Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUInstrInfo.td
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUInstrInfo.td
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUInstrInfo.td
@@ -69,8 +69,6 @@
   [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 @@
   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]
 >;
 
Index: llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -2711,6 +2711,11 @@
   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 @@
         .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::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) &&
Index: llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
+++ llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
@@ -373,7 +373,8 @@
 // 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 @@
 }
 
 // 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;
Index: llvm/trunk/test/CodeGen/AMDGPU/function-call-relocs.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/function-call-relocs.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/function-call-relocs.ll
@@ -0,0 +1,51 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji < %s | FileCheck %s
+
+declare void @func(i32 addrspace(1)* %out)
+
+declare protected void @protected_func(i32 addrspace(1)* %out)
+
+declare hidden void @hidden_func(i32 addrspace(1)* %out)
+
+; CHECK-LABEL: call_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[GOT_ADDR_LO:[0-9]+]], s[[PC_LO]], func@gotpcrel32@lo+4
+; CHECK: s_addc_u32 s[[GOT_ADDR_HI:[0-9]+]], s[[PC_HI]], func@gotpcrel32@hi+4
+; CHECK: s_load_dwordx2 s{{\[}}[[ADDR_LO:[0-9]+]]:[[ADDR_HI:[0-9]+]]{{\]}}, s{{\[}}[[GOT_ADDR_LO]]:[[GOT_ADDR_HI]]{{\]}}, 0x0
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_func(i32 addrspace(1)* %out) {
+  call void @func(i32 addrspace(1)* %out)
+  ret void
+}
+
+; CHECK-LABEL: call_protected_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], protected_func@rel32@lo+4
+; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], protected_func@rel32@hi+4
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_protected_func(i32 addrspace(1)* %out) {
+  call void @protected_func(i32 addrspace(1)* %out)
+  ret void
+}
+
+; CHECK-LABEL: call_hidden_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], hidden_func@rel32@lo+4
+; CHECK: s_addc_u32 s[[ADDR_HI:[0-9]+]], s[[PC_HI]], hidden_func@rel32@hi+4
+; CHECK: s_swappc_b64 s{{\[}}{{[0-9]+:[0-9]+}}{{\]}}, s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define amdgpu_kernel void @call_hidden_func(i32 addrspace(1)* %out) {
+  call void @hidden_func(i32 addrspace(1)* %out)
+  ret void
+}
+
+declare i64 @funci()
+
+; CHECK-LABEL: tail_call_func:
+; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
+; CHECK: s_add_u32 s[[GOT_ADDR_LO:[0-9]+]], s[[PC_LO]], funci@gotpcrel32@lo+4
+; CHECK: s_addc_u32 s[[GOT_ADDR_HI:[0-9]+]], s[[PC_HI]], funci@gotpcrel32@hi+4
+; CHECK: s_load_dwordx2 s{{\[}}[[ADDR_LO:[0-9]+]]:[[ADDR_HI:[0-9]+]]{{\]}}, s{{\[}}[[GOT_ADDR_LO]]:[[GOT_ADDR_HI]]{{\]}}, 0x0
+; CHECK: s_setpc_b64 s{{\[}}[[ADDR_LO]]:[[ADDR_HI]]{{\]}}
+define i64 @tail_call_func() {
+  %ret = tail call i64 @funci()
+  ret i64 %ret
+}