[llvm] Reapply "Prevent duplicate files in debug line header in dwarf 5."

Reapply rL356941 after regenerating the object file in the failing test
llvm/test/tools/llvm-objdump/embedded-source.test from source.

Original commit message:

[llvm] Prevent duplicate files in debug line header in dwarf 5.

Motivation: In previous dwarf versions, file name indexes started from 1, and
the primary source file was not explicit. Dwarf 5 standard (6.2.4) prescribes
the primary source file to be explicitly given an entry with an index number 0.

The current implementation honors the specification by just duplicating the
main source file, once with index number 0, and later maybe with another
index number. While this is compliant with the letter of the standard, the
duplication causes problems for consumers of this information such as lldb.
(Some files are duplicated, where only some of them have a line table although
all refer to the same file)

With this change, dwarf 5 debug line section files always start from 0, and
the zeroth entry is not duplicated whenever possible. This requires different
handling of dwarf 4 and dwarf 5 during generation (e.g. when a function returns
an index zero for a file name, it signals an error in dwarf 4, but not in dwarf 5)
However, I think the minor complication is worth it, because it enables all
consumers (lldb, gdb, dwarfdump, objdump, and so on) to treat all files in the
file name list homogenously.

Tags: #llvm, #debug-info

Differential Revision: https://reviews.llvm.org/D59515

llvm-svn: 357018

14 files changed, 70 insertions, 26 deletions

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
index 1f36e0daed0..6247c31d717 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFDebugLine.h
@@ -275,6 +275,8 @@ public:
     SequenceVector Sequences;
 
   private:
+    const llvm::DWARFDebugLine::FileNameEntry &
+    getFileNameEntry(uint64_t Index) const;
     uint32_t findRowInSeq(const DWARFDebugLine::Sequence &Seq,
                           object::SectionedAddress Address) const;
     Optional<StringRef>
diff --git a/llvm/include/llvm/MC/MCContext.h b/llvm/include/llvm/MC/MCContext.h
index c87df5a82ce..6beb6463964 100644
--- a/llvm/include/llvm/MC/MCContext.h
+++ b/llvm/include/llvm/MC/MCContext.h
@@ -521,7 +521,7 @@ namespace llvm {
     }
 
     MCDwarfLineTable &getMCDwarfLineTable(unsigned CUID) {
-      return MCDwarfLineTablesCUMap[CUID];
+      return MCDwarfLineTablesCUMap.emplace(CUID, DwarfVersion).first->second;
     }
 
     const MCDwarfLineTable &getMCDwarfLineTable(unsigned CUID) const {
diff --git a/llvm/include/llvm/MC/MCDwarf.h b/llvm/include/llvm/MC/MCDwarf.h
index 991ad525f89..70624d0a4df 100644
--- a/llvm/include/llvm/MC/MCDwarf.h
+++ b/llvm/include/llvm/MC/MCDwarf.h
@@ -218,9 +218,11 @@ struct MCDwarfLineTableHeader {
 private:
   bool HasAllMD5 = true;
   bool HasAnyMD5 = false;
+  unsigned DwarfVersion;
 
 public:
-  MCDwarfLineTableHeader() = default;
+  explicit MCDwarfLineTableHeader(unsigned DwarfVersion) :
+    DwarfVersion(DwarfVersion) {}
 
   Expected<unsigned> tryGetFile(StringRef &Directory, StringRef &FileName,
                                 MD5::MD5Result *Checksum,
@@ -245,6 +247,17 @@ public:
     return MCDwarfFiles.empty() || (HasAllMD5 == HasAnyMD5);
   }
 
+  void setRootFile(StringRef Directory, StringRef FileName,
+                   MD5::MD5Result *Checksum, Optional<StringRef> Source) {
+    CompilationDir = Directory;
+    RootFile.Name = FileName;
+    RootFile.DirIndex = 0;
+    RootFile.Checksum = Checksum;
+    RootFile.Source = Source;
+    trackMD5Usage(Checksum);
+    HasSource = Source.hasValue();
+  }
+
 private:
   void emitV2FileDirTables(MCStreamer *MCOS) const;
   void emitV5FileDirTables(MCStreamer *MCOS, Optional<MCDwarfLineStr> &LineStr,
@@ -255,6 +268,8 @@ class MCDwarfDwoLineTable {
   MCDwarfLineTableHeader Header;
 
 public:
+  MCDwarfDwoLineTable(unsigned DwarfVersion) : Header(DwarfVersion) {}
+
   void maybeSetRootFile(StringRef Directory, StringRef FileName,
                         MD5::MD5Result *Checksum, Optional<StringRef> Source) {
     if (!Header.RootFile.Name.empty())
@@ -282,6 +297,7 @@ class MCDwarfLineTable {
   MCLineSection MCLineSections;
 
 public:
+  MCDwarfLineTable(unsigned DwarfVersion) : Header(DwarfVersion) {}
   // This emits the Dwarf file and the line tables for all Compile Units.
   static void Emit(MCObjectStreamer *MCOS, MCDwarfLineTableParams Params);
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h b/llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h
index d9addb52376..683d3245e56 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfCompileUnit.h
@@ -101,6 +101,7 @@ class DwarfCompileUnit final : public DwarfUnit {
   }
 
 public:
+  unsigned getDwarfVersion() const { return DD->getDwarfVersion(); }
   DwarfCompileUnit(unsigned UID, const DICompileUnit *Node, AsmPrinter *A,
                    DwarfDebug *DW, DwarfFile *DWU);
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
index 0e0a5b24864..226014cf0bb 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfDebug.cpp
@@ -319,6 +319,7 @@ DwarfDebug::DwarfDebug(AsmPrinter *A, Module *M)
     : DebugHandlerBase(A), DebugLocs(A->OutStreamer->isVerboseAsm()),
       InfoHolder(A, "info_string", DIEValueAllocator),
       SkeletonHolder(A, "skel_string", DIEValueAllocator),
+      SplitTypeUnitFileTable(A->getDwarfVersion()),
       IsDarwin(A->TM.getTargetTriple().isOSDarwin()) {
   const Triple &TT = Asm->TM.getTargetTriple();
 
diff --git a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
index 6e547469c24..5d8e236a6b3 100644
--- a/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/DwarfUnit.cpp
@@ -397,7 +397,6 @@ void DwarfUnit::addSourceLine(DIE &Die, unsigned Line, const DIFile *File) {
     return;
 
   unsigned FileID = getOrCreateSourceID(File);
-  assert(FileID && "Invalid file id");
   addUInt(Die, dwarf::DW_AT_decl_file, None, FileID);
   addUInt(Die, dwarf::DW_AT_decl_line, None, Line);
 }
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
index 53420187773..6ad06a8553e 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDebugLine.cpp
@@ -1017,14 +1017,28 @@ bool DWARFDebugLine::LineTable::lookupAddressRangeImpl(
 }
 
 bool DWARFDebugLine::LineTable::hasFileAtIndex(uint64_t FileIndex) const {
-  return FileIndex != 0 && FileIndex <= Prologue.FileNames.size();
+  uint16_t DwarfVersion = Prologue.getVersion();
+  assert(DwarfVersion != 0 && "LineTable has no dwarf version information");
+  if (DwarfVersion >= 5)
+    return FileIndex < Prologue.FileNames.size();
+  else
+    return FileIndex != 0 && FileIndex <= Prologue.FileNames.size();
+}
+const llvm::DWARFDebugLine::FileNameEntry &
+DWARFDebugLine::LineTable::getFileNameEntry(uint64_t Index) const {
+  uint16_t DwarfVersion = Prologue.getVersion();
+  assert(DwarfVersion != 0 && "LineTable has no dwarf version information");
+  if (DwarfVersion >= 5)
+    return Prologue.FileNames[Index];
+  else
+    return Prologue.FileNames[Index - 1];
 }
 
 Optional<StringRef> DWARFDebugLine::LineTable::getSourceByIndex(uint64_t FileIndex,
                                                                 FileLineInfoKind Kind) const {
   if (Kind == FileLineInfoKind::None || !hasFileAtIndex(FileIndex))
     return None;
-  const FileNameEntry &Entry = Prologue.FileNames[FileIndex - 1];
+  const FileNameEntry &Entry = getFileNameEntry(FileIndex);
   if (Optional<const char *> source = Entry.Source.getAsCString())
     return StringRef(*source);
   return None;
@@ -1044,7 +1058,7 @@ bool DWARFDebugLine::LineTable::getFileNameByIndex(uint64_t FileIndex,
                                                    std::string &Result) const {
   if (Kind == FileLineInfoKind::None || !hasFileAtIndex(FileIndex))
     return false;
-  const FileNameEntry &Entry = Prologue.FileNames[FileIndex - 1];
+  const FileNameEntry &Entry = getFileNameEntry(FileIndex);
   StringRef FileName = Entry.Name.getAsCString().getValue();
   if (Kind != FileLineInfoKind::AbsoluteFilePath ||
       isPathAbsoluteOnWindowsOrPosix(FileName)) {
diff --git a/llvm/lib/MC/MCContext.cpp b/llvm/lib/MC/MCContext.cpp
index 49fad131a2c..348436f4bd0 100644
--- a/llvm/lib/MC/MCContext.cpp
+++ b/llvm/lib/MC/MCContext.cpp
@@ -603,7 +603,8 @@ Expected<unsigned> MCContext::getDwarfFile(StringRef Directory,
                                            MD5::MD5Result *Checksum,
                                            Optional<StringRef> Source,
                                            unsigned CUID) {
-  MCDwarfLineTable &Table = MCDwarfLineTablesCUMap[CUID];
+  MCDwarfLineTable &Table =
+      MCDwarfLineTablesCUMap.emplace(CUID, DwarfVersion).first->second;
   return Table.tryGetFile(Directory, FileName, Checksum, Source, FileNumber);
 }
 
@@ -612,7 +613,7 @@ Expected<unsigned> MCContext::getDwarfFile(StringRef Directory,
 bool MCContext::isValidDwarfFileNumber(unsigned FileNumber, unsigned CUID) {
   const MCDwarfLineTable &LineTable = getMCDwarfLineTable(CUID);
   if (FileNumber == 0)
-    return getDwarfVersion() >= 5 && LineTable.hasRootFile();
+    return getDwarfVersion() >= 5;
   if (FileNumber >= LineTable.getMCDwarfFiles().size())
     return false;
 
diff --git a/llvm/lib/MC/MCDwarf.cpp b/llvm/lib/MC/MCDwarf.cpp
index 83b6b4f1aa3..73b4d4bcd19 100644
--- a/llvm/lib/MC/MCDwarf.cpp
+++ b/llvm/lib/MC/MCDwarf.cpp
@@ -542,6 +542,15 @@ Expected<unsigned> MCDwarfLineTable::tryGetFile(StringRef &Directory,
   return Header.tryGetFile(Directory, FileName, Checksum, Source, FileNumber);
 }
 
+bool isRootFile(const MCDwarfFile &RootFile, StringRef &Directory,
+                StringRef &FileName, MD5::MD5Result *Checksum) {
+  if (RootFile.Name.empty() || RootFile.Name != FileName.data())
+    return false;
+  if (!RootFile.Checksum)
+    return !Checksum;
+  return *RootFile.Checksum == *Checksum;
+}
+
 Expected<unsigned>
 MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
                                    StringRef &FileName,
@@ -561,6 +570,8 @@ MCDwarfLineTableHeader::tryGetFile(StringRef &Directory,
     trackMD5Usage(Checksum);
     HasSource = (Source != None);
   }
+  if (isRootFile(RootFile, Directory, FileName, Checksum) && DwarfVersion >= 5)
+    return 0;
   if (FileNumber == 0) {
     // File numbers start with 1 and/or after any file numbers
     // allocated by inline-assembler .file directives.
diff --git a/llvm/test/MC/ARM/dwarf-asm-multiple-sections.s b/llvm/test/MC/ARM/dwarf-asm-multiple-sections.s
index cff8f000731..39c69c9f7d2 100644
--- a/llvm/test/MC/ARM/dwarf-asm-multiple-sections.s
+++ b/llvm/test/MC/ARM/dwarf-asm-multiple-sections.s
@@ -2,9 +2,9 @@
 // RUN: llvm-dwarfdump -v %t | FileCheck -check-prefix DWARF -check-prefix DWARF45 %s
 // RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL -check-prefix DWARF-DL-5 -DDWVER=5 -DDWFILE=0 %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-mc < %s -triple=armv7-linux-gnueabi -filetype=obj -o %t -g -dwarf-version 4 -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 -DDWVER=4 -DDWFILE=1 %s
+// RUN: llvm-dwarfdump --debug-line %t | FileCheck -check-prefix DWARF-DL -check-prefix DWARF-DL-4 -DDWVER=4 -DDWFILE=1 %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
@@ -57,11 +57,14 @@ b:
 // DWARF-DL-5:    include_directories[  0] = "/tmp"
 // DWARF-DL:      file_names[  [[DWFILE]]]:
 // DWARF-DL:      name: "{{(<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-DL-5:      0x0000000000000000     17      0      0   0   0  is_stmt
+// DWARF-DL-5-NEXT: 0x0000000000000004     17      0      0   0   0  is_stmt end_sequence
+// DWARF-DL-5-NEXT: 0x0000000000000000     21      0      0   0   0  is_stmt
+// DWARF-DL-5-NEXT: 0x0000000000000004     21      0      0   0   0  is_stmt end_sequence
+// DWARF-DL-4:      0x0000000000000000     17      0      1   0   0  is_stmt
+// DWARF-DL-4-NEXT: 0x0000000000000004     17      0      1   0   0  is_stmt end_sequence
+// DWARF-DL-4-NEXT: 0x0000000000000000     21      0      1   0   0  is_stmt
+// DWARF-DL-4-NEXT: 0x0000000000000004     21      0      1   0   0  is_stmt end_sequence
 
 // DWARF: .debug_ranges contents:
 // DWARF: 00000000 ffffffff 00000000
diff --git a/llvm/test/MC/ELF/debug-mixed-md5.ll b/llvm/test/MC/ELF/debug-mixed-md5.ll
index 2ec8141325f..d48e42c8d12 100644
--- a/llvm/test/MC/ELF/debug-mixed-md5.ll
+++ b/llvm/test/MC/ELF/debug-mixed-md5.ll
@@ -1,8 +1,7 @@
 ; RUN: %llc_dwarf -filetype=asm -dwarf-version=5 %s -o - | FileCheck %s -check-prefix=ASM
 ; RUN: %llc_dwarf -filetype=obj -dwarf-version=5 %s -o - | llvm-dwarfdump -debug-line - | FileCheck %s -check-prefix=OBJ
 ; ASM: .file 0 "{{.+}}" md5
-; ASM: .file 1 "{{.+}}" md5
-; ASM: .file 2 "t1.cpp"
+; ASM: .file 1 "t1.cpp"
 ; ASM-NOT: md5
 ; OBJ: file_names[ 0]:
 ; OBJ-NOT: md5
diff --git a/llvm/test/MC/ELF/dwarf-file0.s b/llvm/test/MC/ELF/dwarf-file0.s
index 1a3afb6875f..f98fdcc2b40 100644
--- a/llvm/test/MC/ELF/dwarf-file0.s
+++ b/llvm/test/MC/ELF/dwarf-file0.s
@@ -19,16 +19,14 @@
 # CHECK:       file_names[ 1]:
 # CHECK-NEXT:  name: "header.h"
 # CHECK-NEXT:  dir_index: 1
-# CHECK:       file_names[ 2]:
-# CHECK-NEXT:  name: "root.cpp"
+# CHECK-4:     file_names[ 2]:
+# CHECK-4-NEXT: name: "root.cpp"
 # CHECK-4-NEXT: dir_index: 2
-# CHECK-5-NEXT: dir_index: 0
 
 # ASM-NOT: .file
 # ASM-5:   .file 0 "/test" "root.cpp"
 # ASM:     .file 1 "/include" "header.h"
 # ASM-4:   .file 2 "/test" "root.cpp"
-# ASM-5:   .file 2 "root.cpp"
 # ASM-NOT: .file
 
 # WARN:      file 0 not supported prior to DWARF-5
diff --git a/llvm/test/tools/llvm-objdump/Inputs/embedded-source b/llvm/test/tools/llvm-objdump/Inputs/embedded-source
index 072b5a90c5c..f59027e0859 100644
--- a/llvm/test/tools/llvm-objdump/Inputs/embedded-source
+++ b/llvm/test/tools/llvm-objdump/Inputs/embedded-source
diff --git a/llvm/test/tools/llvm-objdump/X86/function-sections-line-numbers.s b/llvm/test/tools/llvm-objdump/X86/function-sections-line-numbers.s
index b932a5d3f32..46607440cb9 100644
--- a/llvm/test/tools/llvm-objdump/X86/function-sections-line-numbers.s
+++ b/llvm/test/tools/llvm-objdump/X86/function-sections-line-numbers.s
@@ -30,8 +30,7 @@
 _Z2f1v:                                 # @_Z2f1v
 .Lfunc_begin0:
 	.file	0 "/home/avl" "test.cpp" md5 0xefae234cc05b45384d782316d3a5d338
-	.file	1 "test.cpp" md5 0xefae234cc05b45384d782316d3a5d338
-	.loc	1 1 0                   # test.cpp:1:0
+	.loc	0 1 0                   # test.cpp:1:0
 	.cfi_startproc
 # %bb.0:                                # %entry
 	pushq	%rbp
@@ -40,7 +39,7 @@ _Z2f1v:                                 # @_Z2f1v
 	movq	%rsp, %rbp
 	.cfi_def_cfa_register %rbp
 .Ltmp0:
-	.loc	1 1 12 prologue_end     # test.cpp:1:12
+	.loc	0 1 12 prologue_end     # test.cpp:1:12
 	popq	%rbp
 	.cfi_def_cfa %rsp, 8
 	retq
@@ -55,7 +54,7 @@ _Z2f1v:                                 # @_Z2f1v
 	.type	_Z2f2v,@function
 _Z2f2v:                                 # @_Z2f2v
 .Lfunc_begin1:
-	.loc	1 2 0                   # test.cpp:2:0
+	.loc	0 2 0                   # test.cpp:2:0
 	.cfi_startproc
 # %bb.0:                                # %entry
 	pushq	%rbp
@@ -64,7 +63,7 @@ _Z2f2v:                                 # @_Z2f2v
 	movq	%rsp, %rbp
 	.cfi_def_cfa_register %rbp
 .Ltmp2:
-	.loc	1 2 12 prologue_end     # test.cpp:2:12
+	.loc	0 2 12 prologue_end     # test.cpp:2:12
 	popq	%rbp
 	.cfi_def_cfa %rsp, 8
 	retq