[AMDGPU] Support emitting GOT relocations for function calls

Differential Revision: https://reviews.llvm.org/D57416

llvm-svn: 353083

3 files changed, 20 insertions, 41 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
index 73ae5de76b2..ba924b1f63a 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td
@@ -69,8 +69,6 @@ def AMDGPUAddeSubeOp : SDTypeProfile<2, 3,
   [SDTCisSameAs<0, 2>, SDTCisSameAs<0, 3>, SDTCisVT<0, i32>, SDTCisVT<1, i1>, SDTCisVT<4, i1>]
 >;
 
-def SDT_AMDGPUTCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>]>;
-
 //===----------------------------------------------------------------------===//
 // AMDGPU DAG Nodes
 //
@@ -95,7 +93,8 @@ def AMDGPUcall : SDNode<"AMDGPUISD::CALL",
   SDNPVariadic]
 >;
 
-def AMDGPUtc_return: SDNode<"AMDGPUISD::TC_RETURN", SDT_AMDGPUTCRET,
+def AMDGPUtc_return: SDNode<"AMDGPUISD::TC_RETURN",
+  SDTypeProfile<0, 3, [SDTCisPtrTy<0>]>,
   [SDNPHasChain, SDNPOptInGlue, SDNPVariadic]
 >;
 
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 34643c99e11..94d2853bad1 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -2711,6 +2711,11 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
   std::vector<SDValue> Ops;
   Ops.push_back(Chain);
   Ops.push_back(Callee);
+  // Add a redundant copy of the callee global which will not be legalized, as
+  // we need direct access to the callee later.
+  GlobalAddressSDNode *GSD = cast<GlobalAddressSDNode>(Callee);
+  const GlobalValue *GV = GSD->getGlobal();
+  Ops.push_back(DAG.getTargetGlobalAddress(GV, DL, MVT::i64));
 
   if (IsTailCall) {
     // Each tail call may have to adjust the stack by a different amount, so
@@ -3474,34 +3479,16 @@ MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter(
         .addReg(Info->getFrameOffsetReg(), RegState::Implicit);
     return BB;
   }
-  case AMDGPU::SI_CALL_ISEL:
-  case AMDGPU::SI_TCRETURN_ISEL: {
+  case AMDGPU::SI_CALL_ISEL: {
     const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
     const DebugLoc &DL = MI.getDebugLoc();
-    unsigned ReturnAddrReg = TII->getRegisterInfo().getReturnAddressReg(*MF);
 
-    MachineRegisterInfo &MRI = MF->getRegInfo();
-    unsigned GlobalAddrReg = MI.getOperand(0).getReg();
-    MachineInstr *PCRel = MRI.getVRegDef(GlobalAddrReg);
-    assert(PCRel->getOpcode() == AMDGPU::SI_PC_ADD_REL_OFFSET);
-
-    const GlobalValue *G = PCRel->getOperand(1).getGlobal();
+    unsigned ReturnAddrReg = TII->getRegisterInfo().getReturnAddressReg(*MF);
 
     MachineInstrBuilder MIB;
-    if (MI.getOpcode() == AMDGPU::SI_CALL_ISEL) {
-      MIB = BuildMI(*BB, MI, DL, TII->get(AMDGPU::SI_CALL), ReturnAddrReg)
-        .add(MI.getOperand(0))
-        .addGlobalAddress(G);
-    } else {
-      MIB = BuildMI(*BB, MI, DL, TII->get(AMDGPU::SI_TCRETURN))
-        .add(MI.getOperand(0))
-        .addGlobalAddress(G);
-
-      // There is an additional imm operand for tcreturn, but it should be in the
-      // right place already.
-    }
+    MIB = BuildMI(*BB, MI, DL, TII->get(AMDGPU::SI_CALL), ReturnAddrReg);
 
-    for (unsigned I = 1, E = MI.getNumOperands(); I != E; ++I)
+    for (unsigned I = 0, E = MI.getNumOperands(); I != E; ++I)
       MIB.add(MI.getOperand(I));
 
     MIB.cloneMemRefs(MI);
@@ -4008,7 +3995,10 @@ bool SITargetLowering::shouldEmitFixup(const GlobalValue *GV) const {
 }
 
 bool SITargetLowering::shouldEmitGOTReloc(const GlobalValue *GV) const {
-  return (GV->getType()->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
+  // FIXME: Either avoid relying on address space here or change the default
+  // address space for functions to avoid the explicit check.
+  return (GV->getValueType()->isFunctionTy() ||
+          GV->getType()->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
           GV->getType()->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS ||
           GV->getType()->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS_32BIT) &&
          !shouldEmitFixup(GV) &&
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 61a3e9268df..9b99d1bc3ff 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -373,7 +373,8 @@ def SI_RETURN : SPseudoInstSI <
 // This version is only needed so we can fill in the output regiter in
 // the custom inserter.
 def SI_CALL_ISEL : SPseudoInstSI <
-  (outs), (ins SSrc_b64:$src0), [(AMDGPUcall i64:$src0)]> {
+  (outs), (ins SSrc_b64:$src0, unknown:$callee),
+  [(AMDGPUcall i64:$src0, tglobaladdr:$callee)]> {
   let Size = 4;
   let isCall = 1;
   let SchedRW = [WriteBranch];
@@ -391,20 +392,9 @@ def SI_CALL : SPseudoInstSI <
 }
 
 // Tail call handling pseudo
-def SI_TCRETURN_ISEL : SPseudoInstSI<(outs),
-  (ins SSrc_b64:$src0, i32imm:$fpdiff),
-  [(AMDGPUtc_return i64:$src0, i32:$fpdiff)]> {
-  let isCall = 1;
-  let isTerminator = 1;
-  let isReturn = 1;
-  let isBarrier = 1;
-  let SchedRW = [WriteBranch];
-  let usesCustomInserter = 1;
-}
-
-def SI_TCRETURN : SPseudoInstSI <
-  (outs),
-  (ins SSrc_b64:$src0, unknown:$callee, i32imm:$fpdiff)> {
+def SI_TCRETURN : SPseudoInstSI <(outs),
+  (ins SSrc_b64:$src0, unknown:$callee, i32imm:$fpdiff),
+  [(AMDGPUtc_return i64:$src0, tglobaladdr:$callee, i32:$fpdiff)]> {
   let Size = 4;
   let isCall = 1;
   let isTerminator = 1;