[llvm-debuginfo-analyzer] Add support for LLVM IR format.

Add support for the LLVM IR format and be able to generate
logical views.

Both textual representation (.ll) and bitcode (.bc) format
are supported.

Note: This patch requires:

  Add DebugSSAUpdater class to track debug value liveness
  #135349

Author: CarlosAlbertoEnciso

llvm/docs/CommandGuide/llvm-debuginfo-analyzer.rst

@@ -13,10 +13,11 @@ SYNOPSIS
 DESCRIPTION
 -----------
 :program:`llvm-debuginfo-analyzer` parses debug and text sections in
-binary object files and prints their contents in a logical view, which
-is a human readable representation that closely matches the structure
-of the original user source code. Supported object file formats include
-ELF, Mach-O, WebAssembly, PDB and COFF.
+binary object files and textual IR representations and prints their
+contents in a logical view, which is a human readable representation
+that closely matches the structure of the original user source code.
+Supported object file formats include ELF, Mach-O, WebAssembly, PDB,
+COFF, IR (textual representation and bitcode).
 
 The **logical view** abstracts the complexity associated with the
 different low-level representations of the debugging information that
@@ -2124,6 +2125,138 @@ layout and given the number of matches.
   -----------------------------
   Total           71          8
 
+IR (Textual representation and bitcode) SUPPORT
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The below example is used to show the IR output generated by
+:program:`llvm-debuginfo-analyzer`. We compiled the example for a
+IR 64-bit target with Clang (-O0 -g --target=x86_64-linux):
+
+.. code-block:: c++
+
+  1  using INTPTR = const int *;
+  2  int foo(INTPTR ParamPtr, unsigned ParamUnsigned, bool ParamBool) {
+  3    if (ParamBool) {
+  4      typedef int INTEGER;
+  5      const INTEGER CONSTANT = 7;
+  6      return CONSTANT;
+  7    }
+  8    return ParamUnsigned;
+  9  }
+
+PRINT BASIC DETAILS
+^^^^^^^^^^^^^^^^^^^
+The following command prints basic details for all the logical elements
+sorted by the debug information internal offset; it includes its lexical
+level and debug info format.
+
+.. code-block:: none
+
+  llvm-debuginfo-analyzer --attribute=level,format
+                          --output-sort=offset
+                          --print=scopes,symbols,types,lines,instructions
+                          test-clang.ll
+
+or
+
+.. code-block:: none
+
+  llvm-debuginfo-analyzer --attribute=level,format
+                          --output-sort=offset
+                          --print=elements
+                          test-clang.ll
+
+Each row represents an element that is present within the debug
+information. The first column represents the scope level, followed by
+the associated line number (if any), and finally the description of
+the element.
+
+.. code-block:: none
+
+  Logical View:
+  [000]           {File} 'test-clang.ll' -> Textual IR
+
+  [001]             {CompileUnit} 'test.cpp'
+  [002]     2         {Function} extern not_inlined 'foo' -> 'int'
+  [003]                 {Block}
+  [004]     5             {Variable} 'CONSTANT' -> 'const INTEGER'
+  [004]     5             {Line}
+  [004]                   {Code} 'store i32 7, ptr %CONSTANT, align 4, !dbg !32'
+  [004]     6             {Line}
+  [004]                   {Code} 'store i32 7, ptr %retval, align 4, !dbg !33'
+  [004]     6             {Line}
+  [004]                   {Code} 'br label %return, !dbg !33'
+  [003]     2           {Parameter} 'ParamPtr' -> 'INTPTR'
+  [003]     2           {Parameter} 'ParamUnsigned' -> 'unsigned int'
+  [003]     2           {Parameter} 'ParamBool' -> 'bool'
+  [003]     4           {TypeAlias} 'INTEGER' -> 'int'
+  [003]     2           {Line}
+  [003]                 {Code} '%retval = alloca i32, align 4'
+  [003]                 {Code} '%ParamPtr.addr = alloca ptr, align 8'
+  [003]                 {Code} '%ParamUnsigned.addr = alloca i32, align 4'
+  [003]                 {Code} '%ParamBool.addr = alloca i8, align 1'
+  [003]                 {Code} '%CONSTANT = alloca i32, align 4'
+  [003]                 {Code} 'store ptr %ParamPtr, ptr %ParamPtr.addr, align 8'
+  [003]                 {Code} 'store i32 %ParamUnsigned, ptr %ParamUnsigned.addr, align 4'
+  [003]                 {Code} '%storedv = zext i1 %ParamBool to i8'
+  [003]                 {Code} 'store i8 %storedv, ptr %ParamBool.addr, align 1'
+  [003]     8           {Line}
+  [003]                 {Code} '%1 = load i32, ptr %ParamUnsigned.addr, align 4, !dbg !34'
+  [003]     8           {Line}
+  [003]                 {Code} 'store i32 %1, ptr %retval, align 4, !dbg !35'
+  [003]     8           {Line}
+  [003]                 {Code} 'br label %return, !dbg !35'
+  [003]     9           {Line}
+  [003]                 {Code} '%2 = load i32, ptr %retval, align 4, !dbg !36'
+  [003]     9           {Line}
+  [003]                 {Code} 'ret i32 %2, !dbg !36'
+  [003]     3           {Line}
+  [003]     3           {Line}
+  [003]     3           {Line}
+  [003]                 {Code} 'br i1 %loadedv, label %if.then, label %if.end, !dbg !26'
+  [002]     1         {TypeAlias} 'INTPTR' -> '* const int'
+
+SELECT LOGICAL ELEMENTS
+^^^^^^^^^^^^^^^^^^^^^^^
+The following prints all *instructions*, *symbols* and *types* that
+contain **'block'** or **'.store'** in their names or types, using a tab
+layout and given the number of matches.
+
+.. code-block:: none
+
+  llvm-debuginfo-analyzer --attribute=level
+                          --select-nocase --select-regex
+                          --select=LOAD --select=store
+                          --report=list
+                          --print=symbols,types,instructions,summary
+                          test-clang.ll
+
+  Logical View:
+  [000]           {File} 'test-clang.ll'
+
+  [001]           {CompileUnit} 'test.cpp'
+  [003]           {Code} '%0 = load i8, ptr %ParamBool.addr, align 1, !dbg !26'
+  [003]           {Code} '%1 = load i32, ptr %ParamUnsigned.addr, align 4, !dbg !34'
+  [003]           {Code} '%2 = load i32, ptr %retval, align 4, !dbg !36'
+  [004]           {Code} '%loadedv = trunc i8 %0 to i1, !dbg !26'
+  [003]           {Code} '%storedv = zext i1 %ParamBool to i8'
+  [003]           {Code} 'br i1 %loadedv, label %if.then, label %if.end, !dbg !26'
+  [003]           {Code} 'store i32 %1, ptr %retval, align 4, !dbg !35'
+  [003]           {Code} 'store i32 %ParamUnsigned, ptr %ParamUnsigned.addr, align 4'
+  [004]           {Code} 'store i32 7, ptr %CONSTANT, align 4, !dbg !32'
+  [004]           {Code} 'store i32 7, ptr %retval, align 4, !dbg !33'
+  [003]           {Code} 'store i8 %storedv, ptr %ParamBool.addr, align 1'
+  [003]           {Code} 'store ptr %ParamPtr, ptr %ParamPtr.addr, align 8'
+
+  -----------------------------
+  Element      Total    Printed
+  -----------------------------
+  Scopes           5          0
+  Symbols          4          0
+  Types            2          0
+  Lines           22         12
+  -----------------------------
+  Total           33         12
+
 COMPARISON MODE
 ^^^^^^^^^^^^^^^
 Given the previous example we found the above debug information issue
@@ -2197,6 +2330,34 @@ giving more context by swapping the reference and target object files.
 The output shows the merging view path (reference and target) with the
 missing and added elements.
 
+.. code-block:: none
+
+  llvm-debuginfo-analyzer --attribute=level,format
+                          --compare=types
+                          --report=view
+                          --print=symbols,types
+                          test-clang.bc test-dwarf-gcc.o
+
+  Reference: 'test-clang.bc'
+  Target:    'test-dwarf-gcc.o'
+
+  Logical View:
+   [000]           {File} 'test-clang.bc' -> Bitcode IR
+
+   [001]             {CompileUnit} 'test.cpp'
+   [002]     1         {TypeAlias} 'INTPTR' -> '* const int'
+   [002]     2         {Function} extern not_inlined 'foo' -> 'int'
+   [003]                 {Block}
+   [004]     5             {Variable} 'CONSTANT' -> 'const INTEGER'
+  +[004]     4             {TypeAlias} 'INTEGER' -> 'int'
+   [003]     2           {Parameter} 'ParamBool' -> 'bool'
+   [003]     2           {Parameter} 'ParamPtr' -> 'INTPTR'
+   [003]     2           {Parameter} 'ParamUnsigned' -> 'unsigned int'
+  -[003]     4           {TypeAlias} 'INTEGER' -> 'int'
+
+The same output but this time comparing the Clang bitcode with the
+binary object (DWARF) generated by GCC.
+
 LOGICAL ELEMENTS
 """"""""""""""""
 It compares individual logical elements without considering if their

llvm/include/llvm/DebugInfo/LogicalView/Core/LVReader.h

@@ -56,7 +56,7 @@ class LVSplitContext final {
 
 /// The logical reader owns of all the logical elements created during
 /// the debug information parsing. For its creation it uses a specific
-///  bump allocator for each type of logical element.
+/// bump allocator for each type of logical element.
 class LVReader {
   LVBinaryType BinaryType;
 
@@ -121,7 +121,24 @@ class LVReader {
 
 #undef LV_OBJECT_ALLOCATOR
 
+  // Scopes with ranges for current compile unit. It is used to find a line
+  // giving its exact or closest address. To support comdat functions, all
+  // addresses for the same section are recorded in the same map.
+  using LVSectionRanges = std::map<LVSectionIndex, std::unique_ptr<LVRange>>;
+  LVSectionRanges SectionRanges;
+
 protected:
+  // Current elements during the processing of a DIE/MDNode.
+  LVElement *CurrentElement = nullptr;
+  LVScope *CurrentScope = nullptr;
+  LVSymbol *CurrentSymbol = nullptr;
+  LVType *CurrentType = nullptr;
+  LVLine *CurrentLine = nullptr;
+  LVOffset CurrentOffset = 0;
+
+  // Address ranges collected for current DIE/MDNode/AST Node.
+  std::vector<LVAddressRange> CurrentRanges;
+
   LVScopeRoot *Root = nullptr;
   std::string InputFilename;
   std::string FileFormatName;
@@ -132,11 +149,18 @@ class LVReader {
   // Only for ELF format. The CodeView is handled in a different way.
   LVSectionIndex DotTextSectionIndex = UndefinedSectionIndex;
 
+  void addSectionRange(LVSectionIndex SectionIndex, LVScope *Scope);
+  void addSectionRange(LVSectionIndex SectionIndex, LVScope *Scope,
+                       LVAddress LowerAddress, LVAddress UpperAddress);
+  LVRange *getSectionRanges(LVSectionIndex SectionIndex);
+
   // Record Compilation Unit entry.
   void addCompileUnitOffset(LVOffset Offset, LVScopeCompileUnit *CompileUnit) {
     CompileUnits.emplace(Offset, CompileUnit);
   }
 
+  LVElement *createElement(dwarf::Tag Tag);
+
   // Create the Scope Root.
   virtual Error createScopes() {
     Root = createScopeRoot();

llvm/include/llvm/DebugInfo/LogicalView/Core/LVSupport.h

@@ -99,6 +99,19 @@ template <typename T> class LVProperties {
 #define KIND_3(ENUM, FIELD, F1, F2, F3)                                        \
   BOOL_BIT_3(Kinds, ENUM, FIELD, F1, F2, F3)
 
+const int DEC_WIDTH = 8;
+inline FormattedNumber decValue(uint64_t N, unsigned Width = DEC_WIDTH) {
+  return format_decimal(N, Width);
+}
+
+// Output the decimal representation of 'Value'.
+inline std::string decString(uint64_t Value, size_t Width = DEC_WIDTH) {
+  std::string String;
+  raw_string_ostream Stream(String);
+  Stream << decValue(Value, Width);
+  return Stream.str();
+}
+
 const int HEX_WIDTH = 12;
 inline FormattedNumber hexValue(uint64_t N, unsigned Width = HEX_WIDTH,
                                 bool Upper = false) {

llvm/include/llvm/DebugInfo/LogicalView/LVReaderHandler.h

@@ -17,6 +17,7 @@
 #include "llvm/DebugInfo/LogicalView/Core/LVReader.h"
 #include "llvm/DebugInfo/PDB/Native/PDBFile.h"
 #include "llvm/Object/Archive.h"
+#include "llvm/Object/IRObjectFile.h"
 #include "llvm/Object/MachOUniversal.h"
 #include "llvm/Object/ObjectFile.h"
 #include "llvm/Support/MemoryBuffer.h"
@@ -29,7 +30,9 @@ namespace logicalview {
 
 using LVReaders = std::vector<std::unique_ptr<LVReader>>;
 using ArgVector = std::vector<std::string>;
-using PdbOrObj = PointerUnion<object::ObjectFile *, pdb::PDBFile *>;
+using PdbOrObjOrIr =
+    PointerUnion<object::ObjectFile *, pdb::PDBFile *, object::IRObjectFile *,
+                 MemoryBufferRef *, StringRef *>;
 
 // This class performs the following tasks:
 // - Creates a logical reader for every binary file in the command line,
@@ -60,9 +63,12 @@ class LVReaderHandler {
                      object::Binary &Binary);
   Error handleObject(LVReaders &Readers, StringRef Filename, StringRef Buffer,
                      StringRef ExePath);
+  Error handleObject(LVReaders &Readers, StringRef Filename,
+                     MemoryBufferRef Buffer);
 
-  Error createReader(StringRef Filename, LVReaders &Readers, PdbOrObj &Input,
-                     StringRef FileFormatName, StringRef ExePath = {});
+  Error createReader(StringRef Filename, LVReaders &Readers,
+                     PdbOrObjOrIr &Input, StringRef FileFormatName,
+                     StringRef ExePath = {});
 
 public:
   LVReaderHandler() = delete;

llvm/include/llvm/DebugInfo/LogicalView/Readers/LVBinaryReader.h

@@ -25,6 +25,7 @@
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/TargetRegistry.h"
 #include "llvm/Object/COFF.h"
+#include "llvm/Object/IRObjectFile.h"
 #include "llvm/Object/ObjectFile.h"
 
 namespace llvm {
@@ -93,12 +94,6 @@ class LVBinaryReader : public LVReader {
       SectionAddresses.emplace(Section.getAddress(), Section);
   }
 
-  // Scopes with ranges for current compile unit. It is used to find a line
-  // giving its exact or closest address. To support comdat functions, all
-  // addresses for the same section are recorded in the same map.
-  using LVSectionRanges = std::map<LVSectionIndex, std::unique_ptr<LVRange>>;
-  LVSectionRanges SectionRanges;
-
   // Image base and virtual address for Executable file.
   uint64_t ImageBaseAddress = 0;
   uint64_t VirtualAddress = 0;
@@ -179,11 +174,6 @@ class LVBinaryReader : public LVReader {
   Expected<std::pair<LVSectionIndex, object::SectionRef>>
   getSection(LVScope *Scope, LVAddress Address, LVSectionIndex SectionIndex);
 
-  void addSectionRange(LVSectionIndex SectionIndex, LVScope *Scope);
-  void addSectionRange(LVSectionIndex SectionIndex, LVScope *Scope,
-                       LVAddress LowerAddress, LVAddress UpperAddress);
-  LVRange *getSectionRanges(LVSectionIndex SectionIndex);
-
   void includeInlineeLines(LVSectionIndex SectionIndex, LVScope *Function);
 
   Error createInstructions();

llvm/include/llvm/DebugInfo/LogicalView/Readers/LVDWARFReader.h

@@ -39,22 +39,13 @@ class LVDWARFReader final : public LVBinaryReader {
   LVAddress CUBaseAddress = 0;
   LVAddress CUHighAddress = 0;
 
-  // Current elements during the processing of a DIE.
-  LVElement *CurrentElement = nullptr;
-  LVScope *CurrentScope = nullptr;
-  LVSymbol *CurrentSymbol = nullptr;
-  LVType *CurrentType = nullptr;
-  LVOffset CurrentOffset = 0;
   LVOffset CurrentEndOffset = 0;
 
   // In DWARF v4, the files are 1-indexed.
   // In DWARF v5, the files are 0-indexed.
   // The DWARF reader expects the indexes as 1-indexed.
   bool IncrementFileIndex = false;
 
-  // Address ranges collected for current DIE.
-  std::vector<LVAddressRange> CurrentRanges;
-
   // Symbols with locations for current compile unit.
   LVSymbols SymbolsWithLocations;
 
@@ -82,7 +73,6 @@ class LVDWARFReader final : public LVBinaryReader {
 
   void mapRangeAddress(const object::ObjectFile &Obj) override;
 
-  LVElement *createElement(dwarf::Tag Tag);
   void traverseDieAndChildren(DWARFDie &DIE, LVScope *Parent,
                               DWARFDie &SkeletonDie);
   // Process the attributes for the given DIE.