[Debug-Info][llvm-dwarfdump] Don't try to dump location

list for attributes that don't have the loclist class.

Summary: The overflow error occurs when we try to dump
location list for those attributes that do not have the
loclist class, like DW_AT_count and DW_AT_byte_size.
After re-reviewed the entire list, I sorted those
attributes into two parts, one for dumping location list
and one for dumping the location expression.

Reviewed By: probinson

Differential Revision: https://reviews.llvm.org/D105613

include/llvm/DebugInfo/DWARF/DWARFAttribute.h

@@ -39,9 +39,12 @@ struct DWARFAttribute {
     return isValid();
   }
 
+  /// Identify DWARF attributes that may contain a pointer to a location list.
+  static bool mayHaveLocationList(dwarf::Attribute Attr);
+
   /// Identifies DWARF attributes that may contain a reference to a
   /// DWARF expression.
-  static bool mayHaveLocationDescription(dwarf::Attribute Attr);
+  static bool mayHaveLocationExpr(dwarf::Attribute Attr);
 };
 
 } // end namespace llvm

lib/DWARFLinker/DWARFLinker.cpp

@@ -1029,7 +1029,7 @@ unsigned DWARFLinker::DIECloner::cloneBlockAttribute(
   // buffer using cloneExpression(), otherwise copy the data directly.
   SmallVector<uint8_t, 32> Buffer;
   ArrayRef<uint8_t> Bytes = *Val.getAsBlock();
-  if (DWARFAttribute::mayHaveLocationDescription(AttrSpec.Attr) &&
+  if (DWARFAttribute::mayHaveLocationExpr(AttrSpec.Attr) &&
       (Val.isFormClass(DWARFFormValue::FC_Block) ||
        Val.isFormClass(DWARFFormValue::FC_Exprloc))) {
     DWARFUnit &OrigUnit = Unit.getOrigUnit();

lib/DebugInfo/DWARF/DWARFDie.cpp

@@ -69,22 +69,13 @@ static void dumpRanges(const DWARFObject &Obj, raw_ostream &OS,
   }
 }
 
-static void dumpLocation(raw_ostream &OS, const DWARFFormValue &FormValue,
+static void dumpLocationList(raw_ostream &OS, const DWARFFormValue &FormValue,
                              DWARFUnit *U, unsigned Indent,
                              DIDumpOptions DumpOpts) {
+  assert(FormValue.isFormClass(DWARFFormValue::FC_SectionOffset) &&
+         "bad FORM for location list");
   DWARFContext &Ctx = U->getContext();
   const MCRegisterInfo *MRI = Ctx.getRegisterInfo();
-  if (FormValue.isFormClass(DWARFFormValue::FC_Block) ||
-      FormValue.isFormClass(DWARFFormValue::FC_Exprloc)) {
-    ArrayRef<uint8_t> Expr = *FormValue.getAsBlock();
-    DataExtractor Data(StringRef((const char *)Expr.data(), Expr.size()),
-                       Ctx.isLittleEndian(), 0);
-    DWARFExpression(Data, U->getAddressByteSize(), U->getFormParams().Format)
-        .print(OS, DumpOpts, MRI, U);
-    return;
-  }
-
-  if (FormValue.isFormClass(DWARFFormValue::FC_SectionOffset)) {
   uint64_t Offset = *FormValue.getAsSectionOffset();
 
   if (FormValue.getForm() == DW_FORM_loclistx) {
@@ -95,13 +86,26 @@ static void dumpLocation(raw_ostream &OS, const DWARFFormValue &FormValue,
     else
       return;
   }
-    U->getLocationTable().dumpLocationList(&Offset, OS, U->getBaseAddress(),
+  U->getLocationTable().dumpLocationList(&Offset, OS, U->getBaseAddress(), MRI,
-                                           MRI, Ctx.getDWARFObj(), U, DumpOpts,
+                                         Ctx.getDWARFObj(), U, DumpOpts,
                                          Indent);
   return;
-  }
+}
 
-  FormValue.dump(OS, DumpOpts);
+static void dumpLocationExpr(raw_ostream &OS, const DWARFFormValue &FormValue,
+                             DWARFUnit *U, unsigned Indent,
+                             DIDumpOptions DumpOpts) {
+  assert((FormValue.isFormClass(DWARFFormValue::FC_Block) ||
+          FormValue.isFormClass(DWARFFormValue::FC_Exprloc)) &&
+         "bad FORM for location expression");
+  DWARFContext &Ctx = U->getContext();
+  const MCRegisterInfo *MRI = Ctx.getRegisterInfo();
+  ArrayRef<uint8_t> Expr = *FormValue.getAsBlock();
+  DataExtractor Data(StringRef((const char *)Expr.data(), Expr.size()),
+                     Ctx.isLittleEndian(), 0);
+  DWARFExpression(Data, U->getAddressByteSize(), U->getFormParams().Format)
+      .print(OS, DumpOpts, MRI, U);
+  return;
 }
 
 /// Dump the name encoded in the type tag.
@@ -289,9 +293,15 @@ static void dumpAttribute(raw_ostream &OS, const DWARFDie &Die,
       else
         FormValue.dump(OS, DumpOpts);
     }
-  } else if (Form == dwarf::Form::DW_FORM_exprloc ||
+  } else if (DWARFAttribute::mayHaveLocationList(Attr) &&
-             DWARFAttribute::mayHaveLocationDescription(Attr))
+             FormValue.isFormClass(DWARFFormValue::FC_SectionOffset))
-    dumpLocation(OS, FormValue, U, sizeof(BaseIndent) + Indent + 4, DumpOpts);
+    dumpLocationList(OS, FormValue, U, sizeof(BaseIndent) + Indent + 4,
+                     DumpOpts);
+  else if (FormValue.isFormClass(DWARFFormValue::FC_Exprloc) ||
+           (DWARFAttribute::mayHaveLocationExpr(Attr) &&
+            FormValue.isFormClass(DWARFFormValue::FC_Block)))
+    dumpLocationExpr(OS, FormValue, U, sizeof(BaseIndent) + Indent + 4,
+                     DumpOpts);
   else
     FormValue.dump(OS, DumpOpts);
 
@@ -744,11 +754,29 @@ DWARFDie::attribute_iterator &DWARFDie::attribute_iterator::operator++() {
   return *this;
 }
 
-bool DWARFAttribute::mayHaveLocationDescription(dwarf::Attribute Attr) {
+bool DWARFAttribute::mayHaveLocationList(dwarf::Attribute Attr) {
+  switch(Attr) {
+  case DW_AT_location:
+  case DW_AT_string_length:
+  case DW_AT_return_addr:
+  case DW_AT_data_member_location:
+  case DW_AT_frame_base:
+  case DW_AT_static_link:
+  case DW_AT_segment:
+  case DW_AT_use_location:
+  case DW_AT_vtable_elem_location:
+    return true;
+  default:
+    return false;
+  }
+}
+
+bool DWARFAttribute::mayHaveLocationExpr(dwarf::Attribute Attr) {
   switch (Attr) {
   // From the DWARF v5 specification.
   case DW_AT_location:
   case DW_AT_byte_size:
+  case DW_AT_bit_offset:
   case DW_AT_bit_size:
   case DW_AT_string_length:
   case DW_AT_lower_bound:
@@ -764,6 +792,7 @@ bool DWARFAttribute::mayHaveLocationDescription(dwarf::Attribute Attr) {
   case DW_AT_vtable_elem_location:
   case DW_AT_allocated:
   case DW_AT_associated:
+  case DW_AT_data_location:
   case DW_AT_byte_stride:
   case DW_AT_rank:
   case DW_AT_call_value:

test/tools/llvm-dwarfdump/X86/formclass3.s

@@ -0,0 +1,149 @@
+# Source:
+#   unsigned char arr[0x100000];
+# Compile with:
+#   clang -O2 -gdwarf-3 -S 1.cpp -o 1.s --target=x86_64-pc-linux-gnu
+
+# RUN: llvm-mc -triple x86_64-pc-linux-gnu -o - -filetype obj < %s | \
+# RUN:   llvm-dwarfdump -debug-info - | FileCheck %s
+
+# CHECK: DW_AT_count (0x00100000)
+
+	.text
+	.file	"1.cpp"
+	.file	1 "/llvm-project" "1.cpp"
+	.type	arr,@object                     # @arr
+	.bss
+	.globl	arr
+	.p2align	4
+arr:
+	.zero	1048576
+	.size	arr, 1048576
+
+	.section	.debug_abbrev,"",@progbits
+	.byte	1                               # Abbreviation Code
+	.byte	17                              # DW_TAG_compile_unit
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	37                              # DW_AT_producer
+	.byte	14                              # DW_FORM_strp
+	.byte	19                              # DW_AT_language
+	.byte	5                               # DW_FORM_data2
+	.byte	3                               # DW_AT_name
+	.byte	14                              # DW_FORM_strp
+	.byte	16                              # DW_AT_stmt_list
+	.byte	6                               # DW_FORM_data4
+	.byte	27                              # DW_AT_comp_dir
+	.byte	14                              # DW_FORM_strp
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	2                               # Abbreviation Code
+	.byte	52                              # DW_TAG_variable
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	14                              # DW_FORM_strp
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	63                              # DW_AT_external
+	.byte	12                              # DW_FORM_flag
+	.byte	58                              # DW_AT_decl_file
+	.byte	11                              # DW_FORM_data1
+	.byte	59                              # DW_AT_decl_line
+	.byte	11                              # DW_FORM_data1
+	.byte	2                               # DW_AT_location
+	.byte	10                              # DW_FORM_block1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	3                               # Abbreviation Code
+	.byte	1                               # DW_TAG_array_type
+	.byte	1                               # DW_CHILDREN_yes
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	4                               # Abbreviation Code
+	.byte	33                              # DW_TAG_subrange_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	73                              # DW_AT_type
+	.byte	19                              # DW_FORM_ref4
+	.byte	55                              # DW_AT_count
+	.byte	6                               # DW_FORM_data4
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	5                               # Abbreviation Code
+	.byte	36                              # DW_TAG_base_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	14                              # DW_FORM_strp
+	.byte	62                              # DW_AT_encoding
+	.byte	11                              # DW_FORM_data1
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	6                               # Abbreviation Code
+	.byte	36                              # DW_TAG_base_type
+	.byte	0                               # DW_CHILDREN_no
+	.byte	3                               # DW_AT_name
+	.byte	14                              # DW_FORM_strp
+	.byte	11                              # DW_AT_byte_size
+	.byte	11                              # DW_FORM_data1
+	.byte	62                              # DW_AT_encoding
+	.byte	11                              # DW_FORM_data1
+	.byte	0                               # EOM(1)
+	.byte	0                               # EOM(2)
+	.byte	0                               # EOM(3)
+	.section	.debug_info,"",@progbits
+.Lcu_begin0:
+	.long	.Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+	.short	3                               # DWARF version number
+	.long	.debug_abbrev                   # Offset Into Abbrev. Section
+	.byte	8                               # Address Size (in bytes)
+	.byte	1                               # Abbrev [1] 0xb:0x47 DW_TAG_compile_unit
+	.long	.Linfo_string0                  # DW_AT_producer
+	.short	33                              # DW_AT_language
+	.long	.Linfo_string1                  # DW_AT_name
+	.long	.Lline_table_start0             # DW_AT_stmt_list
+	.long	.Linfo_string2                  # DW_AT_comp_dir
+	.byte	2                               # Abbrev [2] 0x1e:0x16 DW_TAG_variable
+	.long	.Linfo_string3                  # DW_AT_name
+	.long	52                              # DW_AT_type
+	.byte	1                               # DW_AT_external
+	.byte	1                               # DW_AT_decl_file
+	.byte	1                               # DW_AT_decl_line
+	.byte	9                               # DW_AT_location
+	.byte	3
+	.quad	arr
+	.byte	3                               # Abbrev [3] 0x34:0xf DW_TAG_array_type
+	.long	67                              # DW_AT_type
+	.byte	4                               # Abbrev [4] 0x39:0x9 DW_TAG_subrange_type
+	.long	74                              # DW_AT_type
+	.long	1048576                         # DW_AT_count
+	.byte	0                               # End Of Children Mark
+	.byte	5                               # Abbrev [5] 0x43:0x7 DW_TAG_base_type
+	.long	.Linfo_string4                  # DW_AT_name
+	.byte	8                               # DW_AT_encoding
+	.byte	1                               # DW_AT_byte_size
+	.byte	6                               # Abbrev [6] 0x4a:0x7 DW_TAG_base_type
+	.long	.Linfo_string5                  # DW_AT_name
+	.byte	8                               # DW_AT_byte_size
+	.byte	7                               # DW_AT_encoding
+	.byte	0                               # End Of Children Mark
+.Ldebug_info_end0:
+	.section	.debug_str,"MS",@progbits,1
+.Linfo_string0:
+	.asciz	"clang version 13.0.0"          # string offset=0
+.Linfo_string1:
+	.asciz	"1.cpp"                         # string offset=21
+.Linfo_string2:
+	.asciz	"/llvm-project" # string offset=27
+.Linfo_string3:
+	.asciz	"arr"                           # string offset=61
+.Linfo_string4:
+	.asciz	"unsigned char"                 # string offset=65
+.Linfo_string5:
+	.asciz	"__ARRAY_SIZE_TYPE__"           # string offset=79
+	.ident	"clang version 13.0.0"
+	.section	".note.GNU-stack","",@progbits
+	.addrsig
+	.section	.debug_line,"",@progbits
+.Lline_table_start0: