[lldb/DWARF] Make sure bad abbreviation codes do not crash lldb (#93006)

We currently cannot represent abbreviation codes with more than 16 bits,
and we were lldb-asserting if we ever ran into one. While I haven't seen
any real DWARF with these kinds of abbreviations, it is possible to hit
this with handcrafted evil dwarf, due some sort of corruptions, or just
bugs (the addition of PeekDIEName makes these bugs more likely, as the
function blindly dereferences offsets within the debug info section) .

Missing abbreviations were already reporting an error. This patch turns
sure that large abbreviations into an error as well, and adds a test for
both cases.

Author: labath

lldb/source/Plugins/SymbolFile/DWARF/DWARFDebugInfoEntry.cpp

@@ -11,6 +11,7 @@
 #include <cassert>
 
 #include <algorithm>
+#include <limits>
 #include <optional>
 
 #include "llvm/Support/LEB128.h"
@@ -41,13 +42,23 @@ extern int g_verbose;
 // Extract a debug info entry for a given DWARFUnit from the data
 // starting at the offset in offset_ptr
 bool DWARFDebugInfoEntry::Extract(const DWARFDataExtractor &data,
-                                  const DWARFUnit *cu,
+                                  const DWARFUnit &unit,
                                   lldb::offset_t *offset_ptr) {
   m_offset = *offset_ptr;
+  auto report_error = [&](const char *fmt, const auto &...vals) {
+    unit.GetSymbolFileDWARF().GetObjectFile()->GetModule()->ReportError(
+        "[{0:x16}]: {1}, please file a bug and "
+        "attach the file at the start of this error message",
+        static_cast<uint64_t>(m_offset), llvm::formatv(fmt, vals...));
+    *offset_ptr = std::numeric_limits<lldb::offset_t>::max();
+    return false;
+  };
+
   m_parent_idx = 0;
   m_sibling_idx = 0;
   const uint64_t abbr_idx = data.GetULEB128(offset_ptr);
-  lldbassert(abbr_idx <= UINT16_MAX);
+  if (abbr_idx > std::numeric_limits<uint16_t>::max())
+    return report_error("abbreviation code {0} too big", abbr_idx);
   m_abbr_idx = abbr_idx;
 
   if (m_abbr_idx == 0) {
@@ -56,31 +67,18 @@ bool DWARFDebugInfoEntry::Extract(const DWARFDataExtractor &data,
     return true; // NULL debug tag entry
   }
 
-  const auto *abbrevDecl = GetAbbreviationDeclarationPtr(cu);
-  if (abbrevDecl == nullptr) {
-    cu->GetSymbolFileDWARF().GetObjectFile()->GetModule()->ReportError(
-        "[{0:x16}]: invalid abbreviation code {1}, "
-        "please file a bug and "
-        "attach the file at the start of this error message",
-        (uint64_t)m_offset, (unsigned)abbr_idx);
-    // WE can't parse anymore if the DWARF is borked...
-    *offset_ptr = UINT32_MAX;
-    return false;
-  }
+  const auto *abbrevDecl = GetAbbreviationDeclarationPtr(&unit);
+  if (abbrevDecl == nullptr)
+    return report_error("invalid abbreviation code {0}", abbr_idx);
+
   m_tag = abbrevDecl->getTag();
   m_has_children = abbrevDecl->hasChildren();
   // Skip all data in the .debug_info or .debug_types for the attributes
   for (const auto &attribute : abbrevDecl->attributes()) {
-    if (DWARFFormValue::SkipValue(attribute.Form, data, offset_ptr, cu))
+    if (DWARFFormValue::SkipValue(attribute.Form, data, offset_ptr, &unit))
       continue;
 
-    cu->GetSymbolFileDWARF().GetObjectFile()->GetModule()->ReportError(
-        "[{0:x16}]: Unsupported DW_FORM_{1:x}, please file a bug "
-        "and "
-        "attach the file at the start of this error message",
-        (uint64_t)m_offset, (unsigned)attribute.Form);
-    *offset_ptr = m_offset;
-    return false;
+    return report_error("Unsupported DW_FORM_{1:x}", attribute.Form);
   }
   return true;
 }

lldb/source/Plugins/SymbolFile/DWARF/DWARFDebugInfoEntry.h

@@ -49,7 +49,7 @@ class DWARFDebugInfoEntry {
   void BuildFunctionAddressRangeTable(DWARFUnit *cu,
                                       DWARFDebugAranges *debug_aranges) const;
 
-  bool Extract(const DWARFDataExtractor &data, const DWARFUnit *cu,
+  bool Extract(const DWARFDataExtractor &data, const DWARFUnit &cu,
                lldb::offset_t *offset_ptr);
 
   using Recurse = DWARFBaseDIE::Recurse;

lldb/source/Plugins/SymbolFile/DWARF/DWARFUnit.cpp

@@ -63,7 +63,7 @@ void DWARFUnit::ExtractUnitDIENoDwoIfNeeded() {
   // parse
   const DWARFDataExtractor &data = GetData();
   if (offset < GetNextUnitOffset() &&
-      m_first_die.Extract(data, this, &offset)) {
+      m_first_die.Extract(data, *this, &offset)) {
     AddUnitDIE(m_first_die);
     return;
   }
@@ -242,7 +242,7 @@ void DWARFUnit::ExtractDIEsRWLocked() {
   die_index_stack.reserve(32);
   die_index_stack.push_back(0);
   bool prev_die_had_children = false;
-  while (offset < next_cu_offset && die.Extract(data, this, &offset)) {
+  while (offset < next_cu_offset && die.Extract(data, *this, &offset)) {
     const bool null_die = die.IsNULL();
     if (depth == 0) {
       assert(m_die_array.empty() && "Compile unit DIE already added");
@@ -670,7 +670,7 @@ DWARFUnit::GetDIE(dw_offset_t die_offset) {
 
 llvm::StringRef DWARFUnit::PeekDIEName(dw_offset_t die_offset) {
   DWARFDebugInfoEntry die;
-  if (!die.Extract(GetData(), this, &die_offset))
+  if (!die.Extract(GetData(), *this, &die_offset))
     return llvm::StringRef();
 
   // Does die contain a DW_AT_Name?

lldb/test/Shell/SymbolFile/DWARF/x86/invalid_abbreviation.s

@@ -0,0 +1,47 @@
+# REQUIRES: x86
+
+# RUN: llvm-mc -triple=x86_64-pc-linux -filetype=obj %s > %t
+# RUN: %lldb %t \
+# RUN:   -o exit 2>&1 | FileCheck %s
+
+# CHECK-DAG: error: {{.*}} [0x0000000000000022]: abbreviation code 65536 too big, please file a bug and attach the file at the start of this error message
+# CHECK-DAG: error: {{.*}} [0x0000000000000048]: invalid abbreviation code 47, please file a bug and attach the file at the start of this error message
+
+
+        .section        .debug_abbrev,"",@progbits
+        .uleb128 65535                  # Largest representable Abbreviation Code
+        .byte   17                      # DW_TAG_compile_unit
+        .byte   1                       # DW_CHILDREN_yes
+        .byte   37                      # DW_AT_producer
+        .byte   8                       # DW_FORM_string
+        .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  5                       # DWARF version number
+        .byte   1                       # DWARF Unit Type
+        .byte   8                       # Address Size (in bytes)
+        .long   .debug_abbrev           # Offset Into Abbrev. Section
+        .uleb128 65535                  # DW_TAG_compile_unit
+        .asciz  "Hand-written DWARF"    # DW_AT_producer
+        .uleb128 65536                  # Unrepresentable abbreviation
+        .byte   0                       # End Of Children Mark
+.Ldebug_info_end0:
+
+        .section        .debug_info,"",@progbits
+.Lcu_begin1:
+        .long   .Ldebug_info_end1-.Ldebug_info_start1 # Length of Unit
+.Ldebug_info_start1:
+        .short  5                       # DWARF version number
+        .byte   1                       # DWARF Unit Type
+        .byte   8                       # Address Size (in bytes)
+        .long   .debug_abbrev           # Offset Into Abbrev. Section
+        .uleb128 65535                  # DW_TAG_compile_unit
+        .asciz  "Hand-written DWARF"    # DW_AT_producer
+        .byte   47                      # Missing abbreviation
+        .byte   0                       # End Of Children Mark
+.Ldebug_info_end1: