[lld-macho] Set __PAGEZERO size to 4GB

That's what ld64 uses for 64-bit targets. I figured it's best to make
this change sooner rather than later since a bunch of our tests are
relying on hardcoded addresses that depend on this value.

Reviewed By: smeenai

Differential Revision: https://reviews.llvm.org/D80177

lld/MachO/Symbols.cpp

@@ -8,8 +8,6 @@
 
 #include "Symbols.h"
 #include "InputFiles.h"
-#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Strings.h"
 
 using namespace llvm;
 using namespace lld;

lld/MachO/Symbols.h

@@ -11,6 +11,7 @@
 
 #include "InputSection.h"
 #include "Target.h"
+#include "lld/Common/ErrorHandler.h"
 #include "lld/Common/Strings.h"
 #include "llvm/Object/Archive.h"
 
@@ -44,6 +45,8 @@ public:
 
   uint64_t getVA() const;
 
+  uint64_t getFileOffset() const;
+
 protected:
   Symbol(Kind k, StringRefZ name) : symbolKind(k), name(name) {}
 
@@ -102,6 +105,12 @@ inline uint64_t Symbol::getVA() const {
   return 0;
 }
 
+inline uint64_t Symbol::getFileOffset() const {
+  if (auto *d = dyn_cast<Defined>(this))
+    return d->isec->getFileOffset() + d->value;
+  llvm_unreachable("attempt to get an offset from an undefined symbol");
+}
+
 union SymbolUnion {
   alignas(Defined) char a[sizeof(Defined)];
   alignas(Undefined) char b[sizeof(Undefined)];

lld/MachO/SyntheticSections.h

@@ -9,6 +9,7 @@
 #ifndef LLD_MACHO_SYNTHETIC_SECTIONS_H
 #define LLD_MACHO_SYNTHETIC_SECTIONS_H
 
+#include "Config.h"
 #include "ExportTrie.h"
 #include "InputSection.h"
 #include "OutputSection.h"
@@ -66,7 +67,7 @@ class PageZeroSection : public SyntheticSection {
 public:
   PageZeroSection();
   bool isHidden() const override { return true; }
-  size_t getSize() const override { return ImageBase; }
+  size_t getSize() const override { return PageZeroSize; }
   uint64_t getFileSize() const override { return 0; }
   void writeTo(uint8_t *buf) const override {}
 };

lld/MachO/Target.h

@@ -27,7 +27,7 @@ enum {
   // deprecating 32-bit apps.
   WordSize = 8,
   PageSize = 4096,
-  ImageBase = 4096,
+  PageZeroSize = 1ull << 32, // XXX should be 4096 for 32-bit targets
   MaxAlignmentPowerOf2 = 32,
 };
 

lld/MachO/Writer.cpp

@@ -168,7 +168,7 @@ class LCMain : public LoadCommand {
     auto *c = reinterpret_cast<entry_point_command *>(buf);
     c->cmd = LC_MAIN;
     c->cmdsize = getSize();
-    c->entryoff = config->entry->getVA() - ImageBase;
+    c->entryoff = config->entry->getFileOffset();
     c->stacksize = 0;
   }
 };

lld/test/MachO/entry-symbol.s

@@ -1,13 +1,28 @@
 # REQUIRES: x86
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t.o
-# RUN: lld -flavor darwinnew -o /dev/null %t.o -e _not_main
-# RUN: not lld -flavor darwinnew -o /dev/null %t.o -e _missing 2>&1 | FileCheck %s
-# RUN: not lld -flavor darwinnew -o /dev/null %t.o 2>&1 | FileCheck %s --check-prefix=DEFAULT-ENTRY
+# RUN: lld -flavor darwinnew -o %t %t.o -e _not_main
+# RUN: llvm-objdump --macho --all-headers --syms %t | FileCheck %s
+# CHECK-LABEL: SYMBOL TABLE
+# CHECK-NEXT: {{0*}}[[#%x, ENTRY_ADDR:]] {{.*}} __TEXT,__text _not_main
+# CHECK:      cmd  LC_MAIN
+# CHECK-NEXT: cmdsize  24
+# CHECK-NEXT: entryoff [[#ENTRYOFF:]]
+# CHECK:      sectname __text
+# CHECK-NEXT: segname __TEXT
+## Note: the following checks assume that the entry symbol is right at the
+## beginning of __text.
+# CHECK-NEXT: addr 0x{{0*}}[[#ENTRY_ADDR]]
+# CHECK-NEXT: size
+# CHECK-NEXT: offset [[#ENTRYOFF]]
 
-# CHECK: error: undefined symbol: _missing
+
+# RUN: not lld -flavor darwinnew -o /dev/null %t.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
 # DEFAULT-ENTRY: error: undefined symbol: _main
 
 .text
 .global _not_main
 _not_main:
-  ret
+  movq $0, %rax
+  retq

lld/test/MachO/segments.s

@@ -9,8 +9,8 @@
 # CHECK:        Cmd: LC_SEGMENT_64
 # CHECK:        Name: __PAGEZERO
 # CHECK:        Size: 72
-# CHECK:        vmaddr:
-# CHECK:        vmsize:
+# CHECK:        vmaddr: 0x0
+# CHECK:        vmsize: 0x100000000
 # CHECK:        fileoff: 0
 # CHECK:        filesize: 0
 ## The kernel won't execute a binary with the wrong protections for __PAGEZERO.
@@ -23,7 +23,7 @@
 # CHECK:        Cmd: LC_SEGMENT_64
 # CHECK:        Name: __TEXT
 # CHECK:        Size: 152
-# CHECK:        vmaddr:
+# CHECK:        vmaddr: 0x100000000
 # CHECK:        vmsize:
 ## dyld3 assumes that the __TEXT segment starts from the file header
 # CHECK:        fileoff: 0

lld/test/MachO/x86-64-reloc-signed.s

@@ -4,18 +4,18 @@
 # RUN: llvm-objdump -D %t | FileCheck %s
 
 # CHECK:      <_main>:
-# CHECK-NEXT:   movl {{.*}}  # 2000 <_s>
+# CHECK-NEXT:   movl {{.*}}  # 100001000 <_s>
 # CHECK-NEXT:   callq {{.*}}
-# CHECK-NEXT:   movl {{.*}}  # 2002 <_s+0x2>
+# CHECK-NEXT:   movl {{.*}}  # 100001002 <_s+0x2>
 # CHECK-NEXT:   callq {{.*}}
-# CHECK-NEXT:   movb {{.*}}  # 2000 <_s>
+# CHECK-NEXT:   movb {{.*}}  # 100001000 <_s>
 # CHECK-NEXT:   callq {{.*}}
 # CHECK:      <__not_text>:
-# CHECK-NEXT:   movl {{.*}}  # 2005
+# CHECK-NEXT:   movl {{.*}}  # 100001005
 # CHECK-NEXT:   callq {{.*}}
-# CHECK-NEXT:   movl {{.*}}  # 2007
+# CHECK-NEXT:   movl {{.*}}  # 100001007
 # CHECK-NEXT:   callq {{.*}}
-# CHECK-NEXT:   movb {{.*}}  # 2005
+# CHECK-NEXT:   movb {{.*}}  # 100001005
 # CHECK-NEXT:   callq {{.*}}
 
 .section __TEXT,__text

lld/test/MachO/x86-64-reloc-unsigned.s

@@ -3,9 +3,9 @@
 # RUN: lld -flavor darwinnew -o %t %t.o
 # RUN: llvm-objdump --full-contents %t | FileCheck %s
 # CHECK: Contents of section foo:
-# CHECK:  2000 08200000 00000000
+# CHECK:  100001000 08100000 01000000
 # CHECK: Contents of section bar:
-# CHECK:  2008 11311111 01000000
+# CHECK:  100001008 11211111 02000000
 
 .globl _main, _foo, _bar