ARM EABI divmod support

This patch enables calls to __aeabi_idivmod when in EABI mode,
by using the remainder value returned on registers (R1),
enabled by the ARM triple "none-eabi". Note that Darwin and
GNUEABI triples will continue lowering on GNU style, that is,
using the stack for the remainder.

Still need to add SREM/UREM support fix for 64-bit lowering.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186390 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index fdc015b..3648199 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -693,10 +693,36 @@
     setOperationAction(ISD::SDIV,  MVT::i32, Expand);
     setOperationAction(ISD::UDIV,  MVT::i32, Expand);
   }
+
+  // FIXME: Also set divmod for SREM on EABI
   setOperationAction(ISD::SREM,  MVT::i32, Expand);
   setOperationAction(ISD::UREM,  MVT::i32, Expand);
-  setOperationAction(ISD::SDIVREM, MVT::i32, Expand);
-  setOperationAction(ISD::UDIVREM, MVT::i32, Expand);
+  // Register based DivRem for AEABI (RTABI 4.2)
+  if (Subtarget->isTargetAEABI()) {
+    setLibcallName(RTLIB::SDIVREM_I8,  "__aeabi_idivmod");
+    setLibcallName(RTLIB::SDIVREM_I16, "__aeabi_idivmod");
+    setLibcallName(RTLIB::SDIVREM_I32, "__aeabi_idivmod");
+    setLibcallName(RTLIB::SDIVREM_I64, "__aeabi_ldivmod");
+    setLibcallName(RTLIB::UDIVREM_I8,  "__aeabi_uidivmod");
+    setLibcallName(RTLIB::UDIVREM_I16, "__aeabi_uidivmod");
+    setLibcallName(RTLIB::UDIVREM_I32, "__aeabi_uidivmod");
+    setLibcallName(RTLIB::UDIVREM_I64, "__aeabi_uldivmod");
+
+    setLibcallCallingConv(RTLIB::SDIVREM_I8, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::SDIVREM_I16, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::SDIVREM_I32, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::SDIVREM_I64, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::UDIVREM_I8, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::UDIVREM_I16, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::UDIVREM_I32, CallingConv::ARM_AAPCS);
+    setLibcallCallingConv(RTLIB::UDIVREM_I64, CallingConv::ARM_AAPCS);
+
+    setOperationAction(ISD::SDIVREM, MVT::i32, Custom);
+    setOperationAction(ISD::UDIVREM, MVT::i32, Custom);
+  } else {
+    setOperationAction(ISD::SDIVREM, MVT::i32, Expand);
+    setOperationAction(ISD::UDIVREM, MVT::i32, Expand);
+  }
 
   setOperationAction(ISD::GlobalAddress, MVT::i32,   Custom);
   setOperationAction(ISD::ConstantPool,  MVT::i32,   Custom);
@@ -5863,6 +5889,8 @@
   case ISD::SUBE:          return LowerADDC_ADDE_SUBC_SUBE(Op, DAG);
   case ISD::ATOMIC_LOAD:
   case ISD::ATOMIC_STORE:  return LowerAtomicLoadStore(Op, DAG);
+  case ISD::SDIVREM:
+  case ISD::UDIVREM:       return LowerDivRem(Op, DAG);
   }
 }
 
@@ -10677,6 +10705,54 @@
   return TargetLowering::LowerAsmOperandForConstraint(Op, Constraint, Ops, DAG);
 }
 
+SDValue ARMTargetLowering::LowerDivRem(SDValue Op, SelectionDAG &DAG) const {
+  assert(Subtarget->isTargetAEABI() && "Register-based DivRem lowering only");
+  unsigned Opcode = Op->getOpcode();
+  assert((Opcode == ISD::SDIVREM || Opcode == ISD::UDIVREM) &&
+      "Invalid opcode for Div/Rem lowering");
+  bool isSigned = (Opcode == ISD::SDIVREM);
+  EVT VT = Op->getValueType(0);
+  Type *Ty = VT.getTypeForEVT(*DAG.getContext());
+
+  RTLIB::Libcall LC;
+  switch (VT.getSimpleVT().SimpleTy) {
+  default: llvm_unreachable("Unexpected request for libcall!");
+  case MVT::i8:   LC= isSigned ? RTLIB::SDIVREM_I8  : RTLIB::UDIVREM_I8;  break;
+  case MVT::i16:  LC= isSigned ? RTLIB::SDIVREM_I16 : RTLIB::UDIVREM_I16; break;
+  case MVT::i32:  LC= isSigned ? RTLIB::SDIVREM_I32 : RTLIB::UDIVREM_I32; break;
+  case MVT::i64:  LC= isSigned ? RTLIB::SDIVREM_I64 : RTLIB::UDIVREM_I64; break;
+  }
+
+  SDValue InChain = DAG.getEntryNode();
+
+  TargetLowering::ArgListTy Args;
+  TargetLowering::ArgListEntry Entry;
+  for (unsigned i = 0, e = Op->getNumOperands(); i != e; ++i) {
+    EVT ArgVT = Op->getOperand(i).getValueType();
+    Type *ArgTy = ArgVT.getTypeForEVT(*DAG.getContext());
+    Entry.Node = Op->getOperand(i);
+    Entry.Ty = ArgTy;
+    Entry.isSExt = isSigned;
+    Entry.isZExt = !isSigned;
+    Args.push_back(Entry);
+  }
+
+  SDValue Callee = DAG.getExternalSymbol(getLibcallName(LC),
+                                         getPointerTy());
+
+  Type *RetTy = (Type*)StructType::get(Ty, Ty, NULL);
+
+  SDLoc dl(Op);
+  TargetLowering::
+  CallLoweringInfo CLI(InChain, RetTy, isSigned, !isSigned, false, true,
+                    0, getLibcallCallingConv(LC), /*isTailCall=*/false,
+                    /*doesNotReturn=*/false, /*isReturnValueUsed=*/true,
+                    Callee, Args, DAG, dl);
+  std::pair<SDValue, SDValue> CallInfo = LowerCallTo(CLI);
+
+  return CallInfo.first;
+}
+
 bool
 ARMTargetLowering::isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const {
   // The ARM target isn't yet aware of offsets.
diff --git a/lib/Target/ARM/ARMISelLowering.h b/lib/Target/ARM/ARMISelLowering.h
index ed6c405..beba5ce 100644
--- a/lib/Target/ARM/ARMISelLowering.h
+++ b/lib/Target/ARM/ARMISelLowering.h
@@ -457,6 +457,7 @@
                             const ARMSubtarget *ST) const;
     SDValue LowerBUILD_VECTOR(SDValue Op, SelectionDAG &DAG,
                               const ARMSubtarget *ST) const;
+    SDValue LowerDivRem(SDValue Op, SelectionDAG &DAG) const;
 
     /// isFMAFasterThanFMulAndFAdd - Return true if an FMA operation is faster
     /// than a pair of fmul and fadd instructions. fmuladd intrinsics will be
diff --git a/lib/Target/ARM/ARMSubtarget.h b/lib/Target/ARM/ARMSubtarget.h
index 63ba6c5..ad7f1b3 100644
--- a/lib/Target/ARM/ARMSubtarget.h
+++ b/lib/Target/ARM/ARMSubtarget.h
@@ -280,6 +280,14 @@
   bool isTargetNaCl() const { return TargetTriple.getOS() == Triple::NaCl; }
   bool isTargetLinux() const { return TargetTriple.getOS() == Triple::Linux; }
   bool isTargetELF() const { return !isTargetDarwin(); }
+  // ARM EABI is the bare-metal EABI described in ARM ABI documents and
+  // can be accessed via -target arm-none-eabi. This is NOT GNUEABI.
+  // FIXME: Add a flag for bare-metal for that target and set Triple::EABI
+  // even for GNUEABI, so we can make a distinction here and still conform to
+  // the EABI on GNU (and Android) mode. This requires change in Clang, too.
+  bool isTargetAEABI() const {
+    return TargetTriple.getEnvironment() == Triple::EABI;
+  }
 
   bool isAPCS_ABI() const { return TargetABI == ARM_ABI_APCS; }
   bool isAAPCS_ABI() const { return TargetABI == ARM_ABI_AAPCS; }