Add TargetLoweringInfo hook for explicitly setting the ABI calling convention endianess

Summary:
The endianess used in the calling convention does not always match the
endianess of the target on all architectures, namely AVR.

When an argument is too large to be legalised by the architecture and is
split for the ABI, a new hook TargetLoweringInfo::shouldSplitFunctionArgumentsAsLittleEndian
is queried to find the endianess that function arguments must be laid
out in.

This approach was recommended by Eli Friedman.

Originally reported in https://github.com/avr-rust/rust/issues/129.

Patch by Carl Peto.

Reviewers: bogner, t.p.northover, RKSimon, niravd, efriedma

Reviewed By: efriedma

Subscribers: JDevlieghere, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D62003

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@361222 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/CodeGen/TargetLowering.h

@@ -3538,6 +3538,15 @@ public:
     return false;
   }
 
+  /// For most targets, an LLVM type must be broken down into multiple
+  /// smaller types. Usually the halves are ordered according to the endianness
+  /// but for some platform that would break. So this method will default to
+  /// matching the endianness but can be overridden.
+  virtual bool
+  shouldSplitFunctionArgumentsAsLittleEndian(const DataLayout &DL) const {
+    return DL.isLittleEndian();
+  }
+
   /// Returns a 0 terminated array of registers that can be safely used as
   /// scratch registers.
   virtual const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const {

lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -5920,7 +5920,7 @@ bool TargetLowering::expandMULO(SDNode *Node, SDValue &Result,
     // being a legal type for the architecture and thus has to be split to
     // two arguments.
     SDValue Ret;
-    if (DAG.getDataLayout().isLittleEndian()) {
+    if (shouldSplitFunctionArgumentsAsLittleEndian(DAG.getDataLayout())) {
       // Halves of WideVT are packed into registers in different order
       // depending on platform endianness. This is usually handled by
       // the C calling convention, but we can't defer to it in

lib/Target/AVR/AVRISelLowering.h

@@ -128,6 +128,11 @@ public:
   unsigned getRegisterByName(const char* RegName, EVT VT,
                              SelectionDAG &DAG) const override;
 
+  bool shouldSplitFunctionArgumentsAsLittleEndian(const DataLayout &DL)
+    const override {
+    return false;
+  }
+
 private:
   SDValue getAVRCmp(SDValue LHS, SDValue RHS, ISD::CondCode CC, SDValue &AVRcc,
                     SelectionDAG &DAG, SDLoc dl) const;

test/CodeGen/AVR/umul.with.overflow.i16-bug.ll

@@ -0,0 +1,49 @@
+; RUN: llc -O1 < %s -march=avr | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.9"
+
+%Vs6UInt16 = type <{ i16 }>
+%Sb = type <{ i1 }>
+
+define hidden void @setServoAngle(i16) {
+  ; CHECK-LABEL: entry
+entry:
+  %adjustedAngle = alloca %Vs6UInt16, align 2
+  %1 = bitcast %Vs6UInt16* %adjustedAngle to i8*
+  %adjustedAngle._value = getelementptr inbounds %Vs6UInt16, %Vs6UInt16* %adjustedAngle, i32 0, i32 0
+  store i16 %0, i16* %adjustedAngle._value, align 2
+
+;print(unsignedInt: adjustedAngle &* UInt16(11))
+; breaks here
+  %adjustedAngle._value2 = getelementptr inbounds %Vs6UInt16, %Vs6UInt16* %adjustedAngle, i32 0, i32 0
+  %2 = load i16, i16* %adjustedAngle._value2, align 2
+
+; CHECK: mov r22, r24
+; CHECK: mov r23, r25
+
+; CHECK-DAG: ldi r20, 0
+; CHECK-DAG: ldi r21, 0
+; CHECK-DAG: ldi r18, 11
+; CHECK-DAG: ldi r19, 0
+
+; CHECK: mov r24, r20
+; CHECK: mov r25, r21
+; CHECK: call  __mulsi3
+  %3 = call { i16, i1 } @llvm.umul.with.overflow.i16(i16 %2, i16 11)
+  %4 = extractvalue { i16, i1 } %3, 0
+  %5 = extractvalue { i16, i1 } %3, 1
+
+  ; above code looks fine, how is it lowered?
+  %6 = call i1 @printDefaultParam()
+  call void @print(i16 %4, i1 %6)
+
+; CHECK: ret
+  ret void
+}
+
+declare void @print(i16, i1)
+declare i1 @printDefaultParam()
+
+; Function Attrs: nounwind readnone speculatable
+declare { i16, i1 } @llvm.umul.with.overflow.i16(i16, i16)