Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -9713,6 +9713,20 @@
     return DAG.getNode(ISD::FSUB, DL, VT, N1IsFMul ? N0 : N1, Add, Flags);
   }
 
+  // fold (fadd (fmul (fmul B, -2.0) C), A) -> (fsub A, (fmul (fadd B, B) C)
+  // fold (fadd A, (fmul (fmul B, -2.0) C)) -> (fsub A, (fmul (fadd B, B) C)
+  SDValue N0N0 = N0->getOperand(0);
+  SDValue N1N0 = N1->getOperand(0);
+  if ((isFMulNegTwo(N0N0) && N0N0.hasOneUse()) ||
+      (isFMulNegTwo(N1N0) && N1N0.hasOneUse())) {
+    bool N1N0IsFMul = isFMulNegTwo(N1N0);
+    SDValue AddOp = N1N0IsFMul ? N1N0.getOperand(0) : N0N0.getOperand(0);
+    SDValue MulOp = N1N0IsFMul ? N1->getOperand(1) : N0->getOperand(1);
+    SDValue Add = DAG.getNode(ISD::FADD, DL, VT, AddOp, AddOp, Flags);
+    SDValue Mul = DAG.getNode(ISD::FMUL, DL, VT, Add, MulOp, Flags);
+    return DAG.getNode(ISD::FSUB, DL, VT, N1N0IsFMul ? N0 : N1, Mul, Flags);
+  }
+
   // FIXME: Auto-upgrade the target/function-level option.
   if (Options.NoSignedZerosFPMath || N->getFlags().hasNoSignedZeros()) {
     // fold (fadd A, 0) -> A
Index: test/CodeGen/AArch64/fadd-combines.ll
===================================================================
--- test/CodeGen/AArch64/fadd-combines.ll
+++ test/CodeGen/AArch64/fadd-combines.ll
@@ -76,3 +76,28 @@
 }
 
 declare void @use(double)
+
+; CHECK-LABEL: test8:
+; CHECK: fadd  d1, d1, d1
+; CHECK: fmul  d1, d1, d2
+; CHECK: fsub  d0, d0, d1
+define double @test8(double %a, double %b, double %c) local_unnamed_addr #0 {
+entry:
+  %mul = fmul double %b, -2.000000e+00
+  %mul1 = fmul double %mul, %c
+  %add = fadd double %mul1, %a
+  ret double %add
+}
+
+; DAGCombine will canonicalize 'a - 2.0*b*c' to 'a + -2.0*b*c'
+; CHECK-LABEL: test9:
+; CHECK: fadd  d1, d1, d1
+; CHECK: fmul  d1, d1, d2
+; CHECK: fsub  d0, d0, d1
+define double @test9(double %a, double %b, double %c) local_unnamed_addr #0 {
+entry:
+  %mul = fmul double %b, 2.000000e+00
+  %mul1 = fmul double %mul, %c
+  %sub = fsub double %a, %mul1
+  ret double %sub
+}