[ELF] Define __ehdr_start symbol

[phosek]

Summary

This symbol can be used by the program to examine its own headers.

[phosek]

This was added to GNU Binutils ld in this patch.

[ruiu]

LGTM

[pcc]

Is this correct? It looks like the other linkers define __ehdr_start to the address of the ELF file header, rather than the program headers.

[phosek]

In D23750#685190, @pcc wrote:

Is this correct? It looks like the other linkers define __ehdr_start to the address of the ELF file header, rather than the program headers.

You're right, this is incorrect, I'll send a patch shortly.

lld/trunk/ELF/Symbols.h

public:
 
   LazyObjectFile *file() { return (LazyObjectFile *)this->File; }
   std::unique_ptr<InputFile> fetch();
 };
 
 // Some linker-generated symbols need to be created as
 // DefinedRegular symbols.
 template <class ELFT> struct ElfSym {
+  // The content for __ehdr_start symbol.
+  static DefinedRegular<ELFT> *EhdrStart;
+
   // The content for _etext and etext symbols.
   static DefinedRegular<ELFT> *Etext;
   static DefinedRegular<ELFT> *Etext2;
 
   // The content for _edata and edata symbols.
   static DefinedRegular<ELFT> *Edata;
   static DefinedRegular<ELFT> *Edata2;
 
   // The content for _end and end symbols.
   static DefinedRegular<ELFT> *End;
   static DefinedRegular<ELFT> *End2;
 
   // The content for _gp_disp symbol for MIPS target.
   static SymbolBody *MipsGpDisp;
 };
 
+template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::EhdrStart;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::Etext;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::Etext2;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::Edata;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::Edata2;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::End;
 template <class ELFT> DefinedRegular<ELFT> *ElfSym<ELFT>::End2;
 template <class ELFT> SymbolBody *ElfSym<ELFT>::MipsGpDisp;
 

lld/trunk/ELF/Writer.cpp

template <class ELFT> void Writer<ELFT>::addReservedSymbols() {
   // to avoid the undefined symbol error.
   if (!Out<ELFT>::DynSymTab)
     Symtab<ELFT>::X->addIgnored("__tls_get_addr");
 
   // If linker script do layout we do not need to create any standart symbols.
   if (ScriptConfig->HasContents)
     return;
 
+  ElfSym<ELFT>::EhdrStart = Symtab<ELFT>::X->addIgnored("__ehdr_start");
+
   auto Define = [this](StringRef S, DefinedRegular<ELFT> *&Sym1,
                        DefinedRegular<ELFT> *&Sym2) {
     Sym1 = Symtab<ELFT>::X->addIgnored(S, STV_DEFAULT);
 
     // The name without the underscore is not a reserved name,
     // so it is defined only when there is a reference against it.
     assert(S.startswith("_"));
     S = S.substr(1);
if (Config->Relocatable)
     return ET_REL;
   return ET_EXEC;
 }
 
 // This function is called after we have assigned address and size
 // to each section. This function fixes some predefined absolute
 // symbol values that depend on section address and size.
 template <class ELFT> void Writer<ELFT>::fixAbsoluteSymbols() {
+  // __ehdr_start is the location of program headers.
+  if (ElfSym<ELFT>::EhdrStart)
+    ElfSym<ELFT>::EhdrStart->Value = Out<ELFT>::ProgramHeaders->getVA();
+
   auto Set = [](DefinedRegular<ELFT> *S1, DefinedRegular<ELFT> *S2, uintX_t V) {
     if (S1)
       S1->Value = V;
     if (S2)
       S2->Value = V;
   };
 
   // _etext is the first location after the last read-only loadable segment.

lld/trunk/test/ELF/ehdr_start.s

+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
+# RUN: ld.lld %t.o -o %t
+# RUN: llvm-objdump -t %t | FileCheck %s
+# CHECK: 0000000000010040 *ABS* 00000000 .hidden __ehdr_start
+
+.text
+.global _start, __ehdr_start
+_start:
+  .quad __ehdr_start

lld/trunk/test/ELF/linkerscript/linkerscript-ehdr_start.s

+# REQUIRES: x86
+
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
+# RUN: echo "SECTIONS { }" > %t.script
+# RUN: not ld.lld %t.o -script %t.script -o %t 2>&1 | FileCheck %s
+# CHECK: undefined symbol: __ehdr_start
+
+.text
+.global _start, __ehdr_start
+_start:
+  .quad __ehdr_start