Index: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5372,9 +5372,16 @@
 //    |  D  |
 // Into:
 //   (x & m) | (y & ~m)
+// NOTE: we don't unfold the pattern if 'xor' is actually a 'not', because at
+//       the very least that breaks andnpd / andnps patterns, and because those
+//       patterns are simplified in IR and shouldn't be created in the DAG
 SDValue DAGCombiner::unfoldMaskedMerge(SDNode *N) {
   assert(N->getOpcode() == ISD::XOR);
 
+  // Don't touch 'not' (i.e. where y = -1).
+  if (isAllOnesConstantOrAllOnesSplatConstant(N->getOperand(1)))
+    return SDValue();
+
   EVT VT = N->getValueType(0);
 
   // FIXME
@@ -5392,6 +5399,9 @@
       return false;
     SDValue Xor0 = Xor.getOperand(0);
     SDValue Xor1 = Xor.getOperand(1);
+    // Don't touch 'not' (i.e. where y = -1).
+    if (isAllOnesConstantOrAllOnesSplatConstant(Xor1))
+      return false;
     if (Other == Xor0)
       std::swap(Xor0, Xor1);
     if (Other != Xor1)
Index: llvm/trunk/test/CodeGen/AArch64/unfold-masked-merge-scalar-variablemask.ll
===================================================================
--- llvm/trunk/test/CodeGen/AArch64/unfold-masked-merge-scalar-variablemask.ll
+++ llvm/trunk/test/CodeGen/AArch64/unfold-masked-merge-scalar-variablemask.ll
@@ -347,8 +347,8 @@
 define i32 @in_constant_varx_mone(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_constant_varx_mone:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    and w8, w0, w2
-; CHECK-NEXT:    orn w0, w8, w2
+; CHECK-NEXT:    bic w8, w2, w0
+; CHECK-NEXT:    mvn w0, w8
 ; CHECK-NEXT:    ret
   %n0 = xor i32 %x, -1 ; %x
   %n1 = and i32 %n0, %mask
@@ -370,8 +370,9 @@
 define i32 @in_constant_varx_mone_invmask(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_constant_varx_mone_invmask:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    bic w8, w0, w2
-; CHECK-NEXT:    orr w0, w8, w2
+; CHECK-NEXT:    mvn w8, w0
+; CHECK-NEXT:    bic w8, w8, w2
+; CHECK-NEXT:    mvn w0, w8
 ; CHECK-NEXT:    ret
   %notmask = xor i32 %mask, -1
   %n0 = xor i32 %x, -1 ; %x
@@ -449,8 +450,8 @@
 define i32 @in_constant_mone_vary(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_constant_mone_vary:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    bic w8, w1, w2
-; CHECK-NEXT:    orr w0, w2, w8
+; CHECK-NEXT:    bic w8, w2, w1
+; CHECK-NEXT:    eor w0, w8, w1
 ; CHECK-NEXT:    ret
   %n0 = xor i32 -1, %y ; %x
   %n1 = and i32 %n0, %mask
@@ -472,8 +473,9 @@
 define i32 @in_constant_mone_vary_invmask(i32 %x, i32 %y, i32 %mask) {
 ; CHECK-LABEL: in_constant_mone_vary_invmask:
 ; CHECK:       // %bb.0:
-; CHECK-NEXT:    and w8, w1, w2
-; CHECK-NEXT:    orn w0, w8, w2
+; CHECK-NEXT:    mvn w8, w1
+; CHECK-NEXT:    bic w8, w8, w2
+; CHECK-NEXT:    eor w0, w8, w1
 ; CHECK-NEXT:    ret
   %notmask = xor i32 %mask, -1
   %n0 = xor i32 -1, %y ; %x
Index: llvm/trunk/test/CodeGen/X86/unfold-masked-merge-scalar-variablemask.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/unfold-masked-merge-scalar-variablemask.ll
+++ llvm/trunk/test/CodeGen/X86/unfold-masked-merge-scalar-variablemask.ll
@@ -570,10 +570,8 @@
 ;
 ; CHECK-BMI-LABEL: in_constant_varx_mone:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    andl %edx, %edi
-; CHECK-BMI-NEXT:    notl %edx
-; CHECK-BMI-NEXT:    orl %edi, %edx
-; CHECK-BMI-NEXT:    movl %edx, %eax
+; CHECK-BMI-NEXT:    andnl %edx, %edi, %eax
+; CHECK-BMI-NEXT:    notl %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 %x, -1 ; %x
   %n1 = and i32 %n0, %mask
@@ -612,8 +610,9 @@
 ;
 ; CHECK-BMI-LABEL: in_constant_varx_mone_invmask:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    andnl %edi, %edx, %eax
-; CHECK-BMI-NEXT:    orl %edx, %eax
+; CHECK-BMI-NEXT:    notl %edx
+; CHECK-BMI-NEXT:    andnl %edx, %edi, %eax
+; CHECK-BMI-NEXT:    notl %eax
 ; CHECK-BMI-NEXT:    retq
   %notmask = xor i32 %mask, -1
   %n0 = xor i32 %x, -1 ; %x
@@ -743,8 +742,8 @@
 ;
 ; CHECK-BMI-LABEL: in_constant_mone_vary:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    andnl %esi, %edx, %eax
-; CHECK-BMI-NEXT:    orl %edx, %eax
+; CHECK-BMI-NEXT:    andnl %edx, %esi, %eax
+; CHECK-BMI-NEXT:    xorl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %n0 = xor i32 -1, %y ; %x
   %n1 = and i32 %n0, %mask
@@ -785,10 +784,9 @@
 ;
 ; CHECK-BMI-LABEL: in_constant_mone_vary_invmask:
 ; CHECK-BMI:       # %bb.0:
-; CHECK-BMI-NEXT:    andl %edx, %esi
 ; CHECK-BMI-NEXT:    notl %edx
-; CHECK-BMI-NEXT:    orl %esi, %edx
-; CHECK-BMI-NEXT:    movl %edx, %eax
+; CHECK-BMI-NEXT:    andnl %edx, %esi, %eax
+; CHECK-BMI-NEXT:    xorl %esi, %eax
 ; CHECK-BMI-NEXT:    retq
   %notmask = xor i32 %mask, -1
   %n0 = xor i32 -1, %y ; %x