llvm-symbolizer: Fix "start file" to work with Split DWARF

A followup to the feature added in
69da27c7496ea373567ce5121e6fe8613846e7a5 that added the optional "start
file name" to match "start line" - but this didn't work with Split DWARF
because of the need for the decl file number resolution code to refer
back to the skeleton unit to find its .debug_line contribution. So this
patch adds the necessary infrastructure to track the skeleton unit
corresponding to a split full unit for the purpose of this lookup.

diff --git a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
index a340fb3..1292bfb 100644 (file)
--- a/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
+++ b/llvm/include/llvm/DebugInfo/DWARF/DWARFUnit.h
@@ -218,6 +218,7 @@ class DWARFUnit {
   StringRef StringSection;
   const DWARFSection &StringOffsetSection;
   const DWARFSection *AddrOffsetSection;
+  DWARFUnit *SU;
   Optional<uint64_t> AddrOffsetSectionBase;
   bool isLittleEndian;
   bool IsDWO;
@@ -301,6 +302,12 @@ public:
     return StringOffsetSection;
   }
 
+  void setSkeletonUnit(DWARFUnit *SU) { this->SU = SU; }
+  // Returns itself if not using Split DWARF, or if the unit is a skeleton unit
+  // - otherwise returns the split full unit's corresponding skeleton, if
+  // available.
+  DWARFUnit *getLinkedUnit() { return IsDWO ? SU : this; }
+
   void setAddrOffsetSection(const DWARFSection *AOS, uint64_t Base) {
     AddrOffsetSection = AOS;
     AddrOffsetSectionBase = Base;

diff --git a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
index 79438dc..d82de9f 100644 (file)
--- a/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFDie.cpp
@@ -571,11 +571,16 @@ uint64_t DWARFDie::getDeclLine() const {
 
 std::string
 DWARFDie::getDeclFile(DILineInfoSpecifier::FileLineInfoKind Kind) const {
+  auto D = getAttributeValueAsReferencedDie(DW_AT_abstract_origin);
+  if (!D)
+    D = *this;
   std::string FileName;
-  if (auto DeclFile = toUnsigned(findRecursively(DW_AT_decl_file))) {
-    if (const auto *LT = U->getContext().getLineTableForUnit(U)) {
-      LT->getFileNameByIndex(*DeclFile, U->getCompilationDir(), Kind, FileName);
-    }
+  if (auto DeclFile = toUnsigned(D.find(DW_AT_decl_file))) {
+    if (const auto *LineTable =
+            getDwarfUnit()->getContext().getLineTableForUnit(
+                D.getDwarfUnit()->getLinkedUnit()))
+      LineTable->getFileNameByIndex(
+          *DeclFile, D.getDwarfUnit()->getCompilationDir(), Kind, FileName);
   }
   return FileName;
 }

diff --git a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
index 57ac0a5..79d18fa 100644 (file)
--- a/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
+++ b/llvm/lib/DebugInfo/DWARF/DWARFUnit.cpp
@@ -388,6 +388,7 @@ void DWARFUnit::clear() {
   RangeSectionBase = 0;
   LocSectionBase = 0;
   AddrOffsetSectionBase = None;
+  SU = nullptr;
   clearDIEs(false);
   DWO.reset();
 }
@@ -586,6 +587,7 @@ bool DWARFUnit::parseDWO() {
   if (!DWOCU)
     return false;
   DWO = std::shared_ptr<DWARFCompileUnit>(std::move(DWOContext), DWOCU);
+  DWO->setSkeletonUnit(this);
   // Share .debug_addr and .debug_ranges section with compile unit in .dwo
   if (AddrOffsetSectionBase)
     DWO->setAddrOffsetSection(AddrOffsetSection, *AddrOffsetSectionBase);

diff --git a/llvm/test/DebugInfo/X86/symbolize_function_start.s b/llvm/test/DebugInfo/X86/symbolize_function_start.s
new file mode 100644 (file)
index 0000000..df6caa4
--- /dev/null
+++ b/llvm/test/DebugInfo/X86/symbolize_function_start.s
@@ -0,0 +1,211 @@
+# RUN: rm -rf %t
+# RUN: mkdir %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64 -dwarf-version=4 %s -o %t/test.o
+# RUN: cd %t
+# RUN: llvm-symbolizer -verbose 0x0 -obj=test.o | FileCheck --check-prefix=SYM %s
+# RUN: llvm-dwarfdump -lookup=0x1 test.o | FileCheck --check-prefix=LOOKUP %s
+
+# SYM: Filename: ./././test.h
+# SYM: Function start filename: ./test.cpp
+
+# LOOKUP: Line info: line 0, column 0, start file 'test.cpp', start line 1
+
+
+       .text
+       .file   "test.cpp"
+       .globl  _Z2f1v                          # -- Begin function _Z2f1v
+       .p2align        4, 0x90
+       .type   _Z2f1v,@function
+_Z2f1v:                                 # @_Z2f1v
+.Lfunc_begin0:
+       .file   1 "." "test.cpp"
+       .loc    1 1 0                           # test.cpp:1:0
+       .cfi_startproc
+# %bb.0:                                # %entry
+       .file   2 "." "./test.h"
+       .loc    2 1 1 prologue_end              # ./test.h:1:1
+       xorl    %eax, %eax
+       retq
+.Ltmp0:
+.Lfunc_end0:
+       .size   _Z2f1v, .Lfunc_end0-_Z2f1v
+       .cfi_endproc
+                                        # -- End function
+       .section        .debug_abbrev,"",@progbits
+       .byte   1                               # Abbreviation Code
+       .byte   17                              # DW_TAG_compile_unit
+       .byte   0                               # DW_CHILDREN_no
+       .byte   16                              # DW_AT_stmt_list
+       .byte   23                              # DW_FORM_sec_offset
+       .byte   27                              # DW_AT_comp_dir
+       .byte   14                              # DW_FORM_strp
+       .ascii  "\264B"                         # DW_AT_GNU_pubnames
+       .byte   25                              # DW_FORM_flag_present
+       .ascii  "\260B"                         # DW_AT_GNU_dwo_name
+       .byte   14                              # DW_FORM_strp
+       .ascii  "\261B"                         # DW_AT_GNU_dwo_id
+       .byte   7                               # DW_FORM_data8
+       .byte   17                              # DW_AT_low_pc
+       .byte   1                               # DW_FORM_addr
+       .byte   18                              # DW_AT_high_pc
+       .byte   6                               # DW_FORM_data4
+       .ascii  "\263B"                         # DW_AT_GNU_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  4                               # DWARF version number
+       .long   .debug_abbrev                   # Offset Into Abbrev. Section
+       .byte   8                               # Address Size (in bytes)
+       .byte   1                               # Abbrev [1] 0xb:0x25 DW_TAG_compile_unit
+       .long   .Lline_table_start0             # DW_AT_stmt_list
+       .long   .Lskel_string0                  # DW_AT_comp_dir
+                                        # DW_AT_GNU_pubnames
+       .long   .Lskel_string1                  # DW_AT_GNU_dwo_name
+       .quad   7198491773836599109             # DW_AT_GNU_dwo_id
+       .quad   .Lfunc_begin0                   # DW_AT_low_pc
+       .long   .Lfunc_end0-.Lfunc_begin0       # DW_AT_high_pc
+       .long   .Laddr_table_base0              # DW_AT_GNU_addr_base
+.Ldebug_info_end0:
+       .section        .debug_str,"MS",@progbits,1
+.Lskel_string0:
+       .asciz  "."                             # string offset=0
+.Lskel_string1:
+       .asciz  "test.o"                        # string offset=2
+       .section        .debug_str.dwo,"eMS",@progbits,1
+.Linfo_string0:
+       .asciz  "_Z2f1v"                        # string offset=0
+.Linfo_string1:
+       .asciz  "f1"                            # string offset=7
+.Linfo_string2:
+       .asciz  "int"                           # string offset=10
+.Linfo_string3:
+       .asciz  "clang version 13.0.0 (git@github.com:llvm/llvm-project.git 882ee7fbd6fc989fba53f3d9672440771feb80f5)" # string offset=14
+.Linfo_string4:
+       .asciz  "test.cpp"                      # string offset=115
+.Linfo_string5:
+       .asciz  "test.o"                        # string offset=124
+       .section        .debug_str_offsets.dwo,"e",@progbits
+       .long   0
+       .long   7
+       .long   10
+       .long   14
+       .long   115
+       .long   124
+       .section        .debug_info.dwo,"e",@progbits
+       .long   .Ldebug_info_dwo_end0-.Ldebug_info_dwo_start0 # Length of Unit
+.Ldebug_info_dwo_start0:
+       .short  4                               # DWARF version number
+       .long   0                               # Offset Into Abbrev. Section
+       .byte   8                               # Address Size (in bytes)
+       .byte   1                               # Abbrev [1] 0xb:0x23 DW_TAG_compile_unit
+       .byte   3                               # DW_AT_producer
+       .short  33                              # DW_AT_language
+       .byte   4                               # DW_AT_name
+       .byte   5                               # DW_AT_GNU_dwo_name
+       .quad   7198491773836599109             # DW_AT_GNU_dwo_id
+       .byte   2                               # Abbrev [2] 0x19:0x10 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   87
+                                        # DW_AT_GNU_all_call_sites
+       .byte   0                               # DW_AT_linkage_name
+       .byte   1                               # DW_AT_name
+       .byte   1                               # DW_AT_decl_file
+       .byte   1                               # DW_AT_decl_line
+       .long   41                              # DW_AT_type
+                                        # DW_AT_external
+       .byte   3                               # Abbrev [3] 0x29:0x4 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
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .byte   19                              # DW_AT_language
+       .byte   5                               # DW_FORM_data2
+       .byte   3                               # DW_AT_name
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .ascii  "\260B"                         # DW_AT_GNU_dwo_name
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .ascii  "\261B"                         # DW_AT_GNU_dwo_id
+       .byte   7                               # DW_FORM_data8
+       .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
+       .ascii  "\201>"                         # DW_FORM_GNU_addr_index
+       .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   110                             # DW_AT_linkage_name
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .byte   3                               # DW_AT_name
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .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
+       .ascii  "\202>"                         # DW_FORM_GNU_str_index
+       .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
+.Laddr_table_base0:
+       .quad   .Lfunc_begin0
+       .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   48                              # Compilation Unit Length
+       .long   25                              # DIE offset
+       .byte   48                              # Attributes: FUNCTION, EXTERNAL
+       .asciz  "f1"                            # 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   48                              # Compilation Unit Length
+       .long   41                              # DIE offset
+       .byte   144                             # Attributes: TYPE, STATIC
+       .asciz  "int"                           # External Name
+       .long   0                               # End Mark
+.LpubTypes_end0:
+       .ident  "clang version 13.0.0 (git@github.com:llvm/llvm-project.git 882ee7fbd6fc989fba53f3d9672440771feb80f5)"
+       .section        ".note.GNU-stack","",@progbits
+       .addrsig
+       .section        .debug_line,"",@progbits
+.Lline_table_start0: