[DebugInfo] Report errors when DWARFUnitHeader::applyIndexEntry fails (#89156)

Motivation: LLDB is able to report errors about these scenarios whereas
LLVM's DWARF parser only gives a boolean success/fail. I want to migrate
LLDB to using LLVM's DWARFUnitHeader class, but I don't want to lose
some of the error reporting, so I'm adding it to the LLVM class first.

5 files changed, 152 insertions, 11 deletions

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
index f20e71781f46..80c27aea8931 100644
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
@@ -85,7 +85,7 @@ public:
                 uint64_t *offset_ptr, DWARFSectionKind SectionKind);
   // For units in DWARF Package File, remember the index entry and update
   // the abbreviation offset read by extract().
-  bool applyIndexEntry(const DWARFUnitIndex::Entry *Entry);
+  Error applyIndexEntry(const DWARFUnitIndex::Entry *Entry);
   uint64_t getOffset() const { return Offset; }
   const dwarf::FormParams &getFormParams() const { return FormParams; }
   uint16_t getVersion() const { return FormParams.Version; }
diff --git a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
index 9f455fa7e96a..bdd04b00f557 100644
--- a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
@@ -98,8 +98,12 @@ void DWARFUnitVector::addUnitsImpl(
         if (!IndexEntry)
           IndexEntry = Index.getFromOffset(Header.getOffset());
       }
-      if (IndexEntry && !Header.applyIndexEntry(IndexEntry))
-        return nullptr;
+      if (IndexEntry) {
+        if (Error ApplicationErr = Header.applyIndexEntry(IndexEntry)) {
+          Context.getWarningHandler()(std::move(ApplicationErr));
+          return nullptr;
+        }
+      }
       std::unique_ptr<DWARFUnit> U;
       if (Header.isTypeUnit())
         U = std::make_unique<DWARFTypeUnit>(Context, InfoSection, Header, DA,
@@ -334,21 +338,40 @@ Error DWARFUnitHeader::extract(DWARFContext &Context,
   return Error::success();
 }
 
-bool DWARFUnitHeader::applyIndexEntry(const DWARFUnitIndex::Entry *Entry) {
+Error DWARFUnitHeader::applyIndexEntry(const DWARFUnitIndex::Entry *Entry) {
   assert(Entry);
   assert(!IndexEntry);
   IndexEntry = Entry;
   if (AbbrOffset)
-    return false;
+    return createStringError(errc::invalid_argument,
+                             "DWARF package unit at offset 0x%8.8" PRIx64
+                             " has a non-zero abbreviation offset",
+                             Offset);
+
   auto *UnitContrib = IndexEntry->getContribution();
-  if (!UnitContrib ||
-      UnitContrib->getLength() != (getLength() + getUnitLengthFieldByteSize()))
-    return false;
+  if (!UnitContrib)
+    return createStringError(errc::invalid_argument,
+                             "DWARF package unit at offset 0x%8.8" PRIx64
+                             " has no contribution index",
+                             Offset);
+
+  uint64_t IndexLength = getLength() + getUnitLengthFieldByteSize();
+  if (UnitContrib->getLength() != IndexLength)
+    return createStringError(errc::invalid_argument,
+                             "DWARF package unit at offset 0x%8.8" PRIx64
+                             " has an inconsistent index (expected: %" PRIu64
+                             ", actual: %" PRIu64 ")",
+                             Offset, UnitContrib->getLength(), IndexLength);
+
   auto *AbbrEntry = IndexEntry->getContribution(DW_SECT_ABBREV);
   if (!AbbrEntry)
-    return false;
+    return createStringError(errc::invalid_argument,
+                             "DWARF package unit at offset 0x%8.8" PRIx64
+                             " missing abbreviation column",
+                             Offset);
+
   AbbrOffset = AbbrEntry->getOffset();
-  return true;
+  return Error::success();
 }
 
 Error DWARFUnit::extractRangeList(uint64_t RangeListOffset,
diff --git a/llvm/test/DebugInfo/X86/invalid-cu-abbrev-contribution-dwp.s b/llvm/test/DebugInfo/X86/invalid-cu-abbrev-contribution-dwp.s
new file mode 100644
index 000000000000..6cc539cf8594
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/invalid-cu-abbrev-contribution-dwp.s
@@ -0,0 +1,58 @@
+# RUN: llvm-mc -triple x86_64-unknown-linux %s -filetype=obj -o - | \
+# RUN:   llvm-dwarfdump -debug-info - 2>&1 | FileCheck %s
+
+# CHECK: warning: DWARF package unit at offset 0x00000000 missing abbreviation column
+
+    .section .debug_abbrev.dwo, "e", @progbits
+.LAbbrBegin:
+    .uleb128 1                  # Abbreviation Code
+    .uleb128 17                 # DW_TAG_compile_unit
+    .byte 0                     # DW_CHILDREN_no
+    .uleb128 3                  # DW_AT_name
+    .uleb128 8                  # DW_FORM_string
+    .uleb128 0x2131             # DW_AT_GNU_dwo_id
+    .uleb128 7                  # DW_FORM_data8
+    .byte 0                     # EOM(1)
+    .byte 0                     # EOM(2)
+    .byte 0                     # EOM(3)
+.LAbbrEnd:
+
+    .section .debug_info.dwo, "e", @progbits
+.LCUBegin:
+    .long .LCUEnd-.LCUVersion   # Length
+.LCUVersion:
+    .short 4                    # Version
+    .long 0                     # Abbrev offset
+    .byte 4                     # Address size
+    .uleb128 1                  # Abbrev [1] DW_TAG_compile_unit
+    .asciz "a.c"                # DW_AT_name
+    .quad 0x1100001122222222    # DW_AT_GNU_dwo_id
+.LCUEnd:
+
+    .section .debug_cu_index, "", @progbits
+## Header:
+    .short 2                    # Version
+    .space 2                    # Padding
+    .long 1                     # Section count (Invalid, should be 2)
+    .long 1                     # Unit count
+    .long 4                     # Slot count
+## Hash Table of Signatures:
+    .quad 0
+    .quad 0
+    .quad 0x1100001122222222
+    .quad 0
+## Parallel Table of Indexes:
+    .long 0
+    .long 0
+    .long 1
+    .long 0
+## Table of Section Offsets:
+## Row 0:
+    .long 1                     # DW_SECT_INFO
+#    .long 3                     # DW_SECT_ABBREV (Intentionally omitted)
+## Row 1:
+    .long .LCUBegin-.debug_info.dwo     # Offset in .debug_info.dwo
+#    .long .LAbbrBegin-.debug_abbrev.dwo # Offset in .debug_abbrev.dwo (Intentionally omitted)
+## Table of Section Sizes:
+    .long .LCUEnd-.LCUBegin           # Size of the contribution in .debug_info.dwo
+    .long .LAbbrEnd-.LAbbrBegin       # Size of the contribution in .debug_abbrev.dwo (Intentionally omitted)
diff --git a/llvm/test/DebugInfo/X86/invalid-cu-abbrev-offset-dwp.s b/llvm/test/DebugInfo/X86/invalid-cu-abbrev-offset-dwp.s
new file mode 100644
index 000000000000..b9e769e3ed4a
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/invalid-cu-abbrev-offset-dwp.s
@@ -0,0 +1,58 @@
+# RUN: llvm-mc -triple x86_64-unknown-linux %s -filetype=obj -o - | \
+# RUN:   llvm-dwarfdump -debug-info - 2>&1 | FileCheck %s
+
+# CHECK: warning: DWARF package unit at offset 0x00000000 has a non-zero abbreviation offset
+
+    .section .debug_abbrev.dwo, "e", @progbits
+.LAbbrBegin:
+    .uleb128 1                  # Abbreviation Code
+    .uleb128 17                 # DW_TAG_compile_unit
+    .byte 0                     # DW_CHILDREN_no
+    .uleb128 3                  # DW_AT_name
+    .uleb128 8                  # DW_FORM_string
+    .uleb128 0x2131             # DW_AT_GNU_dwo_id
+    .uleb128 7                  # DW_FORM_data8
+    .byte 0                     # EOM(1)
+    .byte 0                     # EOM(2)
+    .byte 0                     # EOM(3)
+.LAbbrEnd:
+
+    .section .debug_info.dwo, "e", @progbits
+.LCUBegin:
+    .long .LCUEnd-.LCUVersion   # Length
+.LCUVersion:
+    .short 4                    # Version
+    .long 1                     # Abbrev offset (Invalid, should be 0)
+    .byte 4                     # Address size
+    .uleb128 1                  # Abbrev [1] DW_TAG_compile_unit
+    .asciz "a.c"                # DW_AT_name
+    .quad 0x1100001122222222    # DW_AT_GNU_dwo_id
+.LCUEnd:
+
+    .section .debug_cu_index, "", @progbits
+## Header:
+    .short 2                    # Version
+    .space 2                    # Padding
+    .long 2                     # Section count
+    .long 1                     # Unit count
+    .long 4                     # Slot count
+## Hash Table of Signatures:
+    .quad 0
+    .quad 0
+    .quad 0x1100001122222222
+    .quad 0
+## Parallel Table of Indexes:
+    .long 0
+    .long 0
+    .long 1
+    .long 0
+## Table of Section Offsets:
+## Row 0:
+    .long 1                     # DW_SECT_INFO
+    .long 3                     # DW_SECT_ABBREV
+## Row 1:
+    .long .LCUBegin-.debug_info.dwo     # Offset in .debug_info.dwo
+    .long .LAbbrBegin-.debug_abbrev.dwo # Offset in .debug_abbrev.dwo
+## Table of Section Sizes:
+    .long .LCUEnd-.LCUBegin
+    .long .LAbbrEnd-.LAbbrBegin
diff --git a/llvm/test/DebugInfo/X86/invalid-cu-length-dwp.s b/llvm/test/DebugInfo/X86/invalid-cu-length-dwp.s
index 299bea1bf1a7..d67416736093 100644
--- a/llvm/test/DebugInfo/X86/invalid-cu-length-dwp.s
+++ b/llvm/test/DebugInfo/X86/invalid-cu-length-dwp.s
@@ -1,9 +1,11 @@
 # RUN: llvm-mc -triple x86_64-unknown-linux %s -filetype=obj -o - | \
-# RUN:   llvm-dwarfdump -debug-info -
+# RUN:   llvm-dwarfdump -debug-info - 2>&1 | FileCheck %s
 
 ## llvm-dwarfdump used to crash with this input because of an invalid size
 ## of the compilation unit contribution in the .debug_cu_index section.
 
+# CHECK: warning: DWARF package unit at offset 0x00000000 has an inconsistent index (expected: 23, actual: 24)
+
     .section .debug_abbrev.dwo, "e", @progbits
 .LAbbrBegin:
     .uleb128 1                  # Abbreviation Code