Index: lib/Target/AArch64/AArch64CallingConvention.td
===================================================================
--- lib/Target/AArch64/AArch64CallingConvention.td
+++ lib/Target/AArch64/AArch64CallingConvention.td
@@ -204,6 +204,26 @@
                                           [Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7]>>
 ]>;
 
+//===----------------------------------------------------------------------===//
+// ARM64 Calling Convention for GHC
+//===----------------------------------------------------------------------===//
+
+def CC_AArch64_GHC : CallingConv<[
+  // Handle all vector types as either f64 or v2f64.
+  CCIfType<[v1i64, v2i32, v4i16, v8i8, v2f32], CCBitConvertToType<f64>>,
+  CCIfType<[v2i64, v4i32, v8i16, v16i8, v4f32, f128], CCBitConvertToType<v2f64>>,
+
+  CCIfType<[v2f64], CCAssignToReg<[Q4, Q5]>>,
+  CCIfType<[f32], CCAssignToReg<[S8, S9, S10, S11]>>,
+  CCIfType<[f64], CCAssignToReg<[D12, D13, D14, D15]>>,
+
+  // Promote i8/i16/i32 arguments to i64.
+  CCIfType<[i8, i16, i32], CCPromoteToType<i64>>,
+
+  // Pass in STG registers: Base, Sp, Hp, R1, R2, R3, R4, R5, R6, SpLim
+  CCIfType<[i64], CCAssignToReg<[X19, X20, X21, X22, X23, X24, X25, X26, X27, X28]>>
+]>;
+
 // FIXME: LR is only callee-saved in the sense that *we* preserve it and are
 // presumably a callee to someone. External functions may not do so, but this
 // is currently safe since BL has LR as an implicit-def and what happens after a
@@ -249,3 +269,4 @@
                            (sequence "S%u", 0, 31), (sequence "D%u", 0, 31),
                            (sequence "Q%u", 0, 31))>;
 
+def CSR_AArch64_NoRegs : CalleeSavedRegs<(add)>;
\ No newline at end of file
Index: lib/Target/AArch64/AArch64FastISel.cpp
===================================================================
--- lib/Target/AArch64/AArch64FastISel.cpp
+++ lib/Target/AArch64/AArch64FastISel.cpp
@@ -302,6 +302,8 @@
 CCAssignFn *AArch64FastISel::CCAssignFnForCall(CallingConv::ID CC) const {
   if (CC == CallingConv::WebKit_JS)
     return CC_AArch64_WebKit_JS;
+  if (CC == CallingConv::GHC)
+    return CC_AArch64_GHC;
   return Subtarget->isTargetDarwin() ? CC_AArch64_DarwinPCS : CC_AArch64_AAPCS;
 }
 
Index: lib/Target/AArch64/AArch64FrameLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64FrameLowering.cpp
+++ lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -215,6 +215,11 @@
   bool HasFP = hasFP(MF);
   DebugLoc DL = MBB.findDebugLoc(MBBI);
 
+  // All calls are tail calls in GHC calling conv, and functions have no
+  // prologue/epilogue.
+  if (MF.getFunction()->getCallingConv() == CallingConv::GHC)
+    return;
+
   int NumBytes = (int)MFI->getStackSize();
   if (!AFI->hasStackFrame()) {
     assert(!HasFP && "unexpected function without stack frame but with FP");
@@ -451,6 +456,11 @@
   int NumBytes = MFI->getStackSize();
   const AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
 
+  // All calls are tail calls in GHC calling conv, and functions have no
+  // prologue/epilogue.
+  if (MF.getFunction()->getCallingConv() == CallingConv::GHC)
+    return;
+
   // Initial and residual are named for consitency with the prologue. Note that
   // in the epilogue, the residual adjustment is executed first.
   uint64_t ArgumentPopSize = 0;
Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1990,6 +1990,8 @@
     llvm_unreachable("Unsupported calling convention.");
   case CallingConv::WebKit_JS:
     return CC_AArch64_WebKit_JS;
+  case CallingConv::GHC:
+    return CC_AArch64_GHC;
   case CallingConv::C:
   case CallingConv::Fast:
     if (!Subtarget->isTargetDarwin())
Index: lib/Target/AArch64/AArch64RegisterInfo.cpp
===================================================================
--- lib/Target/AArch64/AArch64RegisterInfo.cpp
+++ lib/Target/AArch64/AArch64RegisterInfo.cpp
@@ -40,6 +40,10 @@
 const MCPhysReg *
 AArch64RegisterInfo::getCalleeSavedRegs(const MachineFunction *MF) const {
   assert(MF && "Invalid MachineFunction pointer.");
+  if (MF->getFunction()->getCallingConv() == CallingConv::GHC)
+    // GHC set of callee saved regs is empty as all those regs are
+    // used for passing STG regs around
+    return CSR_AArch64_NoRegs_SaveList;
   if (MF->getFunction()->getCallingConv() == CallingConv::AnyReg)
     return CSR_AArch64_AllRegs_SaveList;
   else
@@ -48,6 +52,9 @@
 
 const uint32_t *
 AArch64RegisterInfo::getCallPreservedMask(CallingConv::ID CC) const {
+  if (CC == CallingConv::GHC)
+    // This is academic becase all GHC calls are (supposed to be) tail calls
+    return CSR_AArch64_NoRegs_RegMask;
   if (CC == CallingConv::AnyReg)
     return CSR_AArch64_AllRegs_RegMask;
   else
@@ -63,7 +70,7 @@
 }
 
 const uint32_t *
-AArch64RegisterInfo::getThisReturnPreservedMask(CallingConv::ID) const {
+AArch64RegisterInfo::getThisReturnPreservedMask(CallingConv::ID CC) const {
   // This should return a register mask that is the same as that returned by
   // getCallPreservedMask but that additionally preserves the register used for
   // the first i64 argument (which must also be the register used to return a
@@ -71,6 +78,7 @@
   //
   // In case that the calling convention does not use the same register for
   // both, the function should return NULL (does not currently apply)
+  assert(CC != CallingConv::GHC && "should not be GHC calling convention.");
   return CSR_AArch64_AAPCS_ThisReturn_RegMask;
 }
 
Index: test/CodeGen/AArch64/ghc-tcreturn-lowered.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/ghc-tcreturn-lowered.ll
@@ -0,0 +1,22 @@
+; RUN: llc -mtriple=aarch64-unknown-linux-gnu -o - %s | FileCheck %s
+
+declare cc10 void @gfunc()
+
+define cc10 void @test_direct_tail() {
+; CHECK-LABEL: test_direct_tail:
+; CHECK: bl gfunc
+  tail call cc10 void @gfunc()
+  ret void
+}
+
+@ind_func = global void()* zeroinitializer
+
+define cc10 void @test_indirect_tail() {
+; CHECK-LABEL: test_indirect_tail:
+; CHECK: adrp {{x[0-9]+}}, ind_func
+; CHECK-NEXT: ldr {{x[0-9]+}}, [{{x[0-9]+}}, :lo12:ind_func]
+; CHECK-NEXT: blr {{x[0-9]+}}
+  %func = load void()** @ind_func
+  tail call cc10 void()* %func()
+  ret void
+}