[lld/mac] Don't crash on 32-bit output binaries when dead-stripping

[thakis]

Summary

Fixes PR50974.

[tschuett]

This is not the same as std::numeric_limits<Ptr>::max()?

[thakis]

In D105399#2857040, @tschuett wrote:

This is not the same as std::numeric_limits<Ptr>::max()?

Yes, it's the same.

[tschuett]

In D105399#2857058, @thakis wrote:

In D105399#2857040, @tschuett wrote:

This is not the same as std::numeric_limits<Ptr>::max()?

Yes, it's the same.

static_cast+ Macro feels hacky. numeric_limits is more descriptive.

[thakis]

In D105399#2857141, @tschuett wrote:

static_cast+ Macro feels hacky. numeric_limits is more descriptive.

I don't see any advantage to numeric_limits here.

[int3]

+1 for numeric_limits, it "constructs" the right value, whereas static_cast is "converting" the wrong value into the right one. but feel free to ignore :)

[thakis]

Fine, landed with numeric_limits.

lld/MachO/UnwindInfoSection.cpp

 static ConcatInputSection *checkTextSegment(InputSection *isec) {
   if (isec->getSegName() != segment_names::text)
     error("compact unwind references address in " + toString(isec) +
           " which is not in segment __TEXT");
   // __text should always be a ConcatInputSection.
   return cast<ConcatInputSection>(isec);
 }
 
+template <class Ptr>
+constexpr Ptr TombstoneValue = std::numeric_limits<Ptr>::max();
+
 // We need to apply the relocations to the pre-link compact unwind section
 // before converting it to post-link form. There should only be absolute
 // relocations here: since we are not emitting the pre-link CU section, there
 // is no source address to make a relative location meaningful.
 template <class Ptr>
 static void
 relocateCompactUnwind(ConcatOutputSection *compactUnwindSection,
                       std::vector<CompactUnwindEntry<Ptr>> &cuVector) {
   for (const ConcatInputSection *isec : compactUnwindSection->inputs) {
     assert(isec->parent == compactUnwindSection);
 
     uint8_t *buf =
         reinterpret_cast<uint8_t *>(cuVector.data()) + isec->outSecOff;
     memcpy(buf, isec->data.data(), isec->data.size());
 
     for (const Reloc &r : isec->relocs) {
-      uint64_t referentVA = UINT64_MAX; // Tombstone value
+      uint64_t referentVA = TombstoneValue<Ptr>;
       if (auto *referentSym = r.referent.dyn_cast<Symbol *>()) {
         if (!isa<Undefined>(referentSym)) {
           assert(referentSym->isInGot());
           if (auto *defined = dyn_cast<Defined>(referentSym))
             checkTextSegment(defined->isec);
           // At this point in the link, we may not yet know the final address of
           // the GOT, so we just encode the index. We make it a 1-based index so
           // that we can distinguish the null pointer case.

 // unwind info need explicit "no unwind info" unwind entries -- else the
 // unwinder would think they have the unwind info of the closest function
 // with unwind info right before in the image.
 template <class Ptr>
 static void addEntriesForFunctionsWithoutUnwindInfo(
     std::vector<CompactUnwindEntry<Ptr>> &cuVector) {
   DenseSet<Ptr> hasUnwindInfo;
   for (CompactUnwindEntry<Ptr> &cuEntry : cuVector)
-    if (cuEntry.functionAddress != UINT64_MAX)
+    if (cuEntry.functionAddress != TombstoneValue<Ptr>)
       hasUnwindInfo.insert(cuEntry.functionAddress);
 
   // Add explicit "has no unwind info" entries for all global and local symbols
   // without unwind info.
   auto markNoUnwindInfo = [&cuVector, &hasUnwindInfo](const Defined *d) {
     if (d->isLive() && d->isec && isCodeSection(d->isec)) {
       Ptr ptr = d->getVA();
       if (!hasUnwindInfo.count(ptr))
template <class Ptr> void UnwindInfoSectionImpl<Ptr>::finalize() {
   cuPtrVector.reserve(cuCount);
   for (CompactUnwindEntry<Ptr> &cuEntry : cuVector)
     cuPtrVector.emplace_back(&cuEntry);
   llvm::sort(cuPtrVector, [](const CompactUnwindEntry<Ptr> *a,
                              const CompactUnwindEntry<Ptr> *b) {
     return a->functionAddress < b->functionAddress;
   });
 
-  // Dead-stripped functions get a functionAddress of UINT64_MAX in
+  // Dead-stripped functions get a functionAddress of TombstoneValue in
   // relocateCompactUnwind(). Filter them out here.
   // FIXME: This doesn't yet collect associated data like LSDAs kept
   // alive only by a now-removed CompactUnwindEntry or other comdat-like
   // data (`kindNoneGroupSubordinate*` in ld64).
   CompactUnwindEntry<Ptr> tombstone;
-  tombstone.functionAddress = static_cast<Ptr>(UINT64_MAX);
+  tombstone.functionAddress = TombstoneValue<Ptr>;
   cuPtrVector.erase(
       std::lower_bound(cuPtrVector.begin(), cuPtrVector.end(), &tombstone,
                        [](const CompactUnwindEntry<Ptr> *a,
                           const CompactUnwindEntry<Ptr> *b) {
                          return a->functionAddress < b->functionAddress;
                        }),
       cuPtrVector.end());
 

lld/test/MachO/compact-unwind.s

 # REQUIRES: x86, aarch64
 # RUN: rm -rf %t; split-file %s %t
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin19.0.0 %t/my-personality.s -o %t/x86_64-my-personality.o
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin19.0.0 %t/main.s -o %t/x86_64-main.o
 # RUN: %lld -arch x86_64 -pie -lSystem -lc++ %t/x86_64-my-personality.o %t/x86_64-main.o -o %t/x86_64-personality-first
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/x86_64-personality-first | FileCheck %s --check-prefixes=FIRST,CHECK -D#%x,BASE=0x100000000
-# RUN: %lld -arch x86_64 -pie -lSystem -lc++ %t/x86_64-main.o %t/x86_64-my-personality.o -o %t/x86_64-personality-second
+# RUN: %lld -dead_strip -arch x86_64 -pie -lSystem -lc++ %t/x86_64-main.o %t/x86_64-my-personality.o -o %t/x86_64-personality-second
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/x86_64-personality-second | FileCheck %s --check-prefixes=SECOND,CHECK -D#%x,BASE=0x100000000
 
 # RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin19.0.0 %t/my-personality.s -o %t/arm64-my-personality.o
 # RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin19.0.0 %t/main.s -o %t/arm64-main.o
 # RUN: %lld -arch arm64 -pie -lSystem -lc++ %t/arm64-my-personality.o %t/arm64-main.o -o %t/arm64-personality-first
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/arm64-personality-first | FileCheck %s --check-prefixes=FIRST,CHECK -D#%x,BASE=0x100000000
-# RUN: %lld -arch arm64 -pie -lSystem -lc++ %t/arm64-main.o %t/arm64-my-personality.o -o %t/arm64-personality-second
+# RUN: %lld -dead_strip -arch arm64 -pie -lSystem -lc++ %t/arm64-main.o %t/arm64-my-personality.o -o %t/arm64-personality-second
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/arm64-personality-second | FileCheck %s --check-prefixes=SECOND,CHECK -D#%x,BASE=0x100000000
 
 # RUN: llvm-mc -filetype=obj -triple=arm64_32-apple-watchos %t/my-personality.s -o %t/arm64-32-my-personality.o
 # RUN: llvm-mc -filetype=obj -triple=arm64_32-apple-watchos %t/main.s -o %t/arm64-32-main.o
 # RUN: %lld-watchos -pie -lSystem -lc++ %t/arm64-32-my-personality.o %t/arm64-32-main.o -o %t/arm64-32-personality-first
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/arm64-32-personality-first | FileCheck %s --check-prefixes=FIRST,CHECK -D#%x,BASE=0x4000
-# RUN: %lld-watchos -pie -lSystem -lc++ %t/arm64-32-main.o %t/arm64-32-my-personality.o -o %t/arm64-32-personality-second
+# RUN: %lld-watchos -dead_strip -pie -lSystem -lc++ %t/arm64-32-main.o %t/arm64-32-my-personality.o -o %t/arm64-32-personality-second
 # RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/arm64-32-personality-second | FileCheck %s --check-prefixes=SECOND,CHECK -D#%x,BASE=0x4000
 
 # FIRST:      Indirect symbols for (__DATA_CONST,__got)
 # FIRST-NEXT: address                    index name
 # FIRST-DAG:  0x[[#%x,GXX_PERSONALITY:]] [[#]] ___gxx_personality_v0
 # FIRST-DAG:  0x[[#%x,MY_PERSONALITY:]]  LOCAL
 
 # SECOND:      Indirect symbols for (__DATA_CONST,__got)
_main:
   ret
   .cfi_endproc
 
 ## _quux has no unwind information.
 ## (In real life, it'd be part of a separate TU that was built with
 ## -fno-exceptions, while the previous and next TU might be Objective-C++
 ## which has unwind info for Objective-C).
 .p2align 2
+.no_dead_strip _quux
 _quux:
   ret
 
 .globl _abs
+.no_dead_strip _abs
 _abs = 4
 
 .p2align 2
+.no_dead_strip _baz
 _baz:
   .cfi_startproc
 ## This will generate a symbol relocation. Check that we reuse the personality
 ## referenced by the section relocation in my_personality.s.
   .cfi_personality 155, _my_personality
   .cfi_lsda 16, _exception1
   .cfi_def_cfa_offset 16
   ret
   .cfi_endproc
 
+.globl _stripped
+_stripped:
+  .cfi_startproc
+  .cfi_personality 155, ___gxx_personality_v0
+  .cfi_lsda 16, _exception1
+  .cfi_def_cfa_offset 16
+  ret
+  .cfi_endproc
+
 
 .section __TEXT,__gcc_except_tab
 _exception1:
   .space 1
+
+.subsections_via_symbols