[lld-macho] Weak locals should be relaxed too

[smeenai]

LGTM; good catch.

lld/MachO/SyntheticSections.cpp

269

I don't have strong feelings about this either way, but would this be better as a method on Symbol vs. an out-of-line function?

[int3]

lld/MachO/SyntheticSections.cpp

269

I put it here since its logic is pretty similar (and related) to that in addNonLazyBindingEntries below

lld/MachO/Arch/X86_64.cpp

void X86_64::writeStubHelperEntry(uint8_t *buf, const DylibSymbol &sym,
   writeRipRelative(buf, entryAddr, sizeof(stubHelperEntry),
                    in.stubHelper->addr);
 }
 
 void X86_64::prepareSymbolRelocation(lld::macho::Symbol *sym,
                                      const InputSection *isec, const Reloc &r) {
   switch (r.type) {
   case X86_64_RELOC_GOT_LOAD: {
-    if (sym->isWeakDef() || isa<DylibSymbol>(sym))
+    if (needsBinding(sym))
       in.got->addEntry(sym);
 
     if (sym->isTlv())
       error("found GOT relocation referencing thread-local variable in " +
             toString(isec));
     break;
   }
   case X86_64_RELOC_GOT: {
void X86_64::prepareSymbolRelocation(lld::macho::Symbol *sym,
   }
   case X86_64_RELOC_SIGNED:
   case X86_64_RELOC_SIGNED_1:
   case X86_64_RELOC_SIGNED_2:
   case X86_64_RELOC_SIGNED_4:
     // TODO: warn if they refer to a weak global
     break;
   case X86_64_RELOC_TLV: {
-    if (sym->isWeakDef() || isa<DylibSymbol>(sym))
+    if (needsBinding(sym))
       in.tlvPointers->addEntry(sym);
 
     if (!sym->isTlv())
       error(
           "found X86_64_RELOC_TLV referencing a non-thread-local variable in " +
           toString(isec));
     break;
   }

lld/MachO/SyntheticSections.h

public:
   bool hasNonWeakDefinition() const { return !definitions.empty(); }
 
 private:
   std::vector<WeakBindingEntry> bindings;
   std::vector<const Defined *> definitions;
   SmallVector<char, 128> contents;
 };
 
+// Whether a given symbol's address can only be resolved at runtime.
+bool needsBinding(const Symbol *);
+
 // Add bindings for symbols that need weak or non-lazy bindings.
 void addNonLazyBindingEntries(const Symbol *, SectionPointerUnion,
                               uint64_t offset, int64_t addend = 0);
 
 // The following sections implement lazy symbol binding -- very similar to the
 // PLT mechanism in ELF.
 //
 // ELF's .plt section is broken up into two sections in Mach-O: StubsSection

lld/MachO/SyntheticSections.cpp

void WeakBindingSection::finalizeContents() {
   if (!bindings.empty() || !definitions.empty())
     os << static_cast<uint8_t>(MachO::BIND_OPCODE_DONE);
 }
 
 void WeakBindingSection::writeTo(uint8_t *buf) const {
   memcpy(buf, contents.data(), contents.size());
 }
 
+bool macho::needsBinding(const Symbol *sym) {
+  if (isa<DylibSymbol>(sym)) {
+    return true;
+  } else if (const auto *defined = dyn_cast<Defined>(sym)) {
+    if (defined->isWeakDef() && defined->isExternal())
+      return true;
+  }
+  return false;
+}
+
 void macho::addNonLazyBindingEntries(const Symbol *sym,
                                      SectionPointerUnion section,
                                      uint64_t offset, int64_t addend) {
   if (auto *dysym = dyn_cast<DylibSymbol>(sym)) {
     in.binding->addEntry(dysym, section, offset, addend);
     if (dysym->isWeakDef())
       in.weakBinding->addEntry(sym, section, offset, addend);
   } else if (auto *defined = dyn_cast<Defined>(sym)) {

lld/test/MachO/weak-binding.s

 # CHECK:      Contents of section __got:
 ## Check that this section contains a nonzero pointer. It should point to
 ## _weak_external_for_gotpcrel.
 # CHECK-NEXT: {{[0-9a-f]+}} {{[0-9a-f ]*[1-9a-f]+[0-9a-f ]*}}
 
 # CHECK:      <_main>:
 # CHECK-NEXT: movq  [[#]](%rip), %rax  # [[#%X,WEAK_DY_GOT_ADDR:]]
 # CHECK-NEXT: movq  [[#]](%rip), %rax  # [[#%X,WEAK_EXT_GOT_ADDR:]]
+# CHECK-NEXT: leaq  [[#]](%rip), %rax  # [[#%X,WEAK_INT_GOT_ADDR:]]
 # CHECK-NEXT: movq  [[#]](%rip), %rax  # [[#%X,WEAK_TLV_ADDR:]]
 # CHECK-NEXT: movq  [[#]](%rip), %rax  # [[#%X,WEAK_DY_TLV_ADDR:]]
-# CHECK-NEXT: movq  [[#]](%rip), %rax  # [[#%X,WEAK_INT_TLV_ADDR:]]
+# CHECK-NEXT: leaq  [[#]](%rip), %rax  # [[#%X,WEAK_INT_TLV_ADDR:]]
 # CHECK-NEXT: callq 0x{{[0-9a-f]*}}
 # CHECK-NEXT: callq 0x{{[0-9a-f]*}}
 # CHECK-NEXT: callq 0x{{[0-9a-f]*}}
 
 # CHECK-LABEL: Bind table:
 # CHECK-DAG:   __DATA        __data          0x[[#%x,WEAK_DY:]]      pointer 0 libfoo    _weak_dysym
 # CHECK-DAG:   __DATA        __thread_vars   0x{{[0-9a-f]*}}         pointer 0 libSystem __tlv_bootstrap
 # CHECK-DAG:   __DATA        __thread_ptrs   0x[[#WEAK_DY_TLV_ADDR]] pointer 0 libfoo    _weak_dysym_tlv

 .globl _weak_dysym_tlv
 .weak_definition _weak_dysym_tlv
 _weak_dysym_tlv:
   .quad 0x1234
 
 #--- test.s
 
 .globl _main, _weak_external, _weak_external_for_gotpcrel, _weak_external_fn
-.weak_definition _weak_external, _weak_external_for_gotpcrel, _weak_external_fn, _weak_internal, _weak_internal_fn
+.weak_definition _weak_external, _weak_external_for_gotpcrel, _weak_external_fn, _weak_internal, _weak_internal_for_gotpcrel, _weak_internal_fn
 
 _main:
   mov _weak_dysym_for_gotpcrel@GOTPCREL(%rip), %rax
   mov _weak_external_for_gotpcrel@GOTPCREL(%rip), %rax
+  mov _weak_internal_for_gotpcrel@GOTPCREL(%rip), %rax
   mov _weak_tlv@TLVP(%rip), %rax
   mov _weak_dysym_tlv@TLVP(%rip), %rax
   mov _weak_internal_tlv@TLVP(%rip), %rax
   callq _weak_dysym_fn
   callq _weak_external_fn
   callq _weak_internal_fn
   mov $0, %rax
   ret
 
 _weak_external:
   .quad 0x1234
 
 _weak_external_for_gotpcrel:
   .quad 0x1234
 
 _weak_external_fn:
   ret
 
 _weak_internal:
   .quad 0x1234
 
+_weak_internal_for_gotpcrel:
+  .quad 0x1234
+
 _weak_internal_fn:
   ret
 
 .data
   .quad _weak_dysym
   .quad _weak_external + 2
   .quad _weak_internal