AMDGPU: Return address lowering

The patch computes the return address for the current function.

Differential revision: https://reviews.llvm.org/D59666

llvm-svn: 362001

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

@@ -3695,6 +3695,7 @@ SDValue SITargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   switch (Op.getOpcode()) {
   default: return AMDGPUTargetLowering::LowerOperation(Op, DAG);
   case ISD::BRCOND: return LowerBRCOND(Op, DAG);
+  case ISD::RETURNADDR: return LowerRETURNADDR(Op, DAG);
   case ISD::LOAD: {
     SDValue Result = LowerLOAD(Op, DAG);
     assert((!Result.getNode() ||
@@ -4153,6 +4154,31 @@ SDValue SITargetLowering::LowerBRCOND(SDValue BRCOND,
   return Chain;
 }
 
+SDValue SITargetLowering::LowerRETURNADDR(SDValue Op,
+                                          SelectionDAG &DAG) const {
+  MVT VT = Op.getSimpleValueType();
+  SDLoc DL(Op);
+  // Checking the depth
+  if (cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue() != 0)
+    return DAG.getConstant(0, DL, VT);
+
+  MachineFunction &MF = DAG.getMachineFunction();
+  const SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
+  // Check for kernel and shader functions
+  if (Info->isEntryFunction())
+    return DAG.getConstant(0, DL, VT);
+
+  MachineFrameInfo &MFI = MF.getFrameInfo();
+  // There is a call to @llvm.returnaddress in this function
+  MFI.setReturnAddressIsTaken(true);
+
+  const SIRegisterInfo *TRI = getSubtarget()->getRegisterInfo();
+  // Get the return address reg and mark it as an implicit live-in
+  unsigned Reg = MF.addLiveIn(TRI->getReturnAddressReg(MF), getRegClassFor(VT, Op.getNode()->isDivergent()));
+
+  return DAG.getCopyFromReg(DAG.getEntryNode(), DL, Reg, VT);
+}
+
 SDValue SITargetLowering::getFPExtOrFPTrunc(SelectionDAG &DAG,
                                             SDValue Op,
                                             const SDLoc &DL,

llvm/lib/Target/AMDGPU/SIISelLowering.h

@@ -89,7 +89,7 @@ class SITargetLowering final : public AMDGPUTargetLowering {
   SDValue LowerTrig(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerBRCOND(SDValue Op, SelectionDAG &DAG) const;
-
+  SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
   SDValue adjustLoadValueType(unsigned Opcode, MemSDNode *M,
                               SelectionDAG &DAG, ArrayRef<SDValue> Ops,
                               bool IsIntrinsic = false) const;

llvm/test/CodeGen/AMDGPU/returnaddress.ll

@@ -0,0 +1,65 @@
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
+
+; Test with zero frame
+; GCN-LABEL: {{^}}func1
+; GCN: v_mov_b32_e32 v0, s30
+; GCN: v_mov_b32_e32 v1, s31
+; GCN: s_setpc_b64 s[30:31]
+define i8* @func1() nounwind {
+entry:
+  %0 = tail call i8* @llvm.returnaddress(i32 0)
+  ret i8* %0
+}
+
+; Test with non-zero frame
+; GCN-LABEL: {{^}}func2
+; GCN: v_mov_b32_e32 v0, 0
+; GCN: v_mov_b32_e32 v1, 0
+; GCN: s_setpc_b64 s[30:31]
+define i8* @func2() nounwind {
+entry:
+  %0 = tail call i8* @llvm.returnaddress(i32 1)
+  ret i8* %0
+}
+
+; Test with amdgpu_kernel
+; GCN-LABEL: {{^}}func3
+; GCN: v_mov_b32_e32 v0, 0
+; GCN: v_mov_b32_e32 v1, v0
+define amdgpu_kernel void @func3(i8** %out) nounwind {
+entry:
+  %tmp = tail call i8* @llvm.returnaddress(i32 0)
+  store i8* %tmp, i8** %out, align 4
+  ret void
+}
+
+; Test with use outside the entry-block
+; GCN-LABEL: {{^}}func4
+; GCN: v_mov_b32_e32 v0, 0
+; GCN: v_mov_b32_e32 v1, v0
+define amdgpu_kernel void @func4(i8** %out, i32 %val) nounwind {
+entry:
+  %cmp = icmp ne i32 %val, 0
+  br i1 %cmp, label %store, label %exit
+
+store:
+  %tmp = tail call i8* @llvm.returnaddress(i32 1)
+  store i8* %tmp, i8** %out, align 4
+  ret void
+
+exit:
+  ret void
+}
+
+; Test ending in unreachable
+; GCN-LABEL: {{^}}func5
+; GCN: v_mov_b32_e32 v0, 0
+define void @func5() nounwind {
+entry:
+  %tmp = tail call i8* @llvm.returnaddress(i32 2)
+  store volatile i32 0, i32 addrspace(3)* undef, align 4
+  unreachable
+}
+
+
+declare i8* @llvm.returnaddress(i32) nounwind readnone