[PPC64] Support R_PPC64_DTPREL* relcoations

[sfertile]

Summary

Patch adds support for most of the dynamic thread pointer based relocations generated for local-dynamic tls.

• Its missing the _HIGH and _HIGHA versions because llvm-mc doesn't support them in assembly yet, I've used _HI/_HA versions in the testing of the 64 bit offset generation, and will fix this in a follow on patch.

[sfertile]

ping

[MaskRay]

I think the logic is correct. I created D47966 unaware of this revision and tested it with ld.gold on a powerpc64le machine, the output matches.

[sfertile]

committed in https://reviews.llvm.org/rLLD334465

ELF/Arch/PPC64.cpp

 using namespace llvm;
 using namespace llvm::object;
 using namespace llvm::support::endian;
 using namespace llvm::ELF;
 using namespace lld;
 using namespace lld::elf;
 
 static uint64_t PPC64TocOffset = 0x8000;
+static uint64_t DynamicThreadPointerOffset = 0x8000;
 
 uint64_t elf::getPPC64TocBase() {
   // The TOC consists of sections .got, .toc, .tocbss, .plt in that order. The
   // TOC starts where the first of these sections starts. We always create a
   // .got when we see a relocation that uses it, so for us the start is always
   // the .got.
   uint64_t TocVA = InX::Got->getVA();
 
RelExpr PPC64::getRelExpr(RelType Type, const Symbol &S,
   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_DTPREL16:
+  case R_PPC64_DTPREL16_DS:
+  case R_PPC64_DTPREL16_HA:
+  case R_PPC64_DTPREL16_HI:
+  case R_PPC64_DTPREL16_HIGHER:
+  case R_PPC64_DTPREL16_HIGHERA:
+  case R_PPC64_DTPREL16_HIGHEST:
+  case R_PPC64_DTPREL16_HIGHESTA:
+  case R_PPC64_DTPREL16_LO:
+  case R_PPC64_DTPREL16_LO_DS:
+    return R_ABS;
   case R_PPC64_TLSGD:
   case R_PPC64_TLSLD:
     return R_HINT;
   default:
     return R_ABS;
   }
 }
 
void PPC64::writePlt(uint8_t *Buf, uint64_t GotPltEntryAddr,
                      uint64_t PltEntryAddr, int32_t Index,
                      unsigned RelOff) const {
  int32_t Offset = PltHeaderSize + Index * PltEntrySize;
  // 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;
+  // Relocations relative to the toc-base need to be adjusted by the Toc offset.
+  uint64_t TocBiasedVal = Val - PPC64TocOffset;
+  // Relocations relative to dtv[dtpmod] need to be adjusted by the DTP offset.
+  uint64_t DTPBiasedVal = Val - DynamicThreadPointerOffset;
+
   switch (Type) {
+  // TOC biased relocation.
   case R_PPC64_GOT_TLSGD16:
   case R_PPC64_GOT_TLSLD16:
   case R_PPC64_TOC16:
-    return {R_PPC64_ADDR16, V};
+    return {R_PPC64_ADDR16, TocBiasedVal};
   case R_PPC64_TOC16_DS:
-    return {R_PPC64_ADDR16_DS, V};
+    return {R_PPC64_ADDR16_DS, TocBiasedVal};
   case R_PPC64_GOT_TLSGD16_HA:
   case R_PPC64_GOT_TLSLD16_HA:
   case R_PPC64_TOC16_HA:
-    return {R_PPC64_ADDR16_HA, V};
+    return {R_PPC64_ADDR16_HA, TocBiasedVal};
   case R_PPC64_GOT_TLSGD16_HI:
   case R_PPC64_GOT_TLSLD16_HI:
   case R_PPC64_TOC16_HI:
-    return {R_PPC64_ADDR16_HI, V};
+    return {R_PPC64_ADDR16_HI, TocBiasedVal};
   case R_PPC64_GOT_TLSGD16_LO:
   case R_PPC64_GOT_TLSLD16_LO:
   case R_PPC64_TOC16_LO:
-    return {R_PPC64_ADDR16_LO, V};
+    return {R_PPC64_ADDR16_LO, TocBiasedVal};
   case R_PPC64_TOC16_LO_DS:
-    return {R_PPC64_ADDR16_LO_DS, V};
+    return {R_PPC64_ADDR16_LO_DS, TocBiasedVal};
+
+  // Dynamic Thread pointer biased relocation types.
+  case R_PPC64_DTPREL16:
+    return {R_PPC64_ADDR16, DTPBiasedVal};
+  case R_PPC64_DTPREL16_DS:
+    return {R_PPC64_ADDR16_DS, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HA:
+    return {R_PPC64_ADDR16_HA, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HI:
+    return {R_PPC64_ADDR16_HI, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HIGHER:
+    return {R_PPC64_ADDR16_HIGHER, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HIGHERA:
+    return {R_PPC64_ADDR16_HIGHERA, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HIGHEST:
+    return {R_PPC64_ADDR16_HIGHEST, DTPBiasedVal};
+  case R_PPC64_DTPREL16_HIGHESTA:
+    return {R_PPC64_ADDR16_HIGHESTA, DTPBiasedVal};
+  case R_PPC64_DTPREL16_LO:
+    return {R_PPC64_ADDR16_LO, DTPBiasedVal};
+  case R_PPC64_DTPREL16_LO_DS:
+    return {R_PPC64_ADDR16_LO_DS, DTPBiasedVal};
+
   default:
     return {Type, Val};
   }
 }
 
 void PPC64::relocateOne(uint8_t *Loc, RelType Type, uint64_t Val) const {
   // For a TOC-relative relocation, proceed in terms of the corresponding
   // ADDR16 relocation type.

test/ELF/ppc64-dtprel.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 -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 -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
+        addi 4, 3, i@dtprel
+        lwa 4, i@dtprel(3)
+        ld 0, 16(1)
+        mtlr 0
+        blr
+
+        .globl test_64
+        .p2align        4
+        .type    test_64,@function
+
+        .globl test_adjusted
+        .p2align        4
+        .type    test_adjusted,@function
+test_adjusted:
+.Lfunc_gep1:
+        addis 2, 12, .TOC.-.Lfunc_gep1@ha
+        addi 2, 2, .TOC.-.Lfunc_gep1@l
+.Lfunc_lep1:
+        .localentry     test_adjusted, .Lfunc_lep1-.Lfunc_gep1
+        mflr 0
+        std 0, 16(1)
+        stdu 1, -32(1)
+        addis 3, 2, k@got@tlsld@ha
+        addi 3, 3, k@got@tlsld@l
+        bl __tls_get_addr(k@tlsld)
+        nop
+        lis 4, k@dtprel@highesta
+        ori 4, 4, k@dtprel@highera
+        lis 5, k@dtprel@ha
+        addi 5, 5, k@dtprel@l
+        sldi 4, 4, 32
+        or   4, 4, 5
+        add  3, 3, 4
+        addi 1, 1, 32
+        ld 0, 16(1)
+        mtlr 0
+        blr
+
+        .globl test_not_adjusted
+        .p2align      4
+        .type test_not_adjusted,@function
+test_not_adjusted:
+.Lfunc_gep2:
+        addis 2, 12, .TOC.-.Lfunc_gep2@ha
+        addi 2, 2, .TOC.-.Lfunc_gep2@l
+.Lfunc_lep2:
+        .localentry     test_not_adjusted, .Lfunc_lep2-.Lfunc_gep2
+        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(k@tlsld)
+        nop
+        lis 4, k@dtprel@highest
+        ori 4, 4, k@dtprel@higher
+        sldi 4, 4, 32
+        oris  4, 4, k@dtprel@h
+        ori   4, 4, k@dtprel@l
+        add 3, 3, 4
+        addi 1, 1, 32
+        ld 0, 16(1)
+        mtlr 0
+        blr
+
+        .type   i,@object
+        .section        .tdata,"awT",@progbits
+        .space 1024
+        .p2align        2
+i:
+        .long   55
+        .size   i, 4
+
+        .space 1024 * 1024 * 4
+        .type k,@object
+        .p2align 2
+k:
+       .long 128
+       .size k,4
+
+// Verify the input has all the remaining DTPREL based relocations we want to
+// test.
+// InputRelocs: Relocation section '.rela.text'
+// InputRelocs: R_PPC64_DTPREL16          {{[0-9a-f]+}} i + 0
+// InputRelocs: R_PPC64_DTPREL16_DS       {{[0-9a-f]+}} i + 0
+// InputRelocs: R_PPC64_DTPREL16_HIGHESTA {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_HIGHERA  {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_HA       {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_LO       {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_HIGHEST  {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_HIGHER   {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_HI       {{[0-9a-f]+}} k + 0
+// InputRelocs: R_PPC64_DTPREL16_LO       {{[0-9a-f]+}} k + 0
+
+// Expect a single dynamic relocation in the '.rela.dyn section for the module id.
+// 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
+
+
+// i@dtprel  --> (1024 - 0x8000) = -31744
+// Dis: test:
+// Dis:    addi 4, 3, -31744
+// Dis:    lwa 4, -31744(3)
+
+// #k@dtprel(1024 + 4 + 1024 * 1024 * 4) = 0x400404
+
+// #highesta(k@dtprel) --> ((0x400404 - 0x8000 + 0x8000) >> 48) & 0xffff = 0
+// #highera(k@dtprel)  --> ((0x400404 - 0x8000 + 0x8000) >> 32) & 0xffff = 0
+// #ha(k@dtprel)       --> ((0x400404 - 0x8000 + 0x8000) >> 16) & 0xffff = 64
+// #lo(k@dtprel)       --> ((0x400404 - 0x8000) & 0xffff = -31740
+// Dis:  test_adjusted:
+// Dis:     lis 4, 0
+// Dis:     ori 4, 4, 0
+// Dis:     lis 5, 64
+// Dis:     addi 5, 5, -31740
+
+// #highest(k@dtprel) --> ((0x400404 - 0x8000) >> 48) & 0xffff = 0
+// #higher(k@dtprel)  --> ((0x400404 - 0x8000) >> 32) & 0xffff = 0
+// #hi(k@dtprel)      --> ((0x400404 - 0x8000) >> 16) & 0xffff = 63
+// #lo(k@dtprel)      --> ((0x400404 - 0x8000) & 0xffff = 33796
+// Dis:  test_not_adjusted:
+// Dis:    lis 4, 0
+// Dis:    ori 4, 4, 0
+// Dis:    oris 4, 4, 63
+// Dis:    ori 4, 4, 33796

test/ELF/ppc64-local-dynamic.s

.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
+        addis 3, 3, i@dtprel@ha
+        lwa 3, i@dtprel@l(3)
         ld 0, 16(1)
         mtlr 0
         blr
 
         .globl test_hi
         .p2align 4
         .type test_hi,@function
 test_hi:
j:
 
         .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.
+// Verify that the input contains all the R_PPC64_GOT_TLSLD16* relocations, as
+// well as the DTPREL relocations used in a typical medium code model
+// local-dynamic variable access.
 // 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
+// InputRelocs:     R_PPC64_GOT_TLSLD16_HA {{[0-9a-f]+}} i + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16_LO {{[0-9a-f]+}} i + 0
+// InputRelocs:     R_PPC64_TLSLD          {{[0-9a-f]+}} i + 0
+// InputRelocs:     R_PPC64_DTPREL16_HA    {{[0-9a-f]+}} i + 0
+// InputRelocs:     R_PPC64_DTPREL16_LO_DS {{[0-9a-f]+}} i + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16_HI {{[0-9a-f]+}} j + 0
+// InputRelocs:     R_PPC64_GOT_TLSLD16    {{[0-9a-f]+}} 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
+// When calculating offset relative to the dynamic thread pointer we have to
+// adjust by 0x8000 since each DTV pointer points 0x8000 bytes past the start of
+// its TLS block.
+// #ha(i@dtprel) --> (0x0 -0x8000 + 0x8000) >> 16 = 0
+// #lo(i@dtprel) --> (0x0 -0x8000) = -0x8000 = -32768
 // Dis:     test:
 // Dis:        addis 3, 2, 0
 // Dis-NEXT:   addi 3, 3, -32760
+// Dis-NEXT:   bl .+67108804
+// Dis-NEXT:   ld 2, 24(1)
+// Dis-NEXT:   addis 3, 3, 0
+// Dis-NEXT:   lwa 3, -32768(3)
+
 
 // #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