[lld-macho] Use source information in duplicate symbol errors

[BertalanD]

Summary

Similarly to how undefined symbol diagnostics were changed in D128184,
we now show where in the source file duplicate symbols are defined at:

ld64.lld: error: duplicate symbol: _foo
>> defined in bar.c:42
>>            /path/to/bar.o
>> defined in baz.c:1
>>            /path/to/libbaz.a(baz.o)

For objects that don't contain DWARF data, the format is unchanged.

A slight difference to undefined symbol diagnostics is that we don't
print the name of the symbol on the third line, as it's already
contained on the first line.

---

I've requested commit access, but while I'm waiting for that, please commit this patch with the following author info:
Daniel Bertalan <[e-mail]>

[thakis]

Nice!

lld/MachO/InputSection.cpp

91

If you use dyn_cast_or_null here, you don't need the 3 new lines above.

[BertalanD]

use dyn_cast_or_null

lld/MachO/InputSection.cpp

std::string InputSection::getLocation(uint64_t off) const {
   }
 
   return (toString(getFile()) + ":(" + getName() + "+0x" +
           Twine::utohexstr(off) + ")")
       .str();
 }
 
 std::string InputSection::getSourceLocation(uint64_t off) const {
-  auto *obj = dyn_cast<ObjFile>(getFile());
+  auto *obj = dyn_cast_or_null<ObjFile>(getFile());
   if (!obj)
     return {};
 
   DWARFCache *dwarf = obj->getDwarf();
   if (!dwarf)
     return std::string();
 
   for (const Subsection &subsec : section.subsections) {
     if (subsec.isec == this) {
       off += subsec.offset;
       break;

lld/MachO/SymbolTable.cpp

if (auto *defined = dyn_cast<Defined>(s)) {
       if (defined->isWeakDef()) {
         // FIXME: Handle this for bitcode files.
         if (auto concatIsec =
                 dyn_cast_or_null<ConcatInputSection>(defined->isec)) {
           concatIsec->wasCoalesced = true;
           concatIsec->symbols.erase(llvm::find(concatIsec->symbols, defined));
         }
       } else {
-        error("duplicate symbol: " + toString(*defined) + "\n>>> defined in " +
-              toString(defined->getFile()) + "\n>>> defined in " +
-              toString(file));
+        std::string src1 = defined->getSourceLocation();
+        std::string src2 = isec ? isec->getSourceLocation(value) : "";
+
+        std::string message =
+            "duplicate symbol: " + toString(*defined) + "\n>>> defined in ";
+        if (!src1.empty())
+          message += src1 + "\n>>>            ";
+        message += toString(defined->getFile()) + "\n>>> defined in ";
+        if (!src2.empty())
+          message += src2 + "\n>>>            ";
+        error(message + toString(file));
       }
 
     } else if (auto *dysym = dyn_cast<DylibSymbol>(s)) {
       overridesWeakDef = !isWeakDef && dysym->isWeakDef();
       dysym->unreference();
     }
     // Defined symbols take priority over other types of symbols, so in case
     // of a name conflict, we fall through to the replaceSymbol() call below.

lld/MachO/Symbols.h

public:
   }
   bool isTlv() const override;
 
   bool isExternal() const { return external; }
   bool isAbsolute() const { return isec == nullptr; }
 
   uint64_t getVA() const override;
 
+  std::string getSourceLocation();
+
   // Ensure this symbol's pointers to InputSections point to their canonical
   // copies.
   void canonicalize();
 
   static bool classof(const Symbol *s) { return s->kind() == DefinedKind; }
 
   // Place the bitfields first so that they can get placed in the tail padding
   // of the parent class, on platforms which support it.

lld/MachO/Symbols.cpp

 
 void Defined::canonicalize() {
   if (unwindEntry)
     unwindEntry = unwindEntry->canonical();
   if (isec)
     isec = isec->canonical();
 }
 
+std::string Defined::getSourceLocation() {
+  if (!isec)
+    return {};
+  return isec->getSourceLocation(value);
+}
+
 uint64_t DylibSymbol::getVA() const {
   return isInStubs() ? getStubVA() : Symbol::getVA();
 }
 
 void LazyArchive::fetchArchiveMember() { getFile()->fetch(sym); }

lld/test/MachO/invalid/duplicate-symbol-debug.s

+# REQUIRES: aarch64
+# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t.o
+# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t-dup.o
+# RUN: not %lld -dylib -arch arm64 -o /dev/null %t.o %t-dup.o 2>&1 | FileCheck %s -DFILE_1=%t.o -DFILE_2=%t-dup.o
+
+# CHECK:      error: duplicate symbol: _foo
+# CHECK-NEXT: >>> defined in duplicate-symbol-debug.s:20
+# CHECK-NEXT: >>>            [[FILE_1]]
+# CHECK-NEXT: >>> defined in duplicate-symbol-debug.s:20
+# CHECK-NEXT: >>>            [[FILE_2]]
+
+## Test case adapted from lld/test/ELF/Inputs/vs-diagnostics-duplicate2.s
+
+.file 1 "" "duplicate-symbol-debug.s"
+
+.text
+
+.globl _foo
+.loc 1 20
+_foo:
+  nop
+
+.section __DWARF,__debug_abbrev,regular,debug
+  .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  0                  ; EOM(1)
+  .byte  0                  ; EOM(2)
+  .byte  0                  ; EOM(3)
+
+.section __DWARF,__debug_info,regular,debug
+  .long Lend0 - Lbegin0     ; Length of Unit
+Lbegin0:
+  .short 4                  ; DWARF version number
+  .long  __debug_abbrev     ; Offset Into Abbrev. Section
+  .byte  8                  ; Address Size (in bytes)
+  .byte  1                  ; Abbrev [1] 0xb:0x1f DW_TAG_compile_unit
+  .long  __debug_line       ; DW_AT_stmt_list
+Lend0:
+  .section __DWARF,__debug_line,regular,debug
+