[PowerPC] Ensure that the TOC reload directly follows bctrl on PPC64

On non-Darwin PPC64, the TOC reload needs to come directly after the bctrl
instruction (for indirect calls) because the 'bctrl/ld 2, 40(1)' instruction
sequence is interpreted by the unwinding code in libgcc. To make sure these
occur as a pair, as with other pairings interpreted by the linker, fuse the two
instructions into one instruction (for code generation only).

In the future, we might wish to do this by emitting CFI directives instead,
but this solution is simpler, and mirrors what GCC does. Additional discussion
on this point is contained in the PR.

Fixes PR22015.

llvm-svn: 224788

1 files changed, 12 insertions, 13 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 06cf9af80b6..e430b07d143 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -775,6 +775,7 @@ const char *PPCTargetLowering::getTargetNodeName(unsigned Opcode) const {
   case PPCISD::CALL_NOP_TLS:    return "PPCISD::CALL_NOP_TLS";
   case PPCISD::MTCTR:           return "PPCISD::MTCTR";
   case PPCISD::BCTRL:           return "PPCISD::BCTRL";
+  case PPCISD::BCTRL_LOAD_TOC:  return "PPCISD::BCTRL_LOAD_TOC";
   case PPCISD::RET_FLAG:        return "PPCISD::RET_FLAG";
   case PPCISD::READ_TIME_BASE:  return "PPCISD::READ_TIME_BASE";
   case PPCISD::EH_SJLJ_SETJMP:  return "PPCISD::EH_SJLJ_SETJMP";
@@ -3864,7 +3865,6 @@ PPCTargetLowering::FinishCall(CallingConv::ID CallConv, SDLoc dl,
   // stack frame. If caller and callee belong to the same module (and have the
   // same TOC), the NOP will remain unchanged.
 
-  bool needsTOCRestore = false;
   if (!isTailCall && Subtarget.isSVR4ABI()&& Subtarget.isPPC64()) {
     if (CallOpc == PPCISD::BCTRL) {
       // This is a call through a function pointer.
@@ -3876,7 +3876,17 @@ PPCTargetLowering::FinishCall(CallingConv::ID CallConv, SDLoc dl,
       // since r2 is a reserved register (which prevents the register allocator
       // from allocating it), resulting in an additional register being
       // allocated and an unnecessary move instruction being generated.
-      needsTOCRestore = true;
+      CallOpc = PPCISD::BCTRL_LOAD_TOC;
+
+      EVT PtrVT = DAG.getTargetLoweringInfo().getPointerTy();
+      SDValue StackPtr = DAG.getRegister(PPC::X1, PtrVT);
+      unsigned TOCSaveOffset = PPCFrameLowering::getTOCSaveOffset(isELFv2ABI);
+      SDValue TOCOff = DAG.getIntPtrConstant(TOCSaveOffset);
+      SDValue AddTOC = DAG.getNode(ISD::ADD, dl, MVT::i64, StackPtr, TOCOff);
+
+      // The address needs to go after the chain input but before the flag (or
+      // any other variadic arguments).
+      Ops.insert(std::next(Ops.begin()), AddTOC);
     } else if ((CallOpc == PPCISD::CALL) &&
                (!isLocalCall(Callee) ||
                 DAG.getTarget().getRelocationModel() == Reloc::PIC_)) {
@@ -3890,17 +3900,6 @@ PPCTargetLowering::FinishCall(CallingConv::ID CallConv, SDLoc dl,
   Chain = DAG.getNode(CallOpc, dl, NodeTys, Ops);
   InFlag = Chain.getValue(1);
 
-  if (needsTOCRestore) {
-    SDVTList VTs = DAG.getVTList(MVT::Other, MVT::Glue);
-    EVT PtrVT = DAG.getTargetLoweringInfo().getPointerTy();
-    SDValue StackPtr = DAG.getRegister(PPC::X1, PtrVT);
-    unsigned TOCSaveOffset = PPCFrameLowering::getTOCSaveOffset(isELFv2ABI);
-    SDValue TOCOff = DAG.getIntPtrConstant(TOCSaveOffset);
-    SDValue AddTOC = DAG.getNode(ISD::ADD, dl, MVT::i64, StackPtr, TOCOff);
-    Chain = DAG.getNode(PPCISD::LOAD_TOC, dl, VTs, Chain, AddTOC, InFlag);
-    InFlag = Chain.getValue(1);
-  }
-
   Chain = DAG.getCALLSEQ_END(Chain, DAG.getIntPtrConstant(NumBytes, true),
                              DAG.getIntPtrConstant(BytesCalleePops, true),
                              InFlag, dl);