[ELF][PPC32] Support range extension thunks with addends

MaskRay · MaskRay · commit f15b60b3a2a2 · 2020-01-25T22:33:27.000-08:00
* Generalize the code added in D70637 and D70937. We should eventually remove the EM_MIPS special case. * Handle R_PPC_LOCAL24PC the same way as R_PPC_REL24. Reviewed By: Bdragon28 Differential Revision: https://reviews.llvm.org/D73424 (cherry picked from commit 70389be)
diff --git a/lld/ELF/Arch/PPC.cpp b/lld/ELF/Arch/PPC.cpp
@@ -193,21 +193,21 @@ void PPC::writeGotPlt(uint8_t *buf, const Symbol &s) const {
 }
 
 bool PPC::needsThunk(RelExpr expr, RelType type, const InputFile *file,
-                     uint64_t branchAddr, const Symbol &s, int64_t /*a*/) const {
-  if (type != R_PPC_REL24 && type != R_PPC_PLTREL24)
+                     uint64_t branchAddr, const Symbol &s, int64_t a) const {
+  if (type != R_PPC_LOCAL24PC && type != R_PPC_REL24 && type != R_PPC_PLTREL24)
     return false;
   if (s.isInPlt())
     return true;
   if (s.isUndefWeak())
     return false;
-  return !(expr == R_PC && PPC::inBranchRange(type, branchAddr, s.getVA()));
+  return !PPC::inBranchRange(type, branchAddr, s.getVA(a));
 }
 
 uint32_t PPC::getThunkSectionSpacing() const { return 0x2000000; }
 
 bool PPC::inBranchRange(RelType type, uint64_t src, uint64_t dst) const {
   uint64_t offset = dst - src;
-  if (type == R_PPC_REL24 || type == R_PPC_PLTREL24)
+  if (type == R_PPC_LOCAL24PC || type == R_PPC_REL24 || type == R_PPC_PLTREL24)
     return isInt<26>(offset);
   llvm_unreachable("unsupported relocation type used in branch");
 }
@@ -230,13 +230,13 @@ RelExpr PPC::getRelExpr(RelType type, const Symbol &s,
     return R_DTPREL;
   case R_PPC_REL14:
   case R_PPC_REL32:
-  case R_PPC_LOCAL24PC:
   case R_PPC_REL16_LO:
   case R_PPC_REL16_HI:
   case R_PPC_REL16_HA:
     return R_PC;
   case R_PPC_GOT16:
     return R_GOT_OFF;
+  case R_PPC_LOCAL24PC:
   case R_PPC_REL24:
     return R_PLT_PC;
   case R_PPC_PLTREL24:
diff --git a/lld/ELF/Relocations.cpp b/lld/ELF/Relocations.cpp
@@ -1304,10 +1304,10 @@ static void scanReloc(InputSectionBase &sec, OffsetGetter &getOffset, RelTy *&i,
     if (expr == R_GOT_PC && !isAbsoluteValue(sym)) {
       expr = target->adjustRelaxExpr(type, relocatedAddr, expr);
     } else {
-      // Addend of R_PPC_PLTREL24 is used to choose call stub type. It should be
-      // ignored if optimized to R_PC.
+      // The 0x8000 bit of r_addend of R_PPC_PLTREL24 is used to choose call
+      // stub type. It should be ignored if optimized to R_PC.
       if (config->emachine == EM_PPC && expr == R_PPC32_PLTREL)
-        addend = 0;
+        addend &= ~0x8000;
       expr = fromPlt(expr);
     }
   }
@@ -1826,9 +1826,7 @@ bool ThunkCreator::normalizeExistingThunk(Relocation &rel, uint64_t src) {
                               rel.sym->getVA(rel.addend) + getPCBias(rel.type)))
       return true;
     rel.sym = &t->destination;
-    // TODO Restore addend on all targets.
-    if (config->emachine == EM_AARCH64 || config->emachine == EM_PPC64)
-      rel.addend = t->addend;
+    rel.addend = t->addend;
     if (rel.sym->isInPlt())
       rel.expr = toPlt(rel.expr);
   }
@@ -1906,16 +1904,11 @@ bool ThunkCreator::createThunks(ArrayRef<OutputSection *> outputSections) {
             rel.sym = t->getThunkTargetSym();
             rel.expr = fromPlt(rel.expr);
 
-            // On AArch64 and PPC64, a jump/call relocation may be encoded as
+            // On AArch64 and PPC, a jump/call relocation may be encoded as
             // STT_SECTION + non-zero addend, clear the addend after
             // redirection.
-            //
-            // The addend of R_PPC_PLTREL24 should be ignored after changing to
-            // R_PC.
-            if (config->emachine == EM_AARCH64 ||
-                config->emachine == EM_PPC64 ||
-                (config->emachine == EM_PPC && rel.type == R_PPC_PLTREL24))
-              rel.addend = 0;
+            if (config->emachine != EM_MIPS)
+              rel.addend = -getPCBias(rel.type);
           }
 
         for (auto &p : isd->thunkSections)
diff --git a/lld/ELF/Thunks.cpp b/lld/ELF/Thunks.cpp
@@ -245,8 +245,7 @@ class PPC32PltCallStub final : public Thunk {
   // decide the offsets in the call stub.
   PPC32PltCallStub(const InputSection &isec, const Relocation &rel,
                    Symbol &dest)
-      : Thunk(dest, rel.type == R_PPC_PLTREL24 ? rel.addend : 0),
-        file(isec.file) {}
+      : Thunk(dest, rel.addend), file(isec.file) {}
   uint32_t size() override { return 16; }
   void writeTo(uint8_t *buf) override;
   void addSymbols(ThunkSection &isec) override;
@@ -257,6 +256,14 @@ class PPC32PltCallStub final : public Thunk {
   const InputFile *file;
 };
 
+class PPC32LongThunk final : public Thunk {
+public:
+  PPC32LongThunk(Symbol &dest, int64_t addend) : Thunk(dest, addend) {}
+  uint32_t size() override { return config->isPic ? 32 : 16; }
+  void writeTo(uint8_t *buf) override;
+  void addSymbols(ThunkSection &isec) override;
+};
+
 // PPC64 Plt call stubs.
 // Any call site that needs to call through a plt entry needs a call stub in
 // the .text section. The call stub is responsible for:
@@ -765,6 +772,33 @@ bool PPC32PltCallStub::isCompatibleWith(const InputSection &isec,
   return !config->isPic || (isec.file == file && rel.addend == addend);
 }
 
+void PPC32LongThunk::addSymbols(ThunkSection &isec) {
+  addSymbol(saver.save("__LongThunk_" + destination.getName()), STT_FUNC, 0,
+            isec);
+}
+
+void PPC32LongThunk::writeTo(uint8_t *buf) {
+  auto ha = [](uint32_t v) -> uint16_t { return (v + 0x8000) >> 16; };
+  auto lo = [](uint32_t v) -> uint16_t { return v; };
+  uint32_t d = destination.getVA(addend);
+  if (config->isPic) {
+    uint32_t off = d - (getThunkTargetSym()->getVA() + 8);
+    write32(buf + 0, 0x7c0802a6);            // mflr r12,0
+    write32(buf + 4, 0x429f0005);            // bcl r20,r31,.+4
+    write32(buf + 8, 0x7d8802a6);            // mtctr r12
+    write32(buf + 12, 0x3d8c0000 | ha(off)); // addis r12,r12,off@ha
+    write32(buf + 16, 0x398c0000 | lo(off)); // addi r12,r12,off@l
+    write32(buf + 20, 0x7c0803a6);           // mtlr r0
+    buf += 24;
+  } else {
+    write32(buf + 0, 0x3d800000 | ha(d));    // lis r12,d@ha
+    write32(buf + 4, 0x398c0000 | lo(d));    // addi r12,r12,d@l
+    buf += 8;
+  }
+  write32(buf + 0, 0x7d8903a6);              // mtctr r12
+  write32(buf + 4, 0x4e800420);              // bctr
+}
+
 void writePPC64LoadAndBranch(uint8_t *buf, int64_t offset) {
   uint16_t offHa = (offset + 0x8000) >> 16;
   uint16_t offLo = offset & 0xffff;
@@ -902,9 +936,12 @@ static Thunk *addThunkMips(RelType type, Symbol &s) {
 
 static Thunk *addThunkPPC32(const InputSection &isec, const Relocation &rel,
                             Symbol &s) {
-  assert((rel.type == R_PPC_REL24 || rel.type == R_PPC_PLTREL24) &&
+  assert((rel.type == R_PPC_LOCAL24PC || rel.type == R_PPC_REL24 ||
+          rel.type == R_PPC_PLTREL24) &&
          "unexpected relocation type for thunk");
-  return make<PPC32PltCallStub>(isec, rel, s);
+  if (s.isInPlt())
+    return make<PPC32PltCallStub>(isec, rel, s);
+  return make<PPC32LongThunk>(s, rel.addend);
 }
 
 static Thunk *addThunkPPC64(RelType type, Symbol &s, int64_t a) {
diff --git a/lld/test/ELF/ppc32-long-thunk.s b/lld/test/ELF/ppc32-long-thunk.s
@@ -0,0 +1,87 @@
+# REQUIRES: ppc
+# RUN: echo 'SECTIONS { \
+# RUN:       .text_low 0x2000: { *(.text_low) } \
+# RUN:       .text_high 0x2002000 : { *(.text_high) } \
+# RUN:       }' > %t.script
+
+# RUN: llvm-mc -filetype=obj -triple=powerpc %s -o %t.o
+# RUN: ld.lld -T %t.script %t.o -o %t
+# RUN: llvm-readelf -r %t | FileCheck --check-prefix=SEC %s
+# RUN: llvm-objdump -d --no-show-raw-insn %t | FileCheck --check-prefixes=CHECK,PD %s
+
+# RUN: ld.lld -T %t.script -pie %t.o -o %t
+# RUN: llvm-readelf -r %t | FileCheck --check-prefix=SEC %s
+# RUN: llvm-objdump -d --no-show-raw-insn %t | FileCheck --check-prefixes=CHECK,PI %s
+
+# SEC: There are no relocations in this file.
+
+# CHECK:      _start:
+# CHECK-NEXT:     2000: bl .+24
+# CHECK-NEXT:           bl .+20
+# CHECK-NEXT:           bl .+16
+# CHECK-NEXT:           bl .+33554428
+# PD-NEXT:              bl .+24
+# PI-NEXT:              bl .+40
+
+## high = 0x02002008 = 65536*512+8200
+# PD:         __LongThunk_high:
+# PD-NEXT:        2018: lis 12, 512
+# PD-NEXT:              addi 12, 12, 8200
+# PD-NEXT:              mtctr 12
+# PD-NEXT:              bctr
+
+## .text_high+16 = 0x02002010 = 65536*512+8208
+# PD:         __LongThunk_:
+# PD-NEXT:        2028: lis 12, 512
+# PD-NEXT:              addi 12, 12, 8208
+# PD-NEXT:              mtctr 12
+# PD-NEXT:              bctr
+
+## high-0x2028 = 0x02002008-0x2020 = 65536*512-24
+# PI:         __LongThunk_high:
+# PI-NEXT:        2018: mflr 0
+# PI-NEXT:              bcl 20, 31, .+4
+# PI-NEXT:        2020: mflr 12
+# PI-NEXT:              addis 12, 12, 512
+# PI-NEXT:              addi 12, 12, -24
+# PI-NEXT:              mtlr 0
+# PI-NEXT:              mtctr 12
+# PI-NEXT:              bctr
+
+## .text_high+16-0x2048 = 0x02002010-0x2048 = 65536*512-48
+# PI:         __LongThunk_:
+# PI-NEXT:        2038: mflr 0
+# PI-NEXT:              bcl 20, 31, .+4
+# PI-NEXT:        2040: mflr 12
+# PI-NEXT:              addis 12, 12, 512
+# PI-NEXT:              addi 12, 12, -48
+# PI-NEXT:              mtlr 0
+# PI-NEXT:              mtctr 12
+# PI-NEXT:              bctr
+
+.section .text_low, "ax", %progbits
+.globl _start
+_start:
+bl high@local     # Need a thunk
+bl high@local     # Need a thunk
+bl high+32768@plt # Need a thunk
+bl high
+bl .text_high+16  # Need a thunk
+blr
+
+# PD:         02002008 high:
+# PD-NEXT:              bl .-33554432
+# PD-NEXT:              bl .+4
+# PD:         __LongThunk_:
+# PD-NEXT:     2002010: lis 12, 0
+# PD-NEXT:              addi 12, 12, 8200
+# PD-NEXT:              mtctr 12
+# PD-NEXT:              bctr
+
+.section .text_high, "ax", %progbits
+nop
+nop
+.globl high
+high:
+bl .text_low+8
+bl .text_low+8    # Need a thunk
