Add support for a preserve_most calling convention to the AArch64 backend.

[swiftix]

Summary

This change adds a support for a preserve_most calling convention to the AArch64 backend, similar to how it was done for X86-64.

There is also a subsequent patch on top of this one to add a tail-calls support for this calling convention.

[t.p.northover]

Thanks for updating the patch. Just one issue now as far as I can see (you don't need to upload another revision): you should also test that x15 is saved and restored.

Cheers.

Tim.

[swiftix]

Oh, thanks! You are right about x15. I forgot to update the test. Will add this check.

lib/Target/AArch64/AArch64CallingConvention.td

 def CSR_AArch64_AllRegs
     : CalleeSavedRegs<(add (sequence "W%u", 0, 30), WSP,
                            (sequence "X%u", 0, 28), FP, LR, SP,
                            (sequence "B%u", 0, 31), (sequence "H%u", 0, 31),
                            (sequence "S%u", 0, 31), (sequence "D%u", 0, 31),
                            (sequence "Q%u", 0, 31))>;
 
 def CSR_AArch64_NoRegs : CalleeSavedRegs<(add)>;
+
+def CSR_AArch64_RT_MostRegs :  CalleeSavedRegs<(add CSR_AArch64_AAPCS,
+                                                (sequence "X%u", 9, 15))>;
+

lib/Target/AArch64/AArch64FrameLowering.cpp

static void computeCalleeSaveRegisterPairs(
     MachineFunction &MF, const std::vector<CalleeSavedInfo> &CSI,
     const TargetRegisterInfo *TRI, SmallVectorImpl<RegPairInfo> &RegPairs) {
 
   if (CSI.empty())
     return;
 
   AArch64FunctionInfo *AFI = MF.getInfo<AArch64FunctionInfo>();
   MachineFrameInfo *MFI = MF.getFrameInfo();
+  CallingConv::ID CC = MF.getFunction()->getCallingConv();
   unsigned Count = CSI.size();
+  (void)CC;
   // MachO's compact unwind format relies on all registers being stored in
   // pairs.
   assert((!MF.getSubtarget<AArch64Subtarget>().isTargetMachO() ||
+          CC == CallingConv::PreserveMost ||
           (Count & 1) == 0) &&
          "Odd number of callee-saved regs to spill!");
   unsigned Offset = AFI->getCalleeSavedStackSize();
 
   for (unsigned i = 0; i < Count; ++i) {
     RegPairInfo RPI;
     RPI.Reg1 = CSI[i].getReg();
 
for (unsigned i = 0; i < Count; ++i) {
     // getCalleeSavedRegs(), so they will always be in-order, as well.
     assert((!RPI.isPaired() ||
             (CSI[i].getFrameIdx() + 1 == CSI[i + 1].getFrameIdx())) &&
            "Out of order callee saved regs!");
 
     // MachO's compact unwind format relies on all registers being stored in
     // adjacent register pairs.
     assert((!MF.getSubtarget<AArch64Subtarget>().isTargetMachO() ||
+            CC == CallingConv::PreserveMost ||
             (RPI.isPaired() &&
              ((RPI.Reg1 == AArch64::LR && RPI.Reg2 == AArch64::FP) ||
               RPI.Reg1 + 1 == RPI.Reg2))) &&
            "Callee-save registers not saved as adjacent register pair!");
 
     RPI.FrameIdx = CSI[i].getFrameIdx();
 
     if (Count * 8 != AFI->getCalleeSavedStackSize() && !RPI.isPaired()) {

lib/Target/AArch64/AArch64ISelLowering.cpp

CCAssignFn *AArch64TargetLowering::CCAssignFnForCall(CallingConv::ID CC,
   default:
     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:
+  case CallingConv::PreserveMost:
     if (!Subtarget->isTargetDarwin())
       return CC_AArch64_AAPCS;
     return IsVarArg ? CC_AArch64_DarwinPCS_VarArg : CC_AArch64_DarwinPCS;
   }
 }
 
 SDValue AArch64TargetLowering::LowerFormalArguments(
     SDValue Chain, CallingConv::ID CallConv, bool isVarArg,

 }
 
 bool AArch64TargetLowering::DoesCalleeRestoreStack(CallingConv::ID CallCC,
                                                    bool TailCallOpt) const {
   return CallCC == CallingConv::Fast && TailCallOpt;
 }
 
 bool AArch64TargetLowering::IsTailCallConvention(CallingConv::ID CallCC) const {
-  return CallCC == CallingConv::Fast;
+  return CallCC == CallingConv::Fast ||
+         CallCC == CallingConv::PreserveMost;
 }
 
 /// LowerCall - Lower a call to a callseq_start + CALL + callseq_end chain,
 /// and add input and output parameter nodes.
 SDValue
 AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
                                  SmallVectorImpl<SDValue> &InVals) const {
   SelectionDAG &DAG = CLI.DAG;

lib/Target/AArch64/AArch64RegisterInfo.cpp

if (MF->getFunction()->getCallingConv() == CallingConv::GHC)
     // used for passing STG regs around
     return CSR_AArch64_NoRegs_SaveList;
   if (MF->getFunction()->getCallingConv() == CallingConv::AnyReg)
     return CSR_AArch64_AllRegs_SaveList;
   if (MF->getFunction()->getCallingConv() == CallingConv::CXX_FAST_TLS)
     return MF->getInfo<AArch64FunctionInfo>()->isSplitCSR() ?
            CSR_AArch64_CXX_TLS_Darwin_PE_SaveList :
            CSR_AArch64_CXX_TLS_Darwin_SaveList;
+  if (MF->getFunction()->getCallingConv() == CallingConv::PreserveMost)
+    return CSR_AArch64_RT_MostRegs_SaveList;
   else
     return CSR_AArch64_AAPCS_SaveList;
 }
 
 const MCPhysReg *AArch64RegisterInfo::getCalleeSavedRegsViaCopy(
     const MachineFunction *MF) const {
   assert(MF && "Invalid MachineFunction pointer.");
   if (MF->getFunction()->getCallingConv() == CallingConv::CXX_FAST_TLS &&
       MF->getInfo<AArch64FunctionInfo>()->isSplitCSR())
     return CSR_AArch64_CXX_TLS_Darwin_ViaCopy_SaveList;
   return nullptr;
 }
 
 const uint32_t *
 AArch64RegisterInfo::getCallPreservedMask(const MachineFunction &MF,
                                           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;
   if (CC == CallingConv::CXX_FAST_TLS)
     return CSR_AArch64_CXX_TLS_Darwin_RegMask;
+  if (CC == CallingConv::PreserveMost)
+    return CSR_AArch64_RT_MostRegs_RegMask;
   else
     return CSR_AArch64_AAPCS_RegMask;
 }
 
 const uint32_t *AArch64RegisterInfo::getTLSCallPreservedMask() const {
   if (TT.isOSDarwin())
     return CSR_AArch64_TLS_Darwin_RegMask;
 

lib/Target/ARM/ARMISelLowering.cpp

ARMTargetLowering::getEffectiveCallingConv(CallingConv::ID CC,
                                            bool isVarArg) const {
   switch (CC) {
   default:
     llvm_unreachable("Unsupported calling convention");
   case CallingConv::ARM_AAPCS:
   case CallingConv::ARM_APCS:
   case CallingConv::GHC:
     return CC;
+  case CallingConv::PreserveMost:
+    return CallingConv::PreserveMost;
   case CallingConv::ARM_AAPCS_VFP:
     return isVarArg ? CallingConv::ARM_AAPCS : CallingConv::ARM_AAPCS_VFP;
   case CallingConv::C:
     if (!Subtarget->isAAPCS_ABI())
       return CallingConv::ARM_APCS;
     else if (Subtarget->hasVFP2() && !Subtarget->isThumb1Only() &&
              getTargetMachine().Options.FloatABIType == FloatABI::Hard &&
              !isVarArg)
CCAssignFn *ARMTargetLowering::CCAssignFnForNode(CallingConv::ID CC,
   case CallingConv::ARM_AAPCS:
     return (Return ? RetCC_ARM_AAPCS : CC_ARM_AAPCS);
   case CallingConv::ARM_AAPCS_VFP:
     return (Return ? RetCC_ARM_AAPCS_VFP : CC_ARM_AAPCS_VFP);
   case CallingConv::Fast:
     return (Return ? RetFastCC_ARM_APCS : FastCC_ARM_APCS);
   case CallingConv::GHC:
     return (Return ? RetCC_ARM_APCS : CC_ARM_APCS_GHC);
+  case CallingConv::PreserveMost:
+    return (Return ? RetCC_ARM_AAPCS : CC_ARM_AAPCS);
   }
 }
 
 /// LowerCallResult - Lower the result values of a call into the
 /// appropriate copies out of appropriate physical registers.
 SDValue
 ARMTargetLowering::LowerCallResult(SDValue Chain, SDValue InFlag,
                                    CallingConv::ID CallConv, bool isVarArg,

test/CodeGen/AArch64/preserve_mostcc.ll

+; RUN: llc < %s -mtriple=arm64-apple-ios-8.0.0 | FileCheck %s
+
+declare void @standard_cc_func()
+declare preserve_mostcc void @preserve_mostcc_func()
+
+; Registers r9-r14 should be saved before the call of a function
+; with a standard calling convention.
+define preserve_mostcc void @preserve_mostcc1() nounwind {
+entry:
+;CHECK-LABEL: preserve_mostcc1
+;CHECK-NOT:   stp
+;CHECK:       stp     x14, x13,
+;CHECK-NEXT:  stp     x12, x11,
+;CHECK-NEXT:  stp     x10, x9,
+;CHECK:       bl      _standard_cc_func
+  call void @standard_cc_func()
+;CHECK:       ldp     x10, x9,
+;CHECK-NEXT:  ldp     x12, x11,
+;CHECK-NEXT:  ldp     x14, x13,
+  ret void
+}
+
+; Registers r9-r14 don't need to be saved if one
+; function with preserve_mostcc calling convention calls another
+; function with preserve_mostcc calling convention, because the
+; callee wil save these registers anyways.
+define preserve_mostcc void @preserve_mostcc2() nounwind {
+entry:
+;CHECK-LABEL: preserve_mostcc2
+;CHECK-NOT: x14
+;CHECK:     stp     x29, x30,
+;CHECK-NOT: x14
+;CHECK:     bl      _preserve_mostcc_func
+  call preserve_mostcc void @preserve_mostcc_func()
+  ret void
+}
+

test/CodeGen/AArch64/tail-call.ll

 ; RUN: llc -verify-machineinstrs < %s -mtriple=aarch64-none-linux-gnu -tailcallopt | FileCheck %s
 
 declare fastcc void @callee_stack0()
 declare fastcc void @callee_stack8([8 x i32], i64)
 declare fastcc void @callee_stack16([8 x i32], i64, i64)
 declare extern_weak fastcc void @callee_weak()
+declare void @callee_standard_cc()
+declare preserve_mostcc void @callee_preserve_mostcc()
 
 define fastcc void @caller_to0_from0() nounwind {
 ; CHECK-LABEL: caller_to0_from0:
 ; CHECK-NEXT: // BB
 
   tail call fastcc void @callee_stack0()
   ret void
 
; CHECK: ret
   %val2 = tail call double @get_double()
 
   %res.0 = insertvalue { double, [2 x double] } undef, double %val0, 0
   %res.01 = insertvalue { double, [2 x double] } %res.0, double %val1, 1, 0
   %res.012 = insertvalue { double, [2 x double] } %res.01, double %val2, 1, 1
 
   ret { double, [2 x double] } %res.012
 }
+
+define preserve_mostcc void @caller_to_preserve_mostcc_from_preserve_mostcc() {
+; CHECK-LABEL: caller_to_preserve_mostcc_from_preserve_mostcc:
+
+  tail call preserve_mostcc void @callee_preserve_mostcc()
+  ret void
+
+; CHECK: b callee_preserve_mostcc
+}
+
+define preserve_mostcc void @caller_to_standard_cc_from_preserve_mostcc() {
+; CHECK-LABEL: caller_to_standard_cc_from_preserve_mostcc:
+
+  tail call void @callee_standard_cc()
+  ret void
+
+; CHECK-NOT: b callee_standard_cc
+; CHECK: bl callee_standard_cc
+}
+