[llvm] [llvm-dwp] Fix FoundCUUnit problem on soft-stop with DWARF5 (PR #169783)
Jinjie Huang via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 2 20:36:13 PST 2025
https://github.com/Jinjie-Huang updated https://github.com/llvm/llvm-project/pull/169783
>From ce64dcca5fb130bf52b8fb58cf7127a8bf628318 Mon Sep 17 00:00:00 2001
From: huangjinjie <huangjinjie at bytedance.com>
Date: Thu, 27 Nov 2025 15:48:10 +0800
Subject: [PATCH 1/3] fix FoundCUUnit problem on soft_stop
---
llvm/lib/DWP/DWP.cpp | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/llvm/lib/DWP/DWP.cpp b/llvm/lib/DWP/DWP.cpp
index d823292747393..ea029e97464bc 100644
--- a/llvm/lib/DWP/DWP.cpp
+++ b/llvm/lib/DWP/DWP.cpp
@@ -826,9 +826,7 @@ Error write(MCStreamer &Out, ArrayRef<std::string> Inputs,
"debug_info", OverflowOptValue, AnySectionOverflow))
return Err;
if (AnySectionOverflow) {
- if (Header.Version < 5 ||
- Header.UnitType == dwarf::DW_UT_split_compile)
- FoundCUUnit = true;
+ FoundCUUnit = true;
break;
}
}
>From 7f1a9b190b1561b38778592e96b871c6cc31b2bc Mon Sep 17 00:00:00 2001
From: huangjinjie <huangjinjie at bytedance.com>
Date: Tue, 2 Dec 2025 13:35:37 +0800
Subject: [PATCH 2/3] add a test to force an overflow in TU
---
llvm/test/tools/llvm-dwp/X86/soft_stop.test | 454 ++++++++++++++++++++
1 file changed, 454 insertions(+)
create mode 100644 llvm/test/tools/llvm-dwp/X86/soft_stop.test
diff --git a/llvm/test/tools/llvm-dwp/X86/soft_stop.test b/llvm/test/tools/llvm-dwp/X86/soft_stop.test
new file mode 100644
index 0000000000000..14655236436da
--- /dev/null
+++ b/llvm/test/tools/llvm-dwp/X86/soft_stop.test
@@ -0,0 +1,454 @@
+## This test verifies that llvm-dwp does not trigger a "no compile unit found" error
+## in 'soft-stop' scenario, specifically when the overflow happens to be in a type unit.
+## Use a '.fill' directive after the first TU to force an overflow in the subsequent TU.
+
+RUN: rm -rf %t && split-file %s %t && cd %t
+RUN: llvm-mc --triple=x86_64-unknown-linux --filetype=obj --split-dwarf-file=%t/main.dwo -dwarf-version=5 %t/main.s -o %t/main.o
+RUN: llvm-dwp %t/main.dwo -continue-on-cu-index-overflow=soft-stop -o %t/main.dwp 2>&1 | FileCheck %s
+
+CHECK: warning: debug_info Section Contribution Offset overflow 4G. Previous Offset {{.*}}, After overflow offset {{.*}}.
+CHECK-NOT: error: no compile unit found in file: {{.*}}
+
+#--- main.s
+# Note: This file is compiled from the following code, for
+# the purpose of creating an overflowed dwo section.
+#
+# clang++ -g -gsplit-dwarf -gdwarf-5 -fdebug-types-section -S main.cpp
+#
+#enum class DebugType {
+# INFO,
+# WARNING,
+# ERROR,
+# CRITICAL,
+# DEBUG
+#} g = DebugType::INFO;
+#
+#int main() {
+# return 0;
+#}
+
+ .file "main.cpp"
+ .file 0 "main.cpp" md5 1234567890123456789
+ .section .debug_info.dwo,"e", at progbits
+ .long .Overflow_TU_end-.Overflow_TU_start # Length of Unit
+.Overflow_TU_start:
+ .short 5 # DWARF version number
+ .byte 6 # DWARF Unit Type
+ .byte 8 # Address Size (in bytes)
+ .long 0 # Offset Into Abbrev. Section
+ .quad 1234567890123456789 # Type Signature
+ .long 33 # Type DIE Offset
+ .byte 1 # Abbrev [1] 0x18:0x27 DW_TAG_type_unit
+ .short 33 # DW_AT_language
+ .byte 1 # DW_AT_comp_dir
+ .byte 2 # DW_AT_dwo_name
+ .long 0 # DW_AT_stmt_list
+ .byte 2 # Abbrev [2] 0x21:0x19 DW_TAG_enumeration_type
+ .long 58 # DW_AT_type
+ .fill 4294967233 # 2^32 - 1 - 44, padding with `.fill` directive to make an offset overflow
+.Overflow_TU_end:
+ .section .debug_info.dwo,"e", at progbits
+ .long .Ldebug_info_dwo_end0-.Ldebug_info_dwo_start0 # Length of Unit
+.Ldebug_info_dwo_start0:
+ .short 5 # DWARF version number
+ .byte 6 # DWARF Unit Type
+ .byte 8 # Address Size (in bytes)
+ .long 0 # Offset Into Abbrev. Section
+ .quad 2124196671656770956 # Type Signature
+ .long 33 # Type DIE Offset
+ .byte 1 # Abbrev [1] 0x18:0x27 DW_TAG_type_unit
+ .short 33 # DW_AT_language
+ .byte 1 # DW_AT_comp_dir
+ .byte 2 # DW_AT_dwo_name
+ .long 0 # DW_AT_stmt_list
+ .byte 2 # Abbrev [2] 0x21:0x19 DW_TAG_enumeration_type
+ .long 58 # DW_AT_type
+ # DW_AT_enum_class
+ .byte 9 # DW_AT_name
+ .byte 4 # DW_AT_byte_size
+ .byte 0 # DW_AT_decl_file
+ .byte 1 # DW_AT_decl_line
+ .byte 3 # Abbrev [3] 0x2a:0x3 DW_TAG_enumerator
+ .byte 4 # DW_AT_name
+ .byte 0 # DW_AT_const_value
+ .byte 3 # Abbrev [3] 0x2d:0x3 DW_TAG_enumerator
+ .byte 5 # DW_AT_name
+ .byte 1 # DW_AT_const_value
+ .byte 3 # Abbrev [3] 0x30:0x3 DW_TAG_enumerator
+ .byte 6 # DW_AT_name
+ .byte 2 # DW_AT_const_value
+ .byte 3 # Abbrev [3] 0x33:0x3 DW_TAG_enumerator
+ .byte 7 # DW_AT_name
+ .byte 3 # DW_AT_const_value
+ .byte 3 # Abbrev [3] 0x36:0x3 DW_TAG_enumerator
+ .byte 8 # DW_AT_name
+ .byte 4 # DW_AT_const_value
+ .byte 0 # End Of Children Mark
+ .byte 4 # Abbrev [4] 0x3a:0x4 DW_TAG_base_type
+ .byte 3 # DW_AT_name
+ .byte 5 # DW_AT_encoding
+ .byte 4 # DW_AT_byte_size
+ .byte 0 # End Of Children Mark
+.Ldebug_info_dwo_end0:
+ .text
+ .globl main # -- Begin function main
+ .p2align 4
+ .type main, at function
+main: # @main
+.Lfunc_begin0:
+ .cfi_startproc
+# %bb.0: # %entry
+ .loc 0 10 5 prologue_end # main.cpp:10:5
+ xorl %eax, %eax
+ retq
+.Ltmp0:
+.Lfunc_end0:
+ .size main, .Lfunc_end0-main
+ .cfi_endproc
+ # -- End function
+ .section .debug_abbrev,"", at 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,"", at 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 9071746638605020729
+ .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,"", at progbits
+ .long 12 # Length of String Offsets Set
+ .short 5
+ .short 0
+.Lstr_offsets_base0:
+ .section .debug_str,"MS", at progbits,1
+.Lskel_string0:
+ .asciz "build" # string offset=0
+.Lskel_string1:
+ .asciz "main.dwo" # string offset=45
+ .section .debug_str_offsets,"", at progbits
+ .long .Lskel_string0
+ .long .Lskel_string1
+ .section .debug_str_offsets.dwo,"e", at progbits
+ .long 56 # Length of String Offsets Set
+ .short 5
+ .short 0
+ .section .debug_str.dwo,"eMS", at progbits,1
+.Linfo_string0:
+ .asciz "g" # string offset=0
+.Linfo_string1:
+ .asciz "build" # string offset=2
+.Linfo_string2:
+ .asciz "main.dwo" # string offset=47
+.Linfo_string3:
+ .asciz "int" # string offset=56
+.Linfo_string4:
+ .asciz "INFO" # string offset=60
+.Linfo_string5:
+ .asciz "WARNING" # string offset=65
+.Linfo_string6:
+ .asciz "ERROR" # string offset=73
+.Linfo_string7:
+ .asciz "CRITICAL" # string offset=79
+.Linfo_string8:
+ .asciz "DEBUG" # string offset=88
+.Linfo_string9:
+ .asciz "DebugType" # string offset=94
+.Linfo_string10:
+ .asciz "main" # string offset=104
+.Linfo_string11:
+ .asciz "clang version 22.0.0git" # string offset=109
+.Linfo_string12:
+ .asciz "main.cpp" # string offset=216
+ .section .debug_str_offsets.dwo,"e", at progbits
+ .long 0
+ .long 2
+ .long 47
+ .long 56
+ .long 60
+ .long 65
+ .long 73
+ .long 79
+ .long 88
+ .long 94
+ .long 104
+ .long 109
+ .long 216
+ .section .debug_info.dwo,"e", at progbits
+ .long .Ldebug_info_dwo_end1-.Ldebug_info_dwo_start1 # Length of Unit
+.Ldebug_info_dwo_start1:
+ .short 5 # DWARF version number
+ .byte 5 # DWARF Unit Type
+ .byte 8 # Address Size (in bytes)
+ .long 0 # Offset Into Abbrev. Section
+ .quad 9071746638605020729
+ .byte 5 # Abbrev [5] 0x14:0x2b DW_TAG_compile_unit
+ .byte 11 # DW_AT_producer
+ .short 33 # DW_AT_language
+ .byte 12 # DW_AT_name
+ .byte 2 # DW_AT_dwo_name
+ .byte 6 # Abbrev [6] 0x1a:0x8 DW_TAG_variable
+ .byte 0 # DW_AT_name
+ .long 34 # DW_AT_type
+ # DW_AT_external
+ .byte 0 # DW_AT_decl_file
+ .byte 7 # DW_AT_decl_line
+ .byte 7 # Abbrev [7] 0x22:0x9 DW_TAG_enumeration_type
+ # DW_AT_declaration
+ .quad 2124196671656770956 # DW_AT_signature
+ .byte 8 # Abbrev [8] 0x2b: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 87
+ # DW_AT_call_all_calls
+ .byte 10 # DW_AT_name
+ .byte 0 # DW_AT_decl_file
+ .byte 9 # DW_AT_decl_line
+ .long 58 # DW_AT_type
+ # DW_AT_external
+ .byte 4 # Abbrev [4] 0x3a:0x4 DW_TAG_base_type
+ .byte 3 # DW_AT_name
+ .byte 5 # DW_AT_encoding
+ .byte 4 # DW_AT_byte_size
+ .byte 0 # End Of Children Mark
+.Ldebug_info_dwo_end1:
+ .section .debug_abbrev.dwo,"e", at progbits
+ .byte 1 # Abbreviation Code
+ .byte 65 # DW_TAG_type_unit
+ .byte 1 # DW_CHILDREN_yes
+ .byte 19 # DW_AT_language
+ .byte 5 # DW_FORM_data2
+ .byte 27 # DW_AT_comp_dir
+ .byte 37 # DW_FORM_strx1
+ .byte 118 # DW_AT_dwo_name
+ .byte 37 # DW_FORM_strx1
+ .byte 16 # DW_AT_stmt_list
+ .byte 23 # DW_FORM_sec_offset
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 2 # Abbreviation Code
+ .byte 4 # DW_TAG_enumeration_type
+ .byte 1 # DW_CHILDREN_yes
+ .byte 73 # DW_AT_type
+ .byte 19 # DW_FORM_ref4
+ .byte 109 # DW_AT_enum_class
+ .byte 25 # DW_FORM_flag_present
+ .byte 3 # DW_AT_name
+ .byte 37 # DW_FORM_strx1
+ .byte 11 # DW_AT_byte_size
+ .byte 11 # DW_FORM_data1
+ .byte 58 # DW_AT_decl_file
+ .byte 11 # DW_FORM_data1
+ .byte 59 # DW_AT_decl_line
+ .byte 11 # DW_FORM_data1
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 3 # Abbreviation Code
+ .byte 40 # DW_TAG_enumerator
+ .byte 0 # DW_CHILDREN_no
+ .byte 3 # DW_AT_name
+ .byte 37 # DW_FORM_strx1
+ .byte 28 # DW_AT_const_value
+ .byte 13 # DW_FORM_sdata
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 4 # 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 5 # 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 6 # Abbreviation Code
+ .byte 52 # DW_TAG_variable
+ .byte 0 # DW_CHILDREN_no
+ .byte 3 # DW_AT_name
+ .byte 37 # DW_FORM_strx1
+ .byte 73 # DW_AT_type
+ .byte 19 # DW_FORM_ref4
+ .byte 63 # DW_AT_external
+ .byte 25 # DW_FORM_flag_present
+ .byte 58 # DW_AT_decl_file
+ .byte 11 # DW_FORM_data1
+ .byte 59 # DW_AT_decl_line
+ .byte 11 # DW_FORM_data1
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 7 # Abbreviation Code
+ .byte 4 # DW_TAG_enumeration_type
+ .byte 0 # DW_CHILDREN_no
+ .byte 60 # DW_AT_declaration
+ .byte 25 # DW_FORM_flag_present
+ .byte 105 # DW_AT_signature
+ .byte 32 # DW_FORM_ref_sig8
+ .byte 0 # EOM(1)
+ .byte 0 # EOM(2)
+ .byte 8 # 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 122 # DW_AT_call_all_calls
+ .byte 25 # DW_FORM_flag_present
+ .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 0 # EOM(3)
+ .section .debug_line.dwo,"e", at progbits
+.Ltmp1:
+ .long .Ldebug_line_end0-.Ldebug_line_start0 # unit length
+.Ldebug_line_start0:
+ .short 5
+ .byte 8
+ .byte 0
+ .long .Lprologue_end0-.Lprologue_start0
+.Lprologue_start0:
+ .byte 1
+ .byte 1
+ .byte 1
+ .byte -5
+ .byte 14
+ .byte 1
+ .byte 1
+ .byte 1
+ .byte 8
+ .byte 1
+ .ascii "build"
+ .byte 0
+ .byte 3
+ .byte 1
+ .byte 8
+ .byte 2
+ .byte 15
+ .byte 5
+ .byte 30
+ .byte 1
+ .ascii "main.cpp"
+ .byte 0
+ .byte 0
+ .byte 0xd1, 0x75, 0xf8, 0xd5
+ .byte 0x53, 0x73, 0x15, 0x7c
+ .byte 0x7f, 0x54, 0x3d, 0xd9
+ .byte 0x1d, 0x3c, 0xa8, 0xb5
+.Lprologue_end0:
+.Ldebug_line_end0:
+ .section .debug_addr,"", at 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,"", at 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 20 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "INFO" # External Name
+ .long 20 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "CRITICAL" # External Name
+ .long 20 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "ERROR" # External Name
+ .long 20 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "DEBUG" # External Name
+ .long 20 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "WARNING" # External Name
+ .long 26 # DIE offset
+ .byte 32 # Attributes: VARIABLE, EXTERNAL
+ .asciz "g" # External Name
+ .long 43 # DIE offset
+ .byte 48 # Attributes: FUNCTION, EXTERNAL
+ .asciz "main" # External Name
+ .long 0 # End Mark
+.LpubNames_end0:
+ .section .debug_gnu_pubtypes,"", at 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 34 # DIE offset
+ .byte 16 # Attributes: TYPE, EXTERNAL
+ .asciz "DebugType" # External Name
+ .long 58 # DIE offset
+ .byte 144 # Attributes: TYPE, STATIC
+ .asciz "int" # External Name
+ .long 0 # End Mark
+.LpubTypes_end0:
+ .ident "clang version 22.0.0"
+ .section ".note.GNU-stack","", at progbits
+ .addrsig
+ .section .debug_line,"", at progbits
+.Lline_table_start0:
>From aa0bdad7757fadad568509906a1c475e140d7d5f Mon Sep 17 00:00:00 2001
From: huangjinjie <huangjinjie at bytedance.com>
Date: Wed, 3 Dec 2025 12:35:51 +0800
Subject: [PATCH 3/3] mark test UNSUPPORTED for now
---
llvm/test/tools/llvm-dwp/X86/soft_stop.test | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/llvm/test/tools/llvm-dwp/X86/soft_stop.test b/llvm/test/tools/llvm-dwp/X86/soft_stop.test
index 14655236436da..7d336efa8df5c 100644
--- a/llvm/test/tools/llvm-dwp/X86/soft_stop.test
+++ b/llvm/test/tools/llvm-dwp/X86/soft_stop.test
@@ -1,6 +1,7 @@
+UNSUPPORTED: true
+## Marking as unsupported for now, as this test needs an extra 8GB of disk space.
## This test verifies that llvm-dwp does not trigger a "no compile unit found" error
## in 'soft-stop' scenario, specifically when the overflow happens to be in a type unit.
-## Use a '.fill' directive after the first TU to force an overflow in the subsequent TU.
RUN: rm -rf %t && split-file %s %t && cd %t
RUN: llvm-mc --triple=x86_64-unknown-linux --filetype=obj --split-dwarf-file=%t/main.dwo -dwarf-version=5 %t/main.s -o %t/main.o
@@ -12,6 +13,8 @@ CHECK-NOT: error: no compile unit found in file: {{.*}}
#--- main.s
# Note: This file is compiled from the following code, for
# the purpose of creating an overflowed dwo section.
+# Add a '.fill' directive after the first TU to force
+# an overflow in the subsequent TU.
#
# clang++ -g -gsplit-dwarf -gdwarf-5 -fdebug-types-section -S main.cpp
#
More information about the llvm-commits
mailing list