[BOLT][DWARF] Fix handling of CUs without TU reference

[ayermolo]

Summary

When input is DWP with DWARF5 bolt wasn't handling correctly CUs that didn't
have TU references. Which resulted in a crash.

[ayermolo]

Added code + command used to generate helper file.

[maksfb]

LGTM. Remove “Summary:” from the title before committing.

bolt/lib/Rewrite/DWARFRewriter.cpp

 }
 
 static void extractTypesFromDWPDWARF5(
     const MCObjectFileInfo &MCOFI, const DWARFUnitIndex &TUIndex,
     const DWARFRewriter::DebugTypesSignaturesPerCUMap &TypeSignaturesPerCU,
     MCStreamer &Streamer, StringRef Contents, uint64_t DWOId) {
   std::vector<const DWARFUnitIndex::Entry::SectionContribution *>
       TUContributions;
+  if (!TypeSignaturesPerCU.count(DWOId))
+    return;
   for (const uint64_t Val : TypeSignaturesPerCU.at(DWOId)) {
     const DWARFUnitIndex::Entry *TUE = TUIndex.getFromHash(Val);
     const DWARFUnitIndex::Entry::SectionContribution *C =
         TUE->getContribution(DWARFSectionKind::DW_SECT_INFO);
     TUContributions.push_back(C);
   }
   // Sorting so it's easy to compare output.
   // They should be sharing the same Abbrev.

bolt/test/X86/Inputs/dwarf5-ftypes-split-dwarf-helper.s

+# clang++ helper.cpp -g2 -gsplit-dwarf=split -gdwarf-5 -fdebug-types-section -S
+# int foo() {
+#   return 0;
+# }
+  .text
+  .file "helper.cpp"
+  .globl  _Z3foov                         # -- Begin function _Z3foov
+  .p2align  4, 0x90
+  .type _Z3foov,@function
+_Z3foov:                                # @_Z3foov
+.Lfunc_begin0:
+  .file 0 "." "helper.cpp" md5 0x95a4a33e7fe9423970d3c798fdf8ed43
+  .loc  0 1 0                           # helper.cpp:1:0
+  .cfi_startproc
+# %bb.0:                                # %entry
+  pushq %rbp
+  .cfi_def_cfa_offset 16
+  .cfi_offset %rbp, -16
+  movq  %rsp, %rbp
+  .cfi_def_cfa_register %rbp
+.Ltmp0:
+  .loc  0 2 3 prologue_end              # helper.cpp:2:3
+  xorl  %eax, %eax
+  .loc  0 2 3 epilogue_begin is_stmt 0  # helper.cpp:2:3
+  popq  %rbp
+  .cfi_def_cfa %rsp, 8
+  retq
+.Ltmp1:
+.Lfunc_end0:
+  .size _Z3foov, .Lfunc_end0-_Z3foov
+  .cfi_endproc
+                                        # -- End function
+  .section  .debug_abbrev,"",@progbits
+  .byte 1                               # Abbreviation Code
+  .byte 74                              # DW_TAG_skeleton_unit
+  .byte 0                               # DW_CHILDREN_no
+  .byte 16                              # DW_AT_stmt_list
+  .byte 23                              # DW_FORM_sec_offset
+  .byte 114                             # DW_AT_str_offsets_base
+  .byte 23                              # DW_FORM_sec_offset
+  .byte 27                              # DW_AT_comp_dir
+  .byte 37                              # DW_FORM_strx1
+  .ascii  "\264B"                         # DW_AT_GNU_pubnames
+  .byte 25                              # DW_FORM_flag_present
+  .byte 118                             # DW_AT_dwo_name
+  .byte 37                              # DW_FORM_strx1
+  .byte 17                              # DW_AT_low_pc
+  .byte 27                              # DW_FORM_addrx
+  .byte 18                              # DW_AT_high_pc
+  .byte 6                               # DW_FORM_data4
+  .byte 115                             # DW_AT_addr_base
+  .byte 23                              # DW_FORM_sec_offset
+  .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 4                               # DWARF Unit Type
+  .byte 8                               # Address Size (in bytes)
+  .long .debug_abbrev                   # Offset Into Abbrev. Section
+  .quad -1360665163647638292
+  .byte 1                               # Abbrev [1] 0x14:0x14 DW_TAG_skeleton_unit
+  .long .Lline_table_start0             # DW_AT_stmt_list
+  .long .Lstr_offsets_base0             # DW_AT_str_offsets_base
+  .byte 0                               # DW_AT_comp_dir
+                                        # DW_AT_GNU_pubnames
+  .byte 1                               # DW_AT_dwo_name
+  .byte 0                               # DW_AT_low_pc
+  .long .Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+  .long .Laddr_table_base0              # DW_AT_addr_base
+.Ldebug_info_end0:
+  .section  .debug_str_offsets,"",@progbits
+  .long 12                              # Length of String Offsets Set
+  .short  5
+  .short  0
+.Lstr_offsets_base0:
+  .section  .debug_str,"MS",@progbits,1
+.Lskel_string0:
+  .asciz  "." # string offset=0
+.Lskel_string1:
+  .asciz  "helper.dwo"                    # string offset=50
+  .section  .debug_str_offsets,"",@progbits
+  .long .Lskel_string0
+  .long .Lskel_string1
+  .section  .debug_str_offsets.dwo,"e",@progbits
+  .long 28                              # Length of String Offsets Set
+  .short  5
+  .short  0
+  .section  .debug_str.dwo,"eMS",@progbits,1
+.Linfo_string0:
+  .asciz  "_Z3foov"                       # string offset=0
+.Linfo_string1:
+  .asciz  "foo"                           # string offset=8
+.Linfo_string2:
+  .asciz  "int"                           # string offset=12
+.Linfo_string3:
+  .asciz  "clang version 17.0.0 (https://github.com/llvm/llvm-project.git c8bb7c234c6814b80e2be27eba9718de7ab1ad79)" # string offset=16
+.Linfo_string4:
+  .asciz  "helper.cpp"                    # string offset=121
+.Linfo_string5:
+  .asciz  "helper.dwo"                    # string offset=132
+  .section  .debug_str_offsets.dwo,"e",@progbits
+  .long 0
+  .long 8
+  .long 12
+  .long 16
+  .long 121
+  .long 132
+  .section  .debug_info.dwo,"e",@progbits
+  .long .Ldebug_info_dwo_end0-.Ldebug_info_dwo_start0 # Length of Unit
+.Ldebug_info_dwo_start0:
+  .short  5                               # DWARF version number
+  .byte 5                               # DWARF Unit Type
+  .byte 8                               # Address Size (in bytes)
+  .long 0                               # Offset Into Abbrev. Section
+  .quad -1360665163647638292
+  .byte 1                               # Abbrev [1] 0x14:0x1b DW_TAG_compile_unit
+  .byte 3                               # DW_AT_producer
+  .short  33                              # DW_AT_language
+  .byte 4                               # DW_AT_name
+  .byte 5                               # DW_AT_dwo_name
+  .byte 2                               # Abbrev [2] 0x1a:0x10 DW_TAG_subprogram
+  .byte 0                               # DW_AT_low_pc
+  .long .Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+  .byte 1                               # DW_AT_frame_base
+  .byte 86
+  .byte 0                               # DW_AT_linkage_name
+  .byte 1                               # DW_AT_name
+  .byte 0                               # DW_AT_decl_file
+  .byte 1                               # DW_AT_decl_line
+  .long 42                              # DW_AT_type
+                                        # DW_AT_external
+  .byte 3                               # Abbrev [3] 0x2a:0x4 DW_TAG_base_type
+  .byte 2                               # DW_AT_name
+  .byte 5                               # DW_AT_encoding
+  .byte 4                               # DW_AT_byte_size
+  .byte 0                               # End Of Children Mark
+.Ldebug_info_dwo_end0:
+  .section  .debug_abbrev.dwo,"e",@progbits
+  .byte 1                               # Abbreviation Code
+  .byte 17                              # DW_TAG_compile_unit
+  .byte 1                               # DW_CHILDREN_yes
+  .byte 37                              # DW_AT_producer
+  .byte 37                              # DW_FORM_strx1
+  .byte 19                              # DW_AT_language
+  .byte 5                               # DW_FORM_data2
+  .byte 3                               # DW_AT_name
+  .byte 37                              # DW_FORM_strx1
+  .byte 118                             # DW_AT_dwo_name
+  .byte 37                              # DW_FORM_strx1
+  .byte 0                               # EOM(1)
+  .byte 0                               # EOM(2)
+  .byte 2                               # Abbreviation Code
+  .byte 46                              # DW_TAG_subprogram
+  .byte 0                               # DW_CHILDREN_no
+  .byte 17                              # DW_AT_low_pc
+  .byte 27                              # DW_FORM_addrx
+  .byte 18                              # DW_AT_high_pc
+  .byte 6                               # DW_FORM_data4
+  .byte 64                              # DW_AT_frame_base
+  .byte 24                              # DW_FORM_exprloc
+  .byte 110                             # DW_AT_linkage_name
+  .byte 37                              # DW_FORM_strx1
+  .byte 3                               # DW_AT_name
+  .byte 37                              # DW_FORM_strx1
+  .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 37                              # DW_FORM_strx1
+  .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_addr,"",@progbits
+  .long .Ldebug_addr_end0-.Ldebug_addr_start0 # Length of contribution
+.Ldebug_addr_start0:
+  .short  5                               # DWARF version number
+  .byte 8                               # Address size
+  .byte 0                               # Segment selector size
+.Laddr_table_base0:
+  .quad .Lfunc_begin0
+.Ldebug_addr_end0:
+  .section  .debug_gnu_pubnames,"",@progbits
+  .long .LpubNames_end0-.LpubNames_start0 # Length of Public Names Info
+.LpubNames_start0:
+  .short  2                               # DWARF Version
+  .long .Lcu_begin0                     # Offset of Compilation Unit Info
+  .long 40                              # Compilation Unit Length
+  .long 26                              # DIE offset
+  .byte 48                              # Attributes: FUNCTION, EXTERNAL
+  .asciz  "foo"                           # External Name
+  .long 0                               # End Mark
+.LpubNames_end0:
+  .section  .debug_gnu_pubtypes,"",@progbits
+  .long .LpubTypes_end0-.LpubTypes_start0 # Length of Public Types Info
+.LpubTypes_start0:
+  .short  2                               # DWARF Version
+  .long .Lcu_begin0                     # Offset of Compilation Unit Info
+  .long 40                              # Compilation Unit Length
+  .long 42                              # DIE offset
+  .byte 144                             # Attributes: TYPE, STATIC
+  .asciz  "int"                           # External Name
+  .long 0                               # End Mark
+.LpubTypes_end0:
+  .ident  "clang version 17.0.0 (https://github.com/llvm/llvm-project.git c8bb7c234c6814b80e2be27eba9718de7ab1ad79)"
+  .section  ".note.GNU-stack","",@progbits
+  .addrsig
+  .section  .debug_line,"",@progbits
+.Lline_table_start0:

bolt/test/X86/dwarf5-ftypes-dwp-input-dwo-output.test

 # REQUIRES: system-linux
 ; RUN: rm -rf %t
 ; RUN: mkdir %t
 ; RUN: cd %t
 ; RUN: llvm-mc --split-dwarf-file=main.dwo --triple=x86_64-unknown-linux-gnu \
 ; RUN: --filetype=obj %p/Inputs/dwarf5-ftypes-split-dwarf.s -o=main.o
-; RUN: %clang %cflags -gdwarf-5 -gsplit-dwarf=split main.o -o main.exe
+; RUN: llvm-mc --split-dwarf-file=helper.dwo --triple=x86_64-unknown-linux-gnu \
+; RUN: --filetype=obj %p/Inputs/dwarf5-ftypes-split-dwarf-helper.s -o=helper.o
+; RUN: %clang %cflags -gdwarf-5 -gsplit-dwarf=split main.o helper.o -o main.exe
 ; RUN: llvm-dwp -e main.exe -o main.exe.dwp
 ; RUN: llvm-dwarfdump --show-form --verbose --debug-info main.exe.dwp | FileCheck -check-prefix=PRE-BOLT %s
 ; RUN: llvm-dwarfdump --show-form --verbose --debug-tu-index main.exe.dwp | FileCheck -check-prefix=PRE-BOLT-DWP-TU-INDEX %s
 ; RUN: llvm-bolt main.exe -o main.exe.bolt --update-debug-sections
 ; RUN: llvm-dwarfdump --show-form --verbose --debug-info main.dwo.dwo | FileCheck -check-prefix=BOLT %s
 
 ; Test input into bolt a DWP file with TU Index.
 ; Make sure output in the .dwo files has type information.