[lld-macho] Better deduplication of personality pointers

[int3]

Summary

D95809: [lld-macho] Emit personalities in compact unwind introduced a mechanism for synthetic symbol creation of personality
pointers. When multiple section relocations referred to the same personality
pointer, it would deduplicate them. However, it neglected to consider that we
could have symbol relocations that also refer to the same personality pointer.
This diff fixes it.

In practice, this mix of relocations arises when there is a statically-linked
personality routine that is referenced from multiple object files. Within the
same object file, it will be referred to via section relocations, but
(obviously) other object files will refer to it via symbol relocations. Failing
to deduplicate these references resulted in us going over the
3-personality-pointer limit when linking some larger applications.

Fixes llvm.org/PR48389.

[thakis]

Woot!

lld/MachO/UnwindInfoSection.cpp

123

nit: put a continue; here, move code below out of else and dedent (https://llvm.org/docs/CodingStandards.html#use-early-exits-and-continue-to-simplify-code)

134

same here, add continue here, remove else below

140

same here too: continue after handling the dylib symbol, use if without else here

[int3]

continues

lld/MachO/UnwindInfoSection.cpp

UnwindInfoSection::UnwindInfoSection()
     : SyntheticSection(segment_names::text, section_names::unwindInfo) {
   align = 4; // mimic ld64
 }
 
 bool UnwindInfoSection::isNeeded() const {
   return (compactUnwindSection != nullptr);
 }
 
+SmallDenseMap<std::pair<InputSection *, uint64_t /* addend */>, macho::Symbol *>
+    personalityTable;
+
 // Compact unwind relocations have different semantics, so we handle them in a
 // separate code path from regular relocations. First, we do not wish to add
 // rebase opcodes for __LD,__compact_unwind, because that section doesn't
 // actually end up in the final binary. Second, personality pointers always
 // reside in the GOT and must be treated specially.
 void macho::prepareCompactUnwind(InputSection *isec) {
   assert(isec->segname == segment_names::ld &&
          isec->name == section_names::compactUnwind);
 
-  DenseMap<std::pair<InputSection *, uint64_t /* addend */>, macho::Symbol *>
-      anonPersonalitySymbols;
   for (Reloc &r : isec->relocs) {
-    // TODO: generalize for other archs
-    assert(r.type == X86_64_RELOC_UNSIGNED);
+    assert(target->hasAttr(r.type, RelocAttrBits::UNSIGNED));
     if (r.offset % sizeof(CompactUnwindEntry64) !=
         offsetof(struct CompactUnwindEntry64, personality))
       continue;
 
     if (auto *s = r.referent.dyn_cast<lld::macho::Symbol *>()) {
-      if (auto *undefined = dyn_cast<Undefined>(s))
+      if (auto *undefined = dyn_cast<Undefined>(s)) {
         treatUndefinedSymbol(*undefined);
-      else
+      } else {
+        if (auto *defined = dyn_cast<Defined>(s)) {
+          // Check if we have created a synthetic symbol at the same address.
+          macho::Symbol *&personality =
+              personalityTable[{defined->isec, defined->value}];
+          if (personality == nullptr) {
+            personality = defined;
+            in.got->addEntry(defined);
+          } else if (personality != defined) {
+            r.referent = personality;
+          }
+        } else {
+          assert(isa<DylibSymbol>(s));
           in.got->addEntry(s);
+        }
+      }
     } else if (auto *referentIsec = r.referent.dyn_cast<InputSection *>()) {
       // Personality functions can be referenced via section relocations
-      // if they live in an object file (instead of a dylib). Create
-      // placeholder synthetic symbols for them in the GOT.
-      macho::Symbol *&s = anonPersonalitySymbols[{referentIsec, r.addend}];
+      // if they live in the same object file. Create placeholder synthetic
+      // symbols for them in the GOT.
+      macho::Symbol *&s = personalityTable[{referentIsec, r.addend}];
       if (s == nullptr) {
         s = make<Defined>("<internal>", nullptr, referentIsec, r.addend, false,
                           false, false);
         in.got->addEntry(s);
       }
       r.referent = s;
       r.addend = 0;
     }
void UnwindInfoSection::finalize() {
   // we can fold adjacent CU entries with identical
   // encoding+personality+lsda. Folding is necessary because it reduces
   // the number of CU entries by as much as 3 orders of magnitude!
   compactUnwindSection->finalize();
   assert(compactUnwindSection->getSize() % sizeof(CompactUnwindEntry64) == 0);
   size_t cuCount =
       compactUnwindSection->getSize() / sizeof(CompactUnwindEntry64);
   cuVector.resize(cuCount);
-  // Relocate all __LD,__compact_unwind entries
   relocateCompactUnwind(compactUnwindSection, cuVector);
 
   // Rather than sort & fold the 32-byte entries directly, we create a
   // vector of pointers to entries and sort & fold that instead.
   cuPtrVector.reserve(cuCount);
   for (CompactUnwindEntry64 &cuEntry : cuVector)
     cuPtrVector.emplace_back(&cuEntry);
   std::sort(cuPtrVector.begin(), cuPtrVector.end(),

lld/test/MachO/compact-unwind.s

 # REQUIRES: x86
-# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin19.0.0 %s -o %t.o
-# RUN: %lld -pie -lSystem -lc++ %t.o -o %t
-# RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t | FileCheck %s
-
-# CHECK:      Indirect symbols for (__DATA_CONST,__got)
-# CHECK-NEXT: address                    index name
-# CHECK-DAG:  0x[[#%x,GXX_PERSONALITY:]] [[#]] ___gxx_personality_v0
-# CHECK-DAG:  0x[[#%x,MY_PERSONALITY:]]  LOCAL
+# 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/my_personality.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin19.0.0 %t/main.s -o %t/main.o
+# RUN: %lld -pie -lSystem -lc++ %t/my_personality.o %t/main.o -o %t/personality-first
+# RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/personality-first | FileCheck %s --check-prefixes=FIRST,CHECK
+# RUN: %lld -pie -lSystem -lc++ %t/main.o %t/my_personality.o -o %t/personality-second
+# RUN: llvm-objdump --macho --unwind-info --syms --indirect-symbols --rebase %t/personality-second | FileCheck %s --check-prefixes=SECOND,CHECK
+
+# 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)
+# SECOND-NEXT: address                    index name
+# SECOND-DAG:  0x[[#%x,GXX_PERSONALITY:]] [[#]] ___gxx_personality_v0
+# SECOND-DAG:  0x[[#%x,MY_PERSONALITY:]]  [[#]] _my_personality
 
 # CHECK:      SYMBOL TABLE:
 # CHECK-DAG:  [[#%x,MAIN:]]       g  F __TEXT,__text _main
-# CHECK-DAG:  [[#%x,FOO:]]        g  F __TEXT,__text _foo
+# CHECK-DAG:  [[#%x,FOO:]]        l  F __TEXT,__text _foo
 # CHECK-DAG:  [[#%x,EXCEPTION0:]] g  O __TEXT,__gcc_except_tab _exception0
 # CHECK-DAG:  [[#%x,EXCEPTION1:]] g  O __TEXT,__gcc_except_tab _exception1
 
 # CHECK:      Contents of __unwind_info section:
 # CHECK:        Personality functions: (count = 2)
-# CHECK-NEXT:     personality[1]: 0x{{0*}}[[#MY_PERSONALITY-0x100000000]]
-# CHECK-NEXT:     personality[2]: 0x{{0*}}[[#GXX_PERSONALITY-0x100000000]]
+# CHECK-DAG:     personality[{{[0-9]+}}]: 0x{{0*}}[[#MY_PERSONALITY-0x100000000]]
+# CHECK-DAG:     personality[{{[0-9]+}}]: 0x{{0*}}[[#GXX_PERSONALITY-0x100000000]]
 # CHECK:        LSDA descriptors:
-# CHECK-NEXT:     [0]: function offset=0x{{0*}}[[#FOO-0x100000000]],  LSDA offset=0x{{0*}}[[#EXCEPTION0-0x100000000]]
-# CHECK-NEXT:     [1]: function offset=0x{{0*}}[[#MAIN-0x100000000]], LSDA offset=0x{{0*}}[[#EXCEPTION1-0x100000000]]
+# CHECK-DAG:     function offset=0x{{0*}}[[#FOO-0x100000000]],  LSDA offset=0x{{0*}}[[#EXCEPTION0-0x100000000]]
+# CHECK-DAG:     function offset=0x{{0*}}[[#MAIN-0x100000000]], LSDA offset=0x{{0*}}[[#EXCEPTION1-0x100000000]]
 
 ## Check that we do not add rebase opcodes to the compact unwind section.
 # CHECK:      Rebase table:
 # CHECK-NEXT: segment      section        address          type
 # CHECK-NEXT: __DATA_CONST __got          0x{{[0-9a-f]*}}  pointer
-# CHECK-NEXT: __DATA_CONST __got          0x{{[0-9a-f]*}}  pointer
-# CHECK-EMPTY:
-
-.globl _main, _foo, _my_personality, _bar, _exception0, _exception1
+# CHECK-NOT:  __TEXT
 
+#--- my_personality.s
+.globl _my_personality, _exception0
 .text
 _foo:
   .cfi_startproc
+## This will generate a section relocation.
   .cfi_personality 155, _my_personality
   .cfi_lsda 16, _exception0
   .cfi_def_cfa_offset 16
   retq
   .cfi_endproc
 
 _bar:
   .cfi_startproc
 ## Check that we dedup references to the same statically-linked personality.
   .cfi_personality 155, _my_personality
   .cfi_lsda 16, _exception0
   .cfi_def_cfa_offset 16
   retq
   .cfi_endproc
 
+_my_personality:
+  retq
+
+.section __TEXT,__gcc_except_tab
+_exception0:
+  .space 1
+
+#--- main.s
+.globl _main, _my_personality, _exception1
+
+.text
 _main:
   .cfi_startproc
   .cfi_personality 155, ___gxx_personality_v0
   .cfi_lsda 16, _exception1
   .cfi_def_cfa_offset 16
   retq
   .cfi_endproc
 
-_my_personality:
+_baz:
+  .cfi_startproc
+## This will generate a symbol relocation. Check that we reuse the personality
+## referenced by the section relocations in my_personality.s.
+  .cfi_personality 155, _my_personality
+  .cfi_lsda 16, _exception1
+  .cfi_def_cfa_offset 16
   retq
+  .cfi_endproc
+
 
 .section __TEXT,__gcc_except_tab
-_exception0:
-  .space 1
 _exception1:
   .space 1