[DWARFv5] Emit v5 line-table header

[probinson]

Summary

Note this depends on D38002.

[aprantl]

llvm/lib/MC/MCDwarf.cpp

266

For consistency with the comments below, perhaps turn this into a sentence?
// The DirectoryName.

297

for (auto Dir : MCDwarfDirs) ?

[aprantl]

llvm/lib/MC/MCDwarf.cpp

265

also a range-based for loop?

[probinson]

Range-base for loops; tidy up commentary.

[probinson]

Yeah, I copy-pasted the old code and then hacked on it for the v5 format. I should have looked at it all as new code.

I need to wait for Katya to get back and commit D38002 then I can commit this.
Thanks!

llvm/lib/MC/MCDwarf.cpp

static const MCExpr *forceExpAbs(MCStreamer &OS, const MCExpr* Expr) {
   return MCSymbolRefExpr::create(ABS, Context);
 }
 
 static void emitAbsValue(MCStreamer &OS, const MCExpr *Value, unsigned Size) {
   const MCExpr *ABS = forceExpAbs(OS, Value);
   OS.EmitValue(ABS, Size);
 }
 
+static void
+emitV2FileDirTables(MCStreamer *MCOS,
+                    const SmallVectorImpl<std::string> &MCDwarfDirs,
+                    const SmallVectorImpl<MCDwarfFile> &MCDwarfFiles) {
+  // First the directory table.
+  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
+  }
+  MCOS->EmitIntValue(0, 1); // Terminate the directory list
+
+  // Second the file table.
+  for (unsigned i = 1; i < MCDwarfFiles.size(); i++) {
+    assert(!MCDwarfFiles[i].Name.empty());
+    MCOS->EmitBytes(MCDwarfFiles[i].Name); // FileName
+    MCOS->EmitBytes(StringRef("\0", 1));   // the null term. of the string
+    // the Directory num
+    MCOS->EmitULEB128IntValue(MCDwarfFiles[i].DirIndex);
+    MCOS->EmitIntValue(0, 1); // last modification timestamp (always 0)
+    MCOS->EmitIntValue(0, 1); // filesize (always 0)
+  }
+  MCOS->EmitIntValue(0, 1); // Terminate the file list
+}
+
+static void
+emitV5FileDirTables(MCStreamer *MCOS,
+                    const SmallVectorImpl<std::string> &MCDwarfDirs,
+                    const SmallVectorImpl<MCDwarfFile> &MCDwarfFiles,
+                    StringRef CompilationDir) {
+  // The directory format, which is just inline null-terminated strings.
+  MCOS->EmitIntValue(1, 1);
+  MCOS->EmitULEB128IntValue(dwarf::DW_LNCT_path);
+  MCOS->EmitULEB128IntValue(dwarf::DW_FORM_string);
+  // Then the list of directory paths.  CompilationDir comes first.
+  MCOS->EmitULEB128IntValue(MCDwarfDirs.size() + 1);
+  MCOS->EmitBytes(CompilationDir);
+  MCOS->EmitBytes(StringRef("\0", 1));
+  for (unsigned i = 0; i < MCDwarfDirs.size(); ++i) {
+    MCOS->EmitBytes(MCDwarfDirs[i]);
+    MCOS->EmitBytes(StringRef("\0", 1));
+  }
+
+  // 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);
+  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.
+  MCOS->EmitULEB128IntValue(MCDwarfFiles.size() - 1);
+  for (unsigned i = 1; i < MCDwarfFiles.size(); ++i) {
+    MCOS->EmitBytes(MCDwarfFiles[i].Name);
+    MCOS->EmitBytes(StringRef("\0", 1));
+    MCOS->EmitULEB128IntValue(MCDwarfFiles[i].DirIndex);
+  }
+}
+
 std::pair<MCSymbol *, MCSymbol *>
 MCDwarfLineTableHeader::Emit(MCStreamer *MCOS, MCDwarfLineTableParams Params,
                              ArrayRef<char> StandardOpcodeLengths) const {
   MCContext &context = MCOS->getContext();
 
   // Create a symbol at the beginning of the line table.
   MCSymbol *LineStartSym = Label;
   if (!LineStartSym)
     LineStartSym = context.createTempSymbol();
   // Set the value of the symbol, as we are at the start of the line table.
   MCOS->EmitLabel(LineStartSym);
 
   // Create a symbol for the end of the section (to be set when we get there).
   MCSymbol *LineEndSym = context.createTempSymbol();
 
   // The first 4 bytes is the total length of the information for this
   // compilation unit (not including these 4 bytes for the length).
   emitAbsValue(*MCOS,
                MakeStartMinusEndExpr(*MCOS, *LineStartSym, *LineEndSym, 4), 4);
 
   // Next 2 bytes is the Version.
   unsigned LineTableVersion = context.getDwarfVersion();
-  // FIXME: Right now the compiler doesn't support line table V5. Until it's
-  // supported keep generating line table V4, when Dwarf Info version V5 is used.  
-  if (LineTableVersion >= 5) 
-    LineTableVersion = 4; 
   MCOS->EmitIntValue(LineTableVersion, 2);
 
+  // Keep track of the bytes between the very start and where the header length
+  // comes out.
+  unsigned PreHeaderLengthBytes = 4 + 2;
+
+  // In v5, we get address info next.
+  if (LineTableVersion >= 5) {
+    MCOS->EmitIntValue(context.getAsmInfo()->getCodePointerSize(), 1);
+    MCOS->EmitIntValue(0, 1); // Segment selector; same as EmitGenDwarfAranges.
+    PreHeaderLengthBytes += 2;
+  }
+
   // Create a symbol for the end of the prologue (to be set when we get there).
   MCSymbol *ProEndSym = context.createTempSymbol(); // Lprologue_end
 
-  // Length of the prologue, is the next 4 bytes.  Which is the start of the
-  // section to the end of the prologue.  Not including the 4 bytes for the
-  // total length, the 2 bytes for the version, and these 4 bytes for the
-  // length of the prologue.
-  emitAbsValue(
-      *MCOS,
-      MakeStartMinusEndExpr(*MCOS, *LineStartSym, *ProEndSym, (4 + 2 + 4)), 4);
+  // Length of the prologue, is the next 4 bytes.  This is actually the length
+  // from after the length word, to the end of the prologue.
+  emitAbsValue(*MCOS,
+               MakeStartMinusEndExpr(*MCOS, *LineStartSym, *ProEndSym,
+                                     (PreHeaderLengthBytes + 4)),
+               4);
 
   // Parameters of the state machine, are next.
   MCOS->EmitIntValue(context.getAsmInfo()->getMinInstAlignment(), 1);
   // maximum_operations_per_instruction 
   // For non-VLIW architectures this field is always 1.
   // FIXME: VLIW architectures need to update this field accordingly.
-  if (context.getDwarfVersion() >= 4)
+  if (LineTableVersion >= 4)
     MCOS->EmitIntValue(1, 1);
   MCOS->EmitIntValue(DWARF2_LINE_DEFAULT_IS_STMT, 1);
   MCOS->EmitIntValue(Params.DWARF2LineBase, 1);
   MCOS->EmitIntValue(Params.DWARF2LineRange, 1);
   MCOS->EmitIntValue(StandardOpcodeLengths.size() + 1, 1);
 
   // Standard opcode lengths
   for (char Length : StandardOpcodeLengths)
     MCOS->EmitIntValue(Length, 1);
 
-  // Put out the directory and file tables.
-
-  // First the directory table.
-  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
-  }
-  MCOS->EmitIntValue(0, 1); // Terminate the directory list
-
-  // Second the file table.
-  for (unsigned i = 1; i < MCDwarfFiles.size(); i++) {
-    assert(!MCDwarfFiles[i].Name.empty());
-    MCOS->EmitBytes(MCDwarfFiles[i].Name); // FileName
-    MCOS->EmitBytes(StringRef("\0", 1)); // the null term. of the string
-    // the Directory num
-    MCOS->EmitULEB128IntValue(MCDwarfFiles[i].DirIndex);
-    MCOS->EmitIntValue(0, 1); // last modification timestamp (always 0)
-    MCOS->EmitIntValue(0, 1); // filesize (always 0)
-  }
-  MCOS->EmitIntValue(0, 1); // Terminate the file list
+  // Put out the directory and file tables.  The formats vary depending on
+  // the version.
+  if (LineTableVersion >= 5)
+    emitV5FileDirTables(MCOS, MCDwarfDirs, MCDwarfFiles, CompilationDir);
+  else
+    emitV2FileDirTables(MCOS, MCDwarfDirs, MCDwarfFiles);
 
   // This is the end of the prologue, so set the value of the symbol at the
   // end of the prologue (that was used in a previous expression).
   MCOS->EmitLabel(ProEndSym);
 
   return std::make_pair(LineStartSym, LineEndSym);
 }
 

llvm/test/MC/ARM/dwarf-asm-multiple-sections.s

 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 5 -fdebug-compilation-dir=/tmp
 // RUN: llvm-dwarfdump -v %t | FileCheck -check-prefix DWARF -check-prefix DWARF45 %s
-// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL %s
+// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL -check-prefix DWARF-DL-5 -DDWVER=5 %s
 // RUN: llvm-objdump -r %t | FileCheck -check-prefix RELOC -check-prefix RELOC5 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -fdebug-compilation-dir=/tmp
 // RUN: llvm-dwarfdump -v %t | FileCheck -check-prefix DWARF -check-prefix DWARF45 %s
-// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL %s
+// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL -DDWVER=4 %s
 // RUN: llvm-objdump -r %t | FileCheck -check-prefix RELOC -check-prefix RELOC4 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 3 -fdebug-compilation-dir=/tmp
 // RUN: llvm-dwarfdump -v %t | FileCheck -check-prefix DWARF -check-prefix DWARF3 %s
-// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL %s
+// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL -DDWVER=3 %s
 // RUN: llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 2 2>&1 | FileCheck -check-prefix VERSION %s
 // RUN: not llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 1 2>&1 | FileCheck -check-prefix DWARF1 %s
 // RUN: not llvm-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 6 2>&1 | FileCheck -check-prefix DWARF6 %s
   .section .text, "ax"
 a:
   mov r0, r0
 
   .section foo, "ax"

 
 // DWARF: .debug_aranges contents:
 // DWARF-NEXT: Address Range Header: length = 0x00000024, version = 0x0002, cu_offset = 0x00000000, addr_size = 0x04, seg_size = 0x00
 // DWARF-NEXT: [0x00000000 - 0x00000004)
 // DWARF-NEXT: [0x00000000 - 0x00000004)
 
 
 // DWARF-DL: .debug_line contents:
+// DWARF-DL: version: [[DWVER]]
+// DWARF-DL-5:    address_size: 4
+// DWARF-DL-5:    include_directories[  1] = ''
+// DWARF-DL:      file_names[  1] {{.*}} <stdin>
 // DWARF-DL:      0x0000000000000000     17      0      1   0   0  is_stmt
 // DWARF-DL-NEXT: 0x0000000000000004     17      0      1   0   0  is_stmt end_sequence
 // DWARF-DL-NEXT: 0x0000000000000000     21      0      1   0   0  is_stmt
 // DWARF-DL-NEXT: 0x0000000000000004     21      0      1   0   0  is_stmt end_sequence
 
 
 // DWARF: .debug_ranges contents:
 // DWARF: 00000000 ffffffff 00000000