From 2b5f03aa12313a796b87b9a11414872d598b2c2c Mon Sep 17 00:00:00 2001
From: Tim Northover <tnorthover@apple.com>
Date: Fri, 30 Jun 2017 19:51:02 +0000
Subject: [PATCH] ARM: fix big-endian 64-bit cmpxchg.

On big-endian machines the high and low parts of the value accessed by ldrexd
and strexd are swapped around. To account for this we swap inputs and outputs
in ISelLowering.

Patch by Bharathi Seshadri.

llvm-svn: 306865
---
 llvm/lib/Target/ARM/ARMISelLowering.cpp | 15 ++++++++++----
 llvm/test/CodeGen/ARM/cmpxchg-O0-be.ll  | 26 +++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 4 deletions(-)
 create mode 100644 llvm/test/CodeGen/ARM/cmpxchg-O0-be.ll

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 2bcc707e9fc3..e42514acd76f 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -7580,6 +7580,9 @@ static SDValue createGPRPairNode(SelectionDAG &DAG, SDValue V) {
   SDValue VHi = DAG.getAnyExtOrTrunc(
       DAG.getNode(ISD::SRL, dl, MVT::i64, V, DAG.getConstant(32, dl, MVT::i32)),
       dl, MVT::i32);
+  bool isBigEndian = DAG.getDataLayout().isBigEndian();
+  if (isBigEndian)
+    std::swap (VLo, VHi);
   SDValue RegClass =
       DAG.getTargetConstant(ARM::GPRPairRegClassID, dl, MVT::i32);
   SDValue SubReg0 = DAG.getTargetConstant(ARM::gsub_0, dl, MVT::i32);
@@ -7607,10 +7610,14 @@ static void ReplaceCMP_SWAP_64Results(SDNode *N,
   MemOp[0] = cast<MemSDNode>(N)->getMemOperand();
   cast<MachineSDNode>(CmpSwap)->setMemRefs(MemOp, MemOp + 1);
 
-  Results.push_back(DAG.getTargetExtractSubreg(ARM::gsub_0, SDLoc(N), MVT::i32,
-                                               SDValue(CmpSwap, 0)));
-  Results.push_back(DAG.getTargetExtractSubreg(ARM::gsub_1, SDLoc(N), MVT::i32,
-                                               SDValue(CmpSwap, 0)));
+  bool isBigEndian = DAG.getDataLayout().isBigEndian();
+
+  Results.push_back(
+      DAG.getTargetExtractSubreg(isBigEndian ? ARM::gsub_1 : ARM::gsub_0,
+                                 SDLoc(N), MVT::i32, SDValue(CmpSwap, 0)));
+  Results.push_back(
+      DAG.getTargetExtractSubreg(isBigEndian ? ARM::gsub_0 : ARM::gsub_1,
+                                 SDLoc(N), MVT::i32, SDValue(CmpSwap, 0)));
   Results.push_back(SDValue(CmpSwap, 2));
 }
 
diff --git a/llvm/test/CodeGen/ARM/cmpxchg-O0-be.ll b/llvm/test/CodeGen/ARM/cmpxchg-O0-be.ll
new file mode 100644
index 000000000000..9e9a93e19b6a
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/cmpxchg-O0-be.ll
@@ -0,0 +1,26 @@
+; RUN: llc -verify-machineinstrs -mtriple=armebv8-linux-gnueabi -O0 %s -o - | FileCheck %s
+
+@x = global i64 10, align 8
+@y = global i64 20, align 8
+@z = global i64 20, align 8
+
+; CHECK_LABEL:	main:
+; CHECK:	ldr [[R2:r[0-9]+]], {{\[}}[[R1:r[0-9]+]]{{\]}}
+; CHECK-NEXT:	ldr [[R1]], {{\[}}[[R1]], #4]
+; CHECK:	mov [[R4:r[0-9]+]], [[R2]]
+; CHECK-NEXT:	mov [[R5:r[0-9]+]], [[R1]]
+; CHECK:	ldr [[R2]], {{\[}}[[R1]]{{\]}}
+; CHECK-NEXT:	ldr [[R1]], {{\[}}[[R1]], #4]
+; CHECK:	mov [[R6:r[0-9]+]], [[R2]]
+; CHECK-NEXT:	mov [[R7:r[0-9]+]], [[R1]]
+
+define arm_aapcs_vfpcc i32 @main() #0 {
+entry:
+  %retval = alloca i32, align 4
+  store i32 0, i32* %retval, align 4
+  %0 = load i64, i64* @z, align 8
+  %1 = load i64, i64* @x, align 8
+  %2 = cmpxchg i64* @y, i64 %0, i64 %1 seq_cst seq_cst
+  %3 = extractvalue { i64, i1 } %2, 1
+  ret i32 0
+}