[Debuginfo][DW_OP_implicit_pointer] (1/7) Support for DW_OP_LLVM_impl…

…icit_pointer

New dwarf operator DW_OP_LLVM_implicit_pointer is introduced (present only in LLVM IR)
This operator is required as it is different than DWARF operator
DW_OP_implicit_pointer in representation and specification (number
and types of operands) and later can not be used as multiple level.

Reviewed By: aprantl

Differential Revision: https://reviews.llvm.org/D84113

llvm/docs/LangRef.rst

@@ -5284,6 +5284,33 @@ The current supported opcode vocabulary is limited:
   of the stack. This opcode can be used to calculate bounds of fortran assumed
   rank array which has rank known at run time and current dimension number is
   implicitly first element of the stack.
+- ``DW_OP_LLVM_implicit_pointer`` It specifies the dereferenced value. It can
+  be used to represent pointer variables which are optimized out but the value
+  it points to is known. This operator is required as it is different than DWARF
+  operator DW_OP_implicit_pointer in representation and specification (number
+  and types of operands) and later can not be used as multiple level.
+
+.. code-block:: text
+
+    IR for "*ptr = 4;"
+    --------------
+    call void @llvm.dbg.value(metadata i32 4, metadata !17, metadata !20)
+    !17 = !DILocalVariable(name: "ptr1", scope: !12, file: !3, line: 5,
+                           type: !18)
+    !18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !19, size: 64)
+    !19 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+    !20 = !DIExpression(DW_OP_LLVM_implicit_pointer))
+
+    IR for "**ptr = 4;"
+    --------------
+    call void @llvm.dbg.value(metadata i32 4, metadata !17, metadata !21)
+    !17 = !DILocalVariable(name: "ptr1", scope: !12, file: !3, line: 5,
+                           type: !18)
+    !18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !19, size: 64)
+    !19 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !20, size: 64)
+    !20 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+    !21 = !DIExpression(DW_OP_LLVM_implicit_pointer,
+                        DW_OP_LLVM_implicit_pointer))
 
 DWARF specifies three kinds of simple location descriptions: Register, memory,
 and implicit location descriptions.  Note that a location description is

llvm/include/llvm/BinaryFormat/Dwarf.h

@@ -120,10 +120,11 @@ enum LocationAtom {
 #include "llvm/BinaryFormat/Dwarf.def"
   DW_OP_lo_user = 0xe0,
   DW_OP_hi_user = 0xff,
-  DW_OP_LLVM_fragment = 0x1000,    ///< Only used in LLVM metadata.
-  DW_OP_LLVM_convert = 0x1001,     ///< Only used in LLVM metadata.
-  DW_OP_LLVM_tag_offset = 0x1002,  ///< Only used in LLVM metadata.
-  DW_OP_LLVM_entry_value = 0x1003, ///< Only used in LLVM metadata.
+  DW_OP_LLVM_fragment = 0x1000,         ///< Only used in LLVM metadata.
+  DW_OP_LLVM_convert = 0x1001,          ///< Only used in LLVM metadata.
+  DW_OP_LLVM_tag_offset = 0x1002,       ///< Only used in LLVM metadata.
+  DW_OP_LLVM_entry_value = 0x1003,      ///< Only used in LLVM metadata.
+  DW_OP_LLVM_implicit_pointer = 0x1004, ///< Only used in LLVM metadata.
 };
 
 enum TypeKind : uint8_t {

llvm/lib/BinaryFormat/Dwarf.cpp

@@ -151,6 +151,8 @@ StringRef llvm::dwarf::OperationEncodingString(unsigned Encoding) {
     return "DW_OP_LLVM_tag_offset";
   case DW_OP_LLVM_entry_value:
     return "DW_OP_LLVM_entry_value";
+  case DW_OP_LLVM_implicit_pointer:
+    return "DW_OP_LLVM_implicit_pointer";
   }
 }
 
@@ -163,6 +165,7 @@ unsigned llvm::dwarf::getOperationEncoding(StringRef OperationEncodingString) {
       .Case("DW_OP_LLVM_fragment", DW_OP_LLVM_fragment)
       .Case("DW_OP_LLVM_tag_offset", DW_OP_LLVM_tag_offset)
       .Case("DW_OP_LLVM_entry_value", DW_OP_LLVM_entry_value)
+      .Case("DW_OP_LLVM_implicit_pointer", DW_OP_LLVM_implicit_pointer)
       .Default(0);
 }
 

llvm/lib/IR/DebugInfoMetadata.cpp

@@ -1114,6 +1114,7 @@ bool DIExpression::isValid() const {
       return I->get() == expr_op_begin()->get() && I->getArg(0) == 1 &&
              getNumElements() == 2;
     }
+    case dwarf::DW_OP_LLVM_implicit_pointer:
     case dwarf::DW_OP_LLVM_convert:
     case dwarf::DW_OP_LLVM_tag_offset:
     case dwarf::DW_OP_constu:

llvm/test/DebugInfo/X86/LLVM_implicit_pointer.ll

@@ -0,0 +1,87 @@
+; Round trip test for DW_OP_LLVM_implicit_pointer metadata
+
+; RUN: llvm-as < %s | llvm-dis | FileCheck %s
+
+;---------------------------
+;static const char *b = "opq";
+;volatile int v;
+;int main() {
+;  int var = 4;
+;  int *ptr1;
+;  int **ptr2;
+;
+;  v++;
+;  ptr1 = &var;
+;  ptr2 = &ptr1;
+;  v++;
+;
+;  return *ptr1 - 5 + **ptr2;
+;}
+;---------------------------
+
+; ModuleID = 'LLVM_implicit_pointer.c'
+source_filename = "LLVM_implicit_pointer.c"
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@v = dso_local global i32 0, align 4, !dbg !0
+
+; Function Attrs: nofree norecurse nounwind uwtable
+define dso_local i32 @main() local_unnamed_addr !dbg !12 {
+entry:
+; CHECK: call void @llvm.dbg.value(metadata i32 4, metadata [[VAR:![0-9]+]], metadata !DIExpression())
+  call void @llvm.dbg.value(metadata i32 4, metadata !16, metadata !DIExpression()), !dbg !21
+  %0 = load volatile i32, i32* @v, align 4, !dbg !22, !tbaa !23
+  %inc = add nsw i32 %0, 1, !dbg !22
+  store volatile i32 %inc, i32* @v, align 4, !dbg !22, !tbaa !23
+
+; CHECK: call void @llvm.dbg.value(metadata i32 4, metadata [[PTR1:![0-9]+]], metadata !DIExpression(DW_OP_LLVM_implicit_pointer))
+  call void @llvm.dbg.value(metadata i32 4, metadata !17, metadata !DIExpression(DW_OP_LLVM_implicit_pointer)), !dbg !21
+
+; CHECK: call void @llvm.dbg.value(metadata i32 4, metadata [[PTR2:![0-9]+]], metadata !DIExpression(DW_OP_LLVM_implicit_pointer, DW_OP_LLVM_implicit_pointer))
+  call void @llvm.dbg.value(metadata i32 4, metadata !19, metadata !DIExpression(DW_OP_LLVM_implicit_pointer, DW_OP_LLVM_implicit_pointer)), !dbg !21
+  %1 = load volatile i32, i32* @v, align 4, !dbg !27, !tbaa !23
+  %inc1 = add nsw i32 %1, 1, !dbg !27
+  store volatile i32 %inc1, i32* @v, align 4, !dbg !27, !tbaa !23
+  ret i32 3, !dbg !28
+}
+
+; Function Attrs: nofree nosync nounwind readnone speculatable willreturn
+declare void @llvm.dbg.value(metadata, metadata, metadata) #1
+
+!llvm.dbg.cu = !{!2}
+!llvm.module.flags = !{!8, !9, !10}
+!llvm.ident = !{!11}
+
+!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
+!1 = distinct !DIGlobalVariable(name: "v", scope: !2, file: !3, line: 2, type: !6, isLocal: false, isDefinition: true)
+!2 = distinct !DICompileUnit(language: DW_LANG_C99, file: !3, producer: "clang version 12.0.0", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !4, globals: !5, splitDebugInlining: false, nameTableKind: None)
+!3 = !DIFile(filename: "LLVM_implicit_pointer.c", directory: "/dir", checksumkind: CSK_MD5, checksum: "218aaa8dc9f04b056b56d944d06383dd")
+!4 = !{}
+!5 = !{!0}
+!6 = !DIDerivedType(tag: DW_TAG_volatile_type, baseType: !7)
+!7 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
+!8 = !{i32 7, !"Dwarf Version", i32 5}
+!9 = !{i32 2, !"Debug Info Version", i32 3}
+!10 = !{i32 1, !"wchar_size", i32 4}
+!11 = !{!"clang version 12.0.0"}
+!12 = distinct !DISubprogram(name: "main", scope: !3, file: !3, line: 3, type: !13, scopeLine: 3, flags: DIFlagAllCallsDescribed, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !2, retainedNodes: !15)
+!13 = !DISubroutineType(types: !14)
+!14 = !{!7}
+!15 = !{!16, !17, !19}
+; CHECK: [[VAR]] = !DILocalVariable(name: "var"
+!16 = !DILocalVariable(name: "var", scope: !12, file: !3, line: 4, type: !7)
+; CHECK: [[PTR1]] = !DILocalVariable(name: "ptr1"
+!17 = !DILocalVariable(name: "ptr1", scope: !12, file: !3, line: 5, type: !18)
+!18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !7, size: 64)
+; CHECK: [[PTR2]] = !DILocalVariable(name: "ptr2"
+!19 = !DILocalVariable(name: "ptr2", scope: !12, file: !3, line: 6, type: !20)
+!20 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !18, size: 64)
+!21 = !DILocation(line: 0, scope: !12)
+!22 = !DILocation(line: 8, column: 4, scope: !12)
+!23 = !{!24, !24, i64 0}
+!24 = !{!"int", !25, i64 0}
+!25 = !{!"omnipotent char", !26, i64 0}
+!26 = !{!"Simple C/C++ TBAA"}
+!27 = !DILocation(line: 11, column: 4, scope: !12)
+!28 = !DILocation(line: 13, column: 3, scope: !12)