[ELF][RISCV] Assign st_shndx of __global_pointer$ to 1 if .sdata does not exist

[MaskRay]

Summary

This essentially reverts the code change of D63132 and switches to a simpler approach.

In an executable/shared object, st_shndx of a symbol can be:

1. SHN_UNDEF: undefined symbol (or canonical PLT)
2. SHN_ABS: absolute symbol
3. any other value (usually a regular section index) represents a relative symbol. The actual value does not matter.

Many ld.so (musl, all archs except MIPS of FreeBSD rtld-elf) even treat 2) and 3)
the same. If .sdata does not exist, it does not matter what value/section
__global_pointer$ has, as long as it is relative (otherwise there will be a pedantic
lld error. See D63132). Just set the st_shndx arbitrarily to 1.

Dummy st_shndx=1 may be used by __rela_iplt_start, linker-script-defined symbols outside a section, __dso_handle, etc.

[MaskRay]

This is used by rela_iplt_start, dso_handle, etc

[PkmX]

This should be fine since lld doesn't support linker relaxation, so we just need to fabricate a dummy value for __global_pointer$ that allows it to link.

[ruiu]

I think that PkmX is OK with this patch, so LGTM

[MaskRay]

Try fixing markdown in the description

Fix the comment in the test

lld/trunk/ELF/SyntheticSections.h

 class PartitionIndexSection : public SyntheticSection {
 public:
   PartitionIndexSection();
   size_t getSize() const override;
   void finalizeContents() override;
   void writeTo(uint8_t *buf) override;
 };
 
-// Create a dummy .sdata for __global_pointer$ if .sdata does not exist.
-class RISCVSdataSection final : public SyntheticSection {
-public:
-  RISCVSdataSection();
-  size_t getSize() const override { return 0; }
-  bool isNeeded() const override;
-  void writeTo(uint8_t *buf) override {}
-};
-
 InputSection *createInterpSection();
 MergeInputSection *createCommentSection();
 template <class ELFT> void splitSections();
 void mergeSections();
 
 template <typename ELFT> void writeEhdr(uint8_t *buf, Partition &part);
 template <typename ELFT> void writePhdrs(uint8_t *buf, Partition &part);
 
struct InStruct {
   PPC64LongBranchTargetSection *ppc64LongBranchTarget;
   MipsGotSection *mipsGot;
   MipsRldMapSection *mipsRldMap;
   SyntheticSection *partEnd;
   SyntheticSection *partIndex;
   PltSection *plt;
   PltSection *iplt;
   PPC32Got2Section *ppc32Got2;
-  RISCVSdataSection *riscvSdata;
   RelocationBaseSection *relaPlt;
   RelocationBaseSection *relaIplt;
   StringTableSection *shStrTab;
   StringTableSection *strTab;
   SymbolTableBaseSection *symTab;
   SymtabShndxSection *symTabShndx;
 };
 
 extern InStruct in;
 
 } // namespace elf
 } // namespace lld
 
 #endif

lld/trunk/ELF/SyntheticSections.cpp

bool PPC64LongBranchTargetSection::isNeeded() const {
   // is too early to determine if this section will be empty or not. We need
   // Finalized to keep the section alive until after thunk creation. Finalized
   // only gets set to true once `finalizeSections()` is called after thunk
   // creation. Becuase of this, if we don't create any long-branch thunks we end
   // up with an empty .branch_lt section in the binary.
   return !finalized || !entries.empty();
 }
 
-RISCVSdataSection::RISCVSdataSection()
-    : SyntheticSection(SHF_ALLOC | SHF_WRITE, SHT_PROGBITS, 1, ".sdata") {}
-
-bool RISCVSdataSection::isNeeded() const {
-  if (!ElfSym::riscvGlobalPointer)
-    return false;
-
-  // __global_pointer$ is defined relative to .sdata . If the section does not
-  // exist, create a dummy one.
-  for (BaseCommand *base : getParent()->sectionCommands)
-    if (auto *isd = dyn_cast<InputSectionDescription>(base))
-      for (InputSection *isec : isd->sections)
-        if (isec != this)
-          return false;
-  return true;
-}
-
 static uint8_t getAbiVersion() {
   // MIPS non-PIC executable gets ABI version 1.
   if (config->emachine == EM_MIPS) {
     if (!config->isPic && !config->relocatable &&
         (config->eflags & (EF_MIPS_PIC | EF_MIPS_CPIC)) == EF_MIPS_CPIC)
       return 1;
     return 0;
   }

lld/trunk/ELF/Writer.cpp

if (config->emachine == EM_PPC) {
     add(in.ppc32Got2);
   }
 
   if (config->emachine == EM_PPC64) {
     in.ppc64LongBranchTarget = make<PPC64LongBranchTargetSection>();
     add(in.ppc64LongBranchTarget);
   }
 
-  if (config->emachine == EM_RISCV) {
-    in.riscvSdata = make<RISCVSdataSection>();
-    add(in.riscvSdata);
-  }
-
   in.gotPlt = make<GotPltSection>();
   add(in.gotPlt);
   in.igotPlt = make<IgotPltSection>();
   add(in.igotPlt);
 
   // _GLOBAL_OFFSET_TABLE_ is defined relative to either .got.plt or .got. Treat
   // it as a relocation and ensure the referenced section is created.
   if (ElfSym::globalOffsetTable && config->emachine != EM_MIPS) {
template <class ELFT> void Writer<ELFT>::finalizeSections() {
   if (mainPart->dynamic->parent)
     symtab->addSymbol(Defined{/*file=*/nullptr, "_DYNAMIC", STB_WEAK,
                               STV_HIDDEN, STT_NOTYPE,
                               /*value=*/0, /*size=*/0, mainPart->dynamic});
 
   // Define __rel[a]_iplt_{start,end} symbols if needed.
   addRelIpltSymbols();
 
-  // RISC-V's gp can address +/- 2 KiB, set it to .sdata + 0x800 if not defined.
-  // This symbol should only be defined in an executable.
-  if (config->emachine == EM_RISCV && !config->shared)
+  // RISC-V's gp can address +/- 2 KiB, set it to .sdata + 0x800. This symbol
+  // should only be defined in an executable. If .sdata does not exist, its
+  // value/section does not matter but it has to be relative, so set its
+  // st_shndx arbitrarily to 1 (Out::elfHeader).
+  if (config->emachine == EM_RISCV && !config->shared) {
+    OutputSection *sec = findSection(".sdata");
     ElfSym::riscvGlobalPointer =
-        addOptionalRegular("__global_pointer$", findSection(".sdata"), 0x800,
-                           STV_DEFAULT, STB_GLOBAL);
+        addOptionalRegular("__global_pointer$", sec ? sec : Out::elfHeader,
+                           0x800, STV_DEFAULT, STB_GLOBAL);
+  }
 
   if (config->emachine == EM_X86_64) {
     // On targets that support TLSDESC, _TLS_MODULE_BASE_ is defined in such a
     // way that:
     //
     // 1) Without relaxation: it produces a dynamic TLSDESC relocation that
     // computes 0.
     // 2) With LD->LE relaxation: _TLS_MODULE_BASE_@tpoff = 0 (lowest address in
template <class ELFT> void Writer<ELFT>::finalizeSections() {
   finalizeSynthetic(in.mipsGot);
   finalizeSynthetic(in.igotPlt);
   finalizeSynthetic(in.gotPlt);
   finalizeSynthetic(in.relaIplt);
   finalizeSynthetic(in.relaPlt);
   finalizeSynthetic(in.plt);
   finalizeSynthetic(in.iplt);
   finalizeSynthetic(in.ppc32Got2);
-  finalizeSynthetic(in.riscvSdata);
   finalizeSynthetic(in.partIndex);
 
   // Dynamic section must be the last one in this list and dynamic
   // symbol table section (dynSymTab) must be the first one.
   for (Partition &part : partitions) {
     finalizeSynthetic(part.armExidx);
     finalizeSynthetic(part.dynSymTab);
     finalizeSynthetic(part.gnuHashTab);

lld/trunk/test/ELF/riscv-gp-dummy-sdata.s

-# REQUIRES: riscv
-# RUN: llvm-mc -filetype=obj -triple=riscv32 %s -o %t.32.o
-# RUN: ld.lld -pie %t.32.o -o %t.32
-# RUN: llvm-readelf -S %t.32 | FileCheck --check-prefix=SEC %s
-# RUN: llvm-readelf -s %t.32 | FileCheck --check-prefix=SYM %s
-
-# RUN: llvm-mc -filetype=obj -triple=riscv64 %s -o %t.64.o
-# RUN: ld.lld -pie %t.64.o -o %t.64
-# RUN: llvm-readelf -S %t.64 | FileCheck --check-prefix=SEC %s
-# RUN: llvm-readelf -s %t.64 | FileCheck --check-prefix=SYM %s
-
-## If there is an undefined reference to __global_pointer$ but .sdata doesn't
-## exist, create a dummy one.
-
-## __global_pointer$ = .sdata+0x800
-# SEC: [ 7] .sdata PROGBITS {{0*}}00003000
-# SYM: {{0*}}00003800 0 NOTYPE GLOBAL DEFAULT 7 __global_pointer$
-
-## If __global_pointer$ is not used, don't create .sdata .
-
-# RUN: llvm-mc -filetype=obj -triple=riscv32 /dev/null -o %t.32.o
-# RUN: ld.lld -pie %t.32.o -o %t.32
-# RUN: llvm-readelf -S %t.32 | FileCheck --implicit-check-not=.sdata /dev/null
-
-lla gp, __global_pointer$

lld/trunk/test/ELF/riscv-gp-no-sdata.s

+# REQUIRES: riscv
+# RUN: llvm-mc -filetype=obj -triple=riscv32 %s -o %t.32.o
+# RUN: ld.lld -pie %t.32.o -o %t.32
+# RUN: llvm-readelf -s %t.32 | FileCheck --check-prefix=SYM %s
+
+# RUN: llvm-mc -filetype=obj -triple=riscv64 %s -o %t.64.o
+# RUN: ld.lld -pie %t.64.o -o %t.64
+# RUN: llvm-readelf -s %t.64 | FileCheck --check-prefix=SYM %s
+
+## If there is an undefined reference to __global_pointer$ but .sdata doesn't
+## exist, define __global_pointer$ and set its st_shndx arbitrarily to 1.
+
+# SYM: {{0*}}00000800 0 NOTYPE GLOBAL DEFAULT 1 __global_pointer$
+
+lla gp, __global_pointer$