Fix a crash in DWARFUnit::getInlinedChainForAddress in case of unexpected DWARF information.

[aorlov]

Summary

In some cases a broken or invalid debug info could cause a crash in DWARFUnit::getInlinedChainForAddress during parsing a chain of in-lined functions. This patch fixes this issue.

[dblaikie]

This'll need a test case

[aorlov]

I have added the test file.

[dblaikie]

Seems good enough - though if you're interested in this code being able to handle arbitrarily broken DWARF, this function probably needs to be changed to be able to return some kind of failure (like llvm::Error) for the case where the parent walk reaches DIE types that would never be found in the usual scope chain (ie: something other than inlined_subroutines and lexical_blocks (or lexical_scopes, I can never remember the right tag name)) - because the caller's probably going to be pretty confused by other DIEs appearing in this list.

llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp

DWARFUnit::getInlinedChainForAddress(uint64_t Address,
   assert(InlinedChain.empty());
   // Try to look for subprogram DIEs in the DWO file.
   parseDWO();
   // First, find the subroutine that contains the given address (the leaf
   // of inlined chain).
   DWARFDie SubroutineDIE =
       (DWO ? *DWO : *this).getSubroutineForAddress(Address);
 
-  if (!SubroutineDIE)
+  while (SubroutineDIE) {
+    if (SubroutineDIE.isSubprogramDIE()) {
+      InlinedChain.push_back(SubroutineDIE);
       return;
-
-  while (!SubroutineDIE.isSubprogramDIE()) {
+    }
     if (SubroutineDIE.getTag() == DW_TAG_inlined_subroutine)
       InlinedChain.push_back(SubroutineDIE);
     SubroutineDIE  = SubroutineDIE.getParent();
   }
-  InlinedChain.push_back(SubroutineDIE);
 }
 
 const DWARFUnitIndex &llvm::getDWARFUnitIndex(DWARFContext &Context,
                                               DWARFSectionKind Kind) {
   if (Kind == DW_SECT_INFO)
     return Context.getCUIndex();
   assert(Kind == DW_SECT_EXT_TYPES);
   return Context.getTUIndex();

llvm/test/DebugInfo/invalid-inlined-subroutine.s

+## This test checks how we handle parsing a broken DWARF when 
+## a parent of DW_TAG_inlined_subroutine is anything other than DW_TAG_subprogram.
+
+# REQUIRES: x86-registered-target
+
+# RUN: llvm-mc -filetype=obj -triple=i386-linux-gnu -o %t.o %s
+# RUN: llvm-symbolizer "CODE %t.o 0" \
+# RUN:   | FileCheck %s --strict-whitespace --match-full-lines --implicit-check-not={{.}}
+
+#      CHECK:main
+# CHECK-NEXT:/tmp/test{{/|\\}}test.cpp:2:3
+
+## Generated from:
+##
+## int main() {
+##   return 123;
+## }
+##
+## clang++ --target=i386-linux-gnu test.cpp -g -O2 -std=c++11 -S -o test.s 
+
+  .text
+  .file "test.cpp"
+  .globl  main                            # -- Begin function main
+  .p2align  4, 0x90
+  .type main,@function
+main:                                   # @main
+.Lfunc_begin0:
+  .file 1 "/tmp/test" "test.cpp"
+  .loc  1 1 0                           # test.cpp:1:0
+  .cfi_sections .debug_frame
+  .cfi_startproc
+# %bb.0:                                # %entry
+  .loc  1 2 3 prologue_end              # test.cpp:2:3
+  movl  $123, %eax
+  retl
+.Ltmp0:
+.Lfunc_end0:
+  .size main, .Lfunc_end0-main
+  .cfi_endproc
+                                        # -- End function
+  .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 23                              # DW_FORM_sec_offset
+  .byte 27                              # DW_AT_comp_dir
+  .byte 14                              # DW_FORM_strp
+  .byte 17                              # DW_AT_low_pc
+  .byte 1                               # DW_FORM_addr
+  .byte 18                              # DW_AT_high_pc
+  .byte 6                               # DW_FORM_data4
+  .byte 0                               # EOM(1)
+  .byte 0                               # EOM(2)
+  .byte 2                               # Abbreviation Code
+// Replace DW_TAG_subprogram with DW_TAG_inlined_subroutine
+//  .byte 46                              # DW_TAG_subprogram
+  .byte 29                              # DW_TAG_inlined_subroutine
+  .byte 0                               # DW_CHILDREN_no
+  .byte 17                              # DW_AT_low_pc
+  .byte 1                               # DW_FORM_addr
+  .byte 18                              # DW_AT_high_pc
+  .byte 6                               # DW_FORM_data4
+  .byte 64                              # DW_AT_frame_base
+  .byte 24                              # DW_FORM_exprloc
+  .ascii  "\227B"                         # DW_AT_GNU_all_call_sites
+  .byte 25                              # DW_FORM_flag_present
+  .byte 3                               # DW_AT_name
+  .byte 14                              # DW_FORM_strp
+  .byte 58                              # DW_AT_decl_file
+  .byte 11                              # DW_FORM_data1
+  .byte 59                              # DW_AT_decl_line
+  .byte 11                              # DW_FORM_data1
+  .byte 73                              # DW_AT_type
+  .byte 19                              # DW_FORM_ref4
+  .byte 63                              # DW_AT_external
+  .byte 25                              # DW_FORM_flag_present
+  .byte 0                               # EOM(1)
+  .byte 0                               # EOM(2)
+  .byte 3                               # 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 0                               # EOM(3)
+  .section  .debug_info,"",@progbits
+.Lcu_begin0:
+  .long .Ldebug_info_end0-.Ldebug_info_start0 # Length of Unit
+.Ldebug_info_start0:
+  .short  4                               # DWARF version number
+  .long .debug_abbrev                   # Offset Into Abbrev. Section
+  .byte 4                               # Address Size (in bytes)
+  .byte 1                               # Abbrev [1] 0xb:0x38 DW_TAG_compile_unit
+  .long .Linfo_string0                  # DW_AT_producer
+  .short  26                              # DW_AT_language
+  .long .Linfo_string1                  # DW_AT_name
+  .long .Lline_table_start0             # DW_AT_stmt_list
+  .long .Linfo_string2                  # DW_AT_comp_dir
+  .long .Lfunc_begin0                   # DW_AT_low_pc
+  .long .Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+  .byte 2                               # Abbrev [2] 0x26:0x15 DW_TAG_subprogram
+  .long .Lfunc_begin0                   # DW_AT_low_pc
+  .long .Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+  .byte 1                               # DW_AT_frame_base
+  .byte 84
+                                        # DW_AT_GNU_all_call_sites
+  .long .Linfo_string3                  # DW_AT_name
+  .byte 1                               # DW_AT_decl_file
+  .byte 1                               # DW_AT_decl_line
+  .long 59                              # DW_AT_type
+                                        # DW_AT_external
+  .byte 3                               # Abbrev [3] 0x3b:0x7 DW_TAG_base_type
+  .long .Linfo_string4                  # DW_AT_name
+  .byte 5                               # DW_AT_encoding
+  .byte 4                               # DW_AT_byte_size
+  .byte 0                               # End Of Children Mark
+.Ldebug_info_end0:
+  .section  .debug_str,"MS",@progbits,1
+.Linfo_string0:
+  .asciz  "clang version 13.0.0"
+.Linfo_string1:
+  .asciz  "test.cpp"
+.Linfo_string2:
+  .asciz  "/tmp/test"  # string offset=114
+.Linfo_string3:
+  .asciz  "main"
+.Linfo_string4:
+  .asciz  "int"
+  .ident  "clang version 13.0.0"
+  .section  ".note.GNU-stack","",@progbits
+  .addrsig
+  .section  .debug_line,"",@progbits
+.Lline_table_start0: