/lib/MC/MCAsmStreamer.cpp
index b82dcbdc0f7..94af2881af7 100644
--- a/llvm/lib/MC/MCAsmStreamer.cpp
+++ b/llvm/lib/MC/MCAsmStreamer.cpp
@@ -212,6 +212,7 @@ public:
   void EmitFileDirective(StringRef Filename) override;
   unsigned EmitDwarfFileDirective(unsigned FileNo, StringRef Directory,
                                   StringRef Filename,
+                                  MD5::MD5Result *Checksum = 0,
                                   unsigned CUID = 0) override;
   void EmitDwarfLocDirective(unsigned FileNo, unsigned Line,
                              unsigned Column, unsigned Flags,
@@ -1068,12 +1069,13 @@ void MCAsmStreamer::EmitFileDirective(StringRef Filename) {
 unsigned MCAsmStreamer::EmitDwarfFileDirective(unsigned FileNo,
                                                StringRef Directory,
                                                StringRef Filename,
+                                               MD5::MD5Result *Checksum,
                                                unsigned CUID) {
   assert(CUID == 0);
 
   MCDwarfLineTable &Table = getContext().getMCDwarfLineTable(CUID);
   unsigned NumFiles = Table.getMCDwarfFiles().size();
-  FileNo = Table.getFile(Directory, Filename, FileNo);
+  FileNo = Table.getFile(Directory, Filename, Checksum, FileNo);
   if (FileNo == 0)
     return 0;
   if (NumFiles == Table.getMCDwarfFiles().size())
diff --git a/llvm/lib/MC/MCContext.cpp b/llvm/lib/MC/MCContext.cpp
index 5c25e902bbe..ac2e45484ed 100644
--- a/llvm/lib/MC/MCContext.cpp
+++ b/llvm/lib/MC/MCContext.cpp
@@ -535,9 +535,10 @@ MCSubtargetInfo &MCContext::getSubtargetCopy(const MCSubtargetInfo &STI) {
 /// 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 CUID) {
+                                 unsigned FileNumber, MD5::MD5Result *Checksum,
+                                 unsigned CUID) {
   MCDwarfLineTable &Table = MCDwarfLineTablesCUMap[CUID];
-  return Table.getFile(Directory, FileName, FileNumber);
+  return Table.getFile(Directory, FileName, Checksum, 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 9e5d9ff73c7..62af6d851bf 100644
--- a/llvm/lib/MC/MCDwarf.cpp
+++ b/llvm/lib/MC/MCDwarf.cpp
@@ -284,7 +284,7 @@ static void
 emitV5FileDirTables(MCStreamer *MCOS,
                     const SmallVectorImpl<std::string> &MCDwarfDirs,
                     const SmallVectorImpl<MCDwarfFile> &MCDwarfFiles,
-                    StringRef CompilationDir) {
+                    StringRef CompilationDir, bool HasMD5) {
   // The directory format, which is just inline null-terminated strings.
   MCOS->EmitIntValue(1, 1);
   MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_path);
@@ -300,20 +300,29 @@ emitV5FileDirTables(MCStreamer *MCOS,
 
   // 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.
-  // FIXME: Arrange to emit MD5 signatures for the source files.
-  MCOS->EmitIntValue(2, 1);
+  // in the v5 table.  Emit MD5 checksums if we have them.
+  MCOS->EmitIntValue(HasMD5 ? 3 : 2, 1);
   MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_path);
   MCOS->EmitULEB128IntValue(dwarf::DW_FORM_string);
   MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_directory_index);
   MCOS->EmitULEB128IntValue(dwarf::DW_FORM_udata);
-  // Then the list of file names. These start at 1 for some reason.
+  if (HasMD5) {
+    MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_MD5);
+    MCOS->EmitULEB128IntValue(dwarf::DW_FORM_data16);
+  }
+  // Then the list of file names. These start at 1.
   MCOS->EmitULEB128IntValue(MCDwarfFiles.size() - 1);
   for (unsigned i = 1; i < MCDwarfFiles.size(); ++i) {
     assert(!MCDwarfFiles[i].Name.empty());
     MCOS->EmitBytes(MCDwarfFiles[i].Name); // FileName and...
     MCOS->EmitBytes(StringRef("\0", 1));   // its null terminator.
     MCOS->EmitULEB128IntValue(MCDwarfFiles[i].DirIndex); // Directory number.
+    if (HasMD5) {
+      MD5::MD5Result *Cksum = MCDwarfFiles[i].Checksum;
+      MCOS->EmitBinaryData(
+          StringRef(reinterpret_cast<const char *>(Cksum->Bytes.data()),
+                    Cksum->Bytes.size()));
+    }
   }
 }
 
@@ -384,7 +393,8 @@ MCDwarfLineTableHeader::Emit(MCStreamer *MCOS, MCDwarfLineTableParams Params,
   // Put out the directory and file tables.  The formats vary depending on
   // the version.
   if (LineTableVersion >= 5)
-    emitV5FileDirTables(MCOS, MCDwarfDirs, MCDwarfFiles, CompilationDir);
+    emitV5FileDirTables(MCOS, MCDwarfDirs, MCDwarfFiles, CompilationDir,
+                        HasMD5);
   else
     emitV2FileDirTables(MCOS, MCDwarfDirs, MCDwarfFiles);
 
@@ -409,12 +419,14 @@ void MCDwarfLineTable::EmitCU(MCObjectStreamer *MCOS,
 }
 
 unsigned MCDwarfLineTable::getFile(StringRef &Directory, StringRef &FileName,
+                                   MD5::MD5Result *Checksum,
                                    unsigned FileNumber) {
-  return Header.getFile(Directory, FileName, FileNumber);
+  return Header.getFile(Directory, FileName, Checksum, FileNumber);
 }
 
 unsigned MCDwarfLineTableHeader::getFile(StringRef &Directory,
                                          StringRef &FileName,
+                                         MD5::MD5Result *Checksum,
                                          unsigned FileNumber) {
   if (Directory == CompilationDir)
     Directory = "";
@@ -445,6 +457,10 @@ unsigned MCDwarfLineTableHeader::getFile(StringRef &Directory,
   if (!File.Name.empty())
     return 0;
 
+  // If any files have an MD5 checksum, they all must.
+  if (FileNumber > 1)
+    assert(HasMD5 == (Checksum != nullptr));
+
   if (Directory.empty()) {
     // Separate the directory part from the basename of the FileName.
     StringRef tFileName = sys::path::filename(FileName);
@@ -478,6 +494,9 @@ unsigned MCDwarfLineTableHeader::getFile(StringRef &Directory,
 
   File.Name = FileName;
   File.DirIndex = DirIndex;
+  File.Checksum = Checksum;
+  if (Checksum)
+    HasMD5 = true;
 
   // return the allocated FileNumber.
   return FileNumber;
diff --git a/llvm/lib/MC/MCParser/AsmParser.cpp b/llvm/lib/MC/MCParser/AsmParser.cpp
index 2259136c6ec..17ad4e561e3 100644
--- a/llvm/lib/MC/MCParser/AsmParser.cpp
+++ b/llvm/lib/MC/MCParser/AsmParser.cpp
@@ -50,6 +50,7 @@
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/MD5.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/SMLoc.h"
@@ -3294,8 +3295,8 @@ bool AsmParser::parseDirectiveAlign(bool IsPow2, unsigned ValueSize) {
 }
 
 /// parseDirectiveFile
-/// ::= .file [number] filename
-/// ::= .file number directory filename
+/// ::= .file filename
+/// ::= .file number [directory] filename [md5 checksum]
 bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
   // FIXME: I'm not sure what this is.
   int64_t FileNumber = -1;
@@ -3331,19 +3332,43 @@ bool AsmParser::parseDirectiveFile(SMLoc DirectiveLoc) {
     Filename = Path;
   }
 
-  if (parseToken(AsmToken::EndOfStatement,
-                 "unexpected token in '.file' directive"))
-    return true;
+  std::string Checksum;
+  if (!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"))
+      return true;
+  }
 
   if (FileNumber == -1)
     getStreamer().EmitFileDirective(Filename);
   else {
+    MD5::MD5Result *CKMem = nullptr;
+    if (!Checksum.empty()) {
+      Checksum = fromHex(Checksum);
+      if (check(Checksum.size() != 16, "invalid MD5 checksum specified"))
+        return true;
+      CKMem = (MD5::MD5Result *)Ctx.allocate(sizeof(MD5::MD5Result), 1);
+      memcpy(&CKMem->Bytes, Checksum.data(), 16);
+    }
     // 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 if (getStreamer().EmitDwarfFileDirective(FileNumber, Directory, Filename) ==
-        0)
+    else if (getStreamer().EmitDwarfFileDirective(FileNumber, Directory,
+                                                  Filename, CKMem) == 0)
       return Error(FileNumberLoc, "file number already allocated");
   }
 
diff --git a/llvm/lib/MC/MCStreamer.cpp b/llvm/lib/MC/MCStreamer.cpp
index af1fc5277db..a6784273aab 100644
--- a/llvm/lib/MC/MCStreamer.cpp
+++ b/llvm/lib/MC/MCStreamer.cpp
@@ -194,8 +194,10 @@ void MCStreamer::EmitZeros(uint64_t NumBytes) {
 
 unsigned MCStreamer::EmitDwarfFileDirective(unsigned FileNo,
                                             StringRef Directory,
-                                            StringRef Filename, unsigned CUID) {
-  return getContext().getDwarfFile(Directory, Filename, FileNo, CUID);
+                                            StringRef Filename,
+                                            MD5::MD5Result *Checksum,
+                                            unsigned CUID) {
+  return getContext().getDwarfFile(Directory, Filename, FileNo, Checksum, CUID);
 }
 
 void MCStreamer::EmitDwarfLocDirective(unsigned FileNo, unsigned Line,