[lld-macho] Fix assertion when two symbols at same addr have unwind info

If there are multiple symbols at the same address, our unwind info
implementation assumes that we always register unwind entries to a
single canonical symbol.

This assumption was violated by the `registerEhFrame` code.

Fixes #56570.

Reviewed By: #lld-macho, thakis

Differential Revision: https://reviews.llvm.org/D130208

4 files changed, 193 insertions, 1 deletions

diff --git a/lld/MachO/InputFiles.cpp b/lld/MachO/InputFiles.cpp
index 5bc333f..a2c27f1 100644
--- a/lld/MachO/InputFiles.cpp
+++ b/lld/MachO/InputFiles.cpp
@@ -1528,6 +1528,13 @@ void ObjFile::registerEhFrames(Section &ehFrameSection) {
     Defined *funcSym;
     if (funcAddrRelocIt != isec->relocs.end()) {
       funcSym = targetSymFromCanonicalSubtractor(isec, funcAddrRelocIt);
+      // Canonicalize the symbol. If there are multiple symbols at the same
+      // address, we want both `registerEhFrame` and `registerCompactUnwind`
+      // to register the unwind entry under same symbol.
+      // This is not particularly efficient, but we should run into this case
+      // infrequently (only when handling the output of `ld -r`).
+      funcSym = findSymbolAtOffset(cast<ConcatInputSection>(funcSym->isec),
+                                   funcSym->value);
     } else {
       funcSym = findSymbolAtAddress(sections, funcAddr);
       ehRelocator.makePcRel(funcAddrOff, funcSym, target->p2WordSize);
diff --git a/lld/MachO/UnwindInfoSection.cpp b/lld/MachO/UnwindInfoSection.cpp
index 8c3425a..3220579 100644
--- a/lld/MachO/UnwindInfoSection.cpp
+++ b/lld/MachO/UnwindInfoSection.cpp
@@ -211,7 +211,7 @@ void UnwindInfoSection::addSymbol(const Defined *d) {
   // we use that as the key here.
   auto p = symbols.insert({{d->isec, d->value}, d});
   // If we have multiple symbols at the same address, only one of them can have
-  // an associated CUE.
+  // an associated unwind entry.
   if (!p.second && d->unwindEntry) {
     assert(!p.first->second->unwindEntry);
     p.first->second = d;
diff --git a/lld/test/MachO/Inputs/double-unwind-info.yaml b/lld/test/MachO/Inputs/double-unwind-info.yaml
new file mode 100644
index 0000000..077f334
--- /dev/null
+++ b/lld/test/MachO/Inputs/double-unwind-info.yaml
@@ -0,0 +1,159 @@
+--- !mach-o
+FileHeader:
+  magic:           0xFEEDFACF
+  cputype:         0x1000007
+  cpusubtype:      0x3
+  filetype:        0x1
+  ncmds:           4
+  sizeofcmds:      384
+  flags:           0x2000
+  reserved:        0x0
+LoadCommands:
+  - cmd:             LC_SEGMENT_64
+    cmdsize:         312
+    segname:         ''
+    vmaddr:          0
+    vmsize:          96
+    fileoff:         448
+    filesize:        96
+    maxprot:         7
+    initprot:        7
+    nsects:          3
+    flags:           0
+    Sections:
+      - sectname:        __text
+        segname:         __TEXT
+        addr:            0x0
+        size:            2
+        offset:          0x1C0
+        align:           0
+        reloff:          0x0
+        nreloc:          0
+        flags:           0x80000400
+        reserved1:       0x0
+        reserved2:       0x0
+        reserved3:       0x0
+        content:         '9090'
+      - sectname:        __eh_frame
+        segname:         __TEXT
+        addr:            0x8
+        size:            56
+        offset:          0x1C8
+        align:           3
+        reloff:          0x220
+        nreloc:          4
+        flags:           0x0
+        reserved1:       0x0
+        reserved2:       0x0
+        reserved3:       0x0
+        content:         1400000000000000017A520001781001100C0708900100001C00000004000000F8FFFFFFFFFFFFFF0100000000000000000E080000000000
+        relocations:
+          - address:         0x1C
+            symbolnum:       3
+            pcrel:           false
+            length:          2
+            extern:          true
+            type:            5
+            scattered:       false
+            value:           0
+          - address:         0x1C
+            symbolnum:       4
+            pcrel:           false
+            length:          2
+            extern:          true
+            type:            0
+            scattered:       false
+            value:           0
+          - address:         0x20
+            symbolnum:       4
+            pcrel:           false
+            length:          3
+            extern:          true
+            type:            5
+            scattered:       false
+            value:           0
+          - address:         0x20
+            symbolnum:       2
+            pcrel:           false
+            length:          3
+            extern:          true
+            type:            0
+            scattered:       false
+            value:           0
+      - sectname:        __compact_unwind
+        segname:         __LD
+        addr:            0x40
+        size:            32
+        offset:          0x200
+        align:           3
+        reloff:          0x240
+        nreloc:          1
+        flags:           0x2000000
+        reserved1:       0x0
+        reserved2:       0x0
+        reserved3:       0x0
+        content:         '0000000000000000010000000000010200000000000000000000000000000000'
+        relocations:
+          - address:         0x0
+            symbolnum:       2
+            pcrel:           false
+            length:          3
+            extern:          true
+            type:            0
+            scattered:       false
+            value:           0
+  - cmd:             LC_SYMTAB
+    cmdsize:         24
+    symoff:          584
+    nsyms:           5
+    stroff:          664
+    strsize:         40
+  - cmd:             LC_BUILD_VERSION
+    cmdsize:         32
+    platform:        1
+    minos:           659200
+    sdk:             0
+    ntools:          1
+    Tools:
+      - tool:            3
+        version:         50069504
+  - cmd:             LC_DATA_IN_CODE
+    cmdsize:         16
+    dataoff:         584
+    datasize:        0
+LinkEditData:
+  NameList:
+    - n_strx:          2
+      n_type:          0xE
+      n_sect:          1
+      n_desc:          0
+      n_value:         0
+    - n_strx:          10
+      n_type:          0xE
+      n_sect:          1
+      n_desc:          0
+      n_value:         1
+    - n_strx:          16
+      n_type:          0xE
+      n_sect:          1
+      n_desc:          0
+      n_value:         1
+    - n_strx:          21
+      n_type:          0xE
+      n_sect:          2
+      n_desc:          0
+      n_value:         8
+    - n_strx:          31
+      n_type:          0xE
+      n_sect:          2
+      n_desc:          0
+      n_value:         32
+  StringTable:
+    - ' '
+    - _spacer
+    - ltmp1
+    - _foo
+    - EH_Frame1
+    - func.eh
+    - ''
+...
diff --git a/lld/test/MachO/double-unwind-info.s b/lld/test/MachO/double-unwind-info.s
new file mode 100644
index 0000000..d1301cb
--- /dev/null
+++ b/lld/test/MachO/double-unwind-info.s
@@ -0,0 +1,26 @@
+## When changing the assembly input, uncomment these lines to re-generate the
+## YAML.
+# COM: llvm-mc --emit-dwarf-unwind=always -filetype=obj -triple=x86_64-apple-macos10.15 %s -o %t.o
+# COM: ld -r %t.o -o %t-r.o
+# COM: obj2yaml %t-r.o > %S/Inputs/double-unwind-info.yaml
+
+# RUN: yaml2obj %S/Inputs/double-unwind-info.yaml > %t-r.o
+# RUN: %lld -dylib -lSystem %t-r.o -o /dev/null
+
+.text
+## eh_frame function address relocations are only emitted if the function isn't
+## at address 0x0.
+_spacer:
+  nop
+
+## Check that we perform unwind info registration correctly when there are
+## multiple symbols at the same address. This would previously hit an assertion
+## error (PR56570).
+_foo:
+ltmp1:
+  .cfi_startproc
+  .cfi_def_cfa_offset 8
+  nop
+  .cfi_endproc
+
+.subsections_via_symbols