[DWARF] Check that all fields of a Unit Header are read.

[ikudrin]

Summary

Tests dwarfdump-rnglists-dwarf64.s and dwarfdump-rnglists.s were malformed because they had missing required DWO ID fields in split compilation unit headers. The patch fixes the tests and checks the reading of a unit header more thoroughly.

[dblaikie]

might be worth keeping/duplicating one of the bad test cases to show the new & improved error handling?

[ikudrin]

• Add a test for a CU with missing fields which was considered valid before the patch.

[dblaikie]

Sounds good - thanks!

llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp

 
 bool DWARFUnitHeader::extract(DWARFContext &Context,
                               const DWARFDataExtractor &debug_info,
                               uint64_t *offset_ptr,
                               DWARFSectionKind SectionKind,
                               const DWARFUnitIndex *Index,
                               const DWARFUnitIndex::Entry *Entry) {
   Offset = *offset_ptr;
+  Error Err = Error::success();
   IndexEntry = Entry;
   if (!IndexEntry && Index)
     IndexEntry = Index->getFromOffset(*offset_ptr);
-  Length = debug_info.getRelocatedValue(4, offset_ptr);
+  Length = debug_info.getRelocatedValue(4, offset_ptr, nullptr, &Err);
   FormParams.Format = DWARF32;
   if (Length == dwarf::DW_LENGTH_DWARF64) {
-    Length = debug_info.getU64(offset_ptr);
+    Length = debug_info.getU64(offset_ptr, &Err);
     FormParams.Format = DWARF64;
   }
-  FormParams.Version = debug_info.getU16(offset_ptr);
+  FormParams.Version = debug_info.getU16(offset_ptr, &Err);
   if (FormParams.Version >= 5) {
-    UnitType = debug_info.getU8(offset_ptr);
-    FormParams.AddrSize = debug_info.getU8(offset_ptr);
-    AbbrOffset = debug_info.getRelocatedValue(FormParams.getDwarfOffsetByteSize(), offset_ptr);
+    UnitType = debug_info.getU8(offset_ptr, &Err);
+    FormParams.AddrSize = debug_info.getU8(offset_ptr, &Err);
+    AbbrOffset = debug_info.getRelocatedValue(
+        FormParams.getDwarfOffsetByteSize(), offset_ptr, nullptr, &Err);
   } else {
-    AbbrOffset = debug_info.getRelocatedValue(FormParams.getDwarfOffsetByteSize(), offset_ptr);
-    FormParams.AddrSize = debug_info.getU8(offset_ptr);
+    AbbrOffset = debug_info.getRelocatedValue(
+        FormParams.getDwarfOffsetByteSize(), offset_ptr, nullptr, &Err);
+    FormParams.AddrSize = debug_info.getU8(offset_ptr, &Err);
     // Fake a unit type based on the section type.  This isn't perfect,
     // but distinguishing compile and type units is generally enough.
     if (SectionKind == DW_SECT_TYPES)
       UnitType = DW_UT_type;
     else
       UnitType = DW_UT_compile;
   }
   if (IndexEntry) {
     if (AbbrOffset)
       return false;
     auto *UnitContrib = IndexEntry->getOffset();
     if (!UnitContrib || UnitContrib->Length != (Length + 4))
       return false;
     auto *AbbrEntry = IndexEntry->getOffset(DW_SECT_ABBREV);
     if (!AbbrEntry)
       return false;
     AbbrOffset = AbbrEntry->Offset;
   }
   if (isTypeUnit()) {
-    TypeHash = debug_info.getU64(offset_ptr);
-    TypeOffset =
-        debug_info.getUnsigned(offset_ptr, FormParams.getDwarfOffsetByteSize());
+    TypeHash = debug_info.getU64(offset_ptr, &Err);
+    TypeOffset = debug_info.getUnsigned(
+        offset_ptr, FormParams.getDwarfOffsetByteSize(), &Err);
   } else if (UnitType == DW_UT_split_compile || UnitType == DW_UT_skeleton)
-    DWOId = debug_info.getU64(offset_ptr);
+    DWOId = debug_info.getU64(offset_ptr, &Err);
+
+  if (errorToBool(std::move(Err)))
+    return false;
 
   // Header fields all parsed, capture the size of this unit header.
   assert(*offset_ptr - Offset <= 255 && "unexpected header size");
   Size = uint8_t(*offset_ptr - Offset);
 
   // Type offset is unit-relative; should be after the header and before
   // the end of the current unit.
   bool TypeOffsetOK =

llvm/test/DebugInfo/X86/dwarfdump-rnglists-dwarf64.s

 # DWARF v5 split CU header.
         .long 0xffffffff       # DWARF64 mark
         .quad  CU_split_5_64_end-CU_split_5_64_version  # Length of Unit
 CU_split_5_64_version:
         .short 5               # DWARF version number
         .byte 5                # DWARF Unit Type
         .byte 4                # Address Size (in bytes)
         .quad 0                # Offset Into Abbrev Section
+        .quad 0xdeadbeefbaadf00d  # DWO id
 # The compile-unit DIE, which has DW_AT_rnglists_base and DW_AT_ranges.
         .byte 1                # Abbreviation code
         .uleb128 1             # DW_AT_ranges
 CU_split_5_64_end:
 
         .section .debug_rnglists,"",@progbits
 # A rnglist table with 2 range lists. The first one uses DW_RLE_start_end
 # and DW_RLE_start_length. The second one uses DW_RLE_base_address and

llvm/test/DebugInfo/X86/dwarfdump-rnglists.s

 
 # DWARF v5 split CU header.
         .long  CU_split_5_end-CU_split_5_version  # Length of Unit
 CU_split_5_version:
         .short 5               # DWARF version number
         .byte 5                # DWARF Unit Type
         .byte 4                # Address Size (in bytes)
         .long 0                # Offset Into Abbrev Section
+        .quad 0xdeadbeefbaadf00d  # DWO id
 # The compile-unit DIE, which has DW_AT_rnglists_base and DW_AT_ranges.
         .byte 1                # Abbreviation code
         .uleb128 1             # DW_AT_ranges
         .byte 0                # NULL
 CU_split_5_end:
 
         .section .debug_rnglists,"",@progbits
 # A rnglist table with 2 range lists. The first one uses DW_RLE_start_end

llvm/test/DebugInfo/X86/invalid-unit-header.s

+# RUN: llvm-mc -triple x86_64-unknown-linux %s -filetype=obj -o - | \
+# RUN:   llvm-dwarfdump -debug-info - | \
+# RUN:   FileCheck %s
+
+        .section .debug_abbrev.dwo,"",@progbits
+        .byte 0x01  # Abbrev code
+        .byte 0x11  # DW_TAG_compile_unit
+        .byte 0x00  # DW_CHILDREN_no
+        .byte 0x13  # DW_AT_language
+        .byte 0x05  # DW_FORM_data2
+        .byte 0x00  # EOM(1)
+        .byte 0x00  # EOM(2)
+        .byte 0x00  # EOM(3)
+
+# The CU was considered valid even though there were some required fields
+# missing in the header.
+        .section .debug_info.dwo,"",@progbits
+        .long .CUend - .CUver   # Length of Unit
+.CUver:
+        .short 5                # DWARF version number
+        .byte 5                 # DW_UT_split_compile
+        .byte 4                 # Address Size (in bytes)
+        # .long 0               # Missing: Offset Into Abbrev Section
+        # .quad 0               # Missing: DWO id
+        .byte 1                 # Abbreviation code
+        .short 4                # DW_LANG_C_plus_plus
+.CUend:
+
+# CHECK-NOT: Compile Unit: