[lld-macho] Error on encountering undefined symbols

[int3]

Summary

... instead of silently emitting a reference to the zero address.

Depends on D80049.

[smeenai]

LGTM, thanks for fixing!

LLD ELF does this as part of its scanRelocations loop. That might be nicer cos we'd bail out with undefined symbol errors earlier. It doesn't matter a whole lot right now, but we could add a TODO.

[int3]

move to scanRelocations

lld/MachO/InputSection.cpp

 //===- InputSection.cpp ---------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "InputSection.h"
+#include "InputFiles.h"
 #include "OutputSegment.h"
 #include "Symbols.h"
 #include "Target.h"
+#include "lld/Common/ErrorHandler.h"
 #include "lld/Common/Memory.h"
 #include "llvm/Support/Endian.h"
+#include "llvm/Support/Path.h"
 
+using namespace llvm;
 using namespace llvm::MachO;
 using namespace llvm::support;
 using namespace lld;
 using namespace lld::macho;
 
 std::vector<InputSection *> macho::inputSections;
 
 uint64_t InputSection::getFileOffset() const {
   return parent->fileOff + outSecFileOff;
 }
 
 uint64_t InputSection::getVA() const { return parent->addr + outSecOff; }
 
 void InputSection::writeTo(uint8_t *buf) {
   if (!data.empty())
     memcpy(buf, data.data(), data.size());
 
   for (Reloc &r : relocs) {
     uint64_t va = 0;
     if (auto *s = r.target.dyn_cast<Symbol *>()) {
-      if (auto *dylibSymbol = dyn_cast<DylibSymbol>(s)) {
+      if (isa<Undefined>(s)) {
+        error("undefined symbol " + s->getName() + ", referenced from " +
+              sys::path::filename(file->getName()));
+      } else if (auto *dylibSymbol = dyn_cast<DylibSymbol>(s)) {
         va = target->getDylibSymbolVA(*dylibSymbol, r.type);
       } else {
         va = s->getVA();
       }
     } else if (auto *isec = r.target.dyn_cast<InputSection *>()) {
       va = isec->getVA();
     }
 
     uint64_t val = va + r.addend;
     if (r.pcrel)
       val -= getVA() + r.offset;
     target->relocateOne(*this, r, buf + r.offset, val);
   }
 }

lld/test/MachO/invalid/undefined-symbol.s

+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t.o
+# RUN: not lld -flavor darwinnew -Z -o %t %t.o 2>&1 | FileCheck %s -DBASENAME=%basename_t
+# CHECK: error: undefined symbol _foo, referenced from [[BASENAME]]
+
+.globl _main
+.text
+_main:
+  callq _foo
+  movq $0, %rax
+  retq