[lld-macho][nfc] Refactor subtractor reloc handling

[int3]

Summary

SUBTRACTOR relocations are always paired with UNSIGNED
relocations to indicate a pair of symbols whose address difference we
want. Functionally they are like a single relocation: only one pointer
gets written / relocated. Previously, we would handle these pairs by
skipping over the SUBTRACTOR relocation and writing the pointer when
handling the UNSIGNED reloc. This diff reverses things, so we write
while handling SUBTRACTORs and skip over the UNSIGNED relocs instead.

Being able to distinguish between SUBTRACTOR and UNSIGNED relocs in the
write phase (i.e. inside relocateOne) is useful for the upcoming range
check diff: we want to check that SUBTRACTOR relocs write signed values,
but UNSIGNED relocs (naturally) write unsigned values.

lld/MachO/Arch/ARM64.cpp

#undef B
   assert(type < relocAttrsArray.size() && "invalid relocation type");
   if (type >= relocAttrsArray.size())
     return invalidRelocAttrs;
   return relocAttrsArray[type];
 }
 
 uint64_t ARM64::getEmbeddedAddend(MemoryBufferRef mb, const section_64 &sec,
                                   const relocation_info rel) const {
-  if (rel.r_type != ARM64_RELOC_UNSIGNED) {
+  if (rel.r_type != ARM64_RELOC_UNSIGNED &&
+      rel.r_type != ARM64_RELOC_SUBTRACTOR) {
     // All other reloc types should use the ADDEND relocation to store their
     // addends.
     // TODO(gkm): extract embedded addend just so we can assert that it is 0
     return 0;
   }
 
   auto *buf = reinterpret_cast<const uint8_t *>(mb.getBufferStart());
   const uint8_t *loc = buf + sec.offset + rel.r_address;

 void ARM64::relocateOne(uint8_t *loc, const Reloc &r, uint64_t value,
                         uint64_t pc) const {
   uint32_t base = ((r.length == 2) ? read32le(loc) : 0);
   value += r.addend;
   switch (r.type) {
   case ARM64_RELOC_BRANCH26:
     value = encodeBranch26(base, value - pc);
     break;
+  case ARM64_RELOC_SUBTRACTOR:
   case ARM64_RELOC_UNSIGNED:
     break;
   case ARM64_RELOC_POINTER_TO_GOT:
     if (r.pcrel)
       value -= pc;
     break;
   case ARM64_RELOC_PAGE21:
   case ARM64_RELOC_GOT_LOAD_PAGE21:

lld/MachO/InputFiles.cpp

if (target->hasAttr(relInfo.r_type, RelocAttrBits::ADDEND)) {
       relInfo = relInfos[++i];
     }
     assert(i < relInfos.size());
     if (!validateRelocationInfo(this, sec, relInfo))
       continue;
     if (relInfo.r_address & R_SCATTERED)
       fatal("TODO: Scattered relocations not supported");
 
-    Reloc p;
-    if (target->hasAttr(relInfo.r_type, RelocAttrBits::SUBTRAHEND)) {
-      p.type = relInfo.r_type;
-      p.referent = symbols[relInfo.r_symbolnum];
-      relInfo = relInfos[++i];
-      // SUBTRACTOR relocations should always be followed by an UNSIGNED one
-      // indicating the minuend symbol.
-      assert(target->hasAttr(relInfo.r_type, RelocAttrBits::UNSIGNED) &&
-             relInfo.r_extern);
-    }
     uint64_t embeddedAddend = target->getEmbeddedAddend(mb, sec, relInfo);
     assert(!(embeddedAddend && pairedAddend));
     uint64_t totalAddend = pairedAddend + embeddedAddend;
     Reloc r;
     r.type = relInfo.r_type;
     r.pcrel = relInfo.r_pcrel;
     r.length = relInfo.r_length;
     r.offset = relInfo.r_address;
if (relInfo.r_extern) {
         // The addend for a non-pcrel relocation is its absolute address.
         referentOffset = totalAddend - referentSec.addr;
       }
       r.referent = findContainingSubsection(referentSubsecMap, &referentOffset);
       r.addend = referentOffset;
     }
 
     InputSection *subsec = findContainingSubsection(subsecMap, &r.offset);
-    if (p.type != GENERIC_RELOC_INVALID)
-      subsec->relocs.push_back(p);
     subsec->relocs.push_back(r);
+
+    if (target->hasAttr(r.type, RelocAttrBits::SUBTRAHEND)) {
+      relInfo = relInfos[++i];
+      // SUBTRACTOR relocations should always be followed by an UNSIGNED one
+      // indicating the minuend symbol.
+      assert(target->hasAttr(relInfo.r_type, RelocAttrBits::UNSIGNED) &&
+             relInfo.r_extern);
+      Reloc p;
+      p.type = relInfo.r_type;
+      p.referent = symbols[relInfo.r_symbolnum];
+      subsec->relocs.push_back(p);
+    }
   }
 }
 
 static macho::Symbol *createDefined(const structs::nlist_64 &sym,
                                     StringRef name, InputSection *isec,
                                     uint32_t value) {
   // Symbol scope is determined by sym.n_type & (N_EXT | N_PEXT):
   // N_EXT: Global symbols

lld/MachO/InputSection.cpp

 
 void InputSection::writeTo(uint8_t *buf) {
   if (getFileSize() == 0)
     return;
 
   memcpy(buf, data.data(), data.size());
 
   for (size_t i = 0; i < relocs.size(); i++) {
-    const Symbol *fromSym =
-        target->hasAttr(relocs[i].type, RelocAttrBits::SUBTRAHEND)
-            ? relocs[i++].referent.get<Symbol *>()
-            : nullptr;
     const Reloc &r = relocs[i];
     uint8_t *loc = buf + r.offset;
     uint64_t referentVA = 0;
-    if (fromSym) {
-      const Symbol *toSym = r.referent.get<Symbol *>();
+    if (target->hasAttr(r.type, RelocAttrBits::SUBTRAHEND)) {
+      const Symbol *fromSym = r.referent.get<Symbol *>();
+      const Symbol *toSym = relocs[++i].referent.get<Symbol *>();
       referentVA = toSym->getVA() - fromSym->getVA();
     } else if (auto *referentSym = r.referent.dyn_cast<Symbol *>()) {
       if (target->hasAttr(r.type, RelocAttrBits::LOAD) &&
           !referentSym->isInGot())
         target->relaxGotLoad(loc, r.type);
       referentVA = resolveSymbolVA(loc, *referentSym, r.type);
 
       if (isThreadLocalVariables(flags)) {

lld/test/MachO/reloc-subtractor.s

 # CHECK:       [[#SUB1ADDR]] 10000000
 # CHECK-NEXT:  [[#SUB2ADDR]] f2ffffff
 # CHECK-NEXT:  [[#SUB3ADDR]] 14000000 00000000
 # CHECK-NEXT:  [[#SUB4ADDR]] f6ffffff ffffffff
 # CHECK:       Rebase table:
 # CHECK-NEXT:  segment  section            address     type
 # CHECK-EMPTY:
 
-.globl _main, _subtrahend_1, _subtrahend_2, _minued1, _minued2
+.globl _main, _subtrahend_1, _subtrahend_2, _minuend1, _minuend2
 
 .data
 _subtrahend_1:
   .space 16
 _minuend_1:
   .space 16
 _minuend_2:
   .space 16