diff --git a/bolt/lib/Core/DebugData.cpp b/bolt/lib/Core/DebugData.cpp --- a/bolt/lib/Core/DebugData.cpp +++ b/bolt/lib/Core/DebugData.cpp @@ -480,6 +480,7 @@ DWARFDebugAddrTable AddrTable; DIDumpOptions DumpOpts; constexpr uint32_t HeaderSize = 8; + DenseMap UnmodifiedAddressOffsets; for (std::unique_ptr &CU : BC->DwCtx->compile_units()) { const uint64_t CUID = getCUID(*CU.get()); const uint8_t AddrSize = CU->getAddressByteSize(); @@ -494,11 +495,18 @@ // Address base offset is to the first entry. // The size of header is 8 bytes. uint64_t Offset = *BaseOffset - HeaderSize; + auto Iter = UnmodifiedAddressOffsets.find(Offset); + if (Iter != UnmodifiedAddressOffsets.end()) { + DWOIdToOffsetMap[CUID] = Iter->getSecond(); + continue; + } + UnmodifiedAddressOffsets[Offset] = Buffer.size() + HeaderSize; if (Error Err = AddrTable.extract(AddrData, &Offset, 5, AddrSize, DumpOpts.WarningHandler)) { DumpOpts.RecoverableErrorHandler(std::move(Err)); continue; } + uint32_t Index = 0; for (uint64_t Addr : AddrTable.getAddressEntries()) AMIter->second.insert(Addr, Index++); diff --git a/bolt/test/X86/Inputs/dwarf5-helper1-addr-section-reuse.s b/bolt/test/X86/Inputs/dwarf5-helper1-addr-section-reuse.s new file mode 100644 --- /dev/null +++ b/bolt/test/X86/Inputs/dwarf5-helper1-addr-section-reuse.s @@ -0,0 +1,144 @@ + # int foo() { + # return 0; + #} + + .text + .file "helper1.cpp" + .globl _Z3foov # -- Begin function _Z3foov + .p2align 4, 0x90 + .type _Z3foov,@function +_Z3foov: # @_Z3foov +.Lfunc_begin0: + .file 0 "testAddr" "helper1.cpp" md5 0xd7d0e6ab5d3b7dbefa5b3fd3cd035697 + .loc 0 1 0 # helper1.cpp:1:0 + .cfi_startproc +# %bb.0: + 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 # helper1.cpp:2:3 + xorl %eax, %eax + .loc 0 2 3 epilogue_begin is_stmt 0 # helper1.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 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 114 # DW_AT_str_offsets_base + .byte 23 # DW_FORM_sec_offset + .byte 16 # DW_AT_stmt_list + .byte 23 # DW_FORM_sec_offset + .byte 27 # DW_AT_comp_dir + .byte 37 # DW_FORM_strx1 + .byte 115 # DW_AT_addr_base + .byte 23 # DW_FORM_sec_offset + .byte 0 # EOM(1) + .byte 0 # EOM(2) + .byte 2 # Abbreviation Code + .byte 46 # DW_TAG_subprogram + .byte 0 # DW_CHILDREN_no + .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_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 + .byte 1 # Abbrev [1] 0xc:0x2c DW_TAG_compile_unit + .byte 0 # DW_AT_producer + .short 33 # DW_AT_language + .byte 1 # DW_AT_name + .long .Lstr_offsets_base0 # DW_AT_str_offsets_base + .long .Lline_table_start0 # DW_AT_stmt_list + .byte 2 # DW_AT_comp_dir + .long 0x8 # DW_AT_addr_base + .byte 2 # Abbrev [2] 0x23:0x10 DW_TAG_subprogram + .byte 1 # DW_AT_frame_base + .byte 86 + .byte 3 # DW_AT_linkage_name + .byte 4 # DW_AT_name + .byte 0 # DW_AT_decl_file + .byte 1 # DW_AT_decl_line + .long 51 # DW_AT_type + # DW_AT_external + .byte 3 # Abbrev [3] 0x33:0x4 DW_TAG_base_type + .byte 5 # 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_offsets,"",@progbits + .long 28 # Length of String Offsets Set + .short 5 + .short 0 +.Lstr_offsets_base0: + .section .debug_str,"MS",@progbits,1 +.Linfo_string0: + .asciz "clang version 15.0.0" # string offset=0 +.Linfo_string1: + .asciz "helper1.cpp" # string offset=146 +.Linfo_string2: + .asciz "testAddr" # string offset=158 +.Linfo_string3: + .asciz "_Z3foov" # string offset=205 +.Linfo_string4: + .asciz "foo" # string offset=213 +.Linfo_string5: + .asciz "int" # string offset=217 + .section .debug_str_offsets,"",@progbits + .long .Linfo_string0 + .long .Linfo_string1 + .long .Linfo_string2 + .long .Linfo_string3 + .long .Linfo_string4 + .long .Linfo_string5 + .ident "clang version 15.0.0" + .section ".note.GNU-stack","",@progbits + .addrsig + .section .debug_line,"",@progbits +.Lline_table_start0: diff --git a/bolt/test/X86/Inputs/dwarf5-helper2-addr-section-reuse.s b/bolt/test/X86/Inputs/dwarf5-helper2-addr-section-reuse.s new file mode 100644 --- /dev/null +++ b/bolt/test/X86/Inputs/dwarf5-helper2-addr-section-reuse.s @@ -0,0 +1,144 @@ + # int foo() { + # return 0; + #} + + .text + .file "helper2.cpp" + .globl _Z4foo2v # -- Begin function _Z4foo2v + .p2align 4, 0x90 + .type _Z4foo2v,@function +_Z4foo2v: # @_Z4foo2v +.Lfunc_begin0: + .file 0 "testAddr" "helper2.cpp" md5 0xd625613508584d1558af439616b0e2d3 + .loc 0 1 0 # helper2.cpp:1:0 + .cfi_startproc +# %bb.0: + 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 # helper2.cpp:2:3 + xorl %eax, %eax + .loc 0 2 3 epilogue_begin is_stmt 0 # helper2.cpp:2:3 + popq %rbp + .cfi_def_cfa %rsp, 8 + retq +.Ltmp1: +.Lfunc_end0: + .size _Z4foo2v, .Lfunc_end0-_Z4foo2v + .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 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 114 # DW_AT_str_offsets_base + .byte 23 # DW_FORM_sec_offset + .byte 16 # DW_AT_stmt_list + .byte 23 # DW_FORM_sec_offset + .byte 27 # DW_AT_comp_dir + .byte 37 # DW_FORM_strx1 + .byte 115 # DW_AT_addr_base + .byte 23 # DW_FORM_sec_offset + .byte 0 # EOM(1) + .byte 0 # EOM(2) + .byte 2 # Abbreviation Code + .byte 46 # DW_TAG_subprogram + .byte 0 # DW_CHILDREN_no + .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_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 + .byte 1 # Abbrev [1] 0xc:0x2c DW_TAG_compile_unit + .byte 0 # DW_AT_producer + .short 33 # DW_AT_language + .byte 1 # DW_AT_name + .long .Lstr_offsets_base0 # DW_AT_str_offsets_base + .long .Lline_table_start0 # DW_AT_stmt_list + .byte 2 # DW_AT_comp_dir + .long 0x8 # DW_AT_addr_base + .byte 2 # Abbrev [2] 0x23:0x10 DW_TAG_subprogram + .byte 1 # DW_AT_frame_base + .byte 86 + .byte 3 # DW_AT_linkage_name + .byte 4 # DW_AT_name + .byte 0 # DW_AT_decl_file + .byte 1 # DW_AT_decl_line + .long 51 # DW_AT_type + # DW_AT_external + .byte 3 # Abbrev [3] 0x33:0x4 DW_TAG_base_type + .byte 5 # 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_offsets,"",@progbits + .long 28 # Length of String Offsets Set + .short 5 + .short 0 +.Lstr_offsets_base0: + .section .debug_str,"MS",@progbits,1 +.Linfo_string0: + .asciz "clang version 15.0.0" # string offset=0 +.Linfo_string1: + .asciz "helper2.cpp" # string offset=146 +.Linfo_string2: + .asciz "testAddr" # string offset=158 +.Linfo_string3: + .asciz "_Z4foo2v" # string offset=205 +.Linfo_string4: + .asciz "foo2" # string offset=214 +.Linfo_string5: + .asciz "int" # string offset=219 + .section .debug_str_offsets,"",@progbits + .long .Linfo_string0 + .long .Linfo_string1 + .long .Linfo_string2 + .long .Linfo_string3 + .long .Linfo_string4 + .long .Linfo_string5 + .ident "clang version 15.0.0" + .section ".note.GNU-stack","",@progbits + .addrsig + .section .debug_line,"",@progbits +.Lline_table_start0: diff --git a/bolt/test/X86/Inputs/dwarf5-main-addr-section-reuse.s b/bolt/test/X86/Inputs/dwarf5-main-addr-section-reuse.s new file mode 100644 --- /dev/null +++ b/bolt/test/X86/Inputs/dwarf5-main-addr-section-reuse.s @@ -0,0 +1,160 @@ + #int main() { + # return 0; + #} + + .text + .file "main.cpp" + .globl main # -- Begin function main + .p2align 4, 0x90 + .type main,@function +main: # @main +.Lfunc_begin0: + .file 0 "testAddr" "main.cpp" md5 0xd7b10b0a4a7fb8e0790feb7a5cd9b69a + .loc 0 1 0 # main.cpp:1:0 + .cfi_startproc +# %bb.0: + pushq %rbp + .cfi_def_cfa_offset 16 + .cfi_offset %rbp, -16 + movq %rsp, %rbp + .cfi_def_cfa_register %rbp + movl $0, -4(%rbp) +.Ltmp0: + .loc 0 2 3 prologue_end # main.cpp:2:3 + xorl %eax, %eax + .loc 0 2 3 epilogue_begin is_stmt 0 # main.cpp:2:3 + popq %rbp + .cfi_def_cfa %rsp, 8 + retq +.Ltmp1: +.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 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 114 # DW_AT_str_offsets_base + .byte 23 # DW_FORM_sec_offset + .byte 16 # DW_AT_stmt_list + .byte 23 # DW_FORM_sec_offset + .byte 27 # DW_AT_comp_dir + .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 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 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_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 + .byte 1 # Abbrev [1] 0xc:0x2b DW_TAG_compile_unit + .byte 0 # DW_AT_producer + .short 33 # DW_AT_language + .byte 1 # DW_AT_name + .long .Lstr_offsets_base0 # DW_AT_str_offsets_base + .long .Lline_table_start0 # DW_AT_stmt_list + .byte 2 # DW_AT_comp_dir + .byte 0 # DW_AT_low_pc + .long .Lfunc_end0-.Lfunc_begin0 # DW_AT_high_pc + .long .Laddr_table_base0 # DW_AT_addr_base + .byte 2 # Abbrev [2] 0x23:0xf 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 3 # DW_AT_name + .byte 0 # DW_AT_decl_file + .byte 1 # DW_AT_decl_line + .long 50 # DW_AT_type + # DW_AT_external + .byte 3 # Abbrev [3] 0x32:0x4 DW_TAG_base_type + .byte 4 # 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_offsets,"",@progbits + .long 24 # Length of String Offsets Set + .short 5 + .short 0 +.Lstr_offsets_base0: + .section .debug_str,"MS",@progbits,1 +.Linfo_string0: + .asciz "clang version 15.0.0" # string offset=0 +.Linfo_string1: + .asciz "main.cpp" # string offset=146 +.Linfo_string2: + .asciz "testAddr" # string offset=155 +.Linfo_string3: + .asciz "main" # string offset=202 +.Linfo_string4: + .asciz "int" # string offset=207 + .section .debug_str_offsets,"",@progbits + .long .Linfo_string0 + .long .Linfo_string1 + .long .Linfo_string2 + .long .Linfo_string3 + .long .Linfo_string4 + .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: + .ident "clang version 15.0.0" + .section ".note.GNU-stack","",@progbits + .addrsig + .section .debug_line,"",@progbits +.Lline_table_start0: diff --git a/bolt/test/X86/dwarf5-addr-section-reuse.s b/bolt/test/X86/dwarf5-addr-section-reuse.s new file mode 100644 --- /dev/null +++ b/bolt/test/X86/dwarf5-addr-section-reuse.s @@ -0,0 +1,18 @@ +# RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-main-addr-section-reuse.s -o %tmain.o +# RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-helper1-addr-section-reuse.s -o %thelper1.o +# RUN: llvm-mc -dwarf-version=5 -filetype=obj -triple x86_64-unknown-linux %p/Inputs/dwarf5-helper2-addr-section-reuse.s -o %thelper2.o +# RUN: %clang %cflags -dwarf-5 %tmain.o %thelper1.o %thelper2.o -o %t.exe -Wl,-q +# RUN: llvm-dwarfdump --debug-info %t.exe | FileCheck --check-prefix=PRECHECK %s +# RUN: llvm-bolt %t.exe -o %t.exe.bolt --update-debug-sections +# RUN: llvm-dwarfdump --debug-info %t.exe.bolt | FileCheck --check-prefix=POSTCHECK %s + +# This test checks that when a binary is bolted if CU is not modified and has DW_AT_addr_base that is shared +# after being bolted CUs still share same entry in .debug_addr. + +# PRECHECK: DW_AT_addr_base (0x00000008) +# PRECHECK: DW_AT_addr_base (0x00000008) +# PRECHECK: DW_AT_addr_base (0x00000008) + +# POSTCHECK: DW_AT_addr_base (0x00000008) +# POSTCHECK: DW_AT_addr_base (0x00000020) +# POSTCHECK: DW_AT_addr_base (0x00000020)