[lld-macho] Define __mh_*_header synthetic symbols.

Bug: https://bugs.llvm.org/show_bug.cgi?id=49290

    Differential Revision: https://reviews.llvm.org/D97007

lld/MachO/Driver.cpp

@@ -1043,14 +1043,7 @@ bool macho::link(ArrayRef<const char *> argsArr, bool canExitEarly,
     }
 
     createSyntheticSections();
-
+    createSyntheticSymbols();
-    // The Itanium C++ ABI requires dylibs to pass a pointer to __cxa_atexit
-    // which does e.g. cleanup of static global variables. The ABI document says
-    // that the pointer can point to any address in one of the dylib's segments,
-    // but in practice ld64 seems to set it to point to the header, so that's
-    // what's implemented here.
-    symtab->addSynthetic("___dso_handle", in.header->isec, 0,
-                         /*privateExtern=*/true, /*linkerInternal=*/true);
 
     for (const Arg *arg : args.filtered(OPT_sectcreate)) {
       StringRef segName = arg->getValue(0);

lld/MachO/SymbolTable.cpp

@@ -159,10 +159,10 @@ Symbol *SymbolTable::addLazy(StringRef name, ArchiveFile *file,
 
 Defined *SymbolTable::addSynthetic(StringRef name, InputSection *isec,
                                    uint32_t value, bool isPrivateExtern,
-                                   bool isLinkerInternal) {
+                                   bool includeInSymtab) {
-  Defined *s = addDefined(name, nullptr, isec, value, /*isWeakDef=*/false,
+  Defined *s = addDefined(name, nullptr, isec, value,
-                          isPrivateExtern);
+                          /*isWeakDef=*/false, isPrivateExtern);
-  s->linkerInternal = isLinkerInternal;
+  s->includeInSymtab = includeInSymtab;
   return s;
 }
 

lld/MachO/SymbolTable.h

@@ -9,6 +9,8 @@
 #ifndef LLD_MACHO_SYMBOL_TABLE_H
 #define LLD_MACHO_SYMBOL_TABLE_H
 
+#include "Symbols.h"
+
 #include "lld/Common/LLVM.h"
 #include "llvm/ADT/CachedHashString.h"
 #include "llvm/ADT/DenseMap.h"
@@ -50,7 +52,7 @@ public:
                   const llvm::object::Archive::Symbol &sym);
 
   Defined *addSynthetic(StringRef name, InputSection *, uint32_t value,
-                        bool isPrivateExtern, bool isLinkerInternal);
+                        bool isPrivateExtern, bool includeInSymtab);
 
   ArrayRef<Symbol *> getSymbols() const { return symVector; }
   Symbol *find(llvm::CachedHashStringRef name);

lld/MachO/Symbols.h

@@ -99,7 +99,7 @@ public:
           bool isWeakDef, bool isExternal, bool isPrivateExtern)
       : Symbol(DefinedKind, name, file), isec(isec), value(value),
         overridesWeakDef(false), privateExtern(isPrivateExtern),
-        linkerInternal(false), weakDef(isWeakDef), external(isExternal) {}
+        includeInSymtab(true), weakDef(isWeakDef), external(isExternal) {}
 
   bool isWeakDef() const override { return weakDef; }
   bool isExternalWeakDef() const {
@@ -124,8 +124,8 @@ public:
   bool overridesWeakDef : 1;
   // Whether this symbol should appear in the output binary's export trie.
   bool privateExtern : 1;
-  // Whether this symbol should appear in the output binary's symbol table.
+  // Whether this symbol should appear in the output symbol table.
-  bool linkerInternal : 1;
+  bool includeInSymtab : 1;
 
 private:
   const bool weakDef : 1;

lld/MachO/SyntheticSections.cpp

@@ -53,7 +53,12 @@ SyntheticSection::SyntheticSection(const char *segname, const char *name)
 // dyld3's MachOLoaded::getSlide() assumes that the __TEXT segment starts
 // from the beginning of the file (i.e. the header).
 MachHeaderSection::MachHeaderSection()
-    : SyntheticSection(segment_names::text, section_names::header) {}
+    : SyntheticSection(segment_names::text, section_names::header) {
+  // XXX: This is a hack. (See D97007)
+  // Setting the index to 1 to pretend that this section is the text
+  // section.
+  index = 1;
+}
 
 void MachHeaderSection::addLoadCommand(LoadCommand *lc) {
   loadCommands.push_back(lc);
@@ -754,7 +759,7 @@ void SymtabSection::finalizeContents() {
 
   for (Symbol *sym : symtab->getSymbols()) {
     if (auto *defined = dyn_cast<Defined>(sym)) {
-      if (defined->linkerInternal)
+      if (!defined->includeInSymtab)
         continue;
       assert(defined->isExternal());
       addSymbol(externalSymbols, defined);
@@ -993,3 +998,56 @@ void CodeSignatureSection::writeTo(uint8_t *buf) const {
   memcpy(id, fileName.begin(), fileName.size());
   memset(id + fileName.size(), 0, fileNamePad);
 }
+
+void macho::createSyntheticSymbols() {
+  auto addHeaderSymbol = [](const char *name) {
+    symtab->addSynthetic(name, in.header->isec, 0,
+                         /*privateExtern=*/true,
+                         /*includeInSymtab*/ false);
+  };
+
+  switch (config->outputType) {
+    // FIXME: Assign the right addresse value for these symbols
+    // (rather than 0). But we need to do that after assignAddresses().
+  case MH_EXECUTE:
+    // If linking PIE, __mh_execute_header is a defined symbol in
+    //  __TEXT, __text)
+    // Otherwise, it's an absolute symbol.
+    if (config->isPic)
+      symtab->addSynthetic("__mh_execute_header", in.header->isec, 0,
+                           /*privateExtern*/ false,
+                           /*includeInSymbtab*/ true);
+    else
+      symtab->addSynthetic("__mh_execute_header",
+                           /*isec*/ nullptr, 0,
+                           /*privateExtern*/ false,
+                           /*includeInSymbtab*/ true);
+    break;
+
+    // The following symbols are  N_SECT symbols, even though the header is not
+    // part of any section and that they are private to the bundle/dylib/object
+    // they are part of.
+  case MH_BUNDLE:
+    addHeaderSymbol("__mh_bundle_header");
+    break;
+  case MH_DYLIB:
+    addHeaderSymbol("__mh_dylib_header");
+    break;
+  case MH_DYLINKER:
+    addHeaderSymbol("__mh_dylinker_header");
+    break;
+  case MH_OBJECT:
+    addHeaderSymbol("__mh_object_header");
+    break;
+  default:
+    llvm_unreachable("unexpected outputType");
+    break;
+  }
+
+  // The Itanium C++ ABI requires dylibs to pass a pointer to __cxa_atexit
+  // which does e.g. cleanup of static global variables. The ABI document
+  // says that the pointer can point to any address in one of the dylib's
+  // segments, but in practice ld64 seems to set it to point to the header,
+  // so that's what's implemented here.
+  addHeaderSymbol("___dso_handle");
+}

lld/MachO/SyntheticSections.h

@@ -500,6 +500,8 @@ struct InStruct {
 extern InStruct in;
 extern std::vector<SyntheticSection *> syntheticSections;
 
+void createSyntheticSymbols();
+
 } // namespace macho
 } // namespace lld
 

lld/MachO/Writer.cpp

@@ -751,7 +751,6 @@ static void sortSegmentsAndSections() {
       // output section indices.
       if (!osec->isHidden())
         osec->index = ++sectionIndex;
-
       if (!firstTLVDataSection && isThreadLocalData(osec->flags))
         firstTLVDataSection = osec;
 

lld/test/MachO/export-trie.s

@@ -15,7 +15,9 @@
 # EXPORTS-DAG:   [[#%x, HELLO_WORLD_ADDR:]] {{.*}} _hello_world
 # EXPORTS-DAG:   [[#%x, HELLO_ITS_ME_ADDR:]] {{.*}} _hello_its_me
 # EXPORTS-DAG:   [[#%x, HELLO_ITS_YOU_ADDR:]] {{.*}} _hello_its_you
+# EXPORTS-DAG:   {{0+}} g *ABS* __mh_execute_header
 # EXPORTS-LABEL: Exports trie:
+# EXPORTS-DAG:   0x{{0+}} __mh_execute_header [absolute]
 # EXPORTS-DAG:   0x{{0*}}[[#%X, MAIN_ADDR]] _main
 # EXPORTS-DAG:   0x{{0*}}[[#%X, HELLO_ADDR]] _hello
 # EXPORTS-DAG:   0x{{0*}}[[#%X, HELLO_WORLD_ADDR]] _hello_world
@@ -27,13 +29,16 @@
 # CHECK-LABEL: ExportTrie:
 # CHECK: Name: ''
 # CHECK: Name: _
-# CHECK: Name: main
+# CHECK-DAG: Name: _mh_execute_header
-# CHECK: Name: hello
+# CHECK-DAG: Name: main
+# CHECK-DAG: Name: hello
 # CHECK: Name: _
 # CHECK: Name: world
 # CHECK: Name: its_
-# CHECK: Name: you
+# CHECK-DAG: Name: you
-# CHECK: Name: me
+# CHECK-DAG: Name: me
+
+
 
 .section __TEXT,__cstring
 .globl _hello, _hello_world, _hello_its_me, _hello_its_you, _main

lld/test/MachO/map-file.s

@@ -29,6 +29,7 @@ _main:
 # CHECK-NEXT: [[#%x,MAIN:]]   g     F __TEXT,__text _main
 # CHECK-NEXT: [[#%x,NUMBER:]] g     O __DATA,__common _number
 # CHECK-NEXT: [[#%x,FOO:]]    g     O __TEXT,obj _foo
+# CHECK-NEXT: {{0+}}          g       *ABS* __mh_execute_header
 
 # CHECK-NEXT: # Path: {{.*}}{{/|\\}}map-file.s.tmp/test-map
 # CHECK-NEXT: # Arch: x86_64

lld/test/MachO/mh-execute-header.s

@@ -0,0 +1,16 @@
+# REQUIRES: x86
+# RUN: rm -rf %t; mkdir %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t/test.o
+# RUN: %lld -o %t/test.pie %t/test.o -pie
+# RUN: llvm-objdump --macho --syms %t/test.pie | FileCheck %s --check-prefix=PIE
+
+# RUN: %lld -o %t/test.no_pie %t/test.o -no_pie
+# RUN: llvm-objdump --macho --syms %t/test.no_pie | FileCheck %s --check-prefix=NO-PIE
+
+# PIE:    0000000100000000 g     F __TEXT,__text __mh_execute_header
+# NO-PIE: 0000000000000000 g       *ABS* __mh_execute_header
+
+.text
+.global _main
+_main:
+  ret

lld/test/MachO/mh-header-link.s

@@ -0,0 +1,43 @@
+# REQUIRES: x86
+
+## This tests that we can link against these synthetic symbols even
+## if they are not in the symbol table.
+
+# RUN: rm -rf %t; split-file %s %t
+
+## Test that in a dylib, we can link against __mh_dylib_header
+## (but not in other types of files)
+
+# RUN: llvm-mc %t/dylib.s -triple=x86_64-apple-macos11.0 -filetype=obj -o %t/dylib.o
+# RUN: %lld -pie -dylib %t/dylib.o -o %t/dylib.out
+# RUN: llvm-objdump -m --syms %t/dylib.out | FileCheck %s --check-prefix DYLIB
+
+# RUN: not %lld -pie -o /dev/null %t/dylib.o 2>&1 | FileCheck %s --check-prefix ERR-DYLIB
+
+# DYLIB:      SYMBOL TABLE:
+# DYLIB-NEXT: {{[0-9a-f]+}} g     F __TEXT,__text _main
+# DYLIB-NEXT-EMPTY:
+# ERR-DYLIB: error: undefined symbol: __mh_dylib_header
+
+## Test that in an executable, we can link against __mh_execute_header
+# RUN: llvm-mc %t/main.s -triple=x86_64-apple-macos11.0 -filetype=obj -o %t/exec.o
+# RUN: %lld -pie %t/exec.o -o %t/exec.out
+
+## But it would be an error trying to reference __mh_execute_header in a dylib
+# RUN: not %lld -pie -o /dev/null -dylib %t/exec.o 2>&1 | FileCheck %s --check-prefix ERR-EXEC
+
+# ERR-EXEC: error: undefined symbol: __mh_execute_header
+
+#--- main.s
+.text
+.globl _main
+_main:
+ mov __mh_execute_header@GOTPCREL(%rip), %rax
+ ret
+
+#--- dylib.s
+.text
+.globl _main
+_main:
+ mov __mh_dylib_header@GOTPCREL(%rip), %rax
+ ret

lld/test/MachO/objc.s

@@ -32,7 +32,7 @@
 # NO-OBJC-EMPTY:
 # NO-OBJC-NEXT:  SYMBOL TABLE:
 # NO-OBJC-NEXT:  g     F __TEXT,__text _main
-# NO-OBJC-EMPTY:
+# NO_OBJC-NEXT:  g *ABS* __mh_execute_header
 
 #--- has-objc-symbol.s
 .globl _OBJC_CLASS_$_MyObject

lld/test/MachO/stabs.s

@@ -60,6 +60,7 @@
 # CHECK-NEXT:  [[#ZERO]]        S _zero
 # CHECK-NEXT:  [[#FOO]]         T _foo
 # CHECK-NEXT:  {{[0-9af]+}}     T _no_debug
+# CHECK-NEXT:  {{0+}}           A __mh_execute_header
 # CHECK-EMPTY:
 
 ## Check that we don't attempt to emit rebase opcodes for the debug sections

lld/test/MachO/symtab.s

@@ -56,6 +56,16 @@
 # CHECK-NEXT:     ]
 # CHECK-NEXT:     Value: 0x1{{[0-9a-f]*}}
 # CHECK-NEXT:   }
+# CHECK-NEXT:  Symbol {
+# CHECK-NEXT:    Name: __mh_execute_header (81)
+# CHECK-NEXT:    Extern
+# CHECK-NEXT:    Type: Abs (0x2)
+# CHECK-NEXT:    Section:  (0x0)
+# CHECK-NEXT:    RefType: UndefinedNonLazy (0x0)
+# CHECK-NEXT:    Flags [ (0x0)
+# CHECK-NEXT:    ]
+# CHECK-NEXT:    Value: 0x0
+# CHECK-NEXT:  }
 # CHECK-NEXT:   Symbol {
 # CHECK-NEXT:     Name: dyld_stub_binder
 # CHECK-NEXT:     Extern
@@ -82,8 +92,8 @@
 # CHECK-NEXT:   ilocalsym: 0
 # CHECK-NEXT:   nlocalsym: 2
 # CHECK-NEXT:   iextdefsym: 2
-# CHECK-NEXT:   nextdefsym: 3
+# CHECK-NEXT:   nextdefsym: 4
-# CHECK-NEXT:   iundefsym: 5
+# CHECK-NEXT:   iundefsym: 6
 # CHECK-NEXT:   nundefsym: 2
 
 ## Verify that the first entry in the StringTable is a space, and that