[ELF][PPC32] Implement IPLT code sequence for non-preemptible IFUNC

[MaskRay]

Summary

Similar to D71509 (EM_PPC64), on EM_PPC, the IPLT code sequence should
be similar to a PLT call stub. Unlike EM_PPC64, EM_PPC -msecure-plt has
small/large PIC model differences.

• -fpic/-fpie: R_PPC_PLTREL24 r_addend=0. The call stub loads an address relative to _GLOBAL_OFFSET_TABLE_.
• -fPIC/-fPIE: R_PPC_PLTREL24 r_addend=0x8000. (A partial linked object file may have an addend larger than 0x8000.) The call stub loads an address relative to .got2+0x8000.

Just assume large PIC model for now. This patch makes:

// clang -fuse-ld=lld -fno-pie -no-pie a.c
// clang -fuse-ld=lld -fPIE -pie a.c
#include <stdio.h>
static void impl(void) { puts("meow"); }
void thefunc(void) __attribute__((ifunc("resolver")));
void *resolver(void) { return &impl; }
int main(void) {
  thefunc();
  void (*theptr)(void) = &thefunc;
  theptr();
}

work. -fpie will crash.

[MaskRay]

Make -fPIE -pie work

[MaskRay]

Rebase

[MaskRay]

Properly rebase on top of D71509

[MaskRay]

Add tests

lld/ELF/Arch/PPC.cpp

public:
   void writeGotHeader(uint8_t *buf) const override;
   void writePltHeader(uint8_t *buf) const override {
     llvm_unreachable("should call writePPC32GlinkSection() instead");
   }
   void writePlt(uint8_t *buf, uint64_t gotPltEntryAddr, uint64_t pltEntryAddr,
                 int32_t index) const override {
     llvm_unreachable("should call writePPC32GlinkSection() instead");
   }
+  void writeIplt(uint8_t *buf, uint64_t gotPltEntryAddr, uint64_t pltEntryAddr,
+                 int32_t index) const override;
   void writeGotPlt(uint8_t *buf, const Symbol &s) const override;
   bool needsThunk(RelExpr expr, RelType relocType, const InputFile *file,
                   uint64_t branchAddr, const Symbol &s,
                   int64_t a) const override;
   uint32_t getThunkSectionSpacing() const override;
   bool inBranchRange(RelType type, uint64_t src, uint64_t dst) const override;
   void relocateOne(uint8_t *loc, RelType type, uint64_t val) const override;
   RelExpr adjustRelaxExpr(RelType type, const uint8_t *data,
PPC::PPC() {
   relativeRel = R_PPC_RELATIVE;
   iRelativeRel = R_PPC_IRELATIVE;
   symbolicRel = R_PPC_ADDR32;
   gotBaseSymInGotPlt = false;
   gotHeaderEntriesNum = 3;
   gotPltHeaderEntriesNum = 0;
   pltHeaderSize = 64; // size of PLTresolve in .glink
   pltEntrySize = 4;
-  ipltEntrySize = 4;
+  ipltEntrySize = 16;
 
   needsThunks = true;
 
   tlsModuleIndexRel = R_PPC_DTPMOD32;
   tlsOffsetRel = R_PPC_DTPREL32;
   tlsGotRel = R_PPC_TPREL32;
 
   defaultMaxPageSize = 65536;
   defaultImageBase = 0x10000000;
 
   write32(trapInstr.data(), 0x7fe00008);
 }
 
+void PPC::writeIplt(uint8_t *buf, uint64_t gotPltEntryAddr,
+  uint64_t pltEntryAddr, int32_t index) const {
+  uint64_t va = gotPltEntryAddr;
+  // !config->isPic
+  write32(buf + 0, 0x3d600000 | (va + 0x8000) >> 16); // lis r11,ha
+  write32(buf + 4, 0x816b0000 | (uint16_t)va);        // lwz r11,l(r11)
+  write32(buf + 8, 0x7d6903a6);                       // mtctr r11
+  write32(buf + 12, 0x4e800420);                      // bctr
+
+  // config->isPic
+  // file->ppc32Got2OutSecOff is not known.
+  // See Thunks.cpp PPC32PltCallStub::writeTo
+}
+
 void PPC::writeGotHeader(uint8_t *buf) const {
   // _GLOBAL_OFFSET_TABLE_[0] = _DYNAMIC
   // glibc stores _dl_runtime_resolve in _GLOBAL_OFFSET_TABLE_[1],
   // link_map in _GLOBAL_OFFSET_TABLE_[2].
   write32(buf, mainPart->dynamic->getVA());
 }
 
 void PPC::writeGotPlt(uint8_t *buf, const Symbol &s) const {