[PPC64] Support R_PPC64_GOT_TLSLD16* relocations

[sfertile]

Summary

This patch adds support for the R_PPC64_GOT_TLSLD16 relocations used to build the address of the tls_index struct used in local-dynamic tls.

[ruiu]

LGTM

lld/trunk/ELF/Arch/PPC64.cpp

RelExpr PPC64::getRelExpr(RelType Type, const Symbol &S,
   case R_PPC64_REL32:
   case R_PPC64_REL64:
     return R_PC;
   case R_PPC64_GOT_TLSGD16:
   case R_PPC64_GOT_TLSGD16_HA:
   case R_PPC64_GOT_TLSGD16_HI:
   case R_PPC64_GOT_TLSGD16_LO:
     return R_TLSGD_GOT;
+  case R_PPC64_GOT_TLSLD16:
+  case R_PPC64_GOT_TLSLD16_HA:
+  case R_PPC64_GOT_TLSLD16_HI:
+  case R_PPC64_GOT_TLSLD16_LO:
+    return R_TLSLD_GOT;
   case R_PPC64_TLSGD:
+  case R_PPC64_TLSLD:
     return R_HINT;
   default:
     return R_ABS;
   }
 }
 
 void PPC64::writeGotHeader(uint8_t *Buf) const {
   write64(Buf, getPPC64TocBase());

  // bl __glink_PLTresolve
  write32(Buf, 0x48000000 | ((-Offset) & 0x03FFFFFc));
 }
 
 static std::pair<RelType, uint64_t> toAddr16Rel(RelType Type, uint64_t Val) {
   uint64_t V = Val - PPC64TocOffset;
   switch (Type) {
   case R_PPC64_GOT_TLSGD16:
+  case R_PPC64_GOT_TLSLD16:
   case R_PPC64_TOC16:
     return {R_PPC64_ADDR16, V};
   case R_PPC64_TOC16_DS:
     return {R_PPC64_ADDR16_DS, V};
   case R_PPC64_GOT_TLSGD16_HA:
+  case R_PPC64_GOT_TLSLD16_HA:
   case R_PPC64_TOC16_HA:
     return {R_PPC64_ADDR16_HA, V};
   case R_PPC64_GOT_TLSGD16_HI:
+  case R_PPC64_GOT_TLSLD16_HI:
   case R_PPC64_TOC16_HI:
     return {R_PPC64_ADDR16_HI, V};
   case R_PPC64_GOT_TLSGD16_LO:
+  case R_PPC64_GOT_TLSLD16_LO:
   case R_PPC64_TOC16_LO:
     return {R_PPC64_ADDR16_LO, V};
   case R_PPC64_TOC16_LO_DS:
     return {R_PPC64_ADDR16_LO_DS, V};
   default:
     return {Type, Val};
   }
 }

lld/trunk/ELF/InputSection.cpp

static uint64_t getRelocTargetVA(RelType Type, int64_t A, uint64_t P,
   case R_TLSGD_GOT:
     return InX::Got->getGlobalDynOffset(Sym) + A;
   case R_TLSGD_GOT_FROM_END:
     return InX::Got->getGlobalDynOffset(Sym) + A - InX::Got->getSize();
   case R_TLSGD_PC:
     return InX::Got->getGlobalDynAddr(Sym) + A - P;
   case R_TLSLD_GOT_FROM_END:
     return InX::Got->getTlsIndexOff() + A - InX::Got->getSize();
+  case R_TLSLD_GOT:
+      return InX::Got->getTlsIndexOff() + A;
   case R_TLSLD_PC:
     return InX::Got->getTlsIndexVA() + A - P;
   }
   llvm_unreachable("Invalid expression");
 }
 
 // This function applies relocations to sections without SHF_ALLOC bit.
 // Such sections are never mapped to memory at runtime. Debug sections are

lld/trunk/ELF/Relocations.h

enum RelExpr {
   R_TLS,
   R_TLSDESC,
   R_TLSDESC_CALL,
   R_TLSDESC_PAGE,
   R_TLSGD_GOT,
   R_TLSGD_GOT_FROM_END,
   R_TLSGD_PC,
   R_TLSLD_GOT_FROM_END,
+  R_TLSLD_GOT,
   R_TLSLD_PC,
 };
 
 // Build a bitmask with one bit set for each RelExpr.
 //
 // Constexpr function arguments can't be used in static asserts, so we
 // use template arguments to build the mask.
 // But function template partial specializations don't exist (needed

lld/trunk/ELF/Relocations.cpp

if (InX::Got->addDynTlsEntry(Sym)) {
       InX::RelaDyn->addReloc(
           {Target->TlsDescRel, InX::Got, Off, !Sym.IsPreemptible, &Sym, 0});
     }
     if (Expr != R_TLSDESC_CALL)
       C.Relocations.push_back({Expr, Type, Offset, Addend, &Sym});
     return 1;
   }
 
-  if (isRelExprOneOf<R_TLSLD_PC, R_TLSLD_GOT_FROM_END>(Expr)) {
+  if (isRelExprOneOf<R_TLSLD_GOT, R_TLSLD_GOT_FROM_END, R_TLSLD_PC>(Expr)) {
     // Local-Dynamic relocs can be relaxed to Local-Exec.
     if (!Config->Shared) {
       C.Relocations.push_back(
           {R_RELAX_TLS_LD_TO_LE, Type, Offset, Addend, &Sym});
       return 2;
     }
     if (InX::Got->addTlsIndex())
       InX::RelaDyn->addReloc(Target->TlsModuleIndexRel, InX::Got,

lld/trunk/test/ELF/ppc64-local-dynamic.s

+// REQUIRES: ppc
+
+// RUN: llvm-mc -filetype=obj -triple=powerpc64le-unknown-linux %s -o %t.o
+// RUN: ld.lld -shared %t.o -o %t.so
+// RUN: llvm-readelf -relocations --wide %t.o | FileCheck --check-prefix=InputRelocs %s
+// RUN: llvm-readelf -relocations --wide %t.so | FileCheck --check-prefix=OutputRelocs %s
+// RUN: llvm-objdump --section-headers %t.so | FileCheck --check-prefix=CheckGot %s
+// RUN: llvm-objdump -D %t.so | FileCheck --check-prefix=Dis %s
+
+// RUN: llvm-mc -filetype=obj -triple=powerpc64-unknown-linux %s -o %t.o
+// RUN: ld.lld -shared %t.o -o %t.so
+// RUN: llvm-readelf -relocations --wide %t.o | FileCheck --check-prefix=InputRelocs %s
+// RUN: llvm-readelf -relocations --wide %t.so | FileCheck --check-prefix=OutputRelocs %s
+// RUN: llvm-objdump --section-headers %t.so | FileCheck --check-prefix=CheckGot %s
+// RUN: llvm-objdump -D %t.so | FileCheck --check-prefix=Dis %s
+
+        .text
+        .abiversion 2
+        .globl  test
+        .p2align        4
+        .type   test,@function
+test:
+.Lfunc_gep0:
+        addis 2, 12, .TOC.-.Lfunc_gep0@ha
+        addi 2, 2, .TOC.-.Lfunc_gep0@l
+.Lfunc_lep0:
+        .localentry     test, .Lfunc_lep0-.Lfunc_gep0
+        mflr 0
+        std 0, 16(1)
+        stdu 1, -32(1)
+        addis 3, 2, i@got@tlsld@ha
+        addi 3, 3, i@got@tlsld@l
+        bl __tls_get_addr(i@tlsld)
+        nop
+        ld 0, 16(1)
+        mtlr 0
+        blr
+
+        .globl test_hi
+        .p2align 4
+        .type test_hi,@function
+test_hi:
+         lis 3, j@got@tlsld@h
+         blr
+
+        .globl test_16
+        .p2align 4
+        .type test_16,@function
+test_16:
+         li 3, k@got@tlsld
+         blr
+
+        .type   i,@object
+        .section        .tdata,"awT",@progbits
+        .p2align        2
+i:
+        .long   55
+        .size   i, 4
+
+        .type   j,@object
+        .section        .tbss,"awT",@nobits
+        .p2align        2
+j:
+        .long   0
+        .size   j, 4
+
+        .type   k,@object
+        .section        .tdata,"awT",@progbits
+        .p2align        3
+k:
+        .quad   66
+        .size   k, 8
+
+// Verify that the input contains all the R_PPC64_GOT_TLSLD16* relocations.
+// InputRelocs: Relocation section '.rela.text'
+// InputRelocs:     R_PPC64_GOT_TLSLD16_HA 0000000000000000 i + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16_LO 0000000000000000 i + 0
+// InputRelocs:     R_PPC64_TLSLD          0000000000000000 i + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16_HI 0000000000000000 j + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16    0000000000000008 k + 0
+
+// The local dynamic version of tls needs to use the same mechanism to look up
+// a variables address as general-dynamic. ie a call to __tls_get_addr with the
+// address of a tls_index struct as the argument. However for local-dynamic
+// variables  all will have the same ti_module, and the offset field is left as
+// as 0, so the same struct can be used for every local-dynamic variable
+// used in the shared-object.
+// OutputRelocs:      Relocation section '.rela.dyn' at offset 0x{{[0-9a-f]+}} contains 1 entries:
+// OutputRelocs-NEXT: Offset Info Type Symbol's Value Symbol's Name + Addend
+// OutputRelocs-NEXT: R_PPC64_DTPMOD64
+
+// Check that the got has 3 entries, 1 for the TOC and 1 stucture of 2 entries
+// for the tls variables. Also verify the address so we can check the offsets
+// we calculate for each relocation type.
+// CheckGot: got          00000018 0000000000020100
+
+// got starts at 0x20100 so .TOC. will be 0x28100, and the tls_index struct is
+// at 0x20108.
+
+// #ha(i@got@tlsld) --> (0x20108 - 0x28100 + 0x8000) >> 16 = 0
+// #lo(i@got@tlsld) --> (0x20108 - 0x28100) = -7ff8 = -32760
+// Dis:     test:
+// Dis:        addis 3, 2, 0
+// Dis-NEXT:   addi 3, 3, -32760
+
+// #hi(j@got@tlsld) --> (0x20108 - 0x28100 ) > 16 = -1
+// Dis: test_hi:
+// Dis:   lis 3, -1
+
+// k@got@tlsld --> (0x20108 - 0x28100) = -7ff8 = -32760
+// Dis: test_16:
+// Dis:   li 3, -32760