[lld-macho] Fix duplicate GOT entries for personality functions (#95054)

As stated in `UnwindInfoSectionImpl::prepareRelocations`'s comments, the
unwind info uses section+addend relocations for personality functions
defined in the same file as the function itself. As personality
functions are always accessed via the GOT, we need to resolve those to a
symbol. Previously, we did this by keeping a map which resolves these to
symbols, creating a synthetic symbol if we didn't find it in the map.

This approach has an issue: if we process the object file containing the
personality function before any external uses, the entry in the map
remains unpopulated, so we create a synthetic symbol and a corresponding
GOT entry. If we encounter a relocation to it in a later file which
requires GOT (such as in `__eh_frame`), we add that symbol to the GOT,
too, effectively creating two entries which point to the same piece of
code.

This commit fixes that by searching the personality function's section
for a symbol at that offset which already has a GOT entry, and only
creating a synthetic symbol if there is none. As all non-unwind sections
are already processed by this point, it ensures no duplication.

This should only really affect our tests (and make them clearer), as
personality functions are usually defined in platform runtime libraries.
Or even if they are local, they are likely not in the first object file
to be linked.

Author: BertalanD

lld/MachO/UnwindInfoSection.cpp

@@ -298,19 +298,31 @@ void UnwindInfoSectionImpl::prepareRelocations(ConcatInputSection *isec) {
       assert(!isCoalescedWeak(referentIsec));
       // Personality functions can be referenced via section relocations
       // if they live in the same object file. Create placeholder synthetic
-      // symbols for them in the GOT.
+      // symbols for them in the GOT. If the corresponding symbol is already
+      // in the GOT, use that to avoid creating a duplicate entry. All GOT
+      // entries needed by non-unwind sections will have already been added
+      // by this point.
       Symbol *&s = personalityTable[{referentIsec, r.addend}];
       if (s == nullptr) {
-        // This runs after dead stripping, so the noDeadStrip argument does not
-        // matter.
-        s = make<Defined>("<internal>", /*file=*/nullptr, referentIsec,
-                          r.addend, /*size=*/0, /*isWeakDef=*/false,
-                          /*isExternal=*/false, /*isPrivateExtern=*/false,
-                          /*includeInSymtab=*/true,
-                          /*isReferencedDynamically=*/false,
-                          /*noDeadStrip=*/false);
-        s->used = true;
-        in.got->addEntry(s);
+        Defined *const *gotEntry =
+            llvm::find_if(referentIsec->symbols, [&](Defined const *d) {
+              return d->value == static_cast<uint64_t>(r.addend) &&
+                     d->isInGot();
+            });
+        if (gotEntry != referentIsec->symbols.end()) {
+          s = *gotEntry;
+        } else {
+          // This runs after dead stripping, so the noDeadStrip argument does
+          // not matter.
+          s = make<Defined>("<internal>", /*file=*/nullptr, referentIsec,
+                            r.addend, /*size=*/0, /*isWeakDef=*/false,
+                            /*isExternal=*/false, /*isPrivateExtern=*/false,
+                            /*includeInSymtab=*/true,
+                            /*isReferencedDynamically=*/false,
+                            /*noDeadStrip=*/false);
+          s->used = true;
+          in.got->addEntry(s);
+        }
       }
       r.referent = s;
       r.addend = 0;

lld/test/MachO/compact-unwind-both-local-and-dylib-personality.s

@@ -42,19 +42,20 @@
 
 # RUN: llvm-objdump --macho --indirect-symbols --unwind-info --bind %t/d.out | FileCheck %s --check-prefixes=D -D#%x,OFF=0x100000000
 
-# A:      Indirect symbols for (__DATA_CONST,__got)
+# A:      Indirect symbols for (__DATA_CONST,__got) 4 entries
 # A-NEXT: address                    index name
 # A:      0x[[#%x,GXX_PERSONALITY_LO:]] [[#]] ___gxx_personality_v0
+# A:      0x[[#%x,PERSONALITY_1:]]      [[#]] _personality_1
+# A:      0x[[#%x,PERSONALITY_2:]]      [[#]] _personality_2
 # A:      0x[[#%x,GXX_PERSONALITY_HI:]] [[#]] ___gxx_personality_v0
-# A:      0x[[#%x,PERSONALITY_1:]]  LOCAL
-# A:      0x[[#%x,PERSONALITY_2:]]  LOCAL
 
 # BC:      Indirect symbols for (__DATA_CONST,__got)
 # BC-NEXT: address                    index name
-# C:       0x[[#%x,GXX_PERSONALITY_HI:]] LOCAL
 # BC:      0x[[#%x,GXX_PERSONALITY_LO:]] LOCAL
-# BC:      0x[[#%x,PERSONALITY_1:]]      LOCAL
-# BC:      0x[[#%x,PERSONALITY_2:]]      LOCAL
+# C:       0x[[#%x,GXX_PERSONALITY_HI:]] [[#]] ___gxx_personality_v0
+# BC:      0x[[#%x,PERSONALITY_1:]]      [[#]] _personality_1
+# BC:      0x[[#%x,PERSONALITY_2:]]      [[#]] _personality_2
+# BC-EMPTY:
 
 # CHECK:        Personality functions: (count = 3)
 # CHECK-DAG:     personality[{{[0-9]+}}]: 0x{{0*}}[[#GXX_PERSONALITY_LO-OFF]]
@@ -66,7 +67,7 @@
 # A-NEXT: __DATA_CONST __got        0x[[#GXX_PERSONALITY_LO-0]] pointer         0 libc++abi        ___gxx_personality_v0
 
 
-# D:      Indirect symbols for (__DATA_CONST,__got)
+# D:      Indirect symbols for (__DATA_CONST,__got) 6 entries
 # D-NEXT: address                    index name
 # D:      0x[[#%x,GXX_PERSONALITY_HI:]] [[#]] ___gxx_personality_v0
 # D:      0x[[#%x,PERSONALITY_1:]] [[#]] _personality_1

lld/test/MachO/compact-unwind.s

@@ -29,7 +29,7 @@
 # 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
+# FIRST-DAG:  0x[[#%x,MY_PERSONALITY:]]
 
 # SECOND:      Indirect symbols for (__DATA_CONST,__got)
 # SECOND-NEXT: address                    index name