[lld-macho] Allow the entry symbol to be dynamically bound

Apparently this is used in real programs. I've handled this by reusing
the logic we already have for branch (function call) relocations.

Reviewed By: #lld-macho, smeenai

Differential Revision: https://reviews.llvm.org/D87852

6 files changed, 84 insertions, 31 deletions

diff --git a/lld/MachO/Arch/X86_64.cpp b/lld/MachO/Arch/X86_64.cpp
index 8e07ee4..19e62a9 100644
--- a/lld/MachO/Arch/X86_64.cpp
+++ b/lld/MachO/Arch/X86_64.cpp
@@ -238,28 +238,7 @@ void X86_64::prepareSymbolRelocation(lld::macho::Symbol *sym,
     break;
   }
   case X86_64_RELOC_BRANCH: {
-    // TODO: factor this logic out so it can be reused for different
-    // architectures
-    if (auto *dysym = dyn_cast<DylibSymbol>(sym)) {
-      if (in.stubs->addEntry(dysym)) {
-        if (sym->isWeakDef()) {
-          in.binding->addEntry(dysym, in.lazyPointers,
-                               sym->stubsIndex * WordSize);
-          in.weakBinding->addEntry(sym, in.lazyPointers,
-                                   sym->stubsIndex * WordSize);
-        } else {
-          in.lazyBinding->addEntry(dysym);
-        }
-      }
-    } else if (auto *defined = dyn_cast<Defined>(sym)) {
-      if (defined->isWeakDef() && defined->isExternal()) {
-        if (in.stubs->addEntry(sym)) {
-          in.rebase->addEntry(in.lazyPointers, sym->stubsIndex * WordSize);
-          in.weakBinding->addEntry(sym, in.lazyPointers,
-                                   sym->stubsIndex * WordSize);
-        }
-      }
-    }
+    prepareBranchTarget(sym);
     break;
   }
   case X86_64_RELOC_UNSIGNED: {
diff --git a/lld/MachO/Driver.cpp b/lld/MachO/Driver.cpp
index 4991966..7a8215b 100644
--- a/lld/MachO/Driver.cpp
+++ b/lld/MachO/Driver.cpp
@@ -697,7 +697,7 @@ bool macho::link(llvm::ArrayRef<const char *> argsArr, bool canExitEarly,
   if (!orderFile.empty())
     parseOrderFile(orderFile);
 
-  if (config->outputType == MH_EXECUTE && !isa<Defined>(config->entry)) {
+  if (config->outputType == MH_EXECUTE && isa<Undefined>(config->entry)) {
     error("undefined symbol: " + config->entry->getName());
     return false;
   }
diff --git a/lld/MachO/SyntheticSections.cpp b/lld/MachO/SyntheticSections.cpp
index a243a05..e40b832 100644
--- a/lld/MachO/SyntheticSections.cpp
+++ b/lld/MachO/SyntheticSections.cpp
@@ -529,6 +529,29 @@ uint32_t LazyBindingSection::encode(const DylibSymbol &sym) {
   return opstreamOffset;
 }
 
+void macho::prepareBranchTarget(Symbol *sym) {
+  if (auto *dysym = dyn_cast<DylibSymbol>(sym)) {
+    if (in.stubs->addEntry(dysym)) {
+      if (sym->isWeakDef()) {
+        in.binding->addEntry(dysym, in.lazyPointers,
+                             sym->stubsIndex * WordSize);
+        in.weakBinding->addEntry(sym, in.lazyPointers,
+                                 sym->stubsIndex * WordSize);
+      } else {
+        in.lazyBinding->addEntry(dysym);
+      }
+    }
+  } else if (auto *defined = dyn_cast<Defined>(sym)) {
+    if (defined->isWeakDef() && defined->isExternal()) {
+      if (in.stubs->addEntry(sym)) {
+        in.rebase->addEntry(in.lazyPointers, sym->stubsIndex * WordSize);
+        in.weakBinding->addEntry(sym, in.lazyPointers,
+                                 sym->stubsIndex * WordSize);
+      }
+    }
+  }
+}
+
 ExportSection::ExportSection()
     : LinkEditSection(segment_names::linkEdit, section_names::export_) {}
 
diff --git a/lld/MachO/SyntheticSections.h b/lld/MachO/SyntheticSections.h
index 3bd4e11..1736b6a 100644
--- a/lld/MachO/SyntheticSections.h
+++ b/lld/MachO/SyntheticSections.h
@@ -364,6 +364,10 @@ private:
   llvm::raw_svector_ostream os{contents};
 };
 
+// Adds stubs and bindings where necessary (e.g. if the symbol is a
+// DylibSymbol.)
+void prepareBranchTarget(Symbol *);
+
 // Stores a trie that describes the set of exported symbols.
 class ExportSection : public LinkEditSection {
 public:
diff --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
index 4572c52..c47b878 100644
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -194,7 +194,13 @@ class LCMain : public LoadCommand {
     auto *c = reinterpret_cast<entry_point_command *>(buf);
     c->cmd = LC_MAIN;
     c->cmdsize = getSize();
-    c->entryoff = config->entry->getFileOffset();
+
+    if (config->entry->isInStubs())
+      c->entryoff =
+          in.stubs->fileOff + config->entry->stubsIndex * target->stubSize;
+    else
+      c->entryoff = config->entry->getFileOffset();
+
     c->stacksize = 0;
   }
 };
@@ -617,6 +623,7 @@ void Writer::run() {
   OutputSegment *linkEditSegment =
       getOrCreateOutputSegment(segment_names::linkEdit);
 
+  prepareBranchTarget(config->entry);
   scanRelocations();
   if (in.stubHelper->isNeeded())
     in.stubHelper->setup();
diff --git a/lld/test/MachO/entry-symbol.s b/lld/test/MachO/entry-symbol.s
index 159c7c5..d24d4e6 100644
--- a/lld/test/MachO/entry-symbol.s
+++ b/lld/test/MachO/entry-symbol.s
@@ -1,7 +1,11 @@
 # REQUIRES: x86
-# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t.o
-# RUN: lld -flavor darwinnew -o %t %t.o -e _not_main
-# RUN: llvm-objdump --macho --all-headers --syms %t | FileCheck %s
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/not-main.s -o %t/not-main.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/libfoo.s -o %t/libfoo.o
+# RUN: lld -flavor darwinnew -syslibroot %S/Inputs/MacOSX.sdk -lSystem -dylib %t/libfoo.o -o %t/libfoo.dylib
+
+# RUN: lld -flavor darwinnew -o %t/not-main %t/not-main.o -e _not_main
+# RUN: llvm-objdump --macho --all-headers --syms %t/not-main | FileCheck %s
 # CHECK-LABEL: SYMBOL TABLE
 # CHECK-NEXT: {{0*}}[[#%x, ENTRY_ADDR:]] {{.*}} __TEXT,__text _not_main
 # CHECK:      cmd  LC_MAIN
@@ -15,14 +19,50 @@
 # CHECK-NEXT: size
 # CHECK-NEXT: offset [[#ENTRYOFF]]
 
+# RUN: lld -flavor darwinnew -syslibroot %S/Inputs/MacOSX.sdk -lSystem -o %t/dysym-main %t/not-main.o %t/libfoo.dylib -e _dysym_main
+# RUN: llvm-objdump --macho --all-headers --indirect-symbols --lazy-bind %t/dysym-main | FileCheck %s --check-prefix=DYSYM
+# DYSYM-LABEL: Indirect symbols for (__TEXT,__stubs) 1 entries
+# DYSYM-NEXT:  address                      index  name
+# DYSYM-NEXT:  0x[[#%x,DYSYM_ENTRY_ADDR:]]  [[#]]  _dysym_main
+# DYSYM-LABEL: cmd  LC_MAIN
+# DYSYM-NEXT:  cmdsize  24
+# DYSYM-NEXT:  entryoff [[#%u, DYSYM_ENTRY_ADDR - 0x100000000]]
+# DYSYM-LABEL: Lazy bind table:
+# DYSYM-NEXT:  segment  section            address     dylib            symbol
+# DYSYM-NEXT:  __DATA   __la_symbol_ptr    {{.*}}      libfoo       _dysym_main
+
+# RUN: lld -flavor darwinnew -syslibroot %S/Inputs/MacOSX.sdk -lSystem -o %t/weak-dysym-main %t/not-main.o %t/libfoo.dylib -e _weak_dysym_main
+# RUN: llvm-objdump --macho --all-headers --indirect-symbols --bind --weak-bind %t/weak-dysym-main | FileCheck %s --check-prefix=WEAK-DYSYM
+# WEAK-DYSYM-LABEL: Indirect symbols for (__TEXT,__stubs) 1 entries
+# WEAK-DYSYM-NEXT:  address                      index  name
+# WEAK-DYSYM-NEXT:  0x[[#%x,DYSYM_ENTRY_ADDR:]]  [[#]]  _weak_dysym_main
+# WEAK-DYSYM:       cmd  LC_MAIN
+# WEAK-DYSYM-NEXT:  cmdsize  24
+# WEAK-DYSYM-NEXT:  entryoff [[#%u, DYSYM_ENTRY_ADDR - 0x100000000]]
+# WEAK-DYSYM-LABEL: Bind table:
+# WEAK-DYSYM-NEXT:  segment  section          address  type     addend  dylib      symbol
+# WEAK-DYSYM:       __DATA   __la_symbol_ptr  {{.*}}   pointer       0  libfoo _weak_dysym_main
+# WEAK-DYSYM-LABEL: Weak bind table:
+# WEAK-DYSYM-NEXT:  segment  section          address  type     addend  symbol
+# WEAK-DYSYM-NEXT:  __DATA   __la_symbol_ptr  {{.*}}   pointer       0  _weak_dysym_main
 
-# RUN: not lld -flavor darwinnew -o /dev/null %t.o -e _missing 2>&1 | FileCheck %s --check-prefix=UNDEFINED
+# RUN: not lld -flavor darwinnew -o /dev/null %t/not-main.o -e _missing 2>&1 | FileCheck %s --check-prefix=UNDEFINED
 # UNDEFINED: error: undefined symbol: _missing
-# RUN: not lld -flavor darwinnew -o /dev/null %t.o 2>&1 | FileCheck %s --check-prefix=DEFAULT-ENTRY
+# RUN: not lld -flavor darwinnew -o /dev/null %t/not-main.o 2>&1 | FileCheck %s --check-prefix=DEFAULT-ENTRY
 # DEFAULT-ENTRY: error: undefined symbol: _main
 
+#--- libfoo.s
+.text
+.global _dysym_main, _weak_dysym_main
+.weak_definition _weak_dysym_main
+_dysym_main:
+  ret
+
+_weak_dysym_main:
+  ret
+
+#--- not-main.s
 .text
 .global _not_main
 _not_main:
-  movq $0, %rax
-  retq
+  ret